diff --git a/.editorconfig b/.editorconfig index 854773350cc5a..29a30ccfc07bf 100644 --- a/.editorconfig +++ b/.editorconfig @@ -5,7 +5,6 @@ root = true [{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = true insert_final_newline = true indent_style = tab indent_size = 8 @@ -13,7 +12,6 @@ indent_size = 8 [*.{json,py,rs}] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = true insert_final_newline = true indent_style = space indent_size = 4 @@ -26,7 +24,6 @@ indent_size = 8 [*.yaml] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = unset insert_final_newline = true indent_style = space indent_size = 2 diff --git a/.gitignore b/.gitignore index 689a4fa3f5477..98ad2b813f471 100644 --- a/.gitignore +++ b/.gitignore @@ -79,7 +79,7 @@ modules.order # # Debian directory (make deb-pkg) # -/debian/ +#/debian/ # # Snap directory (make snap-pkg) diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block index 1fe9a553c37b7..f0025d1c3d5ac 100644 --- a/Documentation/ABI/stable/sysfs-block +++ b/Documentation/ABI/stable/sysfs-block @@ -101,6 +101,16 @@ Description: devices that support receiving integrity metadata. +What: /sys/block//partscan +Date: May 2024 +Contact: Christoph Hellwig +Description: + The /sys/block//partscan files reports if partition + scanning is enabled for the disk. It returns "1" if partition + scanning is enabled, or "0" if not. The value type is a 32-bit + unsigned integer, but only "0" and "1" are valid values. + + What: /sys/block///alignment_offset Date: April 2009 Contact: Martin K. Petersen diff --git a/Documentation/ABI/testing/debugfs-driver-qat b/Documentation/ABI/testing/debugfs-driver-qat index b2db010d851ee..bd6793760f298 100644 --- a/Documentation/ABI/testing/debugfs-driver-qat +++ b/Documentation/ABI/testing/debugfs-driver-qat @@ -81,3 +81,29 @@ Description: (RO) Read returns, for each Acceleration Engine (AE), the number : Number of Compress and Verify (CnV) errors and type of the last CnV error detected by Acceleration Engine N. + +What: /sys/kernel/debug/qat__/heartbeat/inject_error +Date: March 2024 +KernelVersion: 6.8 +Contact: qat-linux@intel.com +Description: (WO) Write to inject an error that simulates an heartbeat + failure. This is to be used for testing purposes. + + After writing this file, the driver stops arbitration on a + random engine and disables the fetching of heartbeat counters. + If a workload is running on the device, a job submitted to the + accelerator might not get a response and a read of the + `heartbeat/status` attribute might report -1, i.e. device + unresponsive. + The error is unrecoverable thus the device must be restarted to + restore its functionality. + + This attribute is available only when the kernel is built with + CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION=y. + + A write of 1 enables error injection. + + The following example shows how to enable error injection:: + + # cd /sys/kernel/debug/qat__ + # echo 1 > heartbeat/inject_error diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy index c2385183826cb..a59291b97c24f 100644 --- a/Documentation/ABI/testing/ima_policy +++ b/Documentation/ABI/testing/ima_policy @@ -26,7 +26,7 @@ Description: [uid=] [euid=] [gid=] [egid=] [fowner=] [fgroup=]] lsm: [[subj_user=] [subj_role=] [subj_type=] - [obj_user=] [obj_role=] [obj_type=]] + [obj_user=] [obj_role=] [obj_type=] [lsm=]] option: [digest_type=] [template=] [permit_directio] [appraise_type=] [appraise_flag=] [appraise_algos=] [keyrings=] @@ -138,6 +138,12 @@ Description: measure subj_user=_ func=FILE_CHECK mask=MAY_READ + It is possible to explicitly specify which security + module a rule applies to using lsm=. If the security + module specified is not active on the system the rule + will be rejected. If lsm= is not specified the first + security module registered on the system will be assumed. + Example of measure rules using alternate PCRs:: measure func=KEXEC_KERNEL_CHECK pcr=4 diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index a1db6db475055..710d47be11e04 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -516,6 +516,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling /sys/devices/system/cpu/vulnerabilities/retbleed /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/spectre_v1 diff --git a/Documentation/ABI/testing/sysfs-driver-qat b/Documentation/ABI/testing/sysfs-driver-qat index bbf329cf0d67b..96020fb051c34 100644 --- a/Documentation/ABI/testing/sysfs-driver-qat +++ b/Documentation/ABI/testing/sysfs-driver-qat @@ -141,3 +141,23 @@ Description: 64 This attribute is only available for qat_4xxx devices. + +What: /sys/bus/pci/devices//qat/auto_reset +Date: March 2024 +KernelVersion: 6.8 +Contact: qat-linux@intel.com +Description: (RW) Reports the current state of the autoreset feature + for a QAT device + + Write to the attribute to enable or disable device auto reset. + + Device auto reset is disabled by default. + + The values are: + + * 1/Yy/on: auto reset enabled. If the device encounters an + unrecoverable error, it will be reset automatically. + * 0/Nn/off: auto reset disabled. If the device encounters an + unrecoverable error, it will not be reset. + + This attribute is only available for qat_4xxx devices. diff --git a/Documentation/Makefile b/Documentation/Makefile index 3885bbe260eb2..4d06210dfa2ef 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -111,8 +111,10 @@ $(YNL_INDEX): $(YNL_RST_FILES) $(YNL_RST_DIR)/%.rst: $(YNL_YAML_DIR)/%.yaml $(YNL_TOOL) $(Q)$(YNL_TOOL) -i $< -o $@ -htmldocs: $(YNL_INDEX) - @$(srctree)/scripts/sphinx-pre-install --version-check +htmldocs texinfodocs latexdocs epubdocs xmldocs: $(YNL_INDEX) + +htmldocs: + @$(srctree)/scripts/sphinx-pre-install --version-check --no-virtualenv @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,html,$(var),,$(var))) # If Rust support is available and .config exists, add rustdoc generated contents. diff --git a/Documentation/admin-guide/hw-vuln/core-scheduling.rst b/Documentation/admin-guide/hw-vuln/core-scheduling.rst index cf1eeefdfc32f..a92e10ec402e7 100644 --- a/Documentation/admin-guide/hw-vuln/core-scheduling.rst +++ b/Documentation/admin-guide/hw-vuln/core-scheduling.rst @@ -67,8 +67,8 @@ arg4: will be performed for all tasks in the task group of ``pid``. arg5: - userspace pointer to an unsigned long for storing the cookie returned by - ``PR_SCHED_CORE_GET`` command. Should be 0 for all other commands. + userspace pointer to an unsigned long long for storing the cookie returned + by ``PR_SCHED_CORE_GET`` command. Should be 0 for all other commands. In order for a process to push a cookie to, or pull a cookie from a process, it is required to have the ptrace access mode: `PTRACE_MODE_READ_REALCREDS` to the diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index de99caabf65a3..ff0b440ef2dc9 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -21,3 +21,4 @@ are configurable at compile, boot or run time. cross-thread-rsb srso gather_data_sampling + reg-file-data-sampling diff --git a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst new file mode 100644 index 0000000000000..0585d02b9a6cb --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst @@ -0,0 +1,104 @@ +================================== +Register File Data Sampling (RFDS) +================================== + +Register File Data Sampling (RFDS) is a microarchitectural vulnerability that +only affects Intel Atom parts(also branded as E-cores). RFDS may allow +a malicious actor to infer data values previously used in floating point +registers, vector registers, or integer registers. RFDS does not provide the +ability to choose which data is inferred. CVE-2023-28746 is assigned to RFDS. + +Affected Processors +=================== +Below is the list of affected Intel processors [#f1]_: + + =================== ============ + Common name Family_Model + =================== ============ + ATOM_GOLDMONT 06_5CH + ATOM_GOLDMONT_D 06_5FH + ATOM_GOLDMONT_PLUS 06_7AH + ATOM_TREMONT_D 06_86H + ATOM_TREMONT 06_96H + ALDERLAKE 06_97H + ALDERLAKE_L 06_9AH + ATOM_TREMONT_L 06_9CH + RAPTORLAKE 06_B7H + RAPTORLAKE_P 06_BAH + ATOM_GRACEMONT 06_BEH + RAPTORLAKE_S 06_BFH + =================== ============ + +As an exception to this table, Intel Xeon E family parts ALDERLAKE(06_97H) and +RAPTORLAKE(06_B7H) codenamed Catlow are not affected. They are reported as +vulnerable in Linux because they share the same family/model with an affected +part. Unlike their affected counterparts, they do not enumerate RFDS_CLEAR or +CPUID.HYBRID. This information could be used to distinguish between the +affected and unaffected parts, but it is deemed not worth adding complexity as +the reporting is fixed automatically when these parts enumerate RFDS_NO. + +Mitigation +========== +Intel released a microcode update that enables software to clear sensitive +information using the VERW instruction. Like MDS, RFDS deploys the same +mitigation strategy to force the CPU to clear the affected buffers before an +attacker can extract the secrets. This is achieved by using the otherwise +unused and obsolete VERW instruction in combination with a microcode update. +The microcode clears the affected CPU buffers when the VERW instruction is +executed. + +Mitigation points +----------------- +VERW is executed by the kernel before returning to user space, and by KVM +before VMentry. None of the affected cores support SMT, so VERW is not required +at C-state transitions. + +New bits in IA32_ARCH_CAPABILITIES +---------------------------------- +Newer processors and microcode update on existing affected processors added new +bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate +vulnerability and mitigation capability: + +- Bit 27 - RFDS_NO - When set, processor is not affected by RFDS. +- Bit 28 - RFDS_CLEAR - When set, processor is affected by RFDS, and has the + microcode that clears the affected buffers on VERW execution. + +Mitigation control on the kernel command line +--------------------------------------------- +The kernel command line allows to control RFDS mitigation at boot time with the +parameter "reg_file_data_sampling=". The valid arguments are: + + ========== ================================================================= + on If the CPU is vulnerable, enable mitigation; CPU buffer clearing + on exit to userspace and before entering a VM. + off Disables mitigation. + ========== ================================================================= + +Mitigation default is selected by CONFIG_MITIGATION_RFDS. + +Mitigation status information +----------------------------- +The Linux kernel provides a sysfs interface to enumerate the current +vulnerability status of the system: whether the system is vulnerable, and +which mitigations are active. The relevant sysfs file is: + + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling + +The possible values in this file are: + + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable + * - 'Vulnerable' + - The processor is vulnerable, but no mitigation enabled + * - 'Vulnerable: No microcode' + - The processor is vulnerable but microcode is not updated. + * - 'Mitigation: Clear Register File' + - The processor is vulnerable and the CPU buffer clearing mitigation is + enabled. + +References +---------- +.. [#f1] Affected Processors + https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 32a8893e56177..e0a1be97fa759 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -138,11 +138,10 @@ associated with the source address of the indirect branch. Specifically, the BHB might be shared across privilege levels even in the presence of Enhanced IBRS. -Currently the only known real-world BHB attack vector is via -unprivileged eBPF. Therefore, it's highly recommended to not enable -unprivileged eBPF, especially when eIBRS is used (without retpolines). -For a full mitigation against BHB attacks, it's recommended to use -retpolines (or eIBRS combined with retpolines). +Previously the only known real-world BHB attack vector was via unprivileged +eBPF. Further research has found attacks that don't require unprivileged eBPF. +For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or +use the BHB clearing sequence. Attack scenarios ---------------- @@ -430,6 +429,23 @@ The possible values in this file are: 'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB =========================== ======================================================= + - Branch History Injection (BHI) protection status: + +.. list-table:: + + * - BHI: Not affected + - System is not affected + * - BHI: Retpoline + - System is protected by retpoline + * - BHI: BHI_DIS_S + - System is protected by BHI_DIS_S + * - BHI: SW loop, KVM SW loop + - System is protected by software clearing sequence + * - BHI: Vulnerable + - System is vulnerable to BHI + * - BHI: Vulnerable, KVM: SW loop + - System is vulnerable; KVM is protected by software clearing sequence + Full mitigation might require a microcode update from the CPU vendor. When the necessary microcode is not available, the kernel will report vulnerability. @@ -484,7 +500,11 @@ Spectre variant 2 Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at boot, by setting the IBRS bit, and they're automatically protected against - Spectre v2 variant attacks. + some Spectre v2 variant attacks. The BHB can still influence the choice of + indirect branch predictor entry, and although branch predictor entries are + isolated between modes when eIBRS is enabled, the BHB itself is not isolated + between modes. Systems which support BHI_DIS_S will set it to protect against + BHI attacks. On Intel's enhanced IBRS systems, this includes cross-thread branch target injections on SMT systems (STIBP). In other words, Intel eIBRS enables @@ -638,6 +658,18 @@ kernel command line. spectre_v2=off. Spectre variant 1 mitigations cannot be disabled. + spectre_bhi= + + [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. This setting affects the deployment + of the HW BHI control and the SW BHB clearing sequence. + + on + (default) Enable the HW or SW mitigation as + needed. + off + Disable the mitigation. + For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt Mitigation selection guide diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 31b3a25680d08..e58f3bbb7643c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -848,6 +848,10 @@ Format: ,,,[,] + cpufreq_driver= [X86] Allow only the named cpu frequency scaling driver + to register. Example: cpufreq_driver=powernow-k8 + Format: { none | STRING } + cpuidle.off=1 [CPU_IDLE] disable the cpuidle sub-system @@ -1150,6 +1154,26 @@ The filter can be disabled or changed to another driver later using sysfs. + reg_file_data_sampling= + [X86] Controls mitigation for Register File Data + Sampling (RFDS) vulnerability. RFDS is a CPU + vulnerability which may allow userspace to infer + kernel data values previously stored in floating point + registers, vector registers, or integer registers. + RFDS only affects Intel Atom processors. + + on: Turns ON the mitigation. + off: Turns OFF the mitigation. + + This parameter overrides the compile time default set + by CONFIG_MITIGATION_RFDS. Mitigation cannot be + disabled when other VERW based mitigations (like MDS) + are enabled. In order to disable RFDS mitigation all + VERW based mitigations need to be disabled. + + For details see: + Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst + driver_async_probe= [KNL] List of driver names to be probed asynchronously. * matches with all driver names. If * is specified, the @@ -3320,9 +3344,7 @@ mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control Valid arguments: on, off - Default (depends on kernel configuration option): - on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) - off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n) + Default: off mem_encrypt=on: Activate SME mem_encrypt=off: Do not activate SME @@ -3381,6 +3403,9 @@ arch-independent options, each of which is an aggregation of existing arch-specific options. + Note, "mitigations" is supported if and only if the + kernel was built with CPU_MITIGATIONS=y. + off Disable all optional CPU mitigations. This improves system performance, but it may also @@ -3398,8 +3423,10 @@ nospectre_bhb [ARM64] nospectre_v1 [X86,PPC] nospectre_v2 [X86,PPC,S390,ARM64] + reg_file_data_sampling=off [X86] retbleed=off [X86] spec_store_bypass_disable=off [X86,PPC] + spectre_bhi=off [X86] spectre_v2_user=off [X86] srbds=off [X86,INTEL] ssbd=force-off [ARM64] @@ -4370,6 +4397,12 @@ nomsi [MSI] If the PCI_MSI kernel config parameter is enabled, this kernel boot option can be used to disable the use of MSI interrupts system-wide. + clearmsi [X86] Clears MSI/MSI-X enable bits early in boot + time in order to avoid issues like adapters + screaming irqs and preventing boot progress. + Also, it enforces the PCI Local Bus spec + rule that those bits should be 0 in system reset + events (useful for kexec/kdump cases). noioapicquirk [APIC] Disable all boot interrupt quirks. Safety option to keep boot IRQs enabled. This should never be necessary. @@ -5034,6 +5067,11 @@ this kernel boot parameter, forcibly setting it to zero. + rcutree.enable_rcu_lazy= [KNL] + To save power, batch RCU callbacks and flush after + delay, memory pressure or callback list growing too + big. + rcuscale.gp_async= [KNL] Measure performance of asynchronous grace-period primitives such as call_rcu(). @@ -6012,6 +6050,15 @@ sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/admin-guide/laptops/sonypi.rst + spectre_bhi= [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. This setting affects the + deployment of the HW BHI control and the SW BHB + clearing sequence. + + on - (default) Enable the HW or SW mitigation + as needed. + off - Disable the mitigation. + spectre_v2= [X86] Control mitigation of Spectre variant 2 (indirect branch speculation) vulnerability. The default operation protects the kernel from diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index 9d23144bf9850..87fdc258d1027 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -450,7 +450,7 @@ pages of all memory cgroups except ``/having_care_already``.:: # # further filter out all cgroups except one at '/having_care_already' echo memcg > 1/type echo /having_care_already > 1/memcg_path - echo N > 1/matching + echo Y > 1/matching Note that ``anon`` and ``memcg`` filters are currently supported only when ``paddr`` :ref:`implementation ` is being used. diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 3960916519557..7250c0542828b 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -206,6 +206,11 @@ Will increase power usage. Default: 0 (off) +mem_pcpu_rsv +------------ + +Per-cpu reserved forward alloc cache size in page units. Default 1MB per CPU. + rmem_default ------------ diff --git a/Documentation/arch/x86/amd-memory-encryption.rst b/Documentation/arch/x86/amd-memory-encryption.rst index 07caa8fff852e..414bc7402ae7d 100644 --- a/Documentation/arch/x86/amd-memory-encryption.rst +++ b/Documentation/arch/x86/amd-memory-encryption.rst @@ -87,14 +87,14 @@ The state of SME in the Linux kernel can be documented as follows: kernel is non-zero). SME can also be enabled and activated in the BIOS. If SME is enabled and -activated in the BIOS, then all memory accesses will be encrypted and it will -not be necessary to activate the Linux memory encryption support. If the BIOS -merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), then Linux can activate -memory encryption by default (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) or -by supplying mem_encrypt=on on the kernel command line. However, if BIOS does -not enable SME, then Linux will not be able to activate memory encryption, even -if configured to do so by default or the mem_encrypt=on command line parameter -is specified. +activated in the BIOS, then all memory accesses will be encrypted and it +will not be necessary to activate the Linux memory encryption support. + +If the BIOS merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), +then memory encryption can be enabled by supplying mem_encrypt=on on the +kernel command line. However, if BIOS does not enable SME, then Linux +will not be able to activate memory encryption, even if configured to do +so by default or the mem_encrypt=on command line parameter is specified. Secure Nested Paging (SNP) ========================== diff --git a/Documentation/cgroups/namespace.txt b/Documentation/cgroups/namespace.txt new file mode 100644 index 0000000000000..a5b80e8f295f9 --- /dev/null +++ b/Documentation/cgroups/namespace.txt @@ -0,0 +1,142 @@ + CGroup Namespaces + +CGroup Namespace provides a mechanism to virtualize the view of the +/proc//cgroup file. The CLONE_NEWCGROUP clone-flag can be used with +clone() and unshare() syscalls to create a new cgroup namespace. +The process running inside the cgroup namespace will have its /proc//cgroup +output restricted to cgroupns-root. cgroupns-root is the cgroup of the process +at the time of creation of the cgroup namespace. + +Prior to CGroup Namespace, the /proc//cgroup file used to show complete +path of the cgroup of a process. In a container setup (where a set of cgroups +and namespaces are intended to isolate processes), the /proc//cgroup file +may leak potential system level information to the isolated processes. + +For Example: + $ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/container_id1 + +The path '/batchjobs/container_id1' can generally be considered as system-data +and its desirable to not expose it to the isolated process. + +CGroup Namespaces can be used to restrict visibility of this path. +For Example: + # Before creating cgroup namespace + $ ls -l /proc/self/ns/cgroup + lrwxrwxrwx 1 root root 0 2014-07-15 10:37 /proc/self/ns/cgroup -> cgroup:[4026531835] + $ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/container_id1 + + # unshare(CLONE_NEWCGROUP) and exec /bin/bash + $ ~/unshare -c + [ns]$ ls -l /proc/self/ns/cgroup + lrwxrwxrwx 1 root root 0 2014-07-15 10:35 /proc/self/ns/cgroup -> cgroup:[4026532183] + # From within new cgroupns, process sees that its in the root cgroup + [ns]$ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/ + + # From global cgroupns: + $ cat /proc//cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/container_id1 + + # Unshare cgroupns along with userns and mountns + # Following calls unshare(CLONE_NEWCGROUP|CLONE_NEWUSER|CLONE_NEWNS), then + # sets up uid/gid map and execs /bin/bash + $ ~/unshare -c -u -m + # Originally, we were in /batchjobs/container_id1 cgroup. Mount our own cgroup + # hierarchy. + [ns]$ mount -t cgroup cgroup /tmp/cgroup + [ns]$ ls -l /tmp/cgroup + total 0 + -r--r--r-- 1 root root 0 2014-10-13 09:32 cgroup.controllers + -r--r--r-- 1 root root 0 2014-10-13 09:32 cgroup.populated + -rw-r--r-- 1 root root 0 2014-10-13 09:25 cgroup.procs + -rw-r--r-- 1 root root 0 2014-10-13 09:32 cgroup.subtree_control + +The cgroupns-root (/batchjobs/container_id1 in above example) becomes the +filesystem root for the namespace specific cgroupfs mount. + +The virtualization of /proc/self/cgroup file combined with restricting +the view of cgroup hierarchy by namespace-private cgroupfs mount +should provide a completely isolated cgroup view inside the container. + +In its current form, the cgroup namespaces patcheset provides following +behavior: + +(1) The 'cgroupns-root' for a cgroup namespace is the cgroup in which + the process calling unshare is running. + For ex. if a process in /batchjobs/container_id1 cgroup calls unshare, + cgroup /batchjobs/container_id1 becomes the cgroupns-root. + For the init_cgroup_ns, this is the real root ('/') cgroup + (identified in code as cgrp_dfl_root.cgrp). + +(2) The cgroupns-root cgroup does not change even if the namespace + creator process later moves to a different cgroup. + $ ~/unshare -c # unshare cgroupns in some cgroup + [ns]$ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/ + [ns]$ mkdir sub_cgrp_1 + [ns]$ echo 0 > sub_cgrp_1/cgroup.procs + [ns]$ cat /proc/self/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/sub_cgrp_1 + +(3) Each process gets its CGROUPNS specific view of /proc//cgroup +(a) Processes running inside the cgroup namespace will be able to see + cgroup paths (in /proc/self/cgroup) only inside their root cgroup + [ns]$ sleep 100000 & # From within unshared cgroupns + [1] 7353 + [ns]$ echo 7353 > sub_cgrp_1/cgroup.procs + [ns]$ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/sub_cgrp_1 + +(b) From global cgroupns, the real cgroup path will be visible: + $ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/batchjobs/container_id1/sub_cgrp_1 + +(c) From a sibling cgroupns (cgroupns root-ed at a different cgroup), cgroup + path relative to its own cgroupns-root will be shown: + # ns2's cgroupns-root is at '/batchjobs/container_id2' + [ns2]$ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/../container_id2/sub_cgrp_1 + + Note that the relative path always starts with '/' to indicate that its + relative to the cgroupns-root of the caller. + +(4) Processes inside a cgroupns can move in-and-out of the cgroupns-root + (if they have proper access to external cgroups). + # From inside cgroupns (with cgroupns-root at /batchjobs/container_id1), and + # assuming that the global hierarchy is still accessible inside cgroupns: + $ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/sub_cgrp_1 + $ echo 7353 > batchjobs/container_id2/cgroup.procs + $ cat /proc/7353/cgroup + 0:cpuset,cpu,cpuacct,memory,devices,freezer,hugetlb:/../container_id2 + + Note that this kind of setup is not encouraged. A task inside cgroupns + should only be exposed to its own cgroupns hierarchy. Otherwise it makes + the virtualization of /proc//cgroup less useful. + +(5) Setns to another cgroup namespace is allowed when: + (a) the process has CAP_SYS_ADMIN in its current userns + (b) the process has CAP_SYS_ADMIN in the target cgroupns' userns + No implicit cgroup changes happen with attaching to another cgroupns. It + is expected that the somone moves the attaching process under the target + cgroupns-root. + +(6) When some thread from a multi-threaded process unshares its + cgroup-namespace, the new cgroupns gets applied to the entire process (all + the threads). For the unified-hierarchy this is expected as it only allows + process-level containerization. For the legacy hierarchies this may be + unexpected. So all the threads in the process will have the same cgroup. + +(7) The cgroup namespace is alive as long as there is atleast 1 + process inside it. When the last process exits, the cgroup + namespace is destroyed. The cgroupns-root and the actual cgroups + remain though. + +(8) Namespace specific cgroup hierarchy can be mounted by a process running + inside cgroupns: + $ mount -t cgroup -o __DEVEL__sane_behavior cgroup $MOUNT_POINT + + This will mount the unified cgroup hierarchy with cgroupns-root as the + filesystem root. The process needs CAP_SYS_ADMIN in its userns and mntns. diff --git a/Documentation/conf.py b/Documentation/conf.py index da64c9fb7e072..d148f3e8dd572 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -346,9 +346,9 @@ def get_cline_version(): html_static_path = ['sphinx-static'] # If true, Docutils "smart quotes" will be used to convert quotes and dashes -# to typographically correct entities. This will convert "--" to "—", -# which is not always what we want, so disable it. -smartquotes = False +# to typographically correct entities. However, conversion of "--" to "—" +# is not always what we want, so enable only quotes. +smartquotes_action = 'q' # Custom sidebar templates, maps document names to template names. # Note that the RTD theme ignores this diff --git a/Documentation/dev-tools/ubsan.rst b/Documentation/dev-tools/ubsan.rst index 2de7c63415da0..e3591f8e9d5b4 100644 --- a/Documentation/dev-tools/ubsan.rst +++ b/Documentation/dev-tools/ubsan.rst @@ -49,34 +49,22 @@ Report example Usage ----- -To enable UBSAN configure kernel with:: +To enable UBSAN, configure the kernel with:: - CONFIG_UBSAN=y + CONFIG_UBSAN=y -and to check the entire kernel:: - - CONFIG_UBSAN_SANITIZE_ALL=y - -To enable instrumentation for specific files or directories, add a line -similar to the following to the respective kernel Makefile: - -- For a single file (e.g. main.o):: - - UBSAN_SANITIZE_main.o := y - -- For all files in one directory:: - - UBSAN_SANITIZE := y - -To exclude files from being instrumented even if -``CONFIG_UBSAN_SANITIZE_ALL=y``, use:: +To exclude files from being instrumented use:: UBSAN_SANITIZE_main.o := n -and:: +and to exclude all targets in one directory use:: UBSAN_SANITIZE := n +When disabled for all targets, specific files can be enabled using:: + + UBSAN_SANITIZE_main.o := y + Detection of unaligned accesses controlled through the separate option - CONFIG_UBSAN_ALIGNMENT. It's off by default on architectures that support unaligned accesses (CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y). One could diff --git a/Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml index 0999ea07f47bb..e4576546bf0db 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,mdss.yaml @@ -127,6 +127,7 @@ patternProperties: - qcom,dsi-phy-20nm - qcom,dsi-phy-28nm-8226 - qcom,dsi-phy-28nm-hpm + - qcom,dsi-phy-28nm-hpm-fam-b - qcom,dsi-phy-28nm-lp - qcom,hdmi-phy-8084 - qcom,hdmi-phy-8660 diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml index c0d6a4fdff97e..e6dc5494baee2 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml @@ -53,6 +53,15 @@ patternProperties: compatible: const: qcom,sm8150-dpu + "^displayport-controller@[0-9a-f]+$": + type: object + additionalProperties: true + + properties: + compatible: + contains: + const: qcom,sm8150-dp + "^dsi@[0-9a-f]+$": type: object additionalProperties: true diff --git a/Documentation/devicetree/bindings/dma/fsl,edma.yaml b/Documentation/devicetree/bindings/dma/fsl,edma.yaml index 437db0c62339f..e1b4b910044b0 100644 --- a/Documentation/devicetree/bindings/dma/fsl,edma.yaml +++ b/Documentation/devicetree/bindings/dma/fsl,edma.yaml @@ -47,8 +47,8 @@ properties: - 3 dma-channels: - minItems: 1 - maxItems: 64 + minimum: 1 + maximum: 64 clocks: minItems: 1 diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml index 1812ef31d5f1e..3c36cd0510de8 100644 --- a/Documentation/devicetree/bindings/eeprom/at24.yaml +++ b/Documentation/devicetree/bindings/eeprom/at24.yaml @@ -68,14 +68,10 @@ properties: pattern: cs16$ - items: pattern: c32$ - - items: - pattern: c32d-wl$ - items: pattern: cs32$ - items: pattern: c64$ - - items: - pattern: c64d-wl$ - items: pattern: cs64$ - items: @@ -136,6 +132,7 @@ properties: - renesas,r1ex24128 - samsung,s524ad0xd1 - const: atmel,24c128 + - pattern: '^atmel,24c(32|64)d-wl$' # Actual vendor is st label: description: Descriptive name of the EEPROM. diff --git a/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml b/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml index 6adedd3ec399b..c22e459c175ab 100644 --- a/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml @@ -75,7 +75,7 @@ required: - clocks allOf: - - $ref: i2c-controller.yaml + - $ref: /schemas/i2c/i2c-controller.yaml# - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml index ab151c9db2191..580003cdfff59 100644 --- a/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml +++ b/Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml @@ -21,7 +21,7 @@ description: | google,cros-ec-spi or google,cros-ec-i2c. allOf: - - $ref: i2c-controller.yaml# + - $ref: /schemas/i2c/i2c-controller.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/iio/adc/adi,axi-adc.yaml b/Documentation/devicetree/bindings/iio/adc/adi,axi-adc.yaml index 9996dd93f84b2..e1f450b80db27 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,axi-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,axi-adc.yaml @@ -28,6 +28,9 @@ properties: reg: maxItems: 1 + clocks: + maxItems: 1 + dmas: maxItems: 1 @@ -39,12 +42,16 @@ properties: $ref: /schemas/types.yaml#/definitions/phandle description: A reference to a the actual ADC to which this FPGA ADC interfaces to. + deprecated: true + + '#io-backend-cells': + const: 0 required: - compatible - dmas - reg - - adi,adc-dev + - clocks additionalProperties: false @@ -55,7 +62,7 @@ examples: reg = <0x44a00000 0x10000>; dmas = <&rx_dma 0>; dma-names = "rx"; - - adi,adc-dev = <&spi_adc>; + clocks = <&axi_clk>; + #io-backend-cells = <0>; }; ... diff --git a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml index c13c10c8d65da..eed0df9d3a232 100644 --- a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml +++ b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml @@ -42,7 +42,7 @@ allOf: properties: compatible: contains: - const: maxim,max30100 + const: maxim,max30102 then: properties: maxim,green-led-current-microamp: false diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index a4042ae247702..38c48131e6e7b 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -484,7 +484,12 @@ allOf: - if: properties: compatible: - const: qcom,sm8450-smmu-500 + items: + - const: qcom,sm8450-smmu-500 + - const: qcom,adreno-smmu + - const: qcom,smmu-500 + - const: arm,mmu-500 + then: properties: clock-names: @@ -508,7 +513,11 @@ allOf: - if: properties: compatible: - const: qcom,sm8550-smmu-500 + items: + - const: qcom,sm8550-smmu-500 + - const: qcom,adreno-smmu + - const: qcom,smmu-500 + - const: arm,mmu-500 then: properties: clock-names: diff --git a/Documentation/devicetree/bindings/media/i2c/ovti,ov2680.yaml b/Documentation/devicetree/bindings/media/i2c/ovti,ov2680.yaml index cf456f8d9ddcb..c87677f5e2a25 100644 --- a/Documentation/devicetree/bindings/media/i2c/ovti,ov2680.yaml +++ b/Documentation/devicetree/bindings/media/i2c/ovti,ov2680.yaml @@ -37,15 +37,15 @@ properties: active low. maxItems: 1 - dovdd-supply: + DOVDD-supply: description: Definition of the regulator used as interface power supply. - avdd-supply: + AVDD-supply: description: Definition of the regulator used as analog power supply. - dvdd-supply: + DVDD-supply: description: Definition of the regulator used as digital power supply. @@ -59,9 +59,9 @@ required: - reg - clocks - clock-names - - dovdd-supply - - avdd-supply - - dvdd-supply + - DOVDD-supply + - AVDD-supply + - DVDD-supply - reset-gpios - port @@ -82,9 +82,9 @@ examples: clock-names = "xvclk"; reset-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>; - dovdd-supply = <&sw2_reg>; - dvdd-supply = <&sw2_reg>; - avdd-supply = <®_peri_3p15v>; + DOVDD-supply = <&sw2_reg>; + DVDD-supply = <&sw2_reg>; + AVDD-supply = <®_peri_3p15v>; port { ov2680_to_mipi: endpoint { diff --git a/Documentation/devicetree/bindings/media/i2c/techwell,tw9900.yaml b/Documentation/devicetree/bindings/media/i2c/techwell,tw9900.yaml index e37317f810722..c9673391afdbd 100644 --- a/Documentation/devicetree/bindings/media/i2c/techwell,tw9900.yaml +++ b/Documentation/devicetree/bindings/media/i2c/techwell,tw9900.yaml @@ -36,7 +36,7 @@ properties: properties: port@0: - $ref: /schemas/graph.yaml#/$defs/port-base + $ref: /schemas/graph.yaml#/properties/port description: Analog input port properties: diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml index e74502a0afe86..3202dc7967c5b 100644 --- a/Documentation/devicetree/bindings/net/mediatek,net.yaml +++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml @@ -337,8 +337,8 @@ allOf: minItems: 4 clocks: - minItems: 34 - maxItems: 34 + minItems: 24 + maxItems: 24 clock-names: items: @@ -351,18 +351,6 @@ allOf: - const: ethwarp_wocpu1 - const: ethwarp_wocpu0 - const: esw - - const: netsys0 - - const: netsys1 - - const: sgmii_tx250m - - const: sgmii_rx250m - - const: sgmii2_tx250m - - const: sgmii2_rx250m - - const: top_usxgmii0_sel - - const: top_usxgmii1_sel - - const: top_sgm0_sel - - const: top_sgm1_sel - - const: top_xfi_phy0_xtal_sel - - const: top_xfi_phy1_xtal_sel - const: top_eth_gmii_sel - const: top_eth_refck_50m_sel - const: top_eth_sys_200m_sel @@ -375,16 +363,10 @@ allOf: - const: top_netsys_sync_250m_sel - const: top_netsys_ppefb_250m_sel - const: top_netsys_warp_sel - - const: wocpu1 - - const: wocpu0 - const: xgp1 - const: xgp2 - const: xgp3 - mediatek,sgmiisys: - minItems: 2 - maxItems: 2 - patternProperties: "^mac@[0-1]$": type: object diff --git a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml index b6a7cb32f61e5..835b6db00c279 100644 --- a/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml +++ b/Documentation/devicetree/bindings/pci/rcar-pci-host.yaml @@ -77,6 +77,9 @@ properties: vpcie12v-supply: description: The 12v regulator to use for PCIe. + iommu-map: true + iommu-map-mask: true + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/pci/rockchip,rk3399-pcie.yaml b/Documentation/devicetree/bindings/pci/rockchip,rk3399-pcie.yaml index 531008f0b6ac3..002b728cbc718 100644 --- a/Documentation/devicetree/bindings/pci/rockchip,rk3399-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/rockchip,rk3399-pcie.yaml @@ -37,6 +37,7 @@ properties: description: This property is needed if using 24MHz OSC for RC's PHY. ep-gpios: + maxItems: 1 description: pre-reset GPIO vpcie12v-supply: diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml index 8474eef8d0ff5..b2bae42134a29 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml @@ -73,7 +73,6 @@ required: - reg - clocks - clock-names - - power-domains - resets - reset-names - vdda-phy-supply @@ -134,6 +133,21 @@ allOf: clock-names: maxItems: 1 + - if: + properties: + compatible: + contains: + enum: + - qcom,msm8996-qmp-ufs-phy + - qcom,msm8998-qmp-ufs-phy + then: + properties: + power-domains: + false + else: + required: + - power-domains + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml index 0f200e3f97a9a..fce7f8a19e9c0 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml @@ -15,9 +15,6 @@ description: | properties: compatible: oneOf: - - enum: - - qcom,sc8180x-usb-hs-phy - - qcom,usb-snps-femto-v2-phy - items: - enum: - qcom,sa8775p-usb-hs-phy @@ -26,6 +23,7 @@ properties: - items: - enum: - qcom,sc7280-usb-hs-phy + - qcom,sc8180x-usb-hs-phy - qcom,sdx55-usb-hs-phy - qcom,sdx65-usb-hs-phy - qcom,sm6375-usb-hs-phy diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml index bd72a326e6e06..60f30a59f3853 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml @@ -97,7 +97,8 @@ patternProperties: then: properties: groups: - enum: [emmc, emmc_rst] + items: + enum: [emmc, emmc_rst] - if: properties: function: @@ -105,8 +106,9 @@ patternProperties: then: properties: groups: - enum: [esw, esw_p0_p1, esw_p2_p3_p4, rgmii_via_esw, - rgmii_via_gmac1, rgmii_via_gmac2, mdc_mdio] + items: + enum: [esw, esw_p0_p1, esw_p2_p3_p4, rgmii_via_esw, + rgmii_via_gmac1, rgmii_via_gmac2, mdc_mdio] - if: properties: function: @@ -123,10 +125,11 @@ patternProperties: then: properties: groups: - enum: [i2s_in_mclk_bclk_ws, i2s1_in_data, i2s2_in_data, - i2s3_in_data, i2s4_in_data, i2s_out_mclk_bclk_ws, - i2s1_out_data, i2s2_out_data, i2s3_out_data, - i2s4_out_data] + items: + enum: [i2s_in_mclk_bclk_ws, i2s1_in_data, i2s2_in_data, + i2s3_in_data, i2s4_in_data, i2s_out_mclk_bclk_ws, + i2s1_out_data, i2s2_out_data, i2s3_out_data, + i2s4_out_data] - if: properties: function: @@ -159,10 +162,11 @@ patternProperties: then: properties: groups: - enum: [pcie0_0_waken, pcie0_1_waken, pcie1_0_waken, - pcie0_0_clkreq, pcie0_1_clkreq, pcie1_0_clkreq, - pcie0_pad_perst, pcie1_pad_perst, pcie_pereset, - pcie_wake, pcie_clkreq] + items: + enum: [pcie0_0_waken, pcie0_1_waken, pcie1_0_waken, + pcie0_0_clkreq, pcie0_1_clkreq, pcie1_0_clkreq, + pcie0_pad_perst, pcie1_pad_perst, pcie_pereset, + pcie_wake, pcie_clkreq] - if: properties: function: @@ -178,11 +182,12 @@ patternProperties: then: properties: groups: - enum: [pwm_ch1_0, pwm_ch1_1, pwm_ch1_2, pwm_ch2_0, pwm_ch2_1, - pwm_ch2_2, pwm_ch3_0, pwm_ch3_1, pwm_ch3_2, pwm_ch4_0, - pwm_ch4_1, pwm_ch4_2, pwm_ch4_3, pwm_ch5_0, pwm_ch5_1, - pwm_ch5_2, pwm_ch6_0, pwm_ch6_1, pwm_ch6_2, pwm_ch6_3, - pwm_ch7_0, pwm_0, pwm_1] + items: + enum: [pwm_ch1_0, pwm_ch1_1, pwm_ch1_2, pwm_ch2_0, pwm_ch2_1, + pwm_ch2_2, pwm_ch3_0, pwm_ch3_1, pwm_ch3_2, pwm_ch4_0, + pwm_ch4_1, pwm_ch4_2, pwm_ch4_3, pwm_ch5_0, pwm_ch5_1, + pwm_ch5_2, pwm_ch6_0, pwm_ch6_1, pwm_ch6_2, pwm_ch6_3, + pwm_ch7_0, pwm_0, pwm_1] - if: properties: function: @@ -260,33 +265,34 @@ patternProperties: pins: description: An array of strings. Each string contains the name of a pin. - enum: [GPIO_A, I2S1_IN, I2S1_OUT, I2S_BCLK, I2S_WS, I2S_MCLK, TXD0, - RXD0, SPI_WP, SPI_HOLD, SPI_CLK, SPI_MOSI, SPI_MISO, SPI_CS, - I2C_SDA, I2C_SCL, I2S2_IN, I2S3_IN, I2S4_IN, I2S2_OUT, - I2S3_OUT, I2S4_OUT, GPIO_B, MDC, MDIO, G2_TXD0, G2_TXD1, - G2_TXD2, G2_TXD3, G2_TXEN, G2_TXC, G2_RXD0, G2_RXD1, G2_RXD2, - G2_RXD3, G2_RXDV, G2_RXC, NCEB, NWEB, NREB, NDL4, NDL5, NDL6, - NDL7, NRB, NCLE, NALE, NDL0, NDL1, NDL2, NDL3, MDI_TP_P0, - MDI_TN_P0, MDI_RP_P0, MDI_RN_P0, MDI_TP_P1, MDI_TN_P1, - MDI_RP_P1, MDI_RN_P1, MDI_RP_P2, MDI_RN_P2, MDI_TP_P2, - MDI_TN_P2, MDI_TP_P3, MDI_TN_P3, MDI_RP_P3, MDI_RN_P3, - MDI_RP_P4, MDI_RN_P4, MDI_TP_P4, MDI_TN_P4, PMIC_SCL, - PMIC_SDA, SPIC1_CLK, SPIC1_MOSI, SPIC1_MISO, SPIC1_CS, - GPIO_D, WATCHDOG, RTS3_N, CTS3_N, TXD3, RXD3, PERST0_N, - PERST1_N, WLED_N, EPHY_LED0_N, AUXIN0, AUXIN1, AUXIN2, - AUXIN3, TXD4, RXD4, RTS4_N, CST4_N, PWM1, PWM2, PWM3, PWM4, - PWM5, PWM6, PWM7, GPIO_E, TOP_5G_CLK, TOP_5G_DATA, - WF0_5G_HB0, WF0_5G_HB1, WF0_5G_HB2, WF0_5G_HB3, WF0_5G_HB4, - WF0_5G_HB5, WF0_5G_HB6, XO_REQ, TOP_RST_N, SYS_WATCHDOG, - EPHY_LED0_N_JTDO, EPHY_LED1_N_JTDI, EPHY_LED2_N_JTMS, - EPHY_LED3_N_JTCLK, EPHY_LED4_N_JTRST_N, WF2G_LED_N, - WF5G_LED_N, GPIO_9, GPIO_10, GPIO_11, GPIO_12, UART1_TXD, - UART1_RXD, UART1_CTS, UART1_RTS, UART2_TXD, UART2_RXD, - UART2_CTS, UART2_RTS, SMI_MDC, SMI_MDIO, PCIE_PERESET_N, - PWM_0, GPIO_0, GPIO_1, GPIO_2, GPIO_3, GPIO_4, GPIO_5, - GPIO_6, GPIO_7, GPIO_8, UART0_TXD, UART0_RXD, TOP_2G_CLK, - TOP_2G_DATA, WF0_2G_HB0, WF0_2G_HB1, WF0_2G_HB2, WF0_2G_HB3, - WF0_2G_HB4, WF0_2G_HB5, WF0_2G_HB6] + items: + enum: [GPIO_A, I2S1_IN, I2S1_OUT, I2S_BCLK, I2S_WS, I2S_MCLK, TXD0, + RXD0, SPI_WP, SPI_HOLD, SPI_CLK, SPI_MOSI, SPI_MISO, SPI_CS, + I2C_SDA, I2C_SCL, I2S2_IN, I2S3_IN, I2S4_IN, I2S2_OUT, + I2S3_OUT, I2S4_OUT, GPIO_B, MDC, MDIO, G2_TXD0, G2_TXD1, + G2_TXD2, G2_TXD3, G2_TXEN, G2_TXC, G2_RXD0, G2_RXD1, G2_RXD2, + G2_RXD3, G2_RXDV, G2_RXC, NCEB, NWEB, NREB, NDL4, NDL5, NDL6, + NDL7, NRB, NCLE, NALE, NDL0, NDL1, NDL2, NDL3, MDI_TP_P0, + MDI_TN_P0, MDI_RP_P0, MDI_RN_P0, MDI_TP_P1, MDI_TN_P1, + MDI_RP_P1, MDI_RN_P1, MDI_RP_P2, MDI_RN_P2, MDI_TP_P2, + MDI_TN_P2, MDI_TP_P3, MDI_TN_P3, MDI_RP_P3, MDI_RN_P3, + MDI_RP_P4, MDI_RN_P4, MDI_TP_P4, MDI_TN_P4, PMIC_SCL, + PMIC_SDA, SPIC1_CLK, SPIC1_MOSI, SPIC1_MISO, SPIC1_CS, + GPIO_D, WATCHDOG, RTS3_N, CTS3_N, TXD3, RXD3, PERST0_N, + PERST1_N, WLED_N, EPHY_LED0_N, AUXIN0, AUXIN1, AUXIN2, + AUXIN3, TXD4, RXD4, RTS4_N, CST4_N, PWM1, PWM2, PWM3, PWM4, + PWM5, PWM6, PWM7, GPIO_E, TOP_5G_CLK, TOP_5G_DATA, + WF0_5G_HB0, WF0_5G_HB1, WF0_5G_HB2, WF0_5G_HB3, WF0_5G_HB4, + WF0_5G_HB5, WF0_5G_HB6, XO_REQ, TOP_RST_N, SYS_WATCHDOG, + EPHY_LED0_N_JTDO, EPHY_LED1_N_JTDI, EPHY_LED2_N_JTMS, + EPHY_LED3_N_JTCLK, EPHY_LED4_N_JTRST_N, WF2G_LED_N, + WF5G_LED_N, GPIO_9, GPIO_10, GPIO_11, GPIO_12, UART1_TXD, + UART1_RXD, UART1_CTS, UART1_RTS, UART2_TXD, UART2_RXD, + UART2_CTS, UART2_RTS, SMI_MDC, SMI_MDIO, PCIE_PERESET_N, + PWM_0, GPIO_0, GPIO_1, GPIO_2, GPIO_3, GPIO_4, GPIO_5, + GPIO_6, GPIO_7, GPIO_8, UART0_TXD, UART0_RXD, TOP_2G_CLK, + TOP_2G_DATA, WF0_2G_HB0, WF0_2G_HB1, WF0_2G_HB2, WF0_2G_HB3, + WF0_2G_HB4, WF0_2G_HB5, WF0_2G_HB6] bias-disable: true diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml index bb08ca5a1509e..53d59b641bf78 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm4450-tlmm.yaml @@ -72,40 +72,24 @@ $defs: description: Specify the alternative function to be configured for the specified pins. - enum: [ gpio, atest_char, atest_char0, atest_char1, atest_char2, - atest_char3, atest_usb0, atest_usb00, atest_usb01, atest_usb02, - atest_usb03, audio_ref, cam_mclk, cci_async, cci_i2c, - cci_timer0, cci_timer1, cci_timer2, cci_timer3, cci_timer4, - cmu_rng0, cmu_rng1, cmu_rng2, cmu_rng3, coex_uart1, cri_trng, - cri_trng0, cri_trng1, dbg_out, ddr_bist, ddr_pxi0, ddr_pxi1, - dp0_hot, gcc_gp1, gcc_gp2, gcc_gp3, host2wlan_sol, ibi_i3c, - jitter_bist, mdp_vsync, mdp_vsync0, mdp_vsync1, mdp_vsync2, - mdp_vsync3, mi2s0_data0, mi2s0_data1, mi2s0_sck, mi2s0_ws, - mi2s2_data0, mi2s2_data1, mi2s2_sck, mi2s2_ws, mi2s_mclk0, - mi2s_mclk1, nav_gpio0, nav_gpio1, nav_gpio2, pcie0_clk, - phase_flag0, phase_flag1, phase_flag10, phase_flag11, - phase_flag12, phase_flag13, phase_flag14, phase_flag15, - phase_flag16, phase_flag17, phase_flag18, phase_flag19, - phase_flag2, phase_flag20, phase_flag21, phase_flag22, - phase_flag23, phase_flag24, phase_flag25, phase_flag26, - phase_flag27, phase_flag28, phase_flag29, phase_flag3, - phase_flag30, phase_flag31, phase_flag4, phase_flag5, - phase_flag6, phase_flag7, phase_flag8, phase_flag9, - pll_bist, pll_clk, prng_rosc0, prng_rosc1, prng_rosc2, - prng_rosc3, qdss_cti, qdss_gpio, qdss_gpio0, qdss_gpio1, - qdss_gpio10, qdss_gpio11, qdss_gpio12, qdss_gpio13, qdss_gpio14, - qdss_gpio15, qdss_gpio2, qdss_gpio3, qdss_gpio4, qdss_gpio5, - qdss_gpio6, qdss_gpio7, qdss_gpio8, qdss_gpio9, qlink0_enable, - qlink0_request, qlink0_wmss, qlink1_enable, qlink1_request, - qlink1_wmss, qlink2_enable, qlink2_request, qlink2_wmss, - qup0_se0, qup0_se1, qup0_se2, qup0_se3, qup0_se4, qup0_se5, - qup0_se6, qup0_se7, qup1_se0, qup1_se1, qup1_se2, qup1_se3, - qup1_se4, qup1_se5, qup1_se6, sd_write, tb_trig, tgu_ch0, - tgu_ch1, tgu_ch2, tgu_ch3, tmess_prng0, tmess_prng1, - tmess_prng2, tmess_prng3, tsense_pwm1, tsense_pwm2, uim0_clk, - uim0_data, uim0_present, uim0_reset, uim1_clk, uim1_data, - uim1_present, uim1_reset, usb0_hs, usb0_phy, vfr_0, vfr_1, - vsense_trigger ] + enum: [ gpio, atest_char, atest_usb0, audio_ref_clk, cam_mclk, + cci_async_in0, cci_i2c, cci, cmu_rng, coex_uart1_rx, + coex_uart1_tx, cri_trng, dbg_out_clk, ddr_bist, + ddr_pxi0_test, ddr_pxi1_test, gcc_gp1_clk, gcc_gp2_clk, + gcc_gp3_clk, host2wlan_sol, ibi_i3c_qup0, ibi_i3c_qup1, + jitter_bist_ref, mdp_vsync0_out, mdp_vsync1_out, + mdp_vsync2_out, mdp_vsync3_out, mdp_vsync, nav, + pcie0_clk_req, phase_flag, pll_bist_sync, pll_clk_aux, + prng_rosc, qdss_cti_trig0, qdss_cti_trig1, qdss_gpio, + qlink0_enable, qlink0_request, qlink0_wmss_reset, + qup0_se0, qup0_se1, qup0_se2, qup0_se3, qup0_se4, + qup1_se0, qup1_se1, qup1_se2, qup1_se2_l2, qup1_se3, + qup1_se4, sd_write_protect, tb_trig_sdc1, tb_trig_sdc2, + tgu_ch0_trigout, tgu_ch1_trigout, tgu_ch2_trigout, + tgu_ch3_trigout, tmess_prng, tsense_pwm1_out, + tsense_pwm2_out, uim0, uim1, usb0_hs_ac, usb0_phy_ps, + vfr_0_mira, vfr_0_mirb, vfr_1, vsense_trigger_mirnat, + wlan1_adc_dtest0, wlan1_adc_dtest1 ] required: - pins diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml index 9793ea6f0fe65..575555810c2c2 100644 --- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml +++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml @@ -165,6 +165,7 @@ allOf: unevaluatedProperties: false pcie-phy: + type: object description: Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt diff --git a/Documentation/devicetree/bindings/sound/rt5645.txt b/Documentation/devicetree/bindings/sound/rt5645.txt index 41a62fd2ae1ff..c1fa379f5f3ea 100644 --- a/Documentation/devicetree/bindings/sound/rt5645.txt +++ b/Documentation/devicetree/bindings/sound/rt5645.txt @@ -20,6 +20,11 @@ Optional properties: a GPIO spec for the external headphone detect pin. If jd-mode = 0, we will get the JD status by getting the value of hp-detect-gpios. +- cbj-sleeve-gpios: + a GPIO spec to control the external combo jack circuit to tie the sleeve/ring2 + contacts to the ground or floating. It could avoid some electric noise from the + active speaker jacks. + - realtek,in2-differential Boolean. Indicate MIC2 input are differential, rather than single-ended. @@ -68,6 +73,7 @@ codec: rt5650@1a { compatible = "realtek,rt5650"; reg = <0x1a>; hp-detect-gpios = <&gpio 19 0>; + cbj-sleeve-gpios = <&gpio 20 0>; interrupt-parent = <&gpio>; interrupts = <7 IRQ_TYPE_EDGE_FALLING>; realtek,dmic-en = "true"; diff --git a/Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml b/Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml index f882903769f95..eee7c8d4cf4a2 100644 --- a/Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml +++ b/Documentation/devicetree/bindings/spmi/hisilicon,hisi-spmi-controller.yaml @@ -14,7 +14,7 @@ description: | It is a MIPI System Power Management (SPMI) controller. The PMIC part is provided by - ./Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml. + Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml. allOf: - $ref: spmi.yaml# @@ -48,7 +48,7 @@ patternProperties: PMIC properties, which are specific to the used SPMI PMIC device(s). When used in combination with HiSilicon 6421v600, the properties are documented at - drivers/staging/hikey9xx/hisilicon,hi6421-spmi-pmic.yaml. + Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml b/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml index b634f57cd011d..ca81c8afba79c 100644 --- a/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/loongson,ls2k-thermal.yaml @@ -18,13 +18,15 @@ properties: oneOf: - enum: - loongson,ls2k1000-thermal + - loongson,ls2k2000-thermal - items: - enum: - - loongson,ls2k2000-thermal + - loongson,ls2k0500-thermal - const: loongson,ls2k1000-thermal reg: - maxItems: 1 + minItems: 1 + maxItems: 2 interrupts: maxItems: 1 @@ -38,6 +40,24 @@ required: - interrupts - '#thermal-sensor-cells' +if: + properties: + compatible: + contains: + enum: + - loongson,ls2k2000-thermal + +then: + properties: + reg: + minItems: 2 + maxItems: 2 + +else: + properties: + reg: + maxItems: 1 + unevaluatedProperties: false examples: diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst index 6042085340953..833f68fb07008 100644 --- a/Documentation/driver-api/fpga/fpga-bridge.rst +++ b/Documentation/driver-api/fpga/fpga-bridge.rst @@ -6,9 +6,12 @@ API to implement a new FPGA bridge * struct fpga_bridge - The FPGA Bridge structure * struct fpga_bridge_ops - Low level Bridge driver ops -* fpga_bridge_register() - Create and register a bridge +* __fpga_bridge_register() - Create and register a bridge * fpga_bridge_unregister() - Unregister a bridge +The helper macro ``fpga_bridge_register()`` automatically sets +the module that registers the FPGA bridge as the owner. + .. kernel-doc:: include/linux/fpga/fpga-bridge.h :functions: fpga_bridge @@ -16,7 +19,7 @@ API to implement a new FPGA bridge :functions: fpga_bridge_ops .. kernel-doc:: drivers/fpga/fpga-bridge.c - :functions: fpga_bridge_register + :functions: __fpga_bridge_register .. kernel-doc:: drivers/fpga/fpga-bridge.c :functions: fpga_bridge_unregister diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst index 49c0a95126532..8d2b79f696c1f 100644 --- a/Documentation/driver-api/fpga/fpga-mgr.rst +++ b/Documentation/driver-api/fpga/fpga-mgr.rst @@ -24,7 +24,8 @@ How to support a new FPGA device -------------------------------- To add another FPGA manager, write a driver that implements a set of ops. The -probe function calls fpga_mgr_register() or fpga_mgr_register_full(), such as:: +probe function calls ``fpga_mgr_register()`` or ``fpga_mgr_register_full()``, +such as:: static const struct fpga_manager_ops socfpga_fpga_ops = { .write_init = socfpga_fpga_ops_configure_init, @@ -69,10 +70,11 @@ probe function calls fpga_mgr_register() or fpga_mgr_register_full(), such as:: } Alternatively, the probe function could call one of the resource managed -register functions, devm_fpga_mgr_register() or devm_fpga_mgr_register_full(). -When these functions are used, the parameter syntax is the same, but the call -to fpga_mgr_unregister() should be removed. In the above example, the -socfpga_fpga_remove() function would not be required. +register functions, ``devm_fpga_mgr_register()`` or +``devm_fpga_mgr_register_full()``. When these functions are used, the +parameter syntax is the same, but the call to ``fpga_mgr_unregister()`` should be +removed. In the above example, the ``socfpga_fpga_remove()`` function would not be +required. The ops will implement whatever device specific register writes are needed to do the programming sequence for this particular FPGA. These ops return 0 for @@ -125,15 +127,19 @@ API for implementing a new FPGA Manager driver * struct fpga_manager - the FPGA manager struct * struct fpga_manager_ops - Low level FPGA manager driver ops * struct fpga_manager_info - Parameter structure for fpga_mgr_register_full() -* fpga_mgr_register_full() - Create and register an FPGA manager using the +* __fpga_mgr_register_full() - Create and register an FPGA manager using the fpga_mgr_info structure to provide the full flexibility of options -* fpga_mgr_register() - Create and register an FPGA manager using standard +* __fpga_mgr_register() - Create and register an FPGA manager using standard arguments -* devm_fpga_mgr_register_full() - Resource managed version of - fpga_mgr_register_full() -* devm_fpga_mgr_register() - Resource managed version of fpga_mgr_register() +* __devm_fpga_mgr_register_full() - Resource managed version of + __fpga_mgr_register_full() +* __devm_fpga_mgr_register() - Resource managed version of __fpga_mgr_register() * fpga_mgr_unregister() - Unregister an FPGA manager +Helper macros ``fpga_mgr_register_full()``, ``fpga_mgr_register()``, +``devm_fpga_mgr_register_full()``, and ``devm_fpga_mgr_register()`` are available +to ease the registration. + .. kernel-doc:: include/linux/fpga/fpga-mgr.h :functions: fpga_mgr_states @@ -147,16 +153,16 @@ API for implementing a new FPGA Manager driver :functions: fpga_manager_info .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: fpga_mgr_register_full + :functions: __fpga_mgr_register_full .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: fpga_mgr_register + :functions: __fpga_mgr_register .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: devm_fpga_mgr_register_full + :functions: __devm_fpga_mgr_register_full .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: devm_fpga_mgr_register + :functions: __devm_fpga_mgr_register .. kernel-doc:: drivers/fpga/fpga-mgr.c :functions: fpga_mgr_unregister diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst index dc55d60a0b4a5..2d03b5fb76575 100644 --- a/Documentation/driver-api/fpga/fpga-region.rst +++ b/Documentation/driver-api/fpga/fpga-region.rst @@ -46,13 +46,16 @@ API to add a new FPGA region ---------------------------- * struct fpga_region - The FPGA region struct -* struct fpga_region_info - Parameter structure for fpga_region_register_full() -* fpga_region_register_full() - Create and register an FPGA region using the +* struct fpga_region_info - Parameter structure for __fpga_region_register_full() +* __fpga_region_register_full() - Create and register an FPGA region using the fpga_region_info structure to provide the full flexibility of options -* fpga_region_register() - Create and register an FPGA region using standard +* __fpga_region_register() - Create and register an FPGA region using standard arguments * fpga_region_unregister() - Unregister an FPGA region +Helper macros ``fpga_region_register()`` and ``fpga_region_register_full()`` +automatically set the module that registers the FPGA region as the owner. + The FPGA region's probe function will need to get a reference to the FPGA Manager it will be using to do the programming. This usually would happen during the region's probe function. @@ -82,10 +85,10 @@ following APIs to handle building or tearing down that list. :functions: fpga_region_info .. kernel-doc:: drivers/fpga/fpga-region.c - :functions: fpga_region_register_full + :functions: __fpga_region_register_full .. kernel-doc:: drivers/fpga/fpga-region.c - :functions: fpga_region_register + :functions: __fpga_region_register .. kernel-doc:: drivers/fpga/fpga-region.c :functions: fpga_region_unregister diff --git a/Documentation/driver-api/soundwire/stream.rst b/Documentation/driver-api/soundwire/stream.rst index b432a2de45d37..2a794484f62c9 100644 --- a/Documentation/driver-api/soundwire/stream.rst +++ b/Documentation/driver-api/soundwire/stream.rst @@ -324,12 +324,12 @@ framework, this stream state is linked to .hw_params() operation. int sdw_stream_add_master(struct sdw_bus * bus, struct sdw_stream_config * stream_config, - struct sdw_ports_config * ports_config, + const struct sdw_ports_config * ports_config, struct sdw_stream_runtime * stream); int sdw_stream_add_slave(struct sdw_slave * slave, struct sdw_stream_config * stream_config, - struct sdw_ports_config * ports_config, + const struct sdw_ports_config * ports_config, struct sdw_stream_runtime * stream); diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index d32c6209685d6..dbfbbe9ab28b1 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -126,9 +126,7 @@ norecovery Disable the roll-forward recovery routine, mounted read- discard/nodiscard Enable/disable real-time discard in f2fs, if discard is enabled, f2fs will issue discard/TRIM commands when a segment is cleaned. -no_heap Disable heap-style segment allocation which finds free - segments for data from the beginning of main area, while - for node from the end of main area. +heap/no_heap Deprecated. nouser_xattr Disable Extended User Attributes. Note: xattr is enabled by default if CONFIG_F2FS_FS_XATTR is selected. noacl Disable POSIX Access Control List. Note: acl is enabled @@ -228,8 +226,6 @@ mode=%s Control block allocation mode which supports "adaptive" option for more randomness. Please, use these options for your experiments and we strongly recommend to re-format the filesystem after using these options. -io_bits=%u Set the bit size of write IO requests. It should be set - with "mode=lfs". usrquota Enable plain user disk quota accounting. grpquota Enable plain group disk quota accounting. prjquota Enable plain project quota accounting. diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst index 2466d3363af79..ad50ca6f495eb 100644 --- a/Documentation/mm/arch_pgtable_helpers.rst +++ b/Documentation/mm/arch_pgtable_helpers.rst @@ -140,7 +140,8 @@ PMD Page Table Helpers +---------------------------+--------------------------------------------------+ | pmd_swp_clear_soft_dirty | Clears a soft dirty swapped PMD | +---------------------------+--------------------------------------------------+ -| pmd_mkinvalid | Invalidates a mapped PMD [1] | +| pmd_mkinvalid | Invalidates a present PMD; do not call for | +| | non-present PMD [1] | +---------------------------+--------------------------------------------------+ | pmd_set_huge | Creates a PMD huge mapping | +---------------------------+--------------------------------------------------+ @@ -196,7 +197,8 @@ PUD Page Table Helpers +---------------------------+--------------------------------------------------+ | pud_mkdevmap | Creates a ZONE_DEVICE mapped PUD | +---------------------------+--------------------------------------------------+ -| pud_mkinvalid | Invalidates a mapped PUD [1] | +| pud_mkinvalid | Invalidates a present PUD; do not call for | +| | non-present PUD [1] | +---------------------------+--------------------------------------------------+ | pud_set_huge | Creates a PUD huge mapping | +---------------------------+--------------------------------------------------+ diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index cf6eaa0da821b..09fbb4c03fc8d 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -290,7 +290,7 @@ attribute-sets: enum: eswitch-mode - name: eswitch-inline-mode - type: u16 + type: u8 enum: eswitch-inline-mode - name: dpipe-tables diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 3dcc9ece272aa..d0c821c202036 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -274,6 +274,7 @@ attribute-sets: - name: capabilities type: u32 + enum: pin-capabilities - name: parent-device type: nest diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index 8e4d19adee8cd..4e702ac8bf66b 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -1144,6 +1144,12 @@ attribute-sets: - name: mcast-querier-state type: binary + - + name: fdb-n-learned + type: u32 + - + name: fdb-max-learned + type: u32 - name: linkinfo-brport-attrs name-prefix: ifla-brport- diff --git a/Documentation/networking/device_drivers/wwan/t7xx.rst b/Documentation/networking/device_drivers/wwan/t7xx.rst index dd5b731957ca4..f346f5f85f154 100644 --- a/Documentation/networking/device_drivers/wwan/t7xx.rst +++ b/Documentation/networking/device_drivers/wwan/t7xx.rst @@ -39,6 +39,34 @@ command and receive response: - open the AT control channel using a UART tool or a special user tool +Sysfs +===== +The driver provides sysfs interfaces to userspace. + +t7xx_mode +--------- +The sysfs interface provides userspace with access to the device mode, this interface +supports read and write operations. + +Device mode: + +- ``unknown`` represents that device in unknown status +- ``ready`` represents that device in ready status +- ``reset`` represents that device in reset status +- ``fastboot_switching`` represents that device in fastboot switching status +- ``fastboot_download`` represents that device in fastboot download status +- ``fastboot_dump`` represents that device in fastboot dump status + +Read from userspace to get the current device mode. + +:: + $ cat /sys/bus/pci/devices/${bdf}/t7xx_mode + +Write from userspace to set the device mode. + +:: + $ echo fastboot_switching > /sys/bus/pci/devices/${bdf}/t7xx_mode + Management application development ================================== The driver and userspace interfaces are described below. The MBIM protocol is @@ -97,6 +125,20 @@ The driver exposes an AT port by implementing AT WWAN Port. The userspace end of the control port is a /dev/wwan0at0 character device. Application shall use this interface to issue AT commands. +fastboot port userspace ABI +--------------------------- + +/dev/wwan0fastboot0 character device +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +The driver exposes a fastboot protocol interface by implementing +fastboot WWAN Port. The userspace end of the fastboot channel pipe is a +/dev/wwan0fastboot0 character device. Application shall use this interface for +fastboot protocol communication. + +Please note that driver needs to be reloaded to export /dev/wwan0fastboot0 +port, because device needs a cold reset after enter ``fastboot_switching`` +mode. + The MediaTek's T700 modem supports the 3GPP TS 27.007 [4] specification. References @@ -118,3 +160,7 @@ speak the Mobile Interface Broadband Model (MBIM) protocol"* [4] *Specification # 27.007 - 3GPP* - https://www.3gpp.org/DynaReport/27007.htm + +[5] *fastboot "a mechanism for communicating with bootloaders"* + +- https://android.googlesource.com/platform/system/core/+/refs/heads/main/fastboot/README.md diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index dceb49d56a911..70c4fb9d4e5ce 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -13,7 +13,7 @@ struct_dev_ifalias* ifalias unsigned_long mem_end unsigned_long mem_start unsigned_long base_addr -unsigned_long state +unsigned_long state read_mostly read_mostly netif_running(dev) struct_list_head dev_list struct_list_head napi_list struct_list_head unreg_list diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 50b3d1cb11159..eab7e2f8c1965 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -31,7 +31,7 @@ you probably needn't concern yourself with pcmciautils. ====================== =============== ======================================== GNU C 5.1 gcc --version Clang/LLVM (optional) 11.0.0 clang --version -Rust (optional) 1.74.1 rustc --version +Rust (optional) 1.75.0 rustc --version bindgen (optional) 0.65.1 bindgen --version GNU make 3.82 make --version bash 4.2 bash --version diff --git a/Documentation/sphinx/cdomain.py b/Documentation/sphinx/cdomain.py index e6959af25402d..8f335e23f5906 100644 --- a/Documentation/sphinx/cdomain.py +++ b/Documentation/sphinx/cdomain.py @@ -37,12 +37,29 @@ import sphinx from sphinx import addnodes -from sphinx.domains.c import c_funcptr_sig_re, c_sig_re from sphinx.domains.c import CObject as Base_CObject from sphinx.domains.c import CDomain as Base_CDomain from itertools import chain import re +# fixes https://github.com/sphinx-doc/sphinx/commit/0f49e30c51b5cc5055cda5b4b294c2dd9d1df573#r38750737 + +# pylint: disable=invalid-name +c_sig_re = re.compile( + r'''^([^(]*?) # return type + ([\w:.]+) \s* # thing name (colon allowed for C++) + (?: \((.*)\) )? # optionally arguments + (\s+const)? $ # const specifier + ''', re.VERBOSE) + +c_funcptr_sig_re = re.compile( + r'''^([^(]+?) # return type + (\( [^()]+ \)) \s* # name in parentheses + \( (.*) \) # arguments + (\s+const)? $ # const specifier + ''', re.VERBOSE) +# pylint: enable=invalid-name + __version__ = '1.1' # Get Sphinx version diff --git a/Documentation/sphinx/kernel_include.py b/Documentation/sphinx/kernel_include.py index abe7680883771..6387624423363 100755 --- a/Documentation/sphinx/kernel_include.py +++ b/Documentation/sphinx/kernel_include.py @@ -97,7 +97,6 @@ def _run(self): # HINT: this is the only line I had to change / commented out: #path = utils.relative_path(None, path) - path = nodes.reprunicode(path) encoding = self.options.get( 'encoding', self.state.document.settings.input_encoding) e_handler=self.state.document.settings.input_encoding_error_handler diff --git a/Documentation/userspace-api/media/mediactl/media-types.rst b/Documentation/userspace-api/media/mediactl/media-types.rst index 0ffeece1e0c8e..6332e8395263b 100644 --- a/Documentation/userspace-api/media/mediactl/media-types.rst +++ b/Documentation/userspace-api/media/mediactl/media-types.rst @@ -375,12 +375,11 @@ Types and flags used to represent the media graph elements are origins of links. * - ``MEDIA_PAD_FL_MUST_CONNECT`` - - If this flag is set and the pad is linked to any other pad, then - at least one of those links must be enabled for the entity to be - able to stream. There could be temporary reasons (e.g. device - configuration dependent) for the pad to need enabled links even - when this flag isn't set; the absence of the flag doesn't imply - there is none. + - If this flag is set, then for this pad to be able to stream, it must + be connected by at least one enabled link. There could be temporary + reasons (e.g. device configuration dependent) for the pad to need + enabled links even when this flag isn't set; the absence of the flag + doesn't imply there is none. One and only one of ``MEDIA_PAD_FL_SINK`` and ``MEDIA_PAD_FL_SOURCE`` diff --git a/Kbuild b/Kbuild index 464b34a08f51e..be2896d84de68 100644 --- a/Kbuild +++ b/Kbuild @@ -97,3 +97,4 @@ obj-$(CONFIG_SAMPLES) += samples/ obj-$(CONFIG_NET) += net/ obj-y += virt/ obj-y += $(ARCH_DRIVERS) +obj-y += ubuntu/ diff --git a/Kconfig b/Kconfig index 745bc773f5670..d4e064d7522c0 100644 --- a/Kconfig +++ b/Kconfig @@ -19,6 +19,8 @@ source "net/Kconfig" source "drivers/Kconfig" +source "ubuntu/Kconfig" + source "fs/Kconfig" source "security/Kconfig" diff --git a/MAINTAINERS b/MAINTAINERS index 1aabf1c15bb30..29e9003d123a8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -190,6 +190,18 @@ M: Linus Walleij F: Documentation/devicetree/bindings/power/supply/*ab8500* F: drivers/power/supply/*ab8500* +AAEON DEVICE DRIVER WITH WMI INTERFACE +M: Edward Lin +M: Kunyang Fan +M: Frank Hsieh +M: Jacob Wu +S: Supported +F: drivers/gpio/gpio-aaeon.c +F: drivers/hwmon/hwmon-aaeon.c +F: drivers/leds/leds-aaeon.c +F: drivers/mfd/mfd-aaeon.c +F: drivers/watchdog/wdt_aaeon.c + ABI/API L: linux-api@vger.kernel.org F: include/linux/syscalls.h @@ -1054,7 +1066,6 @@ L: linux-pm@vger.kernel.org S: Supported F: Documentation/admin-guide/pm/amd-pstate.rst F: drivers/cpufreq/amd-pstate* -F: include/linux/amd-pstate.h F: tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py AMD PTDMA DRIVER @@ -10389,6 +10400,14 @@ L: linux-media@vger.kernel.org S: Maintained F: drivers/media/rc/iguanair.c +IIO BACKEND FRAMEWORK +M: Nuno Sa +R: Olivier Moysan +L: linux-iio@vger.kernel.org +S: Maintained +F: drivers/iio/industrialio-backend.c +F: include/linux/iio/backend.h + IIO DIGITAL POTENTIOMETER DAC M: Peter Rosin L: linux-iio@vger.kernel.org diff --git a/Makefile b/Makefile index c7ee53f4bf044..7970efc804ae6 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 8 -SUBLEVEL = 0 +SUBLEVEL = 12 EXTRAVERSION = NAME = Hurr durr I'ma ninja sloth @@ -735,8 +735,11 @@ endif ifeq ($(KBUILD_EXTMOD),) # Objects we will link into vmlinux / subdirs we need to visit -core-y := -drivers-y := +core-y := init/ usr/ arch/$(SRCARCH)/ +drivers-y := drivers/ sound/ +drivers-$(CONFIG_SAMPLES) += samples/ +drivers-$(CONFIG_NET) += net/ +drivers-y += virt/ libs-y := lib/ endif # KBUILD_EXTMOD @@ -943,7 +946,6 @@ endif ifdef CONFIG_LTO_CLANG ifdef CONFIG_LTO_CLANG_THIN CC_FLAGS_LTO := -flto=thin -fsplit-lto-unit -KBUILD_LDFLAGS += --thinlto-cache-dir=$(extmod_prefix).thinlto-cache else CC_FLAGS_LTO := -flto endif @@ -1278,8 +1280,9 @@ export INSTALL_HDR_PATH = $(objtree)/usr quiet_cmd_headers_install = INSTALL $(INSTALL_HDR_PATH)/include cmd_headers_install = \ mkdir -p $(INSTALL_HDR_PATH); \ - rsync -mrl --include='*/' --include='*\.h' --exclude='*' \ - usr/include $(INSTALL_HDR_PATH) + find usr/include -type f -name '*.h' -print0 | \ + tar -czf - --null --no-recursion --no-wildcards-match-slash -T- | \ + tar -xzf - --strip-components=1 -C $(INSTALL_HDR_PATH) PHONY += headers_install headers_install: headers @@ -1479,13 +1482,13 @@ endif # CONFIG_MODULES # Directories & files removed with 'make clean' CLEAN_FILES += vmlinux.symvers modules-only.symvers \ modules.builtin modules.builtin.modinfo modules.nsdeps \ - compile_commands.json .thinlto-cache rust/test \ + compile_commands.json rust/test \ rust-project.json .vmlinux.objs .vmlinux.export.c # Directories & files removed with 'make mrproper' MRPROPER_FILES += include/config include/generated \ arch/$(SRCARCH)/include/generated .objdiff \ - debian snap tar-install \ + snap tar-install \ .config .config.old .version \ Module.symvers \ certs/signing_key.pem \ @@ -1785,7 +1788,7 @@ PHONY += compile_commands.json clean-dirs := $(KBUILD_EXTMOD) clean: rm-files := $(KBUILD_EXTMOD)/Module.symvers $(KBUILD_EXTMOD)/modules.nsdeps \ - $(KBUILD_EXTMOD)/compile_commands.json $(KBUILD_EXTMOD)/.thinlto-cache + $(KBUILD_EXTMOD)/compile_commands.json PHONY += prepare # now expand this into a simple variable to reduce the cost of shell evaluations diff --git a/Ubuntu.md b/Ubuntu.md new file mode 100644 index 0000000000000..1d7bea1caf7fc --- /dev/null +++ b/Ubuntu.md @@ -0,0 +1,8 @@ +Name: linux +Version: 6.1.0 +Series: 23.04 (lunar) +Description: + This is the source code for the Ubuntu linux kernel for the 23.04 series. This + source tree is used to produce the flavours: generic, generic-64k, generic-lpae. + This kernel is configured to support the widest range of desktop, laptop and + server configurations. diff --git a/arch/Kconfig b/arch/Kconfig index a5af0edd3eb8f..03cd763ed40c1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -9,6 +9,14 @@ # source "arch/$(SRCARCH)/Kconfig" +config ARCH_CONFIGURES_CPU_MITIGATIONS + bool + +if !ARCH_CONFIGURES_CPU_MITIGATIONS +config CPU_MITIGATIONS + def_bool y +endif + menu "General architecture-dependent options" config ARCH_HAS_SUBPAGE_FAULTS diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 6691f42550778..41b980df862b1 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -205,7 +205,6 @@ }; gmac: ethernet@8000 { - #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; interrupts = <10>; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0af6709570d14..c45e3bfb9f16e 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -29,7 +29,7 @@ config ARM select ARCH_HAVE_NMI_SAFE_CMPXCHG if CPU_V7 || CPU_V7M || CPU_V6K select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_KEEP_MEMBLOCK - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7 @@ -503,8 +503,8 @@ source "arch/arm/mm/Kconfig" config IWMMXT bool "Enable iWMMXt support" - depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4 || CPU_PJ4B - default y if PXA27x || PXA3xx || ARCH_MMP || CPU_PJ4 || CPU_PJ4B + depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK + default y if PXA27x || PXA3xx || ARCH_MMP help Enable support for iWMMXt context switching at run time if running on a CPU that supports it. diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 473280d5adce3..66f868e817215 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -59,6 +59,9 @@ endif # KBUILD_CFLAGS += $(call cc-option,-fno-ipa-sra) +# Need -msoft-float for gcc 11 for the below instruction set selection +KBUILD_CFLAGS += -msoft-float + # This selects which instruction set is used. arch-$(CONFIG_CPU_32v7M) :=-march=armv7-m arch-$(CONFIG_CPU_32v7) :=-march=armv7-a @@ -141,7 +144,7 @@ endif # Need -Uarm for gcc < 3.x KBUILD_CPPFLAGS +=$(cpp-y) -KBUILD_CFLAGS +=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm +KBUILD_CFLAGS +=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -Uarm KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include asm/unified.h -msoft-float CHECKFLAGS += -D__arm__ diff --git a/arch/arm/boot/dts/arm/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm/arm-realview-pb1176.dts index efed325af88d2..d99bac02232b3 100644 --- a/arch/arm/boot/dts/arm/arm-realview-pb1176.dts +++ b/arch/arm/boot/dts/arm/arm-realview-pb1176.dts @@ -451,7 +451,7 @@ /* Direct-mapped development chip ROM */ pb1176_rom@10200000 { - compatible = "direct-mapped"; + compatible = "mtd-rom"; reg = <0x10200000 0x4000>; bank-width = <1>; }; diff --git a/arch/arm/boot/dts/marvell/mmp2-brownstone.dts b/arch/arm/boot/dts/marvell/mmp2-brownstone.dts index 04f1ae1382e7a..bc64348b82185 100644 --- a/arch/arm/boot/dts/marvell/mmp2-brownstone.dts +++ b/arch/arm/boot/dts/marvell/mmp2-brownstone.dts @@ -28,7 +28,7 @@ &twsi1 { status = "okay"; pmic: max8925@3c { - compatible = "maxium,max8925"; + compatible = "maxim,max8925"; reg = <0x3c>; interrupts = <1>; interrupt-parent = <&intcmux4>; diff --git a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts index 217e9b96c61e5..20b2497657ae4 100644 --- a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts @@ -293,7 +293,7 @@ regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1150000>; + regulator-suspend-microvolt = <1150000>; regulator-mode = <4>; }; @@ -314,7 +314,7 @@ regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1050000>; + regulator-suspend-microvolt = <1050000>; regulator-mode = <4>; }; @@ -331,7 +331,7 @@ regulator-always-on; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; @@ -346,7 +346,7 @@ regulator-max-microvolt = <3700000>; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi index 3be38a3c4bb11..c32ea040fecdd 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp4-common.dtsi @@ -117,17 +117,9 @@ #address-cells = <1>; #size-cells = <0>; - phy_port2: phy@1 { - reg = <1>; - }; - - phy_port3: phy@2 { - reg = <2>; - }; - switch@10 { compatible = "qca,qca8334"; - reg = <10>; + reg = <0x10>; reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; switch_ports: ports { @@ -149,15 +141,30 @@ eth2: port@2 { reg = <2>; label = "eth2"; + phy-mode = "internal"; phy-handle = <&phy_port2>; }; eth1: port@3 { reg = <3>; label = "eth1"; + phy-mode = "internal"; phy-handle = <&phy_port3>; }; }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + phy_port2: ethernet-phy@1 { + reg = <1>; + }; + + phy_port3: ethernet-phy@2 { + reg = <2>; + }; + }; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi index 3fdece5bd31f9..5248a058230c8 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi @@ -805,6 +805,7 @@ &pinctrl_usb_pwr>; dr_mode = "host"; power-active-high; + over-current-active-low; disable-over-current; status = "okay"; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts b/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts index ba7231b364bb8..7bab113ca6da7 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts @@ -210,6 +210,7 @@ remote-endpoint = <&mipi_from_sensor>; clock-lanes = <0>; data-lanes = <1>; + link-frequencies = /bits/ 64 <330000000>; }; }; }; diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi index b1413983787c2..083ab780ab7e4 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-msm8974.dtsi @@ -1234,7 +1234,7 @@ qfprom: qfprom@fc4bc000 { compatible = "qcom,msm8974-qfprom", "qcom,qfprom"; - reg = <0xfc4bc000 0x1000>; + reg = <0xfc4bc000 0x2100>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts b/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts index ed75c01dbee10..3d02f065f71c2 100644 --- a/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts +++ b/arch/arm/boot/dts/renesas/r8a73a4-ape6evm.dts @@ -209,6 +209,18 @@ status = "okay"; }; +&extal1_clk { + clock-frequency = <26000000>; +}; + +&extal2_clk { + clock-frequency = <48000000>; +}; + +&extalr_clk { + clock-frequency = <32768>; +}; + &pfc { scifa0_pins: scifa0 { groups = "scifa0_data"; diff --git a/arch/arm/boot/dts/renesas/r8a73a4.dtsi b/arch/arm/boot/dts/renesas/r8a73a4.dtsi index c39066967053f..d1f4cbd099efb 100644 --- a/arch/arm/boot/dts/renesas/r8a73a4.dtsi +++ b/arch/arm/boot/dts/renesas/r8a73a4.dtsi @@ -450,17 +450,20 @@ extalr_clk: extalr { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <32768>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; extal1_clk: extal1 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <25000000>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; extal2_clk: extal2 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <48000000>; + /* This value must be overridden by the board. */ + clock-frequency = <0>; }; fsiack_clk: fsiack { compatible = "fixed-clock"; diff --git a/arch/arm/boot/dts/rockchip/rk322x.dtsi b/arch/arm/boot/dts/rockchip/rk322x.dtsi index 831561fc18146..96421355c2746 100644 --- a/arch/arm/boot/dts/rockchip/rk322x.dtsi +++ b/arch/arm/boot/dts/rockchip/rk322x.dtsi @@ -736,14 +736,20 @@ status = "disabled"; ports { - hdmi_in: port { - #address-cells = <1>; - #size-cells = <0>; - hdmi_in_vop: endpoint@0 { - reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + + hdmi_in_vop: endpoint { remote-endpoint = <&vop_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm/boot/dts/rockchip/rk3288.dtsi b/arch/arm/boot/dts/rockchip/rk3288.dtsi index ead343dc3df10..3f1d640afafae 100644 --- a/arch/arm/boot/dts/rockchip/rk3288.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3288.dtsi @@ -1240,27 +1240,37 @@ compatible = "rockchip,rk3288-dw-hdmi"; reg = <0x0 0xff980000 0x0 0x20000>; reg-io-width = <4>; - #sound-dai-cells = <0>; - rockchip,grf = <&grf>; interrupts = ; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_HDCP>, <&cru SCLK_HDMI_CEC>; clock-names = "iahb", "isfr", "cec"; power-domains = <&power RK3288_PD_VIO>; + rockchip,grf = <&grf>; + #sound-dai-cells = <0>; status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; + hdmi_in_vopb: endpoint@0 { reg = <0>; remote-endpoint = <&vopb_out_hdmi>; }; + hdmi_in_vopl: endpoint@1 { reg = <1>; remote-endpoint = <&vopl_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm/boot/dts/samsung/exynos4210-smdkv310.dts b/arch/arm/boot/dts/samsung/exynos4210-smdkv310.dts index b566f878ed84f..18f4f494093ba 100644 --- a/arch/arm/boot/dts/samsung/exynos4210-smdkv310.dts +++ b/arch/arm/boot/dts/samsung/exynos4210-smdkv310.dts @@ -88,7 +88,7 @@ &keypad { samsung,keypad-num-rows = <2>; samsung,keypad-num-columns = <8>; - linux,keypad-no-autorepeat; + linux,input-no-autorepeat; wakeup-source; pinctrl-names = "default"; pinctrl-0 = <&keypad_rows &keypad_cols>; diff --git a/arch/arm/boot/dts/samsung/exynos4412-origen.dts b/arch/arm/boot/dts/samsung/exynos4412-origen.dts index 23b151645d668..10ab7bc90f502 100644 --- a/arch/arm/boot/dts/samsung/exynos4412-origen.dts +++ b/arch/arm/boot/dts/samsung/exynos4412-origen.dts @@ -453,7 +453,7 @@ &keypad { samsung,keypad-num-rows = <3>; samsung,keypad-num-columns = <2>; - linux,keypad-no-autorepeat; + linux,input-no-autorepeat; wakeup-source; pinctrl-0 = <&keypad_rows &keypad_cols>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/samsung/exynos4412-smdk4412.dts b/arch/arm/boot/dts/samsung/exynos4412-smdk4412.dts index 715dfcba14174..e16df9e75fcb0 100644 --- a/arch/arm/boot/dts/samsung/exynos4412-smdk4412.dts +++ b/arch/arm/boot/dts/samsung/exynos4412-smdk4412.dts @@ -69,7 +69,7 @@ &keypad { samsung,keypad-num-rows = <3>; samsung,keypad-num-columns = <8>; - linux,keypad-no-autorepeat; + linux,input-no-autorepeat; wakeup-source; pinctrl-0 = <&keypad_rows &keypad_cols>; pinctrl-names = "default"; diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index bddc82f789421..a83d29fed1756 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -110,6 +110,7 @@ CONFIG_DRM_PANEL_LVDS=y CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_PANEL_EDP=y CONFIG_DRM_SIMPLE_BRIDGE=y +CONFIG_DRM_DW_HDMI=y CONFIG_DRM_LIMA=y CONFIG_FB_SIMPLE=y CONFIG_BACKLIGHT_CLASS_DEVICE=y diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c index 433ee4ddce6c8..f85933fdec75f 100644 --- a/arch/arm/crypto/sha256_glue.c +++ b/arch/arm/crypto/sha256_glue.c @@ -24,8 +24,8 @@ #include "sha256_glue.h" -asmlinkage void sha256_block_data_order(u32 *digest, const void *data, - unsigned int num_blks); +asmlinkage void sha256_block_data_order(struct sha256_state *state, + const u8 *data, int num_blks); int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, unsigned int len) @@ -33,23 +33,20 @@ int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, /* make sure casting to sha256_block_fn() is safe */ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); - return sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_block_data_order); + return sha256_base_do_update(desc, data, len, sha256_block_data_order); } EXPORT_SYMBOL(crypto_sha256_arm_update); static int crypto_sha256_arm_final(struct shash_desc *desc, u8 *out) { - sha256_base_do_finalize(desc, - (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_finalize(desc, sha256_block_data_order); return sha256_base_finish(desc, out); } int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_update(desc, data, len, sha256_block_data_order); return crypto_sha256_arm_final(desc, out); } EXPORT_SYMBOL(crypto_sha256_arm_finup); diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c index 0635a65aa488b..1be5bd498af36 100644 --- a/arch/arm/crypto/sha512-glue.c +++ b/arch/arm/crypto/sha512-glue.c @@ -25,27 +25,25 @@ MODULE_ALIAS_CRYPTO("sha512"); MODULE_ALIAS_CRYPTO("sha384-arm"); MODULE_ALIAS_CRYPTO("sha512-arm"); -asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks); +asmlinkage void sha512_block_data_order(struct sha512_state *state, + u8 const *src, int blocks); int sha512_arm_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_block_data_order); + return sha512_base_do_update(desc, data, len, sha512_block_data_order); } static int sha512_arm_final(struct shash_desc *desc, u8 *out) { - sha512_base_do_finalize(desc, - (sha512_block_fn *)sha512_block_data_order); + sha512_base_do_finalize(desc, sha512_block_data_order); return sha512_base_finish(desc, out); } int sha512_arm_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_block_data_order); + sha512_base_do_update(desc, data, len, sha512_block_data_order); return sha512_arm_final(desc, out); } diff --git a/arch/arm/include/asm/mman.h b/arch/arm/include/asm/mman.h new file mode 100644 index 0000000000000..2189e507c8e08 --- /dev/null +++ b/arch/arm/include/asm/mman.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include +#include + +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return cpu_architecture() >= CPU_ARCH_ARMv6; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported + +#endif /* __ASM_MMAN_H__ */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 771264d4726a7..ae2f2b2b4e5ab 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -75,8 +75,6 @@ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_CPU_XSCALE) += xscale-cp0.o obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o -obj-$(CONFIG_CPU_PJ4) += pj4-cp0.o -obj-$(CONFIG_CPU_PJ4B) += pj4-cp0.o obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_xscale.o perf_event_v6.o \ diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S index a0218c4867b9b..4a335d3c59690 100644 --- a/arch/arm/kernel/iwmmxt.S +++ b/arch/arm/kernel/iwmmxt.S @@ -18,18 +18,6 @@ #include #include "iwmmxt.h" -#if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B) -#define PJ4(code...) code -#define XSC(code...) -#elif defined(CONFIG_CPU_MOHAWK) || \ - defined(CONFIG_CPU_XSC3) || \ - defined(CONFIG_CPU_XSCALE) -#define PJ4(code...) -#define XSC(code...) code -#else -#error "Unsupported iWMMXt architecture" -#endif - #define MMX_WR0 (0x00) #define MMX_WR1 (0x08) #define MMX_WR2 (0x10) @@ -81,17 +69,13 @@ ENDPROC(iwmmxt_undef_handler) ENTRY(iwmmxt_task_enable) inc_preempt_count r10, r3 - XSC(mrc p15, 0, r2, c15, c1, 0) - PJ4(mrc p15, 0, r2, c1, c0, 2) + mrc p15, 0, r2, c15, c1, 0 @ CP0 and CP1 accessible? - XSC(tst r2, #0x3) - PJ4(tst r2, #0xf) + tst r2, #0x3 bne 4f @ if so no business here @ enable access to CP0 and CP1 - XSC(orr r2, r2, #0x3) - XSC(mcr p15, 0, r2, c15, c1, 0) - PJ4(orr r2, r2, #0xf) - PJ4(mcr p15, 0, r2, c1, c0, 2) + orr r2, r2, #0x3 + mcr p15, 0, r2, c15, c1, 0 ldr r3, =concan_owner ldr r2, [r0, #S_PC] @ current task pc value @@ -218,12 +202,9 @@ ENTRY(iwmmxt_task_disable) bne 1f @ no: quit @ enable access to CP0 and CP1 - XSC(mrc p15, 0, r4, c15, c1, 0) - XSC(orr r4, r4, #0x3) - XSC(mcr p15, 0, r4, c15, c1, 0) - PJ4(mrc p15, 0, r4, c1, c0, 2) - PJ4(orr r4, r4, #0xf) - PJ4(mcr p15, 0, r4, c1, c0, 2) + mrc p15, 0, r4, c15, c1, 0 + orr r4, r4, #0x3 + mcr p15, 0, r4, c15, c1, 0 mov r0, #0 @ nothing to load str r0, [r3] @ no more current owner @@ -232,10 +213,8 @@ ENTRY(iwmmxt_task_disable) bl concan_save @ disable access to CP0 and CP1 - XSC(bic r4, r4, #0x3) - XSC(mcr p15, 0, r4, c15, c1, 0) - PJ4(bic r4, r4, #0xf) - PJ4(mcr p15, 0, r4, c1, c0, 2) + bic r4, r4, #0x3 + mcr p15, 0, r4, c15, c1, 0 mrc p15, 0, r2, c2, c0, 0 mov r2, r2 @ cpwait @@ -330,11 +309,9 @@ ENDPROC(iwmmxt_task_restore) */ ENTRY(iwmmxt_task_switch) - XSC(mrc p15, 0, r1, c15, c1, 0) - PJ4(mrc p15, 0, r1, c1, c0, 2) + mrc p15, 0, r1, c15, c1, 0 @ CP0 and CP1 accessible? - XSC(tst r1, #0x3) - PJ4(tst r1, #0xf) + tst r1, #0x3 bne 1f @ yes: block them for next task ldr r2, =concan_owner @@ -344,10 +321,8 @@ ENTRY(iwmmxt_task_switch) retne lr @ no: leave Concan disabled 1: @ flip Concan access - XSC(eor r1, r1, #0x3) - XSC(mcr p15, 0, r1, c15, c1, 0) - PJ4(eor r1, r1, #0xf) - PJ4(mcr p15, 0, r1, c1, c0, 2) + eor r1, r1, #0x3 + mcr p15, 0, r1, c15, c1, 0 mrc p15, 0, r1, c2, c0, 0 sub pc, lr, r1, lsr #32 @ cpwait and return diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c deleted file mode 100644 index 4bca8098c4ff5..0000000000000 --- a/arch/arm/kernel/pj4-cp0.c +++ /dev/null @@ -1,135 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * linux/arch/arm/kernel/pj4-cp0.c - * - * PJ4 iWMMXt coprocessor context switching and handling - * - * Copyright (c) 2010 Marvell International Inc. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -static int iwmmxt_do(struct notifier_block *self, unsigned long cmd, void *t) -{ - struct thread_info *thread = t; - - switch (cmd) { - case THREAD_NOTIFY_FLUSH: - /* - * flush_thread() zeroes thread->fpstate, so no need - * to do anything here. - * - * FALLTHROUGH: Ensure we don't try to overwrite our newly - * initialised state information on the first fault. - */ - - case THREAD_NOTIFY_EXIT: - iwmmxt_task_release(thread); - break; - - case THREAD_NOTIFY_SWITCH: - iwmmxt_task_switch(thread); - break; - } - - return NOTIFY_DONE; -} - -static struct notifier_block __maybe_unused iwmmxt_notifier_block = { - .notifier_call = iwmmxt_do, -}; - - -static u32 __init pj4_cp_access_read(void) -{ - u32 value; - - __asm__ __volatile__ ( - "mrc p15, 0, %0, c1, c0, 2\n\t" - : "=r" (value)); - return value; -} - -static void __init pj4_cp_access_write(u32 value) -{ - u32 temp; - - __asm__ __volatile__ ( - "mcr p15, 0, %1, c1, c0, 2\n\t" -#ifdef CONFIG_THUMB2_KERNEL - "isb\n\t" -#else - "mrc p15, 0, %0, c1, c0, 2\n\t" - "mov %0, %0\n\t" - "sub pc, pc, #4\n\t" -#endif - : "=r" (temp) : "r" (value)); -} - -static int __init pj4_get_iwmmxt_version(void) -{ - u32 cp_access, wcid; - - cp_access = pj4_cp_access_read(); - pj4_cp_access_write(cp_access | 0xf); - - /* check if coprocessor 0 and 1 are available */ - if ((pj4_cp_access_read() & 0xf) != 0xf) { - pj4_cp_access_write(cp_access); - return -ENODEV; - } - - /* read iWMMXt coprocessor id register p1, c0 */ - __asm__ __volatile__ ("mrc p1, 0, %0, c0, c0, 0\n" : "=r" (wcid)); - - pj4_cp_access_write(cp_access); - - /* iWMMXt v1 */ - if ((wcid & 0xffffff00) == 0x56051000) - return 1; - /* iWMMXt v2 */ - if ((wcid & 0xffffff00) == 0x56052000) - return 2; - - return -EINVAL; -} - -/* - * Disable CP0/CP1 on boot, and let call_fpe() and the iWMMXt lazy - * switch code handle iWMMXt context switching. - */ -static int __init pj4_cp0_init(void) -{ - u32 __maybe_unused cp_access; - int vers; - - if (!cpu_is_pj4()) - return 0; - - vers = pj4_get_iwmmxt_version(); - if (vers < 0) - return 0; - -#ifndef CONFIG_IWMMXT - pr_info("PJ4 iWMMXt coprocessor detected, but kernel support is missing.\n"); -#else - cp_access = pj4_cp_access_read() & ~0xf; - pj4_cp_access_write(cp_access); - - pr_info("PJ4 iWMMXt v%d coprocessor enabled.\n", vers); - elf_hwcap |= HWCAP_IWMMXT; - thread_register_notifier(&iwmmxt_notifier_block); - register_iwmmxt_undef_handler(); -#endif - - return 0; -} - -late_initcall(pj4_cp0_init); diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index a86a1d4f34618..93afd1005b43c 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -127,6 +127,10 @@ cpu_resume_after_mmu: instr_sync #endif bl cpu_init @ restore the und/abt/irq banked regs +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) + mov r0, sp + bl kasan_unpoison_task_stack_below +#endif mov r0, #0 @ return zero on success ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_resume_after_mmu) diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index 31755a378c736..ff2a4a4d82204 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -79,10 +79,8 @@ static struct musb_hdrc_platform_data tusb_data = { static struct gpiod_lookup_table tusb_gpio_table = { .dev_id = "musb-tusb", .table = { - GPIO_LOOKUP("gpio-0-15", 0, "enable", - GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("gpio-48-63", 10, "int", - GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-0-31", 0, "enable", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-32-63", 26, "int", GPIO_ACTIVE_HIGH), { } }, }; @@ -140,12 +138,11 @@ static int slot1_cover_open; static int slot2_cover_open; static struct device *mmc_device; -static struct gpiod_lookup_table nokia8xx_mmc_gpio_table = { +static struct gpiod_lookup_table nokia800_mmc_gpio_table = { .dev_id = "mmci-omap.0", .table = { /* Slot switch, GPIO 96 */ - GPIO_LOOKUP("gpio-80-111", 16, - "switch", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-96-127", 0, "switch", GPIO_ACTIVE_HIGH), { } }, }; @@ -153,12 +150,12 @@ static struct gpiod_lookup_table nokia8xx_mmc_gpio_table = { static struct gpiod_lookup_table nokia810_mmc_gpio_table = { .dev_id = "mmci-omap.0", .table = { + /* Slot switch, GPIO 96 */ + GPIO_LOOKUP("gpio-96-127", 0, "switch", GPIO_ACTIVE_HIGH), /* Slot index 1, VSD power, GPIO 23 */ - GPIO_LOOKUP_IDX("gpio-16-31", 7, - "vsd", 1, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP_IDX("gpio-0-31", 23, "vsd", 1, GPIO_ACTIVE_HIGH), /* Slot index 1, VIO power, GPIO 9 */ - GPIO_LOOKUP_IDX("gpio-0-15", 9, - "vio", 1, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP_IDX("gpio-0-31", 9, "vio", 1, GPIO_ACTIVE_HIGH), { } }, }; @@ -415,8 +412,6 @@ static struct omap_mmc_platform_data *mmc_data[OMAP24XX_NR_MMC]; static void __init n8x0_mmc_init(void) { - gpiod_add_lookup_table(&nokia8xx_mmc_gpio_table); - if (board_is_n810()) { mmc1_data.slots[0].name = "external"; @@ -429,6 +424,8 @@ static void __init n8x0_mmc_init(void) mmc1_data.slots[1].name = "internal"; mmc1_data.slots[1].ban_openended = 1; gpiod_add_lookup_table(&nokia810_mmc_gpio_table); + } else { + gpiod_add_lookup_table(&nokia800_mmc_gpio_table); } mmc1_data.nr_slots = 2; diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index d19d140a10c7d..0749cf8a66371 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -296,6 +296,9 @@ void __sync_icache_dcache(pte_t pteval) return; folio = page_folio(pfn_to_page(pfn)); + if (folio_test_reserved(folio)) + return; + if (cache_is_vipt_aliasing()) mapping = folio_flush_mapping(folio); else diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1d672457d02ff..72b5cd697f5d9 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -871,16 +871,11 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[], } /* dst = src (4 bytes)*/ -static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off, - struct jit_ctx *ctx) { +static inline void emit_a32_mov_r(const s8 dst, const s8 src, struct jit_ctx *ctx) { const s8 *tmp = bpf2a32[TMP_REG_1]; s8 rt; rt = arm_bpf_get_reg32(src, tmp[0], ctx); - if (off && off != 32) { - emit(ARM_LSL_I(rt, rt, 32 - off), ctx); - emit(ARM_ASR_I(rt, rt, 32 - off), ctx); - } arm_bpf_put_reg32(dst, rt, ctx); } @@ -889,15 +884,15 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], const s8 src[], struct jit_ctx *ctx) { if (!is64) { - emit_a32_mov_r(dst_lo, src_lo, 0, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); if (!ctx->prog->aux->verifier_zext) /* Zero out high 4 bytes */ emit_a32_mov_i(dst_hi, 0, ctx); } else if (__LINUX_ARM_ARCH__ < 6 && ctx->cpu_architecture < CPU_ARCH_ARMv5TE) { /* complete 8 byte move */ - emit_a32_mov_r(dst_lo, src_lo, 0, ctx); - emit_a32_mov_r(dst_hi, src_hi, 0, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); + emit_a32_mov_r(dst_hi, src_hi, ctx); } else if (is_stacked(src_lo) && is_stacked(dst_lo)) { const u8 *tmp = bpf2a32[TMP_REG_1]; @@ -917,17 +912,52 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[], struct jit_ctx *ctx) { const s8 *tmp = bpf2a32[TMP_REG_1]; - const s8 *rt; + s8 rs; + s8 rd; - rt = arm_bpf_get_reg64(dst, tmp, ctx); + if (is_stacked(dst_lo)) + rd = tmp[1]; + else + rd = dst_lo; + rs = arm_bpf_get_reg32(src_lo, rd, ctx); + /* rs may be one of src[1], dst[1], or tmp[1] */ + + /* Sign extend rs if needed. If off == 32, lower 32-bits of src are moved to dst and sign + * extension only happens in the upper 64 bits. + */ + if (off != 32) { + /* Sign extend rs into rd */ + emit(ARM_LSL_I(rd, rs, 32 - off), ctx); + emit(ARM_ASR_I(rd, rd, 32 - off), ctx); + } else { + rd = rs; + } + + /* Write rd to dst_lo + * + * Optimization: + * Assume: + * 1. dst == src and stacked. + * 2. off == 32 + * + * In this case src_lo was loaded into rd(tmp[1]) but rd was not sign extended as off==32. + * So, we don't need to write rd back to dst_lo as they have the same value. + * This saves us one str instruction. + */ + if (dst_lo != src_lo || off != 32) + arm_bpf_put_reg32(dst_lo, rd, ctx); - emit_a32_mov_r(dst_lo, src_lo, off, ctx); if (!is64) { if (!ctx->prog->aux->verifier_zext) /* Zero out high 4 bytes */ emit_a32_mov_i(dst_hi, 0, ctx); } else { - emit(ARM_ASR_I(rt[0], rt[1], 31), ctx); + if (is_stacked(dst_hi)) { + emit(ARM_ASR_I(tmp[0], rd, 31), ctx); + arm_bpf_put_reg32(dst_hi, tmp[0], ctx); + } else { + emit(ARM_ASR_I(dst_hi, rd, 31), ctx); + } } } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index aa7c1d4351396..dca14c61af975 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -107,7 +107,7 @@ config ARM64 select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_NO_INSTR select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARM_AMBA select ARM_ARCH_TIMER select ARM_GIC @@ -198,7 +198,7 @@ config ARM64 if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \ if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG && \ - !CC_OPTIMIZE_FOR_SIZE) + (CC_IS_CLANG || !CC_OPTIMIZE_FOR_SIZE)) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_SAMPLE_FTRACE_DIRECT @@ -1550,7 +1550,7 @@ config XEN # 64K | 29 | 16 | 13 | 13 | config ARCH_FORCE_MAX_ORDER int - default "13" if ARM64_64K_PAGES + default "13" if ARM64_64K_PAGES || (ARCH_THUNDER && ARM64_4K_PAGES) default "11" if ARM64_16K_PAGES default "10" help diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 9ec49ac2f6fd5..381d58cea092d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -291,6 +291,8 @@ }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&spdif_tx_pin>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi index 4903d6358112d..855b7d43bc503 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-tanix.dtsi @@ -166,6 +166,8 @@ }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&spdif_tx_pin>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index ca1d287a0a01d..d11e5041bae9a 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -406,6 +406,7 @@ function = "spi1"; }; + /omit-if-no-ref/ spdif_tx_pin: spdif-tx-pin { pins = "PH7"; function = "spdif"; @@ -655,10 +656,8 @@ clocks = <&ccu CLK_BUS_SPDIF>, <&ccu CLK_SPDIF>; clock-names = "apb", "spdif"; resets = <&ccu RST_BUS_SPDIF>; - dmas = <&dma 2>; - dma-names = "tx"; - pinctrl-names = "default"; - pinctrl-0 = <&spdif_tx_pin>; + dmas = <&dma 2>, <&dma 2>; + dma-names = "rx", "tx"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi index ce90b35686a21..10896f9df682d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi @@ -65,10 +65,15 @@ #clock-cells = <0>; }; - pwrc: power-controller { - compatible = "amlogic,meson-s4-pwrc"; - #power-domain-cells = <1>; - status = "okay"; + firmware { + sm: secure-monitor { + compatible = "amlogic,meson-gxbb-sm"; + + pwrc: power-controller { + compatible = "amlogic,meson-s4-pwrc"; + #power-domain-cells = <1>; + }; + }; }; soc { diff --git a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi index 2f124b027bbf0..aadfa0ae05252 100644 --- a/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcmbca/bcm4908.dtsi @@ -227,9 +227,6 @@ brcm,num-gphy = <5>; brcm,num-rgmii-ports = <2>; - #address-cells = <1>; - #size-cells = <0>; - ports: ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 3c42240e78e24..4aaf5a0c1ed8a 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -41,7 +41,7 @@ conn_subsys: bus@5b000000 { interrupts = ; fsl,usbphy = <&usbphy1>; fsl,usbmisc = <&usbmisc1 0>; - clocks = <&usb2_lpcg 0>; + clocks = <&usb2_lpcg IMX_LPCG_CLK_6>; ahb-burst-config = <0x0>; tx-burst-size-dword = <0x10>; rx-burst-size-dword = <0x10>; @@ -58,7 +58,7 @@ conn_subsys: bus@5b000000 { usbphy1: usbphy@5b100000 { compatible = "fsl,imx7ulp-usbphy"; reg = <0x5b100000 0x1000>; - clocks = <&usb2_lpcg 1>; + clocks = <&usb2_lpcg IMX_LPCG_CLK_7>; power-domains = <&pd IMX_SC_R_USB_0_PHY>; status = "disabled"; }; @@ -67,8 +67,8 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b010000 0x10000>; clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>, - <&sdhc0_lpcg IMX_LPCG_CLK_0>, - <&sdhc0_lpcg IMX_LPCG_CLK_5>; + <&sdhc0_lpcg IMX_LPCG_CLK_5>, + <&sdhc0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_0>; status = "disabled"; @@ -78,8 +78,8 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b020000 0x10000>; clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>, - <&sdhc1_lpcg IMX_LPCG_CLK_0>, - <&sdhc1_lpcg IMX_LPCG_CLK_5>; + <&sdhc1_lpcg IMX_LPCG_CLK_5>, + <&sdhc1_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_1>; fsl,tuning-start-tap = <20>; @@ -91,8 +91,8 @@ conn_subsys: bus@5b000000 { interrupts = ; reg = <0x5b030000 0x10000>; clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>, - <&sdhc2_lpcg IMX_LPCG_CLK_0>, - <&sdhc2_lpcg IMX_LPCG_CLK_5>; + <&sdhc2_lpcg IMX_LPCG_CLK_5>, + <&sdhc2_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_2>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi index b0bb77150adcc..67b3c7573233a 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi @@ -27,8 +27,8 @@ dma_subsys: bus@5a000000 { #size-cells = <0>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&spi0_lpcg 0>, - <&spi0_lpcg 1>; + clocks = <&spi0_lpcg IMX_LPCG_CLK_0>, + <&spi0_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -43,8 +43,8 @@ dma_subsys: bus@5a000000 { #size-cells = <0>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&spi1_lpcg 0>, - <&spi1_lpcg 1>; + clocks = <&spi1_lpcg IMX_LPCG_CLK_0>, + <&spi1_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -59,8 +59,8 @@ dma_subsys: bus@5a000000 { #size-cells = <0>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&spi2_lpcg 0>, - <&spi2_lpcg 1>; + clocks = <&spi2_lpcg IMX_LPCG_CLK_0>, + <&spi2_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_2 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -75,8 +75,8 @@ dma_subsys: bus@5a000000 { #size-cells = <0>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&spi3_lpcg 0>, - <&spi3_lpcg 1>; + clocks = <&spi3_lpcg IMX_LPCG_CLK_0>, + <&spi3_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_3 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -144,8 +144,8 @@ dma_subsys: bus@5a000000 { compatible = "fsl,imx8qxp-pwm", "fsl,imx27-pwm"; reg = <0x5a190000 0x1000>; interrupts = ; - clocks = <&adma_pwm_lpcg 1>, - <&adma_pwm_lpcg 0>; + clocks = <&adma_pwm_lpcg IMX_LPCG_CLK_4>, + <&adma_pwm_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_LCD_0_PWM_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; @@ -377,8 +377,8 @@ dma_subsys: bus@5a000000 { reg = <0x5a880000 0x10000>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&adc0_lpcg 0>, - <&adc0_lpcg 1>; + clocks = <&adc0_lpcg IMX_LPCG_CLK_0>, + <&adc0_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_ADC_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; @@ -392,8 +392,8 @@ dma_subsys: bus@5a000000 { reg = <0x5a890000 0x10000>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&adc1_lpcg 0>, - <&adc1_lpcg 1>; + clocks = <&adc1_lpcg IMX_LPCG_CLK_0>, + <&adc1_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_ADC_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; @@ -406,8 +406,8 @@ dma_subsys: bus@5a000000 { reg = <0x5a8d0000 0x10000>; interrupts = ; interrupt-parent = <&gic>; - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; @@ -427,8 +427,8 @@ dma_subsys: bus@5a000000 { * CAN1 shares CAN0's clock and to enable CAN0's clock it * has to be powered on. */ - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; @@ -448,8 +448,8 @@ dma_subsys: bus@5a000000 { * CAN2 shares CAN0's clock and to enable CAN0's clock it * has to be powered on. */ - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi index 7e510b21bbac5..764c1a08e3b11 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi @@ -25,8 +25,8 @@ lsio_subsys: bus@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d000000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm0_lpcg 4>, - <&pwm0_lpcg 1>; + clocks = <&pwm0_lpcg IMX_LPCG_CLK_6>, + <&pwm0_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; #pwm-cells = <3>; @@ -38,8 +38,8 @@ lsio_subsys: bus@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d010000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm1_lpcg 4>, - <&pwm1_lpcg 1>; + clocks = <&pwm1_lpcg IMX_LPCG_CLK_6>, + <&pwm1_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; #pwm-cells = <3>; @@ -51,8 +51,8 @@ lsio_subsys: bus@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d020000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm2_lpcg 4>, - <&pwm2_lpcg 1>; + clocks = <&pwm2_lpcg IMX_LPCG_CLK_6>, + <&pwm2_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_2 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; #pwm-cells = <3>; @@ -64,8 +64,8 @@ lsio_subsys: bus@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d030000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm3_lpcg 4>, - <&pwm3_lpcg 1>; + clocks = <&pwm3_lpcg IMX_LPCG_CLK_6>, + <&pwm3_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_3 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; #pwm-cells = <3>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts index 8b16bd68576c0..d9fa0deea7002 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl-osm-s.dts @@ -294,8 +294,8 @@ pinctrl_i2c4: i2c4grp { fsl,pins = < - MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x400001c3 - MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x400001c3 + MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x40000083 + MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x40000083 >; }; @@ -313,19 +313,19 @@ pinctrl_uart1: uart1grp { fsl,pins = < - MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x140 - MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x140 - MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x0 + MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x0 + MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x0 >; }; pinctrl_uart2: uart2grp { fsl,pins = < - MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x140 - MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x140 - MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x0 + MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x0 + MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x0 >; }; @@ -337,40 +337,40 @@ pinctrl_usdhc2: usdhc2grp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x190 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d0 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d0 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d0 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d0 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d0 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x194 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d4 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d4 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d4 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d4 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d4 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x196 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d6 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d6 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d6 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d6 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d6 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts index dcec57c20399e..aab8e24216501 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-bl.dts @@ -279,8 +279,8 @@ pinctrl_i2c4: i2c4grp { fsl,pins = < - MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x400001c3 - MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x400001c3 + MX8MM_IOMUXC_I2C4_SCL_I2C4_SCL 0x40000083 + MX8MM_IOMUXC_I2C4_SDA_I2C4_SDA 0x40000083 >; }; @@ -292,19 +292,19 @@ pinctrl_uart1: uart1grp { fsl,pins = < - MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x140 - MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x140 - MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI2_RXC_UART1_DCE_RX 0x0 + MX8MM_IOMUXC_SAI2_RXFS_UART1_DCE_TX 0x0 + MX8MM_IOMUXC_SAI2_RXD0_UART1_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI2_TXFS_UART1_DCE_CTS_B 0x0 >; }; pinctrl_uart2: uart2grp { fsl,pins = < - MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x140 - MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x140 - MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x140 - MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x140 + MX8MM_IOMUXC_SAI3_TXFS_UART2_DCE_RX 0x0 + MX8MM_IOMUXC_SAI3_TXC_UART2_DCE_TX 0x0 + MX8MM_IOMUXC_SAI3_RXD_UART2_DCE_RTS_B 0x0 + MX8MM_IOMUXC_SAI3_RXC_UART2_DCE_CTS_B 0x0 >; }; @@ -316,40 +316,40 @@ pinctrl_usdhc2: usdhc2grp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x190 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d0 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d0 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d0 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d0 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d0 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x194 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d4 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d4 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d4 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d4 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d4 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { fsl,pins = < - MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x196 + MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96 MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x1d6 MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x1d6 MX8MM_IOMUXC_SD2_DATA1_USDHC2_DATA1 0x1d6 MX8MM_IOMUXC_SD2_DATA2_USDHC2_DATA2 0x1d6 MX8MM_IOMUXC_SD2_DATA3_USDHC2_DATA3 0x1d6 - MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x019 - MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x1d0 + MX8MM_IOMUXC_SD2_CD_B_GPIO2_IO12 0x19 + MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0xd0 >; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi index 6e75ab879bf59..60abcb636cedf 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-osm-s.dtsi @@ -210,7 +210,7 @@ reg = <0x52>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_rtc>; - interrupts-extended = <&gpio4 1 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&gpio4 1 IRQ_TYPE_LEVEL_LOW>; trickle-diode-disable; }; }; @@ -252,8 +252,8 @@ pinctrl_i2c1: i2c1grp { fsl,pins = < - MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x400001c3 - MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x400001c3 + MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x40000083 + MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x40000083 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi index 1f8326613ee9e..2076148e08627 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-sl.dtsi @@ -237,8 +237,8 @@ pinctrl_i2c1: i2c1grp { fsl,pins = < - MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x400001c3 - MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x400001c3 + MX8MM_IOMUXC_I2C1_SCL_I2C1_SCL 0x40000083 + MX8MM_IOMUXC_I2C1_SDA_I2C1_SDA 0x40000083 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi index 6425773f68e0a..bbbaf2165ea28 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi @@ -47,17 +47,6 @@ gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; status = "okay"; }; - - reg_usb_otg1_vbus: regulator-usb-otg1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_reg_usb1_en>; - compatible = "regulator-fixed"; - regulator-name = "usb_otg1_vbus"; - gpio = <&gpio1 10 GPIO_ACTIVE_HIGH>; - enable-active-high; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - }; }; /* off-board header */ @@ -144,9 +133,10 @@ }; &usbotg1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usbotg1>; dr_mode = "otg"; over-current-active-low; - vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; @@ -204,14 +194,6 @@ >; }; - pinctrl_reg_usb1_en: regusb1grp { - fsl,pins = < - MX8MM_IOMUXC_GPIO1_IO10_GPIO1_IO10 0x41 - MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x141 - MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC 0x41 - >; - }; - pinctrl_spi2: spi2grp { fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 @@ -234,4 +216,11 @@ MX8MM_IOMUXC_UART3_TXD_UART3_DCE_TX 0x140 >; }; + + pinctrl_usbotg1: usbotg1grp { + fsl,pins = < + MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x141 + MX8MM_IOMUXC_GPIO1_IO13_USB1_OTG_OC 0x41 + >; + }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 6f0811587142d..1b1880c607cfe 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -6,6 +6,7 @@ #include #include #include "imx8mm.dtsi" +#include "imx8mm-overdrive.dtsi" / { chosen { @@ -929,7 +930,7 @@ /* Verdin GPIO_9_DSI (pulled-up as active-low) */ pinctrl_gpio_9_dsi: gpio9dsigrp { fsl,pins = - ; /* SODIMM 17 */ + ; /* SODIMM 17 */ }; /* Verdin GPIO_10_DSI (pulled-up as active-low) */ diff --git a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts index 5828c9d7821de..b5ce7b14b5434 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts @@ -121,7 +121,7 @@ flash@0 { /* W25Q128JVEI */ compatible = "jedec,spi-nor"; reg = <0>; - spi-max-frequency = <100000000>; /* Up to 133 MHz */ + spi-max-frequency = <40000000>; spi-tx-bus-width = <1>; spi-rx-bus-width = <1>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 43f1d45ccc96f..f5115f9e8c473 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -254,7 +254,7 @@ <&clk IMX8MP_CLK_CLKOUT2>, <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; - assigned-clock-rates = <13000000>, <13000000>, <156000000>; + assigned-clock-rates = <13000000>, <13000000>, <208000000>; reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts index f87fa5a948ccc..9beba8d6a0dfe 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts @@ -23,7 +23,7 @@ port { hdmi_connector_in: endpoint { - remote-endpoint = <&adv7533_out>; + remote-endpoint = <&adv7535_out>; }; }; }; @@ -107,6 +107,13 @@ enable-active-high; }; + reg_vext_3v3: regulator-vext-3v3 { + compatible = "regulator-fixed"; + regulator-name = "VEXT_3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + sound { compatible = "simple-audio-card"; simple-audio-card,name = "wm8960-audio"; @@ -364,7 +371,7 @@ regulator-always-on; }; - BUCK5 { + reg_buck5: BUCK5 { regulator-name = "BUCK5"; regulator-min-microvolt = <1650000>; regulator-max-microvolt = <1950000>; @@ -415,14 +422,16 @@ hdmi@3d { compatible = "adi,adv7535"; - reg = <0x3d>, <0x3c>, <0x3e>, <0x3f>; - reg-names = "main", "cec", "edid", "packet"; + reg = <0x3d>; + interrupt-parent = <&gpio1>; + interrupts = <9 IRQ_TYPE_EDGE_FALLING>; adi,dsi-lanes = <4>; - adi,input-depth = <8>; - adi,input-colorspace = "rgb"; - adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; + avdd-supply = <®_buck5>; + dvdd-supply = <®_buck5>; + pvdd-supply = <®_buck5>; + a2vdd-supply = <®_buck5>; + v3p3-supply = <®_vext_3v3>; + v1p2-supply = <®_buck5>; ports { #address-cells = <1>; @@ -431,7 +440,7 @@ port@0 { reg = <0>; - adv7533_in: endpoint { + adv7535_in: endpoint { remote-endpoint = <&dsi_out>; }; }; @@ -439,7 +448,7 @@ port@1 { reg = <1>; - adv7533_out: endpoint { + adv7535_out: endpoint { remote-endpoint = <&hdmi_connector_in>; }; }; @@ -524,7 +533,7 @@ reg = <1>; dsi_out: endpoint { - remote-endpoint = <&adv7533_in>; + remote-endpoint = <&adv7535_in>; data-lanes = <1 2 3 4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi index 41c79d2ebdd62..f24b14744799e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi @@ -14,6 +14,7 @@ pinctrl-0 = <&pinctrl_usbcon1>; type = "micro"; label = "otg"; + vbus-supply = <®_usb1_vbus>; id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; port { @@ -183,7 +184,6 @@ }; &usb3_phy0 { - vbus-supply = <®_usb1_vbus>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi index d5c400b355af5..3c063f8a9383e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi @@ -14,6 +14,7 @@ pinctrl-0 = <&pinctrl_usbcon1>; type = "micro"; label = "otg"; + vbus-supply = <®_usb1_vbus>; id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; port { @@ -182,7 +183,7 @@ bluetooth { compatible = "brcm,bcm4330-bt"; - shutdown-gpios = <&gpio4 16 GPIO_ACTIVE_HIGH>; + shutdown-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>; }; }; @@ -202,7 +203,6 @@ }; &usb3_phy0 { - vbus-supply = <®_usb1_vbus>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts index 6d50838ad17de..70a9da749d80e 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts @@ -36,7 +36,7 @@ regulator-name = "SD1_SPWR"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3000000>; - gpio = <&lsio_gpio4 19 GPIO_ACTIVE_HIGH>; + gpio = <&lsio_gpio4 7 GPIO_ACTIVE_HIGH>; enable-active-high; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi index 69cb8676732ea..cd96f9f75da16 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi @@ -96,15 +96,30 @@ status = "okay"; }; +/* It is eDMA1 in 8QM RM, but 8QXP it is eDMA3 */ &edma3 { + reg = <0x5a9f0000 0x210000>; + dma-channels = <10>; + interrupts = , + , + , + , + , + , + , + , + , + ; power-domains = <&pd IMX_SC_R_DMA_1_CH0>, - <&pd IMX_SC_R_DMA_1_CH1>, - <&pd IMX_SC_R_DMA_1_CH2>, - <&pd IMX_SC_R_DMA_1_CH3>, - <&pd IMX_SC_R_DMA_1_CH4>, - <&pd IMX_SC_R_DMA_1_CH5>, - <&pd IMX_SC_R_DMA_1_CH6>, - <&pd IMX_SC_R_DMA_1_CH7>; + <&pd IMX_SC_R_DMA_1_CH1>, + <&pd IMX_SC_R_DMA_1_CH2>, + <&pd IMX_SC_R_DMA_1_CH3>, + <&pd IMX_SC_R_DMA_1_CH4>, + <&pd IMX_SC_R_DMA_1_CH5>, + <&pd IMX_SC_R_DMA_1_CH6>, + <&pd IMX_SC_R_DMA_1_CH7>, + <&pd IMX_SC_R_DMA_1_CH8>, + <&pd IMX_SC_R_DMA_1_CH9>; }; &flexcan1 { @@ -112,15 +127,15 @@ }; &flexcan2 { - clocks = <&can1_lpcg 1>, - <&can1_lpcg 0>; + clocks = <&can1_lpcg IMX_LPCG_CLK_4>, + <&can1_lpcg IMX_LPCG_CLK_0>; assigned-clocks = <&clk IMX_SC_R_CAN_1 IMX_SC_PM_CLK_PER>; fsl,clk-source = /bits/ 8 <1>; }; &flexcan3 { - clocks = <&can2_lpcg 1>, - <&can2_lpcg 0>; + clocks = <&can2_lpcg IMX_LPCG_CLK_4>, + <&can2_lpcg IMX_LPCG_CLK_0>; assigned-clocks = <&clk IMX_SC_R_CAN_2 IMX_SC_PM_CLK_PER>; fsl,clk-source = /bits/ 8 <1>; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts index 9921ea13ab489..a7cb571d74023 100644 --- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts @@ -175,7 +175,6 @@ vmmc-supply = <®_usdhc2_vmmc>; bus-width = <4>; status = "okay"; - no-sdio; no-mmc; }; diff --git a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi index ed1b5a7a60678..d01023401d7e3 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi @@ -58,7 +58,7 @@ gic: interrupt-controller@f1001000 { compatible = "arm,gic-400"; reg = <0x0 0xf1001000 0x0 0x1000>, /* GICD */ - <0x0 0xf1002000 0x0 0x100>; /* GICC */ + <0x0 0xf1002000 0x0 0x2000>; /* GICC */ #address-cells = <0>; #interrupt-cells = <3>; interrupt-controller; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index e300145ad1a6f..1cc3fa1c354de 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -431,14 +431,14 @@ crypto: crypto@90000 { compatible = "inside-secure,safexcel-eip97ies"; reg = <0x90000 0x20000>; - interrupts = , - , + interrupts = , , , , - ; - interrupt-names = "mem", "ring0", "ring1", - "ring2", "ring3", "eip"; + , + ; + interrupt-names = "ring0", "ring1", "ring2", + "ring3", "eip", "mem"; clocks = <&nb_periph_clk 15>; }; diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi index 4ec1aae0a3a9c..7e595ac80043a 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi @@ -511,14 +511,14 @@ CP11X_LABEL(crypto): crypto@800000 { compatible = "inside-secure,safexcel-eip197b"; reg = <0x800000 0x200000>; - interrupts = <87 IRQ_TYPE_LEVEL_HIGH>, - <88 IRQ_TYPE_LEVEL_HIGH>, + interrupts = <88 IRQ_TYPE_LEVEL_HIGH>, <89 IRQ_TYPE_LEVEL_HIGH>, <90 IRQ_TYPE_LEVEL_HIGH>, <91 IRQ_TYPE_LEVEL_HIGH>, - <92 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "mem", "ring0", "ring1", - "ring2", "ring3", "eip"; + <92 IRQ_TYPE_LEVEL_HIGH>, + <87 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "ring0", "ring1", "ring2", "ring3", + "eip", "mem"; clock-names = "core", "reg"; clocks = <&CP11X_LABEL(clk) 1 26>, <&CP11X_LABEL(clk) 1 17>; diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index fffdb7bbf889e..2d0ef6f23b3a9 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts @@ -129,7 +129,7 @@ }; &pio { - eth_default: eth_default { + eth_default: eth-default-pins { tx_pins { pinmux = , , @@ -156,7 +156,7 @@ }; }; - eth_sleep: eth_sleep { + eth_sleep: eth-sleep-pins { tx_pins { pinmux = , , @@ -182,14 +182,14 @@ }; }; - usb0_id_pins_float: usb0_iddig { + usb0_id_pins_float: usb0-iddig-pins { pins_iddig { pinmux = ; bias-pull-up; }; }; - usb1_id_pins_float: usb1_iddig { + usb1_id_pins_float: usb1-iddig-pins { pins_iddig { pinmux = ; bias-pull-up; diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi index ed1a9d3194153..f767f921bdee1 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi @@ -249,10 +249,11 @@ #clock-cells = <1>; }; - infracfg: syscon@10001000 { + infracfg: clock-controller@10001000 { compatible = "mediatek,mt2712-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; pericfg: syscon@10003000 { diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts index a1f42048dcc70..850b3e2773680 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts @@ -75,6 +75,7 @@ memory@40000000 { reg = <0 0x40000000 0 0x40000000>; + device_type = "memory"; }; reg_1p8v: regulator-1p8v { diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts index 2dc1bdc74e212..5c26021fc4cf1 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts @@ -57,6 +57,7 @@ memory@40000000 { reg = <0 0x40000000 0 0x20000000>; + device_type = "memory"; }; reg_1p8v: regulator-1p8v { diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 3ee9266fa8e98..917fa39a74f8d 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -252,7 +252,7 @@ clock-names = "hif_sel"; }; - cir: cir@10009000 { + cir: ir-receiver@10009000 { compatible = "mediatek,mt7622-cir"; reg = <0 0x10009000 0 0x1000>; interrupts = ; @@ -283,16 +283,14 @@ }; }; - apmixedsys: apmixedsys@10209000 { - compatible = "mediatek,mt7622-apmixedsys", - "syscon"; + apmixedsys: clock-controller@10209000 { + compatible = "mediatek,mt7622-apmixedsys"; reg = <0 0x10209000 0 0x1000>; #clock-cells = <1>; }; - topckgen: topckgen@10210000 { - compatible = "mediatek,mt7622-topckgen", - "syscon"; + topckgen: clock-controller@10210000 { + compatible = "mediatek,mt7622-topckgen"; reg = <0 0x10210000 0 0x1000>; #clock-cells = <1>; }; @@ -515,7 +513,6 @@ <&pericfg CLK_PERI_AUXADC_PD>; clock-names = "therm", "auxadc"; resets = <&pericfg MT7622_PERI_THERM_SW_RST>; - reset-names = "therm"; mediatek,auxadc = <&auxadc>; mediatek,apmixedsys = <&apmixedsys>; nvmem-cells = <&thermal_calibration>; @@ -734,9 +731,8 @@ power-domains = <&scpsys MT7622_POWER_DOMAIN_WB>; }; - ssusbsys: ssusbsys@1a000000 { - compatible = "mediatek,mt7622-ssusbsys", - "syscon"; + ssusbsys: clock-controller@1a000000 { + compatible = "mediatek,mt7622-ssusbsys"; reg = <0 0x1a000000 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -793,9 +789,8 @@ }; }; - pciesys: pciesys@1a100800 { - compatible = "mediatek,mt7622-pciesys", - "syscon"; + pciesys: clock-controller@1a100800 { + compatible = "mediatek,mt7622-pciesys"; reg = <0 0x1a100800 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -921,12 +916,13 @@ }; }; - hifsys: syscon@1af00000 { - compatible = "mediatek,mt7622-hifsys", "syscon"; + hifsys: clock-controller@1af00000 { + compatible = "mediatek,mt7622-hifsys"; reg = <0 0x1af00000 0 0x70>; + #clock-cells = <1>; }; - ethsys: syscon@1b000000 { + ethsys: clock-controller@1b000000 { compatible = "mediatek,mt7622-ethsys", "syscon"; reg = <0 0x1b000000 0 0x1000>; @@ -966,9 +962,7 @@ }; eth: ethernet@1b100000 { - compatible = "mediatek,mt7622-eth", - "mediatek,mt2701-eth", - "syscon"; + compatible = "mediatek,mt7622-eth"; reg = <0 0x1b100000 0 0x20000>; interrupts = , , diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts index d06d4af43cbff..ed79ad1ae8716 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts +++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts @@ -43,7 +43,7 @@ #cooling-cells = <2>; /* cooling level (0, 1, 2) - pwm inverted */ cooling-levels = <255 96 0>; - pwms = <&pwm 0 10000 0>; + pwms = <&pwm 0 10000>; status = "okay"; }; @@ -146,19 +146,19 @@ &cpu_thermal { cooling-maps { - cpu-active-high { + map-cpu-active-high { /* active: set fan to cooling level 2 */ cooling-device = <&fan 2 2>; trip = <&cpu_trip_active_high>; }; - cpu-active-med { + map-cpu-active-med { /* active: set fan to cooling level 1 */ cooling-device = <&fan 1 1>; trip = <&cpu_trip_active_med>; }; - cpu-active-low { + map-cpu-active-low { /* active: set fan to cooling level 0 */ cooling-device = <&fan 0 0>; trip = <&cpu_trip_active_low>; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts b/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts index 3ef371ca254e8..2f884c24f1eb4 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts +++ b/arch/arm64/boot/dts/mediatek/mt7986a-rfb.dts @@ -237,12 +237,13 @@ pinctrl-0 = <&spi_flash_pins>; cs-gpios = <0>, <0>; status = "okay"; - spi_nand: spi_nand@0 { + + spi_nand: flash@0 { compatible = "spi-nand"; reg = <0>; spi-max-frequency = <10000000>; - spi-tx-buswidth = <4>; - spi-rx-buswidth = <4>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi index fc751e049953c..559990dcd1d17 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi @@ -16,49 +16,49 @@ #address-cells = <2>; #size-cells = <2>; - clk40m: oscillator-40m { - compatible = "fixed-clock"; - clock-frequency = <40000000>; - #clock-cells = <0>; - clock-output-names = "clkxtal"; - }; - cpus { #address-cells = <1>; #size-cells = <0>; cpu0: cpu@0 { - device_type = "cpu"; compatible = "arm,cortex-a53"; - enable-method = "psci"; reg = <0x0>; + device_type = "cpu"; + enable-method = "psci"; #cooling-cells = <2>; }; cpu1: cpu@1 { - device_type = "cpu"; compatible = "arm,cortex-a53"; - enable-method = "psci"; reg = <0x1>; + device_type = "cpu"; + enable-method = "psci"; #cooling-cells = <2>; }; cpu2: cpu@2 { - device_type = "cpu"; compatible = "arm,cortex-a53"; - enable-method = "psci"; reg = <0x2>; + device_type = "cpu"; + enable-method = "psci"; #cooling-cells = <2>; }; cpu3: cpu@3 { - device_type = "cpu"; - enable-method = "psci"; compatible = "arm,cortex-a53"; reg = <0x3>; + device_type = "cpu"; + enable-method = "psci"; #cooling-cells = <2>; }; }; + clk40m: oscillator-40m { + compatible = "fixed-clock"; + clock-frequency = <40000000>; + #clock-cells = <0>; + clock-output-names = "clkxtal"; + }; + psci { compatible = "arm,psci-0.2"; method = "smc"; @@ -121,38 +121,30 @@ }; - timer { - compatible = "arm,armv8-timer"; - interrupt-parent = <&gic>; - interrupts = , - , - , - ; - }; - soc { - #address-cells = <2>; - #size-cells = <2>; compatible = "simple-bus"; ranges; + #address-cells = <2>; + #size-cells = <2>; gic: interrupt-controller@c000000 { compatible = "arm,gic-v3"; - #interrupt-cells = <3>; - interrupt-parent = <&gic>; - interrupt-controller; reg = <0 0x0c000000 0 0x10000>, /* GICD */ <0 0x0c080000 0 0x80000>, /* GICR */ <0 0x0c400000 0 0x2000>, /* GICC */ <0 0x0c410000 0 0x1000>, /* GICH */ <0 0x0c420000 0 0x2000>; /* GICV */ + interrupt-parent = <&gic>; interrupts = ; + interrupt-controller; + #interrupt-cells = <3>; }; infracfg: infracfg@10001000 { compatible = "mediatek,mt7986-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; wed_pcie: wed-pcie@10003000 { @@ -202,6 +194,19 @@ #interrupt-cells = <2>; }; + pwm: pwm@10048000 { + compatible = "mediatek,mt7986-pwm"; + reg = <0 0x10048000 0 0x1000>; + #pwm-cells = <2>; + interrupts = ; + clocks = <&topckgen CLK_TOP_PWM_SEL>, + <&infracfg CLK_INFRA_PWM_STA>, + <&infracfg CLK_INFRA_PWM1_CK>, + <&infracfg CLK_INFRA_PWM2_CK>; + clock-names = "top", "main", "pwm1", "pwm2"; + status = "disabled"; + }; + sgmiisys0: syscon@10060000 { compatible = "mediatek,mt7986-sgmiisys_0", "syscon"; @@ -234,26 +239,11 @@ ; interrupt-names = "ring0", "ring1", "ring2", "ring3"; clocks = <&infracfg CLK_INFRA_EIP97_CK>; - clock-names = "infra_eip97_ck"; assigned-clocks = <&topckgen CLK_TOP_EIP_B_SEL>; assigned-clock-parents = <&apmixedsys CLK_APMIXED_NET2PLL>; status = "disabled"; }; - pwm: pwm@10048000 { - compatible = "mediatek,mt7986-pwm"; - reg = <0 0x10048000 0 0x1000>; - #clock-cells = <1>; - #pwm-cells = <2>; - interrupts = ; - clocks = <&topckgen CLK_TOP_PWM_SEL>, - <&infracfg CLK_INFRA_PWM_STA>, - <&infracfg CLK_INFRA_PWM1_CK>, - <&infracfg CLK_INFRA_PWM2_CK>; - clock-names = "top", "main", "pwm1", "pwm2"; - status = "disabled"; - }; - uart0: serial@11002000 { compatible = "mediatek,mt7986-uart", "mediatek,mt6577-uart"; @@ -311,9 +301,9 @@ spi0: spi@1100a000 { compatible = "mediatek,mt7986-spi-ipm", "mediatek,spi-ipm"; + reg = <0 0x1100a000 0 0x100>; #address-cells = <1>; #size-cells = <0>; - reg = <0 0x1100a000 0 0x100>; interrupts = ; clocks = <&topckgen CLK_TOP_MPLL_D2>, <&topckgen CLK_TOP_SPI_SEL>, @@ -325,9 +315,9 @@ spi1: spi@1100b000 { compatible = "mediatek,mt7986-spi-ipm", "mediatek,spi-ipm"; + reg = <0 0x1100b000 0 0x100>; #address-cells = <1>; #size-cells = <0>; - reg = <0 0x1100b000 0 0x100>; interrupts = ; clocks = <&topckgen CLK_TOP_MPLL_D2>, <&topckgen CLK_TOP_SPIM_MST_SEL>, @@ -337,6 +327,20 @@ status = "disabled"; }; + thermal: thermal@1100c800 { + compatible = "mediatek,mt7986-thermal"; + reg = <0 0x1100c800 0 0x800>; + interrupts = ; + clocks = <&infracfg CLK_INFRA_THERM_CK>, + <&infracfg CLK_INFRA_ADC_26M_CK>; + clock-names = "therm", "auxadc"; + nvmem-cells = <&thermal_calibration>; + nvmem-cell-names = "calibration-data"; + #thermal-sensor-cells = <1>; + mediatek,auxadc = <&auxadc>; + mediatek,apmixedsys = <&apmixedsys>; + }; + auxadc: adc@1100d000 { compatible = "mediatek,mt7986-auxadc"; reg = <0 0x1100d000 0 0x1000>; @@ -388,39 +392,23 @@ status = "disabled"; }; - thermal: thermal@1100c800 { - #thermal-sensor-cells = <1>; - compatible = "mediatek,mt7986-thermal"; - reg = <0 0x1100c800 0 0x800>; - interrupts = ; - clocks = <&infracfg CLK_INFRA_THERM_CK>, - <&infracfg CLK_INFRA_ADC_26M_CK>, - <&infracfg CLK_INFRA_ADC_FRC_CK>; - clock-names = "therm", "auxadc", "adc_32k"; - mediatek,auxadc = <&auxadc>; - mediatek,apmixedsys = <&apmixedsys>; - nvmem-cells = <&thermal_calibration>; - nvmem-cell-names = "calibration-data"; - }; - pcie: pcie@11280000 { compatible = "mediatek,mt7986-pcie", "mediatek,mt8192-pcie"; + reg = <0x00 0x11280000 0x00 0x4000>; + reg-names = "pcie-mac"; + ranges = <0x82000000 0x00 0x20000000 0x00 + 0x20000000 0x00 0x10000000>; device_type = "pci"; #address-cells = <3>; #size-cells = <2>; - reg = <0x00 0x11280000 0x00 0x4000>; - reg-names = "pcie-mac"; interrupts = ; bus-range = <0x00 0xff>; - ranges = <0x82000000 0x00 0x20000000 0x00 - 0x20000000 0x00 0x10000000>; clocks = <&infracfg CLK_INFRA_IPCIE_PIPE_CK>, <&infracfg CLK_INFRA_IPCIE_CK>, <&infracfg CLK_INFRA_IPCIER_CK>, <&infracfg CLK_INFRA_IPCIEB_CK>; clock-names = "pl_250m", "tl_26m", "peri_26m", "top_133m"; - status = "disabled"; phys = <&pcie_port PHY_TYPE_PCIE>; phy-names = "pcie-phy"; @@ -431,6 +419,8 @@ <0 0 0 2 &pcie_intc 1>, <0 0 0 3 &pcie_intc 2>, <0 0 0 4 &pcie_intc 3>; + status = "disabled"; + pcie_intc: interrupt-controller { #address-cells = <0>; #interrupt-cells = <1>; @@ -441,9 +431,9 @@ pcie_phy: t-phy { compatible = "mediatek,mt7986-tphy", "mediatek,generic-tphy-v2"; + ranges; #address-cells = <2>; #size-cells = <2>; - ranges; status = "disabled"; pcie_port: pcie-phy@11c00000 { @@ -468,9 +458,9 @@ usb_phy: t-phy@11e10000 { compatible = "mediatek,mt7986-tphy", "mediatek,generic-tphy-v2"; + ranges = <0 0 0x11e10000 0x1700>; #address-cells = <1>; #size-cells = <1>; - ranges = <0 0 0x11e10000 0x1700>; status = "disabled"; u2port0: usb-phy@0 { @@ -498,8 +488,6 @@ }; ethsys: syscon@15000000 { - #address-cells = <1>; - #size-cells = <1>; compatible = "mediatek,mt7986-ethsys", "syscon"; reg = <0 0x15000000 0 0x1000>; @@ -533,20 +521,6 @@ mediatek,wo-ccif = <&wo_ccif1>; }; - wo_ccif0: syscon@151a5000 { - compatible = "mediatek,mt7986-wo-ccif", "syscon"; - reg = <0 0x151a5000 0 0x1000>; - interrupt-parent = <&gic>; - interrupts = ; - }; - - wo_ccif1: syscon@151ad000 { - compatible = "mediatek,mt7986-wo-ccif", "syscon"; - reg = <0 0x151ad000 0 0x1000>; - interrupt-parent = <&gic>; - interrupts = ; - }; - eth: ethernet@15100000 { compatible = "mediatek,mt7986-eth"; reg = <0 0x15100000 0 0x80000>; @@ -579,26 +553,39 @@ <&topckgen CLK_TOP_SGM_325M_SEL>; assigned-clock-parents = <&apmixedsys CLK_APMIXED_NET2PLL>, <&apmixedsys CLK_APMIXED_SGMPLL>; + #address-cells = <1>; + #size-cells = <0>; mediatek,ethsys = <ðsys>; mediatek,sgmiisys = <&sgmiisys0>, <&sgmiisys1>; mediatek,wed-pcie = <&wed_pcie>; mediatek,wed = <&wed0>, <&wed1>; - #reset-cells = <1>; - #address-cells = <1>; - #size-cells = <0>; status = "disabled"; }; + wo_ccif0: syscon@151a5000 { + compatible = "mediatek,mt7986-wo-ccif", "syscon"; + reg = <0 0x151a5000 0 0x1000>; + interrupt-parent = <&gic>; + interrupts = ; + }; + + wo_ccif1: syscon@151ad000 { + compatible = "mediatek,mt7986-wo-ccif", "syscon"; + reg = <0 0x151ad000 0 0x1000>; + interrupt-parent = <&gic>; + interrupts = ; + }; + wifi: wifi@18000000 { compatible = "mediatek,mt7986-wmac"; + reg = <0 0x18000000 0 0x1000000>, + <0 0x10003000 0 0x1000>, + <0 0x11d10000 0 0x1000>; resets = <&watchdog MT7986_TOPRGU_CONSYS_SW_RST>; reset-names = "consys"; clocks = <&topckgen CLK_TOP_CONN_MCUSYS_SEL>, <&topckgen CLK_TOP_AP2CNN_HOST_SEL>; clock-names = "mcu", "ap2conn"; - reg = <0 0x18000000 0 0x1000000>, - <0 0x10003000 0 0x1000>, - <0 0x11d10000 0 0x1000>; interrupts = , , , @@ -646,4 +633,13 @@ }; }; }; + + timer { + compatible = "arm,armv8-timer"; + interrupt-parent = <&gic>; + interrupts = , + , + , + ; + }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts b/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts index dde190442e386..57dcaeef31d7f 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts +++ b/arch/arm64/boot/dts/mediatek/mt7986b-rfb.dts @@ -152,12 +152,13 @@ pinctrl-0 = <&spi_flash_pins>; cs-gpios = <0>, <0>; status = "okay"; - spi_nand: spi_nand@0 { + + spi_nand: flash@0 { compatible = "spi-nand"; reg = <0>; spi-max-frequency = <10000000>; - spi-tx-buswidth = <4>; - spi-rx-buswidth = <4>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts index a2e74b8293206..6a7ae616512d6 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts @@ -82,7 +82,8 @@ }; &mmc1 { - bt_reset: bt-reset { + bluetooth@2 { + reg = <2>; compatible = "mediatek,mt7921s-bluetooth"; pinctrl-names = "default"; pinctrl-0 = <&bt_pins_reset>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi index b6a9830af2696..bfb9e42c8acaa 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kakadu.dtsi @@ -360,6 +360,10 @@ }; &cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + keyboard-controller { compatible = "google,cros-ec-keyb-switches"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi index 306c95166f3fe..5c1bf6a1e4758 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-kodama.dtsi @@ -339,6 +339,10 @@ }; &cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + keyboard-controller { compatible = "google,cros-ec-keyb-switches"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi index 382e4c6d7191c..0f5fa893a7742 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-krane.dtsi @@ -343,6 +343,10 @@ }; &cros_ec { + cbas { + compatible = "google,cros-cbas"; + }; + keyboard-controller { compatible = "google,cros-ec-keyb-switches"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index 1b3396b1cee39..41aef6c3edfc5 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -433,7 +433,6 @@ }; &mt6358_vgpu_reg { - regulator-min-microvolt = <625000>; regulator-max-microvolt = <900000>; regulator-coupled-with = <&mt6358_vsram_gpu_reg>; @@ -937,10 +936,6 @@ google,usb-port-id = <0>; }; - cbas { - compatible = "google,cros-cbas"; - }; - typec { compatible = "google,cros-ec-typec"; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index 920ee415ef5fb..e1767a4e38f3a 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -1628,6 +1628,7 @@ compatible = "mediatek,mt8183-mfgcfg", "syscon"; reg = <0 0x13000000 0 0x1000>; #clock-cells = <1>; + power-domains = <&spm MT8183_POWER_DOMAIN_MFG_ASYNC>; }; gpu: gpu@13040000 { diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi index 2fec6fd1c1a71..84ec6c1aa12b9 100644 --- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi @@ -931,11 +931,17 @@ power-domain@MT8186_POWER_DOMAIN_SSUSB { reg = ; + clocks = <&topckgen CLK_TOP_USB_TOP>, + <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_REF>; + clock-names = "sys_ck", "ref_ck"; #power-domain-cells = <0>; }; power-domain@MT8186_POWER_DOMAIN_SSUSB_P1 { reg = ; + clocks = <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_SYS>, + <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_REF>; + clock-names = "sys_ck", "ref_ck"; #power-domain-cells = <0>; }; @@ -1061,7 +1067,7 @@ reg = ; clocks = <&topckgen CLK_TOP_VENC>, <&vencsys CLK_VENC_CKE1_VENC>; - clock-names = "venc0", "larb"; + clock-names = "venc0", "subsys-larb"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -1530,8 +1536,9 @@ clocks = <&topckgen CLK_TOP_USB_TOP>, <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_REF>, <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_HCLK>, - <&infracfg_ao CLK_INFRA_AO_ICUSB>; - clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck"; + <&infracfg_ao CLK_INFRA_AO_ICUSB>, + <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_XHCI>; + clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck"; interrupts = ; phys = <&u2port0 PHY_TYPE_USB2>; power-domains = <&spm MT8186_POWER_DOMAIN_SSUSB>; @@ -1595,8 +1602,9 @@ clocks = <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_SYS>, <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_REF>, <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_HCLK>, - <&clk26m>; - clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck"; + <&clk26m>, + <&infracfg_ao CLK_INFRA_AO_SSUSB_TOP_P1_XHCI>; + clock-names = "sys_ck", "ref_ck", "mcu_ck", "dma_ck", "xhci_ck"; interrupts = ; phys = <&u2port1 PHY_TYPE_USB2>, <&u3port1 PHY_TYPE_USB3>; power-domains = <&spm MT8186_POWER_DOMAIN_SSUSB_P1>; diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi index d87aab8d7a79e..f62b2498eb1c7 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi @@ -1336,10 +1336,6 @@ #address-cells = <1>; #size-cells = <0>; - base_detection: cbas { - compatible = "google,cros-cbas"; - }; - cros_ec_pwm: pwm { compatible = "google,cros-ec-pwm"; #pwm-cells = <1>; @@ -1424,7 +1420,7 @@ mt6315_6_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; @@ -1434,7 +1430,7 @@ mt6315_6_vbuck3: vbuck3 { regulator-compatible = "vbuck3"; regulator-name = "Vlcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; @@ -1451,7 +1447,7 @@ mt6315_7_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; - regulator-min-microvolt = <606250>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <800000>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi index 6dd32dbfb832e..eea8d141f93cf 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi @@ -1456,6 +1456,7 @@ reg = <0 0x14001000 0 0x1000>; interrupts = ; clocks = <&mmsys CLK_MM_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; mediatek,gce-events = , ; power-domains = <&spm MT8192_POWER_DOMAIN_DISP>; @@ -1814,7 +1815,7 @@ mediatek,scp = <&scp>; power-domains = <&spm MT8192_POWER_DOMAIN_VENC>; clocks = <&vencsys CLK_VENC_SET1_VENC>; - clock-names = "venc-set1"; + clock-names = "venc_sel"; assigned-clocks = <&topckgen CLK_TOP_VENC_SEL>; assigned-clock-parents = <&topckgen CLK_TOP_UNIVPLL_D4>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts index 2d5e8f371b6de..a82d716f10d44 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r1.dts @@ -23,3 +23,7 @@ &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts index 2586c32ce6e6f..2fe20e0dad836 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r2.dts @@ -43,3 +43,7 @@ &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts index f54f9477b99da..dd294ca98194c 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry-tomato-r3.dts @@ -44,3 +44,7 @@ &ts_10 { status = "okay"; }; + +&watchdog { + /delete-property/ mediatek,disable-extrst; +}; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi index 3c6079edda190..121dfd91da07b 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi @@ -264,6 +264,38 @@ status = "okay"; }; +&cpu0 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu1 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu2 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu3 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu4 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu5 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu6 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu7 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + &dp_intf0 { status = "okay"; @@ -1213,7 +1245,7 @@ mt6315_6_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-ramp-delay = <6250>; @@ -1231,7 +1263,7 @@ mt6315_7_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; - regulator-min-microvolt = <625000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-ramp-delay = <6250>; diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index b9101662ce40d..4dd7f755630ea 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -1998,6 +1998,7 @@ compatible = "mediatek,mt8195-vppsys0", "syscon"; reg = <0 0x14000000 0 0x1000>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0 0x1000>; }; dma-controller@14001000 { @@ -2221,6 +2222,7 @@ compatible = "mediatek,mt8195-vppsys1", "syscon"; reg = <0 0x14f00000 0 0x1000>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0 0x1000>; }; mutex@14f01000 { @@ -3050,6 +3052,7 @@ reg = <0 0x1c01a000 0 0x1000>; mboxes = <&gce0 0 CMDQ_THR_PRIO_4>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0xa000 0x1000>; }; @@ -3231,6 +3234,7 @@ interrupts = ; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>; clocks = <&vdosys0 CLK_VDO0_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0x6000 0x1000>; mediatek,gce-events = ; }; @@ -3301,6 +3305,7 @@ power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; clocks = <&vdosys1 CLK_VDO1_DISP_MUTEX>; clock-names = "vdo1_mutex"; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x1000 0x1000>; mediatek,gce-events = ; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts b/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts index bbc2e9bef08da..441216eda487f 100644 --- a/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts +++ b/arch/arm64/boot/dts/nvidia/tegra132-norrin.dts @@ -9,8 +9,8 @@ compatible = "nvidia,norrin", "nvidia,tegra132", "nvidia,tegra124"; aliases { - rtc0 = "/i2c@7000d000/as3722@40"; - rtc1 = "/rtc@7000e000"; + rtc0 = &as3722; + rtc1 = &tegra_rtc; serial0 = &uarta; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra132.dtsi b/arch/arm64/boot/dts/nvidia/tegra132.dtsi index 7e24a212c7e44..5bcccfef3f7f8 100644 --- a/arch/arm64/boot/dts/nvidia/tegra132.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra132.dtsi @@ -572,7 +572,7 @@ status = "disabled"; }; - rtc@7000e000 { + tegra_rtc: rtc@7000e000 { compatible = "nvidia,tegra124-rtc", "nvidia,tegra20-rtc"; reg = <0x0 0x7000e000 0x0 0x100>; interrupts = ; diff --git a/arch/arm64/boot/dts/qcom/pm2250.dtsi b/arch/arm64/boot/dts/qcom/pm4125.dtsi similarity index 91% rename from arch/arm64/boot/dts/qcom/pm2250.dtsi rename to arch/arm64/boot/dts/qcom/pm4125.dtsi index 5f1d15db5c993..d886a9e4b0918 100644 --- a/arch/arm64/boot/dts/qcom/pm2250.dtsi +++ b/arch/arm64/boot/dts/qcom/pm4125.dtsi @@ -19,7 +19,7 @@ compatible = "qcom,pm8916-pon"; reg = <0x800>; - pm2250_pwrkey: pwrkey { + pm4125_pwrkey: pwrkey { compatible = "qcom,pm8941-pwrkey"; interrupts-extended = <&spmi_bus 0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; linux,code = ; @@ -27,7 +27,7 @@ bias-pull-up; }; - pm2250_resin: resin { + pm4125_resin: resin { compatible = "qcom,pm8941-resin"; interrupts-extended = <&spmi_bus 0x0 0x8 1 IRQ_TYPE_EDGE_BOTH>; debounce = <15625>; @@ -43,11 +43,11 @@ interrupts-extended = <&spmi_bus 0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; }; - pm2250_gpios: gpio@c000 { + pm4125_gpios: gpio@c000 { compatible = "qcom,pm2250-gpio", "qcom,spmi-gpio"; reg = <0xc000>; gpio-controller; - gpio-ranges = <&pm2250_gpios 0 0 10>; + gpio-ranges = <&pm4125_gpios 0 0 10>; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arm64/boot/dts/qcom/qcm2290.dtsi b/arch/arm64/boot/dts/qcom/qcm2290.dtsi index 0911fb08ed632..89beac833d435 100644 --- a/arch/arm64/boot/dts/qcom/qcm2290.dtsi +++ b/arch/arm64/boot/dts/qcom/qcm2290.dtsi @@ -442,6 +442,11 @@ #hwlock-cells = <1>; }; + tcsr_regs: syscon@3c0000 { + compatible = "qcom,qcm2290-tcsr", "syscon"; + reg = <0x0 0x003c0000 0x0 0x40000>; + }; + tlmm: pinctrl@500000 { compatible = "qcom,qcm2290-tlmm"; reg = <0x0 0x00500000 0x0 0x300000>; @@ -690,6 +695,8 @@ #phy-cells = <0>; + qcom,tcsr-reg = <&tcsr_regs 0xb244>; + status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts index 176898c9dbbd7..1e85c43a6fd14 100644 --- a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts +++ b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts @@ -82,6 +82,11 @@ no-map; }; + removed_mem: removed@c0000000 { + reg = <0x0 0xc0000000 0x0 0x5100000>; + no-map; + }; + rmtfs_mem: memory@f8500000 { compatible = "qcom,rmtfs-mem"; reg = <0x0 0xf8500000 0x0 0x600000>; diff --git a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts index 03e97e27d16d4..d58d4f5dc3173 100644 --- a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts +++ b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts @@ -5,6 +5,7 @@ /dts-v1/; +#include #include #include "sc7280.dtsi" #include "pm7325.dtsi" @@ -123,8 +124,8 @@ vph_pwr: vph-pwr-regulator { compatible = "regulator-fixed"; regulator-name = "vph_pwr"; - regulator-min-microvolt = <2500000>; - regulator-max-microvolt = <4350000>; + regulator-min-microvolt = <3700000>; + regulator-max-microvolt = <3700000>; }; }; @@ -415,6 +416,33 @@ }; }; +&pm8350c_pwm { + status = "okay"; + + multi-led { + color = ; + function = LED_FUNCTION_STATUS; + + #address-cells = <1>; + #size-cells = <0>; + + led@1 { + reg = <1>; + color = ; + }; + + led@2 { + reg = <2>; + color = ; + }; + + led@3 { + reg = <3>; + color = ; + }; + }; +}; + &qupv3_id_0 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi index 10655401528e4..a22b4501ce1ef 100644 --- a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi +++ b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi @@ -62,7 +62,7 @@ vddrf-supply = <&vreg_l1_1p3>; vddch0-supply = <&vdd_ch0_3p3>; - local-bd-address = [ 02 00 00 00 5a ad ]; + local-bd-address = [ 00 00 00 00 00 00 ]; max-speed = <3200000>; }; diff --git a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts index 8bb7d13d85f66..ac4579119d3ba 100644 --- a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts +++ b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts @@ -124,8 +124,8 @@ vph_pwr: vph-pwr-regulator { compatible = "regulator-fixed"; regulator-name = "vph_pwr"; - regulator-min-microvolt = <2500000>; - regulator-max-microvolt = <4350000>; + regulator-min-microvolt = <3700000>; + regulator-max-microvolt = <3700000>; }; }; @@ -413,6 +413,23 @@ }; }; +&gcc { + protected-clocks = , + , + , + , + , + , + , + , + , + , + , + , + , + ; +}; + &qupv3_id_0 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts index aa53b6af6d9cb..6e9dd0312adc5 100644 --- a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts +++ b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts @@ -7,7 +7,7 @@ #include #include "qcm2290.dtsi" -#include "pm2250.dtsi" +#include "pm4125.dtsi" / { model = "Qualcomm Technologies, Inc. Robotics RB1"; @@ -177,6 +177,24 @@ }; }; +&CPU_PD0 { + /delete-property/ power-domains; +}; + +&CPU_PD1 { + /delete-property/ power-domains; +}; + +&CPU_PD2 { + /delete-property/ power-domains; +}; + +&CPU_PD3 { + /delete-property/ power-domains; +}; + +/delete-node/ &CLUSTER_PD; + &gpi_dma0 { status = "okay"; }; @@ -226,7 +244,7 @@ }; &mdss_dsi0 { - vdda-supply = <&pm2250_l5>; + vdda-supply = <&pm4125_l5>; status = "okay"; }; @@ -239,7 +257,7 @@ status = "okay"; }; -&pm2250_resin { +&pm4125_resin { linux,code = ; status = "okay"; }; @@ -263,23 +281,23 @@ compatible = "qcom,rpm-pm2250-regulators"; vdd_s3-supply = <&vph_pwr>; vdd_s4-supply = <&vph_pwr>; - vdd_l1_l2_l3_l5_l6_l7_l8_l9_l10_l11_l12-supply = <&pm2250_s3>; + vdd_l1_l2_l3_l5_l6_l7_l8_l9_l10_l11_l12-supply = <&pm4125_s3>; vdd_l4_l17_l18_l19_l20_l21_l22-supply = <&vph_pwr>; - vdd_l13_l14_l15_l16-supply = <&pm2250_s4>; + vdd_l13_l14_l15_l16-supply = <&pm4125_s4>; /* * S1 - VDD_APC * S2 - VDD_CX */ - pm2250_s3: s3 { + pm4125_s3: s3 { /* 0.4V-1.6625V -> 1.3V (Power tree requirements) */ regulator-min-microvolt = <1352000>; regulator-max-microvolt = <1352000>; regulator-boot-on; }; - pm2250_s4: s4 { + pm4125_s4: s4 { /* 1.2V-2.35V -> 2.05V (Power tree requirements) */ regulator-min-microvolt = <2072000>; regulator-max-microvolt = <2072000>; @@ -288,7 +306,7 @@ /* L1 - VDD_MX */ - pm2250_l2: l2 { + pm4125_l2: l2 { /* LPDDR4X VDD2 */ regulator-min-microvolt = <1136000>; regulator-max-microvolt = <1136000>; @@ -296,7 +314,7 @@ regulator-boot-on; }; - pm2250_l3: l3 { + pm4125_l3: l3 { /* LPDDR4X VDDQ */ regulator-min-microvolt = <616000>; regulator-max-microvolt = <616000>; @@ -304,14 +322,14 @@ regulator-boot-on; }; - pm2250_l4: l4 { + pm4125_l4: l4 { /* max = 3.05V -> max = 2.7 to disable 3V signaling (SDHCI2) */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <2700000>; regulator-allow-set-load; }; - pm2250_l5: l5 { + pm4125_l5: l5 { /* CSI/DSI */ regulator-min-microvolt = <1232000>; regulator-max-microvolt = <1232000>; @@ -319,7 +337,7 @@ regulator-boot-on; }; - pm2250_l6: l6 { + pm4125_l6: l6 { /* DRAM PLL */ regulator-min-microvolt = <928000>; regulator-max-microvolt = <928000>; @@ -327,7 +345,7 @@ regulator-boot-on; }; - pm2250_l7: l7 { + pm4125_l7: l7 { /* Wi-Fi CX/MX */ regulator-min-microvolt = <664000>; regulator-max-microvolt = <664000>; @@ -338,20 +356,20 @@ * L9 - VDD_LPI_MX */ - pm2250_l10: l10 { + pm4125_l10: l10 { /* Wi-Fi RFA */ regulator-min-microvolt = <1304000>; regulator-max-microvolt = <1304000>; }; - pm2250_l11: l11 { + pm4125_l11: l11 { /* GPS RF1 */ regulator-min-microvolt = <1000000>; regulator-max-microvolt = <1000000>; regulator-boot-on; }; - pm2250_l12: l12 { + pm4125_l12: l12 { /* USB PHYs */ regulator-min-microvolt = <928000>; regulator-max-microvolt = <928000>; @@ -359,7 +377,7 @@ regulator-boot-on; }; - pm2250_l13: l13 { + pm4125_l13: l13 { /* USB/QFPROM/PLLs */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -367,7 +385,7 @@ regulator-boot-on; }; - pm2250_l14: l14 { + pm4125_l14: l14 { /* SDHCI1 VQMMC */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -376,7 +394,7 @@ regulator-always-on; }; - pm2250_l15: l15 { + pm4125_l15: l15 { /* WCD/DSI/BT VDDIO */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -385,38 +403,38 @@ regulator-boot-on; }; - pm2250_l16: l16 { + pm4125_l16: l16 { /* GPS RF2 */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-boot-on; }; - pm2250_l17: l17 { + pm4125_l17: l17 { regulator-min-microvolt = <3000000>; regulator-max-microvolt = <3000000>; }; - pm2250_l18: l18 { + pm4125_l18: l18 { /* VDD_PXn */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; - pm2250_l19: l19 { + pm4125_l19: l19 { /* VDD_PXn */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; - pm2250_l20: l20 { + pm4125_l20: l20 { /* SDHCI1 VMMC */ regulator-min-microvolt = <2400000>; regulator-max-microvolt = <3600000>; regulator-allow-set-load; }; - pm2250_l21: l21 { + pm4125_l21: l21 { /* SDHCI2 VMMC */ regulator-min-microvolt = <2960000>; regulator-max-microvolt = <3300000>; @@ -424,7 +442,7 @@ regulator-boot-on; }; - pm2250_l22: l22 { + pm4125_l22: l22 { /* Wi-Fi */ regulator-min-microvolt = <3312000>; regulator-max-microvolt = <3312000>; @@ -433,8 +451,8 @@ }; &sdhc_1 { - vmmc-supply = <&pm2250_l20>; - vqmmc-supply = <&pm2250_l14>; + vmmc-supply = <&pm4125_l20>; + vqmmc-supply = <&pm4125_l14>; pinctrl-0 = <&sdc1_state_on>; pinctrl-1 = <&sdc1_state_off>; pinctrl-names = "default", "sleep"; @@ -446,8 +464,8 @@ }; &sdhc_2 { - vmmc-supply = <&pm2250_l21>; - vqmmc-supply = <&pm2250_l4>; + vmmc-supply = <&pm4125_l21>; + vqmmc-supply = <&pm4125_l4>; cd-gpios = <&tlmm 88 GPIO_ACTIVE_LOW>; pinctrl-0 = <&sdc2_state_on &sd_det_in_on>; pinctrl-1 = <&sdc2_state_off &sd_det_in_off>; @@ -518,8 +536,8 @@ }; &usb_qmpphy { - vdda-phy-supply = <&pm2250_l12>; - vdda-pll-supply = <&pm2250_l13>; + vdda-phy-supply = <&pm4125_l12>; + vdda-pll-supply = <&pm4125_l13>; status = "okay"; }; @@ -528,17 +546,17 @@ }; &usb_hsphy { - vdd-supply = <&pm2250_l12>; - vdda-pll-supply = <&pm2250_l13>; - vdda-phy-dpdm-supply = <&pm2250_l21>; + vdd-supply = <&pm4125_l12>; + vdda-pll-supply = <&pm4125_l13>; + vdda-phy-dpdm-supply = <&pm4125_l21>; status = "okay"; }; &wifi { - vdd-0.8-cx-mx-supply = <&pm2250_l7>; - vdd-1.8-xo-supply = <&pm2250_l13>; - vdd-1.3-rfa-supply = <&pm2250_l10>; - vdd-3.3-ch0-supply = <&pm2250_l22>; + vdd-0.8-cx-mx-supply = <&pm4125_l7>; + vdd-1.8-xo-supply = <&pm4125_l13>; + vdd-1.3-rfa-supply = <&pm4125_l10>; + vdd-3.3-ch0-supply = <&pm4125_l22>; qcom,ath10k-calibration-variant = "Thundercomm_RB1"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts index 7c19f874fa716..52f31f3166c2f 100644 --- a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts +++ b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts @@ -607,10 +607,6 @@ status = "okay"; }; -&usb_dwc3 { - maximum-speed = "super-speed"; -}; - &usb_hsphy { vdd-supply = <&vreg_l4a_0p9>; vdda-pll-supply = <&vreg_l12a_1p8>; diff --git a/arch/arm64/boot/dts/qcom/sa8155p-adp.dts b/arch/arm64/boot/dts/qcom/sa8155p-adp.dts index 5e4287f8c8cd1..b2cf2c988336c 100644 --- a/arch/arm64/boot/dts/qcom/sa8155p-adp.dts +++ b/arch/arm64/boot/dts/qcom/sa8155p-adp.dts @@ -367,6 +367,16 @@ }; }; +&pmm8155au_1_gpios { + pmm8155au_1_sdc2_cd: sdc2-cd-default-state { + pins = "gpio4"; + function = "normal"; + input-enable; + bias-pull-up; + power-source = <0>; + }; +}; + &qupv3_id_1 { status = "okay"; }; @@ -384,10 +394,10 @@ &sdhc_2 { status = "okay"; - cd-gpios = <&tlmm 4 GPIO_ACTIVE_LOW>; + cd-gpios = <&pmm8155au_1_gpios 4 GPIO_ACTIVE_LOW>; pinctrl-names = "default", "sleep"; - pinctrl-0 = <&sdc2_on>; - pinctrl-1 = <&sdc2_off>; + pinctrl-0 = <&sdc2_on &pmm8155au_1_sdc2_cd>; + pinctrl-1 = <&sdc2_off &pmm8155au_1_sdc2_cd>; vqmmc-supply = <&vreg_l13c_2p96>; /* IO line power */ vmmc-supply = <&vreg_l17a_2p96>; /* Card power line */ bus-width = <4>; @@ -505,13 +515,6 @@ bias-pull-up; /* pull up */ drive-strength = <16>; /* 16 MA */ }; - - sd-cd-pins { - pins = "gpio96"; - function = "gpio"; - bias-pull-up; /* pull up */ - drive-strength = <2>; /* 2 MA */ - }; }; sdc2_off: sdc2-off-state { @@ -532,13 +535,6 @@ bias-pull-up; /* pull up */ drive-strength = <2>; /* 2 MA */ }; - - sd-cd-pins { - pins = "gpio96"; - function = "gpio"; - bias-pull-up; /* pull up */ - drive-strength = <2>; /* 2 MA */ - }; }; usb2phy_ac_en1_default: usb2phy-ac-en1-default-state { diff --git a/arch/arm64/boot/dts/qcom/sa8540p.dtsi b/arch/arm64/boot/dts/qcom/sa8540p.dtsi index 96b2c59ad02b4..23888029cc117 100644 --- a/arch/arm64/boot/dts/qcom/sa8540p.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8540p.dtsi @@ -168,6 +168,9 @@ }; &gpucc { + /* SA8295P and SA8540P doesn't provide gfx.lvl */ + /delete-property/ power-domains; + status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index 46aaeba286047..ebe37678102f0 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -943,6 +943,8 @@ ap_spi_fp: &spi10 { vddrf-supply = <&pp1300_l2c>; vddch0-supply = <&pp3300_l10c>; max-speed = <3200000>; + + qcom,local-bd-address-broken; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 83b5b76ba1794..46545cd6964a9 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -2178,8 +2178,16 @@ ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>, <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>; - interrupts = ; - interrupt-names = "msi"; + interrupts = , + , + , + , + , + , + , + ; + interrupt-names = "msi0", "msi1", "msi2", "msi3", + "msi4", "msi5", "msi6", "msi7"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>, @@ -2345,6 +2353,8 @@ <&apps_smmu 0x4e6 0x0011>; qcom,ee = <0>; qcom,controlled-remotely; + num-channels = <16>; + qcom,num-ees = <4>; }; crypto: crypto@1dfa000 { @@ -3640,7 +3650,7 @@ compatible = "qcom,sc7280-adsp-pas"; reg = <0 0x03700000 0 0x100>; - interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&adsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, <&adsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>, <&adsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>, @@ -3877,7 +3887,7 @@ compatible = "qcom,sc7280-cdsp-pas"; reg = <0 0x0a300000 0 0x10000>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&cdsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, <&cdsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>, <&cdsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sc8180x.dtsi b/arch/arm64/boot/dts/qcom/sc8180x.dtsi index 0430d99091e30..b481c15b255ce 100644 --- a/arch/arm64/boot/dts/qcom/sc8180x.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8180x.dtsi @@ -290,7 +290,7 @@ BIG_CPU_SLEEP_0: cpu-sleep-1-0 { compatible = "arm,idle-state"; arm,psci-suspend-param = <0x40000004>; - entry-latency-us = <241>; + entry-latency-us = <2411>; exit-latency-us = <1461>; min-residency-us = <4488>; local-timer-stop; @@ -298,7 +298,15 @@ }; domain-idle-states { - CLUSTER_SLEEP_0: cluster-sleep-0 { + CLUSTER_SLEEP_APSS_OFF: cluster-sleep-0 { + compatible = "domain-idle-state"; + arm,psci-suspend-param = <0x41000044>; + entry-latency-us = <3300>; + exit-latency-us = <3300>; + min-residency-us = <6000>; + }; + + CLUSTER_SLEEP_AOSS_SLEEP: cluster-sleep-1 { compatible = "domain-idle-state"; arm,psci-suspend-param = <0x4100a344>; entry-latency-us = <3263>; @@ -582,7 +590,7 @@ CLUSTER_PD: power-domain-cpu-cluster0 { #power-domain-cells = <0>; - domain-idle-states = <&CLUSTER_SLEEP_0>; + domain-idle-states = <&CLUSTER_SLEEP_APSS_OFF &CLUSTER_SLEEP_AOSS_SLEEP>; }; }; @@ -782,6 +790,7 @@ clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk"; + power-domains = <&rpmhpd SC8180X_CX>; }; qupv3_id_0: geniqup@8c0000 { @@ -2632,7 +2641,7 @@ resets = <&gcc GCC_USB30_SEC_BCR>; power-domains = <&gcc USB30_SEC_GDSC>; interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 7 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 40 IRQ_TYPE_LEVEL_HIGH>, <&pdc 10 IRQ_TYPE_EDGE_BOTH>, <&pdc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", @@ -2692,9 +2701,15 @@ interrupt-controller; #interrupt-cells = <1>; - interconnects = <&mmss_noc MASTER_MDP_PORT0 0 &mc_virt SLAVE_EBI_CH0 0>, - <&mmss_noc MASTER_MDP_PORT1 0 &mc_virt SLAVE_EBI_CH0 0>; - interconnect-names = "mdp0-mem", "mdp1-mem"; + interconnects = <&mmss_noc MASTER_MDP_PORT0 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI_CH0 QCOM_ICC_TAG_ALWAYS>, + <&mmss_noc MASTER_MDP_PORT1 QCOM_ICC_TAG_ALWAYS + &mc_virt SLAVE_EBI_CH0 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_AMPSS_M0 QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_DISPLAY_CFG QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "mdp0-mem", + "mdp1-mem", + "cpu-cfg"; iommus = <&apps_smmu 0x800 0x420>; @@ -2723,10 +2738,8 @@ "rot", "lut"; - assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>, - <&dispcc DISP_CC_MDSS_VSYNC_CLK>; - assigned-clock-rates = <460000000>, - <19200000>; + assigned-clocks = <&dispcc DISP_CC_MDSS_VSYNC_CLK>; + assigned-clock-rates = <19200000>; operating-points-v2 = <&mdp_opp_table>; power-domains = <&rpmhpd SC8180X_MMCX>; @@ -3184,7 +3197,7 @@ <&dispcc DISP_CC_MDSS_AHB_CLK>; clock-names = "aux", "cfg_ahb"; - power-domains = <&dispcc MDSS_GDSC>; + power-domains = <&rpmhpd SC8180X_MX>; #clock-cells = <1>; #phy-cells = <0>; @@ -3210,6 +3223,7 @@ "edp_phy_pll_link_clk", "edp_phy_pll_vco_div_clk"; power-domains = <&rpmhpd SC8180X_MMCX>; + required-opps = <&rpmhpd_opp_low_svs>; #clock-cells = <1>; #reset-cells = <1>; #power-domain-cells = <1>; @@ -3248,7 +3262,7 @@ aoss_qmp: power-controller@c300000 { compatible = "qcom,sc8180x-aoss-qmp", "qcom,aoss-qmp"; - reg = <0x0 0x0c300000 0x0 0x100000>; + reg = <0x0 0x0c300000 0x0 0x400>; interrupts = ; mboxes = <&apss_shared 0>; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index eb657e544961d..461e7afe662d7 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -416,6 +416,13 @@ regulator-always-on; }; + vreg_l1b: ldo1 { + regulator-name = "vreg_l1b"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; + vreg_l3b: ldo3 { regulator-name = "vreg_l3b"; regulator-min-microvolt = <1200000>; @@ -466,6 +473,13 @@ regulator-initial-mode = ; }; + vreg_l8c: ldo8 { + regulator-name = "vreg_l8c"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-initial-mode = ; + }; + vreg_l12c: ldo12 { regulator-name = "vreg_l12c"; regulator-min-microvolt = <1800000>; @@ -499,6 +513,13 @@ vdd-l6-l9-l10-supply = <&vreg_s12b>; vdd-l8-supply = <&vreg_s12b>; + vreg_l2d: ldo2 { + regulator-name = "vreg_l2d"; + regulator-min-microvolt = <3072000>; + regulator-max-microvolt = <3072000>; + regulator-initial-mode = ; + }; + vreg_l3d: ldo3 { regulator-name = "vreg_l3d"; regulator-min-microvolt = <1200000>; @@ -527,12 +548,26 @@ regulator-initial-mode = ; }; + vreg_l8d: ldo8 { + regulator-name = "vreg_l8d"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; + vreg_l9d: ldo9 { regulator-name = "vreg_l9d"; regulator-min-microvolt = <912000>; regulator-max-microvolt = <912000>; regulator-initial-mode = ; }; + + vreg_l10d: ldo10 { + regulator-name = "vreg_l10d"; + regulator-min-microvolt = <912000>; + regulator-max-microvolt = <912000>; + regulator-initial-mode = ; + }; }; }; @@ -1203,6 +1238,60 @@ remote-endpoint = <&pmic_glink_con1_hs>; }; +&usb_2 { + status = "okay"; +}; + +&usb_2_dwc3 { + dr_mode = "host"; +}; + +&usb_2_hsphy0 { + vdda-pll-supply = <&vreg_l1b>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l7d>; + + status = "okay"; +}; + +&usb_2_hsphy1 { + vdda-pll-supply = <&vreg_l8d>; + vdda18-supply = <&vreg_l1c>; + vdda33-supply = <&vreg_l7d>; + + status = "okay"; +}; + +&usb_2_hsphy2 { + vdda-pll-supply = <&vreg_l10d>; + vdda18-supply = <&vreg_l8c>; + vdda33-supply = <&vreg_l2d>; + + status = "okay"; +}; + +&usb_2_hsphy3 { + vdda-pll-supply = <&vreg_l10d>; + vdda18-supply = <&vreg_l8c>; + vdda33-supply = <&vreg_l2d>; + + status = "okay"; +}; + +&usb_2_qmpphy0 { + vdda-phy-supply = <&vreg_l1b>; + vdda-pll-supply = <&vreg_l4d>; + + status = "okay"; +}; + +&usb_2_qmpphy1 { + vdda-phy-supply = <&vreg_l8d>; + vdda-pll-supply = <&vreg_l4d>; + + status = "okay"; +}; + &vamacro { pinctrl-0 = <&dmic01_default>, <&dmic02_default>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index febf28356ff8b..d99ae6c2ba4cb 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -1774,6 +1774,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_4_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie4_phy>; phy-names = "pciephy"; @@ -1798,6 +1799,7 @@ assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_4_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_4_PHY_BCR>; reset-names = "phy"; @@ -1872,6 +1874,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_3B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie3b_phy>; phy-names = "pciephy"; @@ -1896,6 +1899,7 @@ assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_3B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_3B_PHY_BCR>; reset-names = "phy"; @@ -1970,6 +1974,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_3A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie3a_phy>; phy-names = "pciephy"; @@ -1995,6 +2000,7 @@ assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_3A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_3A_PHY_BCR>; reset-names = "phy"; @@ -2071,6 +2077,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_2B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie2b_phy>; phy-names = "pciephy"; @@ -2095,6 +2102,7 @@ assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_2B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_2B_PHY_BCR>; reset-names = "phy"; @@ -2169,6 +2177,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_2A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie2a_phy>; phy-names = "pciephy"; @@ -2194,6 +2203,7 @@ assigned-clock-rates = <100000000>; power-domains = <&gcc PCIE_2A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; resets = <&gcc GCC_PCIE_2A_PHY_BCR>; reset-names = "phy"; @@ -2635,7 +2645,7 @@ compatible = "qcom,sc8280xp-adsp-pas"; reg = <0 0x03000000 0 0x100>; - interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, @@ -3331,6 +3341,88 @@ interrupts = ; }; + usb_2: usb@a4f8800 { + compatible = "qcom,sc8280xp-dwc3-mp", "qcom,dwc3"; + reg = <0 0x0a4f8800 0 0x400>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + clocks = <&gcc GCC_CFG_NOC_USB3_MP_AXI_CLK>, + <&gcc GCC_USB30_MP_MASTER_CLK>, + <&gcc GCC_AGGRE_USB3_MP_AXI_CLK>, + <&gcc GCC_USB30_MP_SLEEP_CLK>, + <&gcc GCC_USB30_MP_MOCK_UTMI_CLK>, + <&gcc GCC_AGGRE_USB_NOC_AXI_CLK>, + <&gcc GCC_AGGRE_USB_NOC_NORTH_AXI_CLK>, + <&gcc GCC_AGGRE_USB_NOC_SOUTH_AXI_CLK>, + <&gcc GCC_SYS_NOC_USB_AXI_CLK>; + clock-names = "cfg_noc", "core", "iface", "sleep", "mock_utmi", + "noc_aggr", "noc_aggr_north", "noc_aggr_south", "noc_sys"; + + assigned-clocks = <&gcc GCC_USB30_MP_MOCK_UTMI_CLK>, + <&gcc GCC_USB30_MP_MASTER_CLK>; + assigned-clock-rates = <19200000>, <200000000>; + + interrupts-extended = <&intc GIC_SPI 130 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 857 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 856 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 860 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 859 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 127 IRQ_TYPE_EDGE_BOTH>, + <&pdc 126 IRQ_TYPE_EDGE_BOTH>, + <&pdc 129 IRQ_TYPE_EDGE_BOTH>, + <&pdc 128 IRQ_TYPE_EDGE_BOTH>, + <&pdc 131 IRQ_TYPE_EDGE_BOTH>, + <&pdc 130 IRQ_TYPE_EDGE_BOTH>, + <&pdc 133 IRQ_TYPE_EDGE_BOTH>, + <&pdc 132 IRQ_TYPE_EDGE_BOTH>, + <&pdc 16 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 17 IRQ_TYPE_LEVEL_HIGH>; + + interrupt-names = "pwr_event_1", "pwr_event_2", + "pwr_event_3", "pwr_event_4", + "hs_phy_1", "hs_phy_2", + "hs_phy_3", "hs_phy_4", + "dp_hs_phy_1", "dm_hs_phy_1", + "dp_hs_phy_2", "dm_hs_phy_2", + "dp_hs_phy_3", "dm_hs_phy_3", + "dp_hs_phy_4", "dm_hs_phy_4", + "ss_phy_1", "ss_phy_2"; + + power-domains = <&gcc USB30_MP_GDSC>; + required-opps = <&rpmhpd_opp_nom>; + + resets = <&gcc GCC_USB30_MP_BCR>; + + interconnects = <&aggre1_noc MASTER_USB3_MP 0 &mc_virt SLAVE_EBI1 0>, + <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3_MP 0>; + interconnect-names = "usb-ddr", "apps-usb"; + + wakeup-source; + + status = "disabled"; + + usb_2_dwc3: usb@a400000 { + compatible = "snps,dwc3"; + reg = <0 0x0a400000 0 0xcd00>; + interrupts = ; + iommus = <&apps_smmu 0x800 0x0>; + phys = <&usb_2_hsphy0>, <&usb_2_qmpphy0>, + <&usb_2_hsphy1>, <&usb_2_qmpphy1>, + <&usb_2_hsphy2>, + <&usb_2_hsphy3>; + phy-names = "usb2-0", "usb3-0", + "usb2-1", "usb3-1", + "usb2-2", + "usb2-3"; + dr_mode = "host"; + }; + }; + usb_0: usb@a6f8800 { compatible = "qcom,sc8280xp-dwc3", "qcom,dwc3"; reg = <0 0x0a6f8800 0 0x400>; @@ -4407,7 +4499,7 @@ compatible = "qcom,sc8280xp-nsp0-pas"; reg = <0 0x1b300000 0 0x100>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp0_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp0_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp0_in 2 IRQ_TYPE_EDGE_RISING>, @@ -4538,7 +4630,7 @@ compatible = "qcom,sc8280xp-nsp1-pas"; reg = <0 0x21300000 0 0x100>; - interrupts-extended = <&intc GIC_SPI 887 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 887 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp1_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp1_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp1_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index ab6220456513c..1f517328199b9 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -580,7 +580,7 @@ &pcie0 { status = "okay"; perst-gpios = <&tlmm 35 GPIO_ACTIVE_LOW>; - enable-gpio = <&tlmm 134 GPIO_ACTIVE_HIGH>; + wake-gpios = <&tlmm 134 GPIO_ACTIVE_HIGH>; vddpe-3v3-supply = <&pcie0_3p3v_dual>; diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index e821103d49c0a..46e25c53829ad 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -508,13 +508,13 @@ }; &q6afedai { - qi2s@22 { - reg = <22>; + dai@22 { + reg = ; qcom,sd-lines = <1>; }; - qi2s@23 { - reg = <23>; + dai@23 { + reg = ; qcom,sd-lines = <0>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index c2244824355a2..237d404861424 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -3366,8 +3366,8 @@ qcom,qmp = <&aoss_qmp>; - power-domains = <&rpmhpd SDM845_CX>, - <&rpmhpd SDM845_MX>; + power-domains = <&rpmhpd SDM845_LCX>, + <&rpmhpd SDM845_LMX>; power-domain-names = "lcx", "lmx"; memory-region = <&slpi_mem>; diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi index f9849b8befbf2..d33763d092659 100644 --- a/arch/arm64/boot/dts/qcom/sm6115.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi @@ -614,6 +614,11 @@ #hwlock-cells = <1>; }; + tcsr_regs: syscon@3c0000 { + compatible = "qcom,sm6115-tcsr", "syscon"; + reg = <0x0 0x003c0000 0x0 0x40000>; + }; + tlmm: pinctrl@500000 { compatible = "qcom,sm6115-tlmm"; reg = <0x0 0x00500000 0x0 0x400000>, @@ -879,6 +884,8 @@ #phy-cells = <0>; + qcom,tcsr-reg = <&tcsr_regs 0xb244>; + status = "disabled"; }; @@ -1603,7 +1610,6 @@ interconnect-names = "usb-ddr", "apps-usb"; - qcom,select-utmi-as-pipe-clk; status = "disabled"; usb_dwc3: usb@4e00000 { diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index 43cffe8e1247e..7532107580aee 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -1249,7 +1249,7 @@ compatible = "qcom,sm6350-adsp-pas"; reg = <0 0x03000000 0 0x100>; - interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, @@ -1509,7 +1509,7 @@ compatible = "qcom,sm6350-cdsp-pas"; reg = <0 0x08300000 0 0x10000>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm6375.dtsi b/arch/arm64/boot/dts/qcom/sm6375.dtsi index 7ac8bf26dda3a..a74472ac6186d 100644 --- a/arch/arm64/boot/dts/qcom/sm6375.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6375.dtsi @@ -1559,7 +1559,7 @@ compatible = "qcom,sm6375-adsp-pas"; reg = <0 0x0a400000 0 0x100>; - interrupts-extended = <&intc GIC_SPI 282 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 282 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi index 761a6757dc26f..2abd4c87a3ca9 100644 --- a/arch/arm64/boot/dts/qcom/sm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi @@ -1879,7 +1879,7 @@ phy-names = "pciephy"; perst-gpios = <&tlmm 35 GPIO_ACTIVE_HIGH>; - enable-gpio = <&tlmm 37 GPIO_ACTIVE_HIGH>; + wake-gpios = <&tlmm 37 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pcie0_default_state>; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index 760501c1301a6..b07a3bad6eb96 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -3025,7 +3025,7 @@ compatible = "qcom,sm8250-slpi-pas"; reg = <0 0x05c00000 0 0x4000>; - interrupts-extended = <&pdc 9 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 9 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 2 IRQ_TYPE_EDGE_RISING>, @@ -3729,7 +3729,7 @@ compatible = "qcom,sm8250-cdsp-pas"; reg = <0 0x08300000 0 0x10000>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>, @@ -5887,7 +5887,7 @@ compatible = "qcom,sm8250-adsp-pas"; reg = <0 0x17300000 0 0x100>; - interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm8450-hdk.dts b/arch/arm64/boot/dts/qcom/sm8450-hdk.dts index a20d5d76af352..31e74160b8c13 100644 --- a/arch/arm64/boot/dts/qcom/sm8450-hdk.dts +++ b/arch/arm64/boot/dts/qcom/sm8450-hdk.dts @@ -938,8 +938,8 @@ "TX DMIC3", "MIC BIAS1", "TX SWR_INPUT0", "ADC1_OUTPUT", "TX SWR_INPUT1", "ADC2_OUTPUT", - "TX SWR_INPUT2", "ADC3_OUTPUT", - "TX SWR_INPUT3", "ADC4_OUTPUT"; + "TX SWR_INPUT0", "ADC3_OUTPUT", + "TX SWR_INPUT1", "ADC4_OUTPUT"; wcd-playback-dai-link { link-name = "WCD Playback"; diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index 01e4dfc4babd2..b72a48c1d3ba4 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -1028,6 +1028,12 @@ pinctrl-names = "default"; pinctrl-0 = <&qup_uart20_default>; interrupts = ; + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; status = "disabled"; }; @@ -1420,6 +1426,12 @@ pinctrl-names = "default"; pinctrl-0 = <&qup_uart7_tx>, <&qup_uart7_rx>; interrupts = ; + interconnects = <&clk_virt MASTER_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS + &clk_virt SLAVE_QUP_CORE_2 QCOM_ICC_TAG_ALWAYS>, + <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS + &config_noc SLAVE_QUP_2 QCOM_ICC_TAG_ALWAYS>; + interconnect-names = "qup-core", + "qup-config"; status = "disabled"; }; }; @@ -1765,12 +1777,8 @@ ranges = <0x01000000 0x0 0x00000000 0x0 0x60200000 0x0 0x100000>, <0x02000000 0x0 0x60300000 0x0 0x60300000 0x0 0x3d00000>; - /* - * MSIs for BDF (1:0.0) only works with Device ID 0x5980. - * Hence, the IDs are swapped. - */ - msi-map = <0x0 &gic_its 0x5981 0x1>, - <0x100 &gic_its 0x5980 0x1>; + msi-map = <0x0 &gic_its 0x5980 0x1>, + <0x100 &gic_its 0x5981 0x1>; msi-map-mask = <0xff00>; interrupts = ; interrupt-names = "msi"; @@ -1874,12 +1882,8 @@ ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>, <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>; - /* - * MSIs for BDF (1:0.0) only works with Device ID 0x5a00. - * Hence, the IDs are swapped. - */ - msi-map = <0x0 &gic_its 0x5a01 0x1>, - <0x100 &gic_its 0x5a00 0x1>; + msi-map = <0x0 &gic_its 0x5a00 0x1>, + <0x100 &gic_its 0x5a01 0x1>; msi-map-mask = <0xff00>; interrupts = ; interrupt-names = "msi"; diff --git a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts index c1135ad5fa696..a26e169a802a4 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts @@ -874,7 +874,7 @@ wcd_tx: codec@0,3 { compatible = "sdw20217010d00"; reg = <0 3>; - qcom,tx-port-mapping = <1 1 2 3>; + qcom,tx-port-mapping = <2 2 3 4>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts index d401d63e5c4d2..54dfee40d6059 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts @@ -978,7 +978,7 @@ wcd_tx: codec@0,3 { compatible = "sdw20217010d00"; reg = <0 3>; - qcom,tx-port-mapping = <1 1 2 3>; + qcom,tx-port-mapping = <2 2 3 4>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index ee1ba5a8c8fc2..90acdf16b8307 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -3248,7 +3248,7 @@ spmi_bus: spmi@c400000 { compatible = "qcom,spmi-pmic-arb"; reg = <0 0x0c400000 0 0x3000>, - <0 0x0c500000 0 0x4000000>, + <0 0x0c500000 0 0x400000>, <0 0x0c440000 0 0x80000>, <0 0x0c4c0000 0 0x20000>, <0 0x0c42d000 0 0x4000>; diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index 2df77123a8c7b..0e4bd83b2c68a 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -2448,10 +2448,12 @@ compatible = "qcom,sm8650-qmp-ufs-phy"; reg = <0 0x01d80000 0 0x2000>; - clocks = <&tcsr TCSR_UFS_CLKREF_EN>, - <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&gcc GCC_UFS_PHY_PHY_AUX_CLK>, + <&tcsr TCSR_UFS_CLKREF_EN>; clock-names = "ref", - "ref_aux"; + "ref_aux", + "qref"; resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; @@ -3703,7 +3705,7 @@ spmi_bus: spmi@c400000 { compatible = "qcom,spmi-pmic-arb"; reg = <0 0x0c400000 0 0x3000>, - <0 0x0c500000 0 0x4000000>, + <0 0x0c500000 0 0x400000>, <0 0x0c440000 0 0x80000>, <0 0x0c4c0000 0 0x20000>, <0 0x0c42d000 0 0x4000>; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts index a37ad9475c90d..3112487d2a168 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts @@ -243,7 +243,7 @@ qcom,pmic-id = "e"; vdd-l2-supply = <&vreg_s1f_0p7>; - vdd-l3-supply = <&vph_pwr>; + vdd-l3-supply = <&vreg_s5j_1p2>; vreg_l2e_0p8: ldo2 { regulator-name = "vreg_l2e_0p8"; @@ -349,7 +349,7 @@ qcom,pmic-id = "j"; vdd-l1-supply = <&vreg_s1f_0p7>; - vdd-l2-supply = <&vph_pwr>; + vdd-l2-supply = <&vreg_s5j_1p2>; vdd-l3-supply = <&vreg_s1f_0p7>; vdd-s5-supply = <&vph_pwr>; diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index 6f75fc342ceb3..5ba7924aa4355 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -278,7 +278,7 @@ domain-idle-states { CLUSTER_CL4: cluster-sleep-0 { - compatible = "arm,idle-state"; + compatible = "domain-idle-state"; idle-state-name = "l2-ret"; arm,psci-suspend-param = <0x01000044>; entry-latency-us = <350>; @@ -287,7 +287,7 @@ }; CLUSTER_CL5: cluster-sleep-1 { - compatible = "arm,idle-state"; + compatible = "domain-idle-state"; idle-state-name = "ret-pll-off"; arm,psci-suspend-param = <0x01000054>; entry-latency-us = <2200>; @@ -3315,7 +3315,6 @@ <0 0x17510000 0 0x10000>, <0 0x17520000 0 0x10000>; reg-names = "drv-0", "drv-1", "drv-2"; - qcom,drv-count = <3>; interrupts = , , diff --git a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi index 4e67a03564971..504ac8c93faf5 100644 --- a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi @@ -658,7 +658,7 @@ avb0: ethernet@e6800000 { compatible = "renesas,etheravb-r8a779a0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6800000 0 0x800>; + reg = <0 0xe6800000 0 0x1000>; interrupts = , , , @@ -706,7 +706,7 @@ avb1: ethernet@e6810000 { compatible = "renesas,etheravb-r8a779a0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6810000 0 0x800>; + reg = <0 0xe6810000 0 0x1000>; interrupts = , , , diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi index d3d25e077c5d5..d7677595204dc 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi @@ -161,11 +161,6 @@ }; }; - psci { - compatible = "arm,psci-1.0", "arm,psci-0.2"; - method = "smc"; - }; - extal_clk: extal { compatible = "fixed-clock"; #clock-cells = <0>; @@ -185,13 +180,24 @@ interrupts-extended = <&gic GIC_PPI 7 IRQ_TYPE_LEVEL_LOW>; }; - /* External SCIF clock - to be overridden by boards that provide it */ + psci { + compatible = "arm,psci-1.0", "arm,psci-0.2"; + method = "smc"; + }; + + /* External SCIF clocks - to be overridden by boards that provide them */ scif_clk: scif { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <0>; }; + scif_clk2: scif2 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + soc: soc { compatible = "simple-bus"; interrupt-parent = <&gic>; @@ -681,7 +687,7 @@ interrupts = ; clocks = <&cpg CPG_MOD 516>, <&cpg CPG_CORE R8A779G0_CLK_SASYNCPERD1>, - <&scif_clk>; + <&scif_clk2>; clock-names = "fck", "brg_int", "scif_clk"; dmas = <&dmac0 0x35>, <&dmac0 0x34>, <&dmac1 0x35>, <&dmac1 0x34>; @@ -761,7 +767,7 @@ avb0: ethernet@e6800000 { compatible = "renesas,etheravb-r8a779g0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6800000 0 0x800>; + reg = <0 0xe6800000 0 0x1000>; interrupts = , , , @@ -808,7 +814,7 @@ avb1: ethernet@e6810000 { compatible = "renesas,etheravb-r8a779g0", "renesas,etheravb-rcar-gen4"; - reg = <0 0xe6810000 0 0x800>; + reg = <0 0xe6810000 0 0x1000>; interrupts = , , , @@ -1057,7 +1063,7 @@ interrupts = ; clocks = <&cpg CPG_MOD 705>, <&cpg CPG_CORE R8A779G0_CLK_SASYNCPERD1>, - <&scif_clk>; + <&scif_clk2>; clock-names = "fck", "brg_int", "scif_clk"; dmas = <&dmac0 0x59>, <&dmac0 0x58>, <&dmac1 0x59>, <&dmac1 0x58>; @@ -1777,6 +1783,37 @@ }; }; + mmc0: mmc@ee140000 { + compatible = "renesas,sdhi-r8a779g0", + "renesas,rcar-gen4-sdhi"; + reg = <0 0xee140000 0 0x2000>; + interrupts = ; + clocks = <&cpg CPG_MOD 706>, + <&cpg CPG_CORE R8A779G0_CLK_SD0H>; + clock-names = "core", "clkh"; + power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>; + resets = <&cpg 706>; + max-frequency = <200000000>; + iommus = <&ipmmu_ds0 32>; + status = "disabled"; + }; + + rpc: spi@ee200000 { + compatible = "renesas,r8a779g0-rpc-if", + "renesas,rcar-gen4-rpc-if"; + reg = <0 0xee200000 0 0x200>, + <0 0x08000000 0 0x04000000>, + <0 0xee208000 0 0x100>; + reg-names = "regs", "dirmap", "wbuf"; + interrupts = ; + clocks = <&cpg CPG_MOD 629>; + power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>; + resets = <&cpg 629>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + ipmmu_rt0: iommu@ee480000 { compatible = "renesas,ipmmu-r8a779g0", "renesas,rcar-gen4-ipmmu-vmsa"; @@ -1886,37 +1923,6 @@ #iommu-cells = <1>; }; - mmc0: mmc@ee140000 { - compatible = "renesas,sdhi-r8a779g0", - "renesas,rcar-gen4-sdhi"; - reg = <0 0xee140000 0 0x2000>; - interrupts = ; - clocks = <&cpg CPG_MOD 706>, - <&cpg CPG_CORE R8A779G0_CLK_SD0H>; - clock-names = "core", "clkh"; - power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>; - resets = <&cpg 706>; - max-frequency = <200000000>; - iommus = <&ipmmu_ds0 32>; - status = "disabled"; - }; - - rpc: spi@ee200000 { - compatible = "renesas,r8a779g0-rpc-if", - "renesas,rcar-gen4-rpc-if"; - reg = <0 0xee200000 0 0x200>, - <0 0x08000000 0 0x04000000>, - <0 0xee208000 0 0x100>; - reg-names = "regs", "dirmap", "wbuf"; - interrupts = ; - clocks = <&cpg CPG_MOD 629>; - power-domains = <&sysc R8A779G0_PD_ALWAYS_ON>; - resets = <&cpg 629>; - #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; - }; - gic: interrupt-controller@f1000000 { compatible = "arm,gic-v3"; #interrupt-cells = <3>; diff --git a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi index 2ab231572d95f..b3f83d0ebcbb5 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi @@ -109,7 +109,13 @@ , , , - ; + , + , + , + , + , + , + ; interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", "irq4", "irq5", "irq6", "irq7", @@ -121,7 +127,9 @@ "tint20", "tint21", "tint22", "tint23", "tint24", "tint25", "tint26", "tint27", "tint28", "tint29", "tint30", "tint31", - "bus-err"; + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; clocks = <&cpg CPG_MOD R9A07G043_IA55_CLK>, <&cpg CPG_MOD R9A07G043_IA55_PCLK>; clock-names = "clk", "pclk"; diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi index 66f68fc2b2411..081d8f49db879 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi @@ -905,7 +905,27 @@ , , , - ; + , + , + , + , + , + , + , + ; + interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", + "irq4", "irq5", "irq6", "irq7", + "tint0", "tint1", "tint2", "tint3", + "tint4", "tint5", "tint6", "tint7", + "tint8", "tint9", "tint10", "tint11", + "tint12", "tint13", "tint14", "tint15", + "tint16", "tint17", "tint18", "tint19", + "tint20", "tint21", "tint22", "tint23", + "tint24", "tint25", "tint26", "tint27", + "tint28", "tint29", "tint30", "tint31", + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; clocks = <&cpg CPG_MOD R9A07G044_IA55_CLK>, <&cpg CPG_MOD R9A07G044_IA55_PCLK>; clock-names = "clk", "pclk"; diff --git a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi index 1f1d481dc7830..0d327464d2baf 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi @@ -912,7 +912,27 @@ , , , - ; + , + , + , + , + , + , + , + ; + interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", + "irq4", "irq5", "irq6", "irq7", + "tint0", "tint1", "tint2", "tint3", + "tint4", "tint5", "tint6", "tint7", + "tint8", "tint9", "tint10", "tint11", + "tint12", "tint13", "tint14", "tint15", + "tint16", "tint17", "tint18", "tint19", + "tint20", "tint21", "tint22", "tint23", + "tint24", "tint25", "tint26", "tint27", + "tint28", "tint29", "tint30", "tint31", + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; clocks = <&cpg CPG_MOD R9A07G054_IA55_CLK>, <&cpg CPG_MOD R9A07G054_IA55_PCLK>; clock-names = "clk", "pclk"; diff --git a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi index 5facfad961583..6315ffa6c1bb9 100644 --- a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi @@ -152,7 +152,10 @@ , , , - ; + , + , + , + ; interrupt-names = "nmi", "irq0", "irq1", "irq2", "irq3", "irq4", "irq5", "irq6", "irq7", @@ -164,7 +167,8 @@ "tint20", "tint21", "tint22", "tint23", "tint24", "tint25", "tint26", "tint27", "tint28", "tint29", "tint30", "tint31", - "bus-err"; + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0"; clocks = <&cpg CPG_MOD R9A08G045_IA55_CLK>, <&cpg CPG_MOD R9A08G045_IA55_PCLK>; clock-names = "clk", "pclk"; diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi index f062d4ad78b79..d33ab4c887878 100644 --- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi @@ -193,12 +193,14 @@ #endif &pinctrl { +#if SW_CONFIG3 == SW_ON eth0-phy-irq-hog { gpio-hog; gpios = ; input; line-name = "eth0-phy-irq"; }; +#endif eth0_pins: eth0 { txc { @@ -234,12 +236,14 @@ }; }; +#if SW_CONFIG3 == SW_ON eth1-phy-irq-hog { gpio-hog; gpios = ; input; line-name = "eth1-phy-irq"; }; +#endif eth1_pins: eth1 { txc { diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 7b4c15c4a9c31..b6f045069ee2f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -744,11 +744,20 @@ status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + hdmi_in_vop: endpoint { remote-endpoint = <&vop_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 054c6a4d1a45f..294eb2de263de 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -779,7 +779,6 @@ }; &pcie0 { - bus-scan-delay-ms = <1000>; ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index c08e69391c015..2484ad2bd86fc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -416,16 +416,22 @@ gpio1830-supply = <&vcc_1v8>; }; -&pmu_io_domains { - status = "okay"; - pmu1830-supply = <&vcc_1v8>; -}; - -&pwm2 { - status = "okay"; +&pcie_clkreqn_cpm { + rockchip,pins = + <2 RK_PD2 RK_FUNC_GPIO &pcfg_pull_up>; }; &pinctrl { + pinctrl-names = "default"; + pinctrl-0 = <&q7_thermal_pin>; + + gpios { + q7_thermal_pin: q7-thermal-pin { + rockchip,pins = + <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + i2c8 { i2c8_xfer_a: i2c8-xfer { rockchip,pins = @@ -458,11 +464,20 @@ usb3 { usb3_id: usb3-id { rockchip,pins = - <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; + <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_up>; }; }; }; +&pmu_io_domains { + status = "okay"; + pmu1830-supply = <&vcc_1v8>; +}; + +&pwm2 { + status = "okay"; +}; + &sdhci { /* * Signal integrity isn't great at 200MHz but 100MHz has proven stable diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 6e12c5a920cab..fe818a2700aa7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1956,6 +1956,7 @@ hdmi: hdmi@ff940000 { compatible = "rockchip,rk3399-dw-hdmi"; reg = <0x0 0xff940000 0x0 0x20000>; + reg-io-width = <4>; interrupts = ; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_SFR>, @@ -1964,13 +1965,16 @@ <&cru PLL_VPLL>; clock-names = "iahb", "isfr", "cec", "grf", "ref"; power-domains = <&power RK3399_PD_HDCP>; - reg-io-width = <4>; rockchip,grf = <&grf>; #sound-dai-cells = <0>; status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; @@ -1983,6 +1987,10 @@ remote-endpoint = <&vopl_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index f9127ddfbb7df..dc5892d25c100 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -416,6 +416,8 @@ vccio_sd: LDO_REG5 { regulator-name = "vccio_sd"; + regulator-always-on; + regulator-boot-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; @@ -525,9 +527,9 @@ #address-cells = <1>; #size-cells = <0>; - switch@0 { + switch@1f { compatible = "mediatek,mt7531"; - reg = <0>; + reg = <0x1f>; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi index c19c0f1b3778f..92f96ec01385d 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi @@ -597,6 +597,7 @@ compatible = "rockchip,rk3568-vpu"; reg = <0x0 0xfdea0000 0x0 0x800>; interrupts = ; + interrupt-names = "vdpu"; clocks = <&cru ACLK_VPU>, <&cru HCLK_VPU>; clock-names = "aclk", "hclk"; iommus = <&vdpu_mmu>; @@ -1123,7 +1124,7 @@ dmas = <&dmac1 4>, <&dmac1 5>; dma-names = "tx", "rx"; resets = <&cru SRST_M_I2S2_2CH>; - reset-names = "m"; + reset-names = "tx-m"; rockchip,grf = <&grf>; pinctrl-names = "default"; pinctrl-0 = <&i2s2m0_sclktx diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi index cce1c8e835877..94ecb9b4f98f8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi @@ -216,9 +216,9 @@ pinctrl-0 = <&i2c7m0_xfer>; status = "okay"; - es8316: audio-codec@11 { + es8316: audio-codec@10 { compatible = "everest,es8316"; - reg = <0x11>; + reg = <0x10>; assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; assigned-clock-rates = <12288000>; clocks = <&cru I2S0_8CH_MCLKOUT>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts index 3e660ff6cd5ff..e74871491ef56 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts @@ -486,6 +486,7 @@ pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, <&rk806_dvs2_null>, <&rk806_dvs3_null>; spi-max-frequency = <1000000>; + system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; @@ -507,7 +508,7 @@ #gpio-cells = <2>; rk806_dvs1_null: dvs1-null-pins { - pins = "gpio_pwrctrl2"; + pins = "gpio_pwrctrl1"; function = "pin_fun0"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi index 36b1b7acfe6a1..82350ddb262f2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi @@ -1704,7 +1704,6 @@ dmas = <&dmac1 0>, <&dmac1 1>; dma-names = "tx", "rx"; power-domains = <&power RK3588_PD_AUDIO>; - rockchip,trcm-sync-tx-only; pinctrl-names = "default"; pinctrl-0 = <&i2s2m1_lrck &i2s2m1_sclk @@ -1725,7 +1724,6 @@ dmas = <&dmac1 2>, <&dmac1 3>; dma-names = "tx", "rx"; power-domains = <&power RK3588_PD_AUDIO>; - rockchip,trcm-sync-tx-only; pinctrl-names = "default"; pinctrl-0 = <&i2s3_lrck &i2s3_sclk diff --git a/arch/arm64/boot/dts/ti/Makefile b/arch/arm64/boot/dts/ti/Makefile index 52c1dc9103087..08ce34d21d5d0 100644 --- a/arch/arm64/boot/dts/ti/Makefile +++ b/arch/arm64/boot/dts/ti/Makefile @@ -57,6 +57,7 @@ dtb-$(CONFIG_ARCH_K3) += k3-am654-base-board.dtb dtb-$(CONFIG_ARCH_K3) += k3-am654-gp-evm.dtb dtb-$(CONFIG_ARCH_K3) += k3-am654-evm.dtb dtb-$(CONFIG_ARCH_K3) += k3-am654-idk.dtb +dtb-$(CONFIG_ARCH_K3) += k3-am654-base-board-rocktech-rk101-panel.dtbo # Boards with J7200 SoC k3-j7200-evm-dtbs := k3-j7200-common-proc-board.dtb k3-j7200-evm-quad-port-eth-exp.dtbo diff --git a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi index 464b7565d085d..6d07b65a3614e 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi @@ -640,6 +640,8 @@ interrupt-names = "host", "peripheral"; maximum-speed = "high-speed"; dr_mode = "otg"; + snps,usb2-gadget-lpm-disable; + snps,usb2-lpm-disable; }; }; @@ -663,6 +665,8 @@ interrupt-names = "host", "peripheral"; maximum-speed = "high-speed"; dr_mode = "otg"; + snps,usb2-gadget-lpm-disable; + snps,usb2-lpm-disable; }; }; @@ -779,9 +783,10 @@ <0x00 0x30207000 0x00 0x1000>, /* ovr1 */ <0x00 0x30208000 0x00 0x1000>, /* ovr2 */ <0x00 0x3020a000 0x00 0x1000>, /* vp1: Used for OLDI */ - <0x00 0x3020b000 0x00 0x1000>; /* vp2: Used as DPI Out */ + <0x00 0x3020b000 0x00 0x1000>, /* vp2: Used as DPI Out */ + <0x00 0x30201000 0x00 0x1000>; /* common1 */ reg-names = "common", "vidl1", "vid", - "ovr1", "ovr2", "vp1", "vp2"; + "ovr1", "ovr2", "vp1", "vp2", "common1"; power-domains = <&k3_pds 186 TI_SCI_PD_EXCLUSIVE>; clocks = <&k3_clks 186 6>, <&dss_vp1_clk>, diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi index 6a06724b6d168..6321eccccd50f 100644 --- a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi @@ -60,7 +60,7 @@ memory@80000000 { device_type = "memory"; - reg = <0x00000000 0x80000000 0x00000000 0x40000000>; /* 1G RAM */ + reg = <0x00000000 0x80000000 0x00000000 0x80000000>; /* 2G RAM */ }; opp-table { diff --git a/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi index c4b0b91d70cf3..14eb9ba836d32 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p-mcu.dtsi @@ -187,6 +187,8 @@ ranges = <0x79000000 0x00 0x79000000 0x8000>, <0x79020000 0x00 0x79020000 0x8000>; power-domains = <&k3_pds 7 TI_SCI_PD_EXCLUSIVE>; + status = "disabled"; + mcu_r5fss0_core0: r5f@79000000 { compatible = "ti,am62-r5f"; reg = <0x79000000 0x00008000>, diff --git a/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi index 19f42b39394ee..10a7059b2d9b5 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p-wakeup.dtsi @@ -78,6 +78,7 @@ ranges = <0x78000000 0x00 0x78000000 0x8000>, <0x78100000 0x00 0x78100000 0x8000>; power-domains = <&k3_pds 119 TI_SCI_PD_EXCLUSIVE>; + status = "disabled"; wkup_r5fss0_core0: r5f@78000000 { compatible = "ti,am62-r5f"; diff --git a/arch/arm64/boot/dts/ti/k3-am62p.dtsi b/arch/arm64/boot/dts/ti/k3-am62p.dtsi index 84ffe7b9dcaf3..4f22b5d9fb9f0 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p.dtsi @@ -71,7 +71,7 @@ <0x00 0x43600000 0x00 0x43600000 0x00 0x00010000>, /* SA3 sproxy data */ <0x00 0x44043000 0x00 0x44043000 0x00 0x00000fe0>, /* TI SCI DEBUG */ <0x00 0x44860000 0x00 0x44860000 0x00 0x00040000>, /* SA3 sproxy config */ - <0x00 0x48000000 0x00 0x48000000 0x00 0x06400000>, /* DMSS */ + <0x00 0x48000000 0x00 0x48000000 0x00 0x06408000>, /* DMSS */ <0x00 0x60000000 0x00 0x60000000 0x00 0x08000000>, /* FSS0 DAT1 */ <0x00 0x70000000 0x00 0x70000000 0x00 0x00010000>, /* OCSRAM */ <0x01 0x00000000 0x01 0x00000000 0x00 0x00310000>, /* A53 PERIPHBASE */ diff --git a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts index 1773c05f752cd..60868862e3b43 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts @@ -445,6 +445,10 @@ }; &cpsw3g_mdio { + pinctrl-names = "default"; + pinctrl-0 = <&main_mdio1_pins_default>; + status = "okay"; + cpsw3g_phy0: ethernet-phy@0 { reg = <0>; ti,rx-internal-delay = ; diff --git a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi index e348114f42e01..ba624ef72f5b4 100644 --- a/arch/arm64/boot/dts/ti/k3-am64-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am64-main.dtsi @@ -633,6 +633,9 @@ ti,otap-del-sel-mmc-hs = <0x0>; ti,otap-del-sel-ddr52 = <0x6>; ti,otap-del-sel-hs200 = <0x7>; + ti,itap-del-sel-legacy = <0x10>; + ti,itap-del-sel-mmc-hs = <0xa>; + ti,itap-del-sel-ddr52 = <0x3>; status = "disabled"; }; @@ -645,12 +648,16 @@ clock-names = "clk_ahb", "clk_xin"; ti,trm-icp = <0x2>; ti,otap-del-sel-legacy = <0x0>; - ti,otap-del-sel-sd-hs = <0xf>; + ti,otap-del-sel-sd-hs = <0x0>; ti,otap-del-sel-sdr12 = <0xf>; ti,otap-del-sel-sdr25 = <0xf>; ti,otap-del-sel-sdr50 = <0xc>; ti,otap-del-sel-sdr104 = <0x6>; ti,otap-del-sel-ddr50 = <0x9>; + ti,itap-del-sel-legacy = <0x0>; + ti,itap-del-sel-sd-hs = <0x0>; + ti,itap-del-sel-sdr12 = <0x0>; + ti,itap-del-sel-sdr25 = <0x0>; ti,clkbuf-sel = <0x7>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi index fcea544656360..5b2d4365b9111 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-main.dtsi @@ -1019,9 +1019,10 @@ <0x0 0x04a07000 0x0 0x1000>, /* ovr1 */ <0x0 0x04a08000 0x0 0x1000>, /* ovr2 */ <0x0 0x04a0a000 0x0 0x1000>, /* vp1 */ - <0x0 0x04a0b000 0x0 0x1000>; /* vp2 */ + <0x0 0x04a0b000 0x0 0x1000>, /* vp2 */ + <0x0 0x04a01000 0x0 0x1000>; /* common1 */ reg-names = "common", "vidl1", "vid", - "ovr1", "ovr2", "vp1", "vp2"; + "ovr1", "ovr2", "vp1", "vp2", "common1"; ti,am65x-oldi-io-ctrl = <&dss_oldi_io_ctrl>; diff --git a/arch/arm64/boot/dts/ti/k3-am69-sk.dts b/arch/arm64/boot/dts/ti/k3-am69-sk.dts index 8da5915798688..c8fb9dfb89723 100644 --- a/arch/arm64/boot/dts/ti/k3-am69-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-am69-sk.dts @@ -646,7 +646,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pmic_irq_pins_default>; interrupt-parent = <&wkup_gpio0>; - interrupts = <39 IRQ_TYPE_EDGE_FALLING>; + interrupts = <83 IRQ_TYPE_EDGE_FALLING>; gpio-controller; #gpio-cells = <2>; ti,primary-pmic; @@ -918,13 +918,9 @@ pinctrl-names = "default"; pinctrl-0 = <&dss_vout0_pins_default>; assigned-clocks = <&k3_clks 218 2>, - <&k3_clks 218 5>, - <&k3_clks 218 14>, - <&k3_clks 218 18>; + <&k3_clks 218 5>; assigned-clock-parents = <&k3_clks 218 3>, - <&k3_clks 218 7>, - <&k3_clks 218 16>, - <&k3_clks 218 22>; + <&k3_clks 218 7>; }; &serdes_wiz4 { diff --git a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts index cee2b4b0eb87d..7a0c599f2b1c3 100644 --- a/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j7200-common-proc-board.dts @@ -91,24 +91,25 @@ }; &wkup_pmx0 { +}; + +&wkup_pmx2 { mcu_uart0_pins_default: mcu-uart0-default-pins { pinctrl-single,pins = < - J721E_WKUP_IOPAD(0xf4, PIN_INPUT, 0) /* (D20) MCU_UART0_RXD */ - J721E_WKUP_IOPAD(0xf0, PIN_OUTPUT, 0) /* (D19) MCU_UART0_TXD */ - J721E_WKUP_IOPAD(0xf8, PIN_INPUT, 0) /* (E20) MCU_UART0_CTSn */ - J721E_WKUP_IOPAD(0xfc, PIN_OUTPUT, 0) /* (E21) MCU_UART0_RTSn */ + J721E_WKUP_IOPAD(0x90, PIN_INPUT, 0) /* (E20) MCU_UART0_CTSn */ + J721E_WKUP_IOPAD(0x94, PIN_OUTPUT, 0) /* (E21) MCU_UART0_RTSn */ + J721E_WKUP_IOPAD(0x8c, PIN_INPUT, 0) /* (D20) MCU_UART0_RXD */ + J721E_WKUP_IOPAD(0x88, PIN_OUTPUT, 0) /* (D19) MCU_UART0_TXD */ >; }; wkup_uart0_pins_default: wkup-uart0-default-pins { pinctrl-single,pins = < - J721E_WKUP_IOPAD(0xb0, PIN_INPUT, 0) /* (B14) WKUP_UART0_RXD */ - J721E_WKUP_IOPAD(0xb4, PIN_OUTPUT, 0) /* (A14) WKUP_UART0_TXD */ + J721E_WKUP_IOPAD(0x48, PIN_INPUT, 0) /* (B14) WKUP_UART0_RXD */ + J721E_WKUP_IOPAD(0x4c, PIN_OUTPUT, 0) /* (A14) WKUP_UART0_TXD */ >; }; -}; -&wkup_pmx2 { mcu_cpsw_pins_default: mcu-cpsw-default-pins { pinctrl-single,pins = < J721E_WKUP_IOPAD(0x0000, PIN_OUTPUT, 0) /* MCU_RGMII1_TX_CTL */ @@ -210,7 +211,6 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&mcu_uart0_pins_default>; - clock-frequency = <96000000>; }; &main_uart0 { diff --git a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi index a74912d9e4daf..c463e23ced04e 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721e-mcu-wakeup.dtsi @@ -353,9 +353,9 @@ hbmc_mux: mux-controller@47000004 { compatible = "reg-mux"; - reg = <0x00 0x47000004 0x00 0x2>; + reg = <0x00 0x47000004 0x00 0x4>; #mux-control-cells = <1>; - mux-reg-masks = <0x4 0x2>; /* HBMC select */ + mux-reg-masks = <0x0 0x2>; /* HBMC select */ }; hbmc: hyperbus@47034000 { diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts index 188dfe291a32b..658764f7d5443 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts @@ -574,7 +574,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pmic_irq_pins_default>; interrupt-parent = <&wkup_gpio0>; - interrupts = <9 IRQ_TYPE_EDGE_FALLING>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; gpio-controller; #gpio-cells = <2>; ti,primary-pmic; @@ -651,7 +651,7 @@ reg = <0x4c>; system-power-controller; interrupt-parent = <&wkup_gpio0>; - interrupts = <9 IRQ_TYPE_EDGE_FALLING>; + interrupts = <7 IRQ_TYPE_EDGE_FALLING>; gpio-controller; #gpio-cells = <2>; buck1234-supply = <&vsys_3v3>; diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts index c6b85bbf9a179..1ba1f53c72d03 100644 --- a/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts +++ b/arch/arm64/boot/dts/ti/k3-j721s2-common-proc-board.dts @@ -190,8 +190,6 @@ &wkup_pmx2 { wkup_uart0_pins_default: wkup-uart0-default-pins { pinctrl-single,pins = < - J721S2_WKUP_IOPAD(0x070, PIN_INPUT, 0) /* (E25) WKUP_GPIO0_6.WKUP_UART0_CTSn */ - J721S2_WKUP_IOPAD(0x074, PIN_OUTPUT, 0) /* (F28) WKUP_GPIO0_7.WKUP_UART0_RTSn */ J721S2_WKUP_IOPAD(0x048, PIN_INPUT, 0) /* (D28) WKUP_UART0_RXD */ J721S2_WKUP_IOPAD(0x04c, PIN_OUTPUT, 0) /* (D27) WKUP_UART0_TXD */ >; diff --git a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi index 80aa33c58a452..a47cb557dd956 100644 --- a/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j721s2-mcu-wakeup.dtsi @@ -663,7 +663,7 @@ compatible = "ti,j7200-vtm"; reg = <0x00 0x42040000 0x0 0x350>, <0x00 0x42050000 0x0 0x350>; - power-domains = <&k3_pds 154 TI_SCI_PD_SHARED>; + power-domains = <&k3_pds 180 TI_SCI_PD_SHARED>; #thermal-sensor-cells = <1>; }; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts b/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts index f34b92acc56d8..33795a0bc69cf 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts +++ b/arch/arm64/boot/dts/ti/k3-j784s4-evm.dts @@ -335,8 +335,6 @@ wkup_uart0_pins_default: wkup-uart0-default-pins { bootph-all; pinctrl-single,pins = < - J721S2_WKUP_IOPAD(0x070, PIN_INPUT, 0) /* (L37) WKUP_GPIO0_6.WKUP_UART0_CTSn */ - J721S2_WKUP_IOPAD(0x074, PIN_INPUT, 0) /* (L36) WKUP_GPIO0_7.WKUP_UART0_RTSn */ J721S2_WKUP_IOPAD(0x048, PIN_INPUT, 0) /* (K35) WKUP_UART0_RXD */ J721S2_WKUP_IOPAD(0x04c, PIN_INPUT, 0) /* (K34) WKUP_UART0_TXD */ >; diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi index f2b720ed1e4f2..56c8eaad6324b 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-main.dtsi @@ -52,12 +52,12 @@ compatible = "reg-mux"; reg = <0x00004080 0x30>; #mux-control-cells = <1>; - mux-reg-masks = <0x4080 0x3>, <0x4084 0x3>, /* SERDES0 lane0/1 select */ - <0x4088 0x3>, <0x408c 0x3>, /* SERDES0 lane2/3 select */ - <0x4090 0x3>, <0x4094 0x3>, /* SERDES1 lane0/1 select */ - <0x4098 0x3>, <0x409c 0x3>, /* SERDES1 lane2/3 select */ - <0x40a0 0x3>, <0x40a4 0x3>, /* SERDES2 lane0/1 select */ - <0x40a8 0x3>, <0x40ac 0x3>; /* SERDES2 lane2/3 select */ + mux-reg-masks = <0x0 0x3>, <0x4 0x3>, /* SERDES0 lane0/1 select */ + <0x8 0x3>, <0xc 0x3>, /* SERDES0 lane2/3 select */ + <0x10 0x3>, <0x14 0x3>, /* SERDES1 lane0/1 select */ + <0x18 0x3>, <0x1c 0x3>, /* SERDES1 lane2/3 select */ + <0x20 0x3>, <0x24 0x3>, /* SERDES2 lane0/1 select */ + <0x28 0x3>, <0x2c 0x3>; /* SERDES2 lane2/3 select */ idle-states = , , , diff --git a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi index 3902a921d7e58..337122c3f4020 100644 --- a/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi @@ -628,7 +628,7 @@ compatible = "ti,j7200-vtm"; reg = <0x00 0x42040000 0x00 0x350>, <0x00 0x42050000 0x00 0x350>; - power-domains = <&k3_pds 154 TI_SCI_PD_SHARED>; + power-domains = <&k3_pds 243 TI_SCI_PD_SHARED>; #thermal-sensor-cells = <1>; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index e6cf3e5d63c30..df6049a879683 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -632,6 +632,7 @@ CONFIG_GPIO_SYSCON=y CONFIG_GPIO_UNIPHIER=y CONFIG_GPIO_VISCONTI=y CONFIG_GPIO_WCD934X=m +CONFIG_GPIO_VF610=y CONFIG_GPIO_XGENE=y CONFIG_GPIO_XGENE_SB=y CONFIG_GPIO_MAX732X=y @@ -1559,6 +1560,7 @@ CONFIG_INTERCONNECT_QCOM_SC8180X=y CONFIG_INTERCONNECT_QCOM_SC8280XP=y CONFIG_INTERCONNECT_QCOM_SDM845=y CONFIG_INTERCONNECT_QCOM_SDX75=y +CONFIG_INTERCONNECT_QCOM_SM6115=y CONFIG_INTERCONNECT_QCOM_SM8150=m CONFIG_INTERCONNECT_QCOM_SM8250=m CONFIG_INTERCONNECT_QCOM_SM8350=m diff --git a/arch/arm64/include/asm/asm-bug.h b/arch/arm64/include/asm/asm-bug.h index c762038ba4009..6e73809f6492a 100644 --- a/arch/arm64/include/asm/asm-bug.h +++ b/arch/arm64/include/asm/asm-bug.h @@ -28,6 +28,7 @@ 14470: .long 14471f - .; \ _BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ .short flags; \ + .align 2; \ .popsection; \ 14471: #else diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 0a7186a93882d..d4d7451c2c129 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -5,7 +5,6 @@ #ifndef __ASM_IRQFLAGS_H #define __ASM_IRQFLAGS_H -#include #include #include #include diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index c3b19b376c867..5396176d23b7e 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -1036,18 +1036,18 @@ * Permission Indirection Extension (PIE) permission encodings. * Encodings with the _O suffix, have overlays applied (Permission Overlay Extension). */ -#define PIE_NONE_O 0x0 -#define PIE_R_O 0x1 -#define PIE_X_O 0x2 -#define PIE_RX_O 0x3 -#define PIE_RW_O 0x5 -#define PIE_RWnX_O 0x6 -#define PIE_RWX_O 0x7 -#define PIE_R 0x8 -#define PIE_GCS 0x9 -#define PIE_RX 0xa -#define PIE_RW 0xc -#define PIE_RWX 0xe +#define PIE_NONE_O UL(0x0) +#define PIE_R_O UL(0x1) +#define PIE_X_O UL(0x2) +#define PIE_RX_O UL(0x3) +#define PIE_RW_O UL(0x5) +#define PIE_RWnX_O UL(0x6) +#define PIE_RWX_O UL(0x7) +#define PIE_R UL(0x8) +#define PIE_GCS UL(0x9) +#define PIE_RX UL(0xa) +#define PIE_RW UL(0xc) +#define PIE_RWX UL(0xe) #define PIRx_ELx_PERM(idx, perm) ((perm) << ((idx) * 4)) diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 1deb5d789c2e2..bfeb54f3a971f 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -161,12 +161,18 @@ static inline unsigned long get_trans_granule(void) #define MAX_TLBI_RANGE_PAGES __TLBI_RANGE_PAGES(31, 3) /* - * Generate 'num' values from -1 to 30 with -1 rejected by the - * __flush_tlb_range() loop below. + * Generate 'num' values from -1 to 31 with -1 rejected by the + * __flush_tlb_range() loop below. Its return value is only + * significant for a maximum of MAX_TLBI_RANGE_PAGES pages. If + * 'pages' is more than that, you must iterate over the overall + * range. */ -#define TLBI_RANGE_MASK GENMASK_ULL(4, 0) -#define __TLBI_RANGE_NUM(pages, scale) \ - ((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1) +#define __TLBI_RANGE_NUM(pages, scale) \ + ({ \ + int __pages = min((pages), \ + __TLBI_RANGE_PAGES(31, (scale))); \ + (__pages >> (5 * (scale) + 1)) - 1; \ + }) /* * TLB Invalidation @@ -379,10 +385,6 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) * 3. If there is 1 page remaining, flush it through non-range operations. Range * operations can only span an even number of pages. We save this for last to * ensure 64KB start alignment is maintained for the LPA2 case. - * - * Note that certain ranges can be represented by either num = 31 and - * scale or num = 0 and scale + 1. The loop below favours the latter - * since num is limited to 30 by the __TLBI_RANGE_NUM() macro. */ #define __flush_tlb_range_op(op, start, pages, stride, \ asid, tlb_level, tlbi_user, lpa2) \ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index f27acca550d55..7ea1eaa744d1f 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1518,6 +1518,27 @@ static void fpsimd_save_kernel_state(struct task_struct *task) task->thread.kernel_fpsimd_cpu = smp_processor_id(); } +/* + * Invalidate any task's FPSIMD state that is present on this cpu. + * The FPSIMD context should be acquired with get_cpu_fpsimd_context() + * before calling this function. + */ +static void fpsimd_flush_cpu_state(void) +{ + WARN_ON(!system_supports_fpsimd()); + __this_cpu_write(fpsimd_last_state.st, NULL); + + /* + * Leaving streaming mode enabled will cause issues for any kernel + * NEON and leaving streaming mode or ZA enabled may increase power + * consumption. + */ + if (system_supports_sme()) + sme_smstop(); + + set_thread_flag(TIF_FOREIGN_FPSTATE); +} + void fpsimd_thread_switch(struct task_struct *next) { bool wrong_task, wrong_cpu; @@ -1535,7 +1556,7 @@ void fpsimd_thread_switch(struct task_struct *next) if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) { fpsimd_load_kernel_state(next); - set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE); + fpsimd_flush_cpu_state(); } else { /* * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's @@ -1824,27 +1845,6 @@ void fpsimd_flush_task_state(struct task_struct *t) barrier(); } -/* - * Invalidate any task's FPSIMD state that is present on this cpu. - * The FPSIMD context should be acquired with get_cpu_fpsimd_context() - * before calling this function. - */ -static void fpsimd_flush_cpu_state(void) -{ - WARN_ON(!system_supports_fpsimd()); - __this_cpu_write(fpsimd_last_state.st, NULL); - - /* - * Leaving streaming mode enabled will cause issues for any kernel - * NEON and leaving streaming mode or ZA enabled may increase power - * consumption. - */ - if (system_supports_sme()) - sme_smstop(); - - set_thread_flag(TIF_FOREIGN_FPSTATE); -} - /* * Save the FPSIMD state to memory and invalidate cpu view. * This function must be called with preemption disabled. @@ -1923,7 +1923,7 @@ void kernel_neon_begin(void) put_cpu_fpsimd_context(); } -EXPORT_SYMBOL_GPL(kernel_neon_begin); +EXPORT_SYMBOL(kernel_neon_begin); /* * kernel_neon_end(): give the CPU FPSIMD registers back to the current task @@ -1950,7 +1950,7 @@ void kernel_neon_end(void) else clear_thread_flag(TIF_KERNEL_FPSTATE); } -EXPORT_SYMBOL_GPL(kernel_neon_end); +EXPORT_SYMBOL(kernel_neon_end); #ifdef CONFIG_EFI diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index cab7f91949d8f..a92905e6d43ad 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -569,6 +569,11 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) adr_l x1, __hyp_text_end adr_l x2, dcache_clean_poc blr x2 + + mov_q x0, INIT_SCTLR_EL2_MMU_OFF + pre_disable_mmu_workaround + msr sctlr_el2, x0 + isb 0: mov_q x0, HCR_HOST_NVHE_FLAGS msr hcr_el2, x0 diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index e30fd9e32ef3a..9d2c120f378ae 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -308,7 +308,8 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) match_options(buf); for (i = 0; parse_aliases && i < ARRAY_SIZE(aliases); i++) - if (!memcmp(buf, aliases[i].alias, len + 1)) + if (len == strlen(aliases[i].alias) && + !memcmp(buf, aliases[i].alias, len + 1)) __parse_cmdline(aliases[i].feature, false); } while (1); } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index e3bef38fc2e2d..964d0446dae9f 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -729,7 +729,6 @@ static void sve_init_header_from_task(struct user_sve_header *header, { unsigned int vq; bool active; - bool fpsimd_only; enum vec_type task_type; memset(header, 0, sizeof(*header)); @@ -745,12 +744,10 @@ static void sve_init_header_from_task(struct user_sve_header *header, case ARM64_VEC_SVE: if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; - fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE); break; case ARM64_VEC_SME: if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; - fpsimd_only = false; break; default: WARN_ON_ONCE(1); @@ -758,7 +755,7 @@ static void sve_init_header_from_task(struct user_sve_header *header, } if (active) { - if (fpsimd_only) { + if (target->thread.fp_type == FP_STATE_FPSIMD) { header->flags |= SVE_PT_REGS_FPSIMD; } else { header->flags |= SVE_PT_REGS_SVE; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a25265aca4324..d8dd6b66f0b50 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -191,6 +191,23 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) } +static void kvm_destroy_mpidr_data(struct kvm *kvm) +{ + struct kvm_mpidr_data *data; + + mutex_lock(&kvm->arch.config_lock); + + data = rcu_dereference_protected(kvm->arch.mpidr_data, + lockdep_is_held(&kvm->arch.config_lock)); + if (data) { + rcu_assign_pointer(kvm->arch.mpidr_data, NULL); + synchronize_rcu(); + kfree(data); + } + + mutex_unlock(&kvm->arch.config_lock); +} + /** * kvm_arch_destroy_vm - destroy the VM data structure * @kvm: pointer to the KVM struct @@ -205,7 +222,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm) if (is_protected_kvm_enabled()) pkvm_destroy_hyp_vm(kvm); - kfree(kvm->arch.mpidr_data); + kvm_destroy_mpidr_data(kvm); + kvm_destroy_vcpus(kvm); kvm_unshare_hyp(kvm, kvm + 1); @@ -390,6 +408,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; + /* + * This vCPU may have been created after mpidr_data was initialized. + * Throw out the pre-computed mappings if that is the case which forces + * KVM to fall back to iteratively searching the vCPUs. + */ + kvm_destroy_mpidr_data(vcpu->kvm); + err = kvm_vgic_vcpu_init(vcpu); if (err) return err; @@ -589,7 +614,8 @@ static void kvm_init_mpidr_data(struct kvm *kvm) mutex_lock(&kvm->arch.config_lock); - if (kvm->arch.mpidr_data || atomic_read(&kvm->online_vcpus) == 1) + if (rcu_access_pointer(kvm->arch.mpidr_data) || + atomic_read(&kvm->online_vcpus) == 1) goto out; kvm_for_each_vcpu(c, vcpu, kvm) { @@ -626,7 +652,7 @@ static void kvm_init_mpidr_data(struct kvm *kvm) data->cmpidr_to_idx[index] = c; } - kvm->arch.mpidr_data = data; + rcu_assign_pointer(kvm->arch.mpidr_data, data); out: mutex_unlock(&kvm->arch.config_lock); } @@ -2459,21 +2485,27 @@ static int __init init_hyp_mode(void) struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) { - struct kvm_vcpu *vcpu; + struct kvm_vcpu *vcpu = NULL; + struct kvm_mpidr_data *data; unsigned long i; mpidr &= MPIDR_HWID_BITMASK; - if (kvm->arch.mpidr_data) { - u16 idx = kvm_mpidr_index(kvm->arch.mpidr_data, mpidr); + rcu_read_lock(); + data = rcu_dereference(kvm->arch.mpidr_data); - vcpu = kvm_get_vcpu(kvm, - kvm->arch.mpidr_data->cmpidr_to_idx[idx]); + if (data) { + u16 idx = kvm_mpidr_index(data, mpidr); + + vcpu = kvm_get_vcpu(kvm, data->cmpidr_to_idx[idx]); if (mpidr != kvm_vcpu_get_mpidr_aff(vcpu)) vcpu = NULL; + } + rcu_read_unlock(); + + if (vcpu) return vcpu; - } kvm_for_each_vcpu(i, vcpu, kvm) { if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu)) diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index aaf1d49397392..7a6e47e2c6f0e 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -251,6 +251,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) case PSR_AA32_MODE_SVC: case PSR_AA32_MODE_ABT: case PSR_AA32_MODE_UND: + case PSR_AA32_MODE_SYS: if (!vcpu_el1_is_32bit(vcpu)) return -EINVAL; break; @@ -276,7 +277,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { int i, nr_reg; - switch (*vcpu_cpsr(vcpu)) { + switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) { /* * Either we are dealing with user mode, and only the * first 15 registers (+ PC) must be narrowed to 32bit. diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c index f98cbe2626a1c..19efb41aab805 100644 --- a/arch/arm64/kvm/hyp/aarch32.c +++ b/arch/arm64/kvm/hyp/aarch32.c @@ -50,9 +50,23 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu) u32 cpsr_cond; int cond; - /* Top two bits non-zero? Unconditional. */ - if (kvm_vcpu_get_esr(vcpu) >> 30) + /* + * These are the exception classes that could fire with a + * conditional instruction. + */ + switch (kvm_vcpu_trap_get_class(vcpu)) { + case ESR_ELx_EC_CP15_32: + case ESR_ELx_EC_CP15_64: + case ESR_ELx_EC_CP14_MR: + case ESR_ELx_EC_CP14_LS: + case ESR_ELx_EC_FP_ASIMD: + case ESR_ELx_EC_CP10_ID: + case ESR_ELx_EC_CP14_64: + case ESR_ELx_EC_SVC32: + break; + default: return true; + } /* Is condition field valid? */ cond = kvm_vcpu_get_condition(vcpu); diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index a60fb13e21924..2fc68da4036d9 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -154,7 +154,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, /* Switch to requested VMID */ __tlb_switch_to_guest(mmu, &cxt, false); - __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0); + __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, + TLBI_TTL_UNKNOWN); dsb(ish); __tlbi(vmalle1is); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index ab9d05fcf98b2..ce5cef7d73c41 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -829,12 +829,15 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, * Perform the appropriate TLB invalidation based on the * evicted pte value (if any). */ - if (kvm_pte_table(ctx->old, ctx->level)) - kvm_tlb_flush_vmid_range(mmu, ctx->addr, - kvm_granule_size(ctx->level)); - else if (kvm_pte_valid(ctx->old)) + if (kvm_pte_table(ctx->old, ctx->level)) { + u64 size = kvm_granule_size(ctx->level); + u64 addr = ALIGN_DOWN(ctx->addr, size); + + kvm_tlb_flush_vmid_range(mmu, addr, size); + } else if (kvm_pte_valid(ctx->old)) { kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); + } } if (stage2_pte_is_counted(ctx->old)) diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c index b32e2940df7dc..1a60b95381e8e 100644 --- a/arch/arm64/kvm/hyp/vhe/tlb.c +++ b/arch/arm64/kvm/hyp/vhe/tlb.c @@ -171,7 +171,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, /* Switch to requested VMID */ __tlb_switch_to_guest(mmu, &cxt); - __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0); + __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, + TLBI_TTL_UNKNOWN); dsb(ish); __tlbi(vmalle1is); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index d14504821b794..92270acfc00d4 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1631,7 +1631,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); - if (esr_fsc_is_permission_fault(esr)) { + if (esr_fsc_is_translation_fault(esr)) { /* Beyond sanitised PARange (which is the IPA limit) */ if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { kvm_inject_size_fault(vcpu); diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index e949e1d0fd9f7..a2b439ad387c8 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -355,7 +355,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) - vgic_v3_free_redist_region(rdreg); + vgic_v3_free_redist_region(kvm, rdreg); INIT_LIST_HEAD(&dist->rd_regions); } else { dist->vgic_cpu_base = VGIC_ADDR_UNDEF; diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index f48b8dab8b3d2..1d26bb5b02f4b 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -338,12 +338,12 @@ int kvm_register_vgic_device(unsigned long type) int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { - int cpuid; + int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); - cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); - - reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); + if (!reg_attr->vcpu) + return -EINVAL; return 0; } diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index c15ee1df036a2..dad60b1e21d4d 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -919,8 +919,19 @@ static int vgic_v3_alloc_redist_region(struct kvm *kvm, uint32_t index, return ret; } -void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg) +void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg) { + struct kvm_vcpu *vcpu; + unsigned long c; + + lockdep_assert_held(&kvm->arch.config_lock); + + /* Garbage collect the region */ + kvm_for_each_vcpu(c, vcpu, kvm) { + if (vcpu->arch.vgic_cpu.rdreg == rdreg) + vcpu->arch.vgic_cpu.rdreg = NULL; + } + list_del(&rdreg->list); kfree(rdreg); } @@ -945,7 +956,7 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) mutex_lock(&kvm->arch.config_lock); rdreg = vgic_v3_rdist_region_from_index(kvm, index); - vgic_v3_free_redist_region(rdreg); + vgic_v3_free_redist_region(kvm, rdreg); mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 8d134569d0a1f..fae2618da720b 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -310,7 +310,7 @@ vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index); -void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg); +void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg); bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 924843f1f661b..0a62f458c5cb0 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -219,9 +219,6 @@ bool kernel_page_present(struct page *page) pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - if (!can_set_direct_map()) - return true; - pgdp = pgd_offset_k(addr); if (pgd_none(READ_ONCE(*pgdp))) return false; diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8955da5c47cf7..ceed77c29fe6b 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -876,7 +876,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, emit(A64_UXTH(is64, dst, dst), ctx); break; case 32: - emit(A64_REV32(is64, dst, dst), ctx); + emit(A64_REV32(0, dst, dst), ctx); /* upper 32 bits already cleared */ break; case 64: @@ -1189,7 +1189,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, } else { emit_a64_mov_i(1, tmp, off, ctx); if (sign_extend) - emit(A64_LDRSW(dst, src_adj, off_adj), ctx); + emit(A64_LDRSW(dst, src, tmp), ctx); else emit(A64_LDR32(dst, src, tmp), ctx); } @@ -1738,15 +1738,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, emit_call(enter_prog, ctx); + /* save return value to callee saved register x20 */ + emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ branch = ctx->image + ctx->idx; emit(A64_NOP, ctx); - /* save return value to callee saved register x20 */ - emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); - emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx); if (!p->jited) emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx); diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c index 834cffcfbce32..7ba4b98076de1 100644 --- a/arch/csky/kernel/probes/ftrace.c +++ b/arch/csky/kernel/probes/ftrace.c @@ -12,6 +12,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe_ctlblk *kcb; struct pt_regs *regs; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 1140051a0c455..1150b77fa281c 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -63,6 +63,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG ELF_DETAILS + .hexagon.attributes 0 : { *(.hexagon.attributes) } DISCARDS } diff --git a/arch/loongarch/crypto/crc32-loongarch.c b/arch/loongarch/crypto/crc32-loongarch.c index a49e507af38c0..3eebea3a7b478 100644 --- a/arch/loongarch/crypto/crc32-loongarch.c +++ b/arch/loongarch/crypto/crc32-loongarch.c @@ -44,7 +44,6 @@ static u32 crc32_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) CRC32(crc, value, w); p += sizeof(u32); - len -= sizeof(u32); } if (len & sizeof(u16)) { @@ -80,7 +79,6 @@ static u32 crc32c_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) CRC32C(crc, value, w); p += sizeof(u32); - len -= sizeof(u32); } if (len & sizeof(u16)) { diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 93783fa24f6e9..dede0b422cfb9 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -4,6 +4,7 @@ generic-y += mcs_spinlock.h generic-y += parport.h generic-y += early_ioremap.h generic-y += qrwlock.h +generic-y += qspinlock.h generic-y += rwsem.h generic-y += segment.h generic-y += user.h diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h index 21447fb1efc77..d78330916bd18 100644 --- a/arch/loongarch/include/asm/hw_breakpoint.h +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -75,6 +75,8 @@ do { \ #define CSR_MWPC_NUM 0x3f #define CTRL_PLV_ENABLE 0x1e +#define CTRL_PLV0_ENABLE 0x02 +#define CTRL_PLV3_ENABLE 0x10 #define MWPnCFG3_LoadEn 8 #define MWPnCFG3_StoreEn 9 @@ -101,7 +103,7 @@ struct perf_event; struct perf_event_attr; extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset); + int *gen_len, int *gen_type); extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); extern int hw_breakpoint_arch_parse(struct perf_event *bp, const struct perf_event_attr *attr, diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index c486c2341b662..4a8adcca329b8 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -71,6 +71,8 @@ extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t #define memcpy_fromio(a, c, l) __memcpy_fromio((a), (c), (l)) #define memcpy_toio(c, a, l) __memcpy_toio((c), (a), (l)) +#define __io_aw() mmiowb() + #include #define ARCH_HAS_VALID_PHYS_ADDR_RANGE diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h index 27f319b498625..b5f9de9f102e4 100644 --- a/arch/loongarch/include/asm/numa.h +++ b/arch/loongarch/include/asm/numa.h @@ -56,6 +56,7 @@ extern int early_cpu_to_node(int cpu); static inline void early_numa_add_cpu(int cpuid, s16 node) { } static inline void numa_add_cpu(unsigned int cpu) { } static inline void numa_remove_cpu(unsigned int cpu) { } +static inline void set_cpuid_to_node(int cpuid, s16 node) { } static inline int early_cpu_to_node(int cpu) { diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index 9b36ac003f890..8f290e5546cf7 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -29,7 +29,12 @@ static inline void set_my_cpu_offset(unsigned long off) __my_cpu_offset = off; csr_write64(off, PERCPU_BASE_KS); } -#define __my_cpu_offset __my_cpu_offset + +#define __my_cpu_offset \ +({ \ + __asm__ __volatile__("":"+r"(__my_cpu_offset)); \ + __my_cpu_offset; \ +}) #define PERCPU_OP(op, asm_op, c_op) \ static __always_inline unsigned long __percpu_##op(void *ptr, \ diff --git a/arch/loongarch/include/asm/perf_event.h b/arch/loongarch/include/asm/perf_event.h index 2a35a0bc2aaab..f948a0676daf8 100644 --- a/arch/loongarch/include/asm/perf_event.h +++ b/arch/loongarch/include/asm/perf_event.h @@ -7,6 +7,13 @@ #ifndef __LOONGARCH_PERF_EVENT_H__ #define __LOONGARCH_PERF_EVENT_H__ +#include + #define perf_arch_bpf_user_pt_regs(regs) (struct user_pt_regs *)regs +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->csr_era = (__ip); \ + (regs)->regs[3] = (unsigned long) __builtin_frame_address(0); \ +} + #endif /* __LOONGARCH_PERF_EVENT_H__ */ diff --git a/arch/loongarch/include/asm/qspinlock.h b/arch/loongarch/include/asm/qspinlock.h deleted file mode 100644 index 34f43f8ad5912..0000000000000 --- a/arch/loongarch/include/asm/qspinlock.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_QSPINLOCK_H -#define _ASM_QSPINLOCK_H - -#include - -#define queued_spin_unlock queued_spin_unlock - -static inline void queued_spin_unlock(struct qspinlock *lock) -{ - compiletime_assert_atomic_type(lock->locked); - c_sync(); - WRITE_ONCE(lock->locked, 0); -} - -#include - -#endif /* _ASM_QSPINLOCK_H */ diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 4fb1e6408b982..efc8c42290d01 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -41,7 +41,7 @@ .macro JUMP_VIRT_ADDR temp1 temp2 li.d \temp1, CACHE_BASE pcaddi \temp2, 0 - or \temp1, \temp1, \temp2 + bstrins.d \temp1, \temp2, (DMW_PABITS - 1), 0 jirl zero, \temp1, 0xc .endm diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 73858c9029cc9..bff058317062e 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -287,6 +287,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe *p; struct kprobe_ctlblk *kcb; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index c4f7de2e28054..4677ea8fa8e98 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -22,7 +22,7 @@ _head: .word MZ_MAGIC /* "MZ", MS-DOS header */ .org 0x8 - .dword kernel_entry /* Kernel entry point */ + .dword _kernel_entry /* Kernel entry point (physical address) */ .dword _kernel_asize /* Kernel image effective size */ .quad PHYS_LINK_KADDR /* Kernel image load offset from start of RAM */ .org 0x38 /* 0x20 ~ 0x37 reserved */ diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index fc55c4de2a11f..621ad7634df71 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -174,11 +174,21 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) static int hw_breakpoint_control(struct perf_event *bp, enum hw_breakpoint_ops ops) { - u32 ctrl; + u32 ctrl, privilege; int i, max_slots, enable; + struct pt_regs *regs; struct perf_event **slots; struct arch_hw_breakpoint *info = counter_arch_bp(bp); + if (arch_check_bp_in_kernelspace(info)) + privilege = CTRL_PLV0_ENABLE; + else + privilege = CTRL_PLV3_ENABLE; + + /* Whether bp belongs to a task. */ + if (bp->hw.target) + regs = task_pt_regs(bp->hw.target); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { /* Breakpoint */ slots = this_cpu_ptr(bp_on_reg); @@ -197,31 +207,38 @@ static int hw_breakpoint_control(struct perf_event *bp, switch (ops) { case HW_BREAKPOINT_INSTALL: /* Set the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); - write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); - write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); - write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { - write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); + write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, privilege); } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); + write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); ctrl = encode_ctrl_reg(info->ctrl); - write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | privilege); } enable = csr_read64(LOONGARCH_CSR_CRMD); csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); + if (bp->hw.target) + regs->csr_prmd |= CSR_PRMD_PWE; break; case HW_BREAKPOINT_UNINSTALL: /* Reset the FWPnCFG/MWPnCFG 1~4 register. */ - write_wb_reg(CSR_CFG_ADDR, i, 0, 0); - write_wb_reg(CSR_CFG_ADDR, i, 1, 0); - write_wb_reg(CSR_CFG_MASK, i, 0, 0); - write_wb_reg(CSR_CFG_MASK, i, 1, 0); - write_wb_reg(CSR_CFG_CTRL, i, 0, 0); - write_wb_reg(CSR_CFG_CTRL, i, 1, 0); - write_wb_reg(CSR_CFG_ASID, i, 0, 0); - write_wb_reg(CSR_CFG_ASID, i, 1, 0); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + write_wb_reg(CSR_CFG_ADDR, i, 0, 0); + write_wb_reg(CSR_CFG_MASK, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + } else { + write_wb_reg(CSR_CFG_ADDR, i, 1, 0); + write_wb_reg(CSR_CFG_MASK, i, 1, 0); + write_wb_reg(CSR_CFG_CTRL, i, 1, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + } + if (bp->hw.target) + regs->csr_prmd &= ~CSR_PRMD_PWE; break; } @@ -283,7 +300,7 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) * to generic breakpoint descriptions. */ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, - int *gen_len, int *gen_type, int *offset) + int *gen_len, int *gen_type) { /* Type */ switch (ctrl.type) { @@ -303,11 +320,6 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, return -EINVAL; } - if (!ctrl.len) - return -EINVAL; - - *offset = __ffs(ctrl.len); - /* Len */ switch (ctrl.len) { case LOONGARCH_BREAKPOINT_LEN_1: @@ -386,21 +398,17 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, struct arch_hw_breakpoint *hw) { int ret; - u64 alignment_mask, offset; + u64 alignment_mask; /* Build the arch_hw_breakpoint. */ ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; - if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE) - alignment_mask = 0x7; - else + if (hw->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { alignment_mask = 0x3; - offset = hw->address & alignment_mask; - - hw->address &= ~alignment_mask; - hw->ctrl.len <<= offset; + hw->address &= ~alignment_mask; + } return 0; } @@ -471,12 +479,15 @@ void breakpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(bp_on_reg); for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) { - bp = slots[i]; - if (bp == NULL) - continue; - perf_bp_event(bp, regs); + if ((csr_read32(LOONGARCH_CSR_FWPS) & (0x1 << i))) { + bp = slots[i]; + if (bp == NULL) + continue; + perf_bp_event(bp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_FWPS); + update_bp_registers(regs, 0, 0); + } } - update_bp_registers(regs, 0, 0); } NOKPROBE_SYMBOL(breakpoint_handler); @@ -488,12 +499,15 @@ void watchpoint_handler(struct pt_regs *regs) slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) { - wp = slots[i]; - if (wp == NULL) - continue; - perf_bp_event(wp, regs); + if ((csr_read32(LOONGARCH_CSR_MWPS) & (0x1 << i))) { + wp = slots[i]; + if (wp == NULL) + continue; + perf_bp_event(wp, regs); + csr_write32(0x1 << i, LOONGARCH_CSR_MWPS); + update_bp_registers(regs, 0, 1); + } } - update_bp_registers(regs, 0, 1); } NOKPROBE_SYMBOL(watchpoint_handler); diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 0491bf453cd49..cac7cba81b65f 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -884,4 +884,4 @@ static int __init init_hw_perf_events(void) return 0; } -early_initcall(init_hw_perf_events); +pure_initcall(init_hw_perf_events); diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index c114c5ef13325..200109de1971a 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -494,28 +494,14 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { - int err, len, type, offset; + int err, len, type; - err = arch_bp_generic_fields(ctrl, &len, &type, &offset); + err = arch_bp_generic_fields(ctrl, &len, &type); if (err) return err; - switch (note_type) { - case NT_LOONGARCH_HW_BREAK: - if ((type & HW_BREAKPOINT_X) != type) - return -EINVAL; - break; - case NT_LOONGARCH_HW_WATCH: - if ((type & HW_BREAKPOINT_RW) != type) - return -EINVAL; - break; - default: - return -EINVAL; - } - attr->bp_len = len; attr->bp_type = type; - attr->bp_addr += offset; return 0; } @@ -609,10 +595,27 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type, return PTR_ERR(bp); attr = bp->attr; - decode_ctrl_reg(uctrl, &ctrl); - err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); - if (err) - return err; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE; + ctrl.len = LOONGARCH_BREAKPOINT_LEN_4; + break; + case NT_LOONGARCH_HW_WATCH: + decode_ctrl_reg(uctrl, &ctrl); + break; + default: + return -EINVAL; + } + + if (uctrl & CTRL_PLV_ENABLE) { + err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); + if (err) + return err; + attr.disabled = 0; + } else { + attr.disabled = 1; + } return modify_user_hw_breakpoint(bp, &attr); } @@ -643,6 +646,10 @@ static int ptrace_hbp_set_addr(unsigned int note_type, struct perf_event *bp; struct perf_event_attr attr; + /* Kernel-space address cannot be monitored by user-space */ + if ((unsigned long)addr >= XKPRANGE) + return -EINVAL; + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 634ef17fd38bf..da136c377faba 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -281,7 +281,7 @@ static void __init fdt_setup(void) return; /* Prefer to use built-in dtb, checking its legality first. */ - if (!fdt_check_header(__dtb_start)) + if (IS_ENABLED(CONFIG_BUILTIN_DTB) && !fdt_check_header(__dtb_start)) fdt_pointer = __dtb_start; else fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */ diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index aabee0b280fe5..fd22a32755a58 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -262,7 +262,6 @@ static void __init fdt_smp_setup(void) if (cpuid == loongson_sysconf.boot_cpu_id) { cpu = 0; - numa_add_cpu(cpu); } else { cpu = cpumask_next_zero(-1, cpu_present_mask); } @@ -272,6 +271,9 @@ static void __init fdt_smp_setup(void) set_cpu_present(cpu, true); __cpu_number_map[cpuid] = cpu; __cpu_logical_map[cpu] = cpuid; + + early_numa_add_cpu(cpu, 0); + set_cpuid_to_node(cpuid, 0); } loongson_sysconf.nr_cpus = num_processors; @@ -456,6 +458,7 @@ void smp_prepare_boot_cpu(void) set_cpu_possible(0, true); set_cpu_online(0, true); set_my_cpu_offset(per_cpu_offset(0)); + numa_add_cpu(0); rr_node = first_node(node_online_map); for_each_possible_cpu(cpu) { diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index a5d0cd2035da0..d5afd0c80a499 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -5,6 +5,7 @@ #define PAGE_SIZE _PAGE_SIZE #define RO_EXCEPTION_TABLE_ALIGN 4 +#define PHYSADDR_MASK 0xffffffffffff /* 48-bit */ /* * Put .bss..swapper_pg_dir as the first thing in .bss. This will @@ -139,10 +140,11 @@ SECTIONS #ifdef CONFIG_EFI_STUB /* header symbols */ - _kernel_asize = _end - _text; - _kernel_fsize = _edata - _text; - _kernel_vsize = _end - __initdata_begin; - _kernel_rsize = _edata - __initdata_begin; + _kernel_entry = ABSOLUTE(kernel_entry & PHYSADDR_MASK); + _kernel_asize = ABSOLUTE(_end - _text); + _kernel_fsize = ABSOLUTE(_edata - _text); + _kernel_vsize = ABSOLUTE(_end - __initdata_begin); + _kernel_rsize = ABSOLUTE(_edata - __initdata_begin); #endif .gptab.sdata : { diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index 1fc2f6813ea02..97b40defde060 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -202,10 +202,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, if (!(vma->vm_flags & VM_WRITE)) goto bad_area; } else { - if (!(vma->vm_flags & VM_READ) && address != exception_era(regs)) - goto bad_area; if (!(vma->vm_flags & VM_EXEC) && address == exception_era(regs)) goto bad_area; + if (!(vma->vm_flags & (VM_READ | VM_WRITE)) && address != exception_era(regs)) + goto bad_area; } /* diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 3bcdd32a6b366..338b474910f74 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -430,7 +430,9 @@ resume: movec %a0,%dfc /* restore status register */ - movew %a1@(TASK_THREAD+THREAD_SR),%sr + movew %a1@(TASK_THREAD+THREAD_SR),%d0 + oriw #0x0700,%d0 + movew %d0,%sr rts diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index 4c8f8cbfa05f3..e7f0f72c1b36e 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -453,30 +453,18 @@ void mac_poweroff(void) void mac_reset(void) { - if (macintosh_config->adb_type == MAC_ADB_II && - macintosh_config->ident != MAC_MODEL_SE30) { - /* need ROMBASE in booter */ - /* indeed, plus need to MAP THE ROM !! */ - - if (mac_bi_data.rombase == 0) - mac_bi_data.rombase = 0x40800000; - - /* works on some */ - rom_reset = (void *) (mac_bi_data.rombase + 0xa); - - local_irq_disable(); - rom_reset(); #ifdef CONFIG_ADB_CUDA - } else if (macintosh_config->adb_type == MAC_ADB_EGRET || - macintosh_config->adb_type == MAC_ADB_CUDA) { + if (macintosh_config->adb_type == MAC_ADB_EGRET || + macintosh_config->adb_type == MAC_ADB_CUDA) { cuda_restart(); + } else #endif #ifdef CONFIG_ADB_PMU - } else if (macintosh_config->adb_type == MAC_ADB_PB2) { + if (macintosh_config->adb_type == MAC_ADB_PB2) { pmu_restart(); + } else #endif - } else if (CPU_IS_030) { - + if (CPU_IS_030) { /* 030-specific reset routine. The idea is general, but the * specific registers to reset are '030-specific. Until I * have a non-030 machine, I can't test anything else. @@ -524,6 +512,18 @@ void mac_reset(void) "jmp %/a0@\n\t" /* jump to the reset vector */ ".chip 68k" : : "r" (offset), "a" (rombase) : "a0"); + } else { + /* need ROMBASE in booter */ + /* indeed, plus need to MAP THE ROM !! */ + + if (mac_bi_data.rombase == 0) + mac_bi_data.rombase = 0x40800000; + + /* works on some */ + rom_reset = (void *)(mac_bi_data.rombase + 0xa); + + local_irq_disable(); + rom_reset(); } /* should never get here */ diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile index 4393bee64eaf8..85c4d29ef43e9 100644 --- a/arch/microblaze/kernel/Makefile +++ b/arch/microblaze/kernel/Makefile @@ -7,7 +7,6 @@ ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code and low level code CFLAGS_REMOVE_timer.o = -pg CFLAGS_REMOVE_intc.o = -pg -CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_process.o = -pg endif diff --git a/arch/microblaze/kernel/cpu/cpuinfo-static.c b/arch/microblaze/kernel/cpu/cpuinfo-static.c index 85dbda4a08a81..03da36dc6d9c9 100644 --- a/arch/microblaze/kernel/cpu/cpuinfo-static.c +++ b/arch/microblaze/kernel/cpu/cpuinfo-static.c @@ -18,7 +18,7 @@ static const char family_string[] = CONFIG_XILINX_MICROBLAZE0_FAMILY; static const char cpu_ver_string[] = CONFIG_XILINX_MICROBLAZE0_HW_VER; #define err_printk(x) \ - early_printk("ERROR: Microblaze " x "-different for kernel and DTS\n"); + pr_err("ERROR: Microblaze " x "-different for kernel and DTS\n"); void __init set_cpuinfo_static(struct cpuinfo *ci, struct device_node *cpu) { diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 797ae590ebdba..9750ce3e40d59 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -14,7 +14,7 @@ config MIPS select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_KEEP_MEMBLOCK select ARCH_USE_BUILTIN_BSWAP diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index ec180ab92eaa8..66a8ba19c2872 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -110,7 +110,8 @@ static void bcm6358_quirks(void) * RAC flush causes kernel panics on BCM6358 when booting from TP1 * because the bootloader is not initializing it properly. */ - bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)); + bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)) || + !!BMIPS_GET_CBR(); } static void bcm6368_quirks(void) diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index 23c67c0871b17..6cc79296c8ef2 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -33,6 +33,19 @@ extern void __iomem *mips_cm_l2sync_base; */ extern phys_addr_t __mips_cm_phys_base(void); +/** + * mips_cm_l2sync_phys_base - retrieve the physical base address of the CM + * L2-sync region + * + * This function returns the physical base address of the Coherence Manager + * L2-cache only region. It provides a default implementation which reads the + * CMGCRL2OnlySyncBase register where available or returns a 4K region just + * behind the CM GCR base address. It may be overridden by platforms which + * determine this address in a different way by defining a function with the + * same prototype. + */ +extern phys_addr_t mips_cm_l2sync_phys_base(void); + /* * mips_cm_is64 - determine CM register width * diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index d14d0e37ad02d..4a2b40ce39e09 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -159,7 +159,7 @@ extern unsigned long exception_ip(struct pt_regs *regs); #define exception_ip(regs) exception_ip(regs) #define profile_pc(regs) instruction_pointer(regs) -extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall); +extern asmlinkage long syscall_trace_enter(struct pt_regs *regs); extern asmlinkage void syscall_trace_leave(struct pt_regs *regs); extern void die(const char *, struct pt_regs *) __noreturn; diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index d1b11f66f748f..cb1045ebab062 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -101,6 +101,7 @@ void output_thread_info_defines(void) OFFSET(TI_CPU, thread_info, cpu); OFFSET(TI_PRE_COUNT, thread_info, preempt_count); OFFSET(TI_REGS, thread_info, regs); + OFFSET(TI_SYSCALL, thread_info, syscall); DEFINE(_THREAD_SIZE, THREAD_SIZE); DEFINE(_THREAD_MASK, THREAD_MASK); DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE); diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 84b3affb9de88..268ac0b811e35 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -201,7 +201,7 @@ phys_addr_t __mips_cm_phys_base(void) phys_addr_t mips_cm_phys_base(void) __attribute__((weak, alias("__mips_cm_phys_base"))); -static phys_addr_t __mips_cm_l2sync_phys_base(void) +phys_addr_t __weak mips_cm_l2sync_phys_base(void) { u32 base_reg; @@ -217,9 +217,6 @@ static phys_addr_t __mips_cm_l2sync_phys_base(void) return mips_cm_phys_base() + MIPS_CM_GCR_SIZE; } -phys_addr_t mips_cm_l2sync_phys_base(void) - __attribute__((weak, alias("__mips_cm_l2sync_phys_base"))); - static void mips_cm_probe_l2sync(void) { unsigned major_rev; diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 59288c13b581b..61503a36067e9 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -1317,16 +1317,13 @@ long arch_ptrace(struct task_struct *child, long request, * Notification of system call entry/exit * - triggered by current->work.syscall_trace */ -asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) +asmlinkage long syscall_trace_enter(struct pt_regs *regs) { user_exit(); - current_thread_info()->syscall = syscall; - if (test_thread_flag(TIF_SYSCALL_TRACE)) { if (ptrace_report_syscall_entry(regs)) return -1; - syscall = current_thread_info()->syscall; } #ifdef CONFIG_SECCOMP @@ -1335,7 +1332,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) struct seccomp_data sd; unsigned long args[6]; - sd.nr = syscall; + sd.nr = current_thread_info()->syscall; sd.arch = syscall_get_arch(current); syscall_get_arguments(current, regs, args); for (i = 0; i < 6; i++) @@ -1345,23 +1342,23 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) ret = __secure_computing(&sd); if (ret == -1) return ret; - syscall = current_thread_info()->syscall; } #endif if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->regs[2]); - audit_syscall_entry(syscall, regs->regs[4], regs->regs[5], + audit_syscall_entry(current_thread_info()->syscall, + regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); /* * Negative syscall numbers are mistaken for rejected syscalls, but * won't have had the return value set appropriately, so we do so now. */ - if (syscall < 0) + if (current_thread_info()->syscall < 0) syscall_set_return_value(current, regs, -ENOSYS, 0); - return syscall; + return current_thread_info()->syscall; } /* diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 18dc9b3450561..2c604717e6308 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -77,6 +77,18 @@ loads_done: PTR_WD load_a7, bad_stack_a7 .previous + /* + * syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + */ + subu t2, v0, __NR_O32_Linux + bnez t2, 1f /* __NR_syscall at offset 0 */ + LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number + b 2f +1: + LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number +2: + lw t0, TI_FLAGS($28) # syscall tracing enabled? li t1, _TIF_WORK_SYSCALL_ENTRY and t0, t1 @@ -114,16 +126,7 @@ syscall_trace_entry: SAVE_STATIC move a0, sp - /* - * syscall number is in v0 unless we called syscall(__NR_###) - * where the real syscall number is in a0 - */ - move a1, v0 - subu t2, v0, __NR_O32_Linux - bnez t2, 1f /* __NR_syscall at offset 0 */ - lw a1, PT_R4(sp) - -1: jal syscall_trace_enter + jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 97456b2ca7dc3..97788859238c3 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -44,6 +44,8 @@ NESTED(handle_sysn32, PT_SIZE, sp) sd a3, PT_R26(sp) # save a3 for syscall restarting + LONG_S v0, TI_SYSCALL($28) # Store syscall number + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -72,7 +74,6 @@ syscall_common: n32_syscall_trace_entry: SAVE_STATIC move a0, sp - move a1, v0 jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S index e6264aa62e457..be11ea5cc67e0 100644 --- a/arch/mips/kernel/scall64-n64.S +++ b/arch/mips/kernel/scall64-n64.S @@ -46,6 +46,8 @@ NESTED(handle_sys64, PT_SIZE, sp) sd a3, PT_R26(sp) # save a3 for syscall restarting + LONG_S v0, TI_SYSCALL($28) # Store syscall number + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -82,7 +84,6 @@ n64_syscall_exit: syscall_trace_entry: SAVE_STATIC move a0, sp - move a1, v0 jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index d3c2616cba226..7a5abb73e5312 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -79,6 +79,22 @@ loads_done: PTR_WD load_a7, bad_stack_a7 .previous + /* + * absolute syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + * note: NR_syscall is the first O32 syscall but the macro is + * only defined when compiling with -mabi=32 (CONFIG_32BIT) + * therefore __NR_O32_Linux is used (4000) + */ + + subu t2, v0, __NR_O32_Linux + bnez t2, 1f /* __NR_syscall at offset 0 */ + LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number + b 2f +1: + LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number +2: + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -113,22 +129,7 @@ trace_a_syscall: sd a7, PT_R11(sp) # For indirect syscalls move a0, sp - /* - * absolute syscall number is in v0 unless we called syscall(__NR_###) - * where the real syscall number is in a0 - * note: NR_syscall is the first O32 syscall but the macro is - * only defined when compiling with -mabi=32 (CONFIG_32BIT) - * therefore __NR_O32_Linux is used (4000) - */ - .set push - .set reorder - subu t1, v0, __NR_O32_Linux - move a1, v0 - bnez t1, 1f /* __NR_syscall at offset 0 */ - ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ - .set pop - -1: jal syscall_trace_enter + jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/pci/ops-rc32434.c b/arch/mips/pci/ops-rc32434.c index 874ed6df97683..34b9323bdabb0 100644 --- a/arch/mips/pci/ops-rc32434.c +++ b/arch/mips/pci/ops-rc32434.c @@ -112,8 +112,8 @@ static int read_config_dword(struct pci_bus *bus, unsigned int devfn, * gives them time to settle */ if (where == PCI_VENDOR_ID) { - if (ret == 0xffffffff || ret == 0x00000000 || - ret == 0x0000ffff || ret == 0xffff0000) { + if (*val == 0xffffffff || *val == 0x00000000 || + *val == 0x0000ffff || *val == 0xffff0000) { if (delay > 4) return 0; delay *= 2; diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c old mode 100644 new mode 100755 index 2583e318e8c6b..b080c7c6cc463 --- a/arch/mips/pci/pcie-octeon.c +++ b/arch/mips/pci/pcie-octeon.c @@ -230,12 +230,18 @@ static inline uint64_t __cvmx_pcie_build_config_addr(int pcie_port, int bus, { union cvmx_pcie_address pcie_addr; union cvmx_pciercx_cfg006 pciercx_cfg006; + union cvmx_pciercx_cfg032 pciercx_cfg032; pciercx_cfg006.u32 = cvmx_pcie_cfgx_read(pcie_port, CVMX_PCIERCX_CFG006(pcie_port)); if ((bus <= pciercx_cfg006.s.pbnum) && (dev != 0)) return 0; + pciercx_cfg032.u32 = + cvmx_pcie_cfgx_read(pcie_port, CVMX_PCIERCX_CFG032(pcie_port)); + if ((pciercx_cfg032.s.dlla == 0) || (pciercx_cfg032.s.lt == 1)) + return 0; + pcie_addr.u64 = 0; pcie_addr.config.upper = 2; pcie_addr.config.io = 1; diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 9370888c9a7e3..90554a5558fbc 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -180,29 +180,39 @@ asmlinkage void unhandled_exception(struct pt_regs *regs, int ea, int vector) asmlinkage void do_fpe_trap(struct pt_regs *regs, unsigned long address) { - int code = FPE_FLTUNK; - unsigned long fpcsr = regs->fpcsr; - - if (fpcsr & SPR_FPCSR_IVF) - code = FPE_FLTINV; - else if (fpcsr & SPR_FPCSR_OVF) - code = FPE_FLTOVF; - else if (fpcsr & SPR_FPCSR_UNF) - code = FPE_FLTUND; - else if (fpcsr & SPR_FPCSR_DZF) - code = FPE_FLTDIV; - else if (fpcsr & SPR_FPCSR_IXF) - code = FPE_FLTRES; - - /* Clear all flags */ - regs->fpcsr &= ~SPR_FPCSR_ALLF; - - force_sig_fault(SIGFPE, code, (void __user *)regs->pc); + if (user_mode(regs)) { + int code = FPE_FLTUNK; + unsigned long fpcsr = regs->fpcsr; + + if (fpcsr & SPR_FPCSR_IVF) + code = FPE_FLTINV; + else if (fpcsr & SPR_FPCSR_OVF) + code = FPE_FLTOVF; + else if (fpcsr & SPR_FPCSR_UNF) + code = FPE_FLTUND; + else if (fpcsr & SPR_FPCSR_DZF) + code = FPE_FLTDIV; + else if (fpcsr & SPR_FPCSR_IXF) + code = FPE_FLTRES; + + /* Clear all flags */ + regs->fpcsr &= ~SPR_FPCSR_ALLF; + + force_sig_fault(SIGFPE, code, (void __user *)regs->pc); + } else { + pr_emerg("KERNEL: Illegal fpe exception 0x%.8lx\n", regs->pc); + die("Die:", regs, SIGFPE); + } } asmlinkage void do_trap(struct pt_regs *regs, unsigned long address) { - force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); + if (user_mode(regs)) { + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); + } else { + pr_emerg("KERNEL: Illegal trap exception 0x%.8lx\n", regs->pc); + die("Die:", regs, SIGILL); + } } asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address) diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 5c845e8d59d92..42822265c59bb 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -12,7 +12,7 @@ config PARISC select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARCH_HAS_PTE_SPECIAL select ARCH_NO_SG_CHAIN select ARCH_SUPPORTS_HUGETLBFS if PA20 diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 5937d5edaba1e..000a28e1c5e8d 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -97,26 +97,28 @@ * version takes two arguments: a src and destination register. * However, the source and destination registers can not be * the same register. + * + * We use add,l to avoid clobbering the C/B bits in the PSW. */ .macro tophys grvirt, grphys - ldil L%(__PAGE_OFFSET), \grphys - sub \grvirt, \grphys, \grphys + ldil L%(-__PAGE_OFFSET), \grphys + addl \grvirt, \grphys, \grphys .endm - + .macro tovirt grphys, grvirt ldil L%(__PAGE_OFFSET), \grvirt - add \grphys, \grvirt, \grvirt + addl \grphys, \grvirt, \grvirt .endm .macro tophys_r1 gr - ldil L%(__PAGE_OFFSET), %r1 - sub \gr, %r1, \gr + ldil L%(-__PAGE_OFFSET), %r1 + addl \gr, %r1, \gr .endm - + .macro tovirt_r1 gr ldil L%(__PAGE_OFFSET), %r1 - add \gr, %r1, \gr + addl \gr, %r1, \gr .endm .macro delay value diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index ba4c05bc24d69..8394718870e1a 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -31,18 +31,17 @@ void flush_cache_all_local(void); void flush_cache_all(void); void flush_cache_mm(struct mm_struct *mm); -void flush_kernel_dcache_page_addr(const void *addr); - #define flush_kernel_dcache_range(start,size) \ flush_kernel_dcache_range_asm((start), (start)+(size)); +/* The only way to flush a vmap range is to flush whole cache */ #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); -#define flush_cache_vmap(start, end) flush_cache_all() +void flush_cache_vmap(unsigned long start, unsigned long end); #define flush_cache_vmap_early(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) flush_cache_all() +void flush_cache_vunmap(unsigned long start, unsigned long end); void flush_dcache_folio(struct folio *folio); #define flush_dcache_folio flush_dcache_folio @@ -77,17 +76,11 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -/* defined in pacache.S exported in cache.c used by flush_anon_page */ -void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); - #define ARCH_HAS_FLUSH_ANON_PAGE void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP -static inline void kunmap_flush_on_unmap(const void *addr) -{ - flush_kernel_dcache_page_addr(addr); -} +void kunmap_flush_on_unmap(const void *addr); #endif /* _PARISC_CACHEFLUSH_H */ diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h index 3c43baca7b397..2aceebcd695c8 100644 --- a/arch/parisc/include/asm/checksum.h +++ b/arch/parisc/include/asm/checksum.h @@ -40,7 +40,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) " addc %0, %5, %0\n" " addc %0, %3, %0\n" "1: ldws,ma 4(%1), %3\n" -" addib,< 0, %2, 1b\n" +" addib,> -1, %2, 1b\n" " addc %0, %3, %0\n" "\n" " extru %0, 31, 16, %4\n" @@ -126,6 +126,7 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, ** Try to keep 4 registers with "live" values ahead of the ALU. */ +" depdi 0, 31, 32, %0\n"/* clear upper half of incoming checksum */ " ldd,ma 8(%1), %4\n" /* get 1st saddr word */ " ldd,ma 8(%2), %5\n" /* get 1st daddr word */ " add %4, %0, %0\n" @@ -137,8 +138,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " add,dc %3, %0, %0\n" /* fold in proto+len | carry bit */ " extrd,u %0, 31, 32, %4\n"/* copy upper half down */ " depdi 0, 31, 32, %0\n"/* clear upper half */ -" add %4, %0, %0\n" /* fold into 32-bits */ -" addc 0, %0, %0\n" /* add carry */ +" add,dc %4, %0, %0\n" /* fold into 32-bits, plus carry */ +" addc 0, %0, %0\n" /* add final carry */ #else @@ -163,7 +164,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " ldw,ma 4(%2), %7\n" /* 4th daddr */ " addc %6, %0, %0\n" " addc %7, %0, %0\n" -" addc %3, %0, %0\n" /* fold in proto+len, catch carry */ +" addc %3, %0, %0\n" /* fold in proto+len */ +" addc 0, %0, %0\n" /* add carry */ #endif : "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len), diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h new file mode 100644 index 0000000000000..47c5a1991d103 --- /dev/null +++ b/arch/parisc/include/asm/mman.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include + +/* PARISC cannot allow mdwe as it needs writable stacks */ +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return false; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported + +#endif /* __ASM_MMAN_H__ */ diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index 667e703c0e8f6..d6ad1812866a0 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -16,6 +16,7 @@ #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #ifndef __ASSEMBLY__ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 974accac05cd3..babf65751e818 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -448,14 +448,17 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#define ptep_get ptep_get + static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte; - if (!pte_young(*ptep)) - return 0; - - pte = *ptep; + pte = ptep_get(ptep); if (!pte_young(pte)) { return 0; } @@ -463,17 +466,10 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned return 1; } -struct mm_struct; -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - pte_t old_pte; - - old_pte = *ptep; - set_pte(ptep, __pte(0)); - - return old_pte; -} +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { set_pte(ptep, pte_wrprotect(*ptep)); @@ -511,7 +507,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define __HAVE_ARCH_PTEP_CLEAR_FLUSH #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/arch/parisc/include/asm/signal.h b/arch/parisc/include/asm/signal.h index 715c96ba2ec81..e84883c6b4c7a 100644 --- a/arch/parisc/include/asm/signal.h +++ b/arch/parisc/include/asm/signal.h @@ -4,23 +4,11 @@ #include -#define _NSIG 64 -/* bits-per-word, where word apparently means 'long' not 'int' */ -#define _NSIG_BPW BITS_PER_LONG -#define _NSIG_WORDS (_NSIG / _NSIG_BPW) - # ifndef __ASSEMBLY__ /* Most things should be clean enough to redefine this at will, if care is taken to make libc match. */ -typedef unsigned long old_sigset_t; /* at least 32 bits */ - -typedef struct { - /* next_signal() assumes this is a long - no choice */ - unsigned long sig[_NSIG_WORDS]; -} sigset_t; - #include #endif /* !__ASSEMBLY */ diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h index 8e4895c5ea5d3..40d7a574c5dd1 100644 --- a/arch/parisc/include/uapi/asm/signal.h +++ b/arch/parisc/include/uapi/asm/signal.h @@ -57,10 +57,20 @@ #include +#define _NSIG 64 +#define _NSIG_BPW (sizeof(unsigned long) * 8) +#define _NSIG_WORDS (_NSIG / _NSIG_BPW) + # ifndef __ASSEMBLY__ # include +typedef unsigned long old_sigset_t; /* at least 32 bits */ + +typedef struct { + unsigned long sig[_NSIG_WORDS]; +} sigset_t; + /* Avoid too many header ordering problems. */ struct siginfo; diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 422f3e1e6d9ca..483bfafd930cd 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -31,20 +32,31 @@ #include #include +#define PTR_PAGE_ALIGN_DOWN(addr) PTR_ALIGN_DOWN(addr, PAGE_SIZE) + +/* + * When nonzero, use _PAGE_ACCESSED bit to try to reduce the number + * of page flushes done flush_cache_page_if_present. There are some + * pros and cons in using this option. It may increase the risk of + * random segmentation faults. + */ +#define CONFIG_FLUSH_PAGE_ACCESSED 0 + int split_tlb __ro_after_init; int dcache_stride __ro_after_init; int icache_stride __ro_after_init; EXPORT_SYMBOL(dcache_stride); +/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); EXPORT_SYMBOL(flush_dcache_page_asm); void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr); - -/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_data_cache_local(void *); /* flushes local data-cache only */ void flush_instruction_cache_local(void); /* flushes local code-cache only */ +static void flush_kernel_dcache_page_addr(const void *addr); + /* On some machines (i.e., ones with the Merced bus), there can be * only a single PxTLB broadcast at a time; this must be guaranteed * by software. We need a spinlock around all TLB flushes to ensure @@ -321,6 +333,18 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, { if (!static_branch_likely(&parisc_has_cache)) return; + + /* + * The TLB is the engine of coherence on parisc. The CPU is + * entitled to speculate any page with a TLB mapping, so here + * we kill the mapping then flush the page along a special flush + * only alias mapping. This guarantees that the page is no-longer + * in the cache for any process and nor may it be speculatively + * read in (until the user or kernel specifically accesses it, + * of course). + */ + flush_tlb_page(vma, vmaddr); + preempt_disable(); flush_dcache_page_asm(physaddr, vmaddr); if (vma->vm_flags & VM_EXEC) @@ -328,46 +352,44 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) +static void flush_kernel_dcache_page_addr(const void *addr) { - unsigned long flags, space, pgd, prot; -#ifdef CONFIG_TLB_PTLOCK - unsigned long pgd_lock; -#endif + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - vmaddr &= PAGE_MASK; + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent data cache move-in */ preempt_disable(); + flush_dcache_page_asm(__pa(vaddr), vaddr); + preempt_enable(); +} - /* Set context for flush */ - local_irq_save(flags); - prot = mfctl(8); - space = mfsp(SR_USER); - pgd = mfctl(25); -#ifdef CONFIG_TLB_PTLOCK - pgd_lock = mfctl(28); -#endif - switch_mm_irqs_off(NULL, vma->vm_mm, NULL); - local_irq_restore(flags); - - flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - flush_tlb_page(vma, vmaddr); +static void flush_kernel_icache_page_addr(const void *addr) +{ + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - /* Restore previous context */ - local_irq_save(flags); -#ifdef CONFIG_TLB_PTLOCK - mtctl(pgd_lock, 28); -#endif - mtctl(pgd, 25); - mtsp(space, SR_USER); - mtctl(prot, 8); - local_irq_restore(flags); + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent instruction cache move-in */ + preempt_disable(); + flush_icache_page_asm(__pa(vaddr), vaddr); preempt_enable(); } +void kunmap_flush_on_unmap(const void *addr) +{ + flush_kernel_dcache_page_addr(addr); +} +EXPORT_SYMBOL(kunmap_flush_on_unmap); + void flush_icache_pages(struct vm_area_struct *vma, struct page *page, unsigned int nr) { @@ -375,13 +397,16 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page, for (;;) { flush_kernel_dcache_page_addr(kaddr); - flush_kernel_icache_page(kaddr); + flush_kernel_icache_page_addr(kaddr); if (--nr == 0) break; kaddr += PAGE_SIZE; } } +/* + * Walk page directory for MM to find PTEP pointer for address ADDR. + */ static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) { pte_t *ptep = NULL; @@ -410,6 +435,41 @@ static inline bool pte_needs_flush(pte_t pte) == (_PAGE_PRESENT | _PAGE_ACCESSED); } +/* + * Return user physical address. Returns 0 if page is not present. + */ +static inline unsigned long get_upa(struct mm_struct *mm, unsigned long addr) +{ + unsigned long flags, space, pgd, prot, pa; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + /* Save context */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + + /* Set context for lpa_user */ + switch_mm_irqs_off(NULL, mm, NULL); + pa = lpa_user(addr); + + /* Restore previous context */ +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + + return pa; +} + void flush_dcache_folio(struct folio *folio) { struct address_space *mapping = folio_flush_mapping(folio); @@ -458,50 +518,23 @@ void flush_dcache_folio(struct folio *folio) if (addr + nr * PAGE_SIZE > vma->vm_end) nr = (vma->vm_end - addr) / PAGE_SIZE; - if (parisc_requires_coherency()) { - for (i = 0; i < nr; i++) { - pte_t *ptep = get_ptep(vma->vm_mm, - addr + i * PAGE_SIZE); - if (!ptep) - continue; - if (pte_needs_flush(*ptep)) - flush_user_cache_page(vma, - addr + i * PAGE_SIZE); - /* Optimise accesses to the same table? */ - pte_unmap(ptep); - } - } else { + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + for (i = 0; i < nr; i++) + __flush_cache_page(vma, + addr + i * PAGE_SIZE, + (pfn + i) * PAGE_SIZE); /* - * The TLB is the engine of coherence on parisc: - * The CPU is entitled to speculate any page - * with a TLB mapping, so here we kill the - * mapping then flush the page along a special - * flush only alias mapping. This guarantees that - * the page is no-longer in the cache for any - * process and nor may it be speculatively read - * in (until the user or kernel specifically - * accesses it, of course) + * Software is allowed to have any number + * of private mappings to a page. */ - for (i = 0; i < nr; i++) - flush_tlb_page(vma, addr + i * PAGE_SIZE); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - for (i = 0; i < nr; i++) - __flush_cache_page(vma, - addr + i * PAGE_SIZE, - (pfn + i) * PAGE_SIZE); - /* - * Software is allowed to have any number - * of private mappings to a page. - */ - if (!(vma->vm_flags & VM_SHARED)) - continue; - if (old_addr) - pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", - old_addr, addr, vma->vm_file); - if (nr == folio_nr_pages(folio)) - old_addr = addr; - } + if (!(vma->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, vma->vm_file); + if (nr == folio_nr_pages(folio)) + old_addr = addr; } WARN_ON(++count == 4096); } @@ -591,35 +624,28 @@ extern void purge_kernel_dcache_page_asm(unsigned long); extern void clear_user_page_asm(void *, unsigned long); extern void copy_user_page_asm(void *, void *, unsigned long); -void flush_kernel_dcache_page_addr(const void *addr) -{ - unsigned long flags; - - flush_kernel_dcache_page_asm(addr); - purge_tlb_start(flags); - pdtlb(SR_KERNEL, addr); - purge_tlb_end(flags); -} -EXPORT_SYMBOL(flush_kernel_dcache_page_addr); - static void flush_cache_page_if_present(struct vm_area_struct *vma, - unsigned long vmaddr, unsigned long pfn) + unsigned long vmaddr) { +#if CONFIG_FLUSH_PAGE_ACCESSED bool needs_flush = false; - pte_t *ptep; + pte_t *ptep, pte; - /* - * The pte check is racy and sometimes the flush will trigger - * a non-access TLB miss. Hopefully, the page has already been - * flushed. - */ ptep = get_ptep(vma->vm_mm, vmaddr); if (ptep) { - needs_flush = pte_needs_flush(*ptep); + pte = ptep_get(ptep); + needs_flush = pte_needs_flush(pte); pte_unmap(ptep); } if (needs_flush) - flush_cache_page(vma, vmaddr, pfn); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pte_pfn(pte))); +#else + struct mm_struct *mm = vma->vm_mm; + unsigned long physaddr = get_upa(mm, vmaddr); + + if (physaddr) + __flush_cache_page(vma, vmaddr, PAGE_ALIGN_DOWN(physaddr)); +#endif } void copy_user_highpage(struct page *to, struct page *from, @@ -629,7 +655,7 @@ void copy_user_highpage(struct page *to, struct page *from, kfrom = kmap_local_page(from); kto = kmap_local_page(to); - flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + __flush_cache_page(vma, vaddr, PFN_PHYS(page_to_pfn(from))); copy_page_asm(kto, kfrom); kunmap_local(kto); kunmap_local(kfrom); @@ -638,16 +664,17 @@ void copy_user_highpage(struct page *to, struct page *from, void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(dst)); } void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(src)); } /* __flush_tlb_range() @@ -681,32 +708,10 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - unsigned long addr, pfn; - pte_t *ptep; - - for (addr = start; addr < end; addr += PAGE_SIZE) { - bool needs_flush = false; - /* - * The vma can contain pages that aren't present. Although - * the pte search is expensive, we need the pte to find the - * page pfn and to check whether the page should be flushed. - */ - ptep = get_ptep(vma->vm_mm, addr); - if (ptep) { - needs_flush = pte_needs_flush(*ptep); - pfn = pte_pfn(*ptep); - pte_unmap(ptep); - } - if (needs_flush) { - if (parisc_requires_coherency()) { - flush_user_cache_page(vma, addr); - } else { - if (WARN_ON(!pfn_valid(pfn))) - return; - __flush_cache_page(vma, addr, PFN_PHYS(pfn)); - } - } - } + unsigned long addr; + + for (addr = start; addr < end; addr += PAGE_SIZE) + flush_cache_page_if_present(vma, addr); } static inline unsigned long mm_total_size(struct mm_struct *mm) @@ -757,21 +762,19 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) return; flush_tlb_range(vma, start, end); - flush_cache_all(); + if (vma->vm_flags & VM_EXEC) + flush_cache_all(); + else + flush_data_cache(); return; } - flush_cache_pages(vma, start, end); + flush_cache_pages(vma, start & PAGE_MASK, end); } void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (WARN_ON(!pfn_valid(pfn))) - return; - if (parisc_requires_coherency()) - flush_user_cache_page(vma, vmaddr); - else - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) @@ -779,34 +782,133 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon if (!PageAnon(page)) return; - if (parisc_requires_coherency()) { - if (vma->vm_flags & VM_SHARED) - flush_data_cache(); - else - flush_user_cache_page(vma, vmaddr); + __flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page))); +} + +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + + if (!pte_young(pte)) + return 0; + set_pte(ptep, pte_mkold(pte)); +#if CONFIG_FLUSH_PAGE_ACCESSED + __flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte))); +#endif + return 1; +} + +/* + * After a PTE is cleared, we have no way to flush the cache for + * the physical page. On PA8800 and PA8900 processors, these lines + * can cause random cache corruption. Thus, we must flush the cache + * as well as the TLB when clearing a PTE that's valid. + */ +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + struct mm_struct *mm = (vma)->vm_mm; + pte_t pte = ptep_get_and_clear(mm, addr, ptep); + unsigned long pfn = pte_pfn(pte); + + if (pfn_valid(pfn)) + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); + else if (pte_accessible(mm, pte)) + flush_tlb_page(vma, addr); + + return pte; +} + +/* + * The physical address for pages in the ioremap case can be obtained + * from the vm_struct struct. I wasn't able to successfully handle the + * vmalloc and vmap cases. We have an array of struct page pointers in + * the uninitialized vmalloc case but the flush failed using page_to_pfn. + */ +void flush_cache_vmap(unsigned long start, unsigned long end) +{ + unsigned long addr, physaddr; + struct vm_struct *vm; + + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + + if (end - start >= parisc_cache_flush_threshold) { + flush_cache_all(); return; } - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); + if (WARN_ON_ONCE(!is_vmalloc_addr((void *)start))) { + flush_cache_all(); + return; + } + + vm = find_vm_area((void *)start); + if (WARN_ON_ONCE(!vm)) { + flush_cache_all(); + return; + } + + /* The physical addresses of IOREMAP regions are contiguous */ + if (vm->flags & VM_IOREMAP) { + physaddr = vm->phys_addr; + for (addr = start; addr < end; addr += PAGE_SIZE) { + preempt_disable(); + flush_dcache_page_asm(physaddr, start); + flush_icache_page_asm(physaddr, start); + preempt_enable(); + physaddr += PAGE_SIZE; + } + return; + } + + flush_cache_all(); } +EXPORT_SYMBOL(flush_cache_vmap); +/* + * The vm_struct has been retired and the page table is set up. The + * last page in the range is a guard page. Its physical address can't + * be determined using lpa, so there is no way to flush the range + * using flush_dcache_page_asm. + */ +void flush_cache_vunmap(unsigned long start, unsigned long end) +{ + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + flush_data_cache(); +} +EXPORT_SYMBOL(flush_cache_vunmap); + +/* + * On systems with PA8800/PA8900 processors, there is no way to flush + * a vmap range other than using the architected loop to flush the + * entire cache. The page directory is not set up, so we can't use + * fdc, etc. FDCE/FICE don't work to flush a portion of the cache. + * L2 is physically indexed but FDCE/FICE instructions in virtual + * mode output their virtual address on the core bus, not their + * real address. As a result, the L2 cache index formed from the + * virtual address will most likely not be the same as the L2 index + * formed from the real address. + */ void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; unsigned long end = start + size; - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - flush_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(flush_kernel_vmap_range); @@ -818,15 +920,18 @@ void invalidate_kernel_vmap_range(void *vaddr, int size) /* Ensure DMA is complete */ asm_syncdma(); - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - purge_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 621a4b386ae4f..c91f9c2e61ed2 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -206,6 +206,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe *p; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 6f0c92e8149d8..dcf61cbd31470 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -22,6 +22,7 @@ EXPORT_SYMBOL(memset); #include EXPORT_SYMBOL(__xchg8); EXPORT_SYMBOL(__xchg32); +EXPORT_SYMBOL(__cmpxchg_u8); EXPORT_SYMBOL(__cmpxchg_u32); EXPORT_SYMBOL(__cmpxchg_u64); #ifdef CONFIG_SMP diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index c520e551a1652..a8e75e5b884a7 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -169,6 +169,7 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop) static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) { unsigned long saddr = regs->ior; + unsigned long shift, temp1; __u64 val = 0; ASM_EXCEPTIONTABLE_VAR(ret); @@ -180,25 +181,22 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) #ifdef CONFIG_64BIT __asm__ __volatile__ ( -" depd,z %3,60,3,%%r19\n" /* r19=(ofs&7)*8 */ -" mtsp %4, %%sr1\n" -" depd %%r0,63,3,%3\n" -"1: ldd 0(%%sr1,%3),%0\n" -"2: ldd 8(%%sr1,%3),%%r20\n" -" subi 64,%%r19,%%r19\n" -" mtsar %%r19\n" -" shrpd %0,%%r20,%%sar,%0\n" +" depd,z %2,60,3,%3\n" /* shift=(ofs&7)*8 */ +" mtsp %5, %%sr1\n" +" depd %%r0,63,3,%2\n" +"1: ldd 0(%%sr1,%2),%0\n" +"2: ldd 8(%%sr1,%2),%4\n" +" subi 64,%3,%3\n" +" mtsar %3\n" +" shrpd %0,%4,%%sar,%0\n" "3: \n" ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1") ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1") - : "=r" (val), "+r" (ret) - : "0" (val), "r" (saddr), "r" (regs->isr) - : "r19", "r20" ); + : "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1) + : "r" (regs->isr) ); #else - { - unsigned long shift, temp1; __asm__ __volatile__ ( -" zdep %2,29,2,%3\n" /* r19=(ofs&3)*8 */ +" zdep %2,29,2,%3\n" /* shift=(ofs&3)*8 */ " mtsp %5, %%sr1\n" " dep %%r0,31,2,%2\n" "1: ldw 0(%%sr1,%2),%0\n" @@ -214,7 +212,6 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop) ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1") : "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1) : "r" (regs->isr) ); - } #endif DPRINTF("val = 0x%llx\n", val); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b9fc064d38d28..2065973e09d20 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -154,7 +154,7 @@ config PPC select ARCH_HAS_SYSCALL_WRAPPER if !SPU_BASE && !COMPAT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE if PPC_RADIX_MMU diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 051247027da0b..c1c632cf1615d 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -238,7 +238,7 @@ KBUILD_CFLAGS += $(cflags-y) all: zImage # With make 3.82 we cannot mix normal and wildcard targets -BOOT_TARGETS1 := zImage zImage.initrd uImage +BOOT_TARGETS1 := zImage zImage.initrd uImage vmlinux.strip BOOT_TARGETS2 := zImage% dtbImage% treeImage.% cuImage.% simpleImage.% uImage.% PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2) diff --git a/arch/powerpc/crypto/.gitignore b/arch/powerpc/crypto/.gitignore index e1094f08f713a..e9fe73aac8b61 100644 --- a/arch/powerpc/crypto/.gitignore +++ b/arch/powerpc/crypto/.gitignore @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only aesp10-ppc.S +aesp8-ppc.S ghashp10-ppc.S +ghashp8-ppc.S diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c index 74fb86b0d2097..7c728755852e1 100644 --- a/arch/powerpc/crypto/chacha-p10-glue.c +++ b/arch/powerpc/crypto/chacha-p10-glue.c @@ -197,6 +197,9 @@ static struct skcipher_alg algs[] = { static int __init chacha_p10_init(void) { + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return 0; + static_branch_enable(&have_p10); return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); @@ -204,10 +207,13 @@ static int __init chacha_p10_init(void) static void __exit chacha_p10_exit(void) { + if (!static_branch_likely(&have_p10)) + return; + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); } -module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init); +module_init(chacha_p10_init); module_exit(chacha_p10_exit); MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)"); diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index f26c430f39826..24d26c8420aa0 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -3,6 +3,7 @@ #define _ASM_POWERPC_CPUTHREADS_H #ifndef __ASSEMBLY__ +#include #include #include diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index a41e542ba94dd..7a8495660c2f8 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -524,7 +524,7 @@ long plpar_hcall_norets_notrace(unsigned long opcode, ...); * Used for all but the craziest of phyp interfaces (see plpar_hcall9) */ #define PLPAR_HCALL_BUFSIZE 4 -long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...); /** * plpar_hcall_raw: - Make a hypervisor call without calculating hcall stats @@ -538,7 +538,7 @@ long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...); * plpar_hcall, but plpar_hcall_raw works in real mode and does not * calculate hypervisor call statistics. */ -long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...); /** * plpar_hcall9: - Make a pseries hypervisor call with up to 9 return arguments @@ -549,8 +549,8 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); * PLPAR_HCALL9_BUFSIZE to size the return argument buffer. */ #define PLPAR_HCALL9_BUFSIZE 9 -long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...); -long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall9(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...); +long plpar_hcall9_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...); /* pseries hcall tracing */ extern struct static_key hcall_tracepoint_key; @@ -570,7 +570,7 @@ struct hvcall_mpp_data { unsigned long backing_mem; }; -int h_get_mpp(struct hvcall_mpp_data *); +long h_get_mpp(struct hvcall_mpp_data *mpp_data); struct hvcall_mpp_x_data { unsigned long coalesced_bytes; diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 08c550ed49be6..ba2e13bb879dc 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -585,12 +585,12 @@ __do_out_asm(_rec_outl, "stwbrx") #define __do_inw(port) _rec_inw(port) #define __do_inl(port) _rec_inl(port) #else /* CONFIG_PPC32 */ -#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_inb(port) readb((PCI_IO_ADDR)_IO_BASE + port); -#define __do_inw(port) readw((PCI_IO_ADDR)_IO_BASE + port); -#define __do_inl(port) readl((PCI_IO_ADDR)_IO_BASE + port); +#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_inb(port) readb((PCI_IO_ADDR)(_IO_BASE + port)); +#define __do_inw(port) readw((PCI_IO_ADDR)(_IO_BASE + port)); +#define __do_inl(port) readl((PCI_IO_ADDR)(_IO_BASE + port)); #endif /* !CONFIG_PPC32 */ #ifdef CONFIG_EEH @@ -606,12 +606,12 @@ __do_out_asm(_rec_outl, "stwbrx") #define __do_writesw(a, b, n) _outsw(PCI_FIX_ADDR(a),(b),(n)) #define __do_writesl(a, b, n) _outsl(PCI_FIX_ADDR(a),(b),(n)) -#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) -#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) -#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) +#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) +#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) +#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) #define __do_memset_io(addr, c, n) \ _memset_io(PCI_FIX_ADDR(addr), c, n) diff --git a/arch/powerpc/include/asm/plpks.h b/arch/powerpc/include/asm/plpks.h index 23b77027c9163..7a84069759b03 100644 --- a/arch/powerpc/include/asm/plpks.h +++ b/arch/powerpc/include/asm/plpks.h @@ -44,9 +44,8 @@ #define PLPKS_MAX_DATA_SIZE 4000 // Timeouts for PLPKS operations -#define PLPKS_MAX_TIMEOUT 5000 // msec -#define PLPKS_FLUSH_SLEEP 10 // msec -#define PLPKS_FLUSH_SLEEP_RANGE 400 +#define PLPKS_MAX_TIMEOUT (5 * USEC_PER_SEC) +#define PLPKS_FLUSH_SLEEP 10000 // usec struct plpks_var { char *component; diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 005601243dda4..076ae60b4a55d 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -510,6 +510,7 @@ #define PPC_RAW_STB(r, base, i) (0x98000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LBZ(r, base, i) (0x88000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LHA(r, base, i) (0xa8000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) @@ -532,6 +533,7 @@ #define PPC_RAW_MULW(d, a, b) (0x7c0001d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_MULHWU(d, a, b) (0x7c000016 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_MULI(d, a, i) (0x1c000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_DIVW(d, a, b) (0x7c0003d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_DIVWU(d, a, b) (0x7c000396 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_DIVDU(d, a, b) (0x7c000392 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_DIVDE(t, a, b) (0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) @@ -550,6 +552,8 @@ #define PPC_RAW_XOR(d, a, b) (0x7c000278 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) #define PPC_RAW_XORI(d, a, i) (0x68000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) #define PPC_RAW_XORIS(d, a, i) (0x6c000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_EXTSB(d, a) (0x7c000774 | ___PPC_RA(d) | ___PPC_RS(a)) +#define PPC_RAW_EXTSH(d, a) (0x7c000734 | ___PPC_RA(d) | ___PPC_RS(a)) #define PPC_RAW_EXTSW(d, a) (0x7c0007b4 | ___PPC_RA(d) | ___PPC_RS(a)) #define PPC_RAW_SLW(d, a, s) (0x7c000030 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) #define PPC_RAW_SLD(d, a, s) (0x7c000036 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index a21f529c43d96..8359c06d92d9f 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -12,9 +12,16 @@ #ifndef __ASSEMBLY__ /* Performance Monitor Registers */ #define mfpmr(rn) ({unsigned int rval; \ - asm volatile("mfpmr %0," __stringify(rn) \ + asm volatile(".machine push; " \ + ".machine e300; " \ + "mfpmr %0," __stringify(rn) ";" \ + ".machine pop; " \ : "=r" (rval)); rval;}) -#define mtpmr(rn, v) asm volatile("mtpmr " __stringify(rn) ",%0" : : "r" (v)) +#define mtpmr(rn, v) asm volatile(".machine push; " \ + ".machine e300; " \ + "mtpmr " __stringify(rn) ",%0; " \ + ".machine pop; " \ + : : "r" (v)) #endif /* __ASSEMBLY__ */ /* Freescale Book E Performance Monitor APU Registers */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index de10437fd2065..4cba724c88991 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -92,9 +92,25 @@ __pu_failed: \ : label) #endif +#ifdef CONFIG_CC_IS_CLANG +#define DS_FORM_CONSTRAINT "Z<>" +#else +#define DS_FORM_CONSTRAINT "YZ<>" +#endif + #ifdef __powerpc64__ +#ifdef CONFIG_PPC_KERNEL_PREFIXED #define __put_user_asm2_goto(x, ptr, label) \ __put_user_asm_goto(x, ptr, label, "std") +#else +#define __put_user_asm2_goto(x, addr, label) \ + asm goto ("1: std%U1%X1 %0,%1 # put_user\n" \ + EX_TABLE(1b, %l2) \ + : \ + : "r" (x), DS_FORM_CONSTRAINT (*addr) \ + : \ + : label) +#endif // CONFIG_PPC_KERNEL_PREFIXED #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ asm goto( \ diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h index 4c69ece52a31e..59ed89890c902 100644 --- a/arch/powerpc/include/asm/vmalloc.h +++ b/arch/powerpc/include/asm/vmalloc.h @@ -7,14 +7,14 @@ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #define arch_vmap_pud_supported arch_vmap_pud_supported -static inline bool arch_vmap_pud_supported(pgprot_t prot) +static __always_inline bool arch_vmap_pud_supported(pgprot_t prot) { /* HPT does not cope with large pages in the vmalloc area */ return radix_enabled(); } #define arch_vmap_pmd_supported arch_vmap_pmd_supported -static inline bool arch_vmap_pmd_supported(pgprot_t prot) +static __always_inline bool arch_vmap_pmd_supported(pgprot_t prot) { return radix_enabled(); } diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c index 072ebe7f290ba..f8208c027148f 100644 --- a/arch/powerpc/kernel/kprobes-ftrace.c +++ b/arch/powerpc/kernel/kprobes-ftrace.c @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, struct pt_regs *regs; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(nip, parent_nip); if (bit < 0) return; diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 7112adc597a80..195714fc6e22f 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -347,12 +347,13 @@ static unsigned long get_got_size(const Elf64_Ehdr *hdr, static void dedotify_versions(struct modversion_info *vers, unsigned long size) { - struct modversion_info *end; + struct modversion_info *end = (void *)vers + size; - for (end = (void *)vers + size; vers < end; vers++) + for (; vers < end && vers->next; vers = (void *)vers + vers->next) { if (vers->name[0] == '.') { memmove(vers->name, vers->name+1, strlen(vers->name)); } + } } /* diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index d95a48eff412e..5ca2df1bc573d 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -360,6 +360,7 @@ struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node) } return NULL; } +EXPORT_SYMBOL(pci_find_hose_for_OF_device); struct pci_controller *pci_find_controller_for_domain(int domain_nr) { @@ -1630,6 +1631,7 @@ int early_find_capability(struct pci_controller *hose, int bus, int devfn, { return pci_bus_find_capability(fake_pci_bus(hose, bus), devfn, cap); } +EXPORT_SYMBOL_GPL(early_find_capability); struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) { diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 0b5878c3125b1..77364729a1b61 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -375,6 +375,18 @@ static int __init early_init_dt_scan_cpus(unsigned long node, if (IS_ENABLED(CONFIG_PPC64)) boot_cpu_hwid = be32_to_cpu(intserv[found_thread]); + if (nr_cpu_ids % nthreads != 0) { + set_nr_cpu_ids(ALIGN(nr_cpu_ids, nthreads)); + pr_warn("nr_cpu_ids was not a multiple of threads_per_core, adjusted to %d\n", + nr_cpu_ids); + } + + if (boot_cpuid >= nr_cpu_ids) { + set_nr_cpu_ids(min(CONFIG_NR_CPUS, ALIGN(boot_cpuid + 1, nthreads))); + pr_warn("Boot CPU %d >= nr_cpu_ids, adjusted nr_cpu_ids to %d\n", + boot_cpuid, nr_cpu_ids); + } + /* * PAPR defines "logical" PVR values for cpus that * meet various levels of the architecture: diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 9b142b9d5187b..d6b207e8e0844 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -67,6 +68,7 @@ #include #include #include +#include #include "setup.h" @@ -896,6 +898,16 @@ void __init setup_arch(char **cmdline_p) */ initialize_cache_info(); + /* + * Lock down the kernel if booted in secure mode. This is required to + * maintain kernel integrity. + */ + if (IS_ENABLED(CONFIG_LOCK_DOWN_IN_SECURE_BOOT)) { + if (is_ppc_secureboot_enabled()) + security_lock_kernel_down("PowerNV Secure Boot mode", + LOCKDOWN_INTEGRITY_MAX); + } + /* Initialize RTAS if available. */ rtas_initialize(); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 0b921704da45e..e47b954ce2669 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4856,7 +4856,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, * entering a nested guest in which case the decrementer is now owned * by L2 and the L1 decrementer is provided in hdec_expires */ - if (!kvmhv_is_nestedv2() && kvmppc_core_pending_dec(vcpu) && + if (kvmppc_core_pending_dec(vcpu) && ((tb < kvmppc_dec_expires_host_tb(vcpu)) || (trap == BOOK3S_INTERRUPT_SYSCALL && kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED))) diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c index 8e6f5355f08b5..1091f7a83b255 100644 --- a/arch/powerpc/kvm/book3s_hv_nestedv2.c +++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c @@ -71,8 +71,8 @@ gs_msg_ops_kvmhv_nestedv2_config_fill_info(struct kvmppc_gs_buff *gsb, } if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_OUTPUT)) { - kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_OUTPUT, - cfg->vcpu_run_output_cfg); + rc = kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_OUTPUT, + cfg->vcpu_run_output_cfg); if (rc < 0) return rc; } diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 6eac63e79a899..0ab65eeb93ee3 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -76,7 +76,7 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o -CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) # Enable CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 5766180f5380a..852bc414c06fa 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 3438ab72c346b..70a278a301afb 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -130,7 +130,7 @@ void set_pud_at(struct mm_struct *mm, unsigned long addr, WARN_ON(pte_hw_valid(pud_pte(*pudp))); assert_spin_locked(pud_lockptr(mm, pudp)); - WARN_ON(!(pud_large(pud))); + WARN_ON(!(pud_leaf(pud))); #endif trace_hugepage_set_pud(addr, pud_val(pud)); return set_pte_at(mm, addr, pudp_ptep(pudp), pud_pte(pud)); @@ -170,6 +170,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { unsigned long old_pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return __pmd(old_pmd); diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 2f39c50ca729e..a0c4f1bde83e8 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -450,10 +450,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code } break; case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */ - EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, src_reg)); + if (off) + EMIT(PPC_RAW_DIVW(dst_reg, src2_reg, src_reg)); + else + EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, src_reg)); break; case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */ - EMIT(PPC_RAW_DIVWU(_R0, src2_reg, src_reg)); + if (off) + EMIT(PPC_RAW_DIVW(_R0, src2_reg, src_reg)); + else + EMIT(PPC_RAW_DIVWU(_R0, src2_reg, src_reg)); EMIT(PPC_RAW_MULW(_R0, src_reg, _R0)); EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0)); break; @@ -467,10 +473,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code if (imm == 1) { EMIT(PPC_RAW_MR(dst_reg, src2_reg)); } else if (is_power_of_2((u32)imm)) { - EMIT(PPC_RAW_SRWI(dst_reg, src2_reg, ilog2(imm))); + if (off) + EMIT(PPC_RAW_SRAWI(dst_reg, src2_reg, ilog2(imm))); + else + EMIT(PPC_RAW_SRWI(dst_reg, src2_reg, ilog2(imm))); } else { PPC_LI32(_R0, imm); - EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, _R0)); + if (off) + EMIT(PPC_RAW_DIVW(dst_reg, src2_reg, _R0)); + else + EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, _R0)); } break; case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */ @@ -480,11 +492,19 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code if (!is_power_of_2((u32)imm)) { bpf_set_seen_register(ctx, tmp_reg); PPC_LI32(tmp_reg, imm); - EMIT(PPC_RAW_DIVWU(_R0, src2_reg, tmp_reg)); + if (off) + EMIT(PPC_RAW_DIVW(_R0, src2_reg, tmp_reg)); + else + EMIT(PPC_RAW_DIVWU(_R0, src2_reg, tmp_reg)); EMIT(PPC_RAW_MULW(_R0, tmp_reg, _R0)); EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0)); } else if (imm == 1) { EMIT(PPC_RAW_LI(dst_reg, 0)); + } else if (off) { + EMIT(PPC_RAW_SRAWI(_R0, src2_reg, ilog2(imm))); + EMIT(PPC_RAW_ADDZE(_R0, _R0)); + EMIT(PPC_RAW_SLWI(_R0, _R0, ilog2(imm))); + EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0)); } else { imm = ilog2((u32)imm); EMIT(PPC_RAW_RLWINM(dst_reg, src2_reg, 0, 32 - imm, 31)); @@ -497,11 +517,21 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code imm = -imm; if (!is_power_of_2(imm)) return -EOPNOTSUPP; - if (imm == 1) + if (imm == 1) { EMIT(PPC_RAW_LI(dst_reg, 0)); - else + EMIT(PPC_RAW_LI(dst_reg_h, 0)); + } else if (off) { + EMIT(PPC_RAW_SRAWI(dst_reg_h, src2_reg_h, 31)); + EMIT(PPC_RAW_XOR(dst_reg, src2_reg, dst_reg_h)); + EMIT(PPC_RAW_SUBFC(dst_reg, dst_reg_h, dst_reg)); + EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 32 - ilog2(imm), 31)); + EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg_h)); + EMIT(PPC_RAW_SUBFC(dst_reg, dst_reg_h, dst_reg)); + EMIT(PPC_RAW_SUBFE(dst_reg_h, dst_reg_h, dst_reg_h)); + } else { EMIT(PPC_RAW_RLWINM(dst_reg, src2_reg, 0, 32 - ilog2(imm), 31)); - EMIT(PPC_RAW_LI(dst_reg_h, 0)); + EMIT(PPC_RAW_LI(dst_reg_h, 0)); + } break; case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ if (!imm) @@ -727,15 +757,30 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * MOV */ case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */ - if (dst_reg == src_reg) - break; - EMIT(PPC_RAW_MR(dst_reg, src_reg)); - EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h)); + if (off == 8) { + EMIT(PPC_RAW_EXTSB(dst_reg, src_reg)); + EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31)); + } else if (off == 16) { + EMIT(PPC_RAW_EXTSH(dst_reg, src_reg)); + EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31)); + } else if (off == 32 && dst_reg == src_reg) { + EMIT(PPC_RAW_SRAWI(dst_reg_h, src_reg, 31)); + } else if (off == 32) { + EMIT(PPC_RAW_MR(dst_reg, src_reg)); + EMIT(PPC_RAW_SRAWI(dst_reg_h, src_reg, 31)); + } else if (dst_reg != src_reg) { + EMIT(PPC_RAW_MR(dst_reg, src_reg)); + EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h)); + } break; case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */ /* special mov32 for zext */ if (imm == 1) EMIT(PPC_RAW_LI(dst_reg_h, 0)); + else if (off == 8) + EMIT(PPC_RAW_EXTSB(dst_reg, src_reg)); + else if (off == 16) + EMIT(PPC_RAW_EXTSH(dst_reg, src_reg)); else if (dst_reg != src_reg) EMIT(PPC_RAW_MR(dst_reg, src_reg)); break; @@ -751,6 +796,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * BPF_FROM_BE/LE */ case BPF_ALU | BPF_END | BPF_FROM_LE: + case BPF_ALU64 | BPF_END | BPF_FROM_LE: switch (imm) { case 16: /* Copy 16 bits to upper part */ @@ -785,6 +831,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code EMIT(PPC_RAW_MR(dst_reg_h, tmp_reg)); break; } + if (BPF_CLASS(code) == BPF_ALU64 && imm != 64) + EMIT(PPC_RAW_LI(dst_reg_h, 0)); break; case BPF_ALU | BPF_END | BPF_FROM_BE: switch (imm) { @@ -852,6 +900,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code /* Get offset into TMP_REG */ EMIT(PPC_RAW_LI(tmp_reg, off)); + /* + * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync' + * before and after the operation. + * + * This is a requirement in the Linux Kernel Memory Model. + * See __cmpxchg_u32() in asm/cmpxchg.h as an example. + */ + if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); tmp_idx = ctx->idx * 4; /* load value from memory into r0 */ EMIT(PPC_RAW_LWARX(_R0, tmp_reg, dst_reg, 0)); @@ -905,6 +962,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code /* For the BPF_FETCH variant, get old data into src_reg */ if (imm & BPF_FETCH) { + /* Emit 'sync' to enforce full ordering */ + if (IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); EMIT(PPC_RAW_MR(ret_reg, ax_reg)); if (!fp->aux->verifier_zext) EMIT(PPC_RAW_LI(ret_reg - 1, 0)); /* higher 32-bit */ @@ -918,11 +978,17 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * BPF_LDX */ case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_B: case BPF_LDX | BPF_PROBE_MEM | BPF_B: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_H: case BPF_LDX | BPF_PROBE_MEM | BPF_H: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_W: case BPF_LDX | BPF_PROBE_MEM | BPF_W: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */ case BPF_LDX | BPF_PROBE_MEM | BPF_DW: /* @@ -931,7 +997,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * load only if addr is kernel address (see is_kernel_addr()), otherwise * set dst_reg=0 and move on. */ - if (BPF_MODE(code) == BPF_PROBE_MEM) { + if (BPF_MODE(code) == BPF_PROBE_MEM || BPF_MODE(code) == BPF_PROBE_MEMSX) { PPC_LI32(_R0, TASK_SIZE - off); EMIT(PPC_RAW_CMPLW(src_reg, _R0)); PPC_BCC_SHORT(COND_GT, (ctx->idx + 4) * 4); @@ -953,30 +1019,48 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * as there are two load instructions for dst_reg_h & dst_reg * respectively. */ - if (size == BPF_DW) + if (size == BPF_DW || + (size == BPF_B && BPF_MODE(code) == BPF_PROBE_MEMSX)) PPC_JMP((ctx->idx + 3) * 4); else PPC_JMP((ctx->idx + 2) * 4); } - switch (size) { - case BPF_B: - EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off)); - break; - case BPF_H: - EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off)); - break; - case BPF_W: - EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off)); - break; - case BPF_DW: - EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off)); - EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4)); - break; - } + if (BPF_MODE(code) == BPF_MEMSX || BPF_MODE(code) == BPF_PROBE_MEMSX) { + switch (size) { + case BPF_B: + EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off)); + EMIT(PPC_RAW_EXTSB(dst_reg, dst_reg)); + break; + case BPF_H: + EMIT(PPC_RAW_LHA(dst_reg, src_reg, off)); + break; + case BPF_W: + EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off)); + break; + } + if (!fp->aux->verifier_zext) + EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31)); - if (size != BPF_DW && !fp->aux->verifier_zext) - EMIT(PPC_RAW_LI(dst_reg_h, 0)); + } else { + switch (size) { + case BPF_B: + EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off)); + break; + case BPF_H: + EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off)); + break; + case BPF_W: + EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off)); + break; + case BPF_DW: + EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off)); + EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4)); + break; + } + if (size != BPF_DW && !fp->aux->verifier_zext) + EMIT(PPC_RAW_LI(dst_reg_h, 0)); + } if (BPF_MODE(code) == BPF_PROBE_MEM) { int insn_idx = ctx->idx - 1; @@ -1068,6 +1152,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code case BPF_JMP | BPF_JA: PPC_JMP(addrs[i + 1 + off]); break; + case BPF_JMP32 | BPF_JA: + PPC_JMP(addrs[i + 1 + imm]); + break; case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 79f23974a3204..58522de615ff2 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -202,7 +202,8 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_BLR()); } -static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u64 func) +static int +bpf_jit_emit_func_call_hlp(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func) { unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0; long reladdr; @@ -211,19 +212,20 @@ static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u return -EINVAL; if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) { - reladdr = func_addr - CTX_NIA(ctx); + reladdr = func_addr - local_paca->kernelbase; if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) { - pr_err("eBPF: address of %ps out of range of pcrel address.\n", - (void *)func); + pr_err("eBPF: address of %ps out of range of 34-bit relative address.\n", + (void *)func); return -ERANGE; } - /* pla r12,addr */ - EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr)); - EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr)); - EMIT(PPC_RAW_MTCTR(_R12)); - EMIT(PPC_RAW_BCTR()); - + EMIT(PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase))); + /* Align for subsequent prefix instruction */ + if (!IS_ALIGNED((unsigned long)fimage + CTX_NIA(ctx), 8)) + EMIT(PPC_RAW_NOP()); + /* paddi r12,r12,addr */ + EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(0) | IMM_H18(reladdr)); + EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | ___PPC_RA(_R12) | IMM_L(reladdr)); } else { reladdr = func_addr - kernel_toc_addr(); if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { @@ -233,9 +235,9 @@ static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u EMIT(PPC_RAW_ADDIS(_R12, _R2, PPC_HA(reladdr))); EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr))); - EMIT(PPC_RAW_MTCTR(_R12)); - EMIT(PPC_RAW_BCTRL()); } + EMIT(PPC_RAW_MTCTR(_R12)); + EMIT(PPC_RAW_BCTRL()); return 0; } @@ -285,7 +287,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o int b2p_index = bpf_to_ppc(BPF_REG_3); int bpf_tailcall_prologue_size = 8; - if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2)) + if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL) && IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2)) bpf_tailcall_prologue_size += 4; /* skip past the toc load */ /* @@ -803,6 +805,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code /* Get offset into TMP_REG_1 */ EMIT(PPC_RAW_LI(tmp1_reg, off)); + /* + * Enforce full ordering for operations with BPF_FETCH by emitting a 'sync' + * before and after the operation. + * + * This is a requirement in the Linux Kernel Memory Model. + * See __cmpxchg_u64() in asm/cmpxchg.h as an example. + */ + if ((imm & BPF_FETCH) && IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ if (size == BPF_DW) @@ -865,6 +876,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code PPC_BCC_SHORT(COND_NE, tmp_idx); if (imm & BPF_FETCH) { + /* Emit 'sync' to enforce full ordering */ + if (IS_ENABLED(CONFIG_SMP)) + EMIT(PPC_RAW_SYNC()); EMIT(PPC_RAW_MR(ret_reg, _R0)); /* * Skip unnecessary zero-extension for 32-bit cmpxchg. @@ -993,7 +1007,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code return ret; if (func_addr_fixed) - ret = bpf_jit_emit_func_call_hlp(image, ctx, func_addr); + ret = bpf_jit_emit_func_call_hlp(image, fimage, ctx, func_addr); else ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr); diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 27f18119fda17..241551d1282f8 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -695,6 +695,20 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index, ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + /* + * ret value as 'H_PARAMETER' with detail_rc as 'GEN_BUF_TOO_SMALL', + * specifies that the current buffer size cannot accommodate + * all the information and a partial buffer returned. + * Since in this function we are only accessing data for a given starting index, + * we don't need to accommodate whole data and can get required count by + * accessing first entry data. + * Hence hcall fails only incase the ret value is other than H_SUCCESS or + * H_PARAMETER with detail_rc value as GEN_BUF_TOO_SMALL(0x1B). + */ + if (ret == H_PARAMETER && be32_to_cpu(arg->params.detail_rc) == 0x1B) + ret = 0; + if (ret) { pr_devel("hcall failed: 0x%lx\n", ret); goto out; @@ -759,6 +773,7 @@ static int h_gpci_event_init(struct perf_event *event) { u64 count; u8 length; + unsigned long ret; /* Not our event */ if (event->attr.type != event->pmu->type) @@ -789,13 +804,23 @@ static int h_gpci_event_init(struct perf_event *event) } /* check if the request works... */ - if (single_gpci_request(event_get_request(event), + ret = single_gpci_request(event_get_request(event), event_get_starting_index(event), event_get_secondary_index(event), event_get_counter_info_version(event), event_get_offset(event), length, - &count)) { + &count); + + /* + * ret value as H_AUTHORITY implies that partition is not permitted to retrieve + * performance information, and required to set + * "Enable Performance Information Collection" option. + */ + if (ret == H_AUTHORITY) + return -EPERM; + + if (ret) { pr_devel("gpci hcall failed\n"); return -EINVAL; } diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index bf0188dcb9184..a5001d32f978d 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 40aa582068883..e52b848b64b79 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -398,6 +398,7 @@ static void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary) hard_irq_disable(); mpic_teardown_this_cpu(secondary); +#ifdef CONFIG_CRASH_DUMP if (cpu == crashing_cpu && cpu_thread_in_core(cpu) != 0) { /* * We enter the crash kernel on whatever cpu crashed, @@ -406,9 +407,11 @@ static void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary) */ disable_threadbit = 1; disable_cpu = cpu_first_thread_sibling(cpu); - } else if (sibling != crashing_cpu && - cpu_thread_in_core(cpu) == 0 && - cpu_thread_in_core(sibling) != 0) { + } else if (sibling == crashing_cpu) { + return; + } +#endif + if (cpu_thread_in_core(cpu) == 0 && cpu_thread_in_core(sibling) != 0) { disable_threadbit = 2; disable_cpu = sibling; } diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index 9c10aac40c7b1..e265f026eee2a 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -99,9 +99,6 @@ static void __init linkstation_init_IRQ(void) mpic_init(mpic); } -extern void avr_uart_configure(void); -extern void avr_uart_send(const char); - static void __noreturn linkstation_restart(char *cmd) { local_irq_disable(); diff --git a/arch/powerpc/platforms/embedded6xx/mpc10x.h b/arch/powerpc/platforms/embedded6xx/mpc10x.h index 5ad12023e5628..ebc258fa4858d 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc10x.h +++ b/arch/powerpc/platforms/embedded6xx/mpc10x.h @@ -156,4 +156,7 @@ int mpc10x_disable_store_gathering(struct pci_controller *hose); /* For MPC107 boards that use the built-in openpic */ void mpc10x_set_openpic(void); +void avr_uart_configure(void); +void avr_uart_send(const char c); + #endif /* __PPC_KERNEL_MPC10X_H */ diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig index 8bdae0caf21e5..84f101ec53a96 100644 --- a/arch/powerpc/platforms/powermac/Kconfig +++ b/arch/powerpc/platforms/powermac/Kconfig @@ -2,7 +2,7 @@ config PPC_PMAC bool "Apple PowerMac based machines" depends on PPC_BOOK3S && CPU_BIG_ENDIAN - select ADB_CUDA if POWER_RESET && PPC32 + select ADB_CUDA if POWER_RESET && ADB select MPIC select FORCE_PCI select PPC_INDIRECT_PCI if PPC32 diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig index e9c1087dd42ec..706194e5f0b46 100644 --- a/arch/powerpc/platforms/ps3/Kconfig +++ b/arch/powerpc/platforms/ps3/Kconfig @@ -67,6 +67,7 @@ config PS3_VUART config PS3_PS3AV depends on PPC_PS3 tristate "PS3 AV settings driver" if PS3_ADVANCED + select VIDEO select PS3_VUART default y help diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index e8c4129697b14..b1e6d275cda9e 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -786,8 +786,16 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) * parent bus. During reboot, there will be ibm,dma-window property to * define DMA window. For kdump, there will at least be default window or DDW * or both. + * There is an exception to the above. In case the PE goes into frozen + * state, firmware may not provide ibm,dma-window property at the time + * of LPAR boot up. */ + if (!pdn) { + pr_debug(" no ibm,dma-window property !\n"); + return; + } + ppci = PCI_DN(pdn); pr_debug(" parent is %pOF, iommu_table: 0x%p\n", diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 4e9916bb03d71..c1d8bee8f7018 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1886,10 +1886,10 @@ notrace void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf) * h_get_mpp * H_GET_MPP hcall returns info in 7 parms */ -int h_get_mpp(struct hvcall_mpp_data *mpp_data) +long h_get_mpp(struct hvcall_mpp_data *mpp_data) { - int rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + long rc; rc = plpar_hcall9(H_GET_MPP, retbuf); diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 1c151d77e74b3..11d5208817b9d 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -113,8 +113,8 @@ struct hvcall_ppp_data { */ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) { - unsigned long rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + long rc; rc = plpar_hcall9(H_GET_PPP, retbuf); @@ -193,7 +193,7 @@ static void parse_ppp_data(struct seq_file *m) struct hvcall_ppp_data ppp_data; struct device_node *root; const __be32 *perf_level; - int rc; + long rc; rc = h_get_ppp(&ppp_data); if (rc) @@ -357,8 +357,8 @@ static int read_dt_lpar_name(struct seq_file *m) static void read_lpar_name(struct seq_file *m) { - if (read_rtas_lpar_name(m) && read_dt_lpar_name(m)) - pr_err_once("Error can't get the LPAR name"); + if (read_rtas_lpar_name(m)) + read_dt_lpar_name(m); } #define SPLPAR_MAXLENGTH 1026*(sizeof(char)) diff --git a/arch/powerpc/platforms/pseries/papr_platform_attributes.c b/arch/powerpc/platforms/pseries/papr_platform_attributes.c index 526c621b098be..eea2041b270b5 100644 --- a/arch/powerpc/platforms/pseries/papr_platform_attributes.c +++ b/arch/powerpc/platforms/pseries/papr_platform_attributes.c @@ -101,10 +101,12 @@ static int papr_get_attr(u64 id, struct energy_scale_attribute *esi) esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * max_esi_attrs); temp_buf = krealloc(buf, esi_buf_size, GFP_KERNEL); - if (temp_buf) + if (temp_buf) { buf = temp_buf; - else - return -ENOMEM; + } else { + ret = -ENOMEM; + goto out_buf; + } goto retry; } diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c index febe18f251d0c..4a595493d28ae 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -415,8 +415,7 @@ static int plpks_confirm_object_flushed(struct label *label, break; } - usleep_range(PLPKS_FLUSH_SLEEP, - PLPKS_FLUSH_SLEEP + PLPKS_FLUSH_SLEEP_RANGE); + fsleep(PLPKS_FLUSH_SLEEP); timeout = timeout + PLPKS_FLUSH_SLEEP; } while (timeout < PLPKS_MAX_TIMEOUT); @@ -464,9 +463,10 @@ int plpks_signed_update_var(struct plpks_var *var, u64 flags) continuetoken = retbuf[0]; if (pseries_status_to_err(rc) == -EBUSY) { - int delay_ms = get_longbusy_msecs(rc); - mdelay(delay_ms); - timeout += delay_ms; + int delay_us = get_longbusy_msecs(rc) * 1000; + + fsleep(delay_us); + timeout += delay_us; } rc = pseries_status_to_err(rc); } while (rc == -EBUSY && timeout < PLPKS_MAX_TIMEOUT); diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 2dc9cbc4bcd8f..d8809a3834e32 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -39,7 +39,6 @@ static struct vio_dev vio_bus_device = { /* fake "parent" device */ .name = "vio", .type = "", .dev.init_name = "vio", - .dev.bus = &vio_bus_type, }; #ifdef CONFIG_PPC_SMLPAR diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 558ec68d768e6..60a2c5925161a 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -566,10 +566,12 @@ static const struct fsl_msi_feature ipic_msi_feature = { .msiir_offset = 0x38, }; +#ifdef CONFIG_EPAPR_PARAVIRT static const struct fsl_msi_feature vmpic_msi_feature = { .fsl_pic_ip = FSL_PIC_IP_VMPIC, .msiir_offset = 0, }; +#endif static const struct of_device_id fsl_of_msi_ids[] = { { diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index e3142ce531a09..b775a940602a4 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -37,7 +37,7 @@ config RISCV select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARCH_HAS_VDSO_DATA select ARCH_KEEP_MEMBLOCK if ACPI select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX @@ -96,7 +96,7 @@ config RISCV select HAS_IOPORT if MMU select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP - select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT && !XIP_KERNEL + select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL select HAVE_ARCH_KASAN if MMU && 64BIT diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata index 910ba8837add8..2acc7d876e1fb 100644 --- a/arch/riscv/Kconfig.errata +++ b/arch/riscv/Kconfig.errata @@ -82,14 +82,14 @@ config ERRATA_THEAD Otherwise, please say "N" here to avoid unnecessary overhead. -config ERRATA_THEAD_PBMT - bool "Apply T-Head memory type errata" +config ERRATA_THEAD_MAE + bool "Apply T-Head's memory attribute extension (XTheadMae) errata" depends on ERRATA_THEAD && 64BIT && MMU select RISCV_ALTERNATIVE_EARLY default y help - This will apply the memory type errata to handle the non-standard - memory type bits in page-table-entries on T-Head SoCs. + This will apply the memory attribute extension errata to handle the + non-standard PTE utilization on T-Head SoCs (XTheadMae). If you don't know what to do here, say "Y". diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts index 222a39d90f85d..1c2922a435b48 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts @@ -160,9 +160,11 @@ status = "okay"; }; +/* UBUNTU: PCIe support is not yet ready, so disable it for now &pcie { status = "okay"; }; +*/ &qspi { status = "okay"; diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi index 6150f3397bff9..b25167e995adb 100644 --- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi @@ -42,7 +42,7 @@ }; }; cpu1: cpu@1 { - compatible = "sifive,bullet0", "riscv"; + compatible = "sifive,u74-mc", "sifive,bullet0", "riscv"; d-cache-block-size = <64>; d-cache-sets = <64>; d-cache-size = <32768>; @@ -69,7 +69,7 @@ }; }; cpu2: cpu@2 { - compatible = "sifive,bullet0", "riscv"; + compatible = "sifive,u74-mc", "sifive,bullet0", "riscv"; d-cache-block-size = <64>; d-cache-sets = <64>; d-cache-size = <32768>; @@ -96,7 +96,7 @@ }; }; cpu3: cpu@3 { - compatible = "sifive,bullet0", "riscv"; + compatible = "sifive,u74-mc", "sifive,bullet0", "riscv"; d-cache-block-size = <64>; d-cache-sets = <64>; d-cache-size = <32768>; @@ -123,7 +123,7 @@ }; }; cpu4: cpu@4 { - compatible = "sifive,bullet0", "riscv"; + compatible = "sifive,u74-mc", "sifive,bullet0", "riscv"; d-cache-block-size = <64>; d-cache-sets = <64>; d-cache-size = <32768>; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00-microsemi.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00-microsemi.dts new file mode 100644 index 0000000000000..4d25606f4e0cf --- /dev/null +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00-microsemi.dts @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) + +#include "hifive-unleashed-a00.dts" + +/ { + soc { + pcie: pcie@2030000000 { + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + compatible = "microsemi,ms-pf-axi-pcie-host"; + device_type = "pci"; + bus-range = <0x01 0x7f>; + interrupt-map = <0 0 0 1 &ms_pcie_intc 0 0 0 0 2 &ms_pcie_intc 1 0 0 0 3 &ms_pcie_intc 2 0 0 0 4 &ms_pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + interrupt-parent = <&plic0>; + interrupts = <32>; + ranges = <0x3000000 0x0 0x40000000 0x0 0x40000000 0x0 0x20000000>; + reg = <0x20 0x30000000 0x0 0x4000000 0x20 0x0 0x0 0x100000>; + reg-names = "control", "apb"; + ms_pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7100.dtsi b/arch/riscv/boot/dts/starfive/jh7100.dtsi index 8bcf36d07f3f7..5d499d8aa8044 100644 --- a/arch/riscv/boot/dts/starfive/jh7100.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7100.dtsi @@ -116,6 +116,7 @@ osc_sys: osc-sys { compatible = "fixed-clock"; #clock-cells = <0>; + clock-output-names = "osc_sys"; /* This value must be overridden by the board */ clock-frequency = <0>; }; @@ -123,6 +124,7 @@ osc_aud: osc-aud { compatible = "fixed-clock"; #clock-cells = <0>; + clock-output-names = "osc_aud"; /* This value must be overridden by the board */ clock-frequency = <0>; }; @@ -130,6 +132,7 @@ gmac_rmii_ref: gmac-rmii-ref { compatible = "fixed-clock"; #clock-cells = <0>; + clock-output-names = "gmac_rmii_ref"; /* Should be overridden by the board when needed */ clock-frequency = <0>; }; @@ -137,6 +140,7 @@ gmac_gr_mii_rxclk: gmac-gr-mii-rxclk { compatible = "fixed-clock"; #clock-cells = <0>; + clock-output-names = "gmac_gr_mii_rxclk"; /* Should be overridden by the board when needed */ clock-frequency = <0>; }; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi index b89e9791efa72..c9bf3e0332f6d 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi @@ -189,7 +189,6 @@ axp15060: pmic@36 { compatible = "x-powers,axp15060"; reg = <0x36>; - interrupts = <0>; interrupt-controller; #interrupt-cells = <1>; @@ -230,24 +229,6 @@ status = "okay"; }; -&i2srx { - pinctrl-names = "default"; - pinctrl-0 = <&i2srx_pins>; - status = "okay"; -}; - -&i2stx0 { - pinctrl-names = "default"; - pinctrl-0 = <&mclk_ext_pins>; - status = "okay"; -}; - -&i2stx1 { - pinctrl-names = "default"; - pinctrl-0 = <&i2stx1_pins>; - status = "okay"; -}; - &mmc0 { max-frequency = <100000000>; assigned-clocks = <&syscrg JH7110_SYSCLK_SDIO0_SDCARD>; @@ -392,46 +373,6 @@ }; }; - i2srx_pins: i2srx-0 { - clk-sd-pins { - pinmux = , - , - , - , - ; - input-enable; - }; - }; - - i2stx1_pins: i2stx1-0 { - sd-pins { - pinmux = ; - bias-disable; - input-disable; - }; - }; - - mclk_ext_pins: mclk-ext-0 { - mclk-ext-pins { - pinmux = ; - input-enable; - }; - }; - mmc0_pins: mmc0-0 { rst-pins { pinmux = ; - bias-pull-up; - drive-strength = <2>; - input-disable; - input-schmitt-disable; - slew-rate = <0>; - }; - - rx-pins { - pinmux = ; - input-enable; - }; - - sync-pins { - pinmux = ; - input-enable; - }; - - pcmclk-pins { - pinmux = ; - input-enable; - }; - }; - uart0_pins: uart0-0 { tx-pins { pinmux = ; - status = "okay"; -}; - &uart0 { pinctrl-names = "default"; pinctrl-0 = <&uart0_pins>; diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index b1c410bbc1aec..bf6a0a6318ee3 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -19,20 +19,26 @@ #include #include -static bool errata_probe_pbmt(unsigned int stage, - unsigned long arch_id, unsigned long impid) +#define CSR_TH_SXSTATUS 0x5c0 +#define SXSTATUS_MAEE _AC(0x200000, UL) + +static bool errata_probe_mae(unsigned int stage, + unsigned long arch_id, unsigned long impid) { - if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PBMT)) + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_MAE)) return false; if (arch_id != 0 || impid != 0) return false; - if (stage == RISCV_ALTERNATIVES_EARLY_BOOT || - stage == RISCV_ALTERNATIVES_MODULE) - return true; + if (stage != RISCV_ALTERNATIVES_EARLY_BOOT && + stage != RISCV_ALTERNATIVES_MODULE) + return false; + + if (!(csr_read(CSR_TH_SXSTATUS) & SXSTATUS_MAEE)) + return false; - return false; + return true; } /* @@ -140,8 +146,8 @@ static u32 thead_errata_probe(unsigned int stage, { u32 cpu_req_errata = 0; - if (errata_probe_pbmt(stage, archid, impid)) - cpu_req_errata |= BIT(ERRATA_THEAD_PBMT); + if (errata_probe_mae(stage, archid, impid)) + cpu_req_errata |= BIT(ERRATA_THEAD_MAE); errata_probe_cmo(stage, archid, impid); diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index ea33288f8a25b..9bad9dfa2f7a1 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -23,7 +23,7 @@ #endif #ifdef CONFIG_ERRATA_THEAD -#define ERRATA_THEAD_PBMT 0 +#define ERRATA_THEAD_MAE 0 #define ERRATA_THEAD_PMU 1 #define ERRATA_THEAD_NUMBER 2 #endif @@ -53,20 +53,20 @@ asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID, \ * in the default case. */ #define ALT_SVPBMT_SHIFT 61 -#define ALT_THEAD_PBMT_SHIFT 59 +#define ALT_THEAD_MAE_SHIFT 59 #define ALT_SVPBMT(_val, prot) \ asm(ALTERNATIVE_2("li %0, 0\t\nnop", \ "li %0, %1\t\nslli %0,%0,%3", 0, \ RISCV_ISA_EXT_SVPBMT, CONFIG_RISCV_ISA_SVPBMT, \ "li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID, \ - ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \ + ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \ : "=r"(_val) \ : "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT), \ - "I"(prot##_THEAD >> ALT_THEAD_PBMT_SHIFT), \ + "I"(prot##_THEAD >> ALT_THEAD_MAE_SHIFT), \ "I"(ALT_SVPBMT_SHIFT), \ - "I"(ALT_THEAD_PBMT_SHIFT)) + "I"(ALT_THEAD_MAE_SHIFT)) -#ifdef CONFIG_ERRATA_THEAD_PBMT +#ifdef CONFIG_ERRATA_THEAD_MAE /* * IO/NOCACHE memory types are handled together with svpbmt, * so on T-Head chips, check if no other memory type is set, @@ -83,11 +83,11 @@ asm volatile(ALTERNATIVE( \ "slli t3, t3, %3\n\t" \ "or %0, %0, t3\n\t" \ "2:", THEAD_VENDOR_ID, \ - ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \ + ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \ : "+r"(_val) \ - : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT), \ - "I"(_PAGE_PMA_THEAD >> ALT_THEAD_PBMT_SHIFT), \ - "I"(ALT_THEAD_PBMT_SHIFT) \ + : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_MAE_SHIFT), \ + "I"(_PAGE_PMA_THEAD >> ALT_THEAD_MAE_SHIFT), \ + "I"(ALT_THEAD_MAE_SHIFT) \ : "t3") #else #define ALT_THEAD_PMA(_val) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 57e887bfa34cb..94b3d6930fc37 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -89,7 +89,7 @@ typedef struct page *pgtable_t; #define PTE_FMT "%08lx" #endif -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) /* * We override this value as its generic definition uses __pa too early in * the boot process (before kernel_map.va_pa_offset is set). diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 6066822e7396f..39c6bb8254683 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -439,9 +439,11 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } +#ifdef CONFIG_RISCV_ISA_SVNAPOT #define pte_leaf_size(pte) (pte_napot(pte) ? \ napot_cont_size(napot_cont_order(pte)) :\ PAGE_SIZE) +#endif #ifdef CONFIG_NUMA_BALANCING /* @@ -886,7 +888,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) #define PAGE_SHARED __pgprot(0) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL -#define TASK_SIZE 0xffffffffUL +#define TASK_SIZE _AC(-1, UL) #define VMALLOC_START _AC(0, UL) #define VMALLOC_END TASK_SIZE diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 6e68f8dff76bc..0fab508a65b3c 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -370,6 +370,8 @@ static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1 static inline void sbi_init(void) {} #endif /* CONFIG_RISCV_SBI */ +unsigned long riscv_get_mvendorid(void); +unsigned long riscv_get_marchid(void); unsigned long riscv_cached_mvendorid(unsigned int cpu_id); unsigned long riscv_cached_marchid(unsigned int cpu_id); unsigned long riscv_cached_mimpid(unsigned int cpu_id); diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index ec0cab9fbddd0..72ec1d9bd3f31 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -319,7 +319,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ if (unlikely(__kr_err)) \ @@ -328,7 +328,7 @@ do { \ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 10aaa83db89ef..95050ebe9ad00 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -34,7 +34,7 @@ #define AT_L3_CACHEGEOMETRY 47 /* entries in ARCH_DLINFO */ -#define AT_VECTOR_SIZE_ARCH 9 +#define AT_VECTOR_SIZE_ARCH 10 #define AT_MINSIGSTKSZ 51 #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 9f2a8e3ff2048..2902f68dc913a 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -54,7 +54,7 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_EXT_ZFHMIN (1 << 28) #define RISCV_HWPROBE_EXT_ZIHINTNTL (1 << 29) #define RISCV_HWPROBE_EXT_ZVFH (1 << 30) -#define RISCV_HWPROBE_EXT_ZVFHMIN (1 << 31) +#define RISCV_HWPROBE_EXT_ZVFHMIN (1ULL << 31) #define RISCV_HWPROBE_EXT_ZFA (1ULL << 32) #define RISCV_HWPROBE_EXT_ZTSO (1ULL << 33) #define RISCV_HWPROBE_EXT_ZACAS (1ULL << 34) diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index d11d6320fb0d2..c1f3655238fd2 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -139,6 +139,34 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) return -1; } +unsigned long __init riscv_get_marchid(void) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->marchid = csr_read(CSR_MARCHID); +#else + ci->marchid = 0; +#endif + return ci->marchid; +} + +unsigned long __init riscv_get_mvendorid(void) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->mvendorid = csr_read(CSR_MVENDORID); +#else + ci->mvendorid = 0; +#endif + return ci->mvendorid; +} + DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); unsigned long riscv_cached_mvendorid(unsigned int cpu_id) @@ -170,12 +198,16 @@ static int riscv_cpuinfo_starting(unsigned int cpu) struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); #if IS_ENABLED(CONFIG_RISCV_SBI) - ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); - ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); + if (!ci->mvendorid) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); + if (!ci->marchid) + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid(); #elif IS_ENABLED(CONFIG_RISCV_M_MODE) - ci->mvendorid = csr_read(CSR_MVENDORID); - ci->marchid = csr_read(CSR_MARCHID); + if (!ci->mvendorid) + ci->mvendorid = csr_read(CSR_MVENDORID); + if (!ci->marchid) + ci->marchid = csr_read(CSR_MARCHID); ci->mimpid = csr_read(CSR_MIMPID); #else ci->mvendorid = 0; diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c index 1cc7df740eddc..e6fbaaf549562 100644 --- a/arch/riscv/kernel/cpu_ops_sbi.c +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -72,7 +72,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle) /* Make sure tidle is updated */ smp_mb(); bdata->task_ptr = tidle; - bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE; + bdata->stack_ptr = task_pt_regs(tidle); /* Make sure boot data is updated */ smp_mb(); hsm_data = __pa(bdata); diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c index 613872b0a21ac..24869eb889085 100644 --- a/arch/riscv/kernel/cpu_ops_spinwait.c +++ b/arch/riscv/kernel/cpu_ops_spinwait.c @@ -34,8 +34,7 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid, /* Make sure tidle is updated */ smp_mb(); - WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], - task_stack_page(tidle) + THREAD_SIZE); + WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], task_pt_regs(tidle)); WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle); } diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 79a5a35fab964..ec1852f47b280 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -503,6 +503,8 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) struct acpi_table_header *rhct; acpi_status status; unsigned int cpu; + u64 boot_vendorid; + u64 boot_archid; if (!acpi_disabled) { status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); @@ -510,6 +512,9 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) return; } + boot_vendorid = riscv_get_mvendorid(); + boot_archid = riscv_get_marchid(); + for_each_possible_cpu(cpu) { struct riscv_isainfo *isainfo = &hart_isa[cpu]; unsigned long this_hwcap = 0; @@ -557,8 +562,7 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) * CPU cores with the ratified spec will contain non-zero * marchid. */ - if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID && - riscv_cached_marchid(cpu) == 0x0) { + if (acpi_disabled && boot_vendorid == THEAD_VENDOR_ID && boot_archid == 0x0) { this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v]; clear_bit(RISCV_ISA_EXT_v, isainfo->isa); } @@ -612,7 +616,7 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) if (ext->subset_ext_size) { for (int j = 0; j < ext->subset_ext_size; j++) { - if (riscv_isa_extension_check(ext->subset_ext_ids[i])) + if (riscv_isa_extension_check(ext->subset_ext_ids[j])) set_bit(ext->subset_ext_ids[j], isainfo->isa); } } diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 37e87fdcf6a00..30e12b310cab7 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -80,6 +80,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len) */ lockdep_assert_held(&text_mutex); + preempt_disable(); + if (across_pages) patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); @@ -92,6 +94,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len) if (across_pages) patch_unmap(FIX_TEXT_POKE1); + preempt_enable(); + return 0; } NOKPROBE_SYMBOL(__patch_insn_set); @@ -122,6 +126,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len) if (!riscv_patch_in_stop_machine) lockdep_assert_held(&text_mutex); + preempt_disable(); + if (across_pages) patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); @@ -134,6 +140,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len) if (across_pages) patch_unmap(FIX_TEXT_POKE1); + preempt_enable(); + return ret; } NOKPROBE_SYMBOL(__patch_insn_write); diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c index 7142ec42e889f..a69dfa610aa85 100644 --- a/arch/riscv/kernel/probes/ftrace.c +++ b/arch/riscv/kernel/probes/ftrace.c @@ -11,6 +11,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe_ctlblk *kcb; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 92922dbd5b5c1..e4bc61c4e58af 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -27,8 +27,6 @@ #include #include -register unsigned long gp_in_global __asm__("gp"); - #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include unsigned long __stack_chk_guard __read_mostly; @@ -37,7 +35,7 @@ EXPORT_SYMBOL(__stack_chk_guard); extern asmlinkage void ret_from_fork(void); -void arch_cpu_idle(void) +void noinstr arch_cpu_idle(void) { cpu_do_idle(); } @@ -207,7 +205,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (unlikely(args->fn)) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gp = gp_in_global; /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 501e66debf697..5a2edd7f027e5 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -119,6 +119,13 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) struct __sc_riscv_v_state __user *state = sc_vec; void __user *datap; + /* + * Mark the vstate as clean prior performing the actual copy, + * to avoid getting the vstate incorrectly clobbered by the + * discarded vector state. + */ + riscv_v_vstate_set_restore(current, regs); + /* Copy everything of __sc_riscv_v_state except datap. */ err = __copy_from_user(¤t->thread.vstate, &state->v_state, offsetof(struct __riscv_v_ext_state, datap)); @@ -133,13 +140,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) * Copy the whole vector content from user space datap. Use * copy_from_user to prevent information leak. */ - err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); - if (unlikely(err)) - return err; - - riscv_v_vstate_set_restore(current, regs); - - return err; + return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); } #else #define save_v_state(task, regs) (0) diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 519b6bd946e5d..bbdb9ec62df0a 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -26,7 +26,7 @@ #include #include -#include +#include #include #include #include @@ -239,9 +239,10 @@ asmlinkage __visible void smp_callin(void) riscv_user_isa_enable(); /* - * Remote TLB flushes are ignored while the CPU is offline, so emit - * a local TLB flush right now just in case. + * Remote cache and TLB flushes are ignored while the CPU is offline, + * so flush them both right now just in case. */ + local_flush_icache_all(); local_flush_tlb_all(); complete(&cpu_running); /* diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 64a9c093aef93..528ec7cc9a622 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -18,6 +18,16 @@ extern asmlinkage void ret_from_exception(void); +static inline int fp_is_valid(unsigned long fp, unsigned long sp) +{ + unsigned long low, high; + + low = sp + sizeof(struct stackframe); + high = ALIGN(sp, THREAD_SIZE); + + return !(fp < low || fp > high || fp & 0x07); +} + void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { @@ -41,21 +51,19 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, } for (;;) { - unsigned long low, high; struct stackframe *frame; if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc)))) break; - /* Validate frame pointer */ - low = sp + sizeof(struct stackframe); - high = ALIGN(sp, THREAD_SIZE); - if (unlikely(fp < low || fp > high || fp & 0x7)) + if (unlikely(!fp_is_valid(fp, sp))) break; + /* Unwind stack frame */ frame = (struct stackframe *)fp - 1; sp = fp; - if (regs && (regs->epc == pc) && (frame->fp & 0x7)) { + if (regs && (regs->epc == pc) && fp_is_valid(frame->ra, sp)) { + /* We hit function where ra is not saved on the stack */ fp = frame->ra; pc = regs->ra; } else { diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index a1b9be3c4332d..142f5f5168fb1 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -121,7 +121,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) print_vma_addr(KERN_CONT " in ", instruction_pointer(regs)); pr_cont("\n"); __show_regs(regs); - dump_instr(KERN_EMERG, regs); + dump_instr(KERN_INFO, regs); } force_sig_fault(signo, code, (void __user *)addr); diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 8ded225e8c5b1..c2ed4e689bf96 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -632,7 +632,7 @@ void unaligned_emulation_finish(void) * accesses emulated since tasks requesting such control can run on any * CPU. */ - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_EMULATED) { return; diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 9b517fe1b8a8e..272c431ac5b9f 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -37,6 +37,7 @@ endif # Disable -pg to prevent insert call site CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) +CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) # Disable profiling and instrumentation for VDSO code GCOV_PROFILE := n diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c index 39e72aa016a4c..b467ba5ed9100 100644 --- a/arch/riscv/kvm/aia_aplic.c +++ b/arch/riscv/kvm/aia_aplic.c @@ -137,11 +137,21 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) raw_spin_lock_irqsave(&irqd->lock, flags); sm = irqd->sourcecfg & APLIC_SOURCECFG_SM_MASK; - if (!pending && - ((sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) || - (sm == APLIC_SOURCECFG_SM_LEVEL_LOW))) + if (sm == APLIC_SOURCECFG_SM_INACTIVE) goto skip_write_pending; + if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH || + sm == APLIC_SOURCECFG_SM_LEVEL_LOW) { + if (!pending) + goto skip_write_pending; + if ((irqd->state & APLIC_IRQ_STATE_INPUT) && + sm == APLIC_SOURCECFG_SM_LEVEL_LOW) + goto skip_write_pending; + if (!(irqd->state & APLIC_IRQ_STATE_INPUT) && + sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) + goto skip_write_pending; + } + if (pending) irqd->state |= APLIC_IRQ_STATE_PENDING; else @@ -187,16 +197,31 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled) static bool aplic_read_input(struct aplic *aplic, u32 irq) { - bool ret; - unsigned long flags; + u32 sourcecfg, sm, raw_input, irq_inverted; struct aplic_irq *irqd; + unsigned long flags; + bool ret = false; if (!irq || aplic->nr_irqs <= irq) return false; irqd = &aplic->irqs[irq]; raw_spin_lock_irqsave(&irqd->lock, flags); - ret = (irqd->state & APLIC_IRQ_STATE_INPUT) ? true : false; + + sourcecfg = irqd->sourcecfg; + if (sourcecfg & APLIC_SOURCECFG_D) + goto skip; + + sm = sourcecfg & APLIC_SOURCECFG_SM_MASK; + if (sm == APLIC_SOURCECFG_SM_INACTIVE) + goto skip; + + raw_input = (irqd->state & APLIC_IRQ_STATE_INPUT) ? 1 : 0; + irq_inverted = (sm == APLIC_SOURCECFG_SM_LEVEL_LOW || + sm == APLIC_SOURCECFG_SM_EDGE_FALL) ? 1 : 0; + ret = !!(raw_input ^ irq_inverted); + +skip: raw_spin_unlock_irqrestore(&irqd->lock, flags); return ret; diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index 0eb689351b7d0..5cd407c6a8e4f 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -237,10 +237,11 @@ static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr) static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr) { - u32 hart, group = 0; + u32 hart = 0, group = 0; - hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & - GENMASK_ULL(aia->nr_hart_bits - 1, 0); + if (aia->nr_hart_bits) + hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & + GENMASK_ULL(aia->nr_hart_bits - 1, 0); if (aia->nr_group_bits) group = (addr >> aia->nr_group_shift) & GENMASK_ULL(aia->nr_group_bits - 1, 0); diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index 7a6abed41bc17..ee7215f4071f5 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -7,6 +7,8 @@ #include #include +#include + #define INSN_OPCODE_MASK 0x007c #define INSN_OPCODE_SHIFT 2 #define INSN_OPCODE_SYSTEM 28 @@ -213,9 +215,20 @@ struct csr_func { unsigned long wr_mask); }; +static int seed_csr_rmw(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + if (!riscv_isa_extension_available(vcpu->arch.isa, ZKR)) + return KVM_INSN_ILLEGAL_TRAP; + + return KVM_INSN_EXIT_TO_USER_SPACE; +} + static const struct csr_func csr_funcs[] = { KVM_RISCV_VCPU_AIA_CSR_FUNCS KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS + { .base = CSR_SEED, .count = 1, .func = seed_csr_rmw }, }; /** diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index 5f7355e960084..6e138f56e5c1d 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -714,9 +714,9 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu, switch (reg_subtype) { case KVM_REG_RISCV_ISA_SINGLE: return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val); - case KVM_REG_RISCV_SBI_MULTI_EN: + case KVM_REG_RISCV_ISA_MULTI_EN: return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true); - case KVM_REG_RISCV_SBI_MULTI_DIS: + case KVM_REG_RISCV_ISA_MULTI_DIS: return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false); default: return -ENOENT; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index fa34cf55037bd..96ab6d6d73df9 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -232,22 +232,23 @@ static void __init setup_bootmem(void) * In 64-bit, any use of __va/__pa before this point is wrong as we * did not know the start of DRAM before. */ - if (IS_ENABLED(CONFIG_64BIT)) + if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base; /* - * memblock allocator is not aware of the fact that last 4K bytes of - * the addressable memory can not be mapped because of IS_ERR_VALUE - * macro. Make sure that last 4k bytes are not usable by memblock - * if end of dram is equal to maximum addressable memory. For 64-bit - * kernel, this problem can't happen here as the end of the virtual - * address space is occupied by the kernel mapping then this check must - * be done as soon as the kernel mapping base address is determined. + * Reserve physical address space that would be mapped to virtual + * addresses greater than (void *)(-PAGE_SIZE) because: + * - This memory would overlap with ERR_PTR + * - This memory belongs to high memory, which is not supported + * + * This is not applicable to 64-bit kernel, because virtual addresses + * after (void *)(-PAGE_SIZE) are not linearly mapped: they are + * occupied by kernel mapping. Also it is unrealistic for high memory + * to exist on 64-bit platforms. */ if (!IS_ENABLED(CONFIG_64BIT)) { - max_mapped_addr = __pa(~(ulong)0); - if (max_mapped_addr == (phys_ram_end - 1)) - memblock_set_current_limit(max_mapped_addr - 4096); + max_mapped_addr = __va_to_pa_nodebug(-PAGE_SIZE); + memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr); } min_low_pfn = PFN_UP(phys_ram_base); @@ -669,6 +670,9 @@ void __init create_pgd_mapping(pgd_t *pgdp, static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va, phys_addr_t size) { + if (debug_pagealloc_enabled()) + return PAGE_SIZE; + if (pgtable_l5_enabled && !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE) return P4D_SIZE; @@ -824,6 +828,10 @@ static __init void set_satp_mode(uintptr_t dtb_pa) disable_pgtable_l4(); } + /* UBUNTU: Force disable sv57 and fallback to sv48 */ + if (pgtable_l5_enabled) + disable_pgtable_l5(); + memset(early_pg_dir, 0, PAGE_SIZE); memset(early_p4d, 0, PAGE_SIZE); memset(early_pud, 0, PAGE_SIZE); diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index 410056a50aa9f..271d01a5ba4da 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -387,17 +387,33 @@ int set_direct_map_default_noflush(struct page *page) } #ifdef CONFIG_DEBUG_PAGEALLOC +static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data) +{ + int enable = *(int *)data; + + unsigned long val = pte_val(ptep_get(pte)); + + if (enable) + val |= _PAGE_PRESENT; + else + val &= ~_PAGE_PRESENT; + + set_pte(pte, __pte(val)); + + return 0; +} + void __kernel_map_pages(struct page *page, int numpages, int enable) { if (!debug_pagealloc_enabled()) return; - if (enable) - __set_memory((unsigned long)page_address(page), numpages, - __pgprot(_PAGE_PRESENT), __pgprot(0)); - else - __set_memory((unsigned long)page_address(page), numpages, - __pgprot(0), __pgprot(_PAGE_PRESENT)); + unsigned long start = (unsigned long)page_address(page); + unsigned long size = PAGE_SIZE * numpages; + + apply_to_existing_page_range(&init_mm, start, size, debug_pagealloc_set_page, &enable); + + flush_tlb_kernel_range(start, start + size); } #endif diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index 893566e004b73..07d743f87b3f6 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -99,7 +99,7 @@ static void __ipi_flush_tlb_range_asid(void *info) local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid); } -static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid, +static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid, unsigned long start, unsigned long size, unsigned long stride) { @@ -200,7 +200,7 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, void flush_tlb_kernel_range(unsigned long start, unsigned long end) { - __flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID, + __flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID, start, end - start, PAGE_SIZE); } diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 719a97e7edb2c..29f031f68f480 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -516,33 +516,33 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, break; /* src_reg = atomic_fetch_(dst_reg + off16, src_reg) */ case BPF_ADD | BPF_FETCH: - emit(is64 ? rv_amoadd_d(rs, rs, rd, 0, 0) : - rv_amoadd_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoadd_d(rs, rs, rd, 1, 1) : + rv_amoadd_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; case BPF_AND | BPF_FETCH: - emit(is64 ? rv_amoand_d(rs, rs, rd, 0, 0) : - rv_amoand_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoand_d(rs, rs, rd, 1, 1) : + rv_amoand_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; case BPF_OR | BPF_FETCH: - emit(is64 ? rv_amoor_d(rs, rs, rd, 0, 0) : - rv_amoor_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoor_d(rs, rs, rd, 1, 1) : + rv_amoor_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; case BPF_XOR | BPF_FETCH: - emit(is64 ? rv_amoxor_d(rs, rs, rd, 0, 0) : - rv_amoxor_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoxor_d(rs, rs, rd, 1, 1) : + rv_amoxor_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; /* src_reg = atomic_xchg(dst_reg + off16, src_reg); */ case BPF_XCHG: - emit(is64 ? rv_amoswap_d(rs, rs, rd, 0, 0) : - rv_amoswap_w(rs, rs, rd, 0, 0), ctx); + emit(is64 ? rv_amoswap_d(rs, rs, rd, 1, 1) : + rv_amoswap_w(rs, rs, rd, 1, 1), ctx); if (!is64) emit_zext_32(rs, ctx); break; @@ -740,6 +740,9 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of if (ret) return ret; + /* store prog start time */ + emit_mv(RV_REG_S1, RV_REG_A0, ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ @@ -747,9 +750,6 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of /* nop reserved for conditional jump */ emit(rv_nop(), ctx); - /* store prog start time */ - emit_mv(RV_REG_S1, RV_REG_A0, ctx); - /* arg1: &args_off */ emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx); if (!p->jited) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index fe565f3a3a917..a7616d5473e26 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -82,7 +82,7 @@ config S390 select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYSCALL_WRAPPER - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARCH_HAS_VDSO_DATA select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK @@ -113,6 +113,7 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_BH select ARCH_INLINE_WRITE_UNLOCK_IRQ select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 9cc76e631759b..3c2855c3d6df0 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -32,7 +32,6 @@ unsigned long __bootdata_preserved(max_mappable); unsigned long __bootdata(ident_map_size); u64 __bootdata_preserved(stfle_fac_list[16]); -u64 __bootdata_preserved(alt_stfle_fac_list[16]); struct oldmem_data __bootdata_preserved(oldmem_data); struct machine_info machine; diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index e3a4500a5a757..47e1f54c587ae 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -366,7 +366,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pmd = boot_crst_alloc(_SEGMENT_ENTRY_EMPTY); pud_populate(&init_mm, pud, pmd); - } else if (pud_large(*pud)) { + } else if (pud_leaf(*pud)) { continue; } pgtable_pmd_populate(pud, addr, next, mode); diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index b378e2b57ad87..c786538e397c0 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -166,28 +166,86 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t; -/** - * cpacf_query() - check if a specific CPACF function is available - * @opcode: the opcode of the crypto instruction - * @func: the function code to test for - * - * Executes the query function for the given crypto instruction @opcode - * and checks if @func is available - * - * Returns 1 if @func is available for @opcode, 0 otherwise +/* + * Prototype for a not existing function to produce a link + * error if __cpacf_query() or __cpacf_check_opcode() is used + * with an invalid compile time const opcode. */ -static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) +void __cpacf_bad_opcode(void); + +static __always_inline void __cpacf_query_rre(u32 opc, u8 r1, u8 r2, + cpacf_mask_t *mask) { asm volatile( - " lghi 0,0\n" /* query function */ - " lgr 1,%[mask]\n" - " spm 0\n" /* pckmo doesn't change the cc */ - /* Parameter regs are ignored, but must be nonzero and unique */ - "0: .insn rrf,%[opc] << 16,2,4,6,0\n" - " brc 1,0b\n" /* handle partial completion */ - : "=m" (*mask) - : [mask] "d" ((unsigned long)mask), [opc] "i" (opcode) - : "cc", "0", "1"); + " la %%r1,%[mask]\n" + " xgr %%r0,%%r0\n" + " .insn rre,%[opc] << 16,%[r1],%[r2]\n" + : [mask] "=R" (*mask) + : [opc] "i" (opc), + [r1] "i" (r1), [r2] "i" (r2) + : "cc", "r0", "r1"); +} + +static __always_inline void __cpacf_query_rrf(u32 opc, + u8 r1, u8 r2, u8 r3, u8 m4, + cpacf_mask_t *mask) +{ + asm volatile( + " la %%r1,%[mask]\n" + " xgr %%r0,%%r0\n" + " .insn rrf,%[opc] << 16,%[r1],%[r2],%[r3],%[m4]\n" + : [mask] "=R" (*mask) + : [opc] "i" (opc), [r1] "i" (r1), [r2] "i" (r2), + [r3] "i" (r3), [m4] "i" (m4) + : "cc", "r0", "r1"); +} + +static __always_inline void __cpacf_query(unsigned int opcode, + cpacf_mask_t *mask) +{ + switch (opcode) { + case CPACF_KDSA: + __cpacf_query_rre(CPACF_KDSA, 0, 2, mask); + break; + case CPACF_KIMD: + __cpacf_query_rre(CPACF_KIMD, 0, 2, mask); + break; + case CPACF_KLMD: + __cpacf_query_rre(CPACF_KLMD, 0, 2, mask); + break; + case CPACF_KM: + __cpacf_query_rre(CPACF_KM, 2, 4, mask); + break; + case CPACF_KMA: + __cpacf_query_rrf(CPACF_KMA, 2, 4, 6, 0, mask); + break; + case CPACF_KMAC: + __cpacf_query_rre(CPACF_KMAC, 0, 2, mask); + break; + case CPACF_KMC: + __cpacf_query_rre(CPACF_KMC, 2, 4, mask); + break; + case CPACF_KMCTR: + __cpacf_query_rrf(CPACF_KMCTR, 2, 4, 6, 0, mask); + break; + case CPACF_KMF: + __cpacf_query_rre(CPACF_KMF, 2, 4, mask); + break; + case CPACF_KMO: + __cpacf_query_rre(CPACF_KMO, 2, 4, mask); + break; + case CPACF_PCC: + __cpacf_query_rre(CPACF_PCC, 0, 0, mask); + break; + case CPACF_PCKMO: + __cpacf_query_rre(CPACF_PCKMO, 0, 0, mask); + break; + case CPACF_PRNO: + __cpacf_query_rre(CPACF_PRNO, 2, 4, mask); + break; + default: + __cpacf_bad_opcode(); + } } static __always_inline int __cpacf_check_opcode(unsigned int opcode) @@ -211,10 +269,21 @@ static __always_inline int __cpacf_check_opcode(unsigned int opcode) case CPACF_KMA: return test_facility(146); /* check for MSA8 */ default: - BUG(); + __cpacf_bad_opcode(); + return 0; } } +/** + * cpacf_query() - check if a specific CPACF function is available + * @opcode: the opcode of the crypto instruction + * @func: the function code to test for + * + * Executes the query function for the given crypto instruction @opcode + * and checks if @func is available + * + * Returns 1 if @func is available for @opcode, 0 otherwise + */ static __always_inline int cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { if (__cpacf_check_opcode(opcode)) { diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h index 4f21ae561e4dd..390906b8e386e 100644 --- a/arch/s390/include/asm/dwarf.h +++ b/arch/s390/include/asm/dwarf.h @@ -9,6 +9,7 @@ #define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset #define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset #define CFI_RESTORE .cfi_restore +#define CFI_REL_OFFSET .cfi_rel_offset #ifdef CONFIG_AS_CFI_VAL_OFFSET #define CFI_VAL_OFFSET .cfi_val_offset diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 5a82b08f03cd3..77e479d44f1e3 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -8,12 +8,8 @@ #ifndef __ASSEMBLY__ -#ifdef CONFIG_CC_IS_CLANG -/* https://bugs.llvm.org/show_bug.cgi?id=41424 */ -#define ftrace_return_address(n) 0UL -#else -#define ftrace_return_address(n) __builtin_return_address(n) -#endif +unsigned long return_address(unsigned int n); +#define ftrace_return_address(n) return_address(n) void ftrace_caller(void); diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index 5cc46e0dde620..9725586f42597 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -146,7 +146,7 @@ int gmap_mprotect_notify(struct gmap *, unsigned long start, void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); -int gmap_mark_unmergeable(void); +int s390_disable_cow_sharing(void); void s390_unlist_old_asce(struct gmap *gmap); int s390_replace_asce(struct gmap *gmap); void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns); diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index b0d00032479d6..afb9544fb0074 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -139,6 +139,7 @@ int ipl_report_add_component(struct ipl_report *report, struct kexec_buf *kbuf, unsigned char flags, unsigned short cert); int ipl_report_add_certificate(struct ipl_report *report, void *key, unsigned long addr, unsigned long len); +bool ipl_get_secureboot(void); /* * DIAG 308 support diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index bb1b4bef1878b..4c2dc7abc2858 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -32,6 +32,11 @@ typedef struct { unsigned int uses_skeys:1; /* The mmu context uses CMM. */ unsigned int uses_cmm:1; + /* + * The mmu context allows COW-sharing of memory pages (KSM, zeropage). + * Note that COW-sharing during fork() is currently always allowed. + */ + unsigned int allow_cow_sharing:1; /* The gmaps associated with this context are allowed to use huge pages. */ unsigned int allow_gmap_hpage_1m:1; } mm_context_t; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 929af18b09081..a7789a9f62186 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -35,6 +35,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.has_pgste = 0; mm->context.uses_skeys = 0; mm->context.uses_cmm = 0; + mm->context.allow_cow_sharing = 1; mm->context.allow_gmap_hpage_1m = 0; #endif switch (mm->context.asce_limit) { diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 1299b56e43f6f..e74200b1b895a 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -566,10 +566,20 @@ static inline pud_t set_pud_bit(pud_t pud, pgprot_t prot) } /* - * In the case that a guest uses storage keys - * faults should no longer be backed by zero pages + * As soon as the guest uses storage keys or enables PV, we deduplicate all + * mapped shared zeropages and prevent new shared zeropages from getting + * mapped. */ -#define mm_forbids_zeropage mm_has_pgste +#define mm_forbids_zeropage mm_forbids_zeropage +static inline int mm_forbids_zeropage(struct mm_struct *mm) +{ +#ifdef CONFIG_PGSTE + if (!mm->context.allow_cow_sharing) + return 1; +#endif + return 0; +} + static inline int mm_uses_skeys(struct mm_struct *mm) { #ifdef CONFIG_PGSTE @@ -730,7 +740,7 @@ static inline int pud_bad(pud_t pud) { unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK; - if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud)) + if (type > _REGION_ENTRY_TYPE_R3 || pud_leaf(pud)) return 1; if (type < _REGION_ENTRY_TYPE_R3) return 0; @@ -1398,7 +1408,7 @@ static inline unsigned long pud_deref(pud_t pud) unsigned long origin_mask; origin_mask = _REGION_ENTRY_ORIGIN; - if (pud_large(pud)) + if (pud_leaf(pud)) origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; return (unsigned long)__va(pud_val(pud) & origin_mask); } @@ -1766,8 +1776,10 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, static inline pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); + pmd_t pmd; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); return pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd); } diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index c0b6e74d899a4..96dbc1c289611 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -99,6 +99,7 @@ void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; extern void execve_tail(void); +unsigned long vdso_text_size(void); unsigned long vdso_size(void); /* diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 31ec4f545e036..876eb7c3afdf5 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -2,6 +2,7 @@ #ifndef _ASM_S390_STACKTRACE_H #define _ASM_S390_STACKTRACE_H +#include #include #include #include @@ -13,6 +14,17 @@ struct stack_frame_user { unsigned long empty2[4]; }; +struct stack_frame_vdso_wrapper { + struct stack_frame_user sf; + unsigned long return_address; +}; + +struct perf_callchain_entry_ctx; + +void arch_stack_walk_user_common(stack_trace_consume_fn consume_entry, void *cookie, + struct perf_callchain_entry_ctx *entry, + const struct pt_regs *regs, bool perf); + enum stack_type { STACK_TYPE_UNKNOWN, STACK_TYPE_TASK, diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 7a562b4199c81..8bf461222029c 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -11,6 +11,8 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) # Do not trace early setup code CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_stacktrace.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_unwind_bc.o = $(CC_FLAGS_FTRACE) endif diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index fa5f6885c74aa..2f65bca2f3f1c 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -66,6 +66,11 @@ int main(void) OFFSET(__SF_SIE_CONTROL_PHYS, stack_frame, sie_control_block_phys); DEFINE(STACK_FRAME_OVERHEAD, sizeof(struct stack_frame)); BLANK(); + OFFSET(__SFUSER_BACKCHAIN, stack_frame_user, back_chain); + DEFINE(STACK_FRAME_USER_OVERHEAD, sizeof(struct stack_frame_user)); + OFFSET(__SFVDSO_RETURN_ADDRESS, stack_frame_vdso_wrapper, return_address); + DEFINE(STACK_FRAME_VDSO_OVERHEAD, sizeof(struct stack_frame_vdso_wrapper)); + BLANK(); /* idle data offsets */ OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter); OFFSET(__TIMER_IDLE_ENTER, s390_idle_data, timer_idle_enter); diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c index 56254fa06f990..4f26690302209 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -166,5 +166,6 @@ int populate_cache_leaves(unsigned int cpu) ci_leaf_init(this_leaf++, pvt, ctype, level, cpu); } } + this_cpu_ci->cpu_map_populated = true; return 0; } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 49a11f6dd7ae9..26c08ee877407 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -653,6 +653,7 @@ SYM_DATA_START_LOCAL(daton_psw) SYM_DATA_END(daton_psw) .section .rodata, "a" + .balign 8 #define SYSCALL(esame,emu) .quad __s390x_ ## esame SYM_DATA_START(sys_call_table) #include "asm/syscall_table.h" diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index c46381ea04ecb..7f6f8c438c265 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -296,6 +296,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe *p; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index ba75f6bee7742..f0cec6f6050a5 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -962,8 +962,8 @@ static ssize_t reipl_nvme_scpdata_write(struct file *filp, struct kobject *kobj, scpdata_len += padding; } - reipl_block_nvme->hdr.len = IPL_BP_FCP_LEN + scpdata_len; - reipl_block_nvme->nvme.len = IPL_BP0_FCP_LEN + scpdata_len; + reipl_block_nvme->hdr.len = IPL_BP_NVME_LEN + scpdata_len; + reipl_block_nvme->nvme.len = IPL_BP0_NVME_LEN + scpdata_len; reipl_block_nvme->nvme.scp_data_len = scpdata_len; return count; @@ -1858,9 +1858,9 @@ static int __init dump_nvme_init(void) } dump_block_nvme->hdr.len = IPL_BP_NVME_LEN; dump_block_nvme->hdr.version = IPL_PARM_BLOCK_VERSION; - dump_block_nvme->fcp.len = IPL_BP0_NVME_LEN; - dump_block_nvme->fcp.pbt = IPL_PBT_NVME; - dump_block_nvme->fcp.opt = IPL_PB0_NVME_OPT_DUMP; + dump_block_nvme->nvme.len = IPL_BP0_NVME_LEN; + dump_block_nvme->nvme.pbt = IPL_PBT_NVME; + dump_block_nvme->nvme.opt = IPL_PB0_NVME_OPT_DUMP; dump_capabilities |= DUMP_TYPE_NVME; return 0; } @@ -2520,3 +2520,8 @@ int ipl_report_free(struct ipl_report *report) } #endif + +bool ipl_get_secureboot(void) +{ + return !!ipl_secure_flag; +} diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index dfa77da2fd2ec..5fff629b1a898 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -218,39 +218,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - struct stack_frame_user __user *sf; - unsigned long ip, sp; - bool first = true; - - if (is_compat_task()) - return; - perf_callchain_store(entry, instruction_pointer(regs)); - sf = (void __user *)user_stack_pointer(regs); - pagefault_disable(); - while (entry->nr < entry->max_stack) { - if (__get_user(sp, &sf->back_chain)) - break; - if (__get_user(ip, &sf->gprs[8])) - break; - if (ip & 0x1) { - /* - * If the instruction address is invalid, and this - * is the first stack frame, assume r14 has not - * been written to the stack yet. Otherwise exit. - */ - if (first && !(regs->gprs[14] & 0x1)) - ip = regs->gprs[14]; - else - break; - } - perf_callchain_store(entry, ip); - /* Sanity check: ABI requires SP to be aligned 8 bytes. */ - if (!sp || sp & 0x7) - break; - sf = (void __user *)sp; - first = false; - } - pagefault_enable(); + arch_stack_walk_user_common(NULL, NULL, entry, regs, true); } /* Perf definitions for PMU event attributes in sysfs */ diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index bf8a672b15a41..335e3f5d71f74 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -90,7 +90,6 @@ static void paicrypt_event_destroy(struct perf_event *event) event->cpu); struct paicrypt_map *cpump = mp->mapptr; - cpump->event = NULL; static_branch_dec(&pai_key); mutex_lock(&pai_reserve_mutex); debug_sprintf_event(cfm_dbg, 5, "%s event %#llx cpu %d users %d" @@ -348,10 +347,15 @@ static int paicrypt_add(struct perf_event *event, int flags) static void paicrypt_stop(struct perf_event *event, int flags) { - if (!event->attr.sample_period) /* Counting */ + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; + + if (!event->attr.sample_period) { /* Counting */ paicrypt_read(event); - else /* Sampling */ + } else { /* Sampling */ perf_sched_cb_dec(event->pmu); + cpump->event = NULL; + } event->hw.state = PERF_HES_STOPPED; } @@ -721,7 +725,7 @@ static int __init attr_event_init(void) for (i = 0; i < ARRAY_SIZE(paicrypt_ctrnames); i++) { ret = attr_event_init_one(attrs, i); if (ret) { - attr_event_free(attrs, i - 1); + attr_event_free(attrs, i); return ret; } } diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index af7f2b538c8fd..db37c38ddcee4 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -121,7 +121,6 @@ static void paiext_event_destroy(struct perf_event *event) struct paiext_map *cpump = mp->mapptr; mutex_lock(&paiext_reserve_mutex); - cpump->event = NULL; if (refcount_dec_and_test(&cpump->refcnt)) /* Last reference gone */ paiext_free(mp); paiext_root_free(); @@ -355,10 +354,15 @@ static int paiext_add(struct perf_event *event, int flags) static void paiext_stop(struct perf_event *event, int flags) { - if (!event->attr.sample_period) /* Counting */ + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + + if (!event->attr.sample_period) { /* Counting */ paiext_read(event); - else /* Sampling */ + } else { /* Sampling */ perf_sched_cb_dec(event->pmu); + cpump->event = NULL; + } event->hw.state = PERF_HES_STOPPED; } @@ -611,7 +615,7 @@ static int __init attr_event_init(void) for (i = 0; i < ARRAY_SIZE(paiext_ctrnames); i++) { ret = attr_event_init_one(attrs, i); if (ret) { - attr_event_free(attrs, i - 1); + attr_event_free(attrs, i); return ret; } } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index d1f3b56e7afc2..bf460a8c43ddd 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include @@ -155,7 +156,7 @@ unsigned int __bootdata_preserved(zlib_dfltcc_support); EXPORT_SYMBOL(zlib_dfltcc_support); u64 __bootdata_preserved(stfle_fac_list[16]); EXPORT_SYMBOL(stfle_fac_list); -u64 __bootdata_preserved(alt_stfle_fac_list[16]); +u64 alt_stfle_fac_list[16]; struct oldmem_data __bootdata_preserved(oldmem_data); unsigned long VMALLOC_START; @@ -891,6 +892,9 @@ void __init setup_arch(char **cmdline_p) log_component_list(); + if (ipl_get_secureboot()) + security_lock_kernel_down("Secure IPL mode", LOCKDOWN_INTEGRITY_MAX); + /* Have one command line that is parsed and saved in /proc/cmdline */ /* boot_command_line has been already set up in early.c */ *cmdline_p = boot_command_line; diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 94f440e383031..640363b2a1059 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -5,6 +5,7 @@ * Copyright IBM Corp. 2006 */ +#include #include #include #include @@ -62,42 +63,121 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, return 0; } -void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, - const struct pt_regs *regs) +static inline bool store_ip(stack_trace_consume_fn consume_entry, void *cookie, + struct perf_callchain_entry_ctx *entry, bool perf, + unsigned long ip) +{ +#ifdef CONFIG_PERF_EVENTS + if (perf) { + if (perf_callchain_store(entry, ip)) + return false; + return true; + } +#endif + return consume_entry(cookie, ip); +} + +static inline bool ip_invalid(unsigned long ip) +{ + /* + * Perform some basic checks if an instruction address taken + * from unreliable source is invalid. + */ + if (ip & 1) + return true; + if (ip < mmap_min_addr) + return true; + if (ip >= current->mm->context.asce_limit) + return true; + return false; +} + +static inline bool ip_within_vdso(unsigned long ip) { + return in_range(ip, current->mm->context.vdso_base, vdso_text_size()); +} + +void arch_stack_walk_user_common(stack_trace_consume_fn consume_entry, void *cookie, + struct perf_callchain_entry_ctx *entry, + const struct pt_regs *regs, bool perf) +{ + struct stack_frame_vdso_wrapper __user *sf_vdso; struct stack_frame_user __user *sf; unsigned long ip, sp; bool first = true; if (is_compat_task()) return; - if (!consume_entry(cookie, instruction_pointer(regs))) + if (!current->mm) + return; + ip = instruction_pointer(regs); + if (!store_ip(consume_entry, cookie, entry, perf, ip)) return; sf = (void __user *)user_stack_pointer(regs); pagefault_disable(); while (1) { if (__get_user(sp, &sf->back_chain)) break; - if (__get_user(ip, &sf->gprs[8])) + /* + * VDSO entry code has a non-standard stack frame layout. + * See VDSO user wrapper code for details. + */ + if (!sp && ip_within_vdso(ip)) { + sf_vdso = (void __user *)sf; + if (__get_user(ip, &sf_vdso->return_address)) + break; + sp = (unsigned long)sf + STACK_FRAME_VDSO_OVERHEAD; + sf = (void __user *)sp; + if (__get_user(sp, &sf->back_chain)) + break; + } else { + sf = (void __user *)sp; + if (__get_user(ip, &sf->gprs[8])) + break; + } + /* Sanity check: ABI requires SP to be 8 byte aligned. */ + if (sp & 0x7) break; - if (ip & 0x1) { + if (ip_invalid(ip)) { /* * If the instruction address is invalid, and this * is the first stack frame, assume r14 has not * been written to the stack yet. Otherwise exit. */ - if (first && !(regs->gprs[14] & 0x1)) - ip = regs->gprs[14]; - else + if (!first) + break; + ip = regs->gprs[14]; + if (ip_invalid(ip)) break; } - if (!consume_entry(cookie, ip)) - break; - /* Sanity check: ABI requires SP to be aligned 8 bytes. */ - if (!sp || sp & 0x7) - break; - sf = (void __user *)sp; + if (!store_ip(consume_entry, cookie, entry, perf, ip)) + return; first = false; } pagefault_enable(); } + +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs) +{ + arch_stack_walk_user_common(consume_entry, cookie, NULL, regs, false); +} + +unsigned long return_address(unsigned int n) +{ + struct unwind_state state; + unsigned long addr; + + /* Increment to skip current stack entry */ + n++; + + unwind_for_each_frame(&state, NULL, NULL, 0) { + addr = unwind_get_return_address(&state); + if (!addr) + break; + if (!n--) + return addr; + } + return 0; +} +EXPORT_SYMBOL_GPL(return_address); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index bbaefd84f15e4..e5e61121a5a7f 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -213,17 +213,22 @@ static unsigned long vdso_addr(unsigned long start, unsigned long len) return addr; } -unsigned long vdso_size(void) +unsigned long vdso_text_size(void) { - unsigned long size = VVAR_NR_PAGES * PAGE_SIZE; + unsigned long size; if (is_compat_task()) - size += vdso32_end - vdso32_start; + size = vdso32_end - vdso32_start; else - size += vdso64_end - vdso64_start; + size = vdso64_end - vdso64_start; return PAGE_ALIGN(size); } +unsigned long vdso_size(void) +{ + return vdso_text_size() + VVAR_NR_PAGES * PAGE_SIZE; +} + int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { unsigned long addr = VDSO_BASE; diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index caec7db6f9668..4800d80decee6 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -19,10 +19,12 @@ KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) KBUILD_AFLAGS_32 += -m31 -s KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) +KBUILD_CFLAGS_32 := $(filter-out -mpacked-stack,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_32)) -KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin +KBUILD_CFLAGS_32 := $(filter-out -fno-asynchronous-unwind-tables,$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin -fasynchronous-unwind-tables -LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \ +LDFLAGS_vdso32.so.dbg += -shared -soname=linux-vdso32.so.1 \ --hash-style=both --build-id=sha1 -melf_s390 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index e3c9085f8fa72..2f2e4e997030c 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -24,9 +24,12 @@ KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS)) KBUILD_AFLAGS_64 += -m64 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) +KBUILD_CFLAGS_64 := $(filter-out -mpacked-stack,$(KBUILD_CFLAGS_64)) KBUILD_CFLAGS_64 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_64)) -KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin -ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \ +KBUILD_CFLAGS_64 := $(filter-out -munaligned-symbols,$(KBUILD_CFLAGS_64)) +KBUILD_CFLAGS_64 := $(filter-out -fno-asynchronous-unwind-tables,$(KBUILD_CFLAGS_64)) +KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin -fasynchronous-unwind-tables +ldflags-y := -shared -soname=linux-vdso64.so.1 \ --hash-style=both --build-id=sha1 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index 57f62596e53b9..e26e68675c08d 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -6,8 +6,6 @@ #include #include -#define WRAPPER_FRAME_SIZE (STACK_FRAME_OVERHEAD+8) - /* * Older glibc version called vdso without allocating a stackframe. This wrapper * is just used to allocate a stackframe. See @@ -20,14 +18,17 @@ __ALIGN __kernel_\func: CFI_STARTPROC - aghi %r15,-WRAPPER_FRAME_SIZE - CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE) - CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD - stg %r14,STACK_FRAME_OVERHEAD(%r15) + aghi %r15,-STACK_FRAME_VDSO_OVERHEAD + CFI_DEF_CFA_OFFSET (STACK_FRAME_USER_OVERHEAD + STACK_FRAME_VDSO_OVERHEAD) + CFI_VAL_OFFSET 15,-STACK_FRAME_USER_OVERHEAD + stg %r14,__SFVDSO_RETURN_ADDRESS(%r15) + CFI_REL_OFFSET 14,__SFVDSO_RETURN_ADDRESS + xc __SFUSER_BACKCHAIN(8,%r15),__SFUSER_BACKCHAIN(%r15) brasl %r14,__s390_vdso_\func - lg %r14,STACK_FRAME_OVERHEAD(%r15) - aghi %r15,WRAPPER_FRAME_SIZE - CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD + lg %r14,__SFVDSO_RETURN_ADDRESS(%r15) + CFI_RESTORE 14 + aghi %r15,STACK_FRAME_VDSO_OVERHEAD + CFI_DEF_CFA_OFFSET STACK_FRAME_USER_OVERHEAD CFI_RESTORE 15 br %r14 CFI_ENDPROC diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index e0a88dcaf5cb7..24a18e5ef6e8e 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -210,13 +210,13 @@ void vtime_flush(struct task_struct *tsk) virt_timer_expire(); steal = S390_lowcore.steal_timer; - avg_steal = S390_lowcore.avg_steal_timer / 2; + avg_steal = S390_lowcore.avg_steal_timer; if ((s64) steal > 0) { S390_lowcore.steal_timer = 0; account_steal_time(cputime_to_nsecs(steal)); avg_steal += steal; } - S390_lowcore.avg_steal_timer = avg_steal; + S390_lowcore.avg_steal_timer = avg_steal / 2; } static u64 vtime_delta(void) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ea63ac7698891..7c17be6ad4802 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2631,9 +2631,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) if (r) break; - mmap_write_lock(current->mm); - r = gmap_mark_unmergeable(); - mmap_write_unlock(current->mm); + r = s390_disable_cow_sharing(); if (r) break; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 8da39deb56ca4..3b57837f3e914 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -596,7 +596,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) pud = pud_offset(p4d, vmaddr); VM_BUG_ON(pud_none(*pud)); /* large puds cannot yet be handled */ - if (pud_large(*pud)) + if (pud_leaf(*pud)) return -EFAULT; pmd = pmd_offset(pud, vmaddr); VM_BUG_ON(pmd_none(*pmd)); @@ -2547,41 +2547,6 @@ static inline void thp_split_mm(struct mm_struct *mm) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -/* - * Remove all empty zero pages from the mapping for lazy refaulting - * - This must be called after mm->context.has_pgste is set, to avoid - * future creation of zero pages - * - This must be called after THP was disabled. - * - * mm contracts with s390, that even if mm were to remove a page table, - * racing with the loop below and so causing pte_offset_map_lock() to fail, - * it will never insert a page table containing empty zero pages once - * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set. - */ -static int __zap_zero_pages(pmd_t *pmd, unsigned long start, - unsigned long end, struct mm_walk *walk) -{ - unsigned long addr; - - for (addr = start; addr != end; addr += PAGE_SIZE) { - pte_t *ptep; - spinlock_t *ptl; - - ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); - if (!ptep) - break; - if (is_zero_pfn(pte_pfn(*ptep))) - ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID)); - pte_unmap_unlock(ptep, ptl); - } - return 0; -} - -static const struct mm_walk_ops zap_zero_walk_ops = { - .pmd_entry = __zap_zero_pages, - .walk_lock = PGWALK_WRLOCK, -}; - /* * switch on pgstes for its userspace process (for kvm) */ @@ -2599,22 +2564,142 @@ int s390_enable_sie(void) mm->context.has_pgste = 1; /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - walk_page_range(mm, 0, TASK_SIZE, &zap_zero_walk_ops, NULL); mmap_write_unlock(mm); return 0; } EXPORT_SYMBOL_GPL(s390_enable_sie); -int gmap_mark_unmergeable(void) +static int find_zeropage_pte_entry(pte_t *pte, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + unsigned long *found_addr = walk->private; + + /* Return 1 of the page is a zeropage. */ + if (is_zero_pfn(pte_pfn(*pte))) { + /* + * Shared zeropage in e.g., a FS DAX mapping? We cannot do the + * right thing and likely don't care: FAULT_FLAG_UNSHARE + * currently only works in COW mappings, which is also where + * mm_forbids_zeropage() is checked. + */ + if (!is_cow_mapping(walk->vma->vm_flags)) + return -EFAULT; + + *found_addr = addr; + return 1; + } + return 0; +} + +static const struct mm_walk_ops find_zeropage_ops = { + .pte_entry = find_zeropage_pte_entry, + .walk_lock = PGWALK_WRLOCK, +}; + +/* + * Unshare all shared zeropages, replacing them by anonymous pages. Note that + * we cannot simply zap all shared zeropages, because this could later + * trigger unexpected userfaultfd missing events. + * + * This must be called after mm->context.allow_cow_sharing was + * set to 0, to avoid future mappings of shared zeropages. + * + * mm contracts with s390, that even if mm were to remove a page table, + * and racing with walk_page_range_vma() calling pte_offset_map_lock() + * would fail, it will never insert a page table containing empty zero + * pages once mm_forbids_zeropage(mm) i.e. + * mm->context.allow_cow_sharing is set to 0. + */ +static int __s390_unshare_zeropages(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); + unsigned long addr; + vm_fault_t fault; + int rc; + + for_each_vma(vmi, vma) { + /* + * We could only look at COW mappings, but it's more future + * proof to catch unexpected zeropages in other mappings and + * fail. + */ + if ((vma->vm_flags & VM_PFNMAP) || is_vm_hugetlb_page(vma)) + continue; + addr = vma->vm_start; + +retry: + rc = walk_page_range_vma(vma, addr, vma->vm_end, + &find_zeropage_ops, &addr); + if (rc < 0) + return rc; + else if (!rc) + continue; + + /* addr was updated by find_zeropage_pte_entry() */ + fault = handle_mm_fault(vma, addr, + FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, + NULL); + if (fault & VM_FAULT_OOM) + return -ENOMEM; + /* + * See break_ksm(): even after handle_mm_fault() returned 0, we + * must start the lookup from the current address, because + * handle_mm_fault() may back out if there's any difficulty. + * + * VM_FAULT_SIGBUS and VM_FAULT_SIGSEGV are unexpected but + * maybe they could trigger in the future on concurrent + * truncation. In that case, the shared zeropage would be gone + * and we can simply retry and make progress. + */ + cond_resched(); + goto retry; + } + + return 0; +} + +static int __s390_disable_cow_sharing(struct mm_struct *mm) { + int rc; + + if (!mm->context.allow_cow_sharing) + return 0; + + mm->context.allow_cow_sharing = 0; + + /* Replace all shared zeropages by anonymous pages. */ + rc = __s390_unshare_zeropages(mm); /* * Make sure to disable KSM (if enabled for the whole process or * individual VMAs). Note that nothing currently hinders user space * from re-enabling it. */ - return ksm_disable(current->mm); + if (!rc) + rc = ksm_disable(mm); + if (rc) + mm->context.allow_cow_sharing = 1; + return rc; +} + +/* + * Disable most COW-sharing of memory pages for the whole process: + * (1) Disable KSM and unmerge/unshare any KSM pages. + * (2) Disallow shared zeropages and unshare any zerpages that are mapped. + * + * Not that we currently don't bother with COW-shared pages that are shared + * with parent/child processes due to fork(). + */ +int s390_disable_cow_sharing(void) +{ + int rc; + + mmap_write_lock(current->mm); + rc = __s390_disable_cow_sharing(current->mm); + mmap_write_unlock(current->mm); + return rc; } -EXPORT_SYMBOL_GPL(gmap_mark_unmergeable); +EXPORT_SYMBOL_GPL(s390_disable_cow_sharing); /* * Enable storage key handling from now on and initialize the storage @@ -2659,7 +2744,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, return 0; start = pmd_val(*pmd) & HPAGE_MASK; - end = start + HPAGE_SIZE - 1; + end = start + HPAGE_SIZE; __storage_key_init_range(start, end); set_bit(PG_arch_1, &page->flags); cond_resched(); @@ -2683,7 +2768,7 @@ int s390_enable_skey(void) goto out_up; mm->context.uses_skeys = 1; - rc = gmap_mark_unmergeable(); + rc = __s390_disable_cow_sharing(mm); if (rc) { mm->context.uses_skeys = 0; goto out_up; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 297a6d897d5a0..763469e518eec 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -139,7 +139,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) } if (!test_and_set_bit(PG_arch_1, &page->flags)) - __storage_key_init_range(paddr, paddr + size - 1); + __storage_key_init_range(paddr, paddr + size); } void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, @@ -224,7 +224,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, if (p4d_present(*p4dp)) { pudp = pud_offset(p4dp, addr); if (pud_present(*pudp)) { - if (pud_large(*pudp)) + if (pud_leaf(*pudp)) return (pte_t *) pudp; pmdp = pmd_offset(pudp, addr); } @@ -240,7 +240,7 @@ int pmd_huge(pmd_t pmd) int pud_huge(pud_t pud) { - return pud_large(pud); + return pud_leaf(pud); } bool __init arch_hugetlb_valid_size(unsigned long size) diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 43e612bc2bcd3..8d9a60ccb7771 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -281,9 +281,6 @@ int arch_add_memory(int nid, u64 start, u64 size, unsigned long size_pages = PFN_DOWN(size); int rc; - if (WARN_ON_ONCE(params->altmap)) - return -EINVAL; - if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot)) return -EINVAL; diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 631e3a4ee2de8..739185fc39ead 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -274,7 +274,7 @@ static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end, if (pud_none(*pudp)) return -EINVAL; next = pud_addr_end(addr, end); - if (pud_large(*pudp)) { + if (pud_leaf(*pudp)) { need_split = !!(flags & SET_MEMORY_4K); need_split |= !!(addr & ~PUD_MASK); need_split |= !!(addr + PUD_SIZE > next); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 99422926efe1b..3ff07b6bcd65a 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -470,7 +470,7 @@ static int pmd_lookup(struct mm_struct *mm, unsigned long addr, pmd_t **pmdp) return -ENOENT; /* Large PUDs are not supported yet. */ - if (pud_large(*pud)) + if (pud_leaf(*pud)) return -EFAULT; *pmdp = pmd_offset(pud, addr); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 186a020857cf6..83625f0a72250 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -33,8 +33,12 @@ static void __ref *vmem_alloc_pages(unsigned int order) return memblock_alloc(size, size); } -static void vmem_free_pages(unsigned long addr, int order) +static void vmem_free_pages(unsigned long addr, int order, struct vmem_altmap *altmap) { + if (altmap) { + vmem_altmap_free(altmap, 1 << order); + return; + } /* We don't expect boot memory to be removed ever. */ if (!slab_is_available() || WARN_ON_ONCE(PageReserved(virt_to_page((void *)addr)))) @@ -156,7 +160,8 @@ static bool vmemmap_unuse_sub_pmd(unsigned long start, unsigned long end) /* __ref: we'll only call vmemmap_alloc_block() via vmemmap_populate() */ static int __ref modify_pte_table(pmd_t *pmd, unsigned long addr, - unsigned long end, bool add, bool direct) + unsigned long end, bool add, bool direct, + struct vmem_altmap *altmap) { unsigned long prot, pages = 0; int ret = -ENOMEM; @@ -172,11 +177,11 @@ static int __ref modify_pte_table(pmd_t *pmd, unsigned long addr, if (pte_none(*pte)) continue; if (!direct) - vmem_free_pages((unsigned long) pfn_to_virt(pte_pfn(*pte)), 0); + vmem_free_pages((unsigned long)pfn_to_virt(pte_pfn(*pte)), get_order(PAGE_SIZE), altmap); pte_clear(&init_mm, addr, pte); } else if (pte_none(*pte)) { if (!direct) { - void *new_page = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); + void *new_page = vmemmap_alloc_block_buf(PAGE_SIZE, NUMA_NO_NODE, altmap); if (!new_page) goto out; @@ -213,7 +218,8 @@ static void try_free_pte_table(pmd_t *pmd, unsigned long start) /* __ref: we'll only call vmemmap_alloc_block() via vmemmap_populate() */ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr, - unsigned long end, bool add, bool direct) + unsigned long end, bool add, bool direct, + struct vmem_altmap *altmap) { unsigned long next, prot, pages = 0; int ret = -ENOMEM; @@ -234,11 +240,11 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr, if (IS_ALIGNED(addr, PMD_SIZE) && IS_ALIGNED(next, PMD_SIZE)) { if (!direct) - vmem_free_pages(pmd_deref(*pmd), get_order(PMD_SIZE)); + vmem_free_pages(pmd_deref(*pmd), get_order(PMD_SIZE), altmap); pmd_clear(pmd); pages++; } else if (!direct && vmemmap_unuse_sub_pmd(addr, next)) { - vmem_free_pages(pmd_deref(*pmd), get_order(PMD_SIZE)); + vmem_free_pages(pmd_deref(*pmd), get_order(PMD_SIZE), altmap); pmd_clear(pmd); } continue; @@ -261,7 +267,7 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr, * page tables since vmemmap_populate gets * called for each section separately. */ - new_page = vmemmap_alloc_block(PMD_SIZE, NUMA_NO_NODE); + new_page = vmemmap_alloc_block_buf(PMD_SIZE, NUMA_NO_NODE, altmap); if (new_page) { set_pmd(pmd, __pmd(__pa(new_page) | prot)); if (!IS_ALIGNED(addr, PMD_SIZE) || @@ -280,7 +286,7 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr, vmemmap_use_sub_pmd(addr, next); continue; } - ret = modify_pte_table(pmd, addr, next, add, direct); + ret = modify_pte_table(pmd, addr, next, add, direct, altmap); if (ret) goto out; if (!add) @@ -302,12 +308,12 @@ static void try_free_pmd_table(pud_t *pud, unsigned long start) for (i = 0; i < PTRS_PER_PMD; i++, pmd++) if (!pmd_none(*pmd)) return; - vmem_free_pages(pud_deref(*pud), CRST_ALLOC_ORDER); + vmem_free_pages(pud_deref(*pud), CRST_ALLOC_ORDER, NULL); pud_clear(pud); } static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, - bool add, bool direct) + bool add, bool direct, struct vmem_altmap *altmap) { unsigned long next, prot, pages = 0; int ret = -ENOMEM; @@ -323,7 +329,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, if (!add) { if (pud_none(*pud)) continue; - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { if (IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE)) { pud_clear(pud); @@ -344,10 +350,10 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, if (!pmd) goto out; pud_populate(&init_mm, pud, pmd); - } else if (pud_large(*pud)) { + } else if (pud_leaf(*pud)) { continue; } - ret = modify_pmd_table(pud, addr, next, add, direct); + ret = modify_pmd_table(pud, addr, next, add, direct, altmap); if (ret) goto out; if (!add) @@ -370,12 +376,12 @@ static void try_free_pud_table(p4d_t *p4d, unsigned long start) if (!pud_none(*pud)) return; } - vmem_free_pages(p4d_deref(*p4d), CRST_ALLOC_ORDER); + vmem_free_pages(p4d_deref(*p4d), CRST_ALLOC_ORDER, NULL); p4d_clear(p4d); } static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end, - bool add, bool direct) + bool add, bool direct, struct vmem_altmap *altmap) { unsigned long next; int ret = -ENOMEM; @@ -394,7 +400,7 @@ static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end, goto out; p4d_populate(&init_mm, p4d, pud); } - ret = modify_pud_table(p4d, addr, next, add, direct); + ret = modify_pud_table(p4d, addr, next, add, direct, altmap); if (ret) goto out; if (!add) @@ -415,12 +421,12 @@ static void try_free_p4d_table(pgd_t *pgd, unsigned long start) if (!p4d_none(*p4d)) return; } - vmem_free_pages(pgd_deref(*pgd), CRST_ALLOC_ORDER); + vmem_free_pages(pgd_deref(*pgd), CRST_ALLOC_ORDER, NULL); pgd_clear(pgd); } static int modify_pagetable(unsigned long start, unsigned long end, bool add, - bool direct) + bool direct, struct vmem_altmap *altmap) { unsigned long addr, next; int ret = -ENOMEM; @@ -445,7 +451,7 @@ static int modify_pagetable(unsigned long start, unsigned long end, bool add, goto out; pgd_populate(&init_mm, pgd, p4d); } - ret = modify_p4d_table(pgd, addr, next, add, direct); + ret = modify_p4d_table(pgd, addr, next, add, direct, altmap); if (ret) goto out; if (!add) @@ -458,14 +464,16 @@ static int modify_pagetable(unsigned long start, unsigned long end, bool add, return ret; } -static int add_pagetable(unsigned long start, unsigned long end, bool direct) +static int add_pagetable(unsigned long start, unsigned long end, bool direct, + struct vmem_altmap *altmap) { - return modify_pagetable(start, end, true, direct); + return modify_pagetable(start, end, true, direct, altmap); } -static int remove_pagetable(unsigned long start, unsigned long end, bool direct) +static int remove_pagetable(unsigned long start, unsigned long end, bool direct, + struct vmem_altmap *altmap) { - return modify_pagetable(start, end, false, direct); + return modify_pagetable(start, end, false, direct, altmap); } /* @@ -474,7 +482,7 @@ static int remove_pagetable(unsigned long start, unsigned long end, bool direct) static int vmem_add_range(unsigned long start, unsigned long size) { start = (unsigned long)__va(start); - return add_pagetable(start, start + size, true); + return add_pagetable(start, start + size, true, NULL); } /* @@ -483,7 +491,7 @@ static int vmem_add_range(unsigned long start, unsigned long size) static void vmem_remove_range(unsigned long start, unsigned long size) { start = (unsigned long)__va(start); - remove_pagetable(start, start + size, true); + remove_pagetable(start, start + size, true, NULL); } /* @@ -496,9 +504,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, mutex_lock(&vmem_mutex); /* We don't care about the node, just use NUMA_NO_NODE on allocations */ - ret = add_pagetable(start, end, false); + ret = add_pagetable(start, end, false, altmap); if (ret) - remove_pagetable(start, end, false); + remove_pagetable(start, end, false, altmap); mutex_unlock(&vmem_mutex); return ret; } @@ -509,7 +517,7 @@ void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { mutex_lock(&vmem_mutex); - remove_pagetable(start, end, false); + remove_pagetable(start, end, false, altmap); mutex_unlock(&vmem_mutex); } @@ -591,7 +599,7 @@ pte_t *vmem_get_alloc_pte(unsigned long addr, bool alloc) if (!pmd) goto out; pud_populate(&init_mm, pud, pmd); - } else if (WARN_ON_ONCE(pud_large(*pud))) { + } else if (WARN_ON_ONCE(pud_leaf(*pud))) { goto out; } pmd = pmd_offset(pud, addr); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index b418333bb0863..1d168a98ae21b 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -516,11 +516,12 @@ static void bpf_skip(struct bpf_jit *jit, int size) * PLT for hotpatchable calls. The calling convention is the same as for the * ftrace hotpatch trampolines: %r0 is return address, %r1 is clobbered. */ -extern const char bpf_plt[]; -extern const char bpf_plt_ret[]; -extern const char bpf_plt_target[]; -extern const char bpf_plt_end[]; -#define BPF_PLT_SIZE 32 +struct bpf_plt { + char code[16]; + void *ret; + void *target; +} __packed; +extern const struct bpf_plt bpf_plt; asm( ".pushsection .rodata\n" " .balign 8\n" @@ -531,15 +532,14 @@ asm( " .balign 8\n" "bpf_plt_ret: .quad 0\n" "bpf_plt_target: .quad 0\n" - "bpf_plt_end:\n" " .popsection\n" ); -static void bpf_jit_plt(void *plt, void *ret, void *target) +static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target) { - memcpy(plt, bpf_plt, BPF_PLT_SIZE); - *(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret; - *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target ?: ret; + memcpy(plt, &bpf_plt, sizeof(*plt)); + plt->ret = ret; + plt->target = target; } /* @@ -662,9 +662,9 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) jit->prg = ALIGN(jit->prg, 8); jit->prologue_plt = jit->prg; if (jit->prg_buf) - bpf_jit_plt(jit->prg_buf + jit->prg, + bpf_jit_plt((struct bpf_plt *)(jit->prg_buf + jit->prg), jit->prg_buf + jit->prologue_plt_ret, NULL); - jit->prg += BPF_PLT_SIZE; + jit->prg += sizeof(struct bpf_plt); } static int get_probe_mem_regno(const u8 *insn) @@ -1427,8 +1427,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, is32 ? (op32) : (op64), \ (insn->imm & BPF_FETCH) ? src_reg : REG_W0, \ src_reg, dst_reg, off); \ - if (is32 && (insn->imm & BPF_FETCH)) \ - EMIT_ZERO(src_reg); \ + if (insn->imm & BPF_FETCH) { \ + /* bcr 14,0 - see atomic_fetch_{add,and,or,xor}() */ \ + _EMIT2(0x07e0); \ + if (is32) \ + EMIT_ZERO(src_reg); \ + } \ } while (0) case BPF_ADD: case BPF_ADD | BPF_FETCH: @@ -2040,9 +2044,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) struct bpf_jit jit; int pass; - if (WARN_ON_ONCE(bpf_plt_end - bpf_plt != BPF_PLT_SIZE)) - return orig_fp; - if (!fp->jit_requested) return orig_fp; @@ -2148,14 +2149,11 @@ bool bpf_jit_supports_far_kfunc_call(void) int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr) { + struct bpf_plt expected_plt, current_plt, new_plt, *plt; struct { u16 opc; s32 disp; } __packed insn; - char expected_plt[BPF_PLT_SIZE]; - char current_plt[BPF_PLT_SIZE]; - char new_plt[BPF_PLT_SIZE]; - char *plt; char *ret; int err; @@ -2174,18 +2172,18 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, */ } else { /* Verify the PLT. */ - plt = (char *)ip + (insn.disp << 1); - err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE); + plt = ip + (insn.disp << 1); + err = copy_from_kernel_nofault(¤t_plt, plt, + sizeof(current_plt)); if (err < 0) return err; ret = (char *)ip + 6; - bpf_jit_plt(expected_plt, ret, old_addr); - if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE)) + bpf_jit_plt(&expected_plt, ret, old_addr); + if (memcmp(¤t_plt, &expected_plt, sizeof(current_plt))) return -EINVAL; /* Adjust the call address. */ - bpf_jit_plt(new_plt, ret, new_addr); - s390_kernel_write(plt + (bpf_plt_target - bpf_plt), - new_plt + (bpf_plt_target - bpf_plt), + bpf_jit_plt(&new_plt, ret, new_addr); + s390_kernel_write(&plt->target, &new_plt.target, sizeof(void *)); } diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index aed1ea8e2c2f0..74051b8ddf3e7 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -44,17 +44,12 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) if (OPCODE_RTE(opcode)) return -EFAULT; /* Bad breakpoint */ + memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); p->opcode = opcode; return 0; } -void __kprobes arch_copy_kprobe(struct kprobe *p) -{ - memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); - p->opcode = *p->addr; -} - void __kprobes arch_arm_kprobe(struct kprobe *p) { *p->addr = BREAKPOINT_INSTRUCTION; diff --git a/arch/sh/lib/checksum.S b/arch/sh/lib/checksum.S index 3e07074e00981..06fed5a21e8ba 100644 --- a/arch/sh/lib/checksum.S +++ b/arch/sh/lib/checksum.S @@ -33,7 +33,8 @@ */ /* - * asmlinkage __wsum csum_partial(const void *buf, int len, __wsum sum); + * unsigned int csum_partial(const unsigned char *buf, int len, + * unsigned int sum); */ .text @@ -45,31 +46,11 @@ ENTRY(csum_partial) * Fortunately, it is easy to convert 2-byte alignment to 4-byte * alignment for the unrolled loop. */ + mov r5, r1 mov r4, r0 - tst #3, r0 ! Check alignment. - bt/s 2f ! Jump if alignment is ok. - mov r4, r7 ! Keep a copy to check for alignment + tst #2, r0 ! Check alignment. + bt 2f ! Jump if alignment is ok. ! - tst #1, r0 ! Check alignment. - bt 21f ! Jump if alignment is boundary of 2bytes. - - ! buf is odd - tst r5, r5 - add #-1, r5 - bt 9f - mov.b @r4+, r0 - extu.b r0, r0 - addc r0, r6 ! t=0 from previous tst - mov r6, r0 - shll8 r6 - shlr16 r0 - shlr8 r0 - or r0, r6 - mov r4, r0 - tst #2, r0 - bt 2f -21: - ! buf is 2 byte aligned (len could be 0) add #-2, r5 ! Alignment uses up two bytes. cmp/pz r5 ! bt/s 1f ! Jump if we had at least two bytes. @@ -77,17 +58,16 @@ ENTRY(csum_partial) bra 6f add #2, r5 ! r5 was < 2. Deal with it. 1: + mov r5, r1 ! Save new len for later use. mov.w @r4+, r0 extu.w r0, r0 addc r0, r6 bf 2f add #1, r6 2: - ! buf is 4 byte aligned (len could be 0) - mov r5, r1 mov #-5, r0 - shld r0, r1 - tst r1, r1 + shld r0, r5 + tst r5, r5 bt/s 4f ! if it's =0, go to 4f clrt .align 2 @@ -109,31 +89,30 @@ ENTRY(csum_partial) addc r0, r6 addc r2, r6 movt r0 - dt r1 + dt r5 bf/s 3b cmp/eq #1, r0 - ! here, we know r1==0 - addc r1, r6 ! add carry to r6 + ! here, we know r5==0 + addc r5, r6 ! add carry to r6 4: - mov r5, r0 + mov r1, r0 and #0x1c, r0 tst r0, r0 - bt 6f - ! 4 bytes or more remaining - mov r0, r1 - shlr2 r1 + bt/s 6f + mov r0, r5 + shlr2 r5 mov #0, r2 5: addc r2, r6 mov.l @r4+, r2 movt r0 - dt r1 + dt r5 bf/s 5b cmp/eq #1, r0 addc r2, r6 - addc r1, r6 ! r1==0 here, so it means add carry-bit + addc r5, r6 ! r5==0 here, so it means add carry-bit 6: - ! 3 bytes or less remaining + mov r1, r5 mov #3, r0 and r0, r5 tst r5, r5 @@ -159,16 +138,6 @@ ENTRY(csum_partial) mov #0, r0 addc r0, r6 9: - ! Check if the buffer was misaligned, if so realign sum - mov r7, r0 - tst #1, r0 - bt 10f - mov r6, r0 - shll8 r6 - shlr16 r0 - shlr8 r0 - or r0, r6 -10: rts mov r6, r0 diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 204c43cb3d435..37a1cfecd9c73 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -57,6 +57,8 @@ config SPARC32 select CLZ_TAB select DMA_DIRECT_REMAP select GENERIC_ATOMIC64 + select GENERIC_LIB_CMPDI2 + select GENERIC_LIB_UCMPDI2 select HAVE_UID16 select LOCK_MM_AND_FIND_VMA select OLD_SIGACTION @@ -140,10 +142,6 @@ config HIGHMEM default y if SPARC32 select KMAP_LOCAL -config GENERIC_ISA_DMA - bool - default y if SPARC32 - config PGTABLE_LEVELS default 4 if 64BIT default 3 diff --git a/arch/sparc/include/asm/parport.h b/arch/sparc/include/asm/parport.h index 0a7ffcfd59cda..e2eed8f97665f 100644 --- a/arch/sparc/include/asm/parport.h +++ b/arch/sparc/include/asm/parport.h @@ -1,256 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* parport.h: sparc64 specific parport initialization and dma. - * - * Copyright (C) 1999 Eddie C. Dost (ecd@skynet.be) - */ +#ifndef ___ASM_SPARC_PARPORT_H +#define ___ASM_SPARC_PARPORT_H -#ifndef _ASM_SPARC64_PARPORT_H -#define _ASM_SPARC64_PARPORT_H 1 - -#include -#include - -#include -#include -#include - -#define PARPORT_PC_MAX_PORTS PARPORT_MAX - -/* - * While sparc64 doesn't have an ISA DMA API, we provide something that looks - * close enough to make parport_pc happy - */ -#define HAS_DMA - -#ifdef CONFIG_PARPORT_PC_FIFO -static DEFINE_SPINLOCK(dma_spin_lock); - -#define claim_dma_lock() \ -({ unsigned long flags; \ - spin_lock_irqsave(&dma_spin_lock, flags); \ - flags; \ -}) - -#define release_dma_lock(__flags) \ - spin_unlock_irqrestore(&dma_spin_lock, __flags); +#if defined(__sparc__) && defined(__arch64__) +#include +#else +#include +#endif #endif -static struct sparc_ebus_info { - struct ebus_dma_info info; - unsigned int addr; - unsigned int count; - int lock; - - struct parport *port; -} sparc_ebus_dmas[PARPORT_PC_MAX_PORTS]; - -static DECLARE_BITMAP(dma_slot_map, PARPORT_PC_MAX_PORTS); - -static inline int request_dma(unsigned int dmanr, const char *device_id) -{ - if (dmanr >= PARPORT_PC_MAX_PORTS) - return -EINVAL; - if (xchg(&sparc_ebus_dmas[dmanr].lock, 1) != 0) - return -EBUSY; - return 0; -} - -static inline void free_dma(unsigned int dmanr) -{ - if (dmanr >= PARPORT_PC_MAX_PORTS) { - printk(KERN_WARNING "Trying to free DMA%d\n", dmanr); - return; - } - if (xchg(&sparc_ebus_dmas[dmanr].lock, 0) == 0) { - printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr); - return; - } -} - -static inline void enable_dma(unsigned int dmanr) -{ - ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 1); - - if (ebus_dma_request(&sparc_ebus_dmas[dmanr].info, - sparc_ebus_dmas[dmanr].addr, - sparc_ebus_dmas[dmanr].count)) - BUG(); -} - -static inline void disable_dma(unsigned int dmanr) -{ - ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 0); -} - -static inline void clear_dma_ff(unsigned int dmanr) -{ - /* nothing */ -} - -static inline void set_dma_mode(unsigned int dmanr, char mode) -{ - ebus_dma_prepare(&sparc_ebus_dmas[dmanr].info, (mode != DMA_MODE_WRITE)); -} - -static inline void set_dma_addr(unsigned int dmanr, unsigned int addr) -{ - sparc_ebus_dmas[dmanr].addr = addr; -} - -static inline void set_dma_count(unsigned int dmanr, unsigned int count) -{ - sparc_ebus_dmas[dmanr].count = count; -} - -static inline unsigned int get_dma_residue(unsigned int dmanr) -{ - return ebus_dma_residue(&sparc_ebus_dmas[dmanr].info); -} - -static int ecpp_probe(struct platform_device *op) -{ - unsigned long base = op->resource[0].start; - unsigned long config = op->resource[1].start; - unsigned long d_base = op->resource[2].start; - unsigned long d_len; - struct device_node *parent; - struct parport *p; - int slot, err; - - parent = op->dev.of_node->parent; - if (of_node_name_eq(parent, "dma")) { - p = parport_pc_probe_port(base, base + 0x400, - op->archdata.irqs[0], PARPORT_DMA_NOFIFO, - op->dev.parent->parent, 0); - if (!p) - return -ENOMEM; - dev_set_drvdata(&op->dev, p); - return 0; - } - - for (slot = 0; slot < PARPORT_PC_MAX_PORTS; slot++) { - if (!test_and_set_bit(slot, dma_slot_map)) - break; - } - err = -ENODEV; - if (slot >= PARPORT_PC_MAX_PORTS) - goto out_err; - - spin_lock_init(&sparc_ebus_dmas[slot].info.lock); - - d_len = (op->resource[2].end - d_base) + 1UL; - sparc_ebus_dmas[slot].info.regs = - of_ioremap(&op->resource[2], 0, d_len, "ECPP DMA"); - - if (!sparc_ebus_dmas[slot].info.regs) - goto out_clear_map; - - sparc_ebus_dmas[slot].info.flags = 0; - sparc_ebus_dmas[slot].info.callback = NULL; - sparc_ebus_dmas[slot].info.client_cookie = NULL; - sparc_ebus_dmas[slot].info.irq = 0xdeadbeef; - strcpy(sparc_ebus_dmas[slot].info.name, "parport"); - if (ebus_dma_register(&sparc_ebus_dmas[slot].info)) - goto out_unmap_regs; - - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 1); - - /* Configure IRQ to Push Pull, Level Low */ - /* Enable ECP, set bit 2 of the CTR first */ - outb(0x04, base + 0x02); - ns87303_modify(config, PCR, - PCR_EPP_ENABLE | - PCR_IRQ_ODRAIN, - PCR_ECP_ENABLE | - PCR_ECP_CLK_ENA | - PCR_IRQ_POLAR); - - /* CTR bit 5 controls direction of port */ - ns87303_modify(config, PTR, - 0, PTR_LPT_REG_DIR); - - p = parport_pc_probe_port(base, base + 0x400, - op->archdata.irqs[0], - slot, - op->dev.parent, - 0); - err = -ENOMEM; - if (!p) - goto out_disable_irq; - - dev_set_drvdata(&op->dev, p); - - return 0; - -out_disable_irq: - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); - ebus_dma_unregister(&sparc_ebus_dmas[slot].info); - -out_unmap_regs: - of_iounmap(&op->resource[2], sparc_ebus_dmas[slot].info.regs, d_len); - -out_clear_map: - clear_bit(slot, dma_slot_map); - -out_err: - return err; -} - -static int ecpp_remove(struct platform_device *op) -{ - struct parport *p = dev_get_drvdata(&op->dev); - int slot = p->dma; - - parport_pc_unregister_port(p); - - if (slot != PARPORT_DMA_NOFIFO) { - unsigned long d_base = op->resource[2].start; - unsigned long d_len; - - d_len = (op->resource[2].end - d_base) + 1UL; - - ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); - ebus_dma_unregister(&sparc_ebus_dmas[slot].info); - of_iounmap(&op->resource[2], - sparc_ebus_dmas[slot].info.regs, - d_len); - clear_bit(slot, dma_slot_map); - } - - return 0; -} - -static const struct of_device_id ecpp_match[] = { - { - .name = "ecpp", - }, - { - .name = "parallel", - .compatible = "ecpp", - }, - { - .name = "parallel", - .compatible = "ns87317-ecpp", - }, - { - .name = "parallel", - .compatible = "pnpALI,1533,3", - }, - {}, -}; - -static struct platform_driver ecpp_driver = { - .driver = { - .name = "ecpp", - .of_match_table = ecpp_match, - }, - .probe = ecpp_probe, - .remove = ecpp_remove, -}; - -static int parport_pc_find_nonpci_ports(int autoirq, int autodma) -{ - return platform_driver_register(&ecpp_driver); -} - -#endif /* !(_ASM_SPARC64_PARPORT_H */ diff --git a/arch/sparc/include/asm/parport_64.h b/arch/sparc/include/asm/parport_64.h new file mode 100644 index 0000000000000..0a7ffcfd59cda --- /dev/null +++ b/arch/sparc/include/asm/parport_64.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* parport.h: sparc64 specific parport initialization and dma. + * + * Copyright (C) 1999 Eddie C. Dost (ecd@skynet.be) + */ + +#ifndef _ASM_SPARC64_PARPORT_H +#define _ASM_SPARC64_PARPORT_H 1 + +#include +#include + +#include +#include +#include + +#define PARPORT_PC_MAX_PORTS PARPORT_MAX + +/* + * While sparc64 doesn't have an ISA DMA API, we provide something that looks + * close enough to make parport_pc happy + */ +#define HAS_DMA + +#ifdef CONFIG_PARPORT_PC_FIFO +static DEFINE_SPINLOCK(dma_spin_lock); + +#define claim_dma_lock() \ +({ unsigned long flags; \ + spin_lock_irqsave(&dma_spin_lock, flags); \ + flags; \ +}) + +#define release_dma_lock(__flags) \ + spin_unlock_irqrestore(&dma_spin_lock, __flags); +#endif + +static struct sparc_ebus_info { + struct ebus_dma_info info; + unsigned int addr; + unsigned int count; + int lock; + + struct parport *port; +} sparc_ebus_dmas[PARPORT_PC_MAX_PORTS]; + +static DECLARE_BITMAP(dma_slot_map, PARPORT_PC_MAX_PORTS); + +static inline int request_dma(unsigned int dmanr, const char *device_id) +{ + if (dmanr >= PARPORT_PC_MAX_PORTS) + return -EINVAL; + if (xchg(&sparc_ebus_dmas[dmanr].lock, 1) != 0) + return -EBUSY; + return 0; +} + +static inline void free_dma(unsigned int dmanr) +{ + if (dmanr >= PARPORT_PC_MAX_PORTS) { + printk(KERN_WARNING "Trying to free DMA%d\n", dmanr); + return; + } + if (xchg(&sparc_ebus_dmas[dmanr].lock, 0) == 0) { + printk(KERN_WARNING "Trying to free free DMA%d\n", dmanr); + return; + } +} + +static inline void enable_dma(unsigned int dmanr) +{ + ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 1); + + if (ebus_dma_request(&sparc_ebus_dmas[dmanr].info, + sparc_ebus_dmas[dmanr].addr, + sparc_ebus_dmas[dmanr].count)) + BUG(); +} + +static inline void disable_dma(unsigned int dmanr) +{ + ebus_dma_enable(&sparc_ebus_dmas[dmanr].info, 0); +} + +static inline void clear_dma_ff(unsigned int dmanr) +{ + /* nothing */ +} + +static inline void set_dma_mode(unsigned int dmanr, char mode) +{ + ebus_dma_prepare(&sparc_ebus_dmas[dmanr].info, (mode != DMA_MODE_WRITE)); +} + +static inline void set_dma_addr(unsigned int dmanr, unsigned int addr) +{ + sparc_ebus_dmas[dmanr].addr = addr; +} + +static inline void set_dma_count(unsigned int dmanr, unsigned int count) +{ + sparc_ebus_dmas[dmanr].count = count; +} + +static inline unsigned int get_dma_residue(unsigned int dmanr) +{ + return ebus_dma_residue(&sparc_ebus_dmas[dmanr].info); +} + +static int ecpp_probe(struct platform_device *op) +{ + unsigned long base = op->resource[0].start; + unsigned long config = op->resource[1].start; + unsigned long d_base = op->resource[2].start; + unsigned long d_len; + struct device_node *parent; + struct parport *p; + int slot, err; + + parent = op->dev.of_node->parent; + if (of_node_name_eq(parent, "dma")) { + p = parport_pc_probe_port(base, base + 0x400, + op->archdata.irqs[0], PARPORT_DMA_NOFIFO, + op->dev.parent->parent, 0); + if (!p) + return -ENOMEM; + dev_set_drvdata(&op->dev, p); + return 0; + } + + for (slot = 0; slot < PARPORT_PC_MAX_PORTS; slot++) { + if (!test_and_set_bit(slot, dma_slot_map)) + break; + } + err = -ENODEV; + if (slot >= PARPORT_PC_MAX_PORTS) + goto out_err; + + spin_lock_init(&sparc_ebus_dmas[slot].info.lock); + + d_len = (op->resource[2].end - d_base) + 1UL; + sparc_ebus_dmas[slot].info.regs = + of_ioremap(&op->resource[2], 0, d_len, "ECPP DMA"); + + if (!sparc_ebus_dmas[slot].info.regs) + goto out_clear_map; + + sparc_ebus_dmas[slot].info.flags = 0; + sparc_ebus_dmas[slot].info.callback = NULL; + sparc_ebus_dmas[slot].info.client_cookie = NULL; + sparc_ebus_dmas[slot].info.irq = 0xdeadbeef; + strcpy(sparc_ebus_dmas[slot].info.name, "parport"); + if (ebus_dma_register(&sparc_ebus_dmas[slot].info)) + goto out_unmap_regs; + + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 1); + + /* Configure IRQ to Push Pull, Level Low */ + /* Enable ECP, set bit 2 of the CTR first */ + outb(0x04, base + 0x02); + ns87303_modify(config, PCR, + PCR_EPP_ENABLE | + PCR_IRQ_ODRAIN, + PCR_ECP_ENABLE | + PCR_ECP_CLK_ENA | + PCR_IRQ_POLAR); + + /* CTR bit 5 controls direction of port */ + ns87303_modify(config, PTR, + 0, PTR_LPT_REG_DIR); + + p = parport_pc_probe_port(base, base + 0x400, + op->archdata.irqs[0], + slot, + op->dev.parent, + 0); + err = -ENOMEM; + if (!p) + goto out_disable_irq; + + dev_set_drvdata(&op->dev, p); + + return 0; + +out_disable_irq: + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); + ebus_dma_unregister(&sparc_ebus_dmas[slot].info); + +out_unmap_regs: + of_iounmap(&op->resource[2], sparc_ebus_dmas[slot].info.regs, d_len); + +out_clear_map: + clear_bit(slot, dma_slot_map); + +out_err: + return err; +} + +static int ecpp_remove(struct platform_device *op) +{ + struct parport *p = dev_get_drvdata(&op->dev); + int slot = p->dma; + + parport_pc_unregister_port(p); + + if (slot != PARPORT_DMA_NOFIFO) { + unsigned long d_base = op->resource[2].start; + unsigned long d_len; + + d_len = (op->resource[2].end - d_base) + 1UL; + + ebus_dma_irq_enable(&sparc_ebus_dmas[slot].info, 0); + ebus_dma_unregister(&sparc_ebus_dmas[slot].info); + of_iounmap(&op->resource[2], + sparc_ebus_dmas[slot].info.regs, + d_len); + clear_bit(slot, dma_slot_map); + } + + return 0; +} + +static const struct of_device_id ecpp_match[] = { + { + .name = "ecpp", + }, + { + .name = "parallel", + .compatible = "ecpp", + }, + { + .name = "parallel", + .compatible = "ns87317-ecpp", + }, + { + .name = "parallel", + .compatible = "pnpALI,1533,3", + }, + {}, +}; + +static struct platform_driver ecpp_driver = { + .driver = { + .name = "ecpp", + .of_match_table = ecpp_match, + }, + .probe = ecpp_probe, + .remove = ecpp_remove, +}; + +static int parport_pc_find_nonpci_ports(int autoirq, int autodma) +{ + return platform_driver_register(&ecpp_driver); +} + +#endif /* !(_ASM_SPARC64_PARPORT_H */ diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h index 505b6700805dd..0964fede0b2cc 100644 --- a/arch/sparc/include/asm/smp_64.h +++ b/arch/sparc/include/asm/smp_64.h @@ -47,7 +47,6 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask); int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) -void smp_fill_in_cpu_possible_map(void); void smp_fill_in_sib_core_maps(void); void __noreturn cpu_play_dead(void); @@ -77,7 +76,6 @@ void __cpu_die(unsigned int cpu); #define smp_fill_in_sib_core_maps() do { } while (0) #define smp_fetch_global_regs() do { } while (0) #define smp_fetch_global_pmu() do { } while (0) -#define smp_fill_in_cpu_possible_map() do { } while (0) #define smp_init_cpu_poke() do { } while (0) #define scheduler_poke() do { } while (0) diff --git a/arch/sparc/include/uapi/asm/termbits.h b/arch/sparc/include/uapi/asm/termbits.h index 4321322701fcf..0da2b1adc0f52 100644 --- a/arch/sparc/include/uapi/asm/termbits.h +++ b/arch/sparc/include/uapi/asm/termbits.h @@ -10,16 +10,6 @@ typedef unsigned int tcflag_t; typedef unsigned long tcflag_t; #endif -#define NCC 8 -struct termio { - unsigned short c_iflag; /* input mode flags */ - unsigned short c_oflag; /* output mode flags */ - unsigned short c_cflag; /* control mode flags */ - unsigned short c_lflag; /* local mode flags */ - unsigned char c_line; /* line discipline */ - unsigned char c_cc[NCC]; /* control characters */ -}; - #define NCCS 17 struct termios { tcflag_t c_iflag; /* input mode flags */ diff --git a/arch/sparc/include/uapi/asm/termios.h b/arch/sparc/include/uapi/asm/termios.h index ee86f4093d83e..cceb32260881e 100644 --- a/arch/sparc/include/uapi/asm/termios.h +++ b/arch/sparc/include/uapi/asm/termios.h @@ -40,5 +40,14 @@ struct winsize { unsigned short ws_ypixel; }; +#define NCC 8 +struct termio { + unsigned short c_iflag; /* input mode flags */ + unsigned short c_oflag; /* output mode flags */ + unsigned short c_cflag; /* control mode flags */ + unsigned short c_lflag; /* local mode flags */ + unsigned char c_line; /* line discipline */ + unsigned char c_cc[NCC]; /* control characters */ +}; #endif /* _UAPI_SPARC_TERMIOS_H */ diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c index 8700a0e3b0df7..b2b639bee0684 100644 --- a/arch/sparc/kernel/leon_pci_grpci1.c +++ b/arch/sparc/kernel/leon_pci_grpci1.c @@ -697,7 +697,7 @@ static int grpci1_of_probe(struct platform_device *ofdev) return err; } -static const struct of_device_id grpci1_of_match[] __initconst = { +static const struct of_device_id grpci1_of_match[] = { { .name = "GAISLER_PCIFBRG", }, diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index 60b6bdf7761fb..ac2acd62a24ec 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -889,7 +889,7 @@ static int grpci2_of_probe(struct platform_device *ofdev) return err; } -static const struct of_device_id grpci2_of_match[] __initconst = { +static const struct of_device_id grpci2_of_match[] = { { .name = "GAISLER_GRPCI2", }, diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 17cdfdbf1f3b7..149adc0947530 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -279,7 +279,7 @@ static int __init setup_nmi_watchdog(char *str) if (!strncmp(str, "panic", 5)) panic_on_timeout = 1; - return 0; + return 1; } __setup("nmi_watchdog=", setup_nmi_watchdog); diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index 998aa693d4912..ba82884cb92aa 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -483,7 +483,9 @@ static void *record_one_cpu(struct device_node *dp, int cpuid, int arg) ncpus_probed++; #ifdef CONFIG_SMP set_cpu_present(cpuid, true); - set_cpu_possible(cpuid, true); + + if (num_possible_cpus() < nr_cpu_ids) + set_cpu_possible(cpuid, true); #endif return NULL; } diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 6a4797dec34b4..6bbe8e394ad3f 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -671,7 +671,6 @@ void __init setup_arch(char **cmdline_p) paging_init(); init_sparc64_elf_hwcap(); - smp_fill_in_cpu_possible_map(); /* * Once the OF device tree and MDESC have been setup and nr_cpus has * been parsed, we know the list of possible cpus. Therefore we can diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index f3969a3600dbf..e50c38eba2b87 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1220,20 +1220,6 @@ void __init smp_setup_processor_id(void) xcall_deliver_impl = hypervisor_xcall_deliver; } -void __init smp_fill_in_cpu_possible_map(void) -{ - int possible_cpus = num_possible_cpus(); - int i; - - if (possible_cpus > nr_cpu_ids) - possible_cpus = nr_cpu_ids; - - for (i = 0; i < possible_cpus; i++) - set_cpu_possible(i, true); - for (; i < NR_CPUS; i++) - set_cpu_possible(i, false); -} - void smp_fill_in_sib_core_maps(void) { unsigned int i; diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index 59669ebddd4e1..ee5091dd67ed7 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -14,7 +14,7 @@ lib-$(CONFIG_SPARC32) += divdi3.o udivdi3.o lib-$(CONFIG_SPARC32) += copy_user.o locks.o lib-$(CONFIG_SPARC64) += atomic_64.o lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o -lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o +lib-$(CONFIG_SPARC32) += muldi3.o bitext.o lib-$(CONFIG_SPARC64) += multi3.o lib-$(CONFIG_SPARC64) += fls.o lib-$(CONFIG_SPARC64) += fls64.o @@ -51,5 +51,5 @@ lib-$(CONFIG_SPARC64) += copy_in_user.o memmove.o lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o obj-$(CONFIG_SPARC64) += iomap.o -obj-$(CONFIG_SPARC32) += atomic32.o ucmpdi2.o +obj-$(CONFIG_SPARC32) += atomic32.o obj-$(CONFIG_SPARC64) += PeeCeeI.o diff --git a/arch/sparc/lib/cmpdi2.c b/arch/sparc/lib/cmpdi2.c deleted file mode 100644 index 333367fe73533..0000000000000 --- a/arch/sparc/lib/cmpdi2.c +++ /dev/null @@ -1,28 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -#include "libgcc.h" - -word_type __cmpdi2(long long a, long long b) -{ - const DWunion au = { - .ll = a - }; - const DWunion bu = { - .ll = b - }; - - if (au.s.high < bu.s.high) - return 0; - else if (au.s.high > bu.s.high) - return 2; - - if ((unsigned int) au.s.low < (unsigned int) bu.s.low) - return 0; - else if ((unsigned int) au.s.low > (unsigned int) bu.s.low) - return 2; - - return 1; -} - -EXPORT_SYMBOL(__cmpdi2); diff --git a/arch/sparc/lib/ucmpdi2.c b/arch/sparc/lib/ucmpdi2.c deleted file mode 100644 index 82c1cccb12644..0000000000000 --- a/arch/sparc/lib/ucmpdi2.c +++ /dev/null @@ -1,20 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include "libgcc.h" - -word_type __ucmpdi2(unsigned long long a, unsigned long long b) -{ - const DWunion au = {.ll = a}; - const DWunion bu = {.ll = b}; - - if ((unsigned int) au.s.high < (unsigned int) bu.s.high) - return 0; - else if ((unsigned int) au.s.high > (unsigned int) bu.s.high) - return 2; - if ((unsigned int) au.s.low < (unsigned int) bu.s.low) - return 0; - else if ((unsigned int) au.s.low > (unsigned int) bu.s.low) - return 2; - return 1; -} -EXPORT_SYMBOL(__ucmpdi2); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index f83017992eaae..d7db4e737218c 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1665,7 +1665,7 @@ bool kern_addr_valid(unsigned long addr) if (pud_none(*pud)) return false; - if (pud_large(*pud)) + if (pud_leaf(*pud)) return pfn_valid(pud_pfn(*pud)); pmd = pmd_offset(pud, addr); diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index b44d79d778c71..ef69127d7e5e8 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -249,6 +249,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, { pmd_t old, entry; + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID); old = pmdp_establish(vma, address, pmdp, entry); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c index 136c78f28f8ba..1bbf4335de454 100644 --- a/arch/sparc/vdso/vma.c +++ b/arch/sparc/vdso/vma.c @@ -449,9 +449,8 @@ static __init int vdso_setup(char *s) unsigned long val; err = kstrtoul(s, 10, &val); - if (err) - return err; - vdso_enabled = val; - return 0; + if (!err) + vdso_enabled = val; + return 1; } __setup("vdso=", vdso_setup); diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index ffc5cb92fa367..d82bc3fdb86e7 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -676,24 +676,26 @@ void register_winch_irq(int fd, int tty_fd, int pid, struct tty_port *port, goto cleanup; } - *winch = ((struct winch) { .list = LIST_HEAD_INIT(winch->list), - .fd = fd, + *winch = ((struct winch) { .fd = fd, .tty_fd = tty_fd, .pid = pid, .port = port, .stack = stack }); + spin_lock(&winch_handler_lock); + list_add(&winch->list, &winch_handlers); + spin_unlock(&winch_handler_lock); + if (um_request_irq(WINCH_IRQ, fd, IRQ_READ, winch_interrupt, IRQF_SHARED, "winch", winch) < 0) { printk(KERN_ERR "register_winch_irq - failed to register " "IRQ\n"); + spin_lock(&winch_handler_lock); + list_del(&winch->list); + spin_unlock(&winch_handler_lock); goto out_free; } - spin_lock(&winch_handler_lock); - list_add(&winch->list, &winch_handlers); - spin_unlock(&winch_handler_lock); - return; out_free: diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 92ee2697ff398..85e33caf62a0e 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1098,7 +1098,7 @@ static int __init ubd_init(void) if (irq_req_buffer == NULL) { printk(KERN_ERR "Failed to initialize ubd buffering\n"); - return -1; + return -ENOMEM; } io_req_buffer = kmalloc_array(UBD_REQ_BUFFER_SIZE, sizeof(struct io_thread_req *), @@ -1109,7 +1109,7 @@ static int __init ubd_init(void) if (io_req_buffer == NULL) { printk(KERN_ERR "Failed to initialize ubd buffering\n"); - return -1; + return -ENOMEM; } platform_driver_register(&ubd_driver); mutex_lock(&ubd_lock); diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 131b7cb295767..94a4dfac6c236 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -141,7 +141,7 @@ static bool get_bpf_flash(struct arglist *def) if (allow != NULL) { if (kstrtoul(allow, 10, &result) == 0) - return (allow > 0); + return result > 0; } return false; } diff --git a/arch/um/include/asm/kasan.h b/arch/um/include/asm/kasan.h index 0d6547f4ec85c..f97bb1f7b8514 100644 --- a/arch/um/include/asm/kasan.h +++ b/arch/um/include/asm/kasan.h @@ -24,7 +24,6 @@ #ifdef CONFIG_KASAN void kasan_init(void); -void kasan_map_memory(void *start, unsigned long len); extern int kasan_um_is_ready; #ifdef CONFIG_STATIC_LINK diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h index a7555e43ed14a..f2923c767bb9a 100644 --- a/arch/um/include/asm/mmu.h +++ b/arch/um/include/asm/mmu.h @@ -14,8 +14,6 @@ typedef struct mm_context { struct uml_arch_mm_context arch; } mm_context_t; -extern void __switch_mm(struct mm_id * mm_idp); - /* Avoid tangled inclusion with asm/ldt.h */ extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm); extern void free_ldt(struct mm_context *mm); diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 6c3779541845b..5a7c05275aa74 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -94,7 +94,6 @@ extern struct cpuinfo_um boot_cpu_data; #define current_cpu_data boot_cpu_data #define cache_line_size() (boot_cpu_data.cache_alignment) -extern unsigned long get_thread_reg(int reg, jmp_buf *buf); #define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf) extern unsigned long __get_wchan(struct task_struct *p); diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index 789b83013f355..af8cdfc75897e 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -66,4 +66,6 @@ extern void fatal_sigsegv(void) __attribute__ ((noreturn)); void um_idle_sleep(void); +void kasan_map_memory(void *start, size_t len); + #endif diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h index e82e203f5f419..92dbf727e3842 100644 --- a/arch/um/include/shared/skas/mm_id.h +++ b/arch/um/include/shared/skas/mm_id.h @@ -15,4 +15,6 @@ struct mm_id { int kill; }; +void __switch_mm(struct mm_id *mm_idp); + #endif diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index 8530b2e086049..c6c9495b14321 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -15,6 +15,7 @@ #include #include #include +#include #include /* diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5edec175b9bfc..2d870e08af600 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -62,6 +62,7 @@ config X86 select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT + select ARCH_CONFIGURES_CPU_MITIGATIONS select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 @@ -100,7 +101,7 @@ config X86 select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_SYSCALL_WRAPPER - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARCH_HAS_DEBUG_WX select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -1539,19 +1540,6 @@ config AMD_MEM_ENCRYPT This requires an AMD processor that supports Secure Memory Encryption (SME). -config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT - bool "Activate AMD Secure Memory Encryption (SME) by default" - depends on AMD_MEM_ENCRYPT - help - Say yes to have system memory encrypted by default if running on - an AMD processor that supports Secure Memory Encryption (SME). - - If set to Y, then the encryption of system memory can be - deactivated with the mem_encrypt=off command line option. - - If set to N, then the encryption of system memory can be - activated with the mem_encrypt=on command line option. - # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" @@ -2480,17 +2468,21 @@ config PREFIX_SYMBOLS def_bool y depends on CALL_PADDING && !CFI_CLANG -menuconfig SPECULATION_MITIGATIONS - bool "Mitigations for speculative execution vulnerabilities" +menuconfig CPU_MITIGATIONS + bool "Mitigations for CPU vulnerabilities" default y help - Say Y here to enable options which enable mitigations for - speculative execution hardware vulnerabilities. + Say Y here to enable options which enable mitigations for hardware + vulnerabilities (usually related to speculative execution). + Mitigations can be disabled or restricted to SMT systems at runtime + via the "mitigations" kernel parameter. - If you say N, all mitigations will be disabled. You really - should know what you are doing to say so. + If you say N, all mitigations will be disabled. This CANNOT be + overridden at runtime. -if SPECULATION_MITIGATIONS + Say 'Y', unless you really know what you are doing. + +if CPU_MITIGATIONS config PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" @@ -2614,6 +2606,27 @@ config GDS_FORCE_MITIGATION If in doubt, say N. +config MITIGATION_RFDS + bool "RFDS Mitigation" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Register File Data Sampling (RFDS) by default. + RFDS is a hardware vulnerability which affects Intel Atom CPUs. It + allows unprivileged speculative access to stale data previously + stored in floating point, vector and integer registers. + See also + +config MITIGATION_SPECTRE_BHI + bool "Mitigate Spectre-BHB (Branch History Injection)" + depends on CPU_SUP_INTEL + default y + help + Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks + where the branch history buffer is poisoned to speculatively steer + indirect branches. + See + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c5d614d28a759..74777a97e394a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -248,6 +248,7 @@ config UNWINDER_ORC config UNWINDER_FRAME_POINTER bool "Frame pointer unwinder" + select ARCH_WANT_FRAME_POINTERS select FRAME_POINTER help This option enables the frame pointer unwinder for unwinding kernel @@ -271,7 +272,3 @@ config UNWINDER_GUESS overhead. endchoice - -config FRAME_POINTER - depends on !UNWINDER_ORC && !UNWINDER_GUESS - bool diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index f19c038409aa0..8da3466775de8 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -84,7 +84,7 @@ LDFLAGS_vmlinux += -T hostprogs := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include -sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' +sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' quiet_cmd_voffset = VOFFSET $@ cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@ @@ -116,9 +116,9 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o -vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -$(obj)/vmlinux: $(vmlinux-objs-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S index f4e22ef774ab6..876fc6d46a131 100644 --- a/arch/x86/boot/compressed/efi_mixed.S +++ b/arch/x86/boot/compressed/efi_mixed.S @@ -15,10 +15,12 @@ */ #include +#include #include #include #include #include +#include .code64 .text @@ -49,6 +51,11 @@ SYM_FUNC_START(startup_64_mixed_mode) lea efi32_boot_args(%rip), %rdx mov 0(%rdx), %edi mov 4(%rdx), %esi + + /* Switch to the firmware's stack */ + movl efi32_boot_sp(%rip), %esp + andl $~7, %esp + #ifdef CONFIG_EFI_HANDOVER_PROTOCOL mov 8(%rdx), %edx // saved bootparams pointer test %edx, %edx @@ -144,6 +151,7 @@ SYM_FUNC_END(__efi64_thunk) SYM_FUNC_START(efi32_stub_entry) call 1f 1: popl %ecx + leal (efi32_boot_args - 1b)(%ecx), %ebx /* Clear BSS */ xorl %eax, %eax @@ -158,6 +166,7 @@ SYM_FUNC_START(efi32_stub_entry) popl %ecx popl %edx popl %esi + movl %esi, 8(%ebx) jmp efi32_entry SYM_FUNC_END(efi32_stub_entry) #endif @@ -234,8 +243,6 @@ SYM_FUNC_END(efi_enter32) * * Arguments: %ecx image handle * %edx EFI system table pointer - * %esi struct bootparams pointer (or NULL when not using - * the EFI handover protocol) * * Since this is the point of no return for ordinary execution, no registers * are considered live except for the function parameters. [Note that the EFI @@ -254,13 +261,25 @@ SYM_FUNC_START_LOCAL(efi32_entry) /* Store firmware IDT descriptor */ sidtl (efi32_boot_idt - 1b)(%ebx) + /* Store firmware stack pointer */ + movl %esp, (efi32_boot_sp - 1b)(%ebx) + /* Store boot arguments */ leal (efi32_boot_args - 1b)(%ebx), %ebx movl %ecx, 0(%ebx) movl %edx, 4(%ebx) - movl %esi, 8(%ebx) movb $0x0, 12(%ebx) // efi_is64 + /* + * Allocate some memory for a temporary struct boot_params, which only + * needs the minimal pieces that startup_32() relies on. + */ + subl $PARAM_SIZE, %esp + movl %esp, %esi + movl $PAGE_SIZE, BP_kernel_alignment(%esi) + movl $_end - 1b, BP_init_size(%esi) + subl $startup_32 - 1b, BP_init_size(%esi) + /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax @@ -286,8 +305,7 @@ SYM_FUNC_START(efi32_pe_entry) movl 8(%ebp), %ecx // image_handle movl 12(%ebp), %edx // sys_table - xorl %esi, %esi - jmp efi32_entry // pass %ecx, %edx, %esi + jmp efi32_entry // pass %ecx, %edx // no other registers remain live 2: popl %edi // restore callee-save registers @@ -318,5 +336,6 @@ SYM_DATA_END(efi32_boot_idt) SYM_DATA_LOCAL(efi32_boot_cs, .word 0) SYM_DATA_LOCAL(efi32_boot_ds, .word 0) +SYM_DATA_LOCAL(efi32_boot_sp, .long 0) SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index bf4a10a5794f1..1dcb794c5479e 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -398,6 +398,11 @@ SYM_CODE_START(startup_64) call sev_enable #endif + /* Preserve only the CR4 bits that must be preserved, and clear the rest */ + movq %cr4, %rax + andl $(X86_CR4_PAE | X86_CR4_MCE | X86_CR4_LA57), %eax + movq %rax, %cr4 + /* * configure_5level_paging() updates the number of paging levels using * a trampoline in 32-bit addressable memory if the current number does diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index b99e08e6815b1..ee0fac468e7f7 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -330,6 +330,7 @@ static size_t parse_elf(void *output) return ehdr.e_entry - LOAD_PHYSICAL_ADDR; } +const unsigned long kernel_text_size = VO___start_rodata - VO__text; const unsigned long kernel_total_size = VO__end - VO__text; static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4); @@ -357,6 +358,19 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, return entry; } +/* + * Set the memory encryption xloadflag based on the mem_encrypt= command line + * parameter, if provided. + */ +static void parse_mem_encrypt(struct setup_header *hdr) +{ + int on = cmdline_find_option_bool("mem_encrypt=on"); + int off = cmdline_find_option_bool("mem_encrypt=off"); + + if (on > off) + hdr->xloadflags |= XLF_MEM_ENCRYPTION; +} + /* * The compressed kernel image (ZO), has been moved so that its position * is against the end of the buffer used to hold the uncompressed kernel @@ -387,6 +401,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) /* Clear flags intended for solely in-kernel use. */ boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG; + parse_mem_encrypt(&boot_params_ptr->hdr); + sanitize_boot_params(boot_params_ptr); if (boot_params_ptr->screen_info.orig_video_mode == 7) { diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 454acd7a2daff..bea0719d70f2d 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -116,6 +116,9 @@ static bool fault_in_kernel_space(unsigned long address) #undef __init #define __init +#undef __head +#define __head + #define __BOOT_COMPRESSED /* Basic instruction decoding support needed */ @@ -304,6 +307,10 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) if (result != ES_OK) goto finish; + result = vc_check_opcode_bytes(&ctxt, exit_code); + if (result != ES_OK) + goto finish; + switch (exit_code) { case SVM_EXIT_RDTSC: case SVM_EXIT_RDTSCP: diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index c4ea5258ab558..9049f390d8347 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -119,8 +119,8 @@ static void init_heap(void) char *stack_end; if (boot_params.hdr.loadflags & CAN_USE_HEAP) { - asm("leal %P1(%%esp),%0" - : "=r" (stack_end) : "i" (-STACK_SIZE)); + asm("leal %n1(%%esp),%0" + : "=r" (stack_end) : "i" (STACK_SIZE)); heap_end = (char *) ((size_t)boot_params.hdr.heap_end_ptr + 0x200); diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index eeec9986570ed..ddd4efdc79d66 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -3,18 +3,22 @@ * Confidential Computing Platform Capability checks * * Copyright (C) 2021 Advanced Micro Devices, Inc. + * Copyright (C) 2024 Jason A. Donenfeld . All Rights Reserved. * * Author: Tom Lendacky */ #include #include +#include +#include +#include #include #include enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; -static u64 cc_mask __ro_after_init; +u64 cc_mask __ro_after_init; static bool noinstr intel_cc_platform_has(enum cc_attr attr) { @@ -149,7 +153,39 @@ u64 cc_mkdec(u64 val) } EXPORT_SYMBOL_GPL(cc_mkdec); -__init void cc_set_mask(u64 mask) +__init void cc_random_init(void) { - cc_mask = mask; + /* + * The seed is 32 bytes (in units of longs), which is 256 bits, which + * is the security level that the RNG is targeting. + */ + unsigned long rng_seed[32 / sizeof(long)]; + size_t i, longs; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * Since the CoCo threat model includes the host, the only reliable + * source of entropy that can be neither observed nor manipulated is + * RDRAND. Usually, RDRAND failure is considered tolerable, but since + * CoCo guests have no other unobservable source of entropy, it's + * important to at least ensure the RNG gets some initial random seeds. + */ + for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) { + longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i); + + /* + * A zero return value means that the guest doesn't have RDRAND + * or the CPU is physically broken, and in both cases that + * means most crypto inside of the CoCo instance will be + * broken, defeating the purpose of CoCo in the first place. So + * just panic here because it's absolutely unsafe to continue + * executing. + */ + if (longs == 0) + panic("RDRAND is defective."); + } + add_device_randomness(rng_seed, sizeof(rng_seed)); + memzero_explicit(rng_seed, sizeof(rng_seed)); } diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S index ef73a3ab87263..791386d9a83aa 100644 --- a/arch/x86/crypto/nh-avx2-x86_64.S +++ b/arch/x86/crypto/nh-avx2-x86_64.S @@ -154,5 +154,6 @@ SYM_TYPED_FUNC_START(nh_avx2) vpaddq T1, T0, T0 vpaddq T4, T0, T0 vmovdqu T0, (HASH) + vzeroupper RET SYM_FUNC_END(nh_avx2) diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 9918212faf914..0ffb072be9561 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -716,6 +716,7 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) popq %r13 popq %r12 popq %rbx + vzeroupper RET SYM_FUNC_END(sha256_transform_rorx) diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index f08496cd68708..24973f42c43ff 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -680,6 +680,7 @@ SYM_TYPED_FUNC_START(sha512_transform_rorx) pop %r12 pop %rbx + vzeroupper RET SYM_FUNC_END(sha512_transform_rorx) diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 6356060caaf31..6de50b80702e6 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -49,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) if (likely(unr < NR_syscalls)) { unr = array_index_nospec(unr, NR_syscalls); - regs->ax = sys_call_table[unr](regs); + regs->ax = x64_sys_call(regs, unr); return true; } return false; @@ -66,7 +66,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { xnr = array_index_nospec(xnr, X32_NR_syscalls); - regs->ax = x32_sys_call_table[xnr](regs); + regs->ax = x32_sys_call(regs, xnr); return true; } return false; @@ -162,7 +162,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) if (likely(unr < IA32_NR_syscalls)) { unr = array_index_nospec(unr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[unr](regs); + regs->ax = ia32_sys_call(regs, unr); } else if (nr != -1) { regs->ax = __ia32_sys_ni_syscall(regs); } @@ -189,7 +189,7 @@ static __always_inline bool int80_is_external(void) } /** - * int80_emulation - 32-bit legacy syscall entry + * do_int80_emulation - 32-bit legacy syscall C entry from asm * * This entry point can be used by 32-bit and 64-bit programs to perform * 32-bit system calls. Instances of INT $0x80 can be found inline in @@ -207,7 +207,7 @@ static __always_inline bool int80_is_external(void) * eax: system call number * ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6 */ -DEFINE_IDTENTRY_RAW(int80_emulation) +__visible noinstr void do_int80_emulation(struct pt_regs *regs) { int nr; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9bb4859776291..e986331b14e1d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* clobbers %rax, make sure it is after saving the syscall nr */ IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY call do_syscall_64 /* returns with IRQs disabled */ @@ -1494,3 +1495,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead) call make_task_dead SYM_CODE_END(rewind_stack_and_make_dead) .popsection + +/* + * This sequence executes branches in order to remove user branch information + * from the branch history tracker in the Branch Predictor, therefore removing + * user influence on subsequent BTB lookups. + * + * It should be used on parts prior to Alder Lake. Newer parts should use the + * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being + * virtualized on newer hardware the VMM should protect against BHI attacks by + * setting BHI_DIS_S for the guests. + * + * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging + * and not clearing the branch history. The call tree looks like: + * + * call 1 + * call 2 + * call 2 + * call 2 + * call 2 + * call 2 + * ret + * ret + * ret + * ret + * ret + * ret + * + * This means that the stack is non-constant and ORC can't unwind it with %rsp + * alone. Therefore we unconditionally set up the frame pointer, which allows + * ORC to unwind properly. + * + * The alignment is for performance and not for safety, and may be safely + * refactored in the future if needed. + */ +SYM_FUNC_START(clear_bhb_loop) + push %rbp + mov %rsp, %rbp + movl $5, %ecx + ANNOTATE_INTRA_FUNCTION_CALL + call 1f + jmp 5f + .align 64, 0xcc + ANNOTATE_INTRA_FUNCTION_CALL +1: call 2f + RET + .align 64, 0xcc +2: movl $5, %eax +3: jmp 4f + nop +4: sub $1, %eax + jnz 3b + sub $1, %ecx + jnz 1b + RET +5: lfence + pop %rbp + RET +SYM_FUNC_END(clear_bhb_loop) +EXPORT_SYMBOL_GPL(clear_bhb_loop) +STACK_FRAME_NON_STANDARD(clear_bhb_loop) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index eabf48c4d4b4c..c779046cc3fe7 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY /* * SYSENTER doesn't filter flags, so we need to clear NT and AC @@ -206,6 +207,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_fast_syscall_32 @@ -276,3 +278,17 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR int3 SYM_CODE_END(entry_SYSCALL_compat) + +/* + * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries + * point to C routines, however since this is a system call interface the branch + * history needs to be scrubbed to protect against BHI attacks, and that + * scrubbing needs to take place in assembly code prior to entering any C + * routines. + */ +SYM_CODE_START(int80_emulation) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + CLEAR_BRANCH_HISTORY + jmp do_int80_emulation +SYM_CODE_END(int80_emulation) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8cfc9bc73e7f8..c2235bae17ef6 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -18,8 +18,25 @@ #include #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ +#ifdef CONFIG_X86_32 #define __SYSCALL(nr, sym) __ia32_##sym, - -__visible const sys_call_ptr_t ia32_sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include }; +#undef __SYSCALL +#endif + +#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); + +long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __ia32_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index be120eec1fc9f..33b3f09e6f151 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -11,8 +11,23 @@ #include #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ #define __SYSCALL(nr, sym) __x64_##sym, - -asmlinkage const sys_call_ptr_t sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include }; +#undef __SYSCALL + +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); + +long x64_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __x64_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index bdd0e03a1265d..03de4a9321318 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -11,8 +11,12 @@ #include #undef __SYSCALL -#define __SYSCALL(nr, sym) __x64_##sym, +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); -asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { -#include +long x32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include + default: return __x64_sys_ni_syscall(regs); + } }; diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index b1b8dd1608f7e..73ac5adb0b4c9 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -34,8 +34,13 @@ obj-y += vma.o extable.o KASAN_SANITIZE_vma.o := y UBSAN_SANITIZE_vma.o := y KCSAN_SANITIZE_vma.o := y -OBJECT_FILES_NON_STANDARD_vma.o := n -OBJECT_FILES_NON_STANDARD_extable.o := n + +OBJECT_FILES_NON_STANDARD_extable.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n +OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n +OBJECT_FILES_NON_STANDARD_vma.o := n # vDSO images to build vdso_img-$(VDSO64-y) += 64 @@ -43,7 +48,6 @@ vdso_img-$(VDSOX32-y) += x32 vdso_img-$(VDSO32-y) += 32 obj-$(VDSO32-y) += vdso32-setup.o -OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F) diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index e0ca8120aea87..1245000a8792f 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -98,11 +98,6 @@ static int addr_to_vsyscall_nr(unsigned long addr) static bool write_ok_or_segv(unsigned long ptr, size_t size) { - /* - * XXX: if access_ok, get_user, and put_user handled - * sig_on_uaccess_err, this could go away. - */ - if (!access_ok((void __user *)ptr, size)) { struct thread_struct *thread = ¤t->thread; @@ -120,10 +115,8 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size) bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address) { - struct task_struct *tsk; unsigned long caller; int vsyscall_nr, syscall_nr, tmp; - int prev_sig_on_uaccess_err; long ret; unsigned long orig_dx; @@ -172,8 +165,6 @@ bool emulate_vsyscall(unsigned long error_code, goto sigsegv; } - tsk = current; - /* * Check for access_ok violations and find the syscall nr. * @@ -234,12 +225,8 @@ bool emulate_vsyscall(unsigned long error_code, goto do_ret; /* skip requested */ /* - * With a real vsyscall, page faults cause SIGSEGV. We want to - * preserve that behavior to make writing exploits harder. + * With a real vsyscall, page faults cause SIGSEGV. */ - prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err; - current->thread.sig_on_uaccess_err = 1; - ret = -EFAULT; switch (vsyscall_nr) { case 0: @@ -262,23 +249,12 @@ bool emulate_vsyscall(unsigned long error_code, break; } - current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err; - check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall fault (exploit attempt?)"); - - /* - * If we failed to generate a signal for any reason, - * generate one here. (This should be impossible.) - */ - if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) && - !sigismember(&tsk->pending.signal, SIGSEGV))) - goto sigsegv; - - return true; /* Don't emulate the ret. */ + goto sigsegv; } regs->ax = ret; diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 81f6d8275b6bf..eb5c8539d657a 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -250,7 +250,7 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = /* * AMD Performance Monitor Family 17h and later: */ -static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = +static const u64 amd_zen1_perfmon_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, @@ -262,10 +262,24 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, }; +static const u64 amd_zen2_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9, +}; + static u64 amd_pmu_event_map(int hw_event) { - if (boot_cpu_data.x86 >= 0x17) - return amd_f17h_perfmon_event_map[hw_event]; + if (cpu_feature_enabled(X86_FEATURE_ZEN2) || boot_cpu_data.x86 >= 0x19) + return amd_zen2_perfmon_event_map[hw_event]; + + if (cpu_feature_enabled(X86_FEATURE_ZEN1)) + return amd_zen1_perfmon_event_map[hw_event]; return amd_perfmon_event_map[hw_event]; } @@ -604,7 +618,6 @@ static void amd_pmu_cpu_dead(int cpu) kfree(cpuhw->lbr_sel); cpuhw->lbr_sel = NULL; - amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index eb31f850841a8..4a1e600314d5d 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -173,9 +173,11 @@ void amd_pmu_lbr_read(void) /* * Check if a branch has been logged; if valid = 0, spec = 0 - * then no branch was recorded + * then no branch was recorded; if reserved = 1 then an + * erroneous branch was recorded (see Erratum 1452) */ - if (!entry.to.split.valid && !entry.to.split.spec) + if ((!entry.to.split.valid && !entry.to.split.spec) || + entry.to.split.reserved) continue; perf_clear_branch_entry_bitfields(br + out); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 09050641ce5d3..5b0dd07b1ef19 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1644,6 +1644,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; + cpuc->assign[i-1] = cpuc->assign[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index d49d661ec0a7d..807de7b596ab7 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1236,11 +1236,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu = event->pmu; /* - * Make sure we get updated with the first PEBS - * event. It will trigger also during removal, but - * that does not hurt: + * Make sure we get updated with the first PEBS event. + * During removal, ->pebs_data_cfg is still valid for + * the last PEBS event. Don't clear it. */ - if (cpuc->n_pebs == 1) + if ((cpuc->n_pebs == 1) && add) cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index cf1b78cb2d043..c8062975a5316 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -12,6 +12,7 @@ #include #include #include +#include <../kernel/smpboot.h> extern struct boot_params boot_params; static struct real_mode_header hv_vtl_real_mode_header; @@ -64,7 +65,7 @@ static void hv_vtl_ap_entry(void) ((secondary_startup_64_fn)secondary_startup_64)(&boot_params, &boot_params); } -static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored) +static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored) { u64 status; int ret = 0; @@ -78,7 +79,9 @@ static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored) struct ldttss_desc *ldt; struct desc_struct *gdt; - u64 rsp = current->thread.sp; + struct task_struct *idle = idle_thread_get(cpu); + u64 rsp = (unsigned long)idle->thread.sp; + u64 rip = (u64)&hv_vtl_ap_entry; native_store_gdt(&gdt_ptr); @@ -205,7 +208,15 @@ static int hv_vtl_apicid_to_vp_id(u32 apic_id) static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { - int vp_id; + int vp_id, cpu; + + /* Find the logical CPU for the APIC ID */ + for_each_present_cpu(cpu) { + if (arch_match_cpu_phys_id(cpu, apicid)) + break; + } + if (cpu >= nr_cpu_ids) + return -EINVAL; pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid); vp_id = hv_vtl_apicid_to_vp_id(apicid); @@ -219,7 +230,7 @@ static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) return -EINVAL; } - return hv_vtl_bringup_vcpu(vp_id, start_eip); + return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip); } int __init hv_vtl_early_init(void) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index fcd20c6dc7f90..99432696b1814 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -294,10 +294,10 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, newinstr1 is used. * Otherwise, oldinstr is used. */ -#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \ - ft_flags2, input...) \ - asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \ - newinstr2, ft_flags2) \ +#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \ + ft_flags2, input...) \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \ + newinstr2, ft_flags2) \ : : "i" (0), ## input) /* Like alternative_input, but with a single output argument */ @@ -307,7 +307,7 @@ static inline int alternatives_text_reserved(void *start, void *end) /* Like alternative_io, but for replacing a direct call with another one. */ #define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \ - asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", ft_flags) \ + asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \ : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) /* @@ -316,12 +316,12 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, function1 is used. * Otherwise, old function is used. */ -#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ - output, input...) \ - asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", ft_flags1,\ - "call %P[new2]", ft_flags2) \ - : output, ASM_CALL_CONSTRAINT \ - : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ +#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ + output, input...) \ + asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \ + "call %c[new2]", ft_flags2) \ + : output, ASM_CALL_CONSTRAINT \ + : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ [new2] "i" (newfunc2), ## input) /* diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 9d159b771dc81..dddd3fc195efa 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -13,6 +13,7 @@ #include #include #include +#include #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -96,7 +97,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v) static inline u32 native_apic_mem_read(u32 reg) { - return *((volatile u32 *)(APIC_BASE + reg)); + return readl((void __iomem *)(APIC_BASE + reg)); } static inline void native_apic_mem_eoi(void) diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index b1a98fa38828e..0e82074517f6b 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -13,6 +13,7 @@ #include #include #include +#include #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index fbcfec4dc4ccd..ca8eed1d496ab 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -113,6 +113,20 @@ #endif +#ifndef __ASSEMBLY__ +#ifndef __pic__ +static __always_inline __pure void *rip_rel_ptr(void *p) +{ + asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p)); + + return p; +} +#define RIP_REL_REF(var) (*(typeof(&(var)))rip_rel_ptr(&(var))) +#else +#define RIP_REL_REF(var) (var) +#endif +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 3486d91b8595f..d510405e4e1de 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -24,7 +24,7 @@ typedef struct { #ifdef CONFIG_X86_CMPXCHG64 #define __alternative_atomic64(f, g, out, in...) \ - asm volatile("call %P[func]" \ + asm volatile("call %c[func]" \ : out : [func] "i" (atomic64_##g##_cx8), ## in) #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 0216f63a366b5..d0795b5fab46a 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -79,6 +79,9 @@ do { \ #define __smp_mb__before_atomic() do { } while (0) #define __smp_mb__after_atomic() do { } while (0) +/* Writing to CR3 provides a full memory barrier in switch_mm(). */ +#define smp_mb__after_switch_mm() do { } while (0) + #include #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index a38cc0afc90a0..a3e0be0470a40 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -81,6 +81,7 @@ #ifndef __ASSEMBLY__ extern unsigned int output_len; +extern const unsigned long kernel_text_size; extern const unsigned long kernel_total_size; unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 44b08b53ab32f..c1d6cd58f8094 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -62,7 +62,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old, asm volatile(_lock "cmpxchg16b %[ptr]" \ CC_SET(e) \ : CC_OUT(e) (ret), \ - [ptr] "+m" (*ptr), \ + [ptr] "+m" (*(_ptr)), \ "+a" (o.low), "+d" (o.high) \ : "b" (n.low), "c" (n.high) \ : "memory"); \ diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index 76c310b19b11d..a368afce372b9 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_COCO_H #define _ASM_X86_COCO_H +#include #include enum cc_vendor { @@ -12,11 +13,18 @@ enum cc_vendor { #ifdef CONFIG_ARCH_HAS_CC_PLATFORM extern enum cc_vendor cc_vendor; -void cc_set_mask(u64 mask); +extern u64 cc_mask; +static inline void cc_set_mask(u64 mask) +{ + RIP_REL_REF(cc_mask) = mask; +} + u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); +void cc_random_init(void); #else #define cc_vendor (CC_VENDOR_NONE) +static const u64 cc_mask = 0; static inline u64 cc_mkenc(u64 val) { @@ -27,6 +35,7 @@ static inline u64 cc_mkdec(u64 val) { return val; } +static inline void cc_random_init(void) { } #endif #endif /* _ASM_X86_COCO_H */ diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index eb8fcede9e3bf..e8e3dbe7f1730 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -2,6 +2,39 @@ #ifndef _ASM_X86_CPU_DEVICE_ID #define _ASM_X86_CPU_DEVICE_ID +/* + * Can't use because it generates expressions that + * cannot be used in structure initializers. Bitfield construction + * here must match the union in struct cpuinfo_86: + * union { + * struct { + * __u8 x86_model; + * __u8 x86; + * __u8 x86_vendor; + * __u8 x86_reserved; + * }; + * __u32 x86_vfm; + * }; + */ +#define VFM_MODEL_BIT 0 +#define VFM_FAMILY_BIT 8 +#define VFM_VENDOR_BIT 16 +#define VFM_RSVD_BIT 24 + +#define VFM_MODEL_MASK GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT) +#define VFM_FAMILY_MASK GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT) +#define VFM_VENDOR_MASK GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT) + +#define VFM_MODEL(vfm) (((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT) +#define VFM_FAMILY(vfm) (((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT) +#define VFM_VENDOR(vfm) (((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT) + +#define VFM_MAKE(_vendor, _family, _model) ( \ + ((_model) << VFM_MODEL_BIT) | \ + ((_family) << VFM_FAMILY_BIT) | \ + ((_vendor) << VFM_VENDOR_BIT) \ +) + /* * Declare drivers belonging to specific x86 CPUs * Similar in spirit to pci_device_id and related PCI functions @@ -20,6 +53,9 @@ #define X86_CENTAUR_FAM6_C7_D 0xd #define X86_CENTAUR_FAM6_NANO 0xf +/* x86_cpu_id::flags */ +#define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) + #define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching @@ -46,6 +82,18 @@ .model = _model, \ .steppings = _steppings, \ .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ + .driver_data = (unsigned long) _data \ +} + +#define X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \ + _steppings, _feature, _data) { \ + .vendor = _vendor, \ + .family = _family, \ + .model = _model, \ + .steppings = _steppings, \ + .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ .driver_data = (unsigned long) _data \ } @@ -164,6 +212,56 @@ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \ steppings, X86_FEATURE_ANY, data) +/** + * X86_MATCH_VFM - Match encoded vendor/family/model + * @vfm: Encoded 8-bits each for vendor, family, model + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * Stepping and feature are set to wildcards + */ +#define X86_MATCH_VFM(vfm, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + X86_STEPPING_ANY, X86_FEATURE_ANY, data) + +/** + * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping + * @vfm: Encoded 8-bits each for vendor, family, model + * @steppings: Bitmask of steppings to match + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * feature is set to wildcard + */ +#define X86_MATCH_VFM_STEPPINGS(vfm, steppings, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + steppings, X86_FEATURE_ANY, data) + +/** + * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature + * @vfm: Encoded 8-bits each for vendor, family, model + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * Steppings is set to wildcard + */ +#define X86_MATCH_VFM_FEATURE(vfm, feature, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + X86_STEPPING_ANY, feature, data) + /* * Match specific microcode revisions. * diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index a1273698fc430..3508f3fc928d4 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #define X86_CAP_FMT_NUM "%d:%d" @@ -91,8 +93,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -116,8 +119,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ @@ -169,7 +173,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); static __always_inline bool _static_cpu_has(u16 bit) { asm goto( - ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") + ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" " testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n" diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2b62cdd8dd122..76b3b00ff1021 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -456,6 +456,17 @@ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ +/* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc and Linux defined features. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ + /* * BUG word(s) */ @@ -503,4 +514,6 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/crash_core.h b/arch/x86/include/asm/crash_core.h index 76af98f4e8012..041020da8d561 100644 --- a/arch/x86/include/asm/crash_core.h +++ b/arch/x86/include/asm/crash_core.h @@ -39,4 +39,6 @@ static inline unsigned long crash_low_size_default(void) #endif } +#define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY + #endif /* _X86_CRASH_CORE_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 702d93fdd10e8..88fcf08458d9c 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -143,6 +143,7 @@ #define DISABLED_MASK18 (DISABLE_IBT) #define DISABLED_MASK19 0 #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index c4555b269a1b2..a050d329e34bf 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -410,7 +410,6 @@ extern int __init efi_memmap_alloc(unsigned int num_entries, struct efi_memory_map_data *data); extern void __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags); -#define __efi_memmap_free __efi_memmap_free extern int __init efi_memmap_install(struct efi_memory_map_data *data); extern int __init efi_memmap_split_count(efi_memory_desc_t *md, diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index b65e9c46b9221..d0941f4c27249 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -127,6 +127,7 @@ #define INTEL_FAM6_ARROWLAKE_H 0xC5 #define INTEL_FAM6_ARROWLAKE 0xC6 +#define INTEL_FAM6_ARROWLAKE_U 0xB5 #define INTEL_FAM6_LUNARLAKE_M 0xBD diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 3814a9263d64e..294cd2a408181 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -379,7 +379,7 @@ static inline void iosubmit_cmds512(void __iomem *dst, const void *src, const u8 *end = from + count * 64; while (from < end) { - movdir64b(dst, from); + movdir64b_io(dst, from); from += 64; } } diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 798183867d789..b71ad173f8776 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -100,7 +100,7 @@ } #define ASM_CALL_ARG0 \ - "call %P[__func] \n" \ + "call %c[__func] \n" \ ASM_REACHABLE #define ASM_CALL_ARG1 \ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d271ba20a0b21..b7a539ea2986f 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -854,6 +854,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; struct kvm_hypervisor_cpuid kvm_cpuid; + bool is_amd_compatible; /* * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 359ada486fa92..f922b682b9b4c 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -15,7 +15,8 @@ #include #include -#include +#include +struct boot_params; #ifdef CONFIG_X86_MEM_ENCRYPT void __init mem_encrypt_init(void); @@ -46,8 +47,8 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sme_encrypt_kernel(struct boot_params *bp); -void __init sme_enable(struct boot_params *bp); +void sme_encrypt_kernel(struct boot_params *bp); +void sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); @@ -58,6 +59,11 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); +static inline u64 sme_get_me_mask(void) +{ + return RIP_REL_REF(sme_me_mask); +} + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -75,8 +81,8 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } -static inline void __init sme_enable(struct boot_params *bp) { } +static inline void sme_encrypt_kernel(struct boot_params *bp) { } +static inline void sme_enable(struct boot_params *bp) { } static inline void sev_es_init_vc_handling(void) { } @@ -89,6 +95,8 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool en static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline u64 sme_get_me_mask(void) { return 0; } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ @@ -106,11 +114,6 @@ void add_encrypt_protection_map(void); extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; -static inline u64 sme_get_me_mask(void) -{ - return sme_me_mask; -} - #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index f1bd7b91b3c63..d65f8ce6b7cf0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -50,10 +50,13 @@ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) /* A mask for bits which the kernel toggles when controlling mitigations */ #define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ - | SPEC_CTRL_RRSBA_DIS_S) + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -152,6 +155,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. @@ -165,6 +172,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 2aa52cab1e463..3ff081a74ab2b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -271,11 +271,20 @@ .Lskip_rsb_\@: .endm +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) -#define CALL_UNTRAIN_RET "call entry_untrain_ret" -#else -#define CALL_UNTRAIN_RET "" + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif +.endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the @@ -291,8 +300,8 @@ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns #if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY) VALIDATE_UNRET_END - ALTERNATIVE_3 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ + CALL_UNTRAIN_RET + ALTERNATIVE_2 "", \ "call entry_ibpb", \ibpb_feature, \ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif @@ -326,6 +335,19 @@ ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF .endm +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -351,6 +373,8 @@ extern void retbleed_return_thunk(void); static inline void retbleed_return_thunk(void) {} #endif +extern void srso_alias_untrain_ret(void); + #ifdef CONFIG_CPU_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); @@ -366,6 +390,10 @@ extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + extern void (*x86_return_thunk)(void); #ifdef CONFIG_CALL_DEPTH_TRACKING diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index d18e5c332cb9f..1b93ff80b43bc 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -66,10 +66,14 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, * virt_addr_valid(kaddr) returns true. */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) extern bool __virt_addr_valid(unsigned long kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) +static __always_inline void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} + static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) { return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); diff --git a/arch/x86/include/asm/pci-direct.h b/arch/x86/include/asm/pci-direct.h index 94597a3cf3d0f..ebb3db2eee41b 100644 --- a/arch/x86/include/asm/pci-direct.h +++ b/arch/x86/include/asm/pci-direct.h @@ -10,9 +10,11 @@ extern u32 read_pci_config(u8 bus, u8 slot, u8 func, u8 offset); extern u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset); extern u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset); +extern u32 pci_early_find_cap(int bus, int slot, int func, int cap); extern void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset, u32 val); extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val); extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val); +extern unsigned int pci_early_clear_msi; extern int early_pci_allowed(void); #endif /* _ASM_X86_PCI_DIRECT_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0b748ee16b3d9..b786449626267 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -148,7 +148,7 @@ #define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | \ _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \ - _PAGE_DEVMAP | _PAGE_ENC | _PAGE_UFFD_WP) + _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) @@ -173,6 +173,7 @@ enum page_cache_mode { }; #endif +#define _PAGE_CC (_AT(pteval_t, cc_mask)) #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) @@ -566,6 +567,8 @@ static inline void update_page_count(int level, unsigned long pages) { } extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); +pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, + unsigned int *level, bool *nx, bool *rw); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 26620d7642a9f..5636ad697394d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -479,7 +479,6 @@ struct thread_struct { unsigned long iopl_emul; unsigned int iopl_warn:1; - unsigned int sig_on_uaccess_err:1; /* * Protection Keys Register for Userspace. Loaded immediately on diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 7ba1726b71c7b..e9187ddd3d1fd 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -99,6 +99,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 5b4a1ce3d3680..75a5388d40681 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -199,16 +199,16 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) struct snp_guest_request_ioctl; void setup_ghcb(void); -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, - unsigned long npages); -void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, - unsigned long npages); -void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op); +void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned long npages); +void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned long npages); void snp_set_memory_shared(unsigned long vaddr, unsigned long npages); void snp_set_memory_private(unsigned long vaddr, unsigned long npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); -void __init __noreturn snp_abort(void); +void __noreturn snp_abort(void); +void snp_dmi_setup(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); @@ -227,12 +227,12 @@ static inline void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } static inline void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } -static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { } static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { } static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { } static inline void snp_set_wakeup_secondary_cpu(void) { } static inline bool snp_init(struct boot_params *bp) { return false; } static inline void snp_abort(void) { } +static inline void snp_dmi_setup(void) { } static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio) { return -ENOTTY; diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 1be13b2dfe8bf..64df897c0ee30 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -37,8 +37,6 @@ extern int phys_to_target_node(phys_addr_t start); #define phys_to_target_node phys_to_target_node extern int memory_add_physaddr_to_nid(u64 start); #define memory_add_physaddr_to_nid memory_add_physaddr_to_nid -extern int numa_fill_memblks(u64 start, u64 end); -#define numa_fill_memblks numa_fill_memblks #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 48f8dd47cf688..09a5461d72439 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -224,10 +224,10 @@ static inline void serialize(void) } /* The dst parameter must be 64-bytes aligned */ -static inline void movdir64b(void __iomem *dst, const void *src) +static inline void movdir64b(void *dst, const void *src) { const struct { char _[64]; } *__src = src; - struct { char _[64]; } __iomem *__dst = dst; + struct { char _[64]; } *__dst = dst; /* * MOVDIR64B %(rdx), rax. @@ -245,6 +245,11 @@ static inline void movdir64b(void __iomem *dst, const void *src) : "m" (*__src), "a" (__dst), "d" (__src)); } +static inline void movdir64b_io(void __iomem *dst, const void *src) +{ + movdir64b((void __force *)dst, src); +} + /** * enqcmds - Enqueue a command in supervisor (CPL0) mode * @dst: destination, in MMIO space (must be 512-bit aligned) diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a800abb1a9925..d8416b3bf832e 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,11 +12,6 @@ /* image of the saved processor state */ struct saved_context { - /* - * On x86_32, all segment registers except gs are saved at kernel - * entry in pt_regs. - */ - u16 gs; unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; struct saved_msrs saved_msrs; @@ -27,6 +22,11 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + /* + * On x86_32, all segment registers except gs are saved at kernel + * entry in pt_regs. + */ + u16 gs; bool misc_enable_saved; } __attribute__((packed)); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index f44e2f9ab65d7..2fc7bc3863ff6 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,19 +16,17 @@ #include /* for TS_COMPAT */ #include +/* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; -#if defined(CONFIG_X86_32) -#define ia32_sys_call_table sys_call_table -#else /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ -extern const sys_call_ptr_t ia32_sys_call_table[]; -extern const sys_call_ptr_t x32_sys_call_table[]; -#endif +extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. @@ -127,6 +125,7 @@ static inline int syscall_get_arch(struct task_struct *task) } bool do_syscall_64(struct pt_regs *regs, int nr); +void do_int80_emulation(struct pt_regs *regs); #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 237dc8cdd12b9..3a7755c1a4410 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -78,10 +78,10 @@ extern int __get_user_bad(void); int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ - asm volatile("call __" #fn "_%P4" \ + asm volatile("call __" #fn "_%c[size]" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ - : "0" (ptr), "i" (sizeof(*(ptr)))); \ + : "0" (ptr), [size] "i" (sizeof(*(ptr)))); \ instrument_get_user(__val_gu); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ @@ -177,7 +177,7 @@ extern void __put_user_nocheck_8(void); __chk_user_ptr(__ptr); \ __ptr_pu = __ptr; \ __val_pu = __x; \ - asm volatile("call __" #fn "_%P[size]" \ + asm volatile("call __" #fn "_%c[size]" \ : "=c" (__ret_pu), \ ASM_CALL_CONSTRAINT \ : "0" (__ptr_pu), \ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index c878616a18b85..550dcbbbb1756 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -30,12 +30,13 @@ struct x86_init_mpparse { * @reserve_resources: reserve the standard resources for the * platform * @memory_setup: platform specific memory setup - * + * @dmi_setup: platform specific DMI setup */ struct x86_init_resources { void (*probe_roms)(void); void (*reserve_resources)(void); char *(*memory_setup)(void); + void (*dmi_setup)(void); }; /** diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index a9088250770f2..64fbd2dbc5b76 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,6 +62,11 @@ void xen_arch_unregister_cpu(int num); #ifdef CONFIG_PVH void __init xen_pvh_init(struct boot_params *boot_params); void __init mem_map_via_hcall(struct boot_params *boot_params_p); +#ifdef CONFIG_XEN_PVH +void __init xen_reserve_extra_memory(struct boot_params *bootp); +#else +static inline void xen_reserve_extra_memory(struct boot_params *bootp) { } +#endif #endif /* Lazy mode for batching updates / context switch */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 01d19fc223463..eeea058cf6028 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -38,6 +38,7 @@ #define XLF_EFI_KEXEC (1<<4) #define XLF_5LEVEL (1<<5) #define XLF_5LEVEL_ENABLED (1<<6) +#define XLF_MEM_ENCRYPTION (1<<7) #ifndef __ASSEMBLY__ diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 8d8752b44f113..ff8f25faca3dd 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -20,7 +20,7 @@ bool cpc_supported_by_cpu(void) (boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f))) return true; else if (boot_cpu_data.x86 == 0x17 && - boot_cpu_data.x86_model >= 0x70 && boot_cpu_data.x86_model <= 0x7f) + boot_cpu_data.x86_model >= 0x30 && boot_cpu_data.x86_model <= 0x7f) return true; return boot_cpu_has(X86_FEATURE_CPPC); } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 053f6dcc6b2c7..7fa64ad22be01 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -214,7 +214,14 @@ static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) int amd_smn_read(u16 node, u32 address, u32 *value) { - return __amd_smn_rw(node, address, value, false); + int err = __amd_smn_rw(node, address, value, false); + + if (PCI_POSSIBLE_ERROR(*value)) { + err = -ENODEV; + *value = 0; + } + + return err; } EXPORT_SYMBOL_GPL(amd_smn_read); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 89c0c8a3fc7e6..df2dc9fb6c6dd 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -136,32 +136,6 @@ static u32 __init allocate_aperture(void) } -/* Find a PCI capability */ -static u32 __init find_cap(int bus, int slot, int func, int cap) -{ - int bytes; - u8 pos; - - if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) & - PCI_STATUS_CAP_LIST)) - return 0; - - pos = read_pci_config_byte(bus, slot, func, PCI_CAPABILITY_LIST); - for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) { - u8 id; - - pos &= ~3; - id = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_ID); - if (id == 0xff) - break; - if (id == cap) - return pos; - pos = read_pci_config_byte(bus, slot, func, - pos+PCI_CAP_LIST_NEXT); - } - return 0; -} - /* Read a standard AGPv3 bridge header */ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order) { @@ -250,8 +224,8 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) case PCI_CLASS_BRIDGE_HOST: case PCI_CLASS_BRIDGE_OTHER: /* needed? */ /* AGP bridge? */ - cap = find_cap(bus, slot, func, - PCI_CAP_ID_AGP); + cap = pci_early_find_cap(bus, slot, + func, PCI_CAP_ID_AGP); if (!cap) break; *valid_agp = 1; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4667bc4b00ab8..a04a5163e56c3 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1724,11 +1724,11 @@ static int x2apic_state; static bool x2apic_hw_locked(void) { - u64 ia32_cap; + u64 x86_arch_cap_msr; u64 msr; - ia32_cap = x86_read_arch_cap_msr(); - if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + x86_arch_cap_msr = x86_read_arch_cap_msr(); + if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) { rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); return (msr & LEGACY_XAPIC_DISABLED); } @@ -1808,7 +1808,7 @@ void x2apic_setup(void) __x2apic_enable(); } -static __init void apic_set_fixmap(void); +static __init void apic_set_fixmap(bool read_apic); static __init void x2apic_disable(void) { @@ -1830,7 +1830,12 @@ static __init void x2apic_disable(void) } __x2apic_disable(); - apic_set_fixmap(); + /* + * Don't reread the APIC ID as it was already done from + * check_x2apic() and the APIC driver still is a x2APIC variant, + * which fails to do the read after x2APIC was disabled. + */ + apic_set_fixmap(false); } static __init void x2apic_enable(void) @@ -2095,13 +2100,14 @@ void __init init_apic_mappings(void) } } -static __init void apic_set_fixmap(void) +static __init void apic_set_fixmap(bool read_apic) { set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr); apic_mmio_base = APIC_BASE; apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", apic_mmio_base, mp_lapic_addr); - apic_read_boot_cpu_id(false); + if (read_apic) + apic_read_boot_cpu_id(false); } void __init register_lapic_address(unsigned long address) @@ -2111,7 +2117,7 @@ void __init register_lapic_address(unsigned long address) mp_lapic_addr = address; if (!x2apic_mode) - apic_set_fixmap(); + apic_set_fixmap(true); } /* diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 185738c727661..29cd0543fc2fb 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1036,7 +1036,8 @@ static void __vector_schedule_cleanup(struct apic_chip_data *apicd) add_timer_on(&cl->timer, cpu); } } else { - apicd->prev_vector = 0; + pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu); + free_moved_vector(apicd); } raw_spin_unlock(&vector_lock); } @@ -1073,6 +1074,7 @@ void irq_complete_move(struct irq_cfg *cfg) */ void irq_force_complete_move(struct irq_desc *desc) { + unsigned int cpu = smp_processor_id(); struct apic_chip_data *apicd; struct irq_data *irqd; unsigned int vector; @@ -1097,10 +1099,11 @@ void irq_force_complete_move(struct irq_desc *desc) goto unlock; /* - * If prev_vector is empty, no action required. + * If prev_vector is empty or the descriptor is neither currently + * nor previously on the outgoing CPU no action required. */ vector = apicd->prev_vector; - if (!vector) + if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu)) goto unlock; /* diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f3abca334199d..0838ea579eb0f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -572,8 +572,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) case 0x1a: switch (c->x86_model) { - case 0x00 ... 0x0f: - case 0x20 ... 0x2f: + case 0x00 ... 0x2f: case 0x40 ... 0x4f: case 0x70 ... 0x7f: setup_force_cpu_cap(X86_FEATURE_ZEN5); @@ -989,11 +988,11 @@ static bool cpu_has_zenbleed_microcode(void) u32 good_rev = 0; switch (boot_cpu_data.x86_model) { - case 0x30 ... 0x3f: good_rev = 0x0830107a; break; - case 0x60 ... 0x67: good_rev = 0x0860010b; break; - case 0x68 ... 0x6f: good_rev = 0x08608105; break; - case 0x70 ... 0x7f: good_rev = 0x08701032; break; - case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + case 0x30 ... 0x3f: good_rev = 0x0830107b; break; + case 0x60 ... 0x67: good_rev = 0x0860010c; break; + case 0x68 ... 0x6f: good_rev = 0x08608107; break; + case 0x70 ... 0x7f: good_rev = 0x08701033; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00009; break; default: return false; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 48d049cd74e71..e7ceee008bd09 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -61,6 +61,8 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); +static u64 __ro_after_init x86_arch_cap_msr; + static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; @@ -144,6 +146,8 @@ void __init cpu_select_mitigations(void) x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; } + x86_arch_cap_msr = x86_read_arch_cap_msr(); + /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); @@ -301,8 +305,6 @@ static const char * const taa_strings[] = { static void __init taa_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_TAA)) { taa_mitigation = TAA_MITIGATION_OFF; return; @@ -341,9 +343,8 @@ static void __init taa_select_mitigation(void) * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode * update is required. */ - ia32_cap = x86_read_arch_cap_msr(); - if ( (ia32_cap & ARCH_CAP_MDS_NO) && - !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) && + !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)) taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; /* @@ -401,8 +402,6 @@ static const char * const mmio_strings[] = { static void __init mmio_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || cpu_mitigations_off()) { @@ -413,8 +412,6 @@ static void __init mmio_select_mitigation(void) if (mmio_mitigation == MMIO_MITIGATION_OFF) return; - ia32_cap = x86_read_arch_cap_msr(); - /* * Enable CPU buffer clear mitigation for host and VMM, if also affected * by MDS or TAA. Otherwise, enable mitigation for VMM only. @@ -422,6 +419,13 @@ static void __init mmio_select_mitigation(void) if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + + /* + * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based + * mitigations, disable KVM-only mitigation in that case. + */ + if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) + static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); @@ -430,7 +434,7 @@ static void __init mmio_select_mitigation(void) * be propagated to uncore buffers, clearing the Fill buffers on idle * is required irrespective of SMT state. */ - if (!(ia32_cap & ARCH_CAP_FBSDP_NO)) + if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) static_branch_enable(&mds_idle_clear); /* @@ -440,10 +444,10 @@ static void __init mmio_select_mitigation(void) * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS * affected systems. */ - if ((ia32_cap & ARCH_CAP_FB_CLEAR) || + if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) || (boot_cpu_has(X86_FEATURE_MD_CLEAR) && boot_cpu_has(X86_FEATURE_FLUSH_L1D) && - !(ia32_cap & ARCH_CAP_MDS_NO))) + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))) mmio_mitigation = MMIO_MITIGATION_VERW; else mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; @@ -473,6 +477,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str) } early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); +#undef pr_fmt +#define pr_fmt(fmt) "Register File Data Sampling: " fmt + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; + +static const char * const rfds_strings[] = { + [RFDS_MITIGATION_OFF] = "Vulnerable", + [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", + [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", +}; + +static void __init rfds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { + rfds_mitigation = RFDS_MITIGATION_OFF; + return; + } + if (rfds_mitigation == RFDS_MITIGATION_OFF) + return; + + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + else + rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; +} + +static __init int rfds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + return 0; + + if (!strcmp(str, "off")) + rfds_mitigation = RFDS_MITIGATION_OFF; + else if (!strcmp(str, "on")) + rfds_mitigation = RFDS_MITIGATION_VERW; + + return 0; +} +early_param("reg_file_data_sampling", rfds_parse_cmdline); + #undef pr_fmt #define pr_fmt(fmt) "" fmt @@ -498,11 +553,19 @@ static void __init md_clear_update_mitigation(void) taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } - if (mmio_mitigation == MMIO_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + /* + * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear + * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. + */ + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } + if (rfds_mitigation == RFDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_RFDS)) { + rfds_mitigation = RFDS_MITIGATION_VERW; + rfds_select_mitigation(); + } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); @@ -512,6 +575,8 @@ static void __init md_clear_update_mitigation(void) pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); + if (boot_cpu_has_bug(X86_BUG_RFDS)) + pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) @@ -519,11 +584,12 @@ static void __init md_clear_select_mitigation(void) mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); + rfds_select_mitigation(); /* - * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update - * and print their mitigation after MDS, TAA and MMIO Stale Data - * mitigation selection is done. + * As these mitigations are inter-related and rely on VERW instruction + * to clear the microarchitural buffers, update and print their status + * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } @@ -590,8 +656,6 @@ void update_srbds_msr(void) static void __init srbds_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return; @@ -600,8 +664,7 @@ static void __init srbds_select_mitigation(void) * are only exposed to SRBDS when TSX is enabled or when CPU is affected * by Processor MMIO Stale Data vulnerability. */ - ia32_cap = x86_read_arch_cap_msr(); - if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && + if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) @@ -744,7 +807,7 @@ static void __init gds_select_mitigation(void) /* Will verify below that mitigation _can_ be disabled */ /* No microcode */ - if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) { if (gds_mitigation == GDS_MITIGATION_FORCE) { /* * This only needs to be done on the boot CPU so do it @@ -1474,20 +1537,25 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +static bool __ro_after_init rrsba_disabled; + /* Disable in-kernel use of non-RSB RET predictors */ static void __init spec_ctrl_disable_kernel_rrsba(void) { - u64 ia32_cap; + if (rrsba_disabled) + return; - if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) { + rrsba_disabled = true; return; + } - ia32_cap = x86_read_arch_cap_msr(); + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; - if (ia32_cap & ARCH_CAP_RRSBA) { - x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - update_spec_ctrl(x86_spec_ctrl_base); - } + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + rrsba_disabled = true; } static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) @@ -1537,6 +1605,74 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ dump_stack(); } +/* + * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by + * branch history in userspace. Not needed if BHI_NO is set. + */ +static bool __init spec_ctrl_bhi_dis(void) +{ + if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); + + return true; +} + +enum bhi_mitigations { + BHI_MITIGATION_OFF, + BHI_MITIGATION_ON, +}; + +static enum bhi_mitigations bhi_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF; + +static int __init spectre_bhi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + bhi_mitigation = BHI_MITIGATION_OFF; + else if (!strcmp(str, "on")) + bhi_mitigation = BHI_MITIGATION_ON; + else + pr_err("Ignoring unknown spectre_bhi option (%s)", str); + + return 0; +} +early_param("spectre_bhi", spectre_bhi_parse_cmdline); + +static void __init bhi_select_mitigation(void) +{ + if (bhi_mitigation == BHI_MITIGATION_OFF) + return; + + /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + spec_ctrl_disable_kernel_rrsba(); + if (rrsba_disabled) + return; + } + + if (spec_ctrl_bhi_dis()) + return; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Mitigate KVM by default */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + + /* Mitigate syscalls when the mitigation is forced =on */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1648,6 +1784,9 @@ static void __init spectre_v2_select_mitigation(void) mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); + if (boot_cpu_has(X86_BUG_BHI)) + bhi_select_mitigation(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -1762,8 +1901,6 @@ static void update_indir_branch_cond(void) /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { - u64 ia32_cap = x86_read_arch_cap_msr(); - /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. @@ -1778,7 +1915,7 @@ static void update_mds_branch_idle(void) if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || - (ia32_cap & ARCH_CAP_FBSDP_NO)) { + (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); } } @@ -2612,6 +2749,11 @@ static ssize_t mmio_stale_data_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t rfds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -2620,15 +2762,15 @@ static char *stibp_state(void) switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: - return ", STIBP: disabled"; + return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: - return ", STIBP: forced"; + return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: - return ", STIBP: always-on"; + return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) - return ", STIBP: conditional"; + return "; STIBP: conditional"; } return ""; } @@ -2637,10 +2779,10 @@ static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) - return ", IBPB: always-on"; + return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) - return ", IBPB: conditional"; - return ", IBPB: disabled"; + return "; IBPB: conditional"; + return "; IBPB: disabled"; } return ""; } @@ -2650,14 +2792,32 @@ static char *pbrsb_eibrs_state(void) if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) - return ", PBRSB-eIBRS: SW sequence"; + return "; PBRSB-eIBRS: SW sequence"; else - return ", PBRSB-eIBRS: Vulnerable"; + return "; PBRSB-eIBRS: Vulnerable"; } else { - return ", PBRSB-eIBRS: Not affected"; + return "; PBRSB-eIBRS: Not affected"; } } +static const char *spectre_bhi_state(void) +{ + if (!boot_cpu_has_bug(X86_BUG_BHI)) + return "; BHI: Not affected"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + return "; BHI: BHI_DIS_S"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + return "; BHI: SW loop, KVM: SW loop"; + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) && + rrsba_disabled) + return "; BHI: Retpoline"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) + return "; BHI: Vulnerable, KVM: SW loop"; + + return "; BHI: Vulnerable"; +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) @@ -2670,13 +2830,15 @@ static ssize_t spectre_v2_show_state(char *buf) spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sysfs_emit(buf, "%s%s%s%s%s%s%s\n", + return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", pbrsb_eibrs_state(), + spectre_bhi_state(), + /* this should always be at the end */ spectre_v2_module_string()); } @@ -2771,6 +2933,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_GDS: return gds_show_state(buf); + case X86_BUG_RFDS: + return rfds_show_state(buf); + default: break; } @@ -2845,4 +3010,9 @@ ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_GDS); } + +ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); +} #endif diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index c131c412db89c..1cfe0921ac677 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -178,7 +178,16 @@ struct _cpuid4_info_regs { struct amd_northbridge *nb; }; -static unsigned short num_cache_leaves; +static inline unsigned int get_num_cache_leaves(unsigned int cpu) +{ + return get_cpu_cacheinfo(cpu)->num_leaves; +} + +static inline void +set_num_cache_leaves(unsigned int nr_leaves, unsigned int cpu) +{ + get_cpu_cacheinfo(cpu)->num_leaves = nr_leaves; +} /* AMD doesn't have CPUID4. Emulate it here to report the same information to the user. This makes some assumptions about the machine: @@ -718,19 +727,21 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c) void init_amd_cacheinfo(struct cpuinfo_x86 *c) { + unsigned int cpu = c->cpu_index; + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - num_cache_leaves = find_num_cache_leaves(c); + set_num_cache_leaves(find_num_cache_leaves(c), cpu); } else if (c->extended_cpuid_level >= 0x80000006) { if (cpuid_edx(0x80000006) & 0xf000) - num_cache_leaves = 4; + set_num_cache_leaves(4, cpu); else - num_cache_leaves = 3; + set_num_cache_leaves(3, cpu); } } void init_hygon_cacheinfo(struct cpuinfo_x86 *c) { - num_cache_leaves = find_num_cache_leaves(c); + set_num_cache_leaves(find_num_cache_leaves(c), c->cpu_index); } void init_intel_cacheinfo(struct cpuinfo_x86 *c) @@ -742,19 +753,19 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; if (c->cpuid_level > 3) { - static int is_initialized; - - if (is_initialized == 0) { - /* Init num_cache_leaves from boot CPU */ - num_cache_leaves = find_num_cache_leaves(c); - is_initialized++; - } + /* + * There should be at least one leaf. A non-zero value means + * that the number of leaves has been initialized. + */ + if (!get_num_cache_leaves(c->cpu_index)) + set_num_cache_leaves(find_num_cache_leaves(c), + c->cpu_index); /* * Whenever possible use cpuid(4), deterministic cache * parameters cpuid leaf to find the cache details */ - for (i = 0; i < num_cache_leaves; i++) { + for (i = 0; i < get_num_cache_leaves(c->cpu_index); i++) { struct _cpuid4_info_regs this_leaf = {}; int retval; @@ -790,14 +801,14 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for * trace cache */ - if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) { + if ((!get_num_cache_leaves(c->cpu_index) || c->x86 == 15) && c->cpuid_level > 1) { /* supports eax=2 call */ int j, n; unsigned int regs[4]; unsigned char *dp = (unsigned char *)regs; int only_trace = 0; - if (num_cache_leaves != 0 && c->x86 == 15) + if (get_num_cache_leaves(c->cpu_index) && c->x86 == 15) only_trace = 1; /* Number of times to iterate */ @@ -991,14 +1002,6 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, int init_cache_level(unsigned int cpu) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); - - if (!num_cache_leaves) - return -ENOENT; - if (!this_cpu_ci) - return -EINVAL; - this_cpu_ci->num_levels = 3; - this_cpu_ci->num_leaves = num_cache_leaves; return 0; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index fbc4e60d027cb..ccd1c5fa29062 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1096,18 +1096,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) void get_cpu_address_sizes(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; - bool vp_bits_from_cpuid = true; if (!cpu_has(c, X86_FEATURE_CPUID) || - (c->extended_cpuid_level < 0x80000008)) - vp_bits_from_cpuid = false; - - if (vp_bits_from_cpuid) { - cpuid(0x80000008, &eax, &ebx, &ecx, &edx); - - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; - } else { + (c->extended_cpuid_level < 0x80000008)) { if (IS_ENABLED(CONFIG_X86_64)) { c->x86_clflush_size = 64; c->x86_phys_bits = 36; @@ -1121,7 +1112,17 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c) cpu_has(c, X86_FEATURE_PSE36)) c->x86_phys_bits = 36; } + } else { + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); + + c->x86_virt_bits = (eax >> 8) & 0xff; + c->x86_phys_bits = eax & 0xff; + + /* Provide a sane default if not enumerated: */ + if (!c->x86_clflush_size) + c->x86_clflush_size = 32; } + c->x86_cache_bits = c->x86_phys_bits; c->x86_cache_alignment = c->x86_clflush_size; } @@ -1163,6 +1164,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SPECTRE_V2 BIT(8) #define NO_MMIO BIT(9) #define NO_EIBRS_PBRSB BIT(10) +#define NO_BHI BIT(11) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1225,18 +1227,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), {} }; @@ -1267,6 +1269,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SRSO BIT(5) /* CPU is affected by GDS */ #define GDS BIT(6) +/* CPU is affected by Register File Data Sampling */ +#define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1294,9 +1298,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), @@ -1315,28 +1328,46 @@ static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long whi u64 x86_read_arch_cap_msr(void) { - u64 ia32_cap = 0; + u64 x86_arch_cap_msr = 0; if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr); + + return x86_arch_cap_msr; +} - return ia32_cap; +static bool arch_cap_mmio_immune(u64 x86_arch_cap_msr) +{ + return (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO && + x86_arch_cap_msr & ARCH_CAP_PSDP_NO && + x86_arch_cap_msr & ARCH_CAP_SBDR_SSDP_NO); } -static bool arch_cap_mmio_immune(u64 ia32_cap) +static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) { - return (ia32_cap & ARCH_CAP_FBSDP_NO && - ia32_cap & ARCH_CAP_PSDP_NO && - ia32_cap & ARCH_CAP_SBDR_SSDP_NO); + /* The "immunity" bit trumps everything else: */ + if (x86_arch_cap_msr & ARCH_CAP_RFDS_NO) + return false; + + /* + * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to + * indicate that mitigation is needed because guest is running on a + * vulnerable hardware or may migrate to such hardware: + */ + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) + return true; + + /* Only consult the blacklist when there is no enumeration: */ + return cpu_matches(cpu_vuln_blacklist, RFDS); } static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { - u64 ia32_cap = x86_read_arch_cap_msr(); + u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && - !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) @@ -1348,7 +1379,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && - !(ia32_cap & ARCH_CAP_SSB_NO) && + !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -1356,15 +1387,15 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature * flag and protect from vendor-specific bugs via the whitelist. */ - if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { + if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO)) setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && - !(ia32_cap & ARCH_CAP_MDS_NO)) { + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); @@ -1383,9 +1414,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * TSX_CTRL check alone is not sufficient for cases when the microcode * update is not present or running as guest that don't get TSX_CTRL. */ - if (!(ia32_cap & ARCH_CAP_TAA_NO) && + if (!(x86_arch_cap_msr & ARCH_CAP_TAA_NO) && (cpu_has(c, X86_FEATURE_RTM) || - (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + (x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); /* @@ -1411,7 +1442,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (!arch_cap_mmio_immune(ia32_cap)) { + if (!arch_cap_mmio_immune(x86_arch_cap_msr)) { if (cpu_matches(cpu_vuln_blacklist, MMIO)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) @@ -1419,7 +1450,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) } if (!cpu_has(c, X86_FEATURE_BTC_NO)) { - if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (x86_arch_cap_msr & ARCH_CAP_RSBA)) setup_force_cpu_bug(X86_BUG_RETBLEED); } @@ -1437,15 +1468,25 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * disabling AVX2. The only way to do this in HW is to clear XCR0[2], * which means that AVX will be disabled. */ - if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(x86_arch_cap_msr & ARCH_CAP_GDS_NO) && boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); + if (vulnerable_to_rfds(x86_arch_cap_msr)) + setup_force_cpu_bug(X86_BUG_RFDS); + + /* When virtualized, eIBRS could be hidden, assume vulnerable */ + if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && + !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || + boot_cpu_has(X86_FEATURE_HYPERVISOR))) + setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ - if (ia32_cap & ARCH_CAP_RDCL_NO) + if (x86_arch_cap_msr & ARCH_CAP_RDCL_NO) return; setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); @@ -1587,6 +1628,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (have_cpuid_p()) { cpu_detect(c); get_cpu_vendor(c); + intel_unlock_cpuid_leafs(c); get_cpu_cap(c); setup_force_cpu_cap(X86_FEATURE_CPUID); get_cpu_address_sizes(c); @@ -1743,7 +1785,7 @@ static void generic_identify(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); - + intel_unlock_cpuid_leafs(c); get_cpu_cap(c); get_cpu_address_sizes(c); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 885281ae79a54..6ae0e169847aa 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -56,9 +56,11 @@ extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; extern void __init tsx_init(void); void tsx_ap_init(void); +void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c); #else static inline void tsx_init(void) { } static inline void tsx_ap_init(void) { } +static inline void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) { } #endif /* CONFIG_CPU_SUP_INTEL */ extern void init_spectral_chicken(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index e462c1d3800a6..6fb6d8a57ceca 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_VAES, X86_FEATURE_AVX }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, @@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 40dec9b56f87d..605dc6959d65a 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -268,19 +268,26 @@ static void detect_tme_early(struct cpuinfo_x86 *c) c->x86_phys_bits -= keyid_bits; } +void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; + + if (c->x86 < 6 || (c->x86 == 6 && c->x86_model < 0xd)) + return; + + /* + * The BIOS can have limited CPUID to leaf 2, which breaks feature + * enumeration. Unlock it and update the maximum leaf info. + */ + if (msr_clear_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) + c->cpuid_level = cpuid_eax(0); +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; - /* Unmask CPUID levels if masked: */ - if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { - if (msr_clear_bit(MSR_IA32_MISC_ENABLE, - MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) { - c->cpuid_level = cpuid_eax(0); - get_cpu_cap(c); - } - } - if ((c->x86 == 0xf && c->x86_model >= 0x03) || (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index ad6776081e60d..ae71b8ef909c9 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -39,9 +39,7 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; - m->vendor | m->family | m->model | m->steppings | m->feature; - m++) { + for (m = match; m->flags & X86_CPU_ID_FLAG_ENTRY_VALID; m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index bc39252bc54f2..c17f9403cf6c0 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2474,12 +2474,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 13b45b9c806da..620f0af713ca2 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -465,7 +465,7 @@ static bool early_apply_microcode(u32 cpuid_1_eax, u32 old_rev, void *ucode, siz return !__apply_microcode_amd(mc); } -static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) +static bool get_builtin_microcode(struct cpio_data *cp, u8 family) { char fw_name[36] = "amd-ucode/microcode_amd.bin"; struct firmware fw; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 19e0681f04356..d04371e851b4c 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -231,9 +231,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r) static bool __rdt_get_mem_config_amd(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - union cpuid_0x10_3_eax eax; - union cpuid_0x10_x_edx edx; - u32 ebx, ecx, subleaf; + u32 eax, ebx, ecx, edx, subleaf; /* * Query CPUID_Fn80000020_EDX_x01 for MBA and @@ -241,9 +239,9 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) */ subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 : 1; - cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full); - hw_res->num_closid = edx.split.cos_max + 1; - r->default_ctrl = MAX_MBA_BW_AMD; + cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx); + hw_res->num_closid = edx + 1; + r->default_ctrl = 1 << eax; /* AMD does not use delay */ r->membw.delay_linear = false; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index a4f1aa15f0a2a..52e7e7deee106 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -18,7 +18,6 @@ #define MBM_OVERFLOW_INTERVAL 1000 #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 -#define MAX_MBA_BW_AMD 0x800 #define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) @@ -296,14 +295,10 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @prev_bw_bytes: Previous bytes value read for bandwidth calculation * @prev_bw: The most recent bandwidth in MBps - * @delta_bw: Difference between the current and previous bandwidth - * @delta_comp: Indicates whether to compute the delta_bw */ struct mbm_state { u64 prev_bw_bytes; u32 prev_bw; - u32 delta_bw; - bool delta_comp; }; /** @@ -395,6 +390,8 @@ struct rdt_parse_data { * @msr_update: Function pointer to update QOS MSRs * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. + * @mbm_cfg_mask: Bandwidth sources that can be tracked when Bandwidth + * Monitoring Event Configuration (BMEC) is supported. * @cdp_enabled: CDP state of this resource * * Members of this structure are either private to the architecture @@ -409,6 +406,7 @@ struct rdt_hw_resource { struct rdt_resource *r); unsigned int mon_scale; unsigned int mbm_width; + unsigned int mbm_cfg_mask; bool cdp_enabled; }; diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f136ac046851c..3a6c069614eb8 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -440,9 +440,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) cur_bw = bytes / SZ_1M; - if (m->delta_comp) - m->delta_bw = abs(cur_bw - m->prev_bw); - m->delta_comp = false; m->prev_bw = cur_bw; } @@ -520,11 +517,11 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; - u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; struct list_head *head; struct rdtgroup *entry; + u32 cur_bw, user_bw; if (!is_mbm_local_enabled()) return; @@ -543,7 +540,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) cur_bw = pmbm_data->prev_bw; user_bw = dom_mba->mbps_val[closid]; - delta_bw = pmbm_data->delta_bw; /* MBA resource doesn't support CDP */ cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); @@ -555,49 +551,31 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) list_for_each_entry(entry, head, mon.crdtgrp_list) { cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; cur_bw += cmbm_data->prev_bw; - delta_bw += cmbm_data->delta_bw; } /* * Scale up/down the bandwidth linearly for the ctrl group. The * bandwidth step is the bandwidth granularity specified by the * hardware. - * - * The delta_bw is used when increasing the bandwidth so that we - * dont alternately increase and decrease the control values - * continuously. - * - * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if - * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep - * switching between 90 and 110 continuously if we only check - * cur_bw < user_bw. + * Always increase throttling if current bandwidth is above the + * target set by user. + * But avoid thrashing up and down on every poll by checking + * whether a decrease in throttling is likely to push the group + * back over target. E.g. if currently throttling to 30% of bandwidth + * on a system with 10% granularity steps, check whether moving to + * 40% would go past the limit by multiplying current bandwidth by + * "(30 + 10) / 30". */ if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { new_msr_val = cur_msr_val - r_mba->membw.bw_gran; } else if (cur_msr_val < MAX_MBA_BW && - (user_bw > (cur_bw + delta_bw))) { + (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) { new_msr_val = cur_msr_val + r_mba->membw.bw_gran; } else { return; } resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); - - /* - * Delta values are updated dynamically package wise for each - * rdtgrp every time the throttle MSR changes value. - * - * This is because (1)the increase in bandwidth is not perfectly - * linear and only "approximately" linear even when the hardware - * says it is linear.(2)Also since MBA is a core specific - * mechanism, the delta values vary based on number of cores used - * by the rdtgrp. - */ - pmbm_data->delta_comp = true; - list_for_each_entry(entry, head, mon.crdtgrp_list) { - cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; - cmbm_data->delta_comp = true; - } } static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) @@ -813,6 +791,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) return ret; if (rdt_cpu_has(X86_FEATURE_BMEC)) { + u32 eax, ebx, ecx, edx; + + /* Detect list of bandwidth sources that can be tracked */ + cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx); + hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { mbm_total_event.configurable = true; mbm_config_rftype_init("mbm_total_bytes_config"); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 69a1de92384ab..2b69e560b05f1 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1620,12 +1620,6 @@ static int mbm_config_write_domain(struct rdt_resource *r, struct mon_config_info mon_info = {0}; int ret = 0; - /* mon_config cannot be more than the supported set of events */ - if (val > MAX_EVT_CONFIG_BITS) { - rdt_last_cmd_puts("Invalid event configuration\n"); - return -EINVAL; - } - /* * Read the current config value first. If both are the same then * no need to write it again. @@ -1663,6 +1657,7 @@ static int mbm_config_write_domain(struct rdt_resource *r, static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); char *dom_str = NULL, *id_str; unsigned long dom_id, val; struct rdt_domain *d; @@ -1686,6 +1681,13 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) return -EINVAL; } + /* Value from user cannot be more than the supported set of events */ + if ((val & hw_res->mbm_cfg_mask) != val) { + rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n", + hw_res->mbm_cfg_mask); + return -EINVAL; + } + list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { ret = mbm_config_write_domain(r, d, evtid, val); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 0dad49a09b7a9..0ebca40dfd74b 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 59f4aefc6bc16..b98cdd0be07a5 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -29,6 +29,37 @@ #include #include +static void __init early_pci_clear_msi(int bus, int slot, int func) +{ + int pos; + u16 ctrl; + + if (likely(!pci_early_clear_msi)) + return; + + pr_info_once("Clearing MSI/MSI-X enable bits early in boot (quirk)\n"); + + pos = pci_early_find_cap(bus, slot, func, PCI_CAP_ID_MSI); + if (pos) { + ctrl = read_pci_config_16(bus, slot, func, pos + PCI_MSI_FLAGS); + ctrl &= ~PCI_MSI_FLAGS_ENABLE; + write_pci_config_16(bus, slot, func, pos + PCI_MSI_FLAGS, ctrl); + + /* Read again to flush previous write */ + ctrl = read_pci_config_16(bus, slot, func, pos + PCI_MSI_FLAGS); + } + + pos = pci_early_find_cap(bus, slot, func, PCI_CAP_ID_MSIX); + if (pos) { + ctrl = read_pci_config_16(bus, slot, func, pos + PCI_MSIX_FLAGS); + ctrl &= ~PCI_MSIX_FLAGS_ENABLE; + write_pci_config_16(bus, slot, func, pos + PCI_MSIX_FLAGS, ctrl); + + /* Read again to flush previous write */ + ctrl = read_pci_config_16(bus, slot, func, pos + PCI_MSIX_FLAGS); + } +} + static void __init fix_hypertransport_config(int num, int slot, int func) { u32 htcfg; @@ -728,6 +759,7 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, + { PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0, early_pci_clear_msi}, {} }; @@ -780,6 +812,10 @@ static int __init check_dev_quirk(int num, int slot, int func) PCI_HEADER_TYPE); if ((type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) { + /* pci_early_clear_msi scans the buses differently. */ + if (pci_early_clear_msi) + return -1; + sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); if (sec > num) early_pci_scan_bus(sec); @@ -806,8 +842,13 @@ static void __init early_pci_scan_bus(int bus) void __init early_quirks(void) { + int bus; + if (!early_pci_allowed()) return; early_pci_scan_bus(0); + /* pci_early_clear_msi scans more buses. */ + for (bus = 1; pci_early_clear_msi && bus < 256; bus++) + early_pci_scan_bus(bus); } diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index e963344b04490..53935b4d62e30 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -2,6 +2,7 @@ /* * EISA specific code */ +#include #include #include #include @@ -12,7 +13,7 @@ static __init int eisa_bus_probe(void) { void __iomem *p; - if (xen_pv_domain() && !xen_initial_domain()) + if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return 0; p = ioremap(0x0FFFD9, 4); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 117e74c44e756..33a214b1a4cec 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -178,10 +178,11 @@ void fpu__init_cpu_xstate(void) * Must happen after CR4 setup and before xsetbv() to allow KVM * lazy passthrough. Write independent of the dynamic state static * key as that does not work on the boot CPU. This also ensures - * that any stale state is wiped out from XFD. + * that any stale state is wiped out from XFD. Reset the per CPU + * xfd cache too. */ if (cpu_feature_enabled(X86_FEATURE_XFD)) - wrmsrl(MSR_IA32_XFD, init_fpstate.xfd); + xfd_set_state(init_fpstate.xfd); /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 3518fb26d06b0..19ca623ffa2ac 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -148,20 +148,26 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs #endif #ifdef CONFIG_X86_64 +static inline void xfd_set_state(u64 xfd) +{ + wrmsrl(MSR_IA32_XFD, xfd); + __this_cpu_write(xfd_state, xfd); +} + static inline void xfd_update_state(struct fpstate *fpstate) { if (fpu_state_size_dynamic()) { u64 xfd = fpstate->xfd; - if (__this_cpu_read(xfd_state) != xfd) { - wrmsrl(MSR_IA32_XFD, xfd); - __this_cpu_write(xfd_state, xfd); - } + if (__this_cpu_read(xfd_state) != xfd) + xfd_set_state(xfd); } } extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else +static inline void xfd_set_state(u64 xfd) { } + static inline void xfd_update_state(struct fpstate *fpstate) { } static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index a0ce46c0a2d88..a6a3475e1d609 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -335,7 +335,16 @@ static int can_probe(unsigned long paddr) kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, bool *on_func_entry) { - if (is_endbr(*(u32 *)addr)) { + u32 insn; + + /* + * Since 'addr' is not guaranteed to be safe to access, use + * copy_from_kernel_nofault() to read the instruction: + */ + if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32))) + return NULL; + + if (is_endbr(insn)) { *on_func_entry = !offset || offset == 4; if (*on_func_entry) offset = 4; diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index dd2ec14adb77b..15af7e98e161a 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe_ctlblk *kcb; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index bc0a5348b4a62..a0fa9f2825433 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -295,8 +295,15 @@ void machine_kexec_cleanup(struct kimage *image) void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; - void *control_page; + unsigned int host_mem_enc_active; int save_ftrace_enabled; + void *control_page; + + /* + * This must be done before load_segments() since if call depth tracking + * is used then GS must be valid to make any function calls. + */ + host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -358,7 +365,7 @@ void machine_kexec(struct kimage *image) (unsigned long)page_list, image->start, image->preserve_context, - cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)); + host_mem_enc_active); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 3082cf24b69e3..6da2cfa23c293 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -636,7 +636,7 @@ void nmi_backtrace_stall_check(const struct cpumask *btp) msgp = nmi_check_stall_msg[idx]; if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1)) modp = ", but OK because ignore_nmis was set"; - if (nmi_seq & ~0x1) + if (nmi_seq & 0x1) msghp = " (CPU currently in NMI handler function)"; else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) msghp = " (CPU exited one NMI handler function)"; diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 319fef37d9dce..cc2c34ba7228a 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -203,16 +203,6 @@ void __init probe_roms(void) unsigned char c; int i; - /* - * The ROM memory range is not part of the e820 table and is therefore not - * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted - * memory, and SNP requires encrypted memory to be validated before access. - * Do that here. - */ - snp_prep_memory(video_rom_resource.start, - ((system_rom_resource.end + 1) - video_rom_resource.start), - SNP_PAGE_STATE_PRIVATE); - /* video rom */ upper = adapter_rom_resources[0].start; for (start = video_rom_resource.start; start < upper; start += 2048) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 33b268747bb7b..4989095ab7696 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -138,7 +138,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, log_lvl, d3, d6, d7); } - if (cpu_feature_enabled(X86_FEATURE_OSPKE)) + if (cr4 & X86_CR4_PKE) printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 830425e6d38e2..6bea19d4a0cae 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -487,7 +487,46 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"), }, }, - + { /* Handle problems with rebooting on the Latitude E6520. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6520"), + }, + }, + { /* Handle problems with rebooting on the OptiPlex 790. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 790", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 790"), + }, + }, + { /* Handle problems with rebooting on the OptiPlex 990. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), + }, + }, + { /* Handle problems with rebooting on the Latitude E6220. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6220", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6220"), + }, + }, + { /* Handle problems with rebooting on the OptiPlex 390. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 390", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 390"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 84201071dfacd..3f14bb5704205 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include @@ -21,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -902,7 +903,15 @@ void __init setup_arch(char **cmdline_p) efi_init(); reserve_ibft_region(); - dmi_setup(); + + efi_set_secure_boot(boot_params.secure_boot); + +#ifdef CONFIG_LOCK_DOWN_IN_SECURE_BOOT + if (efi_enabled(EFI_SECURE_BOOT)) + security_lock_kernel_down("EFI Secure Boot mode", LOCKDOWN_INTEGRITY_MAX); +#endif + + x86_init.resources.dmi_setup(); /* * VMware detection requires dmi to be available, so this @@ -994,6 +1003,7 @@ void __init setup_arch(char **cmdline_p) * memory size. */ mem_encrypt_setup_arch(); + cc_random_init(); efi_fake_memmap(); efi_find_mirror(); @@ -1064,19 +1074,7 @@ void __init setup_arch(char **cmdline_p) /* Allocate bigger log buffer */ setup_log_buf(1); - if (efi_enabled(EFI_BOOT)) { - switch (boot_params.secure_boot) { - case efi_secureboot_mode_disabled: - pr_info("Secure boot disabled\n"); - break; - case efi_secureboot_mode_enabled: - pr_info("Secure boot enabled\n"); - break; - default: - pr_info("Secure boot could not be determined\n"); - break; - } - } + efi_set_secure_boot(boot_params.secure_boot); reserve_initrd(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 1d24ec6799157..223971c09f19f 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -10,11 +10,15 @@ */ #ifndef __BOOT_COMPRESSED -#define error(v) pr_err(v) -#define has_cpuflag(f) boot_cpu_has(f) +#define error(v) pr_err(v) +#define has_cpuflag(f) boot_cpu_has(f) +#define sev_printk(fmt, ...) printk(fmt, ##__VA_ARGS__) +#define sev_printk_rtl(fmt, ...) printk_ratelimited(fmt, ##__VA_ARGS__) #else #undef WARN #define WARN(condition, format...) (!!(condition)) +#define sev_printk(fmt, ...) +#define sev_printk_rtl(fmt, ...) #endif /* I/O parameters for CPUID-related helpers */ @@ -89,7 +93,8 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) +static void __head __noreturn +sev_es_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; @@ -326,13 +331,7 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid */ static const struct snp_cpuid_table *snp_cpuid_get_table(void) { - void *ptr; - - asm ("lea cpuid_table_copy(%%rip), %0" - : "=r" (ptr) - : "p" (&cpuid_table_copy)); - - return ptr; + return &RIP_REL_REF(cpuid_table_copy); } /* @@ -391,7 +390,7 @@ static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) return xsave_size; } -static bool +static bool __head snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -528,7 +527,8 @@ static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value * should be treated as fatal by caller. */ -static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +static int __head +snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -556,9 +556,9 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; /* Skip post-processing for out-of-range zero leafs. */ - if (!(leaf->fn <= cpuid_std_range_max || - (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || - (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) || + (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) || + (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max)))) return 0; } @@ -570,10 +570,11 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le * page yet, so it only supports the MSR based communication with the * hypervisor and only the CPUID exit-code. */ -void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) +void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); + u16 opcode = *(unsigned short *)regs->ip; struct cpuid_leaf leaf; int ret; @@ -581,6 +582,10 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) if (exit_code != SVM_EXIT_CPUID) goto fail; + /* Is it really a CPUID insn? */ + if (opcode != 0xa20f) + goto fail; + leaf.fn = fn; leaf.subfn = subfn; @@ -1016,7 +1021,8 @@ struct cc_setup_data { * Search for a Confidential Computing blob passed in as a setup_data entry * via the Linux Boot Protocol. */ -static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) +static __head +struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) { struct cc_setup_data *sd = NULL; struct setup_data *hdr; @@ -1043,7 +1049,7 @@ static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) * mapping needs to be updated in sync with all the changes to virtual memory * layout and related mapping facilities throughout the boot process. */ -static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) +static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info) { const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table; int i; @@ -1063,11 +1069,11 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; if (fn->eax_in == 0x0) - cpuid_std_range_max = fn->eax; + RIP_REL_REF(cpuid_std_range_max) = fn->eax; else if (fn->eax_in == 0x40000000) - cpuid_hyp_range_max = fn->eax; + RIP_REL_REF(cpuid_hyp_range_max) = fn->eax; else if (fn->eax_in == 0x80000000) - cpuid_ext_range_max = fn->eax; + RIP_REL_REF(cpuid_ext_range_max) = fn->eax; } } @@ -1170,3 +1176,94 @@ static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) out: return ret; } + +static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt, + unsigned long exit_code) +{ + unsigned int opcode = (unsigned int)ctxt->insn.opcode.value; + u8 modrm = ctxt->insn.modrm.value; + + switch (exit_code) { + + case SVM_EXIT_IOIO: + case SVM_EXIT_NPF: + /* handled separately */ + return ES_OK; + + case SVM_EXIT_CPUID: + if (opcode == 0xa20f) + return ES_OK; + break; + + case SVM_EXIT_INVD: + if (opcode == 0x080f) + return ES_OK; + break; + + case SVM_EXIT_MONITOR: + /* MONITOR and MONITORX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa)) + return ES_OK; + break; + + case SVM_EXIT_MWAIT: + /* MWAIT and MWAITX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb)) + return ES_OK; + break; + + case SVM_EXIT_MSR: + /* RDMSR */ + if (opcode == 0x320f || + /* WRMSR */ + opcode == 0x300f) + return ES_OK; + break; + + case SVM_EXIT_RDPMC: + if (opcode == 0x330f) + return ES_OK; + break; + + case SVM_EXIT_RDTSC: + if (opcode == 0x310f) + return ES_OK; + break; + + case SVM_EXIT_RDTSCP: + if (opcode == 0x010f && modrm == 0xf9) + return ES_OK; + break; + + case SVM_EXIT_READ_DR7: + if (opcode == 0x210f && + X86_MODRM_REG(ctxt->insn.modrm.value) == 7) + return ES_OK; + break; + + case SVM_EXIT_VMMCALL: + if (opcode == 0x010f && modrm == 0xd9) + return ES_OK; + + break; + + case SVM_EXIT_WRITE_DR7: + if (opcode == 0x230f && + X86_MODRM_REG(ctxt->insn.modrm.value) == 7) + return ES_OK; + break; + + case SVM_EXIT_WBINVD: + if (opcode == 0x90f) + return ES_OK; + break; + + default: + break; + } + + sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n", + opcode, exit_code, ctxt->regs->ip); + + return ES_UNSUPPORTED; +} diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index c67285824e826..e77dbd58ac7b0 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -23,8 +23,10 @@ #include #include #include +#include #include +#include #include #include #include @@ -682,8 +684,9 @@ static u64 __init get_jump_table_addr(void) return ret; } -static void early_set_pages_state(unsigned long vaddr, unsigned long paddr, - unsigned long npages, enum psc_op op) +static void __head +early_set_pages_state(unsigned long vaddr, unsigned long paddr, + unsigned long npages, enum psc_op op) { unsigned long paddr_end; u64 val; @@ -739,7 +742,7 @@ static void early_set_pages_state(unsigned long vaddr, unsigned long paddr, sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); } -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, +void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { /* @@ -748,7 +751,7 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* @@ -767,28 +770,13 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* Ask hypervisor to mark the memory pages shared in the RMP table. */ early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED); } -void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) -{ - unsigned long vaddr, npages; - - vaddr = (unsigned long)__va(paddr); - npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - - if (op == SNP_PAGE_STATE_PRIVATE) - early_snp_set_memory_private(vaddr, paddr, npages); - else if (op == SNP_PAGE_STATE_SHARED) - early_snp_set_memory_shared(vaddr, paddr, npages); - else - WARN(1, "invalid memory op %d\n", op); -} - static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr, unsigned long vaddr_end, int op) { @@ -1752,7 +1740,10 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) { - enum es_result result; + enum es_result result = vc_check_opcode_bytes(ctxt, exit_code); + + if (result != ES_OK) + return result; switch (exit_code) { case SVM_EXIT_READ_DR7: @@ -2059,7 +2050,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) * * Scan for the blob in that order. */ -static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2085,7 +2076,7 @@ static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) return cc_info; } -bool __init snp_init(struct boot_params *bp) +bool __head snp_init(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2107,11 +2098,22 @@ bool __init snp_init(struct boot_params *bp) return true; } -void __init __noreturn snp_abort(void) +void __head __noreturn snp_abort(void) { sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } +/* + * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are + * enabled, as the alternative (fallback) logic for DMI probing in the legacy + * ROM region can cause a crash since this region is not pre-validated. + */ +void __init snp_dmi_setup(void) +{ + if (efi_enabled(EFI_CONFIG_TABLES)) + dmi_setup(); +} + static void dump_cpuid_table(void) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 1123ef3ccf901..4334033658edf 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -193,11 +193,9 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) cur->warned = false; /* - * If a non-zero TSC value for socket 0 may be valid then the default - * adjusted value cannot assumed to be zero either. + * The default adjust value cannot be assumed to be zero on any socket. */ - if (tsc_async_resets) - cur->adjusted = bootval; + cur->adjusted = bootval; /* * Check whether this CPU is the first in a package to come up. In diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a37ebd3b47736..3f0718b4a7d28 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -3,6 +3,7 @@ * * For licencing details see kernel-base/COPYING */ +#include #include #include #include @@ -66,6 +67,7 @@ struct x86_init_ops x86_init __initdata = { .probe_roms = probe_roms, .reserve_resources = reserve_standard_io_resources, .memory_setup = e820__memory_setup_default, + .dmi_setup = dmi_setup, }, .mpparse = { diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index adba49afb5fe6..ce1499732cb86 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -366,6 +366,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_update_pv_runtime(vcpu); + vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); @@ -1221,9 +1222,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; + unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned int phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as @@ -1231,16 +1231,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * - * If TDP is enabled but an explicit guest MAXPHYADDR is not - * provided, use the raw bare metal MAXPHYADDR as reductions to - * the HPAs do not affect GPAs. + * If TDP is enabled, use the raw bare metal MAXPHYADDR as + * reductions to the HPAs do not affect GPAs. */ - if (!tdp_enabled) - g_phys_as = boot_cpu_data.x86_phys_bits; - else if (!g_phys_as) - g_phys_as = phys_as; + if (!tdp_enabled) { + phys_as = boot_cpu_data.x86_phys_bits; + } else { + phys_as = entry->eax & 0xff; + } - entry->eax = g_phys_as | (virt_as << 8); + entry->eax = phys_as | (virt_as << 8); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 856e3037e74f3..23dbb9eb277c7 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -120,6 +120,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu) return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx); } +static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.is_amd_compatible; +} + +static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu) +{ + return !guest_cpuid_is_amd_compatible(vcpu); +} + static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3242f3da24576..76fcee92b0706 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -41,6 +41,7 @@ #include "ioapic.h" #include "trace.h" #include "x86.h" +#include "xen.h" #include "cpuid.h" #include "hyperv.h" #include "smm.h" @@ -499,8 +500,10 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) } /* Check if there are APF page ready requests pending */ - if (enabled) + if (enabled) { kvm_make_request(KVM_REQ_APF_READY, apic->vcpu); + kvm_xen_sw_enable_lapic(apic->vcpu); + } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) @@ -2768,7 +2771,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); - if (r && lvt_type == APIC_LVTPC) + if (r && lvt_type == APIC_LVTPC && + guest_cpuid_is_intel_compatible(apic->vcpu)) kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); return r; } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 0544700ca50b8..982cf41e14924 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3126,7 +3126,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, if (pud_none(pud) || !pud_present(pud)) goto out; - if (pud_large(pud)) { + if (pud_leaf(pud)) { level = PG_LEVEL_1G; goto out; } @@ -4922,7 +4922,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, context->cpu_role.base.level, is_efer_nx(context), guest_can_use(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), - guest_cpuid_is_amd_or_hygon(vcpu)); + guest_cpuid_is_amd_compatible(vcpu)); } static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, @@ -7388,7 +7388,8 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, * by the memslot, KVM can't use a hugepage due to the * misaligned address regardless of memory attributes. */ - if (gfn >= slot->base_gfn) { + if (gfn >= slot->base_gfn && + gfn + nr_pages <= slot->base_gfn + slot->npages) { if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) hugepage_clear_mixed(slot, gfn, level); else diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 6ae19b4ee5b1c..953082bf96e27 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1498,6 +1498,16 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, } } +static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp) +{ + /* + * All TDP MMU shadow pages share the same role as their root, aside + * from level, so it is valid to key off any shadow page to determine if + * write protection is needed for an entire tree. + */ + return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled(); +} + /* * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. @@ -1508,7 +1518,8 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { - u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK; + const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; bool spte_set = false; @@ -1523,7 +1534,7 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (!(iter.old_spte & dbit)) @@ -1570,8 +1581,8 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { - u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK : - shadow_dirty_mask; + const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; lockdep_assert_held_write(&kvm->mmu_lock); @@ -1583,7 +1594,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (iter.level > PG_LEVEL_4K || diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 87cc6c8809ad8..2ab2d5213f52f 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -741,6 +741,8 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu) */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm)) return; @@ -750,8 +752,34 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) */ kvm_pmu_reset(vcpu); - bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX); + pmu->version = 0; + pmu->nr_arch_gp_counters = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->counter_bitmask[KVM_PMC_GP] = 0; + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->reserved_bits = 0xffffffff00200000ull; + pmu->raw_event_mask = X86_RAW_EVENT_MASK; + pmu->global_ctrl_mask = ~0ull; + pmu->global_status_mask = ~0ull; + pmu->fixed_ctr_ctrl_mask = ~0ull; + pmu->pebs_enable_mask = ~0ull; + pmu->pebs_data_cfg_mask = ~0ull; + bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX); + + if (!vcpu->kvm->arch.enable_pmu) + return; + static_call(kvm_x86_pmu_refresh)(vcpu); + + /* + * At RESET, both Intel and AMD CPUs set all enable bits for general + * purpose counters in IA32_PERF_GLOBAL_CTRL (so that software that + * was written for v1 PMUs don't unknowingly leave GP counters disabled + * in the global controls). Emulate that behavior when refreshing the + * PMU so that userspace doesn't need to manually set PERF_GLOBAL_CTRL. + */ + if (kvm_pmu_has_perf_global_ctrl(pmu) && pmu->nr_arch_gp_counters) + pmu->global_ctrl = GENMASK_ULL(pmu->nr_arch_gp_counters - 1, 0); } void kvm_pmu_init(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index aadefcaa9561d..2f4e155080bad 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -52,7 +52,7 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) #define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) #define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) -#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) #define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) /* CPUID level 0x80000007 (EDX). */ @@ -102,10 +102,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } @@ -126,6 +128,7 @@ static __always_inline u32 __feature_translate(int x86_feature) KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC); KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); default: return x86_feature; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index a8ce5226b3b57..c87721da5887d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -84,9 +84,10 @@ struct enc_region { }; /* Called with the sev_bitmap_lock held, or on shutdown */ -static int sev_flush_asids(int min_asid, int max_asid) +static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid) { - int ret, asid, error = 0; + int ret, error = 0; + unsigned int asid; /* Check if there are any ASIDs to reclaim before performing a flush */ asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); @@ -116,7 +117,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm) } /* Must be called with the sev_bitmap_lock held */ -static bool __sev_recycle_asids(int min_asid, int max_asid) +static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid) { if (sev_flush_asids(min_asid, max_asid)) return false; @@ -143,8 +144,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) static int sev_asid_new(struct kvm_sev_info *sev) { - int asid, min_asid, max_asid, ret; + /* + * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. + * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. + * Note: min ASID can end up larger than the max if basic SEV support is + * effectively disabled by disallowing use of ASIDs for SEV guests. + */ + unsigned int min_asid = sev->es_active ? 1 : min_sev_asid; + unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; + unsigned int asid; bool retry = true; + int ret; + + if (min_asid > max_asid) + return -ENOTTY; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); @@ -157,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev) mutex_lock(&sev_bitmap_lock); - /* - * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. - * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. - */ - min_asid = sev->es_active ? 1 : min_sev_asid; - max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); if (asid > max_asid) { @@ -187,7 +194,7 @@ static int sev_asid_new(struct kvm_sev_info *sev) return ret; } -static int sev_get_asid(struct kvm *kvm) +static unsigned int sev_get_asid(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -284,8 +291,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { + unsigned int asid = sev_get_asid(kvm); struct sev_data_activate activate; - int asid = sev_get_asid(kvm); int ret; /* activate ASID on the given handle */ @@ -657,6 +664,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, return ret; vcpu->arch.guest_state_protected = true; + + /* + * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it + * only after setting guest_state_protected because KVM_SET_MSRS allows + * dynamic toggling of LBRV (for performance reason) on write access to + * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set. + */ + svm_enable_lbrv(vcpu); return 0; } @@ -2237,8 +2252,10 @@ void __init sev_hardware_setup(void) goto out; } - sev_asid_count = max_sev_asid - min_sev_asid + 1; - WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + if (min_sev_asid <= max_sev_asid) { + sev_asid_count = max_sev_asid - min_sev_asid + 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + } sev_supported = true; /* SEV-ES support requested? */ @@ -2258,6 +2275,12 @@ void __init sev_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_SEV_ES)) goto out; + if (!lbrv) { + WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV), + "LBRV must be present for SEV-ES support"); + goto out; + } + /* Has the system been allocated ASIDs for SEV-ES? */ if (min_sev_asid == 1) goto out; @@ -2269,7 +2292,9 @@ void __init sev_hardware_setup(void) out: if (boot_cpu_has(X86_FEATURE_SEV)) pr_info("SEV %s (ASIDs %u - %u)\n", - sev_supported ? "enabled" : "disabled", + sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" : + "unusable" : + "disabled", min_sev_asid, max_sev_asid); if (boot_cpu_has(X86_FEATURE_SEV_ES)) pr_info("SEV-ES %s (ASIDs %u - %u)\n", @@ -2317,7 +2342,7 @@ int sev_cpu_init(struct svm_cpu_data *sd) */ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { - int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + unsigned int asid = sev_get_asid(vcpu->kvm); /* * Note! The address must be a kernel address, as regular page walk @@ -2635,7 +2660,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) void pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - int asid = sev_get_asid(svm->vcpu.kvm); + unsigned int asid = sev_get_asid(svm->vcpu.kvm); /* Assign the asid allocated with this SEV guest */ svm->asid = asid; @@ -3021,7 +3046,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; - svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; /* * An SEV-ES guest requires a VMSA area that is a separate from the @@ -3073,10 +3097,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* Clear intercepts on selected MSRs */ set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); } void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e90b429c84f15..cf86607bc6961 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_SPEC_CTRL, .always = false }, { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_FLUSH_CMD, .always = false }, + { .index = MSR_IA32_DEBUGCTLMSR, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -215,7 +216,7 @@ int vgif = true; module_param(vgif, int, 0444); /* enable/disable LBR virtualization */ -static int lbrv = true; +int lbrv = true; module_param(lbrv, int, 0444); static int tsc_scaling = true; @@ -990,7 +991,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) vmcb_mark_dirty(to_vmcb, VMCB_LBR); } -static void svm_enable_lbrv(struct kvm_vcpu *vcpu) +void svm_enable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1000,6 +1001,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); + if (sev_es_guest(vcpu->kvm)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1); + /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ if (is_guest_mode(vcpu)) svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); @@ -1009,6 +1013,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); @@ -3845,16 +3851,27 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); /* - * KVM should never request an NMI window when vNMI is enabled, as KVM - * allows at most one to-be-injected NMI and one pending NMI, i.e. if - * two NMIs arrive simultaneously, KVM will inject one and set - * V_NMI_PENDING for the other. WARN, but continue with the standard - * single-step approach to try and salvage the pending NMI. + * If NMIs are outright masked, i.e. the vCPU is already handling an + * NMI, and KVM has not yet intercepted an IRET, then there is nothing + * more to do at this time as KVM has already enabled IRET intercepts. + * If KVM has already intercepted IRET, then single-step over the IRET, + * as NMIs aren't architecturally unmasked until the IRET completes. + * + * If vNMI is enabled, KVM should never request an NMI window if NMIs + * are masked, as KVM allows at most one to-be-injected NMI and one + * pending NMI. If two NMIs arrive simultaneously, KVM will inject one + * NMI and set V_NMI_PENDING for the other, but if and only if NMIs are + * unmasked. KVM _will_ request an NMI window in some situations, e.g. + * if the vCPU is in an STI shadow or if GIF=0, KVM can't immediately + * inject the NMI. In those situations, KVM needs to single-step over + * the STI shadow or intercept STGI. */ - WARN_ON_ONCE(is_vnmi_enabled(svm)); + if (svm_get_nmi_mask(vcpu)) { + WARN_ON_ONCE(is_vnmi_enabled(svm)); - if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion) - return; /* IRET will cause a vm exit */ + if (!svm->awaiting_iret_completion) + return; /* IRET will cause a vm exit */ + } /* * SEV-ES guests are responsible for signaling when a vCPU is ready to @@ -5236,6 +5253,12 @@ static __init int svm_hardware_setup(void) nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS); + if (lbrv) { + if (!boot_cpu_has(X86_FEATURE_LBRV)) + lbrv = false; + else + pr_info("LBR virtualization supported\n"); + } /* * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which * may be modified by svm_adjust_mmio_mask()), as well as nrips. @@ -5289,14 +5312,6 @@ static __init int svm_hardware_setup(void) svm_x86_ops.set_vnmi_pending = NULL; } - - if (lbrv) { - if (!boot_cpu_has(X86_FEATURE_LBRV)) - lbrv = false; - else - pr_info("LBR virtualization supported\n"); - } - if (!enable_pmu) pr_info("PMU virtualization is disabled\n"); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 8ef95139cd245..957f219377769 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -30,7 +30,7 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 47 +#define MAX_DIRECT_ACCESS_MSRS 48 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; @@ -39,6 +39,7 @@ extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; extern bool vnmi; +extern int lbrv; /* * Clean bits in VMCB. @@ -543,6 +544,7 @@ u32 *svm_vcpu_alloc_msrpm(void); void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); void svm_vcpu_free_msrpm(u32 *msrpm); void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); +void svm_enable_lbrv(struct kvm_vcpu *vcpu); void svm_update_lbrv(struct kvm_vcpu *vcpu); int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 83843379813ee..b82e6ed4f0241 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -732,13 +732,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit, * Tracepoint for nested #vmexit because of interrupt pending */ TRACE_EVENT(kvm_invlpga, - TP_PROTO(__u64 rip, int asid, u64 address), + TP_PROTO(__u64 rip, unsigned int asid, u64 address), TP_ARGS(rip, asid, address), TP_STRUCT__entry( - __field( __u64, rip ) - __field( int, asid ) - __field( __u64, address ) + __field( __u64, rip ) + __field( unsigned int, asid ) + __field( __u64, address ) ), TP_fast_assign( @@ -747,7 +747,7 @@ TRACE_EVENT(kvm_invlpga, __entry->address = address; ), - TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", + TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx", __entry->rip, __entry->asid, __entry->address) ); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 315c7c2ba89b1..600a021ae958b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -491,19 +491,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) u64 counter_mask; int i; - pmu->nr_arch_gp_counters = 0; - pmu->nr_arch_fixed_counters = 0; - pmu->counter_bitmask[KVM_PMC_GP] = 0; - pmu->counter_bitmask[KVM_PMC_FIXED] = 0; - pmu->version = 0; - pmu->reserved_bits = 0xffffffff00200000ull; - pmu->raw_event_mask = X86_RAW_EVENT_MASK; - pmu->global_ctrl_mask = ~0ull; - pmu->global_status_mask = ~0ull; - pmu->fixed_ctr_ctrl_mask = ~0ull; - pmu->pebs_enable_mask = ~0ull; - pmu->pebs_data_cfg_mask = ~0ull; - memset(&lbr_desc->records, 0, sizeof(lbr_desc->records)); /* @@ -515,8 +502,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) return; entry = kvm_find_cpuid_entry(vcpu, 0xa); - if (!entry || !vcpu->kvm->arch.enable_pmu) + if (!entry) return; + eax.full = entry->eax; edx.full = entry->edx; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 2bfbf758d0611..f6986dee6f8c7 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -275,6 +275,8 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) call vmx_spec_ctrl_restore_host + CLEAR_BRANCH_HISTORY_VMEXIT + /* Put return value in AX */ mov %_ASM_BX, %_ASM_AX diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 88a4ff200d04b..784f2ecca5d2c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7857,8 +7857,28 @@ static u64 vmx_get_perf_capabilities(void) if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; + + /* + * Disallow adaptive PEBS as it is functionally broken, can be + * used by the guest to read *host* LBRs, and can be used to + * bypass userspace event filters. To correctly and safely + * support adaptive PEBS, KVM needs to: + * + * 1. Account for the ADAPTIVE flag when (re)programming fixed + * counters. + * + * 2. Gain support from perf (or take direct control of counter + * programming) to support events without adaptive PEBS + * enabled for the hardware counter. + * + * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with + * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. + * + * 4. Document which PMU events are effectively exposed to the + * guest via adaptive PEBS, and make adaptive PEBS mutually + * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. + */ + perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e02cc710f56de..3750a0c688b7d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1623,7 +1623,8 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1655,6 +1656,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -3419,7 +3422,7 @@ static bool is_mci_status_msr(u32 msr) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd_or_hygon(vcpu)) + if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; @@ -10639,13 +10642,12 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); + if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); - else { - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); - if (ioapic_in_kernel(vcpu->kvm)) - kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); - } + else if (ioapic_in_kernel(vcpu->kvm)) + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 4b4e738c6f1b7..b0212ba2d87a6 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -493,7 +493,7 @@ void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) kvm_xen_update_runstate_guest(v, state == RUNSTATE_runnable); } -static void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) { struct kvm_lapic_irq irq = { }; int r; diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index f8f1fe22d0906..f5841d9000aeb 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -18,6 +18,7 @@ extern struct static_key_false_deferred kvm_xen_enabled; int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu); void kvm_xen_inject_pending_events(struct kvm_vcpu *vcpu); +void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *vcpu); int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data); int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); @@ -36,6 +37,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm, const struct kvm_irq_routing_entry *ue); void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu); +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ + /* + * The local APIC is being enabled. If the per-vCPU upcall vector is + * set and the vCPU's evtchn_upcall_pending flag is set, inject the + * interrupt. + */ + if (static_branch_unlikely(&kvm_xen_enabled.key) && + vcpu->arch.xen.vcpu_info_cache.active && + vcpu->arch.xen.upcall_vector && __kvm_xen_has_interrupt(vcpu)) + kvm_xen_inject_vcpu_vector(vcpu); +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -101,6 +115,10 @@ static inline void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) { } +static inline void kvm_xen_sw_enable_lapic(struct kvm_vcpu *vcpu) +{ +} + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return false; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index ea3a28e7b613c..f0dae4fb6d071 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -14,19 +14,6 @@ ifdef CONFIG_KCSAN CFLAGS_REMOVE_delay.o = $(CC_FLAGS_FTRACE) endif -# Early boot use of cmdline; don't instrument it -ifdef CONFIG_AMD_MEM_ENCRYPT -KCOV_INSTRUMENT_cmdline.o := n -KASAN_SANITIZE_cmdline.o := n -KCSAN_SANITIZE_cmdline.o := n - -ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_cmdline.o = -pg -endif - -CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables -endif - inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt quiet_cmd_inat_tables = GEN $@ diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 10d5ed8b5990f..a1cb3a4e6742d 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,7 +44,11 @@ or %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax +.if \size != 8 jae .Lbad_get_user +.else + jae .Lbad_get_user_8 +.endif sbb %edx, %edx /* array_index_mask_nospec() */ and %edx, %eax .endif @@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception) #ifdef CONFIG_X86_32 SYM_CODE_START_LOCAL(__get_user_8_handle_exception) ASM_CLAC -bad_get_user_8: +.Lbad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 7b2589877d065..5b26a952e2fa6 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -163,6 +163,7 @@ SYM_CODE_START_NOALIGN(srso_alias_untrain_ret) lfence jmp srso_alias_return_thunk SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) .popsection .pushsection .text..__x86.rethunk_safe @@ -224,10 +225,16 @@ SYM_CODE_START(srso_return_thunk) SYM_CODE_END(srso_return_thunk) #define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret" -#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret" #else /* !CONFIG_CPU_SRSO */ #define JMP_SRSO_UNTRAIN_RET "ud2" -#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2" +/* Dummy for the alternative in CALL_UNTRAIN_RET. */ +SYM_CODE_START(srso_alias_untrain_ret) + ANNOTATE_UNRET_SAFE + ANNOTATE_NOENDBR + ret + int3 +SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) #endif /* CONFIG_CPU_SRSO */ #ifdef CONFIG_CPU_UNRET_ENTRY @@ -319,9 +326,7 @@ SYM_FUNC_END(retbleed_untrain_ret) #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \ - JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO, \ - JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS + ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 5168ee0360b24..d1ccd06c53127 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -148,7 +148,7 @@ AVXcode: 65: SEG=GS (Prefix) 66: Operand-Size (Prefix) 67: Address-Size (Prefix) -68: PUSH Iz (d64) +68: PUSH Iz 69: IMUL Gv,Ev,Iz 6a: PUSH Ib (d64) 6b: IMUL Gv,Ev,Ib @@ -698,10 +698,10 @@ AVXcode: 2 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) -50: vpdpbusd Vx,Hx,Wx (66),(ev) -51: vpdpbusds Vx,Hx,Wx (66),(ev) -52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) -53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) +50: vpdpbusd Vx,Hx,Wx (66) +51: vpdpbusds Vx,Hx,Wx (66) +52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) +53: vpdpwssds Vx,Hx,Wx (66) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) 54: vpopcntb/w Vx,Wx (66),(ev) 55: vpopcntd/q Vx,Wx (66),(ev) 58: vpbroadcastd Vx,Wx (66),(v) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d6375b3c633bc..e604d2d6cc8f9 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -376,7 +376,7 @@ static void dump_pagetable(unsigned long address) goto bad; pr_cont("PUD %lx ", pud_val(*pud)); - if (!pud_present(*pud) || pud_large(*pud)) + if (!pud_present(*pud) || pud_leaf(*pud)) goto out; pmd = pmd_offset(pud, address); @@ -717,39 +717,8 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, WARN_ON_ONCE(user_mode(regs)); /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) { - /* - * Any interrupt that takes a fault gets the fixup. This makes - * the below recursive fault logic only apply to a faults from - * task context. - */ - if (in_interrupt()) - return; - - /* - * Per the above we're !in_interrupt(), aka. task context. - * - * In this case we need to make sure we're not recursively - * faulting through the emulate_vsyscall() logic. - */ - if (current->thread.sig_on_uaccess_err && signal) { - sanitize_error_code(address, &error_code); - - set_signal_archinfo(address, error_code); - - if (si_code == SEGV_PKUERR) { - force_sig_pkuerr((void __user *)address, pkey); - } else { - /* XXX: hwpoison faults will set the wrong code. */ - force_sig_fault(signal, si_code, (void __user *)address); - } - } - - /* - * Barring that, we can do the fixup and be happy. - */ + if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) return; - } /* * AMD erratum #91 manifests as a spurious page fault on a PREFETCH @@ -1037,7 +1006,7 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address) if (!pud_present(*pud)) return 0; - if (pud_large(*pud)) + if (pud_leaf(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index f50cc210a9818..968d7005f4a72 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; - bool use_gbpage; next = (addr & PUD_MASK) + PUD_SIZE; if (next > end) next = end; - /* if this is already a gbpage, this portion is already mapped */ - if (pud_large(*pud)) - continue; - - /* Is using a gbpage allowed? */ - use_gbpage = info->direct_gbpages; - - /* Don't use gbpage if it maps more than the requested region. */ - /* at the begining: */ - use_gbpage &= ((addr & ~PUD_MASK) == 0); - /* ... or at the end: */ - use_gbpage &= ((next & ~PUD_MASK) == 0); - - /* Never overwrite existing mappings */ - use_gbpage &= !pud_present(*pud); - - if (use_gbpage) { + if (info->direct_gbpages) { pud_t pudval; + if (pud_present(*pud)) + continue; + + addr &= PUD_MASK; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a0dffaca6d2bf..534436c9d3997 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -617,7 +617,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, } if (!pud_none(*pud)) { - if (!pud_large(*pud)) { + if (!pud_leaf(*pud)) { pmd = pmd_offset(pud, 0); paddr_last = phys_pmd_init(pmd, paddr, paddr_end, @@ -1163,7 +1163,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, if (!pud_present(*pud)) continue; - if (pud_large(*pud) && + if (pud_leaf(*pud) && IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE)) { spin_lock(&init_mm.page_table_lock); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 0302491d799d1..fcf508c52bdc5 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -115,7 +115,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); - if (!pud_large(*pud)) + if (!pud_leaf(*pud)) kasan_populate_pud(pud, addr, next, nid); } while (pud++, addr = next, addr != end); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 70b91de2e053a..94cd06d4b0af5 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -492,6 +492,24 @@ void __init sme_early_init(void) */ if (sev_status & MSR_AMD64_SEV_ENABLED) ia32_disable(); + + /* + * Override init functions that scan the ROM region in SEV-SNP guests, + * as this memory is not pre-validated and would thus cause a crash. + */ + if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.pci.init_irq = x86_init_noop; + x86_init.resources.probe_roms = x86_init_noop; + + /* + * DMI setup behavior for SEV-SNP guests depends on + * efi_enabled(EFI_CONFIG_TABLES), which hasn't been + * parsed yet. snp_dmi_setup() will run after that + * parsing has happened. + */ + x86_init.resources.dmi_setup = snp_dmi_setup; + } } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index d73aeb16417fc..cc47a818a640a 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -41,9 +41,9 @@ #include #include +#include #include #include -#include #include #include @@ -95,11 +95,7 @@ struct sme_populate_pgd_data { */ static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch"); -static char sme_cmdline_arg[] __initdata = "mem_encrypt"; -static char sme_cmdline_on[] __initdata = "on"; -static char sme_cmdline_off[] __initdata = "off"; - -static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; @@ -114,7 +110,7 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) memset(pgd_p, 0, pgd_size); } -static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) +static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd; p4d_t *p4d; @@ -145,13 +141,13 @@ static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) set_pud(pud, __pud(PUD_FLAGS | __pa(pmd))); } - if (pud_large(*pud)) + if (pud_leaf(*pud)) return NULL; return pud; } -static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -167,7 +163,7 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags)); } -static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -193,7 +189,7 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) set_pte(pte, __pte(ppd->paddr | ppd->pte_flags)); } -static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd_large(ppd); @@ -203,7 +199,7 @@ static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pte(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd(ppd); @@ -213,7 +209,7 @@ static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, +static void __head __sme_map_range(struct sme_populate_pgd_data *ppd, pmdval_t pmd_flags, pteval_t pte_flags) { unsigned long vaddr_end; @@ -237,22 +233,22 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, __sme_map_range_pte(ppd); } -static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); } -static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); } -static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } -static unsigned long __init sme_pgtable_calc(unsigned long len) +static unsigned long __head sme_pgtable_calc(unsigned long len) { unsigned long entries = 0, tables = 0; @@ -289,7 +285,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return entries + tables; } -void __init sme_encrypt_kernel(struct boot_params *bp) +void __head sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; @@ -305,7 +301,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * instrumentation or checking boot_cpu_data in the cc_platform_has() * function. */ - if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED) + if (!sme_get_me_mask() || + RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED) return; /* @@ -323,9 +320,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * memory from being cached. */ - /* Physical addresses gives us the identity mapped virtual addresses */ - kernel_start = __pa_symbol(_text); - kernel_end = ALIGN(__pa_symbol(_end), PMD_SIZE); + kernel_start = (unsigned long)RIP_REL_REF(_text); + kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE); kernel_len = kernel_end - kernel_start; initrd_start = 0; @@ -342,14 +338,6 @@ void __init sme_encrypt_kernel(struct boot_params *bp) } #endif - /* - * We're running identity mapped, so we must obtain the address to the - * SME encryption workarea using rip-relative addressing. - */ - asm ("lea sme_workarea(%%rip), %0" - : "=r" (workarea_start) - : "p" (sme_workarea)); - /* * Calculate required number of workarea bytes needed: * executable encryption area size: @@ -359,7 +347,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * pagetable structures for the encryption of the kernel * pagetable structures for workarea (in case not currently mapped) */ - execute_start = workarea_start; + execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea); execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE; execute_len = execute_end - execute_start; @@ -502,14 +490,11 @@ void __init sme_encrypt_kernel(struct boot_params *bp) native_write_cr3(__native_read_cr3()); } -void __init sme_enable(struct boot_params *bp) +void __head sme_enable(struct boot_params *bp) { - const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; unsigned int eax, ebx, ecx, edx; unsigned long feature_mask; - bool active_by_default; unsigned long me_mask; - char buffer[16]; bool snp; u64 msr; @@ -543,15 +528,18 @@ void __init sme_enable(struct boot_params *bp) me_mask = 1UL << (ebx & 0x3f); /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV); + feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ - if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED)) snp_abort(); /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { + if (!(bp->hdr.xloadflags & XLF_MEM_ENCRYPTION)) + return; + /* * No SME if Hypervisor bit is set. This check is here to * prevent a guest from trying to enable SME. For running as a @@ -571,48 +559,10 @@ void __init sme_enable(struct boot_params *bp) msr = __rdmsr(MSR_AMD64_SYSCFG); if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) return; - } else { - /* SEV state cannot be controlled by a command line option */ - sme_me_mask = me_mask; - goto out; } - /* - * Fixups have not been applied to phys_base yet and we're running - * identity mapped, so we must obtain the address to the SME command - * line argument data using rip-relative addressing. - */ - asm ("lea sme_cmdline_arg(%%rip), %0" - : "=r" (cmdline_arg) - : "p" (sme_cmdline_arg)); - asm ("lea sme_cmdline_on(%%rip), %0" - : "=r" (cmdline_on) - : "p" (sme_cmdline_on)); - asm ("lea sme_cmdline_off(%%rip), %0" - : "=r" (cmdline_off) - : "p" (sme_cmdline_off)); - - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) - active_by_default = true; - else - active_by_default = false; - - cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | - ((u64)bp->ext_cmd_line_ptr << 32)); - - if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0) - return; - - if (!strncmp(buffer, cmdline_on, sizeof(buffer))) - sme_me_mask = me_mask; - else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) - sme_me_mask = 0; - else - sme_me_mask = active_by_default ? me_mask : 0; -out: - if (sme_me_mask) { - physical_mask &= ~sme_me_mask; - cc_vendor = CC_VENDOR_AMD; - cc_set_mask(sme_me_mask); - } + RIP_REL_REF(sme_me_mask) = me_mask; + physical_mask &= ~me_mask; + cc_vendor = CC_VENDOR_AMD; + cc_set_mask(me_mask); } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 65e9a6e391c04..6ce10e3c62285 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -493,7 +493,7 @@ static void __init numa_clear_kernel_node_hotplug(void) for_each_reserved_mem_region(mb_region) { int nid = memblock_get_region_node(mb_region); - if (nid != MAX_NUMNODES) + if (nid != NUMA_NO_NODE) node_set(nid, reserved_nodemask); } @@ -614,9 +614,9 @@ static int __init numa_init(int (*init_func)(void)) nodes_clear(node_online_map); memset(&numa_meminfo, 0, sizeof(numa_meminfo)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, - MAX_NUMNODES)); + NUMA_NO_NODE)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, - MAX_NUMNODES)); + NUMA_NO_NODE)); /* In case that parsing SRAT failed. */ WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); numa_reset_distance(); @@ -929,6 +929,8 @@ int memory_add_physaddr_to_nid(u64 start) } EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); +#endif + static int __init cmp_memblk(const void *a, const void *b) { const struct numa_memblk *ma = *(const struct numa_memblk **)a; @@ -1001,5 +1003,3 @@ int __init numa_fill_memblks(u64 start, u64 end) } return 0; } - -#endif diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 0904d7e8e1260..37d51cfd77cb5 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -950,6 +950,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -960,20 +992,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1048,7 +1073,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1056,11 +1080,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 1028804040463..b4073fb452b6a 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -619,7 +619,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, * Validate strict W^X semantics. */ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start, - unsigned long pfn, unsigned long npg) + unsigned long pfn, unsigned long npg, + bool nx, bool rw) { unsigned long end; @@ -641,6 +642,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW) return new; + /* Non-leaf translation entries can disable writing or execution. */ + if (!rw || nx) + return new; + end = start + npg * PAGE_SIZE - 1; WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n", (unsigned long long)pgprot_val(old), @@ -657,20 +662,26 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star /* * Lookup the page table entry for a virtual address in a specific pgd. - * Return a pointer to the entry and the level of the mapping. + * Return a pointer to the entry, the level of the mapping, and the effective + * NX and RW bits of all page table levels. */ -pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, - unsigned int *level) +pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, + unsigned int *level, bool *nx, bool *rw) { p4d_t *p4d; pud_t *pud; pmd_t *pmd; *level = PG_LEVEL_NONE; + *nx = false; + *rw = true; if (pgd_none(*pgd)) return NULL; + *nx |= pgd_flags(*pgd) & _PAGE_NX; + *rw &= pgd_flags(*pgd) & _PAGE_RW; + p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return NULL; @@ -679,14 +690,20 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, if (p4d_large(*p4d) || !p4d_present(*p4d)) return (pte_t *)p4d; + *nx |= p4d_flags(*p4d) & _PAGE_NX; + *rw &= p4d_flags(*p4d) & _PAGE_RW; + pud = pud_offset(p4d, address); if (pud_none(*pud)) return NULL; *level = PG_LEVEL_1G; - if (pud_large(*pud) || !pud_present(*pud)) + if (pud_leaf(*pud) || !pud_present(*pud)) return (pte_t *)pud; + *nx |= pud_flags(*pud) & _PAGE_NX; + *rw &= pud_flags(*pud) & _PAGE_RW; + pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) return NULL; @@ -695,11 +712,26 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, if (pmd_large(*pmd) || !pmd_present(*pmd)) return (pte_t *)pmd; + *nx |= pmd_flags(*pmd) & _PAGE_NX; + *rw &= pmd_flags(*pmd) & _PAGE_RW; + *level = PG_LEVEL_4K; return pte_offset_kernel(pmd, address); } +/* + * Lookup the page table entry for a virtual address in a specific pgd. + * Return a pointer to the entry and the level of the mapping. + */ +pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, + unsigned int *level) +{ + bool nx, rw; + + return lookup_address_in_pgd_attr(pgd, address, level, &nx, &rw); +} + /* * Lookup the page table entry for a virtual address. Return a pointer * to the entry and the level of the mapping. @@ -715,13 +747,16 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) EXPORT_SYMBOL_GPL(lookup_address); static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, - unsigned int *level) + unsigned int *level, bool *nx, bool *rw) { - if (cpa->pgd) - return lookup_address_in_pgd(cpa->pgd + pgd_index(address), - address, level); + pgd_t *pgd; + + if (!cpa->pgd) + pgd = pgd_offset_k(address); + else + pgd = cpa->pgd + pgd_index(address); - return lookup_address(address, level); + return lookup_address_in_pgd_attr(pgd, address, level, nx, rw); } /* @@ -743,7 +778,7 @@ pmd_t *lookup_pmd_address(unsigned long address) return NULL; pud = pud_offset(p4d, address); - if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud)) + if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud)) return NULL; return pmd_offset(pud, address); @@ -849,12 +884,13 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, pgprot_t old_prot, new_prot, req_prot, chk_prot; pte_t new_pte, *tmp; enum pg_level level; + bool nx, rw; /* * Check for races, another CPU might have split this page * up already: */ - tmp = _lookup_address_cpa(cpa, address, &level); + tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (tmp != kpte) return 1; @@ -965,7 +1001,8 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages, psize, CPA_DETECT); - new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages); + new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages, + nx, rw); /* * If there is a conflict, split the large page. @@ -1046,6 +1083,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, pte_t *pbase = (pte_t *)page_address(base); unsigned int i, level; pgprot_t ref_prot; + bool nx, rw; pte_t *tmp; spin_lock(&pgd_lock); @@ -1053,7 +1091,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, * Check for races, another CPU might have split this page * up for us already: */ - tmp = _lookup_address_cpa(cpa, address, &level); + tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (tmp != kpte) { spin_unlock(&pgd_lock); return 1; @@ -1278,7 +1316,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) */ while (end - start >= PUD_SIZE) { - if (pud_large(*pud)) + if (pud_leaf(*pud)) pud_clear(pud); else unmap_pmd_range(pud, start, start + PUD_SIZE); @@ -1594,10 +1632,11 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) int do_split, err; unsigned int level; pte_t *kpte, old_pte; + bool nx, rw; address = __cpa_addr(cpa, cpa->curpage); repeat: - kpte = _lookup_address_cpa(cpa, address, &level); + kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (!kpte) return __cpa_process_fault(cpa, address, primary); @@ -1619,7 +1658,8 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) new_prot = static_protections(new_prot, address, pfn, 1, 0, CPA_PROTECT); - new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1); + new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1, + nx, rw); new_prot = pgprot_clear_protnone_bits(new_prot); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 0cbc1b8e8e3d1..5f89d1fefa6c7 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -631,6 +631,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. @@ -777,7 +779,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) */ int pud_clear_huge(pud_t *pud) { - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { pud_clear(pud); return 1; } diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 669ba1c345b38..912b1da7ed80c 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -217,7 +217,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) pud = pud_offset(p4d, address); /* The user page tables do not use large mappings: */ - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { WARN_ON(1); return NULL; } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 919f647c740fb..f415c2cf53582 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -466,7 +466,7 @@ static int emit_call(u8 **pprog, void *func, void *ip) static int emit_rsb_call(u8 **pprog, void *func, void *ip) { OPTIMIZER_HIDE_VAR(func); - x86_call_depth_emit_accounting(pprog, func); + ip += x86_call_depth_emit_accounting(pprog, func); return emit_patch(pprog, func, ip, 0xE8); } @@ -1585,36 +1585,41 @@ st: if (is_imm8(insn->off)) if (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { /* Conservatively check that src_reg + insn->off is a kernel address: - * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE - * src_reg is used as scratch for src_reg += insn->off and restored - * after emit_ldx if necessary + * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE + * and + * src_reg + insn->off < VSYSCALL_ADDR */ - u64 limit = TASK_SIZE_MAX + PAGE_SIZE; + u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR; u8 *end_of_jmp; - /* At end of these emitted checks, insn->off will have been added - * to src_reg, so no need to do relative load with insn->off offset - */ - insn_off = 0; + /* movabsq r10, VSYSCALL_ADDR */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32, + (u32)(long)VSYSCALL_ADDR); - /* movabsq r11, limit */ - EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); - EMIT((u32)limit, 4); - EMIT(limit >> 32, 4); + /* mov src_reg, r11 */ + EMIT_mov(AUX_REG, src_reg); if (insn->off) { - /* add src_reg, insn->off */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); } - /* cmp src_reg, r11 */ - maybe_emit_mod(&prog, src_reg, AUX_REG, true); - EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* sub r11, r10 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); + + /* movabsq r10, limit */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32, + (u32)(long)limit); + + /* cmp r10, r11 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); - /* if unsigned '>=', goto load */ - EMIT2(X86_JAE, 0); + /* if unsigned '>', goto load */ + EMIT2(X86_JA, 0); end_of_jmp = prog; /* xor dst_reg, dst_reg */ @@ -1640,18 +1645,6 @@ st: if (is_imm8(insn->off)) /* populate jmp_offset for JMP above */ start_of_ldx[-1] = prog - start_of_ldx; - if (insn->off && src_reg != dst_reg) { - /* sub src_reg, insn->off - * Restore src_reg after "add src_reg, insn->off" in prev - * if statement. But if src_reg == dst_reg, emit_ldx - * above already clobbered src_reg, so no need to restore. - * If add src_reg, insn->off was unnecessary, no need to - * restore either. - */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off); - } - if (!bpf_prog->aux->extable) break; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index ddb798603201e..618b01d60af2c 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -34,6 +34,7 @@ int noioapicreroute = 1; #endif int pcibios_last_bus = -1; unsigned long pirq_table_addr; +unsigned int pci_early_clear_msi; const struct pci_raw_ops *__read_mostly raw_pci_ops; const struct pci_raw_ops *__read_mostly raw_pci_ext_ops; @@ -614,6 +615,9 @@ char *__init pcibios_setup(char *str) } else if (!strcmp(str, "skip_isa_align")) { pci_probe |= PCI_CAN_SKIP_ISA_ALIGN; return NULL; + } else if (!strcmp(str, "clearmsi")) { + pci_early_clear_msi = 1; + return NULL; } else if (!strcmp(str, "noioapicquirk")) { noioapicquirk = 1; return NULL; diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index f5fc953e58483..f1ba9d781b524 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -51,6 +51,31 @@ void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val) outw(val, 0xcfc + (offset&2)); } +u32 pci_early_find_cap(int bus, int slot, int func, int cap) +{ + int bytes; + u8 pos; + + if (!(read_pci_config_16(bus, slot, func, PCI_STATUS) & + PCI_STATUS_CAP_LIST)) + return 0; + + pos = read_pci_config_byte(bus, slot, func, PCI_CAPABILITY_LIST); + for (bytes = 0; bytes < 48 && pos >= 0x40; bytes++) { + u8 id; + + pos &= ~3; + id = read_pci_config_byte(bus, slot, func, pos+PCI_CAP_LIST_ID); + if (id == 0xff) + break; + if (id == cap) + return pos; + pos = read_pci_config_byte(bus, slot, func, + pos+PCI_CAP_LIST_NEXT); + } + return 0; +} + int early_pci_allowed(void) { return (pci_probe & (PCI_PROBE_CONF1|PCI_PROBE_NOEARLY)) == diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f347c20247d30..b33afb240601b 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -907,6 +907,54 @@ static void chromeos_fixup_apl_pci_l1ss_capability(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_save_apl_pci_l1ss_capability); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_fixup_apl_pci_l1ss_capability); +/* + * Disable D3cold on Asus B1400 PCI-NVMe bridge + * + * On this platform with VMD off, the NVMe device cannot successfully power + * back on from D3cold. This appears to be an untested transition by the + * vendor: Windows leaves the NVMe and parent bridge in D0 during suspend. + * + * We disable D3cold on the parent bridge for simplicity, and the fact that + * both parent bridge and NVMe device share the same power resource. + * + * This is only needed on BIOS versions before 308; the newer versions flip + * StorageD3Enable from 1 to 0. + */ +static const struct dmi_system_id asus_nvme_broken_d3cold_table[] = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.304"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.305"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.306"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.307"), + }, + }, + {} +}; + +static void asus_disable_nvme_d3cold(struct pci_dev *pdev) +{ + if (dmi_check_system(asus_nvme_broken_d3cold_table) > 0) + pci_d3cold_disable(pdev); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x9a09, asus_disable_nvme_d3cold); + #ifdef CONFIG_SUSPEND /* * Root Ports on some AMD SoCs advertise PME_Support for D3hot and D3cold, but diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 0cc9520666efb..39255f0eb14df 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -518,7 +518,34 @@ static bool __ref pci_mmcfg_reserved(struct device *dev, { struct resource *conflict; - if (!early && !acpi_disabled) { + if (early) { + + /* + * Don't try to do this check unless configuration type 1 + * is available. How about type 2? + */ + + /* + * 946f2ee5c731 ("Check that MCFG points to an e820 + * reserved area") added this E820 check in 2006 to work + * around BIOS defects. + * + * Per PCI Firmware r3.3, sec 4.1.2, ECAM space must be + * reserved by a PNP0C02 resource, but it need not be + * mentioned in E820. Before the ACPI interpreter is + * available, we can't check for PNP0C02 resources, so + * there's no reliable way to verify the region in this + * early check. Keep it only for the old machines that + * motivated 946f2ee5c731. + */ + if (dmi_get_bios_year() < 2016 && raw_pci_ops) + return is_mmconf_reserved(e820__mapped_all, cfg, dev, + "E820 entry"); + + return true; + } + + if (!acpi_disabled) { if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, "ACPI motherboard resource")) return true; @@ -551,16 +578,7 @@ static bool __ref pci_mmcfg_reserved(struct device *dev, * For MCFG information constructed from hotpluggable host bridge's * _CBA method, just assume it's reserved. */ - if (pci_mmcfg_running_state) - return true; - - /* Don't try to do this check unless configuration - type 1 is available. how about type 2 ?*/ - if (raw_pci_ops) - return is_mmconf_reserved(e820__mapped_all, cfg, dev, - "E820 entry"); - - return false; + return pci_mmcfg_running_state; } static void __init pci_mmcfg_reject_broken(int early) diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c index 4ef20b49eb5e7..6ed1935504b96 100644 --- a/arch/x86/platform/efi/memmap.c +++ b/arch/x86/platform/efi/memmap.c @@ -92,12 +92,22 @@ int __init efi_memmap_alloc(unsigned int num_entries, */ int __init efi_memmap_install(struct efi_memory_map_data *data) { + unsigned long size = efi.memmap.desc_size * efi.memmap.nr_map; + unsigned long flags = efi.memmap.flags; + u64 phys = efi.memmap.phys_map; + int ret; + efi_memmap_unmap(); if (efi_enabled(EFI_PARAVIRT)) return 0; - return __efi_memmap_init(data); + ret = __efi_memmap_init(data); + if (ret) + return ret; + + __efi_memmap_free(phys, size, flags); + return 0; } /** diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 00a92cb2c8147..a12117f3d4de7 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -74,6 +74,9 @@ static void __init init_pvh_bootparams(bool xen_guest) } else xen_raw_printk("Warning: Can fit ISA range into e820\n"); + if (xen_guest) + xen_reserve_extra_memory(&pvh_bootparams); + pvh_bootparams.hdr.cmd_line_ptr = pvh_start_info.cmdline_paddr; diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c index 6f955eb1e1631..d8af46e677503 100644 --- a/arch/x86/power/hibernate.c +++ b/arch/x86/power/hibernate.c @@ -170,7 +170,7 @@ int relocate_restore_code(void) goto out; } pud = pud_offset(p4d, relocated_restore_code); - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); goto out; } diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 08aa0f25f12a0..8d1c82795ea1d 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -42,7 +42,8 @@ KCOV_INSTRUMENT := n # make up the standalone purgatory.ro PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel -PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -g0 +PURGATORY_CFLAGS := -mcmodel=small -ffreestanding -fno-zero-initialized-in-bss -g0 +PURGATORY_CFLAGS += -fpic -fvisibility=hidden PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING PURGATORY_CFLAGS += -fno-stack-protector diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index a3bae2b24626b..e7a44a7f617fb 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -653,6 +653,14 @@ static void print_absolute_relocs(void) if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } + /* + * Do not perform relocations in .notes section; any + * values there are meant for pre-boot consumption (e.g. + * startup_xen). + */ + if (sec_applies->shdr.sh_type == SHT_NOTE) { + continue; + } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { @@ -738,6 +746,15 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel, if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } + + /* + * Do not perform relocations in .notes sections; any + * values there are meant for pre-boot consumption (e.g. + * startup_xen). + */ + if (sec_applies->shdr.sh_type == SHT_NOTE) + continue; + sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h index 166cedbab9266..8c81d1a604a94 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp.h +++ b/arch/x86/um/shared/sysdep/archsetjmp.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_UM_SYSDEP_ARCHSETJMP_H +#define __X86_UM_SYSDEP_ARCHSETJMP_H + #ifdef __i386__ #include "archsetjmp_32.h" #else #include "archsetjmp_64.h" #endif + +unsigned long get_thread_reg(int reg, jmp_buf *buf); + +#endif /* __X86_UM_SYSDEP_ARCHSETJMP_H */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 3c61bb98c10e2..b88722dfc4f86 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -350,3 +351,67 @@ void xen_arch_unregister_cpu(int num) } EXPORT_SYMBOL(xen_arch_unregister_cpu); #endif + +/* Amount of extra memory space we add to the e820 ranges */ +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; + +void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns) +{ + unsigned int i; + + /* + * No need to check for zero size, should happen rarely and will only + * write a new entry regarded to be unused due to zero size. + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + /* Add new region. */ + if (xen_extra_mem[i].n_pfns == 0) { + xen_extra_mem[i].start_pfn = start_pfn; + xen_extra_mem[i].n_pfns = n_pfns; + break; + } + /* Append to existing region. */ + if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == + start_pfn) { + xen_extra_mem[i].n_pfns += n_pfns; + break; + } + } + if (i == XEN_EXTRA_MEM_MAX_REGIONS) + printk(KERN_WARNING "Warning: not enough extra memory regions\n"); + + memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); +} + +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +int __init arch_xen_unpopulated_init(struct resource **res) +{ + unsigned int i; + + if (!xen_domain()) + return -ENODEV; + + /* Must be set strictly before calling xen_free_unpopulated_pages(). */ + *res = &iomem_resource; + + /* + * Initialize with pages from the extra memory regions (see + * arch/x86/xen/setup.c). + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + unsigned int j; + + for (j = 0; j < xen_extra_mem[i].n_pfns; j++) { + struct page *pg = + pfn_to_page(xen_extra_mem[i].start_pfn + j); + + xen_free_unpopulated_pages(1, &pg); + } + + /* Zero so region is not also added to the balloon driver. */ + xen_extra_mem[i].n_pfns = 0; + } + + return 0; +} +#endif diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index ada3868c02c23..c28f073c1df52 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include @@ -72,3 +73,70 @@ void __init mem_map_via_hcall(struct boot_params *boot_params_p) } boot_params_p->e820_entries = memmap.nr_entries; } + +/* + * Reserve e820 UNUSABLE regions to inflate the memory balloon. + * + * On PVH dom0 the host memory map is used, RAM regions available to dom0 are + * located as the same place as in the native memory map, but since dom0 gets + * less memory than the total amount of host RAM the ranges that can't be + * populated are converted from RAM -> UNUSABLE. Use such regions (up to the + * ratio signaled in EXTRA_MEM_RATIO) in order to inflate the balloon driver at + * boot. Doing so prevents the guest (even if just temporary) from using holes + * in the memory map in order to map grants or foreign addresses, and + * hopefully limits the risk of a clash with a device MMIO region. Ideally the + * hypervisor should notify us which memory ranges are suitable for creating + * foreign mappings, but that's not yet implemented. + */ +void __init xen_reserve_extra_memory(struct boot_params *bootp) +{ + unsigned int i, ram_pages = 0, extra_pages; + + for (i = 0; i < bootp->e820_entries; i++) { + struct boot_e820_entry *e = &bootp->e820_table[i]; + + if (e->type != E820_TYPE_RAM) + continue; + ram_pages += PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr); + } + + /* Max amount of extra memory. */ + extra_pages = EXTRA_MEM_RATIO * ram_pages; + + /* + * Convert UNUSABLE ranges to RAM and reserve them for foreign mapping + * purposes. + */ + for (i = 0; i < bootp->e820_entries && extra_pages; i++) { + struct boot_e820_entry *e = &bootp->e820_table[i]; + unsigned long pages; + + if (e->type != E820_TYPE_UNUSABLE) + continue; + + pages = min(extra_pages, + PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr)); + + if (pages != (PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr))) { + struct boot_e820_entry *next; + + if (bootp->e820_entries == + ARRAY_SIZE(bootp->e820_table)) + /* No space left to split - skip region. */ + continue; + + /* Split entry. */ + next = e + 1; + memmove(next, e, + (bootp->e820_entries - i) * sizeof(*e)); + bootp->e820_entries++; + next->addr = PAGE_ALIGN(e->addr) + PFN_PHYS(pages); + e->size = next->addr - e->addr; + next->size -= e->size; + } + e->type = E820_TYPE_RAM; + extra_pages -= pages; + + xen_add_extra_mem(PFN_UP(e->addr), pages); + } +} diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 72af496a160c8..994aef4473a65 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1082,7 +1082,7 @@ static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin) pmd_t *pmd_tbl; int i; - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; xen_free_ro_pages(pa, PUD_SIZE); return; @@ -1863,7 +1863,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) if (!pud_present(pud)) return 0; pa = pud_val(pud) & PTE_PFN_MASK; - if (pud_large(pud)) + if (pud_leaf(pud)) return pa + (vaddr & ~PUD_MASK); pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) * diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index b3e37961065a2..380591028cb8f 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -38,9 +38,6 @@ #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024) -/* Amount of extra memory space we add to the e820 ranges */ -struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; - /* Number of pages released from the initial allocation. */ unsigned long xen_released_pages; @@ -64,18 +61,6 @@ static struct { } xen_remap_buf __initdata __aligned(PAGE_SIZE); static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; -/* - * The maximum amount of extra memory compared to the base size. The - * main scaling factor is the size of struct page. At extreme ratios - * of base:extra, all the base memory can be filled with page - * structures for the extra memory, leaving no space for anything - * else. - * - * 10x seems like a reasonable balance between scaling flexibility and - * leaving a practically usable system. - */ -#define EXTRA_MEM_RATIO (10) - static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); static void __init xen_parse_512gb(void) @@ -96,35 +81,6 @@ static void __init xen_parse_512gb(void) xen_512gb_limit = val; } -static void __init xen_add_extra_mem(unsigned long start_pfn, - unsigned long n_pfns) -{ - int i; - - /* - * No need to check for zero size, should happen rarely and will only - * write a new entry regarded to be unused due to zero size. - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - /* Add new region. */ - if (xen_extra_mem[i].n_pfns == 0) { - xen_extra_mem[i].start_pfn = start_pfn; - xen_extra_mem[i].n_pfns = n_pfns; - break; - } - /* Append to existing region. */ - if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == - start_pfn) { - xen_extra_mem[i].n_pfns += n_pfns; - break; - } - } - if (i == XEN_EXTRA_MEM_MAX_REGIONS) - printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - - memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); -} - static void __init xen_del_extra_mem(unsigned long start_pfn, unsigned long n_pfns) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index a87ab36889e76..79cf93f2c92f1 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -163,4 +163,18 @@ void xen_hvm_post_suspend(int suspend_cancelled); static inline void xen_hvm_post_suspend(int suspend_cancelled) {} #endif +/* + * The maximum amount of extra memory compared to the base size. The + * main scaling factor is the size of struct page. At extreme ratios + * of base:extra, all the base memory can be filled with page + * structures for the extra memory, leaving no space for anything + * else. + * + * 10x seems like a reasonable balance between scaling flexibility and + * leaving a practically usable system. + */ +#define EXTRA_MEM_RATIO (10) + +void xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns); + #endif /* XEN_OPS_H */ diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index d008a153a2b9f..7ed1a2085bd72 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -115,9 +115,9 @@ #define MAKE_RA_FOR_CALL(ra,ws) (((ra) & 0x3fffffff) | (ws) << 30) /* Convert return address to a valid pc - * Note: We assume that the stack pointer is in the same 1GB ranges as the ra + * Note: 'text' is the address within the same 1GB range as the ra */ -#define MAKE_PC_FROM_RA(ra,sp) (((ra) & 0x3fffffff) | ((sp) & 0xc0000000)) +#define MAKE_PC_FROM_RA(ra, text) (((ra) & 0x3fffffff) | ((unsigned long)(text) & 0xc0000000)) #elif defined(__XTENSA_CALL0_ABI__) @@ -127,9 +127,9 @@ #define MAKE_RA_FOR_CALL(ra, ws) (ra) /* Convert return address to a valid pc - * Note: We assume that the stack pointer is in the same 1GB ranges as the ra + * Note: 'text' is not used as 'ra' is always the full address */ -#define MAKE_PC_FROM_RA(ra, sp) (ra) +#define MAKE_PC_FROM_RA(ra, text) (ra) #else #error Unsupported Xtensa ABI diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h index a270467556dc8..86c70117371bb 100644 --- a/arch/xtensa/include/asm/ptrace.h +++ b/arch/xtensa/include/asm/ptrace.h @@ -87,7 +87,7 @@ struct pt_regs { # define user_mode(regs) (((regs)->ps & 0x00000020)!=0) # define instruction_pointer(regs) ((regs)->pc) # define return_pointer(regs) (MAKE_PC_FROM_RA((regs)->areg[0], \ - (regs)->areg[1])) + (regs)->pc)) # ifndef CONFIG_SMP # define profile_pc(regs) instruction_pointer(regs) diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index a815577d25fd0..7bd66677f7b6d 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -47,6 +47,7 @@ #include #include #include +#include #include extern void ret_from_fork(void); @@ -380,7 +381,7 @@ unsigned long __get_wchan(struct task_struct *p) int count = 0; sp = p->thread.sp; - pc = MAKE_PC_FROM_RA(p->thread.ra, p->thread.sp); + pc = MAKE_PC_FROM_RA(p->thread.ra, _text); do { if (sp < stack_page + sizeof(struct task_struct) || @@ -392,7 +393,7 @@ unsigned long __get_wchan(struct task_struct *p) /* Stack layout: sp-4: ra, sp-3: sp' */ - pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), sp); + pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), _text); sp = SPILL_SLOT(sp, 1); } while (count++ < 16); return 0; diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c index 831ffb648bda7..ed324fdf2a2f9 100644 --- a/arch/xtensa/kernel/stacktrace.c +++ b/arch/xtensa/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include #include +#include #include #include #include @@ -189,7 +190,7 @@ void walk_stackframe(unsigned long *sp, if (a1 <= (unsigned long)sp) break; - frame.pc = MAKE_PC_FROM_RA(a0, a1); + frame.pc = MAKE_PC_FROM_RA(a0, _text); frame.sp = a1; if (fn(&frame, data)) diff --git a/block/bdev.c b/block/bdev.c index e9f1b12bd75c7..812872cdc0bef 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -639,6 +639,14 @@ static void blkdev_flush_mapping(struct block_device *bdev) bdev_write_inode(bdev); } +static void blkdev_put_whole(struct block_device *bdev) +{ + if (atomic_dec_and_test(&bdev->bd_openers)) + blkdev_flush_mapping(bdev); + if (bdev->bd_disk->fops->release) + bdev->bd_disk->fops->release(bdev->bd_disk); +} + static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) { struct gendisk *disk = bdev->bd_disk; @@ -657,20 +665,21 @@ static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) if (!atomic_read(&bdev->bd_openers)) set_init_blocksize(bdev); - if (test_bit(GD_NEED_PART_SCAN, &disk->state)) - bdev_disk_changed(disk, false); atomic_inc(&bdev->bd_openers); + if (test_bit(GD_NEED_PART_SCAN, &disk->state)) { + /* + * Only return scanning errors if we are called from contexts + * that explicitly want them, e.g. the BLKRRPART ioctl. + */ + ret = bdev_disk_changed(disk, false); + if (ret && (mode & BLK_OPEN_STRICT_SCAN)) { + blkdev_put_whole(bdev); + return ret; + } + } return 0; } -static void blkdev_put_whole(struct block_device *bdev) -{ - if (atomic_dec_and_test(&bdev->bd_openers)) - blkdev_flush_mapping(bdev); - if (bdev->bd_disk->fops->release) - bdev->bd_disk->fops->release(bdev->bd_disk); -} - static int blkdev_get_part(struct block_device *part, blk_mode_t mode) { struct gendisk *disk = part->bd_disk; @@ -738,17 +747,17 @@ void blkdev_put_no_open(struct block_device *bdev) static bool bdev_writes_blocked(struct block_device *bdev) { - return bdev->bd_writers == -1; + return bdev->bd_writers < 0; } static void bdev_block_writes(struct block_device *bdev) { - bdev->bd_writers = -1; + bdev->bd_writers--; } static void bdev_unblock_writes(struct block_device *bdev) { - bdev->bd_writers = 0; + bdev->bd_writers++; } static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode) @@ -864,7 +873,7 @@ struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, goto abort_claiming; ret = -EBUSY; if (!bdev_may_open(bdev, mode)) - goto abort_claiming; + goto put_module; if (bdev_is_partition(bdev)) ret = blkdev_get_part(bdev, mode); else diff --git a/block/bio.c b/block/bio.c index b9642a41f286e..b52b56067e792 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1152,7 +1152,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty) bio_for_each_folio_all(fi, bio) { struct page *page; - size_t done = 0; + size_t nr_pages; if (mark_dirty) { folio_lock(fi.folio); @@ -1160,10 +1160,11 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty) folio_unlock(fi.folio); } page = folio_page(fi.folio, fi.offset / PAGE_SIZE); + nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE - + fi.offset / PAGE_SIZE + 1; do { bio_release_page(bio, page++); - done += PAGE_SIZE; - } while (done < fi.length); + } while (--nr_pages != 0); } } EXPORT_SYMBOL_GPL(__bio_release_pages); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index ff93c385ba5af..caab7b679bf04 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -323,6 +323,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; + blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); @@ -619,12 +620,45 @@ static void blkg_destroy_all(struct gendisk *disk) spin_unlock_irq(&q->queue_lock); } +static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] = src->bytes[i]; + dst->ios[i] = src->ios[i]; + } +} + +static void __blkg_clear_stat(struct blkg_iostat_set *bis) +{ + struct blkg_iostat cur = {0}; + unsigned long flags; + + flags = u64_stats_update_begin_irqsave(&bis->sync); + blkg_iostat_set(&bis->cur, &cur); + blkg_iostat_set(&bis->last, &cur); + u64_stats_update_end_irqrestore(&bis->sync, flags); +} + +static void blkg_clear_stat(struct blkcg_gq *blkg) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); + + __blkg_clear_stat(s); + } + __blkg_clear_stat(&blkg->iostat); +} + static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; - int i, cpu; + int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); @@ -635,18 +669,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - for_each_possible_cpu(cpu) { - struct blkg_iostat_set *bis = - per_cpu_ptr(blkg->iostat_cpu, cpu); - memset(bis, 0, sizeof(*bis)); - - /* Re-initialize the cleared blkg_iostat_set */ - u64_stats_init(&bis->sync); - bis->blkg = blkg; - } - memset(&blkg->iostat, 0, sizeof(blkg->iostat)); - u64_stats_init(&blkg->iostat.sync); - + blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -949,16 +972,6 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx) } EXPORT_SYMBOL_GPL(blkg_conf_exit); -static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) -{ - int i; - - for (i = 0; i < BLKG_IOSTAT_NR; i++) { - dst->bytes[i] = src->bytes[i]; - dst->ios[i] = src->ios[i]; - } -} - static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; @@ -1024,7 +1037,19 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) struct blkg_iostat cur; unsigned int seq; + /* + * Order assignment of `next_bisc` from `bisc->lnode.next` in + * llist_for_each_entry_safe and clearing `bisc->lqueued` for + * avoiding to assign `next_bisc` with new next pointer added + * in blk_cgroup_bio_start() in case of re-ordering. + * + * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). + */ + smp_mb(); + WRITE_ONCE(bisc->lqueued, false); + if (bisc == &blkg->iostat) + goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { @@ -1034,10 +1059,24 @@ static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) blkcg_iostat_update(blkg, &cur, &bisc->last); +propagate_up: /* propagate global delta to parent (unless that's root) */ - if (parent && parent->parent) + if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); + /* + * Queue parent->iostat to its blkcg's lockless + * list to propagate up to the grandparent if the + * iostat hasn't been queued yet. + */ + if (!parent->iostat.lqueued) { + struct llist_head *plhead; + + plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); + llist_add(&parent->iostat.lnode, plhead); + parent->iostat.lqueued = true; + } + } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: @@ -1409,6 +1448,12 @@ static int blkcg_css_online(struct cgroup_subsys_state *css) return 0; } +void blkg_init_queue(struct request_queue *q) +{ + INIT_LIST_HEAD(&q->blkg_list); + mutex_init(&q->blkcg_mutex); +} + int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; @@ -1416,9 +1461,6 @@ int blkcg_init_disk(struct gendisk *disk) bool preloaded; int ret; - INIT_LIST_HEAD(&q->blkg_list); - mutex_init(&q->blkcg_mutex); - new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index b927a4a0ad030..5b0bdc268ade9 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -188,6 +188,7 @@ struct blkcg_policy { extern struct blkcg blkcg_root; extern bool blkcg_debug_stats; +void blkg_init_queue(struct request_queue *q); int blkcg_init_disk(struct gendisk *disk); void blkcg_exit_disk(struct gendisk *disk); @@ -481,6 +482,7 @@ struct blkcg { }; static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } +static inline void blkg_init_queue(struct request_queue *q) { } static inline int blkcg_init_disk(struct gendisk *disk) { return 0; } static inline void blkcg_exit_disk(struct gendisk *disk) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } diff --git a/block/blk-core.c b/block/blk-core.c index de771093b5268..923b7d91e6dc5 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -431,6 +431,8 @@ struct request_queue *blk_alloc_queue(int node_id) init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); + blkg_init_queue(q); + /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. @@ -974,10 +976,11 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end) unsigned long stamp; again: stamp = READ_ONCE(part->bd_stamp); - if (unlikely(time_after(now, stamp))) { - if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) - __part_stat_add(part, io_ticks, end ? now - stamp : 1); - } + if (unlikely(time_after(now, stamp)) && + likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) && + (end || part_in_flight(part))) + __part_stat_add(part, io_ticks, now - stamp); + if (part->bd_partno) { part = bdev_whole(part); goto again; diff --git a/block/blk-flush.c b/block/blk-flush.c index 3f4d41952ef21..d72b57898b239 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -183,7 +183,7 @@ static void blk_flush_complete_seq(struct request *rq, /* queue for flush */ if (list_empty(pending)) fq->flush_pending_since = jiffies; - list_move_tail(&rq->queuelist, pending); + list_add_tail(&rq->queuelist, pending); break; case REQ_FSEQ_DATA: @@ -261,6 +261,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq, unsigned int seq = blk_flush_cur_seq(rq); BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH); + list_del_init(&rq->queuelist); blk_flush_complete_seq(rq, fq, seq, error); } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 04d44f0bcbc85..f3b68b7994391 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1347,7 +1347,7 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); - u64 tdelta, delay, new_delay; + u64 tdelta, delay, new_delay, shift; s64 vover, vover_pct; u32 hwa; @@ -1362,8 +1362,9 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; - if (iocg->delay) - delay = iocg->delay >> div64_u64(tdelta, USEC_PER_SEC); + shift = div64_u64(tdelta, USEC_PER_SEC); + if (iocg->delay && shift < BITS_PER_LONG) + delay = iocg->delay >> shift; else delay = 0; @@ -1438,8 +1439,11 @@ static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); - /* make sure that nobody messed with @iocg */ - WARN_ON_ONCE(list_empty(&iocg->active_list)); + /* + * make sure that nobody messed with @iocg. Check iocg->pd.online + * to avoid warn when removing blkcg or disk. + */ + WARN_ON_ONCE(list_empty(&iocg->active_list) && iocg->pd.online); WARN_ON_ONCE(iocg->inuse > 1); iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt); diff --git a/block/blk-merge.c b/block/blk-merge.c index 2d470cf2173e2..925c5eaac5815 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -779,6 +779,8 @@ static void blk_account_io_merge_request(struct request *req) if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); + part_stat_local_dec(req->part, + in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } diff --git a/block/blk-mq.c b/block/blk-mq.c index 2dc01551e27c7..f1d071810893e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -771,16 +771,11 @@ static void req_bio_endio(struct request *rq, struct bio *bio, /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. - * For such case, force the completed nbytes to be equal to - * the BIO size so that bio_advance() sets the BIO remaining - * size to 0 and we end up calling bio_endio() before returning. */ - if (bio->bi_iter.bi_size != nbytes) { + if (bio->bi_iter.bi_size != nbytes) bio->bi_status = BLK_STS_IOERR; - nbytes = bio->bi_iter.bi_size; - } else { + else bio->bi_iter.bi_sector = rq->__sector; - } } bio_advance(bio, nbytes); @@ -1003,6 +998,8 @@ static inline void blk_account_io_done(struct request *req, u64 now) update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); + part_stat_local_dec(req->part, + in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } @@ -1025,6 +1022,8 @@ static inline void blk_account_io_start(struct request *req) part_stat_lock(); update_io_ticks(req->part, jiffies, false); + part_stat_local_inc(req->part, + in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } diff --git a/block/blk-settings.c b/block/blk-settings.c index 06ea91e51b8b2..490c1cce49746 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -559,6 +559,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, unsigned int top, bottom, alignment, ret = 0; t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); + t->max_user_sectors = min_not_zero(t->max_user_sectors, + b->max_user_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors); t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors, @@ -689,6 +691,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); t->zoned = max(t->zoned, b->zoned); + if (!t->zoned) { + t->zone_write_granularity = 0; + t->max_zone_append_sectors = 0; + } return ret; } EXPORT_SYMBOL(blk_stack_limits); diff --git a/block/blk-stat.c b/block/blk-stat.c index 7ff76ae6c76a9..e42c263e53fb9 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -27,7 +27,7 @@ void blk_rq_stat_init(struct blk_rq_stat *stat) /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { - if (!src->nr_samples) + if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); diff --git a/block/blk.h b/block/blk.h index 1ef920f72e0f8..1154e87a4022d 100644 --- a/block/blk.h +++ b/block/blk.h @@ -344,6 +344,7 @@ static inline bool blk_do_io_stat(struct request *rq) } void update_io_ticks(struct block_device *part, unsigned long now, bool end); +unsigned int part_in_flight(struct block_device *part); static inline void req_set_nomerge(struct request_queue *q, struct request *req) { diff --git a/block/fops.c b/block/fops.c index 0cf8cf72cdfa1..799821040601a 100644 --- a/block/fops.c +++ b/block/fops.c @@ -387,7 +387,7 @@ static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->bdev = bdev; iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev)); - if (iomap->offset >= isize) + if (offset >= isize) return -EIO; iomap->type = IOMAP_MAPPED; iomap->addr = iomap->offset; diff --git a/block/genhd.c b/block/genhd.c index d74fb5b4ae681..2e4c2521584a1 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -118,7 +118,7 @@ static void part_stat_read_all(struct block_device *part, } } -static unsigned int part_in_flight(struct block_device *part) +unsigned int part_in_flight(struct block_device *part) { unsigned int inflight = 0; int cpu; @@ -345,9 +345,7 @@ int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode) struct bdev_handle *handle; int ret = 0; - if (disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) - return -EINVAL; - if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state)) + if (!disk_has_partscan(disk)) return -EINVAL; if (disk->open_partitions) return -EBUSY; @@ -503,8 +501,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, goto out_unregister_bdi; /* Make sure the first partition scan will be proceed */ - if (get_capacity(disk) && !(disk->flags & GENHD_FL_NO_PART) && - !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state)) + if (get_capacity(disk) && disk_has_partscan(disk)) set_bit(GD_NEED_PART_SCAN, &disk->state); bdev_add(disk->part0, ddev->devt); @@ -1047,6 +1044,12 @@ static ssize_t diskseq_show(struct device *dev, return sprintf(buf, "%llu\n", disk->diskseq); } +static ssize_t partscan_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", disk_has_partscan(dev_to_disk(dev))); +} + static DEVICE_ATTR(range, 0444, disk_range_show, NULL); static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL); static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL); @@ -1060,6 +1063,7 @@ static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store); static DEVICE_ATTR(diskseq, 0444, diskseq_show, NULL); +static DEVICE_ATTR(partscan, 0444, partscan_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, @@ -1106,6 +1110,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_events_async.attr, &dev_attr_events_poll_msecs.attr, &dev_attr_diskseq.attr, + &dev_attr_partscan.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/block/holder.c b/block/holder.c index 37d18c13d9581..791091a7eac23 100644 --- a/block/holder.c +++ b/block/holder.c @@ -8,6 +8,8 @@ struct bd_holder_disk { int refcnt; }; +static DEFINE_MUTEX(blk_holder_mutex); + static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev, struct gendisk *disk) { @@ -80,7 +82,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) kobject_get(bdev->bd_holder_dir); mutex_unlock(&bdev->bd_disk->open_mutex); - mutex_lock(&disk->open_mutex); + mutex_lock(&blk_holder_mutex); WARN_ON_ONCE(!bdev->bd_holder); holder = bd_find_holder_disk(bdev, disk); @@ -108,7 +110,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) goto out_del_symlink; list_add(&holder->list, &disk->slave_bdevs); - mutex_unlock(&disk->open_mutex); + mutex_unlock(&blk_holder_mutex); return 0; out_del_symlink: @@ -116,7 +118,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) out_free_holder: kfree(holder); out_unlock: - mutex_unlock(&disk->open_mutex); + mutex_unlock(&blk_holder_mutex); if (ret) kobject_put(bdev->bd_holder_dir); return ret; @@ -140,7 +142,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) if (WARN_ON_ONCE(!disk->slave_dir)) return; - mutex_lock(&disk->open_mutex); + mutex_lock(&blk_holder_mutex); holder = bd_find_holder_disk(bdev, disk); if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) { del_symlink(disk->slave_dir, bdev_kobj(bdev)); @@ -149,6 +151,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) list_del_init(&holder->list); kfree(holder); } - mutex_unlock(&disk->open_mutex); + mutex_unlock(&blk_holder_mutex); } EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); diff --git a/block/ioctl.c b/block/ioctl.c index 438f79c564cfc..ccab3c54dad3e 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -33,7 +33,7 @@ static int blkpg_do_ioctl(struct block_device *bdev, if (op == BLKPG_DEL_PARTITION) return bdev_del_partition(disk, p.pno); - if (p.start < 0 || p.length <= 0 || p.start + p.length < 0) + if (p.start < 0 || p.length <= 0 || LLONG_MAX - p.length < p.start) return -EINVAL; /* Check that the partition is aligned to the block size */ if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev))) @@ -89,7 +89,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2]; - uint64_t start, len; + uint64_t start, len, end; struct inode *inode = bdev->bd_inode; int err; @@ -110,7 +110,8 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, if (len & 511) return -EINVAL; - if (start + len > bdev_nr_bytes(bdev)) + if (check_add_overflow(start, len, &end) || + end > bdev_nr_bytes(bdev)) return -EINVAL; filemap_invalidate_lock(inode->i_mapping); @@ -556,7 +557,8 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode, return -EACCES; if (bdev_is_partition(bdev)) return -EINVAL; - return disk_scan_partitions(bdev->bd_disk, mode); + return disk_scan_partitions(bdev->bd_disk, + mode | BLK_OPEN_STRICT_SCAN); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACETEARDOWN: diff --git a/block/mq-deadline.c b/block/mq-deadline.c index f958e79277b8b..02a916ba62ee7 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -646,9 +646,8 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; - unsigned int shift = tags->bitmap_tags.sb.shift; - dd->async_depth = max(1U, 3 * (1U << shift) / 4); + dd->async_depth = max(1UL, 3 * q->nr_requests / 4); sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth); } diff --git a/block/partitions/cmdline.c b/block/partitions/cmdline.c index c03bc105e5753..152c85df92b20 100644 --- a/block/partitions/cmdline.c +++ b/block/partitions/cmdline.c @@ -70,8 +70,8 @@ static int parse_subpart(struct cmdline_subpart **subpart, char *partdef) } if (*partdef == '(') { - int length; - char *next = strchr(++partdef, ')'); + partdef++; + char *next = strsep(&partdef, ")"); if (!next) { pr_warn("cmdline partition format is invalid."); @@ -79,11 +79,7 @@ static int parse_subpart(struct cmdline_subpart **subpart, char *partdef) goto fail; } - length = min_t(int, next - partdef, - sizeof(new_subpart->name) - 1); - strscpy(new_subpart->name, partdef, length); - - partdef = ++next; + strscpy(new_subpart->name, next, sizeof(new_subpart->name)); } else new_subpart->name[0] = '\0'; @@ -117,14 +113,12 @@ static void free_subpart(struct cmdline_parts *parts) } } -static int parse_parts(struct cmdline_parts **parts, const char *bdevdef) +static int parse_parts(struct cmdline_parts **parts, char *bdevdef) { int ret = -EINVAL; char *next; - int length; struct cmdline_subpart **next_subpart; struct cmdline_parts *newparts; - char buf[BDEVNAME_SIZE + 32 + 4]; *parts = NULL; @@ -132,28 +126,19 @@ static int parse_parts(struct cmdline_parts **parts, const char *bdevdef) if (!newparts) return -ENOMEM; - next = strchr(bdevdef, ':'); + next = strsep(&bdevdef, ":"); if (!next) { pr_warn("cmdline partition has no block device."); goto fail; } - length = min_t(int, next - bdevdef, sizeof(newparts->name) - 1); - strscpy(newparts->name, bdevdef, length); + strscpy(newparts->name, next, sizeof(newparts->name)); newparts->nr_subparts = 0; next_subpart = &newparts->subpart; - while (next && *(++next)) { - bdevdef = next; - next = strchr(bdevdef, ','); - - length = (!next) ? (sizeof(buf) - 1) : - min_t(int, next - bdevdef, sizeof(buf) - 1); - - strscpy(buf, bdevdef, length); - - ret = parse_subpart(next_subpart, buf); + while ((next = strsep(&bdevdef, ","))) { + ret = parse_subpart(next_subpart, next); if (ret) goto fail; @@ -199,24 +184,17 @@ static int cmdline_parts_parse(struct cmdline_parts **parts, *parts = NULL; - next = pbuf = buf = kstrdup(cmdline, GFP_KERNEL); + pbuf = buf = kstrdup(cmdline, GFP_KERNEL); if (!buf) return -ENOMEM; next_parts = parts; - while (next && *pbuf) { - next = strchr(pbuf, ';'); - if (next) - *next = '\0'; - - ret = parse_parts(next_parts, pbuf); + while ((next = strsep(&pbuf, ";"))) { + ret = parse_parts(next_parts, next); if (ret) goto fail; - if (next) - pbuf = ++next; - next_parts = &(*next_parts)->next_parts; } @@ -250,7 +228,6 @@ static struct cmdline_parts *bdev_parts; static int add_part(int slot, struct cmdline_subpart *subpart, struct parsed_partitions *state) { - int label_min; struct partition_meta_info *info; char tmp[sizeof(info->volname) + 4]; @@ -262,9 +239,7 @@ static int add_part(int slot, struct cmdline_subpart *subpart, info = &state->parts[slot].info; - label_min = min_t(int, sizeof(info->volname) - 1, - sizeof(subpart->name)); - strscpy(info->volname, subpart->name, label_min); + strscpy(info->volname, subpart->name, sizeof(info->volname)); snprintf(tmp, sizeof(tmp), "(%s)", info->volname); strlcat(state->pp_buf, tmp, PAGE_SIZE); diff --git a/block/partitions/core.c b/block/partitions/core.c index 5f5ed5c75f04d..eac887755f4f0 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -584,10 +584,7 @@ static int blk_add_partitions(struct gendisk *disk) struct parsed_partitions *state; int ret = -EAGAIN, p; - if (disk->flags & GENHD_FL_NO_PART) - return 0; - - if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state)) + if (!disk_has_partscan(disk)) return 0; state = check_partition(disk); diff --git a/block/sed-opal.c b/block/sed-opal.c index fa4dba5d85319..441ec3fc0e5af 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -314,7 +314,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen) &key_type_user, key_name, true); if (IS_ERR(kref)) - ret = PTR_ERR(kref); + return PTR_ERR(kref); key = key_ref_to_ptr(kref); down_read(&key->sem); diff --git a/certs/blacklist.c b/certs/blacklist.c index 675dd7a8f07ab..d7d442b2d146a 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -276,6 +276,9 @@ int add_key_to_revocation_list(const char *data, size_t size) if (IS_ERR(key)) { pr_err("Problem with revocation key (%ld)\n", PTR_ERR(key)); return PTR_ERR(key); + } else { + pr_notice("Revoked X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); } return 0; diff --git a/crypto/Kconfig b/crypto/Kconfig index 7d156c75f15f2..44661c2e30ca5 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1269,10 +1269,11 @@ config CRYPTO_JITTERENTROPY A non-physical non-deterministic ("true") RNG (e.g., an entropy source compliant with NIST SP800-90B) intended to provide a seed to a - deterministic RNG (e.g. per NIST SP800-90C). + deterministic RNG (e.g., per NIST SP800-90C). This RNG does not perform any cryptographic whitening of the generated + random numbers. - See https://www.chronox.de/jent.html + See https://www.chronox.de/jent/ if CRYPTO_JITTERENTROPY if CRYPTO_FIPS && EXPERT diff --git a/crypto/aegis128-neon-inner.c b/crypto/aegis128-neon-inner.c index b6a52a386b220..40597d6c7f1ff 100644 --- a/crypto/aegis128-neon-inner.c +++ b/crypto/aegis128-neon-inner.c @@ -148,8 +148,8 @@ void crypto_aegis128_init_neon(void *state, const void *key, const void *iv) kiv, vld1q_u8(const1), vld1q_u8(const0), - k ^ vld1q_u8(const0), - k ^ vld1q_u8(const1), + (uint8x16_t) (k ^ vld1q_u8(const0)), + (uint8x16_t) (k ^ vld1q_u8(const1)), }}; int i; diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig index 59ec726b7c770..684767ab23e24 100644 --- a/crypto/asymmetric_keys/Kconfig +++ b/crypto/asymmetric_keys/Kconfig @@ -15,6 +15,7 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE select MPILIB select CRYPTO_HASH_INFO select CRYPTO_AKCIPHER + select CRYPTO_SIG select CRYPTO_HASH help This option provides support for asymmetric public key type handling. @@ -85,5 +86,7 @@ config FIPS_SIGNATURE_SELFTEST depends on ASYMMETRIC_KEY_TYPE depends on PKCS7_MESSAGE_PARSER=X509_CERTIFICATE_PARSER depends on X509_CERTIFICATE_PARSER + depends on CRYPTO_RSA + depends on CRYPTO_SHA256 endif # ASYMMETRIC_KEY_TYPE diff --git a/crypto/asymmetric_keys/mscode_parser.c b/crypto/asymmetric_keys/mscode_parser.c index 05402ef8964ed..8aecbe4637f36 100644 --- a/crypto/asymmetric_keys/mscode_parser.c +++ b/crypto/asymmetric_keys/mscode_parser.c @@ -75,6 +75,9 @@ int mscode_note_digest_algo(void *context, size_t hdrlen, oid = look_up_OID(value, vlen); switch (oid) { + case OID_sha1: + ctx->digest_algo = "sha1"; + break; case OID_sha256: ctx->digest_algo = "sha256"; break; diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c index 5b08c50722d0f..231ad7b3789d5 100644 --- a/crypto/asymmetric_keys/pkcs7_parser.c +++ b/crypto/asymmetric_keys/pkcs7_parser.c @@ -227,6 +227,9 @@ int pkcs7_sig_note_digest_algo(void *context, size_t hdrlen, struct pkcs7_parse_context *ctx = context; switch (ctx->last_oid) { + case OID_sha1: + ctx->sinfo->sig->hash_algo = "sha1"; + break; case OID_sha256: ctx->sinfo->sig->hash_algo = "sha256"; break; @@ -278,6 +281,7 @@ int pkcs7_sig_note_pkey_algo(void *context, size_t hdrlen, ctx->sinfo->sig->pkey_algo = "rsa"; ctx->sinfo->sig->encoding = "pkcs1"; break; + case OID_id_ecdsa_with_sha1: case OID_id_ecdsa_with_sha224: case OID_id_ecdsa_with_sha256: case OID_id_ecdsa_with_sha384: diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index e5f22691febd5..e314fd57e6f88 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -115,7 +115,8 @@ software_key_determine_akcipher(const struct public_key *pkey, */ if (!hash_algo) return -EINVAL; - if (strcmp(hash_algo, "sha224") != 0 && + if (strcmp(hash_algo, "sha1") != 0 && + strcmp(hash_algo, "sha224") != 0 && strcmp(hash_algo, "sha256") != 0 && strcmp(hash_algo, "sha384") != 0 && strcmp(hash_algo, "sha512") != 0 && diff --git a/crypto/asymmetric_keys/signature.c b/crypto/asymmetric_keys/signature.c index 398983be77e8b..2deff81f8af50 100644 --- a/crypto/asymmetric_keys/signature.c +++ b/crypto/asymmetric_keys/signature.c @@ -115,7 +115,7 @@ EXPORT_SYMBOL_GPL(decrypt_blob); * Sign the specified data blob using the private key specified by params->key. * The signature is wrapped in an encoding if params->encoding is specified * (eg. "pkcs1"). If the encoding needs to know the digest type, this can be - * passed through params->hash_algo (eg. "sha512"). + * passed through params->hash_algo (eg. "sha1"). * * Returns the length of the data placed in the signature buffer or an error. */ diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 487204d394266..bb0bffa271b53 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -198,6 +198,10 @@ int x509_note_sig_algo(void *context, size_t hdrlen, unsigned char tag, default: return -ENOPKG; /* Unsupported combination */ + case OID_sha1WithRSAEncryption: + ctx->cert->sig->hash_algo = "sha1"; + goto rsa_pkcs1; + case OID_sha256WithRSAEncryption: ctx->cert->sig->hash_algo = "sha256"; goto rsa_pkcs1; @@ -214,6 +218,10 @@ int x509_note_sig_algo(void *context, size_t hdrlen, unsigned char tag, ctx->cert->sig->hash_algo = "sha224"; goto rsa_pkcs1; + case OID_id_ecdsa_with_sha1: + ctx->cert->sig->hash_algo = "sha1"; + goto ecdsa; + case OID_id_rsassa_pkcs1_v1_5_with_sha3_256: ctx->cert->sig->hash_algo = "sha3-256"; goto rsa_pkcs1; diff --git a/crypto/asymmetric_keys/x509_loader.c b/crypto/asymmetric_keys/x509_loader.c index a417413269989..2e1ffccf27ce5 100644 --- a/crypto/asymmetric_keys/x509_loader.c +++ b/crypto/asymmetric_keys/x509_loader.c @@ -41,6 +41,7 @@ int x509_load_certificate_list(const u8 cert_list[], if (IS_ERR(key)) { pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", PTR_ERR(key)); + WARN_ON_ONCE(1); } else { pr_notice("Loaded X.509 cert '%s'\n", key_ref_to_ptr(key)->description); diff --git a/crypto/ecdsa.c b/crypto/ecdsa.c index fbd76498aba83..3f9ec273a121f 100644 --- a/crypto/ecdsa.c +++ b/crypto/ecdsa.c @@ -373,4 +373,7 @@ module_exit(ecdsa_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Stefan Berger "); MODULE_DESCRIPTION("ECDSA generic algorithm"); +MODULE_ALIAS_CRYPTO("ecdsa-nist-p192"); +MODULE_ALIAS_CRYPTO("ecdsa-nist-p256"); +MODULE_ALIAS_CRYPTO("ecdsa-nist-p384"); MODULE_ALIAS_CRYPTO("ecdsa-generic"); diff --git a/crypto/ecrdsa.c b/crypto/ecrdsa.c index f3c6b5e15e75b..3811f3805b5d8 100644 --- a/crypto/ecrdsa.c +++ b/crypto/ecrdsa.c @@ -294,4 +294,5 @@ module_exit(ecrdsa_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vitaly Chikunov "); MODULE_DESCRIPTION("EC-RDSA generic algorithm"); +MODULE_ALIAS_CRYPTO("ecrdsa"); MODULE_ALIAS_CRYPTO("ecrdsa-generic"); diff --git a/crypto/fips.c b/crypto/fips.c index 92fd506abb21c..f358524aa3520 100644 --- a/crypto/fips.c +++ b/crypto/fips.c @@ -14,7 +14,8 @@ #include #include -int fips_enabled; +/* LP: #2049082 UBUNTU: SAUCE: FIPS kernels default to FIPS mode */ +int fips_enabled = 1; EXPORT_SYMBOL_GPL(fips_enabled); ATOMIC_NOTIFIER_HEAD(fips_fail_notif_chain); diff --git a/crypto/testmgr.h b/crypto/testmgr.h index 986f331a5fc24..12e1c892f3666 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -653,6 +653,30 @@ static const struct akcipher_testvec rsa_tv_template[] = { static const struct akcipher_testvec ecdsa_nist_p192_tv_template[] = { { .key = + "\x04\xf7\x46\xf8\x2f\x15\xf6\x22\x8e\xd7\x57\x4f\xcc\xe7\xbb\xc1" + "\xd4\x09\x73\xcf\xea\xd0\x15\x07\x3d\xa5\x8a\x8a\x95\x43\xe4\x68" + "\xea\xc6\x25\xc1\xc1\x01\x25\x4c\x7e\xc3\x3c\xa6\x04\x0a\xe7\x08" + "\x98", + .key_len = 49, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x01", + .param_len = 21, + .m = + "\xcd\xb9\xd2\x1c\xb7\x6f\xcd\x44\xb3\xfd\x63\xea\xa3\x66\x7f\xae" + "\x63\x85\xe7\x82", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x35\x02\x19\x00\xba\xe5\x93\x83\x6e\xb6\x3b\x63\xa0\x27\x91" + "\xc6\xf6\x7f\xc3\x09\xad\x59\xad\x88\x27\xd6\x92\x6b\x02\x18\x10" + "\x68\x01\x9d\xba\xce\x83\x08\xef\x95\x52\x7b\xa0\x0f\xe4\x18\x86" + "\x80\x6f\xa5\x79\x77\xda\xd0", + .c_size = 55, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = "\x04\xb6\x4b\xb1\xd1\xac\xba\x24\x8f\x65\xb2\x60\x00\x90\xbf\xbd" "\x78\x05\x73\xe9\x79\x1d\x6f\x7c\x0b\xd2\xc3\x93\xa7\x28\xe1\x75" "\xf7\xd5\x95\x1d\x28\x10\xc0\x75\x50\x5c\x1a\x4f\x3f\x8f\xa5\xee" @@ -756,6 +780,32 @@ static const struct akcipher_testvec ecdsa_nist_p192_tv_template[] = { static const struct akcipher_testvec ecdsa_nist_p256_tv_template[] = { { .key = + "\x04\xb9\x7b\xbb\xd7\x17\x64\xd2\x7e\xfc\x81\x5d\x87\x06\x83\x41" + "\x22\xd6\x9a\xaa\x87\x17\xec\x4f\x63\x55\x2f\x94\xba\xdd\x83\xe9" + "\x34\x4b\xf3\xe9\x91\x13\x50\xb6\xcb\xca\x62\x08\xe7\x3b\x09\xdc" + "\xc3\x63\x4b\x2d\xb9\x73\x53\xe4\x45\xe6\x7c\xad\xe7\x6b\xb0\xe8" + "\xaf", + .key_len = 65, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x07", + .param_len = 21, + .m = + "\xc2\x2b\x5f\x91\x78\x34\x26\x09\x42\x8d\x6f\x51\xb2\xc5\xaf\x4c" + "\x0b\xde\x6a\x42", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x46\x02\x21\x00\xf9\x25\xce\x9f\x3a\xa6\x35\x81\xcf\xd4\xe7" + "\xb7\xf0\x82\x56\x41\xf7\xd4\xad\x8d\x94\x5a\x69\x89\xee\xca\x6a" + "\x52\x0e\x48\x4d\xcc\x02\x21\x00\xd7\xe4\xef\x52\x66\xd3\x5b\x9d" + "\x8a\xfa\x54\x93\x29\xa7\x70\x86\xf1\x03\x03\xf3\x3b\xe2\x73\xf7" + "\xfb\x9d\x8b\xde\xd4\x8d\x6f\xad", + .c_size = 72, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = "\x04\x8b\x6d\xc0\x33\x8e\x2d\x8b\x67\xf5\xeb\xc4\x7f\xa0\xf5\xd9" "\x7b\x03\xa5\x78\x9a\xb5\xea\x14\xe4\x23\xd0\xaf\xd7\x0e\x2e\xa0" "\xc9\x8b\xdb\x95\xf8\xb3\xaf\xac\x00\x2c\x2c\x1f\x7a\xfd\x95\x88" @@ -866,6 +916,36 @@ static const struct akcipher_testvec ecdsa_nist_p256_tv_template[] = { static const struct akcipher_testvec ecdsa_nist_p384_tv_template[] = { { + .key = /* secp384r1(sha1) */ + "\x04\x89\x25\xf3\x97\x88\xcb\xb0\x78\xc5\x72\x9a\x14\x6e\x7a\xb1" + "\x5a\xa5\x24\xf1\x95\x06\x9e\x28\xfb\xc4\xb9\xbe\x5a\x0d\xd9\x9f" + "\xf3\xd1\x4d\x2d\x07\x99\xbd\xda\xa7\x66\xec\xbb\xea\xba\x79\x42" + "\xc9\x34\x89\x6a\xe7\x0b\xc3\xf2\xfe\x32\x30\xbe\xba\xf9\xdf\x7e" + "\x4b\x6a\x07\x8e\x26\x66\x3f\x1d\xec\xa2\x57\x91\x51\xdd\x17\x0e" + "\x0b\x25\xd6\x80\x5c\x3b\xe6\x1a\x98\x48\x91\x45\x7a\x73\xb0\xc3" + "\xf1", + .key_len = 97, + .params = + "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04" + "\x00\x22", + .param_len = 18, + .m = + "\x12\x55\x28\xf0\x77\xd5\xb6\x21\x71\x32\x48\xcd\x28\xa8\x25\x22" + "\x3a\x69\xc1\x93", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x66\x02\x31\x00\xf5\x0f\x24\x4c\x07\x93\x6f\x21\x57\x55\x07" + "\x20\x43\x30\xde\xa0\x8d\x26\x8e\xae\x63\x3f\xbc\x20\x3a\xc6\xf1" + "\x32\x3c\xce\x70\x2b\x78\xf1\x4c\x26\xe6\x5b\x86\xcf\xec\x7c\x7e" + "\xd0\x87\xd7\xd7\x6e\x02\x31\x00\xcd\xbb\x7e\x81\x5d\x8f\x63\xc0" + "\x5f\x63\xb1\xbe\x5e\x4c\x0e\xa1\xdf\x28\x8c\x1b\xfa\xf9\x95\x88" + "\x74\xa0\x0f\xbf\xaf\xc3\x36\x76\x4a\xa1\x59\xf1\x1c\xa4\x58\x26" + "\x79\x12\x2a\xb7\xc5\x15\x92\xc5", + .c_size = 104, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { .key = /* secp384r1(sha224) */ "\x04\x69\x6c\xcf\x62\xee\xd0\x0d\xe5\xb5\x2f\x70\x54\xcf\x26\xa0" "\xd9\x98\x8d\x92\x2a\xab\x9b\x11\xcb\x48\x18\xa1\xa9\x0d\xd5\x18" diff --git a/debian.master/changelog b/debian.master/changelog new file mode 100644 index 0000000000000..ffb1956524406 --- /dev/null +++ b/debian.master/changelog @@ -0,0 +1,26368 @@ +linux (6.8.0-47.47) noble; urgency=medium + + * noble/linux: 6.8.0-47.47 -proposed tracker (LP: #2082118) + + * CVE-2024-45016 + - netem: fix return value if duplicate enqueue fails + + -- Manuel Diewald Fri, 27 Sep 2024 19:21:30 +0200 + +linux (6.8.0-45.45) noble; urgency=medium + + * noble/linux: 6.8.0-45.45 -proposed tracker (LP: #2078100) + + * Packaging resync (LP: #1786013) + - [Packaging] debian.master/dkms-versions -- update from kernel-versions + (main/s2024.08.05) + + * Noble update: upstream stable patchset 2024-08-09 (LP: #2076435) // + CVE-2024-41009 + - bpf: Fix overrunning reservations in ringbuf + + * CVE-2024-42160 + - f2fs: check validation of fault attrs in f2fs_build_fault_attr() + - f2fs: Add inline to f2fs_build_fault_attr() stub + + * Noble update: upstream stable patchset 2024-08-22 (LP: #2077600) // + CVE-2024-42224 + - net: dsa: mv88e6xxx: Correct check for empty list + + * Noble update: upstream stable patchset 2024-08-22 (LP: #2077600) // + CVE-2024-42154 + - tcp_metrics: validate source addr length + + * CVE-2024-42228 + - drm/amdgpu: Using uninitialized value *size when calling amdgpu_vce_cs_reloc + + * CVE-2024-42159 + - scsi: mpi3mr: Sanitise num_phys + + -- Manuel Diewald Fri, 30 Aug 2024 10:32:37 +0200 + +linux (6.8.0-44.44) noble; urgency=medium + + * noble/linux: 6.8.0-44.44 -proposed tracker (LP: #2076647) + + * Packaging resync (LP: #1786013) + - [Packaging] debian.master/dkms-versions -- update from kernel-versions + (main/2024.08.05) + + * Disable PCI_DYNAMIC_OF_NODES in Ubuntu (LP: #2074376) + - [Config] Disable PCI_DYNAMIC_OF_NODES + + * [SRU] Turbostat support for Arrow Lake H (LP: #2074372) + - tools/power turbostat: Enhance ARL/LNL support + - x86/cpu: Add model number for another Intel Arrow Lake mobile processor + - tools/power turbostat: Add ARL-H support + + * Noble update: upstream stable patchset 2024-07-30 (LP: #2075154) + - fs/writeback: bail out if there is no more inodes for IO and queued once + - padata: Disable BH when taking works lock on MT path + - crypto: hisilicon/sec - Fix memory leak for sec resource release + - crypto: hisilicon/qm - Add the err memory release process to qm uninit + - io_uring/sqpoll: work around a potential audit memory leak + - rcutorture: Fix rcu_torture_one_read() pipe_count overflow comment + - rcutorture: Make stall-tasks directly exit when rcutorture tests end + - rcutorture: Fix invalid context warning when enable srcu barrier testing + - block/ioctl: prefer different overflow check + - ssb: Fix potential NULL pointer dereference in ssb_device_uevent() + - selftests/bpf: Prevent client connect before server bind in + test_tc_tunnel.sh + - selftests/bpf: Fix flaky test btf_map_in_map/lookup_update + - batman-adv: bypass empty buckets in batadv_purge_orig_ref() + - wifi: ath9k: work around memset overflow warning + - af_packet: avoid a false positive warning in packet_setsockopt() + - ACPI: x86: Add PNP_UART1_SKIP quirk for Lenovo Blade2 tablets + - drop_monitor: replace spin_lock by raw_spin_lock + - scsi: qedi: Fix crash while reading debugfs attribute + - net: sfp: add quirk for ATS SFP-GE-T 1000Base-TX module + - net/sched: fix false lockdep warning on qdisc root lock + - kselftest: arm64: Add a null pointer check + - net: dsa: realtek: keep default LED state in rtl8366rb + - netpoll: Fix race condition in netpoll_owner_active + - wifi: mt76: mt7921s: fix potential hung tasks during chip recovery + - HID: Add quirk for Logitech Casa touchpad + - HID: asus: fix more n-key report descriptors if n-key quirked + - ACPI: video: Add backlight=native quirk for Lenovo Slim 7 16ARH7 + - Bluetooth: ath3k: Fix multiple issues reported by checkpatch.pl + - drm/amd/display: Exit idle optimizations before HDCP execution + - platform/x86: toshiba_acpi: Add quirk for buttons on Z830 + - ASoC: Intel: sof_sdw: add JD2 quirk for HP Omen 14 + - ASoC: Intel: sof_sdw: add quirk for Dell SKU 0C0F + - drm/lima: add mask irq callback to gp and pp + - drm/lima: mask irqs in timeout path before hard reset + - ALSA: hda/realtek: Add quirks for Lenovo 13X + - powerpc/pseries: Enforce hcall result buffer validity and size + - media: intel/ipu6: Fix build with !ACPI + - media: mtk-vcodec: potential null pointer deference in SCP + - powerpc/io: Avoid clang null pointer arithmetic warnings + - platform/x86: p2sb: Don't init until unassigned resources have been assigned + - power: supply: cros_usbpd: provide ID table for avoiding fallback match + - iommu/arm-smmu-v3: Free MSIs in case of ENOMEM + - ext4: fix uninitialized ratelimit_state->lock access in __ext4_fill_super() + - kprobe/ftrace: bail out if ftrace was killed + - usb: gadget: uvc: configfs: ensure guid to be valid before set + - f2fs: remove clear SB_INLINECRYPT flag in default_options + - usb: misc: uss720: check for incompatible versions of the Belkin F5U002 + - Avoid hw_desc array overrun in dw-axi-dmac + - usb: dwc3: pci: Don't set "linux,phy_charger_detect" property on Lenovo Yoga + Tab2 1380 + - usb: typec: ucsi_glink: drop special handling for CCI_BUSY + - udf: udftime: prevent overflow in udf_disk_stamp_to_time() + - PCI/PM: Avoid D3cold for HP Pavilion 17 PC/1972 PCIe Ports + - f2fs: don't set RO when shutting down f2fs + - MIPS: Octeon: Add PCIe link status check + - serial: imx: Introduce timeout when waiting on transmitter empty + - serial: exar: adding missing CTI and Exar PCI ids + - usb: gadget: function: Remove usage of the deprecated ida_simple_xx() API + - tty: add the option to have a tty reject a new ldisc + - vfio/pci: Collect hot-reset devices to local buffer + - cpufreq: amd-pstate: fix memory leak on CPU EPP exit + - ACPI: EC: Install address space handler at the namespace root + - PCI: Do not wait for disconnected devices when resuming + - ALSA: hda: cs35l41: Possible null pointer dereference in + cs35l41_hda_unbind() + - ALSA: seq: ump: Fix missing System Reset message handling + - MIPS: Routerboard 532: Fix vendor retry check code + - mips: bmips: BCM6358: make sure CBR is correctly set + - tracing: Build event generation tests only as modules + - ALSA: hda/realtek: Remove Framework Laptop 16 from quirks + - ALSA/hda: intel-dsp-config: Document AVS as dsp_driver option + - ice: avoid IRQ collision to fix init failure on ACPI S3 resume + - btrfs: zoned: allocate dummy checksums for zoned NODATASUM writes + - net: mvpp2: use slab_build_skb for oversized frames + - cipso: fix total option length computation + - ALSA: hda: cs35l56: Component should be unbound before deconstruction + - ALSA: hda: tas2781: Component should be unbound before deconstruction + - bpf: Avoid splat in pskb_pull_reason + - ALSA: hda/realtek: Enable headset mic on IdeaPad 330-17IKB 81DM + - netrom: Fix a memory leak in nr_heartbeat_expiry() + - ipv6: prevent possible NULL deref in fib6_nh_init() + - ipv6: prevent possible NULL dereference in rt6_probe() + - xfrm6: check ip6_dst_idev() return value in xfrm6_get_saddr() + - netns: Make get_net_ns() handle zero refcount net + - qca_spi: Make interrupt remembering atomic + - net: lan743x: disable WOL upon resume to restore full data path operation + - net: lan743x: Support WOL at both the PHY and MAC appropriately + - net: phy: mxl-gpy: Remove interrupt mask clearing from config_init + - net/sched: act_api: fix possible infinite loop in tcf_idr_check_alloc() + - tipc: force a dst refcount before doing decryption + - sched: act_ct: add netns into the key of tcf_ct_flow_table + - ptp: fix integer overflow in max_vclocks_store + - selftests: openvswitch: Use bash as interpreter + - net: stmmac: No need to calculate speed divider when offload is disabled + - virtio_net: checksum offloading handling fix + - virtio_net: fixing XDP for fully checksummed packets handling + - octeontx2-pf: Add error handling to VLAN unoffload handling + - octeontx2-pf: Fix linking objects into multiple modules + - netfilter: ipset: Fix suspicious rcu_dereference_protected() + - seg6: fix parameter passing when calling NF_HOOK() in End.DX4 and End.DX6 + behaviors + - netfilter: move the sysctl nf_hooks_lwtunnel into the netfilter core + - ice: Fix VSI list rule with ICE_SW_LKUP_LAST type + - bnxt_en: Restore PTP tx_avail count in case of skb_pad() error + - net: usb: rtl8150 fix unintiatilzed variables in rtl8150_get_link_ksettings + - RDMA/bnxt_re: Fix the max msix vectors macro + - spi: cs42l43: Correct SPI root clock speed + - RDMA/rxe: Fix responder length checking for UD request packets + - regulator: core: Fix modpost error "regulator_get_regmap" undefined + - dmaengine: idxd: Fix possible Use-After-Free in irq_process_work_list + - dmaengine: ioatdma: Fix leaking on version mismatch + - dmaengine: ioatdma: Fix error path in ioat3_dma_probe() + - dmaengine: ioatdma: Fix kmemleak in ioat_pci_probe() + - dmaengine: fsl-edma: avoid linking both modules + - dmaengine: ioatdma: Fix missing kmem_cache_destroy() + - regulator: bd71815: fix ramp values + - thermal/drivers/mediatek/lvts_thermal: Return error in case of invalid efuse + data + - arm64: dts: imx8mp: Fix TC9595 input clock on DH i.MX8M Plus DHCOM SoM + - arm64: dts: freescale: imx8mp-venice-gw73xx-2x: fix BT shutdown GPIO + - arm64: dts: imx93-11x11-evk: Remove the 'no-sdio' property + - arm64: dts: freescale: imx8mm-verdin: enable hysteresis on slow input pin + - ACPICA: Revert "ACPICA: avoid Info: mapping multiple BARs. Your kernel is + fine." + - spi: spi-imx: imx51: revert burst length calculation back to bits_per_word + - io_uring/rsrc: fix incorrect assignment of iter->nr_segs in io_import_fixed + - firmware: psci: Fix return value from psci_system_suspend() + - RDMA/mlx5: Fix unwind flow as part of mlx5_ib_stage_init_init + - RDMA/mlx5: Add check for srq max_sge attribute + - RDMA/mana_ib: Ignore optional access flags for MRs + - ACPI: EC: Evaluate orphan _REG under EC device + - arm64: defconfig: enable the vf610 gpio driver + - ext4: avoid overflow when setting values via sysfs + - ext4: fix slab-out-of-bounds in ext4_mb_find_good_group_avg_frag_lists() + - net: stmmac: Assign configured channel value to EXTTS event + - net: usb: ax88179_178a: improve reset check + - net: do not leave a dangling sk pointer, when socket creation fails + - btrfs: retry block group reclaim without infinite loop + - scsi: ufs: core: Free memory allocated for model before reinit + - cifs: fix typo in module parameter enable_gcm_256 + - LoongArch: Fix watchpoint setting error + - LoongArch: Trigger user-space watchpoints correctly + - LoongArch: Fix multiple hardware watchpoint issues + - KVM: Fix a data race on last_boosted_vcpu in kvm_vcpu_on_spin() + - KVM: arm64: Disassociate vcpus from redistributor region on teardown + - KVM: x86: Always sync PIR to IRR prior to scanning I/O APIC routes + - RDMA/rxe: Fix data copy for IB_SEND_INLINE + - RDMA/mlx5: Remove extra unlock on error path + - RDMA/mlx5: Follow rb_key.ats when creating new mkeys + - ovl: fix encoding fid for lower only root + - ALSA: hda/realtek: Limit mic boost on N14AP7 + - ALSA: hda/realtek: Add quirk for Lenovo Yoga Pro 7 14AHP9 + - drm/i915/mso: using joiner is not possible with eDP MSO + - drm/radeon: fix UBSAN warning in kv_dpm.c + - drm/amdgpu: fix UBSAN warning in kv_dpm.c + - dt-bindings: dma: fsl-edma: fix dma-channels constraints + - ocfs2: fix NULL pointer dereference in ocfs2_journal_dirty() + - ocfs2: fix NULL pointer dereference in ocfs2_abort_trigger() + - gcov: add support for GCC 14 + - kcov: don't lose track of remote references during softirqs + - efi/x86: Free EFI memory map only when installing a new one. + - serial: 8250_dw: Revert "Move definitions to the shared header" + - mm: mmap: allow for the maximum number of bits for randomizing mmap_base by + default + - tcp: clear tp->retrans_stamp in tcp_rcv_fastopen_synack() + - mm/page_table_check: fix crash on ZONE_DEVICE + - i2c: ocores: set IACK bit after core is enabled + - dt-bindings: i2c: atmel,at91sam: correct path to i2c-controller schema + - dt-bindings: i2c: google,cros-ec-i2c-tunnel: correct path to i2c-controller + schema + - spi: stm32: qspi: Fix dual flash mode sanity test in stm32_qspi_setup() + - arm64: dts: imx8qm-mek: fix gpio number for reg_usdhc2_vmmc + - spi: stm32: qspi: Clamp stm32_qspi_get_mode() output to CCR_BUSWIDTH_4 + - perf: script: add raw|disasm arguments to --insn-trace option + - nbd: Improve the documentation of the locking assumptions + - nbd: Fix signal handling + - tracing: Add MODULE_DESCRIPTION() to preemptirq_delay_test + - x86/cpu/vfm: Add new macros to work with (vendor/family/model) values + - x86/cpu: Fix x86_match_cpu() to match just X86_VENDOR_INTEL + - drm/amd/display: revert Exit idle optimizations before HDCP execution + - ASoC: Intel: sof-sdw: really remove FOUR_SPEAKER quirk + - net/sched: unregister lockdep keys in qdisc_create/qdisc_alloc error path + - kprobe/ftrace: fix build error due to bad function definition + - hid: asus: asus_report_fixup: fix potential read out of bounds + - Revert "mm: mmap: allow for the maximum number of bits for randomizing + mmap_base by default" + - platform/chrome: cros_usbpd_logger: provide ID table for avoiding fallback + match + - platform/chrome: cros_usbpd_notify: provide ID table for avoiding fallback + match + - ubsan: Avoid i386 UBSAN handler crashes with Clang + - arm64: defconfig: select INTERCONNECT_QCOM_SM6115 as built-in + - bpf: Avoid kfree_rcu() under lock in bpf_lpm_trie. + - devlink: use kvzalloc() to allocate devlink instance resources + - wifi: rtw89: 8852c: add quirk to set PCI BER for certain platforms + - clocksource: Make watchdog and suspend-timing multiplication overflow safe + - ACPI: resource: Do IRQ override on GMxBGxx (XMG APEX 17 M23) + - wifi: ath12k: add string type to search board data in board-2.bin for + WCN7850 + - wifi: ath12k: add firmware-2.bin support + - wifi: ath12k: fix kernel crash during resume + - arm64/sysreg: Update PIE permission encodings + - ACPI: resource: Skip IRQ override on Asus Vivobook Pro N6506MV + - wifi: ath12k: fix the problem that down grade phy mode operation + - bpf: avoid uninitialized warnings in verifier_global_subprogs.c + - selftests: net: fix timestamp not arriving in cmsg_time.sh + - net: ena: Add validation for completion descriptors consistency + - drm/amd/display: Workaround register access in idle race with cursor + - cgroup/cpuset: Make cpuset hotplug processing synchronous + - platform/x86: x86-android-tablets: Unregister devices in reverse order + - platform/x86: x86-android-tablets: Add Lenovo Yoga Tablet 2 Pro 1380F/L data + - ALSA: hda/realtek: Add quirks for HP Omen models using CS35L41 + - ext4: fold quota accounting into ext4_xattr_inode_lookup_create() + - ext4: do not create EA inode under buffer lock + - f2fs: fix to detect inconsistent nat entry during truncation + - usb: typec: ucsi_glink: rework quirks implementation + - xhci: remove XHCI_TRUST_TX_LENGTH quirk + - clk: Add a devm variant of clk_rate_exclusive_get() + - clk: Provide !COMMON_CLK dummy for devm_clk_rate_exclusive_get() + - i2c: lpi2c: Avoid calling clk_get_rate during transfer + - cxl: Add post-reset warning if reset results in loss of previously committed + HDM decoders + - OPP: Fix required_opp_tables for multiple genpds using same table + - wifi: iwlwifi: mvm: fix ROC version check + - wifi: mac80211: Recalc offload when monitor stop + - ice: fix 200G link speed message log + - ice: implement AQ download pkg retry + - bpf: Fix reg_set_min_max corruption of fake_reg + - ALSA: hda: cs35l41: Component should be unbound before deconstruction + - netdev-genl: fix error codes when outputting XDP features + - arm64: dts: freescale: imx8mm-verdin: Fix GPU speed + - phy: qcom-qmp: qserdes-txrx: Add missing registers offsets + - phy: qcom-qmp: pcs: Add missing v6 N4 register offsets + - phy: qcom: qmp-combo: Switch from V6 to V6 N4 register offsets + - powerpc/crypto: Add generated P8 asm to .gitignore + - spi: Exctract spi_dev_check_cs() helper + - spi: Fix SPI slave probe failure + - net: phy: dp83tg720: wake up PHYs in managed mode + - net: phy: dp83tg720: get master/slave configuration in link down state + - RDMA/mlx5: Ensure created mkeys always have a populated rb_key + - drm/amdgpu: fix locking scope when flushing tlb + - drm/amd/display: Remove redundant idle optimization check + - drm/amd/display: Attempt to avoid empty TUs when endpoint is DPIA + - ata: ahci: Do not enable LPM if no LPM states are supported by the HBA + - dmaengine: xilinx: xdma: Fix data synchronisation in xdma_channel_isr() + - net/tcp_ao: Don't leak ao_info on error-path + - mm: shmem: fix getting incorrect lruvec when replacing a shmem folio + - selftests: mptcp: print_test out of verify_listener_events + - selftests: mptcp: userspace_pm: fixed subtest names + - ima: Avoid blocking in RCU read-side critical section + - virt: guest_memfd: fix reference leak on hwpoisoned page + - thermal: int340x: processor_thermal: Support shared interrupts + - thermal: core: Change PM notifier priority to the minimum + - wifi: ath12k: check M3 buffer size as well whey trying to reuse it + - Upstream stable to v6.6.36, v6.9.7 + + * [SRU] Add Dynamic Tuning Technology (DTT) support for Lunar Lake + (LP: #2073961) + - thermal: int340x: processor_thermal: Add Lunar Lake-M PCI ID + + * Kubuntu 24.04 freezes after plugging in ethernet cable (LP: #2073358) + - e1000e: move force SMBUS near the end of enable_ulp function + - e1000e: fix force smbus during suspend flow + + * Noble update: upstream stable patchset 2024-07-25 (LP: #2074091) + - wifi: mac80211: mesh: Fix leak of mesh_preq_queue objects + - wifi: mac80211: Fix deadlock in ieee80211_sta_ps_deliver_wakeup() + - wifi: cfg80211: fully move wiphy work to unbound workqueue + - wifi: cfg80211: Lock wiphy in cfg80211_get_station + - wifi: cfg80211: pmsr: use correct nla_get_uX functions + - wifi: iwlwifi: mvm: don't initialize csa_work twice + - wifi: iwlwifi: mvm: revert gen2 TX A-MPDU size to 64 + - wifi: iwlwifi: mvm: set properly mac header + - wifi: iwlwifi: dbg_ini: move iwl_dbg_tlv_free outside of debugfs ifdef + - wifi: iwlwifi: mvm: check n_ssids before accessing the ssids + - wifi: iwlwifi: mvm: don't read past the mfuart notifcation + - wifi: mac80211: correctly parse Spatial Reuse Parameter Set element + - scsi: ufs: mcq: Fix error output and clean up ufshcd_mcq_abort() + - RISC-V: KVM: No need to use mask when hart-index-bit is 0 + - RISC-V: KVM: Fix incorrect reg_subtype labels in + kvm_riscv_vcpu_set_reg_isa_ext function + - ax25: Fix refcount imbalance on inbound connections + - ax25: Replace kfree() in ax25_dev_free() with ax25_dev_put() + - net/ncsi: Fix the multi thread manner of NCSI driver + - net: phy: micrel: fix KSZ9477 PHY issues after suspend/resume + - bpf: Fix a potential use-after-free in bpf_link_free() + - KVM: SEV-ES: Disallow SEV-ES guests when X86_FEATURE_LBRV is absent + - KVM: SEV-ES: Delegate LBR virtualization to the processor + - vmxnet3: disable rx data ring on dma allocation failure + - ipv6: ioam: block BH from ioam6_output() + - ipv6: sr: block BH in seg6_output_core() and seg6_input_core() + - net: tls: fix marking packets as decrypted + - bpf: Set run context for rawtp test_run callback + - octeontx2-af: Always allocate PF entries from low prioriy zone + - net/smc: avoid overwriting when adjusting sock bufsizes + - net: phy: Micrel KSZ8061: fix errata solution not taking effect problem + - net: sched: sch_multiq: fix possible OOB write in multiq_tune() + - vxlan: Fix regression when dropping packets due to invalid src addresses + - tcp: count CLOSE-WAIT sockets for TCP_MIB_CURRESTAB + - mptcp: count CLOSE-WAIT sockets for MPTCP_MIB_CURRESTAB + - net/mlx5: Stop waiting for PCI if pci channel is offline + - net/mlx5: Always stop health timer during driver removal + - net/mlx5: Fix tainted pointer delete is case of flow rules creation fail + - net/sched: taprio: always validate TCA_TAPRIO_ATTR_PRIOMAP + - ptp: Fix error message on failed pin verification + - ice: fix iteration of TLVs in Preserved Fields Area + - ice: remove af_xdp_zc_qps bitmap + - ice: add flag to distinguish reset from .ndo_bpf in XDP rings config + - net: wwan: iosm: Fix tainted pointer delete is case of region creation fail + - af_unix: Set sk->sk_state under unix_state_lock() for truly disconencted + peer. + - af_unix: Annodate data-races around sk->sk_state for writers. + - af_unix: Annotate data-race of sk->sk_state in unix_inq_len(). + - af_unix: Annotate data-races around sk->sk_state in unix_write_space() and + poll(). + - af_unix: Annotate data-race of sk->sk_state in unix_stream_connect(). + - af_unix: Annotate data-races around sk->sk_state in sendmsg() and recvmsg(). + - af_unix: Annotate data-race of sk->sk_state in unix_stream_read_skb(). + - af_unix: Annotate data-races around sk->sk_state in UNIX_DIAG. + - af_unix: Annotate data-races around sk->sk_sndbuf. + - af_unix: Annotate data-race of net->unx.sysctl_max_dgram_qlen. + - af_unix: Use unix_recvq_full_lockless() in unix_stream_connect(). + - af_unix: Use skb_queue_empty_lockless() in unix_release_sock(). + - af_unix: Use skb_queue_len_lockless() in sk_diag_show_rqlen(). + - af_unix: Annotate data-race of sk->sk_shutdown in sk_diag_fill(). + - ipv6: fix possible race in __fib6_drop_pcpu_from() + - net: ethtool: fix the error condition in ethtool_get_phy_stats_ethtool() + - selftests/mm: log a consistent test name for check_compaction + - irqchip/riscv-intc: Allow large non-standard interrupt number + - irqchip/riscv-intc: Introduce Andes hart-level interrupt controller + - eventfs: Update all the eventfs_inodes from the events descriptor + - io_uring/rsrc: don't lock while !TASK_RUNNING + - io_uring: check for non-NULL file pointer in io_file_can_poll() + - USB: class: cdc-wdm: Fix CPU lockup caused by excessive log messages + - USB: xen-hcd: Traverse host/ when CONFIG_USB_XEN_HCD is selected + - usb: typec: tcpm: fix use-after-free case in tcpm_register_source_caps + - usb: typec: tcpm: Ignore received Hard Reset in TOGGLING state + - mei: me: release irq in mei_me_pci_resume error path + - tty: n_tty: Fix buffer offsets when lookahead is used + - serial: port: Don't block system suspend even if bytes are left to xmit + - landlock: Fix d_parent walk + - jfs: xattr: fix buffer overflow for invalid xattr + - xhci: Set correct transferred length for cancelled bulk transfers + - xhci: Apply reset resume quirk to Etron EJ188 xHCI host + - xhci: Handle TD clearing for multiple streams case + - xhci: Apply broken streams quirk to Etron EJ188 xHCI host + - thunderbolt: debugfs: Fix margin debugfs node creation condition + - scsi: core: Disable CDL by default + - scsi: mpi3mr: Fix ATA NCQ priority support + - scsi: mpt3sas: Avoid test/set_bit() operating in non-allocated memory + - scsi: sd: Use READ(16) when reading block zero on large capacity disks + - gve: Clear napi->skb before dev_kfree_skb_any() + - powerpc/uaccess: Fix build errors seen with GCC 13/14 + - HID: nvidia-shield: Add missing check for input_ff_create_memless + - cxl/test: Add missing vmalloc.h for tools/testing/cxl/test/mem.c + - cxl/region: Fix memregion leaks in devm_cxl_add_region() + - cachefiles: add output string to cachefiles_obj_[get|put]_ondemand_fd + - cachefiles: remove requests from xarray during flushing requests + - cachefiles: add spin_lock for cachefiles_ondemand_info + - cachefiles: fix slab-use-after-free in cachefiles_ondemand_get_fd() + - cachefiles: fix slab-use-after-free in cachefiles_ondemand_daemon_read() + - cachefiles: remove err_put_fd label in cachefiles_ondemand_daemon_read() + - cachefiles: never get a new anonymous fd if ondemand_id is valid + - cachefiles: defer exposing anon_fd until after copy_to_user() succeeds + - cachefiles: flush all requests after setting CACHEFILES_DEAD + - selftests/ftrace: Fix to check required event file + - clk: sifive: Do not register clkdevs for PRCI clocks + - NFSv4.1 enforce rootpath check in fs_location query + - SUNRPC: return proper error from gss_wrap_req_priv + - NFS: add barriers when testing for NFS_FSDATA_BLOCKED + - selftests/tracing: Fix event filter test to retry up to 10 times + - nvme: fix nvme_pr_* status code parsing + - drm/panel: sitronix-st7789v: Add check for of_drm_get_panel_orientation + - platform/x86: dell-smbios: Fix wrong token data in sysfs + - gpio: tqmx86: fix typo in Kconfig label + - gpio: tqmx86: introduce shadow register for GPIO output value + - gpio: tqmx86: store IRQ trigger type and unmask status separately + - gpio: tqmx86: fix broken IRQ_TYPE_EDGE_BOTH interrupt type + - HID: core: remove unnecessary WARN_ON() in implement() + - iommu/amd: Fix sysfs leak in iommu init + - iommu: Return right value in iommu_sva_bind_device() + - io_uring/io-wq: Use set_bit() and test_bit() at worker->flags + - io_uring/io-wq: avoid garbage value of 'match' in io_wq_enqueue() + - HID: logitech-dj: Fix memory leak in logi_dj_recv_switch_to_dj_mode() + - drm/vmwgfx: Refactor drm connector probing for display modes + - drm/vmwgfx: Filter modes which exceed graphics memory + - drm/vmwgfx: 3D disabled should not effect STDU memory limits + - drm/vmwgfx: Remove STDU logic from generic mode_valid function + - drm/vmwgfx: Don't memcmp equivalent pointers + - af_unix: Annotate data-race of sk->sk_state in unix_accept(). + - modpost: do not warn about missing MODULE_DESCRIPTION() for vmlinux.o + - net: sfp: Always call `sfp_sm_mod_remove()` on remove + - net: hns3: fix kernel crash problem in concurrent scenario + - net: hns3: add cond_resched() to hns3 ring buffer init process + - liquidio: Adjust a NULL pointer handling path in lio_vf_rep_copy_packet + - net: stmmac: dwmac-qcom-ethqos: Configure host DMA width + - drm/komeda: check for error-valued pointer + - drm/bridge/panel: Fix runtime warning on panel bridge release + - tcp: fix race in tcp_v6_syn_recv_sock() + - net dsa: qca8k: fix usages of device_get_named_child_node() + - geneve: Fix incorrect inner network header offset when innerprotoinherit is + set + - net/mlx5e: Fix features validation check for tunneled UDP (non-VXLAN) + packets + - Bluetooth: fix connection setup in l2cap_connect + - netfilter: nft_inner: validate mandatory meta and payload + - netfilter: ipset: Fix race between namespace cleanup and gc in the list:set + type + - x86/asm: Use %c/%n instead of %P operand modifier in asm templates + - x86/uaccess: Fix missed zeroing of ia32 u64 get_user() range checking + - scsi: ufs: core: Quiesce request queues before checking pending cmds + - net: pse-pd: Use EOPNOTSUPP error code instead of ENOTSUPP + - gve: ignore nonrelevant GSO type bits when processing TSO headers + - net: stmmac: replace priv->speed with the portTransmitRate from the tc-cbs + parameters + - block: sed-opal: avoid possible wrong address reference in + read_sed_opal_key() + - block: fix request.queuelist usage in flush + - nvmet-passthru: propagate status from id override functions + - net/ipv6: Fix the RT cache flush via sysctl using a previous delay + - net: bridge: mst: pass vlan group directly to br_mst_vlan_set_state + - net: bridge: mst: fix suspicious rcu usage in br_mst_set_state + - ionic: fix use after netif_napi_del() + - af_unix: Read with MSG_PEEK loops if the first unread byte is OOB + - bnxt_en: Adjust logging of firmware messages in case of released token in + __hwrm_send() + - misc: microchip: pci1xxxx: fix double free in the error handling of + gp_aux_bus_probe() + - ksmbd: move leading slash check to smb2_get_name() + - ksmbd: fix missing use of get_write in in smb2_set_ea() + - x86/boot: Don't add the EFI stub to targets, again + - iio: adc: ad9467: fix scan type sign + - iio: dac: ad5592r: fix temperature channel scaling value + - iio: invensense: fix odr switching to same value + - iio: imu: inv_icm42600: delete unneeded update watermark call + - drivers: core: synchronize really_probe() and dev_uevent() + - parisc: Try to fix random segmentation faults in package builds + - ACPI: x86: Force StorageD3Enable on more products + - drm/exynos/vidi: fix memory leak in .get_modes() + - drm/exynos: hdmi: report safe 640x480 mode as a fallback when no EDID found + - mptcp: ensure snd_una is properly initialized on connect + - mptcp: pm: inc RmAddr MIB counter once per RM_ADDR ID + - mptcp: pm: update add_addr counters after connect + - clkdev: Update clkdev id usage to allow for longer names + - irqchip/gic-v3-its: Fix potential race condition in its_vlpi_prop_update() + - x86/kexec: Fix bug with call depth tracking + - x86/amd_nb: Check for invalid SMN reads + - perf/core: Fix missing wakeup when waiting for context reference + - perf auxtrace: Fix multiple use of --itrace option + - riscv: fix overlap of allocated page and PTR_ERR + - tracing/selftests: Fix kprobe event name test for .isra. functions + - kheaders: explicitly define file modes for archived headers + - null_blk: Print correct max open zones limit in null_init_zoned_dev() + - sock_map: avoid race between sock_map_close and sk_psock_put + - dma-buf: handle testing kthreads creation failure + - vmci: prevent speculation leaks by sanitizing event in event_deliver() + - spmi: hisi-spmi-controller: Do not override device identifier + - knfsd: LOOKUP can return an illegal error value + - fs/proc: fix softlockup in __read_vmcore + - ocfs2: use coarse time for new created files + - ocfs2: fix races between hole punching and AIO+DIO + - PCI: rockchip-ep: Remove wrong mask on subsys_vendor_id + - dmaengine: axi-dmac: fix possible race in remove() + - remoteproc: k3-r5: Wait for core0 power-up before powering up core1 + - remoteproc: k3-r5: Do not allow core1 to power up before core0 via sysfs + - iio: adc: axi-adc: make sure AXI clock is enabled + - iio: invensense: fix interrupt timestamp alignment + - riscv: rewrite __kernel_map_pages() to fix sleeping in invalid context + - rtla/timerlat: Simplify "no value" printing on top + - rtla/auto-analysis: Replace \t with spaces + - drm/i915/gt: Disarm breadcrumbs if engines are already idle + - drm/shmem-helper: Fix BUG_ON() on mmap(PROT_WRITE, MAP_PRIVATE) + - drm/i915/dpt: Make DPT object unshrinkable + - drm/i915: Fix audio component initialization + - intel_th: pci: Add Meteor Lake-S support + - pmdomain: ti-sci: Fix duplicate PD referrals + - btrfs: zoned: fix use-after-free due to race with dev replace + - xfs: fix imprecise logic in xchk_btree_check_block_owner + - xfs: fix scrub stats file permissions + - xfs: fix SEEK_HOLE/DATA for regions with active COW extents + - xfs: shrink failure needs to hold AGI buffer + - xfs: ensure submit buffers on LSN boundaries in error handlers + - xfs: allow sunit mount option to repair bad primary sb stripe values + - xfs: don't use current->journal_info + - xfs: allow cross-linking special files without project quota + - swiotlb: Enforce page alignment in swiotlb_alloc() + - swiotlb: Reinstate page-alignment for mappings >= PAGE_SIZE + - swiotlb: extend buffer pre-padding to alloc_align_mask if necessary + - tick/nohz_full: Don't abuse smp_call_function_single() in + tick_setup_device() + - mm/huge_memory: don't unpoison huge_zero_folio + - serial: 8250_pxa: Configure tx_loadsz to match FIFO IRQ level + - Revert "fork: defer linking file vma until vma is fully initialized" + - remoteproc: k3-r5: Jump to error handling labels in start/stop errors + - greybus: Fix use-after-free bug in gb_interface_release due to race + condition. + - ima: Fix use-after-free on a dentry's dname.name + - serial: core: Add UPIO_UNKNOWN constant for unknown port type + - serial: port: Introduce a common helper to read properties + - serial: 8250_dw: Switch to use uart_read_port_properties() + - serial: 8250_dw: Replace ACPI device check by a quirk + - serial: 8250_dw: Don't use struct dw8250_data outside of 8250_dw + - usb-storage: alauda: Check whether the media is initialized + - misc: microchip: pci1xxxx: Fix a memory leak in the error handling of + gp_aux_bus_probe() + - i2c: at91: Fix the functionality flags of the slave-only interface + - i2c: designware: Fix the functionality flags of the slave-only interface + - zap_pid_ns_processes: clear TIF_NOTIFY_SIGNAL along with TIF_SIGPENDING + - wifi: ath11k: fix WCN6750 firmware crash caused by 17 num_vdevs + - cpufreq: amd-pstate: Unify computation of + {max,min,nominal,lowest_nonlinear}_freq + - cpufreq: amd-pstate: Add quirk for the pstate CPPC capabilities missing + - cpufreq: amd-pstate: remove global header file + - virtio_net: fix possible dim status unrecoverable + - net: ethernet: mtk_eth_soc: handle dma buffer size soc specific + - ice: fix reads from NVM Shadow RAM on E830 and E825-C devices + - ice: map XDP queues to vectors in ice_vsi_map_rings_to_vectors() + - x86/cpu: Get rid of an unnecessary local variable in get_cpu_address_sizes() + - x86/cpu: Provide default cache line size if not enumerated + - selftests/mm: ksft_exit functions do not return + - selftests/mm: compaction_test: fix bogus test success and reduce probability + of OOM-killer invocation + - .editorconfig: remove trim_trailing_whitespace option + - kcov, usb: disable interrupts in kcov_remote_start_usb_softirq + - ata: libata-scsi: Set the RMB bit only for removable media devices + - powerpc/85xx: fix compile error without CONFIG_CRASH_DUMP + - kselftest/alsa: Ensure _GNU_SOURCE is defined + - thermal: core: Do not fail cdev registration because of invalid initial + state + - Bluetooth: hci_sync: Fix not using correct handle + - net/sched: initialize noop_qdisc owner + - tcp: use signed arithmetic in tcp_rtx_probe0_timed_out() + - drm/nouveau: don't attempt to schedule hpd_work on headless cards + - drm/xe/xe_gt_idle: use GT forcewake domain assertion + - drm/xe: flush engine buffers before signalling user fence on all engines + - drm/xe: Remove mem_access from guc_pc calls + - drm/xe: move disable_c6 call + - bnxt_en: Cap the size of HWRM_PORT_PHY_QCFG forwarded response + - iio: imu: bmi323: Fix trigger notification in case of error + - iio: pressure: bmp280: Fix BMP580 temperature reading + - iio: temperature: mlx90635: Fix ERR_PTR dereference in mlx90635_probe() + - thermal: ACPI: Invalidate trip points with temperature of 0 or below + - x86/mm/numa: Use NUMA_NO_NODE when calling memblock_set_node() + - memblock: make memblock_set_node() also warn about use of MAX_NUMNODES + - perf script: Show also errors for --insn-trace option + - wifi: cfg80211: validate HE operation element parsing + - wifi: rtlwifi: Ignore IEEE80211_CONF_CHANGE_RETRY_LIMITS + - locking/atomic: scripts: fix ${atomic}_sub_and_test() kerneldoc + - ata: ahci: Do not apply Intel PCS quirk on Intel Alder Lake + - ata: libata-core: Add ATA_HORKAGE_NOLPM for Apacer AS340 + - ata: libata-core: Add ATA_HORKAGE_NOLPM for Crucial CT240BX500SSD1 + - ata: libata-core: Add ATA_HORKAGE_NOLPM for AMD Radeon S3 SSD + - kexec: fix the unexpected kexec_dprintk() macro + - ocfs2: update inode fsync transaction id in ocfs2_unlink and ocfs2_link + - dm-integrity: set discard_granularity to logical block size + - drm/bridge: aux-hpd-bridge: correct devm_drm_dp_hpd_bridge_add() stub + - iio: temperature: mcp9600: Fix temperature reading for negative values + - drm/mst: Fix NULL pointer dereference at drm_dp_add_payload_part2 + - riscv: force PAGE_SIZE linear mapping if debug_pagealloc is enabled + - drm/xe: Properly handle alloc_guc_id() failure + - wifi: iwlwifi: mvm: support iwl_dev_tx_power_cmd_v8 + - wifi: iwlwifi: mvm: fix a crash on 7265 + - mei: vsc: Fix wrong invocation of ACPI SID method + - Upstream stable to v6.6.35, v6.9.6 + + * [SRU] Add support for intel trace hub for last platforms (LP: #2073926) // + Noble update: upstream stable patchset 2024-07-25 (LP: #2074091) + - intel_th: pci: Add Granite Rapids support + - intel_th: pci: Add Granite Rapids SOC support + - intel_th: pci: Add Sapphire Rapids SOC support + - intel_th: pci: Add Lunar Lake support + + * Fix L2CAP/LE/CPU/BV-02-C bluetooth certification failure (LP: #2072858) // + Noble update: upstream stable patchset 2024-07-25 (LP: #2074091) + - Bluetooth: L2CAP: Fix rejecting L2CAP_CONN_PARAM_UPDATE_REQ + + * Noble update: upstream stable patchset 2024-07-22 (LP: #2073788) + - drm/i915/hwmon: Get rid of devm + - afs: Don't cross .backup mountpoint from backup volume + - erofs: avoid allocating DEFLATE streams before mounting + - vxlan: Fix regression when dropping packets due to invalid src addresses + - drm/sun4i: hdmi: Convert encoder to atomic + - drm/sun4i: hdmi: Move mode_set into enable + - f2fs: fix to do sanity check on i_xattr_nid in sanity_check_inode() + - media: lgdt3306a: Add a check against null-pointer-def + - drm/amdgpu: add error handle to avoid out-of-bounds + - wifi: rtw89: correct aSIFSTime for 6GHz band + - ata: pata_legacy: make legacy_exit() work again + - fsverity: use register_sysctl_init() to avoid kmemleak warning + - proc: Move fdinfo PTRACE_MODE_READ check into the inode .permission + operation + - platform/chrome: cros_ec: Handle events during suspend after resume + completion + - thermal/drivers/qcom/lmh: Check for SCM availability at probe + - soc: qcom: rpmh-rsc: Enhance check for VRM in-flight request + - ACPI: resource: Do IRQ override on TongFang GXxHRXx and GMxHGxx + - arm64: tegra: Correct Tegra132 I2C alias + - arm64: dts: qcom: qcs404: fix bluetooth device address + - md/raid5: fix deadlock that raid5d() wait for itself to clear + MD_SB_CHANGE_PENDING + - wifi: rtl8xxxu: Fix the TX power of RTL8192CU, RTL8723AU + - wifi: rtlwifi: rtl8192de: Fix 5 GHz TX power + - wifi: rtlwifi: rtl8192de: Fix low speed with WPA3-SAE + - wifi: rtlwifi: rtl8192de: Fix endianness issue in RX path + - arm64: dts: qcom: sc8280xp: add missing PCIe minimum OPP + - arm64: dts: hi3798cv200: fix the size of GICR + - arm64: dts: ti: verdin-am62: Set memory size to 2gb + - media: mc: Fix graph walk in media_pipeline_start + - media: mc: mark the media devnode as registered from the, start + - media: mxl5xx: Move xpt structures off stack + - media: v4l2-core: hold videodev_lock until dev reg, finishes + - media: v4l: async: Properly re-initialise notifier entry in unregister + - media: v4l: async: Don't set notifier's V4L2 device if registering fails + - media: v4l: async: Fix notifier list entry init + - mmc: core: Add mmc_gpiod_set_cd_config() function + - mmc: sdhci: Add support for "Tuning Error" interrupts + - mmc: sdhci-acpi: Sort DMI quirks alphabetically + - mmc: sdhci-acpi: Fix Lenovo Yoga Tablet 2 Pro 1380 sdcard slot not working + - mmc: sdhci-acpi: Disable write protect detection on Toshiba WT10-A + - mmc: sdhci-acpi: Add quirk to enable pull-up on the card-detect GPIO on Asus + T100TA + - drm/fbdev-generic: Do not set physical framebuffer address + - fbdev: savage: Handle err return when savagefb_check_var failed + - drm/amdgpu/atomfirmware: add intergrated info v2.3 table + - 9p: add missing locking around taking dentry fid list + - drm/amd: Fix shutdown (again) on some SMU v13.0.4/11 platforms + - Revert "drm/amdkfd: fix gfx_target_version for certain 11.0.3 devices" + - KVM: SVM: WARN on vNMI + NMI window iff NMIs are outright masked + - KVM: arm64: Fix AArch32 register narrowing on userspace write + - KVM: arm64: Allow AArch32 PSTATE.M to be restored as System mode + - KVM: arm64: AArch32: Fix spurious trapping of conditional instructions + - LoongArch: Add all CPUs enabled by fdt to NUMA node 0 + - LoongArch: Override higher address bits in JUMP_VIRT_ADDR + - clk: bcm: dvp: Assign ->num before accessing ->hws + - clk: bcm: rpi: Assign ->num before accessing ->hws + - clk: qcom: clk-alpha-pll: fix rate setting for Stromer PLLs + - crypto: ecdsa - Fix module auto-load on add-key + - crypto: ecrdsa - Fix module auto-load on add_key + - crypto: qat - Fix ADF_DEV_RESET_SYNC memory leak + - kbuild: Remove support for Clang's ThinLTO caching + - mm: fix race between __split_huge_pmd_locked() and GUP-fast + - filemap: add helper mapping_max_folio_size() + - iomap: fault in smaller chunks for non-large folio mappings + - i2c: acpi: Unbind mux adapters before delete + - HID: i2c-hid: elan: fix reset suspend current leakage + - scsi: core: Handle devices which return an unusually large VPD page count + - net/ipv6: Fix route deleting failure when metric equals 0 + - net/9p: fix uninit-value in p9_client_rpc() + - mm/ksm: fix ksm_pages_scanned accounting + - mm/ksm: fix ksm_zero_pages accounting + - kmsan: do not wipe out origin when doing partial unpoisoning + - tpm_tis: Do *not* flush uninitialized work + - intel_th: pci: Add Meteor Lake-S CPU support + - rtla/timerlat: Fix histogram report when a cpu count is 0 + - sparc64: Fix number of online CPUs + - mm/cma: drop incorrect alignment check in cma_init_reserved_mem + - mm/hugetlb: pass correct order_per_bit to cma_declare_contiguous_nid + - mm: /proc/pid/smaps_rollup: avoid skipping vma after getting mmap_lock again + - mm/vmalloc: fix vmalloc which may return null if called with __GFP_NOFAIL + - selftests/mm: compaction_test: fix incorrect write of zero to nr_hugepages + - selftests/mm: fix build warnings on ppc64 + - watchdog: rti_wdt: Set min_hw_heartbeat_ms to accommodate a safety margin + - bonding: fix oops during rmmod + - wifi: ath10k: fix QCOM_RPROC_COMMON dependency + - kdb: Fix buffer overflow during tab-complete + - kdb: Use format-strings rather than '\0' injection in kdb_read() + - kdb: Fix console handling when editing and tab-completing commands + - kdb: Merge identical case statements in kdb_read() + - kdb: Use format-specifiers rather than memset() for padding in kdb_read() + - sparc: move struct termio to asm/termios.h + - drm/amdkfd: handle duplicate BOs in reserve_bo_and_cond_vms + - ext4: Fixes len calculation in mpage_journal_page_buffers + - ext4: set type of ac_groups_linear_remaining to __u32 to avoid overflow + - ext4: fix mb_cache_entry's e_refcnt leak in ext4_xattr_block_cache_find() + - riscv: dts: starfive: Remove PMIC interrupt info for Visionfive 2 board + - ARM: dts: samsung: smdkv310: fix keypad no-autorepeat + - ARM: dts: samsung: smdk4412: fix keypad no-autorepeat + - ARM: dts: samsung: exynos4412-origen: fix keypad no-autorepeat + - parisc: Define HAVE_ARCH_HUGETLB_UNMAPPED_AREA + - parisc: Define sigset_t in parisc uapi header + - s390/ap: Fix crash in AP internal function modify_bitmap() + - s390/cpacf: Split and rework cpacf query functions + - s390/cpacf: Make use of invalid opcode produce a link error + - i3c: master: svc: fix invalidate IBI type and miss call client IBI handler + - genirq/irqdesc: Prevent use-after-free in irq_find_at_or_after() + - ASoC: SOF: ipc4-topology: Fix input format query of process modules without + base extension + - ALSA: ump: Don't clear bank selection after sending a program change + - ALSA: ump: Don't accept an invalid UMP protocol number + - EDAC/amd64: Convert PCIBIOS_* return codes to errnos + - EDAC/igen6: Convert PCIBIOS_* return codes to errnos + - nfs: fix undefined behavior in nfs_block_bits() + - NFS: Fix READ_PLUS when server doesn't support OP_READ_PLUS + - eventfs: Fix a possible null pointer dereference in eventfs_find_events() + - eventfs: Keep the directories from having the same inode number as files + - tracefs: Clear EVENT_INODE flag in tracefs_drop_inode() + - btrfs: fix crash on racing fsync and size-extending write into prealloc + - btrfs: fix leak of qgroup extent records after transaction abort + - ALSA: seq: Fix incorrect UMP type for system messages + - powerpc/bpf: enforce full ordering for ATOMIC operations with BPF_FETCH + - smb: client: fix deadlock in smb2_find_smb_tcon() + - smp: Provide 'setup_max_cpus' definition on UP too + - drm/xe/bb: assert width in xe_bb_create_job() + - crypto: starfive - Do not free stack buffer + - btrfs: qgroup: fix initialization of auto inherit array + - wifi: rtl8xxxu: enable MFP support with security flag of RX descriptor + - media: mgb4: Fix double debugfs remove + - media: ov2740: Fix LINK_FREQ and PIXEL_RATE control value reporting + - firmware: qcom_scm: disable clocks if qcom_scm_bw_enable() fails + - LoongArch: Fix built-in DTB detection + - LoongArch: Fix entry point in kernel image header + - clk: qcom: apss-ipq-pll: use stromer ops for IPQ5018 to fix boot failure + - net/tcp: Don't consider TCP_CLOSE in TCP_AO_ESTABLISHED + - selftests: net: lib: support errexit with busywait + - selftests: net: lib: avoid error removing empty netns name + - cpufreq: amd-pstate: Fix the inconsistency in max frequency units + - mm/memory-failure: fix handling of dissolved but not taken off from buddy + pages + - selftests/mm: compaction_test: fix bogus test success on Aarch64 + - irqchip/riscv-intc: Prevent memory leak when riscv_intc_init_common() fails + - Revert "perf record: Reduce memory for recording PERF_RECORD_LOST_SAMPLES + event" + - hwmon: (ltc2992) Fix memory leak in ltc2992_parse_dt() + - riscv: enable HAVE_ARCH_HUGE_VMAP for XIP kernel + - btrfs: qgroup: update rescan message levels and error codes + - btrfs: qgroup: fix qgroup id collision across mounts + - btrfs: cache folio size and shift in extent_buffer + - btrfs: protect folio::private when attaching extent buffer folios + - bpf: fix multi-uprobe PID filtering logic + - powerpc/64/bpf: fix tail calls for PCREL addressing + - nilfs2: fix potential kernel bug due to lack of writeback flag waiting + - nilfs2: fix nilfs_empty_dir() misjudgment and long loop on I/O errors + - Upstream stable to v6.6.34, v6.9.5 + + * Noble update: upstream stable patchset 2024-07-19 (LP: #2073603) + - perf record: Delete session after stopping sideband thread + - perf probe: Add missing libgen.h header needed for using basename() + - iio: core: Leave private pointer NULL when no private data supplied + - greybus: lights: check return of get_channel_from_mode + - phy: qcom: qmp-combo: fix duplicate return in qmp_v4_configure_dp_phy + - f2fs: multidev: fix to recognize valid zero block address + - f2fs: fix to wait on page writeback in __clone_blkaddrs() + - fpga: manager: add owner module and take its refcount + - fpga: bridge: add owner module and take its refcount + - counter: linux/counter.h: fix Excess kernel-doc description warning + - perf annotate: Get rid of duplicate --group option item + - usb: typec: ucsi: always register a link to USB PD device + - usb: typec: ucsi: simplify partner's PD caps registration + - perf stat: Do not fail on metrics on s390 z/VM systems + - soundwire: cadence: fix invalid PDI offset + - dmaengine: idma64: Add check for dma_set_max_seg_size + - firmware: dmi-id: add a release callback function + - perf annotate: Fix annotation_calc_lines() to pass correct address to + get_srcline() + - serial: max3100: Lock port->lock when calling uart_handle_cts_change() + - serial: max3100: Update uart_driver_registered on driver removal + - serial: max3100: Fix bitwise types + - greybus: arche-ctrl: move device table to its right location + - PCI: tegra194: Fix probe path for Endpoint mode + - serial: sc16is7xx: add proper sched.h include for sched_set_fifo() + - module: don't ignore sysfs_create_link() failures + - interconnect: qcom: qcm2290: Fix mas_snoc_bimc QoS port assignment + - arm64: dts: meson: fix S4 power-controller node + - perf tests: Make "test data symbol" more robust on Neoverse N1 + - perf tests: Apply attributes to all events in object code reading test + - perf record: Fix debug message placement for test consumption + - dt-bindings: PCI: rcar-pci-host: Add missing IOMMU properties + - perf bench uprobe: Remove lib64 from libc.so.6 binary path + - f2fs: compress: fix to relocate check condition in + f2fs_{release,reserve}_compress_blocks() + - f2fs: compress: fix to relocate check condition in + f2fs_ioc_{,de}compress_file() + - f2fs: fix to relocate check condition in f2fs_fallocate() + - f2fs: fix to check pinfile flag in f2fs_move_file_range() + - iio: adc: stm32: Fixing err code to not indicate success + - riscv: dts: starfive: visionfive 2: Remove non-existing TDM hardware + - coresight: etm4x: Fix unbalanced pm_runtime_enable() + - perf docs: Document bpf event modifier + - perf test shell arm_coresight: Increase buffer size for Coresight basic + tests + - iio: pressure: dps310: support negative temperature values + - iio: buffer-dmaengine: export buffer alloc and free functions + - iio: add the IIO backend framework + - [CONFIG] Update CONFIG_IIO_BACKEND + - iio: adc: ad9467: convert to backend framework + - [Config] Update CONFIG_AD9467 + - iio: adc: adi-axi-adc: move to backend framework + - [Config] Update CONFIG_ADI_AXI_ADC + - iio: adc: adi-axi-adc: only error out in major version mismatch + - coresight: etm4x: Do not hardcode IOMEM access for register restore + - coresight: etm4x: Do not save/restore Data trace control registers + - coresight: etm4x: Safe access for TRCQCLTR + - coresight: etm4x: Fix access to resource selector registers + - vfio/pci: fix potential memory leak in vfio_intx_enable() + - fpga: region: add owner module and take its refcount + - udf: Remove GFP_NOFS allocation in udf_expand_file_adinicb() + - udf: Convert udf_expand_file_adinicb() to use a folio + - microblaze: Remove gcc flag for non existing early_printk.c file + - microblaze: Remove early printk call from cpuinfo-static.c + - PCI: Wait for Link Training==0 before starting Link retrain + - perf intel-pt: Fix unassigned instruction op (discovered by MemorySanitizer) + - leds: pwm: Disable PWM when going to suspend + - ovl: remove upper umask handling from ovl_create_upper() + - PCI: of_property: Return error for int_map allocation failure + - VMCI: Fix an error handling path in vmci_guest_probe_device() + - dt-bindings: pinctrl: mediatek: mt7622: fix array properties + - pinctrl: qcom: pinctrl-sm7150: Fix sdc1 and ufs special pins regs + - watchdog: cpu5wdt.c: Fix use-after-free bug caused by cpu5wdt_trigger + - watchdog: bd9576: Drop "always-running" property + - watchdog: sa1100: Fix PTR_ERR_OR_ZERO() vs NULL check in sa1100dog_probe() + - dt-bindings: phy: qcom,sc8280xp-qmp-ufs-phy: fix msm899[68] power-domains + - dt-bindings: phy: qcom,usb-snps-femto-v2: use correct fallback for sc8180x + - dmaengine: idxd: Avoid unnecessary destruction of file_ida + - usb: gadget: u_audio: Fix race condition use of controls after free during + gadget unbind. + - usb: gadget: u_audio: Clear uac pointer when freed. + - stm class: Fix a double free in stm_register_device() + - ppdev: Add an error check in register_device + - i2c: cadence: Avoid fifo clear after start + - i2c: synquacer: Fix an error handling path in synquacer_i2c_probe() + - perf bench internals inject-build-id: Fix trap divide when collecting just + one DSO + - perf ui browser: Don't save pointer to stack memory + - extcon: max8997: select IRQ_DOMAIN instead of depending on it + - dt-bindings: spmi: hisilicon,hisi-spmi-controller: fix binding references + - PCI/EDR: Align EDR_PORT_DPC_ENABLE_DSM with PCI Firmware r3.3 + - PCI/EDR: Align EDR_PORT_LOCATE_DSM with PCI Firmware r3.3 + - f2fs: support printk_ratelimited() in f2fs_printk() + - f2fs: use BLKS_PER_SEG, BLKS_PER_SEC, and SEGS_PER_SEC + - f2fs: separate f2fs_gc_range() to use GC for a range + - f2fs: kill heap-based allocation + - f2fs: support file pinning for zoned devices + - f2fs: fix block migration when section is not aligned to pow2 + - perf ui browser: Avoid SEGV on title + - perf report: Avoid SEGV in report__setup_sample_type() + - perf thread: Fixes to thread__new() related to initializing comm + - perf symbols: Fix ownership of string in dso__load_vmlinux() + - f2fs: compress: fix to update i_compr_blocks correctly + - f2fs: deprecate io_bits + - f2fs: introduce get_available_block_count() for cleanup + - f2fs: compress: fix error path of inc_valid_block_count() + - f2fs: compress: fix to cover {reserve,release}_compress_blocks() w/ cp_rwsem + lock + - f2fs: fix to release node block count in error path of f2fs_new_node_page() + - f2fs: compress: don't allow unaligned truncation on released compress inode + - serial: sh-sci: protect invalidating RXDMA on shutdown + - libsubcmd: Fix parse-options memory leak + - perf daemon: Fix file leak in daemon_session__control + - f2fs: fix to add missing iput() in gc_data_segment() + - usb: fotg210: Add missing kernel doc description + - perf stat: Don't display metric header for non-leader uncore events + - perf tools: Use pmus to describe type from attribute + - perf tools: Add/use PMU reverse lookup from config to name + - perf pmu: Assume sysfs events are always the same case + - perf pmu: Count sys and cpuid JSON events separately + - LoongArch: Fix callchain parse error with kernel tracepoint events again + - s390/vdso64: filter out munaligned-symbols flag for vdso + - s390/vdso: Generate unwind information for C modules + - s390/vdso: Create .build-id links for unstripped vdso files + - s390/vdso: Use standard stack frame layout + - s390/ipl: Fix incorrect initialization of len fields in nvme reipl block + - s390/ipl: Fix incorrect initialization of nvme dump block + - s390/boot: Remove alt_stfle_fac_list from decompressor + - dt-bindings: PCI: rockchip,rk3399-pcie: Add missing maxItems to ep-gpios + - gpiolib: acpi: Fix failed in acpi_gpiochip_find() by adding parent node + match + - eventfs: Do not differentiate the toplevel events directory + - eventfs: Create eventfs_root_inode to store dentry + - eventfs/tracing: Add callback for release of an eventfs_inode + - eventfs: Free all of the eventfs_inode after RCU + - eventfs: Have "events" directory get permissions from its parent + - dt-bindings: adc: axi-adc: update bindings for backend framework + - dt-bindings: adc: axi-adc: add clocks property + - Input: ims-pcu - fix printf string overflow + - mmc: sdhci_am654: Add tuning algorithm for delay chain + - mmc: sdhci_am654: Write ITAPDLY for DDR52 timing + - mmc: sdhci_am654: Add OTAP/ITAP delay enable + - mmc: sdhci_am654: Add ITAPDLYSEL in sdhci_j721e_4bit_set_clock + - mmc: sdhci_am654: Fix ITAPDLY for HS400 timing + - Input: pm8xxx-vibrator - correct VIB_MAX_LEVELS calculation + - media: v4l: Don't turn on privacy LED if streamon fails + - media: ov2680: Clear the 'ret' variable on success + - media: ov2680: Allow probing if link-frequencies is absent + - media: ov2680: Do not fail if data-lanes property is absent + - drm/msm/dsi: Print dual-DSI-adjusted pclk instead of original mode pclk + - drm/msm/dpu: Always flush the slave INTF on the CTL + - drm/mediatek: dp: Fix mtk_dp_aux_transfer return value + - drm/meson: gate px_clk when setting rate + - um: Fix return value in ubd_init() + - um: vector: fix bpfflash parameter evaluation + - fs/ntfs3: Check 'folio' pointer for NULL + - fs/ntfs3: Use 64 bit variable to avoid 32 bit overflow + - fs/ntfs3: Use variable length array instead of fixed size + - drm/msm/dpu: Add callback function pointer check before its call + - drm/bridge: tc358775: fix support for jeida-18 and jeida-24 + - media: stk1160: fix bounds checking in stk1160_copy_video() + - Input: cyapa - add missing input core locking to suspend/resume functions + - drm/amdgpu: init microcode chip name from ip versions + - drm/amdgpu: Fix buffer size in gfx_v9_4_3_init_ cp_compute_microcode() and + rlc_microcode() + - media: mediatek: vcodec: fix possible unbalanced PM counter + - tools/arch/x86/intel_sdsi: Fix maximum meter bundle length + - tools/arch/x86/intel_sdsi: Fix meter_show display + - tools/arch/x86/intel_sdsi: Fix meter_certificate decoding + - platform/x86: thinkpad_acpi: Take hotkey_mutex during hotkey_exit() + - media: flexcop-usb: fix sanity check of bNumEndpoints + - powerpc/pseries: Add failure related checks for h_get_mpp and h_get_ppp + - um: Fix the -Wmissing-prototypes warning for __switch_mm + - um: Fix the -Wmissing-prototypes warning for get_thread_reg + - um: Fix the declaration of kasan_map_memory + - cxl/trace: Correct DPA field masks for general_media & dram events + - cxl/region: Fix cxlr_pmem leaks + - media: sunxi: a83-mips-csi2: also select GENERIC_PHY + - media: cec: cec-adap: always cancel work in cec_transmit_msg_fh + - media: cec: cec-api: add locking in cec_release() + - media: cec: core: avoid recursive cec_claim_log_addrs + - media: cec: core: avoid confusing "transmit timed out" message + - Revert "drm/bridge: ti-sn65dsi83: Fix enable error path" + - drm: zynqmp_dpsub: Always register bridge + - selftests/powerpc/dexcr: Add -no-pie to hashchk tests + - drm/msm/a6xx: Avoid a nullptr dereference when speedbin setting fails + - ASoC: tas2781: Fix a warning reported by robot kernel test + - null_blk: Fix the WARNING: modpost: missing MODULE_DESCRIPTION() + - ALSA: hda/cs_dsp_ctl: Use private_free for control cleanup + - ALSA: hda: cs35l56: Fix lifetime of cs_dsp instance + - ASoC: mediatek: mt8192: fix register configuration for tdm + - drm/nouveau: use tile_mode and pte_kind for VM_BIND bo allocations + - blk-cgroup: fix list corruption from resetting io stat + - blk-cgroup: fix list corruption from reorder of WRITE ->lqueued + - blk-cgroup: Properly propagate the iostat update up the hierarchy + - regulator: bd71828: Don't overwrite runtime voltages + - xen/x86: add extra pages to unpopulated-alloc if available + - perf/arm-dmc620: Fix lockdep assert in ->event_init() + - x86/kconfig: Select ARCH_WANT_FRAME_POINTERS again when + UNWINDER_FRAME_POINTER=y + - [Config] Update CONFIG_ARCH_WANT_FRAME_POINTERS + - net: Always descend into dsa/ folder with CONFIG_NET_DSA enabled + - ipv6: sr: fix missing sk_buff release in seg6_input_core + - selftests: net: kill smcrouted in the cleanup logic in amt.sh + - nfc: nci: Fix uninit-value in nci_rx_work + - ASoC: tas2552: Add TX path for capturing AUDIO-OUT data + - ASoC: tas2781: Fix wrong loading calibrated data sequence + - NFSv4: Fixup smatch warning for ambiguous return + - nfs: keep server info for remounts + - sunrpc: fix NFSACL RPC retry on soft mount + - rpcrdma: fix handling for RDMA_CM_EVENT_DEVICE_REMOVAL + - regulator: pickable ranges: don't always cache vsel + - regulator: tps6287x: Force writing VSEL bit + - af_unix: Update unix_sk(sk)->oob_skb under sk_receive_queue lock. + - ipv6: sr: fix memleak in seg6_hmac_init_algo + - regulator: tps6594-regulator: Correct multi-phase configuration + - tcp: Fix shift-out-of-bounds in dctcp_update_alpha(). + - pNFS/filelayout: fixup pNfs allocation modes + - openvswitch: Set the skbuff pkt_type for proper pmtud support. + - arm64: asm-bug: Add .align 2 to the end of __BUG_ENTRY + - rv: Update rv_en(dis)able_monitor doc to match kernel-doc + - net: lan966x: Remove ptp traps in case the ptp is not enabled. + - virtio: delete vq in vp_find_vqs_msix() when request_irq() fails + - i3c: master: svc: change ENXIO to EAGAIN when IBI occurs during start frame + - Revert "ixgbe: Manual AN-37 for troublesome link partners for X550 SFI" + - net: fec: avoid lock evasion when reading pps_enable + - tls: fix missing memory barrier in tls_init + - net: relax socket state check at accept time. + - nfc: nci: Fix handling of zero-length payload packets in nci_rx_work() + - drivers/xen: Improve the late XenStore init protocol + - ice: Interpret .set_channels() input differently + - kasan, fortify: properly rename memintrinsics + - tracing/probes: fix error check in parse_btf_field() + - tpm_tis_spi: Account for SPI header when allocating TPM SPI xfer buffer + - netfilter: nfnetlink_queue: acquire rcu_read_lock() in + instance_destroy_rcu() + - netfilter: ipset: Add list flush to cancel_gc + - netfilter: nft_payload: restore vlan q-in-q match support + - spi: Don't mark message DMA mapped when no transfer in it is + - dma-mapping: benchmark: fix up kthread-related error handling + - dma-mapping: benchmark: fix node id validation + - dma-mapping: benchmark: handle NUMA_NO_NODE correctly + - nvme-multipath: fix io accounting on failover + - nvmet: fix ns enable/disable possible hang + - drm/amd/display: Enable colorspace property for MST connectors + - net: phy: micrel: set soft_reset callback to genphy_soft_reset for KSZ8061 + - net/mlx5: Lag, do bond only if slaves agree on roce state + - net/mlx5: Fix MTMP register capability offset in MCAM register + - net/mlx5: Use mlx5_ipsec_rx_status_destroy to correctly delete status rules + - net/mlx5e: Fix IPsec tunnel mode offload feature check + - net/mlx5e: Use rx_missed_errors instead of rx_dropped for reporting buffer + exhaustion + - net/mlx5e: Fix UDP GSO for encapsulated packets + - dma-buf/sw-sync: don't enable IRQ from sync_print_obj() + - bpf: Fix potential integer overflow in resolve_btfids + - ALSA: jack: Use guard() for locking + - ALSA: core: Remove debugfs at disconnection + - ALSA: hda/realtek: Adjust G814JZR to use SPI init for amp + - enic: Validate length of nl attributes in enic_set_vf_port + - af_unix: Annotate data-race around unix_sk(sk)->addr. + - af_unix: Read sk->sk_hash under bindlock during bind(). + - Octeontx2-pf: Free send queue buffers incase of leaf to inner + - net: usb: smsc95xx: fix changing LED_SEL bit value updated from EEPROM + - ASoC: cs42l43: Only restrict 44.1kHz for the ASP + - bpf: Allow delete from sockmap/sockhash only if update is allowed + - net:fec: Add fec_enet_deinit() + - net: micrel: Fix lan8841_config_intr after getting out of sleep mode + - ice: fix accounting if a VLAN already exists + - selftests: mptcp: simult flows: mark 'unbalanced' tests as flaky + - selftests: mptcp: add ms units for tc-netem delay + - selftests: mptcp: join: mark 'fail' tests as flaky + - ALSA: seq: Fix missing bank setup between MIDI1/MIDI2 UMP conversion + - ALSA: seq: Don't clear bank selection at event -> UMP MIDI2 conversion + - net: ti: icssg-prueth: Fix start counter for ft1 filter + - netfilter: nft_payload: skbuff vlan metadata mangle support + - netfilter: tproxy: bail out if IP has been disabled on the device + - netfilter: nft_fib: allow from forward/input without iif selector + - net/sched: taprio: make q->picos_per_byte available to fill_sched_entry() + - net/sched: taprio: extend minimum interval restriction to entire cycle too + - kconfig: fix comparison to constant symbols, 'm', 'n' + - drm/i915/guc: avoid FIELD_PREP warning + - kheaders: use `command -v` to test for existence of `cpio` + - spi: stm32: Don't warn about spurious interrupts + - net: dsa: microchip: fix RGMII error in KSZ DSA driver + - net: ena: Reduce lines with longer column width boundary + - net: ena: Fix redundant device NUMA node override + - ipvlan: Dont Use skb->sk in ipvlan_process_v{4,6}_outbound + - ALSA: seq: Fix yet another spot for system message conversion + - powerpc/pseries/lparcfg: drop error message from guest name lookup + - drm/panel: sitronix-st7789v: fix timing for jt240mhqs_hwt_ek_e3 panel + - drm/panel: sitronix-st7789v: tweak timing for jt240mhqs_hwt_ek_e3 panel + - drm/panel: sitronix-st7789v: fix display size for jt240mhqs_hwt_ek_e3 panel + - hwmon: (intel-m10-bmc-hwmon) Fix multiplier for N6000 board power sensor + - hwmon: (shtc1) Fix property misspelling + - ALSA: seq: ump: Fix swapped song position pointer data + - ALSA: timer: Set lower bound of start tick time + - x86/efistub: Omit physical KASLR when memory reservations exist + - efi: libstub: only free priv.runtime_map when allocated + - x86/pci: Skip early E820 check for ECAM region + - KVM: x86: Don't advertise guest.MAXPHYADDR as host.MAXPHYADDR in CPUID + - genirq/cpuhotplug, x86/vector: Prevent vector leak during CPU offline + - platform/x86/intel/tpmi: Handle error from tpmi_process_info() + - platform/x86/intel-uncore-freq: Don't present root domain on error + - perf sched timehist: Fix -g/--call-graph option failure + - f2fs: write missing last sum blk of file pinning section + - f2fs: use f2fs_{err,info}_ratelimited() for cleanup + - SUNRPC: Fix loop termination condition in gss_free_in_token_pages() + - riscv: prevent pt_regs corruption for secondary idle threads + - riscv: stacktrace: fixed walk_stackframe() + - perf build: Fix out of tree build related to installation of sysreg-defs + - dt-bindings: pinctrl: qcom: update functions to match with driver + - usb: typec: ucsi: allow non-partner GET_PDOS for Qualcomm devices + - perf report: Fix PAI counter names for s390 virtual machines + - PCI: dwc: ep: Fix DBI access failure for drivers requiring refclk from host + - perf map: Remove kernel map before updating start and end addresses + - riscv: dts: starfive: visionfive 2: Remove non-existing I2S hardware + - pinctrl: renesas: rzg2l: Limit 2.5V power supply to Ethernet interfaces + - riscv: Flush the instruction cache during SMP bringup + - usb: xhci: check if 'requested segments' exceeds ERST capacity + - spmi: pmic-arb: Replace three IS_ERR() calls by null pointer checks in + spmi_pmic_arb_probe() + - perf symbols: Remove map from list before updating addresses + - perf symbols: Update kcore map before merging in remaining symbols + - s390/ftrace: Use unwinder instead of __builtin_return_address() + - s390/stacktrace: Merge perf_callchain_user() and arch_stack_walk_user() + - s390/stacktrace: Skip first user stack frame + - s390/stacktrace: Improve detection of invalid instruction pointers + - s390/vdso: Introduce and use struct stack_frame_vdso_wrapper + - s390/stackstrace: Detect vdso stack frames + - s390/ap: Fix bind complete udev event sent after each AP bus scan + - ocfs2: correctly use ocfs2_find_next_zero_bit() + - mailbox: mtk-cmdq: Fix pm_runtime_get_sync() warning in mbox shutdown + - Input: ioc3kbd - add device table + - phy: qcom: qmp-combo: fix sm8650 voltage swing table + - media: ti: j721e-csi2rx: Fix races while restarting DMA + - drm/msm/dpu: Allow configuring multiple active DSC blocks + - drm: Make drivers depends on DRM_DW_HDMI + - [Config] Drivers now depend on DRM_DW_HDMI + - string: Prepare to merge strscpy_kunit.c into string_kunit.c + - string: Prepare to merge strcat KUnit tests into string_kunit.c + - drm/msm/adreno: fix CP cycles stat retrieval on a7xx + - printk: Fix LOG_CPU_MAX_BUF_SHIFT when BASE_SMALL is enabled + - powerpc/bpf/32: Fix failing test_bpf tests + - KVM: PPC: Book3S HV nestedv2: Cancel pending DEC exception + - KVM: PPC: Book3S HV nestedv2: Fix an error handling path in + gs_msg_ops_kvmhv_nestedv2_config_fill_info() + - KVM: arm64: Destroy mpidr_data for 'late' vCPU creation + - Bluetooth: ISO: Handle PA sync when no BIGInfo reports are generated + - Bluetooth: L2CAP: Fix div-by-zero in l2cap_le_flowctl_init() + - ubsan: Restore dependency on ARCH_HAS_UBSAN + - selftests: forwarding: Have RET track kselftest framework constants + - selftests: forwarding: Convert log_test() to recognize RET values + - selftests: net: Unify code of busywait() and slowwait() + - selftests/net: use tc rule to filter the na packet + - virtio_balloon: Give the balloon its own wakeup source + - riscv: cpufeature: Fix thead vector hwcap removal + - riscv: cpufeature: Fix extension subset checking + - riscv: selftests: Add hwprobe binaries to .gitignore + - idpf: Interpret .set_channels() input differently + - null_blk: fix null-ptr-dereference while configuring 'power' and + 'submit_queues' + - netfs: Fix setting of BDP_ASYNC from iocb flags + - cifs: Set zero_point in the copy_file_range() and remap_file_range() + - cifs: Fix missing set of remote_i_size + - selftests: net: lib: set 'i' as local + - nvme: fix multipath batched completion accounting + - netkit: Fix setting mac address in l2 mode + - netkit: Fix pkt_type override upon netkit pass verdict + - null_blk: Fix return value of nullb_device_power_store() + - idpf: don't enable NAPI and interrupts prior to allocating Rx buffers + - selftests: mptcp: join: mark 'fastclose' tests as flaky + - drm/xe: Add dbg messages on the suspend resume functions. + - drm/xe: check pcode init status only on root gt of root tile + - drm/xe: Change pcode timeout to 50msec while polling again + - drm/xe: Only use reserved BCS instances for usm migrate exec queue + - sd: also set max_user_sectors when setting max_sectors + - block: stack max_user_sectors + - ipv6: introduce dst_rt6_info() helper + - inet: introduce dst_rtable() helper + - net: fix __dst_negative_advice() race + - ice: fix 200G PHY types to link speed mapping + - x86/topology/intel: Unlock CPUID before evaluating anything + - Upstream stable to v6.6.33, v6.9.4 + + * Reenable CONFIG_UBSAN for noble (LP: #2076650) + - ubsan: Remove CONFIG_UBSAN_SANITIZE_ALL + - [Config] Remove CONFIG_UBSAN_SANITIZE_ALL + + * Dangling symlink to linux-lib-rust when Rust is disabled (LP: #2072592) + - [Packaging] Check do_lib_rust before linking Rust lib files + + * kdump doesn't work with UEFI secure boot and kernel lockdown enabled on + ARM64 (LP: #2033007) + - [Config]: Enable CONFIG_KEXEC_IMAGE_VERIFY_SIG on arm64 + + * net/sched: Fix conntrack use-after-free (LP: #2073092) + - net/sched: Fix UAF when resolving a clash + + * No sound on Huawei Matebook D14 AMD since Linux 6.8.0-38 [regression] + (LP: #2073049) + - ASoC: amd: acp: fix for acp platform device creation failure + + * i915: Fixup regressions introduced with enabling single CCS engine + (LP: #2072755) + - drm/i915/gt: Fix CCS id's calculation for CCS mode setting + + * [Ubuntu 24.04] FW1060.00 (NH1060_026) sosreport is running to Kernel OOPS + crash (LP: #2070358) + - nfsd: initialise nfsd_info.mutex early. + + * 6.8 generic & amdpgu / polaris (LP: #2072428) + - drm/amdgpu: Adjust logic in amdgpu_device_partner_bandwidth() + + * md: nvme over tcp with a striped underlying md raid device leads to data + corruption (LP: #2075110) + - md/md-bitmap: fix writing non bitmap pages + + * Linux 6.8 fails to boot on ARM64 if any param is more than 146 chars + (LP: #2069534) + - SAUCE: arm64: v6.8: cmdline param >= 146 chars kills kernel + + * CVE-2024-39484 + - mmc: davinci: Don't strip remove function when driver is builtin + + * CVE-2024-39292 + - um: Add winch to winch_handlers before registering winch IRQ + + * Miscellaneous upstream changes + - bnx2x: Fix multiple UBSAN array-index-out-of-bounds + + -- Roxana Nicolescu Tue, 13 Aug 2024 12:20:36 +0200 + +linux (6.8.0-40.40) noble; urgency=medium + + * noble/linux: 6.8.0-40.40 -proposed tracker (LP: #2072201) + + * FPS of glxgear with fullscreen is too low on MTL platform (LP: #2069380) + - drm/i915: Bypass LMEMBAR/GTTMMADR for MTL stolen memory access + + * a critical typo in the code managing the ASPM settings for PCI Express + devices (LP: #2071889) + - PCI/ASPM: Restore parent state to parent, child state to child + + * [UBUNTU 24.04] IOMMU DMA mode changed in kernel config causes massive + throughput degradation for PCI-related network workloads (LP: #2071471) + - [Config] Set IOMMU_DEFAULT_DMA_STRICT=n and IOMMU_DEFAULT_DMA_LAZY=yes for + s390x + + * UBSAN: array-index-out-of-bounds in + /build/linux-D15vQj/linux-6.5.0/drivers/md/bcache/bset.c:1098:3 + (LP: #2039368) + - bcache: fix variable length array abuse in btree_iter + + * Mute/mic LEDs and speaker no function on EliteBook 645/665 G11 + (LP: #2071296) + - ALSA: hda/realtek: fix mute/micmute LEDs don't work for EliteBook 645/665 + G11. + + * failed to enable IPU6 camera sensor on kernel >= 6.8: ivsc_ace + intel_vsc-5db76cf6-0a68-4ed6-9b78-0361635e2447: switch camera to host + failed: -110 (LP: #2067364) + - mei: vsc: Don't stop/restart mei device during system suspend/resume + - SAUCE: media: ivsc: csi: don't count privacy on as error + - SAUCE: media: ivsc: csi: add separate lock for v4l2 control handler + - SAUCE: media: ivsc: csi: remove privacy status in struct mei_csi + - SAUCE: mei: vsc: Enhance IVSC chipset stability during warm reboot + - SAUCE: mei: vsc: Enhance SPI transfer of IVSC rom + - SAUCE: mei: vsc: Utilize the appropriate byte order swap function + - SAUCE: mei: vsc: Prevent timeout error with added delay post-firmware + download + + * failed to probe camera sensor on Dell XPS 9315: ov01a10 i2c-OVTI01A0:00: + failed to check hwcfg: -22 (LP: #2070251) + - ACPI: utils: Make acpi_handle_path() not static + - ACPI: property: Ignore bad graph port nodes on Dell XPS 9315 + - ACPI: property: Polish ignoring bad data nodes + - ACPI: scan: Ignore camera graph port nodes on all Dell Tiger, Alder and + Raptor Lake models + + * Update amd_sfh for AMD strix series (LP: #2058331) + - HID: amd_sfh: Increase sensor command timeout + - HID: amd_sfh: Improve boot time when SFH is available + - HID: amd_sfh: Extend MP2 register access to SFH + - HID: amd_sfh: Set the AMD SFH driver to depend on x86 + + * RFIM and SAGV Linux Support for G10 models (LP: #2070158) + - drm/i915/display: Add meaningful traces for QGV point info error handling + - drm/i915/display: Extract code required to calculate max qgv/psf gv point + - drm/i915/display: extract code to prepare qgv points mask + - drm/i915/display: Disable SAGV on bw init, to force QGV point recalculation + - drm/i915/display: handle systems with duplicate psf gv points + - drm/i915/display: force qgv check after the hw state readout + + * Update amd-pmf for AMD strix series (LP: #2058330) + - platform/x86/amd/pmf: Differentiate PMF ACPI versions + - platform/x86/amd/pmf: Disable debugfs support for querying power thermals + - platform/x86/amd/pmf: Add support to get sbios requests in PMF driver + - platform/x86/amd/pmf: Add support to notify sbios heart beat event + - platform/x86/amd/pmf: Add support to get APTS index numbers for static + slider + - platform/x86/amd/pmf: Add support to get sps default APTS index values + - platform/x86/amd/pmf: Update sps power thermals according to the platform- + profiles + + * noble:linux: ADT ubuntu-regression-suite misses fakeroot dependency + (LP: #2070042) + - [DEP-8] Add missing fakeroot dependency + + * Noble update: v6.8.12 upstream stable release (LP: #2071621) + - sunrpc: use the struct net as the svc proc private + - x86/tsc: Trust initial offset in architectural TSC-adjust MSRs + - selftests/ftrace: Fix BTFARG testcase to check fprobe is enabled correctly + - ftrace: Fix possible use-after-free issue in ftrace_location() + - Revert "arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD" + - arm64/fpsimd: Avoid erroneous elide of user state reload + - Reapply "arm64: fpsimd: Implement lazy restore for kernel mode FPSIMD" + - tty: n_gsm: fix missing receive state reset after mode switch + - speakup: Fix sizeof() vs ARRAY_SIZE() bug + - serial: sc16is7xx: fix bug in sc16is7xx_set_baud() when using prescaler + - serial: 8250_bcm7271: use default_mux_rate if possible + - serial: 8520_mtk: Set RTS on shutdown for Rx in-band wakeup + - Input: try trimming too long modalias strings + - io_uring: fail NOP if non-zero op flags is passed in + - Revert "r8169: don't try to disable interrupts if NAPI is, scheduled + already" + - r8169: Fix possible ring buffer corruption on fragmented Tx packets. + - ring-buffer: Fix a race between readers and resize checks + - net: mana: Fix the extra HZ in mana_hwc_send_request + - tools/latency-collector: Fix -Wformat-security compile warns + - tools/nolibc/stdlib: fix memory error in realloc() + - net: ti: icssg_prueth: Fix NULL pointer dereference in prueth_probe() + - net: lan966x: remove debugfs directory in probe() error path + - net: smc91x: Fix m68k kernel compilation for ColdFire CPU + - nilfs2: fix use-after-free of timer for log writer thread + - nilfs2: fix unexpected freezing of nilfs_segctor_sync() + - nilfs2: fix potential hang in nilfs_detach_log_writer() + - fs/ntfs3: Remove max link count info display during driver init + - fs/ntfs3: Taking DOS names into account during link counting + - fs/ntfs3: Fix case when index is reused during tree transformation + - fs/ntfs3: Break dir enumeration if directory contents error + - ksmbd: avoid to send duplicate oplock break notifications + - ksmbd: ignore trailing slashes in share paths + - ALSA: core: Fix NULL module pointer assignment at card init + - ALSA: Fix deadlocks with kctl removals at disconnection + - KEYS: asymmetric: Add missing dependency on CRYPTO_SIG + - [Config] updateconfigs for CRYPTO_SIG + - KEYS: asymmetric: Add missing dependencies of FIPS_SIGNATURE_SELFTEST + - HID: nintendo: Fix N64 controller being identified as mouse + - dmaengine: xilinx: xdma: Clarify kdoc in XDMA driver + - wifi: mac80211: don't use rate mask for scanning + - wifi: mac80211: ensure beacon is non-S1G prior to extracting the beacon + timestamp field + - wifi: cfg80211: fix the order of arguments for trace events of the tx_rx_evt + class + - dt-bindings: rockchip: grf: Add missing type to 'pcie-phy' node + - HID: mcp-2221: cancel delayed_work only when CONFIG_IIO is enabled + - net: usb: qmi_wwan: add Telit FN920C04 compositions + - drm/amd/display: Set color_mgmt_changed to true on unsuspend + - drm/amdgpu: Update BO eviction priorities + - drm/amd/pm: Restore config space after reset + - drm/amdkfd: Add VRAM accounting for SVM migration + - drm/amdgpu: Fix the ring buffer size for queue VM flush + - Revert "net: txgbe: fix i2c dev name cannot match clkdev" + - Revert "net: txgbe: fix clk_name exceed MAX_DEV_ID limits" + - cpu: Ignore "mitigations" kernel parameter if CPU_MITIGATIONS=n + - LoongArch: Lately init pmu after smp is online + - drm/etnaviv: fix tx clock gating on some GC7000 variants + - selftests: sud_test: return correct emulated syscall value on RISC-V + - riscv: thead: Rename T-Head PBMT to MAE + - [Config] updateconfigs for ERRATA_THEAD_MAE + - riscv: T-Head: Test availability bit before enabling MAE errata + - sched/isolation: Fix boot crash when maxcpus < first housekeeping CPU + - ASoC: Intel: bytcr_rt5640: Apply Asus T100TA quirk to Asus T100TAM too + - regulator: irq_helpers: duplicate IRQ name + - ALSA: hda: cs35l56: Exit cache-only after cs35l56_wait_for_firmware_boot() + - ASoC: SOF: ipc4-pcm: Use consistent name for snd_sof_pcm_stream pointer + - ASoC: SOF: ipc4-pcm: Use consistent name for sof_ipc4_timestamp_info pointer + - ASoC: SOF: ipc4-pcm: Introduce generic sof_ipc4_pcm_stream_priv + - ASoC: SOF: pcm: Restrict DSP D0i3 during S0ix to IPC3 + - ASoC: acp: Support microphone from device Acer 315-24p + - ASoC: rt5645: Fix the electric noise due to the CBJ contacts floating + - ASoC: dt-bindings: rt5645: add cbj sleeve gpio property + - ASoC: rt722-sdca: modify channel number to support 4 channels + - ASoC: rt722-sdca: add headset microphone vrefo setting + - regulator: qcom-refgen: fix module autoloading + - regulator: vqmmc-ipq4019: fix module autoloading + - ASoC: cs35l41: Update DSP1RX5/6 Sources for DSP config + - ASoC: rt715: add vendor clear control register + - ASoC: rt715-sdca: volume step modification + - KVM: selftests: Add test for uaccesses to non-existent vgic-v2 CPUIF + - Input: xpad - add support for ASUS ROG RAIKIRI + - btrfs: take the cleaner_mutex earlier in qgroup disable + - EDAC/versal: Do not register for NOC errors + - fpga: dfl-pci: add PCI subdevice ID for Intel D5005 card + - bpf, x86: Fix PROBE_MEM runtime load check + - ALSA: emu10k1: make E-MU FPGA writes potentially more reliable + - softirq: Fix suspicious RCU usage in __do_softirq() + - platform/x86: ISST: Add Grand Ridge to HPM CPU list + - ASoC: da7219-aad: fix usage of device_get_named_child_node() + - ASoC: cs35l56: fix usages of device_get_named_child_node() + - ALSA: hda: intel-dsp-config: harden I2C/I2S codec detection + - Input: amimouse - mark driver struct with __refdata to prevent section + mismatch + - drm/amdgpu: Fix VRAM memory accounting + - drm/amd/display: Ensure that dmcub support flag is set for DCN20 + - drm/amd/display: Add dtbclk access to dcn315 + - drm/amd/display: Allocate zero bw after bw alloc enable + - drm/amd/display: Add VCO speed parameter for DCN31 FPU + - drm/amd/display: Fix DC mode screen flickering on DCN321 + - drm/amd/display: Disable seamless boot on 128b/132b encoding + - drm/amdkfd: Flush the process wq before creating a kfd_process + - x86/mm: Remove broken vsyscall emulation code from the page fault code + - nvme: find numa distance only if controller has valid numa id + - nvmet-auth: return the error code to the nvmet_auth_host_hash() callers + - nvmet-auth: replace pr_debug() with pr_err() to report an error. + - nvme: cancel pending I/O if nvme controller is in terminal state + - nvmet-tcp: fix possible memory leak when tearing down a controller + - nvmet: fix nvme status code when namespace is disabled + - nvme-tcp: strict pdu pacing to avoid send stalls on TLS + - epoll: be better about file lifetimes + - nvmet: prevent sprintf() overflow in nvmet_subsys_nsid_exists() + - openpromfs: finish conversion to the new mount API + - crypto: bcm - Fix pointer arithmetic + - firmware: qcom: qcm: fix unused qcom_scm_qseecom_allowlist + - mm/slub, kunit: Use inverted data to corrupt kmem cache + - firmware: raspberrypi: Use correct device for DMA mappings + - ecryptfs: Fix buffer size for tag 66 packet + - nilfs2: fix out-of-range warning + - parisc: add missing export of __cmpxchg_u8() + - crypto: ccp - drop platform ifdef checks + - crypto: x86/nh-avx2 - add missing vzeroupper + - crypto: x86/sha256-avx2 - add missing vzeroupper + - crypto: x86/sha512-avx2 - add missing vzeroupper + - s390/cio: fix tracepoint subchannel type field + - io_uring: use the right type for work_llist empty check + - rcu-tasks: Fix show_rcu_tasks_trace_gp_kthread buffer overflow + - rcu: Fix buffer overflow in print_cpu_stall_info() + - ARM: configs: sunxi: Enable DRM_DW_HDMI + - jffs2: prevent xattr node from overflowing the eraseblock + - libfs: Re-arrange locking in offset_iterate_dir() + - libfs: Define a minimum directory offset + - libfs: Add simple_offset_empty() + - maple_tree: Add mtree_alloc_cyclic() + - libfs: Convert simple directory offsets to use a Maple Tree + - libfs: Fix simple_offset_rename_exchange() + - libfs: Add simple_offset_rename() API + - shmem: Fix shmem_rename2() + - io-wq: write next_work before dropping acct_lock + - mm/userfaultfd: Do not place zeropages when zeropages are disallowed + - s390/mm: Re-enable the shared zeropage for !PV and !skeys KVM guests + - crypto: octeontx2 - add missing check for dma_map_single + - crypto: qat - improve error message in adf_get_arbiter_mapping() + - crypto: qat - improve error logging to be consistent across features + - soc: qcom: pmic_glink: don't traverse clients list without a lock + - soc: qcom: pmic_glink: notify clients about the current state + - firmware: qcom: scm: Fix __scm and waitq completion variable initialization + - soc: mediatek: cmdq: Fix typo of CMDQ_JUMP_RELATIVE + - null_blk: Fix missing mutex_destroy() at module removal + - crypto: qat - validate slices count returned by FW + - hwrng: stm32 - use logical OR in conditional + - hwrng: stm32 - put IP into RPM suspend on failure + - hwrng: stm32 - repair clock handling + - kunit/fortify: Fix mismatched kvalloc()/vfree() usage + - io_uring/net: remove dependency on REQ_F_PARTIAL_IO for sr->done_io + - io_uring/net: fix sendzc lazy wake polling + - soc: qcom: pmic_glink: Make client-lock non-sleeping + - lkdtm: Disable CFI checking for perms functions + - md: fix resync softlockup when bitmap size is less than array size + - crypto: qat - specify firmware files for 402xx + - block: refine the EOF check in blkdev_iomap_begin + - block: fix and simplify blkdevparts= cmdline parsing + - block: support to account io_ticks precisely + - wifi: ath10k: poll service ready message before failing + - wifi: brcmfmac: pcie: handle randbuf allocation failure + - wifi: ath11k: don't force enable power save on non-running vdevs + - bpftool: Fix missing pids during link show + - libbpf: Prevent null-pointer dereference when prog to load has no BTF + - wifi: ath12k: use correct flag field for 320 MHz channels + - wifi: mt76: mt7915: workaround too long expansion sparse warnings + - x86/boot: Ignore relocations in .notes sections in walk_relocs() too + - wifi: ieee80211: fix ieee80211_mle_basic_sta_prof_size_ok() + - wifi: iwlwifi: mvm: Do not warn on invalid link on scan complete + - wifi: iwlwifi: mvm: allocate STA links only for active links + - wifi: mac80211: don't select link ID if not provided in scan request + - wifi: iwlwifi: implement can_activate_links callback + - wifi: iwlwifi: mvm: fix active link counting during recovery + - wifi: iwlwifi: mvm: select STA mask only for active links + - wifi: iwlwifi: reconfigure TLC during HW restart + - wifi: iwlwifi: mvm: fix check in iwl_mvm_sta_fw_id_mask + - sched/fair: Add EAS checks before updating root_domain::overutilized + - ACPI: bus: Indicate support for _TFP thru _OSC + - ACPI: bus: Indicate support for more than 16 p-states thru _OSC + - ACPI: bus: Indicate support for the Generic Event Device thru _OSC + - ACPI: Fix Generic Initiator Affinity _OSC bit + - ACPI: bus: Indicate support for IRQ ResourceSource thru _OSC + - enetc: avoid truncating error message + - qed: avoid truncating work queue length + - mlx5: avoid truncating error message + - mlx5: stop warning for 64KB pages + - bitops: add missing prototype check + - dlm: fix user space lock decision to copy lvb + - wifi: carl9170: re-fix fortified-memset warning + - bpftool: Mount bpffs on provided dir instead of parent dir + - bpf: Pack struct bpf_fib_lookup + - bpf: prevent r10 register from being marked as precise + - x86/microcode/AMD: Avoid -Wformat warning with clang-15 + - scsi: ufs: qcom: Perform read back after writing reset bit + - scsi: ufs: qcom: Perform read back after writing REG_UFS_SYS1CLK_1US + - scsi: ufs: qcom: Perform read back after writing unipro mode + - scsi: ufs: qcom: Perform read back after writing CGC enable + - scsi: ufs: cdns-pltfrm: Perform read back after writing HCLKDIV + - scsi: ufs: core: Perform read back after writing UTP_TASK_REQ_LIST_BASE_H + - scsi: ufs: core: Perform read back after disabling interrupts + - scsi: ufs: core: Perform read back after disabling UIC_COMMAND_COMPL + - ACPI: LPSS: Advertise number of chip selects via property + - EDAC/skx_common: Allow decoding of SGX addresses + - locking/atomic/x86: Correct the definition of __arch_try_cmpxchg128() + - irqchip/alpine-msi: Fix off-by-one in allocation error path + - irqchip/loongson-pch-msi: Fix off-by-one on allocation error path + - ACPI: disable -Wstringop-truncation + - gfs2: Don't forget to complete delayed withdraw + - gfs2: Fix "ignore unlock failures after withdraw" + - arm64: Remove unnecessary irqflags alternative.h include + - x86/boot/64: Clear most of CR4 in startup_64(), except PAE, MCE and LA57 + - selftests/bpf: Fix umount cgroup2 error in test_sockmap + - tcp: increase the default TCP scaling ratio + - cpufreq: exit() callback is optional + - x86/pat: Introduce lookup_address_in_pgd_attr() + - x86/pat: Restructure _lookup_address_cpa() + - x86/pat: Fix W^X violation false-positives when running as Xen PV guest + - udp: Avoid call to compute_score on multiple sites + - openrisc: traps: Don't send signals to kernel mode threads + - cppc_cpufreq: Fix possible null pointer dereference + - wifi: iwlwifi: mvm: init vif works only once + - scsi: libsas: Fix the failure of adding phy with zero-address to port + - scsi: hpsa: Fix allocation size for Scsi_Host private data + - x86/purgatory: Switch to the position-independent small code model + - wifi: ath12k: fix out-of-bound access of qmi_invoke_handler() + - thermal/drivers/mediatek/lvts_thermal: Add coeff for mt8192 + - thermal/drivers/tsens: Fix null pointer dereference + - dt-bindings: thermal: loongson,ls2k-thermal: Add Loongson-2K0500 compatible + - dt-bindings: thermal: loongson,ls2k-thermal: Fix incorrect compatible + definition + - wifi: ath10k: Fix an error code problem in + ath10k_dbg_sta_write_peer_debug_trigger() + - gfs2: Remove ill-placed consistency check + - gfs2: Fix potential glock use-after-free on unmount + - gfs2: finish_xmote cleanup + - gfs2: do_xmote fixes + - thermal/debugfs: Avoid excessive updates of trip point statistics + - selftests/bpf: Fix a fd leak in error paths in open_netns + - scsi: ufs: core: mcq: Fix ufshcd_mcq_sqe_search() + - cpufreq: brcmstb-avs-cpufreq: ISO C90 forbids mixed declarations + - wifi: ath10k: populate board data for WCN3990 + - net: dsa: mv88e6xxx: Add support for model-specific pre- and post-reset + handlers + - net: dsa: mv88e6xxx: Avoid EEPROM timeout without EEPROM on 88E6250-family + switches + - tcp: avoid premature drops in tcp_add_backlog() + - thermal/debugfs: Create records for cdev states as they get used + - thermal/debugfs: Pass cooling device state to thermal_debug_cdev_add() + - pwm: sti: Prepare removing pwm_chip from driver data + - pwm: sti: Simplify probe function using devm functions + - drivers/perf: hisi_pcie: Fix out-of-bound access when valid event group + - drivers/perf: hisi: hns3: Fix out-of-bound access when valid event group + - drivers/perf: hisi: hns3: Actually use devm_add_action_or_reset() + - net: give more chances to rcu in netdev_wait_allrefs_any() + - macintosh/via-macii: Fix "BUG: sleeping function called from invalid + context" + - wifi: carl9170: add a proper sanity check for endpoints + - bpf: Fix verifier assumptions about socket->sk + - selftests/bpf: Run cgroup1_hierarchy test in own mount namespace + - wifi: ar5523: enable proper endpoint verification + - pwm: Drop useless member .of_pwm_n_cells of struct pwm_chip + - pwm: Let the of_xlate callbacks accept references without period + - pwm: Drop duplicate check against chip->npwm in of_pwm_xlate_with_flags() + - pwm: Reorder symbols in core.c + - pwm: Provide an inline function to get the parent device of a given chip + - pwm: meson: Change prototype of a few helpers to prepare further changes + - pwm: meson: Make use of pwmchip_parent() accessor + - pwm: meson: Add check for error from clk_round_rate() + - pwm: meson: Use mul_u64_u64_div_u64() for frequency calculating + - bpf: Add BPF_PROG_TYPE_CGROUP_SKB attach type enforcement in BPF_LINK_CREATE + - sh: kprobes: Merge arch_copy_kprobe() into arch_prepare_kprobe() + - Revert "sh: Handle calling csum_partial with misaligned data" + - wifi: mt76: mt7603: fix tx queue of loopback packets + - wifi: mt76: mt7603: add wpdma tx eof flag for PSE client reset + - wifi: mt76: mt7996: fix size of txpower MCU command + - wifi: mt76: mt7925: ensure 4-byte alignment for suspend & wow command + - wifi: mt76: mt7996: fix uninitialized variable in mt7996_irq_tasklet() + - wifi: mt76: mt7996: fix potential memory leakage when reading chip + temperature + - libbpf: Fix error message in attach_kprobe_multi + - wifi: nl80211: Avoid address calculations via out of bounds array indexing + - wifi: rtw89: wow: refine WoWLAN flows of HCI interrupts and low power mode + - selftests/binderfs: use the Makefile's rules, not Make's implicit rules + - selftests/resctrl: fix clang build failure: use LOCAL_HDRS + - selftests: default to host arch for LLVM builds + - kunit: Fix kthread reference + - kunit: unregister the device on error + - kunit: bail out early in __kunit_test_suites_init() if there are no suites + to test + - selftests/bpf: Fix pointer arithmetic in test_xdp_do_redirect + - HID: intel-ish-hid: ipc: Add check for pci_alloc_irq_vectors + - scsi: bfa: Ensure the copied buf is NUL terminated + - scsi: qedf: Ensure the copied buf is NUL terminated + - scsi: qla2xxx: Fix debugfs output for fw_resource_count + - gpio: nuvoton: Fix sgpio irq handle error + - x86/numa: Fix SRAT lookup of CFMWS ranges with numa_fill_memblks() + - wifi: mwl8k: initialize cmd->addr[] properly + - HID: amd_sfh: Handle "no sensors" in PM operations + - usb: aqc111: stop lying about skb->truesize + - net: usb: sr9700: stop lying about skb->truesize + - m68k: Fix spinlock race in kernel thread creation + - m68k: mac: Fix reboot hang on Mac IIci + - dm-delay: fix workqueue delay_timer race + - dm-delay: fix hung task introduced by kthread mode + - dm-delay: fix max_delay calculations + - ptp: ocp: fix DPLL functions + - net: ipv6: fix wrong start position when receive hop-by-hop fragment + - eth: sungem: remove .ndo_poll_controller to avoid deadlocks + - selftests: net: add missing config for amt.sh + - selftests: net: move amt to socat for better compatibility + - net: ethernet: mediatek: split tx and rx fields in mtk_soc_data struct + - net: ethernet: mediatek: use ADMAv1 instead of ADMAv2.0 on MT7981 and MT7986 + - ice: Fix package download algorithm + - net: ethernet: cortina: Locking fixes + - af_unix: Fix data races in unix_release_sock/unix_stream_sendmsg + - net: usb: smsc95xx: stop lying about skb->truesize + - net: openvswitch: fix overwriting ct original tuple for ICMPv6 + - ipv6: sr: add missing seg6_local_exit + - ipv6: sr: fix incorrect unregister order + - ipv6: sr: fix invalid unregister error path + - net/mlx5: Fix peer devlink set for SF representor devlink port + - net/mlx5: Reload only IB representors upon lag disable/enable + - net/mlx5: Add a timeout to acquire the command queue semaphore + - net/mlx5: Discard command completions in internal error + - s390/bpf: Emit a barrier for BPF_FETCH instructions + - riscv, bpf: make some atomic operations fully ordered + - ax25: Use kernel universal linked list to implement ax25_dev_list + - ax25: Fix reference count leak issues of ax25_dev + - ax25: Fix reference count leak issue of net_device + - dpll: fix return value check for kmemdup + - net: fec: remove .ndo_poll_controller to avoid deadlocks + - mptcp: SO_KEEPALIVE: fix getsockopt support + - mptcp: cleanup writer wake-up + - mptcp: avoid some duplicate code in socket option handling + - mptcp: implement TCP_NOTSENT_LOWAT support + - mptcp: cleanup SOL_TCP handling + - mptcp: fix full TCP keep-alive support + - net: stmmac: Offload queueMaxSDU from tc-taprio + - net: stmmac: est: Per Tx-queue error count for HLBF + - net: stmmac: Report taprio offload status + - net: stmmac: move the EST lock to struct stmmac_priv + - net: micrel: Fix receiving the timestamp in the frame for lan8841 + - Bluetooth: compute LE flow credits based on recvbuf space + - Bluetooth: qca: Fix error code in qca_read_fw_build_info() + - Bluetooth: ISO: Add hcon for listening bis sk + - Bluetooth: ISO: Clean up returns values in iso_connect_ind() + - Bluetooth: ISO: Make iso_get_sock_listen generic + - Bluetooth: Remove usage of the deprecated ida_simple_xx() API + - Bluetooth: hci_event: Remove code to removed CONFIG_BT_HS + - Bluetooth: HCI: Remove HCI_AMP support + - ice: make ice_vsi_cfg_rxq() static + - ice: make ice_vsi_cfg_txq() static + - overflow: Change DEFINE_FLEX to take __counted_by member + - Bluetooth: hci_conn, hci_sync: Use __counted_by() to avoid -Wfamnae warnings + - Bluetooth: hci_core: Fix not handling hdev->le_num_of_adv_sets=1 + - drm/bridge: Fix improper bridge init order with pre_enable_prev_first + - drm/ci: update device type for volteer devices + - drm/nouveau/dp: Fix incorrect return code in r535_dp_aux_xfer() + - drm/omapdrm: Fix console by implementing fb_dirty + - drm/omapdrm: Fix console with deferred ops + - printk: Let no_printk() use _printk() + - dev_printk: Add and use dev_no_printk() + - drm/lcdif: Do not disable clocks on already suspended hardware + - drm/dp: Don't attempt AUX transfers when eDP panels are not powered + - drm/panel: atna33xc20: Fix unbalanced regulator in the case HPD doesn't + assert + - drm/amd/display: Fix potential index out of bounds in color transformation + function + - drm/amd/display: Remove redundant condition in dcn35_calc_blocks_to_gate() + - ASoC: Intel: Disable route checks for Skylake boards + - ASoC: Intel: avs: ssm4567: Do not ignore route checks + - mtd: core: Report error if first mtd_otp_size() call fails in + mtd_otp_nvmem_add() + - mtd: rawnand: hynix: fixed typo + - drm/imagination: avoid -Woverflow warning + - ASoC: mediatek: Assign dummy when codec not specified for a DAI link + - drm/panel: ltk050h3146w: add MIPI_DSI_MODE_VIDEO to LTK050H3148W flags + - drm/panel: ltk050h3146w: drop duplicate commands from LTK050H3148W init + - fbdev: shmobile: fix snprintf truncation + - ASoC: kirkwood: Fix potential NULL dereference + - drm/meson: vclk: fix calculation of 59.94 fractional rates + - drm/mediatek: Add 0 size check to mtk_drm_gem_obj + - drm/mediatek: Init `ddp_comp` with devm_kcalloc() + - ASoC: SOF: Intel: hda-dai: fix channel map configuration for aggregated + dailink + - powerpc/fsl-soc: hide unused const variable + - ASoC: SOF: Intel: mtl: Correct rom_status_reg + - ASoC: SOF: Intel: lnl: Correct rom_status_reg + - ASoC: SOF: Intel: mtl: Disable interrupts when firmware boot failed + - ASoC: SOF: Intel: mtl: Implement firmware boot state check + - fbdev: sisfb: hide unused variables + - selftests: cgroup: skip test_cgcore_lesser_ns_open when cgroup2 mounted + without nsdelegate + - ASoC: Intel: avs: Restore stream decoupling on prepare + - ASoC: Intel: avs: Fix ASRC module initialization + - ASoC: Intel: avs: Fix potential integer overflow + - ASoC: Intel: avs: Test result of avs_get_module_entry() + - media: ngene: Add dvb_ca_en50221_init return value check + - staging: media: starfive: Remove links when unregistering devices + - media: rcar-vin: work around -Wenum-compare-conditional warning + - media: radio-shark2: Avoid led_names truncations + - drm: bridge: cdns-mhdp8546: Fix possible null pointer dereference + - platform/x86: xiaomi-wmi: Fix race condition when reporting key events + - drm/msm/dp: allow voltage swing / pre emphasis of 3 + - drm/msm/dp: Avoid a long timeout for AUX transfer if nothing connected + - media: ipu3-cio2: Request IRQ earlier + - media: dt-bindings: ovti,ov2680: Fix the power supply names + - media: i2c: et8ek8: Don't strip remove function when driver is builtin + - media: v4l2-subdev: Fix stream handling for crop API + - fbdev: sh7760fb: allow modular build + - media: atomisp: ssh_css: Fix a null-pointer dereference in + load_video_binaries + - drm/arm/malidp: fix a possible null pointer dereference + - drm: vc4: Fix possible null pointer dereference + - ASoC: tracing: Export SND_SOC_DAPM_DIR_OUT to its value + - drm/bridge: anx7625: Don't log an error when DSI host can't be found + - drm/bridge: icn6211: Don't log an error when DSI host can't be found + - drm/bridge: lt8912b: Don't log an error when DSI host can't be found + - drm/bridge: lt9611: Don't log an error when DSI host can't be found + - drm/bridge: lt9611uxc: Don't log an error when DSI host can't be found + - drm/bridge: tc358775: Don't log an error when DSI host can't be found + - drm/bridge: dpc3433: Don't log an error when DSI host can't be found + - drm/panel: novatek-nt35950: Don't log an error when DSI host can't be found + - drm/bridge: anx7625: Update audio status while detecting + - drm/panel: simple: Add missing Innolux G121X1-L03 format, flags, connector + - ALSA: hda: cs35l41: Remove Speaker ID for Lenovo Legion slim 7 16ARHA7 + - drm/mipi-dsi: use correct return type for the DSC functions + - media: uvcvideo: Add quirk for Logitech Rally Bar + - drm/rockchip: vop2: Do not divide height twice for YUV + - drm/edid: Parse topology block for all DispID structure v1.x + - media: cadence: csi2rx: configure DPHY before starting source stream + - clk: samsung: exynosautov9: fix wrong pll clock id value + - RDMA/mlx5: Uncacheable mkey has neither rb_key or cache_ent + - RDMA/mlx5: Change check for cacheable mkeys + - RDMA/mlx5: Adding remote atomic access flag to updatable flags + - clk: mediatek: pllfh: Don't log error for missing fhctl node + - iommu: Undo pasid attachment only for the devices that have succeeded + - RDMA/hns: Fix return value in hns_roce_map_mr_sg + - RDMA/hns: Fix deadlock on SRQ async events. + - RDMA/hns: Fix UAF for cq async event + - RDMA/hns: Fix GMV table pagesize + - RDMA/hns: Use complete parentheses in macros + - RDMA/hns: Modify the print level of CQE error + - clk: mediatek: mt8365-mm: fix DPI0 parent + - clk: rs9: fix wrong default value for clock amplitude + - clk: qcom: clk-alpha-pll: remove invalid Stromer register offset + - RDMA/rxe: Fix seg fault in rxe_comp_queue_pkt + - RDMA/rxe: Allow good work requests to be executed + - RDMA/rxe: Fix incorrect rxe_put in error path + - IB/mlx5: Use __iowrite64_copy() for write combining stores + - clk: renesas: r8a779a0: Fix CANFD parent clock + - clk: renesas: r9a07g043: Add clock and reset entry for PLIC + - lib/test_hmm.c: handle src_pfns and dst_pfns allocation failure + - mm/ksm: fix ksm exec support for prctl + - clk: qcom: dispcc-sm8450: fix DisplayPort clocks + - clk: qcom: dispcc-sm6350: fix DisplayPort clocks + - clk: qcom: dispcc-sm8550: fix DisplayPort clocks + - clk: qcom: dispcc-sm8650: fix DisplayPort clocks + - clk: qcom: mmcc-msm8998: fix venus clock issue + - x86/insn: Fix PUSH instruction in x86 instruction decoder opcode map + - x86/insn: Add VEX versions of VPDPBUSD, VPDPBUSDS, VPDPWSSD and VPDPWSSDS + - ext4: avoid excessive credit estimate in ext4_tmpfile() + - RDMA/mana_ib: Introduce helpers to create and destroy mana queues + - RDMA/mana_ib: Use struct mana_ib_queue for CQs + - RDMA/mana_ib: boundary check before installing cq callbacks + - virt: acrn: stop using follow_pfn + - drivers/virt/acrn: fix PFNMAP PTE checks in acrn_vm_ram_map() + - sunrpc: removed redundant procp check + - nfsd: don't create nfsv4recoverydir in nfsdfs when not used. + - ext4: fix potential unnitialized variable + - ext4: remove the redundant folio_wait_stable() + - clk: qcom: Fix SC_CAMCC_8280XP dependencies + - [Config] updateconfigs for SC_CAMCC_8280XP + - clk: qcom: Fix SM_GPUCC_8650 dependencies + - [Config] updateconfigs for SM_GPUCC_8650 + - clk: qcom: apss-ipq-pll: fix PLL rate for IPQ5018 + - of: module: add buffer overflow check in of_modalias() + - bnxt_re: avoid shift undefined behavior in bnxt_qplib_alloc_init_hwq + - SUNRPC: Fix gss_free_in_token_pages() + - selftests/damon/_damon_sysfs: check errors from nr_schemes file reads + - selftests/kcmp: remove unused open mode + - RDMA/IPoIB: Fix format truncation compilation errors + - RDMA/cma: Fix kmemleak in rdma_core observed during blktests nvme/rdma use + siw + - samples/landlock: Fix incorrect free in populate_ruleset_net + - tracing/user_events: Prepare find/delete for same name events + - tracing/user_events: Fix non-spaced field matching + - modules: Drop the .export_symbol section from the final modules + - net: bridge: xmit: make sure we have at least eth header len bytes + - selftests: net: bridge: increase IGMP/MLD exclude timeout membership + interval + - net: bridge: mst: fix vlan use-after-free + - net: qrtr: ns: Fix module refcnt + - selftests/net/lib: no need to record ns name if it already exist + - idpf: don't skip over ethtool tcp-data-split setting + - netrom: fix possible dead-lock in nr_rt_ioctl() + - af_packet: do not call packet_read_pending() from tpacket_destruct_skb() + - sched/fair: Allow disabling sched_balance_newidle with + sched_relax_domain_level + - sched/core: Fix incorrect initialization of the 'burst' parameter in + cpu_max_write() + - net: wangxun: fix to change Rx features + - net: wangxun: match VLAN CTAG and STAG features + - net: txgbe: move interrupt codes to a separate file + - net: txgbe: use irq_domain for interrupt controller + - net: txgbe: fix to control VLAN strip + - l2tp: fix ICMP error handling for UDP-encap sockets + - io_uring/net: ensure async prep handlers always initialize ->done_io + - pwm: Fix setting period with #pwm-cells = <1> and of_pwm_single_xlate() + - net: txgbe: fix to clear interrupt status after handling IRQ + - net: txgbe: fix GPIO interrupt blocking + - Linux 6.8.12 + + * Noble update: v6.8.11 upstream stable release (LP: #2070355) + - drm/amd/display: Fix division by zero in setup_dsc_config + - net: ks8851: Fix another TX stall caused by wrong ISR flag handling + - ice: pass VSI pointer into ice_vc_isvalid_q_id + - ice: remove unnecessary duplicate checks for VF VSI ID + - Bluetooth: L2CAP: Fix slab-use-after-free in l2cap_connect() + - Bluetooth: L2CAP: Fix div-by-zero in l2cap_le_flowctl_init() + - KEYS: trusted: Fix memory leak in tpm2_key_encode() + - erofs: get rid of erofs_fs_context + - erofs: reliably distinguish block based and fscache mode + - binder: fix max_thread type inconsistency + - usb: dwc3: Wait unconditionally after issuing EndXfer command + - net: usb: ax88179_178a: fix link status when link is set to down/up + - usb: typec: ucsi: displayport: Fix potential deadlock + - usb: typec: tipd: fix event checking for tps25750 + - usb: typec: tipd: fix event checking for tps6598x + - serial: kgdboc: Fix NMI-safety problems from keyboard reset code + - remoteproc: mediatek: Make sure IPI buffer fits in L2TCM + - KEYS: trusted: Do not use WARN when encode fails + - admin-guide/hw-vuln/core-scheduling: fix return type of PR_SCHED_CORE_GET + - docs: kernel_include.py: Cope with docutils 0.21 + - Docs/admin-guide/mm/damon/usage: fix wrong example of DAMOS filter matching + sysfs file + - block: add a disk_has_partscan helper + - block: add a partscan sysfs attribute for disks + - Linux 6.8.11 + + * Noble update: v6.8.10 upstream stable release (LP: #2070349) + - rust: module: place generated init_module() function in .init.text + - rust: macros: fix soundness issue in `module!` macro + - wifi: nl80211: don't free NULL coalescing rule + - pinctrl: pinctrl-aspeed-g6: Fix register offset for pinconf of GPIOR-T + - pinctrl/meson: fix typo in PDM's pin name + - pinctrl: core: delete incorrect free in pinctrl_enable() + - pinctrl: mediatek: paris: Fix PIN_CONFIG_INPUT_SCHMITT_ENABLE readback + - pinctrl: mediatek: paris: Rework support for + PIN_CONFIG_{INPUT,OUTPUT}_ENABLE + - sunrpc: add a struct rpc_stats arg to rpc_create_args + - nfs: expose /proc/net/sunrpc/nfs in net namespaces + - nfs: make the rpc_stat per net namespace + - nfs: Handle error of rpc_proc_register() in nfs_net_init(). + - pinctrl: baytrail: Fix selecting gpio pinctrl state + - power: rt9455: hide unused rt9455_boost_voltage_values + - power: supply: mt6360_charger: Fix of_match for usb-otg-vbus regulator + - pinctrl: devicetree: fix refcount leak in pinctrl_dt_to_map() + - nfsd: rename NFSD_NET_* to NFSD_STATS_* + - nfsd: expose /proc/net/sunrpc/nfsd in net namespaces + - nfsd: make all of the nfsd stats per-network namespace + - NFSD: add support for CB_GETATTR callback + - NFSD: Fix nfsd4_encode_fattr4() crasher + - regulator: mt6360: De-capitalize devicetree regulator subnodes + - regulator: change stubbed devm_regulator_get_enable to return Ok + - regulator: change devm_regulator_get_enable_optional() stub to return Ok + - bpf, kconfig: Fix DEBUG_INFO_BTF_MODULES Kconfig definition + - bpf, skmsg: Fix NULL pointer dereference in sk_psock_skb_ingress_enqueue + - regmap: Add regmap_read_bypassed() + - ASoC: SOF: Intel: add default firmware library path for LNL + - nvme: fix warn output about shared namespaces without CONFIG_NVME_MULTIPATH + - bpf: Fix a verifier verbose message + - spi: axi-spi-engine: use common AXI macros + - spi: axi-spi-engine: fix version format string + - spi: hisi-kunpeng: Delete the dump interface of data registers in debugfs + - bpf, arm64: Fix incorrect runtime stats + - riscv, bpf: Fix incorrect runtime stats + - ASoC: Intel: avs: Set name of control as in topology + - ASoC: codecs: wsa881x: set clk_stop_mode1 flag + - s390/mm: Fix storage key clearing for guest huge pages + - s390/mm: Fix clearing storage keys for huge pages + - arm32, bpf: Reimplement sign-extension mov instruction + - xdp: use flags field to disambiguate broadcast redirect + - efi/unaccepted: touch soft lockup during memory accept + - ice: ensure the copied buf is NUL terminated + - bna: ensure the copied buf is NUL terminated + - octeontx2-af: avoid off-by-one read from userspace + - thermal/debugfs: Free all thermal zone debug memory on zone removal + - thermal/debugfs: Fix two locking issues with thermal zone debug + - nsh: Restore skb->{protocol,data,mac_header} for outer header in + nsh_gso_segment(). + - net l2tp: drop flow hash on forward + - thermal/debugfs: Prevent use-after-free from occurring after cdev removal + - s390/vdso: Add CFI for RA register to asm macro vdso_func + - Fix a potential infinite loop in extract_user_to_sg() + - ALSA: emu10k1: fix E-MU card dock presence monitoring + - ALSA: emu10k1: factor out snd_emu1010_load_dock_firmware() + - ALSA: emu10k1: move the whole GPIO event handling to the workqueue + - ALSA: emu10k1: fix E-MU dock initialization + - net: qede: sanitize 'rc' in qede_add_tc_flower_fltr() + - net: qede: use return from qede_parse_flow_attr() for flower + - net: qede: use return from qede_parse_flow_attr() for flow_spec + - net: qede: use return from qede_parse_actions() + - vxlan: Fix racy device stats updates. + - vxlan: Add missing VNI filter counter update in arp_reduce(). + - ASoC: meson: axg-fifo: use FIELD helpers + - ASoC: meson: axg-fifo: use threaded irq to check periods + - ASoC: meson: axg-card: make links nonatomic + - ASoC: meson: axg-tdm-interface: manage formatters in trigger + - ASoC: meson: cards: select SND_DYNAMIC_MINORS + - ALSA: hda: intel-sdw-acpi: fix usage of device_get_named_child_node() + - s390/cio: Ensure the copied buf is NUL terminated + - cxgb4: Properly lock TX queue for the selftest. + - net: dsa: mv88e6xxx: Fix number of databases for 88E6141 / 88E6341 + - drm/amdgpu: fix doorbell regression + - spi: fix null pointer dereference within spi_sync + - net: bridge: fix multicast-to-unicast with fraglist GSO + - net: core: reject skb_copy(_expand) for fraglist GSO skbs + - rxrpc: Clients must accept conn from any address + - tipc: fix a possible memleak in tipc_buf_append + - vxlan: Pull inner IP header in vxlan_rcv(). + - s390/qeth: Fix kernel panic after setting hsuid + - drm/panel: ili9341: Correct use of device property APIs + - [Config] updateconfigs for DRM_PANEL_ILITEK_ILI9341 + - drm/panel: ili9341: Respect deferred probe + - drm/panel: ili9341: Use predefined error codes + - ipv4: Fix uninit-value access in __ip_make_skb() + - net: gro: fix udp bad offset in socket lookup by adding + {inner_}network_offset to napi_gro_cb + - net: gro: add flush check in udp_gro_receive_segment + - drm/xe/display: Fix ADL-N detection + - clk: qcom: smd-rpm: Restore msm8976 num_clk + - clk: sunxi-ng: h6: Reparent CPUX during PLL CPUX rate change + - powerpc/pseries: make max polling consistent for longer H_CALLs + - powerpc/pseries/iommu: LPAR panics during boot up with a frozen PE + - EDAC/versal: Do not log total error counts + - swiotlb: initialise restricted pool list_head when SWIOTLB_DYNAMIC=y + - KVM: arm64: vgic-v2: Check for non-NULL vCPU in vgic_v2_parse_attr() + - exfat: fix timing of synchronizing bitmap and inode + - firmware: microchip: don't unconditionally print validation success + - scsi: ufs: core: Fix MCQ MAC configuration + - scsi: lpfc: Move NPIV's transport unregistration to after resource clean up + - scsi: lpfc: Remove IRQF_ONESHOT flag from threaded IRQ handling + - scsi: lpfc: Update lpfc_ramp_down_queue_handler() logic + - scsi: lpfc: Replace hbalock with ndlp lock in lpfc_nvme_unregister_port() + - scsi: lpfc: Release hbalock before calling lpfc_worker_wake_up() + - scsi: lpfc: Use a dedicated lock for ras_fwlog state + - gfs2: Fix invalid metadata access in punch_hole + - fs/9p: fix uninitialized values during inode evict + - wifi: mac80211: fix ieee80211_bss_*_flags kernel-doc + - wifi: cfg80211: fix rdev_dump_mpp() arguments order + - wifi: mac80211: fix prep_connection error path + - wifi: iwlwifi: read txq->read_ptr under lock + - wifi: iwlwifi: mvm: guard against invalid STA ID on removal + - net: mark racy access on sk->sk_rcvbuf + - drm/xe: Fix END redefinition + - scsi: mpi3mr: Avoid memcpy field-spanning write WARNING + - scsi: bnx2fc: Remove spin_lock_bh while releasing resources after upload + - btrfs: return accurate error code on open failure in open_fs_devices() + - drm/amdkfd: Check cgroup when returning DMABuf info + - drm/amdkfd: range check cp bad op exception interrupts + - bpf: Check bloom filter map value size + - selftests/ftrace: Fix event filter target_func selection + - kbuild: Disable KCSAN for autogenerated *.mod.c intermediaries + - ASoC: SOF: Intel: hda-dsp: Skip IMR boot on ACE platforms in case of S3 + suspend + - regulator: tps65132: Add of_match table + - OSS: dmasound/paula: Mark driver struct with __refdata to prevent section + mismatch + - scsi: ufs: core: WLUN suspend dev/link state error recovery + - scsi: libsas: Align SMP request allocation to ARCH_DMA_MINALIGN + - scsi: ufs: core: Fix MCQ mode dev command timeout + - ALSA: line6: Zero-initialize message buffers + - block: fix overflow in blk_ioctl_discard() + - ASoC: codecs: ES8326: Solve error interruption issue + - ASoC: codecs: ES8326: modify clock table + - net: bcmgenet: Reset RBUF on first open + - vboxsf: explicitly deny setlease attempts + - ata: sata_gemini: Check clk_enable() result + - firewire: ohci: mask bus reset interrupts between ISR and bottom half + - tools/power turbostat: Fix added raw MSR output + - tools/power turbostat: Increase the limit for fd opened + - tools/power turbostat: Fix Bzy_MHz documentation typo + - tools/power turbostat: Do not print negative LPI residency + - tools/power turbostat: Expand probe_intel_uncore_frequency() + - tools/power turbostat: Print ucode revision only if valid + - tools/power turbostat: Fix warning upon failed /dev/cpu_dma_latency read + - btrfs: make btrfs_clear_delalloc_extent() free delalloc reserve + - btrfs: always clear PERTRANS metadata during commit + - memblock tests: fix undefined reference to `early_pfn_to_nid' + - memblock tests: fix undefined reference to `panic' + - memblock tests: fix undefined reference to `BIT' + - nouveau/gsp: Avoid addressing beyond end of rpc->entries + - scsi: target: Fix SELinux error when systemd-modules loads the target module + - scsi: hisi_sas: Handle the NCQ error returned by D2H frame + - blk-iocost: avoid out of bounds shift + - accel/ivpu: Remove d3hot_after_power_off WA + - accel/ivpu: Improve clarity of MMU error messages + - accel/ivpu: Fix missed error message after VPU rename + - platform/x86: acer-wmi: Add support for Acer PH18-71 + - gpu: host1x: Do not setup DMA for virtual devices + - MIPS: scall: Save thread_info.syscall unconditionally on entry + - tools/power/turbostat: Fix uncore frequency file string + - net: add copy_safe_from_sockptr() helper + - nfc: llcp: fix nfc_llcp_setsockopt() unsafe copies + - drm/amdgpu: Refine IB schedule error logging + - drm/amd/display: add DCN 351 version for microcode load + - drm/amdgpu: add smu 14.0.1 discovery support + - drm/amdgpu: implement IRQ_STATE_ENABLE for SDMA v4.4.2 + - drm/amd/display: Skip on writeback when it's not applicable + - drm/amd/pm: fix the high voltage issue after unload + - drm/amdgpu: Fix VCN allocation in CPX partition + - amd/amdkfd: sync all devices to wait all processes being evicted + - selftests: timers: Fix valid-adjtimex signed left-shift undefined behavior + - Drivers: hv: vmbus: Leak pages if set_memory_encrypted() fails + - Drivers: hv: vmbus: Track decrypted status in vmbus_gpadl + - hv_netvsc: Don't free decrypted memory + - uio_hv_generic: Don't free decrypted memory + - Drivers: hv: vmbus: Don't free ring buffers that couldn't be re-encrypted + - drm/xe/xe_migrate: Cast to output precision before multiplying operands + - drm/xe: Label RING_CONTEXT_CONTROL as masked + - smb3: fix broken reconnect when password changing on the server by allowing + password rotation + - iommu: mtk: fix module autoloading + - fs/9p: only translate RWX permissions for plain 9P2000 + - fs/9p: translate O_TRUNC into OTRUNC + - fs/9p: fix the cache always being enabled on files with qid flags + - 9p: explicitly deny setlease attempts + - powerpc/crypto/chacha-p10: Fix failure on non Power10 + - gpio: wcove: Use -ENOTSUPP consistently + - gpio: crystalcove: Use -ENOTSUPP consistently + - clk: Don't hold prepare_lock when calling kref_put() + - fs/9p: remove erroneous nlink init from legacy stat2inode + - fs/9p: drop inodes immediately on non-.L too + - gpio: lpc32xx: fix module autoloading + - drm/nouveau/dp: Don't probe eDP ports twice harder + - platform/x86/amd: pmf: Decrease error message to debug + - platform/x86: ISST: Add Granite Rapids-D to HPM CPU list + - drm/radeon: silence UBSAN warning (v3) + - net:usb:qmi_wwan: support Rolling modules + - blk-iocost: do not WARN if iocg was already offlined + - SUNRPC: add a missing rpc_stat for TCP TLS + - qibfs: fix dentry leak + - xfrm: Preserve vlan tags for transport mode software GRO + - ARM: 9381/1: kasan: clear stale stack poison + - tcp: defer shutdown(SEND_SHUTDOWN) for TCP_SYN_RECV sockets + - tcp: Use refcount_inc_not_zero() in tcp_twsk_unique(). + - Bluetooth: Fix use-after-free bugs caused by sco_sock_timeout + - Bluetooth: msft: fix slab-use-after-free in msft_do_close() + - arm64: dts: mediatek: mt8183-pico6: Fix bluetooth node + - Bluetooth: HCI: Fix potential null-ptr-deref + - Bluetooth: l2cap: fix null-ptr-deref in l2cap_chan_timeout + - net: ks8851: Queue RX packets in IRQ handler instead of disabling BHs + - rtnetlink: Correct nested IFLA_VF_VLAN_LIST attribute validation + - hwmon: (corsair-cpro) Use a separate buffer for sending commands + - hwmon: (corsair-cpro) Use complete_all() instead of complete() in + ccp_raw_event() + - hwmon: (corsair-cpro) Protect ccp->wait_input_report with a spinlock + - phonet: fix rtm_phonet_notify() skb allocation + - netlink: specs: Add missing bridge linkinfo attrs + - nfc: nci: Fix kcov check in nci_rx_work() + - net: bridge: fix corrupted ethernet header on multicast-to-unicast + - ipv6: Fix potential uninit-value access in __ip6_make_skb() + - selftests: test_bridge_neigh_suppress.sh: Fix failures due to duplicate MAC + - rxrpc: Fix the names of the fields in the ACK trailer struct + - rxrpc: Fix congestion control algorithm + - rxrpc: Only transmit one ACK per jumbo packet received + - dt-bindings: net: mediatek: remove wrongly added clocks and SerDes + - ipv6: fib6_rules: avoid possible NULL dereference in fib6_rule_action() + - net-sysfs: convert dev->operstate reads to lockless ones + - hsr: Simplify code for announcing HSR nodes timer setup + - ipv6: annotate data-races around cnf.disable_ipv6 + - ipv6: prevent NULL dereference in ip6_output() + - net/smc: fix neighbour and rtable leak in smc_ib_find_route() + - net: hns3: using user configure after hardware reset + - net: hns3: direct return when receive a unknown mailbox message + - net: hns3: change type of numa_node_mask as nodemask_t + - net: hns3: release PTP resources if pf initialization failed + - net: hns3: use appropriate barrier function after setting a bit value + - net: hns3: fix port vlan filter not disabled issue + - net: hns3: fix kernel crash when devlink reload during initialization + - net: dsa: mv88e6xxx: add phylink_get_caps for the mv88e6320/21 family + - drm/meson: dw-hdmi: power up phy on device init + - drm/meson: dw-hdmi: add bandgap setting for g12 + - drm/connector: Add \n to message about demoting connector force-probes + - dm/amd/pm: Fix problems with reboot/shutdown for some SMU 13.0.4/13.0.11 + users + - gpiolib: cdev: Fix use after free in lineinfo_changed_notify + - gpiolib: cdev: fix uninitialised kfifo + - drm/amdgpu: Fix comparison in amdgpu_res_cpu_visible + - drm/amdgpu: once more fix the call oder in amdgpu_ttm_move() v2 + - firewire: nosy: ensure user_length is taken into account when fetching + packet contents + - Reapply "drm/qxl: simplify qxl_fence_wait" + - usb: typec: ucsi: Check for notifications after init + - usb: typec: ucsi: Fix connector check on init + - usb: Fix regression caused by invalid ep0 maxpacket in virtual SuperSpeed + device + - usb: ohci: Prevent missed ohci interrupts + - USB: core: Fix access violation during port device removal + - usb: gadget: composite: fix OS descriptors w_value logic + - usb: gadget: uvc: use correct buffer size when parsing configfs lists + - usb: gadget: f_fs: Fix race between aio_cancel() and AIO request complete + - usb: gadget: f_fs: Fix a race condition when processing setup packets. + - usb: xhci-plat: Don't include xhci.h + - usb: dwc3: core: Prevent phy suspend during init + - usb: typec: tcpm: clear pd_event queue in PORT_RESET + - usb: typec: tcpm: unregister existing source caps before re-registration + - usb: typec: tcpm: Check for port partner validity before consuming it + - ALSA: hda/realtek: Fix mute led of HP Laptop 15-da3001TU + - ALSA: hda/realtek: Fix conflicting PCI SSID 17aa:386f for Lenovo Legion + models + - firewire: ohci: fulfill timestamp for some local asynchronous transaction + - mm/slub: avoid zeroing outside-object freepointer for single free + - btrfs: add missing mutex_unlock in btrfs_relocate_sys_chunks() + - btrfs: set correct ram_bytes when splitting ordered extent + - btrfs: qgroup: do not check qgroup inherit if qgroup is disabled + - btrfs: make sure that WRITTEN is set on all metadata blocks + - maple_tree: fix mas_empty_area_rev() null pointer dereference + - mm/slab: make __free(kfree) accept error pointers + - mptcp: ensure snd_nxt is properly initialized on connect + - mptcp: only allow set existing scheduler for net.mptcp.scheduler + - workqueue: Fix selection of wake_cpu in kick_pool() + - dt-bindings: iio: health: maxim,max30102: fix compatible check + - iio:imu: adis16475: Fix sync mode setting + - iio: pressure: Fixes BME280 SPI driver data + - iio: pressure: Fixes SPI support for BMP3xx devices + - iio: accel: mxc4005: Interrupt handling fixes + - iio: accel: mxc4005: Reset chip on probe() and resume() + - kmsan: compiler_types: declare __no_sanitize_or_inline + - e1000e: change usleep_range to udelay in PHY mdic access + - tipc: fix UAF in error path + - xtensa: fix MAKE_PC_FROM_RA second argument + - net: bcmgenet: synchronize EXT_RGMII_OOB_CTRL access + - net: bcmgenet: synchronize use of bcmgenet_set_rx_mode() + - net: bcmgenet: synchronize UMAC_CMD access + - ASoC: tegra: Fix DSPK 16-bit playback + - ASoC: ti: davinci-mcasp: Fix race condition during probe + - dyndbg: fix old BUG_ON in >control parser + - slimbus: qcom-ngd-ctrl: Add timeout for wait operation + - clk: samsung: Revert "clk: Use device_get_match_data()" + - clk: sunxi-ng: common: Support minimum and maximum rate + - clk: sunxi-ng: a64: Set minimum and maximum rate for PLL-MIPI + - mei: me: add lunar lake point M DID + - drm/nouveau/firmware: Fix SG_DEBUG error with nvkm_firmware_ctor() + - Revert "drm/nouveau/firmware: Fix SG_DEBUG error with nvkm_firmware_ctor()" + - drm/amdkfd: don't allow mapping the MMIO HDP page with large pages + - drm/ttm: Print the memory decryption status just once + - drm/vmwgfx: Fix Legacy Display Unit + - drm/vmwgfx: Fix invalid reads in fence signaled events + - drm/imagination: Ensure PVR_MIPS_PT_PAGE_COUNT is never zero + - drm/amd/display: Fix idle optimization checks for multi-display and dual eDP + - drm/nouveau/gsp: Use the sg allocator for level 2 of radix3 + - drm/i915/gt: Automate CCS Mode setting during engine resets + - drm/i915/bios: Fix parsing backlight BDB data + - drm/amd/display: Handle Y carry-over in VCP X.Y calculation + - drm/amd/display: Fix incorrect DSC instance for MST + - arm64: dts: qcom: sa8155p-adp: fix SDHC2 CD pin configuration + - iommu/arm-smmu: Use the correct type in nvidia_smmu_context_fault() + - net: fix out-of-bounds access in ops_init + - hwmon: (pmbus/ucd9000) Increase delay from 250 to 500us + - misc/pvpanic-pci: register attributes via pci_driver + - x86/apic: Don't access the APIC when disabling x2APIC + - selftests/mm: fix powerpc ARCH check + - mm: use memalloc_nofs_save() in page_cache_ra_order() + - mm/userfaultfd: reset ptes when close() for wr-protected ones + - iommu/amd: Enhance def_domain_type to handle untrusted device + - fs/proc/task_mmu: fix loss of young/dirty bits during pagemap scan + - fs/proc/task_mmu: fix uffd-wp confusion in pagemap_scan_pmd_entry() + - nvme-pci: Add quirk for broken MSIs + - regulator: core: fix debugfs creation regression + - spi: microchip-core-qspi: fix setting spi bus clock rate + - ksmbd: off ipv6only for both ipv4/ipv6 binding + - ksmbd: avoid to send duplicate lease break notifications + - ksmbd: do not grant v2 lease if parent lease key and epoch are not set + - tracefs: Reset permissions on remount if permissions are options + - tracefs: Still use mount point as default permissions for instances + - eventfs: Do not treat events directory different than other directories + - Bluetooth: qca: fix invalid device address check + - Bluetooth: qca: fix wcn3991 device address check + - Bluetooth: qca: add missing firmware sanity checks + - Bluetooth: qca: fix NVM configuration parsing + - Bluetooth: qca: generalise device address check + - Bluetooth: qca: fix info leak when fetching board id + - Bluetooth: qca: fix info leak when fetching fw build id + - Bluetooth: qca: fix firmware check error path + - keys: Fix overwrite of key expiration on instantiation + - Linux 6.8.10 + + * Noble update: v6.8.9 upstream stable release (LP: #2070337) + - cifs: Fix reacquisition of volume cookie on still-live connection + - smb: client: fix rename(2) regression against samba + - cifs: reinstate original behavior again for forceuid/forcegid + - HID: intel-ish-hid: ipc: Fix dev_err usage with uninitialized dev->devc + - HID: logitech-dj: allow mice to use all types of reports + - arm64: dts: rockchip: set PHY address of MT7531 switch to 0x1f + - arm64: dts: rockchip: enable internal pull-up on Q7_USB_ID for RK3399 Puma + - arm64: dts: rockchip: fix alphabetical ordering RK3399 puma + - arm64: dts: rockchip: enable internal pull-up on PCIE_WAKE# for RK3399 Puma + - arm64: dts: rockchip: Fix the i2c address of es8316 on Cool Pi CM5 + - arm64: dts: rockchip: Remove unsupported node from the Pinebook Pro dts + - arm64: dts: mediatek: mt8183: Add power-domains properity to mfgcfg + - arm64: dts: mediatek: mt8192: Add missing gce-client-reg to mutex + - arm64: dts: mediatek: mt8195: Add missing gce-client-reg to vpp/vdosys + - arm64: dts: mediatek: mt8195: Add missing gce-client-reg to mutex + - arm64: dts: mediatek: mt8195: Add missing gce-client-reg to mutex1 + - arm64: dts: mediatek: cherry: Describe CPU supplies + - arm64: dts: mediatek: mt8192-asurada: Update min voltage constraint for + MT6315 + - arm64: dts: mediatek: mt8195-cherry: Update min voltage constraint for + MT6315 + - arm64: dts: mediatek: mt8183-kukui: Use default min voltage for MT6358 + - arm64: dts: mediatek: mt7622: fix clock controllers + - arm64: dts: mediatek: mt7622: fix IR nodename + - arm64: dts: mediatek: mt7622: fix ethernet controller "compatible" + - arm64: dts: mediatek: mt7622: drop "reset-names" from thermal block + - arm64: dts: mediatek: mt7986: reorder properties + - arm64: dts: mediatek: mt7986: drop invalid properties from ethsys + - arm64: dts: mediatek: mt7986: drop "#reset-cells" from Ethernet controller + - arm64: dts: mediatek: mt7986: reorder nodes + - arm64: dts: mediatek: mt7986: drop invalid thermal block clock + - arm64: dts: mediatek: mt7986: prefix BPI-R3 cooling maps with "map-" + - arm64: dts: mediatek: mt2712: fix validation errors + - arm64: dts: rockchip: mark system power controller and fix typo on + orangepi-5-plus + - arm64: dts: rockchip: regulator for sd needs to be always on for BPI-R2Pro + - block: fix module reference leakage from bdev_open_by_dev error path + - arm64: dts: qcom: Fix type of "wdog" IRQs for remoteprocs + - arm64: dts: qcom: x1e80100: Fix the compatible for cluster idle states + - arm64: dts: qcom: sc8180x: Fix ss_phy_irq for secondary USB controller + - gpio: tangier: Use correct type for the IRQ chip data + - ARC: [plat-hsdk]: Remove misplaced interrupt-cells property + - wifi: mac80211: clean up assignments to pointer cache. + - wifi: mac80211: split mesh fast tx cache into local/proxied/forwarded + - wifi: iwlwifi: mvm: remove old PASN station when adding a new one + - wifi: iwlwifi: mvm: return uid from iwl_mvm_build_scan_cmd + - drm/gma500: Remove lid code + - wifi: mac80211_hwsim: init peer measurement result + - wifi: mac80211: remove link before AP + - wifi: mac80211: fix unaligned le16 access + - net: libwx: fix alloc msix vectors failed + - vxlan: drop packets from invalid src-address + - net: bcmasp: fix memory leak when bringing down interface + - mlxsw: core: Unregister EMAD trap using FORWARD action + - mlxsw: core_env: Fix driver initialization with old firmware + - mlxsw: pci: Fix driver initialization with old firmware + - ARM: dts: microchip: at91-sama7g5ek: Replace regulator-suspend-voltage with + the valid property + - icmp: prevent possible NULL dereferences from icmp_build_probe() + - bridge/br_netlink.c: no need to return void function + - bnxt_en: refactor reset close code + - bnxt_en: Fix the PCI-AER routines + - bnxt_en: Fix error recovery for 5760X (P7) chips + - cxl/core: Fix potential payload size confusion in cxl_mem_get_poison() + - net: dsa: mv88e6xx: fix supported_interfaces setup in + mv88e6250_phylink_get_caps() + - NFC: trf7970a: disable all regulators on removal + - netfs: Fix writethrough-mode error handling + - ax25: Fix netdev refcount issue + - soc: mediatek: mtk-svs: Append "-thermal" to thermal zone names + - tools: ynl: don't ignore errors in NLMSG_DONE messages + - net: usb: ax88179_178a: stop lying about skb->truesize + - tcp: Fix Use-After-Free in tcp_ao_connect_init + - net: gtp: Fix Use-After-Free in gtp_dellink + - net: phy: mediatek-ge-soc: follow netdev LED trigger semantics + - gpio: tegra186: Fix tegra186_gpio_is_accessible() check + - drm/xe: Remove sysfs only once on action add failure + - drm/xe: call free_gsc_pkt only once on action add failure + - Bluetooth: hci_event: Use HCI error defines instead of magic values + - Bluetooth: hci_conn: Only do ACL connections sequentially + - Bluetooth: Remove pending ACL connection attempts + - Bluetooth: hci_conn: Always use sk_timeo as conn_timeout + - Bluetooth: hci_conn: Fix UAF Write in __hci_acl_create_connection_sync + - Bluetooth: hci_sync: Add helper functions to manipulate cmd_sync queue + - Bluetooth: hci_sync: Attempt to dequeue connection attempt + - Bluetooth: ISO: Reassemble PA data for bcast sink + - Bluetooth: hci_sync: Use advertised PHYs on hci_le_ext_create_conn_sync + - Bluetooth: btusb: Fix triggering coredump implementation for QCA + - Bluetooth: hci_event: Fix sending HCI_OP_READ_ENC_KEY_SIZE + - Bluetooth: MGMT: Fix failing to MGMT_OP_ADD_UUID/MGMT_OP_REMOVE_UUID + - Bluetooth: btusb: mediatek: Fix double free of skb in coredump + - Bluetooth: hci_sync: Using hci_cmd_sync_submit when removing Adv Monitor + - Bluetooth: qca: set power_ctrl_enabled on NULL returned by + gpiod_get_optional() + - ipvs: Fix checksumming on GSO of SCTP packets + - net: openvswitch: Fix Use-After-Free in ovs_ct_exit + - mlxsw: Use refcount_t for reference counting + - mlxsw: spectrum_acl_tcam: Fix race in region ID allocation + - mlxsw: spectrum_acl_tcam: Fix race during rehash delayed work + - mlxsw: spectrum_acl_tcam: Fix possible use-after-free during activity update + - mlxsw: spectrum_acl_tcam: Fix possible use-after-free during rehash + - mlxsw: spectrum_acl_tcam: Rate limit error message + - mlxsw: spectrum_acl_tcam: Fix memory leak during rehash + - mlxsw: spectrum_acl_tcam: Fix warning during rehash + - mlxsw: spectrum_acl_tcam: Fix incorrect list API usage + - mlxsw: spectrum_acl_tcam: Fix memory leak when canceling rehash work + - eth: bnxt: fix counting packets discarded due to OOM and netpoll + - ARM: dts: imx6ull-tarragon: fix USB over-current polarity + - netfilter: nf_tables: honor table dormant flag from netdev release event + path + - net: phy: dp83869: Fix MII mode failure + - net: ti: icssg-prueth: Fix signedness bug in prueth_init_rx_chns() + - i40e: Do not use WQ_MEM_RECLAIM flag for workqueue + - i40e: Report MFS in decimal base instead of hex + - iavf: Fix TC config comparison with existing adapter TC config + - ice: fix LAG and VF lock dependency in ice_reset_vf() + - net: ethernet: ti: am65-cpts: Fix PTPv1 message type on TX packets + - octeontx2-af: fix the double free in rvu_npc_freemem() + - dpll: check that pin is registered in __dpll_pin_unregister() + - dpll: fix dpll_pin_on_pin_register() for multiple parent pins + - tls: fix lockless read of strp->msg_ready in ->poll + - af_unix: Suppress false-positive lockdep splat for spin_lock() in + __unix_gc(). + - netfs: Fix the pre-flush when appending to a file in writethrough mode + - drm/amd/display: Check DP Alt mode DPCS state via DMUB + - Revert "drm/amd/display: fix USB-C flag update after enc10 feature init" + - xhci: move event processing for one interrupter to a separate function + - usb: xhci: correct return value in case of STS_HCE + - KVM: x86/pmu: Zero out PMU metadata on AMD if PMU is disabled + - KVM: x86/pmu: Set enable bits for GP counters in PERF_GLOBAL_CTRL at "RESET" + - drm: add drm_gem_object_is_shared_for_memory_stats() helper + - drm/amdgpu: add shared fdinfo stats + - drm/amdgpu: fix visible VRAM handling during faults + - Revert "UBUNTU: SAUCE: selftests/seccomp: fix check of fds being assigned" + - selftests/seccomp: user_notification_addfd check nextfd is available + - selftests/seccomp: Change the syscall used in KILL_THREAD test + - selftests/seccomp: Handle EINVAL on unshare(CLONE_NEWPID) + - x86/CPU/AMD: Add models 0x10-0x1f to the Zen5 range + - x86/cpu: Fix check for RDPKRU in __show_regs() + - rust: phy: implement `Send` for `Registration` + - rust: kernel: require `Send` for `Module` implementations + - rust: don't select CONSTRUCTORS + - [Config] updateconfigs to drop CONSTRUCTORS for rust + - rust: init: remove impl Zeroable for Infallible + - rust: make mutually exclusive with CFI_CLANG + - kbuild: rust: remove unneeded `@rustc_cfg` to avoid ICE + - kbuild: rust: force `alloc` extern to allow "empty" Rust files + - rust: remove `params` from `module` macro example + - Bluetooth: Fix type of len in {l2cap,sco}_sock_getsockopt_old() + - Bluetooth: btusb: Add Realtek RTL8852BE support ID 0x0bda:0x4853 + - Bluetooth: qca: fix NULL-deref on non-serdev suspend + - Bluetooth: qca: fix NULL-deref on non-serdev setup + - mtd: rawnand: qcom: Fix broken OP_RESET_DEVICE command in + qcom_misc_cmd_type_exec() + - mm/hugetlb: fix missing hugetlb_lock for resv uncharge + - mmc: sdhci-msm: pervent access to suspended controller + - mmc: sdhci-of-dwcmshc: th1520: Increase tuning loop count to 128 + - mm: create FOLIO_FLAG_FALSE and FOLIO_TYPE_OPS macros + - mm: support page_mapcount() on page_has_type() pages + - mm/hugetlb: fix DEBUG_LOCKS_WARN_ON(1) when dissolve_free_hugetlb_folio() + - smb: client: Fix struct_group() usage in __packed structs + - smb3: missing lock when picking channel + - smb3: fix lock ordering potential deadlock in cifs_sync_mid_result + - btrfs: fallback if compressed IO fails for ENOSPC + - btrfs: fix wrong block_start calculation for btrfs_drop_extent_map_range() + - btrfs: scrub: run relocation repair when/only needed + - btrfs: fix information leak in btrfs_ioctl_logical_to_ino() + - x86/tdx: Preserve shared bit on mprotect() + - cpu: Re-enable CPU mitigations by default for !X86 architectures + - [Config] updateconfigs for CPU_MITIGATIONS + - eeprom: at24: fix memory corruption race condition + - LoongArch: Fix callchain parse error with kernel tracepoint events + - LoongArch: Fix access error when read fault on a write-only VMA + - arm64: dts: qcom: sc8280xp: add missing PCIe minimum OPP + - arm64: dts: qcom: sm8450: Fix the msi-map entries + - arm64: dts: rockchip: enable internal pull-up for Q7_THRM# on RK3399 Puma + - dmaengine: Revert "dmaengine: pl330: issue_pending waits until WFP state" + - dmaengine: xilinx: xdma: Fix wrong offsets in the buffers addresses in dma + descriptor + - dmaengine: xilinx: xdma: Fix synchronization issue + - drm/amdgpu/sdma5.2: use legacy HDP flush for SDMA2/3 + - drm/amdgpu: Assign correct bits for SDMA HDP flush + - drm/atomic-helper: fix parameter order in drm_format_conv_state_copy() call + - drm/amdgpu/pm: Remove gpu_od if it's an empty directory + - drm/amdgpu/umsch: don't execute umsch test when GPU is in reset/suspend + - drm/amdgpu: Fix leak when GPU memory allocation fails + - drm/amdkfd: Fix rescheduling of restore worker + - drm/amdkfd: Fix eviction fence handling + - irqchip/gic-v3-its: Prevent double free on error + - ACPI: CPPC: Use access_width over bit_width for system memory accesses + - ACPI: CPPC: Fix bit_offset shift in MASK_VAL() macro + - ACPI: CPPC: Fix access width used for PCC registers + - net/mlx5e: Advertise mlx5 ethernet driver updates sk_buff md_dst for MACsec + - ethernet: Add helper for assigning packet type when dest address does not + match device address + - net: b44: set pause params only when interface is up + - macsec: Enable devices to advertise whether they update sk_buff md_dst + during offloads + - macsec: Detect if Rx skb is macsec-related for offloading devices that + update md_dst + - stackdepot: respect __GFP_NOLOCKDEP allocation flag + - fbdev: fix incorrect address computation in deferred IO + - udp: preserve the connected status if only UDP cmsg + - mtd: limit OTP NVMEM cell parse to non-NAND devices + - mtd: diskonchip: work around ubsan link failure + - firmware: qcom: uefisecapp: Fix memory related IO errors and crashes + - phy: qcom: qmp-combo: Fix register base for QSERDES_DP_PHY_MODE + - phy: qcom: qmp-combo: Fix VCO div offset on v3 + - mm: turn folio_test_hugetlb into a PageType + - mm: zswap: fix shrinker NULL crash with cgroup_disable=memory + - dmaengine: owl: fix register access functions + - dmaengine: tegra186: Fix residual calculation + - idma64: Don't try to serve interrupts when device is powered off + - soundwire: amd: fix for wake interrupt handling for clockstop mode + - phy: marvell: a3700-comphy: Fix hardcoded array size + - phy: freescale: imx8m-pcie: fix pcie link-up instability + - phy: rockchip-snps-pcie3: fix bifurcation on rk3588 + - phy: rockchip-snps-pcie3: fix clearing PHP_GRF_PCIESEL_CON bits + - phy: rockchip: naneng-combphy: Fix mux on rk3588 + - phy: qcom: m31: match requested regulator name with dt schema + - dmaengine: idxd: Convert spinlock to mutex to lock evl workqueue + - dmaengine: idxd: Fix oops during rmmod on single-CPU platforms + - riscv: Fix TASK_SIZE on 64-bit NOMMU + - riscv: Fix loading 64-bit NOMMU kernels past the start of RAM + - phy: ti: tusb1210: Resolve charger-det crash if charger psy is unregistered + - dt-bindings: eeprom: at24: Fix ST M24C64-D compatible schema + - sched/eevdf: Always update V if se->on_rq when reweighting + - sched/eevdf: Fix miscalculation in reweight_entity() when se is not curr + - riscv: hwprobe: fix invalid sign extension for RISCV_HWPROBE_EXT_ZVFHMIN + - RISC-V: selftests: cbo: Ensure asm operands match constraints, take 2 + - phy: qcom: qmp-combo: fix VCO div offset on v5_5nm and v6 + - bounds: Use the right number of bits for power-of-two CONFIG_NR_CPUS + - Bluetooth: hci_sync: Fix UAF in hci_acl_create_conn_sync + - Bluetooth: hci_sync: Fix UAF on create_le_conn_complete + - Bluetooth: hci_sync: Fix UAF on hci_abort_conn_sync + - Linux 6.8.9 + + * amdgpu hangs on DCN 3.5 at bootup: RIP: + 0010:dcn35_clk_mgr_construct+0x183/0x2210 [amdgpu] (LP: #2066233) + - drm/amd/display: Atom Integrated System Info v2_2 for DCN35 + + * [MTL] ACPI: PM: s2idle: Backport Linux ACPI s2idle patches to fix + suspend/resume issue (LP: #2069231) + - ACPI: PM: s2idle: Enable Low-Power S0 Idle MSFT UUID for non-AMD systems + - ACPI: PM: s2idle: Evaluate all Low-Power S0 Idle _DSM functions + + * Removing legacy virtio-pci devices causes kernel panic (LP: #2067862) + - virtio-pci: Check if is_avq is NULL + + * Mute/mic LEDs no function on ProBook 445/465 G11 (LP: #2069664) + - ALSA: hda/realtek: fix mute/micmute LEDs don't work for ProBook 445/465 G11. + + * Mute/mic LEDs no function on ProBook 440/460 G11 (LP: #2067669) + - ALSA: hda/realtek: fix mute/micmute LEDs don't work for ProBook 440/460 G11. + + * rtw89_8852ce - Lost WIFI connection after suspend (LP: #2065128) + - wifi: rtw89: reset AFEDIG register in power off sequence + - wifi: rtw89: 8852c: refine power sequence to imporve power consumption + + * CVE-2024-25742 + - x86/sev: Harden #VC instruction emulation somewhat + - x86/sev: Check for MWAITX and MONITORX opcodes in the #VC handler + + * Noble update: v6.8.9 upstream stable release (LP: #2070337) // + CVE-2024-35984 + - i2c: smbus: fix NULL function pointer dereference + + * Noble update: v6.8.9 upstream stable release (LP: #2070337) // + CVE-2024-35990 + - dma: xilinx_dpdma: Fix locking + + * Noble update: v6.8.9 upstream stable release (LP: #2070337) // + CVE-2024-35997 + - HID: i2c-hid: remove I2C_HID_READ_PENDING flag to prevent lock-up + + * CVE-2024-36016 + - tty: n_gsm: fix possible out-of-bounds in gsm0_receive() + + * CVE-2024-36008 + - ipv4: check for NULL idev in ip_route_use_hint() + + * CVE-2024-35992 + - phy: marvell: a3700-comphy: Fix out of bounds read + + -- Stefan Bader Fri, 05 Jul 2024 10:31:38 +0200 + +linux (6.8.0-38.38) noble; urgency=medium + + * noble/linux: 6.8.0-38.38 -proposed tracker (LP: #2068318) + + * race_sched in ubuntu_stress_smoke_test will cause kernel panic on 6.8 with + Azure Standard_A2_v2 instance (LP: #2068024) + - sched/eevdf: Prevent vlag from going out of bounds in reweight_eevdf() + + * Noble: btrfs: re-introduce 'norecovery' mount option (LP: #2068591) + - btrfs: re-introduce 'norecovery' mount option + + * Fix system hang while entering suspend with AMD Navi3x graphics + (LP: #2063417) + - drm/amdgpu/mes: fix use-after-free issue + + * Noble update: v6.8.8 upstream stable release (LP: #2068087) + - io_uring: Fix io_cqring_wait() not restoring sigmask on get_timespec64() + failure + - drm/i915/cdclk: Fix voltage_level programming edge case + - Revert "vmgenid: emit uevent when VMGENID updates" + - SUNRPC: Fix rpcgss_context trace event acceptor field + - selftests/ftrace: Limit length in subsystem-enable tests + - random: handle creditable entropy from atomic process context + - scsi: core: Fix handling of SCMD_FAIL_IF_RECOVERING + - net: usb: ax88179_178a: avoid writing the mac address before first reading + - btrfs: do not wait for short bulk allocation + - btrfs: zoned: do not flag ZEROOUT on non-dirty extent buffer + - r8169: fix LED-related deadlock on module removal + - r8169: add missing conditional compiling for call to r8169_remove_leds + - scsi: ufs: qcom: Add missing interconnect bandwidth values for Gear 5 + - netfilter: nf_tables: Fix potential data-race in __nft_expr_type_get() + - netfilter: nf_tables: Fix potential data-race in __nft_obj_type_get() + - netfilter: br_netfilter: skip conntrack input hook for promisc packets + - netfilter: nft_set_pipapo: constify lookup fn args where possible + - netfilter: nft_set_pipapo: walk over current view on netlink dump + - netfilter: flowtable: validate pppoe header + - netfilter: flowtable: incorrect pppoe tuple + - af_unix: Call manage_oob() for every skb in unix_stream_read_generic(). + - af_unix: Don't peek OOB data without MSG_OOB. + - net: sparx5: flower: fix fragment flags handling + - net/mlx5: Lag, restore buckets number to default after hash LAG deactivation + - net/mlx5: Restore mistakenly dropped parts in register devlink flow + - net/mlx5e: Prevent deadlock while disabling aRFS + - net: change maximum number of UDP segments to 128 + - octeontx2-pf: fix FLOW_DIS_IS_FRAGMENT implementation + - selftests/tcp_ao: Make RST tests less flaky + - selftests/tcp_ao: Zero-init tcp_ao_info_opt + - selftests/tcp_ao: Fix fscanf() call for format-security + - selftests/tcp_ao: Printing fixes to confirm with format-security + - net: stmmac: Apply half-duplex-less constraint for DW QoS Eth only + - net: stmmac: Fix max-speed being ignored on queue re-init + - net: stmmac: Fix IP-cores specific MAC capabilities + - ice: tc: check src_vsi in case of traffic from VF + - ice: tc: allow zero flags in parsing tc flower + - ice: Fix checking for unsupported keys on non-tunnel device + - tun: limit printing rate when illegal packet received by tun dev + - net: dsa: mt7530: fix mirroring frames received on local port + - net: dsa: mt7530: fix port mirroring for MT7988 SoC switch + - s390/ism: Properly fix receive message buffer allocation + - netfilter: nf_tables: missing iterator type in lookup walk + - netfilter: nf_tables: restore set elements when delete set fails + - gpiolib: swnode: Remove wrong header inclusion + - netfilter: nf_tables: fix memleak in map from abort path + - net/sched: Fix mirred deadlock on device recursion + - net: ethernet: mtk_eth_soc: fix WED + wifi reset + - ravb: Group descriptor types used in Rx ring + - net: ravb: Count packets instead of descriptors in R-Car RX path + - net: ravb: Allow RX loop to move past DMA mapping errors + - net: ethernet: ti: am65-cpsw-nuss: cleanup DMA Channels before using them + - NFSD: fix endianness issue in nfsd4_encode_fattr4 + - RDMA/rxe: Fix the problem "mutex_destroy missing" + - RDMA/cm: Print the old state when cm_destroy_id gets timeout + - RDMA/mlx5: Fix port number for counter query in multi-port configuration + - perf annotate: Make sure to call symbol__annotate2() in TUI + - perf lock contention: Add a missing NULL check + - s390/qdio: handle deferred cc1 + - s390/cio: fix race condition during online processing + - iommufd: Add missing IOMMUFD_DRIVER kconfig for the selftest + - iommufd: Add config needed for iommufd_fail_nth + - drm: nv04: Fix out of bounds access + - drm/v3d: Don't increment `enabled_ns` twice + - userfaultfd: change src_folio after ensuring it's unpinned in UFFDIO_MOVE + - thunderbolt: Introduce tb_port_reset() + - thunderbolt: Introduce tb_path_deactivate_hop() + - thunderbolt: Make tb_switch_reset() support Thunderbolt 2, 3 and USB4 + routers + - thunderbolt: Reset topology created by the boot firmware + - drm/panel: visionox-rm69299: don't unregister DSI device + - drm/radeon: make -fstrict-flex-arrays=3 happy + - ALSA: hda/realtek: Fix volumn control of ThinkBook 16P Gen4 + - thermal/debugfs: Add missing count increment to thermal_debug_tz_trip_up() + - platform/x86/amd/pmc: Extend Framework 13 quirk to more BIOSes + - interconnect: qcom: x1e80100: Remove inexistent ACV_PERF BCM + - interconnect: Don't access req_list while it's being manipulated + - clk: Remove prepare_lock hold assertion in __clk_release() + - clk: Initialize struct clk_core kref earlier + - clk: Get runtime PM before walking tree during disable_unused + - clk: Get runtime PM before walking tree for clk_summary + - clk: mediatek: Do a runtime PM get on controllers during probe + - clk: mediatek: mt7988-infracfg: fix clocks for 2nd PCIe port + - selftests/powerpc/papr-vpd: Fix missing variable initialization + - x86/bugs: Fix BHI retpoline check + - x86/cpufeatures: Fix dependencies for GFNI, VAES, and VPCLMULQDQ + - block: propagate partition scanning errors to the BLKRRPART ioctl + - net/mlx5: E-switch, store eswitch pointer before registering devlink_param + - ALSA: seq: ump: Fix conversion from MIDI2 to MIDI1 UMP messages + - ALSA: hda/tas2781: correct the register for pow calibrated data + - ALSA: hda/realtek: Add quirks for Huawei Matebook D14 NBLB-WAX9N + - ALSA: hda/realtek - Enable audio jacks of Haier Boyue G42 with ALC269VC + - usb: misc: onboard_usb_hub: Disable the USB hub clock on failure + - misc: rtsx: Fix rts5264 driver status incorrect when card removed + - thunderbolt: Avoid notify PM core about runtime PM resume + - thunderbolt: Fix wake configurations after device unplug + - thunderbolt: Do not create DisplayPort tunnels on adapters of the same + router + - comedi: vmk80xx: fix incomplete endpoint checking + - serial: mxs-auart: add spinlock around changing cts state + - serial/pmac_zilog: Remove flawed mitigation for rx irq flood + - serial: 8250_dw: Revert: Do not reclock if already at correct rate + - serial: stm32: Return IRQ_NONE in the ISR if no handling happend + - serial: stm32: Reset .throttled state in .startup() + - serial: core: Fix regression when runtime PM is not enabled + - serial: core: Clearing the circular buffer before NULLifying it + - serial: core: Fix missing shutdown and startup for serial base port + - USB: serial: option: add Fibocom FM135-GL variants + - USB: serial: option: add support for Fibocom FM650/FG650 + - USB: serial: option: add Lonsung U8300/U9300 product + - USB: serial: option: support Quectel EM060K sub-models + - USB: serial: option: add Rolling RW101-GL and RW135-GL support + - USB: serial: option: add Telit FN920C04 rmnet compositions + - Revert "usb: cdc-wdm: close race between read and workqueue" + - usb: dwc2: host: Fix dereference issue in DDMA completion flow. + - usb: Disable USB3 LPM at shutdown + - usb: gadget: f_ncm: Fix UAF ncm object at re-bind after usb ep transport + error + - usb: typec: tcpm: Correct the PDO counting in pd_set + - mei: me: disable RPL-S on SPS and IGN firmwares + - speakup: Avoid crash on very long word + - fs: sysfs: Fix reference leak in sysfs_break_active_protection() + - sched: Add missing memory barrier in switch_mm_cid + - KVM: x86: Snapshot if a vCPU's vendor model is AMD vs. Intel compatible + - KVM: x86/pmu: Disable support for adaptive PEBS + - KVM: x86/pmu: Do not mask LVTPC when handling a PMI on AMD platforms + - KVM: x86/mmu: x86: Don't overflow lpage_info when checking attributes + - KVM: x86/mmu: Write-protect L2 SPTEs in TDP MMU when clearing dirty status + - arm64/head: Disable MMU at EL2 before clearing HCR_EL2.E2H + - arm64: hibernate: Fix level3 translation fault in swsusp_save() + - init/main.c: Fix potential static_command_line memory overflow + - mm/madvise: make MADV_POPULATE_(READ|WRITE) handle VM_FAULT_RETRY properly + - mm/userfaultfd: allow hugetlb change protection upon poison entry + - mm,swapops: update check in is_pfn_swap_entry for hwpoison entries + - mm/memory-failure: fix deadlock when hugetlb_optimize_vmemmap is enabled + - mm/shmem: inline shmem_is_huge() for disabled transparent hugepages + - fuse: fix leaked ENOSYS error on first statx call + - drm/amdkfd: Fix memory leak in create_process failure + - drm/amdgpu: remove invalid resource->start check v2 + - drm/ttm: stop pooling cached NUMA pages v2 + - drm/xe: Fix bo leak in intel_fb_bo_framebuffer_init + - drm/vmwgfx: Fix prime import/export + - drm/vmwgfx: Sort primary plane formats by order of preference + - drm/vmwgfx: Fix crtc's atomic check conditional + - nouveau: fix instmem race condition around ptr stores + - bootconfig: use memblock_free_late to free xbc memory to buddy + - Squashfs: check the inode number is not the invalid value of zero + - nilfs2: fix OOB in nilfs_set_de_type + - fork: defer linking file vma until vma is fully initialized + - net: dsa: mt7530: fix improper frames on all 25MHz and 40MHz XTAL MT7530 + - net: dsa: mt7530: fix enabling EEE on MT7531 switch on all boards + - ksmbd: fix slab-out-of-bounds in smb2_allocate_rsp_buf + - ksmbd: validate request buffer size in smb2_allocate_rsp_buf() + - ksmbd: clear RENAME_NOREPLACE before calling vfs_rename + - ksmbd: common: use struct_group_attr instead of struct_group for + network_open_info + - thunderbolt: Reset only non-USB4 host routers in resume + - Linux 6.8.8 + + * Fix inaudible HDMI/DP audio on USB-C MST dock (LP: #2064689) + - drm/i915/audio: Fix audio time stamp programming for DP + + * Add Cirrus Logic CS35L56 amplifier support (LP: #2062135) + - ALSA: hda: realtek: Re-work CS35L41 fixups to re-use for other amps + - ALSA: hda/realtek: Add quirks for HP G11 Laptops using CS35L56 + + * net:fib_rule_tests.sh in ubuntu_kselftests_net fails on Noble (LP: #2066332) + - Revert "UBUNTU: SAUCE: selftests: net: fix "from" match test in + fib_rule_tests.sh" + + * mtk_t7xx WWAN module fails to probe with: Invalid device status 0x1 + (LP: #2049358) + - Revert "UBUNTU: SAUCE: net: wwan: t7xx: PCIe reset rescan" + - Revert "UBUNTU: SAUCE: net: wwan: t7xx: Add AP CLDMA" + - net: wwan: t7xx: Add AP CLDMA + - wwan: core: Add WWAN fastboot port type + - net: wwan: t7xx: Add sysfs attribute for device state machine + - net: wwan: t7xx: Infrastructure for early port configuration + - net: wwan: t7xx: Add fastboot WWAN port + + * Pull-request to address TPM bypass issue (LP: #2037688) + - [Config]: Configure TPM drivers as builtins for arm64 in annotations + + * re-enable Ubuntu FAN in the Noble kernel (LP: #2064508) + - SAUCE: fan: add VXLAN implementation + - SAUCE: fan: Fix NULL pointer dereference + - SAUCE: fan: support vxlan strict length validation + + * update for V3 kernel bits and improved multiple fan slice support + (LP: #1470091) // re-enable Ubuntu FAN in the Noble kernel (LP: #2064508) + - SAUCE: fan: tunnel multiple mapping mode (v3) + + * TCP memory leak, slow network (arm64) (LP: #2045560) + - net: make SK_MEMORY_PCPU_RESERV tunable + - net: fix sk_memory_allocated_{add|sub} vs softirqs + + * panel flickering after the i915.psr2 is enabled (LP: #2046315) + - drm/i915/alpm: Add ALPM register definitions + - drm/i915/psr: Add alpm_parameters struct + - drm/i915/alpm: Calculate ALPM Entry check + - drm/i915/alpm: Alpm aux wake configuration for lnl + - drm/i915/display: Make intel_dp_aux_fw_sync_len available for PSR code + - drm/i915/psr: Improve fast and IO wake lines calculation + - drm/i915/psr: Calculate IO wake and fast wake lines for DISPLAY_VER < 12 + - drm/i915/display: Increase number of fast wake precharge pulses + + * I2C HID device sometimes fails to initialize causing touchpad to not work + (LP: #2061040) + - HID: i2c-hid: Revert to await reset ACK before reading report descriptor + + * Fix the RTL8852CE BT FW Crash based on SER false alarm (LP: #2060904) + - wifi: rtw89: disable txptctrl IMR to avoid flase alarm + - wifi: rtw89: pci: correct TX resource checking for PCI DMA channel of + firmware command + + * [X13s] Fingerprint reader is not working (LP: #2065376) + - SAUCE: arm64: dts: qcom: sc8280xp: Add USB DWC3 Multiport controller + - SAUCE: arm64: dts: qcom: sc8280xp-x13s: enable USB MP and fingerprint reader + + * Fix random HuC/GuC initialization failure of Intel i915 driver + (LP: #2061049) + - drm/i915/huc: Allow for very slow HuC loading + + * Add support of TAS2781 amp of audio (LP: #2064064) + - ALSA: hda/tas2781: Add new vendor_id and subsystem_id to support ThinkPad + ICE-1 + + * Noble update: v6.8.7 upstream stable release (LP: #2065912) + - smb3: fix Open files on server counter going negative + - ata: libata-core: Allow command duration limits detection for ACS-4 drives + - ata: libata-scsi: Fix ata_scsi_dev_rescan() error path + - drm/amdgpu/vpe: power on vpe when hw_init + - batman-adv: Avoid infinite loop trying to resize local TT + - ceph: redirty page before returning AOP_WRITEPAGE_ACTIVATE + - ceph: switch to use cap_delay_lock for the unlink delay list + - virtio_net: Do not send RSS key if it is not supported + - arm64: tlb: Fix TLBI RANGE operand + - ARM: dts: imx7s-warp: Pass OV2680 link-frequencies + - raid1: fix use-after-free for original bio in raid1_write_request() + - ring-buffer: Only update pages_touched when a new page is touched + - Bluetooth: Fix memory leak in hci_req_sync_complete() + - drm/amd/pm: fixes a random hang in S4 for SMU v13.0.4/11 + - platform/chrome: cros_ec_uart: properly fix race condition + - ACPI: scan: Do not increase dep_unmet for already met dependencies + - PM: s2idle: Make sure CPUs will wakeup directly on resume + - media: cec: core: remove length check of Timer Status + - btrfs: tests: allocate dummy fs_info and root in test_find_delalloc() + - ARM: OMAP2+: fix bogus MMC GPIO labels on Nokia N8x0 + - ARM: OMAP2+: fix N810 MMC gpiod table + - mmc: omap: fix broken slot switch lookup + - mmc: omap: fix deferred probe + - mmc: omap: restore original power up/down steps + - ARM: OMAP2+: fix USB regression on Nokia N8x0 + - firmware: arm_ffa: Fix the partition ID check in ffa_notification_info_get() + - firmware: arm_scmi: Make raw debugfs entries non-seekable + - cxl/mem: Fix for the index of Clear Event Record Handle + - cxl/core/regs: Fix usage of map->reg_type in cxl_decode_regblock() before + assigned + - arm64: dts: freescale: imx8mp-venice-gw72xx-2x: fix USB vbus regulator + - arm64: dts: freescale: imx8mp-venice-gw73xx-2x: fix USB vbus regulator + - drm/msm: Add newlines to some debug prints + - drm/msm/dpu: don't allow overriding data from catalog + - drm/msm/dpu: make error messages at dpu_core_irq_register_callback() more + sensible + - dt-bindings: display/msm: sm8150-mdss: add DP node + - arm64: dts: imx8-ss-conn: fix usdhc wrong lpcg clock order + - cxl/core: Fix initialization of mbox_cmd.size_out in get event + - Revert "drm/qxl: simplify qxl_fence_wait" + - nouveau: fix function cast warning + - drm/msm/adreno: Set highest_bank_bit for A619 + - scsi: hisi_sas: Modify the deadline for ata_wait_after_reset() + - scsi: qla2xxx: Fix off by one in qla_edif_app_getstats() + - net: openvswitch: fix unwanted error log on timeout policy probing + - u64_stats: fix u64_stats_init() for lockdep when used repeatedly in one file + - xsk: validate user input for XDP_{UMEM|COMPLETION}_FILL_RING + - octeontx2-pf: Fix transmit scheduler resource leak + - block: fix q->blkg_list corruption during disk rebind + - lib: checksum: hide unused expected_csum_ipv6_magic[] + - geneve: fix header validation in geneve[6]_xmit_skb + - s390/ism: fix receive message buffer allocation + - bnxt_en: Fix possible memory leak in bnxt_rdma_aux_device_init() + - bnxt_en: Fix error recovery for RoCE ulp client + - bnxt_en: Reset PTP tx_avail after possible firmware reset + - ACPI: bus: allow _UID matching for integer zero + - base/node / ACPI: Enumerate node access class for 'struct access_coordinate' + - ACPI: HMAT: Introduce 2 levels of generic port access class + - ACPI: HMAT / cxl: Add retrieval of generic port coordinates for both access + classes + - cxl: Split out combine_coordinates() for common shared usage + - cxl: Split out host bridge access coordinates + - cxl: Remove checking of iter in cxl_endpoint_get_perf_coordinates() + - cxl: Fix retrieving of access_coordinates in PCIe path + - net: ks8851: Inline ks8851_rx_skb() + - net: ks8851: Handle softirqs at the end of IRQ thread to fix hang + - af_unix: Clear stale u->oob_skb. + - octeontx2-af: Fix NIX SQ mode and BP config + - ipv6: fib: hide unused 'pn' variable + - ipv4/route: avoid unused-but-set-variable warning + - ipv6: fix race condition between ipv6_get_ifaddr and ipv6_del_addr + - pds_core: use pci_reset_function for health reset + - pds_core: Fix pdsc_check_pci_health function to use work thread + - Bluetooth: ISO: Align broadcast sync_timeout with connection timeout + - Bluetooth: ISO: Don't reject BT_ISO_QOS if parameters are unset + - Bluetooth: hci_sync: Use QoS to determine which PHY to scan + - Bluetooth: hci_sync: Fix using the same interval and window for Coded PHY + - Bluetooth: SCO: Fix not validating setsockopt user input + - Bluetooth: RFCOMM: Fix not validating setsockopt user input + - Bluetooth: L2CAP: Fix not validating setsockopt user input + - Bluetooth: ISO: Fix not validating setsockopt user input + - Bluetooth: hci_sock: Fix not validating setsockopt user input + - Bluetooth: l2cap: Don't double set the HCI_CONN_MGMT_CONNECTED bit + - netfilter: complete validation of user input + - net/mlx5: SF, Stop waiting for FW as teardown was called + - net/mlx5: Register devlink first under devlink lock + - net/mlx5: offset comp irq index in name by one + - net/mlx5: Properly link new fs rules into the tree + - net/mlx5: Correctly compare pkt reformat ids + - net/mlx5e: RSS, Block changing channels number when RXFH is configured + - net/mlx5e: Fix mlx5e_priv_init() cleanup flow + - net/mlx5e: HTB, Fix inconsistencies with QoS SQs number + - net/mlx5e: Do not produce metadata freelist entries in Tx port ts WQE xmit + - net: sparx5: fix wrong config being used when reconfiguring PCS + - Revert "s390/ism: fix receive message buffer allocation" + - net: dsa: mt7530: trap link-local frames regardless of ST Port State + - af_unix: Do not use atomic ops for unix_sk(sk)->inflight. + - af_unix: Fix garbage collector racing against connect() + - net: ena: Fix potential sign extension issue + - net: ena: Wrong missing IO completions check order + - net: ena: Fix incorrect descriptor free behavior + - net: ena: Set tx_info->xdpf value to NULL + - drm/xe/display: Fix double mutex initialization + - drm/xe/hwmon: Cast result to output precision on left shift of operand + - tracing: hide unused ftrace_event_id_fops + - iommu/vt-d: Fix wrong use of pasid config + - iommu/vt-d: Allocate local memory for page request queue + - iommu/vt-d: Fix WARN_ON in iommu probe path + - io_uring: refactor DEFER_TASKRUN multishot checks + - io_uring: disable io-wq execution of multishot NOWAIT requests + - btrfs: qgroup: correctly model root qgroup rsv in convert + - btrfs: qgroup: fix qgroup prealloc rsv leak in subvolume operations + - btrfs: record delayed inode root in transaction + - btrfs: qgroup: convert PREALLOC to PERTRANS after record_root_in_trans + - io_uring/net: restore msg_control on sendzc retry + - kprobes: Fix possible use-after-free issue on kprobe registration + - fs/proc: remove redundant comments from /proc/bootconfig + - fs/proc: Skip bootloader comment if no embedded kernel parameters + - scsi: sg: Avoid sg device teardown race + - scsi: sg: Avoid race in error handling & drop bogus warn + - accel/ivpu: Check return code of ipc->lock init + - accel/ivpu: Fix PCI D0 state entry in resume + - accel/ivpu: Put NPU back to D3hot after failed resume + - accel/ivpu: Return max freq for DRM_IVPU_PARAM_CORE_CLOCK_RATE + - accel/ivpu: Fix deadlock in context_xa + - drm/vmwgfx: Enable DMA mappings with SEV + - drm/i915/vrr: Disable VRR when using bigjoiner + - drm/amdkfd: Reset GPU on queue preemption failure + - drm/ast: Fix soft lockup + - drm/panfrost: Fix the error path in panfrost_mmu_map_fault_addr() + - drm/client: Fully protect modes[] with dev->mode_config.mutex + - drm/msm/dp: fix runtime PM leak on disconnect + - drm/msm/dp: fix runtime PM leak on connect failure + - drm/amdgpu/umsch: reinitialize write pointer in hw init + - arm64: dts: imx8qm-ss-dma: fix can lpcg indices + - arm64: dts: imx8-ss-dma: fix can lpcg indices + - arm64: dts: imx8-ss-dma: fix adc lpcg indices + - arm64: dts: imx8-ss-conn: fix usb lpcg indices + - arm64: dts: imx8-ss-dma: fix pwm lpcg indices + - arm64: dts: imx8-ss-lsio: fix pwm lpcg indices + - arm64: dts: imx8-ss-dma: fix spi lpcg indices + - vhost: Add smp_rmb() in vhost_vq_avail_empty() + - vhost: Add smp_rmb() in vhost_enable_notify() + - perf/x86: Fix out of range data + - x86/cpu: Actually turn off mitigations by default for + SPECULATION_MITIGATIONS=n + - selftests/timers/posix_timers: Reimplement check_timer_distribution() + - selftests: timers: Fix posix_timers ksft_print_msg() warning + - selftests: timers: Fix abs() warning in posix_timers test + - selftests: kselftest: Mark functions that unconditionally call exit() as + __noreturn + - x86/apic: Force native_apic_mem_read() to use the MOV instruction + - irqflags: Explicitly ignore lockdep_hrtimer_exit() argument + - selftests: kselftest: Fix build failure with NOLIBC + - kernfs: annotate different lockdep class for of->mutex of writable files + - x86/bugs: Fix return type of spectre_bhi_state() + - x86/bugs: Fix BHI documentation + - x86/bugs: Cache the value of MSR_IA32_ARCH_CAPABILITIES + - x86/bugs: Rename various 'ia32_cap' variables to 'x86_arch_cap_msr' + - x86/bugs: Fix BHI handling of RRSBA + - x86/bugs: Clarify that syscall hardening isn't a BHI mitigation + - x86/bugs: Remove CONFIG_BHI_MITIGATION_AUTO and spectre_bhi=auto + - [Config] updateconfigs to remove obsolete SPECTRE_BHI_AUTO + - x86/bugs: Replace CONFIG_SPECTRE_BHI_{ON,OFF} with + CONFIG_MITIGATION_SPECTRE_BHI + - [Config] updateconfigs to enable new MITIGATION_SPECTRE_BHI + - drm/i915/cdclk: Fix CDCLK programming order when pipes are active + - drm/i915/psr: Disable PSR when bigjoiner is used + - drm/i915: Disable port sync when bigjoiner is used + - drm/i915: Disable live M/N updates when using bigjoiner + - drm/amdgpu: Reset dGPU if suspend got aborted + - drm/amdgpu: always force full reset for SOC21 + - drm/amdgpu: fix incorrect number of active RBs for gfx11 + - drm/amdgpu: differentiate external rev id for gfx 11.5.0 + - drm/amd/display: Program VSC SDP colorimetry for all DP sinks >= 1.4 + - drm/amd/display: Set VSC SDP Colorimetry same way for MST and SST + - drm/amd/display: Do not recursively call manual trigger programming + - drm/amd/display: Return max resolution supported by DWB + - drm/amd/display: always reset ODM mode in context when adding first plane + - drm/amd/display: fix disable otg wa logic in DCN316 + - Linux 6.8.7 + + * Noble update: v6.8.6 upstream stable release (LP: #2065899) + - amdkfd: use calloc instead of kzalloc to avoid integer overflow + - wifi: ath9k: fix LNA selection in ath_ant_try_scan() + - wifi: rtw89: fix null pointer access when abort scan + - bnx2x: Fix firmware version string character counts + - net: stmmac: dwmac-starfive: Add support for JH7100 SoC + - net: phy: phy_device: Prevent nullptr exceptions on ISR + - wifi: rtw89: pci: validate RX tag for RXQ and RPQ + - wifi: rtw89: pci: enlarge RX DMA buffer to consider size of RX descriptor + - VMCI: Fix memcpy() run-time warning in dg_dispatch_as_host() + - wifi: iwlwifi: pcie: Add the PCI device id for new hardware + - arm64: dts: qcom: qcm6490-idp: Add definition for three LEDs + - net: dsa: qca8k: put MDIO controller OF node if unavailable + - arm64: dts: qcom: qrb2210-rb1: disable cluster power domains + - printk: For @suppress_panic_printk check for other CPU in panic + - panic: Flush kernel log buffer at the end + - dump_stack: Do not get cpu_sync for panic CPU + - wifi: iwlwifi: pcie: Add new PCI device id and CNVI + - cpuidle: Avoid potential overflow in integer multiplication + - ARM: dts: rockchip: fix rk3288 hdmi ports node + - ARM: dts: rockchip: fix rk322x hdmi ports node + - arm64: dts: rockchip: fix rk3328 hdmi ports node + - arm64: dts: rockchip: fix rk3399 hdmi ports node + - net: add netdev_lockdep_set_classes() to virtual drivers + - arm64: dts: qcom: qcs6490-rb3gen2: Declare GCC clocks protected + - pmdomain: ti: Add a null pointer check to the omap_prm_domain_init + - pmdomain: imx8mp-blk-ctrl: imx8mp_blk: Add fdcc clock to hdmimix domain + - ACPI: resource: Add IRQ override quirk for ASUS ExpertBook B2502FBA + - ionic: set adminq irq affinity + - net: skbuff: add overflow debug check to pull/push helpers + - firmware: tegra: bpmp: Return directly after a failed kzalloc() in + get_filename() + - wifi: brcmfmac: Add DMI nvram filename quirk for ACEPC W5 Pro + - wifi: mt76: mt7915: add locking for accessing mapped registers + - wifi: mt76: mt7996: disable AMSDU for non-data frames + - wifi: mt76: mt7996: add locking for accessing mapped registers + - ACPI: x86: Move acpi_quirk_skip_serdev_enumeration() out of + CONFIG_X86_ANDROID_TABLETS + - ACPI: x86: Add DELL0501 handling to acpi_quirk_skip_serdev_enumeration() + - pstore/zone: Add a null pointer check to the psz_kmsg_read + - tools/power x86_energy_perf_policy: Fix file leak in get_pkg_num() + - net: pcs: xpcs: Return EINVAL in the internal methods + - dma-direct: Leak pages on dma_set_decrypted() failure + - wifi: ath11k: decrease MHI channel buffer length to 8KB + - iommu/arm-smmu-v3: Hold arm_smmu_asid_lock during all of attach_dev + - cpufreq: Don't unregister cpufreq cooling on CPU hotplug + - overflow: Allow non-type arg to type_max() and type_min() + - wifi: iwlwifi: Add missing MODULE_FIRMWARE() for *.pnvm + - wifi: cfg80211: check A-MSDU format more carefully + - btrfs: handle chunk tree lookup error in btrfs_relocate_sys_chunks() + - btrfs: export: handle invalid inode or root reference in btrfs_get_parent() + - btrfs: send: handle path ref underflow in header iterate_inode_ref() + - ice: use relative VSI index for VFs instead of PF VSI number + - net/smc: reduce rtnl pressure in smc_pnet_create_pnetids_list() + - netdev: let netlink core handle -EMSGSIZE errors + - Bluetooth: btintel: Fix null ptr deref in btintel_read_version + - Bluetooth: btmtk: Add MODULE_FIRMWARE() for MT7922 + - Bluetooth: Add new quirk for broken read key length on ATS2851 + - drm/vc4: don't check if plane->state->fb == state->fb + - drm/ci: uprev mesa version: fix kdl commit fetch + - drm/amdgpu: Skip do PCI error slot reset during RAS recovery + - Input: synaptics-rmi4 - fail probing if memory allocation for "phys" fails + - drm: panel-orientation-quirks: Add quirk for GPD Win Mini + - ASoC: SOF: amd: Optimize quirk for Valve Galileo + - drm/ttm: return ENOSPC from ttm_bo_mem_space v3 + - scsi: ufs: qcom: Avoid re-init quirk when gears match + - drm/amd/display: increased min_dcfclk_mhz and min_fclk_mhz + - pinctrl: renesas: checker: Limit cfg reg enum checks to provided IDs + - sysv: don't call sb_bread() with pointers_lock held + - scsi: lpfc: Fix possible memory leak in lpfc_rcv_padisc() + - drm/amd/display: Disable idle reallow as part of command/gpint execution + - isofs: handle CDs with bad root inode but good Joliet root directory + - ASoC: Intel: sof_rt5682: dmi quirk cleanup for mtl boards + - ASoC: Intel: common: DMI remap for rebranded Intel NUC M15 (LAPRC710) + laptops + - rcu/nocb: Fix WARN_ON_ONCE() in the rcu_nocb_bypass_lock() + - rcu-tasks: Repair RCU Tasks Trace quiescence check + - Julia Lawall reported this null pointer dereference, this should fix it. + - media: sta2x11: fix irq handler cast + - ALSA: firewire-lib: handle quirk to calculate payload quadlets as data block + counter + - drm/panel: simple: Add BOE BP082WX1-100 8.2" panel + - x86/vdso: Fix rethunk patching for vdso-image-{32,64}.o + - ASoC: Intel: avs: Populate board selection with new I2S entries + - ext4: add a hint for block bitmap corrupt state in mb_groups + - ext4: forbid commit inconsistent quota data when errors=remount-ro + - drm/amd/display: Fix nanosec stat overflow + - accel/habanalabs: increase HL_MAX_STR to 64 bytes to avoid warnings + - i2c: designware: Fix RX FIFO depth define on Wangxun 10Gb NIC + - HID: input: avoid polling stylus battery on Chromebook Pompom + - drm/amd/amdgpu: Fix potential ioremap() memory leaks in amdgpu_device_init() + - drm: Check output polling initialized before disabling + - drm: Check polling initialized before enabling in + drm_helper_probe_single_connector_modes + - SUNRPC: increase size of rpc_wait_queue.qlen from unsigned short to unsigned + int + - PCI: Disable D3cold on Asus B1400 PCI-NVMe bridge + - Revert "ACPI: PM: Block ASUS B1400CEAE from suspend to idle by default" + - libperf evlist: Avoid out-of-bounds access + - crypto: iaa - Fix async_disable descriptor leak + - input/touchscreen: imagis: Correct the maximum touch area value + - drivers/perf: hisi: Enable HiSilicon Erratum 162700402 quirk for HIP09 + - block: prevent division by zero in blk_rq_stat_sum() + - RDMA/cm: add timeout to cm_destroy_id wait + - Input: imagis - use FIELD_GET where applicable + - Input: allocate keycode for Display refresh rate toggle + - platform/x86: acer-wmi: Add support for Acer PH16-71 + - platform/x86: acer-wmi: Add predator_v4 module parameter + - platform/x86: touchscreen_dmi: Add an extra entry for a variant of the Chuwi + Vi8 tablet + - perf/x86/amd/lbr: Discard erroneous branch entries + - ALSA: hda/realtek: Add quirk for Lenovo Yoga 9 14IMH9 + - ktest: force $buildonly = 1 for 'make_warnings_file' test type + - Input: xpad - add support for Snakebyte GAMEPADs + - ring-buffer: use READ_ONCE() to read cpu_buffer->commit_page in concurrent + environment + - tools: iio: replace seekdir() in iio_generic_buffer + - bus: mhi: host: Add MHI_PM_SYS_ERR_FAIL state + - kernfs: RCU protect kernfs_nodes and avoid kernfs_idr_lock in + kernfs_find_and_get_node_by_id() + - usb: typec: ucsi: Add qcm6490-pmic-glink as needing PDOS quirk + - thunderbolt: Calculate DisplayPort tunnel bandwidth after DPRX capabilities + read + - usb: gadget: uvc: refactor the check for a valid buffer in the pump worker + - usb: gadget: uvc: mark incomplete frames with UVC_STREAM_ERR + - usb: typec: ucsi: Limit read size on v1.2 + - serial: 8250_of: Drop quirk fot NPCM from 8250_port + - thunderbolt: Keep the domain powered when USB4 port is in redrive mode + - usb: typec: tcpci: add generic tcpci fallback compatible + - usb: sl811-hcd: only defined function checkdone if QUIRK2 is defined + - ASoC: amd: yc: Fix non-functional mic on ASUS M7600RE + - thermal/of: Assume polling-delay(-passive) 0 when absent + - ASoC: soc-core.c: Skip dummy codec when adding platforms + - x86/xen: attempt to inflate the memory balloon on PVH + - fbdev: viafb: fix typo in hw_bitblt_1 and hw_bitblt_2 + - io_uring: clear opcode specific data for an early failure + - modpost: fix null pointer dereference + - drivers/nvme: Add quirks for device 126f:2262 + - fbmon: prevent division by zero in fb_videomode_from_videomode() + - ALSA: hda/realtek: Add quirks for some Clevo laptops + - drm/amdgpu: Init zone device and drm client after mode-1 reset on reload + - gcc-plugins/stackleak: Avoid .head.text section + - media: mediatek: vcodec: Fix oops when HEVC init fails + - media: mediatek: vcodec: adding lock to protect decoder context list + - media: mediatek: vcodec: adding lock to protect encoder context list + - randomize_kstack: Improve entropy diffusion + - platform/x86/intel/hid: Don't wake on 5-button releases + - platform/x86: intel-vbtn: Update tablet mode switch at end of probe + - nouveau: fix devinit paths to only handle display on GSP. + - Bluetooth: btintel: Fixe build regression + - net: mpls: error out if inner headers are not set + - VMCI: Fix possible memcpy() run-time warning in + vmci_datagram_invoke_guest_handler() + - x86/vdso: Fix rethunk patching for vdso-image-x32.o too + - Revert "drm/amd/amdgpu: Fix potential ioremap() memory leaks in + amdgpu_device_init()" + - Linux 6.8.6 + + * Noble update: v6.8.5 upstream stable release (LP: #2065400) + - scripts/bpf_doc: Use silent mode when exec make cmd + - xsk: Don't assume metadata is always requested in TX completion + - s390/bpf: Fix bpf_plt pointer arithmetic + - bpf, arm64: fix bug in BPF_LDX_MEMSX + - dma-buf: Fix NULL pointer dereference in sanitycheck() + - arm64: bpf: fix 32bit unconditional bswap + - nfc: nci: Fix uninit-value in nci_dev_up and nci_ntf_packet + - nfsd: Fix error cleanup path in nfsd_rename() + - tools: ynl: fix setting presence bits in simple nests + - mlxbf_gige: stop PHY during open() error paths + - wifi: iwlwifi: mvm: pick the version of SESSION_PROTECTION_NOTIF + - wifi: iwlwifi: mvm: rfi: fix potential response leaks + - wifi: iwlwifi: mvm: include link ID when releasing frames + - ALSA: hda: cs35l56: Set the init_done flag before component_add() + - ice: Refactor FW data type and fix bitmap casting issue + - ice: fix memory corruption bug with suspend and rebuild + - ixgbe: avoid sleeping allocation in ixgbe_ipsec_vf_add_sa() + - igc: Remove stale comment about Tx timestamping + - drm/xe: Remove unused xe_bo->props struct + - drm/xe: Add exec_queue.sched_props.job_timeout_ms + - drm/xe/guc_submit: use jiffies for job timeout + - drm/xe/queue: fix engine_class bounds check + - drm/xe/device: fix XE_MAX_GT_PER_TILE check + - drm/xe/device: fix XE_MAX_TILES_PER_DEVICE check + - dpll: indent DPLL option type by a tab + - s390/qeth: handle deferred cc1 + - net: hsr: hsr_slave: Fix the promiscuous mode in offload mode + - tcp: properly terminate timers for kernel sockets + - net: wwan: t7xx: Split 64bit accesses to fix alignment issues + - drm/rockchip: vop2: Remove AR30 and AB30 format support + - selftests: vxlan_mdb: Fix failures with old libnet + - gpiolib: Fix debug messaging in gpiod_find_and_request() + - ACPICA: debugger: check status of acpi_evaluate_object() in + acpi_db_walk_for_fields() + - net: hns3: fix index limit to support all queue stats + - net: hns3: fix kernel crash when devlink reload during pf initialization + - net: hns3: mark unexcuted loopback test result as UNEXECUTED + - tls: recv: process_rx_list shouldn't use an offset with kvec + - tls: adjust recv return with async crypto and failed copy to userspace + - tls: get psock ref after taking rxlock to avoid leak + - mlxbf_gige: call request_irq() after NAPI initialized + - drm/amd/display: Update P010 scaling cap + - drm/amd/display: Send DTBCLK disable message on first commit + - bpf: Protect against int overflow for stack access size + - cifs: Fix duplicate fscache cookie warnings + - netfilter: nf_tables: reject destroy command to remove basechain hooks + - netfilter: nf_tables: reject table flag and netdev basechain updates + - netfilter: nf_tables: skip netdev hook unregistration if table is dormant + - iommu: Validate the PASID in iommu_attach_device_pasid() + - net: bcmasp: Bring up unimac after PHY link up + - net: lan743x: Add set RFE read fifo threshold for PCI1x1x chips + - Octeontx2-af: fix pause frame configuration in GMP mode + - inet: inet_defrag: prevent sk release while still in use + - drm/i915: Stop doing double audio enable/disable on SDVO and g4x+ DP + - drm/i915/display: Disable AuxCCS framebuffers if built for Xe + - drm/i915/xelpg: Extend some workarounds/tuning to gfx version 12.74 + - drm/i915/mtl: Update workaround 14018575942 + - drm/i915: Do not print 'pxp init failed with 0' when it succeed + - dm integrity: fix out-of-range warning + - modpost: do not make find_tosym() return NULL + - kbuild: make -Woverride-init warnings more consistent + - mm/treewide: replace pud_large() with pud_leaf() + - Revert "x86/mm/ident_map: Use gbpages only where full GB page should be + mapped." + - gpio: cdev: sanitize the label before requesting the interrupt + - RISC-V: KVM: Fix APLIC setipnum_le/be write emulation + - RISC-V: KVM: Fix APLIC in_clrip[x] read emulation + - KVM: arm64: Fix host-programmed guest events in nVHE + - KVM: arm64: Fix out-of-IPA space translation fault handling + - selinux: avoid dereference of garbage after mount failure + - r8169: fix issue caused by buggy BIOS on certain boards with RTL8168d + - x86/cpufeatures: Add CPUID_LNX_5 to track recently added Linux-defined word + - x86/bpf: Fix IP after emitting call depth accounting + - Revert "Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT" + - arm64: dts: qcom: sc7180-trogdor: mark bluetooth address as broken + - Bluetooth: qca: fix device-address endianness + - Bluetooth: add quirk for broken address properties + - Bluetooth: hci_event: set the conn encrypted before conn establishes + - Bluetooth: Fix TOCTOU in HCI debugfs implementation + - netfilter: nf_tables: release batch on table validation from abort path + - netfilter: nf_tables: release mutex after nft_gc_seq_end from abort path + - selftests: mptcp: join: fix dev in check_endpoint + - net/rds: fix possible cp null dereference + - net: usb: ax88179_178a: avoid the interface always configured as random + address + - net: mana: Fix Rx DMA datasize and skb_over_panic + - vsock/virtio: fix packet delivery to tap device + - netfilter: nf_tables: reject new basechain after table flag update + - netfilter: nf_tables: flush pending destroy work before exit_net release + - netfilter: nf_tables: Fix potential data-race in __nft_flowtable_type_get() + - netfilter: nf_tables: discard table flag update with pending basechain + deletion + - netfilter: validate user input for expected length + - vboxsf: Avoid an spurious warning if load_nls_xxx() fails + - bpf, sockmap: Prevent lock inversion deadlock in map delete elem + - mptcp: prevent BPF accessing lowat from a subflow socket. + - x86/retpoline: Do the necessary fixup to the Zen3/4 srso return thunk for + !SRSO + - KVM: arm64: Use TLBI_TTL_UNKNOWN in __kvm_tlb_flush_vmid_range() + - KVM: arm64: Ensure target address is granule-aligned for range TLBI + - net/sched: act_skbmod: prevent kernel-infoleak + - net: dsa: sja1105: Fix parameters order in sja1110_pcs_mdio_write_c45() + - net/sched: fix lockdep splat in qdisc_tree_reduce_backlog() + - net: stmmac: fix rx queue priority assignment + - net: phy: micrel: lan8814: Fix when enabling/disabling 1-step timestamping + - net: txgbe: fix i2c dev name cannot match clkdev + - net: fec: Set mac_managed_pm during probe + - net: phy: micrel: Fix potential null pointer dereference + - net: dsa: mv88e6xxx: fix usable ports on 88e6020 + - selftests: net: gro fwd: update vxlan GRO test expectations + - gro: fix ownership transfer + - idpf: fix kernel panic on unknown packet types + - ice: fix enabling RX VLAN filtering + - i40e: Fix VF MAC filter removal + - tcp: Fix bind() regression for v6-only wildcard and v4-mapped-v6 non- + wildcard addresses. + - erspan: make sure erspan_base_hdr is present in skb->head + - selftests: reuseaddr_conflict: add missing new line at the end of the output + - tcp: Fix bind() regression for v6-only wildcard and v4(-mapped-v6) non- + wildcard addresses. + - ax25: fix use-after-free bugs caused by ax25_ds_del_timer + - e1000e: Workaround for sporadic MDI error on Meteor Lake systems + - ipv6: Fix infinite recursion in fib6_dump_done(). + - mlxbf_gige: stop interface during shutdown + - r8169: skip DASH fw status checks when DASH is disabled + - udp: do not accept non-tunnel GSO skbs landing in a tunnel + - udp: do not transition UDP GRO fraglist partial checksums to unnecessary + - udp: prevent local UDP tunnel packets from being GROed + - octeontx2-af: Fix issue with loading coalesced KPU profiles + - octeontx2-pf: check negative error code in otx2_open() + - octeontx2-af: Add array index check + - i40e: fix i40e_count_filters() to count only active/new filters + - i40e: fix vf may be used uninitialized in this function warning + - i40e: Enforce software interrupt during busy-poll exit + - drm/amd: Flush GFXOFF requests in prepare stage + - e1000e: Minor flow correction in e1000_shutdown function + - e1000e: move force SMBUS from enable ulp function to avoid PHY loss issue + - mean_and_variance: Drop always failing tests + - net: ravb: Let IP-specific receive function to interrogate descriptors + - net: ravb: Always process TX descriptor ring + - net: ravb: Always update error counters + - KVM: SVM: Use unsigned integers when dealing with ASIDs + - KVM: SVM: Add support for allowing zero SEV ASIDs + - selftests: mptcp: connect: fix shellcheck warnings + - selftests: mptcp: use += operator to append strings + - mptcp: don't account accept() of non-MPC client as fallback to TCP + - 9p: Fix read/write debug statements to report server reply + - ASoC: wm_adsp: Fix missing mutex_lock in wm_adsp_write_ctl() + - ASoC: cs42l43: Correct extraction of data pointer in suspend/resume + - riscv: mm: Fix prototype to avoid discarding const + - riscv: hwprobe: do not produce frtace relocation + - drivers/perf: riscv: Disable PERF_SAMPLE_BRANCH_* while not supported + - block: count BLK_OPEN_RESTRICT_WRITES openers + - RISC-V: Update AT_VECTOR_SIZE_ARCH for new AT_MINSIGSTKSZ + - ASoC: amd: acp: fix for acp pdm configuration check + - regmap: maple: Fix cache corruption in regcache_maple_drop() + - ALSA: hda: cs35l56: Add ACPI device match tables + - drm/panfrost: fix power transition timeout warnings + - nouveau/uvmm: fix addr/range calcs for remap operations + - drm/prime: Unbreak virtgpu dma-buf export + - ASoC: rt5682-sdw: fix locking sequence + - ASoC: rt711-sdca: fix locking sequence + - ASoC: rt711-sdw: fix locking sequence + - ASoC: rt712-sdca-sdw: fix locking sequence + - ASoC: rt722-sdca-sdw: fix locking sequence + - ASoC: ops: Fix wraparound for mask in snd_soc_get_volsw + - spi: s3c64xx: Extract FIFO depth calculation to a dedicated macro + - spi: s3c64xx: sort headers alphabetically + - spi: s3c64xx: explicitly include + - spi: s3c64xx: remove else after return + - spi: s3c64xx: define a magic value + - spi: s3c64xx: allow full FIFO masks + - spi: s3c64xx: determine the fifo depth only once + - spi: s3c64xx: Use DMA mode from fifo size + - ASoC: amd: acp: fix for acp_init function error handling + - regmap: maple: Fix uninitialized symbol 'ret' warnings + - ata: sata_sx4: fix pdc20621_get_from_dimm() on 64-bit + - scsi: mylex: Fix sysfs buffer lengths + - scsi: sd: Unregister device if device_add_disk() failed in sd_probe() + - Revert "ALSA: emu10k1: fix synthesizer sample playback position and caching" + - drm/i915/dp: Fix DSC state HW readout for SST connectors + - cifs: Fix caching to try to do open O_WRONLY as rdwr on server + - spi: mchp-pci1xxx: Fix a possible null pointer dereference in + pci1xxx_spi_probe + - s390/pai: fix sampling event removal for PMU device driver + - thermal: gov_power_allocator: Allow binding without cooling devices + - thermal: gov_power_allocator: Allow binding without trip points + - drm/i915/gt: Limit the reserved VM space to only the platforms that need it + - ata: sata_mv: Fix PCI device ID table declaration compilation warning + - ASoC: SOF: amd: fix for false dsp interrupts + - SUNRPC: Fix a slow server-side memory leak with RPC-over-TCP + - riscv: use KERN_INFO in do_trap + - riscv: Fix warning by declaring arch_cpu_idle() as noinstr + - riscv: Disable preemption when using patch_map() + - nfsd: hold a lighter-weight client reference over CB_RECALL_ANY + - lib/stackdepot: move stack_record struct definition into the header + - stackdepot: rename pool_index to pool_index_plus_1 + - x86/retpoline: Add NOENDBR annotation to the SRSO dummy return thunk + - Revert "drm/amd/display: Send DTBCLK disable message on first commit" + - gpio: cdev: check for NULL labels when sanitizing them for irqs + - gpio: cdev: fix missed label sanitizing in debounce_setup() + - ksmbd: don't send oplock break if rename fails + - ksmbd: validate payload size in ipc response + - ksmbd: do not set SMB2_GLOBAL_CAP_ENCRYPTION for SMB 3.1.1 + - ALSA: hda: Add pplcllpl/u members to hdac_ext_stream + - ALSA: hda/realtek - Fix inactive headset mic jack + - ALSA: hda/realtek: Add sound quirks for Lenovo Legion slim 7 16ARHA7 models + - ALSA: hda/realtek: cs35l41: Support ASUS ROG G634JYR + - ALSA: hda/realtek: Update Panasonic CF-SZ6 quirk to support headset with + microphone + - io_uring/kbuf: get rid of lower BGID lists + - io_uring/kbuf: get rid of bl->is_ready + - io_uring/kbuf: protect io_buffer_list teardown with a reference + - io_uring/rw: don't allow multishot reads without NOWAIT support + - io_uring: use private workqueue for exit work + - io_uring/kbuf: hold io_buffer_list reference over mmap + - ASoC: SOF: Add dsp_max_burst_size_in_ms member to snd_sof_pcm_stream + - ASoC: SOF: ipc4-topology: Save the DMA maximum burst size for PCMs + - ASoC: SOF: Intel: hda-pcm: Use dsp_max_burst_size_in_ms to place constraint + - ASoC: SOF: Intel: hda: Implement get_stream_position (Linear Link Position) + - ASoC: SOF: Intel: mtl/lnl: Use the generic get_stream_position callback + - ASoC: SOF: Introduce a new callback pair to be used for PCM delay reporting + - ASoC: SOF: Intel: Set the dai/host get frame/byte counter callbacks + - ASoC: SOF: Intel: hda-common-ops: Do not set the get_stream_position + callback + - ASoC: SOF: ipc4-pcm: Use the snd_sof_pcm_get_dai_frame_counter() for + pcm_delay + - ASoC: SOF: Remove the get_stream_position callback + - ASoC: SOF: ipc4-pcm: Move struct sof_ipc4_timestamp_info definition locally + - ASoC: SOF: ipc4-pcm: Combine the SOF_IPC4_PIPE_PAUSED cases in pcm_trigger + - ASoC: SOF: ipc4-pcm: Invalidate the stream_start_offset in PAUSED state + - ASoC: SOF: sof-pcm: Add pointer callback to sof_ipc_pcm_ops + - ASoC: SOF: ipc4-pcm: Correct the delay calculation + - ASoC: SOF: Intel: hda: Compensate LLP in case it is not reset + - driver core: Introduce device_link_wait_removal() + - of: dynamic: Synchronize of_changeset_destroy() with the devlink removals + - of: module: prevent NULL pointer dereference in vsnprintf() + - x86/mm/pat: fix VM_PAT handling in COW mappings + - x86/mce: Make sure to grab mce_sysfs_mutex in set_bank() + - x86/coco: Require seeding RNG with RDRAND on CoCo systems + - perf/x86/intel/ds: Don't clear ->pebs_data_cfg for the last PEBS event + - riscv: Fix vector state restore in rt_sigreturn() + - arm64/ptrace: Use saved floating point state type to determine SVE layout + - mm/secretmem: fix GUP-fast succeeding on secretmem folios + - selftests/mm: include strings.h for ffsl + - s390/entry: align system call table on 8 bytes + - riscv: Fix spurious errors from __get/put_kernel_nofault + - riscv: process: Fix kernel gp leakage + - smb: client: fix UAF in smb2_reconnect_server() + - smb: client: guarantee refcounted children from parent session + - smb: client: refresh referral without acquiring refpath_lock + - smb: client: handle DFS tcons in cifs_construct_tcon() + - smb: client: serialise cifs_construct_tcon() with cifs_mount_mutex + - smb3: retrying on failed server close + - smb: client: fix potential UAF in cifs_debug_files_proc_show() + - smb: client: fix potential UAF in cifs_stats_proc_write() + - smb: client: fix potential UAF in cifs_stats_proc_show() + - smb: client: fix potential UAF in cifs_dump_full_key() + - smb: client: fix potential UAF in smb2_is_valid_oplock_break() + - smb: client: fix potential UAF in smb2_is_valid_lease_break() + - smb: client: fix potential UAF in is_valid_oplock_break() + - smb: client: fix potential UAF in smb2_is_network_name_deleted() + - smb: client: fix potential UAF in cifs_signal_cifsd_for_reconnect() + - drm/i915/mst: Limit MST+DSC to TGL+ + - drm/i915/mst: Reject FEC+MST on ICL + - drm/i915/dp: Fix the computation for compressed_bpp for DISPLAY < 13 + - drm/i915/gt: Disable HW load balancing for CCS + - drm/i915/gt: Do not generate the command streamer for all the CCS + - drm/i915/gt: Enable only one CCS for compute workload + - drm/xe: Use ring ops TLB invalidation for rebinds + - drm/xe: Rework rebinding + - Revert "x86/mpparse: Register APIC address only once" + - bpf: put uprobe link's path and task in release callback + - bpf: support deferring bpf_link dealloc to after RCU grace period + - efi/libstub: Add generic support for parsing mem_encrypt= + - x86/boot: Move mem_encrypt= parsing to the decompressor + - x86/sme: Move early SME kernel encryption handling into .head.text + - x86/sev: Move early startup code into .head.text section + - Linux 6.8.5 + + * CVE-2024-26926 + - binder: check offset alignment in binder_get_object() + + * CVE-2024-26922 + - drm/amdgpu: validate the parameters of bo mapping operations more clearly + + * CVE-2024-26924 + - netfilter: nft_set_pipapo: do not free live element + + -- Stefan Bader Fri, 07 Jun 2024 14:51:17 +0200 + +linux (6.8.0-35.35) noble; urgency=medium + + * noble/linux: 6.8.0-35.35 -proposed tracker (LP: #2065886) + + * CVE-2024-21823 + - VFIO: Add the SPR_DSA and SPR_IAX devices to the denylist + - dmaengine: idxd: add a new security check to deal with a hardware erratum + - dmaengine: idxd: add a write() method for applications to submit work + + -- Roxana Nicolescu Mon, 20 May 2024 16:26:15 +0200 + +linux (6.8.0-34.34) noble; urgency=medium + + * noble/linux: 6.8.0-34.34 -proposed tracker (LP: #2065167) + + * Packaging resync (LP: #1786013) + - [Packaging] debian.master/dkms-versions -- update from kernel-versions + (main/2024.04.29) + + -- Roxana Nicolescu Wed, 08 May 2024 13:14:41 +0200 + +linux (6.8.0-32.32) noble; urgency=medium + + * noble/linux: 6.8.0-32.32 -proposed tracker (LP: #2064344) + + * Packaging resync (LP: #1786013) + - [Packaging] drop getabis data + - [Packaging] update variants + - [Packaging] update annotations scripts + - [Packaging] debian.master/dkms-versions -- update from kernel-versions + (main/2024.04.29) + + * Enable Nezha board (LP: #1975592) + - [Config] Enable CONFIG_REGULATOR_FIXED_VOLTAGE on riscv64 + + * Enable Nezha board (LP: #1975592) // Enable StarFive VisionFive 2 board + (LP: #2013232) + - [Config] Enable CONFIG_SERIAL_8250_DW on riscv64 + + * RISC-V kernel config is out of sync with other archs (LP: #1981437) + - [Config] Sync riscv64 config with other architectures + + * obsolete out-of-tree ivsc dkms in favor of in-tree one (LP: #2061747) + - ACPI: scan: Defer enumeration of devices with a _DEP pointing to IVSC device + - Revert "mei: vsc: Call wake_up() in the threaded IRQ handler" + - mei: vsc: Unregister interrupt handler for system suspend + - media: ipu-bridge: Add ov01a10 in Dell XPS 9315 + - SAUCE: media: ipu-bridge: Support more sensors + + * Fix after-suspend-mediacard/sdhc-insert test failed (LP: #2042500) + - PCI/ASPM: Move pci_configure_ltr() to aspm.c + - PCI/ASPM: Always build aspm.c + - PCI/ASPM: Move pci_save_ltr_state() to aspm.c + - PCI/ASPM: Save L1 PM Substates Capability for suspend/resume + - PCI/ASPM: Call pci_save_ltr_state() from pci_save_pcie_state() + - PCI/ASPM: Disable L1 before configuring L1 Substates + - PCI/ASPM: Update save_state when configuration changes + + * RTL8852BE fw security fail then lost WIFI function during suspend/resume + cycle (LP: #2063096) + - wifi: rtw89: download firmware with five times retry + + * intel_rapl_common: Add support for ARL and LNL (LP: #2061953) + - powercap: intel_rapl: Add support for Lunar Lake-M paltform + - powercap: intel_rapl: Add support for Arrow Lake + + * Kernel panic during checkbox stress_ng_test on Grace running noble 6.8 + (arm64+largemem) kernel (LP: #2058557) + - aio: Fix null ptr deref in aio_complete() wakeup + + * Avoid creating non-working backlight sysfs knob from ASUS board + (LP: #2060422) + - platform/x86: asus-wmi: Consider device is absent when the read is ~0 + + * Include cifs.ko in linux-modules package (LP: #2042546) + - [Packaging] Replace fs/cifs with fs/smb/client in inclusion list + + * Add Real-time Linux Analysis tool (rtla) to linux-tools (LP: #2059080) + - SAUCE: rtla: fix deb build + - [Packaging] add Real-time Linux Analysis tool (rtla) to linux-tools + - [Packaging] update dependencies for rtla + + * Noble update: v6.8.4 upstream stable release (LP: #2060533) + - Revert "workqueue: Shorten events_freezable_power_efficient name" + - Revert "workqueue: Don't call cpumask_test_cpu() with -1 CPU in + wq_update_node_max_active()" + - Revert "workqueue: Implement system-wide nr_active enforcement for unbound + workqueues" + - Revert "workqueue: Introduce struct wq_node_nr_active" + - Revert "workqueue: RCU protect wq->dfl_pwq and implement accessors for it" + - Revert "workqueue: Make wq_adjust_max_active() round-robin pwqs while + activating" + - Revert "workqueue: Move nr_active handling into helpers" + - Revert "workqueue: Replace pwq_activate_inactive_work() with + [__]pwq_activate_work()" + - Revert "workqueue: Factor out pwq_is_empty()" + - Revert "workqueue: Move pwq->max_active to wq->max_active" + - Revert "workqueue.c: Increase workqueue name length" + - Linux 6.8.4 + + * Noble update: v6.8.3 upstream stable release (LP: #2060531) + - drm/vmwgfx: Unmap the surface before resetting it on a plane state + - wifi: brcmfmac: Fix use-after-free bug in brcmf_cfg80211_detach + - wifi: brcmfmac: avoid invalid list operation when vendor attach fails + - media: staging: ipu3-imgu: Set fields before media_entity_pads_init() + - arm64: dts: qcom: sc7280: Add additional MSI interrupts + - remoteproc: virtio: Fix wdg cannot recovery remote processor + - clk: qcom: gcc-sdm845: Add soft dependency on rpmhpd + - smack: Set SMACK64TRANSMUTE only for dirs in smack_inode_setxattr() + - smack: Handle SMACK64TRANSMUTE in smack_inode_setsecurity() + - arm: dts: marvell: Fix maxium->maxim typo in brownstone dts + - drm/vmwgfx: Fix possible null pointer derefence with invalid contexts + - arm64: dts: qcom: sm8450-hdk: correct AMIC4 and AMIC5 microphones + - serial: max310x: fix NULL pointer dereference in I2C instantiation + - drm/vmwgfx: Fix the lifetime of the bo cursor memory + - pci_iounmap(): Fix MMIO mapping leak + - media: xc4000: Fix atomicity violation in xc4000_get_frequency + - media: mc: Add local pad to pipeline regardless of the link state + - media: mc: Fix flags handling when creating pad links + - media: nxp: imx8-isi: Check whether crossbar pad is non-NULL before access + - media: mc: Add num_links flag to media_pad + - media: mc: Rename pad variable to clarify intent + - media: mc: Expand MUST_CONNECT flag to always require an enabled link + - media: nxp: imx8-isi: Mark all crossbar sink pads as MUST_CONNECT + - md: use RCU lock to protect traversal in md_spares_need_change() + - KVM: Always flush async #PF workqueue when vCPU is being destroyed + - arm64: dts: qcom: sm8550-qrd: correct WCD9385 TX port mapping + - arm64: dts: qcom: sm8550-mtp: correct WCD9385 TX port mapping + - cpufreq: amd-pstate: Fix min_perf assignment in amd_pstate_adjust_perf() + - thermal/intel: Fix intel_tcc_get_temp() to support negative CPU temperature + - powercap: intel_rapl: Fix a NULL pointer dereference + - powercap: intel_rapl: Fix locking in TPMI RAPL + - powercap: intel_rapl_tpmi: Fix a register bug + - powercap: intel_rapl_tpmi: Fix System Domain probing + - powerpc/smp: Adjust nr_cpu_ids to cover all threads of a core + - powerpc/smp: Increase nr_cpu_ids to include the boot CPU + - sparc64: NMI watchdog: fix return value of __setup handler + - sparc: vDSO: fix return value of __setup handler + - selftests/mqueue: Set timeout to 180 seconds + - pinctrl: qcom: sm8650-lpass-lpi: correct Kconfig name + - ext4: correct best extent lstart adjustment logic + - drm/amdgpu/display: Address kdoc for 'is_psr_su' in 'fill_dc_dirty_rects' + - block: Clear zone limits for a non-zoned stacked queue + - kasan/test: avoid gcc warning for intentional overflow + - bounds: support non-power-of-two CONFIG_NR_CPUS + - fat: fix uninitialized field in nostale filehandles + - fuse: fix VM_MAYSHARE and direct_io_allow_mmap + - mfd: twl: Select MFD_CORE + - ubifs: Set page uptodate in the correct place + - ubi: Check for too small LEB size in VTBL code + - ubi: correct the calculation of fastmap size + - ubifs: ubifs_symlink: Fix memleak of inode->i_link in error path + - mtd: rawnand: meson: fix scrambling mode value in command macro + - md/md-bitmap: fix incorrect usage for sb_index + - x86/nmi: Fix the inverse "in NMI handler" check + - parisc/unaligned: Rewrite 64-bit inline assembly of emulate_ldd() + - parisc: Avoid clobbering the C/B bits in the PSW with tophys and tovirt + macros + - parisc: Fix ip_fast_csum + - parisc: Fix csum_ipv6_magic on 32-bit systems + - parisc: Fix csum_ipv6_magic on 64-bit systems + - parisc: Strip upper 32 bit of sum in csum_ipv6_magic for 64-bit builds + - md/raid5: fix atomicity violation in raid5_cache_count + - iio: adc: rockchip_saradc: fix bitmask for channels on SARADCv2 + - iio: adc: rockchip_saradc: use mask for write_enable bitfield + - docs: Restore "smart quotes" for quotes + - cpufreq: Limit resolving a frequency to policy min/max + - PM: suspend: Set mem_sleep_current during kernel command line setup + - vfio/pds: Always clear the save/restore FDs on reset + - clk: qcom: gcc-ipq5018: fix terminating of frequency table arrays + - clk: qcom: gcc-ipq6018: fix terminating of frequency table arrays + - clk: qcom: gcc-ipq8074: fix terminating of frequency table arrays + - clk: qcom: gcc-ipq9574: fix terminating of frequency table arrays + - clk: qcom: camcc-sc8280xp: fix terminating of frequency table arrays + - clk: qcom: mmcc-apq8084: fix terminating of frequency table arrays + - clk: qcom: mmcc-msm8974: fix terminating of frequency table arrays + - usb: xhci: Add error handling in xhci_map_urb_for_dma + - powerpc/fsl: Fix mfpmr build errors with newer binutils + - USB: serial: ftdi_sio: add support for GMC Z216C Adapter IR-USB + - USB: serial: add device ID for VeriFone adapter + - USB: serial: cp210x: add ID for MGP Instruments PDS100 + - wifi: mac80211: track capability/opmode NSS separately + - USB: serial: option: add MeiG Smart SLM320 product + - KVM: x86/xen: inject vCPU upcall vector when local APIC is enabled + - USB: serial: cp210x: add pid/vid for TDK NC0110013M and MM0110113M + - PM: sleep: wakeirq: fix wake irq warning in system suspend + - mmc: tmio: avoid concurrent runs of mmc_request_done() + - fuse: replace remaining make_bad_inode() with fuse_make_bad() + - fuse: fix root lookup with nonzero generation + - fuse: don't unhash root + - usb: typec: ucsi: Clean up UCSI_CABLE_PROP macros + - usb: dwc3-am62: fix module unload/reload behavior + - usb: dwc3-am62: Disable wakeup at remove + - serial: core: only stop transmit when HW fifo is empty + - serial: Lock console when calling into driver before registration + - btrfs: qgroup: always free reserved space for extent records + - btrfs: fix off-by-one chunk length calculation at contains_pending_extent() + - wifi: rtw88: Add missing VID/PIDs for 8811CU and 8821CU + - docs: Makefile: Add dependency to $(YNL_INDEX) for targets other than + htmldocs + - PCI/PM: Drain runtime-idle callbacks before driver removal + - PCI/DPC: Quirk PIO log size for Intel Raptor Lake Root Ports + - Revert "Revert "md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d"" + - md: don't clear MD_RECOVERY_FROZEN for new dm-raid until resume + - md: export helpers to stop sync_thread + - md: export helper md_is_rdwr() + - md: add a new helper reshape_interrupted() + - dm-raid: really frozen sync_thread during suspend + - md/dm-raid: don't call md_reap_sync_thread() directly + - dm-raid: add a new helper prepare_suspend() in md_personality + - dm-raid456, md/raid456: fix a deadlock for dm-raid456 while io concurrent + with reshape + - dm-raid: fix lockdep waring in "pers->hot_add_disk" + - powerpc: xor_vmx: Add '-mhard-float' to CFLAGS + - mac802154: fix llsec key resources release in mac802154_llsec_key_del + - mm: swap: fix race between free_swap_and_cache() and swapoff() + - mmc: core: Fix switch on gp3 partition + - Bluetooth: btnxpuart: Fix btnxpuart_close + - leds: trigger: netdev: Fix kernel panic on interface rename trig notify + - drm/etnaviv: Restore some id values + - landlock: Warn once if a Landlock action is requested while disabled + - io_uring: fix mshot read defer taskrun cqe posting + - hwmon: (amc6821) add of_match table + - io_uring: fix io_queue_proc modifying req->flags + - ext4: fix corruption during on-line resize + - nvmem: meson-efuse: fix function pointer type mismatch + - slimbus: core: Remove usage of the deprecated ida_simple_xx() API + - phy: tegra: xusb: Add API to retrieve the port number of phy + - usb: gadget: tegra-xudc: Fix USB3 PHY retrieval logic + - speakup: Fix 8bit characters from direct synth + - debugfs: fix wait/cancellation handling during remove + - PCI/AER: Block runtime suspend when handling errors + - io_uring/net: correctly handle multishot recvmsg retry setup + - io_uring: fix mshot io-wq checks + - PCI: qcom: Disable ASPM L0s for sc8280xp, sa8540p and sa8295p + - sparc32: Fix parport build with sparc32 + - nfs: fix UAF in direct writes + - NFS: Read unlock folio on nfs_page_create_from_folio() error + - kbuild: Move -Wenum-{compare-conditional,enum-conversion} into W=1 + - PCI: qcom: Enable BDF to SID translation properly + - PCI: dwc: endpoint: Fix advertised resizable BAR size + - PCI: hv: Fix ring buffer size calculation + - cifs: prevent updating file size from server if we have a read/write lease + - cifs: allow changing password during remount + - thermal/drivers/mediatek: Fix control buffer enablement on MT7896 + - vfio/pci: Disable auto-enable of exclusive INTx IRQ + - vfio/pci: Lock external INTx masking ops + - vfio/platform: Disable virqfds on cleanup + - vfio/platform: Create persistent IRQ handlers + - vfio/fsl-mc: Block calling interrupt handler without trigger + - tpm,tpm_tis: Avoid warning splat at shutdown + - ksmbd: replace generic_fillattr with vfs_getattr + - ksmbd: retrieve number of blocks using vfs_getattr in + set_file_allocation_info + - platform/x86/intel/tpmi: Change vsec offset to u64 + - io_uring/rw: return IOU_ISSUE_SKIP_COMPLETE for multishot retry + - io_uring: clean rings on NO_MMAP alloc fail + - ring-buffer: Do not set shortest_full when full target is hit + - ring-buffer: Fix full_waiters_pending in poll + - ring-buffer: Use wait_event_interruptible() in ring_buffer_wait() + - tracing/ring-buffer: Fix wait_on_pipe() race + - dlm: fix user space lkb refcounting + - soc: fsl: qbman: Always disable interrupts when taking cgr_lock + - soc: fsl: qbman: Use raw spinlock for cgr_lock + - s390/zcrypt: fix reference counting on zcrypt card objects + - drm/probe-helper: warn about negative .get_modes() + - drm/panel: do not return negative error codes from drm_panel_get_modes() + - drm/exynos: do not return negative values from .get_modes() + - drm/imx/ipuv3: do not return negative values from .get_modes() + - drm/vc4: hdmi: do not return negative values from .get_modes() + - clocksource/drivers/timer-riscv: Clear timer interrupt on timer + initialization + - memtest: use {READ,WRITE}_ONCE in memory scanning + - Revert "block/mq-deadline: use correct way to throttling write requests" + - lsm: use 32-bit compatible data types in LSM syscalls + - lsm: handle the NULL buffer case in lsm_fill_user_ctx() + - f2fs: mark inode dirty for FI_ATOMIC_COMMITTED flag + - f2fs: truncate page cache before clearing flags when aborting atomic write + - nilfs2: fix failure to detect DAT corruption in btree and direct mappings + - nilfs2: prevent kernel bug at submit_bh_wbc() + - cifs: make sure server interfaces are requested only for SMB3+ + - cifs: reduce warning log level for server not advertising interfaces + - cifs: open_cached_dir(): add FILE_READ_EA to desired access + - mtd: rawnand: Fix and simplify again the continuous read derivations + - mtd: rawnand: Add a helper for calculating a page index + - mtd: rawnand: Ensure all continuous terms are always in sync + - mtd: rawnand: Constrain even more when continuous reads are enabled + - cpufreq: dt: always allocate zeroed cpumask + - io_uring/futex: always remove futex entry for cancel all + - io_uring/waitid: always remove waitid entry for cancel all + - x86/CPU/AMD: Update the Zenbleed microcode revisions + - ksmbd: fix slab-out-of-bounds in smb_strndup_from_utf16() + - net: esp: fix bad handling of pages from page_pool + - NFSD: Fix nfsd_clid_class use of __string_len() macro + - drm/i915: Add missing ; to __assign_str() macros in tracepoint code + - net: hns3: tracing: fix hclgevf trace event strings + - cxl/trace: Properly initialize cxl_poison region name + - ksmbd: fix potencial out-of-bounds when buffer offset is invalid + - virtio: reenable config if freezing device failed + - LoongArch: Change __my_cpu_offset definition to avoid mis-optimization + - LoongArch: Define the __io_aw() hook as mmiowb() + - LoongArch/crypto: Clean up useless assignment operations + - wireguard: netlink: check for dangling peer via is_dead instead of empty + list + - wireguard: netlink: access device through ctx instead of peer + - wireguard: selftests: set RISCV_ISA_FALLBACK on riscv{32,64} + - ahci: asm1064: asm1166: don't limit reported ports + - drm/amd/display: Change default size for dummy plane in DML2 + - drm/amdgpu: amdgpu_ttm_gart_bind set gtt bound flag + - drm/amdgpu/pm: Fix NULL pointer dereference when get power limit + - drm/amdgpu/pm: Check the validity of overdiver power limit + - drm/amd/display: Override min required DCFCLK in dml1_validate + - drm/amd/display: Allow dirty rects to be sent to dmub when abm is active + - drm/amd/display: Init DPPCLK from SMU on dcn32 + - drm/amd/display: Update odm when ODM combine is changed on an otg master + pipe with no plane + - drm/amd/display: Fix idle check for shared firmware state + - drm/amd/display: Amend coasting vtotal for replay low hz + - drm/amd/display: Lock all enabled otg pipes even with no planes + - drm/amd/display: Implement wait_for_odm_update_pending_complete + - drm/amd/display: Return the correct HDCP error code + - drm/amd/display: Add a dc_state NULL check in dc_state_release + - drm/amd/display: Fix noise issue on HDMI AV mute + - dm snapshot: fix lockup in dm_exception_table_exit + - x86/pm: Work around false positive kmemleak report in msr_build_context() + - wifi: brcmfmac: add per-vendor feature detection callback + - wifi: brcmfmac: cfg80211: Use WSEC to set SAE password + - wifi: brcmfmac: Demote vendor-specific attach/detach messages to info + - drm/ttm: Make sure the mapped tt pages are decrypted when needed + - drm/amd/display: Unify optimize_required flags and VRR adjustments + - drm/amd/display: Add more checks for exiting idle in DC + - btrfs: add set_folio_extent_mapped() helper + - btrfs: replace sb::s_blocksize by fs_info::sectorsize + - btrfs: add helpers to get inode from page/folio pointers + - btrfs: add helpers to get fs_info from page/folio pointers + - btrfs: add helper to get fs_info from struct inode pointer + - btrfs: qgroup: validate btrfs_qgroup_inherit parameter + - vfio: Introduce interface to flush virqfd inject workqueue + - vfio/pci: Create persistent INTx handler + - drm/bridge: add ->edid_read hook and drm_bridge_edid_read() + - drm/bridge: lt8912b: use drm_bridge_edid_read() + - drm/bridge: lt8912b: clear the EDID property on failures + - drm/bridge: lt8912b: do not return negative values from .get_modes() + - drm/amd/display: Remove pixle rate limit for subvp + - drm/amd/display: Revert Remove pixle rate limit for subvp + - workqueue: Shorten events_freezable_power_efficient name + - drm/amd/display: Use freesync when `DRM_EDID_FEATURE_CONTINUOUS_FREQ` found + - netfilter: nf_tables: reject constant set with timeout + - Revert "crypto: pkcs7 - remove sha1 support" + - x86/efistub: Call mixed mode boot services on the firmware's stack + - ASoC: amd: yc: Revert "Fix non-functional mic on Lenovo 21J2" + - ASoC: amd: yc: Revert "add new YC platform variant (0x63) support" + - Fix memory leak in posix_clock_open() + - wifi: rtw88: 8821cu: Fix connection failure + - x86/Kconfig: Remove CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT + - x86/sev: Fix position dependent variable references in startup code + - clocksource/drivers/arm_global_timer: Fix maximum prescaler value + - ARM: 9352/1: iwmmxt: Remove support for PJ4/PJ4B cores + - ARM: 9359/1: flush: check if the folio is reserved for no-mapping addresses + - entry: Respect changes to system call number by trace_sys_enter() + - swiotlb: Fix double-allocation of slots due to broken alignment handling + - swiotlb: Honour dma_alloc_coherent() alignment in swiotlb_alloc() + - swiotlb: Fix alignment checks when both allocation and DMA masks are present + - iommu/dma: Force swiotlb_max_mapping_size on an untrusted device + - printk: Update @console_may_schedule in console_trylock_spinning() + - irqchip/renesas-rzg2l: Flush posted write in irq_eoi() + - irqchip/renesas-rzg2l: Rename rzg2l_tint_eoi() + - irqchip/renesas-rzg2l: Rename rzg2l_irq_eoi() + - irqchip/renesas-rzg2l: Prevent spurious interrupts when setting trigger type + - kprobes/x86: Use copy_from_kernel_nofault() to read from unsafe address + - efi/libstub: fix efi_random_alloc() to allocate memory at alloc_min or + higher address + - x86/mpparse: Register APIC address only once + - x86/fpu: Keep xfd_state in sync with MSR_IA32_XFD + - efi: fix panic in kdump kernel + - pwm: img: fix pwm clock lookup + - selftests/mm: Fix build with _FORTIFY_SOURCE + - btrfs: handle errors returned from unpin_extent_cache() + - btrfs: fix warning messages not printing interval at unpin_extent_range() + - btrfs: do not skip re-registration for the mounted device + - mfd: intel-lpss: Switch to generalized quirk table + - mfd: intel-lpss: Introduce QUIRK_CLOCK_DIVIDER_UNITY for XPS 9530 + - drm/i915: Replace a memset() with zero initialization + - drm/i915: Try to preserve the current shared_dpll for fastset on type-c + ports + - drm/i915: Include the PLL name in the debug messages + - drm/i915: Suppress old PLL pipe_mask checks for MG/TC/TBT PLLs + - crypto: iaa - Fix nr_cpus < nr_iaa case + - drm/amd/display: Prevent crash when disable stream + - ALSA: hda/tas2781: remove digital gain kcontrol + - ALSA: hda/tas2781: add locks to kcontrols + - mm: zswap: fix writeback shinker GFP_NOIO/GFP_NOFS recursion + - init: open /initrd.image with O_LARGEFILE + - x86/efistub: Add missing boot_params for mixed mode compat entry + - efi/libstub: Cast away type warning in use of max() + - x86/efistub: Reinstate soft limit for initrd loading + - prctl: generalize PR_SET_MDWE support check to be per-arch + - ARM: prctl: reject PR_SET_MDWE on pre-ARMv6 + - tmpfs: fix race on handling dquot rbtree + - btrfs: validate device maj:min during open + - btrfs: fix race in read_extent_buffer_pages() + - btrfs: zoned: don't skip block groups with 100% zone unusable + - btrfs: zoned: use zone aware sb location for scrub + - btrfs: zoned: fix use-after-free in do_zone_finish() + - wifi: mac80211: check/clear fast rx for non-4addr sta VLAN changes + - wifi: cfg80211: add a flag to disable wireless extensions + - wifi: iwlwifi: mvm: disable MLO for the time being + - wifi: iwlwifi: fw: don't always use FW dump trig + - wifi: iwlwifi: mvm: handle debugfs names more carefully + - Revert "drm/amd/display: Fix sending VSC (+ colorimetry) packets for DP/eDP + displays without PSR" + - fbdev: Select I/O-memory framebuffer ops for SBus + - exec: Fix NOMMU linux_binprm::exec in transfer_args_to_stack() + - hexagon: vmlinux.lds.S: handle attributes section + - mm: cachestat: fix two shmem bugs + - selftests/mm: sigbus-wp test requires UFFD_FEATURE_WP_HUGETLBFS_SHMEM + - selftests/mm: fix ARM related issue with fork after pthread_create + - mmc: sdhci-omap: re-tuning is needed after a pm transition to support emmc + HS200 mode + - mmc: core: Initialize mmc_blk_ioc_data + - mmc: core: Avoid negative index with array access + - sdhci-of-dwcmshc: disable PM runtime in dwcmshc_remove() + - block: Do not force full zone append completion in req_bio_endio() + - thermal: devfreq_cooling: Fix perf state when calculate dfc res_util + - Revert "thermal: core: Don't update trip points inside the hysteresis range" + - nouveau/dmem: handle kcalloc() allocation failure + - net: ll_temac: platform_get_resource replaced by wrong function + - net: wan: framer: Add missing static inline qualifiers + - net: phy: qcom: at803x: fix kernel panic with at8031_probe + - drm/xe/query: fix gt_id bounds check + - drm/dp: Fix divide-by-zero regression on DP MST unplug with nouveau + - drm/vmwgfx: Create debugfs ttm_resource_manager entry only if needed + - drm/amdkfd: fix TLB flush after unmap for GFX9.4.2 + - drm/amdgpu: fix deadlock while reading mqd from debugfs + - drm/amd/display: Remove MPC rate control logic from DCN30 and above + - drm/amd/display: Set DCN351 BB and IP the same as DCN35 + - drm/i915/hwmon: Fix locking inversion in sysfs getter + - drm/i915/vma: Fix UAF on destroy against retire race + - drm/i915/bios: Tolerate devdata==NULL in + intel_bios_encoder_supports_dp_dual_mode() + - drm/i915/vrr: Generate VRR "safe window" for DSB + - drm/i915/dsi: Go back to the previous INIT_OTP/DISPLAY_ON order, mostly + - drm/i915/dsb: Fix DSB vblank waits when using VRR + - drm/i915: Do not match JSL in ehl_combo_pll_div_frac_wa_needed() + - drm/i915: Pre-populate the cursor physical dma address + - drm/i915/gt: Reset queue_priority_hint on parking + - drm/amd/display: Fix bounds check for dcn35 DcfClocks + - Bluetooth: hci_sync: Fix not checking error on hci_cmd_sync_cancel_sync + - mtd: spinand: Add support for 5-byte IDs + - Revert "usb: phy: generic: Get the vbus supply" + - usb: cdc-wdm: close race between read and workqueue + - usb: misc: ljca: Fix double free in error handling path + - USB: UAS: return ENODEV when submit urbs fail with device not attached + - vfio/pds: Make sure migration file isn't accessed after reset + - ring-buffer: Make wake once of ring_buffer_wait() more robust + - btrfs: fix extent map leak in unexpected scenario at unpin_extent_cache() + - ALSA: sh: aica: reorder cleanup operations to avoid UAF bugs + - scsi: ufs: qcom: Provide default cycles_in_1us value + - scsi: sd: Fix TCG OPAL unlock on system resume + - scsi: core: Fix unremoved procfs host directory regression + - staging: vc04_services: changen strncpy() to strscpy_pad() + - staging: vc04_services: fix information leak in create_component() + - genirq: Introduce IRQF_COND_ONESHOT and use it in pinctrl-amd + - usb: dwc3: Properly set system wakeup + - USB: core: Fix deadlock in usb_deauthorize_interface() + - USB: core: Add hub_get() and hub_put() routines + - USB: core: Fix deadlock in port "disable" sysfs attribute + - usb: dwc2: host: Fix remote wakeup from hibernation + - usb: dwc2: host: Fix hibernation flow + - usb: dwc2: host: Fix ISOC flow in DDMA mode + - usb: dwc2: gadget: Fix exiting from clock gating + - usb: dwc2: gadget: LPM flow fix + - usb: udc: remove warning when queue disabled ep + - usb: typec: ucsi: Fix race between typec_switch and role_switch + - usb: typec: tcpm: fix double-free issue in tcpm_port_unregister_pd() + - usb: typec: tcpm: Correct port source pdo array in pd_set callback + - usb: typec: tcpm: Update PD of Type-C port upon pd_set + - usb: typec: Return size of buffer if pd_set operation succeeds + - usb: typec: ucsi: Clear EVENT_PENDING under PPM lock + - usb: typec: ucsi: Ack unsupported commands + - usb: typec: ucsi_acpi: Refactor and fix DELL quirk + - usb: typec: ucsi: Clear UCSI_CCI_RESET_COMPLETE before reset + - scsi: qla2xxx: Prevent command send on chip reset + - scsi: qla2xxx: Fix N2N stuck connection + - scsi: qla2xxx: Split FCE|EFT trace control + - scsi: qla2xxx: Update manufacturer detail + - scsi: qla2xxx: NVME|FCP prefer flag not being honored + - scsi: qla2xxx: Fix command flush on cable pull + - scsi: qla2xxx: Fix double free of the ha->vp_map pointer + - scsi: qla2xxx: Fix double free of fcport + - scsi: qla2xxx: Change debug message during driver unload + - scsi: qla2xxx: Delay I/O Abort on PCI error + - x86/bugs: Fix the SRSO mitigation on Zen3/4 + - crash: use macro to add crashk_res into iomem early for specific arch + - drm/amd/display: fix IPX enablement + - x86/bugs: Use fixed addressing for VERW operand + - Revert "x86/bugs: Use fixed addressing for VERW operand" + - usb: dwc3: pci: Drop duplicate ID + - scsi: lpfc: Correct size for cmdwqe/rspwqe for memset() + - scsi: lpfc: Correct size for wqe for memset() + - scsi: libsas: Add a helper sas_get_sas_addr_and_dev_type() + - scsi: libsas: Fix disk not being scanned in after being removed + - perf/x86/amd/core: Update and fix stalled-cycles-* events for Zen 2 and + later + - x86/sev: Skip ROM range scans and validation for SEV-SNP guests + - tools/resolve_btfids: fix build with musl libc + - drm/amdgpu: fix use-after-free bug + - drm/sched: fix null-ptr-deref in init entity + - Linux 6.8.3 + - [Config] updateconfigs following v6.8.3 import + + * Noble update: v6.8.3 upstream stable release (LP: #2060531) // + [Ubuntu-24.04] Hugepage memory is not getting released even after destroying + the guest! (LP: #2062556) + - block: Fix page refcounts for unaligned buffers in __bio_release_pages() + + * [SPR][EMR][GNR] TDX: efi: TD Measurement support for kernel cmdline/initrd + sections from EFI stub (LP: #2060130) + - efi/libstub: Use TPM event typedefs from the TCG PC Client spec + - efi/tpm: Use symbolic GUID name from spec for final events table + - efi/libstub: Add Confidential Computing (CC) measurement typedefs + - efi/libstub: Measure into CC protocol if TCG2 protocol is absent + - efi/libstub: Add get_event_log() support for CC platforms + - x86/efistub: Remap kernel text read-only before dropping NX attribute + + * Fix acpi_power_meter accessing IPMI region before it's ready (LP: #2059263) + - ACPI: IPMI: Add helper to wait for when SMI is selected + - hwmon: (acpi_power_meter) Ensure IPMI space handler is ready on Dell systems + + * Drop fips-checks script from trees (LP: #2055083) + - [Packaging] Remove fips-checks script + + * alsa/realtek: adjust max output valume for headphone on 2 LG machines + (LP: #2058573) + - ALSA: hda/realtek: fix the hp playback volume issue for LG machines + + * Noble update: v6.8.2 upstream stable release (LP: #2060097) + - do_sys_name_to_handle(): use kzalloc() to fix kernel-infoleak + - workqueue.c: Increase workqueue name length + - workqueue: Move pwq->max_active to wq->max_active + - workqueue: Factor out pwq_is_empty() + - workqueue: Replace pwq_activate_inactive_work() with [__]pwq_activate_work() + - workqueue: Move nr_active handling into helpers + - workqueue: Make wq_adjust_max_active() round-robin pwqs while activating + - workqueue: RCU protect wq->dfl_pwq and implement accessors for it + - workqueue: Introduce struct wq_node_nr_active + - workqueue: Implement system-wide nr_active enforcement for unbound + workqueues + - workqueue: Don't call cpumask_test_cpu() with -1 CPU in + wq_update_node_max_active() + - iomap: clear the per-folio dirty bits on all writeback failures + - fs: Fix rw_hint validation + - io_uring: remove looping around handling traditional task_work + - io_uring: remove unconditional looping in local task_work handling + - s390/dasd: Use dev_*() for device log messages + - s390/dasd: fix double module refcount decrement + - fs/hfsplus: use better @opf description + - md: fix kmemleak of rdev->serial + - rcu/exp: Fix RCU expedited parallel grace period kworker allocation failure + recovery + - rcu/exp: Handle RCU expedited grace period kworker allocation failure + - fs/select: rework stack allocation hack for clang + - block: fix deadlock between bd_link_disk_holder and partition scan + - md: Don't clear MD_CLOSING when the raid is about to stop + - kunit: Setup DMA masks on the kunit device + - ovl: Always reject mounting over case-insensitive directories + - kunit: test: Log the correct filter string in executor_test + - lib/cmdline: Fix an invalid format specifier in an assertion msg + - lib: memcpy_kunit: Fix an invalid format specifier in an assertion msg + - time: test: Fix incorrect format specifier + - rtc: test: Fix invalid format specifier. + - net: test: Fix printf format specifier in skb_segment kunit test + - drm/xe/tests: Fix printf format specifiers in xe_migrate test + - drm: tests: Fix invalid printf format specifiers in KUnit tests + - md/raid1: factor out helpers to add rdev to conf + - md/raid1: record nonrot rdevs while adding/removing rdevs to conf + - md/raid1: fix choose next idle in read_balance() + - io_uring/net: unify how recvmsg and sendmsg copy in the msghdr + - io_uring/net: move receive multishot out of the generic msghdr path + - io_uring/net: fix overflow check in io_recvmsg_mshot_prep() + - nvme: host: fix double-free of struct nvme_id_ns in ns_update_nuse() + - aoe: fix the potential use-after-free problem in aoecmd_cfg_pkts + - x86/mm: Ensure input to pfn_to_kaddr() is treated as a 64-bit type + - x86/resctrl: Remove hard-coded memory bandwidth limit + - x86/resctrl: Read supported bandwidth sources from CPUID + - x86/resctrl: Implement new mba_MBps throttling heuristic + - x86/sme: Fix memory encryption setting if enabled by default and not + overridden + - timekeeping: Fix cross-timestamp interpolation on counter wrap + - timekeeping: Fix cross-timestamp interpolation corner case decision + - timekeeping: Fix cross-timestamp interpolation for non-x86 + - x86/asm: Remove the __iomem annotation of movdir64b()'s dst argument + - sched/fair: Take the scheduling domain into account in select_idle_smt() + - sched/fair: Take the scheduling domain into account in select_idle_core() + - wifi: ath10k: fix NULL pointer dereference in + ath10k_wmi_tlv_op_pull_mgmt_tx_compl_ev() + - wifi: b43: Stop/wake correct queue in DMA Tx path when QoS is disabled + - wifi: b43: Stop/wake correct queue in PIO Tx path when QoS is disabled + - wifi: b43: Stop correct queue in DMA worker when QoS is disabled + - wifi: b43: Disable QoS for bcm4331 + - wifi: wilc1000: fix declarations ordering + - wifi: wilc1000: fix RCU usage in connect path + - wifi: ath11k: add support to select 6 GHz regulatory type + - wifi: ath11k: store cur_regulatory_info for each radio + - wifi: ath11k: fix a possible dead lock caused by ab->base_lock + - wifi: rtl8xxxu: add cancel_work_sync() for c2hcmd_work + - wifi: wilc1000: do not realloc workqueue everytime an interface is added + - wifi: wilc1000: fix multi-vif management when deleting a vif + - wifi: mwifiex: debugfs: Drop unnecessary error check for + debugfs_create_dir() + - ARM: dts: renesas: r8a73a4: Fix external clocks and clock rate + - arm64: dts: qcom: x1e80100: drop qcom,drv-count + - arm64: dts: qcom: sc8180x: Hook up VDD_CX as GCC parent domain + - arm64: dts: qcom: sc8180x: Fix up big CPU idle state entry latency + - arm64: dts: qcom: sc8180x: Add missing CPU off state + - arm64: dts: qcom: sc8180x: Fix eDP PHY power-domains + - arm64: dts: qcom: sc8180x: Don't hold MDP core clock at FMAX + - arm64: dts: qcom: sc8180x: Require LOW_SVS vote for MMCX if DISPCC is on + - arm64: dts: qcom: sc8180x: Add missing CPU<->MDP_CFG path + - arm64: dts: qcom: sc8180x: Shrink aoss_qmp register space size + - cpufreq: brcmstb-avs-cpufreq: add check for cpufreq_cpu_get's return value + - cpufreq: mediatek-hw: Wait for CPU supplies before probing + - sock_diag: annotate data-races around sock_diag_handlers[family] + - inet_diag: annotate data-races around inet_diag_table[] + - bpftool: Silence build warning about calloc() + - selftests/bpf: Fix potential premature unload in bpf_testmod + - libbpf: Apply map_set_def_max_entries() for inner_maps on creation + - selftest/bpf: Add map_in_maps with BPF_MAP_TYPE_PERF_EVENT_ARRAY values + - bpftool: Fix wrong free call in do_show_link + - wifi: ath12k: Fix issues in channel list update + - selftests/bpf: Fix the flaky tc_redirect_dtime test + - selftests/bpf: Wait for the netstamp_needed_key static key to be turned on + - wifi: cfg80211: add RNR with reporting AP information + - wifi: mac80211: use deflink and fix typo in link ID check + - wifi: iwlwifi: change link id in time event to s8 + - af_unix: Annotate data-race of gc_in_progress in wait_for_unix_gc(). + - arm64: dts: qcom: sm8450: Add missing interconnects to serial + - soc: qcom: socinfo: rename PM2250 to PM4125 + - arm64: dts: qcom: sc7280: Add static properties to cryptobam + - arm64: dts: qcom: qcm6490-fairphone-fp5: Add missing reserved-memory + - arm64: dts: qcom: sdm845-oneplus-common: improve DAI node naming + - arm64: dts: qcom: rename PM2250 to PM4125 + - cpufreq: mediatek-hw: Don't error out if supply is not found + - libbpf: Fix faccessat() usage on Android + - libbpf: fix __arg_ctx type enforcement for perf_event programs + - pmdomain: qcom: rpmhpd: Drop SA8540P gfx.lvl + - arm64: dts: qcom: sa8540p: Drop gfx.lvl as power-domain for gpucc + - arm64: dts: renesas: r8a779g0: Restore sort order + - arm64: dts: renesas: r8a779g0: Add missing SCIF_CLK2 + - selftests/bpf: Disable IPv6 for lwt_redirect test + - arm64: dts: imx8mm-kontron: Disable pullups for I2C signals on OSM-S i.MX8MM + - arm64: dts: imx8mm-kontron: Disable pullups for I2C signals on SL/BL i.MX8MM + - arm64: dts: imx8mm-kontron: Disable pullups for onboard UART signals on BL + OSM-S board + - arm64: dts: imx8mm-kontron: Disable pullups for onboard UART signals on BL + board + - arm64: dts: imx8mm-kontron: Disable pull resistors for SD card signals on BL + OSM-S board + - arm64: dts: imx8mm-kontron: Disable pull resistors for SD card signals on BL + board + - arm64: dts: imx8mm-kontron: Fix interrupt for RTC on OSM-S i.MX8MM module + - arm64: dts: imx8qm: Align edma3 power-domains resources indentation + - arm64: dts: imx8qm: Correct edma3 power-domains and interrupt numbers + - libbpf: Add missing LIBBPF_API annotation to libbpf_set_memlock_rlim API + - wifi: ath9k: delay all of ath9k_wmi_event_tasklet() until init is complete + - wifi: ath11k: change to move WMI_VDEV_PARAM_SET_HEMU_MODE before + WMI_PEER_ASSOC_CMDID + - wifi: ath12k: fix fetching MCBC flag for QCN9274 + - wifi: iwlwifi: mvm: report beacon protection failures + - wifi: iwlwifi: dbg-tlv: ensure NUL termination + - wifi: iwlwifi: acpi: fix WPFC reading + - wifi: iwlwifi: mvm: initialize rates in FW earlier + - wifi: iwlwifi: fix EWRD table validity check + - wifi: iwlwifi: mvm: d3: fix IPN byte order + - wifi: iwlwifi: always have 'uats_enabled' + - wifi: iwlwifi: mvm: fix the TLC command after ADD_STA + - wifi: iwlwifi: read BIOS PNVM only for non-Intel SKU + - gpio: vf610: allow disabling the vf610 driver + - selftests/bpf: trace_helpers.c: do not use poisoned type + - bpf: make sure scalar args don't accept __arg_nonnull tag + - bpf: don't emit warnings intended for global subprogs for static subprogs + - arm64: dts: imx8mm-venice-gw71xx: fix USB OTG VBUS + - pwm: atmel-hlcdc: Fix clock imbalance related to suspend support + - net: blackhole_dev: fix build warning for ethh set but not used + - spi: consolidate setting message->spi + - spi: move split xfers for CS_WORD emulation + - arm64: dts: ti: k3-am62p5-sk: Enable CPSW MDIO node + - arm64: dts: ti: k3-j721s2: Fix power domain for VTM node + - arm64: dts: ti: k3-j784s4: Fix power domain for VTM node + - wifi: ath11k: initialize rx_mcs_80 and rx_mcs_160 before use + - wifi: libertas: fix some memleaks in lbs_allocate_cmd_buffer() + - arm64: dts: ti: k3-am69-sk: remove assigned-clock-parents for unused VP + - libbpf: fix return value for PERF_EVENT __arg_ctx type fix up check + - arm64: dts: ti: k3-am62p-mcu/wakeup: Disable MCU and wakeup R5FSS nodes + - arm64: dts: qcom: x1e80100-qcp: Fix supplies for LDOs 3E and 2J + - libbpf: Use OPTS_SET() macro in bpf_xdp_query() + - wifi: wfx: fix memory leak when starting AP + - arm64: dts: qcom: qcm2290: declare VLS CLAMP register for USB3 PHY + - arm64: dts: qcom: sm6115: declare VLS CLAMP register for USB3 PHY + - arm64: dts: qcom: sm8650: Fix UFS PHY clocks + - wifi: ath12k: fix incorrect logic of calculating vdev_stats_id + - printk: nbcon: Relocate 32bit seq macros + - printk: ringbuffer: Do not skip non-finalized records with prb_next_seq() + - printk: Wait for all reserved records with pr_flush() + - printk: Add this_cpu_in_panic() + - printk: ringbuffer: Cleanup reader terminology + - printk: ringbuffer: Skip non-finalized records in panic + - printk: Disable passing console lock owner completely during panic() + - pwm: sti: Fix capture for st,pwm-num-chan < st,capture-num-chan + - tools/resolve_btfids: Refactor set sorting with types from btf_ids.h + - tools/resolve_btfids: Fix cross-compilation to non-host endianness + - wifi: iwlwifi: support EHT for WH + - wifi: iwlwifi: properly check if link is active + - wifi: iwlwifi: mvm: fix erroneous queue index mask + - wifi: iwlwifi: mvm: don't set the MFP flag for the GTK + - wifi: iwlwifi: mvm: don't set replay counters to 0xff + - s390/pai: fix attr_event_free upper limit for pai device drivers + - s390/vdso: drop '-fPIC' from LDFLAGS + - arm64: dts: qcom: qcm6490-idp: Correct the voltage setting for vph_pwr + - arm64: dts: qcom: qcs6490-rb3gen2: Correct the voltage setting for vph_pwr + - selftests: forwarding: Add missing config entries + - selftests: forwarding: Add missing multicast routing config entries + - arm64: dts: qcom: sm6115: drop pipe clock selection + - ipv6: mcast: remove one synchronize_net() barrier in ipv6_mc_down() + - arm64: dts: mt8183: Move CrosEC base detection node to kukui-based DTs + - arm64: dts: mediatek: mt7986: fix reference to PWM in fan node + - arm64: dts: mediatek: mt7986: drop crypto's unneeded/invalid clock name + - arm64: dts: mediatek: mt7986: fix SPI bus width properties + - arm64: dts: mediatek: mt7986: fix SPI nodename + - arm64: dts: mediatek: mt7986: drop "#clock-cells" from PWM + - arm64: dts: mediatek: mt7986: add "#reset-cells" to infracfg + - arm64: dts: mediatek: mt8192-asurada: Remove CrosEC base detection node + - arm64: dts: mediatek: mt8192: fix vencoder clock name + - arm64: dts: mediatek: mt8186: fix VENC power domain clocks + - arm64: dts: mediatek: mt7622: add missing "device_type" to memory nodes + - can: m_can: Start/Cancel polling timer together with interrupts + - wifi: iwlwifi: mvm: Fix the listener MAC filter flags + - bpf: Mark bpf_spin_{lock,unlock}() helpers with notrace correctly + - arm64: dts: qcom: sdm845: Use the Low Power Island CX/MX for SLPI + - soc: qcom: llcc: Check return value on Broadcast_OR reg read + - ARM: dts: qcom: msm8974: correct qfprom node size + - arm64: dts: mediatek: mt8186: Add missing clocks to ssusb power domains + - arm64: dts: mediatek: mt8186: Add missing xhci clock to usb controllers + - arm64: dts: ti: am65x: Fix dtbs_install for Rocktech OLDI overlay + - cpufreq: qcom-hw: add CONFIG_COMMON_CLK dependency + - wifi: wilc1000: prevent use-after-free on vif when cleaning up all + interfaces + - pwm: dwc: use pm_sleep_ptr() macro + - arm64: dts: ti: k3-am69-sk: fix PMIC interrupt number + - arm64: dts: ti: k3-j721e-sk: fix PMIC interrupt number + - arm64: dts: ti: k3-am62-main: disable usb lpm + - ACPI: processor_idle: Fix memory leak in acpi_processor_power_exit() + - bus: tegra-aconnect: Update dependency to ARCH_TEGRA + - iommu/amd: Mark interrupt as managed + - wifi: brcmsmac: avoid function pointer casts + - arm64: dts: qcom: sdm845-db845c: correct PCIe wake-gpios + - arm64: dts: qcom: sm8150: correct PCIe wake-gpios + - powercap: dtpm_cpu: Fix error check against freq_qos_add_request() + - net: ena: Remove ena_select_queue + - arm64: dts: ti: k3-j7200-common-proc-board: Modify Pinmux for wkup_uart0 and + mcu_uart0 + - arm64: dts: ti: k3-j7200-common-proc-board: Remove clock-frequency from + mcu_uart0 + - arm64: dts: ti: k3-j721s2-common-proc-board: Remove Pinmux for CTS and RTS + in wkup_uart0 + - arm64: dts: ti: k3-j784s4-evm: Remove Pinmux for CTS and RTS in wkup_uart0 + - arm64: dts: ti: k3-am64-main: Fix ITAP/OTAP values for MMC + - arm64: dts: mt8195-cherry-tomato: change watchdog reset boot flow + - arm64: dts: ti: Add common1 register space for AM65x SoC + - arm64: dts: ti: Add common1 register space for AM62x SoC + - firmware: arm_scmi: Fix double free in SMC transport cleanup path + - wifi: cfg80211: set correct param change count in ML element + - arm64: dts: ti: k3-j721e: Fix mux-reg-masks in hbmc_mux + - arm64: dts: ti: k3-j784s4-main: Fix mux-reg-masks in serdes_ln_ctrl + - arm64: dts: ti: k3-am62p: Fix memory ranges for DMSS + - wifi: wilc1000: revert reset line logic flip + - ARM: dts: arm: realview: Fix development chip ROM compatible value + - memory: tegra: Correct DLA client names + - wifi: mt76: mt7996: fix fw loading timeout + - wifi: mt76: mt7925: fix connect to 80211b mode fail in 2Ghz band + - wifi: mt76: mt7925: fix SAP no beacon issue in 5Ghz and 6Ghz band + - wifi: mt76: mt7925: fix mcu query command fail + - wifi: mt76: mt7925: fix wmm queue mapping + - wifi: mt76: mt7925: fix fw download fail + - wifi: mt76: mt7925: fix WoW failed in encrypted mode + - wifi: mt76: mt7925: fix the wrong header translation config + - wifi: mt76: mt7925: add flow to avoid chip bt function fail + - wifi: mt76: mt7925: add support to set ifs time by mcu command + - wifi: mt76: mt7925: update PCIe DMA settings + - wifi: mt76: mt7996: check txs format before getting skb by pid + - wifi: mt76: mt7996: fix TWT issues + - wifi: mt76: mt7996: fix incorrect interpretation of EHT MCS caps + - wifi: mt76: mt7996: fix HE beamformer phy cap for station vif + - wifi: mt76: mt7996: fix efuse reading issue + - wifi: mt76: mt7996: fix HIF_TXD_V2_1 value + - wifi: mt76: mt792x: fix ethtool warning + - wifi: mt76: mt7921e: fix use-after-free in free_irq() + - wifi: mt76: mt7925e: fix use-after-free in free_irq() + - wifi: mt76: mt7921: fix incorrect type conversion for CLC command + - wifi: mt76: mt792x: fix a potential loading failure of the 6Ghz channel + config from ACPI + - wifi: mt76: fix the issue of missing txpwr settings from ch153 to ch177 + - arm64: dts: renesas: rzg2l: Add missing interrupts to IRQC nodes + - arm64: dts: renesas: r9a08g045: Add missing interrupts to IRQC node + - arm64: dts: renesas: rzg3s-smarc-som: Guard Ethernet IRQ GPIO hogs + - arm64: dts: renesas: r8a779a0: Correct avb[01] reg sizes + - arm64: dts: renesas: r8a779g0: Correct avb[01] reg sizes + - net: mctp: copy skb ext data when fragmenting + - pstore: inode: Only d_invalidate() is needed + - arm64: dts: allwinner: h6: Add RX DMA channel for SPDIF + - ARM: dts: imx6dl-yapp4: Fix typo in the QCA switch register address + - ARM: dts: imx6dl-yapp4: Move the internal switch PHYs under the switch node + - arm64: dts: imx8mp: Set SPI NOR to max 40 MHz on Data Modul i.MX8M Plus eDM + SBC + - arm64: dts: imx8mp-evk: Fix hdmi@3d node + - regulator: userspace-consumer: add module device table + - gpiolib: Pass consumer device through to core in + devm_fwnode_gpiod_get_index() + - arm64: dts: marvell: reorder crypto interrupts on Armada SoCs + - ACPI: resource: Do IRQ override on Lunnen Ground laptops + - ACPI: resource: Add MAIBENBEN X577 to irq1_edge_low_force_override + - ACPI: scan: Fix device check notification handling + - arm64: dts: rockchip: add missing interrupt-names for rk356x vdpu + - arm64: dts: rockchip: fix reset-names for rk356x i2s2 controller + - arm64: dts: rockchip: drop rockchip,trcm-sync-tx-only from rk3588 i2s + - objtool: Fix UNWIND_HINT_{SAVE,RESTORE} across basic blocks + - x86, relocs: Ignore relocations in .notes section + - SUNRPC: fix a memleak in gss_import_v2_context + - SUNRPC: fix some memleaks in gssx_dec_option_array + - arm64: dts: qcom: sm8550: Fix SPMI channels size + - arm64: dts: qcom: sm8650: Fix SPMI channels size + - mmc: wmt-sdmmc: remove an incorrect release_mem_region() call in the .remove + function + - ACPI: CPPC: enable AMD CPPC V2 support for family 17h processors + - btrfs: fix race when detecting delalloc ranges during fiemap + - wifi: rtw88: 8821cu: Fix firmware upload fail + - wifi: rtw88: 8821c: Fix beacon loss and disconnect + - wifi: rtw88: 8821c: Fix false alarm count + - wifi: brcm80211: handle pmk_op allocation failure + - riscv: dts: starfive: jh7100: fix root clock names + - PCI: Make pci_dev_is_disconnected() helper public for other drivers + - iommu/vt-d: Don't issue ATS Invalidation request when device is disconnected + - iommu/vt-d: Use rbtree to track iommu probed devices + - iommu/vt-d: Improve ITE fault handling if target device isn't present + - iommu/vt-d: Use device rbtree in iopf reporting path + - iommu: Add static iommu_ops->release_domain + - iommu/vt-d: Fix NULL domain on device release + - igc: Fix missing time sync events + - igb: Fix missing time sync events + - ice: fix stats being updated by way too large values + - Bluetooth: Remove HCI_POWER_OFF_TIMEOUT + - Bluetooth: mgmt: Remove leftover queuing of power_off work + - Bluetooth: Remove superfluous call to hci_conn_check_pending() + - Bluetooth: Remove BT_HS + - Bluetooth: hci_event: Fix not indicating new connection for BIG Sync + - Bluetooth: hci_qca: don't use IS_ERR_OR_NULL() with gpiod_get_optional() + - Bluetooth: hci_core: Cancel request on command timeout + - Bluetooth: hci_sync: Fix overwriting request callback + - Bluetooth: hci_h5: Add ability to allocate memory for private data + - Bluetooth: btrtl: fix out of bounds memory access + - Bluetooth: hci_core: Fix possible buffer overflow + - Bluetooth: msft: Fix memory leak + - Bluetooth: btusb: Fix memory leak + - Bluetooth: af_bluetooth: Fix deadlock + - Bluetooth: fix use-after-free in accessing skb after sending it + - sr9800: Add check for usbnet_get_endpoints + - s390/cache: prevent rebuild of shared_cpu_list + - bpf: Fix DEVMAP_HASH overflow check on 32-bit arches + - bpf: Fix hashtab overflow check on 32-bit arches + - bpf: Fix stackmap overflow check on 32-bit arches + - net: dsa: microchip: make sure drive strength configuration is not lost by + soft reset + - dpll: spec: use proper enum for pin capabilities attribute + - iommu: Fix compilation without CONFIG_IOMMU_INTEL + - ipv6: fib6_rules: flush route cache when rule is changed + - net: ip_tunnel: make sure to pull inner header in ip_tunnel_rcv() + - octeontx2-af: Fix devlink params + - net: phy: fix phy_get_internal_delay accessing an empty array + - dpll: fix dpll_xa_ref_*_del() for multiple registrations + - net: hns3: fix wrong judgment condition issue + - net: hns3: fix kernel crash when 1588 is received on HIP08 devices + - net: hns3: fix port duplex configure error in IMP reset + - Bluetooth: Fix eir name length + - net: phy: dp83822: Fix RGMII TX delay configuration + - erofs: fix lockdep false positives on initializing erofs_pseudo_mnt + - OPP: debugfs: Fix warning around icc_get_name() + - tcp: fix incorrect parameter validation in the do_tcp_getsockopt() function + - ipmr: fix incorrect parameter validation in the ip_mroute_getsockopt() + function + - l2tp: fix incorrect parameter validation in the pppol2tp_getsockopt() + function + - udp: fix incorrect parameter validation in the udp_lib_getsockopt() function + - net: kcm: fix incorrect parameter validation in the kcm_getsockopt) function + - net/x25: fix incorrect parameter validation in the x25_getsockopt() function + - devlink: Fix length of eswitch inline-mode + - r8152: fix unknown device for choose_configuration + - nfp: flower: handle acti_netdevs allocation failure + - bpf: hardcode BPF_PROG_PACK_SIZE to 2MB * num_possible_nodes() + - dm raid: fix false positive for requeue needed during reshape + - dm: call the resume method on internal suspend + - fbdev/simplefb: change loglevel when the power domains cannot be parsed + - drm/tegra: dsi: Add missing check for of_find_device_by_node + - drm/tegra: dpaux: Fix PM disable depth imbalance in tegra_dpaux_probe + - drm/tegra: dsi: Fix some error handling paths in tegra_dsi_probe() + - drm/tegra: dsi: Fix missing pm_runtime_disable() in the error handling path + of tegra_dsi_probe() + - drm/tegra: hdmi: Fix some error handling paths in tegra_hdmi_probe() + - drm/tegra: rgb: Fix some error handling paths in tegra_dc_rgb_probe() + - drm/tegra: rgb: Fix missing clk_put() in the error handling paths of + tegra_dc_rgb_probe() + - drm/tegra: output: Fix missing i2c_put_adapter() in the error handling paths + of tegra_output_probe() + - drm/rockchip: inno_hdmi: Fix video timing + - drm: Don't treat 0 as -1 in drm_fixp2int_ceil + - drm/vkms: Avoid reading beyond LUT array + - drm/vmwgfx: fix a memleak in vmw_gmrid_man_get_node + - drm/rockchip: lvds: do not overwrite error code + - drm/rockchip: lvds: do not print scary message when probing defer + - drm/panel-edp: use put_sync in unprepare + - drm/lima: fix a memleak in lima_heap_alloc + - ASoC: amd: acp: Add missing error handling in sof-mach + - ASoC: SOF: amd: Fix memory leak in amd_sof_acp_probe() + - ASoC: SOF: core: Skip firmware test for custom loaders + - ASoC: SOF: amd: Compute file paths on firmware load + - soundwire: stream: add missing const to Documentation + - dmaengine: tegra210-adma: Update dependency to ARCH_TEGRA + - media: tc358743: register v4l2 async device only after successful setup + - media: cadence: csi2rx: use match fwnode for media link + - PCI/DPC: Print all TLP Prefixes, not just the first + - perf record: Fix possible incorrect free in record__switch_output() + - perf record: Check conflict between '--timestamp-filename' option and pipe + mode before recording + - HID: lenovo: Add middleclick_workaround sysfs knob for cptkbd + - drm/amd/display: Fix a potential buffer overflow in 'dp_dsc_clock_en_read()' + - perf pmu: Treat the msr pmu as software + - crypto: qat - avoid memcpy() overflow warning + - ALSA: hda: cs35l41: Set Channel Index correctly when system is missing _DSD + - drm/amd/display: Fix potential NULL pointer dereferences in + 'dcn10_set_output_transfer_func()' + - ASoC: sh: rz-ssi: Fix error message print + - drm/vmwgfx: Fix vmw_du_get_cursor_mob fencing of newly-created MOBs + - clk: renesas: r8a779g0: Fix PCIe clock name + - pinctrl: renesas: rzg2l: Fix locking in rzg2l_dt_subnode_to_map() + - pinctrl: renesas: r8a779g0: Add missing SCIF_CLK2 pin group/function + - clk: samsung: exynos850: Propagate SPI IPCLK rate change + - media: v4l2: cci: print leading 0 on error + - perf evsel: Fix duplicate initialization of data->id in + evsel__parse_sample() + - perf bpf: Clean up the generated/copied vmlinux.h + - clk: meson: Add missing clocks to axg_clk_regmaps + - media: em28xx: annotate unchecked call to media_device_register() + - media: v4l2-tpg: fix some memleaks in tpg_alloc + - media: v4l2-mem2mem: fix a memleak in v4l2_m2m_register_entity + - media: dt-bindings: techwell,tw9900: Fix port schema ref + - mtd: spinand: esmt: Extend IDs to 5 bytes + - media: edia: dvbdev: fix a use-after-free + - pinctrl: mediatek: Drop bogus slew rate register range for MT8186 + - pinctrl: mediatek: Drop bogus slew rate register range for MT8192 + - drm/amdgpu: Fix potential out-of-bounds access in + 'amdgpu_discovery_reg_base_init()' + - clk: qcom: reset: Commonize the de/assert functions + - clk: qcom: reset: Ensure write completion on reset de/assertion + - quota: Fix potential NULL pointer dereference + - quota: Fix rcu annotations of inode dquot pointers + - quota: Properly annotate i_dquot arrays with __rcu + - ASoC: Intel: ssp-common: Add stub for sof_ssp_get_codec_name + - PCI/P2PDMA: Fix a sleeping issue in a RCU read section + - PCI: switchtec: Fix an error handling path in switchtec_pci_probe() + - crypto: xilinx - call finalize with bh disabled + - drivers/ps3: select VIDEO to provide cmdline functions + - perf thread_map: Free strlist on normal path in thread_map__new_by_tid_str() + - perf srcline: Add missed addr2line closes + - dt-bindings: msm: qcom, mdss: Include ommited fam-b compatible + - drm/msm/dpu: fix the programming of INTF_CFG2_DATA_HCTL_EN + - drm/msm/dpu: Only enable DSC_MODE_MULTIPLEX if dsc_merge is enabled + - drm/radeon/ni: Fix wrong firmware size logging in ni_init_microcode() + - drm/amd/display: fix NULL checks for adev->dm.dc in amdgpu_dm_fini() + - clk: renesas: r8a779g0: Correct PFC/GPIO parent clocks + - clk: renesas: r8a779f0: Correct PFC/GPIO parent clock + - clk: renesas: r9a07g04[34]: Use SEL_SDHI1_STS status configuration for SD1 + mux + - ALSA: seq: fix function cast warnings + - perf expr: Fix "has_event" function for metric style events + - perf stat: Avoid metric-only segv + - perf metric: Don't remove scale from counts + - ASoC: meson: aiu: fix function pointer type mismatch + - ASoC: meson: t9015: fix function pointer type mismatch + - powerpc: Force inlining of arch_vmap_p{u/m}d_supported() + - ASoC: SOF: Add some bounds checking to firmware data + - drm: ci: use clk_ignore_unused for apq8016 + - NTB: fix possible name leak in ntb_register_device() + - media: cedrus: h265: Fix configuring bitstream size + - media: sun8i-di: Fix coefficient writes + - media: sun8i-di: Fix power on/off sequences + - media: sun8i-di: Fix chroma difference threshold + - staging: media: starfive: Set 16 bpp for capture_raw device + - media: imx: csc/scaler: fix v4l2_ctrl_handler memory leak + - media: go7007: add check of return value of go7007_read_addr() + - media: pvrusb2: remove redundant NULL check + - media: videobuf2: Add missing doc comment for waiting_in_dqbuf + - media: pvrusb2: fix pvr2_stream_callback casts + - clk: qcom: dispcc-sdm845: Adjust internal GDSC wait times + - drm/amd/display: Add 'replay' NULL check in 'edp_set_replay_allow_active()' + - drm/panel: boe-tv101wum-nl6: make use of prepare_prev_first + - drm/msm/dpu: finalise global state object + - drm/mediatek: dsi: Fix DSI RGB666 formats and definitions + - PCI: Mark 3ware-9650SE Root Port Extended Tags as broken + - drm/bridge: adv7511: fix crash on irq during probe + - pinctrl: renesas: Allow the compiler to optimize away sh_pfc_pm + - clk: hisilicon: hi3519: Release the correct number of gates in + hi3519_clk_unregister() + - clk: hisilicon: hi3559a: Fix an erroneous devm_kfree() + - clk: mediatek: mt8135: Fix an error handling path in + clk_mt8135_apmixed_probe() + - clk: mediatek: mt7622-apmixedsys: Fix an error handling path in + clk_mt8135_apmixed_probe() + - clk: mediatek: mt8183: Correct parent of CLK_INFRA_SSPM_32K_SELF + - clk: mediatek: mt7981-topckgen: flag SGM_REG_SEL as critical + - drm/tegra: put drm_gem_object ref on error in tegra_fb_create + - tty: mips_ejtag_fdc: Fix passing incompatible pointer type warning + - media: ivsc: csi: Swap SINK and SOURCE pads + - media: i2c: imx290: Fix IMX920 typo + - mfd: syscon: Call of_node_put() only when of_parse_phandle() takes a ref + - mfd: altera-sysmgr: Call of_node_put() only when of_parse_phandle() takes a + ref + - perf print-events: make is_event_supported() more robust + - crypto: arm/sha - fix function cast warnings + - crypto: ccp - Avoid discarding errors in psp_send_platform_access_msg() + - crypto: qat - remove unused macros in qat_comp_alg.c + - crypto: qat - removed unused macro in adf_cnv_dbgfs.c + - crypto: qat - avoid division by zero + - crypto: qat - remove double initialization of value + - crypto: qat - fix ring to service map for dcc in 4xxx + - crypto: qat - fix ring to service map for dcc in 420xx + - crypto: jitter - fix CRYPTO_JITTERENTROPY help text + - drm/tidss: Fix initial plane zpos values + - drm/tidss: Fix sync-lost issue with two displays + - clk: imx: imx8mp: Fix SAI_MCLK_SEL definition + - mtd: maps: physmap-core: fix flash size larger than 32-bit + - mtd: rawnand: lpc32xx_mlc: fix irq handler prototype + - mtd: rawnand: brcmnand: exec_op helper functions return type fixes + - ASoC: meson: axg-tdm-interface: fix mclk setup without mclk-fs + - ASoC: meson: axg-tdm-interface: add frame rate constraint + - drm/msm/a6xx: specify UBWC config for sc7180 + - drm/msm/a7xx: Fix LLC typo + - dt-bindings: arm-smmu: fix SM8[45]50 GPU SMMU if condition + - perf pmu: Fix a potential memory leak in perf_pmu__lookup() + - HID: amd_sfh: Update HPD sensor structure elements + - HID: amd_sfh: Avoid disabling the interrupt + - drm/amdgpu: Fix missing break in ATOM_ARG_IMM Case of atom_get_src_int() + - media: pvrusb2: fix uaf in pvr2_context_set_notify + - media: dvb-frontends: avoid stack overflow warnings with clang + - media: go7007: fix a memleak in go7007_load_encoder + - media: ttpci: fix two memleaks in budget_av_attach + - media: mediatek: vcodec: avoid -Wcast-function-type-strict warning + - arm64: ftrace: Don't forbid CALL_OPS+CC_OPTIMIZE_FOR_SIZE with Clang + - drm/tests: helpers: Include missing drm_drv header + - drm/amd/pm: Fix esm reg mask use to get pcie speed + - gpio: nomadik: fix offset bug in nmk_pmx_set() + - drm/mediatek: Fix a null pointer crash in mtk_drm_crtc_finish_page_flip + - mfd: cs42l43: Fix wrong register defaults + - powerpc/32: fix ADB_CUDA kconfig warning + - powerpc/pseries: Fix potential memleak in papr_get_attr() + - powerpc/hv-gpci: Fix the H_GET_PERF_COUNTER_INFO hcall return value checks + - clk: qcom: gcc-ipq5018: fix 'enable_reg' offset of 'gcc_gmac0_sys_clk' + - clk: qcom: gcc-ipq5018: fix 'halt_reg' offset of 'gcc_pcie1_pipe_clk' + - clk: qcom: gcc-ipq5018: fix register offset for GCC_UBI0_AXI_ARES reset + - perf vendor events amd: Fix Zen 4 cache latency events + - drm/msm/dpu: allow certain formats for CDM for DP + - drm/msm/dpu: add division of drm_display_mode's hskew parameter + - media: usbtv: Remove useless locks in usbtv_video_free() + - drm/xe: Fix ref counting leak on page fault + - drm/xe: Replace 'grouped target' in Makefile with pattern rule + - lib/stackdepot: fix first entry having a 0-handle + - lib/stackdepot: off by one in depot_fetch_stack() + - modules: wait do_free_init correctly + - mfd: cs42l43: Fix wrong GPIO_FN_SEL and SPI_CLK_CONFIG1 defaults + - power: supply: mm8013: fix "not charging" detection + - powerpc/embedded6xx: Fix no previous prototype for avr_uart_send() etc. + - powerpc/4xx: Fix warp_gpio_leds build failure + - RISC-V: KVM: Forward SEED CSR access to user space + - leds: aw2013: Unlock mutex before destroying it + - leds: sgm3140: Add missing timer cleanup and flash gpio control + - backlight: hx8357: Fix potential NULL pointer dereference + - backlight: ktz8866: Correct the check for of_property_read_u32 + - backlight: lm3630a: Initialize backlight_properties on init + - backlight: lm3630a: Don't set bl->props.brightness in get_brightness + - backlight: da9052: Fully initialize backlight_properties during probe + - backlight: lm3639: Fully initialize backlight_properties during probe + - backlight: lp8788: Fully initialize backlight_properties during probe + - sparc32: Use generic cmpdi2/ucmpdi2 variants + - mtd: maps: sun_uflash: Declare uflash_devinit static + - sparc32: Do not select GENERIC_ISA_DMA + - sparc32: Fix section mismatch in leon_pci_grpci + - clk: Fix clk_core_get NULL dereference + - clk: zynq: Prevent null pointer dereference caused by kmalloc failure + - PCI: brcmstb: Fix broken brcm_pcie_mdio_write() polling + - cifs: Fix writeback data corruption + - ALSA: hda/realtek: fix ALC285 issues on HP Envy x360 laptops + - ALSA: hda/tas2781: use dev_dbg in system_resume + - ALSA: hda/tas2781: add lock to system_suspend + - ALSA: hda/tas2781: do not reset cur_* values in runtime_suspend + - ALSA: hda/tas2781: do not call pm_runtime_force_* in system_resume/suspend + - ALSA: hda/tas2781: restore power state after system_resume + - ALSA: scarlett2: Fix Scarlett 4th Gen 4i4 low-voltage detection + - ALSA: scarlett2: Fix Scarlett 4th Gen autogain status values + - ALSA: scarlett2: Fix Scarlett 4th Gen input gain range + - ALSA: scarlett2: Fix Scarlett 4th Gen input gain range again + - mips: cm: Convert __mips_cm_l2sync_phys_base() to weak function + - platform/x86/intel/pmc/lnl: Remove SSRAM support + - platform/x86/intel/pmc/arl: Put GNA device in D3 + - platform/x86/amd/pmf: Do not use readl() for policy buffer access + - ALSA: usb-audio: Stop parsing channels bits when all channels are found. + - phy: qcom: qmp-usb: split USB-C PHY driver + - phy: qcom: qmp-usbc: add support for the Type-C handling + - phy: qcom: qmp-usbc: handle CLAMP register in a correct way + - scsi: hisi_sas: Fix a deadlock issue related to automatic dump + - RDMA/irdma: Remove duplicate assignment + - RDMA/srpt: Do not register event handler until srpt device is fully setup + - f2fs: compress: fix to guarantee persisting compressed blocks by CP + - f2fs: compress: fix to cover normal cluster write with cp_rwsem + - f2fs: compress: fix to check unreleased compressed cluster + - f2fs: compress: fix to avoid inconsistence bewteen i_blocks and dnode + - f2fs: fix to remove unnecessary f2fs_bug_on() to avoid panic + - f2fs: zone: fix to wait completion of last bio in zone correctly + - f2fs: fix NULL pointer dereference in f2fs_submit_page_write() + - f2fs: compress: fix to cover f2fs_disable_compressed_file() w/ i_sem + - f2fs: fix to avoid potential panic during recovery + - scsi: csiostor: Avoid function pointer casts + - i3c: dw: Disable IBI IRQ depends on hot-join and SIR enabling + - RDMA/hns: Fix mis-modifying default congestion control algorithm + - RDMA/device: Fix a race between mad_client and cm_client init + - RDMA/rtrs-clt: Check strnlen return len in sysfs mpath_policy_store() + - scsi: bfa: Fix function pointer type mismatch for hcb_qe->cbfn + - f2fs: fix to create selinux label during whiteout initialization + - f2fs: compress: fix to check zstd compress level correctly in mount option + - net: sunrpc: Fix an off by one in rpc_sockaddr2uaddr() + - NFSv4.2: fix nfs4_listxattr kernel BUG at mm/usercopy.c:102 + - NFSv4.2: fix listxattr maximum XDR buffer size + - f2fs: compress: fix to check compress flag w/ .i_sem lock + - f2fs: check number of blocks in a current section + - watchdog: starfive: Check pm_runtime_enabled() before decrementing usage + counter + - watchdog: stm32_iwdg: initialize default timeout + - f2fs: fix to use correct segment type in f2fs_allocate_data_block() + - f2fs: ro: compress: fix to avoid caching unaligned extent + - RDMA/mana_ib: Fix bug in creation of dma regions + - RDMA/mana_ib: Introduce mdev_to_gc helper function + - RDMA/mana_ib: Introduce mana_ib_get_netdev helper function + - RDMA/mana_ib: Introduce mana_ib_install_cq_cb helper function + - RDMA/mana_ib: Use virtual address in dma regions for MRs + - Input: iqs7222 - add support for IQS7222D v1.1 and v1.2 + - NFS: Fix nfs_netfs_issue_read() xarray locking for writeback interrupt + - NFS: Fix an off by one in root_nfs_cat() + - NFSv4.1/pnfs: fix NFS with TLS in pnfs + - ACPI: HMAT: Remove register of memory node for generic target + - f2fs: compress: relocate some judgments in f2fs_reserve_compress_blocks + - f2fs: compress: fix reserve_cblocks counting error when out of space + - f2fs: fix to truncate meta inode pages forcely + - f2fs: zone: fix to remove pow2 check condition for zoned block device + - cxl: Fix the incorrect assignment of SSLBIS entry pointer initial location + - perf/x86/amd/core: Avoid register reset when CPU is dead + - afs: Revert "afs: Hide silly-rename files from userspace" + - afs: Don't cache preferred address + - afs: Fix occasional rmdir-then-VNOVNODE with generic/011 + - f2fs: fix to avoid use-after-free issue in f2fs_filemap_fault + - nfs: fix panic when nfs4_ff_layout_prepare_ds() fails + - ovl: relax WARN_ON in ovl_verify_area() + - io_uring/net: correct the type of variable + - remoteproc: stm32: Fix incorrect type in assignment for va + - remoteproc: stm32: Fix incorrect type assignment returned by + stm32_rproc_get_loaded_rsc_tablef + - iio: pressure: mprls0025pa fix off-by-one enum + - usb: phy: generic: Get the vbus supply + - tty: vt: fix 20 vs 0x20 typo in EScsiignore + - serial: max310x: fix syntax error in IRQ error message + - tty: serial: samsung: fix tx_empty() to return TIOCSER_TEMT + - arm64: dts: broadcom: bcmbca: bcm4908: drop invalid switch cells + - coresight: Fix issue where a source device's helpers aren't disabled + - coresight: etm4x: Set skip_power_up in etm4_init_arch_data function + - xhci: Add interrupt pending autoclear flag to each interrupter + - xhci: make isoc_bei_interval variable interrupter specific. + - xhci: remove unnecessary event_ring_deq parameter from xhci_handle_event() + - xhci: update event ring dequeue pointer position to controller correctly + - coccinelle: device_attr_show: Remove useless expression STR + - kconfig: fix infinite loop when expanding a macro at the end of file + - iio: gts-helper: Fix division loop + - bus: mhi: ep: check the correct variable in mhi_ep_register_controller() + - hwtracing: hisi_ptt: Move type check to the beginning of + hisi_ptt_pmu_event_init() + - rtc: mt6397: select IRQ_DOMAIN instead of depending on it + - rtc: max31335: fix interrupt status reg + - serial: 8250_exar: Don't remove GPIO device on suspend + - staging: greybus: fix get_channel_from_mode() failure path + - mei: vsc: Call wake_up() in the threaded IRQ handler + - mei: vsc: Don't use sleeping condition in wait_event_timeout() + - usb: gadget: net2272: Use irqflags in the call to net2272_probe_fin + - char: xilinx_hwicap: Fix NULL vs IS_ERR() bug + - x86/hyperv: Use per cpu initial stack for vtl context + - ASoC: tlv320adc3xxx: Don't strip remove function when driver is builtin + - thermal/drivers/mediatek/lvts_thermal: Fix a memory leak in an error + handling path + - thermal/drivers/qoriq: Fix getting tmu range + - io_uring: don't save/restore iowait state + - spi: lpspi: Avoid potential use-after-free in probe() + - spi: Restore delays for non-GPIO chip select + - ASoC: rockchip: i2s-tdm: Fix inaccurate sampling rates + - nouveau: reset the bo resource bus info after an eviction + - tcp: Fix NEW_SYN_RECV handling in inet_twsk_purge() + - rds: tcp: Fix use-after-free of net in reqsk_timer_handler(). + - octeontx2-af: Use matching wake_up API variant in CGX command interface + - s390/vtime: fix average steal time calculation + - net/sched: taprio: proper TCA_TAPRIO_TC_ENTRY_INDEX check + - devlink: Fix devlink parallel commands processing + - riscv: Only check online cpus for emulated accesses + - soc: fsl: dpio: fix kcalloc() argument order + - cpufreq: Fix per-policy boost behavior on SoCs using cpufreq_boost_set_sw() + - io_uring: Fix release of pinned pages when __io_uaddr_map fails + - tcp: Fix refcnt handling in __inet_hash_connect(). + - vmxnet3: Fix missing reserved tailroom + - hsr: Fix uninit-value access in hsr_get_node() + - net: txgbe: fix clk_name exceed MAX_DEV_ID limits + - spi: spi-mem: add statistics support to ->exec_op() calls + - spi: Fix error code checking in spi_mem_exec_op() + - nvme: fix reconnection fail due to reserved tag allocation + - drm/xe: Invalidate userptr VMA on page pin fault + - drm/xe: Skip VMAs pin when requesting signal to the last XE_EXEC + - net: mediatek: mtk_eth_soc: clear MAC_MCR_FORCE_LINK only when MAC is up + - net: ethernet: mtk_eth_soc: fix PPE hanging issue + - io_uring: fix poll_remove stalled req completion + - ASoC: SOF: amd: Move signed_fw_image to struct acp_quirk_entry + - ASoC: SOF: amd: Skip IRAM/DRAM size modification for Steam Deck OLED + - riscv: Fix compilation error with FAST_GUP and rv32 + - xen/evtchn: avoid WARN() when unbinding an event channel + - xen/events: increment refcnt only if event channel is refcounted + - packet: annotate data-races around ignore_outgoing + - xfrm: Allow UDP encapsulation only in offload modes + - net: veth: do not manipulate GRO when using XDP + - net: dsa: mt7530: prevent possible incorrect XTAL frequency selection + - spi: spi-imx: fix off-by-one in mx51 CPU mode burst length + - drm: Fix drm_fixp2int_round() making it add 0.5 + - virtio: uapi: Drop __packed attribute in linux/virtio_pci.h + - vdpa_sim: reset must not run + - vdpa/mlx5: Allow CVQ size changes + - virtio: packed: fix unmap leak for indirect desc table + - net: move dev->state into net_device_read_txrx group + - wireguard: receive: annotate data-race around receiving_counter.counter + - rds: introduce acquire/release ordering in acquire/release_in_xmit() + - hsr: Handle failures in module init + - ipv4: raw: Fix sending packets from raw sockets via IPsec tunnels + - nouveau/gsp: don't check devinit disable on GSP. + - ceph: stop copying to iter at EOF on sync reads + - net: phy: fix phy_read_poll_timeout argument type in genphy_loopback + - dm-integrity: fix a memory leak when rechecking the data + - net/bnx2x: Prevent access to a freed page in page_pool + - devlink: fix port new reply cmd type + - octeontx2: Detect the mbox up or down message via register + - octeontx2-pf: Wait till detach_resources msg is complete + - octeontx2-pf: Use default max_active works instead of one + - octeontx2-pf: Send UP messages to VF only when VF is up. + - octeontx2-af: Use separate handlers for interrupts + - drm/amdgpu: add MMHUB 3.3.1 support + - drm/amdgpu: fix mmhub client id out-of-bounds access + - drm/amdgpu: drop setting buffer funcs in sdma442 + - netfilter: nft_set_pipapo: release elements in clone only from destroy path + - netfilter: nf_tables: do not compare internal table flags on updates + - rcu: add a helper to report consolidated flavor QS + - net: report RCU QS on threaded NAPI repolling + - bpf: report RCU QS in cpumap kthread + - net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports + - net: dsa: mt7530: fix handling of all link-local frames + - netfilter: nf_tables: Fix a memory leak in nf_tables_updchain + - spi: spi-mt65xx: Fix NULL pointer access in interrupt handler + - selftests: forwarding: Fix ping failure due to short timeout + - dm io: Support IO priority + - dm-integrity: align the outgoing bio in integrity_recheck + - x86/efistub: Clear decompressor BSS in native EFI entrypoint + - x86/efistub: Don't clear BSS twice in mixed mode + - printk: Adjust mapping for 32bit seq macros + - printk: Use prb_first_seq() as base for 32bit seq macros + - Linux 6.8.2 + - [Config] updateconfig following v6.8.2 import + + * Provide python perf module (LP: #2051560) + - [Packaging] enable perf python module + - [Packaging] provide a wrapper module for python-perf + + * To support AMD Adaptive Backlight Management (ABM) for power profiles daemon + >= 2.0 (LP: #2056716) + - drm/amd/display: add panel_power_savings sysfs entry to eDP connectors + - drm/amdgpu: respect the abmlevel module parameter value if it is set + + * Miscellaneous Ubuntu changes + - [Config] Disable StarFive JH7100 support + - [Config] Disable Renesas RZ/Five support + - [Config] Disable BINFMT_FLAT for riscv64 + + -- Roxana Nicolescu Wed, 01 May 2024 16:02:05 +0200 + +linux (6.8.0-31.31) noble; urgency=medium + + * noble/linux: 6.8.0-31.31 -proposed tracker (LP: #2062933) + + * Packaging resync (LP: #1786013) + - [Packaging] debian.master/dkms-versions -- update from kernel-versions + (main/d2024.04.04) + + -- Andrea Righi Fri, 19 Apr 2024 23:46:38 +0200 + +linux (6.8.0-30.30) noble; urgency=medium + + * noble/linux: 6.8.0-30.30 -proposed tracker (LP: #2061893) + + * System unstable, kernel ring buffer flooded with "BUG: Bad page state in + process swapper/0" (LP: #2056706) + - xen-netfront: Add missing skb_mark_for_recycle + + -- Andrea Righi Tue, 16 Apr 2024 21:17:11 +0200 + +linux (6.8.0-29.29) noble; urgency=medium + + * noble/linux: 6.8.0-29.29 -proposed tracker (LP: #2061888) + + * [24.04 FEAT] [SEC2353] zcrypt: extend error recovery to deal with device + scans (LP: #2050019) + - s390/zcrypt: harmonize debug feature calls and defines + - s390/zcrypt: introduce dynamic debugging for AP and zcrypt code + - s390/pkey: harmonize pkey s390 debug feature calls + - s390/pkey: introduce dynamic debugging for pkey + - s390/ap: add debug possibility for AP messages + - s390/zcrypt: add debug possibility for CCA and EP11 messages + - s390/ap: rearm APQNs bindings complete completion + - s390/ap: clarify AP scan bus related functions and variables + - s390/ap: rework ap_scan_bus() to return true on config change + - s390/ap: introduce mutex to lock the AP bus scan + - s390/zcrypt: introduce retries on in-kernel send CPRB functions + - s390/zcrypt: improve zcrypt retry behavior + - s390/pkey: improve pkey retry behavior + + * [24.04 FEAT] Memory hotplug vmem pages (s390x) (LP: #2051835) + - mm/memory_hotplug: introduce MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers + - s390/mm: allocate vmemmap pages from self-contained memory range + - s390/sclp: remove unhandled memory notifier type + - s390/mm: implement MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers + - s390: enable MHP_MEMMAP_ON_MEMORY + - [Config] enable CONFIG_ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE and + CONFIG_MHP_MEMMAP_ON_MEMORY for s390x + + -- Paolo Pisati Tue, 16 Apr 2024 20:32:09 +0200 + +linux (6.8.0-28.28) noble; urgency=medium + + * noble/linux: 6.8.0-28.28 -proposed tracker (LP: #2061867) + + * linux-gcp 6.8.0-1005.5 (+ others) Noble kernel regression iwth new apparmor + profiles/features (LP: #2061851) + - SAUCE: apparmor4.0.0 [92/90]: fix address mapping for recvfrom + + -- Paolo Pisati Tue, 16 Apr 2024 18:29:17 +0200 + +linux (6.8.0-25.25) noble; urgency=medium + + * noble/linux: 6.8.0-25.25 -proposed tracker (LP: #2061083) + + * Packaging resync (LP: #1786013) + - [Packaging] debian.master/dkms-versions -- update from kernel-versions + (main/d2024.04.04) + + * Apply mitigations for the native BHI hardware vulnerabilty (LP: #2060909) + - x86/cpufeatures: Add new word for scattered features + - x86/bugs: Change commas to semicolons in 'spectre_v2' sysfs file + - x86/syscall: Don't force use of indirect calls for system calls + - x86/bhi: Add support for clearing branch history at syscall entry + - x86/bhi: Define SPEC_CTRL_BHI_DIS_S + - x86/bhi: Enumerate Branch History Injection (BHI) bug + - x86/bhi: Add BHI mitigation knob + - x86/bhi: Mitigate KVM by default + - KVM: x86: Add BHI_NO + - x86: set SPECTRE_BHI_ON as default + - [Config] enable spectre_bhi=auto by default + + * update apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor4.0.0 [01/90]: LSM stacking v39: integrity: disassociate + ima_filter_rule from security_audit_rule + - SAUCE: apparmor4.0.0 [02/90]: LSM stacking v39: SM: Infrastructure + management of the sock security + - SAUCE: apparmor4.0.0 [03/90]: LSM stacking v39: LSM: Add the lsmblob data + structure. + - SAUCE: apparmor4.0.0 [04/90]: LSM stacking v39: IMA: avoid label collisions + with stacked LSMs + - SAUCE: apparmor4.0.0 [05/90]: LSM stacking v39: LSM: Use lsmblob in + security_audit_rule_match + - SAUCE: apparmor4.0.0 [06/90]: LSM stacking v39: LSM: Add lsmblob_to_secctx + hook + - SAUCE: apparmor4.0.0 [07/90]: LSM stacking v39: Audit: maintain an lsmblob + in audit_context + - SAUCE: apparmor4.0.0 [08/90]: LSM stacking v39: LSM: Use lsmblob in + security_ipc_getsecid + - SAUCE: apparmor4.0.0 [09/90]: LSM stacking v39: Audit: Update shutdown LSM + data + - SAUCE: apparmor4.0.0 [10/90]: LSM stacking v39: LSM: Use lsmblob in + security_current_getsecid + - SAUCE: apparmor4.0.0 [11/90]: LSM stacking v39: LSM: Use lsmblob in + security_inode_getsecid + - SAUCE: apparmor4.0.0 [12/90]: LSM stacking v39: Audit: use an lsmblob in + audit_names + - SAUCE: apparmor4.0.0 [13/90]: LSM stacking v39: LSM: Create new + security_cred_getlsmblob LSM hook + - SAUCE: apparmor4.0.0 [14/90]: LSM stacking v39: Audit: Change context data + from secid to lsmblob + - SAUCE: apparmor4.0.0 [15/90]: LSM stacking v39: Netlabel: Use lsmblob for + audit data + - SAUCE: apparmor4.0.0 [16/90]: LSM stacking v39: LSM: Ensure the correct LSM + context releaser + - SAUCE: apparmor4.0.0 [17/90]: LSM stacking v39: LSM: Use lsmcontext in + security_secid_to_secctx + - SAUCE: apparmor4.0.0 [18/90]: LSM stacking v39: LSM: Use lsmcontext in + security_lsmblob_to_secctx + - SAUCE: apparmor4.0.0 [19/90]: LSM stacking v39: LSM: Use lsmcontext in + security_inode_getsecctx + - SAUCE: apparmor4.0.0 [20/90]: LSM stacking v39: LSM: Use lsmcontext in + security_dentry_init_security + - SAUCE: apparmor4.0.0 [21/90]: LSM stacking v39: LSM: + security_lsmblob_to_secctx module selection + - SAUCE: apparmor4.0.0 [22/90]: LSM stacking v39: Audit: Create audit_stamp + structure + - SAUCE: apparmor4.0.0 [23/90]: LSM stacking v39: Audit: Allow multiple + records in an audit_buffer + - SAUCE: apparmor4.0.0 [24/90]: LSM stacking v39: Audit: Add record for + multiple task security contexts + - SAUCE: apparmor4.0.0 [25/90]: LSM stacking v39: audit: multiple subject lsm + values for netlabel + - SAUCE: apparmor4.0.0 [26/90]: LSM stacking v39: Audit: Add record for + multiple object contexts + - SAUCE: apparmor4.0.0 [27/90]: LSM stacking v39: LSM: Remove unused + lsmcontext_init() + - SAUCE: apparmor4.0.0 [28/90]: LSM stacking v39: LSM: Improve logic in + security_getprocattr + - SAUCE: apparmor4.0.0 [29/90]: LSM stacking v39: LSM: secctx provider check + on release + - SAUCE: apparmor4.0.0 [31/90]: LSM stacking v39: LSM: Exclusive secmark usage + - SAUCE: apparmor4.0.0 [32/90]: LSM stacking v39: LSM: Identify which LSM + handles the context string + - SAUCE: apparmor4.0.0 [33/90]: LSM stacking v39: AppArmor: Remove the + exclusive flag + - SAUCE: apparmor4.0.0 [34/90]: LSM stacking v39: LSM: Add mount opts blob + size tracking + - SAUCE: apparmor4.0.0 [35/90]: LSM stacking v39: LSM: allocate mnt_opts blobs + instead of module specific data + - SAUCE: apparmor4.0.0 [36/90]: LSM stacking v39: LSM: Infrastructure + management of the key security blob + - SAUCE: apparmor4.0.0 [37/90]: LSM stacking v39: LSM: Infrastructure + management of the mnt_opts security blob + - SAUCE: apparmor4.0.0 [38/90]: LSM stacking v39: LSM: Correct handling of + ENOSYS in inode_setxattr + - SAUCE: apparmor4.0.0 [39/90]: LSM stacking v39: LSM: Remove lsmblob + scaffolding + - SAUCE: apparmor4.0.0 [40/90]: LSM stacking v39: LSM: Allow reservation of + netlabel + - SAUCE: apparmor4.0.0 [41/90]: LSM stacking v39: LSM: restrict + security_cred_getsecid() to a single LSM + - SAUCE: apparmor4.0.0 [42/90]: LSM stacking v39: Smack: Remove + LSM_FLAG_EXCLUSIVE + - SAUCE: apparmor4.0.0 [43/90]: LSM stacking v39: UBUNTU: SAUCE: apparmor4.0.0 + [12/95]: add/use fns to print hash string hex value + - SAUCE: apparmor4.0.0 [44/90]: patch to provide compatibility with v2.x net + rules + - SAUCE: apparmor4.0.0 [45/90]: add unpriviled user ns mediation + - SAUCE: apparmor4.0.0 [46/90]: Add sysctls for additional controls of unpriv + userns restrictions + - SAUCE: apparmor4.0.0 [47/90]: af_unix mediation + - SAUCE: apparmor4.0.0 [48/90]: Add fine grained mediation of posix mqueues + - SAUCE: apparmor4.0.0 [49/90]: setup slab cache for audit data + - SAUCE: apparmor4.0.0 [50/90]: Improve debug print infrastructure + - SAUCE: apparmor4.0.0 [51/90]: add the ability for profiles to have a + learning cache + - SAUCE: apparmor4.0.0 [52/90]: enable userspace upcall for mediation + - SAUCE: apparmor4.0.0 [53/90]: prompt - lock down prompt interface + - SAUCE: apparmor4.0.0 [54/90]: prompt - allow controlling of caching of a + prompt response + - SAUCE: apparmor4.0.0 [55/90]: prompt - add refcount to audit_node in prep or + reuse and delete + - SAUCE: apparmor4.0.0 [56/90]: prompt - refactor to moving caching to + uresponse + - SAUCE: apparmor4.0.0 [57/90]: prompt - Improve debug statements + - SAUCE: apparmor4.0.0 [58/90]: prompt - fix caching + - SAUCE: apparmor4.0.0 [59/90]: prompt - rework build to use append fn, to + simplify adding strings + - SAUCE: apparmor4.0.0 [60/90]: prompt - refcount notifications + - SAUCE: apparmor4.0.0 [61/90]: prompt - add the ability to reply with a + profile name + - SAUCE: apparmor4.0.0 [62/90]: prompt - fix notification cache when updating + - SAUCE: apparmor4.0.0 [63/90]: prompt - add tailglob on name for cache + support + - SAUCE: apparmor4.0.0 [64/90]: prompt - allow profiles to set prompts as + interruptible + - SAUCE: apparmor4.0.0 [65/90] v6.8 prompt:fixup interruptible + - SAUCE: apparmor4.0.0 [69/90]: add io_uring mediation + - SAUCE: apparmor4.0.0 [70/90]: apparmor: fix oops when racing to retrieve + notification + - SAUCE: apparmor4.0.0 [71/90]: apparmor: fix notification header size + - SAUCE: apparmor4.0.0 [72/90]: apparmor: fix request field from a prompt + reply that denies all access + - SAUCE: apparmor4.0.0 [73/90]: apparmor: open userns related sysctl so lxc + can check if restriction are in place + - SAUCE: apparmor4.0.0 [74/90]: apparmor: cleanup attachment perm lookup to + use lookup_perms() + - SAUCE: apparmor4.0.0 [75/90]: apparmor: remove redundant unconfined check. + - SAUCE: apparmor4.0.0 [76/90]: apparmor: switch signal mediation to using + RULE_MEDIATES + - SAUCE: apparmor4.0.0 [77/90]: apparmor: ensure labels with more than one + entry have correct flags + - SAUCE: apparmor4.0.0 [78/90]: apparmor: remove explicit restriction that + unconfined cannot use change_hat + - SAUCE: apparmor4.0.0 [79/90]: apparmor: cleanup: refactor file_perm() to + provide semantics of some checks + - SAUCE: apparmor4.0.0 [80/90]: apparmor: carry mediation check on label + - SAUCE: apparmor4.0.0 [81/90]: apparmor: convert easy uses of unconfined() to + label_mediates() + - SAUCE: apparmor4.0.0 [82/90]: apparmor: add additional flags to extended + permission. + - SAUCE: apparmor4.0.0 [83/90]: apparmor: add support for profiles to define + the kill signal + - SAUCE: apparmor4.0.0 [84/90]: apparmor: fix x_table_lookup when stacking is + not the first entry + - SAUCE: apparmor4.0.0 [85/90]: apparmor: allow profile to be transitioned + when a user ns is created + - SAUCE: apparmor4.0.0 [86/90]: apparmor: add ability to mediate caps with + policy state machine + - SAUCE: apparmor4.0.0 [87/90]: fixup notify + - SAUCE: apparmor4.0.0 [88/90]: apparmor: add fine grained ipv4/ipv6 mediation + - SAUCE: apparmor4.0.0 [89/90]:apparmor: disable tailglob responses for now + - SAUCE: apparmor4.0.0 [90/90]: apparmor: Fix notify build warnings + - SAUCE: apparmor4.0.0: fix reserved mem for when we save ipv6 addresses + - [Config] disable CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + + * update apparmor and LSM stacking patch set (LP: #2028253) // [FFe] + apparmor-4.0.0-alpha2 for unprivileged user namespace restrictions in mantic + (LP: #2032602) + - SAUCE: apparmor4.0.0 [66/90]: prompt - add support for advanced filtering of + notifications + - SAUCE: apparmor4.0.0 [67/90]: userns - add the ability to reference a global + variable for a feature value + - SAUCE: apparmor4.0.0 [68/90]: userns - make it so special unconfined + profiles can mediate user namespaces + + * [MTL] x86: Fix Cache info sysfs is not populated (LP: #2049793) + - SAUCE: cacheinfo: Check for null last-level cache info + - SAUCE: cacheinfo: Allocate memory for memory if not done from the primary + CPU + - SAUCE: x86/cacheinfo: Delete global num_cache_leaves + - SAUCE: x86/cacheinfo: Clean out init_cache_level() + + * Miscellaneous Ubuntu changes + - SAUCE: apparmor4.0.0: LSM stacking v39: fix build error with + CONFIG_SECURITY=n + - [Config] toolchain version update + + -- Paolo Pisati Fri, 12 Apr 2024 10:42:33 +0200 + +linux (6.8.0-22.22) noble; urgency=medium + + * noble/linux: 6.8.0-22.22 -proposed tracker (LP: #2060238) + + -- Andrea Righi Thu, 04 Apr 2024 23:00:49 +0200 + +linux (6.8.0-21.21) noble; urgency=medium + + * noble/linux: 6.8.0-21.21 -proposed tracker (LP: #2060225) + + * Miscellaneous Ubuntu changes + - [Config] update toolchain version in annotations + + -- Andrea Righi Thu, 04 Apr 2024 22:20:27 +0200 + +linux (6.8.0-20.20) noble; urgency=medium + + * noble/linux: 6.8.0-20.20 -proposed tracker (LP: #2058221) + + * Noble update: v6.8.1 upstream stable release (LP: #2058224) + - x86/mmio: Disable KVM mitigation when X86_FEATURE_CLEAR_CPU_BUF is set + - Documentation/hw-vuln: Add documentation for RFDS + - x86/rfds: Mitigate Register File Data Sampling (RFDS) + - KVM/x86: Export RFDS_NO and RFDS_CLEAR to guests + - Linux 6.8.1 + + * Autopkgtest failures on amd64 (LP: #2048768) + - [Packaging] update to clang-18 + + * Miscellaneous Ubuntu changes + - SAUCE: apparmor4.0.0: LSM stacking v39: fix build error with + CONFIG_SECURITY=n + - [Config] amd64: MITIGATION_RFDS=y + + -- Paolo Pisati Mon, 18 Mar 2024 11:08:14 +0100 + +linux (6.8.0-19.19) noble; urgency=medium + + * noble/linux: 6.8.0-19.19 -proposed tracker (LP: #2057910) + + * Miscellaneous Ubuntu changes + - [Packaging] re-introduce linux-doc as an empty package + + -- Paolo Pisati Thu, 14 Mar 2024 14:36:14 +0100 + +linux (6.8.0-18.18) noble; urgency=medium + + * noble/linux: 6.8.0-18.18 -proposed tracker (LP: #2057456) + + * Miscellaneous Ubuntu changes + - [Packaging] drop dependency on libclang-17 + + -- Paolo Pisati Tue, 12 Mar 2024 14:44:13 +0100 + +linux (6.8.0-17.17) noble; urgency=medium + + * noble/linux: 6.8.0-17.17 -proposed tracker (LP: #2056745) + + * Miscellaneous upstream changes + - Revert "UBUNTU: [Packaging] Add debian/control sanity check" + + -- Paolo Pisati Mon, 11 Mar 2024 12:46:38 +0100 + +linux (6.8.0-16.16) noble; urgency=medium + + * noble/linux: 6.8.0-16.16 -proposed tracker (LP: #2056738) + + * left-over ceph debugging printks (LP: #2056616) + - Revert "UBUNTU: SAUCE: ceph: make sure all the files successfully put before + unmounting" + + * qat: Improve error recovery flows (LP: #2056354) + - crypto: qat - add heartbeat error simulator + - crypto: qat - disable arbitration before reset + - crypto: qat - update PFVF protocol for recovery + - crypto: qat - re-enable sriov after pf reset + - crypto: qat - add fatal error notification + - crypto: qat - add auto reset on error + - crypto: qat - limit heartbeat notifications + - crypto: qat - improve aer error reset handling + - crypto: qat - change SLAs cleanup flow at shutdown + - crypto: qat - resolve race condition during AER recovery + - Documentation: qat: fix auto_reset section + + * update apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor4.0.0 [01/87]: LSM stacking v39: integrity: disassociate + ima_filter_rule from security_audit_rule + - SAUCE: apparmor4.0.0 [02/87]: LSM stacking v39: SM: Infrastructure + management of the sock security + - SAUCE: apparmor4.0.0 [03/87]: LSM stacking v39: LSM: Add the lsmblob data + structure. + - SAUCE: apparmor4.0.0 [04/87]: LSM stacking v39: IMA: avoid label collisions + with stacked LSMs + - SAUCE: apparmor4.0.0 [05/87]: LSM stacking v39: LSM: Use lsmblob in + security_audit_rule_match + - SAUCE: apparmor4.0.0 [06/87]: LSM stacking v39: LSM: Add lsmblob_to_secctx + hook + - SAUCE: apparmor4.0.0 [07/87]: LSM stacking v39: Audit: maintain an lsmblob + in audit_context + - SAUCE: apparmor4.0.0 [08/87]: LSM stacking v39: LSM: Use lsmblob in + security_ipc_getsecid + - SAUCE: apparmor4.0.0 [09/87]: LSM stacking v39: Audit: Update shutdown LSM + data + - SAUCE: apparmor4.0.0 [10/87]: LSM stacking v39: LSM: Use lsmblob in + security_current_getsecid + - SAUCE: apparmor4.0.0 [11/87]: LSM stacking v39: LSM: Use lsmblob in + security_inode_getsecid + - SAUCE: apparmor4.0.0 [12/87]: LSM stacking v39: Audit: use an lsmblob in + audit_names + - SAUCE: apparmor4.0.0 [13/87]: LSM stacking v39: LSM: Create new + security_cred_getlsmblob LSM hook + - SAUCE: apparmor4.0.0 [14/87]: LSM stacking v39: Audit: Change context data + from secid to lsmblob + - SAUCE: apparmor4.0.0 [15/87]: LSM stacking v39: Netlabel: Use lsmblob for + audit data + - SAUCE: apparmor4.0.0 [16/87]: LSM stacking v39: LSM: Ensure the correct LSM + context releaser + - SAUCE: apparmor4.0.0 [17/87]: LSM stacking v39: LSM: Use lsmcontext in + security_secid_to_secctx + - SAUCE: apparmor4.0.0 [18/87]: LSM stacking v39: LSM: Use lsmcontext in + security_lsmblob_to_secctx + - SAUCE: apparmor4.0.0 [19/87]: LSM stacking v39: LSM: Use lsmcontext in + security_inode_getsecctx + - SAUCE: apparmor4.0.0 [20/87]: LSM stacking v39: LSM: Use lsmcontext in + security_dentry_init_security + - SAUCE: apparmor4.0.0 [21/87]: LSM stacking v39: LSM: + security_lsmblob_to_secctx module selection + - SAUCE: apparmor4.0.0 [22/87]: LSM stacking v39: Audit: Create audit_stamp + structure + - SAUCE: apparmor4.0.0 [23/87]: LSM stacking v39: Audit: Allow multiple + records in an audit_buffer + - SAUCE: apparmor4.0.0 [24/87]: LSM stacking v39: Audit: Add record for + multiple task security contexts + - SAUCE: apparmor4.0.0 [25/87]: LSM stacking v39: audit: multiple subject lsm + values for netlabel + - SAUCE: apparmor4.0.0 [26/87]: LSM stacking v39: Audit: Add record for + multiple object contexts + - SAUCE: apparmor4.0.0 [27/87]: LSM stacking v39: LSM: Remove unused + lsmcontext_init() + - SAUCE: apparmor4.0.0 [28/87]: LSM stacking v39: LSM: Improve logic in + security_getprocattr + - SAUCE: apparmor4.0.0 [29/87]: LSM stacking v39: LSM: secctx provider check + on release + - SAUCE: apparmor4.0.0 [31/87]: LSM stacking v39: LSM: Exclusive secmark usage + - SAUCE: apparmor4.0.0 [32/87]: LSM stacking v39: LSM: Identify which LSM + handles the context string + - SAUCE: apparmor4.0.0 [33/87]: LSM stacking v39: AppArmor: Remove the + exclusive flag + - SAUCE: apparmor4.0.0 [34/87]: LSM stacking v39: LSM: Add mount opts blob + size tracking + - SAUCE: apparmor4.0.0 [35/87]: LSM stacking v39: LSM: allocate mnt_opts blobs + instead of module specific data + - SAUCE: apparmor4.0.0 [36/87]: LSM stacking v39: LSM: Infrastructure + management of the key security blob + - SAUCE: apparmor4.0.0 [37/87]: LSM stacking v39: LSM: Infrastructure + management of the mnt_opts security blob + - SAUCE: apparmor4.0.0 [38/87]: LSM stacking v39: LSM: Correct handling of + ENOSYS in inode_setxattr + - SAUCE: apparmor4.0.0 [39/87]: LSM stacking v39: LSM: Remove lsmblob + scaffolding + - SAUCE: apparmor4.0.0 [40/87]: LSM stacking v39: LSM: Allow reservation of + netlabel + - SAUCE: apparmor4.0.0 [41/87]: LSM stacking v39: LSM: restrict + security_cred_getsecid() to a single LSM + - SAUCE: apparmor4.0.0 [42/87]: LSM stacking v39: Smack: Remove + LSM_FLAG_EXCLUSIVE + - SAUCE: apparmor4.0.0 [43/87]: LSM stacking v39: UBUNTU: SAUCE: apparmor4.0.0 + [12/95]: add/use fns to print hash string hex value + - SAUCE: apparmor4.0.0 [44/87]: patch to provide compatibility with v2.x net + rules + - SAUCE: apparmor4.0.0 [45/87]: add unpriviled user ns mediation + - SAUCE: apparmor4.0.0 [46/87]: Add sysctls for additional controls of unpriv + userns restrictions + - SAUCE: apparmor4.0.0 [47/87]: af_unix mediation + - SAUCE: apparmor4.0.0 [48/87]: Add fine grained mediation of posix mqueues + - SAUCE: apparmor4.0.0 [49/87]: setup slab cache for audit data + - SAUCE: apparmor4.0.0 [50/87]: Improve debug print infrastructure + - SAUCE: apparmor4.0.0 [51/87]: add the ability for profiles to have a + learning cache + - SAUCE: apparmor4.0.0 [52/87]: enable userspace upcall for mediation + - SAUCE: apparmor4.0.0 [53/87]: prompt - lock down prompt interface + - SAUCE: apparmor4.0.0 [54/87]: prompt - allow controlling of caching of a + prompt response + - SAUCE: apparmor4.0.0 [55/87]: prompt - add refcount to audit_node in prep or + reuse and delete + - SAUCE: apparmor4.0.0 [56/87]: prompt - refactor to moving caching to + uresponse + - SAUCE: apparmor4.0.0 [57/87]: prompt - Improve debug statements + - SAUCE: apparmor4.0.0 [58/87]: prompt - fix caching + - SAUCE: apparmor4.0.0 [59/87]: prompt - rework build to use append fn, to + simplify adding strings + - SAUCE: apparmor4.0.0 [60/87]: prompt - refcount notifications + - SAUCE: apparmor4.0.0 [61/87]: prompt - add the ability to reply with a + profile name + - SAUCE: apparmor4.0.0 [62/87]: prompt - fix notification cache when updating + - SAUCE: apparmor4.0.0 [63/87]: prompt - add tailglob on name for cache + support + - SAUCE: apparmor4.0.0 [64/87]: prompt - allow profiles to set prompts as + interruptible + - SAUCE: apparmor4.0.0 [65/87] v6.8 prompt:fixup interruptible + - SAUCE: apparmor4.0.0 [69/87]: add io_uring mediation + - SAUCE: apparmor4.0.0 [70/87]: apparmor: fix oops when racing to retrieve + notification + - SAUCE: apparmor4.0.0 [71/87]: apparmor: fix notification header size + - SAUCE: apparmor4.0.0 [72/87]: apparmor: fix request field from a prompt + reply that denies all access + - SAUCE: apparmor4.0.0 [73/87]: apparmor: open userns related sysctl so lxc + can check if restriction are in place + - SAUCE: apparmor4.0.0 [74/87]: apparmor: cleanup attachment perm lookup to + use lookup_perms() + - SAUCE: apparmor4.0.0 [75/87]: apparmor: remove redundant unconfined check. + - SAUCE: apparmor4.0.0 [76/87]: apparmor: switch signal mediation to using + RULE_MEDIATES + - SAUCE: apparmor4.0.0 [77/87]: apparmor: ensure labels with more than one + entry have correct flags + - SAUCE: apparmor4.0.0 [78/87]: apparmor: remove explicit restriction that + unconfined cannot use change_hat + - SAUCE: apparmor4.0.0 [79/87]: apparmor: cleanup: refactor file_perm() to + provide semantics of some checks + - SAUCE: apparmor4.0.0 [80/87]: apparmor: carry mediation check on label + - SAUCE: apparmor4.0.0 [81/87]: apparmor: convert easy uses of unconfined() to + label_mediates() + - SAUCE: apparmor4.0.0 [82/87]: apparmor: add additional flags to extended + permission. + - SAUCE: apparmor4.0.0 [83/87]: apparmor: add support for profiles to define + the kill signal + - SAUCE: apparmor4.0.0 [84/87]: apparmor: fix x_table_lookup when stacking is + not the first entry + - SAUCE: apparmor4.0.0 [85/87]: apparmor: allow profile to be transitioned + when a user ns is created + - SAUCE: apparmor4.0.0 [86/87]: apparmor: add ability to mediate caps with + policy state machine + - SAUCE: apparmor4.0.0 [87/87]: fixup notify + - [Config] disable CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + + * update apparmor and LSM stacking patch set (LP: #2028253) // [FFe] + apparmor-4.0.0-alpha2 for unprivileged user namespace restrictions in mantic + (LP: #2032602) + - SAUCE: apparmor4.0.0 [66/87]: prompt - add support for advanced filtering of + notifications + - SAUCE: apparmor4.0.0 [67/87]: userns - add the ability to reference a global + variable for a feature value + - SAUCE: apparmor4.0.0 [68/87]: userns - make it so special unconfined + profiles can mediate user namespaces + + * Enable lowlatency settings in the generic kernel (LP: #2051342) + - [Config] enable low-latency settings + + * hwmon: (coretemp) Fix core count limitation (LP: #2056126) + - hwmon: (coretemp) Introduce enum for attr index + - hwmon: (coretemp) Remove unnecessary dependency of array index + - hwmon: (coretemp) Replace sensor_device_attribute with device_attribute + - hwmon: (coretemp) Remove redundant pdata->cpu_map[] + - hwmon: (coretemp) Abstract core_temp helpers + - hwmon: (coretemp) Split package temp_data and core temp_data + - hwmon: (coretemp) Remove redundant temp_data->is_pkg_data + - hwmon: (coretemp) Use dynamic allocated memory for core temp_data + + * Miscellaneous Ubuntu changes + - [Config] Disable CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION + - [Packaging] remove debian/scripts/misc/arch-has-odm-enabled.sh + - rebase on v6.8 + - [Config] toolchain version update + + * Miscellaneous upstream changes + - crypto: qat - add fatal error notify method + + * Rebase on v6.8 + + -- Paolo Pisati Mon, 11 Mar 2024 10:14:10 +0100 + +linux (6.8.0-15.15) noble; urgency=medium + + * noble/linux: 6.8.0-15.15 -proposed tracker (LP: #2055871) + + * Miscellaneous Ubuntu changes + - rebase on v6.8-rc7 + + * Miscellaneous upstream changes + - Revert "UBUNTU: [Packaging] Transition laptop-23.10 to generic" + + * Rebase on v6.8-rc7 + + -- Paolo Pisati Mon, 04 Mar 2024 11:50:51 +0100 + +linux (6.8.0-14.14) noble; urgency=medium + + * noble/linux: 6.8.0-14.14 -proposed tracker (LP: #2055551) + + * Please change CONFIG_CONSOLE_LOGLEVEL_QUIET to 3 (LP: #2049390) + - [Config] reduce verbosity when booting in quiet mode + + * linux: please move erofs.ko (CONFIG_EROFS for EROFS support) from linux- + modules-extra to linux-modules (LP: #2054809) + - UBUNTU [Packaging]: Include erofs in linux-modules instead of linux-modules- + extra + + * linux: please move dmi-sysfs.ko (CONFIG_DMI_SYSFS for SMBIOS support) from + linux-modules-extra to linux-modules (LP: #2045561) + - [Packaging] Move dmi-sysfs.ko into linux-modules + + * Enable CONFIG_INTEL_IOMMU_DEFAULT_ON and + CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON (LP: #1951440) + - [Config] enable Intel DMA remapping by default + + * disable Intel DMA remapping by default (LP: #1971699) + - [Config] update tracking bug for CONFIG_INTEL_IOMMU_DEFAULT_ON + + * Packaging resync (LP: #1786013) + - debian.master/dkms-versions -- update from kernel-versions + (main/d2024.02.29) + + * Miscellaneous Ubuntu changes + - SAUCE: modpost: Replace 0-length array with flex-array member + - [packaging] do not include debian/ directory in a binary package + - [packaging] remove debian/stamps/keep-dir + + -- Paolo Pisati Fri, 01 Mar 2024 11:45:12 +0100 + +linux (6.8.0-13.13) noble; urgency=medium + + * noble/linux: 6.8.0-13.13 -proposed tracker (LP: #2055421) + + * Packaging resync (LP: #1786013) + - debian.master/dkms-versions -- update from kernel-versions + (main/d2024.02.29) + + * Miscellaneous Ubuntu changes + - rebase on v6.8-rc6 + - [Config] updateconfifs following v6.8-rc6 rebase + + * Rebase on v6.8-rc6 + + -- Paolo Pisati Thu, 29 Feb 2024 15:02:24 +0100 + +linux (6.8.0-12.12) noble; urgency=medium + + * linux-tools-common: man page of usbip[d] is misplaced (LP: #2054094) + - [Packaging] rules: Put usbip manpages in the correct directory + + * Validate connection interval to pass Bluetooth Test Suite (LP: #2052005) + - Bluetooth: Enforce validation on max value of connection interval + + * Turning COMPAT_32BIT_TIME off on s390x (LP: #2038583) + - [Config] Turn off 31-bit COMPAT on s390x + + * Don't produce linux-source binary package (LP: #2043994) + - [Packaging] Add debian/control sanity check + + * Don't produce linux-*-source- package (LP: #2052439) + - [Packaging] Move linux-source package stub to debian/control.d + - [Packaging] Build linux-source package only for the main kernel + + * Don't produce linux-*-cloud-tools-common, linux-*-tools-common and + linux-*-tools-host binary packages (LP: #2048183) + - [Packaging] Move indep tools package stubs to debian/control.d + - [Packaging] Build indep tools packages only for the main kernel + + * Enable CONFIG_INTEL_IOMMU_DEFAULT_ON and + CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON (LP: #1951440) + - [Config] enable Intel DMA remapping by default + + * disable Intel DMA remapping by default (LP: #1971699) + - [Config] update tracking bug for CONFIG_INTEL_IOMMU_DEFAULT_ON + + * Miscellaneous Ubuntu changes + - [Packaging] Transition laptop-23.10 to generic + + -- Paolo Pisati Thu, 22 Feb 2024 14:31:00 +0100 + +linux (6.8.0-11.11) noble; urgency=medium + + * noble/linux: 6.8.0-11.11 -proposed tracker (LP: #2053094) + + * Miscellaneous Ubuntu changes + - [Packaging] riscv64: disable building unnecessary binary debs + + -- Paolo Pisati Wed, 14 Feb 2024 00:04:31 +0100 + +linux (6.8.0-10.10) noble; urgency=medium + + * noble/linux: 6.8.0-10.10 -proposed tracker (LP: #2053015) + + * Miscellaneous Ubuntu changes + - [Packaging] add Rust build-deps for riscv64 + + * Miscellaneous upstream changes + - Revert "Revert "UBUNTU: [Packaging] temporarily disable Rust dependencies on + riscv64"" + + -- Paolo Pisati Tue, 13 Feb 2024 13:23:47 +0100 + +linux (6.8.0-9.9) noble; urgency=medium + + * noble/linux: 6.8.0-9.9 -proposed tracker (LP: #2052945) + + * Miscellaneous upstream changes + - Revert "UBUNTU: [Packaging] temporarily disable Rust dependencies on + riscv64" + + -- Paolo Pisati Mon, 12 Feb 2024 15:49:20 +0100 + +linux (6.8.0-8.8) noble; urgency=medium + + * noble/linux: 6.8.0-8.8 -proposed tracker (LP: #2052918) + + * Miscellaneous Ubuntu changes + - [Packaging] riscv64: enable linux-libc-dev build + - v6.8-rc4 rebase + + * Rebase on v6.8-rc4 + + -- Paolo Pisati Mon, 12 Feb 2024 10:13:34 +0100 + +linux (6.8.0-7.7) noble; urgency=medium + + * noble/linux: 6.8.0-7.7 -proposed tracker (LP: #2052691) + + * update apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor4.0.0 [01/87]: LSM stacking v39: integrity: disassociate + ima_filter_rule from security_audit_rule + - SAUCE: apparmor4.0.0 [02/87]: LSM stacking v39: SM: Infrastructure + management of the sock security + - SAUCE: apparmor4.0.0 [03/87]: LSM stacking v39: LSM: Add the lsmblob data + structure. + - SAUCE: apparmor4.0.0 [04/87]: LSM stacking v39: IMA: avoid label collisions + with stacked LSMs + - SAUCE: apparmor4.0.0 [05/87]: LSM stacking v39: LSM: Use lsmblob in + security_audit_rule_match + - SAUCE: apparmor4.0.0 [06/87]: LSM stacking v39: LSM: Add lsmblob_to_secctx + hook + - SAUCE: apparmor4.0.0 [07/87]: LSM stacking v39: Audit: maintain an lsmblob + in audit_context + - SAUCE: apparmor4.0.0 [08/87]: LSM stacking v39: LSM: Use lsmblob in + security_ipc_getsecid + - SAUCE: apparmor4.0.0 [09/87]: LSM stacking v39: Audit: Update shutdown LSM + data + - SAUCE: apparmor4.0.0 [10/87]: LSM stacking v39: LSM: Use lsmblob in + security_current_getsecid + - SAUCE: apparmor4.0.0 [11/87]: LSM stacking v39: LSM: Use lsmblob in + security_inode_getsecid + - SAUCE: apparmor4.0.0 [12/87]: LSM stacking v39: Audit: use an lsmblob in + audit_names + - SAUCE: apparmor4.0.0 [13/87]: LSM stacking v39: LSM: Create new + security_cred_getlsmblob LSM hook + - SAUCE: apparmor4.0.0 [14/87]: LSM stacking v39: Audit: Change context data + from secid to lsmblob + - SAUCE: apparmor4.0.0 [15/87]: LSM stacking v39: Netlabel: Use lsmblob for + audit data + - SAUCE: apparmor4.0.0 [16/87]: LSM stacking v39: LSM: Ensure the correct LSM + context releaser + - SAUCE: apparmor4.0.0 [17/87]: LSM stacking v39: LSM: Use lsmcontext in + security_secid_to_secctx + - SAUCE: apparmor4.0.0 [18/87]: LSM stacking v39: LSM: Use lsmcontext in + security_lsmblob_to_secctx + - SAUCE: apparmor4.0.0 [19/87]: LSM stacking v39: LSM: Use lsmcontext in + security_inode_getsecctx + - SAUCE: apparmor4.0.0 [20/87]: LSM stacking v39: LSM: Use lsmcontext in + security_dentry_init_security + - SAUCE: apparmor4.0.0 [21/87]: LSM stacking v39: LSM: + security_lsmblob_to_secctx module selection + - SAUCE: apparmor4.0.0 [22/87]: LSM stacking v39: Audit: Create audit_stamp + structure + - SAUCE: apparmor4.0.0 [23/87]: LSM stacking v39: Audit: Allow multiple + records in an audit_buffer + - SAUCE: apparmor4.0.0 [24/87]: LSM stacking v39: Audit: Add record for + multiple task security contexts + - SAUCE: apparmor4.0.0 [25/87]: LSM stacking v39: audit: multiple subject lsm + values for netlabel + - SAUCE: apparmor4.0.0 [26/87]: LSM stacking v39: Audit: Add record for + multiple object contexts + - SAUCE: apparmor4.0.0 [27/87]: LSM stacking v39: LSM: Remove unused + lsmcontext_init() + - SAUCE: apparmor4.0.0 [28/87]: LSM stacking v39: LSM: Improve logic in + security_getprocattr + - SAUCE: apparmor4.0.0 [29/87]: LSM stacking v39: LSM: secctx provider check + on release + - SAUCE: apparmor4.0.0 [31/87]: LSM stacking v39: LSM: Exclusive secmark usage + - SAUCE: apparmor4.0.0 [32/87]: LSM stacking v39: LSM: Identify which LSM + handles the context string + - SAUCE: apparmor4.0.0 [33/87]: LSM stacking v39: AppArmor: Remove the + exclusive flag + - SAUCE: apparmor4.0.0 [34/87]: LSM stacking v39: LSM: Add mount opts blob + size tracking + - SAUCE: apparmor4.0.0 [35/87]: LSM stacking v39: LSM: allocate mnt_opts blobs + instead of module specific data + - SAUCE: apparmor4.0.0 [36/87]: LSM stacking v39: LSM: Infrastructure + management of the key security blob + - SAUCE: apparmor4.0.0 [37/87]: LSM stacking v39: LSM: Infrastructure + management of the mnt_opts security blob + - SAUCE: apparmor4.0.0 [38/87]: LSM stacking v39: LSM: Correct handling of + ENOSYS in inode_setxattr + - SAUCE: apparmor4.0.0 [39/87]: LSM stacking v39: LSM: Remove lsmblob + scaffolding + - SAUCE: apparmor4.0.0 [40/87]: LSM stacking v39: LSM: Allow reservation of + netlabel + - SAUCE: apparmor4.0.0 [41/87]: LSM stacking v39: LSM: restrict + security_cred_getsecid() to a single LSM + - SAUCE: apparmor4.0.0 [42/87]: LSM stacking v39: Smack: Remove + LSM_FLAG_EXCLUSIVE + - SAUCE: apparmor4.0.0 [43/87]: LSM stacking v39: UBUNTU: SAUCE: apparmor4.0.0 + [12/95]: add/use fns to print hash string hex value + - SAUCE: apparmor4.0.0 [44/87]: patch to provide compatibility with v2.x net + rules + - SAUCE: apparmor4.0.0 [45/87]: add unpriviled user ns mediation + - SAUCE: apparmor4.0.0 [46/87]: Add sysctls for additional controls of unpriv + userns restrictions + - SAUCE: apparmor4.0.0 [47/87]: af_unix mediation + - SAUCE: apparmor4.0.0 [48/87]: Add fine grained mediation of posix mqueues + - SAUCE: apparmor4.0.0 [49/87]: setup slab cache for audit data + - SAUCE: apparmor4.0.0 [50/87]: Improve debug print infrastructure + - SAUCE: apparmor4.0.0 [51/87]: add the ability for profiles to have a + learning cache + - SAUCE: apparmor4.0.0 [52/87]: enable userspace upcall for mediation + - SAUCE: apparmor4.0.0 [53/87]: prompt - lock down prompt interface + - SAUCE: apparmor4.0.0 [54/87]: prompt - allow controlling of caching of a + prompt response + - SAUCE: apparmor4.0.0 [55/87]: prompt - add refcount to audit_node in prep or + reuse and delete + - SAUCE: apparmor4.0.0 [56/87]: prompt - refactor to moving caching to + uresponse + - SAUCE: apparmor4.0.0 [57/87]: prompt - Improve debug statements + - SAUCE: apparmor4.0.0 [58/87]: prompt - fix caching + - SAUCE: apparmor4.0.0 [59/87]: prompt - rework build to use append fn, to + simplify adding strings + - SAUCE: apparmor4.0.0 [60/87]: prompt - refcount notifications + - SAUCE: apparmor4.0.0 [61/87]: prompt - add the ability to reply with a + profile name + - SAUCE: apparmor4.0.0 [62/87]: prompt - fix notification cache when updating + - SAUCE: apparmor4.0.0 [63/87]: prompt - add tailglob on name for cache + support + - SAUCE: apparmor4.0.0 [64/87]: prompt - allow profiles to set prompts as + interruptible + - SAUCE: apparmor4.0.0 [65/87] v6.8 prompt:fixup interruptible + - SAUCE: apparmor4.0.0 [69/87]: add io_uring mediation + - SAUCE: apparmor4.0.0 [70/87]: apparmor: fix oops when racing to retrieve + notification + - SAUCE: apparmor4.0.0 [71/87]: apparmor: fix notification header size + - SAUCE: apparmor4.0.0 [72/87]: apparmor: fix request field from a prompt + reply that denies all access + - SAUCE: apparmor4.0.0 [73/87]: apparmor: open userns related sysctl so lxc + can check if restriction are in place + - SAUCE: apparmor4.0.0 [74/87]: apparmor: cleanup attachment perm lookup to + use lookup_perms() + - SAUCE: apparmor4.0.0 [75/87]: apparmor: remove redundant unconfined check. + - SAUCE: apparmor4.0.0 [76/87]: apparmor: switch signal mediation to using + RULE_MEDIATES + - SAUCE: apparmor4.0.0 [77/87]: apparmor: ensure labels with more than one + entry have correct flags + - SAUCE: apparmor4.0.0 [78/87]: apparmor: remove explicit restriction that + unconfined cannot use change_hat + - SAUCE: apparmor4.0.0 [79/87]: apparmor: cleanup: refactor file_perm() to + provide semantics of some checks + - SAUCE: apparmor4.0.0 [80/87]: apparmor: carry mediation check on label + - SAUCE: apparmor4.0.0 [81/87]: apparmor: convert easy uses of unconfined() to + label_mediates() + - SAUCE: apparmor4.0.0 [82/87]: apparmor: add additional flags to extended + permission. + - SAUCE: apparmor4.0.0 [83/87]: apparmor: add support for profiles to define + the kill signal + - SAUCE: apparmor4.0.0 [84/87]: apparmor: fix x_table_lookup when stacking is + not the first entry + - SAUCE: apparmor4.0.0 [85/87]: apparmor: allow profile to be transitioned + when a user ns is created + - SAUCE: apparmor4.0.0 [86/87]: apparmor: add ability to mediate caps with + policy state machine + - SAUCE: apparmor4.0.0 [87/87]: fixup notify + - [Config] disable CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + + * update apparmor and LSM stacking patch set (LP: #2028253) // [FFe] + apparmor-4.0.0-alpha2 for unprivileged user namespace restrictions in mantic + (LP: #2032602) + - SAUCE: apparmor4.0.0 [66/87]: prompt - add support for advanced filtering of + notifications + - SAUCE: apparmor4.0.0 [67/87]: userns - add the ability to reference a global + variable for a feature value + - SAUCE: apparmor4.0.0 [68/87]: userns - make it so special unconfined + profiles can mediate user namespaces + + -- Paolo Pisati Thu, 08 Feb 2024 12:05:44 +0100 + +linux (6.8.0-6.6) noble; urgency=medium + + * noble/linux: 6.8.0-6.6 -proposed tracker (LP: #2052592) + + * Packaging resync (LP: #1786013) + - debian.master/dkms-versions -- update from kernel-versions + (main/d2024.02.07) + - [Packaging] update variants + + * FIPS kernels should default to fips mode (LP: #2049082) + - SAUCE: Enable fips mode by default, in FIPS kernels only + + * Fix snapcraftyaml.yaml for jammy:linux-raspi (LP: #2051468) + - [Packaging] Remove old snapcraft.yaml + + * Azure: Fix regression introduced in LP: #2045069 (LP: #2052453) + - hv_netvsc: Register VF in netvsc_probe if NET_DEVICE_REGISTER missed + + * Miscellaneous Ubuntu changes + - [Packaging] Remove in-tree abi checks + - [Packaging] drop abi files with clean + - [Packaging] Remove do_full_source variable (fixup) + - [Packaging] Remove update-dkms-versions and move dkms-versions + - [Config] updateconfigs following v6.8-rc3 rebase + - [packaging] rename to linux + - [packaging] rebase on v6.8-rc3 + - [packaging] disable signing for ppc64el + + * Rebase on v6.8-rc3 + + -- Paolo Pisati Wed, 07 Feb 2024 15:13:52 +0100 + +linux (6.8.0-5.5) noble; urgency=medium + + * noble/linux-unstable: 6.8.0-5.5 -proposed tracker (LP: #2052136) + + * Miscellaneous upstream changes + - Revert "mm/sparsemem: fix race in accessing memory_section->usage" + + -- Paolo Pisati Fri, 02 Feb 2024 12:59:09 +0100 + +linux-unstable (6.8.0-4.4) noble; urgency=medium + + * noble/linux-unstable: 6.8.0-4.4 -proposed tracker (LP: #2051502) + + * Migrate from fbdev drivers to simpledrm and DRM fbdev emulation layer + (LP: #1965303) + - [Config] enable simpledrm and DRM fbdev emulation layer + + * Miscellaneous Ubuntu changes + - [Config] toolchain update + + * Miscellaneous upstream changes + - rust: upgrade to Rust 1.75.0 + + -- Paolo Pisati Mon, 29 Jan 2024 14:49:49 +0100 + +linux-unstable (6.8.0-3.3) noble; urgency=medium + + * noble/linux-unstable: 6.8.0-3.3 -proposed tracker (LP: #2051488) + + * update apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor4.0.0 [43/87]: LSM stacking v39: UBUNTU: SAUCE: apparmor4.0.0 + [12/95]: add/use fns to print hash string hex value + - SAUCE: apparmor4.0.0 [44/87]: patch to provide compatibility with v2.x net + rules + - SAUCE: apparmor4.0.0 [45/87]: add unpriviled user ns mediation + - SAUCE: apparmor4.0.0 [46/87]: Add sysctls for additional controls of unpriv + userns restrictions + - SAUCE: apparmor4.0.0 [47/87]: af_unix mediation + - SAUCE: apparmor4.0.0 [48/87]: Add fine grained mediation of posix mqueues + - SAUCE: apparmor4.0.0 [49/87]: setup slab cache for audit data + - SAUCE: apparmor4.0.0 [50/87]: Improve debug print infrastructure + - SAUCE: apparmor4.0.0 [51/87]: add the ability for profiles to have a + learning cache + - SAUCE: apparmor4.0.0 [52/87]: enable userspace upcall for mediation + - SAUCE: apparmor4.0.0 [53/87]: prompt - lock down prompt interface + - SAUCE: apparmor4.0.0 [54/87]: prompt - allow controlling of caching of a + prompt response + - SAUCE: apparmor4.0.0 [55/87]: prompt - add refcount to audit_node in prep or + reuse and delete + - SAUCE: apparmor4.0.0 [56/87]: prompt - refactor to moving caching to + uresponse + - SAUCE: apparmor4.0.0 [57/87]: prompt - Improve debug statements + - SAUCE: apparmor4.0.0 [58/87]: prompt - fix caching + - SAUCE: apparmor4.0.0 [59/87]: prompt - rework build to use append fn, to + simplify adding strings + - SAUCE: apparmor4.0.0 [60/87]: prompt - refcount notifications + - SAUCE: apparmor4.0.0 [61/87]: prompt - add the ability to reply with a + profile name + - SAUCE: apparmor4.0.0 [62/87]: prompt - fix notification cache when updating + - SAUCE: apparmor4.0.0 [63/87]: prompt - add tailglob on name for cache + support + - SAUCE: apparmor4.0.0 [64/87]: prompt - allow profiles to set prompts as + interruptible + - SAUCE: apparmor4.0.0 [69/87]: add io_uring mediation + - [Config] disable CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + + * apparmor restricts read access of user namespace mediation sysctls to root + (LP: #2040194) + - SAUCE: apparmor4.0.0 [73/87]: apparmor: open userns related sysctl so lxc + can check if restriction are in place + + * AppArmor spams kernel log with assert when auditing (LP: #2040192) + - SAUCE: apparmor4.0.0 [72/87]: apparmor: fix request field from a prompt + reply that denies all access + + * apparmor notification files verification (LP: #2040250) + - SAUCE: apparmor4.0.0 [71/87]: apparmor: fix notification header size + + * apparmor oops when racing to retrieve a notification (LP: #2040245) + - SAUCE: apparmor4.0.0 [70/87]: apparmor: fix oops when racing to retrieve + notification + + * update apparmor and LSM stacking patch set (LP: #2028253) // [FFe] + apparmor-4.0.0-alpha2 for unprivileged user namespace restrictions in mantic + (LP: #2032602) + - SAUCE: apparmor4.0.0 [66/87]: prompt - add support for advanced filtering of + notifications + - SAUCE: apparmor4.0.0 [67/87]: userns - add the ability to reference a global + variable for a feature value + - SAUCE: apparmor4.0.0 [68/87]: userns - make it so special unconfined + profiles can mediate user namespaces + + * Miscellaneous Ubuntu changes + - SAUCE: apparmor4.0.0 [01/87]: LSM stacking v39: integrity: disassociate + ima_filter_rule from security_audit_rule + - SAUCE: apparmor4.0.0 [02/87]: LSM stacking v39: SM: Infrastructure + management of the sock security + - SAUCE: apparmor4.0.0 [03/87]: LSM stacking v39: LSM: Add the lsmblob data + structure. + - SAUCE: apparmor4.0.0 [04/87]: LSM stacking v39: IMA: avoid label collisions + with stacked LSMs + - SAUCE: apparmor4.0.0 [05/87]: LSM stacking v39: LSM: Use lsmblob in + security_audit_rule_match + - SAUCE: apparmor4.0.0 [06/87]: LSM stacking v39: LSM: Add lsmblob_to_secctx + hook + - SAUCE: apparmor4.0.0 [07/87]: LSM stacking v39: Audit: maintain an lsmblob + in audit_context + - SAUCE: apparmor4.0.0 [08/87]: LSM stacking v39: LSM: Use lsmblob in + security_ipc_getsecid + - SAUCE: apparmor4.0.0 [09/87]: LSM stacking v39: Audit: Update shutdown LSM + data + - SAUCE: apparmor4.0.0 [10/87]: LSM stacking v39: LSM: Use lsmblob in + security_current_getsecid + - SAUCE: apparmor4.0.0 [11/87]: LSM stacking v39: LSM: Use lsmblob in + security_inode_getsecid + - SAUCE: apparmor4.0.0 [12/87]: LSM stacking v39: Audit: use an lsmblob in + audit_names + - SAUCE: apparmor4.0.0 [13/87]: LSM stacking v39: LSM: Create new + security_cred_getlsmblob LSM hook + - SAUCE: apparmor4.0.0 [14/87]: LSM stacking v39: Audit: Change context data + from secid to lsmblob + - SAUCE: apparmor4.0.0 [15/87]: LSM stacking v39: Netlabel: Use lsmblob for + audit data + - SAUCE: apparmor4.0.0 [16/87]: LSM stacking v39: LSM: Ensure the correct LSM + context releaser + - SAUCE: apparmor4.0.0 [17/87]: LSM stacking v39: LSM: Use lsmcontext in + security_secid_to_secctx + - SAUCE: apparmor4.0.0 [18/87]: LSM stacking v39: LSM: Use lsmcontext in + security_lsmblob_to_secctx + - SAUCE: apparmor4.0.0 [19/87]: LSM stacking v39: LSM: Use lsmcontext in + security_inode_getsecctx + - SAUCE: apparmor4.0.0 [20/87]: LSM stacking v39: LSM: Use lsmcontext in + security_dentry_init_security + - SAUCE: apparmor4.0.0 [21/87]: LSM stacking v39: LSM: + security_lsmblob_to_secctx module selection + - SAUCE: apparmor4.0.0 [22/87]: LSM stacking v39: Audit: Create audit_stamp + structure + - SAUCE: apparmor4.0.0 [23/87]: LSM stacking v39: Audit: Allow multiple + records in an audit_buffer + - SAUCE: apparmor4.0.0 [24/87]: LSM stacking v39: Audit: Add record for + multiple task security contexts + - SAUCE: apparmor4.0.0 [25/87]: LSM stacking v39: audit: multiple subject lsm + values for netlabel + - SAUCE: apparmor4.0.0 [26/87]: LSM stacking v39: Audit: Add record for + multiple object contexts + - SAUCE: apparmor4.0.0 [27/87]: LSM stacking v39: LSM: Remove unused + lsmcontext_init() + - SAUCE: apparmor4.0.0 [28/87]: LSM stacking v39: LSM: Improve logic in + security_getprocattr + - SAUCE: apparmor4.0.0 [29/87]: LSM stacking v39: LSM: secctx provider check + on release + - SAUCE: apparmor4.0.0 [30/87]: LSM stacking v39: LSM: Single calls in + socket_getpeersec hooks + - SAUCE: apparmor4.0.0 [31/87]: LSM stacking v39: LSM: Exclusive secmark usage + - SAUCE: apparmor4.0.0 [32/87]: LSM stacking v39: LSM: Identify which LSM + handles the context string + - SAUCE: apparmor4.0.0 [33/87]: LSM stacking v39: AppArmor: Remove the + exclusive flag + - SAUCE: apparmor4.0.0 [34/87]: LSM stacking v39: LSM: Add mount opts blob + size tracking + - SAUCE: apparmor4.0.0 [35/87]: LSM stacking v39: LSM: allocate mnt_opts blobs + instead of module specific data + - SAUCE: apparmor4.0.0 [36/87]: LSM stacking v39: LSM: Infrastructure + management of the key security blob + - SAUCE: apparmor4.0.0 [37/87]: LSM stacking v39: LSM: Infrastructure + management of the mnt_opts security blob + - SAUCE: apparmor4.0.0 [38/87]: LSM stacking v39: LSM: Correct handling of + ENOSYS in inode_setxattr + - SAUCE: apparmor4.0.0 [39/87]: LSM stacking v39: LSM: Remove lsmblob + scaffolding + - SAUCE: apparmor4.0.0 [40/87]: LSM stacking v39: LSM: Allow reservation of + netlabel + - SAUCE: apparmor4.0.0 [41/87]: LSM stacking v39: LSM: restrict + security_cred_getsecid() to a single LSM + - SAUCE: apparmor4.0.0 [42/87]: LSM stacking v39: Smack: Remove + LSM_FLAG_EXCLUSIVE + - SAUCE: apparmor4.0.0 [65/87] v6.8 prompt:fixup interruptible + - SAUCE: apparmor4.0.0 [74/87]: apparmor: cleanup attachment perm lookup to + use lookup_perms() + - SAUCE: apparmor4.0.0 [75/87]: apparmor: remove redundant unconfined check. + - SAUCE: apparmor4.0.0 [76/87]: apparmor: switch signal mediation to using + RULE_MEDIATES + - SAUCE: apparmor4.0.0 [77/87]: apparmor: ensure labels with more than one + entry have correct flags + - SAUCE: apparmor4.0.0 [78/87]: apparmor: remove explicit restriction that + unconfined cannot use change_hat + - SAUCE: apparmor4.0.0 [79/87]: apparmor: cleanup: refactor file_perm() to + provide semantics of some checks + - SAUCE: apparmor4.0.0 [80/87]: apparmor: carry mediation check on label + - SAUCE: apparmor4.0.0 [81/87]: apparmor: convert easy uses of unconfined() to + label_mediates() + - SAUCE: apparmor4.0.0 [82/87]: apparmor: add additional flags to extended + permission. + - SAUCE: apparmor4.0.0 [83/87]: apparmor: add support for profiles to define + the kill signal + - SAUCE: apparmor4.0.0 [84/87]: apparmor: fix x_table_lookup when stacking is + not the first entry + - SAUCE: apparmor4.0.0 [85/87]: apparmor: allow profile to be transitioned + when a user ns is created + - SAUCE: apparmor4.0.0 [86/87]: apparmor: add ability to mediate caps with + policy state machine + - SAUCE: apparmor4.0.0 [87/87]: fixup notify + - [Config] updateconfigs following v6.8-rc2 rebase + + -- Paolo Pisati Mon, 29 Jan 2024 08:59:32 +0100 + +linux-unstable (6.8.0-2.2) noble; urgency=medium + + * noble/linux-unstable: 6.8.0-2.2 -proposed tracker (LP: #2051110) + + * Miscellaneous Ubuntu changes + - [Config] toolchain update + - [Config] enable Rust + + -- Paolo Pisati Wed, 24 Jan 2024 13:10:07 +0100 + +linux-unstable (6.8.0-1.1) noble; urgency=medium + + * noble/linux-unstable: 6.8.0-1.1 -proposed tracker (LP: #2051102) + + * Miscellaneous Ubuntu changes + - [packaging] move to v6.8-rc1 + - [Config] updateconfigs following v6.8-rc1 rebase + - SAUCE: export file_close_fd() instead of close_fd_get_file() + - SAUCE: cpufreq: s/strlcpy/strscpy/ + - debian/dkms-versions -- temporarily disable zfs dkms + - debian/dkms-versions -- temporarily disable ipu6 and isvsc dkms + - debian/dkms-versions -- temporarily disable v4l2loopback + + -- Paolo Pisati Wed, 24 Jan 2024 10:48:37 +0100 + +linux-unstable (6.8.0-0.0) noble; urgency=medium + + * Empty entry. + + -- Paolo Pisati Tue, 23 Jan 2024 11:36:40 +0100 + +linux-unstable (6.7.0-7.7) noble; urgency=medium + + * noble/linux-unstable: 6.7.0-7.7 -proposed tracker (LP: #2049357) + + * Packaging resync (LP: #1786013) + - [Packaging] update variants + + * Miscellaneous Ubuntu changes + - [Packaging] re-enable signing for s390x and ppc64el + + -- Andrea Righi Mon, 15 Jan 2024 08:41:11 +0100 + +linux-unstable (6.7.0-6.6) noble; urgency=medium + + * Empty entry. + + -- Andrea Righi Mon, 15 Jan 2024 08:30:50 +0100 + +linux (6.7.0-2.2) noble; urgency=medium + + * noble/linux: 6.7.0-2.2 -proposed tracker (LP: #2049182) + + * Packaging resync (LP: #1786013) + - [Packaging] resync getabis + + * Enforce RETPOLINE and SLS mitigrations (LP: #2046440) + - SAUCE: objtool: Make objtool check actually fatal upon fatal errors + - SAUCE: objtool: make objtool SLS validation fatal when building with + CONFIG_SLS=y + - SAUCE: objtool: make objtool RETPOLINE validation fatal when building with + CONFIG_RETPOLINE=y + - SAUCE: scripts: remove generating .o-ur objects + - [Packaging] Remove all custom retpoline-extract code + - Revert "UBUNTU: SAUCE: vga_set_mode -- avoid jump tables" + - Revert "UBUNTU: SAUCE: early/late -- annotate indirect calls in early/late + initialisation code" + - Revert "UBUNTU: SAUCE: apm -- annotate indirect calls within + firmware_restrict_branch_speculation_{start,end}" + + * Miscellaneous Ubuntu changes + - [Packaging] temporarily disable riscv64 builds + - [Packaging] temporarily disable Rust dependencies on riscv64 + + -- Andrea Righi Fri, 12 Jan 2024 09:21:57 +0100 + +linux (6.7.0-1.1) noble; urgency=medium + + * noble/linux: 6.7.0-1.1 -proposed tracker (LP: #2048859) + + * Packaging resync (LP: #1786013) + - [Packaging] update variants + - debian/dkms-versions -- update from kernel-versions (main/d2024.01.02) + + * [UBUNTU 23.04] Regression: Ubuntu 23.04/23.10 do not include uvdevice + anymore (LP: #2048919) + - [Config] Enable S390_UV_UAPI (built-in) + + * Support mipi camera on Intel Meteor Lake platform (LP: #2031412) + - SAUCE: iommu: intel-ipu: use IOMMU passthrough mode for Intel IPUs on Meteor + Lake + - SAUCE: platform/x86: int3472: Add handshake GPIO function + + * [SRU][J/L/M] UBUNTU: [Packaging] Make WWAN driver a loadable module + (LP: #2033406) + - [Packaging] Make WWAN driver loadable modules + + * usbip: error: failed to open /usr/share/hwdata//usb.ids (LP: #2039439) + - [Packaging] Make linux-tools-common depend on hwdata + + * [Mediatek] mt8195-demo: enable CONFIG_MTK_IOMMU as module for multimedia and + PCIE peripherals (LP: #2036587) + - [Config] Enable CONFIG_MTK_IOMMU on arm64 + + * linux-*: please enable dm-verity kconfigs to allow MoK/db verified root + images (LP: #2019040) + - [Config] CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG_SECONDARY_KEYRING=y + + * kexec enable to load/kdump zstd compressed zimg (LP: #2037398) + - [Packaging] Revert arm64 image format to Image.gz + + * Mantic minimized/minimal cloud images do not receive IP address during + provisioning; systemd regression with wait-online (LP: #2036968) + - [Config] Enable virtio-net as built-in to avoid race + + * Make backlight module auto detect dell_uart_backlight (LP: #2008882) + - SAUCE: ACPI: video: Dell AIO UART backlight detection + + * Linux 6.2 fails to reboot with current u-boot-nezha (LP: #2021364) + - [Config] Default to performance CPUFreq governor on riscv64 + + * Enable Nezha board (LP: #1975592) + - [Config] Build in D1 clock drivers on riscv64 + - [Config] Enable CONFIG_SUN6I_RTC_CCU on riscv64 + - [Config] Enable CONFIG_SUNXI_WATCHDOG on riscv64 + - [Config] Disable SUN50I_DE2_BUS on riscv64 + - [Config] Disable unneeded sunxi pinctrl drivers on riscv64 + + * Enable StarFive VisionFive 2 board (LP: #2013232) + - [Config] Enable CONFIG_PINCTRL_STARFIVE_JH7110_SYS on riscv64 + - [Config] Enable CONFIG_STARFIVE_WATCHDOG on riscv64 + + * rcu_sched detected stalls on CPUs/tasks (LP: #1967130) + - [Config] Enable virtually mapped stacks on riscv64 + + * Check for changes relevant for security certifications (LP: #1945989) + - [Packaging] Add a new fips-checks script + + * Installation support for SMARC RZ/G2L platform (LP: #2030525) + - [Config] build Renesas RZ/G2L USBPHY control driver statically + + * Add support for kernels compiled with CONFIG_EFI_ZBOOT (LP: #2002226) + - [Config]: Turn on CONFIG_EFI_ZBOOT on ARM64 + + * Default module signing algo should be accelerated (LP: #2034061) + - [Config] Default module signing algo should be accelerated + + * Miscellaneous Ubuntu changes + - [Config] annotations clean-up + + [ Upstream Kernel Changes ] + + * Rebase to v6.7 + + -- Andrea Righi Thu, 11 Jan 2024 11:49:07 +0100 + +linux (6.7.0-0.0) noble; urgency=medium + + * Empty entry + + -- Andrea Righi Tue, 09 Jan 2024 09:27:23 +0100 + +linux-unstable (6.7.0-5.5) noble; urgency=medium + + * noble/linux-unstable: 6.7.0-5.5 -proposed tracker (LP: #2048118) + + * Packaging resync (LP: #1786013) + - debian/dkms-versions -- update from kernel-versions (main/d2024.01.02) + + * Miscellaneous Ubuntu changes + - [Packaging] re-enable Rust support + - [Packaging] temporarily disable riscv64 builds + + -- Andrea Righi Fri, 05 Jan 2024 12:33:10 +0100 + +linux-unstable (6.7.0-4.4) noble; urgency=medium + + * noble/linux-unstable: 6.7.0-4.4 -proposed tracker (LP: #2047807) + + * unconfined profile denies userns_create for chromium based processes + (LP: #1990064) + - [Config] disable CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + + * apparmor restricts read access of user namespace mediation sysctls to root + (LP: #2040194) + - SAUCE: apparmor4.0.0 [69/69]: apparmor: open userns related sysctl so lxc + can check if restriction are in place + + * AppArmor spams kernel log with assert when auditing (LP: #2040192) + - SAUCE: apparmor4.0.0 [68/69]: apparmor: fix request field from a prompt + reply that denies all access + + * apparmor notification files verification (LP: #2040250) + - SAUCE: apparmor4.0.0 [67/69]: apparmor: fix notification header size + + * apparmor oops when racing to retrieve a notification (LP: #2040245) + - SAUCE: apparmor4.0.0 [66/69]: apparmor: fix oops when racing to retrieve + notification + + * update apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor4.0.0 [01/69]: add/use fns to print hash string hex value + - SAUCE: apparmor4.0.0 [02/69]: patch to provide compatibility with v2.x net + rules + - SAUCE: apparmor4.0.0 [03/69]: add unpriviled user ns mediation + - SAUCE: apparmor4.0.0 [04/69]: Add sysctls for additional controls of unpriv + userns restrictions + - SAUCE: apparmor4.0.0 [05/69]: af_unix mediation + - SAUCE: apparmor4.0.0 [06/69]: Add fine grained mediation of posix mqueues + - SAUCE: apparmor4.0.0 [07/69]: Stacking v38: LSM: Identify modules by more + than name + - SAUCE: apparmor4.0.0 [08/69]: Stacking v38: LSM: Add an LSM identifier for + external use + - SAUCE: apparmor4.0.0 [09/69]: Stacking v38: LSM: Identify the process + attributes for each module + - SAUCE: apparmor4.0.0 [10/69]: Stacking v38: LSM: Maintain a table of LSM + attribute data + - SAUCE: apparmor4.0.0 [11/69]: Stacking v38: proc: Use lsmids instead of lsm + names for attrs + - SAUCE: apparmor4.0.0 [12/69]: Stacking v38: integrity: disassociate + ima_filter_rule from security_audit_rule + - SAUCE: apparmor4.0.0 [13/69]: Stacking v38: LSM: Infrastructure management + of the sock security + - SAUCE: apparmor4.0.0 [14/69]: Stacking v38: LSM: Add the lsmblob data + structure. + - SAUCE: apparmor4.0.0 [15/69]: Stacking v38: LSM: provide lsm name and id + slot mappings + - SAUCE: apparmor4.0.0 [16/69]: Stacking v38: IMA: avoid label collisions with + stacked LSMs + - SAUCE: apparmor4.0.0 [17/69]: Stacking v38: LSM: Use lsmblob in + security_audit_rule_match + - SAUCE: apparmor4.0.0 [18/69]: Stacking v38: LSM: Use lsmblob in + security_kernel_act_as + - SAUCE: apparmor4.0.0 [19/69]: Stacking v38: LSM: Use lsmblob in + security_secctx_to_secid + - SAUCE: apparmor4.0.0 [20/69]: Stacking v38: LSM: Use lsmblob in + security_secid_to_secctx + - SAUCE: apparmor4.0.0 [21/69]: Stacking v38: LSM: Use lsmblob in + security_ipc_getsecid + - SAUCE: apparmor4.0.0 [22/69]: Stacking v38: LSM: Use lsmblob in + security_current_getsecid + - SAUCE: apparmor4.0.0 [23/69]: Stacking v38: LSM: Use lsmblob in + security_inode_getsecid + - SAUCE: apparmor4.0.0 [24/69]: Stacking v38: LSM: Use lsmblob in + security_cred_getsecid + - SAUCE: apparmor4.0.0 [25/69]: Stacking v38: LSM: Specify which LSM to + display + - SAUCE: apparmor4.0.0 [27/69]: Stacking v38: LSM: Ensure the correct LSM + context releaser + - SAUCE: apparmor4.0.0 [28/69]: Stacking v38: LSM: Use lsmcontext in + security_secid_to_secctx + - SAUCE: apparmor4.0.0 [29/69]: Stacking v38: LSM: Use lsmcontext in + security_inode_getsecctx + - SAUCE: apparmor4.0.0 [30/69]: Stacking v38: Use lsmcontext in + security_dentry_init_security + - SAUCE: apparmor4.0.0 [31/69]: Stacking v38: LSM: security_secid_to_secctx in + netlink netfilter + - SAUCE: apparmor4.0.0 [32/69]: Stacking v38: NET: Store LSM netlabel data in + a lsmblob + - SAUCE: apparmor4.0.0 [33/69]: Stacking v38: binder: Pass LSM identifier for + confirmation + - SAUCE: apparmor4.0.0 [34/69]: Stacking v38: LSM: security_secid_to_secctx + module selection + - SAUCE: apparmor4.0.0 [35/69]: Stacking v38: Audit: Keep multiple LSM data in + audit_names + - SAUCE: apparmor4.0.0 [36/69]: Stacking v38: Audit: Create audit_stamp + structure + - SAUCE: apparmor4.0.0 [37/69]: Stacking v38: LSM: Add a function to report + multiple LSMs + - SAUCE: apparmor4.0.0 [38/69]: Stacking v38: Audit: Allow multiple records in + an audit_buffer + - SAUCE: apparmor4.0.0 [39/69]: Stacking v38: Audit: Add record for multiple + task security contexts + - SAUCE: apparmor4.0.0 [40/69]: Stacking v38: audit: multiple subject lsm + values for netlabel + - SAUCE: apparmor4.0.0 [41/69]: Stacking v38: Audit: Add record for multiple + object contexts + - SAUCE: apparmor4.0.0 [42/69]: Stacking v38: netlabel: Use a struct lsmblob + in audit data + - SAUCE: apparmor4.0.0 [43/69]: Stacking v38: LSM: Removed scaffolding + function lsmcontext_init + - SAUCE: apparmor4.0.0 [44/69]: Stacking v38: AppArmor: Remove the exclusive + flag + - SAUCE: apparmor4.0.0 [45/69]: setup slab cache for audit data + - SAUCE: apparmor4.0.0 [46/69]: Improve debug print infrastructure + - SAUCE: apparmor4.0.0 [47/69]: add the ability for profiles to have a + learning cache + - SAUCE: apparmor4.0.0 [48/69]: enable userspace upcall for mediation + - SAUCE: apparmor4.0.0 [49/69]: prompt - lock down prompt interface + - SAUCE: apparmor4.0.0 [50/69]: prompt - allow controlling of caching of a + prompt response + - SAUCE: apparmor4.0.0 [51/69]: prompt - add refcount to audit_node in prep or + reuse and delete + - SAUCE: apparmor4.0.0 [52/69]: prompt - refactor to moving caching to + uresponse + - SAUCE: apparmor4.0.0 [53/69]: prompt - Improve debug statements + - SAUCE: apparmor4.0.0 [54/69]: prompt - fix caching + - SAUCE: apparmor4.0.0 [55/69]: prompt - rework build to use append fn, to + simplify adding strings + - SAUCE: apparmor4.0.0 [56/69]: prompt - refcount notifications + - SAUCE: apparmor4.0.0 [57/69]: prompt - add the ability to reply with a + profile name + - SAUCE: apparmor4.0.0 [58/69]: prompt - fix notification cache when updating + - SAUCE: apparmor4.0.0 [59/69]: prompt - add tailglob on name for cache + support + - SAUCE: apparmor4.0.0 [60/69]: prompt - allow profiles to set prompts as + interruptible + - SAUCE: apparmor4.0.0 [64/69]: advertise disconnected.path is available + - SAUCE: apparmor4.0.0 [65/69]: add io_uring mediation + + * update apparmor and LSM stacking patch set (LP: #2028253) // [FFe] + apparmor-4.0.0-alpha2 for unprivileged user namespace restrictions in mantic + (LP: #2032602) + - SAUCE: apparmor4.0.0 [61/69]: prompt - add support for advanced filtering of + notifications + - SAUCE: apparmor4.0.0 [62/69]: userns - add the ability to reference a global + variable for a feature value + - SAUCE: apparmor4.0.0 [63/69]: userns - make it so special unconfined + profiles can mediate user namespaces + + * udev fails to make prctl() syscall with apparmor=0 (as used by maas by + default) (LP: #2016908) // update apparmor and LSM stacking patch set + (LP: #2028253) + - SAUCE: apparmor4.0.0 [26/69]: Stacking v38: Fix prctl() syscall with + apparmor=0 + + * Fix RPL-U CPU C-state always keep at C3 when system run PHM with idle screen + on (LP: #2042385) + - SAUCE: r8169: Add quirks to enable ASPM on Dell platforms + + * [Debian] autoreconstruct - Do not generate chmod -x for deleted files + (LP: #2045562) + - [Debian] autoreconstruct - Do not generate chmod -x for deleted files + + * Disable Legacy TIOCSTI (LP: #2046192) + - [Config]: disable CONFIG_LEGACY_TIOCSTI + + * Packaging resync (LP: #1786013) + - [Packaging] update variants + - [Packaging] remove helper scripts + - [Packaging] update annotations scripts + + * Miscellaneous Ubuntu changes + - [Packaging] rules: Remove unused dkms make variables + - [Config] update annotations after rebase to v6.7-rc8 + + [ Upstream Kernel Changes ] + + * Rebase to v6.7-rc8 + + -- Andrea Righi Tue, 02 Jan 2024 14:57:21 +0100 + +linux-unstable (6.7.0-3.3) noble; urgency=medium + + * noble/linux-unstable: 6.7.0-3.3 -proposed tracker (LP: #2046060) + + * enable CONFIG_INTEL_TDX_HOST in linux >= 6.7 for noble (LP: #2046040) + - [Config] enable CONFIG_INTEL_TDX_HOST + + * linux tools packages for derived kernels refuse to install simultaneously + due to libcpupower name collision (LP: #2035971) + - [Packaging] Statically link libcpupower into cpupower tool + + * make lazy RCU a boot time option (LP: #2045492) + - SAUCE: rcu: Provide a boot time parameter to control lazy RCU + + * Build failure if run in a console (LP: #2044512) + - [Packaging] Fix kernel module compression failures + + * Turning COMPAT_32BIT_TIME off on arm64 (64k & derivatives) (LP: #2038582) + - [Config] y2038: Turn off COMPAT and COMPAT_32BIT_TIME on arm64 64k + + * Turning COMPAT_32BIT_TIME off on riscv64 (LP: #2038584) + - [Config] y2038: Disable COMPAT_32BIT_TIME on riscv64 + + * Turning COMPAT_32BIT_TIME off on ppc64el (LP: #2038587) + - [Config] y2038: Disable COMPAT and COMPAT_32BIT_TIME on ppc64le + + * [UBUNTU 23.04] Kernel config option missing for s390x PCI passthrough + (LP: #2042853) + - [Config] CONFIG_VFIO_PCI_ZDEV_KVM=y + + * back-out zstd module compression automatic for backports (LP: #2045593) + - [Packaging] make ZSTD module compression conditional + + * Miscellaneous Ubuntu changes + - [Packaging] Remove do_full_source variable + - [Packaging] Remove obsolete config handling + - [Packaging] Remove support for sub-flavors + - [Packaging] Remove old linux-libc-dev version hack + - [Packaging] Remove obsolete scripts + - [Packaging] Remove README.inclusion-list + - [Packaging] make $(stampdir)/stamp-build-perarch depend on build-arch + - [Packaging] Enable rootless builds + - [Packaging] Allow to run debian/rules without (fake)root + - [Packaging] remove unneeded trailing slash for INSTALL_MOD_PATH + - [Packaging] override KERNELRELEASE instead of KERNELVERSION + - [Config] update toolchain versions in annotations + - [Packaging] drop useless linux-doc + - [Packaging] scripts: Rewrite insert-ubuntu-changes in Python + - [Packaging] enable riscv64 builds + - [Packaging] remove the last sub-flavours bit + - [Packaging] check debian.env to determine do_libc_dev_package + - [Packaging] remove debian.*/variants + - [Packaging] remove do_libc_dev_package variable + - [Packaging] move linux-libc-dev.stub to debian/control.d/ + - [Packaging] Update check to build linux-libc-dev to the source package name + - [Packaging] rules: Remove startnewrelease target + - [Packaging] Remove debian/commit-templates + - [Config] update annotations after rebase to v6.7-rc4 + + [ Upstream Kernel Changes ] + + * Rebase to v6.7-rc4 + + -- Andrea Righi Mon, 11 Dec 2023 15:56:11 +0100 + +linux-unstable (6.7.0-2.2) noble; urgency=medium + + * noble/linux-unstable: 6.7.0-2.2 -proposed tracker (LP: #2045107) + + * Miscellaneous Ubuntu changes + - [Packaging] re-enable Rust + - [Config] enable Rust in annotations + - [Packaging] Remove do_enforce_all variable + - [Config] disable Softlogic 6x10 capture card driver on armhf + - [Packaging] disable Rust support + - [Config] update annotations after rebase to v6.7-rc3 + + [ Upstream Kernel Changes ] + + * Rebase to v6.7-rc3 + + -- Andrea Righi Wed, 29 Nov 2023 07:51:17 +0100 + +linux-unstable (6.7.0-1.1) noble; urgency=medium + + * noble/linux-unstable: 6.7.0-1.1 -proposed tracker (LP: #2044069) + + * Packaging resync (LP: #1786013) + - [Packaging] update annotations scripts + - [Packaging] update helper scripts + + * Miscellaneous Ubuntu changes + - [Config] update annotations after rebase to v6.7-rc2 + + [ Upstream Kernel Changes ] + + * Rebase to v6.7-rc2 + + -- Andrea Righi Tue, 21 Nov 2023 10:45:24 +0100 + +linux-unstable (6.7.0-0.0) noble; urgency=medium + + * Empty entry + + -- Andrea Righi Tue, 21 Nov 2023 07:26:46 +0100 + +linux-unstable (6.6.0-12.12) noble; urgency=medium + + * noble/linux-unstable: 6.6.0-12.12 -proposed tracker (LP: #2043664) + + * Miscellaneous Ubuntu changes + - [Packaging] temporarily disable zfs dkms + + -- Paolo Pisati Thu, 16 Nov 2023 10:20:26 +0100 + +linux-unstable (6.6.0-11.11) noble; urgency=medium + + * noble/linux-unstable: 6.6.0-11.11 -proposed tracker (LP: #2043480) + + * Packaging resync (LP: #1786013) + - [Packaging] resync git-ubuntu-log + - [Packaging] resync update-dkms-versions helper + - [Packaging] update variants + - debian/dkms-versions -- update from kernel-versions (main/d2023.11.14) + + * Miscellaneous Ubuntu changes + - [Packaging] move to Noble + - [Config] toolchain version update + + -- Paolo Pisati Wed, 15 Nov 2023 14:50:40 +0100 + +linux-unstable (6.6.0-10.10) noble; urgency=medium + + * mantic/linux-unstable: 6.6.0-10.10 -proposed tracker (LP: #2043088) + + * Bump arm64's CONFIG_NR_CPUS to 512 (LP: #2042897) + - [Config] Bump CONFIG_NR_CPUS to 512 for arm64 + + * Miscellaneous Ubuntu changes + - [Config] Include a note for the NR_CPUS setting on riscv64 + - SAUCE: apparmor4.0.0 [83/83]: Fix inode_init for changed prototype + + -- Paolo Pisati Thu, 09 Nov 2023 12:05:11 +0200 + +linux-unstable (6.6.0-9.9) mantic; urgency=medium + + * mantic/linux-unstable: 6.6.0-9.9 -proposed tracker (LP: #2041852) + + * Switch IMA default hash to sha256 (LP: #2041735) + - [Config] Switch IMA_DEFAULT_HASH from sha1 to sha256 + + * apparmor restricts read access of user namespace mediation sysctls to root + (LP: #2040194) + - SAUCE: apparmor4.0.0 [82/82]: apparmor: open userns related sysctl so lxc + can check if restriction are in place + + * AppArmor spams kernel log with assert when auditing (LP: #2040192) + - SAUCE: apparmor4.0.0 [81/82]: apparmor: fix request field from a prompt + reply that denies all access + + * apparmor notification files verification (LP: #2040250) + - SAUCE: apparmor4.0.0 [80/82]: apparmor: fix notification header size + + * apparmor oops when racing to retrieve a notification (LP: #2040245) + - SAUCE: apparmor4.0.0 [79/82]: apparmor: fix oops when racing to retrieve + notification + + * Disable restricting unprivileged change_profile by default, due to LXD + latest/stable not yet compatible with this new apparmor feature + (LP: #2038567) + - SAUCE: apparmor4.0.0 [78/82]: apparmor: Make + apparmor_restrict_unprivileged_unconfined opt-in + + * update apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor4.0.0 [01/82]: add/use fns to print hash string hex value + - SAUCE: apparmor4.0.0 [02/82]: rename SK_CTX() to aa_sock and make it an + inline fn + - SAUCE: apparmor4.0.0 [03/82]: patch to provide compatibility with v2.x net + rules + - SAUCE: apparmor4.0.0 [04/82]: add user namespace creation mediation + - SAUCE: apparmor4.0.0 [05/82]: Add sysctls for additional controls of unpriv + userns restrictions + - SAUCE: apparmor4.0.0 [06/82]: af_unix mediation + - SAUCE: apparmor4.0.0 [07/82]: Add fine grained mediation of posix mqueues + - SAUCE: apparmor4.0.0 [08/82]: Stacking v38: LSM: Identify modules by more + than name + - SAUCE: apparmor4.0.0 [09/82]: Stacking v38: LSM: Add an LSM identifier for + external use + - SAUCE: apparmor4.0.0 [10/82]: Stacking v38: LSM: Identify the process + attributes for each module + - SAUCE: apparmor4.0.0 [11/82]: Stacking v38: LSM: Maintain a table of LSM + attribute data + - SAUCE: apparmor4.0.0 [12/82]: Stacking v38: proc: Use lsmids instead of lsm + names for attrs + - SAUCE: apparmor4.0.0 [13/82]: Stacking v38: integrity: disassociate + ima_filter_rule from security_audit_rule + - SAUCE: apparmor4.0.0 [14/82]: Stacking v38: LSM: Infrastructure management + of the sock security + - SAUCE: apparmor4.0.0 [15/82]: Stacking v38: LSM: Add the lsmblob data + structure. + - SAUCE: apparmor4.0.0 [16/82]: Stacking v38: LSM: provide lsm name and id + slot mappings + - SAUCE: apparmor4.0.0 [17/82]: Stacking v38: IMA: avoid label collisions with + stacked LSMs + - SAUCE: apparmor4.0.0 [18/82]: Stacking v38: LSM: Use lsmblob in + security_audit_rule_match + - SAUCE: apparmor4.0.0 [19/82]: Stacking v38: LSM: Use lsmblob in + security_kernel_act_as + - SAUCE: apparmor4.0.0 [20/82]: Stacking v38: LSM: Use lsmblob in + security_secctx_to_secid + - SAUCE: apparmor4.0.0 [21/82]: Stacking v38: LSM: Use lsmblob in + security_secid_to_secctx + - SAUCE: apparmor4.0.0 [22/82]: Stacking v38: LSM: Use lsmblob in + security_ipc_getsecid + - SAUCE: apparmor4.0.0 [23/82]: Stacking v38: LSM: Use lsmblob in + security_current_getsecid + - SAUCE: apparmor4.0.0 [24/82]: Stacking v38: LSM: Use lsmblob in + security_inode_getsecid + - SAUCE: apparmor4.0.0 [25/82]: Stacking v38: LSM: Use lsmblob in + security_cred_getsecid + - SAUCE: apparmor4.0.0 [26/82]: Stacking v38: LSM: Specify which LSM to + display + - SAUCE: apparmor4.0.0 [28/82]: Stacking v38: LSM: Ensure the correct LSM + context releaser + - SAUCE: apparmor4.0.0 [29/82]: Stacking v38: LSM: Use lsmcontext in + security_secid_to_secctx + - SAUCE: apparmor4.0.0 [30/82]: Stacking v38: LSM: Use lsmcontext in + security_inode_getsecctx + - SAUCE: apparmor4.0.0 [31/82]: Stacking v38: Use lsmcontext in + security_dentry_init_security + - SAUCE: apparmor4.0.0 [32/82]: Stacking v38: LSM: security_secid_to_secctx in + netlink netfilter + - SAUCE: apparmor4.0.0 [33/82]: Stacking v38: NET: Store LSM netlabel data in + a lsmblob + - SAUCE: apparmor4.0.0 [34/82]: Stacking v38: binder: Pass LSM identifier for + confirmation + - SAUCE: apparmor4.0.0 [35/82]: Stacking v38: LSM: security_secid_to_secctx + module selection + - SAUCE: apparmor4.0.0 [36/82]: Stacking v38: Audit: Keep multiple LSM data in + audit_names + - SAUCE: apparmor4.0.0 [37/82]: Stacking v38: Audit: Create audit_stamp + structure + - SAUCE: apparmor4.0.0 [38/82]: Stacking v38: LSM: Add a function to report + multiple LSMs + - SAUCE: apparmor4.0.0 [39/82]: Stacking v38: Audit: Allow multiple records in + an audit_buffer + - SAUCE: apparmor4.0.0 [40/82]: Stacking v38: Audit: Add record for multiple + task security contexts + - SAUCE: apparmor4.0.0 [41/82]: Stacking v38: audit: multiple subject lsm + values for netlabel + - SAUCE: apparmor4.0.0 [42/82]: Stacking v38: Audit: Add record for multiple + object contexts + - SAUCE: apparmor4.0.0 [43/82]: Stacking v38: netlabel: Use a struct lsmblob + in audit data + - SAUCE: apparmor4.0.0 [44/82]: Stacking v38: LSM: Removed scaffolding + function lsmcontext_init + - SAUCE: apparmor4.0.0 [45/82]: Stacking v38: AppArmor: Remove the exclusive + flag + - SAUCE: apparmor4.0.0 [46/82]: combine common_audit_data and + apparmor_audit_data + - SAUCE: apparmor4.0.0 [47/82]: setup slab cache for audit data + - SAUCE: apparmor4.0.0 [48/82]: rename audit_data->label to + audit_data->subj_label + - SAUCE: apparmor4.0.0 [49/82]: pass cred through to audit info. + - SAUCE: apparmor4.0.0 [50/82]: Improve debug print infrastructure + - SAUCE: apparmor4.0.0 [51/82]: add the ability for profiles to have a + learning cache + - SAUCE: apparmor4.0.0 [52/82]: enable userspace upcall for mediation + - SAUCE: apparmor4.0.0 [53/82]: cache buffers on percpu list if there is lock + contention + - SAUCE: apparmor4.0.0 [54/82]: advertise availability of exended perms + - SAUCE: apparmor4.0.0 [56/82]: cleanup: provide separate audit messages for + file and policy checks + - SAUCE: apparmor4.0.0 [57/82]: prompt - lock down prompt interface + - SAUCE: apparmor4.0.0 [58/82]: prompt - ref count pdb + - SAUCE: apparmor4.0.0 [59/82]: prompt - allow controlling of caching of a + prompt response + - SAUCE: apparmor4.0.0 [60/82]: prompt - add refcount to audit_node in prep or + reuse and delete + - SAUCE: apparmor4.0.0 [61/82]: prompt - refactor to moving caching to + uresponse + - SAUCE: apparmor4.0.0 [62/82]: prompt - Improve debug statements + - SAUCE: apparmor4.0.0 [63/82]: prompt - fix caching + - SAUCE: apparmor4.0.0 [64/82]: prompt - rework build to use append fn, to + simplify adding strings + - SAUCE: apparmor4.0.0 [65/82]: prompt - refcount notifications + - SAUCE: apparmor4.0.0 [66/82]: prompt - add the ability to reply with a + profile name + - SAUCE: apparmor4.0.0 [67/82]: prompt - fix notification cache when updating + - SAUCE: apparmor4.0.0 [68/82]: prompt - add tailglob on name for cache + support + - SAUCE: apparmor4.0.0 [69/82]: prompt - allow profiles to set prompts as + interruptible + - SAUCE: apparmor4.0.0 [74/82]: advertise disconnected.path is available + - SAUCE: apparmor4.0.0 [75/82]: fix invalid reference on profile->disconnected + - SAUCE: apparmor4.0.0 [76/82]: add io_uring mediation + - SAUCE: apparmor4.0.0 [77/82]: apparmor: Fix regression in mount mediation + + * update apparmor and LSM stacking patch set (LP: #2028253) // [FFe] + apparmor-4.0.0-alpha2 for unprivileged user namespace restrictions in mantic + (LP: #2032602) + - SAUCE: apparmor4.0.0 [70/82]: prompt - add support for advanced filtering of + notifications + - SAUCE: apparmor4.0.0 [71/82]: userns - add the ability to reference a global + variable for a feature value + - SAUCE: apparmor4.0.0 [72/82]: userns - make it so special unconfined + profiles can mediate user namespaces + - SAUCE: apparmor4.0.0 [73/82]: userns - allow restricting unprivileged + change_profile + + * LSM stacking and AppArmor for 6.2: additional fixes (LP: #2017903) // update + apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor4.0.0 [55/82]: fix profile verification and enable it + + * udev fails to make prctl() syscall with apparmor=0 (as used by maas by + default) (LP: #2016908) // update apparmor and LSM stacking patch set + (LP: #2028253) + - SAUCE: apparmor4.0.0 [27/82]: Stacking v38: Fix prctl() syscall with + apparmor=0 + + * Miscellaneous Ubuntu changes + - [Config] SECURITY_APPARMOR_RESTRICT_USERNS=y + + -- Paolo Pisati Fri, 03 Nov 2023 11:59:12 +0100 + +linux-unstable (6.6.0-8.8) mantic; urgency=medium + + * mantic/linux-unstable: 6.6.0-8.8 -proposed tracker (LP: #2040243) + + * Miscellaneous Ubuntu changes + - abi: gc reference to phy-rtk-usb2/phy-rtk-usb3 + + -- Paolo Pisati Tue, 24 Oct 2023 10:55:34 +0200 + +linux-unstable (6.6.0-7.7) mantic; urgency=medium + + * mantic/linux-unstable: 6.6.0-7.7 -proposed tracker (LP: #2040147) + + * test_021_aslr_dapper_libs from ubuntu_qrt_kernel_security failed on K-5.19 / + J-OEM-6.1 / J-6.2 AMD64 (LP: #1983357) + - [Config]: set ARCH_MMAP_RND_{COMPAT_, }BITS to the maximum + + * Miscellaneous Ubuntu changes + - [Config] updateconfigs following v6.6-rc7 rebase + + -- Paolo Pisati Mon, 23 Oct 2023 11:51:14 +0200 + +linux-unstable (6.6.0-6.6) mantic; urgency=medium + + * mantic/linux-unstable: 6.6.0-6.6 -proposed tracker (LP: #2039780) + + * Miscellaneous Ubuntu changes + - rebase on v6.6-rc6 + - [Config] updateconfigs following v6.6-rc6 rebase + + [ Upstream Kernel Changes ] + + * Rebase to v6.6-rc6 + + -- Paolo Pisati Thu, 19 Oct 2023 12:09:16 +0200 + +linux-unstable (6.6.0-5.5) mantic; urgency=medium + + * mantic/linux-unstable: 6.6.0-5.5 -proposed tracker (LP: #2038899) + + * Miscellaneous Ubuntu changes + - rebase on v6.6-rc5 + - [Config] updateconfigs following v6.6-rc5 rebase + + [ Upstream Kernel Changes ] + + * Rebase to v6.6-rc5 + + -- Paolo Pisati Tue, 10 Oct 2023 11:18:41 +0200 + +linux-unstable (6.6.0-4.4) mantic; urgency=medium + + * mantic/linux-unstable: 6.6.0-4.4 -proposed tracker (LP: #2038423) + + * Miscellaneous Ubuntu changes + - rebase on v6.6-rc4 + + [ Upstream Kernel Changes ] + + * Rebase to v6.6-rc4 + + -- Paolo Pisati Wed, 04 Oct 2023 11:16:25 +0200 + +linux-unstable (6.6.0-3.3) mantic; urgency=medium + + * mantic/linux-unstable: 6.6.0-3.3 -proposed tracker (LP: #2037622) + + * Miscellaneous Ubuntu changes + - [Config] updateconfigs following v6.6-rc3 rebase + + * Miscellaneous upstream changes + - Revert "UBUNTU: SAUCE: enforce rust availability only on x86_64" + - arm64: rust: Enable Rust support for AArch64 + - arm64: rust: Enable PAC support for Rust. + - arm64: Restrict Rust support to little endian only. + + -- Paolo Pisati Thu, 28 Sep 2023 10:45:38 +0200 + +linux-unstable (6.6.0-2.2) mantic; urgency=medium + + * Miscellaneous upstream changes + - UBUBNTU: [Config] build all COMEDI drivers as modules + + -- Paolo Pisati Mon, 18 Sep 2023 14:42:56 +0200 + +linux-unstable (6.6.0-1.1) mantic; urgency=medium + + * Miscellaneous Ubuntu changes + - [Packaging] move linux to linux-unstable + - [Packaging] rebase on v6.6-rc1 + - [Config] updateconfigs following v6.6-rc1 rebase + - [packaging] skip ABI, modules and retpoline checks + - update dropped.txt + - [Config] SHIFT_FS FTBFS with Linux 6.6, disable it + - [Config] DELL_UART_BACKLIGHT FTBFS with Linux 6.6, disable it + - [Packaging] debian/dkms-versions: temporarily disable dkms + - [Packaging] temporarily disable signing for s390x + + [ Upstream Kernel Changes ] + + * Rebase to v6.6-rc1 + + -- Paolo Pisati Fri, 15 Sep 2023 14:42:18 +0200 + +linux-unstable (6.6.0-0.0) mantic; urgency=medium + + * Empty entry + + -- Paolo Pisati Thu, 14 Sep 2023 15:03:19 +0200 + +linux (6.5.0-5.5) mantic; urgency=medium + + * mantic/linux: 6.5.0-5.5 -proposed tracker (LP: #2034546) + + * Packaging resync (LP: #1786013) + - [Packaging] update helper scripts + - debian/dkms-versions -- update from kernel-versions (main/d2023.08.23) + + +linux (6.5.0-4.4) mantic; urgency=medium + + * mantic/linux: 6.5.0-4.4 -proposed tracker (LP: #2034042) + + * Packaging resync (LP: #1786013) + - debian/dkms-versions -- update from kernel-versions (main/d2023.08.23) + + -- Andrea Righi Mon, 04 Sep 2023 16:55:44 +0200 + +linux (6.5.0-3.3) mantic; urgency=medium + + * mantic/linux: 6.5.0-3.3 -proposed tracker (LP: #2033904) + + * Packaging resync (LP: #1786013) + - debian/dkms-versions -- update from kernel-versions (main/d2023.08.23) + + * [23.10] Please test secure-boot and lockdown on the early 6.5 kernel (s390x) + (LP: #2026833) + - [Packaging] re-enable signing for s390x + + * Miscellaneous upstream changes + - module/decompress: use vmalloc() for zstd decompression workspace + + -- Andrea Righi Fri, 01 Sep 2023 16:15:33 +0200 + +linux (6.5.0-2.2) mantic; urgency=medium + + * mantic/linux: 6.5.0-2.2 -proposed tracker (LP: #2033240) + + * Soundwire support for Dell SKU0C87 devices (LP: #2029281) + - SAUCE: ASoC: Intel: soc-acpi: add support for Dell SKU0C87 devices + + * Fix numerous AER related issues (LP: #2033025) + - SAUCE: PCI/AER: Disable AER service during suspend, again + - SAUCE: PCI/DPC: Disable DPC service during suspend, again + + * Support Realtek RTL8852CE WiFi 6E/BT Combo (LP: #2025672) + - wifi: rtw89: debug: Fix error handling in rtw89_debug_priv_btc_manual_set() + - Bluetooth: btrtl: Load FW v2 otherwise FW v1 for RTL8852C + + [ Upstream Kernel Changes ] + + * Rebase to v6.5 + + -- Andrea Righi Mon, 28 Aug 2023 08:53:19 +0200 + +linux (6.5.0-1.1) mantic; urgency=medium + + * mantic/linux: 6.5.0-1.1 -proposed tracker (LP: #2032750) + + * Packaging resync (LP: #1786013) + - [Packaging] resync update-dkms-versions helper + - [Packaging] update variants + - debian/dkms-versions -- update from kernel-versions (main/d2023.07.26) + + * ceph: support idmapped mounts (LP: #2032959) + - SAUCE: libceph: add spinlock around osd->o_requests + - SAUCE: libceph: define struct ceph_sparse_extent and add some helpers + - SAUCE: libceph: new sparse_read op, support sparse reads on msgr2 crc + codepath + - SAUCE: libceph: support sparse reads on msgr2 secure codepath + - SAUCE: libceph: add sparse read support to msgr1 + - SAUCE: libceph: add sparse read support to OSD client + - SAUCE: ceph: add new mount option to enable sparse reads + - SAUCE: ceph: preallocate inode for ops that may create one + - SAUCE: ceph: make ceph_msdc_build_path use ref-walk + - SAUCE: libceph: add new iov_iter-based ceph_msg_data_type and + ceph_osd_data_type + - SAUCE: ceph: use osd_req_op_extent_osd_iter for netfs reads + - SAUCE: ceph: fscrypt_auth handling for ceph + - SAUCE: ceph: implement -o test_dummy_encryption mount option + - SAUCE: ceph: add fscrypt ioctls and ceph.fscrypt.auth vxattr + - SAUCE: ceph: make ioctl cmds more readable in debug log + - SAUCE: ceph: add base64 endcoding routines for encrypted names + - SAUCE: ceph: encode encrypted name in ceph_mdsc_build_path and dentry + release + - SAUCE: ceph: send alternate_name in MClientRequest + - SAUCE: ceph: decode alternate_name in lease info + - SAUCE: ceph: set DCACHE_NOKEY_NAME flag in ceph_lookup/atomic_open() + - SAUCE: ceph: make d_revalidate call fscrypt revalidator for encrypted + dentries + - SAUCE: ceph: add helpers for converting names for userland presentation + - SAUCE: ceph: make ceph_fill_trace and ceph_get_name decrypt names + - SAUCE: ceph: pass the request to parse_reply_info_readdir() + - SAUCE: ceph: add support to readdir for encrypted names + - SAUCE: ceph: create symlinks with encrypted and base64-encoded targets + - SAUCE: ceph: add some fscrypt guardrails + - SAUCE: ceph: allow encrypting a directory while not having Ax caps + - SAUCE: ceph: mark directory as non-complete after loading key + - SAUCE: ceph: size handling in MClientRequest, cap updates and inode traces + - SAUCE: ceph: handle fscrypt fields in cap messages from MDS + - SAUCE: ceph: add infrastructure for file encryption and decryption + - SAUCE: libceph: add CEPH_OSD_OP_ASSERT_VER support + - SAUCE: libceph: allow ceph_osdc_new_request to accept a multi-op read + - SAUCE: ceph: add object version support for sync read + - SAUCE: ceph: add truncate size handling support for fscrypt + - SAUCE: ceph: don't use special DIO path for encrypted inodes + - SAUCE: ceph: align data in pages in ceph_sync_write + - SAUCE: ceph: add read/modify/write to ceph_sync_write + - SAUCE: ceph: add encryption support to writepage and writepages + - SAUCE: ceph: plumb in decryption during reads + - SAUCE: ceph: invalidate pages when doing direct/sync writes + - SAUCE: ceph: add support for encrypted snapshot names + - SAUCE: ceph: prevent snapshot creation in encrypted locked directories + - SAUCE: ceph: update documentation regarding snapshot naming limitations + - SAUCE: ceph: drop messages from MDS when unmounting + - SAUCE: ceph: wait for OSD requests' callbacks to finish when unmounting + - SAUCE: ceph: fix updating i_truncate_pagecache_size for fscrypt + - SAUCE: ceph: switch ceph_lookup/atomic_open() to use new fscrypt helper + - SAUCE: libceph: do not include crypto/algapi.h + - SAUCE: rbd: bump RBD_MAX_PARENT_CHAIN_LEN to 128 + - SAUCE: ceph: dump info about cap flushes when we're waiting too long for + them + - SAUCE: mm: BUG if filemap_alloc_folio gives us a folio with a non-NULL + ->private + - SAUCE: ceph: make sure all the files successfully put before unmounting + - SAUCE: ceph: BUG if MDS changed truncate_seq with client caps still + outstanding + - SAUCE: ceph: add the *_client debug macros support + - SAUCE: ceph: pass the mdsc to several helpers + - SAUCE: ceph: rename _to_client() to _to_fs_client() + - SAUCE: ceph: move mdsmap.h to fs/ceph/ + - SAUCE: ceph: add ceph_inode_to_client() helper support + - SAUCE: ceph: print the client global_id in all the debug logs + - SAUCE: ceph: make the members in struct ceph_mds_request_args_ext an union + - SAUCE: ceph: make num_fwd and num_retry to __u32 + - SAUCE: fs: export mnt_idmap_get/mnt_idmap_put + - SAUCE: ceph: stash idmapping in mdsc request + - SAUCE: ceph: handle idmapped mounts in create_request_message() + - SAUCE: ceph: add enable_unsafe_idmap module parameter + - SAUCE: ceph: pass an idmapping to mknod/symlink/mkdir + - SAUCE: ceph: allow idmapped getattr inode op + - SAUCE: ceph: allow idmapped permission inode op + - SAUCE: ceph: pass idmap to __ceph_setattr + - SAUCE: ceph: allow idmapped setattr inode op + - SAUCE: ceph/acl: allow idmapped set_acl inode op + - SAUCE: ceph/file: allow idmapped atomic_open inode op + - SAUCE: ceph: allow idmapped mounts + + * Got soft lockup CPU if dell_uart_backlight is probed (LP: #2032174) + - SAUCE: platform/x86: dell-uart-backlight: replace chars_in_buffer() with + flush_chars() + + * Fix ACPI TAD on some Intel based systems (LP: #2032767) + - ACPI: TAD: Install SystemCMOS address space handler for ACPI000E + + * Fix unreliable ethernet cable detection on I219 NIC (LP: #2028122) + - e1000e: Use PME poll to circumvent unreliable ACPI wake + + * Fix panel brightness issues on HP laptops (LP: #2032704) + - ACPI: video: Put ACPI video and its child devices into D0 on boot + + * FATAL:credentials.cc(127)] Check failed: . : Permission denied (13) + (LP: #2017980) + - [Config] disable CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + + * Support initrdless boot on default qemu virt models and openstack + (LP: #2030745) + - [Config] set VIRTIO_BLK=y for default qemu/openstack boot + + * Miscellaneous Ubuntu changes + - [Packaging] rust: use Rust 1.68.2 + - [Packaging] depend on clang/libclang-15 for Rust + - [Config] update toolchain versions in annotations + - [Config] update annotations after rebase to v6.5-rc6 + - [Config] update toolchain version in annotations + - [Packaging] temporarily disable Rust support + - [Packaging] temporarily disable signing for ppc64el + - [Packaging] temporarily disable signing for s390x + + -- Andrea Righi Thu, 24 Aug 2023 17:47:10 +0200 + +linux (6.5.0-0.0) mantic; urgency=medium + + * Empty entry + + -- Andrea Righi Wed, 23 Aug 2023 08:14:48 +0200 + +linux-unstable (6.5.0-4.4) mantic; urgency=medium + + * mantic/linux-unstable: 6.5.0-4.4 -proposed tracker (LP: #2029086) + + * Miscellaneous Ubuntu changes + - [Packaging] Add .NOTPARALLEL + - [Packaging] Remove meaningless $(header_arch) + - [Packaging] Fix File exists error in install-arch-headers + - [Packaging] clean debian/linux-* directories + - [Packaging] remove hmake + - [Packaging] install headers to debian/linux-libc-dev directly + - [Config] define CONFIG options for arm64 instead of arm64-generic + - [Config] update annotations after rebase to v6.5-rc4 + - [Packaging] temporarily disable Rust support + + [ Upstream Kernel Changes ] + + * Rebase to v6.5-rc4 + + -- Andrea Righi Mon, 31 Jul 2023 08:41:59 +0200 + +linux-unstable (6.5.0-3.3) mantic; urgency=medium + + * mantic/linux-unstable: 6.5.0-3.3 -proposed tracker (LP: #2028779) + + * enable Rust support in the kernel (LP: #2007654) + - SAUCE: rust: support rustc-1.69.0 + - [Packaging] depend on rustc-1.69.0 + + * Packaging resync (LP: #1786013) + - [Packaging] resync update-dkms-versions helper + - [Packaging] resync getabis + + * Fix UBSAN in Intel EDAC driver (LP: #2028746) + - EDAC/i10nm: Skip the absent memory controllers + + * Ship kernel modules Zstd compressed (LP: #2028568) + - SAUCE: Support but do not require compressed modules + - [Config] Enable support for ZSTD compressed modules + - [Packaging] ZSTD compress modules + + * update apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor3.2.0 [02/60]: rename SK_CTX() to aa_sock and make it an + inline fn + - SAUCE: apparmor3.2.0 [05/60]: Add sysctls for additional controls of unpriv + userns restrictions + - SAUCE: apparmor3.2.0 [08/60]: Stacking v38: LSM: Identify modules by more + than name + - SAUCE: apparmor3.2.0 [09/60]: Stacking v38: LSM: Add an LSM identifier for + external use + - SAUCE: apparmor3.2.0 [10/60]: Stacking v38: LSM: Identify the process + attributes for each module + - SAUCE: apparmor3.2.0 [11/60]: Stacking v38: LSM: Maintain a table of LSM + attribute data + - SAUCE: apparmor3.2.0 [12/60]: Stacking v38: proc: Use lsmids instead of lsm + names for attrs + - SAUCE: apparmor3.2.0 [13/60]: Stacking v38: integrity: disassociate + ima_filter_rule from security_audit_rule + - SAUCE: apparmor3.2.0 [14/60]: Stacking v38: LSM: Infrastructure management + of the sock security + - SAUCE: apparmor3.2.0 [15/60]: Stacking v38: LSM: Add the lsmblob data + structure. + - SAUCE: apparmor3.2.0 [16/60]: Stacking v38: LSM: provide lsm name and id + slot mappings + - SAUCE: apparmor3.2.0 [17/60]: Stacking v38: IMA: avoid label collisions with + stacked LSMs + - SAUCE: apparmor3.2.0 [18/60]: Stacking v38: LSM: Use lsmblob in + security_audit_rule_match + - SAUCE: apparmor3.2.0 [19/60]: Stacking v38: LSM: Use lsmblob in + security_kernel_act_as + - SAUCE: apparmor3.2.0 [20/60]: Stacking v38: LSM: Use lsmblob in + security_secctx_to_secid + - SAUCE: apparmor3.2.0 [21/60]: Stacking v38: LSM: Use lsmblob in + security_secid_to_secctx + - SAUCE: apparmor3.2.0 [22/60]: Stacking v38: LSM: Use lsmblob in + security_ipc_getsecid + - SAUCE: apparmor3.2.0 [23/60]: Stacking v38: LSM: Use lsmblob in + security_current_getsecid + - SAUCE: apparmor3.2.0 [24/60]: Stacking v38: LSM: Use lsmblob in + security_inode_getsecid + - SAUCE: apparmor3.2.0 [25/60]: Stacking v38: LSM: Use lsmblob in + security_cred_getsecid + - SAUCE: apparmor3.2.0 [26/60]: Stacking v38: LSM: Specify which LSM to + display + - SAUCE: apparmor3.2.0 [28/60]: Stacking v38: LSM: Ensure the correct LSM + context releaser + - SAUCE: apparmor3.2.0 [29/60]: Stacking v38: LSM: Use lsmcontext in + security_secid_to_secctx + - SAUCE: apparmor3.2.0 [30/60]: Stacking v38: LSM: Use lsmcontext in + security_inode_getsecctx + - SAUCE: apparmor3.2.0 [31/60]: Stacking v38: Use lsmcontext in + security_dentry_init_security + - SAUCE: apparmor3.2.0 [32/60]: Stacking v38: LSM: security_secid_to_secctx in + netlink netfilter + - SAUCE: apparmor3.2.0 [33/60]: Stacking v38: NET: Store LSM netlabel data in + a lsmblob + - SAUCE: apparmor3.2.0 [34/60]: Stacking v38: binder: Pass LSM identifier for + confirmation + - SAUCE: apparmor3.2.0 [35/60]: Stacking v38: LSM: security_secid_to_secctx + module selection + - SAUCE: apparmor3.2.0 [36/60]: Stacking v38: Audit: Keep multiple LSM data in + audit_names + - SAUCE: apparmor3.2.0 [37/60]: Stacking v38: Audit: Create audit_stamp + structure + - SAUCE: apparmor3.2.0 [38/60]: Stacking v38: LSM: Add a function to report + multiple LSMs + - SAUCE: apparmor3.2.0 [39/60]: Stacking v38: Audit: Allow multiple records in + an audit_buffer + - SAUCE: apparmor3.2.0 [40/60]: Stacking v38: Audit: Add record for multiple + task security contexts + - SAUCE: apparmor3.2.0 [41/60]: Stacking v38: audit: multiple subject lsm + values for netlabel + - SAUCE: apparmor3.2.0 [42/60]: Stacking v38: Audit: Add record for multiple + object contexts + - SAUCE: apparmor3.2.0 [43/60]: Stacking v38: netlabel: Use a struct lsmblob + in audit data + - SAUCE: apparmor3.2.0 [44/60]: Stacking v38: LSM: Removed scaffolding + function lsmcontext_init + - SAUCE: apparmor3.2.0 [45/60]: Stacking v38: AppArmor: Remove the exclusive + flag + - SAUCE: apparmor3.2.0 [46/60]: combine common_audit_data and + apparmor_audit_data + - SAUCE: apparmor3.2.0 [47/60]: setup slab cache for audit data + - SAUCE: apparmor3.2.0 [48/60]: rename audit_data->label to + audit_data->subj_label + - SAUCE: apparmor3.2.0 [49/60]: pass cred through to audit info. + - SAUCE: apparmor3.2.0 [50/60]: Improve debug print infrastructure + - SAUCE: apparmor3.2.0 [51/60]: add the ability for profiles to have a + learning cache + - SAUCE: apparmor3.2.0 [52/60]: enable userspace upcall for mediation + - SAUCE: apparmor3.2.0 [53/60]: cache buffers on percpu list if there is lock + contention + - SAUCE: apparmor3.2.0 [55/60]: advertise availability of exended perms + - SAUCE: apparmor3.2.0 [60/60]: [Config] enable + CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + + * LSM stacking and AppArmor for 6.2: additional fixes (LP: #2017903) // update + apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor3.2.0 [57/60]: fix profile verification and enable it + + * udev fails to make prctl() syscall with apparmor=0 (as used by maas by + default) (LP: #2016908) // update apparmor and LSM stacking patch set + (LP: #2028253) + - SAUCE: apparmor3.2.0 [27/60]: Stacking v38: Fix prctl() syscall with + apparmor=0 + + * kinetic: apply new apparmor and LSM stacking patch set (LP: #1989983) // + update apparmor and LSM stacking patch set (LP: #2028253) + - SAUCE: apparmor3.2.0 [01/60]: add/use fns to print hash string hex value + - SAUCE: apparmor3.2.0 [03/60]: patch to provide compatibility with v2.x net + rules + - SAUCE: apparmor3.2.0 [04/60]: add user namespace creation mediation + - SAUCE: apparmor3.2.0 [06/60]: af_unix mediation + - SAUCE: apparmor3.2.0 [07/60]: Add fine grained mediation of posix mqueues + + * Miscellaneous Ubuntu changes + - [Packaging] Use consistent llvm/clang for rust + + [ Upstream Kernel Changes ] + + * Rebase to v6.5-rc3 + + -- Andrea Righi Fri, 28 Jul 2023 07:44:20 +0200 + +linux-unstable (6.5.0-2.2) mantic; urgency=medium + + * mantic/linux-unstable: 6.5.0-2.2 -proposed tracker (LP: #2027953) + + * Remove non-LPAE kernel flavor (LP: #2025265) + - [Packaging] Rename armhf generic-lpae flavor to generic + + * Please enable Renesas RZ platform serial installer (LP: #2022361) + - [Config] enable hihope RZ/G2M serial console + + * Miscellaneous Ubuntu changes + - [Packaging] snap: Remove old configs handling + - [Packaging] checks/final-checks: Remove old configs handling + - [Packaging] checks/final-checks: check existance of Makefile first + - [Packaging] checks/final-checks: Fix shellcheck issues + - [Packaging] add libstdc++-dev to the build dependencies + - [Config] update annotations after rebase to v6.5-rc2 + + * Miscellaneous upstream changes + - kbuild: rust: avoid creating temporary files + - rust: fix bindgen build error with UBSAN_BOUNDS_STRICT + + [ Upstream Kernel Changes ] + + * Rebase to v6.5-rc2 + + -- Andrea Righi Tue, 18 Jul 2023 10:14:14 +0200 + +linux-unstable (6.5.0-1.1) mantic; urgency=medium + + * mantic/linux-unstable: 6.5.0-1.1 -proposed tracker (LP: #2026689) + + * CVE-2023-31248 + - netfilter: nf_tables: do not ignore genmask when looking up chain by id + + * CVE-2023-35001 + - netfilter: nf_tables: prevent OOB access in nft_byteorder_eval + + * HDMI output with More than one child device for port B in VBT error + (LP: #2025195) + - SAUCE: drm/i915/quirks: Add multiple VBT quirk for HP ZBook Power G10 + + * CVE-2023-2640 // CVE-2023-32629 + - SAUCE: overlayfs: default to userxattr when mounted from non initial user + namespace + + * Packaging resync (LP: #1786013) + - [Packaging] resync update-dkms-versions helper + + * enable Rust support in the kernel (LP: #2007654) + - SAUCE: btf, scripts: rust: drop is_rust_module.sh + - [Packaging] add rust dependencies + + * CVE-2023-2612 + - SAUCE: shiftfs: prevent lock unbalance in shiftfs_create_object() + + * Miscellaneous Ubuntu changes + - SAUCE: shiftfs: support linux 6.5 + - [Config] update annotations after rebase to v6.5-rc1 + - [Config] temporarily disable Rust + + [ Upstream Kernel Changes ] + + * Rebase to v6.5-rc1 + + -- Andrea Righi Mon, 10 Jul 2023 09:15:26 +0200 + +linux-unstable (6.5.0-0.0) mantic; urgency=medium + + * Empty entry + + -- Andrea Righi Wed, 05 Jul 2023 12:48:39 +0200 + +linux-unstable (6.4.0-8.8) mantic; urgency=medium + + * mantic/linux-unstable: 6.4.0-8.8 -proposed tracker (LP: #2025018) + + * Miscellaneous Ubuntu changes + - [Config] update toolchain version (gcc) in annotations + + [ Upstream Kernel Changes ] + + * Rebase to v6.4 + + -- Andrea Righi Mon, 26 Jun 2023 09:14:02 +0200 + +linux-unstable (6.4.0-7.7) mantic; urgency=medium + + * mantic/linux-unstable: 6.4.0-7.7 -proposed tracker (LP: #2024338) + + [ Upstream Kernel Changes ] + + * Rebase to v6.4-rc7 + + -- Andrea Righi Mon, 19 Jun 2023 08:51:27 +0200 + +linux-unstable (6.4.0-6.6) mantic; urgency=medium + + * mantic/linux-unstable: 6.4.0-6.6 -proposed tracker (LP: #2023966) + + * Packaging resync (LP: #1786013) + - [Packaging] update annotations scripts + + * enable multi-gen LRU by default (LP: #2023629) + - [Config] enable multi-gen LRU by default + + * Fix Monitor lost after replug WD19TBS to SUT port with VGA/DVI to type-C + dongle (LP: #2021949) + - thunderbolt: Do not touch CL state configuration during discovery + - thunderbolt: Increase DisplayPort Connection Manager handshake timeout + + * Neuter signing tarballs (LP: #2012776) + - [Packaging] remove the signing tarball support + + * Enable Tracing Configs for OSNOISE and TIMERLAT (LP: #2018591) + - [Config] Enable OSNOISE_TRACER and TIMERLAT_TRACER configs + + * Miscellaneous Ubuntu changes + - [Config] Add CONFIG_AS_HAS_NON_CONST_LEB128 on riscv64 + - [Packaging] introduce do_lib_rust and enable it only on generic amd64 + - [Config] update annotations after rebase to v6.4-rc6 + + [ Upstream Kernel Changes ] + + * Rebase to v6.4-rc6 + + -- Andrea Righi Thu, 15 Jun 2023 20:11:07 +0200 + +linux-unstable (6.4.0-5.5) mantic; urgency=medium + + * mantic/linux-unstable: 6.4.0-5.5 -proposed tracker (LP: #2022886) + + * Miscellaneous Ubuntu changes + - [Packaging] update getabis to support linux-unstable + - UBUNTU [Config]: disable hibernation on riscv64 + + [ Upstream Kernel Changes ] + + * Rebase to v6.4-rc5 + + -- Andrea Righi Tue, 06 Jun 2023 08:18:01 +0200 + +linux-unstable (6.4.0-4.4) mantic; urgency=medium + + * mantic/linux-unstable: 6.4.0-4.4 -proposed tracker (LP: #2021597) + + * Miscellaneous Ubuntu changes + - [Config] udpate annotations after rebase to v6.4-rc4 + + -- Andrea Righi Tue, 30 May 2023 11:55:41 +0200 + +linux-unstable (6.4.0-3.3) mantic; urgency=medium + + * mantic/linux-unstable: 6.4.0-3.3 -proposed tracker (LP: #2021497) + + * Packaging resync (LP: #1786013) + - [Packaging] resync git-ubuntu-log + - [Packaging] resync getabis + + * support python < 3.9 with annotations (LP: #2020531) + - [Packaging] kconfig/annotations.py: support older way of merging dicts + + * generate linux-lib-rust only on amd64 (LP: #2020356) + - [Packaging] generate linux-lib-rust only on amd64 + + * Miscellaneous Ubuntu changes + - [Packaging] annotations: never drop configs that have notes different than + the parent + - [Config] drop CONFIG_SMBFS_COMMON from annotations + - [Packaging] perf: build without libtraceevent + + [ Upstream Kernel Changes ] + + * Rebase to v6.4-rc4 + + -- Andrea Righi Tue, 30 May 2023 08:38:10 +0200 + +linux-unstable (6.4.0-2.2) mantic; urgency=medium + + * mantic/linux-unstable: 6.4.0-2.2 -proposed tracker (LP: #2020330) + + * Computer with Intel Atom CPU will not boot with Kernel 6.2.0-20 + (LP: #2017444) + - [Config]: Disable CONFIG_INTEL_ATOMISP + + * Fix NVME storage with RAID ON disappeared under Dell factory WINPE + environment (LP: #2011768) + - SAUCE: PCI: vmd: Reset VMD config register between soft reboots + + * Miscellaneous Ubuntu changes + - [Packaging] Drop support of old config handling + - [Config] update annotations after rebase to v6.4-rc3 + + [ Upstream Kernel Changes ] + + * Rebase to v6.4-rc3 + + -- Andrea Righi Mon, 22 May 2023 11:22:14 +0200 + +linux-unstable (6.4.0-1.1) mantic; urgency=medium + + * mantic/linux-unstable: 6.4.0-1.1 -proposed tracker (LP: #2019965) + + * Packaging resync (LP: #1786013) + - [Packaging] update variants + - [Packaging] update helper scripts + + * Kernel 6.1 bumped the disk consumption on default images by 15% + (LP: #2015867) + - [Packaging] introduce a separate linux-lib-rust package + + * Miscellaneous Ubuntu changes + - [Config] enable CONFIG_BLK_DEV_UBLK on amd64 + - [Packaging] annotations: use python3 in the shebang + - SAUCE: blk-throttle: Fix io statistics for cgroup v1 + - [Packaging] move to v6.4 and rename to linux-unstable + - [Config] update annotations after rebase to v6.4-rc1 + - [Packaging] temporarily disable perf + - [Packaging] temporarily disable bpftool + - [Config] ppc64el: reduce CONFIG_ARCH_FORCE_MAX_ORDER from 9 to 8 + - SAUCE: perf: explicitly disable libtraceevent + + [ Upstream Kernel Changes ] + + * Rebase to v6.4-rc2 + + -- Andrea Righi Thu, 18 May 2023 07:34:09 +0200 + +linux-unstable (6.4.0-0.0) mantic; urgency=medium + + * Empty entry + + -- Andrea Righi Wed, 17 May 2023 15:29:25 +0200 + +linux-unstable (6.3.0-2.2) lunar; urgency=medium + + * lunar/linux-unstable: 6.3.0-2.2 -proposed tracker (LP: #2017788) + + * Miscellaneous Ubuntu changes + - [Packaging] move python3-dev to build-depends + + -- Andrea Righi Wed, 26 Apr 2023 21:52:12 +0200 + +linux-unstable (6.3.0-1.1) lunar; urgency=medium + + * lunar/linux-unstable: 6.3.0-1.1 -proposed tracker (LP: #2017776) + + * RFC: virtio and virtio-scsi should be built in (LP: #1685291) + - [Config] Mark CONFIG_SCSI_VIRTIO built-in + + * Debian autoreconstruct Fix restoration of execute permissions (LP: #2015498) + - [Debian] autoreconstruct - fix restoration of execute permissions + + * [SRU][Jammy] CONFIG_PCI_MESON is not enabled (LP: #2007745) + - [Config] arm64: Enable PCI_MESON module + + * vmd may fail to create sysfs entry while `pci_rescan_bus()` called in some + other drivers like wwan (LP: #2011389) + - SAUCE: PCI: vmd: guard device addition and removal + + * Lunar update: v6.2.9 upstream stable release (LP: #2016877) + - [Config] ppc64: updateconfigs following v6.2.9 stable updates + + * Lunar update: v6.2.8 upstream stable release (LP: #2016876) + - [Config] ppc64: updateconfigs following v6.2.8 stable updates + + * Miscellaneous Ubuntu changes + - [Packaging] Move final-checks script to debian/scripts/checks + - [Packaging] checks/final-checks: Honor 'do_skip_checks' + - [Packaging] Drop wireguard DKMS + - [Packaging] Remove update-version-dkms + - [Packaging] debian/rules: Add DKMS info to 'printenv' output + - [Packaging] ignore KBUILD_VERBOSE in arch-has-odm-enabled.sh + - SAUCE: shiftfs: support linux 6.3 + - [Packaging] move to v6.3 and rename to linux-unstable + - [Config] latency-related optimizations + - [Config] update annotations after rebase to v6.3 + - [Packaging] temporarily disable dkms + + [ Upstream Kernel Changes ] + + * Rebase to v6.3 + + -- Andrea Righi Wed, 26 Apr 2023 14:53:52 +0200 + +linux-unstable (6.3.0-0.0) lunar; urgency=medium + + * Empty entry + + -- Andrea Righi Tue, 25 Apr 2023 10:24:12 +0200 + +linux (6.2.0-21.21) lunar; urgency=medium + + * lunar/linux: 6.2.0-21.21 -proposed tracker (LP: #2016249) + + * efivarfs:efivarfs.sh in ubuntu_kernel_selftests crash L-6.2 ARM64 node + dazzle (rcu_preempt detected stalls) (LP: #2015741) + - efi/libstub: smbios: Use length member instead of record struct size + - arm64: efi: Use SMBIOS processor version to key off Ampere quirk + - efi/libstub: smbios: Drop unused 'recsize' parameter + + * Miscellaneous Ubuntu changes + - SAUCE: selftests/bpf: ignore pointer types check with clang + - SAUCE: selftests/bpf: avoid conflicting data types in profiler.inc.h + - [Packaging] get rid of unnecessary artifacts in linux-headers + + * Miscellaneous upstream changes + - Revert "UBUNTU: SAUCE: Revert "efi: random: refresh non-volatile random seed + when RNG is initialized"" + - Revert "UBUNTU: SAUCE: Revert "efi: random: fix NULL-deref when refreshing + seed"" + + -- Andrea Righi Fri, 14 Apr 2023 12:11:49 +0200 + +linux (6.2.0-20.20) lunar; urgency=medium + + * lunar/linux: 6.2.0-20.20 -proposed tracker (LP: #2015429) + + * Packaging resync (LP: #1786013) + - debian/dkms-versions -- update from kernel-versions (main/master) + + * FTBFS with different dkms or when makeflags are set (LP: #2015361) + - [Packaging] FTBFS with different dkms or when makeflags are set + + * expoline.o is packaged unconditionally for s390x (LP: #2013209) + - [Packaging] Copy expoline.o only when produced by the build + + * net:l2tp.sh failure with lunar:linux 6.2 (LP: #2013014) + - SAUCE: l2tp: generate correct module alias strings + + * Miscellaneous Ubuntu changes + - [Packaging] annotations: prevent duplicate include lines + + -- Andrea Righi Thu, 06 Apr 2023 08:33:14 +0200 + +linux (6.2.0-19.19) lunar; urgency=medium + + * lunar/linux: 6.2.0-19.19 -proposed tracker (LP: #2012488) + + * Neuter signing tarballs (LP: #2012776) + - [Packaging] neuter the signing tarball + + * LSM stacking and AppArmor refresh for 6.2 kernel (LP: #2012136) + - Revert "UBUNTU: [Config] define CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS" + - Revert "UBUNTU: SAUCE: apparmor: add user namespace creation mediation" + - Revert "UBUNTU: SAUCE: apparmor: Add fine grained mediation of posix + mqueues" + - Revert "UBUNTU: SAUCE: Revert "apparmor: make __aa_path_perm() static"" + - Revert "UBUNTU: SAUCE: LSM: Specify which LSM to display (using struct cred + as input)" + - Revert "UBUNTU: SAUCE: apparmor: Fix build error, make sk parameter const" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in smk_netlbl_mls()" + - Revert "UBUNTU: SAUCE: LSM: change ima_read_file() to use lsmblob" + - Revert "UBUNTU: SAUCE: apparmor: rename kzfree() to kfree_sensitive()" + - Revert "UBUNTU: SAUCE: AppArmor: Remove the exclusive flag" + - Revert "UBUNTU: SAUCE: LSM: Add /proc attr entry for full LSM context" + - Revert "UBUNTU: SAUCE: Audit: Fix incorrect static inline function + declration." + - Revert "UBUNTU: SAUCE: Audit: Fix for missing NULL check" + - Revert "UBUNTU: SAUCE: Audit: Add a new record for multiple object LSM + attributes" + - Revert "UBUNTU: SAUCE: Audit: Add new record for multiple process LSM + attributes" + - Revert "UBUNTU: SAUCE: NET: Store LSM netlabel data in a lsmblob" + - Revert "UBUNTU: SAUCE: LSM: security_secid_to_secctx in netlink netfilter" + - Revert "UBUNTU: SAUCE: LSM: Use lsmcontext in security_inode_getsecctx" + - Revert "UBUNTU: SAUCE: LSM: Use lsmcontext in security_secid_to_secctx" + - Revert "UBUNTU: SAUCE: LSM: Ensure the correct LSM context releaser" + - Revert "UBUNTU: SAUCE: LSM: Specify which LSM to display" + - Revert "UBUNTU: SAUCE: IMA: Change internal interfaces to use lsmblobs" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in security_cred_getsecid" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in security_inode_getsecid" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in security_task_getsecid" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in security_ipc_getsecid" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in security_secid_to_secctx" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in security_secctx_to_secid" + - Revert "UBUNTU: SAUCE: net: Prepare UDS for security module stacking" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in security_kernel_act_as" + - Revert "UBUNTU: SAUCE: LSM: Use lsmblob in security_audit_rule_match" + - Revert "UBUNTU: SAUCE: LSM: Create and manage the lsmblob data structure." + - Revert "UBUNTU: SAUCE: LSM: Infrastructure management of the sock security" + - Revert "UBUNTU: SAUCE: apparmor: LSM stacking: switch from SK_CTX() to + aa_sock()" + - Revert "UBUNTU: SAUCE: apparmor: rename aa_sock() to aa_unix_sk()" + - Revert "UBUNTU: SAUCE: apparmor: disable showing the mode as part of a secid + to secctx" + - Revert "UBUNTU: SAUCE: apparmor: fix use after free in sk_peer_label" + - Revert "UBUNTU: SAUCE: apparmor: af_unix mediation" + - Revert "UBUNTU: SAUCE: apparmor: patch to provide compatibility with v2.x + net rules" + - Revert "UBUNTU: SAUCE: apparmor: add/use fns to print hash string hex value" + - SAUCE: apparmor: rename SK_CTX() to aa_sock and make it an inline fn + - SAUCE: apparmor: Add sysctls for additional controls of unpriv userns + restrictions + - SAUCE: Stacking v38: LSM: Identify modules by more than name + - SAUCE: Stacking v38: LSM: Add an LSM identifier for external use + - SAUCE: Stacking v38: LSM: Identify the process attributes for each module + - SAUCE: Stacking v38: LSM: Maintain a table of LSM attribute data + - SAUCE: Stacking v38: proc: Use lsmids instead of lsm names for attrs + - SAUCE: Stacking v38: integrity: disassociate ima_filter_rule from + security_audit_rule + - SAUCE: Stacking v38: LSM: Infrastructure management of the sock security + - SAUCE: Stacking v38: LSM: Add the lsmblob data structure. + - SAUCE: Stacking v38: LSM: provide lsm name and id slot mappings + - SAUCE: Stacking v38: IMA: avoid label collisions with stacked LSMs + - SAUCE: Stacking v38: LSM: Use lsmblob in security_audit_rule_match + - SAUCE: Stacking v38: LSM: Use lsmblob in security_kernel_act_as + - SAUCE: Stacking v38: LSM: Use lsmblob in security_secctx_to_secid + - SAUCE: Stacking v38: LSM: Use lsmblob in security_secid_to_secctx + - SAUCE: Stacking v38: LSM: Use lsmblob in security_ipc_getsecid + - SAUCE: Stacking v38: LSM: Use lsmblob in security_current_getsecid + - SAUCE: Stacking v38: LSM: Use lsmblob in security_inode_getsecid + - SAUCE: Stacking v38: LSM: Use lsmblob in security_cred_getsecid + - SAUCE: Stacking v38: LSM: Specify which LSM to display + - SAUCE: Stacking v38: LSM: Ensure the correct LSM context releaser + - SAUCE: Stacking v38: LSM: Use lsmcontext in security_secid_to_secctx + - SAUCE: Stacking v38: LSM: Use lsmcontext in security_inode_getsecctx + - SAUCE: Stacking v38: Use lsmcontext in security_dentry_init_security + - SAUCE: Stacking v38: LSM: security_secid_to_secctx in netlink netfilter + - SAUCE: Stacking v38: NET: Store LSM netlabel data in a lsmblob + - SAUCE: Stacking v38: binder: Pass LSM identifier for confirmation + - SAUCE: Stacking v38: LSM: security_secid_to_secctx module selection + - SAUCE: Stacking v38: Audit: Keep multiple LSM data in audit_names + - SAUCE: Stacking v38: Audit: Create audit_stamp structure + - SAUCE: Stacking v38: LSM: Add a function to report multiple LSMs + - SAUCE: Stacking v38: Audit: Allow multiple records in an audit_buffer + - SAUCE: Stacking v38: Audit: Add record for multiple task security contexts + - SAUCE: Stacking v38: audit: multiple subject lsm values for netlabel + - SAUCE: Stacking v38: Audit: Add record for multiple object contexts + - SAUCE: Stacking v38: netlabel: Use a struct lsmblob in audit data + - SAUCE: Stacking v38: LSM: Removed scaffolding function lsmcontext_init + - SAUCE: Stacking v38: AppArmor: Remove the exclusive flag + - SAUCE: apparmor: combine common_audit_data and apparmor_audit_data + - SAUCE: apparmor: setup slab cache for audit data + - SAUCE: apparmor: rename audit_data->label to audit_data->subj_label + - SAUCE: apparmor: pass cred through to audit info. + - SAUCE: apparmor: Improve debug print infrastructure + - SAUCE: apparmor: add the ability for profiles to have a learning cache + - SAUCE: apparmor: enable userspace upcall for mediation + - SAUCE: apparmor: cache buffers on percpu list if there is lock contention + - SAUCE: apparmor: fix policy_compat permission remap with extended + permissions + - SAUCE: apparmor: advertise availability of exended perms + - [Config] define CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + + * kinetic: apply new apparmor and LSM stacking patch set (LP: #1989983) // LSM + stacking and AppArmor refresh for 6.2 kernel (LP: #2012136) + - SAUCE: apparmor: add/use fns to print hash string hex value + - SAUCE: apparmor: patch to provide compatibility with v2.x net rules + - SAUCE: apparmor: add user namespace creation mediation + - SAUCE: apparmor: af_unix mediation + - SAUCE: apparmor: Add fine grained mediation of posix mqueues + + * devlink_port_split from ubuntu_kernel_selftests.net fails on hirsute + (KeyError: 'flavour') (LP: #1937133) + - selftests: net: devlink_port_split.py: skip test if no suitable device + available + + * NFS deathlock with last Kernel 5.4.0-144.161 and 5.15.0-67.74 (LP: #2009325) + - NFS: Correct timing for assigning access cache timestamp + + -- Andrea Righi Sat, 25 Mar 2023 07:37:30 +0100 + +linux (6.2.0-18.18) lunar; urgency=medium + + * lunar/linux: 6.2.0-18.18 -proposed tracker (LP: #2011750) + + * lunar/linux 6.2 fails to boot on arm64 (LP: #2011748) + - SAUCE: Revert "efi: random: fix NULL-deref when refreshing seed" + - SAUCE: Revert "efi: random: refresh non-volatile random seed when RNG is + initialized" + + -- Andrea Righi Wed, 15 Mar 2023 23:54:18 +0100 + +linux (6.2.0-17.17) lunar; urgency=medium + + * lunar/linux: 6.2.0-17.17 -proposed tracker (LP: #2011593) + + * lunar/linux 6.2 fails to boot on ppc64el (LP: #2011413) + - SAUCE: Revert "powerpc: remove STACK_FRAME_OVERHEAD" + - SAUCE: Revert "powerpc/pseries: hvcall stack frame overhead" + + * Speaker / Audio/Mic mute LED don't work on a HP platform (LP: #2011379) + - SAUCE: ALSA: hda/realtek: fix speaker, mute/micmute LEDs not work on a HP + platform + + * Some QHD panels fail to refresh when PSR2 enabled (LP: #2009014) + - SAUCE: drm/i915/psr: Use calculated io and fast wake lines + + * Lunar update: v6.2.6 upstream stable release (LP: #2011431) + - tpm: disable hwrng for fTPM on some AMD designs + - wifi: cfg80211: Partial revert "wifi: cfg80211: Fix use after free for wext" + - staging: rtl8192e: Remove function ..dm_check_ac_dc_power calling a script + - staging: rtl8192e: Remove call_usermodehelper starting RadioPower.sh + - Linux 6.2.6 + + * Lunar update: v6.2.5 upstream stable release (LP: #2011430) + - net/sched: Retire tcindex classifier + - auxdisplay: hd44780: Fix potential memory leak in hd44780_remove() + - fs/jfs: fix shift exponent db_agl2size negative + - driver: soc: xilinx: fix memory leak in xlnx_add_cb_for_notify_event() + - f2fs: don't rely on F2FS_MAP_* in f2fs_iomap_begin + - f2fs: fix to avoid potential deadlock + - objtool: Fix memory leak in create_static_call_sections() + - soc: mediatek: mtk-pm-domains: Allow mt8186 ADSP default power on + - soc: qcom: socinfo: Fix soc_id order + - memory: renesas-rpc-if: Split-off private data from struct rpcif + - memory: renesas-rpc-if: Move resource acquisition to .probe() + - soc: mediatek: mtk-svs: Enable the IRQ later + - pwm: sifive: Always let the first pwm_apply_state succeed + - pwm: stm32-lp: fix the check on arr and cmp registers update + - f2fs: introduce trace_f2fs_replace_atomic_write_block + - f2fs: clear atomic_write_task in f2fs_abort_atomic_write() + - soc: mediatek: mtk-svs: restore default voltages when svs_init02() fail + - soc: mediatek: mtk-svs: reset svs when svs_resume() fail + - soc: mediatek: mtk-svs: Use pm_runtime_resume_and_get() in svs_init01() + - f2fs: fix to do sanity check on extent cache correctly + - fs: f2fs: initialize fsdata in pagecache_write() + - f2fs: allow set compression option of files without blocks + - f2fs: fix to abort atomic write only during do_exist() + - um: vector: Fix memory leak in vector_config + - ubi: ensure that VID header offset + VID header size <= alloc, size + - ubifs: Fix build errors as symbol undefined + - ubifs: Fix memory leak in ubifs_sysfs_init() + - ubifs: Rectify space budget for ubifs_symlink() if symlink is encrypted + - ubifs: Rectify space budget for ubifs_xrename() + - ubifs: Fix wrong dirty space budget for dirty inode + - ubifs: do_rename: Fix wrong space budget when target inode's nlink > 1 + - ubifs: Reserve one leb for each journal head while doing budget + - ubi: Fix use-after-free when volume resizing failed + - ubi: Fix unreferenced object reported by kmemleak in ubi_resize_volume() + - ubifs: Fix memory leak in alloc_wbufs() + - ubi: Fix possible null-ptr-deref in ubi_free_volume() + - ubifs: Re-statistic cleaned znode count if commit failed + - ubifs: dirty_cow_znode: Fix memleak in error handling path + - ubifs: ubifs_writepage: Mark page dirty after writing inode failed + - ubifs: ubifs_releasepage: Remove ubifs_assert(0) to valid this process + - ubi: fastmap: Fix missed fm_anchor PEB in wear-leveling after disabling + fastmap + - ubi: Fix UAF wear-leveling entry in eraseblk_count_seq_show() + - ubi: ubi_wl_put_peb: Fix infinite loop when wear-leveling work failed + - f2fs: fix to handle F2FS_IOC_START_ATOMIC_REPLACE in f2fs_compat_ioctl() + - f2fs: fix to avoid potential memory corruption in __update_iostat_latency() + - f2fs: fix to update age extent correctly during truncation + - f2fs: fix to update age extent in f2fs_do_zero_range() + - soc: qcom: stats: Populate all subsystem debugfs files + - f2fs: introduce IS_F2FS_IPU_* macro + - f2fs: fix to set ipu policy + - ext4: use ext4_fc_tl_mem in fast-commit replay path + - ext4: don't show commit interval if it is zero + - netfilter: nf_tables: allow to fetch set elements when table has an owner + - x86: um: vdso: Add '%rcx' and '%r11' to the syscall clobber list + - um: virtio_uml: free command if adding to virtqueue failed + - um: virtio_uml: mark device as unregistered when breaking it + - um: virtio_uml: move device breaking into workqueue + - um: virt-pci: properly remove PCI device from bus + - f2fs: synchronize atomic write aborts + - watchdog: rzg2l_wdt: Issue a reset before we put the PM clocks + - watchdog: rzg2l_wdt: Handle TYPE-B reset for RZ/V2M + - watchdog: at91sam9_wdt: use devm_request_irq to avoid missing free_irq() in + error path + - watchdog: Fix kmemleak in watchdog_cdev_register + - watchdog: pcwd_usb: Fix attempting to access uninitialized memory + - watchdog: sbsa_wdog: Make sure the timeout programming is within the limits + - netfilter: ctnetlink: fix possible refcount leak in + ctnetlink_create_conntrack() + - netfilter: conntrack: fix rmmod double-free race + - netfilter: ip6t_rpfilter: Fix regression with VRF interfaces + - netfilter: ebtables: fix table blob use-after-free + - netfilter: xt_length: use skb len to match in length_mt6 + - netfilter: ctnetlink: make event listener tracking global + - netfilter: x_tables: fix percpu counter block leak on error path when + creating new netns + - swiotlb: mark swiotlb_memblock_alloc() as __init + - ptp: vclock: use mutex to fix "sleep on atomic" bug + - drm/i915: move a Kconfig symbol to unbreak the menu presentation + - ipv6: Add lwtunnel encap size of all siblings in nexthop calculation + - drm/i915/xelpmp: Consider GSI offset when doing MCR lookups + - octeontx2-pf: Recalculate UDP checksum for ptp 1-step sync packet + - net: sunhme: Fix region request + - sctp: add a refcnt in sctp_stream_priorities to avoid a nested loop + - octeontx2-pf: Use correct struct reference in test condition + - net: fix __dev_kfree_skb_any() vs drop monitor + - 9p/xen: fix version parsing + - 9p/xen: fix connection sequence + - 9p/rdma: unmap receive dma buffer in rdma_request()/post_recv() + - spi: tegra210-quad: Fix validate combined sequence + - mlx5: fix skb leak while fifo resync and push + - mlx5: fix possible ptp queue fifo use-after-free + - net/mlx5: ECPF, wait for VF pages only after disabling host PFs + - net/mlx5e: Verify flow_source cap before using it + - net/mlx5: Geneve, Fix handling of Geneve object id as error code + - ext4: fix incorrect options show of original mount_opt and extend mount_opt2 + - nfc: fix memory leak of se_io context in nfc_genl_se_io + - net/sched: transition act_pedit to rcu and percpu stats + - net/sched: act_pedit: fix action bind logic + - net/sched: act_mpls: fix action bind logic + - net/sched: act_sample: fix action bind logic + - net: dsa: seville: ignore mscc-miim read errors from Lynx PCS + - net: dsa: felix: fix internal MDIO controller resource length + - ARM: dts: aspeed: p10bmc: Update battery node name + - ARM: dts: spear320-hmi: correct STMPE GPIO compatible + - tcp: tcp_check_req() can be called from process context + - vc_screen: modify vcs_size() handling in vcs_read() + - spi: tegra210-quad: Fix iterator outside loop + - rtc: sun6i: Always export the internal oscillator + - genirq/ipi: Fix NULL pointer deref in irq_data_get_affinity_mask() + - scsi: ipr: Work around fortify-string warning + - scsi: mpi3mr: Fix an issue found by KASAN + - scsi: mpi3mr: Use number of bits to manage bitmap sizes + - rtc: allow rtc_read_alarm without read_alarm callback + - io_uring: fix size calculation when registering buf ring + - loop: loop_set_status_from_info() check before assignment + - ASoC: adau7118: don't disable regulators on device unbind + - ASoC: apple: mca: Fix final status read on SERDES reset + - ASoC: apple: mca: Fix SERDES reset sequence + - ASoC: apple: mca: Improve handling of unavailable DMA channels + - nvme: bring back auto-removal of deleted namespaces during sequential scan + - nvme-tcp: don't access released socket during error recovery + - nvme-fabrics: show well known discovery name + - ASoC: zl38060 add gpiolib dependency + - ASoC: mediatek: mt8195: add missing initialization + - thermal: intel: quark_dts: fix error pointer dereference + - thermal: intel: BXT_PMIC: select REGMAP instead of depending on it + - cpufreq: apple-soc: Fix an IS_ERR() vs NULL check + - tracing: Add NULL checks for buffer in ring_buffer_free_read_page() + - kernel/printk/index.c: fix memory leak with using debugfs_lookup() + - firmware/efi sysfb_efi: Add quirk for Lenovo IdeaPad Duet 3 + - bootconfig: Increase max nodes of bootconfig from 1024 to 8192 for DCC + support + - mfd: arizona: Use pm_runtime_resume_and_get() to prevent refcnt leak + - IB/hfi1: Update RMT size calculation + - iommu: Remove deferred attach check from __iommu_detach_device() + - PCI/ACPI: Account for _S0W of the target bridge in acpi_pci_bridge_d3() + - media: uvcvideo: Remove format descriptions + - media: uvcvideo: Handle cameras with invalid descriptors + - media: uvcvideo: Handle errors from calls to usb_string + - media: uvcvideo: Quirk for autosuspend in Logitech B910 and C910 + - media: uvcvideo: Silence memcpy() run-time false positive warnings + - USB: fix memory leak with using debugfs_lookup() + - cacheinfo: Fix shared_cpu_map to handle shared caches at different levels + - usb: fotg210: List different variants + - dt-bindings: usb: Add device id for Genesys Logic hub controller + - staging: emxx_udc: Add checks for dma_alloc_coherent() + - tty: fix out-of-bounds access in tty_driver_lookup_tty() + - tty: serial: fsl_lpuart: disable the CTS when send break signal + - serial: sc16is7xx: setup GPIO controller later in probe + - mei: bus-fixup:upon error print return values of send and receive + - tools/iio/iio_utils:fix memory leak + - bus: mhi: ep: Fix the debug message for MHI_PKT_TYPE_RESET_CHAN_CMD cmd + - iio: accel: mma9551_core: Prevent uninitialized variable in + mma9551_read_status_word() + - iio: accel: mma9551_core: Prevent uninitialized variable in + mma9551_read_config_word() + - media: uvcvideo: Add GUID for BGRA/X 8:8:8:8 + - soundwire: bus_type: Avoid lockdep assert in sdw_drv_probe() + - PCI/portdrv: Prevent LS7A Bus Master clearing on shutdown + - PCI: loongson: Prevent LS7A MRRS increases + - staging: pi433: fix memory leak with using debugfs_lookup() + - USB: dwc3: fix memory leak with using debugfs_lookup() + - USB: chipidea: fix memory leak with using debugfs_lookup() + - USB: ULPI: fix memory leak with using debugfs_lookup() + - USB: uhci: fix memory leak with using debugfs_lookup() + - USB: sl811: fix memory leak with using debugfs_lookup() + - USB: fotg210: fix memory leak with using debugfs_lookup() + - USB: isp116x: fix memory leak with using debugfs_lookup() + - USB: isp1362: fix memory leak with using debugfs_lookup() + - USB: gadget: gr_udc: fix memory leak with using debugfs_lookup() + - USB: gadget: bcm63xx_udc: fix memory leak with using debugfs_lookup() + - USB: gadget: lpc32xx_udc: fix memory leak with using debugfs_lookup() + - USB: gadget: pxa25x_udc: fix memory leak with using debugfs_lookup() + - USB: gadget: pxa27x_udc: fix memory leak with using debugfs_lookup() + - usb: host: xhci: mvebu: Iterate over array indexes instead of using pointer + math + - USB: ene_usb6250: Allocate enough memory for full object + - usb: uvc: Enumerate valid values for color matching + - usb: gadget: uvc: Make bSourceID read/write + - PCI: Align extra resources for hotplug bridges properly + - PCI: Take other bus devices into account when distributing resources + - PCI: Distribute available resources for root buses, too + - tty: pcn_uart: fix memory leak with using debugfs_lookup() + - misc: vmw_balloon: fix memory leak with using debugfs_lookup() + - drivers: base: component: fix memory leak with using debugfs_lookup() + - drivers: base: dd: fix memory leak with using debugfs_lookup() + - kernel/fail_function: fix memory leak with using debugfs_lookup() + - PCI: loongson: Add more devices that need MRRS quirk + - PCI: Add ACS quirk for Wangxun NICs + - PCI: pciehp: Add Qualcomm quirk for Command Completed erratum + - phy: rockchip-typec: Fix unsigned comparison with less than zero + - RDMA/cma: Distinguish between sockaddr_in and sockaddr_in6 by size + - soundwire: cadence: Remove wasted space in response_buf + - soundwire: cadence: Drain the RX FIFO after an IO timeout + - eth: fealnx: bring back this old driver + - net: tls: avoid hanging tasks on the tx_lock + - x86/resctl: fix scheduler confusion with 'current' + - vDPA/ifcvf: decouple hw features manipulators from the adapter + - vDPA/ifcvf: decouple config space ops from the adapter + - vDPA/ifcvf: alloc the mgmt_dev before the adapter + - vDPA/ifcvf: decouple vq IRQ releasers from the adapter + - vDPA/ifcvf: decouple config IRQ releaser from the adapter + - vDPA/ifcvf: decouple vq irq requester from the adapter + - vDPA/ifcvf: decouple config/dev IRQ requester and vectors allocator from the + adapter + - vDPA/ifcvf: ifcvf_request_irq works on ifcvf_hw + - vDPA/ifcvf: manage ifcvf_hw in the mgmt_dev + - vDPA/ifcvf: allocate the adapter in dev_add() + - drm/display/dp_mst: Add drm_atomic_get_old_mst_topology_state() + - drm/display/dp_mst: Fix down/up message handling after sink disconnect + - drm/display/dp_mst: Fix down message handling after a packet reception error + - drm/display/dp_mst: Fix payload addition on a disconnected sink + - drm/i915/dp_mst: Add the MST topology state for modesetted CRTCs + - drm/display/dp_mst: Handle old/new payload states in drm_dp_remove_payload() + - drm/i915/dp_mst: Fix payload removal during output disabling + - drm/i915: Fix system suspend without fbdev being initialized + - media: uvcvideo: Fix race condition with usb_kill_urb + - arm64: efi: Make efi_rt_lock a raw_spinlock + - usb: gadget: uvc: fix missing mutex_unlock() if kstrtou8() fails + - Linux 6.2.5 + + * Lunar update: v6.2.4 upstream stable release (LP: #2011428) + - Revert "blk-cgroup: synchronize pd_free_fn() from blkg_free_workfn() and + blkcg_deactivate_policy()" + - Revert "blk-cgroup: dropping parent refcount after pd_free_fn() is done" + - Linux 6.2.4 + + * Lunar update: v6.2.3 upstream stable release (LP: #2011425) + - HID: asus: use spinlock to protect concurrent accesses + - HID: asus: use spinlock to safely schedule workers + - iommu/amd: Fix error handling for pdev_pri_ats_enable() + - iommu/amd: Skip attach device domain is same as new domain + - iommu/amd: Improve page fault error reporting + - iommu: Attach device group to old domain in error path + - powerpc/mm: Rearrange if-else block to avoid clang warning + - ata: ahci: Revert "ata: ahci: Add Tiger Lake UP{3,4} AHCI controller" + - ARM: OMAP2+: Fix memory leak in realtime_counter_init() + - arm64: dts: qcom: qcs404: use symbol names for PCIe resets + - arm64: dts: qcom: msm8996-tone: Fix USB taking 6 minutes to wake up + - arm64: dts: qcom: sm6115: Fix UFS node + - arm64: dts: qcom: sm6115: Provide xo clk to rpmcc + - arm64: dts: qcom: sm8150-kumano: Panel framebuffer is 2.5k instead of 4k + - arm64: dts: qcom: pmi8950: Correct rev_1250v channel label to mv + - arm64: dts: qcom: sm6350: Fix up the ramoops node + - arm64: dts: qcom: sdm670-google-sargo: keep pm660 ldo8 on + - arm64: dts: qcom: Re-enable resin on MSM8998 and SDM845 boards + - arm64: dts: qcom: sm8350-sagami: Configure SLG51000 PMIC on PDX215 + - arm64: dts: qcom: sm8350-sagami: Add GPIO line names for PMIC GPIOs + - arm64: dts: qcom: sm8350-sagami: Rectify GPIO keys + - arm64: dts: qcom: sm6350-lena: Flatten gpio-keys pinctrl state + - arm64: dts: qcom: sm6125: Reorder HSUSB PHY clocks to match bindings + - arm64: dts: qcom: sm6125-seine: Clean up gpio-keys (volume down) + - arm64: dts: imx8m: Align SoC unique ID node unit address + - ARM: zynq: Fix refcount leak in zynq_early_slcr_init + - fs: dlm: fix return value check in dlm_memory_init() + - arm64: dts: mediatek: mt8195: Add power domain to U3PHY1 T-PHY + - arm64: dts: mediatek: mt8183: Fix systimer 13 MHz clock description + - arm64: dts: mediatek: mt8192: Fix systimer 13 MHz clock description + - arm64: dts: mediatek: mt8195: Fix systimer 13 MHz clock description + - arm64: dts: mediatek: mt8186: Fix systimer 13 MHz clock description + - arm64: dts: qcom: sdm845-db845c: fix audio codec interrupt pin name + - arm64: dts: qcom: sdm845-xiaomi-beryllium: fix audio codec interrupt pin + name + - x86/acpi/boot: Do not register processors that cannot be onlined for x2APIC + - arm64: dts: qcom: sc7180: correct SPMI bus address cells + - arm64: dts: qcom: sc7280: correct SPMI bus address cells + - arm64: dts: qcom: sc8280xp: correct SPMI bus address cells + - arm64: dts: qcom: sm8450: correct Soundwire wakeup interrupt name + - arm64: dts: qcom: sdm845: make DP node follow the schema + - arm64: dts: qcom: msm8996-oneplus-common: drop vdda-supply from DSI PHY + - arm64: dts: qcom: sc8280xp: Vote for CX in USB controllers + - arm64: dts: meson-gxl: jethub-j80: Fix WiFi MAC address node + - arm64: dts: meson-gxl: jethub-j80: Fix Bluetooth MAC node name + - arm64: dts: meson-axg: jethub-j1xx: Fix MAC address node names + - arm64: dts: meson-gx: Fix Ethernet MAC address unit name + - arm64: dts: meson-g12a: Fix internal Ethernet PHY unit name + - arm64: dts: meson-gx: Fix the SCPI DVFS node name and unit address + - cpuidle, intel_idle: Fix CPUIDLE_FLAG_IRQ_ENABLE *again* + - arm64: dts: ti: k3-am62-main: Fix clocks for McSPI + - arm64: tegra: Fix duplicate regulator on Jetson TX1 + - arm64: dts: qcom: msm8992-bullhead: Fix cont_splash_mem size + - arm64: dts: qcom: msm8992-bullhead: Disable dfps_data_mem + - arm64: dts: qcom: msm8956: use SoC-specific compat for tsens + - arm64: dts: qcom: ipq8074: correct USB3 QMP PHY-s clock output names + - arm64: dts: qcom: ipq8074: fix Gen2 PCIe QMP PHY + - arm64: dts: qcom: ipq8074: fix Gen3 PCIe QMP PHY + - arm64: dts: qcom: ipq8074: correct Gen2 PCIe ranges + - arm64: dts: qcom: ipq8074: fix Gen3 PCIe node + - arm64: dts: qcom: ipq8074: correct PCIe QMP PHY output clock names + - arm64: dts: meson: remove CPU opps below 1GHz for G12A boards + - ARM: OMAP1: call platform_device_put() in error case in + omap1_dm_timer_init() + - arm64: dts: mediatek: mt8192: Mark scp_adsp clock as broken + - ARM: bcm2835_defconfig: Enable the framebuffer + - ARM: s3c: fix s3c64xx_set_timer_source prototype + - arm64: dts: ti: k3-j7200: Fix wakeup pinmux range + - ARM: dts: exynos: correct wr-active property in Exynos3250 Rinato + - ARM: imx: Call ida_simple_remove() for ida_simple_get + - arm64: dts: amlogic: meson-gx: fix SCPI clock dvfs node name + - arm64: dts: amlogic: meson-axg: fix SCPI clock dvfs node name + - arm64: dts: amlogic: meson-gx: add missing SCPI sensors compatible + - arm64: dts: amlogic: meson-axg-jethome-jethub-j1xx: fix supply name of USB + controller node + - arm64: dts: amlogic: meson-gxl-s905d-sml5442tw: drop invalid clock-names + property + - arm64: dts: amlogic: meson-gx: add missing unit address to rng node name + - arm64: dts: amlogic: meson-gxl-s905w-jethome-jethub-j80: fix invalid rtc + node name + - arm64: dts: amlogic: meson-axg-jethome-jethub-j1xx: fix invalid rtc node + name + - arm64: dts: amlogic: meson-gxl: add missing unit address to eth-phy-mux node + name + - arm64: dts: amlogic: meson-gx-libretech-pc: fix update button name + - arm64: dts: amlogic: meson-sm1-bananapi-m5: fix adc keys node names + - arm64: dts: amlogic: meson-gxl-s905d-phicomm-n1: fix led node name + - arm64: dts: amlogic: meson-gxbb-kii-pro: fix led node name + - arm64: dts: amlogic: meson-g12b-odroid-go-ultra: fix rk818 pmic properties + - arm64: dts: amlogic: meson-sm1-odroid-hc4: fix active fan thermal trip + - locking/rwsem: Disable preemption in all down_read*() and up_read() code + paths + - arm64: tegra: Mark host1x as dma-coherent on Tegra194/234 + - arm64: dts: renesas: beacon-renesom: Fix gpio expander reference + - arm64: dts: meson: radxa-zero: allow usb otg mode + - arm64: dts: meson: bananapi-m5: switch VDDIO_C pin to OPEN_DRAIN + - ARM: dts: sun8i: nanopi-duo2: Fix regulator GPIO reference + - ublk_drv: remove nr_aborted_queues from ublk_device + - ublk_drv: don't probe partitions if the ubq daemon isn't trusted + - ARM: dts: imx7s: correct iomuxc gpr mux controller cells + - sbitmap: remove redundant check in __sbitmap_queue_get_batch + - sbitmap: correct wake_batch recalculation to avoid potential IO hung + - arm64: dts: mt8195: Fix CPU map for single-cluster SoC + - arm64: dts: mt8192: Fix CPU map for single-cluster SoC + - arm64: dts: mt8186: Fix CPU map for single-cluster SoC + - arm64: dts: mediatek: mt7622: Add missing pwm-cells to pwm node + - arm64: dts: mediatek: mt8186: Fix watchdog compatible + - arm64: dts: mediatek: mt8195: Fix watchdog compatible + - arm64: dts: mediatek: mt7986: Fix watchdog compatible + - ARM: dts: stm32: Update part number NVMEM description on stm32mp131 + - arm64: dts: qcom: sm8450-nagara: Correct firmware paths + - blk-mq: avoid sleep in blk_mq_alloc_request_hctx + - blk-mq: remove stale comment for blk_mq_sched_mark_restart_hctx + - blk-mq: wait on correct sbitmap_queue in blk_mq_mark_tag_wait + - blk-mq: Fix potential io hung for shared sbitmap per tagset + - blk-mq: correct stale comment of .get_budget + - arm64: dts: qcom: msm8996: support using GPLL0 as kryocc input + - arm64: dts: qcom: msm8996 switch from RPM_SMD_BB_CLK1 to RPM_SMD_XO_CLK_SRC + - arm64: dts: qcom: sm8350: drop incorrect cells from serial + - arm64: dts: qcom: sm8450: drop incorrect cells from serial + - arm64: dts: qcom: msm8992-lg-bullhead: Correct memory overlaps with the SMEM + and MPSS memory regions + - arm64: dts: qcom: msm8953: correct TLMM gpio-ranges + - arm64: dts: qcom: sm6115: correct TLMM gpio-ranges + - arm64: dts: qcom: msm8992-lg-bullhead: Enable regulators + - s390/dasd: Fix potential memleak in dasd_eckd_init() + - io_uring,audit: don't log IORING_OP_MADVISE + - sched/rt: pick_next_rt_entity(): check list_entry + - perf/x86/intel/ds: Fix the conversion from TSC to perf time + - x86/perf/zhaoxin: Add stepping check for ZXC + - KEYS: asymmetric: Fix ECDSA use via keyctl uapi + - block: ublk: check IO buffer based on flag need_get_data + - arm64: dts: qcom: pmk8350: Use the correct PON compatible + - erofs: relinquish volume with mutex held + - block: sync mixed merged request's failfast with 1st bio's + - block: Fix io statistics for cgroup in throttle path + - block: bio-integrity: Copy flags when bio_integrity_payload is cloned + - block: use proper return value from bio_failfast() + - wifi: mt76: mt7915: add missing of_node_put() + - wifi: mt76: mt7921s: fix slab-out-of-bounds access in sdio host + - wifi: mt76: mt7915: fix mt7915_rate_txpower_get() resource leaks + - wifi: mt76: mt7996: fix insecure data handling of mt7996_mcu_ie_countdown() + - wifi: mt76: mt7996: fix insecure data handling of + mt7996_mcu_rx_radar_detected() + - wifi: mt76: mt7996: fix integer handling issue of mt7996_rf_regval_set() + - wifi: mt76: mt7915: check return value before accessing free_block_num + - wifi: mt76: mt7996: check return value before accessing free_block_num + - wifi: mt76: mt7915: drop always true condition of __mt7915_reg_addr() + - wifi: mt76: mt7996: drop always true condition of __mt7996_reg_addr() + - wifi: mt76: mt7996: fix endianness warning in mt7996_mcu_sta_he_tlv + - wifi: mt76: mt76x0: fix oob access in mt76x0_phy_get_target_power + - wifi: mt76: mt7996: fix unintended sign extension of mt7996_hw_queue_read() + - wifi: mt76: mt7915: fix unintended sign extension of mt7915_hw_queue_read() + - wifi: mt76: fix coverity uninit_use_in_call in + mt76_connac2_reverse_frag0_hdr_trans() + - wifi: mt76: mt7921: resource leaks at mt7921_check_offload_capability() + - wifi: rsi: Fix memory leak in rsi_coex_attach() + - wifi: rtlwifi: rtl8821ae: don't call kfree_skb() under spin_lock_irqsave() + - wifi: rtlwifi: rtl8188ee: don't call kfree_skb() under spin_lock_irqsave() + - wifi: rtlwifi: rtl8723be: don't call kfree_skb() under spin_lock_irqsave() + - wifi: iwlegacy: common: don't call dev_kfree_skb() under spin_lock_irqsave() + - wifi: libertas: fix memory leak in lbs_init_adapter() + - wifi: rtl8xxxu: Fix assignment to bit field priv->pi_enabled + - wifi: rtl8xxxu: Fix assignment to bit field priv->cck_agc_report_type + - wifi: rtl8xxxu: don't call dev_kfree_skb() under spin_lock_irqsave() + - wifi: rtw89: 8852c: rfk: correct DACK setting + - wifi: rtw89: 8852c: rfk: correct DPK settings + - wifi: rtlwifi: Fix global-out-of-bounds bug in + _rtl8812ae_phy_set_txpower_limit() + - libbpf: Fix single-line struct definition output in btf_dump + - libbpf: Fix btf__align_of() by taking into account field offsets + - wifi: ipw2x00: don't call dev_kfree_skb() under spin_lock_irqsave() + - wifi: ipw2200: fix memory leak in ipw_wdev_init() + - wifi: wilc1000: fix potential memory leak in wilc_mac_xmit() + - wifi: wilc1000: add missing unregister_netdev() in wilc_netdev_ifc_init() + - wifi: brcmfmac: fix potential memory leak in brcmf_netdev_start_xmit() + - wifi: brcmfmac: unmap dma buffer in brcmf_msgbuf_alloc_pktid() + - wifi: libertas_tf: don't call kfree_skb() under spin_lock_irqsave() + - wifi: libertas: if_usb: don't call kfree_skb() under spin_lock_irqsave() + - wifi: libertas: main: don't call kfree_skb() under spin_lock_irqsave() + - wifi: libertas: cmdresp: don't call kfree_skb() under spin_lock_irqsave() + - wifi: wl3501_cs: don't call kfree_skb() under spin_lock_irqsave() + - libbpf: Fix invalid return address register in s390 + - crypto: x86/ghash - fix unaligned access in ghash_setkey() + - crypto: ux500 - update debug config after ux500 cryp driver removal + - ACPICA: Drop port I/O validation for some regions + - genirq: Fix the return type of kstat_cpu_irqs_sum() + - rcu-tasks: Improve comments explaining tasks_rcu_exit_srcu purpose + - rcu-tasks: Remove preemption disablement around srcu_read_[un]lock() calls + - rcu-tasks: Fix synchronize_rcu_tasks() VS zap_pid_ns_processes() + - lib/mpi: Fix buffer overrun when SG is too long + - crypto: ccp - Avoid page allocation failure warning for SEV_GET_ID2 + - platform/chrome: cros_ec_typec: Update port DP VDO + - ACPICA: nsrepair: handle cases without a return value correctly + - libbpf: Fix map creation flags sanitization + - bpf_doc: Fix build error with older python versions + - selftests/xsk: print correct payload for packet dump + - selftests/xsk: print correct error codes when exiting + - arm64/cpufeature: Fix field sign for DIT hwcap detection + - arm64/sysreg: Fix errors in 32 bit enumeration values + - kselftest/arm64: Fix syscall-abi for systems without 128 bit SME + - workqueue: Protects wq_unbound_cpumask with wq_pool_attach_mutex + - s390/early: fix sclp_early_sccb variable lifetime + - s390/vfio-ap: fix an error handling path in vfio_ap_mdev_probe_queue() + - x86/signal: Fix the value returned by strict_sas_size() + - thermal/drivers/tsens: Drop msm8976-specific defines + - thermal/drivers/tsens: Sort out msm8976 vs msm8956 data + - thermal/drivers/tsens: fix slope values for msm8939 + - thermal/drivers/tsens: limit num_sensors to 9 for msm8939 + - wifi: rtw89: fix potential leak in rtw89_append_probe_req_ie() + - wifi: rtw89: Add missing check for alloc_workqueue + - wifi: rtl8xxxu: Fix memory leaks with RTL8723BU, RTL8192EU + - wifi: orinoco: check return value of hermes_write_wordrec() + - wifi: rtw88: Use rtw_iterate_vifs() for rtw_vif_watch_dog_iter() + - wifi: rtw88: Use non-atomic sta iterator in rtw_ra_mask_info_update() + - thermal/drivers/imx_sc_thermal: Fix the loop condition + - wifi: ath9k: htc_hst: free skb in ath9k_htc_rx_msg() if there is no callback + function + - wifi: ath9k: hif_usb: clean up skbs if ath9k_hif_usb_rx_stream() fails + - wifi: ath9k: Fix potential stack-out-of-bounds write in + ath9k_wmi_rsp_callback() + - wifi: ath11k: Fix memory leak in ath11k_peer_rx_frag_setup + - wifi: cfg80211: Fix extended KCK key length check in + nl80211_set_rekey_data() + - ACPI: battery: Fix missing NUL-termination with large strings + - selftests/bpf: Fix build errors if CONFIG_NF_CONNTRACK=m + - crypto: ccp - Failure on re-initialization due to duplicate sysfs filename + - crypto: essiv - Handle EBUSY correctly + - crypto: seqiv - Handle EBUSY correctly + - powercap: fix possible name leak in powercap_register_zone() + - bpf: Fix state pruning for STACK_DYNPTR stack slots + - bpf: Fix missing var_off check for ARG_PTR_TO_DYNPTR + - bpf: Fix partial dynptr stack slot reads/writes + - x86/microcode: Add a parameter to microcode_check() to store CPU + capabilities + - x86/microcode: Check CPU capabilities after late microcode update correctly + - x86/microcode: Adjust late loading result reporting message + - net: ethernet: ti: am65-cpsw/cpts: Fix CPTS release action + - selftests/bpf: Fix vmtest static compilation error + - crypto: xts - Handle EBUSY correctly + - leds: led-class: Add missing put_device() to led_put() + - drm/nouveau/disp: Fix nvif_outp_acquire_dp() argument size + - s390/bpf: Add expoline to tail calls + - wifi: iwlwifi: mei: fix compilation errors in rfkill() + - kselftest/arm64: Fix enumeration of systems without 128 bit SME + - can: rcar_canfd: Fix R-Car V3U CAN mode selection + - can: rcar_canfd: Fix R-Car V3U GAFLCFG field accesses + - selftests/bpf: Initialize tc in xdp_synproxy + - crypto: ccp - Flush the SEV-ES TMR memory before giving it to firmware + - bpftool: profile online CPUs instead of possible + - wifi: mt76: mt7921: fix deadlock in mt7921_abort_roc + - wifi: mt76: mt7915: call mt7915_mcu_set_thermal_throttling() only after + init_work + - wifi: mt76: mt7915: rework mt7915_mcu_set_thermal_throttling + - wifi: mt76: mt7915: rework mt7915_thermal_temp_store() + - wifi: mt76: mt7921: fix channel switch fail in monitor mode + - wifi: mt76: mt7996: fix chainmask calculation in mt7996_set_antenna() + - wifi: mt76: mt7996: update register for CFEND_RATE + - wifi: mt76: connac: fix POWER_CTRL command name typo + - wifi: mt76: mt7921: fix invalid remain_on_channel duration + - wifi: mt76: mt7915: fix memory leak in mt7915_mcu_exit + - wifi: mt76: mt7996: fix memory leak in mt7996_mcu_exit + - wifi: mt76: dma: fix memory leak running mt76_dma_tx_cleanup + - wifi: mt76: fix switch default case in mt7996_reverse_frag0_hdr_trans + - wifi: mt76: mt7915: fix WED TxS reporting + - wifi: mt76: add memory barrier to SDIO queue kick + - wifi: mt76: mt7996: rely on mt76_connac2_mac_tx_rate_val + - net/mlx5: Enhance debug print in page allocation failure + - irqchip: Fix refcount leak in platform_irqchip_probe + - irqchip/alpine-msi: Fix refcount leak in alpine_msix_init_domains + - irqchip/irq-mvebu-gicp: Fix refcount leak in mvebu_gicp_probe + - irqchip/ti-sci: Fix refcount leak in ti_sci_intr_irq_domain_probe + - s390/mem_detect: fix detect_memory() error handling + - s390/vmem: fix empty page tables cleanup under KASAN + - s390/boot: cleanup decompressor header files + - s390/mem_detect: rely on diag260() if sclp_early_get_memsize() fails + - s390/boot: fix mem_detect extended area allocation + - net: add sock_init_data_uid() + - tun: tun_chr_open(): correctly initialize socket uid + - tap: tap_open(): correctly initialize socket uid + - rxrpc: Fix overwaking on call poking + - OPP: fix error checking in opp_migrate_dentry() + - cpufreq: davinci: Fix clk use after free + - Bluetooth: hci_conn: Refactor hci_bind_bis() since it always succeeds + - Bluetooth: L2CAP: Fix potential user-after-free + - Bluetooth: hci_qca: get wakeup status from serdev device handle + - net: ipa: generic command param fix + - s390: vfio-ap: tighten the NIB validity check + - s390/ap: fix status returned by ap_aqic() + - s390/ap: fix status returned by ap_qact() + - libbpf: Fix alen calculation in libbpf_nla_dump_errormsg() + - xen/grant-dma-iommu: Implement a dummy probe_device() callback + - rds: rds_rm_zerocopy_callback() correct order for list_add_tail() + - crypto: rsa-pkcs1pad - Use akcipher_request_complete + - m68k: /proc/hardware should depend on PROC_FS + - RISC-V: time: initialize hrtimer based broadcast clock event device + - clocksource/drivers/riscv: Patch riscv_clock_next_event() jump before first + use + - wifi: iwl3945: Add missing check for create_singlethread_workqueue + - wifi: iwl4965: Add missing check for create_singlethread_workqueue() + - wifi: brcmfmac: Rename Cypress 89459 to BCM4355 + - wifi: brcmfmac: pcie: Add IDs/properties for BCM4355 + - wifi: brcmfmac: pcie: Add IDs/properties for BCM4377 + - wifi: brcmfmac: pcie: Perform correct BCM4364 firmware selection + - wifi: mwifiex: fix loop iterator in mwifiex_update_ampdu_txwinsize() + - wifi: rtw89: fix parsing offset for MCC C2H + - selftests/bpf: Fix out-of-srctree build + - ACPI: resource: Add IRQ overrides for MAINGEAR Vector Pro 2 models + - ACPI: resource: Do IRQ override on all TongFang GMxRGxx + - crypto: octeontx2 - Fix objects shared between several modules + - crypto: crypto4xx - Call dma_unmap_page when done + - vfio/ccw: remove WARN_ON during shutdown + - wifi: mac80211: move color collision detection report in a delayed work + - wifi: mac80211: make rate u32 in sta_set_rate_info_rx() + - wifi: mac80211: fix non-MLO station association + - wifi: mac80211: Don't translate MLD addresses for multicast + - wifi: mac80211: avoid u32_encode_bits() warning + - wifi: mac80211: fix off-by-one link setting + - tools/lib/thermal: Fix thermal_sampling_exit() + - thermal/drivers/hisi: Drop second sensor hi3660 + - selftests/bpf: Fix map_kptr test. + - wifi: mac80211: pass 'sta' to ieee80211_rx_data_set_sta() + - bpf: Zeroing allocated object from slab in bpf memory allocator + - selftests/bpf: Fix xdp_do_redirect on s390x + - can: esd_usb: Move mislocated storage of SJA1000_ECC_SEG bits in case of a + bus error + - can: esd_usb: Make use of can_change_state() and relocate checking skb for + NULL + - xsk: check IFF_UP earlier in Tx path + - LoongArch, bpf: Use 4 instructions for function address in JIT + - bpf: Fix global subprog context argument resolution logic + - irqchip/irq-brcmstb-l2: Set IRQ_LEVEL for level triggered interrupts + - irqchip/irq-bcm7120-l2: Set IRQ_LEVEL for level triggered interrupts + - net/smc: fix potential panic dues to unprotected smc_llc_srv_add_link() + - net/smc: fix application data exception + - selftests/net: Interpret UDP_GRO cmsg data as an int value + - l2tp: Avoid possible recursive deadlock in l2tp_tunnel_register() + - net: bcmgenet: fix MoCA LED control + - net: lan966x: Fix possible deadlock inside PTP + - net/mlx4_en: Introduce flexible array to silence overflow warning + - net/mlx5e: Align IPsec ASO result memory to be as required by hardware + - selftest: fib_tests: Always cleanup before exit + - sefltests: netdevsim: wait for devlink instance after netns removal + - drm: Fix potential null-ptr-deref due to drmm_mode_config_init() + - drm/fourcc: Add missing big-endian XRGB1555 and RGB565 formats + - drm/bridge: ti-sn65dsi83: Fix delay after reset deassert to match spec + - drm: mxsfb: DRM_IMX_LCDIF should depend on ARCH_MXC + - drm: mxsfb: DRM_MXSFB should depend on ARCH_MXS || ARCH_MXC + - drm/bridge: megachips: Fix error handling in i2c_register_driver() + - drm/vkms: Fix memory leak in vkms_init() + - drm/vkms: Fix null-ptr-deref in vkms_release() + - drm/modes: Use strscpy() to copy command-line mode name + - drm/vc4: dpi: Fix format mapping for RGB565 + - drm/bridge: it6505: Guard bridge power in IRQ handler + - drm: tidss: Fix pixel format definition + - gpu: ipu-v3: common: Add of_node_put() for reference returned by + of_graph_get_port_by_id() + - drm/ast: Init iosys_map pointer as I/O memory for damage handling + - drm/vc4: drop all currently held locks if deadlock happens + - hwmon: (ftsteutates) Fix scaling of measurements + - drm/msm/dpu: check for null return of devm_kzalloc() in dpu_writeback_init() + - drm/msm/hdmi: Add missing check for alloc_ordered_workqueue + - pinctrl: qcom: pinctrl-msm8976: Correct function names for wcss pins + - pinctrl: stm32: Fix refcount leak in stm32_pctrl_get_irq_domain + - pinctrl: rockchip: Fix refcount leak in rockchip_pinctrl_parse_groups + - drm/vc4: hvs: Configure the HVS COB allocations + - drm/vc4: hvs: Set AXI panic modes + - drm/vc4: hvs: SCALER_DISPBKGND_AUTOHS is only valid on HVS4 + - drm/vc4: hvs: Correct interrupt masking bit assignment for HVS5 + - drm/vc4: hvs: Fix colour order for xRGB1555 on HVS5 + - drm/vc4: hdmi: Correct interlaced timings again + - drm/msm: clean event_thread->worker in case of an error + - drm/panel-edp: fix name for IVO product id 854b + - scsi: qla2xxx: Fix exchange oversubscription + - scsi: qla2xxx: Fix exchange oversubscription for management commands + - scsi: qla2xxx: edif: Fix clang warning + - ASoC: fsl_sai: initialize is_dsp_mode flag + - drm/bridge: tc358767: Set default CLRSIPO count + - drm/msm/adreno: Fix null ptr access in adreno_gpu_cleanup() + - ALSA: hda/ca0132: minor fix for allocation size + - drm/amdgpu: Use the sched from entity for amdgpu_cs trace + - drm/msm/gem: Add check for kmalloc + - drm/msm/dpu: Disallow unallocated resources to be returned + - drm/bridge: lt9611: fix sleep mode setup + - drm/bridge: lt9611: fix HPD reenablement + - drm/bridge: lt9611: fix polarity programming + - drm/bridge: lt9611: fix programming of video modes + - drm/bridge: lt9611: fix clock calculation + - drm/bridge: lt9611: pass a pointer to the of node + - regulator: tps65219: use IS_ERR() to detect an error pointer + - drm/mipi-dsi: Fix byte order of 16-bit DCS set/get brightness + - drm: exynos: dsi: Fix MIPI_DSI*_NO_* mode flags + - drm/msm/dsi: Allow 2 CTRLs on v2.5.0 + - scsi: ufs: exynos: Fix DMA alignment for PAGE_SIZE != 4096 + - drm/msm/dpu: sc7180: add missing WB2 clock control + - drm/msm: use strscpy instead of strncpy + - drm/msm/dpu: Add check for cstate + - drm/msm/dpu: Add check for pstates + - drm/msm/mdp5: Add check for kzalloc + - habanalabs: bugs fixes in timestamps buff alloc + - pinctrl: bcm2835: Remove of_node_put() in bcm2835_of_gpio_ranges_fallback() + - pinctrl: mediatek: Initialize variable pullen and pullup to zero + - pinctrl: mediatek: Initialize variable *buf to zero + - gpu: host1x: Fix mask for syncpoint increment register + - gpu: host1x: Don't skip assigning syncpoints to channels + - drm/tegra: firewall: Check for is_addr_reg existence in IMM check + - drm/i915/mtl: Add initial gt workarounds + - drm/i915/xehp: GAM registers don't need to be re-applied on engine resets + - pinctrl: renesas: rzg2l: Fix configuring the GPIO pins as interrupts + - drm/i915/xehp: Annotate a couple more workaround registers as MCR + - drm/msm/dpu: set pdpu->is_rt_pipe early in dpu_plane_sspp_atomic_update() + - drm/mediatek: dsi: Reduce the time of dsi from LP11 to sending cmd + - drm/mediatek: Use NULL instead of 0 for NULL pointer + - drm/mediatek: Drop unbalanced obj unref + - drm/mediatek: mtk_drm_crtc: Add checks for devm_kcalloc + - drm/mediatek: Clean dangling pointer on bind error path + - ASoC: soc-compress.c: fixup private_data on snd_soc_new_compress() + - dt-bindings: display: mediatek: Fix the fallback for mediatek,mt8186-disp- + ccorr + - gpio: pca9570: rename platform_data to chip_data + - gpio: vf610: connect GPIO label to dev name + - ASoC: topology: Properly access value coming from topology file + - spi: dw_bt1: fix MUX_MMIO dependencies + - ASoC: mchp-spdifrx: fix controls which rely on rsr register + - ASoC: mchp-spdifrx: fix return value in case completion times out + - ASoC: mchp-spdifrx: fix controls that works with completion mechanism + - ASoC: mchp-spdifrx: disable all interrupts in mchp_spdifrx_dai_remove() + - dm: improve shrinker debug names + - regmap: apply reg_base and reg_downshift for single register ops + - accel: fix CONFIG_DRM dependencies + - ASoC: rsnd: fixup #endif position + - ASoC: mchp-spdifrx: Fix uninitialized use of mr in mchp_spdifrx_hw_params() + - ASoC: dt-bindings: meson: fix gx-card codec node regex + - regulator: tps65219: use generic set_bypass() + - hwmon: (asus-ec-sensors) add missing mutex path + - hwmon: (ltc2945) Handle error case in ltc2945_value_store + - ALSA: hda: Fix the control element identification for multiple codecs + - drm/amdgpu: fix enum odm_combine_mode mismatch + - scsi: mpt3sas: Fix a memory leak + - scsi: aic94xx: Add missing check for dma_map_single() + - HID: multitouch: Add quirks for flipped axes + - HID: retain initial quirks set up when creating HID devices + - ASoC: qcom: q6apm-lpass-dai: unprepare stream if its already prepared + - ASoC: qcom: q6apm-dai: fix race condition while updating the position + pointer + - ASoC: qcom: q6apm-dai: Add SNDRV_PCM_INFO_BATCH flag + - ASoC: codecs: lpass: register mclk after runtime pm + - ASoC: codecs: lpass: fix incorrect mclk rate + - drm/amd/display: don't call dc_interrupt_set() for disabled crtcs + - HID: logitech-hidpp: Hard-code HID++ 1.0 fast scroll support + - spi: bcm63xx-hsspi: Fix multi-bit mode setting + - hwmon: (mlxreg-fan) Return zero speed for broken fan + - ASoC: tlv320adcx140: fix 'ti,gpio-config' DT property init + - dm: remove flush_scheduled_work() during local_exit() + - nfs4trace: fix state manager flag printing + - NFS: fix disabling of swap + - drm/i915/pvc: Implement recommended caching policy + - drm/i915/pvc: Annotate two more workaround/tuning registers as MCR + - drm/i915: Fix GEN8_MISCCPCTL + - spi: synquacer: Fix timeout handling in synquacer_spi_transfer_one() + - ASoC: soc-dapm.h: fixup warning struct snd_pcm_substream not declared + - HID: bigben: use spinlock to protect concurrent accesses + - HID: bigben_worker() remove unneeded check on report_field + - HID: bigben: use spinlock to safely schedule workers + - hid: bigben_probe(): validate report count + - ALSA: hda/hdmi: Register with vga_switcheroo on Dual GPU Macbooks + - drm/shmem-helper: Fix locking for drm_gem_shmem_get_pages_sgt() + - NFSD: enhance inter-server copy cleanup + - NFSD: fix leaked reference count of nfsd4_ssc_umount_item + - nfsd: fix race to check ls_layouts + - nfsd: clean up potential nfsd_file refcount leaks in COPY codepath + - NFSD: fix problems with cleanup on errors in nfsd4_copy + - nfsd: fix courtesy client with deny mode handling in nfs4_upgrade_open + - nfsd: don't fsync nfsd_files on last close + - NFSD: copy the whole verifier in nfsd_copy_write_verifier + - cifs: Fix lost destroy smbd connection when MR allocate failed + - cifs: Fix warning and UAF when destroy the MR list + - cifs: use tcon allocation functions even for dummy tcon + - gfs2: jdata writepage fix + - perf llvm: Fix inadvertent file creation + - leds: led-core: Fix refcount leak in of_led_get() + - leds: is31fl319x: Wrap mutex_destroy() for devm_add_action_or_rest() + - leds: simatic-ipc-leds-gpio: Make sure we have the GPIO providing driver + - tools/tracing/rtla: osnoise_hist: use total duration for average calculation + - perf inject: Use perf_data__read() for auxtrace + - perf intel-pt: Do not try to queue auxtrace data on pipe + - perf stat: Hide invalid uncore event output for aggr mode + - perf jevents: Correct bad character encoding + - perf test bpf: Skip test if kernel-debuginfo is not present + - perf tools: Fix auto-complete on aarch64 + - perf stat: Avoid merging/aggregating metric counts twice + - sparc: allow PM configs for sparc32 COMPILE_TEST + - selftests: find echo binary to use -ne options + - selftests/ftrace: Fix bash specific "==" operator + - selftests: use printf instead of echo -ne + - perf record: Fix segfault with --overwrite and --max-size + - printf: fix errname.c list + - perf tests stat_all_metrics: Change true workload to sleep workload for + system wide check + - objtool: add UACCESS exceptions for __tsan_volatile_read/write + - selftests/ftrace: Fix probepoint testcase to ignore __pfx_* symbols + - sysctl: fix proc_dobool() usability + - mfd: rk808: Re-add rk808-clkout to RK818 + - mfd: cs5535: Don't build on UML + - mfd: pcf50633-adc: Fix potential memleak in pcf50633_adc_async_read() + - dmaengine: idxd: Set traffic class values in GRPCFG on DSA 2.0 + - RDMA/erdma: Fix refcount leak in erdma_mmap + - dmaengine: HISI_DMA should depend on ARCH_HISI + - RDMA/hns: Fix refcount leak in hns_roce_mmap + - iio: light: tsl2563: Do not hardcode interrupt trigger type + - usb: gadget: fusb300_udc: free irq on the error path in fusb300_probe() + - i2c: designware: fix i2c_dw_clk_rate() return size to be u32 + - i2c: qcom-geni: change i2c_master_hub to static + - soundwire: cadence: Don't overflow the command FIFOs + - driver core: fix potential null-ptr-deref in device_add() + - kobject: Fix slab-out-of-bounds in fill_kobj_path() + - alpha/boot/tools/objstrip: fix the check for ELF header + - media: uvcvideo: Check for INACTIVE in uvc_ctrl_is_accessible() + - media: uvcvideo: Implement mask for V4L2_CTRL_TYPE_MENU + - media: uvcvideo: Refactor uvc_ctrl_mappings_uvcXX + - media: uvcvideo: Refactor power_line_frequency_controls_limited + - coresight: etm4x: Fix accesses to TRCSEQRSTEVR and TRCSEQSTR + - coresight: cti: Prevent negative values of enable count + - coresight: cti: Add PM runtime call in enable_store + - usb: typec: intel_pmc_mux: Don't leak the ACPI device reference count + - PCI/IOV: Enlarge virtfn sysfs name buffer + - PCI: switchtec: Return -EFAULT for copy_to_user() errors + - PCI: endpoint: pci-epf-vntb: Add epf_ntb_mw_bar_clear() num_mws kernel-doc + - hwtracing: hisi_ptt: Only add the supported devices to the filters list + - tty: serial: fsl_lpuart: disable Rx/Tx DMA in lpuart32_shutdown() + - tty: serial: fsl_lpuart: clear LPUART Status Register in lpuart32_shutdown() + - serial: tegra: Add missing clk_disable_unprepare() in tegra_uart_hw_init() + - Revert "char: pcmcia: cm4000_cs: Replace mdelay with usleep_range in + set_protocol" + - eeprom: idt_89hpesx: Fix error handling in idt_init() + - applicom: Fix PCI device refcount leak in applicom_init() + - firmware: stratix10-svc: add missing gen_pool_destroy() in + stratix10_svc_drv_probe() + - firmware: stratix10-svc: fix error handle while alloc/add device failed + - VMCI: check context->notify_page after call to get_user_pages_fast() to + avoid GPF + - mei: pxp: Use correct macros to initialize uuid_le + - misc/mei/hdcp: Use correct macros to initialize uuid_le + - misc: fastrpc: Fix an error handling path in fastrpc_rpmsg_probe() + - iommu/exynos: Fix error handling in exynos_iommu_init() + - driver core: fix resource leak in device_add() + - driver core: location: Free struct acpi_pld_info *pld before return false + - drivers: base: transport_class: fix possible memory leak + - drivers: base: transport_class: fix resource leak when + transport_add_device() fails + - firmware: dmi-sysfs: Fix null-ptr-deref in dmi_sysfs_register_handle + - selftests: iommu: Fix test_cmd_destroy_access() call in user_copy + - iommufd: Add three missing structures in ucmd_buffer + - fotg210-udc: Add missing completion handler + - dmaengine: dw-edma: Fix missing src/dst address of interleaved xfers + - fpga: microchip-spi: move SPI I/O buffers out of stack + - fpga: microchip-spi: rewrite status polling in a time measurable way + - usb: early: xhci-dbc: Fix a potential out-of-bound memory access + - tty: serial: fsl_lpuart: Fix the wrong RXWATER setting for rx dma case + - RDMA/cxgb4: add null-ptr-check after ip_dev_find() + - usb: musb: mediatek: don't unregister something that wasn't registered + - usb: gadget: configfs: Restrict symlink creation is UDC already binded + - phy: mediatek: remove temporary variable @mask_ + - PCI: mt7621: Delay phy ports initialization + - iommu/vt-d: Set No Execute Enable bit in PASID table entry + - power: supply: remove faulty cooling logic + - RDMA/siw: Fix user page pinning accounting + - RDMA/cxgb4: Fix potential null-ptr-deref in pass_establish() + - usb: max-3421: Fix setting of I/O pins + - RDMA/irdma: Cap MSIX used to online CPUs + 1 + - serial: fsl_lpuart: fix RS485 RTS polariy inverse issue + - tty: serial: imx: disable Ageing Timer interrupt request irq + - driver core: fw_devlink: Add DL_FLAG_CYCLE support to device links + - driver core: fw_devlink: Don't purge child fwnode's consumer links + - driver core: fw_devlink: Allow marking a fwnode link as being part of a + cycle + - driver core: fw_devlink: Consolidate device link flag computation + - driver core: fw_devlink: Improve check for fwnode with no device/driver + - driver core: fw_devlink: Make cycle detection more robust + - mtd: mtdpart: Don't create platform device that'll never probe + - usb: host: fsl-mph-dr-of: reuse device_set_of_node_from_dev + - dmaengine: dw-edma: Fix readq_ch() return value truncation + - PCI: Fix dropping valid root bus resources with .end = zero + - phy: rockchip-typec: fix tcphy_get_mode error case + - PCI: qcom: Fix host-init error handling + - iw_cxgb4: Fix potential NULL dereference in c4iw_fill_res_cm_id_entry() + - iommu: Fix error unwind in iommu_group_alloc() + - iommu/amd: Do not identity map v2 capable device when snp is enabled + - dmaengine: sf-pdma: pdma_desc memory leak fix + - dmaengine: dw-axi-dmac: Do not dereference NULL structure + - dmaengine: ptdma: check for null desc before calling pt_cmd_callback + - iommu/vt-d: Fix error handling in sva enable/disable paths + - iommu/vt-d: Allow to use flush-queue when first level is default + - RDMA/rxe: Cleanup mr_check_range + - RDMA/rxe: Move rxe_map_mr_sg to rxe_mr.c + - RDMA-rxe: Isolate mr code from atomic_reply() + - RDMA-rxe: Isolate mr code from atomic_write_reply() + - RDMA/rxe: Cleanup page variables in rxe_mr.c + - RDMA/rxe: Replace rxe_map and rxe_phys_buf by xarray + - Subject: RDMA/rxe: Handle zero length rdma + - RDMA/mana_ib: Fix a bug when the PF indicates more entries for registering + memory on first packet + - RDMA/rxe: Fix missing memory barriers in rxe_queue.h + - IB/hfi1: Fix math bugs in hfi1_can_pin_pages() + - IB/hfi1: Fix sdma.h tx->num_descs off-by-one errors + - Revert "remoteproc: qcom_q6v5_mss: map/unmap metadata region before/after + use" + - remoteproc: qcom_q6v5_mss: Use a carveout to authenticate modem headers + - media: ti: cal: fix possible memory leak in cal_ctx_create() + - media: platform: ti: Add missing check for devm_regulator_get + - media: imx: imx7-media-csi: fix missing clk_disable_unprepare() in + imx7_csi_init() + - powerpc: Remove linker flag from KBUILD_AFLAGS + - s390/vdso: Drop '-shared' from KBUILD_CFLAGS_64 + - builddeb: clean generated package content + - media: max9286: Fix memleak in max9286_v4l2_register() + - media: ov2740: Fix memleak in ov2740_init_controls() + - media: ov5675: Fix memleak in ov5675_init_controls() + - media: i2c: tc358746: fix missing return assignment + - media: i2c: tc358746: fix ignoring read error in g_register callback + - media: i2c: tc358746: fix possible endianness issue + - media: ov5640: Fix soft reset sequence and timings + - media: ov5640: Handle delays when no reset_gpio set + - media: mc: Get media_device directly from pad + - media: i2c: ov772x: Fix memleak in ov772x_probe() + - media: i2c: imx219: Split common registers from mode tables + - media: i2c: imx219: Fix binning for RAW8 capture + - media: platform: mtk-mdp3: Fix return value check in mdp_probe() + - media: camss: csiphy-3ph: avoid undefined behavior + - media: platform: mtk-mdp3: fix Kconfig dependencies + - media: v4l2-jpeg: correct the skip count in jpeg_parse_app14_data + - media: v4l2-jpeg: ignore the unknown APP14 marker + - media: hantro: Fix JPEG encoder ENUM_FRMSIZE on RK3399 + - media: imx-jpeg: Apply clk_bulk api instead of operating specific clk + - media: amphion: correct the unspecified color space + - media: drivers/media/v4l2-core/v4l2-h264 : add detection of null pointers + - media: rc: Fix use-after-free bugs caused by ene_tx_irqsim() + - media: atomisp: fix videobuf2 Kconfig depenendency + - media: atomisp: Only set default_run_mode on first open of a stream/asd + - media: i2c: ov7670: 0 instead of -EINVAL was returned + - media: usb: siano: Fix use after free bugs caused by do_submit_urb + - media: saa7134: Use video_unregister_device for radio_dev + - rpmsg: glink: Avoid infinite loop on intent for missing channel + - rpmsg: glink: Release driver_override + - ARM: OMAP2+: omap4-common: Fix refcount leak bug + - arm64: dts: qcom: msm8996: Add additional A2NoC clocks + - udf: Define EFSCORRUPTED error code + - context_tracking: Fix noinstr vs KASAN + - exit: Detect and fix irq disabled state in oops + - ARM: dts: exynos: Use Exynos5420 compatible for the MIPI video phy + - fs: Use CHECK_DATA_CORRUPTION() when kernel bugs are detected + - blk-iocost: fix divide by 0 error in calc_lcoefs() + - blk-cgroup: dropping parent refcount after pd_free_fn() is done + - blk-cgroup: synchronize pd_free_fn() from blkg_free_workfn() and + blkcg_deactivate_policy() + - trace/blktrace: fix memory leak with using debugfs_lookup() + - btrfs: scrub: improve tree block error reporting + - arm64: zynqmp: Enable hs termination flag for USB dwc3 controller + - cpuidle, intel_idle: Fix CPUIDLE_FLAG_INIT_XSTATE + - x86/fpu: Don't set TIF_NEED_FPU_LOAD for PF_IO_WORKER threads + - cpuidle: drivers: firmware: psci: Dont instrument suspend code + - cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG + - perf/x86/intel/uncore: Add Meteor Lake support + - wifi: ath9k: Fix use-after-free in ath9k_hif_usb_disconnect() + - wifi: ath11k: fix monitor mode bringup crash + - wifi: brcmfmac: Fix potential stack-out-of-bounds in brcmf_c_preinit_dcmds() + - rcu: Make RCU_LOCKDEP_WARN() avoid early lockdep checks + - rcu: Suppress smp_processor_id() complaint in + synchronize_rcu_expedited_wait() + - srcu: Delegate work to the boot cpu if using SRCU_SIZE_SMALL + - rcu-tasks: Make rude RCU-Tasks work well with CPU hotplug + - rcu-tasks: Handle queue-shrink/callback-enqueue race condition + - wifi: ath11k: debugfs: fix to work with multiple PCI devices + - thermal: intel: Fix unsigned comparison with less than zero + - timers: Prevent union confusion from unexpected restart_syscall() + - x86/bugs: Reset speculation control settings on init + - bpftool: Always disable stack protection for BPF objects + - wifi: brcmfmac: ensure CLM version is null-terminated to prevent stack-out- + of-bounds + - wifi: rtw89: fix assignation of TX BD RAM table + - wifi: mt7601u: fix an integer underflow + - inet: fix fast path in __inet_hash_connect() + - ice: restrict PTP HW clock freq adjustments to 100, 000, 000 PPB + - ice: add missing checks for PF vsi type + - Compiler attributes: GCC cold function alignment workarounds + - ACPI: Don't build ACPICA with '-Os' + - bpf, docs: Fix modulo zero, division by zero, overflow, and underflow + - thermal: intel: intel_pch: Add support for Wellsburg PCH + - clocksource: Suspend the watchdog temporarily when high read latency + detected + - crypto: hisilicon: Wipe entire pool on error + - net: bcmgenet: Add a check for oversized packets + - m68k: Check syscall_trace_enter() return code + - s390/mm,ptdump: avoid Kasan vs Memcpy Real markers swapping + - netfilter: nf_tables: NULL pointer dereference in nf_tables_updobj() + - can: isotp: check CAN address family in isotp_bind() + - gcc-plugins: drop -std=gnu++11 to fix GCC 13 build + - tools/power/x86/intel-speed-select: Add Emerald Rapid quirk + - platform/x86: dell-ddv: Add support for interface version 3 + - wifi: mt76: dma: free rx_head in mt76_dma_rx_cleanup + - ACPI: video: Fix Lenovo Ideapad Z570 DMI match + - net/mlx5: fw_tracer: Fix debug print + - coda: Avoid partial allocation of sig_inputArgs + - uaccess: Add minimum bounds check on kernel buffer size + - s390/idle: mark arch_cpu_idle() noinstr + - time/debug: Fix memory leak with using debugfs_lookup() + - PM: domains: fix memory leak with using debugfs_lookup() + - PM: EM: fix memory leak with using debugfs_lookup() + - Bluetooth: Fix issue with Actions Semi ATS2851 based devices + - Bluetooth: btusb: Add new PID/VID 0489:e0f2 for MT7921 + - Bluetooth: btusb: Add VID:PID 13d3:3529 for Realtek RTL8821CE + - wifi: rtw89: debug: avoid invalid access on RTW89_DBG_SEL_MAC_30 + - hv_netvsc: Check status in SEND_RNDIS_PKT completion message + - s390/kfence: fix page fault reporting + - devlink: Fix TP_STRUCT_entry in trace of devlink health report + - scm: add user copy checks to put_cmsg() + - drm: panel-orientation-quirks: Add quirk for Lenovo Yoga Tab 3 X90F + - drm: panel-orientation-quirks: Add quirk for DynaBook K50 + - drm/amd/display: Reduce expected sdp bandwidth for dcn321 + - drm/amd/display: Revert Reduce delay when sink device not able to ACK 00340h + write + - drm/amd/display: Fix potential null-deref in dm_resume + - drm/omap: dsi: Fix excessive stack usage + - HID: Add Mapping for System Microphone Mute + - drm/tiny: ili9486: Do not assume 8-bit only SPI controllers + - drm/amd/display: Defer DIG FIFO disable after VID stream enable + - drm/radeon: free iio for atombios when driver shutdown + - drm/amd: Avoid BUG() for case of SRIOV missing IP version + - drm/amdkfd: Page aligned memory reserve size + - scsi: lpfc: Fix use-after-free KFENCE violation during sysfs firmware write + - Revert "fbcon: don't lose the console font across generic->chip driver + switch" + - drm/amd: Avoid ASSERT for some message failures + - drm: amd: display: Fix memory leakage + - drm/amd/display: fix mapping to non-allocated address + - HID: uclogic: Add frame type quirk + - HID: uclogic: Add battery quirk + - HID: uclogic: Add support for XP-PEN Deco Pro SW + - HID: uclogic: Add support for XP-PEN Deco Pro MW + - drm/msm/dsi: Add missing check for alloc_ordered_workqueue + - drm: rcar-du: Add quirk for H3 ES1.x pclk workaround + - drm: rcar-du: Fix setting a reserved bit in DPLLCR + - drm/drm_print: correct format problem + - drm/amd/display: Set hvm_enabled flag for S/G mode + - drm/client: Test for connectors before sending hotplug event + - habanalabs: extend fatal messages to contain PCI info + - habanalabs: fix bug in timestamps registration code + - docs/scripts/gdb: add necessary make scripts_gdb step + - drm/msm/dpu: Add DSC hardware blocks to register snapshot + - ASoC: soc-compress: Reposition and add pcm_mutex + - ASoC: kirkwood: Iterate over array indexes instead of using pointer math + - regulator: max77802: Bounds check regulator id against opmode + - regulator: s5m8767: Bounds check id indexing into arrays + - Revert "drm/amdgpu: TA unload messages are not actually sent to psp when + amdgpu is uninstalled" + - drm/amd/display: fix FCLK pstate change underflow + - gfs2: Improve gfs2_make_fs_rw error handling + - hwmon: (coretemp) Simplify platform device handling + - hwmon: (nct6775) Directly call ASUS ACPI WMI method + - hwmon: (nct6775) B650/B660/X670 ASUS boards support + - pinctrl: at91: use devm_kasprintf() to avoid potential leaks + - drm/amd/display: Do not commit pipe when updating DRR + - scsi: snic: Fix memory leak with using debugfs_lookup() + - scsi: ufs: core: Fix device management cmd timeout flow + - HID: logitech-hidpp: Don't restart communication if not necessary + - drm/amd/display: Enable P-state validation checks for DCN314 + - drm: panel-orientation-quirks: Add quirk for Lenovo IdeaPad Duet 3 10IGL5 + - drm/amd/display: Disable HUBP/DPP PG on DCN314 for now + - drm/amd/display: disable SubVP + DRR to prevent underflow + - dm thin: add cond_resched() to various workqueue loops + - dm cache: add cond_resched() to various workqueue loops + - nfsd: zero out pointers after putting nfsd_files on COPY setup error + - nfsd: don't hand out delegation on setuid files being opened for write + - cifs: prevent data race in smb2_reconnect() + - drm/i915/mtl: Correct implementation of Wa_18018781329 + - drm/shmem-helper: Revert accidental non-GPL export + - driver core: fw_devlink: Avoid spurious error message + - wifi: rtl8xxxu: fixing transmisison failure for rtl8192eu + - firmware: coreboot: framebuffer: Ignore reserved pixel color bits + - block: don't allow multiple bios for IOCB_NOWAIT issue + - block: clear bio->bi_bdev when putting a bio back in the cache + - block: be a bit more careful in checking for NULL bdev while polling + - rtc: pm8xxx: fix set-alarm race + - ipmi: ipmb: Fix the MODULE_PARM_DESC associated to 'retry_time_ms' + - ipmi:ssif: resend_msg() cannot fail + - ipmi_ssif: Rename idle state and check + - ipmi:ssif: Add a timer between request retries + - io_uring: Replace 0-length array with flexible array + - io_uring: use user visible tail in io_uring_poll() + - io_uring: handle TIF_NOTIFY_RESUME when checking for task_work + - io_uring: add a conditional reschedule to the IOPOLL cancelation loop + - io_uring: add reschedule point to handle_tw_list() + - io_uring/rsrc: disallow multi-source reg buffers + - io_uring: remove MSG_NOSIGNAL from recvmsg + - io_uring/poll: allow some retries for poll triggering spuriously + - io_uring: fix fget leak when fs don't support nowait buffered read + - s390/extmem: return correct segment type in __segment_load() + - s390: discard .interp section + - s390/kprobes: fix irq mask clobbering on kprobe reenter from post_handler + - s390/kprobes: fix current_kprobe never cleared after kprobes reenter + - KVM: s390: disable migration mode when dirty tracking is disabled + - cifs: improve checking of DFS links over STATUS_OBJECT_NAME_INVALID + - cifs: Fix uninitialized memory read in smb3_qfs_tcon() + - cifs: Fix uninitialized memory reads for oparms.mode + - cifs: fix mount on old smb servers + - cifs: introduce cifs_io_parms in smb2_async_writev() + - cifs: split out smb3_use_rdma_offload() helper + - cifs: don't try to use rdma offload on encrypted connections + - cifs: Check the lease context if we actually got a lease + - cifs: return a single-use cfid if we did not get a lease + - scsi: mpi3mr: Fix missing mrioc->evtack_cmds initialization + - scsi: mpi3mr: Fix issues in mpi3mr_get_all_tgt_info() + - scsi: mpi3mr: Remove unnecessary memcpy() to alltgt_info->dmi + - btrfs: hold block group refcount during async discard + - btrfs: sysfs: update fs features directory asynchronously + - locking/rwsem: Prevent non-first waiter from spinning in down_write() + slowpath + - ksmbd: fix wrong data area length for smb2 lock request + - ksmbd: do not allow the actual frame length to be smaller than the rfc1002 + length + - ksmbd: fix possible memory leak in smb2_lock() + - torture: Fix hang during kthread shutdown phase + - ARM: dts: exynos: correct HDMI phy compatible in Exynos4 + - io_uring: mark task TASK_RUNNING before handling resume/task work + - hfs: fix missing hfs_bnode_get() in __hfs_bnode_create + - fs: hfsplus: fix UAF issue in hfsplus_put_super + - exfat: fix reporting fs error when reading dir beyond EOF + - exfat: fix unexpected EOF while reading dir + - exfat: redefine DIR_DELETED as the bad cluster number + - exfat: fix inode->i_blocks for non-512 byte sector size device + - fs: dlm: start midcomms before scand + - fs: dlm: fix use after free in midcomms commit + - fs: dlm: be sure to call dlm_send_queue_flush() + - fs: dlm: fix race setting stop tx flag + - fs: dlm: don't set stop rx flag after node reset + - fs: dlm: move sending fin message into state change handling + - fs: dlm: send FIN ack back in right cases + - f2fs: fix information leak in f2fs_move_inline_dirents() + - f2fs: retry to update the inode page given data corruption + - f2fs: fix cgroup writeback accounting with fs-layer encryption + - f2fs: fix kernel crash due to null io->bio + - f2fs: Revert "f2fs: truncate blocks in batch in __complete_revoke_list()" + - ocfs2: fix defrag path triggering jbd2 ASSERT + - ocfs2: fix non-auto defrag path not working issue + - fs/cramfs/inode.c: initialize file_ra_state + - selftests/landlock: Skip overlayfs tests when not supported + - selftests/landlock: Test ptrace as much as possible with Yama + - udf: Truncate added extents on failed expansion + - udf: Do not bother merging very long extents + - udf: Do not update file length for failed writes to inline files + - udf: Preserve link count of system files + - udf: Detect system inodes linked into directory hierarchy + - udf: Fix file corruption when appending just after end of preallocated + extent + - md: don't update recovery_cp when curr_resync is ACTIVE + - KVM: Destroy target device if coalesced MMIO unregistration fails + - KVM: VMX: Fix crash due to uninitialized current_vmcs + - KVM: Register /dev/kvm as the _very_ last thing during initialization + - KVM: x86: Purge "highest ISR" cache when updating APICv state + - KVM: x86: Blindly get current x2APIC reg value on "nodecode write" traps + - KVM: x86: Don't inhibit APICv/AVIC on xAPIC ID "change" if APIC is disabled + - KVM: x86: Don't inhibit APICv/AVIC if xAPIC ID mismatch is due to 32-bit ID + - KVM: SVM: Flush the "current" TLB when activating AVIC + - KVM: SVM: Process ICR on AVIC IPI delivery failure due to invalid target + - KVM: SVM: Don't put/load AVIC when setting virtual APIC mode + - KVM: x86: Inject #GP if WRMSR sets reserved bits in APIC Self-IPI + - KVM: x86: Inject #GP on x2APIC WRMSR that sets reserved bits 63:32 + - KVM: SVM: Fix potential overflow in SEV's send|receive_update_data() + - KVM: SVM: hyper-v: placate modpost section mismatch error + - selftests: x86: Fix incorrect kernel headers search path + - x86/virt: Force GIF=1 prior to disabling SVM (for reboot flows) + - x86/crash: Disable virt in core NMI crash handler to avoid double shootdown + - x86/reboot: Disable virtualization in an emergency if SVM is supported + - x86/reboot: Disable SVM, not just VMX, when stopping CPUs + - x86/kprobes: Fix __recover_optprobed_insn check optimizing logic + - x86/kprobes: Fix arch_check_optimized_kprobe check within optimized_kprobe + range + - x86/microcode/amd: Remove load_microcode_amd()'s bsp parameter + - x86/microcode/AMD: Add a @cpu parameter to the reloading functions + - x86/microcode/AMD: Fix mixed steppings support + - x86/speculation: Allow enabling STIBP with legacy IBRS + - Documentation/hw-vuln: Document the interaction between IBRS and STIBP + - virt/sev-guest: Return -EIO if certificate buffer is not large enough + - brd: mark as nowait compatible + - brd: return 0/-error from brd_insert_page() + - brd: check for REQ_NOWAIT and set correct page allocation mask + - ima: fix error handling logic when file measurement failed + - ima: Align ima_file_mmap() parameters with mmap_file LSM hook + - selftests/powerpc: Fix incorrect kernel headers search path + - selftests/ftrace: Fix eprobe syntax test case to check filter support + - selftests: sched: Fix incorrect kernel headers search path + - selftests: core: Fix incorrect kernel headers search path + - selftests: pid_namespace: Fix incorrect kernel headers search path + - selftests: arm64: Fix incorrect kernel headers search path + - selftests: clone3: Fix incorrect kernel headers search path + - selftests: pidfd: Fix incorrect kernel headers search path + - selftests: membarrier: Fix incorrect kernel headers search path + - selftests: kcmp: Fix incorrect kernel headers search path + - selftests: media_tests: Fix incorrect kernel headers search path + - selftests: gpio: Fix incorrect kernel headers search path + - selftests: filesystems: Fix incorrect kernel headers search path + - selftests: user_events: Fix incorrect kernel headers search path + - selftests: ptp: Fix incorrect kernel headers search path + - selftests: sync: Fix incorrect kernel headers search path + - selftests: rseq: Fix incorrect kernel headers search path + - selftests: move_mount_set_group: Fix incorrect kernel headers search path + - selftests: mount_setattr: Fix incorrect kernel headers search path + - selftests: perf_events: Fix incorrect kernel headers search path + - selftests: ipc: Fix incorrect kernel headers search path + - selftests: futex: Fix incorrect kernel headers search path + - selftests: drivers: Fix incorrect kernel headers search path + - selftests: dmabuf-heaps: Fix incorrect kernel headers search path + - selftests: vm: Fix incorrect kernel headers search path + - selftests: seccomp: Fix incorrect kernel headers search path + - irqdomain: Fix association race + - irqdomain: Fix disassociation race + - irqdomain: Look for existing mapping only once + - irqdomain: Drop bogus fwspec-mapping error handling + - irqdomain: Refactor __irq_domain_alloc_irqs() + - irqdomain: Fix mapping-creation race + - irqdomain: Fix domain registration race + - crypto: qat - fix out-of-bounds read + - mm/damon/paddr: fix missing folio_put() + - ALSA: ice1712: Do not left ice->gpio_mutex locked in aureon_add_controls() + - ALSA: hda/realtek: Add quirk for HP EliteDesk 800 G6 Tower PC + - jbd2: fix data missing when reusing bh which is ready to be checkpointed + - ext4: optimize ea_inode block expansion + - ext4: refuse to create ea block when umounted + - cxl/pmem: Fix nvdimm registration races + - Input: exc3000 - properly stop timer on shutdown + - mtd: spi-nor: sfdp: Fix index value for SCCR dwords + - mtd: spi-nor: spansion: Consider reserved bits in CFR5 register + - dm: send just one event on resize, not two + - dm: add cond_resched() to dm_wq_work() + - dm: add cond_resched() to dm_wq_requeue_work() + - wifi: rtw88: use RTW_FLAG_POWERON flag to prevent to power on/off twice + - wifi: rtl8xxxu: Use a longer retry limit of 48 + - wifi: ath11k: allow system suspend to survive ath11k + - wifi: cfg80211: Fix use after free for wext + - wifi: cfg80211: Set SSID if it is not already set + - cpuidle: add ARCH_SUSPEND_POSSIBLE dependencies + - qede: fix interrupt coalescing configuration + - thermal: intel: powerclamp: Fix cur_state for multi package system + - dm flakey: fix logic when corrupting a bio + - dm cache: free background tracker's queued work in btracker_destroy + - dm flakey: don't corrupt the zero page + - dm flakey: fix a bug with 32-bit highmem systems + - hwmon: (peci/cputemp) Fix off-by-one in coretemp_label allocation + - hwmon: (nct6775) Fix incorrect parenthesization in nct6775_write_fan_div() + - spi: intel: Check number of chip selects after reading the descriptor + - ARM: dts: qcom: sdx65: Add Qcom SMMU-500 as the fallback for IOMMU node + - ARM: dts: qcom: sdx55: Add Qcom SMMU-500 as the fallback for IOMMU node + - ARM: dts: exynos: correct TMU phandle in Exynos4210 + - ARM: dts: exynos: correct TMU phandle in Exynos4 + - ARM: dts: exynos: correct TMU phandle in Odroid XU3 family + - ARM: dts: exynos: correct TMU phandle in Exynos5250 + - ARM: dts: exynos: correct TMU phandle in Odroid XU + - ARM: dts: exynos: correct TMU phandle in Odroid HC1 + - arm64: acpi: Fix possible memory leak of ffh_ctxt + - arm64: mm: hugetlb: Disable HUGETLB_PAGE_OPTIMIZE_VMEMMAP + - arm64: Reset KASAN tag in copy_highpage with HW tags only + - fuse: add inode/permission checks to fileattr_get/fileattr_set + - rbd: avoid use-after-free in do_rbd_add() when rbd_dev_create() fails + - ceph: update the time stamps and try to drop the suid/sgid + - regulator: core: Use ktime_get_boottime() to determine how long a regulator + was off + - panic: fix the panic_print NMI backtrace setting + - mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON + - genirq/msi, platform-msi: Ensure that MSI descriptors are unreferenced + - genirq/msi: Take the per-device MSI lock before validating the control + structure + - spi: spi-sn-f-ospi: fix duplicate flag while assigning to mode_bits + - alpha: fix FEN fault handling + - dax/kmem: Fix leak of memory-hotplug resources + - mips: fix syscall_get_nr + - media: ipu3-cio2: Fix PM runtime usage_count in driver unbind + - remoteproc/mtk_scp: Move clk ops outside send_lock + - vfio: Fix NULL pointer dereference caused by uninitialized group->iommufd + - docs: gdbmacros: print newest record + - mm: memcontrol: deprecate charge moving + - mm/thp: check and bail out if page in deferred queue already + - ktest.pl: Give back console on Ctrt^C on monitor + - kprobes: Fix to handle forcibly unoptimized kprobes on freeing_list + - ktest.pl: Fix missing "end_monitor" when machine check fails + - ktest.pl: Add RUN_TIMEOUT option with default unlimited + - memory tier: release the new_memtier in find_create_memory_tier() + - ring-buffer: Handle race between rb_move_tail and rb_check_pages + - tools/bootconfig: fix single & used for logical condition + - tracing/eprobe: Fix to add filter on eprobe description in README file + - iommu/amd: Add a length limitation for the ivrs_acpihid command-line + parameter + - scsi: aacraid: Allocate cmd_priv with scsicmd + - scsi: qla2xxx: Fix link failure in NPIV environment + - scsi: qla2xxx: Check if port is online before sending ELS + - scsi: qla2xxx: Fix DMA-API call trace on NVMe LS requests + - scsi: qla2xxx: Remove unintended flag clearing + - scsi: qla2xxx: Fix erroneous link down + - scsi: qla2xxx: Remove increment of interface err cnt + - scsi: ses: Don't attach if enclosure has no components + - scsi: ses: Fix slab-out-of-bounds in ses_enclosure_data_process() + - scsi: ses: Fix possible addl_desc_ptr out-of-bounds accesses + - scsi: ses: Fix possible desc_ptr out-of-bounds accesses + - scsi: ses: Fix slab-out-of-bounds in ses_intf_remove() + - RISC-V: add a spin_shadow_stack declaration + - riscv: Avoid enabling interrupts in die() + - riscv: mm: fix regression due to update_mmu_cache change + - riscv: jump_label: Fixup unaligned arch_static_branch function + - riscv: ftrace: Fixup panic by disabling preemption + - riscv, mm: Perform BPF exhandler fixup on page fault + - riscv: ftrace: Remove wasted nops for !RISCV_ISA_C + - riscv: ftrace: Reduce the detour code size to half + - MIPS: DTS: CI20: fix otg power gpio + - PCI/PM: Observe reset delay irrespective of bridge_d3 + - PCI: Unify delay handling for reset and resume + - PCI: hotplug: Allow marking devices as disconnected during bind/unbind + - PCI: Avoid FLR for AMD FCH AHCI adapters + - PCI/DPC: Await readiness of secondary bus after reset + - bus: mhi: ep: Only send -ENOTCONN status if client driver is available + - bus: mhi: ep: Move chan->lock to the start of processing queued ch ring + - bus: mhi: ep: Save channel state locally during suspend and resume + - iommufd: Make sure to zero vfio_iommu_type1_info before copying to user + - iommufd: Do not add the same hwpt to the ioas->hwpt_list twice + - iommu/vt-d: Avoid superfluous IOTLB tracking in lazy mode + - iommu/vt-d: Fix PASID directory pointer coherency + - vfio/type1: exclude mdevs from VFIO_UPDATE_VADDR + - vfio/type1: prevent underflow of locked_vm via exec() + - vfio/type1: track locked_vm per dma + - vfio/type1: restore locked_vm + - drm/amd: Fix initialization for nbio 7.5.1 + - drm/i915/quirks: Add inverted backlight quirk for HP 14-r206nv + - drm/radeon: Fix eDP for single-display iMac11,2 + - drm/i915: Don't use stolen memory for ring buffers with LLC + - drm/i915: Don't use BAR mappings for ring buffers with LLC + - drm/gud: Fix UBSAN warning + - drm/edid: fix AVI infoframe aspect ratio handling + - drm/edid: fix parsing of 3D modes from HDMI VSDB + - qede: avoid uninitialized entries in coal_entry array + - brd: use radix_tree_maybe_preload instead of radix_tree_preload + - net: avoid double iput when sock_alloc_file fails + - Linux 6.2.3 + + * Miscellaneous Ubuntu changes + - [Config] update annotations after applying 6.2.3 stable patches + - [Config] update annotations after applying 6.2.6 stable patches + + -- Andrea Righi Tue, 14 Mar 2023 16:43:44 +0100 + +linux (6.2.0-16.16) lunar; urgency=medium + + * lunar/linux: 6.2.0-16.16 -proposed tracker (LP: #2009914) + + * linux-libc-dev is no longer multi-arch safe (LP: #2009355) + - Revert "UBUNTU: [Packaging] install headers to debian/linux-libc-dev + directly" + + * linux: CONFIG_SERIAL_8250_MID=y (LP: #2009283) + - [Config] enable CONFIG_SERIAL_8250_MID=y + + * cpufreq: intel_pstate: Update Balance performance EPP for Sapphire Rapids + (LP: #2008519) + - cpufreq: intel_pstate: Adjust balance_performance EPP for Sapphire Rapids + + -- Andrea Righi Fri, 10 Mar 2023 18:34:28 +0100 + +linux (6.2.0-15.15) lunar; urgency=medium + + * Miscellaneous Ubuntu changes + - [Packaging] annotations: document annotations headers + + -- Andrea Righi Fri, 10 Mar 2023 07:36:59 +0100 + +linux (6.2.0-14.14) lunar; urgency=medium + + * lunar/linux: 6.2.0-14.14 -proposed tracker (LP: #2009856) + + * Miscellaneous Ubuntu changes + - [Packaging] rust: add rust build dependencies to all arches + - [Packaging] Support skipped dkms modules + - [Packaging] actually enforce set -e in dkms-build--nvidia-N + - [Packaging] Preserve the correct log file variable value + - [Packaging] update getabis + + -- Andrea Righi Thu, 09 Mar 2023 16:40:36 +0100 + +linux (6.2.0-13.13) lunar; urgency=medium + + * lunar/linux: 6.2.0-13.13 -proposed tracker (LP: #2009704) + + * Packaging resync (LP: #1786013) + - debian/dkms-versions -- update from kernel-versions (main/master) + + * mt7921: add support of MTFG table (LP: #2009642) + - wifi: mt76: mt7921: add support to update fw capability with MTFG table + + -- Andrea Righi Wed, 08 Mar 2023 14:40:25 +0100 + +linux (6.2.0-12.12) lunar; urgency=medium + + * lunar/linux: 6.2.0-12.12 -proposed tracker (LP: #2009698) + + * Miscellaneous Ubuntu changes + - SAUCE: enforce rust availability only on x86_64 + - [Config] update CONFIG_RUST_IS_AVAILABLE + + -- Andrea Righi Wed, 08 Mar 2023 12:50:15 +0100 + +linux (6.2.0-11.11) lunar; urgency=medium + + * lunar/linux: 6.2.0-11.11 -proposed tracker (LP: #2009697) + + * Miscellaneous Ubuntu changes + - [Packaging] do not stop the build if rust is not available + + -- Andrea Righi Wed, 08 Mar 2023 12:24:55 +0100 + +linux (6.2.0-10.10) lunar; urgency=medium + + * lunar/linux: 6.2.0-10.10 -proposed tracker (LP: #2009673) + + * Packaging resync (LP: #1786013) + - debian/dkms-versions -- update from kernel-versions (main/master) + + * enable Rust support in the kernel (LP: #2007654) + - [Packaging] propagate makefile variables to kernelconfig + - SAUCE: rust: fix regexp in scripts/is_rust_module.sh + - SAUCE: scripts: rust: drop is_rust_module.sh + - SAUCE: rust: allow to use INIT_STACK_ALL_ZERO + - SAUCE: scripts: Exclude Rust CUs with pahole + - SAUCE: modpost: support arbitrary symbol length in modversion + - SAUCE: allows to enable Rust with modversions + - SAUCE: rust: properly detect the version of libclang used by bindgen + - [Packaging] rust: add the proper make flags to enable rust support + - [Packaging] add rust dependencies + - [Packaging] bpftool: always use vmlinux to generate headers + - [Packaging] run rustavailable target as debugging before build + - [Config] enable Rust support + + * Fail to output sound to external monitor which connects via docking station + (LP: #2009024) + - [Config] Enable CONFIG_SND_HDA_INTEL_HDMI_SILENT_STREAM + + * Miscellaneous Ubuntu changes + - SAUCE: Makefile: replace rsync with tar + + -- Andrea Righi Wed, 08 Mar 2023 12:01:56 +0100 + +linux (6.2.0-1.1) lunar; urgency=medium + + * lunar/linux: 6.2.0-1.1 -proposed tracker (LP: #2009621) + + * Packaging resync (LP: #1786013) + - [Packaging] update variants + - debian/dkms-versions -- update from kernel-versions (main/master) + + * kinetic: apply new apparmor and LSM stacking patch set (LP: #1989983) + - SAUCE: apparmor: Add fine grained mediation of posix mqueues + - SAUCE: apparmor: add user namespace creation mediation + + * Lunar update: v6.2.2 upstream stable release (LP: #2009358) + - ALSA: hda: cs35l41: Correct error condition handling + - crypto: arm64/sm4-gcm - Fix possible crash in GCM cryption + - bpf: bpf_fib_lookup should not return neigh in NUD_FAILED state + - vc_screen: don't clobber return value in vcs_read + - drm/amd/display: Move DCN314 DOMAIN power control to DMCUB + - drm/amd/display: Properly reuse completion structure + - scripts/tags.sh: fix incompatibility with PCRE2 + - wifi: rtw88: usb: Set qsel correctly + - wifi: rtw88: usb: send Zero length packets if necessary + - wifi: rtw88: usb: drop now unnecessary URB size check + - usb: dwc3: pci: add support for the Intel Meteor Lake-M + - USB: serial: option: add support for VW/Skoda "Carstick LTE" + - usb: gadget: u_serial: Add null pointer check in gserial_resume + - arm64: dts: uniphier: Fix property name in PXs3 USB node + - usb: typec: pd: Remove usb_suspend_supported sysfs from sink PDO + - USB: core: Don't hold device lock while reading the "descriptors" sysfs file + - Linux 6.2.2 + + * Lunar update: v6.2.1 upstream stable release (LP: #2009127) + - uaccess: Add speculation barrier to copy_from_user() + - x86/alternatives: Introduce int3_emulate_jcc() + - x86/alternatives: Teach text_poke_bp() to patch Jcc.d32 instructions + - x86/static_call: Add support for Jcc tail-calls + - HID: mcp-2221: prevent UAF in delayed work + - wifi: mwifiex: Add missing compatible string for SD8787 + - audit: update the mailing list in MAINTAINERS + - platform/x86/amd/pmf: Add depends on CONFIG_POWER_SUPPLY + - platform/x86: nvidia-wmi-ec-backlight: Add force module parameter + - ext4: Fix function prototype mismatch for ext4_feat_ktype + - randstruct: disable Clang 15 support + - bpf: add missing header file include + - Linux 6.2.1 + + * Fix mediatek wifi driver crash when loading wrong SAR table (LP: #2009118) + - wifi: mt76: mt7921: fix error code of return in mt7921_acpi_read + + * overlayfs mounts as R/O over idmapped mount (LP: #2009065) + - SAUCE: overlayfs: handle idmapped mounts in ovl_do_(set|remove)xattr + + * RaptorLake: Fix the Screen is shaking by onboard HDMI port in mirror mode + (LP: #1993561) + - drm/i915/display: Drop check for doublescan mode in modevalid + - drm/i915/display: Prune Interlace modes for Display >=12 + + * screen flicker after PSR2 enabled (LP: #2007516) + - SAUCE: drm/i915/display/psr: Disable PSR2 sel fetch on panel SHP 5457 + + * [23.04 FEAT] Support for new IBM Z Hardware (IBM z16) - Reset DAT-Protection + facility support (LP: #1982378) + - s390/mm: add support for RDP (Reset DAT-Protection) + + * [23.04 FEAT] zcrypt DD: AP command filtering (LP: #2003637) + - s390/zcrypt: introduce ctfm field in struct CPRBX + + * rtcpie in timers from ubuntu_kernel_selftests randomly failing + (LP: #1814234) + - SAUCE: selftest: rtcpie: Force passing unreliable subtest + + * [23.04 FEAT] Support for List-Directed IPL and re-IPL from ECKD DASD + (LP: #2003394) + - s390/ipl: add DEFINE_GENERIC_LOADPARM() + - s390/ipl: add loadparm parameter to eckd ipl/reipl data + + * Miscellaneous Ubuntu changes + - SAUCE: drm/i915/sseu: fix max_subslices array-index-out-of-bounds access + - SAUCE: mtd: spi-nor: Fix shift-out-of-bounds in spi_nor_set_erase_type + - SAUCE: Revert "fbdev: Make registered_fb[] private to fbmem.c" + - [Packaging] disable signing for ppc64el + - [Config] define CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS + - SAUCE: Revert "arm64/fpsimd: Make kernel_neon_ API _GPL" + + -- Andrea Righi Tue, 07 Mar 2023 18:45:31 +0100 + +linux (6.2.0-0.0) lunar; urgency=medium + + * Empty entry + + -- Andrea Righi Fri, 03 Mar 2023 08:42:43 +0100 + +linux-unstable (6.2.0-10.10) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-10.10 -proposed tracker (LP: #2007818) + + * Built-in camera device dies after runtime suspended (LP: #2007530) + - SAUCE: usb: xhci: Workaround for runpm issue on AMD xHC + + * Miscellaneous Ubuntu changes + - [Config] update annotations after rebase to v6.2 + + [ Upstream Kernel Changes ] + + * Rebase to v6.2 + + -- Andrea Righi Mon, 20 Feb 2023 10:36:20 +0100 + +linux-unstable (6.2.0-9.9) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-9.9 -proposed tracker (LP: #2007069) + + * Move kernel ADT tests to python3 (LP: #2004429) + - [Debian] Use a python3 compatable kernel-testing repo + + * Mediatek FM350-GL wwan module failed to init: Invalid device status 0x1 + (LP: #2002089) + - SAUCE: Revert "net: wwan: t7xx: Add AP CLDMA" + - SAUCE: net: wwan: t7xx: Add AP CLDMA + - SAUCE: net: wwan: t7xx: Infrastructure for early port configuration + - SAUCE: net: wwan: t7xx: PCIe reset rescan + - SAUCE: net: wwan: t7xx: Enable devlink based fw flashing and coredump + collection + - SAUCE: net: wwan: t7xx: Devlink documentation + + * LXD containers using shiftfs on ZFS or TMPFS broken on 5.15.0-48.54 + (LP: #1990849) + - SAUCE: shiftfs: fix -EOVERFLOW inside the container + + * Miscellaneous Ubuntu changes + - [Packaging] annotations: do not drop undefined configs in derivatives + - [Packaging]: annotations: fix _remove_entry() logic + - [Packaging] rsync no longer available on lunar + - [Packaging] annotations: Handle single-line annoation rules + - [Packaging] annotations: Preserve single-line annotation rules + - [Packaging] annotations: Fix linter errors + - [Packaging] annotations: Clean up policy writes + - [Packaging] annotations: Handle tabs in annotations file + - [Packaging] annotations: Fail on invalid lines + - [Packaging] annotations: Write out annotations with notes first + - [Packaging] annotations: Check validity of FLAVOUR_DEP + - [Config] update annotations to split configs with/without notes + - [Packaging] annotations: various code cleanups + - [Config] update annotations after rebase to v6.2-rc8 + + * Miscellaneous upstream changes + - selftests/net: mv bpf/nat6to4.c to net folder + + [ Upstream Kernel Changes ] + + * Rebase to v6.1-rc8 + + -- Andrea Righi Mon, 13 Feb 2023 09:32:18 +0100 + +linux-unstable (6.2.0-8.8) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-8.8 -proposed tracker (LP: #2004229) + + * Miscellaneous Ubuntu changes + - [Packaging] re-enable signing for ppc64el and s390x + - SAUCE: s390/decompressor: specify __decompress() buf len to avoid overflow + + -- Andrea Righi Tue, 31 Jan 2023 08:21:21 +0100 + +linux-unstable (6.2.0-7.7) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-7.7 -proposed tracker (LP: #2004142) + + -- Andrea Righi Mon, 30 Jan 2023 10:23:15 +0100 + +linux-unstable (6.2.0-6.6) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-6.6 -proposed tracker (LP: #2004138) + + * Miscellaneous Ubuntu changes + - [Packaging] debian/rules: Bring back 'editconfigs' + - [Packaging] debian/rules: 1-maintainer.mk -- Use make's if-else + - [Packaging] annotations: make sure to always drop undefined configs + - [Config] update annotations after rebase to v6.2-rc6 + + [ Upstream Kernel Changes ] + + * Rebase to v6.1-rc6 + + -- Andrea Righi Mon, 30 Jan 2023 09:20:26 +0100 + +linux-unstable (6.2.0-5.5) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-5.5 -proposed tracker (LP: #2003682) + + * [23.04] Kernel 6.2 does not boot on s390x (LP: #2003348) + - SAUCE Revert "zstd: import usptream v1.5.2" + - SAUCE: Revert "zstd: Move zstd-common module exports to + zstd_common_module.c" + + * Revoke & rotate to new signing key (LP: #2002812) + - [Packaging] Revoke and rotate to new signing key + + * CVE-2023-0179 + - netfilter: nft_payload: incorrect arithmetics when fetching VLAN header bits + + * [23.04] net/smc: Alibaba patches about tunable buffer sizes may cause errors + and need to be removed (kernel 6.2) (LP: #2003547) + - SAUCE: Revert "net/smc: Unbind r/w buffer size from clcsock and make them + tunable" + - SAUCE: Revert "net/smc: Introduce a specific sysctl for TEST_LINK time" + + * 5.15 stuck at boot on c4.large (LP: #1956780) + - SAUCE: Revert "PCI/MSI: Mask MSI-X vectors only on success" + + * Miscellaneous Ubuntu changes + - [Packaging] scripts/misc/kernelconfig: Disable config checks for mainline + builds + - [Packaging] annotations: add CONFIG_GCC_VERSION to the list of ignored + configs + + -- Andrea Righi Mon, 23 Jan 2023 08:20:26 +0100 + +linux-unstable (6.2.0-4.4) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-4.4 -proposed tracker (LP: #2003051) + + * Miscellaneous Ubuntu changes + - [Packaging] add python3 as a build dependency + - [Packaging] scripts/misc/kernelconfig: Rewrite + + -- Andrea Righi Tue, 17 Jan 2023 09:18:54 +0100 + +linux-unstable (6.2.0-3.3) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-3.3 -proposed tracker (LP: #2002939) + + * Enable kernel config for P2PDMA (LP: #1987394) + - [Config] Enable CONFIG_HSA_AMD_P2P + + * Miscellaneous Ubuntu changes + - SAUCE: (no-up) Remove obj- += foo.o hack + - SAUCE: (no-up) re-add ubuntu/ directory + - [Config] enable EFI handover protocol + - [Packaging] Fix module-check error when modules are compressed + - SAUCE: (no-up) do not remove debian directory by 'make mrproper' + - [Packaging] debian/rules: Drop AUTOBUILD + - [Packaging] debian/rules: Drop NOKERNLOG and PRINTSHAS env variables + - [Packaging] debian/rules: Replace skip variables with skip_checks + - [Packaging] checks/retpoline-check: Make 'skipretpoline' argument optional + - [Packaging] checks/module-signature-check: Add 'skip_checks' argument + - [Packaging] debian/rules: Rename 'skip_dbg' to 'do_dbgsym_package' + - [Packaging] debian/rules: Rename 'skip_checks' to 'do_skip_checks' + - [Packaging] debian/rules: Rename 'full_build' to 'do_full_build' + - [Packaging] debian/rules: Fix PPA debug package builds + - [Packaging] debian/rules: Remove debug package install directory earlier + - [Packaging] debian/rules: Remove unnecessary 'lockme_' variables + - [Packaging] debian/rules: Remove unused target 'diffupstream' + - [Packaging] debian/rules: Mark PHONY targets individually + - [Packaging] debian/rules: Clean up 'help' target output + - [Packaging] debian/rules: Clean up 'printenv' target output + - [Packaging] debian/rules: Add missing 'do_' variables to 'printenv' + - [Config] update annotations after rebase to v6.2-rc4 + + [ Upstream Kernel Changes ] + + * Rebase to v6.1-rc4 + + -- Andrea Righi Mon, 16 Jan 2023 16:01:40 +0100 + +linux-unstable (6.2.0-2.2) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-2.2 -proposed tracker (LP: #2001892) + + * Soundwire support for the Intel RPL Gen 0C40/0C11 platforms (LP: #2000030) + - SAUCE: ASoC: Intel: soc-acpi: add configuration for variant of 0C40 product + - SAUCE: ASoC: Intel: soc-acpi: add configuration for variant of 0C11 product + + * Miscellaneous Ubuntu changes + - [Config] update toolchain version in annotations + + * Miscellaneous upstream changes + - Revert "UBUNTU: [Packaging] Support skipped dkms modules" + + [ Upstream Kernel Changes ] + + * Rebase to v6.1-rc2 + + -- Andrea Righi Thu, 05 Jan 2023 09:19:55 +0100 + +linux-unstable (6.2.0-1.1) lunar; urgency=medium + + * lunar/linux-unstable: 6.2.0-1.1 -proposed tracker (LP: #2000904) + + * Packaging resync (LP: #1786013) + - [Packaging] update variants + + * Miscellaneous Ubuntu changes + - [Packaging] annotations: remove configs that are undefined across all + arches/flavours + - SAUCE: Revert "apparmor: make __aa_path_perm() static" + - [Packaging] abi-check: ignore failures when abi check is skipped + - [Packaging] temporarily disable zfs dkms + - [Config] update annotations after rebase to 6.2-rc1 + + [ Upstream Kernel Changes ] + + * Rebase to v6.1-rc1 + + -- Andrea Righi Wed, 04 Jan 2023 12:08:32 +0100 + +linux-unstable (6.2.0-0.0) lunar; urgency=medium + + * Empty entry + + -- Andrea Righi Sun, 01 Jan 2023 10:16:00 +0100 + +linux (6.1.0-11.11) lunar; urgency=medium + + * lunar/linux: 6.1.0-11.11 -proposed tracker (LP: #2000704) + + * Packaging resync (LP: #1786013) + - [Packaging] update helper scripts + + * Lunar update: v6.1.1 upstream stable release (LP: #2000706) + - x86/vdso: Conditionally export __vdso_sgx_enter_enclave() + - libbpf: Fix uninitialized warning in btf_dump_dump_type_data + - PCI: mt7621: Add sentinel to quirks table + - mips: ralink: mt7621: define MT7621_SYSC_BASE with __iomem + - mips: ralink: mt7621: soc queries and tests as functions + - mips: ralink: mt7621: do not use kzalloc too early + - irqchip/ls-extirq: Fix endianness detection + - udf: Discard preallocation before extending file with a hole + - udf: Fix preallocation discarding at indirect extent boundary + - udf: Do not bother looking for prealloc extents if i_lenExtents matches + i_size + - udf: Fix extending file within last block + - usb: gadget: uvc: Prevent buffer overflow in setup handler + - USB: serial: option: add Quectel EM05-G modem + - USB: serial: cp210x: add Kamstrup RF sniffer PIDs + - USB: serial: f81232: fix division by zero on line-speed change + - USB: serial: f81534: fix division by zero on line-speed change + - xhci: Apply XHCI_RESET_TO_DEFAULT quirk to ADL-N + - staging: r8188eu: fix led register settings + - igb: Initialize mailbox message for VF reset + - usb: typec: ucsi: Resume in separate work + - usb: dwc3: pci: Update PCIe device ID for USB3 controller on CPU sub-system + for Raptor Lake + - cifs: fix oops during encryption + - KEYS: encrypted: fix key instantiation with user-provided data + - Linux 6.1.1 + + * Expose built-in trusted and revoked certificates (LP: #1996892) + - [Packaging] Expose built-in trusted and revoked certificates + + * Fix System cannot detect bluetooth after running suspend stress test + (LP: #1998727) + - wifi: rtw88: 8821c: enable BT device recovery mechanism + + * Gnome doesn't run smooth when performing normal usage with RPL-P CPU + (LP: #1998419) + - drm/i915/rpl-p: Add stepping info + + * Mute/mic LEDs no function on a HP platfrom (LP: #1998882) + - ALSA: hda/realtek: fix mute/micmute LEDs for a HP ProBook + + * Add additional Mediatek MT7922 BT device ID (LP: #1998885) + - Bluetooth: btusb: Add a new VID/PID 0489/e0f2 for MT7922 + + * Support Icicle Kit reference design v2022.10 (LP: #1993148) + - SAUCE: riscv: dts: microchip: Disable PCIe on the Icicle Kit + + * Add iommu passthrough quirk for Intel IPU6 on RaptorLake (LP: #1989041) + - SAUCE: iommu: intel-ipu: use IOMMU passthrough mode for Intel IPUs on Raptor + Lake + + * Enable Intel FM350 wwan CCCI driver port logging (LP: #1997686) + - net: wwan: t7xx: use union to group port type specific data + - net: wwan: t7xx: Add port for modem logging + + * TEE Support for CCP driver (LP: #1991608) + - crypto: ccp - Add support for TEE for PCI ID 0x14CA + + * Kinetic update: v5.19.17 upstream stable release (LP: #1994179) + - Revert "fs: check FMODE_LSEEK to control internal pipe splicing" + - kbuild: Add skip_encoding_btf_enum64 option to pahole + + * Kinetic update: v5.19.15 upstream stable release (LP: #1994078) + - Revert "clk: ti: Stop using legacy clkctrl names for omap4 and 5" + + * support independent clock and LED GPIOs for Intel IPU6 platforms + (LP: #1989046) + - SAUCE: platform/x86: int3472: support independent clock and LED GPIOs + + * Kernel livepatch support for for s390x (LP: #1639924) + - [Config] Enable EXPOLINE_EXTERN on s390x + + * Kinetic update: v5.19.7 upstream stable release (LP: #1988733) + - Revert "PCI/portdrv: Don't disable AER reporting in + get_port_device_capability()" + + * Kinetic update: v5.19.3 upstream stable release (LP: #1987345) + - Revert "mm: kfence: apply kmemleak_ignore_phys on early allocated pool" + + * Fix non-working e1000e device after resume (LP: #1951861) + - SAUCE: Revert "e1000e: Add polling mechanism to indicate CSME DPG exit" + + * Add additional Mediatek MT7921 WiFi/BT device IDs (LP: #1937004) + - SAUCE: Bluetooth: btusb: Add support for Foxconn Mediatek Chip + + * Fix system sleep on TGL systems with Intel ME (LP: #1919321) + - SAUCE: PCI: Serialize TGL e1000e PM ops + + * Fix broken e1000e device after S3 (LP: #1897755) + - SAUCE: e1000e: Increase polling timeout on MDIC ready bit + + * Fix unusable USB hub on Dell TB16 after S3 (LP: #1855312) + - SAUCE: USB: core: Make port power cycle a seperate helper function + - SAUCE: USB: core: Attempt power cycle port when it's in eSS.Disabled state + + * Set explicit CC in the headers package (LP: #1999750) + - [Packaging] Set explicit CC in the headers package + + * commit cf58599cded35cf4affed1e659c0e2c742d3fda7 seems to be missing in + kinetic master to remove "hio" reference from Makefile (LP: #1999556) + - SAUCE: remove leftover reference to ubuntu/hio driver + + * Miscellaneous Ubuntu changes + - [Packaging] kernelconfig: always complete all config checks + - [Packaging] annotations: unify same rule across all flavour within the same + arch + - [Config] annotations: compact annotations file + - [Config] disable EFI_ZBOOT + - SAUCE: input: i8042: fix section mismatch warning + - debian/dkms-versions -- re-enable zfs + - [Packaging] old-kernelconfig: update config-check path + - [Packaging] update getabis + - [Packaging] update Ubuntu.md + + * Miscellaneous upstream changes + - Revert "drm/i915/opregion: check port number bounds for SWSCI display power + state" + + -- Andrea Righi Fri, 30 Dec 2022 11:23:16 +0100 + +linux (6.1.0-10.10) lunar; urgency=medium + + * lunar/linux: 6.1.0-10.10 -proposed tracker (LP: #1999569) + + * Soundwire support for the Intel RPL Gen platforms (LP: #1997944) + - ASoC: Intel: sof_sdw: Add support for SKU 0C10 product + - ASoC: Intel: soc-acpi: add SKU 0C10 SoundWire configuration + - ASoC: Intel: sof_sdw: Add support for SKU 0C40 product + - ASoC: Intel: soc-acpi: add SKU 0C40 SoundWire configuration + - ASoC: Intel: sof_sdw: Add support for SKU 0C4F product + - ASoC: rt1318: Add RT1318 SDCA vendor-specific driver + - ASoC: intel: sof_sdw: add rt1318 codec support. + - ASoC: Intel: sof_sdw: Add support for SKU 0C11 product + - ASoC: Intel: soc-acpi: add SKU 0C11 SoundWire configuration + - SAUCE: ASoC: Intel: soc-acpi: update codec addr on 0C11/0C4F product + - [Config] enable CONFIG_SND_SOC_RT1318_SDW + + * Virtual GPU driver packaging regression (LP: #1996112) + - [Packaging] Reintroduce VM DRM drivers into modules + + -- Andrea Righi Tue, 13 Dec 2022 22:14:08 +0100 + +linux (6.1.0-9.9) lunar; urgency=medium + + * Empty entry (ABI bump) + + -- Andrea Righi Tue, 13 Dec 2022 21:31:08 +0100 + +linux (6.1.0-3.3) lunar; urgency=medium + + * lunar/linux: 6.1.0-3.3 -proposed tracker (LP: #1999534) + + * [DEP-8] Run ADT regression suite for lowlatency kernels Jammy and later + (LP: #1999528) + - [DEP-8] Fix regression suite to run on lowlatency + + * Miscellaneous Ubuntu changes + - [Packaging] annotations: do not add constraints on toolchain versions + + -- Andrea Righi Tue, 13 Dec 2022 16:45:59 +0100 + +linux (6.1.0-2.2) lunar; urgency=medium + + * lunar/linux: 6.1.0-2.2 -proposed tracker (LP: #1999411) + + * Miscellaneous Ubuntu changes + - [Packaging] annotations: do not enforce toolchain versions + + -- Andrea Righi Mon, 12 Dec 2022 17:05:59 +0100 + +linux (6.1.0-1.1) lunar; urgency=medium + + * lunar/linux: 6.1.0-1.1 -proposed tracker (LP: #1999373) + + * Packaging resync (LP: #1786013) + - [Packaging] update variants + + * Miscellaneous Ubuntu changes + - [Packaging] annotations: set and delete configs from command line + - [Packaging] migrateconfigs: ignore README.rst if it doesn't exist + - [Packaging] migrate-annotations: properly determine arches in derivatives + - [Packaging] annotations: allow to set note to config options directly + - [Packaging] annotations: assume --query as default command + - [Packaging] annotations: allow to query using CONFIG_" +[Unit] +Description=Hyper-V KVP Protocol Daemon +ConditionVirtualization=microsoft +ConditionKernelCommandLine=!snapd_recovery_mode +DefaultDependencies=no +BindsTo=sys-devices-virtual-misc-vmbus\x21hv_kvp.device +After=sys-devices-virtual-misc-vmbus\x21hv_kvp.device systemd-remount-fs.service +Before=shutdown.target cloud-init-local.service walinuxagent.service +Conflicts=shutdown.target +RequiresMountsFor=/var/lib/hyperv + +[Service] +ExecStart=/usr/sbin/hv_kvp_daemon -n + +[Install] +WantedBy=multi-user.target diff --git a/debian/linux-cloud-tools-common.hv-kvp-daemon.udev b/debian/linux-cloud-tools-common.hv-kvp-daemon.udev new file mode 100644 index 0000000000000..0c648f54d4c49 --- /dev/null +++ b/debian/linux-cloud-tools-common.hv-kvp-daemon.udev @@ -0,0 +1 @@ +SUBSYSTEM=="misc", KERNEL=="vmbus/hv_kvp", TAG+="systemd", ENV{SYSTEMD_WANTS}+="hv-kvp-daemon.service" diff --git a/debian/linux-cloud-tools-common.hv-kvp-daemon.upstart b/debian/linux-cloud-tools-common.hv-kvp-daemon.upstart new file mode 100644 index 0000000000000..198184add9d33 --- /dev/null +++ b/debian/linux-cloud-tools-common.hv-kvp-daemon.upstart @@ -0,0 +1,22 @@ +# On Azure/Hyper-V systems start the hv_kvp_daemon +# +description "Hyper-V KVP Protocol Daemon" +author "Adam Conrad " + +start on runlevel [2345] +stop on runlevel [!2345] +console log + +pre-start script + if [ -e "/etc/default/hv-kvp-daemon-init" ]; then + . /etc/default/hv-kvp-daemon-init + fi + [ "$RUN_KVP_DAEMON" = 0 ] && { stop; exit 0; } + if [ -d /sys/class/dmi/id/. ]; then + read company " +[Unit] +Description=Hyper-V VSS Protocol Daemon +ConditionVirtualization=microsoft +ConditionPathExists=/dev/vmbus/hv_vss +BindsTo=sys-devices-virtual-misc-vmbus\x21hv_vss.device + +[Service] +ExecStart=/usr/sbin/hv_vss_daemon -n + +[Install] +WantedBy=multi-user.target diff --git a/debian/linux-cloud-tools-common.hv-vss-daemon.udev b/debian/linux-cloud-tools-common.hv-vss-daemon.udev new file mode 100644 index 0000000000000..f4b9a91ad4bfc --- /dev/null +++ b/debian/linux-cloud-tools-common.hv-vss-daemon.udev @@ -0,0 +1 @@ +SUBSYSTEM=="misc", KERNEL=="vmbus/hv_vss", TAG+="systemd", ENV{SYSTEMD_WANTS}+="hv-vss-daemon.service" diff --git a/debian/linux-cloud-tools-common.hv-vss-daemon.upstart b/debian/linux-cloud-tools-common.hv-vss-daemon.upstart new file mode 100644 index 0000000000000..3f3326aef2025 --- /dev/null +++ b/debian/linux-cloud-tools-common.hv-vss-daemon.upstart @@ -0,0 +1,22 @@ +# On Azure/Hyper-V systems start the hv_vss_daemon +# +description "Hyper-V VSS Protocol Daemon" +author "Ben Howard " + +start on runlevel [2345] +stop on runlevel [!2345] +console log + +pre-start script + if [ -e "/etc/default/hv-kvp-daemon-init" ]; then + . /etc/default/hv-kvp-daemon-init + fi + [ "$RUN_VSS_DAEMON" -eq 0 ] && { stop; exit 0; } + if [ -d /sys/class/dmi/id/. ]; then + read company +# + +# Do not use make's built-in rules and variables +# (this increases performance and avoids hard-to-debug behaviour) +MAKEFLAGS += -rR + +# Allow to run debian/rules directly without root +export DEB_RULES_REQUIRES_ROOT := no + +.NOTPARALLEL: + +DEBIAN=$(shell awk -F= '($$1 == "DEBIAN") { print $$2 }' $(DEBIAN)/control.stub; + flavours="$(sort $(wildcard $(DEBIAN)/control.d/vars.*))";\ + for i in $$flavours; do \ + $(SHELL) $(DROOT)/scripts/control-create $$i "$(any_signed)" | \ + sed -e 's/PKGVER/$(release)/g' \ + -e 's/ABINUM/$(abinum)/g' \ + -e 's/SRCPKGNAME/$(src_pkg_name)/g' \ + -e 's/=HUMAN=/$(human_arch)/g' \ + -e 's/=SERIES=/$(series)/g' \ + >> $(DEBIAN)/control.stub; \ + done + +.PHONY: debian/control +debian/control: $(DEBIAN)/control.stub + cp $(DEBIAN)/control.stub debian/control + +debian/canonical-certs.pem: $(wildcard $(DROOT)/certs/*-all.pem) $(wildcard $(DROOT)/certs/*-$(arch).pem) $(wildcard $(DEBIAN)/certs/*-all.pem) $(wildcard $(DEBIAN)/certs/*-$(arch).pem) + for cert in $(sort $(notdir $^)); \ + do \ + for dir in $(DEBIAN) $(DROOT); \ + do \ + if [ -f "$$dir/certs/$$cert" ]; then \ + cat "$$dir/certs/$$cert"; \ + break; \ + fi; \ + done; \ + done >"$@" + +debian/canonical-revoked-certs.pem: $(wildcard $(DROOT)/revoked-certs/*-all.pem) $(wildcard $(DROOT)/revoked-certs/*-$(arch).pem) $(wildcard $(DEBIAN)/revoked-certs/*-all.pem) $(wildcard $(DEBIAN)/revoked-certs/*-$(arch).pem) + for cert in $(sort $(notdir $^)); \ + do \ + for dir in $(DEBIAN) $(DROOT); \ + do \ + if [ -f "$$dir/revoked-certs/$$cert" ]; then \ + cat "$$dir/revoked-certs/$$cert"; \ + break; \ + fi; \ + done; \ + done >"$@" diff --git a/debian/rules.d/0-common-vars.mk b/debian/rules.d/0-common-vars.mk new file mode 100644 index 0000000000000..98347b798c5f1 --- /dev/null +++ b/debian/rules.d/0-common-vars.mk @@ -0,0 +1,269 @@ +# Used when you need to 'escape' a comma. +comma = , +empty := +space := $(empty) $(empty) + +# +# The source package name will be the first token from $(DEBIAN)/changelog +# +src_pkg_name := $(shell dpkg-parsechangelog -l$(DEBIAN)/changelog -S source) + +# Get the series +series := $(shell dpkg-parsechangelog -l$(DEBIAN)/changelog -S distribution | sed -e 's/-\(security\|updates\|proposed\)$$//') + +# Get some version info +version := $(shell dpkg-parsechangelog -l$(DEBIAN)/changelog -S version) +revision ?= $(lastword $(subst -,$(space),$(version))) +release := $(patsubst %-$(revision),%,$(version)) + +prev_fullver ?= $(shell dpkg-parsechangelog -l$(DEBIAN)/changelog -o1 -c1 -S version) +prev_revision := $(lastword 0.0 $(subst -,$(space),$(prev_fullver))) + +# Get upstream version info +upstream_version := $(shell sed -n 's/^VERSION = \(.*\)$$/\1/p' Makefile) +upstream_patchlevel := $(shell sed -n 's/^PATCHLEVEL = \(.*\)$$/\1/p' Makefile) +upstream_tag := "v$(upstream_version).$(upstream_patchlevel)" + +# Get the kernels own extra version to be added to the release signature. +raw_kernelversion=$(shell make kernelversion) + +packages_enabled := $(shell dh_listpackages 2>/dev/null) +define if_package +$(if $(filter $(1),$(packages_enabled)),$(2)) +endef + +stamp = [ -d $(dir $@) ] || mkdir $(dir $@); touch $@ + +# +# do_full_build -- are we doing a full buildd style build, i.e., are we +# building in a PPA +# +ifeq ($(wildcard /CurrentlyBuilding),) + do_full_build ?= false +else + do_full_build ?= true +endif + +# +# The debug packages are ginormous, so you probably want to skip +# building them (as a developer). +# +do_dbgsym_package = true +ifeq ($(do_full_build),false) + do_dbgsym_package = false +endif +ifeq ($(filter $(DEB_BUILD_OPTIONS),noautodbgsym),noautodbgsym) + # Disable debug package builds if we're building in a PPA that has the + # 'Build debug symbols' option disabled + do_dbgsym_package = false +endif + +abinum := $(firstword $(subst .,$(space),$(revision))) +prev_abinum := $(firstword $(subst .,$(space),$(prev_revision))) +abi_release := $(release)-$(abinum) + +uploadnum := $(patsubst $(abinum).%,%,$(revision)) +ifneq ($(do_full_build),false) + uploadnum := $(uploadnum)-Ubuntu +endif + +DEB_HOST_MULTIARCH = $(shell dpkg-architecture -qDEB_HOST_MULTIARCH) +DEB_HOST_GNU_TYPE = $(shell dpkg-architecture -qDEB_HOST_GNU_TYPE) +DEB_BUILD_GNU_TYPE = $(shell dpkg-architecture -qDEB_BUILD_GNU_TYPE) +DEB_HOST_ARCH = $(shell dpkg-architecture -qDEB_HOST_ARCH) +DEB_BUILD_ARCH = $(shell dpkg-architecture -qDEB_BUILD_ARCH) + +# +# Detect invocations of the form 'fakeroot debian/rules binary arch=armhf' +# within an x86'en schroot. This only gets you part of the way since the +# packaging phase fails, but you can at least compile the kernel quickly. +# +arch := $(DEB_HOST_ARCH) +CROSS_COMPILE ?= $(DEB_HOST_GNU_TYPE)- + +# +# Set consistent toolchain +# If a given kernel wants to change this, they can do so via their own +# $(DEBIAN)/rules.d/hooks.mk and $(DEBIAN)/rules.d/$(arch).mk files +# +export gcc?=gcc-13 +GCC_BUILD_DEPENDS=\ $(gcc), $(gcc)-aarch64-linux-gnu [arm64] , $(gcc)-arm-linux-gnueabihf [armhf] , $(gcc)-powerpc64le-linux-gnu [ppc64el] , $(gcc)-riscv64-linux-gnu [riscv64] , $(gcc)-s390x-linux-gnu [s390x] , $(gcc)-x86-64-linux-gnu [amd64] , + +abidir := $(CURDIR)/$(DEBIAN)/__abi.current/$(arch) +commonconfdir := $(CURDIR)/$(DEBIAN)/config +archconfdir := $(CURDIR)/$(DEBIAN)/config/$(arch) +sharedconfdir := $(CURDIR)/debian.master/config +builddir := $(CURDIR)/debian/build +stampdir := $(CURDIR)/debian/stamps + +# +# The binary package name always starts with linux-image-$KVER-$ABI.$UPLOAD_NUM. There +# are places that you'll find linux-image hard coded, but I guess thats OK since the +# assumption that the binary package always starts with linux-image will never change. +# +bin_pkg_name_signed=linux-image-$(abi_release) +bin_pkg_name_unsigned=linux-image-unsigned-$(abi_release) +mods_pkg_name=linux-modules-$(abi_release) +mods_extra_pkg_name=linux-modules-extra-$(abi_release) +bldinfo_pkg_name=linux-buildinfo-$(abi_release) +hdrs_pkg_name=linux-headers-$(abi_release) +rust_pkg_name=$(src_pkg_name)-lib-rust-$(abi_release) +indep_hdrs_pkg_name=$(src_pkg_name)-headers-$(abi_release) +indep_lib_rust_pkg_name=$(src_pkg_name)-lib-rust-$(abi_release) + +# +# Similarly with the linux-source package, you need not build it as a developer. Its +# somewhat I/O intensive and utterly useless. +# +do_source_package=true +do_source_package_content=true +ifeq ($(do_full_build),false) +do_source_package_content=false +endif + +# common headers normally is built as an indep package, but may be arch +do_common_headers_indep=true + +# build tools +ifneq ($(wildcard $(CURDIR)/tools),) + ifeq ($(do_tools),) + ifneq ($(DEB_BUILD_GNU_TYPE),$(DEB_HOST_GNU_TYPE)) + do_tools=false + endif + endif + do_tools?=true +else + do_tools?=false +endif +tools_pkg_name=$(src_pkg_name)-tools-$(abi_release) +tools_common_pkg_name=linux-tools-common +tools_flavour_pkg_name=linux-tools-$(abi_release) +cloud_pkg_name=$(src_pkg_name)-cloud-tools-$(abi_release) +cloud_common_pkg_name=linux-cloud-tools-common +cloud_flavour_pkg_name=linux-cloud-tools-$(abi_release) +hosttools_pkg_name=linux-tools-host + +# The general flavour specific image package. +do_flavour_image_package=true + +# The general flavour specific header package. +do_flavour_header_package=true + +# DTBs +do_dtbs=false + +# ZSTD compressed kernel modules +do_zstd_ko=true +ifeq ($(series),jammy) +do_zstd_ko= +endif + +# Support parallel= in DEB_BUILD_OPTIONS (see #209008) +# +# These 2 environment variables set the -j value of the kernel build. For example, +# CONCURRENCY_LEVEL=16 fakeroot $(DEBIAN)/rules binary-debs +# or +# DEB_BUILD_OPTIONS=parallel=16 fakeroot $(DEBIAN)/rules binary-debs +# +# The default is to use the number of CPUs. +# +COMMA=, +DEB_BUILD_OPTIONS_PARA = $(subst parallel=,,$(filter parallel=%,$(subst $(COMMA), ,$(DEB_BUILD_OPTIONS)))) +ifneq (,$(DEB_BUILD_OPTIONS_PARA)) + CONCURRENCY_LEVEL := $(DEB_BUILD_OPTIONS_PARA) +endif + +ifeq ($(CONCURRENCY_LEVEL),) + # Check the environment + CONCURRENCY_LEVEL := $(shell echo $$CONCURRENCY_LEVEL) + # No? Then build with the number of CPUs on the host. + ifeq ($(CONCURRENCY_LEVEL),) + CONCURRENCY_LEVEL := $(shell expr `getconf _NPROCESSORS_ONLN` \* 1) + endif + # Oh hell, give 'em one + ifeq ($(CONCURRENCY_LEVEL),) + CONCURRENCY_LEVEL := 1 + endif +endif + +conc_level = -j$(CONCURRENCY_LEVEL) + +PYTHON ?= $(firstword $(wildcard /usr/bin/python3) $(wildcard /usr/bin/python2) $(wildcard /usr/bin/python)) + +HOSTCC ?= $(DEB_BUILD_GNU_TYPE)-$(gcc) + +# target_flavour is filled in for each step +kmake = make ARCH=$(build_arch) \ + CROSS_COMPILE=$(CROSS_COMPILE) \ + HOSTCC=$(HOSTCC) \ + CC=$(CROSS_COMPILE)$(gcc) \ + BINDGEN=bindgen-0.65 \ + KERNELRELEASE=$(abi_release)-$(target_flavour) \ + CONFIG_DEBUG_SECTION_MISMATCH=y \ + KBUILD_BUILD_VERSION="$(uploadnum)" \ + CFLAGS_MODULE='-DPKG_ABI=\"$(abinum)\"' \ + PYTHON=$(PYTHON) +ifneq ($(LOCAL_ENV_CC),) +kmake += CC="$(LOCAL_ENV_CC)" DISTCC_HOSTS="$(LOCAL_ENV_DISTCC_HOSTS)" +endif + +# Locking is required in parallel builds to prevent loss of contents +# of the debian/files. +lockme = flock -w 60 $(CURDIR)/debian/.LOCK + +# Don't fail if a link already exists. +LN = ln -sf + +# Checks if a var is overriden by the custom rules. Called with var and +# flavour as arguments. +custom_override = $(or $($(1)_$(2)),$($(1))) + +# selftests that Ubuntu cares about +ubuntu_selftests = breakpoints cpu-hotplug efivarfs memfd memory-hotplug mount net ptrace seccomp timers powerpc user ftrace + +# DKMS +all_dkms_modules = + +subst_paired = $(subst $(firstword $(subst =, ,$(1))),$(lastword $(subst =, ,$(1))),$(2)) +recursive_call = $(if $(2),$(call recursive_call,$(1),$(wordlist 2,$(words $(2)),$(2)),$(call $(1),$(firstword $(2)),$(3))),$(3)) + +$(foreach _line,$(shell gawk '{ OFS = "!"; $$1 = $$1; print }' $(DEBIAN)/dkms-versions), \ + $(eval _params = $(subst !, ,$(_line))) \ + $(eval _deb_pkgname = $(firstword $(_params))) \ + $(eval _deb_version = $(word 2,$(_params))) \ + $(if $(filter modulename=%,$(_params)), \ + $(eval _m = $(word 2,$(subst =, ,$(filter modulename=%,$(_params))))) \ + , \ + $(info modulename for $(_deb_pkgname) not specified in dkms-versions. Assume $(_deb_pkgname).) \ + $(eval _m = $(_deb_pkgname)) \ + ) \ + $(eval all_dkms_modules += $(_m)) \ + $(eval dkms_$(_m)_version = $(_deb_version)) \ + $(foreach _p,$(patsubst debpath=%,%,$(filter debpath=%,$(_params))), \ + $(eval dkms_$(_m)_debpath += $(strip \ + $(call recursive_call,subst_paired, \ + %module%=$(_m) \ + %package%=$(_deb_pkgname) \ + %version%=$(lastword $(subst :, ,$(_deb_version))) \ + , \ + $(_p) \ + ) \ + )) \ + ) \ + $(if $(dkms_$(_m)_debpath),,$(error debpath for $(_deb_pkgname) not specified.)) \ + $(if $(filter arch=%,$(_params)), \ + $(eval dkms_$(_m)_archs = $(patsubst arch=%,%,$(filter arch=%,$(_params)))) \ + , \ + $(eval dkms_$(_m)_archs = any) \ + ) \ + $(eval dkms_$(_m)_rprovides = $(patsubst rprovides=%,%,$(filter rprovides=%,$(_params)))) \ + $(eval dkms_$(_m)_type = $(word 1,$(patsubst type=%,%,$(filter type=%,$(_params))) built-in)) \ + $(eval all_$(dkms_$(_m)_type)_dkms_modules += $(_m)) \ + $(if $(filter standalone,$(dkms_$(_m)_type)), \ + $(eval dkms_$(_m)_pkg_name = linux-modules-$(_m)-$(abi_release)) \ + $(eval dkms_$(_m)_subdir = ubuntu) \ + , \ + $(eval dkms_$(_m)_pkg_name = $(mods_pkg_name)) \ + $(eval dkms_$(_m)_subdir = kernel) \ + ) \ +) diff --git a/debian/rules.d/1-maintainer.mk b/debian/rules.d/1-maintainer.mk new file mode 100644 index 0000000000000..82b035b625fe7 --- /dev/null +++ b/debian/rules.d/1-maintainer.mk @@ -0,0 +1,135 @@ +# The following targets are for the maintainer only! do not run if you don't +# know what they do. + +.PHONY: help +help: + @echo "These are the targets in addition to the normal $(DEBIAN) ones:" + @echo + @echo " printenv : Print some variables used in the build" + @echo " updateconfigs : Update core arch configs" + @echo " defaultconfigs : Update core arch configs using defaults" + @echo " genconfigs : Generate core arch configs in CONFIGS/*" + @echo " editconfigs : Edit core arch configs" + @echo " printchanges : Print the current changelog entries (from git)" + @echo " insertchanges : Insert current changelog entries (from git)" + @echo " compileselftests : Only compile the selftests listed on ubuntu_selftests variable" + @echo " runselftests : Run the selftests listed on ubuntu_selftests variable" + @echo + @echo "Environment variables:" + @echo + @echo " CONCURRENCY_LEVEL=X : Use -jX for kernel compile" + +.PHONY: printdebian +printdebian: + @echo "$(DEBIAN)" + +configs-targets := updateconfigs defaultconfigs genconfigs editconfigs + +.PHONY: $(configs-targets) +$(configs-targets): + dh_testdir + kmake='$(kmake)' skip_checks=$(do_skip_checks) conc_level=$(conc_level) \ + $(SHELL) $(DROOT)/scripts/misc/kernelconfig $@ + +.PHONY: printenv +printenv: + @dh_testdir + @echo "src_pkg_name = $(src_pkg_name)" + @echo "series = $(series)" + @echo "release = $(release)" + @echo "revision = $(revision)" + @echo "uploadnum = $(uploadnum)" + @echo "prev_revision = $(prev_revision)" + @echo "abinum = $(abinum)" + @echo "upstream_tag = $(upstream_tag)" + @echo "flavours = $(flavours)" + @echo "bin_pkg_name = $(bin_pkg_name)" + @echo "hdr_pkg_name = $(hdrs_pkg_name)" + @echo "rust_pkg_name = $(rust_pkg_name)" + @echo "ubuntu_selftests = $(ubuntu_selftests)" + @echo "arch = $(arch)" + @echo "kmake = $(kmake)" + @echo + @echo "CONCURRENCY_LEVEL = $(CONCURRENCY_LEVEL)" + @echo "DEB_HOST_GNU_TYPE = $(DEB_HOST_GNU_TYPE)" + @echo "DEB_BUILD_GNU_TYPE = $(DEB_BUILD_GNU_TYPE)" + @echo "DEB_HOST_ARCH = $(DEB_HOST_ARCH)" + @echo "DEB_BUILD_ARCH = $(DEB_BUILD_ARCH)" + @echo + @echo "any_signed = $(any_signed)" + @echo " uefi_signed = $(uefi_signed)" + @echo " opal_signed = $(opal_signed)" + @echo " sipl_signed = $(sipl_signed)" + @echo + @echo "do_skip_checks = $(do_skip_checks)" + @echo "do_full_build = $(do_full_build)" + @echo "do_mainline_build = $(do_mainline_build)" + @echo "do_dbgsym_package = $(do_dbgsym_package)" + @echo "do_dtbs = $(do_dtbs)" + @echo "do_source_package = $(do_source_package)" + @echo "do_source_package_content = $(do_source_package_content)" + @echo "do_extras_package = $(do_extras_package)" + @echo "do_flavour_image_package = $(do_flavour_image_package)" + @echo "do_flavour_header_package = $(do_flavour_header_package)" + @echo "do_common_headers_indep = $(do_common_headers_indep)" + @echo "do_lib_rust = $(do_lib_rust)" + @echo "do_tools = $(do_tools)" + @echo "do_tools_common = $(do_tools_common)" + @echo "do_any_tools = $(do_any_tools)" + @echo "do_linux_tools = $(do_linux_tools)" + @echo " do_tools_acpidbg = $(do_tools_acpidbg)" + @echo " do_tools_bpftool = $(do_tools_bpftool)" + @echo " do_tools_cpupower = $(do_tools_cpupower)" + @echo " do_tools_host = $(do_tools_host)" + @echo " do_tools_perf = $(do_tools_perf)" + @echo " do_tools_perf_jvmti = $(do_tools_perf_jvmti)" + @echo " do_tools_perf_python = $(do_tools_perf_python)" + @echo " do_tools_usbip = $(do_tools_usbip)" + @echo " do_tools_x86 = $(do_tools_x86)" + @echo "do_cloud_tools = $(do_cloud_tools)" + @echo " do_tools_hyperv = $(do_tools_hyperv)" + @echo + @echo "all_dkms_modules = $(all_dkms_modules)" + @$(foreach mod,$(all_dkms_modules),$(foreach var,$(do_$(mod)),\ + printf " %-24s = %s\n" "do_$(mod)" "$(var)";)) + +.PHONY: printchanges +printchanges: + @baseCommit=$$(git log --pretty=format:'%H %s' | \ + gawk '/UBUNTU: '".*Ubuntu-.*`echo $(prev_fullver) | sed 's/+/\\\\+/'`"'(~.*)?$$/ { print $$1; exit }'); \ + if [ -z "$$baseCommit" ]; then \ + echo "WARNING: couldn't find a commit for the previous version. Using the lastest one." >&2; \ + baseCommit=$$(git log --pretty=format:'%H %s' | \ + gawk '/UBUNTU:\s*Ubuntu-.*$$/ { print $$1; exit }'); \ + fi; \ + git log "$$baseCommit"..HEAD | \ + $(DROOT)/scripts/misc/git-ubuntu-log + +.PHONY: insertchanges +insertchanges: autoreconstruct finalchecks + $(DROOT)/scripts/misc/insert-changes $(DROOT) $(DEBIAN) + +.PHONY: autoreconstruct +autoreconstruct: + # No need for reconstruct for -rc kernels since we don't upload an + # orig tarball, so just remove it. + if grep -q "^EXTRAVERSION = -rc[0-9]\+$$" Makefile; then \ + echo "exit 0" >$(DEBIAN)/reconstruct; \ + else \ + $(DROOT)/scripts/misc/gen-auto-reconstruct $(upstream_tag) $(DEBIAN)/reconstruct $(DROOT)/source/options; \ + fi + +.PHONY: finalchecks +finalchecks: debian/control + $(DROOT)/scripts/checks/final-checks "$(DEBIAN)" "$(prev_fullver)" $(do_skip_checks) + +.PHONY: compileselftests +compileselftests: + # a loop is needed here to fail on errors + for test in $(ubuntu_selftests); do \ + $(kmake) -C tools/testing/selftests TARGETS="$$test"; \ + done; + +.PHONY: runselftests +runselftests: + $(kmake) -C tools/testing/selftests TARGETS="$(ubuntu_selftests)" run_tests diff --git a/debian/rules.d/2-binary-arch.mk b/debian/rules.d/2-binary-arch.mk new file mode 100644 index 0000000000000..7d1af53379f05 --- /dev/null +++ b/debian/rules.d/2-binary-arch.mk @@ -0,0 +1,771 @@ +# We don't want make removing intermediary stamps +.SECONDARY : + +# TODO this is probably wrong, and should be using $(DEB_HOST_MULTIARCH) +shlibdeps_opts = $(if $(CROSS_COMPILE),-- -l$(CROSS_COMPILE:%-=/usr/%)/lib) + +debian/scripts/fix-filenames: debian/scripts/fix-filenames.c + $(HOSTCC) $^ -o $@ + +$(stampdir)/stamp-prepare-%: $(stampdir)/stamp-prepare-tree-% + @echo Debug: $@ + $(stamp) + +$(stampdir)/stamp-prepare-tree-%: target_flavour = $* +$(stampdir)/stamp-prepare-tree-%: debian/scripts/fix-filenames + @echo Debug: $@ + install -d $(builddir)/build-$* + touch $(builddir)/build-$*/ubuntu-build + python3 debian/scripts/misc/annotations --export --arch $(arch) --flavour $(target_flavour) > $(builddir)/build-$*/.config + sed -i 's/.*CONFIG_VERSION_SIGNATURE.*/CONFIG_VERSION_SIGNATURE="Ubuntu $(release)-$(revision)-$* $(raw_kernelversion)"/' $(builddir)/build-$*/.config + find $(builddir)/build-$* -name "*.ko" | xargs rm -f + $(kmake) O=$(builddir)/build-$* $(conc_level) rustavailable || true + $(kmake) O=$(builddir)/build-$* $(conc_level) olddefconfig + $(stamp) + +# Used by developers as a shortcut to prepare a tree for compilation. +prepare-%: $(stampdir)/stamp-prepare-% + @echo Debug: $@ +# Used by developers to allow efficient pre-building without fakeroot. +build-%: $(stampdir)/stamp-install-% + @echo Debug: $@ + +# Do the actual build, including image and modules +$(stampdir)/stamp-build-%: target_flavour = $* +$(stampdir)/stamp-build-%: bldimg = $(call custom_override,build_image,$*) +$(stampdir)/stamp-build-%: $(stampdir)/stamp-prepare-% + @echo Debug: $@ build_image $(build_image) bldimg $(bldimg) + $(kmake) O=$(builddir)/build-$* $(conc_level) $(bldimg) modules $(if $(filter true,$(do_dtbs)),dtbs) + +ifeq ($(do_dbgsym_package),true) + # The target scripts_gdb is part of "all", so we need to call it manually + if grep -q CONFIG_GDB_SCRIPTS=y $(builddir)/build-$*/.config; then \ + $(kmake) O=$(builddir)/build-$* $(conc_level) scripts_gdb ; \ + fi +endif + $(stamp) + +define build_dkms_sign = + $(shell set -x; if grep -q CONFIG_MODULE_SIG=y $(1)/.config; then + echo $(1)/scripts/sign-file $(MODHASHALGO) $(MODSECKEY) $(MODPUBKEY); + else + echo "-"; + fi + ) +endef +define build_dkms = + rc=0; unset MAKEFLAGS; ARCH=$(build_arch) CROSS_COMPILE=$(CROSS_COMPILE) $(SHELL) $(DROOT)/scripts/dkms-build $(dkms_dir) $(abi_release)-$* '$(call build_dkms_sign,$(builddir)/build-$*)' $(1) $(2) $(3) $(4) $(5) || rc=$$?; if [ "$$rc" = "9" -o "$$rc" = "77" ]; then echo do_$(4)_$*=false >> $(builddir)/skipped-dkms.mk; rc=0; fi; if [ "$$rc" != "0" ]; then exit $$rc; fi +endef + +define install_control = + for which in $(3); \ + do \ + template="$(DROOT)/templates/$(2).$$which.in"; \ + script="$(DROOT)/$(1).$$which"; \ + sed -e 's/@abiname@/$(abi_release)/g' \ + -e 's/@localversion@/-$*/g' \ + -e 's/@image-stem@/$(instfile)/g' \ + <"$$template" >"$$script"; \ + done +endef + +# Ensure the directory prefix is exactly 140 characters long so pathnames are the +# exact same length in any binary files produced by the builds. These will be +# commonised later. +dkms_20d=.................... +dkms_140d=$(dkms_20d)$(dkms_20d)$(dkms_20d)$(dkms_20d)$(dkms_20d)$(dkms_20d)$(dkms_20d) +dkms_140c=$(shell echo '$(dkms_140d)' | sed -e 's/\./_/g') +define dkms_dir_prefix = +$(shell echo $(1)/$(dkms_140c) | \ + sed -e 's/\($(dkms_140d)\).*/\1/' -e 's/^\(.*\)....$$/\1dkms/') +endef + +# Install the finished build +$(stampdir)/stamp-install-%: pkgdir_bin = $(CURDIR)/debian/$(bin_pkg_name)-$* +$(stampdir)/stamp-install-%: pkgdir = $(CURDIR)/debian/$(mods_pkg_name)-$* +$(stampdir)/stamp-install-%: pkgdir_ex = $(CURDIR)/debian/$(mods_extra_pkg_name)-$* +$(stampdir)/stamp-install-%: pkgdir_bldinfo = $(CURDIR)/debian/$(bldinfo_pkg_name)-$* +$(stampdir)/stamp-install-%: bindoc = $(pkgdir)/usr/share/doc/$(bin_pkg_name)-$* +$(stampdir)/stamp-install-%: dbgpkgdir = $(CURDIR)/debian/$(bin_pkg_name)-$*-dbgsym +$(stampdir)/stamp-install-%: signingv = $(CURDIR)/debian/$(bin_pkg_name)-signing/$(release)-$(revision) +$(stampdir)/stamp-install-%: toolspkgdir = $(CURDIR)/debian/$(tools_flavour_pkg_name)-$* +$(stampdir)/stamp-install-%: cloudpkgdir = $(CURDIR)/debian/$(cloud_flavour_pkg_name)-$* +$(stampdir)/stamp-install-%: basepkg = $(hdrs_pkg_name) +$(stampdir)/stamp-install-%: baserustpkg = $(rust_pkg_name) +$(stampdir)/stamp-install-%: indeppkg = $(indep_hdrs_pkg_name) +$(stampdir)/stamp-install-%: kernfile = $(call custom_override,kernel_file,$*) +$(stampdir)/stamp-install-%: instfile = $(call custom_override,install_file,$*) +$(stampdir)/stamp-install-%: hdrdir = $(CURDIR)/debian/$(basepkg)-$*/usr/src/$(basepkg)-$* +$(stampdir)/stamp-install-%: rustdir = $(CURDIR)/debian/$(baserustpkg)-$*/usr/src/$(baserustpkg)-$* +$(stampdir)/stamp-install-%: target_flavour = $* +$(stampdir)/stamp-install-%: MODHASHALGO=sha512 +$(stampdir)/stamp-install-%: MODSECKEY=$(builddir)/build-$*/certs/signing_key.pem +$(stampdir)/stamp-install-%: MODPUBKEY=$(builddir)/build-$*/certs/signing_key.x509 +$(stampdir)/stamp-install-%: build_dir=$(builddir)/build-$* +$(stampdir)/stamp-install-%: dkms_dir=$(call dkms_dir_prefix,$(builddir)/build-$*) +$(foreach _m,$(all_dkms_modules), \ + $(eval $$(stampdir)/stamp-install-%: enable_$(_m) = $$(filter true,$$(call custom_override,do_$(_m),$$*))) \ + $(eval $$(stampdir)/stamp-install-%: dkms_$(_m)_pkgdir = $$(CURDIR)/debian/$(dkms_$(_m)_pkg_name)-$$*) \ +) +$(stampdir)/stamp-install-%: dbgpkgdir_dkms = $(if $(filter true,$(do_dbgsym_package)),$(dbgpkgdir)/usr/lib/debug/lib/modules/$(abi_release)-$*/kernel,"") +$(stampdir)/stamp-install-%: $(stampdir)/stamp-build-% $(stampdir)/stamp-install-headers + @echo Debug: $@ kernel_file $(kernel_file) kernfile $(kernfile) install_file $(install_file) instfile $(instfile) + dh_testdir + dh_prep -p$(bin_pkg_name)-$* + dh_prep -p$(mods_pkg_name)-$* + dh_prep -p$(hdrs_pkg_name)-$* +ifeq ($(do_lib_rust),true) + dh_prep -p$(rust_pkg_name)-$* +endif + $(foreach _m,$(all_standalone_dkms_modules), \ + $(if $(enable_$(_m)),dh_prep -p$(dkms_$(_m)_pkg_name)-$*;)\ + ) +ifeq ($(do_dbgsym_package),true) + dh_prep -p$(bin_pkg_name)-$*-dbgsym +endif +ifeq ($(do_extras_package),true) + dh_prep -p$(mods_extra_pkg_name)-$* +endif + + # The main image + # compress_file logic required because not all architectures + # generate a zImage automatically out of the box +ifeq ($(compress_file),) + install -m600 -D $(builddir)/build-$*/$(kernfile) \ + $(pkgdir_bin)/boot/$(instfile)-$(abi_release)-$* +else + install -d $(pkgdir_bin)/boot + gzip -c9v $(builddir)/build-$*/$(kernfile) > \ + $(pkgdir_bin)/boot/$(instfile)-$(abi_release)-$* + chmod 600 $(pkgdir_bin)/boot/$(instfile)-$(abi_release)-$* +endif + install -d $(pkgdir)/boot + install -m644 $(builddir)/build-$*/.config \ + $(pkgdir)/boot/config-$(abi_release)-$* + install -m600 $(builddir)/build-$*/System.map \ + $(pkgdir)/boot/System.map-$(abi_release)-$* + +ifeq ($(do_dtbs),true) + $(kmake) O=$(builddir)/build-$* $(conc_level) dtbs_install \ + INSTALL_DTBS_PATH=$(pkgdir)/lib/firmware/$(abi_release)-$*/device-tree +endif + +ifeq ($(no_dumpfile),) + makedumpfile -g $(pkgdir)/boot/vmcoreinfo-$(abi_release)-$* \ + -x $(builddir)/build-$*/vmlinux + chmod 0600 $(pkgdir)/boot/vmcoreinfo-$(abi_release)-$* +endif + + $(kmake) O=$(builddir)/build-$* $(conc_level) modules_install $(vdso) \ + INSTALL_MOD_STRIP=1 INSTALL_MOD_PATH=$(pkgdir) + + # + # Build module blacklists: + # - blacklist all watchdog drivers (LP:1432837) + # + install -d $(pkgdir)/lib/modprobe.d + echo "# Kernel supplied blacklist for $(src_pkg_name) $(abi_release)-$* $(arch)" \ + >$(pkgdir)/lib/modprobe.d/blacklist_$(src_pkg_name)_$(abi_release)-$*.conf + for conf in $(arch)-$* $(arch) common.conf; do \ + if [ -f $(DEBIAN)/modprobe.d/$$conf ]; then \ + echo "# modprobe.d/$$conf"; \ + cat $(DEBIAN)/modprobe.d/$$conf; \ + fi; \ + done >>$(pkgdir)/lib/modprobe.d/blacklist_$(src_pkg_name)_$(abi_release)-$*.conf + echo "# Autogenerated watchdog blacklist" \ + >>$(pkgdir)/lib/modprobe.d/blacklist_$(src_pkg_name)_$(abi_release)-$*.conf + ls -1 $(pkgdir)/lib/modules/$(abi_release)-$*/kernel/drivers/watchdog/ | \ + grep -v '^bcm2835_wdt$$' | \ + sed -e 's/^/blacklist /' -e 's/.ko$$//' | \ + sort -u \ + >>$(pkgdir)/lib/modprobe.d/blacklist_$(src_pkg_name)_$(abi_release)-$*.conf + +ifeq ($(do_extras_package),true) + # + # Remove all modules not in the inclusion list. + # + if [ -f $(DEBIAN)/control.d/$(target_flavour).inclusion-list ] ; then \ + /sbin/depmod -v -b $(pkgdir) $(abi_release)-$* | \ + sed -e "s@$(pkgdir)/lib/modules/$(abi_release)-$*/kernel/@@g" | \ + awk '{ print $$1 " " $$NF}' >$(build_dir)/module-inclusion.depmap; \ + mkdir -p $(pkgdir_ex)/lib/modules/$(abi_release)-$*; \ + mv $(pkgdir)/lib/modules/$(abi_release)-$*/kernel \ + $(pkgdir_ex)/lib/modules/$(abi_release)-$*/kernel; \ + $(SHELL) $(DROOT)/scripts/module-inclusion --master \ + $(pkgdir_ex)/lib/modules/$(abi_release)-$*/kernel \ + $(pkgdir)/lib/modules/$(abi_release)-$*/kernel \ + $(DEBIAN)/control.d/$(target_flavour).inclusion-list \ + $(build_dir)/module-inclusion.depmap 2>&1 | \ + tee $(target_flavour).inclusion-list.log; \ + /sbin/depmod -b $(pkgdir) -ea -F $(pkgdir)/boot/System.map-$(abi_release)-$* \ + $(abi_release)-$* 2>&1 |tee $(target_flavour).depmod.log; \ + if [ `grep -c 'unknown symbol' $(target_flavour).depmod.log` -gt 0 ]; then \ + echo "EE: Unresolved module dependencies in base package!"; \ + exit 1; \ + fi \ + fi +endif + +ifeq ($(no_dumpfile),) + makedumpfile -g $(pkgdir)/boot/vmcoreinfo-$(abi_release)-$* \ + -x $(builddir)/build-$*/vmlinux + chmod 0600 $(pkgdir)/boot/vmcoreinfo-$(abi_release)-$* +endif + rm -f $(pkgdir)/lib/modules/$(abi_release)-$*/build + rm -f $(pkgdir)/lib/modules/$(abi_release)-$*/source + + # Some initramfs-tools specific modules + install -d $(pkgdir)/lib/modules/$(abi_release)-$*/initrd + if [ -f $(pkgdir)/lib/modules/$(abi_release)-$*/kernel/drivers/video/vesafb.ko ]; then\ + $(LN) $(pkgdir)/lib/modules/$(abi_release)-$*/kernel/drivers/video/vesafb.ko \ + $(pkgdir)/lib/modules/$(abi_release)-$*/initrd/; \ + fi + + echo "interest linux-update-$(abi_release)-$*" >"$(DROOT)/$(bin_pkg_name)-$*.triggers" + install -d $(pkgdir_bin)/usr/lib/linux/triggers + $(call install_control,$(bin_pkg_name)-$*,image,postinst postrm preinst prerm) + install -d $(pkgdir)/usr/lib/linux/triggers + $(call install_control,$(mods_pkg_name)-$*,extra,postinst postrm) +ifeq ($(do_extras_package),true) + # Install the postinit/postrm scripts in the extras package. + if [ -f $(DEBIAN)/control.d/$(target_flavour).inclusion-list ] ; then \ + install -d $(pkgdir_ex)/usr/lib/linux/triggers; \ + $(call install_control,$(mods_extra_pkg_name)-$*,extra,postinst postrm); \ + fi +endif + $(foreach _m,$(all_standalone_dkms_modules), \ + $(if $(enable_$(_m)), \ + install -d $(dkms_$(_m)_pkgdir)/usr/lib/linux/triggers; \ + $(call install_control,$(dkms_$(_m)_pkg_name)-$*,extra,postinst postrm); \ + ) \ + ) + +ifeq ($(do_dbgsym_package),true) + # Debug image is simple + install -m644 -D $(builddir)/build-$*/vmlinux \ + $(dbgpkgdir)/usr/lib/debug/boot/vmlinux-$(abi_release)-$* + if [ -d $(builddir)/build-$*/scripts/gdb/linux ]; then \ + install -m644 -D $(builddir)/build-$*/vmlinux-gdb.py \ + $(dbgpkgdir)/usr/share/gdb/auto-load/boot/vmlinux-$(abi_release)-$*/vmlinuz-$(abi_release)-$*-gdb.py; \ + install -m644 -D $(builddir)/build-$*/scripts/gdb/linux/* \ + --target-directory=$(dbgpkgdir)/usr/share/gdb/auto-load/boot/vmlinux-$(abi_release)-$*/scripts/gdb/linux; \ + fi + $(kmake) O=$(builddir)/build-$* modules_install $(vdso) \ + INSTALL_MOD_PATH=$(dbgpkgdir)/usr/lib/debug + # Add .gnu_debuglink sections only after all/DKMS modules are built. + rm -f $(dbgpkgdir)/usr/lib/debug/lib/modules/$(abi_release)-$*/build + rm -f $(dbgpkgdir)/usr/lib/debug/lib/modules/$(abi_release)-$*/source + rm -f $(dbgpkgdir)/usr/lib/debug/lib/modules/$(abi_release)-$*/modules.* + rm -fr $(dbgpkgdir)/usr/lib/debug/lib/firmware +endif +ifeq ($(do_tools_bpftool),true) + cp $(builddir)/build-$*/vmlinux tools/bpf/bpftool/ +endif + + # The flavour specific headers image + # TODO: Would be nice if we didn't have to dupe the original builddir + install -d -m755 $(hdrdir) + cp $(builddir)/build-$*/.config $(hdrdir) + chmod 644 $(hdrdir)/.config + $(kmake) O=$(hdrdir) -j1 syncconfig prepare scripts + # Makefile may need per-arch-flavour CC settings, which are + # normally set via $(kmake) during build + rm -f $(hdrdir)/Makefile + cp -a $(indep_hdrdir)/Makefile $(hdrdir)/Makefile + sed -i 's|\(^HOSTCC = \)gcc$$|\1$(gcc)|' $(hdrdir)/Makefile + sed -i 's|\(^CC = $$(CROSS_COMPILE)\)gcc$$|\1$(gcc)|' $(hdrdir)/Makefile + # Quick check for successful substitutions + grep '^HOSTCC .*$(gcc)$$' $(hdrdir)/Makefile + grep '^CC .*$(gcc)$$' $(hdrdir)/Makefile + rm -rf $(hdrdir)/include2 $(hdrdir)/source + # Copy over the compilation version. + cp "$(builddir)/build-$*/include/generated/compile.h" \ + "$(hdrdir)/include/generated/compile.h" + # Add UTS_UBUNTU_RELEASE_ABI since UTS_RELEASE is difficult to parse. + echo "#define UTS_UBUNTU_RELEASE_ABI $(abinum)" >> $(hdrdir)/include/generated/utsrelease.h + # powerpc kernel arch seems to need some .o files for external module linking. Add them in. +ifeq ($(build_arch),powerpc) + mkdir -p $(hdrdir)/arch/powerpc/lib + cp $(builddir)/build-$*/arch/powerpc/lib/*.o $(hdrdir)/arch/powerpc/lib +endif +ifeq ($(build_arch),s390) + if [ -n "$$(find $(builddir)/build-$*/arch/s390/lib/expoline -maxdepth 1 -name '*.o' -print -quit)" ]; then \ + mkdir -p $(hdrdir)/arch/s390/lib/expoline/; \ + cp $(builddir)/build-$*/arch/s390/lib/expoline/*.o $(hdrdir)/arch/s390/lib/expoline/; \ + fi +endif + # Copy over scripts/module.lds for building external modules + cp $(builddir)/build-$*/scripts/module.lds $(hdrdir)/scripts + # Script to symlink everything up + $(SHELL) $(DROOT)/scripts/link-headers "$(hdrdir)" "$(indeppkg)" "$*" + # The build symlink + install -d debian/$(basepkg)-$*/lib/modules/$(abi_release)-$* + $(LN) /usr/src/$(basepkg)-$* \ + debian/$(basepkg)-$*/lib/modules/$(abi_release)-$*/build + # And finally the symvers + install -m644 $(builddir)/build-$*/Module.symvers \ + $(hdrdir)/Module.symvers + + # Now the header scripts + $(call install_control,$(hdrs_pkg_name)-$*,headers,postinst) + + # At the end of the package prep, call the tests + DPKG_ARCH="$(arch)" KERN_ARCH="$(build_arch)" FLAVOUR="$*" \ + VERSION="$(abi_release)" REVISION="$(revision)" \ + PREV_REVISION="$(prev_revision)" ABI_NUM="$(abinum)" \ + PREV_ABI_NUM="$(prev_abinum)" BUILD_DIR="$(builddir)/build-$*" \ + INSTALL_DIR="$(pkgdir)" SOURCE_DIR="$(CURDIR)" \ + run-parts -v $(DROOT)/tests-build + + # + # Remove files which are generated at installation by postinst, + # except for modules.order and modules.builtin + # + # NOTE: need to keep this list in sync with postrm + # + mkdir $(pkgdir)/lib/modules/$(abi_release)-$*/_ + mv $(pkgdir)/lib/modules/$(abi_release)-$*/modules.order \ + $(pkgdir)/lib/modules/$(abi_release)-$*/_ + if [ -f $(pkgdir)/lib/modules/$(abi_release)-$*/modules.builtin ] ; then \ + mv $(pkgdir)/lib/modules/$(abi_release)-$*/modules.builtin \ + $(pkgdir)/lib/modules/$(abi_release)-$*/_; \ + fi + if [ -f $(pkgdir)/lib/modules/$(abi_release)-$*/modules.builtin.modinfo ] ; then \ + mv $(pkgdir)/lib/modules/$(abi_release)-$*/modules.builtin.modinfo \ + $(pkgdir)/lib/modules/$(abi_release)-$*/_; \ + fi + rm -f $(pkgdir)/lib/modules/$(abi_release)-$*/modules.* + mv $(pkgdir)/lib/modules/$(abi_release)-$*/_/* \ + $(pkgdir)/lib/modules/$(abi_release)-$* + rmdir $(pkgdir)/lib/modules/$(abi_release)-$*/_ + +ifeq ($(do_linux_tools),true) + # Create the linux-tools tool links + install -d $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +ifeq ($(do_tools_usbip),true) + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/usbip $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/usbipd $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +endif +ifeq ($(do_tools_acpidbg),true) + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/acpidbg $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +endif +ifeq ($(do_tools_cpupower),true) + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/cpupower $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +endif +ifeq ($(do_tools_rtla),true) + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/rtla $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +endif +ifeq ($(do_tools_perf),true) + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/perf $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +ifeq ($(do_tools_perf_jvmti),true) + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/libperf-jvmti.so $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +endif +endif +ifeq ($(do_tools_bpftool),true) + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/bpftool $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +endif +ifeq ($(do_tools_x86),true) + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/x86_energy_perf_policy $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/turbostat $(toolspkgdir)/usr/lib/linux-tools/$(abi_release)-$* +endif +endif +ifeq ($(do_cloud_tools),true) +ifeq ($(do_tools_hyperv),true) + # Create the linux-hyperv tool links + install -d $(cloudpkgdir)/usr/lib/linux-tools/$(abi_release)-$* + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/hv_kvp_daemon $(cloudpkgdir)/usr/lib/linux-tools/$(abi_release)-$* + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/hv_vss_daemon $(cloudpkgdir)/usr/lib/linux-tools/$(abi_release)-$* + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/hv_fcopy_daemon $(cloudpkgdir)/usr/lib/linux-tools/$(abi_release)-$* + $(LN) ../../$(src_pkg_name)-tools-$(abi_release)/lsvmbus $(cloudpkgdir)/usr/lib/linux-tools/$(abi_release)-$* +endif +endif + + # Build a temporary "installed headers" directory. + install -d $(dkms_dir) $(dkms_dir)/headers $(dkms_dir)/build $(dkms_dir)/source + cp -rp "$(hdrdir)" "$(indep_hdrdir)" "$(dkms_dir)/headers" + + $(foreach _m,$(all_dkms_modules), \ + $(if $(enable_$(_m)), \ + $(call build_dkms,$(dkms_$(_m)_pkg_name)-$*,$(dkms_$(_m)_pkgdir)/lib/modules/$(abi_release)-$*/$(dkms_$(_m)_subdir),$(dbgpkgdir_dkms),$(_m),$(dkms_$(_m)_debpath)); \ + ) \ + ) + + +ifeq ($(do_dbgsym_package),true) + # Add .gnu_debuglink sections to each stripped .ko + # pointing to unstripped verson + find $(pkgdir) \ + $(if $(filter true,$(do_extras_package)),$(pkgdir_ex)) \ + -name '*.ko' | while read path_module ; do \ + module="/lib/modules/$${path_module#*/lib/modules/}"; \ + if [[ -f "$(dbgpkgdir)/usr/lib/debug/$$module" ]] ; then \ + while IFS= read -r -d '' signature < <(tail -c 28 "$$path_module"); do \ + break; \ + done; \ + $(CROSS_COMPILE)objcopy \ + --add-gnu-debuglink=$(dbgpkgdir)/usr/lib/debug/$$module \ + $$path_module; \ + if grep -q CONFIG_MODULE_SIG=y $(builddir)/build-$*/.config && \ + [ "$$signature" = $$'~Module signature appended~\n' ]; then \ + $(builddir)/build-$*/scripts/sign-file $(MODHASHALGO) \ + $(MODSECKEY) \ + $(MODPUBKEY) \ + $$path_module; \ + fi; \ + else \ + echo "WARNING: Missing debug symbols for module '$$module'."; \ + fi; \ + done +endif + + # Build the final ABI information. + install -d $(abidir) + sed -e 's/^\(.\+\)[[:space:]]\+\(.\+\)[[:space:]]\(.\+\)$$/\3 \2 \1/' \ + $(builddir)/build-$*/Module.symvers | sort > $(abidir)/$* + + # Build the final ABI modules information. + find $(pkgdir_bin) $(pkgdir) $(pkgdir_ex) \( -name '*.ko' -o -name '*.ko.*' \) | \ + sed -e 's/.*\/\([^\/]*\)\.ko.*/\1/' | sort > $(abidir)/$*.modules + + # Build the final ABI built-in modules information. + if [ -f $(pkgdir)/lib/modules/$(abi_release)-$*/modules.builtin ] ; then \ + sed -e 's/.*\/\([^\/]*\)\.ko/\1/' $(pkgdir)/lib/modules/$(abi_release)-$*/modules.builtin | \ + sort > $(abidir)/$*.modules.builtin; \ + fi + + # Build the final ABI firmware information. + find $(pkgdir_bin) $(pkgdir) $(pkgdir_ex) -name \*.ko | \ + while read ko; do \ + /sbin/modinfo $$ko | grep ^firmware || true; \ + done | sort -u >$(abidir)/$*.fwinfo + + # Build the final ABI built-in firmware information. + if [ -f $(pkgdir)/lib/modules/$(abi_release)-$*/modules.builtin.modinfo ] ; then \ + cat $(pkgdir)/lib/modules/$(abi_release)-$*/modules.builtin.modinfo | \ + tr '\0' '\n' | sed -n 's/^.*firmware=/firmware: /p' | \ + sort -u > $(abidir)/$*.fwinfo.builtin; \ + fi + + # Build the final ABI compiler information. + ko=$$(find $(pkgdir_bin) $(pkgdir) $(pkgdir_ex) -name \*.ko | head -1); \ + readelf -p .comment "$$ko" | gawk ' \ + ($$1 == "[") { \ + printf("%s", $$3); \ + for (n=4; n<=NF; n++) { \ + printf(" %s", $$n); \ + } \ + print "" \ + }' | sort -u >$(abidir)/$*.compiler + + # Build the buildinfo package content. + install -d $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$* + install -m644 $(builddir)/build-$*/.config \ + $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/config + install -m644 $(abidir)/$* \ + $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/abi + install -m644 $(abidir)/$*.modules \ + $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/modules + install -m644 $(abidir)/$*.fwinfo \ + $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/fwinfo + install -m644 $(abidir)/$*.compiler \ + $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/compiler + if [ -f $(abidir)/$*.modules.builtin ] ; then \ + install -m644 $(abidir)/$*.modules.builtin \ + $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/modules.builtin; \ + fi + if [ -f $(abidir)/$*.fwinfo.builtin ] ; then \ + install -m644 $(abidir)/$*.fwinfo.builtin \ + $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/fwinfo.builtin; \ + fi + install -m644 $(DROOT)/canonical-certs.pem $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/canonical-certs.pem + install -m644 $(DROOT)/canonical-revoked-certs.pem $(pkgdir_bldinfo)/usr/lib/linux/$(abi_release)-$*/canonical-revoked-certs.pem + + # Get rid of .o and .cmd artifacts in headers + find $(hdrdir) -name \*.o -or -name \*.cmd -exec rm -f {} \; + # Strip .so files (e.g., rust/libmacros.so) to reduce size even more + find $(hdrdir) -name libmacros.so -exec strip -s {} \; + +ifeq ($(do_lib_rust),true) + # Generate Rust lib files + install -d -m755 $(rustdir) + mv $(hdrdir)/rust $(rustdir) + # Generate symlink for Rust lib directory in headers + $(SHELL) $(DROOT)/scripts/link-lib-rust "$(hdrdir)" "$(indeppkg)" "$*" +endif + +ifneq ($(do_full_build),false) + # Clean out this flavours build directory. + rm -rf $(builddir)/build-$* +endif + $(stamp) + +headers_tmp := $(CURDIR)/debian/tmp-headers +headers_dir := $(CURDIR)/debian/linux-libc-dev + +.PHONY: install-arch-headers +install-arch-headers: + @echo Debug: $@ + dh_testdir + dh_testroot + $(call if_package, linux-libc-dev, dh_prep -plinux-libc-dev) + rm -rf $(headers_tmp) $(headers_dir) + $(kmake) O=$(headers_tmp) INSTALL_HDR_PATH=$(headers_dir)/usr $(conc_level) headers_install + mkdir $(headers_dir)/usr/include/$(DEB_HOST_MULTIARCH) + mv $(headers_dir)/usr/include/asm $(headers_dir)/usr/include/$(DEB_HOST_MULTIARCH)/ + rm -rf $(headers_tmp) + +define dh_all + dh_installchangelogs -p$(1) + dh_installdocs -p$(1) + dh_compress -p$(1) + # Compress kernel modules, on mantic+ + $(if $(do_zstd_ko),find debian/$(1) -name '*.ko' -print0 | xargs -0 -n1 -P $(CONCURRENCY_LEVEL) -r zstd -19 --quiet --rm, true) + dh_fixperms -p$(1) -X/boot/ + dh_shlibdeps -p$(1) $(shlibdeps_opts) + dh_installdeb -p$(1) + dh_installdebconf -p$(1) + $(lockme) dh_gencontrol -p$(1) -- -Vlinux:rprovides='$(rprovides)' $(2) + dh_md5sums -p$(1) + dh_builddeb -p$(1) +endef +define newline + + +endef +define dh_all_inline + $(subst ${newline},; \${newline},$(call dh_all,$(1),$(2))) +endef + +.PHONY: binary-arch-headers +binary-arch-headers: install-arch-headers + @echo Debug: $@ + dh_testdir + dh_testroot + $(call if_package, linux-libc-dev, $(call dh_all,linux-libc-dev)) + +-include $(builddir)/skipped-dkms.mk +binary-%: pkgimg = $(bin_pkg_name)-$* +binary-%: pkgimg_mods = $(mods_pkg_name)-$* +binary-%: pkgimg_ex = $(mods_extra_pkg_name)-$* +binary-%: pkgdir_ex = $(CURDIR)/debian/$(extra_pkg_name)-$* +binary-%: pkgbldinfo = $(bldinfo_pkg_name)-$* +binary-%: pkghdr = $(hdrs_pkg_name)-$* +binary-%: pkgrust = $(rust_pkg_name)-$* +binary-%: dbgpkg = $(bin_pkg_name)-$*-dbgsym +binary-%: dbgpkgdir = $(CURDIR)/debian/$(bin_pkg_name)-$*-dbgsym +binary-%: pkgtools = $(tools_flavour_pkg_name)-$* +binary-%: pkgcloud = $(cloud_flavour_pkg_name)-$* +$(foreach _m,$(all_dkms_modules), \ + $(eval binary-%: enable_$(_m) = $$(filter true,$$(call custom_override,do_$(_m),$$*))) \ +) +binary-%: rprovides = $(foreach _m,$(all_built-in_dkms_modules),$(if $(enable_$(_m)),$(foreach _r,$(dkms_$(_m)_rprovides),$(_r)$(comma) ))) +binary-%: target_flavour = $* +binary-%: checks-% + @echo Debug: $@ + dh_testdir + dh_testroot + + $(call dh_all,$(pkgimg)) -- -Znone + $(call dh_all,$(pkgimg_mods))$(if $(do_zstd_ko), -- -Znone) + +ifeq ($(do_extras_package),true) + ifeq ($(ship_extras_package),false) + # If $(ship_extras_package) is explicitly set to false, then do not + # construct the linux-image-extra package; instead just log all of the + # "extra" modules which were pointlessly built yet won't be shipped. + find $(pkgdir_ex) -name '*.ko' | sort \ + | sed 's|^$(pkgdir_ex)/|NOT-SHIPPED |' \ + | tee -a $(target_flavour).not-shipped.log; + else + if [ -f $(DEBIAN)/control.d/$(target_flavour).inclusion-list ] ; then \ + $(call dh_all_inline,$(pkgimg_ex))$(if $(do_zstd_ko), -- -Znone); \ + fi + endif +endif + + $(foreach _m,$(all_standalone_dkms_modules), \ + $(if $(enable_$(_m)),$(call dh_all,$(dkms_$(_m)_pkg_name)-$*)$(if $(do_zstd_ko), -- -Znone);)\ + ) + + $(call dh_all,$(pkgbldinfo)) + $(call dh_all,$(pkghdr)) +ifeq ($(do_lib_rust),true) + $(call dh_all,$(pkgrust)) +endif + +ifeq ($(do_dbgsym_package),true) + $(call dh_all,$(dbgpkg)) -- -Zxz + + # Hokay...here's where we do a little twiddling... + # Renaming the debug package prevents it from getting into + # the primary archive, and therefore prevents this very large + # package from being mirrored. It is instead, through some + # archive admin hackery, copied to http://ddebs.ubuntu.com. + # + mv ../$(dbgpkg)_$(release)-$(revision)_$(arch).deb \ + ../$(dbgpkg)_$(release)-$(revision)_$(arch).ddeb + $(lockme) sed -i '/^$(dbgpkg)_/s/\.deb /.ddeb /' debian/files + # Now, the package wont get into the archive, but it will get put + # into the debug system. + + # Clean out the debugging package source directory. + rm -rf $(dbgpkgdir) +endif + +ifeq ($(do_linux_tools),true) + $(call dh_all,$(pkgtools)) +endif +ifeq ($(do_cloud_tools),true) + $(call dh_all,$(pkgcloud)) +endif + +# +# per-architecture packages +# +builddirpa = $(builddir)/tools-perarch + +$(stampdir)/stamp-prepare-perarch: + @echo Debug: $@ +ifeq ($(do_any_tools),true) + rm -rf $(builddirpa) + install -d $(builddirpa) + rsync -a --exclude debian --exclude debian.master --exclude $(DEBIAN) --exclude .git -a ./ $(builddirpa)/ +endif + $(stamp) + +$(stampdir)/stamp-build-perarch: $(stampdir)/stamp-prepare-perarch install-arch-headers build-arch + @echo Debug: $@ +ifeq ($(do_linux_tools),true) +ifeq ($(do_tools_usbip),true) + chmod 755 $(builddirpa)/tools/usb/usbip/autogen.sh + cd $(builddirpa)/tools/usb/usbip && ./autogen.sh + chmod 755 $(builddirpa)/tools/usb/usbip/configure + cd $(builddirpa)/tools/usb/usbip && ./configure --prefix=$(builddirpa)/tools/usb/usbip/bin + cd $(builddirpa)/tools/usb/usbip && make install CFLAGS="-g -O2 -static" CROSS_COMPILE=$(CROSS_COMPILE) +endif +ifeq ($(do_tools_acpidbg),true) + cd $(builddirpa)/tools/power/acpi && make clean && make CFLAGS="-g -O2 -static -I$(builddirpa)/include" CROSS_COMPILE=$(CROSS_COMPILE) acpidbg +endif +ifeq ($(do_tools_rtla),true) + cd $(builddirpa)/tools/tracing/rtla && make clean && make CFLAGS='-g -O -Wall -I/usr/include/tracefs -I/usr/include/traceevent -DVERSION="\"6.8.1\""' static +endif +ifeq ($(do_tools_cpupower),true) + make -C $(builddirpa)/tools/power/cpupower \ + CROSS_COMPILE=$(CROSS_COMPILE) \ + CROSS=$(CROSS_COMPILE) \ + STATIC=true \ + CPUFREQ_BENCH=false +endif +ifeq ($(do_tools_perf),true) + cd $(builddirpa) && $(kmake) $(defconfig) + mv $(builddirpa)/.config $(builddirpa)/.config.old + sed -e 's/^# \(CONFIG_MODVERSIONS\) is not set$$/\1=y/' \ + -e 's/.*CONFIG_LOCALVERSION_AUTO.*/# CONFIG_LOCALVERSION_AUTO is not set/' \ + $(builddirpa)/.config.old > $(builddirpa)/.config + cd $(builddirpa) && $(kmake) syncconfig + cd $(builddirpa) && $(kmake) prepare + cd $(builddirpa)/tools/perf && \ + $(kmake) prefix=/usr NO_LIBTRACEEVENT=1 HAVE_CPLUS_DEMANGLE_SUPPORT=1 CROSS_COMPILE=$(CROSS_COMPILE) NO_LIBPERL=1 WERROR=0 +endif +ifeq ($(do_tools_bpftool),true) + mv $(builddirpa)/tools/bpf/bpftool/vmlinux $(builddirpa)/vmlinux + $(kmake) NO_LIBTRACEEVENT=1 CROSS_COMPILE=$(CROSS_COMPILE) -C $(builddirpa)/tools/bpf/bpftool + rm -f $(builddirpa)/vmlinux +endif +ifeq ($(do_tools_x86),true) + cd $(builddirpa)/tools/power/x86/x86_energy_perf_policy && make CROSS_COMPILE=$(CROSS_COMPILE) + cd $(builddirpa)/tools/power/x86/turbostat && make CROSS_COMPILE=$(CROSS_COMPILE) +endif +endif +ifeq ($(do_cloud_tools),true) +ifeq ($(do_tools_hyperv),true) + cd $(builddirpa)/tools/hv && make CFLAGS="-I$(headers_dir)/usr/include -I$(headers_dir)/usr/include/$(DEB_HOST_MULTIARCH)" CROSS_COMPILE=$(CROSS_COMPILE) hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon +endif +endif + $(stamp) + +.PHONY: install-perarch +install-perarch: toolspkgdir = $(CURDIR)/debian/$(tools_pkg_name) +install-perarch: cloudpkgdir = $(CURDIR)/debian/$(cloud_pkg_name) +install-perarch: $(stampdir)/stamp-build-perarch + @echo Debug: $@ + # Add the tools. +ifeq ($(do_linux_tools),true) + install -d $(toolspkgdir)/usr/lib + install -d $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +ifeq ($(do_tools_usbip),true) + install -m755 $(addprefix $(builddirpa)/tools/usb/usbip/bin/sbin/, usbip usbipd) \ + $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +endif +ifeq ($(do_tools_acpidbg),true) + install -m755 $(builddirpa)/tools/power/acpi/acpidbg \ + $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +endif +ifeq ($(do_tools_cpupower),true) + install -m755 $(builddirpa)/tools/power/cpupower/cpupower \ + $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +endif +ifeq ($(do_tools_rtla),true) + install -m755 $(builddirpa)/tools/tracing/rtla/rtla-static \ + $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release)/rtla +endif +ifeq ($(do_tools_perf),true) + install -m755 $(builddirpa)/tools/perf/perf $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +ifeq ($(do_tools_perf_jvmti),true) + install -m755 $(builddirpa)/tools/perf/libperf-jvmti.so $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +endif +ifeq ($(do_tools_perf_python),true) + install -d $(toolspkgdir)/usr/lib/python3/dist-packages/$(src_pkg_name)-tools-$(abi_release) + install -m755 $(builddirpa)/tools/perf/python/perf*.so $(toolspkgdir)/usr/lib/python3/dist-packages/$(src_pkg_name)-tools-$(abi_release) +endif +endif +ifeq ($(do_tools_bpftool),true) + install -m755 $(builddirpa)/tools/bpf/bpftool/bpftool $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +endif +ifeq ($(do_tools_x86),true) + install -m755 \ + $(addprefix $(builddirpa)/tools/power/x86/, x86_energy_perf_policy/x86_energy_perf_policy turbostat/turbostat) \ + $(toolspkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +endif +endif +ifeq ($(do_cloud_tools),true) +ifeq ($(do_tools_hyperv),true) + install -d $(cloudpkgdir)/usr/lib + install -d $(cloudpkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) + install -m755 $(addprefix $(builddirpa)/tools/hv/, hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon lsvmbus) \ + $(cloudpkgdir)/usr/lib/$(src_pkg_name)-tools-$(abi_release) +endif +endif + +.PHONY: binary-perarch +binary-perarch: toolspkg = $(tools_pkg_name) +binary-perarch: cloudpkg = $(cloud_pkg_name) +binary-perarch: install-perarch + @echo Debug: $@ +ifeq ($(do_linux_tools),true) + $(call dh_all,$(toolspkg)) +endif +ifeq ($(do_cloud_tools),true) + $(call dh_all,$(cloudpkg)) +endif + +.PHONY: binary-debs +binary-debs: binary-perarch $(addprefix binary-,$(flavours)) + @echo Debug: $@ + +build-arch-deps-$(do_flavour_image_package) += $(addprefix $(stampdir)/stamp-install-,$(flavours)) + +.PHONY: build-arch +build-arch: $(build-arch-deps-true) + @echo Debug: $@ + +binary-arch-deps-$(do_flavour_image_package) += binary-debs +binary-arch-deps-true += binary-arch-headers +ifneq ($(do_common_headers_indep),true) +binary-arch-deps-$(do_flavour_header_package) += binary-headers +endif + +.PHONY: binary-arch +binary-arch: $(binary-arch-deps-true) + @echo Debug: $@ + diff --git a/debian/rules.d/3-binary-indep.mk b/debian/rules.d/3-binary-indep.mk new file mode 100644 index 0000000000000..5a3418cd66b01 --- /dev/null +++ b/debian/rules.d/3-binary-indep.mk @@ -0,0 +1,213 @@ +.PHONY: build-indep +build-indep: + @echo Debug: $@ + +# The binary-indep dependency chain is: +# +# install-headers <- install-source <- install-tools <- install-indep <- binary-indep +# install-headers <- binary-headers +# +indep_hdrpkg = $(indep_hdrs_pkg_name) +indep_hdrdir = $(CURDIR)/debian/$(indep_hdrpkg)/usr/src/$(indep_hdrpkg) + +$(stampdir)/stamp-install-headers: $(stampdir)/stamp-prepare-indep + @echo Debug: $@ + dh_testdir + +ifeq ($(do_flavour_header_package),true) + install -d $(indep_hdrdir) + find . -path './debian' -prune -o -path './$(DEBIAN)' -prune \ + -o -path './include/*' -prune \ + -o -path './scripts/*' -prune -o -type f \ + \( -name 'Makefile*' -o -name 'Kconfig*' -o -name 'Kbuild*' -o \ + -name '*.sh' -o -name '*.pl' -o -name '*.lds' \) \ + -print | cpio -pd --preserve-modification-time $(indep_hdrdir) + cp -a scripts include $(indep_hdrdir) + (find arch -name include -type d -print | \ + xargs -n1 -i: find : -type f) | \ + cpio -pd --preserve-modification-time $(indep_hdrdir) + # Do not ship .o and .cmd artifacts in headers + find $(indep_hdrdir) -name \*.o -or -name \*.cmd -exec rm -f {} \; +endif + $(stamp) + +srcpkg = linux-source-$(release) +srcdir = $(CURDIR)/debian/$(srcpkg)/usr/src/$(srcpkg) +balldir = $(CURDIR)/debian/$(srcpkg)/usr/src/$(srcpkg)/$(srcpkg) +install-source: $(stampdir)/stamp-prepare-indep + @echo Debug: $@ +ifeq ($(do_source_package),true) + + install -d $(srcdir) +ifeq ($(do_source_package_content),true) + find . -path './debian' -prune -o -path './$(DEBIAN)' -prune -o \ + -path './.*' -prune -o -print | \ + cpio -pd --preserve-modification-time $(balldir) + (cd $(srcdir); tar cf - $(srcpkg)) | bzip2 -9c > \ + $(srcdir)/$(srcpkg).tar.bz2 + rm -rf $(balldir) + $(LN) $(srcpkg)/$(srcpkg).tar.bz2 $(srcdir)/.. +endif +endif + +.PHONY: install-tools +install-tools: toolspkg = $(tools_common_pkg_name) +install-tools: toolsbin = $(CURDIR)/debian/$(toolspkg)/usr/bin +install-tools: toolssbin = $(CURDIR)/debian/$(toolspkg)/usr/sbin +install-tools: toolsman = $(CURDIR)/debian/$(toolspkg)/usr/share/man +install-tools: toolspython = $(CURDIR)/debian/$(toolspkg)/usr/lib/python3/dist-packages +install-tools: toolsbashcomp = $(CURDIR)/debian/$(toolspkg)/usr/share/bash-completion/completions +install-tools: hosttoolspkg = $(hosttools_pkg_name) +install-tools: hosttoolsbin = $(CURDIR)/debian/$(hosttoolspkg)/usr/bin +install-tools: hosttoolsman = $(CURDIR)/debian/$(hosttoolspkg)/usr/share/man +install-tools: hosttoolssystemd = $(CURDIR)/debian/$(hosttoolspkg)/lib/systemd/system +install-tools: cloudpkg = $(cloud_common_pkg_name) +install-tools: cloudbin = $(CURDIR)/debian/$(cloudpkg)/usr/bin +install-tools: cloudsbin = $(CURDIR)/debian/$(cloudpkg)/usr/sbin +install-tools: cloudman = $(CURDIR)/debian/$(cloudpkg)/usr/share/man +install-tools: $(stampdir)/stamp-prepare-indep $(stampdir)/stamp-build-perarch + @echo Debug: $@ + +ifeq ($(do_tools_common),true) + rm -rf $(builddir)/tools + install -d $(builddir)/tools + for i in *; do $(LN) $(CURDIR)/$$i $(builddir)/tools/; done + rm $(builddir)/tools/tools + rsync -a tools/ $(builddir)/tools/tools/ + + install -d $(toolsbin) + install -d $(toolssbin) + install -d $(toolsman)/man1 + install -d $(toolsman)/man8 + install -d $(toolsbashcomp) + install -d $(toolspython) + + install -m755 debian/tools/generic $(toolsbin)/usbip + install -m755 debian/tools/generic $(toolsbin)/usbipd + install -m644 $(CURDIR)/tools/usb/usbip/doc/*.8 $(toolsman)/man8/ + + install -m755 debian/tools/generic $(toolsbin)/cpupower + install -m644 $(CURDIR)/tools/power/cpupower/man/*.1 $(toolsman)/man1/ + + install -m755 debian/tools/generic $(toolsbin)/rtla + + install -m755 debian/tools/generic $(toolsbin)/perf + + install -m755 debian/tools/generic $(toolssbin)/bpftool + make -C $(builddir)/tools/tools/bpf/bpftool doc + install -m644 $(builddir)/tools/tools/bpf/bpftool/Documentation/*.8 \ + $(toolsman)/man8 + install -m644 $(builddir)/tools/tools/bpf/bpftool/bash-completion/bpftool \ + $(toolsbashcomp) + + install -m755 debian/tools/generic $(toolsbin)/x86_energy_perf_policy + install -m755 debian/tools/generic $(toolsbin)/turbostat + + cd $(builddir)/tools/tools/perf && make NO_LIBTRACEEVENT=1 man + install -m644 $(builddir)/tools/tools/perf/Documentation/*.1 \ + $(toolsman)/man1 + + install -m644 $(CURDIR)/tools/power/x86/x86_energy_perf_policy/*.8 $(toolsman)/man8 + install -m644 $(CURDIR)/tools/power/x86/turbostat/*.8 $(toolsman)/man8 + +ifeq ($(do_tools_perf_python),true) + # Python wrapper module for python-perf + install -d $(toolspython)/perf + install -m755 debian/tools/python-perf.py $(toolspython)/perf/__init__.py +endif +ifeq ($(do_cloud_tools),true) +ifeq ($(do_tools_hyperv),true) + install -d $(cloudsbin) + install -m755 debian/tools/generic $(cloudsbin)/hv_kvp_daemon + install -m755 debian/tools/generic $(cloudsbin)/hv_vss_daemon + install -m755 debian/tools/generic $(cloudsbin)/hv_fcopy_daemon + install -m755 debian/tools/generic $(cloudsbin)/lsvmbus + install -m755 debian/cloud-tools/hv_get_dhcp_info $(cloudsbin) + install -m755 debian/cloud-tools/hv_get_dns_info $(cloudsbin) + install -m755 debian/cloud-tools/hv_set_ifconfig $(cloudsbin) + + install -d $(cloudman)/man8 + install -m644 $(CURDIR)/tools/hv/*.8 $(cloudman)/man8 +endif +endif + +ifeq ($(do_tools_acpidbg),true) + install -m755 debian/tools/generic $(toolsbin)/acpidbg +endif + +endif + +ifeq ($(do_tools_host),true) + install -d $(hosttoolsbin) + install -d $(hosttoolsman)/man1 + install -d $(hosttoolssystemd) + + install -m 755 $(CURDIR)/tools/kvm/kvm_stat/kvm_stat $(hosttoolsbin)/ + install -m 644 $(CURDIR)/tools/kvm/kvm_stat/kvm_stat.service \ + $(hosttoolssystemd)/ + + cd $(builddir)/tools/tools/kvm/kvm_stat && make NO_LIBTRACEEVENT=1 man + install -m644 $(builddir)/tools/tools/kvm/kvm_stat/*.1 \ + $(hosttoolsman)/man1 +endif + +$(stampdir)/stamp-prepare-indep: + @echo Debug: $@ + dh_prep -i + $(stamp) + +.PHONY: install-indep +install-indep: $(stampdir)/stamp-install-headers install-source install-tools + @echo Debug: $@ + +# This is just to make it easy to call manually. Normally done in +# binary-indep target during builds. +.PHONY: binary-headers +binary-headers: $(stampdir)/stamp-prepare-indep $(stampdir)/stamp-install-headers + @echo Debug: $@ + dh_installchangelogs -p$(indep_hdrpkg) + dh_installdocs -p$(indep_hdrpkg) + dh_compress -p$(indep_hdrpkg) + dh_fixperms -p$(indep_hdrpkg) + dh_installdeb -p$(indep_hdrpkg) + $(lockme) dh_gencontrol -p$(indep_hdrpkg) + dh_md5sums -p$(indep_hdrpkg) + dh_builddeb -p$(indep_hdrpkg) + +binary-indep: cloudpkg = $(cloud_common_pkg_name) +binary-indep: hosttoolspkg = $(hosttools_pkg_name) +binary-indep: install-indep + @echo Debug: $@ + dh_installchangelogs -i + dh_installdocs -i + dh_compress -i + dh_fixperms -i +ifeq ($(do_tools_common),true) +ifeq ($(do_cloud_tools),true) +ifeq ($(do_tools_hyperv),true) + dh_installinit -p$(cloudpkg) -n --name hv-kvp-daemon + dh_installinit -p$(cloudpkg) -n --name hv-vss-daemon + dh_installinit -p$(cloudpkg) -n --name hv-fcopy-daemon + dh_installudev -p$(cloudpkg) -n --name hv-kvp-daemon + dh_installudev -p$(cloudpkg) -n --name hv-vss-daemon + dh_installudev -p$(cloudpkg) -n --name hv-fcopy-daemon + dh_systemd_enable -p$(cloudpkg) + dh_installinit -p$(cloudpkg) -o --name hv-kvp-daemon + dh_installinit -p$(cloudpkg) -o --name hv-vss-daemon + dh_installinit -p$(cloudpkg) -o --name hv-fcopy-daemon + dh_systemd_start -p$(cloudpkg) +endif + # Keep intel_sgx service disabled by default, so add it after dh_systemd_enable + # and dh_systemd_start are called: + dh_installinit -p$(cloudpkg) --no-start --no-enable --name intel-sgx-load-module +endif +endif +ifeq ($(do_tools_host),true) + # Keep kvm_stat.service disabled by default (after dh_systemd_enable + # and dh_systemd_start: + dh_installinit -p$(hosttoolspkg) --no-enable --no-start --name kvm_stat +endif + dh_installdeb -i + $(lockme) dh_gencontrol -i + dh_md5sums -i + dh_builddeb -i diff --git a/debian/rules.d/4-checks.mk b/debian/rules.d/4-checks.mk new file mode 100644 index 0000000000000..7cb84e9f71e59 --- /dev/null +++ b/debian/rules.d/4-checks.mk @@ -0,0 +1,18 @@ +# Check the signature of staging modules +module-signature-check-%: $(stampdir)/stamp-install-% + @echo Debug: $@ + $(DROOT)/scripts/checks/module-signature-check "$*" \ + "$(DROOT)/$(mods_pkg_name)-$*" \ + "$(DROOT)/$(mods_extra_pkg_name)-$*" \ + $(do_skip_checks) + +checks-%: module-signature-check-% + @echo Debug: $@ + +# Check the config against the known options list. +config-prepare-check-%: $(stampdir)/stamp-prepare-tree-% + @echo Debug: $@ +ifneq ($(do_skip_checks),true) + python3 $(DROOT)/scripts/misc/annotations -f $(commonconfdir)/annotations \ + --arch $(arch) --flavour $* --check $(builddir)/build-$*/.config +endif diff --git a/debian/scripts/checks/final-checks b/debian/scripts/checks/final-checks new file mode 100755 index 0000000000000..98986b341bdab --- /dev/null +++ b/debian/scripts/checks/final-checks @@ -0,0 +1,47 @@ +#!/bin/bash + +debian="$1" +abi="$2" + +archs=$(awk '/^Architecture:/ { $1=""; for (i=1; i<=NF; i++) { if ($i != "all") { print $i }}}' debian/control | sort -u) + +fail=0 + +failure() +{ + echo "EE: $*" 1>&2 + fail=1 +} + +for arch in $archs +do + if [ ! -f "$debian/rules.d/$arch.mk" ]; then + continue + fi + + image_pkg=$(awk -F '\\s*=\\s*' '$1 == "do_flavour_image_package" { print $2 }' "$debian/rules.d/$arch.mk") + if [ "$image_pkg" = "false" ]; then + continue + fi + + flavours=$( + awk '/^\s*flavours\s*=/{ + sub(/^\s*flavours\s*=\s*/, ""); + print + }' "$debian/rules.d/$arch.mk") + for flavour in $flavours + do + if [ -d debian/certs ]; then + if ! python3 debian/scripts/misc/annotations --export -c CONFIG_SYSTEM_TRUSTED_KEYS --arch "$arch" --flavour "$flavour" | grep -q '^CONFIG_SYSTEM_TRUSTED_KEYS="debian/canonical-certs.pem"$' ; then + failure "'CONFIG_SYSTEM_TRUSTED_KEYS=\"debian/canonical-certs.pem\"' is required" + fi + fi + if [ -d debian/revoked-certs ]; then + if ! python3 debian/scripts/misc/annotations --export -c CONFIG_SYSTEM_REVOCATION_KEYS --arch "$arch" --flavour "$flavour" | grep -q '^CONFIG_SYSTEM_REVOCATION_KEYS="debian/canonical-revoked-certs.pem"$' ; then + failure "'CONFIG_SYSTEM_REVOCATION_KEYS=\"debian/canonical-revoked-certs.pem\"' is required" + fi + fi + done +done + +exit "$fail" diff --git a/debian/scripts/checks/module-signature-check b/debian/scripts/checks/module-signature-check new file mode 100755 index 0000000000000..2df07a4c324ea --- /dev/null +++ b/debian/scripts/checks/module-signature-check @@ -0,0 +1,91 @@ +#!/bin/bash -eu + +flavor="${1}" +mods_dir="${2}" +mods_extra_dir="${3}" + +skip_checks=${4:-} +case "${skip_checks,,}" in + 1|true|yes) skip_checks=1 ;; + *) skip_checks=0 ;; +esac + +echo "II: Checking signature of staging modules for ${flavor}..." + +root=$(dirname "$(realpath -e "${0}")")/../../.. +. "${root}"/debian/debian.env + +# Collect the signature-inclusion files +sig_incs=() +for d in debian "${DEBIAN}" ; do + if [ -f "${root}"/"${d}"/signature-inclusion ] ; then + sig_incs+=("${root}"/"${d}"/signature-inclusion) + fi +done + +if [ "${#sig_incs[@]}" -gt 0 ] ; then + echo "II: Use signature inclusion file(s):" + printf " %s\n" "${sig_incs[@]}" + sig_all=0 +else + echo "WW: Signature inclusion file(s) missing" + echo "II: All modules must be signed" + sig_all=1 +fi + +if ! [ -d "${mods_dir}" ] ; then + echo "EE: Modules directory missing:" + echo " ${mods_dir}" + if [ ${skip_checks} -eq 1 ] ; then + echo "WW: Explicitly asked to ignore failures" + echo "II: Done" + exit 0 + fi + exit 1 +fi + +echo "II: Checking modules directory:" +echo " ${mods_dir}" +mods_dirs=("${mods_dir}") + +if [ -d "${mods_extra_dir}" ] ; then + echo " ${mods_extra_dir}" + mods_dirs+=("${mods_extra_dir}") +fi + +pass=0 +fail=0 +while IFS= read -r mod ; do + is=0 + if /sbin/modinfo "${mod}" | grep -q "^signature:" ; then + # Module is signed + is=1 + fi + + must=0 + if [ ${sig_all} -eq 1 ] || grep -qFx "${mod##*/}" "${sig_incs[@]}" ; then + # Module must be signed + must=1 + fi + + case "${is}${must}" in + 00) echo " PASS (unsigned) : ${mod##*/}" ; pass=$((pass + 1)) ;; + 01) echo " FAIL (unsigned) : ${mod##*/}" ; fail=$((fail + 1)) ;; + 10) echo " FAIL (signed) : ${mod##*/}" ; fail=$((fail + 1)) ;; + 11) echo " PASS (signed) : ${mod##*/}" ; pass=$((pass + 1)) ;; + esac +done < <(find "${mods_dirs[@]}" -path '*/drivers/staging/*.ko' | sort) + +echo "II: Checked $((pass + fail)) modules : ${pass} PASS, ${fail} FAIL" + +if [ ${fail} -ne 0 ] ; then + if [ ${skip_checks} -eq 1 ] ; then + echo "WW: Explicitly asked to ignore failures" + else + echo "EE: Modules signature failures" + exit 1 + fi +fi + +echo "II: Done" +exit 0 diff --git a/debian/scripts/control-create b/debian/scripts/control-create new file mode 100755 index 0000000000000..f2af8b9bb2f47 --- /dev/null +++ b/debian/scripts/control-create @@ -0,0 +1,62 @@ +#!/bin/bash + +. debian/debian.env + +vars=$1 +any_signed=$2 + +. $vars + +[ "$provides" != '' ] && provides="$provides, " + +flavour=$(basename $vars | sed 's/.*\.//') +stub="${DEBIAN}/control.d/flavour-control.stub debian/control.d/flavour-buildinfo.stub" +if [ "$any_signed" = 'true' ]; then + sign_me_pkg="-unsigned" + sign_me_txt=" unsigned" + sign_peer_pkg="" +else + sign_me_pkg="" + sign_me_txt="" + sign_peer_pkg="-unsigned" +fi + +cat $stub | grep -v '^#' | sed \ + -e "s#FLAVOUR#$flavour#g" \ + -e "s#DESC#$desc#g" \ + -e "s#ARCH#$arch#g" \ + -e "s#SUPPORTED#$supported#g" \ + -e "s#TARGET#$target#g" \ + -e "s#BOOTLOADER#$bootloader#g" \ + -e "s#=PROVIDES=#$provides#g" \ + -e "s#=CONFLICTS=#$conflicts#g" \ + -e "s#=SIGN-ME-PKG=#$sign_me_pkg#g" \ + -e "s#=SIGN-ME-TXT=#$sign_me_txt#g" \ + -e "s#=SIGN-PEER-PKG=#$sign_peer_pkg#g" + +while read package version extras +do + module="$package" + module_type= + + # Module arch parameters are skipped here, so a package section will + # be generated for each flavour, and its Architecture will be set to + # all architectures with that flavour. Even that is being generated, + # it doesn't follow all of them will be built. That's to work-around + # dkms_exclude/dkms_include that manipulates supported architectures + # in $(DEBIAN)/rules.d/$(arch).mk. + for param in $extras; do + case "$param" in + modulename=*) module="${param#modulename=}" ;; + type=*) module_type="${param#type=}" ;; + *) continue ;; + esac + done + + [ "$module_type" = "standalone" ] || continue + + cat debian/control.d/flavour-module.stub | grep -v '^#' | sed \ + -e "s#ARCH#$arch#g" \ + -e "s#MODULE#$module#g" \ + -e "s#FLAVOUR#$flavour#g" +done <"${DEBIAN}/dkms-versions" diff --git a/debian/scripts/dkms-build b/debian/scripts/dkms-build new file mode 100755 index 0000000000000..de97466d587a8 --- /dev/null +++ b/debian/scripts/dkms-build @@ -0,0 +1,271 @@ +#!/bin/sh +set -e + +dkms_dir="$1" +abi_flavour="$2" +sign="$3" +pkgname="$4" +pkgdir="$5" +dbgpkgdir="$6" +package="$7" +shift 7 + +here=$(dirname "$(readlink -f "${0}")") + +srcdir=$(pwd) +cd "$dkms_dir" || exit 1 + +built_using_record() +{ + local subst="$1" + local built_using="$2" + if [ ! -f "$subst" ]; then + touch "$subst" + fi + if ! grep -q -s "^linux:BuiltUsing=" "$subst"; then + echo "linux:BuiltUsing=" >>"$subst" + fi + sed -i -e "s/^\(linux:BuiltUsing=.*\)/\1$built_using, /" "$subst" +} + +# ABI: returns present in $? and located path in lpackage_path when found. +package_present() +{ + for lpackage_path in "$1"_*.deb + do + break + done + [ -f "$lpackage_path" ] +} + +# Download and extract the DKMS package -- note there may be more +# than one package to install. +for package_path in "$@" +do + package_file=$(basename "$package_path") + echo "II: dkms-build downloading $package ($package_file)" + rpackage=$( echo "$package_path" | sed -e 's@.*/@@' -e 's@_.*@@' ) + lpackage=$( echo "$rpackage" | sed -e 's@=.*@@' ) + + while true + do + if package_present "$lpackage"; then + break + fi + case "$package_path" in + pool/*) + # Attempt download from the launchpad librarian first. + "$here/file-downloader" "https://launchpad.net/ubuntu/+archive/primary/+files/$package_file" || true + if package_present "$lpackage"; then + break + fi + + # Download from the available pools. + for pool in $( grep -h '^deb ' /etc/apt/sources.list /etc/apt/sources.list.d/*.list | awk '{print $2}' | sort -u ) + do + if package_present "$lpackage"; then + break + fi + url="$pool/$package_path" + "$here/file-downloader" "$url" && break || true + # No components in PPAs. + url=$(echo "$url" | sed -e 's@/pool/[^/]*/@/pool/main/@') + "$here/file-downloader" "$url" && break || true + done + ;; + http*:*) + "$here/file-downloader" "$package_path" + ;; + */*) + cp -p "$package_path" . + ;; + *) + apt-get download "$rpackage" + ;; + esac + break + done + if ! package_present "$lpackage"; then + echo "EE: $lpackage not found" + exit 1 + fi + + dpkg -x "$lpackage"_*.deb "$package" + + lversion=$( echo "$lpackage_path" | sed -e 's@.*/@@' -e 's@_[^_]*$@@' -e 's@.*_@@') + #built_using_record "$srcdir/debian/$pkgname.substvars" "$built_using$lpackage (= $lversion)" +done + +# Pick out the package/version from the dkms.conf. +for dkms_conf in "$package/usr/src"/*/"dkms.conf" +do + break +done + +# It seems some packages have a # in the name which works fine if the +# package is installed directly, but not so much if we build it out +# of the normal location. +sed -i -e '/^PACKAGE_NAME=/ s/#//g' "$dkms_conf" + +# Run any dkms-package specfic configuration steps +dkms_config_specific="$srcdir/$0-configure--$package" +dkms_config_generic=$(echo "$dkms_config_specific" | sed -e 's/-[0-9][0-9]*$/-N/') +for dkms_config in "$dkms_config_specific" "$dkms_config_generic" +do + if [ -z "$dkms_config" -o ! -e "$dkms_config" ]; then + continue + fi + echo "II: dkms-build-configure $(basename "$dkms_config") found, executing" + "$dkms_config" \ + "$srcdir" \ + "$dkms_conf" \ + "$dkms_dir" \ + "$abi_flavour" \ + "$sign" \ + "$pkgname" \ + "$pkgdir" \ + "$dbgpkgdir" \ + "$package" \ + "$@" || exit 1 + break +done + +cat - <<'EOF' >>"$dkms_conf" +POST_BUILD="ubuntu-save-objects ${dkms_tree}/${PACKAGE_NAME}/${PACKAGE_VERSION}/build ${dkms_tree}/${PACKAGE_NAME}/${PACKAGE_VERSION}/objects $POST_BUILD" +EOF +ubuntu_script="$(dirname "$dkms_conf")/ubuntu-save-objects" +cat - <<'EOF' >"$ubuntu_script" +#!/bin/sh +from="$1" +to="$2" +script="$3" +shift 2 + +# Copy the objects. +echo "II: copying objects to '$to'" +mkdir -p "$to" +(cd "$from" && find -name \*.o -o -name \*.mod | cpio -Lpd "$to") + +# Call the original post_install script if there is one. +[ "$script" = '' ] && exit 0 + +shift +exec "$(dirname "$0")/$script" "$@" +EOF +chmod +x "$ubuntu_script" +dkms_package=$( sed -ne 's/PACKAGE_NAME="\(.*\)"/\1/p' "$dkms_conf" ) +dkms_version=$( sed -ne 's/PACKAGE_VERSION="\(.*\)"/\1/p' "$dkms_conf" ) + +# Build the DKMS binaries. +echo "II: dkms-build building $package" +fakeroot="" +[ $(id -u) -ne 0 ] && fakeroot="/usr/bin/fakeroot" +rc=0 +$fakeroot /usr/sbin/dkms build --no-prepare-kernel --no-clean-kernel \ + -k "$abi_flavour" ${ARCH:+-a $ARCH} \ + --sourcetree "$dkms_dir/source" \ + --dkmstree "$dkms_dir/build" \ + --kernelsourcedir "$dkms_dir/headers/linux-headers-$abi_flavour" \ + "$dkms_conf" || rc=$? + +# Find the log and add it to our own. +for log in "$dkms_dir/build/$dkms_package/$dkms_version/$abi_flavour"/*/"log/make.log" "$dkms_dir/build/$dkms_package/$dkms_version/build/make.log" +do + if [ -f "$log" ]; then + sed -e "s@$dkms_dir@<>@g" <"$log" + break + fi +done + +# If this build failed then exit here. +[ "$rc" != 0 ] && exit "$rc" + +# Install the modules with debug symbols we possibly built, +# and strip the original modules for the next install step. +if [ -n "$dbgpkgdir" ]; then + dbgpkgdir="$dbgpkgdir/$package" + echo "II: dkms-build installing $package into $dbgpkgdir (debug symbols)" + install -d "$dbgpkgdir" + find "$dkms_dir/build/$dkms_package/$dkms_version/$abi_version" -name \*.ko | + while read module; do + vmodule=$( basename "$module" ) + + # Check for '.debug_info' section in order to copy module. + # Useful if debug symbols are requested but not built for + # any reason (including not yet supported by DKMS package). + # Strip module just in case even if section isn't present. + if ${CROSS_COMPILE}objdump -h -j '.debug_info' "$module" >/dev/null 2>&1 + then + echo "copying $vmodule" + cp "$module" "$dbgpkgdir" + else + echo "ignoring $vmodule (missing debug symbols)" + fi + + # Just 'strip -g' as '/usr/sbin/dkms' does. + echo "stripping $vmodule" + strip -g "$module" + done +fi + +# Install and optionally sign the modules we have built. +pkgdir="$pkgdir/$package" +echo "II: dkms-build installing $package into $pkgdir" +install -d "$pkgdir" +find "$dkms_dir/build/$dkms_package/$dkms_version/$abi_version" -name \*.ko | +while read module; do + vmodule=$( basename "$module" ) + case "$sign" in + --*) + echo "copying $vmodule" + cp "$module" "$pkgdir" + ;; + *) + echo "signing $vmodule" + $sign "$module" "$pkgdir/$vmodule" + ;; + esac +done + +find "$dkms_dir/build/$dkms_package/$dkms_version/objects" -name \*.o -print | \ +while read object +do + "$srcdir/debian/scripts/fix-filenames" "$object" "$dkms_dir" +done + +# This assumes that .mod files are in the top level build tree +# If there are ever .mod files in sub-directories, the dirname of objectlist needs to be stripped as well +find "$dkms_dir/build/$dkms_package/$dkms_version/objects" -name \*.mod -print | \ +while read objectlist +do + sed "s|^$dkms_dir/build/$dkms_package/$dkms_version/build/||" -i $objectlist +done + +# Finally see if there is a dkms-package specific post processor present. Hand +# it the original source directory, destination package directory, the objects +# as squirreled away, and the log in case it is useful. Finally pass a formed +# signing command line in case we need to do that. +dkms_build_specific="$srcdir/$0--$package" +dkms_build_generic=$(echo "$dkms_build_specific" | sed -n -e 's/-[0-9][0-9]*[a-z]*$/-N/p') +for dkms_build in "$dkms_build_specific" "$dkms_build_generic" +do + if [ -z "$dkms_build" -o ! -e "$dkms_build" ]; then + continue + fi + echo "II: dkms-build override $(basename "$dkms_build") found, executing" + "$dkms_build" \ + "$srcdir" \ + "$dkms_dir/build/$dkms_package/$dkms_version/objects" \ + "$log" \ + "$dkms_dir" \ + "$abi_flavour" \ + "$sign" \ + "$pkgname" \ + "$pkgdir" \ + "$dbgpkgdir" \ + "$package" \ + "$@" || exit 1 + break +done + +echo "II: dkms-build build $package complete" diff --git a/debian/scripts/dkms-build--nvidia-N b/debian/scripts/dkms-build--nvidia-N new file mode 100755 index 0000000000000..22e60cafa0878 --- /dev/null +++ b/debian/scripts/dkms-build--nvidia-N @@ -0,0 +1,112 @@ +#!/bin/sh +set -e + +srcdir="$1" +objects="$2" +log="$3" +shift 3 + +dkms_dir="$1" +abi_flavour="$2" +sign="$3" +pkgname="$4" +pkgdir="$5" +dbgpkgdir="$6" +package="$7" +shift 7 + +build="$( dirname "$objects" )/build" + +# Copy over the objects ready for reconstruction. The objects copy +# contains the *.o files. For our purposes we only want the *.o files, +# elide the rest. And .mod files for ld linking in recentish kernels. +mkdir -p "$pkgdir/bits/scripts" +( + gcc_variant1=$(gcc --version | head -1 | sed -e 's/^gcc/GCC:/') + gcc_variant2=$(gcc --version | head -1 | sed -e 's/^\(gcc\) \((.*)\) \(.*\)$/\1 version \3 \2/') + cd "$objects" || exit 1 + find -name \*.o -o -name \*.mod | \ + while read file + do + cp --parents "$file" "$pkgdir/bits" + "$srcdir/debian/scripts/fix-filenames" "$pkgdir/bits/$file" "$gcc_variant1" + "$srcdir/debian/scripts/fix-filenames" "$pkgdir/bits/$file" "$gcc_variant2" + done +) + +# Install the support files we need. +echo "II: copying support files ..." +for lds_src in \ + "$dkms_dir/headers/linux-headers-$abi_flavour/scripts/module.lds" \ + "/usr/src/linux-headers-$abi_flavour/scripts/module.lds" \ + "$dkms_dir/headers/linux-headers-$abi_flavour/scripts/module-common.lds" \ + "/usr/src/linux-headers-$abi_flavour/scripts/module-common.lds" +do + [ ! -f "$lds_src" ] && continue + echo "II: copying support files ... found $lds_src" + cp "$lds_src" "$pkgdir/bits/scripts" + break +done + +# Build helper scripts. +cat - <<'EOL' >"$pkgdir/bits/BUILD" +[ "$1" = "unsigned" ] && { signed_only=:; shift; } +[ "$1" = "nocheck" ] && { check_only=:; shift; } +EOL +grep /usr/bin/ld.bfd "$log" | grep -v scripts/genksyms/genksyms | grep -v "warning:\|NOTE:" | sed -e "s@$build/@@g" >>"$pkgdir/bits/BUILD" +sed -e 's/.*-o *\([^ ]*\) .*/rm -f \1/g' <"$pkgdir/bits/BUILD" >"$pkgdir/bits/CLEAN" + +# As the builds contain the absolute filenames as used. Use RECONSTRUCT to +# rebuild the .ko's, sign them, pull off the signatures and then finally clean +# up again. +( + cd "$pkgdir/bits" + + # Add checksum check. + echo "\$check_only sha256sum -c SHA256SUMS || exit 1" >>"$pkgdir/bits/BUILD" + + # Add .ko handling to the CLEAN/BUILD dance. + for ko in "$pkgdir"/*.ko + do + ko=$(basename "$ko") + echo "\$signed_only cat '$ko' '$ko.sig' >'../$ko'" >>"$pkgdir/bits/BUILD" + echo "\$signed_only rm -f '$ko'" >>"$pkgdir/bits/BUILD" + echo "rm -f '../$ko'" >>"$pkgdir/bits/CLEAN" + done + + # Clear out anything we are not going to distribute and build unsigned .kos. + sh ./CLEAN + sh ./BUILD unsigned nocheck + + if [ "$sign" = "--custom" ]; then + # We are building for and archive custom signing upload. Keep everything. + : + elif [ "$sign" = "--lrm" ]; then + # We are in the LRM build; grab sha256 checksums and clean up. + sha256sum -b *.ko >"SHA256SUMS" + sh ./CLEAN + + else + # We are in the main kernel, put the .kos together as we will + # on the users machine, sign them, and keep just the signature. + : >"SHA256SUMS" + for ko in *.ko + do + echo "detached-signature $ko" + $sign "$ko" "$ko.signed" + length=$( stat --format %s "$ko" ) + dd if="$ko.signed" of="$ko.sig" bs=1 skip="$length" 2>/dev/null + + rm -f "$ko.signed" + # Keep a checksum of the pre-signed object so we can check it is + # built correctly in LRM. + sha256sum -b "$ko" >>"SHA256SUMS" + done + + # Clean out anything which not a signature. + mv "$pkgdir/bits/"*.sig "$pkgdir" + mv "$pkgdir/bits/SHA256SUMS" "$pkgdir" + find "$pkgdir" -name \*.sig -prune -o -name SHA256SUMS -prune -o -type f -print | xargs rm -f + find "$pkgdir" -depth -type d -print | xargs rmdir --ignore-fail-on-non-empty + fi +) diff --git a/debian/scripts/dkms-build-configure--zfs b/debian/scripts/dkms-build-configure--zfs new file mode 100755 index 0000000000000..09db28802ee72 --- /dev/null +++ b/debian/scripts/dkms-build-configure--zfs @@ -0,0 +1,24 @@ +#!/bin/sh +set -e + +srcdir="$1" +dkms_conf="$2" +shift 2 + +dkms_dir="$1" +abi_flavour="$2" +sign="$3" +pkgname="$4" +pkgdir="$5" +dbgpkgdir="$6" +package="$7" +shift 7 + +# ZFS debug symbols are enabled in dkms.conf via PACKAGE_CONFIG file. +if [ -n "$dbgpkgdir" ]; then + echo "enable zfs debug symbols" + pkg_cfg="$(dirname "$dkms_conf")/pkg_cfg" + echo 'ZFS_DKMS_ENABLE_DEBUGINFO=yes' >"$pkg_cfg" + echo 'ZFS_DKMS_DISABLE_STRIP=yes' >>"$pkg_cfg" + sed -i "s,^\(PACKAGE_CONFIG=\).*,\1$pkg_cfg," $dkms_conf +fi diff --git a/debian/scripts/file-downloader b/debian/scripts/file-downloader new file mode 100755 index 0000000000000..0ebfb4de24194 --- /dev/null +++ b/debian/scripts/file-downloader @@ -0,0 +1,34 @@ +#!/bin/sh + +if [ "$#" -ne 1 ]; then + echo "Usage: $0 " 1>&2 + exit 1 +fi +url="$1" + +to=$(basename "$url") + +count=0 +what='fetching' +while : +do + if [ "$count" -eq 20 ]; then + echo "EE: excessive redirects" 1>&2 + exit 1 + fi + count=$(($count+1)) + + echo "II: $what $url" + + curl --silent --fail --show-error "$url" -o "$to" -D "$to.hdr" || exit 1 + redirect=$(awk '/^Location: / {gsub(/^[[:space:]]+|[[:space:]]+$/,"",$2); print $2;}' "$to.hdr") + [ -z "$redirect" ] && break + what=' following' + + url=$(echo "$redirect" | sed -e 's@https://launchpadlibrarian.net/@http://launchpadlibrarian.net/@') + if [ "$redirect" != "$url" ]; then + echo "II: fixing $redirect" + fi +done + +exit 0 diff --git a/debian/scripts/fix-filenames.c b/debian/scripts/fix-filenames.c new file mode 100644 index 0000000000000..9bd144a6efa8c --- /dev/null +++ b/debian/scripts/fix-filenames.c @@ -0,0 +1,80 @@ +/* + * fix-filenames: find a specified pathname prefix and remove it from + * C strings. + * + * Copyright (C) 2018 Canonical Ltd. + * Author: Andy Whitcroft + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +int +main(int argc, char *argv[]) +{ + int rc; + char *in_name; + char *prefix; + int prefix_len; + int in_fd; + struct stat in_info; + char *in; + off_t size; + int length; + + if (argc != 3) { + fprintf(stderr, "Usage: %s \n", argv[0]); + exit(1); + } + in_name = argv[1]; + prefix = argv[2]; + prefix_len = strlen(prefix); + + in_fd = open(in_name, O_RDWR); + if (in_fd < 0) { + perror("open input failed"); + exit(1); + } + + rc = fstat(in_fd, &in_info); + if (rc < 0) { + perror("fstat input failed"); + exit(1); + } + size = in_info.st_size; + + in = mmap((void *)0, size, PROT_READ|PROT_WRITE, MAP_SHARED, in_fd, (off_t)0); + if (!in) { + perror("mmap failed"); + exit(1); + } + + for (; size > 0; size--, in++) { + if (*in != *prefix) + continue; + if (strncmp(in, prefix, prefix_len) != 0) + continue; + /* In the case of an exact match there there is nothing to move. */ + if (in[prefix_len] == '\0') + length = 0; + /* If this is a filename, strip the leading slash. */ + else if (in[prefix_len] == '/') + length = strlen(in + prefix_len + 1) + 1; + /* Otherwise just keep the suffix. */ + else + length = strlen(in + prefix_len) + 1; + + /* + * Copy the suffix portion down to the start and clear + * the remainder of the space to 0. + */ + memmove(in, in + prefix_len + 1, length); + memset(in + length, '\0', prefix_len); + } +} diff --git a/debian/scripts/link-headers b/debian/scripts/link-headers new file mode 100755 index 0000000000000..fb42dbd12e4df --- /dev/null +++ b/debian/scripts/link-headers @@ -0,0 +1,42 @@ +#!/bin/bash -e + +. debian/debian.env + +hdrdir="$1" +symdir="$2" +flavour="$3" + +echo "Symlinking and copying headers for $flavour..." + +excludes="( -path ./debian -prune -o -path ./${DEBIAN} -prune -o -path ./.git ) -prune -o" + +( +find . $excludes -type f \ + \( -name 'Makefile*' -o -name 'Kconfig*' -o -name 'Kbuild*' -o \ + -name '*.sh' -o -name '*.pl' -o -name '*.lds' \) -print +find ./include ./scripts -name .gitignore -prune -o -type f -print +find ./include -mindepth 1 -maxdepth 1 $excludes -type d -print +) | ( +while read file; do + dir=$file + lastdir=$file + + if [ -e "$hdrdir/$file" -o -L "$hdrdir/$file" ]; then + continue + fi + + while [ ! -e "$hdrdir/$dir" -a ! -L "$hdrdir/$dir" ]; do + lastdir=$dir + dir=`dirname $dir` + done + # If the last item to exist is a symlink we assume all is good + if [ ! -L "$hdrdir/$dir" ]; then + # Turns things like "./foo" into "../" + deref="`echo -n $lastdir | sed -e 's/^\.//' -e's,/[^/]*,../,g'`" + item="`echo -n $lastdir | sed -e 's/^\.\///'`" + ln -s $deref$symdir/$item $hdrdir/$item + fi +done +) + +exit diff --git a/debian/scripts/link-lib-rust b/debian/scripts/link-lib-rust new file mode 100755 index 0000000000000..0bea9729431d2 --- /dev/null +++ b/debian/scripts/link-lib-rust @@ -0,0 +1,17 @@ +#!/bin/bash -e + +. debian/debian.env + +hdrdir="$1" +symdir="$2" +flavour="$3" + +echo "Symlinking and copying Rust files for $flavour..." + +# Symlink Rust folder +item=rust +relpath=$(echo $symdir | sed s/headers/lib-rust/)-$flavour/$item +echo ln -s ../$relpath $hdrdir/$item +ln -s ../$relpath $hdrdir/$item + +exit diff --git a/debian/scripts/misc/annotations b/debian/scripts/misc/annotations new file mode 100755 index 0000000000000..3a05fe96343e3 --- /dev/null +++ b/debian/scripts/misc/annotations @@ -0,0 +1,34 @@ +#!/usr/bin/env python3 +# -*- mode: python -*- + +# This file is not installed; it's just to run annotations from inside a source +# distribution without installing it in the system. + +import sys + +# Prevent generating .pyc files on import +# +# We may end up adding these files to our git repos by mistake, so simply +# prevent generating them in advance. +# +# There's a tiny performance penalty with this, because python needs to +# re-generate the bytecode on-the-fly every time the script is executed, but +# this overhead is absolutely negligible compared the rest of the kernel build +# time. +sys.dont_write_bytecode = True + +import os # noqa: E402 Import not at top of file +from kconfig import run # noqa: E402 Import not at top of file + + +# Update PATH to make sure that annotations can be executed directly from the +# source directory. +def update_path(): + script_dir = os.path.dirname(os.path.abspath(__file__)) + current_path = os.environ.get("PATH", "") + new_path = f"{script_dir}:{current_path}" + os.environ["PATH"] = new_path + + +update_path() +exit(run.main()) diff --git a/debian/scripts/misc/find-missing-sauce.sh b/debian/scripts/misc/find-missing-sauce.sh new file mode 100755 index 0000000000000..2bdcf72607bb7 --- /dev/null +++ b/debian/scripts/misc/find-missing-sauce.sh @@ -0,0 +1,15 @@ +#!/bin/bash +# +# Find the 'UBUNTU: SAUCE:' patches that have been dropped from +# the previous release. +# +PREV_REL=focal +PREV_REPO=git://kernel.ubuntu.com/ubuntu/ubuntu-${PREV_REL}.git + +git fetch ${PREV_REPO} master-next +git log --pretty=oneline FETCH_HEAD|grep SAUCE|while read c m;do echo $m;done |sort > $$.prev-rel +git log --pretty=oneline |grep SAUCE|while read c m;do echo $m;done |sort > $$.curr-rel + +diff -u $$.prev-rel $$.curr-rel |grep "^-" +rm -f $$.prev-rel $$.curr-rel + diff --git a/debian/scripts/misc/gen-auto-reconstruct b/debian/scripts/misc/gen-auto-reconstruct new file mode 100755 index 0000000000000..2746d27d4c5f0 --- /dev/null +++ b/debian/scripts/misc/gen-auto-reconstruct @@ -0,0 +1,89 @@ +#!/bin/bash + +if [ "$#" -ne 3 ]; then + echo "Usage: $0 | " 1>&2 + exit 1 +fi +tag="$1" +reconstruct="$2" +options="$3" + +case "$tag" in +v*) ;; +*) tag="v${tag%.*}" ;; +esac + +# Validate the tag. +count=$( git tag -l "$tag" | wc -l ) +if [ "$count" != 1 ]; then + echo "$0: $tag: tag invalid" 1>&2 + exit 1 +fi + +#git ls-tree -r --full-tree HEAD | grep ^120 | \ +#while read mode type blobid name + +( + # Identify all new symlinks since the proffered tag. + echo "# Recreate any symlinks created since the orig." + git diff "$tag.." --raw --no-renames | awk '(/^:000000 120000/ && $5 == "A") { print $NF }' | \ + while read name + do + link=$( readlink "$name" ) + + echo "[ ! -L '$name' ] && ln -sf '$link' '$name'" + done + + # Identify files with execute permissions added since the proffered tag. + git diff "$tag.." --raw --no-renames | awk -F '[: \t]' '{print $2, $3, $NF }' | \ + while IFS=" " read old new name + do + old=$( printf "0%s" $old ) + new=$( printf "0%s" $new ) + changed=$(( (old ^ new) & 0111 )) + if [ "$changed" -ne 0 ]; then + added=$(( new & 0111 )) + if [ "$added" -ne 0 ]; then + echo "chmod +x '$name'" + elif [ "$new" -ne 0 ]; then + echo "chmod -x '$name'" + fi + fi + done + + # Identify all removed files since the proffered tag. + echo "# Remove any files deleted from the orig." + git diff "$tag.." --raw --no-renames | awk '(/^:/ && $5 == "D") { print $NF }' | \ + while read name + do + echo "rm -f '$name'" + done + + # All done, make sure this does not complete in error. + echo "exit 0" +) >"$reconstruct" + +( + # Identify all new symlinks since the proffered tag. + echo "# Ignore any symlinks created since the orig which are rebuilt by reconstruct." + git diff "$tag.." --raw --no-renames | awk '(/^:000000 120000/ && $5 == "A") { print $NF }' | \ + while read name + do + echo "extend-diff-ignore=^$name\$" + done +) >"$options.update" + + +head='^## autoreconstruct -- begin$' +foot='^## autoreconstruct -- end$' +sed -i -e " + /$head/,/$foot/{ + /$head/{ + p; + r $options.update + }; + /$foot/p; + d + } +" "$options" +rm -f "$options.update" diff --git a/debian/scripts/misc/git-ubuntu-log b/debian/scripts/misc/git-ubuntu-log new file mode 100755 index 0000000000000..8efdb404b5613 --- /dev/null +++ b/debian/scripts/misc/git-ubuntu-log @@ -0,0 +1,166 @@ +#!/usr/bin/env python3 + +import sys + +import codecs +import urllib.request +import json + +import textwrap + +sys.stdin = codecs.getreader("utf-8")(sys.stdin.detach()) +sys.stdout = codecs.getwriter("utf-8")(sys.stdout.detach()) + +entries = [] + + +def add_entry(entry): + if entry and 'ignore' not in entry: + combo = [] + for bug in set(entry.get('bugs', [])): + combo.append(bug) + for cve in set(entry.get('cves', [])): + combo.append(cve) + combo = sorted(combo) + + if len(combo) == 0: + if entry.get('subject', "").startswith('UBUNTU'): + combo = '__packaging__' + else: + combo = '__mainline__' + else: + if entry.get('subject', "") == 'UBUNTU: link-to-tracker: update tracking bug': + # Construct a key with '__trackingbug__' on the first position + # and the tracking bug number afterwards + combo.insert(0, '__trackingbug__') + # Tracking bug goes at the top + keys.insert(0, combo) + else: + if combo not in keys: + keys.append(combo) + + entry['key'] = combo + entries.append(entry) + + +# Suck up the git log output and extract the information we need. +keys = [] +entry = None +subject_wait = False +for line in sys.stdin: + if line.startswith('commit '): + add_entry(entry) + entry = {} + subject_wait = True + + elif line.startswith('Author: '): + bits = line.strip().split(maxsplit=1) + entry['author'] = bits[1] + + elif subject_wait and line.startswith(' '): + subject_wait = False + entry['subject'] = line.strip() + + elif line.startswith(' BugLink: '): + bits = line.strip().split(maxsplit=2) + if len(bits) > 2: + # There is text after the URL, so use that (after stripping the + # enclosing characters) + entry.setdefault('bugs', []).append(bits[2][1:-1]) + elif 'launchpad.net' in bits[1]: + # Extract the bug number from the launchpad URL + bits = bits[1].split('/') + entry.setdefault('bugs', []).append(bits[-1]) + + elif line.startswith(' CVE-'): + entry.setdefault('cves', []).append(line.strip()) + + elif line.startswith(' Ignore:'): + entry['ignore'] = True + + elif line.startswith(' Properties:'): + for prop in line.strip().split()[1:]: + if prop in ('ignore', 'no-changelog'): + entry['ignore'] = True + +add_entry(entry) + +entries.reverse() + +# Go through the entries and clear out authors for upstream commits. +for entry in entries: + if entry['subject'].startswith('UBUNTU:'): + entry['subject'] = entry['subject'][7:].strip() + else: + del entry['author'] + +# Lump everything without a bug at the bottom. +keys.append('__packaging__') +keys.append('__mainline__') + +emit_nl = False +for key in keys: + if key == '__packaging__': + title_set = ['Miscellaneous Ubuntu changes'] + elif key == '__mainline__': + title_set = ['Miscellaneous upstream changes'] + else: + title_set = [] + for bug in key: + if bug.startswith('CVE-'): + title_set.append(bug) + elif bug == '__trackingbug__': + # Look for the tracking bug number on the second + # position of the key + continue + elif bug.isdigit(): + # Assume that it is an LP bug number if 'bug' contains only digits + bug_info = None + + try: + # urllib.request.urlcleanup() + request = urllib.request.Request('https://api.launchpad.net/devel/bugs/' + bug) + request.add_header('Cache-Control', 'no-cache') + with urllib.request.urlopen(request) as response: + data = response.read() + bug_info = json.loads(data.decode('utf-8')) + + title = bug_info['title'] + if 'description' in bug_info: + for line in bug_info['description'].split('\n'): + if line.startswith('Kernel-Description:'): + title = line.split(' ', 1)[1] + + except urllib.error.HTTPError: + title = 'INVALID or PRIVATE BUG' + + title += ' (LP###' + bug + ')' + title_set.append(title) + else: + # Finally treat 'bug' itself as the title + title_set.append(bug) + + emit_title = True + for entry in entries: + if entry['key'] != key: + continue + + if emit_title: + if emit_nl: + print('') + emit_nl = True + + title_lines = textwrap.wrap('#// '.join(title_set), 76) + print(' * ' + title_lines[0].replace('LP###', 'LP: #').replace('#//', ' //')) + for line in title_lines[1:]: + line = line.replace('LP###', 'LP: #').replace('#//', ' //') + print(' ' + line) + + emit_title = False + + if key[0] != '__trackingbug__': + title_lines = textwrap.wrap(entry['subject'], 76) + print(' - ' + title_lines[0]) + for line in title_lines[1:]: + line = line.replace('LP###', 'LP: #') + print(' ' + line) diff --git a/debian/scripts/misc/insert-changes b/debian/scripts/misc/insert-changes new file mode 100755 index 0000000000000..e21aaa409884f --- /dev/null +++ b/debian/scripts/misc/insert-changes @@ -0,0 +1,42 @@ +#!/usr/bin/python3 + +import os +import sys + +from subprocess import check_output + +droot = 'debian' +if len(sys.argv) > 1: + droot = sys.argv[1] + +debian = 'debian.master' +if len(sys.argv) > 2: + debian = sys.argv[2] + +rules = os.path.join(droot, 'rules') +changelog = os.path.join(debian, 'changelog') +changelog_new = os.path.join(debian, 'changelog.new') + +# Generate the list of new changes +changes = check_output(['make', '-s', '-f', rules, 'printchanges']).decode('UTF-8') + +# Insert the new changes into the changelog +with open(changelog) as orig, open(changelog_new, 'w') as new: + printed = False + skip_newline = False + for line in orig: + if line.startswith(' CHANGELOG: '): + if not printed: + printed = True + if changes == '': + skip_newline = True + continue + new.write(changes) + else: + if skip_newline and line.strip() == '': + skip_newline = False + continue + new.write(line) + +# Replace the original changelog with the new one +os.rename(changelog_new, changelog) diff --git a/debian/scripts/misc/insert-ubuntu-changes b/debian/scripts/misc/insert-ubuntu-changes new file mode 100755 index 0000000000000..557d4e2d0b8c6 --- /dev/null +++ b/debian/scripts/misc/insert-ubuntu-changes @@ -0,0 +1,64 @@ +#!/usr/bin/env python3 + +import re +import os +import sys + +def version_cmp(a, b): + a = re.split(r"[\.-]+", a) + b = re.split(r"[\.-]+", b) + i = 0 + while True: + if len(a) <= i: + if len(b) <= i: + return 0 + return -1 + if len(b) <= i: + return 1 + if int(a[i]) < int(b[i]): + return -1 + if int(a[i]) > int(b[i]): + return 1 + i += 1 + +if len(sys.argv) == 4: + sys.argv.append("debian.master/changelog") + +if len(sys.argv) == 5: + changelog, end, start, source_changelog = sys.argv[1:] +else: + print("Usage: insert-ubuntu-changes []") + sys.exit(1) + +changes = [] +output = False +with open(source_changelog) as fh: + for line in fh: + m = re.match(r"^\S+\s+\((.*)\)", line) + if m: + if version_cmp(m.group(1), end) <= 0: + break + if m.group(1) == start: + output = True + if output: + changes.append("\n") + changes.append(" [ Ubuntu: {} ]\n".format(m.group(1))) + changes.append("\n") + continue + + if output and re.match(r"^( * | | )\S", line): + changes.append(line) + +printed = 3 +with open(changelog + ".new", "w") as fh_new: + with open(changelog) as fh: + for line in fh: + if line.startswith(" CHANGELOG: "): + printed -= 1 + fh_new.write(line) + if printed == 0: + fh_new.write("".join(changes)) + continue + fh_new.write(line) + +os.rename(changelog + ".new", changelog) diff --git a/debian/scripts/misc/kconfig/__init__.py b/debian/scripts/misc/kconfig/__init__.py new file mode 100644 index 0000000000000..e69de29bb2d1d diff --git a/debian/scripts/misc/kconfig/annotations.py b/debian/scripts/misc/kconfig/annotations.py new file mode 100644 index 0000000000000..af9dbdfa2eb20 --- /dev/null +++ b/debian/scripts/misc/kconfig/annotations.py @@ -0,0 +1,522 @@ +# -*- mode: python -*- +# python module to manage Ubuntu kernel .config and annotations +# Copyright © 2022 Canonical Ltd. + +import json +import re +import shutil +import tempfile + +from abc import abstractmethod +from ast import literal_eval +from os.path import dirname, abspath + +from kconfig.version import ANNOTATIONS_FORMAT_VERSION + + +class Config: + def __init__(self, fname, do_include=True): + """ + Basic configuration file object + """ + self.fname = fname + self.config = {} + self.do_include = do_include + + raw_data = self._load(fname) + self._parse(raw_data) + + @staticmethod + def _load(fname: str) -> str: + with open(fname, "rt", encoding="utf-8") as fd: + data = fd.read() + return data.rstrip() + + def __str__(self): + """Return a JSON representation of the config""" + return json.dumps(self.config, indent=4) + + @abstractmethod + def _parse(self, data: str): + pass + + +class KConfig(Config): + """ + Parse a .config file, individual config options can be accessed via + .config[] + """ + + def _parse(self, data: str): + self.config = {} + for line in data.splitlines(): + m = re.match(r"^# (CONFIG_.*) is not set$", line) + if m: + self.config[m.group(1)] = literal_eval("'n'") + continue + m = re.match(r"^(CONFIG_[A-Za-z0-9_]+)=(.*)$", line) + if m: + self.config[m.group(1)] = literal_eval("'" + m.group(2) + "'") + continue + + +class Annotation(Config): + """ + Parse body of annotations file + """ + + def __init__(self, fname, do_include=True, do_json=False): + self.do_json = do_json + super().__init__(fname, do_include=True) + + def _parse_body(self, data: str, parent=True): + for line in data.splitlines(): + # Replace tabs with spaces, squeeze multiple into singles and + # remove leading and trailing spaces + line = line.replace("\t", " ") + line = re.sub(r" +", " ", line) + line = line.strip() + + # Ignore empty lines + if not line: + continue + + # Catpure flavors of included files + if line.startswith("# FLAVOUR: "): + self.include_flavour += line.split(" ")[2:] + continue + + # Ignore comments + if line.startswith("#"): + continue + + # Handle includes (recursively) + m = re.match(r'^include\s+"?([^"]*)"?', line) + if m: + if parent: + self.include.append(m.group(1)) + if self.do_include: + include_fname = dirname(abspath(self.fname)) + "/" + m.group(1) + include_data = self._load(include_fname) + self._parse_body(include_data, parent=False) + continue + + # Handle policy and note lines + if re.match(r".* (policy|note)<", line): + try: + conf = line.split(" ")[0] + if conf in self.config: + entry = self.config[conf] + else: + entry = {"policy": {}} + + match = False + m = re.match(r".* policy<(.*?)>", line) + if m: + match = True + # Update the previous entry considering potential overrides: + # - if the new entry is adding a rule for a new + # arch/flavour, simply add that + # - if the new entry is overriding a previous + # arch-flavour item, then overwrite that item + # - if the new entry is overriding a whole arch, then + # remove all the previous flavour rules of that arch + new_entry = literal_eval(m.group(1)) + for key in new_entry: + if key in self.arch: + for flavour_key in list(entry["policy"].keys()): + if flavour_key.startswith(key): + del entry["policy"][flavour_key] + entry["policy"][key] = new_entry[key] + else: + entry["policy"][key] = new_entry[key] + + m = re.match(r".* note<(.*?)>", line) + if m: + entry["oneline"] = match + match = True + entry["note"] = "'" + m.group(1).replace("'", "") + "'" + + if not match: + raise SyntaxError("syntax error") + self.config[conf] = entry + except Exception as e: + raise SyntaxError(str(e) + f", line = {line}") from e + continue + + # Invalid line + raise SyntaxError(f"invalid line: {line}") + + def _legacy_parse(self, data: str): + """ + Parse main annotations file, individual config options can be accessed + via self.config[] + """ + self.config = {} + self.arch = [] + self.flavour = [] + self.flavour_dep = {} + self.include = [] + self.header = "" + self.include_flavour = [] + + # Parse header (only main header will considered, headers in includes + # will be treated as comments) + for line in data.splitlines(): + if re.match(r"^#.*", line): + m = re.match(r"^# ARCH: (.*)", line) + if m: + self.arch = list(m.group(1).split(" ")) + m = re.match(r"^# FLAVOUR: (.*)", line) + if m: + self.flavour = list(m.group(1).split(" ")) + m = re.match(r"^# FLAVOUR_DEP: (.*)", line) + if m: + self.flavour_dep = literal_eval(m.group(1)) + self.header += line + "\n" + else: + break + + # Return an error if architectures are not defined + if not self.arch: + raise SyntaxError("ARCH not defined in annotations") + # Return an error if flavours are not defined + if not self.flavour: + raise SyntaxError("FLAVOUR not defined in annotations") + + # Parse body + self._parse_body(data) + + # Sanity check: Verify that all FLAVOUR_DEP flavors are valid + if self.do_include: + for src, tgt in self.flavour_dep.items(): + if src not in self.flavour: + raise SyntaxError(f"Invalid source flavour in FLAVOUR_DEP: {src}") + if tgt not in self.include_flavour: + raise SyntaxError(f"Invalid target flavour in FLAVOUR_DEP: {tgt}") + + def _json_parse(self, data, is_included=False): + data = json.loads(data) + + # Check if version is supported + version = data["attributes"]["_version"] + if version > ANNOTATIONS_FORMAT_VERSION: + raise SyntaxError(f"annotations format version {version} not supported") + + # Check for top-level annotations vs imported annotations + if not is_included: + self.config = data["config"] + self.arch = data["attributes"]["arch"] + self.flavour = data["attributes"]["flavour"] + self.flavour_dep = data["attributes"]["flavour_dep"] + self.include = data["attributes"]["include"] + self.include_flavour = [] + else: + # We are procesing an imported annotations, so merge all the + # configs and attributes. + try: + self.config = data["config"] | self.config + except TypeError: + self.config = {**self.config, **data["config"]} + self.arch = list(set(self.arch) | set(data["attributes"]["arch"])) + self.flavour = list(set(self.flavour) | set(data["attributes"]["flavour"])) + self.include_flavour = list(set(self.include_flavour) | set(data["attributes"]["flavour"])) + self.flavour_dep = self.flavour_dep | data["attributes"]["flavour_dep"] + + # Handle recursive inclusions + if self.do_include: + for f in data["attributes"]["include"]: + include_fname = dirname(abspath(self.fname)) + "/" + f + data = self._load(include_fname) + self._json_parse(data, is_included=True) + + def _parse(self, data: str): + if self.do_json: + self._json_parse(data, is_included=False) + else: + self._legacy_parse(data) + + def _remove_entry(self, config: str): + if self.config[config]: + del self.config[config] + + def remove(self, config: str, arch: str = None, flavour: str = None): + if config not in self.config: + return + if arch is not None: + if flavour is not None: + flavour = f"{arch}-{flavour}" + else: + flavour = arch + del self.config[config]["policy"][flavour] + if not self.config[config]["policy"]: + self._remove_entry(config) + else: + self._remove_entry(config) + + def set( + self, + config: str, + arch: str = None, + flavour: str = None, + value: str = None, + note: str = None, + ): + if value is not None: + if config not in self.config: + self.config[config] = {"policy": {}} + if arch is not None: + if flavour is not None: + flavour = f"{arch}-{flavour}" + else: + flavour = arch + self.config[config]["policy"][flavour] = value + else: + for a in self.arch: + self.config[config]["policy"][a] = value + if note is not None: + self.config[config]["note"] = "'" + note.replace("'", "") + "'" + + def update(self, c: KConfig, arch: str, flavour: str = None, configs: list = None): + """Merge configs from a Kconfig object into Annotation object""" + + # Determine if we need to import all configs or a single config + if not configs: + configs = c.config.keys() + try: + configs |= self.search_config(arch=arch, flavour=flavour).keys() + except TypeError: + configs = { + **configs, + **self.search_config(arch=arch, flavour=flavour).keys(), + } + + # Import configs from the Kconfig object into Annotations + flavour_arg = flavour + if flavour is not None: + flavour = arch + f"-{flavour}" + else: + flavour = arch + for conf in configs: + if conf in c.config: + val = c.config[conf] + else: + val = "-" + if conf in self.config: + if "policy" in self.config[conf]: + # Add a TODO if a config with a note is changing and print + # a warning + old_val = self.search_config(config=conf, arch=arch, flavour=flavour_arg) + if old_val: + old_val = old_val[conf] + if val != old_val and "note" in self.config[conf]: + self.config[conf]["note"] = "TODO: update note" + print(f"WARNING: {conf} changed from {old_val} to {val}, updating note") + self.config[conf]["policy"][flavour] = val + else: + self.config[conf]["policy"] = {flavour: val} + else: + self.config[conf] = {"policy": {flavour: val}} + + def _compact(self): + # Try to remove redundant settings: if the config value of a flavour is + # the same as the one of the main arch simply drop it. + for conf in self.config.copy(): + if "policy" not in self.config[conf]: + continue + for flavour in self.flavour: + if flavour not in self.config[conf]["policy"]: + continue + m = re.match(r"^(.*?)-(.*)$", flavour) + if not m: + continue + arch = m.group(1) + if arch in self.config[conf]["policy"]: + if self.config[conf]["policy"][flavour] == self.config[conf]["policy"][arch]: + del self.config[conf]["policy"][flavour] + continue + if flavour not in self.flavour_dep: + continue + generic = self.flavour_dep[flavour] + if generic in self.config[conf]["policy"]: + if self.config[conf]["policy"][flavour] == self.config[conf]["policy"][generic]: + del self.config[conf]["policy"][flavour] + continue + # Remove rules for flavours / arches that are not supported (not + # listed in the annotations header). + for flavour in self.config[conf]["policy"].copy(): + if flavour not in list(set(self.arch + self.flavour)): + del self.config[conf]["policy"][flavour] + # Remove configs that are all undefined across all arches/flavours + # (unless we have includes) + if not self.include: + if "policy" in self.config[conf]: + if list(set(self.config[conf]["policy"].values())) == ["-"]: + self.config[conf]["policy"] = {} + # Drop empty rules + if not self.config[conf]["policy"]: + del self.config[conf] + else: + # Compact same value across all flavour within the same arch + for arch in self.arch: + arch_flavours = [i for i in self.flavour if i.startswith(arch)] + value = None + for flavour in arch_flavours: + if flavour not in self.config[conf]["policy"]: + break + if value is None: + value = self.config[conf]["policy"][flavour] + elif value != self.config[conf]["policy"][flavour]: + break + else: + for flavour in arch_flavours: + del self.config[conf]["policy"][flavour] + self.config[conf]["policy"][arch] = value + # After the first round of compaction we may end up having configs that + # are undefined across all arches, so do another round of compaction to + # drop these settings that are not needed anymore + # (unless we have includes). + if not self.include: + for conf in self.config.copy(): + # Remove configs that are all undefined across all arches/flavours + if "policy" in self.config[conf]: + if list(set(self.config[conf]["policy"].values())) == ["-"]: + self.config[conf]["policy"] = {} + # Drop empty rules + if not self.config[conf]["policy"]: + del self.config[conf] + + @staticmethod + def _sorted(config): + """Sort configs alphabetically but return configs with a note first""" + w_note = [] + wo_note = [] + for c in sorted(config): + if "note" in config[c]: + w_note.append(c) + else: + wo_note.append(c) + return w_note + wo_note + + def save(self, fname: str): + """Save annotations data to the annotation file""" + # Compact annotations structure + self._compact() + + # Save annotations to disk + with tempfile.NamedTemporaryFile(mode="w+t", delete=False) as tmp: + # Write header + tmp.write(self.header + "\n") + + # Write includes + for i in self.include: + tmp.write(f'include "{i}"\n') + if self.include: + tmp.write("\n") + + # Write config annotations and notes + tmp.flush() + shutil.copy(tmp.name, fname) + tmp_a = Annotation(fname) + + # Only save local differences (preserve includes) + marker = False + for conf in self._sorted(self.config): + new_val = self.config[conf] + if "policy" not in new_val: + continue + + # If new_val is a subset of old_val, skip it unless there are + # new notes that are different than the old ones. + old_val = tmp_a.config.get(conf) + if old_val and "policy" in old_val: + try: + can_skip = old_val["policy"] == old_val["policy"] | new_val["policy"] + except TypeError: + can_skip = old_val["policy"] == { + **old_val["policy"], + **new_val["policy"], + } + if can_skip: + if "note" not in new_val: + continue + if "note" in old_val and "note" in new_val: + if old_val["note"] == new_val["note"]: + continue + + # Write out the policy (and note) line(s) + val = dict(sorted(new_val["policy"].items())) + line = f"{conf : <47} policy<{val}>" + if "note" in new_val: + val = new_val["note"] + if new_val.get("oneline", False): + # Single line + line += f" note<{val}>" + else: + # Separate policy and note lines, + # followed by an empty line + line += f"\n{conf : <47} note<{val}>\n" + elif not marker: + # Write out a marker indicating the start of annotations + # without notes + tmp.write("\n# ---- Annotations without notes ----\n\n") + marker = True + tmp.write(line + "\n") + + # Replace annotations with the updated version + tmp.flush() + shutil.move(tmp.name, fname) + + def search_config(self, config: str = None, arch: str = None, flavour: str = None) -> dict: + """Return config value of a specific config option or architecture""" + if flavour is None: + flavour = "generic" + flavour = f"{arch}-{flavour}" + if flavour in self.flavour_dep: + generic = self.flavour_dep[flavour] + else: + generic = flavour + if config is None and arch is None: + # Get all config options for all architectures + return self.config + if config is None and arch is not None: + # Get config options of a specific architecture + ret = {} + for c, val in self.config.items(): + if "policy" not in val: + continue + if flavour in val["policy"]: + ret[c] = val["policy"][flavour] + elif generic != flavour and generic in val["policy"]: + ret[c] = val["policy"][generic] + elif arch in val["policy"]: + ret[c] = val["policy"][arch] + return ret + if config is not None and arch is None: + # Get a specific config option for all architectures + return self.config[config] if config in self.config else None + if config is not None and arch is not None: + # Get a specific config option for a specific architecture + if config in self.config: + if "policy" in self.config[config]: + if flavour in self.config[config]["policy"]: + return {config: self.config[config]["policy"][flavour]} + if generic != flavour and generic in self.config[config]["policy"]: + return {config: self.config[config]["policy"][generic]} + if arch in self.config[config]["policy"]: + return {config: self.config[config]["policy"][arch]} + return None + + @staticmethod + def to_config(data: dict) -> str: + """Convert annotations data to .config format""" + s = "" + for c in data: + v = data[c] + if v == "n": + s += f"# {c} is not set\n" + elif v == "-": + pass + else: + s += f"{c}={v}\n" + return s.rstrip() diff --git a/debian/scripts/misc/kconfig/run.py b/debian/scripts/misc/kconfig/run.py new file mode 100644 index 0000000000000..63b0c9435a5c6 --- /dev/null +++ b/debian/scripts/misc/kconfig/run.py @@ -0,0 +1,370 @@ +# -*- mode: python -*- +# Manage Ubuntu kernel .config and annotations +# Copyright © 2022 Canonical Ltd. + +import sys +import os +import argparse +import json +from signal import signal, SIGPIPE, SIG_DFL + +try: + from argcomplete import autocomplete +except ModuleNotFoundError: + # Allow to run this program also when argcomplete is not available + def autocomplete(_unused): + pass + + +from kconfig.annotations import Annotation, KConfig # noqa: E402 Import not at top of file +from kconfig.utils import autodetect_annotations, arg_fail # noqa: E402 Import not at top of file +from kconfig.version import VERSION, ANNOTATIONS_FORMAT_VERSION # noqa: E402 Import not at top of file + + +SKIP_CONFIGS = ( + # CONFIG_VERSION_SIGNATURE is dynamically set during the build + "CONFIG_VERSION_SIGNATURE", + # Allow to use a different versions of toolchain tools + "CONFIG_GCC_VERSION", + "CONFIG_CC_VERSION_TEXT", + "CONFIG_AS_VERSION", + "CONFIG_LD_VERSION", + "CONFIG_LLD_VERSION", + "CONFIG_CLANG_VERSION", + "CONFIG_PAHOLE_VERSION", + "CONFIG_RUSTC_VERSION_TEXT", + "CONFIG_BINDGEN_VERSION_TEXT", +) + + +def make_parser(): + parser = argparse.ArgumentParser( + description="Manage Ubuntu kernel .config and annotations", + ) + parser.add_argument("--version", "-v", action="version", version=f"%(prog)s {VERSION}") + + parser.add_argument( + "--file", + "-f", + action="store", + help="Pass annotations or .config file to be parsed", + ) + parser.add_argument("--arch", "-a", action="store", help="Select architecture") + parser.add_argument("--flavour", "-l", action="store", help='Select flavour (default is "generic")') + parser.add_argument("--config", "-c", action="store", help="Select a specific config option") + parser.add_argument("--query", "-q", action="store_true", help="Query annotations") + parser.add_argument( + "--note", + "-n", + action="store", + help="Write a specific note to a config option in annotations", + ) + parser.add_argument( + "--autocomplete", + action="store_true", + help="Enable config bash autocomplete: `source <(annotations --autocomplete)`", + ) + parser.add_argument( + "--source", + "-t", + action="store_true", + help="Jump to a config definition in the kernel source code", + ) + parser.add_argument( + "--no-include", + action="store_true", + help="Do not process included annotations (stop at the main file)", + ) + parser.add_argument( + "--json", + action="store_true", + help="Try to parse annotations file in pure JSON format", + ) + + ga = parser.add_argument_group(title="Action").add_mutually_exclusive_group(required=False) + ga.add_argument( + "--write", + "-w", + action="store", + metavar="VALUE", + dest="value", + help="Set a specific config value in annotations (use 'null' to remove)", + ) + ga.add_argument( + "--export", + "-e", + action="store_true", + help="Convert annotations to .config format", + ) + ga.add_argument( + "--import", + "-i", + action="store", + metavar="FILE", + dest="import_file", + help="Import a full .config for a specific arch and flavour into annotations", + ) + ga.add_argument( + "--update", + "-u", + action="store", + metavar="FILE", + dest="update_file", + help="Import a partial .config into annotations (only resync configs specified in FILE)", + ) + ga.add_argument( + "--check", + "-k", + action="store", + metavar="FILE", + dest="check_file", + help="Validate kernel .config with annotations", + ) + return parser + + +_ARGPARSER = make_parser() + + +def export_result(data): + # Dump metadata / attributes first + out = '{\n "attributes": {\n' + for key, value in sorted(data["attributes"].items()): + out += f' "{key}": {json.dumps(value)},\n' + out = out.rstrip(",\n") + out += "\n }," + print(out) + + configs_with_note = {key: value for key, value in data["config"].items() if "note" in value} + configs_without_note = {key: value for key, value in data["config"].items() if "note" not in value} + + # Dump configs, sorted alphabetically, showing items with a note first + out = ' "config": {\n' + for key in sorted(configs_with_note) + sorted(configs_without_note): + policy = data["config"][key]["policy"] + if "note" in data["config"][key]: + note = data["config"][key]["note"] + out += f' "{key}": {{"policy": {json.dumps(policy)}, "note": {json.dumps(note)}}},\n' + else: + out += f' "{key}": {{"policy": {json.dumps(policy)}}},\n' + out = out.rstrip(",\n") + out += "\n }\n}" + print(out) + + +def print_result(config, data): + if data is not None and config is not None and config not in data: + data = {config: data} + print(json.dumps(data, sort_keys=True, indent=2)) + + +def do_query(args): + if args.arch is None and args.flavour is not None: + arg_fail(_ARGPARSER, "error: --flavour requires --arch") + a = Annotation(args.file, do_include=(not args.no_include), do_json=args.json) + res = a.search_config(config=args.config, arch=args.arch, flavour=args.flavour) + # If no arguments are specified dump the whole annotations structure + if args.config is None and args.arch is None and args.flavour is None: + res = { + "attributes": { + "arch": a.arch, + "flavour": a.flavour, + "flavour_dep": a.flavour_dep, + "include": a.include, + "_version": ANNOTATIONS_FORMAT_VERSION, + }, + "config": res, + } + export_result(res) + else: + print_result(args.config, res) + + +def do_autocomplete(args): + a = Annotation(args.file) + res = (c.removeprefix("CONFIG_") for c in a.search_config()) + res_str = " ".join(res) + print(f'complete -W "{res_str}" annotations') + + +def do_source(args): + if args.config is None: + arg_fail(_ARGPARSER, "error: --source requires --config") + if not os.path.exists("tags"): + print("tags not found in the current directory, try: `make tags`") + sys.exit(1) + os.system(f"vim -t {args.config}") + + +def do_note(args): + if args.config is None: + arg_fail(_ARGPARSER, "error: --note requires --config") + + # Set the note in annotations + a = Annotation(args.file) + a.set(args.config, note=args.note) + + # Save back to annotations + a.save(args.file) + + # Query and print back the value + a = Annotation(args.file) + res = a.search_config(config=args.config) + print_result(args.config, res) + + +def do_write(args): + if args.config is None: + arg_fail(_ARGPARSER, "error: --write requires --config") + + # Set the value in annotations ('null' means remove) + a = Annotation(args.file) + if args.value == "null": + a.remove(args.config, arch=args.arch, flavour=args.flavour) + else: + a.set( + args.config, + arch=args.arch, + flavour=args.flavour, + value=args.value, + note=args.note, + ) + + # Save back to annotations + a.save(args.file) + + # Query and print back the value + a = Annotation(args.file) + res = a.search_config(config=args.config) + print_result(args.config, res) + + +def do_export(args): + if args.arch is None: + arg_fail(_ARGPARSER, "error: --export requires --arch") + a = Annotation(args.file) + conf = a.search_config(config=args.config, arch=args.arch, flavour=args.flavour) + if conf: + print(a.to_config(conf)) + + +def do_import(args): + if args.arch is None: + arg_fail(_ARGPARSER, "error: --arch is required with --import") + if args.flavour is None: + arg_fail(_ARGPARSER, "error: --flavour is required with --import") + if args.config is not None: + arg_fail(_ARGPARSER, "error: --config cannot be used with --import (try --update)") + + # Merge with the current annotations + a = Annotation(args.file) + c = KConfig(args.import_file) + a.update(c, arch=args.arch, flavour=args.flavour) + + # Save back to annotations + a.save(args.file) + + +def do_update(args): + if args.arch is None: + arg_fail(_ARGPARSER, "error: --arch is required with --update") + + # Merge with the current annotations + a = Annotation(args.file) + c = KConfig(args.update_file) + if args.config is None: + configs = list(set(c.config.keys()) - set(SKIP_CONFIGS)) + if configs: + a.update(c, arch=args.arch, flavour=args.flavour, configs=configs) + + # Save back to annotations + a.save(args.file) + + +def do_check(args): + # Determine arch and flavour + if args.arch is None: + arg_fail(_ARGPARSER, "error: --arch is required with --check") + + print(f"check-config: loading annotations from {args.file}") + total = good = ret = 0 + + # Load annotations settings + a = Annotation(args.file) + a_configs = a.search_config(arch=args.arch, flavour=args.flavour).keys() + + # Parse target .config + c = KConfig(args.check_file) + c_configs = c.config.keys() + + # Validate .config against annotations + for conf in sorted(a_configs | c_configs): + if conf in SKIP_CONFIGS: + continue + entry = a.search_config(config=conf, arch=args.arch, flavour=args.flavour) + expected = entry[conf] if entry else "-" + value = c.config[conf] if conf in c.config else "-" + if value != expected: + policy = a.config[conf] if conf in a.config else "undefined" + if "policy" in policy: + policy = f"policy<{policy['policy']}>" + print(f"check-config: {conf} changed from {expected} to {value}: {policy})") + ret = 1 + else: + good += 1 + total += 1 + + num = total - good + if ret: + if os.path.exists(".git"): + print(f"check-config: {num} config options have been changed, review them with `git diff`") + else: + print(f"check-config: {num} config options have changed") + else: + print("check-config: all good") + sys.exit(ret) + + +def main(): + # Prevent broken pipe errors when showing output in pipe to other tools + # (less for example) + signal(SIGPIPE, SIG_DFL) + + # Main annotations program + autocomplete(_ARGPARSER) + args = _ARGPARSER.parse_args() + + if args.file is None: + args.file = autodetect_annotations() + if args.file is None: + arg_fail( + _ARGPARSER, + "error: could not determine DEBDIR, try using: --file/-f", + show_usage=False, + ) + + if args.config and not args.config.startswith("CONFIG_"): + args.config = "CONFIG_" + args.config + + if args.value: + do_write(args) + elif args.note: + do_note(args) + elif args.export: + do_export(args) + elif args.import_file: + do_import(args) + elif args.update_file: + do_update(args) + elif args.check_file: + do_check(args) + elif args.autocomplete: + do_autocomplete(args) + elif args.source: + do_source(args) + else: + do_query(args) + + +if __name__ == "__main__": + main() diff --git a/debian/scripts/misc/kconfig/utils.py b/debian/scripts/misc/kconfig/utils.py new file mode 100644 index 0000000000000..f4ced6b33f4a0 --- /dev/null +++ b/debian/scripts/misc/kconfig/utils.py @@ -0,0 +1,20 @@ +# -*- mode: python -*- +# Misc helpers for Kconfig and annotations +# Copyright © 2023 Canonical Ltd. + +import sys + + +def autodetect_annotations(): + try: + with open("debian/debian.env", "rt", encoding="utf-8") as fd: + return fd.read().rstrip().split("=")[1] + "/config/annotations" + except (FileNotFoundError, IndexError): + return None + + +def arg_fail(parser, message, show_usage=True): + print(message) + if show_usage: + parser.print_usage() + sys.exit(1) diff --git a/debian/scripts/misc/kconfig/version.py b/debian/scripts/misc/kconfig/version.py new file mode 100644 index 0000000000000..833ffa34654bb --- /dev/null +++ b/debian/scripts/misc/kconfig/version.py @@ -0,0 +1,10 @@ +# -*- mode: python -*- +# version of annotations module +# Copyright © 2022 Canonical Ltd. + +VERSION = "0.1" + +ANNOTATIONS_FORMAT_VERSION = 5 + +if __name__ == "__main__": + print(VERSION) diff --git a/debian/scripts/misc/kernelconfig b/debian/scripts/misc/kernelconfig new file mode 100755 index 0000000000000..035426762f8a7 --- /dev/null +++ b/debian/scripts/misc/kernelconfig @@ -0,0 +1,178 @@ +#!/bin/bash -u +# +# Manage kernel config annotations +# +# Supported environment variales: +# conc_level : Concurrency level for upstream make (-jX) +# skip_checks : Skip config checks if set to 'true' +# gcc : Default gcc to use (mandatory) +# + +function cleanup() +{ + rm -rf build "${TMP_DIR}" +} + +# We have to be in the top level Ubuntu kernel source directory +if ! [ -e debian/debian.env ] ; then + echo "ERROR: This is not an Ubuntu kernel source directory" >&2 + exit 1 +fi + +if [ -z "${gcc:-}" ] ; then + echo "ERROR: 'gcc' environment variable must be set" >&2 + exit 1 +fi + +if [ ${#} -ne 1 ] ; then + echo "Usage: $0 updateconfigs|defaultconfigs|genconfigs|editconfigs" + exit 2 +fi + +mode=${1} + +case "${mode}" in + updateconfigs) target="syncconfig" ;; + defaultconfigs) target="olddefconfig" ;; + genconfigs) target="oldconfig" ;; + editconfigs) ;; # Target is set later based on user input + *) echo "ERROR: Invalid mode: ${1}" >&2 + exit 1 ;; +esac + +. debian/debian.env + +annotations_file=${DEBIAN}/config/annotations +warning_partial=() + +TMP_DIR=$(mktemp -d) +trap cleanup EXIT + +# Use annotations to generate configs +FLAVOURS=$(sed -ne 's/^# FLAVOUR: //p' "${annotations_file}") + +for arch_flavour in ${FLAVOURS} ; do + arch=${arch_flavour%%-*} + flavour=${arch_flavour#*-} + tmp_conf_file=${TMP_DIR}/${arch}-config.flavour.${flavour} + + # Map debian archs to kernel archs + case "${arch}" in + amd64) kern_arch="x86_64" ;; + arm64) kern_arch="arm64" ;; + armhf) kern_arch="arm" ;; + ppc64el) kern_arch="powerpc" ;; + riscv64) kern_arch="riscv" ;; + s390x) kern_arch="s390" ;; + *) echo "WARNING: Unsupported architecture: ${arch}" + warning_partial+=("${arch}") + continue ;; + esac + + # Determine cross toolchain to use for Kconfig compiler tests + cross_compile="$(dpkg-architecture -qDEB_HOST_GNU_TYPE -a"${arch}" 2>/dev/null)-" + + # Arch-specific compiler, if any + arch_gcc=$(cat < build/.config + + # Environment variables for 'make *config' + env=(ARCH="${kern_arch}" + DEB_ARCH="${arch}" + CROSS_COMPILE="${cross_compile}" + CC="${gcc_path}") + + # Concurrency level + if [ -n "${conc_level:-}" ] ; then + env+=("${conc_level}") + fi + + # Call config target + echo + echo "* Run ${target} on ${arch}/${flavour} ..." + ${kmake} O=build "${env[@]}" "${target}" + + # Move config for further processing + mv build/.config "${tmp_conf_file}" +done + +rc=0 + +if [ "${skip_checks:-}" = "true" ] ; then + echo + echo "Skipping config-check (skip_checks=${skip_checks}) ..." +else + echo + echo "Running config-check for all configurations ..." + fail=0 + for arch_flavour in ${FLAVOURS} ; do + arch=${arch_flavour%%-*} + flavour=${arch_flavour#*-} + tmp_conf_file=${TMP_DIR}/${arch}-config.flavour.${flavour} + + echo + echo "* Run config-check for ${arch}-${flavour} ..." + python3 debian/scripts/misc/annotations -f "${annotations_file}" \ + --arch "${arch}" --flavour "${flavour}" --check "${tmp_conf_file}" || \ + fail=$((fail + 1)) + done + + if [ ${fail} -gt 0 ] ; then + rc=1 + echo "ERROR: ${fail} config-check failures detected" >&2 + fi +fi + +if [ ${#warning_partial[@]} -gt 0 ] ; then + rc=1 + echo "ERROR: Config operation not applied to all architectures (skipped ${warning_partial[*]})" >&2 +fi + +# Recreate the annotations file +if [ "${mode}" = "genconfigs" ] ; then + rm -rf CONFIGS + mv "${TMP_DIR}" CONFIGS +else + echo + echo "Importing all configurations ..." + echo + for arch_flavour in ${FLAVOURS} ; do + arch=${arch_flavour%%-*} + flavour=${arch_flavour#*-} + tmp_conf_file=${TMP_DIR}/${arch}-config.flavour.${flavour} + + echo "* Import configs for ${arch}-${flavour} ..." + python3 debian/scripts/misc/annotations -f "${annotations_file}" \ + --arch "${arch}" --flavour "${flavour}" --import "${tmp_conf_file}" + done +fi + +exit "${rc}" diff --git a/debian/scripts/module-inclusion b/debian/scripts/module-inclusion new file mode 100755 index 0000000000000..ccec0f215e082 --- /dev/null +++ b/debian/scripts/module-inclusion @@ -0,0 +1,104 @@ +#!/bin/bash + +# +# Build a new directory of modules based on an inclusion list. +# The includsion list format must be a bash regular expression. +# +# usage: $0 ROOT INCLUSION_LIST +# example: $0 \ +# debian/build/build-virtual-ALL debian/build/build-virtual \ +# debian.master/control.d/virtual.inclusion-list \ +# virtual.depmap +master=0 +if [ "$1" = "--master" ]; then + master=1 + shift +fi + +ROOT=$1 +NROOT=$2 +ILIST=$3 +DEPMAP=$4 + +tmp="/tmp/module-inclusion.$$" + +# +# Prep a destination directory. +# +mkdir -p ${NROOT} + +{ + # Copy over the framework into the master package. + if [ "$master" -eq 1 ]; then + (cd ${ROOT}; find . ! -name "*.ko" -type f) + fi + + # Copy over modules by name or pattern. + while read -r i + do + # + # 'find' blurts a warning if it cannot find any ko files. + # + case "$i" in + \!*) + (cd ${ROOT}; ${i#!} || true) + ;; + *\**) + (cd ${ROOT}; eval find "${i}" -name "*.ko" || true) + ;; + *) + echo "$i" + ;; + esac + done <"${ILIST}" +} >"$tmp" + +# Copy over the listed modules. +while read i +do + # If this is already moved over, all is good. + if [ -f "${NROOT}/$i" ]; then + : + + # If present in the source, moved it over. + elif [ -f "${ROOT}/$i" ]; then + mkdir -p "${NROOT}/`dirname $i`" + mv "${ROOT}/$i" "${NROOT}/$i" + + # Otherwise, it is missing. + else + echo "Warning: Could not find ${ROOT}/$i" 1>&2 + fi +done <"$tmp" + +# Copy over any dependancies, note if those are missing +# we know they are in a pre-requisite package as they must +# have existed at depmap generation time, and can only have +# moved into a package. +let n=0 || true +while [ -s "$tmp" ] +do + let n="$n+1" || true + [ "$n" = "20" ] && break || true + + echo "NOTE: pass $n: dependency scan" 1>&2 + + while read i + do + grep "^$i " "$DEPMAP" | \ + while read m d + do + if [ -f "${ROOT}/$d" ]; then + echo "NOTE: pass $n: ${i} pulls in ${d}" 1>&2 + echo "$d" + mkdir -p "${NROOT}/`dirname $d`" + mv "${ROOT}/$d" "${NROOT}/$d" + fi + done + done <"$tmp" >"$tmp.new" + mv -f "$tmp.new" "$tmp" +done + +rm -f "$tmp" + +exit 0 diff --git a/debian/scripts/sign-module b/debian/scripts/sign-module new file mode 100755 index 0000000000000..03ce543de7f8e --- /dev/null +++ b/debian/scripts/sign-module @@ -0,0 +1,40 @@ +#!/bin/bash -eu +# +# Staging drivers must not be signed if they are not listed in a +# signature-inclusion file to prevent loading of 'unsafe' drivers in a +# Secure Boot environment. +# +# Exit with status 0 if the provided module needs to be signed, 1 otherwise +# + +mod=${1} + +# Sign the module if not a staging driver +if [ "${mod/\/drivers\/staging\//}" = "${mod}" ] ; then + exit 0 +fi + +root=$(dirname "$(realpath -e "${0}")")/../.. +. "${root}"/debian/debian.env + +# Collect the signature-inclusion files +sig_incls=() +for d in debian "${DEBIAN}" ; do + if [ -f "${root}"/"${d}"/signature-inclusion ] ; then + sig_incls+=("${root}"/"${d}"/signature-inclusion) + fi +done + +# Sign the module if no signature-inclusion files +if [ ${#sig_incls[@]} -eq 0 ] ; then + exit 0 +fi + +# Sign the module if listed in signature-inclusion files +if grep -qFx "${mod##*/}" "${sig_incls[@]}" ; then + exit 0 +fi + +# Don't sign the module +echo "UBUNTU: Not signing ${1}" +exit 1 diff --git a/debian/signature-inclusion b/debian/signature-inclusion new file mode 100644 index 0000000000000..f919d4dfddfa5 --- /dev/null +++ b/debian/signature-inclusion @@ -0,0 +1,12 @@ +# +# This file lists the staging drivers that are safe for signing +# and loading in a secure boot environment with signed module enforcement. +# +r8188eu.ko +r8192e_pci.ko +r8192u_usb.ko +r8712u.ko +rtllib_crypt_ccmp.ko +rtllib_crypt_tkip.ko +rtllib_crypt_wep.ko +rtllib.ko diff --git a/debian/snapcraft.mk b/debian/snapcraft.mk new file mode 100644 index 0000000000000..bbccdcc2fecad --- /dev/null +++ b/debian/snapcraft.mk @@ -0,0 +1,11 @@ +ifeq ($(ARCH),) + arch := $(shell uname -m | sed -e s/i.86/i386/ -e s/x86_64/amd64/ \ + -e s/arm.*/armhf/ -e s/s390/s390x/ -e s/ppc.*/powerpc/ \ + -e s/aarch64.*/arm64/ ) +else ifeq ($(ARCH),arm) + arch := armhf +else + arch := $(ARCH) +endif +config: + python3 debian/scripts/misc/annotations --export --arch $(arch) --flavour $(flavour) >.config diff --git a/debian/source/format b/debian/source/format new file mode 100644 index 0000000000000..d3827e75a5cad --- /dev/null +++ b/debian/source/format @@ -0,0 +1 @@ +1.0 diff --git a/debian/source/options b/debian/source/options new file mode 100644 index 0000000000000..b29684e492759 --- /dev/null +++ b/debian/source/options @@ -0,0 +1,8 @@ +# Ignore vbox symlinks, we will regenerate these at clean (LP:1426113) +## autoreconstruct -- begin +# Ignore any symlinks created since the orig which are rebuilt by reconstruct. +## autoreconstruct -- end + +# force "dpkg-source -I -i" behavior +diff-ignore +tar-ignore diff --git a/debian/templates/extra.postinst.in b/debian/templates/extra.postinst.in new file mode 100755 index 0000000000000..c4a556c5a6b94 --- /dev/null +++ b/debian/templates/extra.postinst.in @@ -0,0 +1,20 @@ +#!/bin/sh +set -e + +version=@abiname@@localversion@ +image_path=/boot/@image-stem@-$version + +if [ "$1" != configure ]; then + exit 0 +fi + +depmod -a -F /boot/System.map-$version $version || true +if [ -d /etc/kernel/postinst.d ]; then + cat - >/usr/lib/linux/triggers/$version </dev/null || true +# +# We should be rebuilding the initramfs here on removal to pare down the +# initramfs if it contains any of the objects we just removed. But people +# commonly remove kernels in order to free space in /boot, and rebuilding the +# initramfs now risks ENOSPC when we are trying to make space. The files we +# leave lying about could be confusing, but we trade that against safety on +# removal. +# +#if [ -d /etc/kernel/postinst.d ]; then +# # We want to behave as if linux-image (without us) was installed, therefore +# # we do not want the postinst support to know we are being removed, claim +# # this is an installation event. +# cat - >/usr/lib/linux/triggers/$version </usr/lib/linux/triggers/$version </dev/null; then + linux-update-symlinks remove $version $image_path +fi + +if [ -d /etc/kernel/postrm.d ]; then + # We cannot trigger ourselves as at the end of this we will no longer + # exist and can no longer respond to the trigger. The trigger would + # then become lost. Therefore we clear any pending trigger and apply + # postrm directly. + if [ -f /usr/lib/linux/triggers/$version ]; then + echo "$0 ... removing pending trigger" + rm -f /usr/lib/linux/triggers/$version + fi + DEB_MAINT_PARAMS="$*" run-parts --report --exit-on-error --arg=$version \ + --arg=$image_path /etc/kernel/postrm.d +fi + +if [ "$1" = purge ]; then + for extra_file in modules.dep modules.isapnpmap modules.pcimap \ + modules.usbmap modules.parportmap \ + modules.generic_string modules.ieee1394map \ + modules.ieee1394map modules.pnpbiosmap \ + modules.alias modules.ccwmap modules.inputmap \ + modules.symbols modules.ofmap \ + modules.seriomap modules.\*.bin \ + modules.softdep modules.devname; do + eval rm -f /lib/modules/$version/$extra_file + done + rmdir /lib/modules/$version || true +fi + +exit 0 diff --git a/debian/templates/image.preinst.in b/debian/templates/image.preinst.in new file mode 100755 index 0000000000000..74bdb97b76847 --- /dev/null +++ b/debian/templates/image.preinst.in @@ -0,0 +1,22 @@ +#!/bin/sh +set -e + +version=@abiname@@localversion@ +image_path=/boot/@image-stem@-$version + +if [ "$1" = abort-upgrade ]; then + exit 0 +fi + +if [ "$1" = install ]; then + # Create a flag file for postinst + mkdir -p /lib/modules/$version + touch /lib/modules/$version/.fresh-install +fi + +if [ -d /etc/kernel/preinst.d ]; then + DEB_MAINT_PARAMS="$*" run-parts --report --exit-on-error --arg=$version \ + --arg=$image_path /etc/kernel/preinst.d +fi + +exit 0 diff --git a/debian/templates/image.prerm.in b/debian/templates/image.prerm.in new file mode 100755 index 0000000000000..347104d6e1824 --- /dev/null +++ b/debian/templates/image.prerm.in @@ -0,0 +1,18 @@ +#!/bin/sh +set -e + +version=@abiname@@localversion@ +image_path=/boot/@image-stem@-$version + +if [ "$1" != remove ]; then + exit 0 +fi + +linux-check-removal $version + +if [ -d /etc/kernel/prerm.d ]; then + DEB_MAINT_PARAMS="$*" run-parts --report --exit-on-error --arg=$version \ + --arg=$image_path /etc/kernel/prerm.d +fi + +exit 0 diff --git a/debian/tests-build/README b/debian/tests-build/README new file mode 100644 index 0000000000000..c74d1c4aef859 --- /dev/null +++ b/debian/tests-build/README @@ -0,0 +1,21 @@ +Scripts placed in this directory get called one at a time by run-parts(8). +The scripts are expected to perform some sort of sanity checks on the +finished build. Scripts will be called once for each flavour. + +Some environment variables are exported to make life a little easier: + +DPKG_ARCH : The dpkg architecture (e.g. "amd64") +KERN_ARCH : The kernel architecture (e.g. "x86_64") +FLAVOUR : The specific flavour for this run (e.g. "generic") +VERSION : The full version of this build (e.g. 2.6.22-1) +REVISION : The exact revision of this build (e.g. 1.3) +PREV_REVISION : The revision prior to this one +ABI_NUM : The specific ABI number for this build (e.g. 2) +PREV_ABI_NUM : The previous ABI number. Can be the same as ABI_NUM. +BUILD_DIR : The directory where this build took place +INSTALL_DIR : The directory where the package is prepared +SOURCE_DIR : Where the main kernel source is + +Scripts are expected to have a zero exit status when no problems occur, +and non-zero when an error occurs that should stop the build. Scripts +should print whatever info they deem needed to deduce the problem. diff --git a/debian/tests-build/check-aliases b/debian/tests-build/check-aliases new file mode 100755 index 0000000000000..ab3f23a7ec6e9 --- /dev/null +++ b/debian/tests-build/check-aliases @@ -0,0 +1,26 @@ +#!/usr/bin/perl -w + +my %map; + +print "Checking for dupe aliases in $ENV{'FLAVOUR'}...\n"; + +$aliases = + "$ENV{'INSTALL_DIR'}/lib/modules/$ENV{'VERSION'}-$ENV{'FLAVOUR'}/modules.alias"; + +exit 0 unless (-e $aliases); + +open(ALIASES, "< $aliases") or die "Could not open $aliases"; + +while () { + chomp; + my ($junk, $alias, $module) = split; + + if (defined($map{$alias})) { + printf("%s %20s / %-20s : %s \n", ("$map{$alias}" eq "$module") + ? "INT" : " ", $map{$alias}, $module, $alias); + } else { + $map{$alias} = $module; + } +} + +exit(0); diff --git a/debian/tests/control b/debian/tests/control new file mode 100644 index 0000000000000..bb05f71c6cbc3 --- /dev/null +++ b/debian/tests/control @@ -0,0 +1,7 @@ +Tests: rebuild +Depends: @builddeps@, fakeroot +Restrictions: allow-stderr, skippable + +Tests: ubuntu-regression-suite +Depends: build-essential, fakeroot, gcc-multilib [amd64 armhf i386], gdb, git, python3 +Restrictions: allow-stderr, isolation-machine, breaks-testbed, skippable diff --git a/debian/tests/rebuild b/debian/tests/rebuild new file mode 100755 index 0000000000000..365835c92d926 --- /dev/null +++ b/debian/tests/rebuild @@ -0,0 +1,20 @@ +#!/bin/sh + +# If we are triggering for just linux or linux-meta we know we have +# just built the kernel and there is no point in repeating that +# build, it just wastes time. (LP: #1498862) +build_needed=0 +for trigger in ${ADT_TEST_TRIGGERS:-force} +do + case "$trigger" in + linux/*|linux-lts-*/*|linux-meta*/*|linux-oem*/*|fakeroot/*|gdb/*|git/*|bzr/*|gcc-multilib/*) ;; + *) build_needed=1 ;; + esac +done +if [ "$build_needed" -eq 0 ]; then + echo "rebuild: short circuiting build for '${ADT_TEST_TRIGGERS}'" + exit 77 +fi + +set -e +dpkg-buildpackage -rfakeroot -us -uc -b -Pautopkgtest diff --git a/debian/tests/ubuntu-regression-suite b/debian/tests/ubuntu-regression-suite new file mode 100755 index 0000000000000..ef73cf5f7c1d8 --- /dev/null +++ b/debian/tests/ubuntu-regression-suite @@ -0,0 +1,46 @@ +#!/bin/sh +set -e + +# Only run regression-suite on kernels we can boot in canonistack +source=`dpkg-parsechangelog -SSource` +case $source in + linux|linux-unstable|linux-hwe*|linux-lowlatency*|linux-kvm|linux-oem) + ;; + *) + echo "ubuntu-regression-suite is pointless, if one cannot boot the kernel" + exit 77 + ;; +esac + +# Only run regression-suite if we were requested to +have_meta=0 +for trigger in ${ADT_TEST_TRIGGERS} +do + case "$trigger" in + linux-meta/*|linux-meta-*/*) + have_meta=1 + ;; + esac +done +if [ -n "$ADT_TEST_TRIGGERS" ] && [ "$have_meta" -eq 0 ]; then + echo "ubuntu-regression-suite is not requested, as there is no linux-meta trigger" + exit 77 +fi + +sver=`dpkg-parsechangelog -SVersion` +read x rver x &2 + exit 1 +fi + +git clone --depth=1 -b autotest3 git://git.launchpad.net/~canonical-kernel-team/+git/kernel-testing +git -C kernel-testing/ show HEAD -q +kernel-testing/run-dep8-tests diff --git a/debian/tools/generic b/debian/tools/generic new file mode 100644 index 0000000000000..ebc87fd8c5b8c --- /dev/null +++ b/debian/tools/generic @@ -0,0 +1,60 @@ +#!/bin/bash +full_version=`uname -r` + +# First check for a fully qualified version. +this="/usr/lib/linux-tools/$full_version/`basename $0`" +if [ -f "$this" ]; then + exec "$this" "$@" +fi + +# Removing flavour from version i.e. generic or server. +flavour_abi=${full_version#*-} +flavour=${flavour_abi#*-} +version=${full_version%-$flavour} +this="$0_$version" +if [ -f "$this" ]; then + exec "$this" "$@" +fi + +# Before saucy kernels we had no flavour linkage. +if dpkg --compare-versions "$version" lt "3.11.0"; then + flavour='' +else + flavour="-$flavour" +fi +# Hint at the cloud tools if they exist (trusty and later) +if dpkg --compare-versions "$version" ge "3.13.0"; then + cld="" +else + cld=":" +fi +# Work out if this is an LTS backport or not. +codename=`lsb_release -cs` +case "$codename" in +precise) base='3.2.0-9999' ;; +trusty) base='3.13.0-9999' ;; +*) base='' ;; +esac +std="" +lts=":" +if [ "$base" != "" ]; then + if dpkg --compare-versions "$version" gt "$base"; then + std=":" + lts="" + fi +fi + +# Give them a hint as to what to install. + echo "WARNING: `basename $0` not found for kernel $version" >&2 + echo "" >&2 + echo " You may need to install the following packages for this specific kernel:" >&2 + echo " linux-tools-$version$flavour" >&2 +$cld echo " linux-cloud-tools-$version$flavour" >&2 + echo "" >&2 + echo " You may also want to install one of the following packages to keep up to date:" >&2 +$std echo " linux-tools$flavour" >&2 +$std $cld echo " linux-cloud-tools$flavour" >&2 +$lts echo " linux-tools$flavour-lts-" >&2 +$lts $cld echo " linux-cloud-tools$flavour-lts-" >&2 + +exit 2 diff --git a/debian/tools/python-perf.py b/debian/tools/python-perf.py new file mode 100644 index 0000000000000..d572fece82aaa --- /dev/null +++ b/debian/tools/python-perf.py @@ -0,0 +1,32 @@ +import os +import importlib.util +from glob import glob + +class KernelNotFoundError(Exception): + def __init__(self): + kernel_version = os.uname().release + super().__init__(f"WARNING: python perf module not found for kernel {kernel_version}\n\n" + f"You may need to install the following packages for this specific kernel:\n" + f" linux-tools-{kernel_version}-generic\n" + f"You may also want to install of the following package to keep up to date:\n" + f" linux-tools-generic") + +# Extract ABI number from kernel version +def _get_abi_version(): + _kernel_version = os.uname().release + _parts = _kernel_version.split("-") + return "-".join(_parts[:-1]) + +# Load the actual python-perf module for the running kernel +_abi_version = _get_abi_version() +_perf_dir = f"/usr/lib/python3/dist-packages/linux-tools-{_abi_version}" +if not os.path.exists(_perf_dir): + raise KernelNotFoundError() +_perf_lib = glob(os.path.join(_perf_dir, "*.so"))[-1] + +_spec = importlib.util.spec_from_file_location("perf", _perf_lib) +_perf = importlib.util.module_from_spec(_spec) +_spec.loader.exec_module(_perf) + +# Expose the 'perf' module. +__all__ = ['perf'] diff --git a/debian/v4l2loopback-modules.ignore b/debian/v4l2loopback-modules.ignore new file mode 100644 index 0000000000000..d394e47bc8194 --- /dev/null +++ b/debian/v4l2loopback-modules.ignore @@ -0,0 +1 @@ +v4l2loopback diff --git a/debian/zfs-modules.ignore b/debian/zfs-modules.ignore new file mode 100644 index 0000000000000..987d577ec9e8e --- /dev/null +++ b/debian/zfs-modules.ignore @@ -0,0 +1,11 @@ +icp +spl +splat +zavl +zcommon +zfs +zlua +znvpair +zpios +zunicode +zzstd diff --git a/delphix b/delphix new file mode 100644 index 0000000000000..e69de29bb2d1d diff --git a/drivers/Makefile b/drivers/Makefile index 37fd6ce3bd7f5..062a48f608873 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -66,14 +66,9 @@ obj-y += char/ # iommu/ comes before gpu as gpu are using iommu controllers obj-y += iommu/ -# gpu/ comes after char for AGP vs DRM startup and after iommu -obj-y += gpu/ obj-$(CONFIG_CONNECTOR) += connector/ -# i810fb depends on char/agp/ -obj-$(CONFIG_FB_I810) += video/fbdev/i810/ - obj-$(CONFIG_PARPORT) += parport/ obj-y += base/ block/ misc/ mfd/ nfc/ obj-$(CONFIG_LIBNVDIMM) += nvdimm/ @@ -85,6 +80,11 @@ obj-y += macintosh/ obj-y += scsi/ obj-y += nvme/ obj-$(CONFIG_ATA) += ata/ + +# gpu/ comes after char for AGP vs DRM startup and after iommu +obj-y += gpu/ +# i810fb depends on char/agp/ +obj-$(CONFIG_FB_I810) += video/fbdev/i810/ obj-$(CONFIG_TARGET_CORE) += target/ obj-$(CONFIG_MTD) += mtd/ obj-$(CONFIG_SPI) += spi/ diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h index 2a900c9941fee..41c7aac2ffcf9 100644 --- a/drivers/accel/habanalabs/common/habanalabs.h +++ b/drivers/accel/habanalabs/common/habanalabs.h @@ -2547,7 +2547,7 @@ struct hl_state_dump_specs { * DEVICES */ -#define HL_STR_MAX 32 +#define HL_STR_MAX 64 #define HL_DEV_STS_MAX (HL_DEVICE_STATUS_LAST + 1) diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 4b06402269869..bad1ccc81ad73 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include @@ -131,22 +131,6 @@ static int ivpu_get_capabilities(struct ivpu_device *vdev, struct drm_ivpu_param return 0; } -static int ivpu_get_core_clock_rate(struct ivpu_device *vdev, u64 *clk_rate) -{ - int ret; - - ret = ivpu_rpm_get_if_active(vdev); - if (ret < 0) - return ret; - - *clk_rate = ret ? ivpu_hw_reg_pll_freq_get(vdev) : 0; - - if (ret) - ivpu_rpm_put(vdev); - - return 0; -} - static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { struct ivpu_file_priv *file_priv = file->driver_priv; @@ -170,7 +154,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f args->value = vdev->platform; break; case DRM_IVPU_PARAM_CORE_CLOCK_RATE: - ret = ivpu_get_core_clock_rate(vdev, &args->value); + args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio); break; case DRM_IVPU_PARAM_NUM_CONTEXTS: args->value = ivpu_get_context_count(vdev); @@ -387,12 +371,15 @@ int ivpu_shutdown(struct ivpu_device *vdev) { int ret; - ivpu_prepare_for_reset(vdev); + /* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */ + pci_save_state(to_pci_dev(vdev->drm.dev)); ret = ivpu_hw_power_down(vdev); if (ret) ivpu_warn(vdev, "Failed to power down HW: %d\n", ret); + pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); + return ret; } @@ -530,7 +517,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev) vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID; vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID; atomic64_set(&vdev->unique_id_counter, 0); - xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC); + xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1); lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key); INIT_LIST_HEAD(&vdev->bo_list); @@ -559,11 +546,11 @@ static int ivpu_dev_init(struct ivpu_device *vdev) /* Power up early so the rest of init code can access VPU registers */ ret = ivpu_hw_power_up(vdev); if (ret) - goto err_power_down; + goto err_shutdown; ret = ivpu_mmu_global_context_init(vdev); if (ret) - goto err_power_down; + goto err_shutdown; ret = ivpu_mmu_init(vdev); if (ret) @@ -600,10 +587,8 @@ static int ivpu_dev_init(struct ivpu_device *vdev) ivpu_mmu_reserved_context_fini(vdev); err_mmu_gctx_fini: ivpu_mmu_global_context_fini(vdev); -err_power_down: - ivpu_hw_power_down(vdev); - if (IVPU_WA(d3hot_after_power_off)) - pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); +err_shutdown: + ivpu_shutdown(vdev); err_xa_destroy: xa_destroy(&vdev->submitted_jobs_xa); xa_destroy(&vdev->context_xa); @@ -626,9 +611,8 @@ static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev) static void ivpu_dev_fini(struct ivpu_device *vdev) { ivpu_pm_disable(vdev); + ivpu_prepare_for_reset(vdev); ivpu_shutdown(vdev); - if (IVPU_WA(d3hot_after_power_off)) - pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); ivpu_jobs_abort_all(vdev); ivpu_job_done_consumer_fini(vdev); diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 069ace4adb2d1..e7a9e849940ea 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #ifndef __IVPU_DRV_H__ @@ -87,7 +87,6 @@ struct ivpu_wa_table { bool punit_disabled; bool clear_runtime_mem; - bool d3hot_after_power_off; bool interrupt_clear_with_0; bool disable_clock_relinquish; bool disable_d0i3_msg; diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h index b2909168a0a69..094c659d2800b 100644 --- a/drivers/accel/ivpu/ivpu_hw.h +++ b/drivers/accel/ivpu/ivpu_hw.h @@ -21,6 +21,7 @@ struct ivpu_hw_ops { u32 (*profiling_freq_get)(struct ivpu_device *vdev); void (*profiling_freq_drive)(struct ivpu_device *vdev, bool enable); u32 (*reg_pll_freq_get)(struct ivpu_device *vdev); + u32 (*ratio_to_freq)(struct ivpu_device *vdev, u32 ratio); u32 (*reg_telemetry_offset_get)(struct ivpu_device *vdev); u32 (*reg_telemetry_size_get)(struct ivpu_device *vdev); u32 (*reg_telemetry_enable_get)(struct ivpu_device *vdev); @@ -130,6 +131,11 @@ static inline u32 ivpu_hw_reg_pll_freq_get(struct ivpu_device *vdev) return vdev->hw->ops->reg_pll_freq_get(vdev); }; +static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) +{ + return vdev->hw->ops->ratio_to_freq(vdev, ratio); +} + static inline u32 ivpu_hw_reg_telemetry_offset_get(struct ivpu_device *vdev) { return vdev->hw->ops->reg_telemetry_offset_get(vdev); diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index 89af1006df558..5e392b6823764 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include "ivpu_drv.h" @@ -75,7 +75,6 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) { vdev->wa.punit_disabled = false; vdev->wa.clear_runtime_mem = false; - vdev->wa.d3hot_after_power_off = true; REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK); if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) { @@ -86,7 +85,6 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) IVPU_PRINT_WA(punit_disabled); IVPU_PRINT_WA(clear_runtime_mem); - IVPU_PRINT_WA(d3hot_after_power_off); IVPU_PRINT_WA(interrupt_clear_with_0); } @@ -805,12 +803,12 @@ static void ivpu_hw_37xx_profiling_freq_drive(struct ivpu_device *vdev, bool ena /* Profiling freq - is a debug feature. Unavailable on VPU 37XX. */ } -static u32 ivpu_hw_37xx_pll_to_freq(u32 ratio, u32 config) +static u32 ivpu_hw_37xx_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) { u32 pll_clock = PLL_REF_CLK_FREQ * ratio; u32 cpu_clock; - if ((config & 0xff) == PLL_RATIO_4_3) + if ((vdev->hw->config & 0xff) == PLL_RATIO_4_3) cpu_clock = pll_clock * 2 / 4; else cpu_clock = pll_clock * 2 / 5; @@ -829,7 +827,7 @@ static u32 ivpu_hw_37xx_reg_pll_freq_get(struct ivpu_device *vdev) if (!ivpu_is_silicon(vdev)) return PLL_SIMULATION_FREQ; - return ivpu_hw_37xx_pll_to_freq(pll_curr_ratio, vdev->hw->config); + return ivpu_hw_37xx_ratio_to_freq(vdev, pll_curr_ratio); } static u32 ivpu_hw_37xx_reg_telemetry_offset_get(struct ivpu_device *vdev) @@ -1052,6 +1050,7 @@ const struct ivpu_hw_ops ivpu_hw_37xx_ops = { .profiling_freq_get = ivpu_hw_37xx_profiling_freq_get, .profiling_freq_drive = ivpu_hw_37xx_profiling_freq_drive, .reg_pll_freq_get = ivpu_hw_37xx_reg_pll_freq_get, + .ratio_to_freq = ivpu_hw_37xx_ratio_to_freq, .reg_telemetry_offset_get = ivpu_hw_37xx_reg_telemetry_offset_get, .reg_telemetry_size_get = ivpu_hw_37xx_reg_telemetry_size_get, .reg_telemetry_enable_get = ivpu_hw_37xx_reg_telemetry_enable_get, diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index a1523d0b1ef36..0be353ad872d0 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -980,6 +980,11 @@ static u32 ivpu_hw_40xx_reg_pll_freq_get(struct ivpu_device *vdev) return PLL_RATIO_TO_FREQ(pll_curr_ratio); } +static u32 ivpu_hw_40xx_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) +{ + return PLL_RATIO_TO_FREQ(ratio); +} + static u32 ivpu_hw_40xx_reg_telemetry_offset_get(struct ivpu_device *vdev) { return REGB_RD32(VPU_40XX_BUTTRESS_VPU_TELEMETRY_OFFSET); @@ -1230,6 +1235,7 @@ const struct ivpu_hw_ops ivpu_hw_40xx_ops = { .profiling_freq_get = ivpu_hw_40xx_profiling_freq_get, .profiling_freq_drive = ivpu_hw_40xx_profiling_freq_drive, .reg_pll_freq_get = ivpu_hw_40xx_reg_pll_freq_get, + .ratio_to_freq = ivpu_hw_40xx_ratio_to_freq, .reg_telemetry_offset_get = ivpu_hw_40xx_reg_telemetry_offset_get, .reg_telemetry_size_get = ivpu_hw_40xx_reg_telemetry_size_get, .reg_telemetry_enable_get = ivpu_hw_40xx_reg_telemetry_enable_get, diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c index fa66c39b57eca..f4c5392483656 100644 --- a/drivers/accel/ivpu/ivpu_ipc.c +++ b/drivers/accel/ivpu/ivpu_ipc.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include @@ -501,7 +501,11 @@ int ivpu_ipc_init(struct ivpu_device *vdev) spin_lock_init(&ipc->cons_lock); INIT_LIST_HEAD(&ipc->cons_list); INIT_LIST_HEAD(&ipc->cb_msg_list); - drmm_mutex_init(&vdev->drm, &ipc->lock); + ret = drmm_mutex_init(&vdev->drm, &ipc->lock); + if (ret) { + ivpu_err(vdev, "Failed to initialize ipc->lock, ret %d\n", ret); + goto err_free_rx; + } ivpu_ipc_reset(vdev); return 0; diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c index 91bd640655ab3..2e46b322c4505 100644 --- a/drivers/accel/ivpu/ivpu_mmu.c +++ b/drivers/accel/ivpu/ivpu_mmu.c @@ -278,7 +278,7 @@ static const char *ivpu_mmu_event_to_str(u32 cmd) case IVPU_MMU_EVT_F_VMS_FETCH: return "Fetch of VMS caused external abort"; default: - return "Unknown CMDQ command"; + return "Unknown event"; } } @@ -286,15 +286,15 @@ static const char *ivpu_mmu_cmdq_err_to_str(u32 err) { switch (err) { case IVPU_MMU_CERROR_NONE: - return "No CMDQ Error"; + return "No error"; case IVPU_MMU_CERROR_ILL: return "Illegal command"; case IVPU_MMU_CERROR_ABT: - return "External abort on CMDQ read"; + return "External abort on command queue read"; case IVPU_MMU_CERROR_ATC_INV_SYNC: return "Sync failed to complete ATS invalidation"; default: - return "Unknown CMDQ Error"; + return "Unknown error"; } } diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 5f73854234ba9..64618fc2cec40 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include @@ -58,14 +58,11 @@ static int ivpu_suspend(struct ivpu_device *vdev) { int ret; - /* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */ - pci_save_state(to_pci_dev(vdev->drm.dev)); + ivpu_prepare_for_reset(vdev); ret = ivpu_shutdown(vdev); if (ret) - ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret); - - pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); + ivpu_err(vdev, "Failed to shutdown NPU: %d\n", ret); return ret; } @@ -74,10 +71,10 @@ static int ivpu_resume(struct ivpu_device *vdev) { int ret; - pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0); +retry: pci_restore_state(to_pci_dev(vdev->drm.dev)); + pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0); -retry: ret = ivpu_hw_power_up(vdev); if (ret) { ivpu_err(vdev, "Failed to power up HW: %d\n", ret); @@ -100,6 +97,7 @@ static int ivpu_resume(struct ivpu_device *vdev) ivpu_mmu_disable(vdev); err_power_down: ivpu_hw_power_down(vdev); + pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); if (!ivpu_fw_is_cold_boot(vdev)) { ivpu_pm_prepare_cold_boot(vdev); diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index 1fbc9b921c4fc..f677ad2177c2f 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -574,7 +574,7 @@ static u_long get_word(struct vc_data *vc) } attr_ch = get_char(vc, (u_short *)tmp_pos, &spk_attr); buf[cnt++] = attr_ch; - while (tmpx < vc->vc_cols - 1) { + while (tmpx < vc->vc_cols - 1 && cnt < ARRAY_SIZE(buf) - 1) { tmp_pos += 2; tmpx++; ch = get_char(vc, (u_short *)tmp_pos, &temp); diff --git a/drivers/accessibility/speakup/synth.c b/drivers/accessibility/speakup/synth.c index eea2a2fa4f015..45f9061031338 100644 --- a/drivers/accessibility/speakup/synth.c +++ b/drivers/accessibility/speakup/synth.c @@ -208,8 +208,10 @@ void spk_do_flush(void) wake_up_process(speakup_task); } -void synth_write(const char *buf, size_t count) +void synth_write(const char *_buf, size_t count) { + const unsigned char *buf = (const unsigned char *) _buf; + while (count--) synth_buffer_add(*buf++); synth_start(); diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c index 0555f68c2dfd6..5fba4dab5d088 100644 --- a/drivers/acpi/acpi_ipmi.c +++ b/drivers/acpi/acpi_ipmi.c @@ -22,6 +22,8 @@ MODULE_LICENSE("GPL"); /* the IPMI timeout is 5s */ #define IPMI_TIMEOUT (5000) #define ACPI_IPMI_MAX_MSG_LENGTH 64 +/* 2s should be suffient for SMI being selected */ +#define ACPI_IPMI_SMI_SELECTION_TIMEOUT (2 * HZ) struct acpi_ipmi_device { /* the device list attached to driver_data.ipmi_devices */ @@ -54,6 +56,7 @@ struct ipmi_driver_data { * to this selected global IPMI system interface. */ struct acpi_ipmi_device *selected_smi; + struct completion smi_selection_done; }; struct acpi_ipmi_msg { @@ -463,8 +466,10 @@ static void ipmi_register_bmc(int iface, struct device *dev) if (temp->handle == handle) goto err_lock; } - if (!driver_data.selected_smi) + if (!driver_data.selected_smi) { driver_data.selected_smi = ipmi_device; + complete(&driver_data.smi_selection_done); + } list_add_tail(&ipmi_device->head, &driver_data.ipmi_devices); mutex_unlock(&driver_data.ipmi_lock); @@ -578,6 +583,20 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address, return status; } +int acpi_wait_for_acpi_ipmi(void) +{ + long ret; + + ret = wait_for_completion_interruptible_timeout(&driver_data.smi_selection_done, + ACPI_IPMI_SMI_SELECTION_TIMEOUT); + + if (ret <= 0) + return -ETIMEDOUT; + + return 0; +} +EXPORT_SYMBOL_GPL(acpi_wait_for_acpi_ipmi); + static int __init acpi_ipmi_init(void) { int result; @@ -586,6 +605,8 @@ static int __init acpi_ipmi_init(void) if (acpi_disabled) return 0; + init_completion(&driver_data.smi_selection_done); + status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT, ACPI_ADR_SPACE_IPMI, &acpi_ipmi_space_handler, diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 04e273167e92a..8e01792228d1e 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -325,6 +325,7 @@ static const struct lpss_device_desc bsw_i2c_dev_desc = { static const struct property_entry bsw_spi_properties[] = { PROPERTY_ENTRY_U32("intel,spi-pxa2xx-type", LPSS_BSW_SSP), + PROPERTY_ENTRY_U32("num-cs", 2), { } }; diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile index 30f3fc13c29d1..8d18af396de92 100644 --- a/drivers/acpi/acpica/Makefile +++ b/drivers/acpi/acpica/Makefile @@ -5,6 +5,7 @@ ccflags-y := -D_LINUX -DBUILDING_ACPICA ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT +CFLAGS_tbfind.o += $(call cc-disable-warning, stringop-truncation) # use acpi.o to put all files here into acpi.o modparam namespace obj-y += acpi.o diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index ddd072cbc738d..2133085deda77 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -191,6 +191,10 @@ void acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, acpi_adr_space_type space_id, u32 function); +void +acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node, + acpi_adr_space_type space_id); + acpi_status acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function); diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c index b91155ea9c343..c9131259f717b 100644 --- a/drivers/acpi/acpica/dbnames.c +++ b/drivers/acpi/acpica/dbnames.c @@ -550,8 +550,12 @@ acpi_db_walk_for_fields(acpi_handle obj_handle, ACPI_FREE(buffer.pointer); buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER; - acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); - + status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) { + acpi_os_printf("Could Not evaluate object %p\n", + obj_handle); + return (AE_OK); + } /* * Since this is a field unit, surround the output in braces */ diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c index a43336f052065..415bec7a54365 100644 --- a/drivers/acpi/acpica/dswexec.c +++ b/drivers/acpi/acpica/dswexec.c @@ -397,11 +397,11 @@ acpi_status acpi_ds_exec_end_op(struct acpi_walk_state *walk_state) /* Resolve all operands */ + union acpi_operand_object **stack_ptr = NULL; + if (walk_state->num_operands > 0) + stack_ptr = ACPI_WALK_OPERANDS; status = acpi_ex_resolve_operands(walk_state->opcode, - &(walk_state-> - operands - [walk_state-> - num_operands - 1]), + stack_ptr, walk_state); } diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 18fdf2bc2d499..dc6004daf624b 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -20,10 +20,6 @@ extern u8 acpi_gbl_default_address_spaces[]; /* Local prototypes */ -static void -acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, - acpi_adr_space_type space_id); - static acpi_status acpi_ev_reg_run(acpi_handle obj_handle, u32 level, void *context, void **return_value); @@ -818,7 +814,7 @@ acpi_ev_reg_run(acpi_handle obj_handle, * ******************************************************************************/ -static void +void acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, acpi_adr_space_type space_id) { diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 3197e6303c5b0..624361a5f34d8 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -306,3 +306,57 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) } ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods) + +/******************************************************************************* + * + * FUNCTION: acpi_execute_orphan_reg_method + * + * PARAMETERS: device - Handle for the device + * space_id - The address space ID + * + * RETURN: Status + * + * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI + * device. This is a _REG method that has no corresponding region + * within the device's scope. + * + ******************************************************************************/ +acpi_status +acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id) +{ + struct acpi_namespace_node *node; + acpi_status status; + + ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method); + + /* Parameter validation */ + + if (!device) { + return_ACPI_STATUS(AE_BAD_PARAMETER); + } + + status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } + + /* Convert and validate the device handle */ + + node = acpi_ns_validate_handle(device); + if (node) { + + /* + * If an "orphan" _REG method is present in the device's scope + * for the given address space ID, run it. + */ + + acpi_ev_execute_orphan_reg_method(node, space_id); + } else { + status = AE_BAD_PARAMETER; + } + + (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); + return_ACPI_STATUS(status); +} + +ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method) diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index 8907b8bf42672..c49b9f8de723d 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -44,7 +44,6 @@ acpi_ex_system_memory_space_handler(u32 function, struct acpi_mem_mapping *mm = mem_info->cur_mm; u32 length; acpi_size map_length; - acpi_size page_boundary_map_length; #ifdef ACPI_MISALIGNMENT_NOT_SUPPORTED u32 remainder; #endif @@ -138,26 +137,8 @@ acpi_ex_system_memory_space_handler(u32 function, map_length = (acpi_size) ((mem_info->address + mem_info->length) - address); - /* - * If mapping the entire remaining portion of the region will cross - * a page boundary, just map up to the page boundary, do not cross. - * On some systems, crossing a page boundary while mapping regions - * can cause warnings if the pages have different attributes - * due to resource management. - * - * This has the added benefit of constraining a single mapping to - * one page, which is similar to the original code that used a 4k - * maximum window. - */ - page_boundary_map_length = (acpi_size) - (ACPI_ROUND_UP(address, ACPI_DEFAULT_PAGE_SIZE) - address); - if (page_boundary_map_length == 0) { - page_boundary_map_length = ACPI_DEFAULT_PAGE_SIZE; - } - - if (map_length > page_boundary_map_length) { - map_length = page_boundary_map_length; - } + if (map_length > ACPI_DEFAULT_PAGE_SIZE) + map_length = ACPI_DEFAULT_PAGE_SIZE; /* Create a new mapping starting at the address given */ diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 569bd15f211be..3f84d8ed9d299 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -316,9 +316,14 @@ static void acpi_bus_osc_negotiate_platform_control(void) capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PAD_SUPPORT; if (IS_ENABLED(CONFIG_ACPI_PROCESSOR)) capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PPC_OST_SUPPORT; + if (IS_ENABLED(CONFIG_ACPI_THERMAL)) + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT; capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT; capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PCLPI_SUPPORT; + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_OVER_16_PSTATES_SUPPORT; + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GED_SUPPORT; + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT; if (IS_ENABLED(CONFIG_ACPI_PRMT)) capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PRM_SUPPORT; if (IS_ENABLED(CONFIG_ACPI_FFH)) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index d155a86a86148..1b27ebc6d01d0 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -166,6 +166,13 @@ show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_freq); show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf); show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time); +/* Check for valid access_width, otherwise, fallback to using bit_width */ +#define GET_BIT_WIDTH(reg) ((reg)->access_width ? (8 << ((reg)->access_width - 1)) : (reg)->bit_width) + +/* Shift and apply the mask for CPC reads/writes */ +#define MASK_VAL(reg, val) (((val) >> (reg)->bit_offset) & \ + GENMASK(((reg)->bit_width) - 1, 0)) + static ssize_t show_feedback_ctrs(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -780,6 +787,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) } else if (gas_t->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { if (gas_t->address) { void __iomem *addr; + size_t access_width; if (!osc_cpc_flexible_adr_space_confirmed) { pr_debug("Flexible address space capability not supported\n"); @@ -787,7 +795,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) goto out_free; } - addr = ioremap(gas_t->address, gas_t->bit_width/8); + access_width = GET_BIT_WIDTH(gas_t) / 8; + addr = ioremap(gas_t->address, access_width); if (!addr) goto out_free; cpc_ptr->cpc_regs[i-2].sys_mem_vaddr = addr; @@ -983,6 +992,7 @@ int __weak cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) { void __iomem *vaddr = NULL; + int size; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; @@ -992,14 +1002,14 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) } *val = 0; + size = GET_BIT_WIDTH(reg); if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { - u32 width = 8 << (reg->access_width - 1); u32 val_u32; acpi_status status; status = acpi_os_read_port((acpi_io_address)reg->address, - &val_u32, width); + &val_u32, size); if (ACPI_FAILURE(status)) { pr_debug("Error: Failed to read SystemIO port %llx\n", reg->address); @@ -1008,17 +1018,24 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *val = val_u32; return 0; - } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) { + /* + * For registers in PCC space, the register size is determined + * by the bit width field; the access size is used to indicate + * the PCC subspace id. + */ + size = reg->bit_width; vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); + } else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) return cpc_read_ffh(cpu, reg, val); else return acpi_os_read_memory((acpi_physical_address)reg->address, - val, reg->bit_width); + val, size); - switch (reg->bit_width) { + switch (size) { case 8: *val = readb_relaxed(vaddr); break; @@ -1032,27 +1049,37 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *val = readq_relaxed(vaddr); break; default: - pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n", - reg->bit_width, pcc_ss_id); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + pr_debug("Error: Cannot read %u bit width from system memory: 0x%llx\n", + size, reg->address); + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n", + size, pcc_ss_id); + } return -EFAULT; } + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + *val = MASK_VAL(reg, *val); + return 0; } static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) { int ret_val = 0; + int size; void __iomem *vaddr = NULL; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; + size = GET_BIT_WIDTH(reg); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { - u32 width = 8 << (reg->access_width - 1); acpi_status status; status = acpi_os_write_port((acpi_io_address)reg->address, - (u32)val, width); + (u32)val, size); if (ACPI_FAILURE(status)) { pr_debug("Error: Failed to write SystemIO port %llx\n", reg->address); @@ -1060,17 +1087,27 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) } return 0; - } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) { + /* + * For registers in PCC space, the register size is determined + * by the bit width field; the access size is used to indicate + * the PCC subspace id. + */ + size = reg->bit_width; vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); + } else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) return cpc_write_ffh(cpu, reg, val); else return acpi_os_write_memory((acpi_physical_address)reg->address, - val, reg->bit_width); + val, size); + + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + val = MASK_VAL(reg, val); - switch (reg->bit_width) { + switch (size) { case 8: writeb_relaxed(val, vaddr); break; @@ -1084,8 +1121,13 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) writeq_relaxed(val, vaddr); break; default: - pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n", - reg->bit_width, pcc_ss_id); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + pr_debug("Error: Cannot write %u bit width to system memory: 0x%llx\n", + size, reg->address); + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n", + size, pcc_ss_id); + } ret_val = -EFAULT; break; } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 02255795b800d..1cec29ab64ce8 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1482,13 +1482,14 @@ static bool install_gpio_irq_event_handler(struct acpi_ec *ec) static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, bool call_reg) { + acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; acpi_status status; acpi_ec_start(ec, false); if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { acpi_ec_enter_noirq(ec); - status = acpi_install_address_space_handler_no_reg(ec->handle, + status = acpi_install_address_space_handler_no_reg(scope_handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler, NULL, ec); @@ -1497,11 +1498,13 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, return -ENODEV; } set_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); - ec->address_space_handler_holder = ec->handle; } if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { - acpi_execute_reg_methods(ec->handle, ACPI_ADR_SPACE_EC); + acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); + if (scope_handle != ec->handle) + acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC); + set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } @@ -1553,10 +1556,13 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, static void ec_remove_handlers(struct acpi_ec *ec) { + acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; + if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_address_space_handler( - ec->address_space_handler_holder, - ACPI_ADR_SPACE_EC, &acpi_ec_space_handler))) + scope_handle, + ACPI_ADR_SPACE_EC, + &acpi_ec_space_handler))) pr_err("failed to remove space handler\n"); clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } @@ -1595,14 +1601,18 @@ static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device, bool ca { int ret; - ret = ec_install_handlers(ec, device, call_reg); - if (ret) - return ret; - /* First EC capable of handling transactions */ if (!first_ec) first_ec = ec; + ret = ec_install_handlers(ec, device, call_reg); + if (ret) { + if (ec == first_ec) + first_ec = NULL; + + return ret; + } + pr_info("EC_CMD/EC_SC=0x%lx, EC_DATA=0x%lx\n", ec->command_addr, ec->data_addr); diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 6588525c45efa..7e17e2a3f2f09 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -184,7 +184,6 @@ enum acpi_ec_event_state { struct acpi_ec { acpi_handle handle; - acpi_handle address_space_handler_holder; int gpe; int irq; unsigned long command_addr; @@ -301,5 +300,10 @@ void acpi_mipi_check_crs_csi2(acpi_handle handle); void acpi_mipi_scan_crs_csi2(void); void acpi_mipi_init_crs_csi2_swnodes(void); void acpi_mipi_crs_csi2_cleanup(void); +#ifdef CONFIG_X86 +bool acpi_graph_ignore_port(acpi_handle handle); +#else +static inline bool acpi_graph_ignore_port(acpi_handle handle) { return false; } +#endif #endif /* _ACPI_INTERNAL_H_ */ diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c index 7286cf4579bcf..0ab13751f0dbc 100644 --- a/drivers/acpi/mipi-disco-img.c +++ b/drivers/acpi/mipi-disco-img.c @@ -19,6 +19,7 @@ */ #include +#include #include #include #include @@ -723,3 +724,83 @@ void acpi_mipi_crs_csi2_cleanup(void) list_for_each_entry_safe(csi2, csi2_tmp, &acpi_mipi_crs_csi2_list, entry) acpi_mipi_del_crs_csi2(csi2); } + +#ifdef CONFIG_X86 +#include +#include + +/* CPU matches for Dell generations with broken ACPI MIPI DISCO info */ +static const struct x86_cpu_id dell_broken_mipi_disco_cpu_gens[] = { + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, NULL), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, NULL), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, NULL), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, NULL), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, NULL), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, NULL), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, NULL), + {} +}; + +static const char *strnext(const char *s1, const char *s2) +{ + s1 = strstr(s1, s2); + + if (!s1) + return NULL; + + return s1 + strlen(s2); +} + +/** + * acpi_graph_ignore_port - Tell whether a port node should be ignored + * @handle: The ACPI handle of the node (which may be a port node) + * + * Return: true if a port node should be ignored and the data to that should + * come from other sources instead (Windows ACPI definitions and + * ipu-bridge). This is currently used to ignore bad port nodes related to IPU6 + * ("IPU?") and camera sensor devices ("LNK?") in certain Dell systems with + * Intel VSC. + */ +bool acpi_graph_ignore_port(acpi_handle handle) +{ + const char *path = NULL, *orig_path; + static bool dmi_tested, ignore_port; + + if (!dmi_tested) { + if (dmi_name_in_vendors("Dell Inc.") && + x86_match_cpu(dell_broken_mipi_disco_cpu_gens)) + ignore_port = true; + + dmi_tested = true; + } + + if (!ignore_port) + return false; + + /* Check if the device is either "IPU" or "LNK" (sensor). */ + orig_path = acpi_handle_path(handle); + if (!orig_path) + return false; + path = strnext(orig_path, "IPU"); + if (!path) + path = strnext(orig_path, "LNK"); + if (!path) + goto out_free; + + if (!(isdigit(path[0]) && path[1] == '.')) + goto out_free; + + /* Check if the node has a "PRT" prefix. */ + path = strnext(path, "PRT"); + if (path && isdigit(path[0]) && !path[1]) { + acpi_handle_debug(handle, "ignoring data node\n"); + + kfree(orig_path); + return true; + } + +out_free: + kfree(orig_path); + return false; +} +#endif diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index d6b85f0f6082f..75e9aac43228a 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -59,9 +59,8 @@ struct target_cache { }; enum { - NODE_ACCESS_CLASS_0 = 0, - NODE_ACCESS_CLASS_1, - NODE_ACCESS_CLASS_GENPORT_SINK, + NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL = ACCESS_COORDINATE_MAX, + NODE_ACCESS_CLASS_GENPORT_SINK_CPU, NODE_ACCESS_CLASS_MAX, }; @@ -127,7 +126,8 @@ static struct memory_target *acpi_find_genport_target(u32 uid) /** * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port * @uid: ACPI unique id - * @coord: The access coordinates written back out for the generic port + * @coord: The access coordinates written back out for the generic port. + * Expect 2 levels array. * * Return: 0 on success. Errno on failure. * @@ -143,7 +143,10 @@ int acpi_get_genport_coordinates(u32 uid, if (!target) return -ENOENT; - *coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK]; + coord[ACCESS_COORDINATE_LOCAL] = + target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL]; + coord[ACCESS_COORDINATE_CPU] = + target->coord[NODE_ACCESS_CLASS_GENPORT_SINK_CPU]; return 0; } @@ -374,11 +377,11 @@ static __init void hmat_update_target(unsigned int tgt_pxm, unsigned int init_px if (target && target->processor_pxm == init_pxm) { hmat_update_target_access(target, type, value, - NODE_ACCESS_CLASS_0); + ACCESS_COORDINATE_LOCAL); /* If the node has a CPU, update access 1 */ if (node_state(pxm_to_node(init_pxm), N_CPU)) hmat_update_target_access(target, type, value, - NODE_ACCESS_CLASS_1); + ACCESS_COORDINATE_CPU); } } @@ -697,7 +700,8 @@ static void hmat_update_target_attrs(struct memory_target *target, int i; /* Don't update for generic port if there's no device handle */ - if (access == NODE_ACCESS_CLASS_GENPORT_SINK && + if ((access == NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL || + access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) && !(*(u16 *)target->gen_port_device_handle)) return; @@ -709,7 +713,8 @@ static void hmat_update_target_attrs(struct memory_target *target, */ if (target->processor_pxm != PXM_INVAL) { cpu_nid = pxm_to_node(target->processor_pxm); - if (access == 0 || node_state(cpu_nid, N_CPU)) { + if (access == ACCESS_COORDINATE_LOCAL || + node_state(cpu_nid, N_CPU)) { set_bit(target->processor_pxm, p_nodes); return; } @@ -737,7 +742,9 @@ static void hmat_update_target_attrs(struct memory_target *target, list_for_each_entry(initiator, &initiators, node) { u32 value; - if (access == 1 && !initiator->has_cpu) { + if ((access == ACCESS_COORDINATE_CPU || + access == NODE_ACCESS_CLASS_GENPORT_SINK_CPU) && + !initiator->has_cpu) { clear_bit(initiator->processor_pxm, p_nodes); continue; } @@ -770,20 +777,24 @@ static void __hmat_register_target_initiators(struct memory_target *target, } } -static void hmat_register_generic_target_initiators(struct memory_target *target) +static void hmat_update_generic_target(struct memory_target *target) { static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); - __hmat_register_target_initiators(target, p_nodes, - NODE_ACCESS_CLASS_GENPORT_SINK); + hmat_update_target_attrs(target, p_nodes, + NODE_ACCESS_CLASS_GENPORT_SINK_LOCAL); + hmat_update_target_attrs(target, p_nodes, + NODE_ACCESS_CLASS_GENPORT_SINK_CPU); } static void hmat_register_target_initiators(struct memory_target *target) { static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); - __hmat_register_target_initiators(target, p_nodes, 0); - __hmat_register_target_initiators(target, p_nodes, 1); + __hmat_register_target_initiators(target, p_nodes, + ACCESS_COORDINATE_LOCAL); + __hmat_register_target_initiators(target, p_nodes, + ACCESS_COORDINATE_CPU); } static void hmat_register_target_cache(struct memory_target *target) @@ -835,7 +846,7 @@ static void hmat_register_target(struct memory_target *target) */ mutex_lock(&target_lock); if (*(u16 *)target->gen_port_device_handle) { - hmat_register_generic_target_initiators(target); + hmat_update_generic_target(target); target->registered = true; } mutex_unlock(&target_lock); @@ -854,8 +865,8 @@ static void hmat_register_target(struct memory_target *target) if (!target->registered) { hmat_register_target_initiators(target); hmat_register_target_cache(target); - hmat_register_target_perf(target, NODE_ACCESS_CLASS_0); - hmat_register_target_perf(target, NODE_ACCESS_CLASS_1); + hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL); + hmat_register_target_perf(target, ACCESS_COORDINATE_CPU); target->registered = true; } mutex_unlock(&target_lock); @@ -927,7 +938,7 @@ static int hmat_calculate_adistance(struct notifier_block *self, return NOTIFY_OK; mutex_lock(&target_lock); - hmat_update_target_attrs(target, p_nodes, 1); + hmat_update_target_attrs(target, p_nodes, ACCESS_COORDINATE_CPU); mutex_unlock(&target_lock); perf = &target->coord[1]; diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 0214518fc582f..3ca22db3ed5db 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -206,6 +206,11 @@ int __init srat_disabled(void) return acpi_numa < 0; } +__weak int __init numa_fill_memblks(u64 start, u64 end) +{ + return NUMA_NO_MEMBLK; +} + #if defined(CONFIG_X86) || defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) /* * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c index df9328c850bd3..956f7fe403a35 100644 --- a/drivers/acpi/osi.c +++ b/drivers/acpi/osi.c @@ -443,6 +443,77 @@ static const struct dmi_system_id acpi_osi_dmi_table[] __initconst = { }, }, + /* + * The following Lenovo models have a broken workaround in the + * acpi_video backlight implementation to meet the Windows 8 + * requirement of 101 backlight levels. Reverting to pre-Win8 + * behavior fixes the problem. + */ + { + .callback = dmi_disable_osi_win8, + .ident = "Lenovo ThinkPad L430", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L430"), + }, + }, + { + .callback = dmi_disable_osi_win8, + .ident = "Lenovo ThinkPad T430", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430"), + }, + }, + { + .callback = dmi_disable_osi_win8, + .ident = "Lenovo ThinkPad T430s", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430s"), + }, + }, + { + .callback = dmi_disable_osi_win8, + .ident = "Lenovo ThinkPad T530", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T530"), + }, + }, + { + .callback = dmi_disable_osi_win8, + .ident = "Lenovo ThinkPad W530", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W530"), + }, + }, + { + .callback = dmi_disable_osi_win8, + .ident = "Lenovo ThinkPad X1 Carbon", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X1 Carbon"), + }, + }, + { + .callback = dmi_disable_osi_win8, + .ident = "Lenovo ThinkPad X230", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X230"), + }, + }, + { + .callback = dmi_disable_osi_win8, + .ident = "Lenovo ThinkPad Edge E330", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Edge E330"), + }, + }, + /* * BIOS invocation of _OSI(Linux) is almost always a BIOS bug. * Linux ignores it, except for the machines enumerated below. diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 55437f5e0c3ae..bd6a7857ce058 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -1430,6 +1430,8 @@ int acpi_processor_power_exit(struct acpi_processor *pr) acpi_processor_registered--; if (acpi_processor_registered == 0) cpuidle_unregister_driver(&acpi_idle_driver); + + kfree(dev); } pr->flags.power_setup_done = 0; diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index a6ead5204046b..2b73580c9f36d 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -80,6 +80,9 @@ static bool acpi_nondev_subnode_extract(union acpi_object *desc, struct acpi_data_node *dn; bool result; + if (acpi_graph_ignore_port(handle)) + return false; + dn = kzalloc(sizeof(*dn), GFP_KERNEL); if (!dn) return false; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index dacad1d846c0d..4acbae6dc8eec 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -489,6 +489,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { DMI_MATCH(DMI_BOARD_NAME, "B2502CBA"), }, }, + { + /* Asus ExpertBook B2502FBA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B2502FBA"), + }, + }, { /* Asus Vivobook E1504GA */ .matches = { @@ -503,6 +510,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { DMI_MATCH(DMI_BOARD_NAME, "E1504GAB"), }, }, + { + /* Asus Vivobook Pro N6506MV */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "N6506MV"), + }, + }, { /* LG Electronics 17U70P */ .matches = { @@ -510,6 +524,18 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { DMI_MATCH(DMI_BOARD_NAME, "17U70P"), }, }, + { + /* TongFang GXxHRXx/TUXEDO InfinityBook Pro Gen9 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GXxHRXx"), + }, + }, + { + /* TongFang GMxHGxx/TUXEDO Stellaris Slim Gen1 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxHGxx"), + }, + }, { } }; @@ -519,6 +545,12 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { * to have a working keyboard. */ static const struct dmi_system_id irq1_edge_low_force_override[] = { + { + /* XMG APEX 17 (M23) */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxBGxx"), + }, + }, { /* TongFang GMxRGxx/XMG CORE 15 (M22)/TUXEDO Stellaris 15 Gen4 AMD */ .matches = { @@ -588,6 +620,27 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = { DMI_MATCH(DMI_BOARD_NAME, "GM5RGEE0016COM"), }, }, + { + /* Lunnen Ground 15 / AMD Ryzen 5 5500U */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Lunnen"), + DMI_MATCH(DMI_BOARD_NAME, "LLL5DAW"), + }, + }, + { + /* Lunnen Ground 16 / AMD Ryzen 7 5800U */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Lunnen"), + DMI_MATCH(DMI_BOARD_NAME, "LL6FA"), + }, + }, + { + /* MAIBENBEN X577 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MAIBENBEN"), + DMI_MATCH(DMI_BOARD_NAME, "X577"), + }, + }, { } }; diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index e6ed1ba91e5c9..1668171bb4eb9 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -314,18 +314,14 @@ static int acpi_scan_device_check(struct acpi_device *adev) * again). */ if (adev->handler) { - dev_warn(&adev->dev, "Already enumerated\n"); - return -EALREADY; + dev_dbg(&adev->dev, "Already enumerated\n"); + return 0; } error = acpi_bus_scan(adev->handle); if (error) { dev_warn(&adev->dev, "Namespace scan failure\n"); return error; } - if (!adev->handler) { - dev_warn(&adev->dev, "Enumeration failure\n"); - error = -ENODEV; - } } else { error = acpi_scan_device_not_enumerated(adev); } @@ -798,6 +794,7 @@ static const char * const acpi_honor_dep_ids[] = { "INTC1059", /* IVSC (TGL) driver must be loaded to allow i2c access to camera sensors */ "INTC1095", /* IVSC (ADL) driver must be loaded to allow i2c access to camera sensors */ "INTC100A", /* IVSC (RPL) driver must be loaded to allow i2c access to camera sensors */ + "INTC10CF", /* IVSC (MTL) driver must be loaded to allow i2c access to camera sensors */ NULL }; @@ -1806,7 +1803,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev) if (dep->honor_dep) adev->flags.honor_deps = 1; - adev->dep_unmet++; + if (!dep->met) + adev->dep_unmet++; } } } diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 808484d112097..728acfeb774d8 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -385,18 +385,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"), }, }, - /* - * ASUS B1400CEAE hangs on resume from suspend (see - * https://bugzilla.kernel.org/show_bug.cgi?id=215742). - */ - { - .callback = init_default_s3, - .ident = "ASUS B1400CEAE", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK B1400CEAE"), - }, - }, {}, }; diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 4748e80612534..aadeb94e7ac0d 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -167,11 +167,17 @@ static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz) static int acpi_thermal_temp(struct acpi_thermal *tz, int temp_deci_k) { + int temp; + if (temp_deci_k == THERMAL_TEMP_INVALID) return THERMAL_TEMP_INVALID; - return deci_kelvin_to_millicelsius_with_offset(temp_deci_k, + temp = deci_kelvin_to_millicelsius_with_offset(temp_deci_k, tz->kelvin_offset); + if (temp <= 0) + return THERMAL_TEMP_INVALID; + + return temp; } static bool acpi_thermal_trip_valid(struct acpi_thermal_trip *acpi_trip) diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index abac5cc254774..202234ba54bd9 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -559,7 +559,7 @@ EXPORT_SYMBOL(acpi_evaluate_ost); * * Caller must free the returned buffer */ -static char *acpi_handle_path(acpi_handle handle) +char *acpi_handle_path(acpi_handle handle) { struct acpi_buffer buffer = { .length = ACPI_ALLOCATE_BUFFER, diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 9fdcc620c6524..046b8226a982d 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -497,6 +497,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82BK"), }, }, + { + .callback = video_detect_force_native, + /* Lenovo Slim 7 16ARH7 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82UX"), + }, + }, { .callback = video_detect_force_native, /* Lenovo ThinkPad X131e (3371 AMD version) */ @@ -894,6 +902,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto static DEFINE_MUTEX(init_mutex); static bool nvidia_wmi_ec_present; static bool apple_gmux_present; + static bool dell_uart_backlight_present; static bool native_available; static bool init_done; static long video_caps; @@ -908,6 +917,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto &video_caps, NULL); nvidia_wmi_ec_present = nvidia_wmi_ec_supported(); apple_gmux_present = apple_gmux_detect(NULL, NULL); + dell_uart_backlight_present = acpi_dev_found("DELL0501"); init_done = true; } if (native) @@ -938,6 +948,9 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto if (apple_gmux_present) return acpi_backlight_apple_gmux; + if (dell_uart_backlight_present) + return acpi_backlight_vendor; + /* Use ACPI video if available, except when native should be preferred. */ if ((video_caps & ACPI_VIDEO_BACKLIGHT) && !(native_available && prefer_native_over_acpi_video())) diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 7d64e655f1b86..dd0b40b9bbe8b 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -488,7 +488,19 @@ static int lps0_device_attach(struct acpi_device *adev, rev_id = 1; lps0_dsm_func_mask = validate_dsm(adev->handle, ACPI_LPS0_DSM_UUID, rev_id, &lps0_dsm_guid); - lps0_dsm_func_mask_microsoft = -EINVAL; + if (lps0_dsm_func_mask > 0 && lps0_dsm_func_mask_microsoft > 0) { + unsigned int func_mask; + + /* + * Log a message if the _DSM function sets for two + * different UUIDs overlap. + */ + func_mask = lps0_dsm_func_mask & lps0_dsm_func_mask_microsoft; + if (func_mask) + acpi_handle_info(adev->handle, + "Duplicate LPS0 _DSM functions (mask: 0x%x)\n", + func_mask); + } } if (lps0_dsm_func_mask < 0 && lps0_dsm_func_mask_microsoft < 0) @@ -549,19 +561,22 @@ int acpi_s2idle_prepare_late(void) lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); /* LPS0 entry */ - if (lps0_dsm_func_mask > 0) - acpi_sleep_run_lps0_dsm(acpi_s2idle_vendor_amd() ? - ACPI_LPS0_ENTRY_AMD : - ACPI_LPS0_ENTRY, + if (lps0_dsm_func_mask > 0 && acpi_s2idle_vendor_amd()) + acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY_AMD, lps0_dsm_func_mask, lps0_dsm_guid); + if (lps0_dsm_func_mask_microsoft > 0) { - /* modern standby entry */ + /* Modern Standby entry */ acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_ENTRY, lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY, lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); } + if (lps0_dsm_func_mask > 0 && !acpi_s2idle_vendor_amd()) + acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY, + lps0_dsm_func_mask, lps0_dsm_guid); + list_for_each_entry(handler, &lps0_s2idle_devops_head, list_node) { if (handler->prepare) handler->prepare(); @@ -600,14 +615,14 @@ void acpi_s2idle_restore_early(void) ACPI_LPS0_EXIT_AMD : ACPI_LPS0_EXIT, lps0_dsm_func_mask, lps0_dsm_guid); - if (lps0_dsm_func_mask_microsoft > 0) + + if (lps0_dsm_func_mask_microsoft > 0) { acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT, lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); - - /* Modern standby exit */ - if (lps0_dsm_func_mask_microsoft > 0) + /* Modern Standby exit */ acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_EXIT, lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); + } /* Screen on */ if (lps0_dsm_func_mask_microsoft > 0) diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index bc65ebfcdf767..448e0d14fd7bd 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -197,16 +197,16 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s } /* - * AMD systems from Renoir and Lucienne *require* that the NVME controller + * AMD systems from Renoir onwards *require* that the NVME controller * is put into D3 over a Modern Standby / suspend-to-idle cycle. * * This is "typically" accomplished using the `StorageD3Enable` * property in the _DSD that is checked via the `acpi_storage_d3` function - * but this property was introduced after many of these systems launched - * and most OEM systems don't have it in their BIOS. + * but some OEM systems still don't have it in their BIOS. * * The Microsoft documentation for StorageD3Enable mentioned that Windows has - * a hardcoded allowlist for D3 support, which was used for these platforms. + * a hardcoded allowlist for D3 support as well as a registry key to override + * the BIOS, which has been used for these cases. * * This allows quirking on Linux in a similar fashion. * @@ -219,19 +219,15 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s * https://bugzilla.kernel.org/show_bug.cgi?id=216773 * https://bugzilla.kernel.org/show_bug.cgi?id=217003 * 2) On at least one HP system StorageD3Enable is missing on the second NVME - disk in the system. + * disk in the system. + * 3) On at least one HP Rembrandt system StorageD3Enable is missing on the only + * NVME device. */ -static const struct x86_cpu_id storage_d3_cpu_ids[] = { - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 24, NULL), /* Picasso */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL), /* Renoir */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL), /* Lucienne */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 25, 80, NULL), /* Cezanne */ - {} -}; - bool force_storage_d3(void) { - return x86_match_cpu(storage_d3_cpu_ids); + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return false; + return acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0; } /* @@ -260,9 +256,10 @@ bool force_storage_d3(void) #define ACPI_QUIRK_SKIP_I2C_CLIENTS BIT(0) #define ACPI_QUIRK_UART1_SKIP BIT(1) #define ACPI_QUIRK_UART1_TTY_UART2_SKIP BIT(2) -#define ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY BIT(3) -#define ACPI_QUIRK_USE_ACPI_AC_AND_BATTERY BIT(4) -#define ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS BIT(5) +#define ACPI_QUIRK_PNP_UART1_SKIP BIT(3) +#define ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY BIT(4) +#define ACPI_QUIRK_USE_ACPI_AC_AND_BATTERY BIT(5) +#define ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS BIT(6) static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { /* @@ -342,6 +339,7 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21"), }, .driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS | + ACPI_QUIRK_PNP_UART1_SKIP | ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), }, { @@ -428,7 +426,7 @@ bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev) } EXPORT_SYMBOL_GPL(acpi_quirk_skip_i2c_client_enumeration); -int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) +static int acpi_dmi_skip_serdev_enumeration(struct device *controller_parent, bool *skip) { struct acpi_device *adev = ACPI_COMPANION(controller_parent); const struct dmi_system_id *dmi_id; @@ -436,20 +434,22 @@ int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *s u64 uid; int ret; - *skip = false; - ret = acpi_dev_uid_to_integer(adev, &uid); if (ret) return 0; - /* to not match on PNP enumerated debug UARTs */ - if (!dev_is_platform(controller_parent)) - return 0; - dmi_id = dmi_first_match(acpi_quirk_skip_dmi_ids); if (dmi_id) quirks = (unsigned long)dmi_id->driver_data; + if (!dev_is_platform(controller_parent)) { + /* PNP enumerated UARTs */ + if ((quirks & ACPI_QUIRK_PNP_UART1_SKIP) && uid == 1) + *skip = true; + + return 0; + } + if ((quirks & ACPI_QUIRK_UART1_SKIP) && uid == 1) *skip = true; @@ -463,7 +463,6 @@ int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *s return 0; } -EXPORT_SYMBOL_GPL(acpi_quirk_skip_serdev_enumeration); bool acpi_quirk_skip_gpio_event_handlers(void) { @@ -478,8 +477,41 @@ bool acpi_quirk_skip_gpio_event_handlers(void) return (quirks & ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS); } EXPORT_SYMBOL_GPL(acpi_quirk_skip_gpio_event_handlers); +#else +static int acpi_dmi_skip_serdev_enumeration(struct device *controller_parent, bool *skip) +{ + return 0; +} #endif +int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) +{ + struct acpi_device *adev = ACPI_COMPANION(controller_parent); + + *skip = false; + + /* + * The DELL0501 ACPI HID represents an UART (CID is set to PNP0501) with + * a backlight-controller attached. There is no separate ACPI device with + * an UartSerialBusV2() resource to model the backlight-controller. + * Set skip to true so that the tty core creates a serdev ctrl device. + * The backlight driver will manually create the serdev client device. + */ + if (acpi_dev_hid_match(adev, "DELL0501")) { + *skip = true; + /* + * Create a platform dev for dell-uart-backlight to bind to. + * This is a static device, so no need to store the result. + */ + platform_device_register_simple("dell-uart-backlight", PLATFORM_DEVID_NONE, + NULL, 0); + return 0; + } + + return acpi_dmi_skip_serdev_enumeration(controller_parent, skip); +} +EXPORT_SYMBOL_GPL(acpi_quirk_skip_serdev_enumeration); + /* Lists of PMIC ACPI HIDs with an (often better) native charger driver */ static const struct { const char *hid; diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig index 07aa8ae0a058c..fe5287e3525be 100644 --- a/drivers/android/Kconfig +++ b/drivers/android/Kconfig @@ -2,7 +2,7 @@ menu "Android" config ANDROID_BINDER_IPC - bool "Android Binder IPC Driver" + tristate "Android Binder IPC Driver" depends on MMU default n help @@ -14,8 +14,8 @@ config ANDROID_BINDER_IPC between said processes. config ANDROID_BINDERFS - bool "Android Binderfs filesystem" - depends on ANDROID_BINDER_IPC + tristate "Android Binderfs filesystem" + depends on (ANDROID_BINDER_IPC=y) || (ANDROID_BINDER_IPC=m && m) default n help Binderfs is a pseudo-filesystem for the Android Binder IPC driver diff --git a/drivers/android/Makefile b/drivers/android/Makefile index c9d3d0c99c257..b9d5ce8deca2b 100644 --- a/drivers/android/Makefile +++ b/drivers/android/Makefile @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only ccflags-y += -I$(src) # needed for trace events -obj-$(CONFIG_ANDROID_BINDERFS) += binderfs.o -obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o binder_alloc.o -obj-$(CONFIG_ANDROID_BINDER_IPC_SELFTEST) += binder_alloc_selftest.o +binder_linux-y := binder.o binder_alloc.o +obj-$(CONFIG_ANDROID_BINDER_IPC) += binder_linux.o +binder_linux-$(CONFIG_ANDROID_BINDERFS) += binderfs.o +binder_linux-$(CONFIG_ANDROID_BINDER_IPC_SELFTEST) += binder_alloc_selftest.o + +# binder-$(CONFIG_ANDROID_BINDER_IPC) := binder.o binder_alloc.o +# binder-$(CONFIG_ANDROID_BINDERFS) += binderfs.o diff --git a/drivers/android/binder.c b/drivers/android/binder.c index eca24f41556df..610b18c0ed6f6 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1708,8 +1708,10 @@ static size_t binder_get_object(struct binder_proc *proc, size_t object_size = 0; read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset); - if (offset > buffer->data_size || read_size < sizeof(*hdr)) + if (offset > buffer->data_size || read_size < sizeof(*hdr) || + !IS_ALIGNED(offset, sizeof(u32))) return 0; + if (u) { if (copy_from_user(object, u + offset, read_size)) return 0; @@ -2930,8 +2932,7 @@ static void binder_transaction(struct binder_proc *proc, struct binder_context *context = proc->context; int t_debug_id = atomic_inc_return(&binder_last_id); ktime_t t_start_time = ktime_get(); - char *secctx = NULL; - u32 secctx_sz = 0; + struct lsmcontext lsmctx; struct list_head sgc_head; struct list_head pf_head; const void __user *user_buffer = (const void __user *) @@ -3210,8 +3211,8 @@ static void binder_transaction(struct binder_proc *proc, size_t added_size; security_cred_getsecid(proc->cred, &secid); - ret = security_secid_to_secctx(secid, &secctx, &secctx_sz); - if (ret) { + ret = security_secid_to_secctx(secid, &lsmctx); + if (ret < 0) { binder_txn_error("%d:%d failed to get security context\n", thread->pid, proc->pid); return_error = BR_FAILED_REPLY; @@ -3219,7 +3220,7 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_get_secctx_failed; } - added_size = ALIGN(secctx_sz, sizeof(u64)); + added_size = ALIGN(lsmctx.len, sizeof(u64)); extra_buffers_size += added_size; if (extra_buffers_size < added_size) { binder_txn_error("%d:%d integer overflow of extra_buffers_size\n", @@ -3253,23 +3254,23 @@ static void binder_transaction(struct binder_proc *proc, t->buffer = NULL; goto err_binder_alloc_buf_failed; } - if (secctx) { + if (lsmctx.context) { int err; size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) + ALIGN(tr->offsets_size, sizeof(void *)) + ALIGN(extra_buffers_size, sizeof(void *)) - - ALIGN(secctx_sz, sizeof(u64)); + ALIGN(lsmctx.len, sizeof(u64)); t->security_ctx = t->buffer->user_data + buf_offset; err = binder_alloc_copy_to_buffer(&target_proc->alloc, t->buffer, buf_offset, - secctx, secctx_sz); + lsmctx.context, lsmctx.len); if (err) { t->security_ctx = 0; WARN_ON(1); } - security_release_secctx(secctx, secctx_sz); - secctx = NULL; + security_release_secctx(&lsmctx); + lsmctx.context = NULL; } t->buffer->debug_id = t->debug_id; t->buffer->transaction = t; @@ -3313,7 +3314,7 @@ static void binder_transaction(struct binder_proc *proc, off_end_offset = off_start_offset + tr->offsets_size; sg_buf_offset = ALIGN(off_end_offset, sizeof(void *)); sg_buf_end_offset = sg_buf_offset + extra_buffers_size - - ALIGN(secctx_sz, sizeof(u64)); + ALIGN(lsmctx.len, sizeof(u64)); off_min = 0; for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { @@ -3691,8 +3692,8 @@ static void binder_transaction(struct binder_proc *proc, binder_alloc_free_buf(&target_proc->alloc, t->buffer); err_binder_alloc_buf_failed: err_bad_extra_size: - if (secctx) - security_release_secctx(secctx, secctx_sz); + if (lsmctx.context) + security_release_secctx(&lsmctx); err_get_secctx_failed: kfree(tcomplete); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); @@ -5365,7 +5366,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) goto err; break; case BINDER_SET_MAX_THREADS: { - int max_threads; + u32 max_threads; if (copy_from_user(&max_threads, ubuf, sizeof(max_threads))) { @@ -6631,9 +6632,20 @@ static int __init binder_init(void) return ret; } -device_initcall(binder_init); +module_init(binder_init); +/* + * binder will have no exit function since binderfs instances can be mounted + * multiple times and also in user namespaces finding and destroying them all + * is not feasible without introducing insane locking. Just ignoring existing + * instances on module unload also wouldn't work since we would loose track of + * what major numer was dynamically allocated and also what minor numbers are + * already given out. So this would get us into all kinds of issues with device + * number reuse. So simply don't allow unloading unless we are forced to do so. + */ + +MODULE_AUTHOR("Google, Inc."); +MODULE_DESCRIPTION("Driver for Android binder device"); +MODULE_LICENSE("GPL v2"); #define CREATE_TRACE_POINTS #include "binder_trace.h" - -MODULE_LICENSE("GPL v2"); diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index e0e4dc38b6920..4975e01be80f1 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -38,8 +38,7 @@ enum { }; static uint32_t binder_alloc_debug_mask = BINDER_DEBUG_USER_ERROR; -module_param_named(debug_mask, binder_alloc_debug_mask, - uint, 0644); +module_param_named(alloc_debug_mask, binder_alloc_debug_mask, uint, 0644); #define binder_alloc_debug(mask, x...) \ do { \ diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 70387234477e0..a0087ab1f348e 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -6,6 +6,7 @@ #ifndef _LINUX_BINDER_ALLOC_H #define _LINUX_BINDER_ALLOC_H +#include #include #include #include @@ -111,7 +112,7 @@ struct binder_alloc { bool oneway_spam_detected; }; -#ifdef CONFIG_ANDROID_BINDER_IPC_SELFTEST +#if IS_ENABLED(CONFIG_ANDROID_BINDER_IPC_SELFTEST) void binder_selftest_alloc(struct binder_alloc *alloc); #else static inline void binder_selftest_alloc(struct binder_alloc *alloc) {} diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index 7270d4d222070..6a1b00271b09d 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -5,6 +5,7 @@ #include #include +#include #include #include #include @@ -77,7 +78,7 @@ extern const struct file_operations binder_fops; extern char *binder_devices_param; -#ifdef CONFIG_ANDROID_BINDERFS +#if IS_ENABLED(CONFIG_ANDROID_BINDERFS) extern bool is_binderfs_device(const struct inode *inode); extern struct dentry *binderfs_create_file(struct dentry *dir, const char *name, const struct file_operations *fops, @@ -98,7 +99,7 @@ static inline struct dentry *binderfs_create_file(struct dentry *dir, static inline void binderfs_remove_file(struct dentry *dentry) {} #endif -#ifdef CONFIG_ANDROID_BINDERFS +#if IS_ENABLED(CONFIG_ANDROID_BINDERFS) extern int __init init_binderfs(void); #else static inline int __init init_binderfs(void) @@ -421,7 +422,7 @@ struct binder_proc { struct list_head todo; struct binder_stats stats; struct list_head delivered_death; - int max_threads; + u32 max_threads; int requested_threads; int requested_threads_started; int tmp_ref; diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 3001d754ac369..822ddbdc543c2 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -120,7 +120,7 @@ static int binderfs_binder_device_create(struct inode *ref_inode, struct super_block *sb = ref_inode->i_sb; struct binderfs_info *info = sb->s_fs_info; #if defined(CONFIG_IPC_NS) - bool use_reserve = (info->ipc_ns == &init_ipc_ns); + bool use_reserve = (info->ipc_ns == show_init_ipc_ns()); #else bool use_reserve = true; #endif @@ -397,7 +397,7 @@ static int binderfs_binder_ctl_create(struct super_block *sb) struct dentry *root = sb->s_root; struct binderfs_info *info = sb->s_fs_info; #if defined(CONFIG_IPC_NS) - bool use_reserve = (info->ipc_ns == &init_ipc_ns); + bool use_reserve = (info->ipc_ns == show_init_ipc_ns()); #else bool use_reserve = true; #endif @@ -683,7 +683,7 @@ static int binderfs_fill_super(struct super_block *sb, struct fs_context *fc) return -ENOMEM; info = sb->s_fs_info; - info->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns); + info->ipc_ns = get_ipc_ns_exported(current->nsproxy->ipc_ns); info->root_gid = make_kgid(sb->s_user_ns, 0); if (!gid_valid(info->root_gid)) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 682ff550ccfb9..d4d80481b8ecf 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -431,7 +431,6 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x02d7), board_ahci_low_power }, /* Comet Lake PCH RAID */ /* Elkhart Lake IDs 0x4b60 & 0x4b62 https://sata-io.org/product/8803 not tested yet */ { PCI_VDEVICE(INTEL, 0x4b63), board_ahci_low_power }, /* Elkhart Lake AHCI */ - { PCI_VDEVICE(INTEL, 0x7ae2), board_ahci_low_power }, /* Alder Lake-P AHCI */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, @@ -671,19 +670,6 @@ MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets"); static void ahci_pci_save_initial_config(struct pci_dev *pdev, struct ahci_host_priv *hpriv) { - if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA) { - switch (pdev->device) { - case 0x1166: - dev_info(&pdev->dev, "ASM1166 has only six ports\n"); - hpriv->saved_port_map = 0x3f; - break; - case 0x1064: - dev_info(&pdev->dev, "ASM1064 has only four ports\n"); - hpriv->saved_port_map = 0xf; - break; - } - } - if (pdev->vendor == PCI_VENDOR_ID_JMICRON && pdev->device == 0x2361) { dev_info(&pdev->dev, "JMB361 has only one port\n"); hpriv->saved_port_map = 1; @@ -1660,6 +1646,14 @@ static void ahci_update_initial_lpm_policy(struct ata_port *ap, if (!(hpriv->flags & AHCI_HFLAG_USE_LPM_POLICY)) return; + /* If no LPM states are supported by the HBA, do not bother with LPM */ + if ((ap->host->flags & ATA_HOST_NO_PART) && + (ap->host->flags & ATA_HOST_NO_SSC) && + (ap->host->flags & ATA_HOST_NO_DEVSLP)) { + ata_port_dbg(ap, "no LPM states supported, not enabling LPM\n"); + return; + } + /* user modified policy via module param */ if (mobile_lpm_policy != -1) { policy = mobile_lpm_policy; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index be3412cdb22e7..28caed151e05f 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2539,7 +2539,7 @@ static void ata_dev_config_cdl(struct ata_device *dev) bool cdl_enabled; u64 val; - if (ata_id_major_version(dev->id) < 12) + if (ata_id_major_version(dev->id) < 11) goto not_supported; if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE) || @@ -4180,8 +4180,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "PIONEER BD-RW BDR-207M", NULL, ATA_HORKAGE_NOLPM }, { "PIONEER BD-RW BDR-205", NULL, ATA_HORKAGE_NOLPM }, - /* Crucial BX100 SSD 500GB has broken LPM support */ + /* Crucial devices with broken LPM support */ { "CT500BX100SSD1", NULL, ATA_HORKAGE_NOLPM }, + { "CT240BX500SSD1", NULL, ATA_HORKAGE_NOLPM }, /* 512GB MX100 with MU01 firmware has both queued TRIM and LPM issues */ { "Crucial_CT512MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | @@ -4199,6 +4200,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM }, + /* Apacer models with LPM issues */ + { "Apacer AS340*", NULL, ATA_HORKAGE_NOLPM }, + + /* AMD Radeon devices with broken LPM support */ + { "R3SL240G", NULL, ATA_HORKAGE_NOLPM }, + /* These specific Samsung models/firmware-revs do not handle LPM well */ { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM }, { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM }, diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index b0d6e69c4a5b2..214b935c2ced7 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -712,8 +712,10 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) ehc->saved_ncq_enabled |= 1 << devno; /* If we are resuming, wake up the device */ - if (ap->pflags & ATA_PFLAG_RESUMING) + if (ap->pflags & ATA_PFLAG_RESUMING) { + dev->flags |= ATA_DFLAG_RESUMING; ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE; + } } } @@ -3169,6 +3171,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, return 0; err: + dev->flags &= ~ATA_DFLAG_RESUMING; *r_failed_dev = dev; return rc; } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 0a0f483124c3a..9c3daa7d195c4 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1828,11 +1828,11 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) 2 }; - /* set scsi removable (RMB) bit per ata bit, or if the - * AHCI port says it's external (Hotplug-capable, eSATA). + /* + * Set the SCSI Removable Media Bit (RMB) if the ATA removable media + * device bit (obsolete since ATA-8 ACS) is set. */ - if (ata_id_removable(args->id) || - (args->dev->link->ap->pflags & ATA_PFLAG_EXTERNAL)) + if (ata_id_removable(args->id)) hdr[1] |= (1 << 7); if (args->dev->class == ATA_DEV_ZAC) { @@ -4730,6 +4730,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) struct ata_link *link; struct ata_device *dev; unsigned long flags; + bool do_resume; int ret = 0; mutex_lock(&ap->scsi_scan_mutex); @@ -4744,25 +4745,34 @@ void ata_scsi_dev_rescan(struct work_struct *work) * bail out. */ if (ap->pflags & ATA_PFLAG_SUSPENDED) - goto unlock; + goto unlock_ap; if (!sdev) continue; if (scsi_device_get(sdev)) continue; + do_resume = dev->flags & ATA_DFLAG_RESUMING; + spin_unlock_irqrestore(ap->lock, flags); + if (do_resume) { + ret = scsi_resume_device(sdev); + if (ret == -EWOULDBLOCK) + goto unlock_scan; + dev->flags &= ~ATA_DFLAG_RESUMING; + } ret = scsi_rescan_device(sdev); scsi_device_put(sdev); spin_lock_irqsave(ap->lock, flags); if (ret) - goto unlock; + goto unlock_ap; } } -unlock: +unlock_ap: spin_unlock_irqrestore(ap->lock, flags); +unlock_scan: mutex_unlock(&ap->scsi_scan_mutex); /* Reschedule with a delay if scsi_rescan_device() returned an error */ diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index 448a511cbc179..e7ac142c2423d 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -173,8 +173,6 @@ static int legacy_port[NR_HOST] = { 0x1f0, 0x170, 0x1e8, 0x168, 0x1e0, 0x160 }; static struct legacy_probe probe_list[NR_HOST]; static struct legacy_data legacy_data[NR_HOST]; static struct ata_host *legacy_host[NR_HOST]; -static int nr_legacy_host; - /** * legacy_probe_add - Add interface to probe list @@ -1276,9 +1274,11 @@ static __exit void legacy_exit(void) { int i; - for (i = 0; i < nr_legacy_host; i++) { + for (i = 0; i < NR_HOST; i++) { struct legacy_data *ld = &legacy_data[i]; - ata_host_detach(legacy_host[i]); + + if (legacy_host[i]) + ata_host_detach(legacy_host[i]); platform_device_unregister(ld->platform_dev); } } diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c index 400b22ee99c33..4c270999ba3cc 100644 --- a/drivers/ata/sata_gemini.c +++ b/drivers/ata/sata_gemini.c @@ -200,7 +200,10 @@ int gemini_sata_start_bridge(struct sata_gemini *sg, unsigned int bridge) pclk = sg->sata0_pclk; else pclk = sg->sata1_pclk; - clk_enable(pclk); + ret = clk_enable(pclk); + if (ret) + return ret; + msleep(10); /* Do not keep clocking a bridge that is not online */ diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index e82786c63fbd7..9bec0aee92e04 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -787,37 +787,6 @@ static const struct ata_port_info mv_port_info[] = { }, }; -static const struct pci_device_id mv_pci_tbl[] = { - { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, - { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, - /* RocketRAID 1720/174x have different identifiers */ - { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, - - { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, - { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, - { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, - - { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, - - /* Adaptec 1430SA */ - { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, - - /* Marvell 7042 support */ - { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, - - /* Highpoint RocketRAID PCIe series */ - { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, - { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, - - { } /* terminate list */ -}; - static const struct mv_hw_ops mv5xxx_ops = { .phy_errata = mv5_phy_errata, .enable_leds = mv5_enable_leds, @@ -4303,6 +4272,36 @@ static int mv_pci_init_one(struct pci_dev *pdev, static int mv_pci_device_resume(struct pci_dev *pdev); #endif +static const struct pci_device_id mv_pci_tbl[] = { + { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, + { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, + /* RocketRAID 1720/174x have different identifiers */ + { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, + + { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, + { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, + { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, + + { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, + + /* Adaptec 1430SA */ + { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, + + /* Marvell 7042 support */ + { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, + + /* Highpoint RocketRAID PCIe series */ + { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, + { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, + + { } /* terminate list */ +}; static struct pci_driver mv_pci_driver = { .name = DRV_NAME, @@ -4315,6 +4314,7 @@ static struct pci_driver mv_pci_driver = { #endif }; +MODULE_DEVICE_TABLE(pci, mv_pci_tbl); /** * mv_print_info - Dump key info to kernel log for perusal. @@ -4487,7 +4487,6 @@ static void __exit mv_exit(void) MODULE_AUTHOR("Brett Russ"); MODULE_DESCRIPTION("SCSI low-level driver for Marvell SATA controllers"); MODULE_LICENSE("GPL v2"); -MODULE_DEVICE_TABLE(pci, mv_pci_tbl); MODULE_VERSION(DRV_VERSION); MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index b51d7a9d0d90c..a482741eb181f 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -957,8 +957,7 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, offset -= (idx * window_size); idx++; - dist = ((long) (window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_fromio(psource, dimm_mmio + offset / 4, dist); psource += dist; @@ -1005,8 +1004,7 @@ static void pdc20621_put_to_dimm(struct ata_host *host, void *psource, readl(mmio + PDC_DIMM_WINDOW_CTLR); offset -= (idx * window_size); idx++; - dist = ((long)(s32)(window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_toio(dimm_mmio + offset / 4, psource, dist); writel(0x01, mmio + PDC_GENERAL_CTLR); readl(mmio + PDC_GENERAL_CTLR); diff --git a/drivers/base/base.h b/drivers/base/base.h index eb4c0ace92420..a8e3d8165232f 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -192,11 +192,14 @@ extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) -void module_add_driver(struct module *mod, struct device_driver *drv); +int module_add_driver(struct module *mod, struct device_driver *drv); void module_remove_driver(struct device_driver *drv); #else -static inline void module_add_driver(struct module *mod, - struct device_driver *drv) { } +static inline int module_add_driver(struct module *mod, + struct device_driver *drv) +{ + return 0; +} static inline void module_remove_driver(struct device_driver *drv) { } #endif diff --git a/drivers/base/bus.c b/drivers/base/bus.c index daee55c9b2d9e..ffea0728b8b2f 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -674,7 +674,12 @@ int bus_add_driver(struct device_driver *drv) if (error) goto out_del_list; } - module_add_driver(drv->owner, drv); + error = module_add_driver(drv->owner, drv); + if (error) { + printk(KERN_ERR "%s: failed to create module links for %s\n", + __func__, drv->name); + goto out_detach; + } error = driver_create_file(drv, &driver_attr_uevent); if (error) { @@ -699,6 +704,8 @@ int bus_add_driver(struct device_driver *drv) return 0; +out_detach: + driver_detach(drv); out_del_list: klist_del(&priv->knode_bus); out_unregister: diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index f1e79263fe61e..735ccead190ec 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -61,6 +61,9 @@ bool last_level_cache_is_valid(unsigned int cpu) if (!cache_leaves(cpu)) return false; + if (!per_cpu_cacheinfo(cpu)) + return false; + llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1); return (llc->attributes & CACHE_ID) || !!llc->fw_token; @@ -554,7 +557,11 @@ static inline int init_level_allocate_ci(unsigned int cpu) */ ci_cacheinfo(cpu)->early_ci_levels = false; - if (cache_leaves(cpu) <= early_leaves) + /* + * Some architectures (e.g., x86) do not use early initialization. + * Allocate memory now in such case. + */ + if (cache_leaves(cpu) <= early_leaves && per_cpu_cacheinfo(cpu)) return 0; kfree(per_cpu_cacheinfo(cpu)); diff --git a/drivers/base/core.c b/drivers/base/core.c index 9828da9b933cb..4a17c74d5cca2 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -44,6 +44,7 @@ static bool fw_devlink_is_permissive(void); static void __fw_devlink_link_to_consumers(struct device *dev); static bool fw_devlink_drv_reg_done; static bool fw_devlink_best_effort; +static struct workqueue_struct *device_link_wq; /** * __fwnode_link_add - Create a link between two fwnode_handles. @@ -532,12 +533,26 @@ static void devlink_dev_release(struct device *dev) /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or - * supplier devices get deleted when it runs, so put it into the "long" - * workqueue. + * supplier devices get deleted when it runs, so put it into the + * dedicated workqueue. */ - queue_work(system_long_wq, &link->rm_work); + queue_work(device_link_wq, &link->rm_work); } +/** + * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate + */ +void device_link_wait_removal(void) +{ + /* + * devlink removal jobs are queued in the dedicated work queue. + * To be sure that all removal jobs are terminated, ensure that any + * scheduled work has run to completion. + */ + flush_workqueue(device_link_wq); +} +EXPORT_SYMBOL_GPL(device_link_wait_removal); + static struct class devlink_class = { .name = "devlink", .dev_groups = devlink_groups, @@ -2657,8 +2672,11 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, if (!env) return -ENOMEM; + /* Synchronize with really_probe() */ + device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(&dev->kobj, env); + device_unlock(dev); if (retval) goto out; @@ -4098,9 +4116,14 @@ int __init devices_init(void) sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; + device_link_wq = alloc_workqueue("device_link_wq", 0, 0); + if (!device_link_wq) + goto wq_err; return 0; + wq_err: + kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 47de0f140ba65..0b33e81f9c9b6 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -588,6 +588,7 @@ CPU_SHOW_VULN_FALLBACK(mmio_stale_data); CPU_SHOW_VULN_FALLBACK(retbleed); CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); +CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -602,6 +603,7 @@ static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); +static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -617,6 +619,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_retbleed.attr, &dev_attr_spec_rstack_overflow.attr, &dev_attr_gather_data_sampling.attr, + &dev_attr_reg_file_data_sampling.attr, NULL }; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 14f964a7719bd..c0436f46cfb70 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -188,6 +188,7 @@ static int memory_block_online(struct memory_block *mem) unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; unsigned long nr_vmemmap_pages = 0; + struct memory_notify arg; struct zone *zone; int ret; @@ -207,9 +208,19 @@ static int memory_block_online(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + arg.altmap_start_pfn = start_pfn; + arg.altmap_nr_pages = nr_vmemmap_pages; + arg.start_pfn = start_pfn + nr_vmemmap_pages; + arg.nr_pages = nr_pages - nr_vmemmap_pages; mem_hotplug_begin(); + ret = memory_notify(MEM_PREPARE_ONLINE, &arg); + ret = notifier_to_errno(ret); + if (ret) + goto out_notifier; + if (nr_vmemmap_pages) { - ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); + ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, + zone, mem->altmap->inaccessible); if (ret) goto out; } @@ -231,7 +242,11 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; + mem_hotplug_done(); + return ret; out: + memory_notify(MEM_FINISH_OFFLINE, &arg); +out_notifier: mem_hotplug_done(); return ret; } @@ -244,6 +259,7 @@ static int memory_block_offline(struct memory_block *mem) unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; unsigned long nr_vmemmap_pages = 0; + struct memory_notify arg; int ret; if (!mem->zone) @@ -275,6 +291,11 @@ static int memory_block_offline(struct memory_block *mem) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; + arg.altmap_start_pfn = start_pfn; + arg.altmap_nr_pages = nr_vmemmap_pages; + arg.start_pfn = start_pfn + nr_vmemmap_pages; + arg.nr_pages = nr_pages - nr_vmemmap_pages; + memory_notify(MEM_FINISH_OFFLINE, &arg); out: mem_hotplug_done(); return ret; diff --git a/drivers/base/module.c b/drivers/base/module.c index 46ad4d636731d..a1b55da07127d 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -30,14 +30,14 @@ static void module_create_drivers_dir(struct module_kobject *mk) mutex_unlock(&drivers_dir_mutex); } -void module_add_driver(struct module *mod, struct device_driver *drv) +int module_add_driver(struct module *mod, struct device_driver *drv) { char *driver_name; - int no_warn; struct module_kobject *mk = NULL; + int ret; if (!drv) - return; + return 0; if (mod) mk = &mod->mkobj; @@ -56,17 +56,37 @@ void module_add_driver(struct module *mod, struct device_driver *drv) } if (!mk) - return; + return 0; + + ret = sysfs_create_link(&drv->p->kobj, &mk->kobj, "module"); + if (ret) + return ret; - /* Don't check return codes; these calls are idempotent */ - no_warn = sysfs_create_link(&drv->p->kobj, &mk->kobj, "module"); driver_name = make_driver_name(drv); - if (driver_name) { - module_create_drivers_dir(mk); - no_warn = sysfs_create_link(mk->drivers_dir, &drv->p->kobj, - driver_name); - kfree(driver_name); + if (!driver_name) { + ret = -ENOMEM; + goto out; + } + + module_create_drivers_dir(mk); + if (!mk->drivers_dir) { + ret = -EINVAL; + goto out; } + + ret = sysfs_create_link(mk->drivers_dir, &drv->p->kobj, driver_name); + if (ret) + goto out; + + kfree(driver_name); + + return 0; +out: + sysfs_remove_link(&drv->p->kobj, "module"); + sysfs_remove_link(mk->drivers_dir, driver_name); + kfree(driver_name); + + return ret; } void module_remove_driver(struct device_driver *drv) diff --git a/drivers/base/node.c b/drivers/base/node.c index 1c05640461dd1..a73b0c9a401ad 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -126,7 +126,7 @@ static void node_access_release(struct device *dev) } static struct node_access_nodes *node_init_node_access(struct node *node, - unsigned int access) + enum access_coordinate_class access) { struct node_access_nodes *access_node; struct device *dev; @@ -191,7 +191,7 @@ static struct attribute *access_attrs[] = { * @access: The access class the for the given attributes */ void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord, - unsigned int access) + enum access_coordinate_class access) { struct node_access_nodes *c; struct node *node; @@ -689,7 +689,7 @@ int register_cpu_under_node(unsigned int cpu, unsigned int nid) */ int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, - unsigned int access) + enum access_coordinate_class access) { struct node *init_node, *targ_node; struct node_access_nodes *initiator, *target; diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 42171f766dcba..5a5a9e978e85f 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -313,8 +313,10 @@ void dev_pm_enable_wake_irq_complete(struct device *dev) return; if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED && - wirq->status & WAKE_IRQ_DEDICATED_REVERSE) + wirq->status & WAKE_IRQ_DEDICATED_REVERSE) { enable_irq(wirq->irq); + wirq->status |= WAKE_IRQ_DEDICATED_ENABLED; + } } /** diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index 41edd6a430eb4..55999a50ccc0b 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -112,7 +112,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min, unsigned long *entry, *lower, *upper; unsigned long lower_index, lower_last; unsigned long upper_index, upper_last; - int ret; + int ret = 0; lower = NULL; upper = NULL; @@ -145,7 +145,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min, upper_index = max + 1; upper_last = mas.last; - upper = kmemdup(&entry[max + 1], + upper = kmemdup(&entry[max - mas.index + 1], ((mas.last - max) * sizeof(unsigned long)), map->alloc_flags); @@ -244,7 +244,7 @@ static int regcache_maple_sync(struct regmap *map, unsigned int min, unsigned long lmin = min; unsigned long lmax = max; unsigned int r, v, sync_start; - int ret; + int ret = 0; bool sync_needed = false; map->cache_bypass = true; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 6db77d8e45f92..4ae399c30f0f2 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -2836,6 +2836,43 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) } EXPORT_SYMBOL_GPL(regmap_read); +/** + * regmap_read_bypassed() - Read a value from a single register direct + * from the device, bypassing the cache + * + * @map: Register map to read from + * @reg: Register to be read from + * @val: Pointer to store read value + * + * A value of zero will be returned on success, a negative errno will + * be returned in error cases. + */ +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val) +{ + int ret; + bool bypass, cache_only; + + if (!IS_ALIGNED(reg, map->reg_stride)) + return -EINVAL; + + map->lock(map->lock_arg); + + bypass = map->cache_bypass; + cache_only = map->cache_only; + map->cache_bypass = true; + map->cache_only = false; + + ret = _regmap_read(map, reg, val); + + map->cache_bypass = bypass; + map->cache_only = cache_only; + + map->unlock(map->lock_arg); + + return ret; +} +EXPORT_SYMBOL_GPL(regmap_read_bypassed); + /** * regmap_raw_read() - Read raw data from the device * diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index d7317425be510..cc9077b588d7e 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -419,13 +419,16 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu rcu_read_lock(); for_each_netdev_rcu(&init_net, ifp) { dev_hold(ifp); - if (!is_aoe_netif(ifp)) - goto cont; + if (!is_aoe_netif(ifp)) { + dev_put(ifp); + continue; + } skb = new_skb(sizeof *h + sizeof *ch); if (skb == NULL) { printk(KERN_INFO "aoe: skb alloc failure\n"); - goto cont; + dev_put(ifp); + continue; } skb_put(skb, sizeof *h + sizeof *ch); skb->dev = ifp; @@ -440,9 +443,6 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu h->major = cpu_to_be16(aoemajor); h->minor = aoeminor; h->cmd = AOECMD_CFG; - -cont: - dev_put(ifp); } rcu_read_unlock(); } diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c index c51ea95bc2ce4..923a134fd7665 100644 --- a/drivers/block/aoe/aoenet.c +++ b/drivers/block/aoe/aoenet.c @@ -63,6 +63,7 @@ tx(int id) __must_hold(&txlock) pr_warn("aoe: packet could not be sent on %s. %s\n", ifp ? ifp->name : "netif", "consider increasing tx_queue_len"); + dev_put(ifp); spin_lock_irq(&txlock); } return 0; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 33a8f37bb6a1f..a672ca43cbe85 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -567,7 +567,10 @@ static inline int was_interrupted(int result) return result == -ERESTARTSYS || result == -EINTR; } -/* always call with the tx_lock held */ +/* + * Returns BLK_STS_RESOURCE if the caller should retry after a delay. Returns + * -EAGAIN if the caller should requeue @cmd. Returns -EIO if sending failed. + */ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); @@ -584,6 +587,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) u32 nbd_cmd_flags = 0; int sent = nsock->sent, skip = 0; + lockdep_assert_held(&cmd->lock); + lockdep_assert_held(&nsock->tx_lock); + iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request)); type = req_to_nbd_cmd_type(req); @@ -648,7 +654,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->sent = sent; } set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return BLK_STS_RESOURCE; + return (__force int)BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), "Send control failed (result %d)\n", result); @@ -689,7 +695,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->pending = req; nsock->sent = sent; set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return BLK_STS_RESOURCE; + return (__force int)BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", @@ -986,7 +992,7 @@ static int wait_for_reconnect(struct nbd_device *nbd) return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); } -static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) +static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_device *nbd = cmd->nbd; @@ -994,18 +1000,20 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) struct nbd_sock *nsock; int ret; + lockdep_assert_held(&cmd->lock); + config = nbd_get_config_unlocked(nbd); if (!config) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Socks array is empty\n"); - return -EINVAL; + return BLK_STS_IOERR; } if (index >= config->num_connections) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Attempted send on invalid socket\n"); nbd_config_put(nbd); - return -EINVAL; + return BLK_STS_IOERR; } cmd->status = BLK_STS_OK; again: @@ -1028,7 +1036,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) */ sock_shutdown(nbd); nbd_config_put(nbd); - return -EIO; + return BLK_STS_IOERR; } goto again; } @@ -1041,7 +1049,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { nbd_requeue_cmd(cmd); - ret = 0; + ret = BLK_STS_OK; goto out; } /* @@ -1060,19 +1068,19 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); nbd_requeue_cmd(cmd); - ret = 0; + ret = BLK_STS_OK; } out: mutex_unlock(&nsock->tx_lock); nbd_config_put(nbd); - return ret; + return ret < 0 ? BLK_STS_IOERR : (__force blk_status_t)ret; } static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); - int ret; + blk_status_t ret; /* * Since we look at the bio's to send the request over the network we @@ -1092,10 +1100,6 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); - if (ret < 0) - ret = BLK_STS_IOERR; - else if (!ret) - ret = BLK_STS_OK; mutex_unlock(&cmd->lock); return ret; @@ -2433,6 +2437,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) } dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); + if (!dev_list) { + nlmsg_free(reply); + ret = -EMSGSIZE; + goto out; + } + if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 36755f263e8ec..aef00f1543d36 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -392,13 +392,25 @@ static int nullb_update_nr_hw_queues(struct nullb_device *dev, static int nullb_apply_submit_queues(struct nullb_device *dev, unsigned int submit_queues) { - return nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues); + int ret; + + mutex_lock(&lock); + ret = nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues); + mutex_unlock(&lock); + + return ret; } static int nullb_apply_poll_queues(struct nullb_device *dev, unsigned int poll_queues) { - return nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues); + int ret; + + mutex_lock(&lock); + ret = nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues); + mutex_unlock(&lock); + + return ret; } NULLB_DEVICE_ATTR(size, ulong, NULL); @@ -444,28 +456,32 @@ static ssize_t nullb_device_power_store(struct config_item *item, if (ret < 0) return ret; + ret = count; + mutex_lock(&lock); if (!dev->power && newp) { if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags)) - return count; + goto out; + ret = null_add_dev(dev); if (ret) { clear_bit(NULLB_DEV_FL_UP, &dev->flags); - return ret; + goto out; } set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); dev->power = newp; + ret = count; } else if (dev->power && !newp) { if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) { - mutex_lock(&lock); dev->power = newp; null_del_dev(dev->nullb); - mutex_unlock(&lock); } clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); } - return count; +out: + mutex_unlock(&lock); + return ret; } CONFIGFS_ATTR(nullb_device_, power); @@ -2173,15 +2189,12 @@ static int null_add_dev(struct nullb_device *dev) nullb->q->queuedata = nullb; blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q); - mutex_lock(&lock); rv = ida_alloc(&nullb_indexes, GFP_KERNEL); - if (rv < 0) { - mutex_unlock(&lock); + if (rv < 0) goto out_cleanup_zone; - } + nullb->index = rv; dev->index = rv; - mutex_unlock(&lock); blk_queue_logical_block_size(nullb->q, dev->blocksize); blk_queue_physical_block_size(nullb->q, dev->blocksize); @@ -2205,9 +2218,7 @@ static int null_add_dev(struct nullb_device *dev) if (rv) goto out_ida_free; - mutex_lock(&lock); list_add_tail(&nullb->list, &nullb_list); - mutex_unlock(&lock); pr_info("disk %s created\n", nullb->disk_name); @@ -2256,7 +2267,9 @@ static int null_create_dev(void) if (!dev) return -ENOMEM; + mutex_lock(&lock); ret = null_add_dev(dev); + mutex_unlock(&lock); if (ret) { null_free_dev(dev); return ret; @@ -2372,10 +2385,13 @@ static void __exit null_exit(void) if (g_queue_mode == NULL_Q_MQ && shared_tags) blk_mq_free_tag_set(&tag_set); + + mutex_destroy(&lock); } module_init(null_init); module_exit(null_exit); MODULE_AUTHOR("Jens Axboe "); +MODULE_DESCRIPTION("multi queue aware block test driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index 6f5e0994862ea..cbca721b7078d 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -112,7 +112,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q) if (dev->zone_max_active && dev->zone_max_open > dev->zone_max_active) { dev->zone_max_open = dev->zone_max_active; pr_info("changed the maximum number of open zones to %u\n", - dev->nr_zones); + dev->zone_max_open); } else if (dev->zone_max_open >= dev->nr_zones - dev->zone_nr_conv) { dev->zone_max_open = 0; pr_info("zone_max_open limit disabled, limit >= zone count\n"); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 12b5d53ec8564..1dfbb43d72941 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -89,7 +89,7 @@ static int atomic_dec_return_safe(atomic_t *v) #define RBD_MINORS_PER_MAJOR 256 #define RBD_SINGLE_MAJOR_PART_SHIFT 4 -#define RBD_MAX_PARENT_CHAIN_LEN 16 +#define RBD_MAX_PARENT_CHAIN_LEN 128 #define RBD_SNAP_DEV_NAME_PREFIX "snap_" #define RBD_MAX_SNAP_NAME_LEN \ diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 88262d3a93923..ce97b336fbfb8 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -3,7 +3,6 @@ * Copyright (c) 2008-2009 Atheros Communications Inc. */ - #include #include #include @@ -128,7 +127,6 @@ MODULE_DEVICE_TABLE(usb, ath3k_table); * for AR3012 */ static const struct usb_device_id ath3k_blist_tbl[] = { - /* Atheros AR3012 with sflash firmware*/ { USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 }, @@ -202,7 +200,7 @@ static inline void ath3k_log_failed_loading(int err, int len, int size, #define TIMEGAP_USEC_MAX 100 static int ath3k_load_firmware(struct usb_device *udev, - const struct firmware *firmware) + const struct firmware *firmware) { u8 *send_buf; int len = 0; @@ -237,9 +235,9 @@ static int ath3k_load_firmware(struct usb_device *udev, memcpy(send_buf, firmware->data + sent, size); err = usb_bulk_msg(udev, pipe, send_buf, size, - &len, 3000); + &len, 3000); - if (err || (len != size)) { + if (err || len != size) { ath3k_log_failed_loading(err, len, size, count); goto error; } @@ -262,7 +260,7 @@ static int ath3k_get_state(struct usb_device *udev, unsigned char *state) } static int ath3k_get_version(struct usb_device *udev, - struct ath3k_version *version) + struct ath3k_version *version) { return usb_control_msg_recv(udev, 0, ATH3K_GETVERSION, USB_TYPE_VENDOR | USB_DIR_IN, 0, 0, @@ -271,7 +269,7 @@ static int ath3k_get_version(struct usb_device *udev, } static int ath3k_load_fwfile(struct usb_device *udev, - const struct firmware *firmware) + const struct firmware *firmware) { u8 *send_buf; int len = 0; @@ -310,8 +308,8 @@ static int ath3k_load_fwfile(struct usb_device *udev, memcpy(send_buf, firmware->data + sent, size); err = usb_bulk_msg(udev, pipe, send_buf, size, - &len, 3000); - if (err || (len != size)) { + &len, 3000); + if (err || len != size) { ath3k_log_failed_loading(err, len, size, count); kfree(send_buf); return err; @@ -425,7 +423,6 @@ static int ath3k_load_syscfg(struct usb_device *udev) } switch (fw_version.ref_clock) { - case ATH3K_XTAL_FREQ_26M: clk_value = 26; break; @@ -441,7 +438,7 @@ static int ath3k_load_syscfg(struct usb_device *udev) } snprintf(filename, ATH3K_NAME_LEN, "ar3k/ramps_0x%08x_%d%s", - le32_to_cpu(fw_version.rom_version), clk_value, ".dfu"); + le32_to_cpu(fw_version.rom_version), clk_value, ".dfu"); ret = request_firmware(&firmware, filename, &udev->dev); if (ret < 0) { @@ -456,7 +453,7 @@ static int ath3k_load_syscfg(struct usb_device *udev) } static int ath3k_probe(struct usb_interface *intf, - const struct usb_device_id *id) + const struct usb_device_id *id) { const struct firmware *firmware; struct usb_device *udev = interface_to_usbdev(intf); @@ -505,10 +502,10 @@ static int ath3k_probe(struct usb_interface *intf, if (ret < 0) { if (ret == -ENOENT) BT_ERR("Firmware file \"%s\" not found", - ATH3K_FIRMWARE); + ATH3K_FIRMWARE); else BT_ERR("Firmware file \"%s\" request failed (err=%d)", - ATH3K_FIRMWARE, ret); + ATH3K_FIRMWARE, ret); return ret; } diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index cdc5c08824a0a..e532e2be1715d 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -441,7 +441,7 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver) return PTR_ERR(skb); } - if (skb->len != sizeof(*ver)) { + if (!skb || skb->len != sizeof(*ver)) { bt_dev_err(hdev, "Intel version event size mismatch"); kfree_skb(skb); return -EILSEQ; diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index 9658b33c824a7..18f34998a1204 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -121,13 +121,6 @@ int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb) ((event->data[2] == MODULE_BROUGHT_UP) || (event->data[2] == MODULE_ALREADY_UP)) ? "Bring-up succeed" : "Bring-up failed"); - - if (event->length > 3 && event->data[3]) - priv->btmrvl_dev.dev_type = HCI_AMP; - else - priv->btmrvl_dev.dev_type = HCI_PRIMARY; - - BT_DBG("dev_type: %d", priv->btmrvl_dev.dev_type); } else if (priv->btmrvl_dev.sendcmdflag && event->data[1] == MODULE_SHUTDOWN_REQ) { BT_DBG("EVENT:%s", (event->data[2]) ? @@ -686,8 +679,6 @@ int btmrvl_register_hdev(struct btmrvl_private *priv) hdev->wakeup = btmrvl_wakeup; SET_HCIDEV_DEV(hdev, &card->func->dev); - hdev->dev_type = priv->btmrvl_dev.dev_type; - ret = hci_register_dev(hdev); if (ret < 0) { BT_ERR("Can not register HCI device"); diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index aaabb732082cd..812fd2a8f853e 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -372,14 +372,18 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) struct btmediatek_data *data = hci_get_priv(hdev); int err; - if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) + if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) { + kfree_skb(skb); return 0; + } switch (data->cd_info.state) { case HCI_DEVCOREDUMP_IDLE: err = hci_devcd_init(hdev, MTK_COREDUMP_SIZE); - if (err < 0) + if (err < 0) { + kfree_skb(skb); break; + } data->cd_info.cnt = 0; /* It is supposed coredump can be done within 5 seconds */ @@ -405,9 +409,6 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) break; } - if (err < 0) - kfree_skb(skb); - return err; } EXPORT_SYMBOL_GPL(btmtk_process_coredump); @@ -420,5 +421,6 @@ MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_MT7622); MODULE_FIRMWARE(FIRMWARE_MT7663); MODULE_FIRMWARE(FIRMWARE_MT7668); +MODULE_FIRMWARE(FIRMWARE_MT7922); MODULE_FIRMWARE(FIRMWARE_MT7961); MODULE_FIRMWARE(FIRMWARE_MT7925); diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index 56f5502baadf9..cbcdb99a22e6d 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -4,6 +4,7 @@ #define FIRMWARE_MT7622 "mediatek/mt7622pr2h.bin" #define FIRMWARE_MT7663 "mediatek/mt7663pr2h.bin" #define FIRMWARE_MT7668 "mediatek/mt7668pr2h.bin" +#define FIRMWARE_MT7922 "mediatek/BT_RAM_CODE_MT7922_1_1_hdr.bin" #define FIRMWARE_MT7961 "mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin" #define FIRMWARE_MT7925 "mediatek/mt7925/BT_RAM_CODE_MT7925_1_1_hdr.bin" diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 1d592ac413d1f..c19dc8a2987f3 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1234,6 +1234,9 @@ static int btnxpuart_close(struct hci_dev *hdev) ps_wakeup(nxpdev); serdev_device_close(nxpdev->serdev); + skb_queue_purge(&nxpdev->txq); + kfree_skb(nxpdev->rx_skb); + nxpdev->rx_skb = NULL; clear_bit(BTNXPUART_SERDEV_OPEN, &nxpdev->tx_state); return 0; } diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index b40b32fa7f1c3..35fb26cbf2294 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -99,7 +99,8 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) { struct sk_buff *skb; struct edl_event_hdr *edl; - char cmd, build_label[QCA_FW_BUILD_VER_LEN]; + char *build_label; + char cmd; int build_lbl_len, err = 0; bt_dev_dbg(hdev, "QCA read fw build info"); @@ -114,6 +115,11 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) return err; } + if (skb->len < sizeof(*edl)) { + err = -EILSEQ; + goto out; + } + edl = (struct edl_event_hdr *)(skb->data); if (!edl) { bt_dev_err(hdev, "QCA read fw build info with no header"); @@ -129,14 +135,27 @@ static int qca_read_fw_build_info(struct hci_dev *hdev) goto out; } + if (skb->len < sizeof(*edl) + 1) { + err = -EILSEQ; + goto out; + } + build_lbl_len = edl->data[0]; - if (build_lbl_len <= QCA_FW_BUILD_VER_LEN - 1) { - memcpy(build_label, edl->data + 1, build_lbl_len); - *(build_label + build_lbl_len) = '\0'; + + if (skb->len < sizeof(*edl) + 1 + build_lbl_len) { + err = -EILSEQ; + goto out; + } + + build_label = kstrndup(&edl->data[1], build_lbl_len, GFP_KERNEL); + if (!build_label) { + err = -ENOMEM; + goto out; } hci_set_fw_info(hdev, "%s", build_label); + kfree(build_label); out: kfree_skb(skb); return err; @@ -235,6 +254,11 @@ static int qca_read_fw_board_id(struct hci_dev *hdev, u16 *bid) goto out; } + if (skb->len < 3) { + err = -EILSEQ; + goto out; + } + *bid = (edl->data[1] << 8) + edl->data[2]; bt_dev_dbg(hdev, "%s: bid = %x", __func__, *bid); @@ -265,9 +289,10 @@ int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) } EXPORT_SYMBOL_GPL(qca_send_pre_shutdown_cmd); -static void qca_tlv_check_data(struct hci_dev *hdev, +static int qca_tlv_check_data(struct hci_dev *hdev, struct qca_fw_config *config, - u8 *fw_data, enum qca_btsoc_type soc_type) + u8 *fw_data, size_t fw_size, + enum qca_btsoc_type soc_type) { const u8 *data; u32 type_len; @@ -277,12 +302,16 @@ static void qca_tlv_check_data(struct hci_dev *hdev, struct tlv_type_patch *tlv_patch; struct tlv_type_nvm *tlv_nvm; uint8_t nvm_baud_rate = config->user_baud_rate; + u8 type; config->dnld_mode = QCA_SKIP_EVT_NONE; config->dnld_type = QCA_SKIP_EVT_NONE; switch (config->type) { case ELF_TYPE_PATCH: + if (fw_size < 7) + return -EINVAL; + config->dnld_mode = QCA_SKIP_EVT_VSE_CC; config->dnld_type = QCA_SKIP_EVT_VSE_CC; @@ -291,6 +320,9 @@ static void qca_tlv_check_data(struct hci_dev *hdev, bt_dev_dbg(hdev, "File version : 0x%x", fw_data[6]); break; case TLV_TYPE_PATCH: + if (fw_size < sizeof(struct tlv_type_hdr) + sizeof(struct tlv_type_patch)) + return -EINVAL; + tlv = (struct tlv_type_hdr *)fw_data; type_len = le32_to_cpu(tlv->type_len); tlv_patch = (struct tlv_type_patch *)tlv->data; @@ -330,25 +362,64 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; case TLV_TYPE_NVM: + if (fw_size < sizeof(struct tlv_type_hdr)) + return -EINVAL; + tlv = (struct tlv_type_hdr *)fw_data; type_len = le32_to_cpu(tlv->type_len); - length = (type_len >> 8) & 0x00ffffff; + length = type_len >> 8; + type = type_len & 0xff; - BT_DBG("TLV Type\t\t : 0x%x", type_len & 0x000000ff); + /* Some NVM files have more than one set of tags, only parse + * the first set when it has type 2 for now. When there is + * more than one set there is an enclosing header of type 4. + */ + if (type == 4) { + if (fw_size < 2 * sizeof(struct tlv_type_hdr)) + return -EINVAL; + + tlv++; + + type_len = le32_to_cpu(tlv->type_len); + length = type_len >> 8; + type = type_len & 0xff; + } + + BT_DBG("TLV Type\t\t : 0x%x", type); BT_DBG("Length\t\t : %d bytes", length); + if (type != 2) + break; + + if (fw_size < length + (tlv->data - fw_data)) + return -EINVAL; + idx = 0; data = tlv->data; - while (idx < length) { + while (idx < length - sizeof(struct tlv_type_nvm)) { tlv_nvm = (struct tlv_type_nvm *)(data + idx); tag_id = le16_to_cpu(tlv_nvm->tag_id); tag_len = le16_to_cpu(tlv_nvm->tag_len); + if (length < idx + sizeof(struct tlv_type_nvm) + tag_len) + return -EINVAL; + /* Update NVM tags as needed */ switch (tag_id) { + case EDL_TAG_ID_BD_ADDR: + if (tag_len != sizeof(bdaddr_t)) + return -EINVAL; + + memcpy(&config->bdaddr, tlv_nvm->data, sizeof(bdaddr_t)); + + break; + case EDL_TAG_ID_HCI: + if (tag_len < 3) + return -EINVAL; + /* HCI transport layer parameters * enabling software inband sleep * onto controller side. @@ -364,6 +435,9 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; case EDL_TAG_ID_DEEP_SLEEP: + if (tag_len < 1) + return -EINVAL; + /* Sleep enable mask * enabling deep sleep feature on controller. */ @@ -372,14 +446,16 @@ static void qca_tlv_check_data(struct hci_dev *hdev, break; } - idx += (sizeof(u16) + sizeof(u16) + 8 + tag_len); + idx += sizeof(struct tlv_type_nvm) + tag_len; } break; default: BT_ERR("Unknown TLV type %d", config->type); - break; + return -EINVAL; } + + return 0; } static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size, @@ -529,7 +605,9 @@ static int qca_download_firmware(struct hci_dev *hdev, memcpy(data, fw->data, size); release_firmware(fw); - qca_tlv_check_data(hdev, config, data, soc_type); + ret = qca_tlv_check_data(hdev, config, data, size, soc_type); + if (ret) + goto out; segment = data; remain = size; @@ -612,6 +690,38 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) } EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome); +static int qca_check_bdaddr(struct hci_dev *hdev, const struct qca_fw_config *config) +{ + struct hci_rp_read_bd_addr *bda; + struct sk_buff *skb; + int err; + + if (bacmp(&hdev->public_addr, BDADDR_ANY)) + return 0; + + skb = __hci_cmd_sync(hdev, HCI_OP_READ_BD_ADDR, 0, NULL, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + bt_dev_err(hdev, "Failed to read device address (%d)", err); + return err; + } + + if (skb->len != sizeof(*bda)) { + bt_dev_err(hdev, "Device address length mismatch"); + kfree_skb(skb); + return -EIO; + } + + bda = (struct hci_rp_read_bd_addr *)skb->data; + if (!bacmp(&bda->bdaddr, &config->bdaddr)) + set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + + kfree_skb(skb); + + return 0; +} + static void qca_generate_hsp_nvm_name(char *fwname, size_t max_size, struct qca_btsoc_version ver, u8 rom_ver, u16 bid) { @@ -633,7 +743,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, enum qca_btsoc_type soc_type, struct qca_btsoc_version ver, const char *firmware_name) { - struct qca_fw_config config; + struct qca_fw_config config = {}; int err; u8 rom_ver = 0; u32 soc_ver; @@ -818,6 +928,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, break; } + err = qca_check_bdaddr(hdev, &config); + if (err) + return err; + bt_dev_info(hdev, "QCA setup on UART is completed"); return 0; @@ -826,11 +940,15 @@ EXPORT_SYMBOL_GPL(qca_uart_setup); int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) { + bdaddr_t bdaddr_swapped; struct sk_buff *skb; int err; - skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, bdaddr, - HCI_EV_VENDOR, HCI_INIT_TIMEOUT); + baswap(&bdaddr_swapped, bdaddr); + + skb = __hci_cmd_sync_ev(hdev, EDL_WRITE_BD_ADDR_OPCODE, 6, + &bdaddr_swapped, HCI_EV_VENDOR, + HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "QCA Change address cmd failed (%d)", err); diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index dc31984f71dc1..215433fd76a10 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -29,6 +29,7 @@ #define EDL_PATCH_CONFIG_RES_EVT (0x00) #define QCA_DISABLE_LOGGING_SUB_OP (0x14) +#define EDL_TAG_ID_BD_ADDR 2 #define EDL_TAG_ID_HCI (17) #define EDL_TAG_ID_DEEP_SLEEP (27) @@ -47,7 +48,6 @@ #define get_soc_ver(soc_id, rom_ver) \ ((le32_to_cpu(soc_id) << 16) | (le16_to_cpu(rom_ver))) -#define QCA_FW_BUILD_VER_LEN 255 #define QCA_HSP_GF_SOC_ID 0x1200 #define QCA_HSP_GF_SOC_MASK 0x0000ff00 @@ -94,6 +94,7 @@ struct qca_fw_config { uint8_t user_baud_rate; enum qca_tlv_dnld_mode dnld_mode; enum qca_tlv_dnld_mode dnld_type; + bdaddr_t bdaddr; }; struct edl_event_hdr { diff --git a/drivers/bluetooth/btrsi.c b/drivers/bluetooth/btrsi.c index 634cf8f5ed2db..0c91d7635ac39 100644 --- a/drivers/bluetooth/btrsi.c +++ b/drivers/bluetooth/btrsi.c @@ -134,7 +134,6 @@ static int rsi_hci_attach(void *priv, struct rsi_proto_ops *ops) hdev->bus = HCI_USB; hci_set_drvdata(hdev, h_adapter); - hdev->dev_type = HCI_PRIMARY; hdev->open = rsi_hci_open; hdev->close = rsi_hci_close; hdev->flush = rsi_hci_flush; diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index f19d31ee37ea8..fdcfe9c50313e 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -32,9 +32,6 @@ static const struct sdio_device_id btsdio_table[] = { /* Generic Bluetooth Type-B SDIO device */ { SDIO_DEVICE_CLASS(SDIO_CLASS_BT_B) }, - /* Generic Bluetooth AMP controller */ - { SDIO_DEVICE_CLASS(SDIO_CLASS_BT_AMP) }, - { } /* Terminating entry */ }; @@ -319,11 +316,6 @@ static int btsdio_probe(struct sdio_func *func, hdev->bus = HCI_SDIO; hci_set_drvdata(hdev, data); - if (id->class == SDIO_CLASS_BT_AMP) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - data->hdev = hdev; SET_HCIDEV_DEV(hdev, &func->dev); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index d31edad7a0560..33386a70d2f09 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -542,6 +543,8 @@ static const struct usb_device_id quirks_table[] = { /* Realtek 8852BE Bluetooth devices */ { USB_DEVICE(0x0cb8, 0xc559), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0bda, 0x4853), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0x887b), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0xb85b), .driver_info = BTUSB_REALTEK | @@ -583,6 +586,9 @@ static const struct usb_device_id quirks_table[] = { { USB_DEVICE(0x0489, 0xe0c8), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x0489, 0xe0cd), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, { USB_DEVICE(0x0489, 0xe0e0), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, @@ -3273,7 +3279,6 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb) { struct btusb_data *data = hci_get_drvdata(hdev); u16 handle = le16_to_cpu(hci_acl_hdr(skb)->handle); - struct sk_buff *skb_cd; switch (handle) { case 0xfc6f: /* Firmware dump from device */ @@ -3286,9 +3291,12 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb) * for backward compatibility, so we have to clone the packet * extraly for the in-kernel coredump support. */ - skb_cd = skb_clone(skb, GFP_ATOMIC); - if (skb_cd) - btmtk_process_coredump(hdev, skb_cd); + if (IS_ENABLED(CONFIG_DEV_COREDUMP)) { + struct sk_buff *skb_cd = skb_clone(skb, GFP_ATOMIC); + + if (skb_cd) + btmtk_process_coredump(hdev, skb_cd); + } fallthrough; case 0x05ff: /* Firmware debug logging 1 */ @@ -3366,6 +3374,35 @@ static int btusb_set_bdaddr_marvell(struct hci_dev *hdev, return 0; } +#define BTUSB_EDGE_LED_COMMAND 0xfc77 + +static void btusb_edge_set_led(struct hci_dev *hdev, bool state) +{ + struct sk_buff *skb; + u8 config_led[] = { 0x09, 0x00, 0x01, 0x01 }; + + if (state) + config_led[1] = 0x01; + + skb = __hci_cmd_sync(hdev, BTUSB_EDGE_LED_COMMAND, sizeof(config_led), config_led, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) + BT_ERR("%s fail to set LED (%ld)", hdev->name, PTR_ERR(skb)); + else + kfree_skb(skb); +} + +static int btusb_edge_post_init(struct hci_dev *hdev) +{ + btusb_edge_set_led(hdev, true); + return 0; +} + +static int btusb_edge_shutdown(struct hci_dev *hdev) +{ + btusb_edge_set_led(hdev, false); + return 0; +} + static int btusb_set_bdaddr_ath3012(struct hci_dev *hdev, const bdaddr_t *bdaddr) { @@ -3461,13 +3498,12 @@ static void btusb_dump_hdr_qca(struct hci_dev *hdev, struct sk_buff *skb) static void btusb_coredump_qca(struct hci_dev *hdev) { + int err; static const u8 param[] = { 0x26 }; - struct sk_buff *skb; - skb = __hci_cmd_sync(hdev, 0xfc0c, 1, param, HCI_CMD_TIMEOUT); - if (IS_ERR(skb)) - bt_dev_err(hdev, "%s: triggle crash failed (%ld)", __func__, PTR_ERR(skb)); - kfree_skb(skb); + err = __hci_cmd_send(hdev, 0xfc0c, 1, param); + if (err < 0) + bt_dev_err(hdev, "%s: triggle crash failed (%d)", __func__, err); } /* @@ -4311,11 +4347,6 @@ static int btusb_probe(struct usb_interface *intf, hdev->bus = HCI_USB; hci_set_drvdata(hdev, data); - if (id->driver_info & BTUSB_AMP) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - data->hdev = hdev; SET_HCIDEV_DEV(hdev, &intf->dev); @@ -4398,8 +4429,18 @@ static int btusb_probe(struct usb_interface *intf, btintel_set_flag(hdev, INTEL_BROKEN_SHUTDOWN_LED); } - if (id->driver_info & BTUSB_MARVELL) + if (id->driver_info & BTUSB_MARVELL) { + struct pci_dev *pdev; hdev->set_bdaddr = btusb_set_bdaddr_marvell; + pdev = pci_get_subsys(PCI_ANY_ID, PCI_ANY_ID, 0x1028, 0x0720, NULL); + if (!pdev) + pdev = pci_get_subsys(PCI_ANY_ID, PCI_ANY_ID, 0x1028, 0x0733, NULL); + if (pdev) { + pci_dev_put(pdev); + hdev->post_init = btusb_edge_post_init; + hdev->shutdown = btusb_edge_shutdown; + } + } if (IS_ENABLED(CONFIG_BT_HCIBTUSB_MTK) && (id->driver_info & BTUSB_MEDIATEK)) { @@ -4481,6 +4522,7 @@ static int btusb_probe(struct usb_interface *intf, set_bit(HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, &hdev->quirks); set_bit(HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, &hdev->quirks); set_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &hdev->quirks); + set_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks); } if (!reset) diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c index 9a7243d5db71f..0c2f15235b4cd 100644 --- a/drivers/bluetooth/hci_bcm4377.c +++ b/drivers/bluetooth/hci_bcm4377.c @@ -2361,7 +2361,6 @@ static int bcm4377_probe(struct pci_dev *pdev, const struct pci_device_id *id) bcm4377->hdev = hdev; hdev->bus = HCI_PCI; - hdev->dev_type = HCI_PRIMARY; hdev->open = bcm4377_hci_open; hdev->close = bcm4377_hci_close; hdev->send = bcm4377_hci_send_frame; diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index 71e748a9477e4..c0436881a533c 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -113,6 +113,7 @@ struct h5_vnd { int (*suspend)(struct h5 *h5); int (*resume)(struct h5 *h5); const struct acpi_gpio_mapping *acpi_gpio_map; + int sizeof_priv; }; struct h5_device_data { @@ -863,7 +864,8 @@ static int h5_serdev_probe(struct serdev_device *serdev) if (IS_ERR(h5->device_wake_gpio)) return PTR_ERR(h5->device_wake_gpio); - return hci_uart_register_device(&h5->serdev_hu, &h5p); + return hci_uart_register_device_priv(&h5->serdev_hu, &h5p, + h5->vnd->sizeof_priv); } static void h5_serdev_remove(struct serdev_device *serdev) @@ -1070,6 +1072,7 @@ static struct h5_vnd rtl_vnd = { .suspend = h5_btrtl_suspend, .resume = h5_btrtl_resume, .acpi_gpio_map = acpi_btrtl_gpios, + .sizeof_priv = sizeof(struct btrealtek_data), }; static const struct h5_device_data h5_data_rtl8822cs = { diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index a26367e9fb197..17a2f158a0dfa 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -667,11 +667,6 @@ static int hci_uart_register_dev(struct hci_uart *hu) if (!test_bit(HCI_UART_RESET_ON_INIT, &hu->hdev_flags)) set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); - if (test_bit(HCI_UART_CREATE_AMP, &hu->hdev_flags)) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - /* Only call open() for the protocol after hdev is fully initialized as * open() (or a timer/workqueue it starts) may attempt to reference it. */ @@ -722,7 +717,6 @@ static int hci_uart_set_flags(struct hci_uart *hu, unsigned long flags) { unsigned long valid_flags = BIT(HCI_UART_RAW_DEVICE) | BIT(HCI_UART_RESET_ON_INIT) | - BIT(HCI_UART_CREATE_AMP) | BIT(HCI_UART_INIT_PENDING) | BIT(HCI_UART_EXT_CONFIG) | BIT(HCI_UART_VND_DETECT); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index edd2a81b4d5ed..0c9c9ee56592d 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -7,7 +7,6 @@ * * Copyright (C) 2007 Texas Instruments, Inc. * Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved. - * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. * * Acknowledgements: * This file is based on hci_ll.c, which was... @@ -226,6 +225,7 @@ struct qca_serdev { struct qca_power *bt_power; u32 init_speed; u32 oper_speed; + bool bdaddr_property_broken; const char *firmware_name; }; @@ -1672,6 +1672,9 @@ static bool qca_wakeup(struct hci_dev *hdev) struct hci_uart *hu = hci_get_drvdata(hdev); bool wakeup; + if (!hu->serdev) + return true; + /* BT SoC attached through the serial bus is handled by the serdev driver. * So we need to use the device handle of the serdev driver to get the * status of device may wakeup. @@ -1843,6 +1846,7 @@ static int qca_setup(struct hci_uart *hu) const char *firmware_name = qca_get_firmware_name(hu); int ret; struct qca_btsoc_version ver; + struct qca_serdev *qcadev; const char *soc_name; ret = qca_check_speeds(hu); @@ -1904,16 +1908,9 @@ static int qca_setup(struct hci_uart *hu) case QCA_WCN6750: case QCA_WCN6855: case QCA_WCN7850: - - /* Set BDA quirk bit for reading BDA value from fwnode property - * only if that property exist in DT. - */ - if (fwnode_property_present(dev_fwnode(hdev->dev.parent), "local-bd-address")) { - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); - bt_dev_info(hdev, "setting quirk bit to read BDA from fwnode later"); - } else { - bt_dev_dbg(hdev, "local-bd-address` is not present in the devicetree so not setting quirk bit for BDA"); - } + qcadev = serdev_device_get_drvdata(hu->serdev); + if (qcadev->bdaddr_property_broken) + set_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks); hci_set_aosp_capable(hdev); @@ -1961,8 +1958,10 @@ static int qca_setup(struct hci_uart *hu) qca_debugfs_init(hdev); hu->hdev->hw_error = qca_hw_error; hu->hdev->cmd_timeout = qca_cmd_timeout; - if (device_can_wakeup(hu->serdev->ctrl->dev.parent)) - hu->hdev->wakeup = qca_wakeup; + if (hu->serdev) { + if (device_can_wakeup(hu->serdev->ctrl->dev.parent)) + hu->hdev->wakeup = qca_wakeup; + } } else if (ret == -ENOENT) { /* No patch/nvm-config found, run with original fw/config */ set_bit(QCA_ROM_FW, &qca->flags); @@ -2295,6 +2294,9 @@ static int qca_serdev_probe(struct serdev_device *serdev) if (!qcadev->oper_speed) BT_DBG("UART will pick default operating speed"); + qcadev->bdaddr_property_broken = device_property_read_bool(&serdev->dev, + "qcom,local-bd-address-broken"); + if (data) qcadev->btsoc_type = data->soc_type; else @@ -2326,20 +2328,25 @@ static int qca_serdev_probe(struct serdev_device *serdev) qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en) && + if (IS_ERR(qcadev->bt_en) && (data->soc_type == QCA_WCN6750 || data->soc_type == QCA_WCN6855)) { dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n"); - power_ctrl_enabled = false; + return PTR_ERR(qcadev->bt_en); } + if (!qcadev->bt_en) + power_ctrl_enabled = false; + qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl", GPIOD_IN); - if (IS_ERR_OR_NULL(qcadev->sw_ctrl) && + if (IS_ERR(qcadev->sw_ctrl) && (data->soc_type == QCA_WCN6750 || data->soc_type == QCA_WCN6855 || - data->soc_type == QCA_WCN7850)) - dev_warn(&serdev->dev, "failed to acquire SW_CTRL gpio\n"); + data->soc_type == QCA_WCN7850)) { + dev_err(&serdev->dev, "failed to acquire SW_CTRL gpio\n"); + return PTR_ERR(qcadev->sw_ctrl); + } qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); if (IS_ERR(qcadev->susclk)) { @@ -2357,11 +2364,14 @@ static int qca_serdev_probe(struct serdev_device *serdev) default: qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en)) { - dev_warn(&serdev->dev, "failed to acquire enable gpio\n"); - power_ctrl_enabled = false; + if (IS_ERR(qcadev->bt_en)) { + dev_err(&serdev->dev, "failed to acquire enable gpio\n"); + return PTR_ERR(qcadev->bt_en); } + if (!qcadev->bt_en) + power_ctrl_enabled = false; + qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); if (IS_ERR(qcadev->susclk)) { dev_warn(&serdev->dev, "failed to acquire clk\n"); diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 39c8b567da3c0..0eaec878fa1d8 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -300,8 +300,9 @@ static const struct serdev_device_ops hci_serdev_client_ops = { .write_wakeup = hci_uart_write_wakeup, }; -int hci_uart_register_device(struct hci_uart *hu, - const struct hci_uart_proto *p) +int hci_uart_register_device_priv(struct hci_uart *hu, + const struct hci_uart_proto *p, + int sizeof_priv) { int err; struct hci_dev *hdev; @@ -325,7 +326,7 @@ int hci_uart_register_device(struct hci_uart *hu, set_bit(HCI_UART_PROTO_READY, &hu->flags); /* Initialize and register HCI device */ - hdev = hci_alloc_dev(); + hdev = hci_alloc_dev_priv(sizeof_priv); if (!hdev) { BT_ERR("Can't allocate HCI device"); err = -ENOMEM; @@ -365,11 +366,6 @@ int hci_uart_register_device(struct hci_uart *hu, if (test_bit(HCI_UART_EXT_CONFIG, &hu->hdev_flags)) set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks); - if (test_bit(HCI_UART_CREATE_AMP, &hu->hdev_flags)) - hdev->dev_type = HCI_AMP; - else - hdev->dev_type = HCI_PRIMARY; - if (test_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags)) return 0; @@ -394,7 +390,7 @@ int hci_uart_register_device(struct hci_uart *hu, percpu_free_rwsem(&hu->proto_lock); return err; } -EXPORT_SYMBOL_GPL(hci_uart_register_device); +EXPORT_SYMBOL_GPL(hci_uart_register_device_priv); void hci_uart_unregister_device(struct hci_uart *hu) { diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index fb4a2d0d8cc80..00bf7ae82c5b7 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -37,7 +37,6 @@ #define HCI_UART_RAW_DEVICE 0 #define HCI_UART_RESET_ON_INIT 1 -#define HCI_UART_CREATE_AMP 2 #define HCI_UART_INIT_PENDING 3 #define HCI_UART_EXT_CONFIG 4 #define HCI_UART_VND_DETECT 5 @@ -97,7 +96,17 @@ struct hci_uart { int hci_uart_register_proto(const struct hci_uart_proto *p); int hci_uart_unregister_proto(const struct hci_uart_proto *p); -int hci_uart_register_device(struct hci_uart *hu, const struct hci_uart_proto *p); + +int hci_uart_register_device_priv(struct hci_uart *hu, + const struct hci_uart_proto *p, + int sizeof_priv); + +static inline int hci_uart_register_device(struct hci_uart *hu, + const struct hci_uart_proto *p) +{ + return hci_uart_register_device_priv(hu, p, 0); +} + void hci_uart_unregister_device(struct hci_uart *hu); int hci_uart_tx_wakeup(struct hci_uart *hu); diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 572d68d52965f..28750a40f0ed5 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -384,17 +384,10 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) { struct hci_dev *hdev; struct sk_buff *skb; - __u8 dev_type; if (data->hdev) return -EBADFD; - /* bits 0-1 are dev_type (Primary or AMP) */ - dev_type = opcode & 0x03; - - if (dev_type != HCI_PRIMARY && dev_type != HCI_AMP) - return -EINVAL; - /* bits 2-5 are reserved (must be zero) */ if (opcode & 0x3c) return -EINVAL; @@ -412,7 +405,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) data->hdev = hdev; hdev->bus = HCI_VIRTUAL; - hdev->dev_type = dev_type; hci_set_drvdata(hdev, data); hdev->open = vhci_open_dev; @@ -634,7 +626,7 @@ static void vhci_open_timeout(struct work_struct *work) struct vhci_data *data = container_of(work, struct vhci_data, open_timeout.work); - vhci_create_device(data, amp ? HCI_AMP : HCI_PRIMARY); + vhci_create_device(data, 0x00); } static int vhci_open(struct inode *inode, struct file *file) diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 2ac70b560c46d..18208e152a367 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -274,7 +274,6 @@ static int virtbt_probe(struct virtio_device *vdev) switch (type) { case VIRTIO_BT_CONFIG_TYPE_PRIMARY: - case VIRTIO_BT_CONFIG_TYPE_AMP: break; default: return -EINVAL; @@ -303,7 +302,6 @@ static int virtbt_probe(struct virtio_device *vdev) vbt->hdev = hdev; hdev->bus = HCI_VIRTIO; - hdev->dev_type = type; hci_set_drvdata(hdev, vbt); hdev->open = virtbt_open; diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig index e6742998f372c..d5e7fa9173a16 100644 --- a/drivers/bus/Kconfig +++ b/drivers/bus/Kconfig @@ -186,11 +186,12 @@ config SUNXI_RSB config TEGRA_ACONNECT tristate "Tegra ACONNECT Bus Driver" - depends on ARCH_TEGRA_210_SOC + depends on ARCH_TEGRA depends on OF && PM help Driver for the Tegra ACONNECT bus which is used to interface with - the devices inside the Audio Processing Engine (APE) for Tegra210. + the devices inside the Audio Processing Engine (APE) for + Tegra210 and later. config TEGRA_GMI tristate "Tegra Generic Memory Interface bus driver" diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c index 65fc1d738bec2..65f1f6b9b5df3 100644 --- a/drivers/bus/mhi/ep/main.c +++ b/drivers/bus/mhi/ep/main.c @@ -1496,7 +1496,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, mhi_cntrl->ring_item_cache = kmem_cache_create("mhi_ep_ring_item", sizeof(struct mhi_ep_ring_item), 0, 0, NULL); - if (!mhi_cntrl->ev_ring_el_cache) { + if (!mhi_cntrl->ring_item_cache) { ret = -ENOMEM; goto err_destroy_tre_buf_cache; } diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c index 65ceac1837f9a..8e5ec1a409b80 100644 --- a/drivers/bus/mhi/host/init.c +++ b/drivers/bus/mhi/host/init.c @@ -62,6 +62,7 @@ static const char * const mhi_pm_state_str[] = { [MHI_PM_STATE_FW_DL_ERR] = "Firmware Download Error", [MHI_PM_STATE_SYS_ERR_DETECT] = "SYS ERROR Detect", [MHI_PM_STATE_SYS_ERR_PROCESS] = "SYS ERROR Process", + [MHI_PM_STATE_SYS_ERR_FAIL] = "SYS ERROR Failure", [MHI_PM_STATE_SHUTDOWN_PROCESS] = "SHUTDOWN Process", [MHI_PM_STATE_LD_ERR_FATAL_DETECT] = "Linkdown or Error Fatal Detect", }; diff --git a/drivers/bus/mhi/host/internal.h b/drivers/bus/mhi/host/internal.h index 30ac415a3000f..4b6deea17bcd2 100644 --- a/drivers/bus/mhi/host/internal.h +++ b/drivers/bus/mhi/host/internal.h @@ -88,6 +88,7 @@ enum mhi_pm_state { MHI_PM_STATE_FW_DL_ERR, MHI_PM_STATE_SYS_ERR_DETECT, MHI_PM_STATE_SYS_ERR_PROCESS, + MHI_PM_STATE_SYS_ERR_FAIL, MHI_PM_STATE_SHUTDOWN_PROCESS, MHI_PM_STATE_LD_ERR_FATAL_DETECT, MHI_PM_STATE_MAX @@ -104,14 +105,16 @@ enum mhi_pm_state { #define MHI_PM_FW_DL_ERR BIT(7) #define MHI_PM_SYS_ERR_DETECT BIT(8) #define MHI_PM_SYS_ERR_PROCESS BIT(9) -#define MHI_PM_SHUTDOWN_PROCESS BIT(10) +#define MHI_PM_SYS_ERR_FAIL BIT(10) +#define MHI_PM_SHUTDOWN_PROCESS BIT(11) /* link not accessible */ -#define MHI_PM_LD_ERR_FATAL_DETECT BIT(11) +#define MHI_PM_LD_ERR_FATAL_DETECT BIT(12) #define MHI_REG_ACCESS_VALID(pm_state) ((pm_state & (MHI_PM_POR | MHI_PM_M0 | \ MHI_PM_M2 | MHI_PM_M3_ENTER | MHI_PM_M3_EXIT | \ MHI_PM_SYS_ERR_DETECT | MHI_PM_SYS_ERR_PROCESS | \ - MHI_PM_SHUTDOWN_PROCESS | MHI_PM_FW_DL_ERR))) + MHI_PM_SYS_ERR_FAIL | MHI_PM_SHUTDOWN_PROCESS | \ + MHI_PM_FW_DL_ERR))) #define MHI_PM_IN_ERROR_STATE(pm_state) (pm_state >= MHI_PM_FW_DL_ERR) #define MHI_PM_IN_FATAL_STATE(pm_state) (pm_state == MHI_PM_LD_ERR_FATAL_DETECT) #define MHI_DB_ACCESS_VALID(mhi_cntrl) (mhi_cntrl->pm_state & mhi_cntrl->db_access) diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c index a2f2feef14768..d0d033ce9984b 100644 --- a/drivers/bus/mhi/host/pm.c +++ b/drivers/bus/mhi/host/pm.c @@ -36,7 +36,10 @@ * M0 <--> M0 * M0 -> FW_DL_ERR * M0 -> M3_ENTER -> M3 -> M3_EXIT --> M0 - * L1: SYS_ERR_DETECT -> SYS_ERR_PROCESS --> POR + * L1: SYS_ERR_DETECT -> SYS_ERR_PROCESS + * SYS_ERR_PROCESS -> SYS_ERR_FAIL + * SYS_ERR_FAIL -> SYS_ERR_DETECT + * SYS_ERR_PROCESS --> POR * L2: SHUTDOWN_PROCESS -> LD_ERR_FATAL_DETECT * SHUTDOWN_PROCESS -> DISABLE * L3: LD_ERR_FATAL_DETECT <--> LD_ERR_FATAL_DETECT @@ -93,7 +96,12 @@ static const struct mhi_pm_transitions dev_state_transitions[] = { }, { MHI_PM_SYS_ERR_PROCESS, - MHI_PM_POR | MHI_PM_SHUTDOWN_PROCESS | + MHI_PM_POR | MHI_PM_SYS_ERR_FAIL | MHI_PM_SHUTDOWN_PROCESS | + MHI_PM_LD_ERR_FATAL_DETECT + }, + { + MHI_PM_SYS_ERR_FAIL, + MHI_PM_SYS_ERR_DETECT | MHI_PM_SHUTDOWN_PROCESS | MHI_PM_LD_ERR_FATAL_DETECT }, /* L2 States */ @@ -629,7 +637,13 @@ static void mhi_pm_sys_error_transition(struct mhi_controller *mhi_cntrl) !in_reset, timeout); if (!ret || in_reset) { dev_err(dev, "Device failed to exit MHI Reset state\n"); - goto exit_sys_error_transition; + write_lock_irq(&mhi_cntrl->pm_lock); + cur_state = mhi_tryset_pm_state(mhi_cntrl, + MHI_PM_SYS_ERR_FAIL); + write_unlock_irq(&mhi_cntrl->pm_lock); + /* Shutdown may have occurred, otherwise cleanup now */ + if (cur_state != MHI_PM_SYS_ERR_FAIL) + goto exit_sys_error_transition; } /* diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index a5e07270e0d41..2637ad08deec1 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -282,7 +282,7 @@ static bool debug; /* default compatibility mode */ static bool autoclose=1; static bool autoeject; -static bool lockdoor = 1; +static bool lockdoor = 0; /* will we ever get to use this... sigh. */ static bool check_media_type; /* automatically restart mrw format */ diff --git a/drivers/char/hw_random/stm32-rng.c b/drivers/char/hw_random/stm32-rng.c index 379bc245c5202..0e903d6e22e30 100644 --- a/drivers/char/hw_random/stm32-rng.c +++ b/drivers/char/hw_random/stm32-rng.c @@ -220,7 +220,8 @@ static int stm32_rng_read(struct hwrng *rng, void *data, size_t max, bool wait) if (err && i > RNG_NB_RECOVER_TRIES) { dev_err((struct device *)priv->rng.priv, "Couldn't recover from seed error\n"); - return -ENOTRECOVERABLE; + retval = -ENOTRECOVERABLE; + goto exit_rpm; } continue; @@ -238,7 +239,8 @@ static int stm32_rng_read(struct hwrng *rng, void *data, size_t max, bool wait) if (err && i > RNG_NB_RECOVER_TRIES) { dev_err((struct device *)priv->rng.priv, "Couldn't recover from seed error"); - return -ENOTRECOVERABLE; + retval = -ENOTRECOVERABLE; + goto exit_rpm; } continue; @@ -250,6 +252,7 @@ static int stm32_rng_read(struct hwrng *rng, void *data, size_t max, bool wait) max -= sizeof(u32); } +exit_rpm: pm_runtime_mark_last_busy((struct device *) priv->rng.priv); pm_runtime_put_sync_autosuspend((struct device *) priv->rng.priv); @@ -353,13 +356,15 @@ static int stm32_rng_init(struct hwrng *rng) err = readl_relaxed_poll_timeout_atomic(priv->base + RNG_SR, reg, reg & RNG_SR_DRDY, 10, 100000); - if (err | (reg & ~RNG_SR_DRDY)) { + if (err || (reg & ~RNG_SR_DRDY)) { clk_disable_unprepare(priv->clk); dev_err((struct device *)priv->rng.priv, "%s: timeout:%x SR: %x!\n", __func__, err, reg); return -EINVAL; } + clk_disable_unprepare(priv->clk); + return 0; } @@ -384,6 +389,11 @@ static int __maybe_unused stm32_rng_runtime_suspend(struct device *dev) static int __maybe_unused stm32_rng_suspend(struct device *dev) { struct stm32_rng_private *priv = dev_get_drvdata(dev); + int err; + + err = clk_prepare_enable(priv->clk); + if (err) + return err; if (priv->data->has_cond_reset) { priv->pm_conf.nscr = readl_relaxed(priv->base + RNG_NSCR); @@ -465,6 +475,8 @@ static int __maybe_unused stm32_rng_resume(struct device *dev) writel_relaxed(reg, priv->base + RNG_CR); } + clk_disable_unprepare(priv->clk); + return 0; } diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c index ee951b265213f..58e9dcc2a3087 100644 --- a/drivers/char/ppdev.c +++ b/drivers/char/ppdev.c @@ -296,28 +296,35 @@ static int register_device(int minor, struct pp_struct *pp) if (!port) { pr_warn("%s: no associated port!\n", name); rc = -ENXIO; - goto err; + goto err_free_name; } index = ida_alloc(&ida_index, GFP_KERNEL); + if (index < 0) { + pr_warn("%s: failed to get index!\n", name); + rc = index; + goto err_put_port; + } + memset(&ppdev_cb, 0, sizeof(ppdev_cb)); ppdev_cb.irq_func = pp_irq; ppdev_cb.flags = (pp->flags & PP_EXCL) ? PARPORT_FLAG_EXCL : 0; ppdev_cb.private = pp; pdev = parport_register_dev_model(port, name, &ppdev_cb, index); - parport_put_port(port); if (!pdev) { pr_warn("%s: failed to register device!\n", name); rc = -ENXIO; ida_free(&ida_index, index); - goto err; + goto err_put_port; } pp->pdev = pdev; pp->index = index; dev_dbg(&pdev->dev, "registered pardevice\n"); -err: +err_put_port: + parport_put_port(port); +err_free_name: kfree(name); return rc; } diff --git a/drivers/char/random.c b/drivers/char/random.c index 456be28ba67cb..2597cb43f4387 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -702,7 +702,7 @@ static void extract_entropy(void *buf, size_t len) static void __cold _credit_init_bits(size_t bits) { - static struct execute_work set_ready; + static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; @@ -718,8 +718,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - if (static_key_initialized) - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized && system_unbound_wq) + queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); @@ -890,8 +890,8 @@ void __init random_init(void) /* * If we were initialized by the cpu or bootloader before jump labels - * are initialized, then we should enable the static branch here, where - * it's guaranteed that jump labels have been initialized. + * or workqueues are initialized, then we should enable the static + * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 1b350412d8a6b..f6aa0dfadb93e 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -919,8 +919,6 @@ static int tpm_tis_probe_irq_single(struct tpm_chip *chip, u32 intmask, int rc; u32 int_status; - INIT_WORK(&priv->free_irq_work, tpm_tis_free_irq_func); - rc = devm_request_threaded_irq(chip->dev.parent, irq, NULL, tis_int_handler, IRQF_ONESHOT | flags, dev_name(&chip->dev), chip); @@ -1022,7 +1020,8 @@ void tpm_tis_remove(struct tpm_chip *chip) interrupt = 0; tpm_tis_write32(priv, reg, ~TPM_GLOBAL_INT_ENABLE & interrupt); - flush_work(&priv->free_irq_work); + if (priv->free_irq_work.func) + flush_work(&priv->free_irq_work); tpm_tis_clkrun_enable(chip, false); @@ -1132,6 +1131,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, priv->phy_ops = phy_ops; priv->locality_count = 0; mutex_init(&priv->locality_count_mutex); + INIT_WORK(&priv->free_irq_work, tpm_tis_free_irq_func); dev_set_drvdata(&chip->dev, priv); diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c index c5c3197ee29f0..4bdad9e3667fa 100644 --- a/drivers/char/tpm/tpm_tis_spi_main.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c @@ -37,6 +37,7 @@ #include "tpm_tis_spi.h" #define MAX_SPI_FRAMESIZE 64 +#define SPI_HDRSIZE 4 /* * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short, @@ -247,7 +248,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr, int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, int irq, const struct tpm_tis_phy_ops *phy_ops) { - phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL); + phy->iobuf = devm_kmalloc(&spi->dev, SPI_HDRSIZE + MAX_SPI_FRAMESIZE, GFP_KERNEL); if (!phy->iobuf) return -ENOMEM; diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c index 019cf6079cecd..6d2eadefd9dc9 100644 --- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c +++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c @@ -639,8 +639,8 @@ static int hwicap_setup(struct platform_device *pdev, int id, dev_set_drvdata(dev, (void *)drvdata); drvdata->base_address = devm_platform_ioremap_resource(pdev, 0); - if (!drvdata->base_address) { - retval = -ENODEV; + if (IS_ERR(drvdata->base_address)) { + retval = PTR_ERR(drvdata->base_address); goto failed; } diff --git a/drivers/clk/bcm/clk-bcm2711-dvp.c b/drivers/clk/bcm/clk-bcm2711-dvp.c index e4fbbf3c40fe2..3cb235df9d379 100644 --- a/drivers/clk/bcm/clk-bcm2711-dvp.c +++ b/drivers/clk/bcm/clk-bcm2711-dvp.c @@ -56,6 +56,8 @@ static int clk_dvp_probe(struct platform_device *pdev) if (ret) return ret; + data->num = NR_CLOCKS; + data->hws[0] = clk_hw_register_gate_parent_data(&pdev->dev, "hdmi0-108MHz", &clk_dvp_parent, 0, @@ -76,7 +78,6 @@ static int clk_dvp_probe(struct platform_device *pdev) goto unregister_clk0; } - data->num = NR_CLOCKS; ret = of_clk_add_hw_provider(pdev->dev.of_node, of_clk_hw_onecell_get, data); if (ret) diff --git a/drivers/clk/bcm/clk-raspberrypi.c b/drivers/clk/bcm/clk-raspberrypi.c index 829406dc44a20..4d411408e4afe 100644 --- a/drivers/clk/bcm/clk-raspberrypi.c +++ b/drivers/clk/bcm/clk-raspberrypi.c @@ -371,8 +371,8 @@ static int raspberrypi_discover_clocks(struct raspberrypi_clk *rpi, if (IS_ERR(hw)) return PTR_ERR(hw); - data->hws[clks->id] = hw; data->num = clks->id + 1; + data->hws[clks->id] = hw; } clks++; diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c index 53e21ac302e6d..4c3a5e4eb77ac 100644 --- a/drivers/clk/clk-renesas-pcie.c +++ b/drivers/clk/clk-renesas-pcie.c @@ -25,10 +25,12 @@ #define RS9_REG_SS_AMP_0V7 0x1 #define RS9_REG_SS_AMP_0V8 0x2 #define RS9_REG_SS_AMP_0V9 0x3 +#define RS9_REG_SS_AMP_DEFAULT RS9_REG_SS_AMP_0V8 #define RS9_REG_SS_AMP_MASK 0x3 #define RS9_REG_SS_SSC_100 0 #define RS9_REG_SS_SSC_M025 (1 << 3) #define RS9_REG_SS_SSC_M050 (3 << 3) +#define RS9_REG_SS_SSC_DEFAULT RS9_REG_SS_SSC_100 #define RS9_REG_SS_SSC_MASK (3 << 3) #define RS9_REG_SS_SSC_LOCK BIT(5) #define RS9_REG_SR 0x2 @@ -205,8 +207,8 @@ static int rs9_get_common_config(struct rs9_driver_data *rs9) int ret; /* Set defaults */ - rs9->pll_amplitude = RS9_REG_SS_AMP_0V7; - rs9->pll_ssc = RS9_REG_SS_SSC_100; + rs9->pll_amplitude = RS9_REG_SS_AMP_DEFAULT; + rs9->pll_ssc = RS9_REG_SS_SSC_DEFAULT; /* Output clock amplitude */ ret = of_property_read_u32(np, "renesas,out-amplitude-microvolt", @@ -247,13 +249,13 @@ static void rs9_update_config(struct rs9_driver_data *rs9) int i; /* If amplitude is non-default, update it. */ - if (rs9->pll_amplitude != RS9_REG_SS_AMP_0V7) { + if (rs9->pll_amplitude != RS9_REG_SS_AMP_DEFAULT) { regmap_update_bits(rs9->regmap, RS9_REG_SS, RS9_REG_SS_AMP_MASK, rs9->pll_amplitude); } /* If SSC is non-default, update it. */ - if (rs9->pll_ssc != RS9_REG_SS_SSC_100) { + if (rs9->pll_ssc != RS9_REG_SS_SSC_DEFAULT) { regmap_update_bits(rs9->regmap, RS9_REG_SS, RS9_REG_SS_SSC_MASK, rs9->pll_ssc); } diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 2253c154a8248..8cca52be993f4 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -37,6 +37,10 @@ static HLIST_HEAD(clk_root_list); static HLIST_HEAD(clk_orphan_list); static LIST_HEAD(clk_notifier_list); +/* List of registered clks that use runtime PM */ +static HLIST_HEAD(clk_rpm_list); +static DEFINE_MUTEX(clk_rpm_list_lock); + static const struct hlist_head *all_lists[] = { &clk_root_list, &clk_orphan_list, @@ -59,6 +63,7 @@ struct clk_core { struct clk_hw *hw; struct module *owner; struct device *dev; + struct hlist_node rpm_node; struct device_node *of_node; struct clk_core *parent; struct clk_parent_map *parents; @@ -122,6 +127,89 @@ static void clk_pm_runtime_put(struct clk_core *core) pm_runtime_put_sync(core->dev); } +/** + * clk_pm_runtime_get_all() - Runtime "get" all clk provider devices + * + * Call clk_pm_runtime_get() on all runtime PM enabled clks in the clk tree so + * that disabling unused clks avoids a deadlock where a device is runtime PM + * resuming/suspending and the runtime PM callback is trying to grab the + * prepare_lock for something like clk_prepare_enable() while + * clk_disable_unused_subtree() holds the prepare_lock and is trying to runtime + * PM resume/suspend the device as well. + * + * Context: Acquires the 'clk_rpm_list_lock' and returns with the lock held on + * success. Otherwise the lock is released on failure. + * + * Return: 0 on success, negative errno otherwise. + */ +static int clk_pm_runtime_get_all(void) +{ + int ret; + struct clk_core *core, *failed; + + /* + * Grab the list lock to prevent any new clks from being registered + * or unregistered until clk_pm_runtime_put_all(). + */ + mutex_lock(&clk_rpm_list_lock); + + /* + * Runtime PM "get" all the devices that are needed for the clks + * currently registered. Do this without holding the prepare_lock, to + * avoid the deadlock. + */ + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + ret = clk_pm_runtime_get(core); + if (ret) { + failed = core; + pr_err("clk: Failed to runtime PM get '%s' for clk '%s'\n", + dev_name(failed->dev), failed->name); + goto err; + } + } + + return 0; + +err: + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + if (core == failed) + break; + + clk_pm_runtime_put(core); + } + mutex_unlock(&clk_rpm_list_lock); + + return ret; +} + +/** + * clk_pm_runtime_put_all() - Runtime "put" all clk provider devices + * + * Put the runtime PM references taken in clk_pm_runtime_get_all() and release + * the 'clk_rpm_list_lock'. + */ +static void clk_pm_runtime_put_all(void) +{ + struct clk_core *core; + + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) + clk_pm_runtime_put(core); + mutex_unlock(&clk_rpm_list_lock); +} + +static void clk_pm_runtime_init(struct clk_core *core) +{ + struct device *dev = core->dev; + + if (dev && pm_runtime_enabled(dev)) { + core->rpm_enabled = true; + + mutex_lock(&clk_rpm_list_lock); + hlist_add_head(&core->rpm_node, &clk_rpm_list); + mutex_unlock(&clk_rpm_list_lock); + } +} + /*** locking ***/ static void clk_prepare_lock(void) { @@ -418,6 +506,9 @@ static struct clk_core *clk_core_get(struct clk_core *core, u8 p_index) if (IS_ERR(hw)) return ERR_CAST(hw); + if (!hw) + return NULL; + return hw->core; } @@ -939,6 +1030,25 @@ int clk_rate_exclusive_get(struct clk *clk) } EXPORT_SYMBOL_GPL(clk_rate_exclusive_get); +static void devm_clk_rate_exclusive_put(void *data) +{ + struct clk *clk = data; + + clk_rate_exclusive_put(clk); +} + +int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk) +{ + int ret; + + ret = clk_rate_exclusive_get(clk); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, devm_clk_rate_exclusive_put, clk); +} +EXPORT_SYMBOL_GPL(devm_clk_rate_exclusive_get); + static void clk_core_unprepare(struct clk_core *core) { lockdep_assert_held(&prepare_lock); @@ -1359,9 +1469,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) if (core->flags & CLK_IGNORE_UNUSED) return; - if (clk_pm_runtime_get(core)) - return; - if (clk_core_is_prepared(core)) { trace_clk_unprepare(core); if (core->ops->unprepare_unused) @@ -1370,8 +1477,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) core->ops->unprepare(core->hw); trace_clk_unprepare_complete(core); } - - clk_pm_runtime_put(core); } static void __init clk_disable_unused_subtree(struct clk_core *core) @@ -1387,9 +1492,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_prepare_enable(core->parent); - if (clk_pm_runtime_get(core)) - goto unprepare_out; - flags = clk_enable_lock(); if (core->enable_count) @@ -1414,8 +1516,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) unlock_out: clk_enable_unlock(flags); - clk_pm_runtime_put(core); -unprepare_out: if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_disable_unprepare(core->parent); } @@ -1431,6 +1531,7 @@ __setup("clk_ignore_unused", clk_ignore_unused_setup); static int __init clk_disable_unused(void) { struct clk_core *core; + int ret; if (clk_ignore_unused) { pr_warn("clk: Not disabling unused clocks\n"); @@ -1439,6 +1540,13 @@ static int __init clk_disable_unused(void) pr_info("clk: Disabling unused clocks\n"); + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; + /* + * Grab the prepare lock to keep the clk topology stable while iterating + * over clks. + */ clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) @@ -1455,6 +1563,8 @@ static int __init clk_disable_unused(void) clk_prepare_unlock(); + clk_pm_runtime_put_all(); + return 0; } late_initcall_sync(clk_disable_unused); @@ -3230,9 +3340,7 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, { struct clk_core *child; - clk_pm_runtime_get(c); clk_summary_show_one(s, c, level); - clk_pm_runtime_put(c); hlist_for_each_entry(child, &c->children, child_node) clk_summary_show_subtree(s, child, level + 1); @@ -3242,11 +3350,15 @@ static int clk_summary_show(struct seq_file *s, void *data) { struct clk_core *c; struct hlist_head **lists = s->private; + int ret; seq_puts(s, " enable prepare protect duty hardware connection\n"); seq_puts(s, " clock count count count rate accuracy phase cycle enable consumer id\n"); seq_puts(s, "---------------------------------------------------------------------------------------------------------------------------------------------\n"); + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; clk_prepare_lock(); @@ -3255,6 +3367,7 @@ static int clk_summary_show(struct seq_file *s, void *data) clk_summary_show_subtree(s, c, 0); clk_prepare_unlock(); + clk_pm_runtime_put_all(); return 0; } @@ -3302,8 +3415,14 @@ static int clk_dump_show(struct seq_file *s, void *data) struct clk_core *c; bool first_node = true; struct hlist_head **lists = s->private; + int ret; + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; seq_putc(s, '{'); + clk_prepare_lock(); for (; *lists; lists++) { @@ -3316,6 +3435,7 @@ static int clk_dump_show(struct seq_file *s, void *data) } clk_prepare_unlock(); + clk_pm_runtime_put_all(); seq_puts(s, "}\n"); return 0; @@ -3959,8 +4079,6 @@ static int __clk_core_init(struct clk_core *core) } clk_core_reparent_orphans_nolock(); - - kref_init(&core->ref); out: clk_pm_runtime_put(core); unlock: @@ -4189,6 +4307,22 @@ static void clk_core_free_parent_map(struct clk_core *core) kfree(core->parents); } +/* Free memory allocated for a struct clk_core */ +static void __clk_release(struct kref *ref) +{ + struct clk_core *core = container_of(ref, struct clk_core, ref); + + if (core->rpm_enabled) { + mutex_lock(&clk_rpm_list_lock); + hlist_del(&core->rpm_node); + mutex_unlock(&clk_rpm_list_lock); + } + + clk_core_free_parent_map(core); + kfree_const(core->name); + kfree(core); +} + static struct clk * __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) { @@ -4209,6 +4343,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_out; } + kref_init(&core->ref); + core->name = kstrdup_const(init->name, GFP_KERNEL); if (!core->name) { ret = -ENOMEM; @@ -4221,9 +4357,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) } core->ops = init->ops; - if (dev && pm_runtime_enabled(dev)) - core->rpm_enabled = true; core->dev = dev; + clk_pm_runtime_init(core); core->of_node = np; if (dev && dev->driver) core->owner = dev->driver->owner; @@ -4263,12 +4398,10 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) hw->clk = NULL; fail_create_clk: - clk_core_free_parent_map(core); fail_parents: fail_ops: - kfree_const(core->name); fail_name: - kfree(core); + kref_put(&core->ref, __clk_release); fail_out: return ERR_PTR(ret); } @@ -4348,18 +4481,6 @@ int of_clk_hw_register(struct device_node *node, struct clk_hw *hw) } EXPORT_SYMBOL_GPL(of_clk_hw_register); -/* Free memory allocated for a clock. */ -static void __clk_release(struct kref *ref) -{ - struct clk_core *core = container_of(ref, struct clk_core, ref); - - lockdep_assert_held(&prepare_lock); - - clk_core_free_parent_map(core); - kfree_const(core->name); - kfree(core); -} - /* * Empty clk_ops for unregistered clocks. These are used temporarily * after clk_unregister() was called on a clock and until last clock @@ -4450,7 +4571,8 @@ void clk_unregister(struct clk *clk) if (ops == &clk_nodrv_ops) { pr_err("%s: unregistered clock: %s\n", __func__, clk->core->name); - goto unlock; + clk_prepare_unlock(); + return; } /* * Assign empty clock ops for consumers that might still hold @@ -4484,11 +4606,10 @@ void clk_unregister(struct clk *clk) if (clk->core->protect_count) pr_warn("%s: unregistering protected clock: %s\n", __func__, clk->core->name); + clk_prepare_unlock(); kref_put(&clk->core->ref, __clk_release); free_clk(clk); -unlock: - clk_prepare_unlock(); } EXPORT_SYMBOL_GPL(clk_unregister); @@ -4647,13 +4768,11 @@ void __clk_put(struct clk *clk) if (clk->min_rate > 0 || clk->max_rate < ULONG_MAX) clk_set_rate_range_nolock(clk, 0, ULONG_MAX); - owner = clk->core->owner; - kref_put(&clk->core->ref, __clk_release); - clk_prepare_unlock(); + owner = clk->core->owner; + kref_put(&clk->core->ref, __clk_release); module_put(owner); - free_clk(clk); } diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c index ee37d0be6877d..9cd80522ca2d7 100644 --- a/drivers/clk/clkdev.c +++ b/drivers/clk/clkdev.c @@ -144,7 +144,7 @@ void clkdev_add_table(struct clk_lookup *cl, size_t num) mutex_unlock(&clocks_mutex); } -#define MAX_DEV_ID 20 +#define MAX_DEV_ID 24 #define MAX_CON_ID 16 struct clk_lookup_alloc { diff --git a/drivers/clk/hisilicon/clk-hi3519.c b/drivers/clk/hisilicon/clk-hi3519.c index b871872d9960d..141b727ff60d6 100644 --- a/drivers/clk/hisilicon/clk-hi3519.c +++ b/drivers/clk/hisilicon/clk-hi3519.c @@ -130,7 +130,7 @@ static void hi3519_clk_unregister(struct platform_device *pdev) of_clk_del_provider(pdev->dev.of_node); hisi_clk_unregister_gate(hi3519_gate_clks, - ARRAY_SIZE(hi3519_mux_clks), + ARRAY_SIZE(hi3519_gate_clks), crg->clk_data); hisi_clk_unregister_mux(hi3519_mux_clks, ARRAY_SIZE(hi3519_mux_clks), diff --git a/drivers/clk/hisilicon/clk-hi3559a.c b/drivers/clk/hisilicon/clk-hi3559a.c index ff4ca0edce06a..4623befafaec4 100644 --- a/drivers/clk/hisilicon/clk-hi3559a.c +++ b/drivers/clk/hisilicon/clk-hi3559a.c @@ -491,7 +491,6 @@ static void hisi_clk_register_pll(struct hi3559av100_pll_clock *clks, clk = clk_register(NULL, &p_clk->hw); if (IS_ERR(clk)) { - devm_kfree(dev, p_clk); dev_err(dev, "%s: failed to register clock %s\n", __func__, clks[i].name); continue; diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c index e4300df88f1ac..55ed211a5e0b1 100644 --- a/drivers/clk/imx/clk-imx8mp-audiomix.c +++ b/drivers/clk/imx/clk-imx8mp-audiomix.c @@ -18,7 +18,12 @@ #define CLKEN0 0x000 #define CLKEN1 0x004 -#define SAI_MCLK_SEL(n) (0x300 + 4 * (n)) /* n in 0..5 */ +#define SAI1_MCLK_SEL 0x300 +#define SAI2_MCLK_SEL 0x304 +#define SAI3_MCLK_SEL 0x308 +#define SAI5_MCLK_SEL 0x30C +#define SAI6_MCLK_SEL 0x310 +#define SAI7_MCLK_SEL 0x314 #define PDM_SEL 0x318 #define SAI_PLL_GNRL_CTL 0x400 @@ -95,13 +100,13 @@ static const struct clk_parent_data clk_imx8mp_audiomix_pll_bypass_sels[] = { IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK1_SEL, {}, \ clk_imx8mp_audiomix_sai##n##_mclk1_parents, \ ARRAY_SIZE(clk_imx8mp_audiomix_sai##n##_mclk1_parents), \ - SAI_MCLK_SEL(n), 1, 0 \ + SAI##n##_MCLK_SEL, 1, 0 \ }, { \ "sai"__stringify(n)"_mclk2_sel", \ IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK2_SEL, {}, \ clk_imx8mp_audiomix_sai_mclk2_parents, \ ARRAY_SIZE(clk_imx8mp_audiomix_sai_mclk2_parents), \ - SAI_MCLK_SEL(n), 4, 1 \ + SAI##n##_MCLK_SEL, 4, 1 \ }, { \ "sai"__stringify(n)"_ipg_cg", \ IMX8MP_CLK_AUDIOMIX_SAI##n##_IPG, \ diff --git a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c index 9cffd278e9a43..1b8f859b6b6cc 100644 --- a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c @@ -127,7 +127,6 @@ static void clk_mt7622_apmixed_remove(struct platform_device *pdev) of_clk_del_provider(node); mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); - mtk_free_clk_data(clk_data); } static const struct of_device_id of_match_clk_mt7622_apmixed[] = { diff --git a/drivers/clk/mediatek/clk-mt7981-topckgen.c b/drivers/clk/mediatek/clk-mt7981-topckgen.c index 682f4ca9e89ad..493aa11d3a175 100644 --- a/drivers/clk/mediatek/clk-mt7981-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7981-topckgen.c @@ -357,8 +357,9 @@ static const struct mtk_mux top_muxes[] = { MUX_GATE_CLR_SET_UPD(CLK_TOP_SGM_325M_SEL, "sgm_325m_sel", sgm_325m_parents, 0x050, 0x054, 0x058, 8, 1, 15, 0x1C0, 21), - MUX_GATE_CLR_SET_UPD(CLK_TOP_SGM_REG_SEL, "sgm_reg_sel", sgm_reg_parents, - 0x050, 0x054, 0x058, 16, 1, 23, 0x1C0, 22), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_SGM_REG_SEL, "sgm_reg_sel", sgm_reg_parents, + 0x050, 0x054, 0x058, 16, 1, 23, 0x1C0, 22, + CLK_IS_CRITICAL | CLK_SET_RATE_PARENT), MUX_GATE_CLR_SET_UPD(CLK_TOP_EIP97B_SEL, "eip97b_sel", eip97b_parents, 0x050, 0x054, 0x058, 24, 3, 31, 0x1C0, 23), /* CLK_CFG_6 */ diff --git a/drivers/clk/mediatek/clk-mt7988-infracfg.c b/drivers/clk/mediatek/clk-mt7988-infracfg.c index 8011ef278bea3..df02997c6b7c9 100644 --- a/drivers/clk/mediatek/clk-mt7988-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7988-infracfg.c @@ -152,7 +152,7 @@ static const struct mtk_gate infra_clks[] = { GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P1, "infra_pcie_peri_ck_26m_ck_p1", "csw_infra_f26m_sel", 8), GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P2, "infra_pcie_peri_ck_26m_ck_p2", - "csw_infra_f26m_sel", 9), + "infra_pcie_peri_ck_26m_ck_p3", 9), GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P3, "infra_pcie_peri_ck_26m_ck_p3", "csw_infra_f26m_sel", 10), /* INFRA1 */ diff --git a/drivers/clk/mediatek/clk-mt8135-apmixedsys.c b/drivers/clk/mediatek/clk-mt8135-apmixedsys.c index d1239b4b3db74..41bb2d2e2ea74 100644 --- a/drivers/clk/mediatek/clk-mt8135-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8135-apmixedsys.c @@ -59,7 +59,7 @@ static int clk_mt8135_apmixed_probe(struct platform_device *pdev) ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); if (ret) - return ret; + goto free_clk_data; ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (ret) @@ -69,6 +69,8 @@ static int clk_mt8135_apmixed_probe(struct platform_device *pdev) unregister_plls: mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); +free_clk_data: + mtk_free_clk_data(clk_data); return ret; } diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 6e23461a04559..934d5a15acfc5 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -790,7 +790,7 @@ static const struct mtk_gate infra_clks[] = { /* infra_sspm_26m_self is main clock in co-processor, should not be closed in Linux. */ GATE_INFRA3_FLAGS(CLK_INFRA_SSPM_26M_SELF, "infra_sspm_26m_self", "f_f26m_ck", 3, CLK_IS_CRITICAL), /* infra_sspm_32k_self is main clock in co-processor, should not be closed in Linux. */ - GATE_INFRA3_FLAGS(CLK_INFRA_SSPM_32K_SELF, "infra_sspm_32k_self", "f_f26m_ck", 4, CLK_IS_CRITICAL), + GATE_INFRA3_FLAGS(CLK_INFRA_SSPM_32K_SELF, "infra_sspm_32k_self", "clk32k", 4, CLK_IS_CRITICAL), GATE_INFRA3(CLK_INFRA_UFS_AXI, "infra_ufs_axi", "axi_sel", 5), GATE_INFRA3(CLK_INFRA_I2C6, "infra_i2c6", "i2c_sel", 6), GATE_INFRA3(CLK_INFRA_AP_MSDC0, "infra_ap_msdc0", "msdc50_hclk_sel", 7), diff --git a/drivers/clk/mediatek/clk-mt8365-mm.c b/drivers/clk/mediatek/clk-mt8365-mm.c index 01a2ef8f594ef..3f62ec7507336 100644 --- a/drivers/clk/mediatek/clk-mt8365-mm.c +++ b/drivers/clk/mediatek/clk-mt8365-mm.c @@ -53,7 +53,7 @@ static const struct mtk_gate mm_clks[] = { GATE_MM0(CLK_MM_MM_DSI0, "mm_dsi0", "mm_sel", 17), GATE_MM0(CLK_MM_MM_DISP_RDMA1, "mm_disp_rdma1", "mm_sel", 18), GATE_MM0(CLK_MM_MM_MDP_RDMA1, "mm_mdp_rdma1", "mm_sel", 19), - GATE_MM0(CLK_MM_DPI0_DPI0, "mm_dpi0_dpi0", "vpll_dpix", 20), + GATE_MM0(CLK_MM_DPI0_DPI0, "mm_dpi0_dpi0", "dpi0_sel", 20), GATE_MM0(CLK_MM_MM_FAKE, "mm_fake", "mm_sel", 21), GATE_MM0(CLK_MM_MM_SMI_COMMON, "mm_smi_common", "mm_sel", 22), GATE_MM0(CLK_MM_MM_SMI_LARB0, "mm_smi_larb0", "mm_sel", 23), diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index 2e55368dc4d82..bd37ab4d1a9bb 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "clk-mtk.h" @@ -494,6 +495,16 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, return IS_ERR(base) ? PTR_ERR(base) : -ENOMEM; } + + devm_pm_runtime_enable(&pdev->dev); + /* + * Do a pm_runtime_resume_and_get() to workaround a possible + * deadlock between clk_register() and the genpd framework. + */ + r = pm_runtime_resume_and_get(&pdev->dev); + if (r) + return r; + /* Calculate how many clk_hw_onecell_data entries to allocate */ num_clks = mcd->num_clks + mcd->num_composite_clks; num_clks += mcd->num_fixed_clks + mcd->num_factor_clks; @@ -574,6 +585,8 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, goto unregister_clks; } + pm_runtime_put(&pdev->dev); + return r; unregister_clks: @@ -604,6 +617,8 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, free_base: if (mcd->shared_io && base) iounmap(base); + + pm_runtime_put(&pdev->dev); return r; } diff --git a/drivers/clk/mediatek/clk-pllfh.c b/drivers/clk/mediatek/clk-pllfh.c index 3a2b3f90be25d..094ec8a26d668 100644 --- a/drivers/clk/mediatek/clk-pllfh.c +++ b/drivers/clk/mediatek/clk-pllfh.c @@ -68,7 +68,7 @@ void fhctl_parse_dt(const u8 *compatible_node, struct mtk_pllfh_data *pllfhs, node = of_find_compatible_node(NULL, NULL, compatible_node); if (!node) { - pr_err("cannot find \"%s\"\n", compatible_node); + pr_warn("cannot find \"%s\"\n", compatible_node); return; } diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c index c12f81dfa6745..5f60f2bcca592 100644 --- a/drivers/clk/meson/axg.c +++ b/drivers/clk/meson/axg.c @@ -2142,7 +2142,9 @@ static struct clk_regmap *const axg_clk_regmaps[] = { &axg_vclk_input, &axg_vclk2_input, &axg_vclk_div, + &axg_vclk_div1, &axg_vclk2_div, + &axg_vclk2_div1, &axg_vclk_div2_en, &axg_vclk_div4_en, &axg_vclk_div6_en, diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 2a9da0939377a..be35803c7a4bf 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -439,6 +439,7 @@ config SC_CAMCC_7280 config SC_CAMCC_8280XP tristate "SC8280XP Camera Clock Controller" + depends on ARM64 || COMPILE_TEST select SC_GCC_8280XP help Support for the camera clock controller on Qualcomm Technologies, Inc @@ -1069,6 +1070,7 @@ config SM_GPUCC_8550 config SM_GPUCC_8650 tristate "SM8650 Graphics Clock Controller" + depends on ARM64 || COMPILE_TEST select SM_GCC_8650 help Support for the graphics clock controller on SM8650 devices. diff --git a/drivers/clk/qcom/apss-ipq-pll.c b/drivers/clk/qcom/apss-ipq-pll.c index 678b805f13d45..d7ab5bd5d4b41 100644 --- a/drivers/clk/qcom/apss-ipq-pll.c +++ b/drivers/clk/qcom/apss-ipq-pll.c @@ -55,6 +55,29 @@ static struct clk_alpha_pll ipq_pll_huayra = { }, }; +static struct clk_alpha_pll ipq_pll_stromer = { + .offset = 0x0, + /* + * Reuse CLK_ALPHA_PLL_TYPE_STROMER_PLUS register offsets. + * Although this is a bit confusing, but the offset values + * are correct nevertheless. + */ + .regs = ipq_pll_offsets[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], + .flags = SUPPORTS_DYNAMIC_UPDATE, + .clkr = { + .enable_reg = 0x0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "a53pll", + .parent_data = &(const struct clk_parent_data) { + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_stromer_ops, + }, + }, +}; + static struct clk_alpha_pll ipq_pll_stromer_plus = { .offset = 0x0, .regs = ipq_pll_offsets[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], @@ -73,8 +96,9 @@ static struct clk_alpha_pll ipq_pll_stromer_plus = { }, }; +/* 1.008 GHz configuration */ static const struct alpha_pll_config ipq5018_pll_config = { - .l = 0x32, + .l = 0x2a, .config_ctl_val = 0x4001075b, .config_ctl_hi_val = 0x304, .main_output_mask = BIT(0), @@ -144,8 +168,8 @@ struct apss_pll_data { }; static const struct apss_pll_data ipq5018_pll_data = { - .pll_type = CLK_ALPHA_PLL_TYPE_STROMER_PLUS, - .pll = &ipq_pll_stromer_plus, + .pll_type = CLK_ALPHA_PLL_TYPE_STROMER, + .pll = &ipq_pll_stromer, .pll_config = &ipq5018_pll_config, }; @@ -203,7 +227,8 @@ static int apss_ipq_pll_probe(struct platform_device *pdev) if (data->pll_type == CLK_ALPHA_PLL_TYPE_HUAYRA) clk_alpha_pll_configure(data->pll, regmap, data->pll_config); - else if (data->pll_type == CLK_ALPHA_PLL_TYPE_STROMER_PLUS) + else if (data->pll_type == CLK_ALPHA_PLL_TYPE_STROMER || + data->pll_type == CLK_ALPHA_PLL_TYPE_STROMER_PLUS) clk_stromer_pll_configure(data->pll, regmap, data->pll_config); ret = devm_clk_register_regmap(dev, &data->pll->clkr); diff --git a/drivers/clk/qcom/camcc-sc8280xp.c b/drivers/clk/qcom/camcc-sc8280xp.c index 3dcd79b015151..7f0ae9a5f28b2 100644 --- a/drivers/clk/qcom/camcc-sc8280xp.c +++ b/drivers/clk/qcom/camcc-sc8280xp.c @@ -630,6 +630,7 @@ static const struct freq_tbl ftbl_camcc_bps_clk_src[] = { F(480000000, P_CAMCC_PLL7_OUT_EVEN, 1, 0, 0), F(600000000, P_CAMCC_PLL0_OUT_MAIN, 2, 0, 0), F(760000000, P_CAMCC_PLL3_OUT_EVEN, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_bps_clk_src = { @@ -654,6 +655,7 @@ static const struct freq_tbl ftbl_camcc_camnoc_axi_clk_src[] = { F(320000000, P_CAMCC_PLL7_OUT_ODD, 1, 0, 0), F(400000000, P_CAMCC_PLL0_OUT_ODD, 1, 0, 0), F(480000000, P_CAMCC_PLL7_OUT_EVEN, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_camnoc_axi_clk_src = { @@ -673,6 +675,7 @@ static struct clk_rcg2 camcc_camnoc_axi_clk_src = { static const struct freq_tbl ftbl_camcc_cci_0_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), F(37500000, P_CAMCC_PLL0_OUT_EVEN, 16, 0, 0), + { } }; static struct clk_rcg2 camcc_cci_0_clk_src = { @@ -735,6 +738,7 @@ static const struct freq_tbl ftbl_camcc_cphy_rx_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), F(240000000, P_CAMCC_PLL0_OUT_EVEN, 2.5, 0, 0), F(400000000, P_CAMCC_PLL0_OUT_ODD, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_cphy_rx_clk_src = { @@ -754,6 +758,7 @@ static struct clk_rcg2 camcc_cphy_rx_clk_src = { static const struct freq_tbl ftbl_camcc_csi0phytimer_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), F(300000000, P_CAMCC_PLL0_OUT_EVEN, 2, 0, 0), + { } }; static struct clk_rcg2 camcc_csi0phytimer_clk_src = { @@ -818,6 +823,7 @@ static const struct freq_tbl ftbl_camcc_fast_ahb_clk_src[] = { F(200000000, P_CAMCC_PLL0_OUT_EVEN, 3, 0, 0), F(300000000, P_CAMCC_PLL0_OUT_MAIN, 4, 0, 0), F(400000000, P_CAMCC_PLL0_OUT_MAIN, 3, 0, 0), + { } }; static struct clk_rcg2 camcc_fast_ahb_clk_src = { @@ -838,6 +844,7 @@ static const struct freq_tbl ftbl_camcc_icp_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), F(400000000, P_CAMCC_PLL0_OUT_ODD, 1, 0, 0), F(600000000, P_CAMCC_PLL0_OUT_MAIN, 2, 0, 0), + { } }; static struct clk_rcg2 camcc_icp_clk_src = { @@ -860,6 +867,7 @@ static const struct freq_tbl ftbl_camcc_ife_0_clk_src[] = { F(558000000, P_CAMCC_PLL3_OUT_EVEN, 1, 0, 0), F(637000000, P_CAMCC_PLL3_OUT_EVEN, 1, 0, 0), F(760000000, P_CAMCC_PLL3_OUT_EVEN, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_ife_0_clk_src = { @@ -883,6 +891,7 @@ static const struct freq_tbl ftbl_camcc_ife_0_csid_clk_src[] = { F(400000000, P_CAMCC_PLL0_OUT_ODD, 1, 0, 0), F(480000000, P_CAMCC_PLL7_OUT_EVEN, 1, 0, 0), F(600000000, P_CAMCC_PLL0_OUT_MAIN, 2, 0, 0), + { } }; static struct clk_rcg2 camcc_ife_0_csid_clk_src = { @@ -905,6 +914,7 @@ static const struct freq_tbl ftbl_camcc_ife_1_clk_src[] = { F(558000000, P_CAMCC_PLL4_OUT_EVEN, 1, 0, 0), F(637000000, P_CAMCC_PLL4_OUT_EVEN, 1, 0, 0), F(760000000, P_CAMCC_PLL4_OUT_EVEN, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_ife_1_clk_src = { @@ -941,6 +951,7 @@ static const struct freq_tbl ftbl_camcc_ife_2_clk_src[] = { F(558000000, P_CAMCC_PLL5_OUT_EVEN, 1, 0, 0), F(637000000, P_CAMCC_PLL5_OUT_EVEN, 1, 0, 0), F(760000000, P_CAMCC_PLL5_OUT_EVEN, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_ife_2_clk_src = { @@ -962,6 +973,7 @@ static const struct freq_tbl ftbl_camcc_ife_2_csid_clk_src[] = { F(400000000, P_CAMCC_PLL0_OUT_ODD, 1, 0, 0), F(480000000, P_CAMCC_PLL7_OUT_EVEN, 1, 0, 0), F(600000000, P_CAMCC_PLL0_OUT_MAIN, 2, 0, 0), + { } }; static struct clk_rcg2 camcc_ife_2_csid_clk_src = { @@ -984,6 +996,7 @@ static const struct freq_tbl ftbl_camcc_ife_3_clk_src[] = { F(558000000, P_CAMCC_PLL6_OUT_EVEN, 1, 0, 0), F(637000000, P_CAMCC_PLL6_OUT_EVEN, 1, 0, 0), F(760000000, P_CAMCC_PLL6_OUT_EVEN, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_ife_3_clk_src = { @@ -1020,6 +1033,7 @@ static const struct freq_tbl ftbl_camcc_ife_lite_0_clk_src[] = { F(400000000, P_CAMCC_PLL0_OUT_ODD, 1, 0, 0), F(480000000, P_CAMCC_PLL7_OUT_EVEN, 1, 0, 0), F(600000000, P_CAMCC_PLL0_OUT_MAIN, 2, 0, 0), + { } }; static struct clk_rcg2 camcc_ife_lite_0_clk_src = { @@ -1140,6 +1154,7 @@ static const struct freq_tbl ftbl_camcc_ipe_0_clk_src[] = { F(475000000, P_CAMCC_PLL1_OUT_EVEN, 1, 0, 0), F(520000000, P_CAMCC_PLL1_OUT_EVEN, 1, 0, 0), F(600000000, P_CAMCC_PLL1_OUT_EVEN, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_ipe_0_clk_src = { @@ -1163,6 +1178,7 @@ static const struct freq_tbl ftbl_camcc_jpeg_clk_src[] = { F(400000000, P_CAMCC_PLL0_OUT_ODD, 1, 0, 0), F(480000000, P_CAMCC_PLL7_OUT_EVEN, 1, 0, 0), F(600000000, P_CAMCC_PLL0_OUT_MAIN, 2, 0, 0), + { } }; static struct clk_rcg2 camcc_jpeg_clk_src = { @@ -1184,6 +1200,7 @@ static const struct freq_tbl ftbl_camcc_lrme_clk_src[] = { F(300000000, P_CAMCC_PLL0_OUT_EVEN, 2, 0, 0), F(320000000, P_CAMCC_PLL7_OUT_ODD, 1, 0, 0), F(400000000, P_CAMCC_PLL0_OUT_MAIN, 3, 0, 0), + { } }; static struct clk_rcg2 camcc_lrme_clk_src = { @@ -1204,6 +1221,7 @@ static const struct freq_tbl ftbl_camcc_mclk0_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), F(24000000, P_CAMCC_PLL2_OUT_EARLY, 10, 1, 4), F(64000000, P_CAMCC_PLL2_OUT_EARLY, 15, 0, 0), + { } }; static struct clk_rcg2 camcc_mclk0_clk_src = { @@ -1320,6 +1338,7 @@ static struct clk_rcg2 camcc_mclk7_clk_src = { static const struct freq_tbl ftbl_camcc_sleep_clk_src[] = { F(32000, P_SLEEP_CLK, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_sleep_clk_src = { @@ -1339,6 +1358,7 @@ static struct clk_rcg2 camcc_sleep_clk_src = { static const struct freq_tbl ftbl_camcc_slow_ahb_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), F(80000000, P_CAMCC_PLL7_OUT_EVEN, 6, 0, 0), + { } }; static struct clk_rcg2 camcc_slow_ahb_clk_src = { @@ -1357,6 +1377,7 @@ static struct clk_rcg2 camcc_slow_ahb_clk_src = { static const struct freq_tbl ftbl_camcc_xo_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), + { } }; static struct clk_rcg2 camcc_xo_clk_src = { diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index 05898d2a8b22c..35db45280b26d 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -212,7 +212,6 @@ const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = { [PLL_OFF_USER_CTL] = 0x18, [PLL_OFF_USER_CTL_U] = 0x1c, [PLL_OFF_CONFIG_CTL] = 0x20, - [PLL_OFF_CONFIG_CTL_U] = 0xff, [PLL_OFF_TEST_CTL] = 0x30, [PLL_OFF_TEST_CTL_U] = 0x34, [PLL_OFF_STATUS] = 0x28, @@ -2474,6 +2473,8 @@ static int clk_alpha_pll_stromer_set_rate(struct clk_hw *hw, unsigned long rate, rate = alpha_pll_round_rate(rate, prate, &l, &a, ALPHA_REG_BITWIDTH); regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l); + + a <<= ALPHA_REG_BITWIDTH - ALPHA_BITWIDTH; regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a); regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll), a >> ALPHA_BITWIDTH); diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 8602c02047d04..45c5255bcd11b 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -768,6 +768,7 @@ static struct clk_smd_rpm *msm8976_clks[] = { static const struct rpm_smd_clk_desc rpm_clk_msm8976 = { .clks = msm8976_clks, + .num_clks = ARRAY_SIZE(msm8976_clks), .icc_clks = bimc_pcnoc_snoc_smmnoc_icc_clks, .num_icc_clks = ARRAY_SIZE(bimc_pcnoc_snoc_smmnoc_icc_clks), }; diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c index 735adfefc3798..e792e0b130d33 100644 --- a/drivers/clk/qcom/dispcc-sdm845.c +++ b/drivers/clk/qcom/dispcc-sdm845.c @@ -759,6 +759,8 @@ static struct clk_branch disp_cc_mdss_vsync_clk = { static struct gdsc mdss_gdsc = { .gdscr = 0x3000, + .en_few_wait_val = 0x6, + .en_rest_wait_val = 0x5, .pd = { .name = "mdss_gdsc", }, diff --git a/drivers/clk/qcom/dispcc-sm6350.c b/drivers/clk/qcom/dispcc-sm6350.c index ea6f54ed846ec..441f042f5ea45 100644 --- a/drivers/clk/qcom/dispcc-sm6350.c +++ b/drivers/clk/qcom/dispcc-sm6350.c @@ -221,26 +221,17 @@ static struct clk_rcg2 disp_cc_mdss_dp_crypto_clk_src = { }, }; -static const struct freq_tbl ftbl_disp_cc_mdss_dp_link_clk_src[] = { - F(162000, P_DP_PHY_PLL_LINK_CLK, 1, 0, 0), - F(270000, P_DP_PHY_PLL_LINK_CLK, 1, 0, 0), - F(540000, P_DP_PHY_PLL_LINK_CLK, 1, 0, 0), - F(810000, P_DP_PHY_PLL_LINK_CLK, 1, 0, 0), - { } -}; - static struct clk_rcg2 disp_cc_mdss_dp_link_clk_src = { .cmd_rcgr = 0x10f8, .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_0, - .freq_tbl = ftbl_disp_cc_mdss_dp_link_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "disp_cc_mdss_dp_link_clk_src", .parent_data = disp_cc_parent_data_0, .num_parents = ARRAY_SIZE(disp_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; diff --git a/drivers/clk/qcom/dispcc-sm8450.c b/drivers/clk/qcom/dispcc-sm8450.c index 2c4aecd75186b..239cc726c7e29 100644 --- a/drivers/clk/qcom/dispcc-sm8450.c +++ b/drivers/clk/qcom/dispcc-sm8450.c @@ -309,26 +309,17 @@ static struct clk_rcg2 disp_cc_mdss_dptx0_aux_clk_src = { }, }; -static const struct freq_tbl ftbl_disp_cc_mdss_dptx0_link_clk_src[] = { - F(162000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(270000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(540000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(810000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - { } -}; - static struct clk_rcg2 disp_cc_mdss_dptx0_link_clk_src = { .cmd_rcgr = 0x819c, .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx0_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -382,13 +373,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx1_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -442,13 +432,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx2_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx2_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -502,13 +491,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx3_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx3_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; diff --git a/drivers/clk/qcom/dispcc-sm8550.c b/drivers/clk/qcom/dispcc-sm8550.c index f96d8b81fd9ad..c9b8c2eb5c64a 100644 --- a/drivers/clk/qcom/dispcc-sm8550.c +++ b/drivers/clk/qcom/dispcc-sm8550.c @@ -345,26 +345,17 @@ static struct clk_rcg2 disp_cc_mdss_dptx0_aux_clk_src = { }, }; -static const struct freq_tbl ftbl_disp_cc_mdss_dptx0_link_clk_src[] = { - F(162000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(270000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(540000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(810000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - { } -}; - static struct clk_rcg2 disp_cc_mdss_dptx0_link_clk_src = { .cmd_rcgr = 0x8170, .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_7, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx0_link_clk_src", .parent_data = disp_cc_parent_data_7, .num_parents = ARRAY_SIZE(disp_cc_parent_data_7), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -418,13 +409,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx1_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -478,13 +468,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx2_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx2_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -538,13 +527,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx3_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(struct clk_init_data) { .name = "disp_cc_mdss_dptx3_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; diff --git a/drivers/clk/qcom/dispcc-sm8650.c b/drivers/clk/qcom/dispcc-sm8650.c index f3b1d9d16baea..c9b139faf1a8f 100644 --- a/drivers/clk/qcom/dispcc-sm8650.c +++ b/drivers/clk/qcom/dispcc-sm8650.c @@ -343,26 +343,17 @@ static struct clk_rcg2 disp_cc_mdss_dptx0_aux_clk_src = { }, }; -static const struct freq_tbl ftbl_disp_cc_mdss_dptx0_link_clk_src[] = { - F(162000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(270000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(540000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - F(810000, P_DP0_PHY_PLL_LINK_CLK, 1, 0, 0), - { } -}; - static struct clk_rcg2 disp_cc_mdss_dptx0_link_clk_src = { .cmd_rcgr = 0x8170, .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_7, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(const struct clk_init_data) { .name = "disp_cc_mdss_dptx0_link_clk_src", .parent_data = disp_cc_parent_data_7, .num_parents = ARRAY_SIZE(disp_cc_parent_data_7), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -416,13 +407,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(const struct clk_init_data) { .name = "disp_cc_mdss_dptx1_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -476,13 +466,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx2_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(const struct clk_init_data) { .name = "disp_cc_mdss_dptx2_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; @@ -536,13 +525,12 @@ static struct clk_rcg2 disp_cc_mdss_dptx3_link_clk_src = { .mnd_width = 0, .hid_width = 5, .parent_map = disp_cc_parent_map_3, - .freq_tbl = ftbl_disp_cc_mdss_dptx0_link_clk_src, .clkr.hw.init = &(const struct clk_init_data) { .name = "disp_cc_mdss_dptx3_link_clk_src", .parent_data = disp_cc_parent_data_3, .num_parents = ARRAY_SIZE(disp_cc_parent_data_3), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_byte2_ops, }, }; diff --git a/drivers/clk/qcom/gcc-ipq5018.c b/drivers/clk/qcom/gcc-ipq5018.c index 4aba47e8700d2..c1732d70e3a23 100644 --- a/drivers/clk/qcom/gcc-ipq5018.c +++ b/drivers/clk/qcom/gcc-ipq5018.c @@ -857,6 +857,7 @@ static struct clk_rcg2 lpass_sway_clk_src = { static const struct freq_tbl ftbl_pcie0_aux_clk_src[] = { F(2000000, P_XO, 12, 0, 0), + { } }; static struct clk_rcg2 pcie0_aux_clk_src = { @@ -1099,6 +1100,7 @@ static const struct freq_tbl ftbl_qpic_io_macro_clk_src[] = { F(100000000, P_GPLL0, 8, 0, 0), F(200000000, P_GPLL0, 4, 0, 0), F(320000000, P_GPLL0, 2.5, 0, 0), + { } }; static struct clk_rcg2 qpic_io_macro_clk_src = { @@ -1194,6 +1196,7 @@ static struct clk_rcg2 ubi0_axi_clk_src = { static const struct freq_tbl ftbl_ubi0_core_clk_src[] = { F(850000000, P_UBI32_PLL, 1, 0, 0), F(1000000000, P_UBI32_PLL, 1, 0, 0), + { } }; static struct clk_rcg2 ubi0_core_clk_src = { @@ -1754,7 +1757,7 @@ static struct clk_branch gcc_gmac0_sys_clk = { .halt_check = BRANCH_HALT_DELAY, .halt_bit = 31, .clkr = { - .enable_reg = 0x683190, + .enable_reg = 0x68190, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data) { .name = "gcc_gmac0_sys_clk", @@ -2180,7 +2183,7 @@ static struct clk_branch gcc_pcie1_axi_s_clk = { }; static struct clk_branch gcc_pcie1_pipe_clk = { - .halt_reg = 8, + .halt_reg = 0x76018, .halt_check = BRANCH_HALT_DELAY, .halt_bit = 31, .clkr = { @@ -3632,7 +3635,7 @@ static const struct qcom_reset_map gcc_ipq5018_resets[] = { [GCC_SYSTEM_NOC_BCR] = { 0x26000, 0 }, [GCC_TCSR_BCR] = { 0x28000, 0 }, [GCC_TLMM_BCR] = { 0x34000, 0 }, - [GCC_UBI0_AXI_ARES] = { 0x680}, + [GCC_UBI0_AXI_ARES] = { 0x68010, 0 }, [GCC_UBI0_AHB_ARES] = { 0x68010, 1 }, [GCC_UBI0_NC_AXI_ARES] = { 0x68010, 2 }, [GCC_UBI0_DBG_ARES] = { 0x68010, 3 }, diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index b366912cd6480..ef1e2ce4804d2 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -1554,6 +1554,7 @@ static struct clk_regmap_div nss_ubi0_div_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(24000000, P_XO, 1, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_core_pi_sleep_clk[] = { @@ -1734,6 +1735,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(160000000, P_GPLL0, 5, 0, 0), F(216000000, P_GPLL6, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_div2[] = { diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c index b7faf12a511a1..7bc679871f324 100644 --- a/drivers/clk/qcom/gcc-ipq8074.c +++ b/drivers/clk/qcom/gcc-ipq8074.c @@ -644,6 +644,7 @@ static struct clk_rcg2 pcie0_axi_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(19200000, P_XO, 1, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_sleep_clk[] = { @@ -795,6 +796,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(19200000, P_XO, 1, 0, 0), F(160000000, P_GPLL0, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_div2[] = { diff --git a/drivers/clk/qcom/gcc-ipq9574.c b/drivers/clk/qcom/gcc-ipq9574.c index e8190108e1aef..0a3f846695b80 100644 --- a/drivers/clk/qcom/gcc-ipq9574.c +++ b/drivers/clk/qcom/gcc-ipq9574.c @@ -2082,6 +2082,7 @@ static struct clk_branch gcc_sdcc1_apps_clk = { static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(150000000, P_GPLL4, 8, 0, 0), F(300000000, P_GPLL4, 4, 0, 0), + { } }; static struct clk_rcg2 sdcc1_ice_core_clk_src = { diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index 725cd52d2398e..ea4c3bf4fb9bf 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -4037,3 +4037,4 @@ module_exit(gcc_sdm845_exit); MODULE_DESCRIPTION("QTI GCC SDM845 Driver"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:gcc-sdm845"); +MODULE_SOFTDEP("pre: rpmhpd"); diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c index 02fc21208dd14..c89700ab93f9c 100644 --- a/drivers/clk/qcom/mmcc-apq8084.c +++ b/drivers/clk/qcom/mmcc-apq8084.c @@ -348,6 +348,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(333430000, P_MMPLL1, 3.5, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -372,6 +373,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(228570000, P_MMPLL0, 3.5, 0, 0), F(320000000, P_MMPLL0, 2.5, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c index a31f6cf0c4e0c..36f460b78be2c 100644 --- a/drivers/clk/qcom/mmcc-msm8974.c +++ b/drivers/clk/qcom/mmcc-msm8974.c @@ -290,6 +290,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -314,6 +315,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/mmcc-msm8998.c b/drivers/clk/qcom/mmcc-msm8998.c index 1180e48c687ac..275fb3b71ede4 100644 --- a/drivers/clk/qcom/mmcc-msm8998.c +++ b/drivers/clk/qcom/mmcc-msm8998.c @@ -2535,6 +2535,8 @@ static struct clk_branch vmem_ahb_clk = { static struct gdsc video_top_gdsc = { .gdscr = 0x1024, + .cxcs = (unsigned int []){ 0x1028, 0x1034, 0x1038 }, + .cxc_count = 3, .pd = { .name = "video_top", }, @@ -2543,20 +2545,26 @@ static struct gdsc video_top_gdsc = { static struct gdsc video_subcore0_gdsc = { .gdscr = 0x1040, + .cxcs = (unsigned int []){ 0x1048 }, + .cxc_count = 1, .pd = { .name = "video_subcore0", }, .parent = &video_top_gdsc.pd, .pwrsts = PWRSTS_OFF_ON, + .flags = HW_CTRL, }; static struct gdsc video_subcore1_gdsc = { .gdscr = 0x1044, + .cxcs = (unsigned int []){ 0x104c }, + .cxc_count = 1, .pd = { .name = "video_subcore1", }, .parent = &video_top_gdsc.pd, .pwrsts = PWRSTS_OFF_ON, + .flags = HW_CTRL, }; static struct gdsc mdss_gdsc = { diff --git a/drivers/clk/qcom/reset.c b/drivers/clk/qcom/reset.c index e45e32804d2c7..d96c96a9089f4 100644 --- a/drivers/clk/qcom/reset.c +++ b/drivers/clk/qcom/reset.c @@ -22,8 +22,8 @@ static int qcom_reset(struct reset_controller_dev *rcdev, unsigned long id) return 0; } -static int -qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) +static int qcom_reset_set_assert(struct reset_controller_dev *rcdev, + unsigned long id, bool assert) { struct qcom_reset_controller *rst; const struct qcom_reset_map *map; @@ -33,21 +33,22 @@ qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) map = &rst->reset_map[id]; mask = map->bitmask ? map->bitmask : BIT(map->bit); - return regmap_update_bits(rst->regmap, map->reg, mask, mask); + regmap_update_bits(rst->regmap, map->reg, mask, assert ? mask : 0); + + /* Read back the register to ensure write completion, ignore the value */ + regmap_read(rst->regmap, map->reg, &mask); + + return 0; } -static int -qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +static int qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) { - struct qcom_reset_controller *rst; - const struct qcom_reset_map *map; - u32 mask; - - rst = to_qcom_reset_controller(rcdev); - map = &rst->reset_map[id]; - mask = map->bitmask ? map->bitmask : BIT(map->bit); + return qcom_reset_set_assert(rcdev, id, true); +} - return regmap_update_bits(rst->regmap, map->reg, mask, 0); +static int qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +{ + return qcom_reset_set_assert(rcdev, id, false); } const struct reset_control_ops qcom_reset_ops = { diff --git a/drivers/clk/renesas/r8a779a0-cpg-mssr.c b/drivers/clk/renesas/r8a779a0-cpg-mssr.c index 4c2872f45387f..ff3f85e906fe1 100644 --- a/drivers/clk/renesas/r8a779a0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779a0-cpg-mssr.c @@ -139,7 +139,7 @@ static const struct mssr_mod_clk r8a779a0_mod_clks[] __initconst = { DEF_MOD("avb3", 214, R8A779A0_CLK_S3D2), DEF_MOD("avb4", 215, R8A779A0_CLK_S3D2), DEF_MOD("avb5", 216, R8A779A0_CLK_S3D2), - DEF_MOD("canfd0", 328, R8A779A0_CLK_CANFD), + DEF_MOD("canfd0", 328, R8A779A0_CLK_S3D2), DEF_MOD("csi40", 331, R8A779A0_CLK_CSI0), DEF_MOD("csi41", 400, R8A779A0_CLK_CSI0), DEF_MOD("csi42", 401, R8A779A0_CLK_CSI0), diff --git a/drivers/clk/renesas/r8a779f0-cpg-mssr.c b/drivers/clk/renesas/r8a779f0-cpg-mssr.c index f721835c7e212..cc06127406ab5 100644 --- a/drivers/clk/renesas/r8a779f0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779f0-cpg-mssr.c @@ -161,7 +161,7 @@ static const struct mssr_mod_clk r8a779f0_mod_clks[] __initconst = { DEF_MOD("cmt1", 911, R8A779F0_CLK_R), DEF_MOD("cmt2", 912, R8A779F0_CLK_R), DEF_MOD("cmt3", 913, R8A779F0_CLK_R), - DEF_MOD("pfc0", 915, R8A779F0_CLK_CL16M), + DEF_MOD("pfc0", 915, R8A779F0_CLK_CPEX), DEF_MOD("tsc", 919, R8A779F0_CLK_CL16M), DEF_MOD("rswitch2", 1505, R8A779F0_CLK_RSW2), DEF_MOD("ether-serdes", 1506, R8A779F0_CLK_S0D2_HSC), diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index 5974adcef3eda..c4b1938db76b3 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -22,7 +22,7 @@ enum clk_ids { /* Core Clock Outputs exported to DT */ - LAST_DT_CORE_CLK = R8A779G0_CLK_R, + LAST_DT_CORE_CLK = R8A779G0_CLK_CP, /* External Input Clocks */ CLK_EXTAL, @@ -141,6 +141,7 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = { DEF_FIXED("svd2_vip", R8A779G0_CLK_SVD2_VIP, CLK_SV_VIP, 2, 1), DEF_FIXED("cbfusa", R8A779G0_CLK_CBFUSA, CLK_EXTAL, 2, 1), DEF_FIXED("cpex", R8A779G0_CLK_CPEX, CLK_EXTAL, 2, 1), + DEF_FIXED("cp", R8A779G0_CLK_CP, CLK_EXTAL, 2, 1), DEF_FIXED("viobus", R8A779G0_CLK_VIOBUS, CLK_VIO, 1, 1), DEF_FIXED("viobusd2", R8A779G0_CLK_VIOBUSD2, CLK_VIO, 2, 1), DEF_FIXED("vcbus", R8A779G0_CLK_VCBUS, CLK_VC, 1, 1), @@ -193,7 +194,7 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("msi4", 622, R8A779G0_CLK_MSO), DEF_MOD("msi5", 623, R8A779G0_CLK_MSO), DEF_MOD("pciec0", 624, R8A779G0_CLK_S0D2_HSC), - DEF_MOD("pscie1", 625, R8A779G0_CLK_S0D2_HSC), + DEF_MOD("pciec1", 625, R8A779G0_CLK_S0D2_HSC), DEF_MOD("pwm", 628, R8A779G0_CLK_SASYNCPERD4), DEF_MOD("rpc-if", 629, R8A779G0_CLK_RPCD2), DEF_MOD("scif0", 702, R8A779G0_CLK_SASYNCPERD4), @@ -232,10 +233,10 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("cmt1", 911, R8A779G0_CLK_R), DEF_MOD("cmt2", 912, R8A779G0_CLK_R), DEF_MOD("cmt3", 913, R8A779G0_CLK_R), - DEF_MOD("pfc0", 915, R8A779G0_CLK_CL16M), - DEF_MOD("pfc1", 916, R8A779G0_CLK_CL16M), - DEF_MOD("pfc2", 917, R8A779G0_CLK_CL16M), - DEF_MOD("pfc3", 918, R8A779G0_CLK_CL16M), + DEF_MOD("pfc0", 915, R8A779G0_CLK_CP), + DEF_MOD("pfc1", 916, R8A779G0_CLK_CP), + DEF_MOD("pfc2", 917, R8A779G0_CLK_CP), + DEF_MOD("pfc3", 918, R8A779G0_CLK_CP), DEF_MOD("tsc", 919, R8A779G0_CLK_CL16M), DEF_MOD("tsn", 2723, R8A779G0_CLK_S0D4_HSC), DEF_MOD("ssiu", 2926, R8A779G0_CLK_S0D6_PER), diff --git a/drivers/clk/renesas/r9a07g043-cpg.c b/drivers/clk/renesas/r9a07g043-cpg.c index b70bb378ab469..9ad7ceb3ab1ba 100644 --- a/drivers/clk/renesas/r9a07g043-cpg.c +++ b/drivers/clk/renesas/r9a07g043-cpg.c @@ -138,7 +138,7 @@ static const struct cpg_core_clk r9a07g043_core_clks[] __initconst = { DEF_FIXED("SPI1", R9A07G043_CLK_SPI1, CLK_DIV_PLL3_C, 1, 4), DEF_SD_MUX("SD0", R9A07G043_CLK_SD0, SEL_SDHI0, SEL_SDHI0_STS, sel_shdi, mtable_sdhi, 0, rzg2l_cpg_sd_clk_mux_notifier), - DEF_SD_MUX("SD1", R9A07G043_CLK_SD1, SEL_SDHI1, SEL_SDHI0_STS, sel_shdi, + DEF_SD_MUX("SD1", R9A07G043_CLK_SD1, SEL_SDHI1, SEL_SDHI1_STS, sel_shdi, mtable_sdhi, 0, rzg2l_cpg_sd_clk_mux_notifier), DEF_FIXED("SD0_DIV4", CLK_SD0_DIV4, R9A07G043_CLK_SD0, 1, 4), DEF_FIXED("SD1_DIV4", CLK_SD1_DIV4, R9A07G043_CLK_SD1, 1, 4), @@ -265,6 +265,10 @@ static struct rzg2l_mod_clk r9a07g043_mod_clks[] = { 0x5a8, 1), DEF_MOD("tsu_pclk", R9A07G043_TSU_PCLK, R9A07G043_CLK_TSU, 0x5ac, 0), +#ifdef CONFIG_RISCV + DEF_MOD("nceplic_aclk", R9A07G043_NCEPLIC_ACLK, R9A07G043_CLK_P1, + 0x608, 0), +#endif }; static struct rzg2l_reset r9a07g043_resets[] = { @@ -318,6 +322,10 @@ static struct rzg2l_reset r9a07g043_resets[] = { DEF_RST(R9A07G043_ADC_PRESETN, 0x8a8, 0), DEF_RST(R9A07G043_ADC_ADRST_N, 0x8a8, 1), DEF_RST(R9A07G043_TSU_PRESETN, 0x8ac, 0), +#ifdef CONFIG_RISCV + DEF_RST(R9A07G043_NCEPLIC_ARESETN, 0x908, 0), +#endif + }; static const unsigned int r9a07g043_crit_mod_clks[] __initconst = { @@ -327,6 +335,7 @@ static const unsigned int r9a07g043_crit_mod_clks[] __initconst = { #endif #ifdef CONFIG_RISCV MOD_CLK_BASE + R9A07G043_IAX45_CLK, + MOD_CLK_BASE + R9A07G043_NCEPLIC_ACLK, #endif MOD_CLK_BASE + R9A07G043_DMAC_ACLK, }; diff --git a/drivers/clk/renesas/r9a07g044-cpg.c b/drivers/clk/renesas/r9a07g044-cpg.c index 1047278c9079a..bc822b9fd7ce6 100644 --- a/drivers/clk/renesas/r9a07g044-cpg.c +++ b/drivers/clk/renesas/r9a07g044-cpg.c @@ -178,7 +178,7 @@ static const struct { DEF_FIXED("SPI1", R9A07G044_CLK_SPI1, CLK_DIV_PLL3_C, 1, 4), DEF_SD_MUX("SD0", R9A07G044_CLK_SD0, SEL_SDHI0, SEL_SDHI0_STS, sel_shdi, mtable_sdhi, 0, rzg2l_cpg_sd_clk_mux_notifier), - DEF_SD_MUX("SD1", R9A07G044_CLK_SD1, SEL_SDHI1, SEL_SDHI0_STS, sel_shdi, + DEF_SD_MUX("SD1", R9A07G044_CLK_SD1, SEL_SDHI1, SEL_SDHI1_STS, sel_shdi, mtable_sdhi, 0, rzg2l_cpg_sd_clk_mux_notifier), DEF_FIXED("SD0_DIV4", CLK_SD0_DIV4, R9A07G044_CLK_SD0, 1, 4), DEF_FIXED("SD1_DIV4", CLK_SD1_DIV4, R9A07G044_CLK_SD1, 1, 4), diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c index 3484e6cc80ad1..503c6f5b20d5c 100644 --- a/drivers/clk/samsung/clk-exynos-clkout.c +++ b/drivers/clk/samsung/clk-exynos-clkout.c @@ -13,9 +13,9 @@ #include #include #include +#include #include #include -#include #define EXYNOS_CLKOUT_NR_CLKS 1 #define EXYNOS_CLKOUT_PARENTS 32 @@ -84,17 +84,24 @@ MODULE_DEVICE_TABLE(of, exynos_clkout_ids); static int exynos_clkout_match_parent_dev(struct device *dev, u32 *mux_mask) { const struct exynos_clkout_variant *variant; + const struct of_device_id *match; if (!dev->parent) { dev_err(dev, "not instantiated from MFD\n"); return -EINVAL; } - variant = device_get_match_data(dev->parent); - if (!variant) { + /* + * 'exynos_clkout_ids' arrays is not the ids array matched by + * the dev->parent driver, so of_device_get_match_data() or + * device_get_match_data() cannot be used here. + */ + match = of_match_device(exynos_clkout_ids, dev->parent); + if (!match) { dev_err(dev, "cannot match parent device\n"); return -EINVAL; } + variant = match->data; *mux_mask = variant->mux_mask; diff --git a/drivers/clk/samsung/clk-exynos850.c b/drivers/clk/samsung/clk-exynos850.c index bdc1eef7d6e54..c7b0b9751307b 100644 --- a/drivers/clk/samsung/clk-exynos850.c +++ b/drivers/clk/samsung/clk-exynos850.c @@ -605,7 +605,7 @@ static const struct samsung_div_clock apm_div_clks[] __initconst = { static const struct samsung_gate_clock apm_gate_clks[] __initconst = { GATE(CLK_GOUT_CLKCMU_CMGP_BUS, "gout_clkcmu_cmgp_bus", "dout_apm_bus", - CLK_CON_GAT_CLKCMU_CMGP_BUS, 21, 0, 0), + CLK_CON_GAT_CLKCMU_CMGP_BUS, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CLKCMU_CHUB_BUS, "gout_clkcmu_chub_bus", "mout_clkcmu_chub_bus", CLK_CON_GAT_GATE_CLKCMU_CHUB_BUS, 21, 0, 0), @@ -974,19 +974,19 @@ static const struct samsung_fixed_rate_clock cmgp_fixed_clks[] __initconst = { static const struct samsung_mux_clock cmgp_mux_clks[] __initconst = { MUX(CLK_MOUT_CMGP_ADC, "mout_cmgp_adc", mout_cmgp_adc_p, CLK_CON_MUX_CLK_CMGP_ADC, 0, 1), - MUX(CLK_MOUT_CMGP_USI0, "mout_cmgp_usi0", mout_cmgp_usi0_p, - CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP0, 0, 1), - MUX(CLK_MOUT_CMGP_USI1, "mout_cmgp_usi1", mout_cmgp_usi1_p, - CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP1, 0, 1), + MUX_F(CLK_MOUT_CMGP_USI0, "mout_cmgp_usi0", mout_cmgp_usi0_p, + CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP0, 0, 1, CLK_SET_RATE_PARENT, 0), + MUX_F(CLK_MOUT_CMGP_USI1, "mout_cmgp_usi1", mout_cmgp_usi1_p, + CLK_CON_MUX_MUX_CLK_CMGP_USI_CMGP1, 0, 1, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_div_clock cmgp_div_clks[] __initconst = { DIV(CLK_DOUT_CMGP_ADC, "dout_cmgp_adc", "gout_clkcmu_cmgp_bus", CLK_CON_DIV_DIV_CLK_CMGP_ADC, 0, 4), - DIV(CLK_DOUT_CMGP_USI0, "dout_cmgp_usi0", "mout_cmgp_usi0", - CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP0, 0, 5), - DIV(CLK_DOUT_CMGP_USI1, "dout_cmgp_usi1", "mout_cmgp_usi1", - CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP1, 0, 5), + DIV_F(CLK_DOUT_CMGP_USI0, "dout_cmgp_usi0", "mout_cmgp_usi0", + CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP0, 0, 5, CLK_SET_RATE_PARENT, 0), + DIV_F(CLK_DOUT_CMGP_USI1, "dout_cmgp_usi1", "mout_cmgp_usi1", + CLK_CON_DIV_DIV_CLK_CMGP_USI_CMGP1, 0, 5, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_gate_clock cmgp_gate_clks[] __initconst = { @@ -1001,12 +1001,12 @@ static const struct samsung_gate_clock cmgp_gate_clks[] __initconst = { "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_GPIO_PCLK, 21, CLK_IGNORE_UNUSED, 0), GATE(CLK_GOUT_CMGP_USI0_IPCLK, "gout_cmgp_usi0_ipclk", "dout_cmgp_usi0", - CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CMGP_USI0_PCLK, "gout_cmgp_usi0_pclk", "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_USI_CMGP0_PCLK, 21, 0, 0), GATE(CLK_GOUT_CMGP_USI1_IPCLK, "gout_cmgp_usi1_ipclk", "dout_cmgp_usi1", - CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_CMGP_USI1_PCLK, "gout_cmgp_usi1_pclk", "gout_clkcmu_cmgp_bus", CLK_CON_GAT_GOUT_CMGP_USI_CMGP1_PCLK, 21, 0, 0), @@ -1557,8 +1557,9 @@ static const struct samsung_mux_clock peri_mux_clks[] __initconst = { mout_peri_uart_user_p, PLL_CON0_MUX_CLKCMU_PERI_UART_USER, 4, 1), MUX(CLK_MOUT_PERI_HSI2C_USER, "mout_peri_hsi2c_user", mout_peri_hsi2c_user_p, PLL_CON0_MUX_CLKCMU_PERI_HSI2C_USER, 4, 1), - MUX(CLK_MOUT_PERI_SPI_USER, "mout_peri_spi_user", mout_peri_spi_user_p, - PLL_CON0_MUX_CLKCMU_PERI_SPI_USER, 4, 1), + MUX_F(CLK_MOUT_PERI_SPI_USER, "mout_peri_spi_user", + mout_peri_spi_user_p, PLL_CON0_MUX_CLKCMU_PERI_SPI_USER, 4, 1, + CLK_SET_RATE_PARENT, 0), }; static const struct samsung_div_clock peri_div_clks[] __initconst = { @@ -1568,8 +1569,8 @@ static const struct samsung_div_clock peri_div_clks[] __initconst = { CLK_CON_DIV_DIV_CLK_PERI_HSI2C_1, 0, 5), DIV(CLK_DOUT_PERI_HSI2C2, "dout_peri_hsi2c2", "gout_peri_hsi2c2", CLK_CON_DIV_DIV_CLK_PERI_HSI2C_2, 0, 5), - DIV(CLK_DOUT_PERI_SPI0, "dout_peri_spi0", "mout_peri_spi_user", - CLK_CON_DIV_DIV_CLK_PERI_SPI_0, 0, 5), + DIV_F(CLK_DOUT_PERI_SPI0, "dout_peri_spi0", "mout_peri_spi_user", + CLK_CON_DIV_DIV_CLK_PERI_SPI_0, 0, 5, CLK_SET_RATE_PARENT, 0), }; static const struct samsung_gate_clock peri_gate_clks[] __initconst = { @@ -1611,7 +1612,7 @@ static const struct samsung_gate_clock peri_gate_clks[] __initconst = { "mout_peri_bus_user", CLK_CON_GAT_GOUT_PERI_PWM_MOTOR_PCLK, 21, 0, 0), GATE(CLK_GOUT_SPI0_IPCLK, "gout_spi0_ipclk", "dout_peri_spi0", - CLK_CON_GAT_GOUT_PERI_SPI_0_IPCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_PERI_SPI_0_IPCLK, 21, CLK_SET_RATE_PARENT, 0), GATE(CLK_GOUT_SPI0_PCLK, "gout_spi0_pclk", "mout_peri_bus_user", CLK_CON_GAT_GOUT_PERI_SPI_0_PCLK, 21, 0, 0), GATE(CLK_GOUT_SYSREG_PERI_PCLK, "gout_sysreg_peri_pclk", diff --git a/drivers/clk/samsung/clk-exynosautov9.c b/drivers/clk/samsung/clk-exynosautov9.c index e9c06eb93e666..f04bacacab2cb 100644 --- a/drivers/clk/samsung/clk-exynosautov9.c +++ b/drivers/clk/samsung/clk-exynosautov9.c @@ -352,13 +352,13 @@ static const struct samsung_pll_clock top_pll_clks[] __initconst = { /* CMU_TOP_PURECLKCOMP */ PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared0_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED0, PLL_CON3_PLL_SHARED0, NULL), - PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared1_pll", "oscclk", + PLL(pll_0822x, FOUT_SHARED1_PLL, "fout_shared1_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED1, PLL_CON3_PLL_SHARED1, NULL), - PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared2_pll", "oscclk", + PLL(pll_0822x, FOUT_SHARED2_PLL, "fout_shared2_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED2, PLL_CON3_PLL_SHARED2, NULL), - PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared3_pll", "oscclk", + PLL(pll_0822x, FOUT_SHARED3_PLL, "fout_shared3_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED3, PLL_CON3_PLL_SHARED3, NULL), - PLL(pll_0822x, FOUT_SHARED0_PLL, "fout_shared4_pll", "oscclk", + PLL(pll_0822x, FOUT_SHARED4_PLL, "fout_shared4_pll", "oscclk", PLL_LOCKTIME_PLL_SHARED4, PLL_CON3_PLL_SHARED4, NULL), }; diff --git a/drivers/clk/sifive/sifive-prci.c b/drivers/clk/sifive/sifive-prci.c index 25b8e1a80ddce..b32a59fe55e74 100644 --- a/drivers/clk/sifive/sifive-prci.c +++ b/drivers/clk/sifive/sifive-prci.c @@ -4,7 +4,6 @@ * Copyright (C) 2020 Zong Li */ -#include #include #include #include @@ -537,13 +536,6 @@ static int __prci_register_clocks(struct device *dev, struct __prci_data *pd, return r; } - r = clk_hw_register_clkdev(&pic->hw, pic->name, dev_name(dev)); - if (r) { - dev_warn(dev, "Failed to register clkdev for %s: %d\n", - init.name, r); - return r; - } - pd->hw_clks.hws[i] = &pic->hw; } diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c index 8951ffc14ff52..6a4b2b9ef30a8 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c @@ -182,6 +182,8 @@ static struct ccu_nkm pll_mipi_clk = { &ccu_nkm_ops, CLK_SET_RATE_UNGATE | CLK_SET_RATE_PARENT), .features = CCU_FEATURE_CLOSEST_RATE, + .min_rate = 500000000, + .max_rate = 1400000000, }, }; diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c index 42568c6161814..892df807275c8 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c @@ -1181,11 +1181,18 @@ static const u32 usb2_clk_regs[] = { SUN50I_H6_USB3_CLK_REG, }; +static struct ccu_mux_nb sun50i_h6_cpu_nb = { + .common = &cpux_clk.common, + .cm = &cpux_clk.mux, + .delay_us = 1, + .bypass_index = 0, /* index of 24 MHz oscillator */ +}; + static int sun50i_h6_ccu_probe(struct platform_device *pdev) { void __iomem *reg; + int i, ret; u32 val; - int i; reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(reg)) @@ -1252,7 +1259,15 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev) val |= BIT(24); writel(val, reg + SUN50I_H6_HDMI_CEC_CLK_REG); - return devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc); + ret = devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc); + if (ret) + return ret; + + /* Reparent CPU during PLL CPUX rate changes */ + ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, + &sun50i_h6_cpu_nb); + + return 0; } static const struct of_device_id sun50i_h6_ccu_ids[] = { diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c index 8babce55302f5..ac0091b4ce242 100644 --- a/drivers/clk/sunxi-ng/ccu_common.c +++ b/drivers/clk/sunxi-ng/ccu_common.c @@ -44,6 +44,16 @@ bool ccu_is_better_rate(struct ccu_common *common, unsigned long current_rate, unsigned long best_rate) { + unsigned long min_rate, max_rate; + + clk_hw_get_rate_range(&common->hw, &min_rate, &max_rate); + + if (current_rate > max_rate) + return false; + + if (current_rate < min_rate) + return false; + if (common->features & CCU_FEATURE_CLOSEST_RATE) return abs(current_rate - target_rate) < abs(best_rate - target_rate); @@ -122,6 +132,7 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev, for (i = 0; i < desc->hw_clks->num ; i++) { struct clk_hw *hw = desc->hw_clks->hws[i]; + struct ccu_common *common = hw_to_ccu_common(hw); const char *name; if (!hw) @@ -136,6 +147,14 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev, pr_err("Couldn't register clock %d - %s\n", i, name); goto err_clk_unreg; } + + if (common->max_rate) + clk_hw_set_rate_range(hw, common->min_rate, + common->max_rate); + else + WARN(common->min_rate, + "No max_rate, ignoring min_rate of clock %d - %s\n", + i, name); } ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h index 942a72c094374..329734f8cf42b 100644 --- a/drivers/clk/sunxi-ng/ccu_common.h +++ b/drivers/clk/sunxi-ng/ccu_common.h @@ -31,6 +31,9 @@ struct ccu_common { u16 lock_reg; u32 prediv; + unsigned long min_rate; + unsigned long max_rate; + unsigned long features; spinlock_t *lock; struct clk_hw hw; diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c index 7bdeaff2bfd68..c28d3dacf0fb2 100644 --- a/drivers/clk/zynq/clkc.c +++ b/drivers/clk/zynq/clkc.c @@ -42,6 +42,7 @@ static void __iomem *zynq_clkc_base; #define SLCR_SWDT_CLK_SEL (zynq_clkc_base + 0x204) #define NUM_MIO_PINS 54 +#define CLK_NAME_LEN 16 #define DBG_CLK_CTRL_CLKACT_TRC BIT(0) #define DBG_CLK_CTRL_CPU_1XCLKACT BIT(1) @@ -215,7 +216,7 @@ static void __init zynq_clk_setup(struct device_node *np) int i; u32 tmp; int ret; - char *clk_name; + char clk_name[CLK_NAME_LEN]; unsigned int fclk_enable = 0; const char *clk_output_name[clk_max]; const char *cpu_parents[4]; @@ -426,12 +427,10 @@ static void __init zynq_clk_setup(struct device_node *np) "gem1_emio_mux", CLK_SET_RATE_PARENT, SLCR_GEM1_CLK_CTRL, 0, 0, &gem1clk_lock); - tmp = strlen("mio_clk_00x"); - clk_name = kmalloc(tmp, GFP_KERNEL); for (i = 0; i < NUM_MIO_PINS; i++) { int idx; - snprintf(clk_name, tmp, "mio_clk_%2.2d", i); + snprintf(clk_name, CLK_NAME_LEN, "mio_clk_%2.2d", i); idx = of_property_match_string(np, "clock-names", clk_name); if (idx >= 0) can_mio_mux_parents[i] = of_clk_get_parent_name(np, @@ -439,7 +438,6 @@ static void __init zynq_clk_setup(struct device_node *np) else can_mio_mux_parents[i] = dummy_nm; } - kfree(clk_name); clk_register_mux(NULL, "can_mux", periph_parents, 4, CLK_SET_RATE_NO_REPARENT, SLCR_CAN_CLK_CTRL, 4, 2, 0, &canclk_lock); diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index 44a61dc6f9320..e1c773bb55359 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -32,7 +32,7 @@ #define GT_CONTROL_IRQ_ENABLE BIT(2) /* banked */ #define GT_CONTROL_AUTO_INC BIT(3) /* banked */ #define GT_CONTROL_PRESCALER_SHIFT 8 -#define GT_CONTROL_PRESCALER_MAX 0xF +#define GT_CONTROL_PRESCALER_MAX 0xFF #define GT_CONTROL_PRESCALER_MASK (GT_CONTROL_PRESCALER_MAX << \ GT_CONTROL_PRESCALER_SHIFT) diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index e66dcbd665665..79bb9a98baa7b 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -108,6 +108,9 @@ static int riscv_timer_starting_cpu(unsigned int cpu) { struct clock_event_device *ce = per_cpu_ptr(&riscv_clock_event, cpu); + /* Clear timer interrupt */ + riscv_clock_event_stop(); + ce->cpumask = cpumask_of(cpu); ce->irq = riscv_clock_event_irq; if (riscv_timer_cannot_wake_cpu) diff --git a/drivers/comedi/drivers/vmk80xx.c b/drivers/comedi/drivers/vmk80xx.c index 4536ed43f65b2..84dce5184a77a 100644 --- a/drivers/comedi/drivers/vmk80xx.c +++ b/drivers/comedi/drivers/vmk80xx.c @@ -641,33 +641,22 @@ static int vmk80xx_find_usb_endpoints(struct comedi_device *dev) struct vmk80xx_private *devpriv = dev->private; struct usb_interface *intf = comedi_to_usb_interface(dev); struct usb_host_interface *iface_desc = intf->cur_altsetting; - struct usb_endpoint_descriptor *ep_desc; - int i; - - if (iface_desc->desc.bNumEndpoints != 2) - return -ENODEV; - - for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) { - ep_desc = &iface_desc->endpoint[i].desc; - - if (usb_endpoint_is_int_in(ep_desc) || - usb_endpoint_is_bulk_in(ep_desc)) { - if (!devpriv->ep_rx) - devpriv->ep_rx = ep_desc; - continue; - } + struct usb_endpoint_descriptor *ep_rx_desc, *ep_tx_desc; + int ret; - if (usb_endpoint_is_int_out(ep_desc) || - usb_endpoint_is_bulk_out(ep_desc)) { - if (!devpriv->ep_tx) - devpriv->ep_tx = ep_desc; - continue; - } - } + if (devpriv->model == VMK8061_MODEL) + ret = usb_find_common_endpoints(iface_desc, &ep_rx_desc, + &ep_tx_desc, NULL, NULL); + else + ret = usb_find_common_endpoints(iface_desc, NULL, NULL, + &ep_rx_desc, &ep_tx_desc); - if (!devpriv->ep_rx || !devpriv->ep_tx) + if (ret) return -ENODEV; + devpriv->ep_rx = ep_rx_desc; + devpriv->ep_tx = ep_tx_desc; + if (!usb_endpoint_maxp(devpriv->ep_rx) || !usb_endpoint_maxp(devpriv->ep_tx)) return -EINVAL; diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index f911606897b8d..a0ebad77666e3 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -173,6 +173,7 @@ config ARM_QCOM_CPUFREQ_NVMEM config ARM_QCOM_CPUFREQ_HW tristate "QCOM CPUFreq HW driver" depends on ARCH_QCOM || COMPILE_TEST + depends on COMMON_CLK help Support for the CPUFreq HW driver. Some QCOM chipsets have a HW engine to offload the steps diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c index f04ae67dda372..fc275d41d51e9 100644 --- a/drivers/cpufreq/amd-pstate-ut.c +++ b/drivers/cpufreq/amd-pstate-ut.c @@ -26,10 +26,11 @@ #include #include #include -#include #include +#include "amd-pstate.h" + /* * Abbreviations: * amd_pstate_ut: used as a shortform for AMD P-State unit test. diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 1791d37fbc53c..d8188075c992d 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -36,7 +36,6 @@ #include #include #include -#include #include #include @@ -45,11 +44,44 @@ #include #include #include + +#include "amd-pstate.h" #include "amd-pstate-trace.h" #define AMD_PSTATE_TRANSITION_LATENCY 20000 #define AMD_PSTATE_TRANSITION_DELAY 1000 +#define AMD_CPPC_EPP_PERFORMANCE 0x00 +#define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 +#define AMD_CPPC_EPP_BALANCE_POWERSAVE 0xBF +#define AMD_CPPC_EPP_POWERSAVE 0xFF + +/* + * enum amd_pstate_mode - driver working mode of amd pstate + */ +enum amd_pstate_mode { + AMD_PSTATE_UNDEFINED = 0, + AMD_PSTATE_DISABLE, + AMD_PSTATE_PASSIVE, + AMD_PSTATE_ACTIVE, + AMD_PSTATE_GUIDED, + AMD_PSTATE_MAX, +}; + +static const char * const amd_pstate_mode_string[] = { + [AMD_PSTATE_UNDEFINED] = "undefined", + [AMD_PSTATE_DISABLE] = "disable", + [AMD_PSTATE_PASSIVE] = "passive", + [AMD_PSTATE_ACTIVE] = "active", + [AMD_PSTATE_GUIDED] = "guided", + NULL, +}; + +struct quirk_entry { + u32 nominal_freq; + u32 lowest_freq; +}; + /* * TODO: We need more time to fine tune processors with shared memory solution * with community together. @@ -64,6 +96,7 @@ static struct cpufreq_driver amd_pstate_driver; static struct cpufreq_driver amd_pstate_epp_driver; static int cppc_state = AMD_PSTATE_UNDEFINED; static bool cppc_enabled; +static struct quirk_entry *quirks; /* * AMD Energy Preference Performance (EPP) @@ -108,6 +141,41 @@ static unsigned int epp_values[] = { typedef int (*cppc_mode_transition_fn)(int); +static struct quirk_entry quirk_amd_7k62 = { + .nominal_freq = 2600, + .lowest_freq = 550, +}; + +static int __init dmi_matched_7k62_bios_bug(const struct dmi_system_id *dmi) +{ + /** + * match the broken bios for family 17h processor support CPPC V2 + * broken BIOS lack of nominal_freq and lowest_freq capabilities + * definition in ACPI tables + */ + if (boot_cpu_has(X86_FEATURE_ZEN2)) { + quirks = dmi->driver_data; + pr_info("Overriding nominal and lowest frequencies for %s\n", dmi->ident); + return 1; + } + + return 0; +} + +static const struct dmi_system_id amd_pstate_quirks_table[] __initconst = { + { + .callback = dmi_matched_7k62_bios_bug, + .ident = "AMD EPYC 7K62", + .matches = { + DMI_MATCH(DMI_BIOS_VERSION, "5.14"), + DMI_MATCH(DMI_BIOS_RELEASE, "12/12/2019"), + }, + .driver_data = &quirk_amd_7k62, + }, + {} +}; +MODULE_DEVICE_TABLE(dmi, amd_pstate_quirks_table); + static inline int get_mode_idx_from_str(const char *str, size_t size) { int i; @@ -570,7 +638,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (target_perf < capacity) des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity); - min_perf = READ_ONCE(cpudata->highest_perf); + min_perf = READ_ONCE(cpudata->lowest_perf); if (_min_perf < capacity) min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity); @@ -592,74 +660,22 @@ static void amd_pstate_adjust_perf(unsigned int cpu, static int amd_get_min_freq(struct amd_cpudata *cpudata) { - struct cppc_perf_caps cppc_perf; - - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; - - /* Switch to khz */ - return cppc_perf.lowest_freq * 1000; + return READ_ONCE(cpudata->min_freq); } static int amd_get_max_freq(struct amd_cpudata *cpudata) { - struct cppc_perf_caps cppc_perf; - u32 max_perf, max_freq, nominal_freq, nominal_perf; - u64 boost_ratio; - - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; - - nominal_freq = cppc_perf.nominal_freq; - nominal_perf = READ_ONCE(cpudata->nominal_perf); - max_perf = READ_ONCE(cpudata->highest_perf); - - boost_ratio = div_u64(max_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); - - max_freq = nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT; - - /* Switch to khz */ - return max_freq * 1000; + return READ_ONCE(cpudata->max_freq); } static int amd_get_nominal_freq(struct amd_cpudata *cpudata) { - struct cppc_perf_caps cppc_perf; - - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; - - /* Switch to khz */ - return cppc_perf.nominal_freq * 1000; + return READ_ONCE(cpudata->nominal_freq); } static int amd_get_lowest_nonlinear_freq(struct amd_cpudata *cpudata) { - struct cppc_perf_caps cppc_perf; - u32 lowest_nonlinear_freq, lowest_nonlinear_perf, - nominal_freq, nominal_perf; - u64 lowest_nonlinear_ratio; - - int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); - if (ret) - return ret; - - nominal_freq = cppc_perf.nominal_freq; - nominal_perf = READ_ONCE(cpudata->nominal_perf); - - lowest_nonlinear_perf = cppc_perf.lowest_nonlinear_perf; - - lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT, - nominal_perf); - - lowest_nonlinear_freq = nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT; - - /* Switch to khz */ - return lowest_nonlinear_freq * 1000; + return READ_ONCE(cpudata->lowest_nonlinear_freq); } static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) @@ -675,7 +691,7 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) if (state) policy->cpuinfo.max_freq = cpudata->max_freq; else - policy->cpuinfo.max_freq = cpudata->nominal_freq; + policy->cpuinfo.max_freq = cpudata->nominal_freq * 1000; policy->max = policy->cpuinfo.max_freq; @@ -706,6 +722,61 @@ static void amd_perf_ctl_reset(unsigned int cpu) wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); } +/** + * amd_pstate_init_freq: Initialize the max_freq, min_freq, + * nominal_freq and lowest_nonlinear_freq for + * the @cpudata object. + * + * Requires: highest_perf, lowest_perf, nominal_perf and + * lowest_nonlinear_perf members of @cpudata to be + * initialized. + * + * Returns 0 on success, non-zero value on failure. + */ +static int amd_pstate_init_freq(struct amd_cpudata *cpudata) +{ + int ret; + u32 min_freq; + u32 highest_perf, max_freq; + u32 nominal_perf, nominal_freq; + u32 lowest_nonlinear_perf, lowest_nonlinear_freq; + u32 boost_ratio, lowest_nonlinear_ratio; + struct cppc_perf_caps cppc_perf; + + + ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf); + if (ret) + return ret; + + if (quirks && quirks->lowest_freq) + min_freq = quirks->lowest_freq * 1000; + else + min_freq = cppc_perf.lowest_freq * 1000; + + if (quirks && quirks->nominal_freq) + nominal_freq = quirks->nominal_freq ; + else + nominal_freq = cppc_perf.nominal_freq; + + nominal_perf = READ_ONCE(cpudata->nominal_perf); + + highest_perf = READ_ONCE(cpudata->highest_perf); + boost_ratio = div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf); + max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000; + + lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); + lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT, + nominal_perf); + lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT) * 1000; + + WRITE_ONCE(cpudata->min_freq, min_freq); + WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq); + WRITE_ONCE(cpudata->nominal_freq, nominal_freq); + WRITE_ONCE(cpudata->max_freq, max_freq); + + return 0; +} + static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; @@ -731,6 +802,10 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) if (ret) goto free_cpudata1; + ret = amd_pstate_init_freq(cpudata); + if (ret) + goto free_cpudata1; + min_freq = amd_get_min_freq(cpudata); max_freq = amd_get_max_freq(cpudata); nominal_freq = amd_get_nominal_freq(cpudata); @@ -772,13 +847,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) goto free_cpudata2; } - /* Initial processor data capability frequencies */ - cpudata->max_freq = max_freq; - cpudata->min_freq = min_freq; cpudata->max_limit_freq = max_freq; cpudata->min_limit_freq = min_freq; - cpudata->nominal_freq = nominal_freq; - cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; policy->driver_data = cpudata; @@ -1155,6 +1225,10 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) if (ret) goto free_cpudata1; + ret = amd_pstate_init_freq(cpudata); + if (ret) + goto free_cpudata1; + min_freq = amd_get_min_freq(cpudata); max_freq = amd_get_max_freq(cpudata); nominal_freq = amd_get_nominal_freq(cpudata); @@ -1171,12 +1245,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) /* It will be updated by governor */ policy->cur = policy->cpuinfo.min_freq; - /* Initial processor data capability frequencies */ - cpudata->max_freq = max_freq; - cpudata->min_freq = min_freq; - cpudata->nominal_freq = nominal_freq; - cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; - policy->driver_data = cpudata; cpudata->epp_cached = amd_pstate_get_epp(cpudata, 0); @@ -1216,6 +1284,13 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) { + struct amd_cpudata *cpudata = policy->driver_data; + + if (cpudata) { + kfree(cpudata); + policy->driver_data = NULL; + } + pr_debug("CPU %d exiting\n", policy->cpu); return 0; } @@ -1486,6 +1561,11 @@ static int __init amd_pstate_init(void) if (cpufreq_get_current_driver()) return -EEXIST; + quirks = NULL; + + /* check if this machine need CPPC quirks */ + dmi_check_system(amd_pstate_quirks_table); + switch (cppc_state) { case AMD_PSTATE_UNDEFINED: /* Disable on the following configs by default: diff --git a/include/linux/amd-pstate.h b/drivers/cpufreq/amd-pstate.h similarity index 80% rename from include/linux/amd-pstate.h rename to drivers/cpufreq/amd-pstate.h index 6ad02ad9c7b42..dae22660c9acc 100644 --- a/include/linux/amd-pstate.h +++ b/drivers/cpufreq/amd-pstate.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * linux/include/linux/amd-pstate.h - * * Copyright (C) 2022 Advanced Micro Devices, Inc. * * Author: Meng Li @@ -12,11 +10,6 @@ #include -#define AMD_CPPC_EPP_PERFORMANCE 0x00 -#define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 -#define AMD_CPPC_EPP_BALANCE_POWERSAVE 0xBF -#define AMD_CPPC_EPP_POWERSAVE 0xFF - /********************************************************************* * AMD P-state INTERFACE * *********************************************************************/ @@ -94,24 +87,4 @@ struct amd_cpudata { bool suspended; }; -/* - * enum amd_pstate_mode - driver working mode of amd pstate - */ -enum amd_pstate_mode { - AMD_PSTATE_UNDEFINED = 0, - AMD_PSTATE_DISABLE, - AMD_PSTATE_PASSIVE, - AMD_PSTATE_ACTIVE, - AMD_PSTATE_GUIDED, - AMD_PSTATE_MAX, -}; - -static const char * const amd_pstate_mode_string[] = { - [AMD_PSTATE_UNDEFINED] = "undefined", - [AMD_PSTATE_DISABLE] = "disable", - [AMD_PSTATE_PASSIVE] = "passive", - [AMD_PSTATE_ACTIVE] = "active", - [AMD_PSTATE_GUIDED] = "guided", - NULL, -}; #endif /* _LINUX_AMD_PSTATE_H */ diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 35fb3a559ea97..ea8438550b490 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -481,7 +481,12 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv) static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct private_data *priv = policy->driver_data; + struct private_data *priv; + + if (!policy) + return 0; + + priv = policy->driver_data; cpufreq_cpu_put(policy); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 64420d9cfd1ed..15f1d41920a33 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -741,10 +741,15 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) { struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0}; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_cpudata *cpu_data; u64 delivered_perf; int ret; + if (!policy) + return -ENODEV; + + cpu_data = policy->driver_data; + cpufreq_cpu_put(policy); ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0); @@ -822,10 +827,15 @@ static struct cpufreq_driver cppc_cpufreq_driver = { static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct cppc_cpudata *cpu_data = policy->driver_data; + struct cppc_cpudata *cpu_data; u64 desired_perf; int ret; + if (!policy) + return -ENODEV; + + cpu_data = policy->driver_data; + cpufreq_cpu_put(policy); ret = cppc_get_desired_perf(cpu, &desired_perf); diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 8bd6e5e8f121c..2d83bbc65dd0b 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -208,7 +208,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu) if (!priv) return -ENOMEM; - if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&priv->cpus, GFP_KERNEL)) return -ENOMEM; cpumask_set_cpu(cpu, priv->cpus); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 44db4f59c4cc6..b4b530c94ba46 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -644,14 +644,16 @@ static ssize_t store_local_boost(struct cpufreq_policy *policy, if (policy->boost_enabled == enable) return count; + policy->boost_enabled = enable; + cpus_read_lock(); ret = cpufreq_driver->set_boost(policy, enable); cpus_read_unlock(); - if (ret) + if (ret) { + policy->boost_enabled = !policy->boost_enabled; return ret; - - policy->boost_enabled = enable; + } return count; } @@ -1419,6 +1421,9 @@ static int cpufreq_online(unsigned int cpu) goto out_free_policy; } + /* Let the per-policy boost flag mirror the cpufreq_driver boost during init */ + policy->boost_enabled = cpufreq_boost_enabled() && policy_has_boost_freq(policy); + /* * The initialization has succeeded and the policy is online. * If there is a problem with its frequency table, take it @@ -1571,7 +1576,8 @@ static int cpufreq_online(unsigned int cpu) if (cpufreq_driver->ready) cpufreq_driver->ready(policy); - if (cpufreq_thermal_control_enabled(cpufreq_driver)) + /* Register cpufreq cooling only for a new policy */ + if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); pr_debug("initialization complete\n"); @@ -1655,11 +1661,6 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) else policy->last_policy = policy->policy; - if (cpufreq_thermal_control_enabled(cpufreq_driver)) { - cpufreq_cooling_unregister(policy->cdev); - policy->cdev = NULL; - } - if (has_target()) cpufreq_exit_governor(policy); @@ -1669,10 +1670,13 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy) */ if (cpufreq_driver->offline) { cpufreq_driver->offline(policy); - } else if (cpufreq_driver->exit) { - cpufreq_driver->exit(policy); - policy->freq_table = NULL; + return; } + + if (cpufreq_driver->exit) + cpufreq_driver->exit(policy); + + policy->freq_table = NULL; } static int cpufreq_offline(unsigned int cpu) @@ -1720,8 +1724,17 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) return; } + /* + * Unregister cpufreq cooling once all the CPUs of the policy are + * removed. + */ + if (cpufreq_thermal_control_enabled(cpufreq_driver)) { + cpufreq_cooling_unregister(policy->cdev); + policy->cdev = NULL; + } + /* We did light-weight exit earlier, do full tear down now */ - if (cpufreq_driver->offline) + if (cpufreq_driver->offline && cpufreq_driver->exit) cpufreq_driver->exit(policy); up_write(&policy->rwsem); @@ -2755,11 +2768,12 @@ int cpufreq_boost_trigger_state(int state) cpus_read_lock(); for_each_active_policy(policy) { + policy->boost_enabled = state; ret = cpufreq_driver->set_boost(policy, state); - if (ret) + if (ret) { + policy->boost_enabled = !policy->boost_enabled; goto err_reset_state; - - policy->boost_enabled = state; + } } cpus_read_unlock(); @@ -2841,6 +2855,20 @@ static int cpuhp_cpufreq_offline(unsigned int cpu) return 0; } +static char cpufreq_driver_name[CPUFREQ_NAME_LEN]; + +static int __init cpufreq_driver_setup(char *str) +{ + strscpy(cpufreq_driver_name, str, CPUFREQ_NAME_LEN); + return 1; +} + +/* + * Set this name to only allow one specific cpu freq driver, e.g., + * cpufreq_driver=powernow-k8 + */ +__setup("cpufreq_driver=", cpufreq_driver_setup); + /** * cpufreq_register_driver - register a CPU Frequency driver * @driver_data: A struct cpufreq_driver containing the values# @@ -2876,7 +2904,13 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) (driver_data->adjust_perf && !driver_data->fast_switch)) return -EINVAL; - pr_debug("trying to register driver %s\n", driver_data->name); + pr_debug("trying to register driver %s, cpufreq_driver=%s\n", + driver_data->name, cpufreq_driver_name); + + if (cpufreq_driver_name[0]) + if (!driver_data->name || + strcmp(cpufreq_driver_name, driver_data->name)) + return -EINVAL; /* Protect against concurrent CPU online/offline. */ cpus_read_lock(); diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index c4d4643b6ca65..c17dc51a5a022 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -40,7 +40,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, cpufreq_for_each_valid_entry(pos, table) { freq = pos->frequency; - if (!cpufreq_boost_enabled() + if ((!cpufreq_boost_enabled() || !policy->boost_enabled) && (pos->flags & CPUFREQ_BOOST_FREQ)) continue; diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c index d46afb3c00923..8d097dcddda47 100644 --- a/drivers/cpufreq/mediatek-cpufreq-hw.c +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #define LUT_MAX_ENTRIES 32U @@ -300,7 +301,23 @@ static struct cpufreq_driver cpufreq_mtk_hw_driver = { static int mtk_cpufreq_hw_driver_probe(struct platform_device *pdev) { const void *data; - int ret; + int ret, cpu; + struct device *cpu_dev; + struct regulator *cpu_reg; + + /* Make sure that all CPU supplies are available before proceeding. */ + for_each_possible_cpu(cpu) { + cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) + return dev_err_probe(&pdev->dev, -EPROBE_DEFER, + "Failed to get cpu%d device\n", cpu); + + cpu_reg = devm_regulator_get(cpu_dev, "cpu"); + if (IS_ERR(cpu_reg)) + return dev_err_probe(&pdev->dev, PTR_ERR(cpu_reg), + "CPU%d regulator get failed\n", cpu); + } + data = of_device_get_match_data(&pdev->dev); if (!data) diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index d9cda7f6ccb98..cf5873cc45dc8 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "cpuidle.h" @@ -187,7 +188,7 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) s->target_residency = div_u64(s->target_residency_ns, NSEC_PER_USEC); if (s->exit_latency > 0) - s->exit_latency_ns = s->exit_latency * NSEC_PER_USEC; + s->exit_latency_ns = mul_u32_u32(s->exit_latency, NSEC_PER_USEC); else if (s->exit_latency_ns < 0) s->exit_latency_ns = 0; else diff --git a/drivers/crypto/bcm/spu2.c b/drivers/crypto/bcm/spu2.c index 07989bb8c220a..3fdc64b5a65e7 100644 --- a/drivers/crypto/bcm/spu2.c +++ b/drivers/crypto/bcm/spu2.c @@ -495,7 +495,7 @@ static void spu2_dump_omd(u8 *omd, u16 hash_key_len, u16 ciph_key_len, if (hash_iv_len) { packet_log(" Hash IV Length %u bytes\n", hash_iv_len); packet_dump(" hash IV: ", ptr, hash_iv_len); - ptr += ciph_key_len; + ptr += hash_iv_len; } if (ciph_iv_len) { diff --git a/drivers/crypto/ccp/platform-access.c b/drivers/crypto/ccp/platform-access.c index 94367bc49e35b..1b8ed33897332 100644 --- a/drivers/crypto/ccp/platform-access.c +++ b/drivers/crypto/ccp/platform-access.c @@ -118,9 +118,16 @@ int psp_send_platform_access_msg(enum psp_platform_access_msg msg, goto unlock; } - /* Store the status in request header for caller to investigate */ + /* + * Read status from PSP. If status is non-zero, it indicates an error + * occurred during "processing" of the command. + * If status is zero, it indicates the command was "processed" + * successfully, but the result of the command is in the payload. + * Return both cases to the caller as -EIO to investigate. + */ cmd_reg = ioread32(cmd); - req->header.status = FIELD_GET(PSP_CMDRESP_STS, cmd_reg); + if (FIELD_GET(PSP_CMDRESP_STS, cmd_reg)) + req->header.status = FIELD_GET(PSP_CMDRESP_STS, cmd_reg); if (req->header.status) { ret = -EIO; goto unlock; diff --git a/drivers/crypto/ccp/sp-platform.c b/drivers/crypto/ccp/sp-platform.c index 4733012377601..ff6ceb4feee04 100644 --- a/drivers/crypto/ccp/sp-platform.c +++ b/drivers/crypto/ccp/sp-platform.c @@ -39,44 +39,38 @@ static const struct sp_dev_vdata dev_vdata[] = { }, }; -#ifdef CONFIG_ACPI static const struct acpi_device_id sp_acpi_match[] = { { "AMDI0C00", (kernel_ulong_t)&dev_vdata[0] }, { }, }; MODULE_DEVICE_TABLE(acpi, sp_acpi_match); -#endif -#ifdef CONFIG_OF static const struct of_device_id sp_of_match[] = { { .compatible = "amd,ccp-seattle-v1a", .data = (const void *)&dev_vdata[0] }, { }, }; MODULE_DEVICE_TABLE(of, sp_of_match); -#endif static struct sp_dev_vdata *sp_get_of_version(struct platform_device *pdev) { -#ifdef CONFIG_OF const struct of_device_id *match; match = of_match_node(sp_of_match, pdev->dev.of_node); if (match && match->data) return (struct sp_dev_vdata *)match->data; -#endif + return NULL; } static struct sp_dev_vdata *sp_get_acpi_version(struct platform_device *pdev) { -#ifdef CONFIG_ACPI const struct acpi_device_id *match; match = acpi_match_device(sp_acpi_match, &pdev->dev); if (match && match->driver_data) return (struct sp_dev_vdata *)match->driver_data; -#endif + return NULL; } @@ -212,12 +206,8 @@ static int sp_platform_resume(struct platform_device *pdev) static struct platform_driver sp_platform_driver = { .driver = { .name = "ccp", -#ifdef CONFIG_ACPI .acpi_match_table = sp_acpi_match, -#endif -#ifdef CONFIG_OF .of_match_table = sp_of_match, -#endif }, .probe = sp_platform_probe, .remove_new = sp_platform_remove, diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 4b20b94e6371a..5f3f2f1dd71ef 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -2833,12 +2833,9 @@ void hisi_qm_uninit(struct hisi_qm *qm) hisi_qm_set_state(qm, QM_NOT_READY); up_write(&qm->qps_lock); + qm_remove_uacce(qm); qm_irqs_unregister(qm); hisi_qm_pci_uninit(qm); - if (qm->use_sva) { - uacce_remove(qm->uacce); - qm->uacce = NULL; - } } EXPORT_SYMBOL_GPL(hisi_qm_uninit); diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index f028dcfd0ead7..fcbeddf22dd2b 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -481,8 +481,10 @@ static void sec_alg_resource_free(struct sec_ctx *ctx, if (ctx->pbuf_supported) sec_free_pbuf_resource(dev, qp_ctx->res); - if (ctx->alg_type == SEC_AEAD) + if (ctx->alg_type == SEC_AEAD) { sec_free_mac_resource(dev, qp_ctx->res); + sec_free_aiv_resource(dev, qp_ctx->res); + } } static int sec_alloc_qp_ctx_resource(struct hisi_qm *qm, struct sec_ctx *ctx, diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c index dfd3baf0a8d87..64a2e87a55b3c 100644 --- a/drivers/crypto/intel/iaa/iaa_crypto_main.c +++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c @@ -908,6 +908,8 @@ static int save_iaa_wq(struct idxd_wq *wq) return -EINVAL; cpus_per_iaa = (nr_nodes * nr_cpus_per_node) / nr_iaa; + if (!cpus_per_iaa) + cpus_per_iaa = 1; out: return 0; } @@ -923,10 +925,12 @@ static void remove_iaa_wq(struct idxd_wq *wq) } } - if (nr_iaa) + if (nr_iaa) { cpus_per_iaa = (nr_nodes * nr_cpus_per_node) / nr_iaa; - else - cpus_per_iaa = 0; + if (!cpus_per_iaa) + cpus_per_iaa = 1; + } else + cpus_per_iaa = 1; } static int wq_table_add_wqs(int iaa, int cpu) @@ -1324,7 +1328,7 @@ static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req, *compression_crc = idxd_desc->iax_completion->crc; - if (!ctx->async_mode) + if (!ctx->async_mode || disable_async) idxd_free_desc(wq, idxd_desc); out: return ret; @@ -1570,7 +1574,7 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req, *dlen = req->dlen; - if (!ctx->async_mode) + if (!ctx->async_mode || disable_async) idxd_free_desc(wq, idxd_desc); /* Update stats */ diff --git a/drivers/crypto/intel/qat/Kconfig b/drivers/crypto/intel/qat/Kconfig index c120f6715a09a..02fb8abe4e6ed 100644 --- a/drivers/crypto/intel/qat/Kconfig +++ b/drivers/crypto/intel/qat/Kconfig @@ -106,3 +106,17 @@ config CRYPTO_DEV_QAT_C62XVF To compile this as a module, choose M here: the module will be called qat_c62xvf. + +config CRYPTO_DEV_QAT_ERROR_INJECTION + bool "Support for Intel(R) QAT Devices Heartbeat Error Injection" + depends on CRYPTO_DEV_QAT + depends on DEBUG_FS + help + Enables a mechanism that allows to inject a heartbeat error on + Intel(R) QuickAssist devices for testing purposes. + + This is intended for developer use only. + If unsure, say N. + + This functionality is available via debugfs entry of the Intel(R) + QuickAssist device diff --git a/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c index a87d29ae724fe..7b8abfb797fff 100644 --- a/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c +++ b/drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c @@ -296,7 +296,7 @@ static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev) { if (adf_gen4_init_thd2arb_map(accel_dev)) dev_warn(&GET_DEV(accel_dev), - "Generate of the thread to arbiter map failed"); + "Failed to generate thread to arbiter mapping"); return GET_HW_DATA(accel_dev)->thd_to_arb_map; } @@ -372,6 +372,13 @@ static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev) if (!fw_config) return 0; + /* If dcc, all rings handle compression requests */ + if (adf_get_service_enabled(accel_dev) == SVC_DCC) { + for (i = 0; i < RP_GROUP_COUNT; i++) + rps[i] = COMP; + goto set_mask; + } + for (i = 0; i < RP_GROUP_COUNT; i++) { switch (fw_config[i].ae_mask) { case ADF_AE_GROUP_0: @@ -400,6 +407,7 @@ static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev) } } +set_mask: ring_to_svc_map = rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_0_SHIFT | rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_1_SHIFT | rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_2_SHIFT | diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c index 94a0ebb03d8c9..7a5c5f9711c8b 100644 --- a/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c +++ b/drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c @@ -208,7 +208,7 @@ static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev) { if (adf_gen4_init_thd2arb_map(accel_dev)) dev_warn(&GET_DEV(accel_dev), - "Generate of the thread to arbiter map failed"); + "Failed to generate thread to arbiter mapping"); return GET_HW_DATA(accel_dev)->thd_to_arb_map; } @@ -331,6 +331,13 @@ static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev) if (!fw_config) return 0; + /* If dcc, all rings handle compression requests */ + if (adf_get_service_enabled(accel_dev) == SVC_DCC) { + for (i = 0; i < RP_GROUP_COUNT; i++) + rps[i] = COMP; + goto set_mask; + } + for (i = 0; i < RP_GROUP_COUNT; i++) { switch (fw_config[i].ae_mask) { case ADF_AE_GROUP_0: @@ -359,6 +366,7 @@ static u16 get_ring_to_svc_map(struct adf_accel_dev *accel_dev) } } +set_mask: ring_to_svc_map = rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_0_SHIFT | rps[RP_GROUP_1] << ADF_CFG_SERV_RING_PAIR_1_SHIFT | rps[RP_GROUP_0] << ADF_CFG_SERV_RING_PAIR_2_SHIFT | diff --git a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c index 9762f2bf7727f..d26564cebdec4 100644 --- a/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c +++ b/drivers/crypto/intel/qat/qat_4xxx/adf_drv.c @@ -197,7 +197,9 @@ module_pci_driver(adf_driver); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Intel"); MODULE_FIRMWARE(ADF_4XXX_FW); +MODULE_FIRMWARE(ADF_402XX_FW); MODULE_FIRMWARE(ADF_4XXX_MMP); +MODULE_FIRMWARE(ADF_402XX_MMP); MODULE_DESCRIPTION("Intel(R) QuickAssist Technology"); MODULE_VERSION(ADF_DRV_VERSION); MODULE_SOFTDEP("pre: crypto-intel_qat"); diff --git a/drivers/crypto/intel/qat/qat_common/Makefile b/drivers/crypto/intel/qat/qat_common/Makefile index 6908727bff3b8..5915cde8a7aa4 100644 --- a/drivers/crypto/intel/qat/qat_common/Makefile +++ b/drivers/crypto/intel/qat/qat_common/Makefile @@ -53,3 +53,5 @@ intel_qat-$(CONFIG_PCI_IOV) += adf_sriov.o adf_vf_isr.o adf_pfvf_utils.o \ adf_pfvf_pf_msg.o adf_pfvf_pf_proto.o \ adf_pfvf_vf_msg.o adf_pfvf_vf_proto.o \ adf_gen2_pfvf.o adf_gen4_pfvf.o + +intel_qat-$(CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION) += adf_heartbeat_inject.o diff --git a/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h index a16c7e6edc65d..0f26aa976c8ca 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h +++ b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h @@ -332,6 +332,7 @@ struct adf_accel_vf_info { struct ratelimit_state vf2pf_ratelimit; u32 vf_nr; bool init; + bool restarting; u8 vf_compat_ver; }; @@ -401,6 +402,7 @@ struct adf_accel_dev { struct adf_error_counters ras_errors; struct mutex state_lock; /* protect state of the device */ bool is_vf; + bool autoreset_on_error; u32 accel_id; }; #endif diff --git a/drivers/crypto/intel/qat/qat_common/adf_aer.c b/drivers/crypto/intel/qat/qat_common/adf_aer.c index a39e70bd4b21b..04260f61d0429 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_aer.c +++ b/drivers/crypto/intel/qat/qat_common/adf_aer.c @@ -7,8 +7,15 @@ #include #include "adf_accel_devices.h" #include "adf_common_drv.h" +#include "adf_pfvf_pf_msg.h" + +struct adf_fatal_error_data { + struct adf_accel_dev *accel_dev; + struct work_struct work; +}; static struct workqueue_struct *device_reset_wq; +static struct workqueue_struct *device_sriov_wq; static pci_ers_result_t adf_error_detected(struct pci_dev *pdev, pci_channel_state_t state) @@ -26,6 +33,19 @@ static pci_ers_result_t adf_error_detected(struct pci_dev *pdev, return PCI_ERS_RESULT_DISCONNECT; } + set_bit(ADF_STATUS_RESTARTING, &accel_dev->status); + if (accel_dev->hw_device->exit_arb) { + dev_dbg(&pdev->dev, "Disabling arbitration\n"); + accel_dev->hw_device->exit_arb(accel_dev); + } + adf_error_notifier(accel_dev); + adf_pf2vf_notify_fatal_error(accel_dev); + adf_dev_restarting_notify(accel_dev); + adf_pf2vf_notify_restarting(accel_dev); + adf_pf2vf_wait_for_restarting_complete(accel_dev); + pci_clear_master(pdev); + adf_dev_down(accel_dev, false); + return PCI_ERS_RESULT_NEED_RESET; } @@ -37,6 +57,13 @@ struct adf_reset_dev_data { struct work_struct reset_work; }; +/* sriov dev data */ +struct adf_sriov_dev_data { + struct adf_accel_dev *accel_dev; + struct completion compl; + struct work_struct sriov_work; +}; + void adf_reset_sbr(struct adf_accel_dev *accel_dev) { struct pci_dev *pdev = accel_to_pci_dev(accel_dev); @@ -82,11 +109,22 @@ void adf_dev_restore(struct adf_accel_dev *accel_dev) } } +static void adf_device_sriov_worker(struct work_struct *work) +{ + struct adf_sriov_dev_data *sriov_data = + container_of(work, struct adf_sriov_dev_data, sriov_work); + + adf_reenable_sriov(sriov_data->accel_dev); + complete(&sriov_data->compl); +} + static void adf_device_reset_worker(struct work_struct *work) { struct adf_reset_dev_data *reset_data = container_of(work, struct adf_reset_dev_data, reset_work); struct adf_accel_dev *accel_dev = reset_data->accel_dev; + unsigned long wait_jiffies = msecs_to_jiffies(10000); + struct adf_sriov_dev_data sriov_data; adf_dev_restarting_notify(accel_dev); if (adf_dev_restart(accel_dev)) { @@ -97,14 +135,22 @@ static void adf_device_reset_worker(struct work_struct *work) WARN(1, "QAT: device restart failed. Device is unusable\n"); return; } + + sriov_data.accel_dev = accel_dev; + init_completion(&sriov_data.compl); + INIT_WORK(&sriov_data.sriov_work, adf_device_sriov_worker); + queue_work(device_sriov_wq, &sriov_data.sriov_work); + if (wait_for_completion_timeout(&sriov_data.compl, wait_jiffies)) + adf_pf2vf_notify_restarted(accel_dev); + adf_dev_restarted_notify(accel_dev); clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status); /* The dev is back alive. Notify the caller if in sync mode */ - if (reset_data->mode == ADF_DEV_RESET_SYNC) - complete(&reset_data->compl); - else + if (reset_data->mode == ADF_DEV_RESET_ASYNC) kfree(reset_data); + else + complete(&reset_data->compl); } static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, @@ -136,6 +182,7 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, if (!timeout) { dev_err(&GET_DEV(accel_dev), "Reset device timeout expired\n"); + cancel_work_sync(&reset_data->reset_work); ret = -EFAULT; } kfree(reset_data); @@ -147,14 +194,25 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, static pci_ers_result_t adf_slot_reset(struct pci_dev *pdev) { struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev); + int res = 0; if (!accel_dev) { pr_err("QAT: Can't find acceleration device\n"); return PCI_ERS_RESULT_DISCONNECT; } - if (adf_dev_aer_schedule_reset(accel_dev, ADF_DEV_RESET_SYNC)) + + if (!pdev->is_busmaster) + pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); + res = adf_dev_up(accel_dev, false); + if (res && res != -EALREADY) return PCI_ERS_RESULT_DISCONNECT; + adf_reenable_sriov(accel_dev); + adf_pf2vf_notify_restarted(accel_dev); + adf_dev_restarted_notify(accel_dev); + clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status); return PCI_ERS_RESULT_RECOVERED; } @@ -171,11 +229,62 @@ const struct pci_error_handlers adf_err_handler = { }; EXPORT_SYMBOL_GPL(adf_err_handler); +int adf_dev_autoreset(struct adf_accel_dev *accel_dev) +{ + if (accel_dev->autoreset_on_error) + return adf_dev_aer_schedule_reset(accel_dev, ADF_DEV_RESET_ASYNC); + + return 0; +} + +static void adf_notify_fatal_error_worker(struct work_struct *work) +{ + struct adf_fatal_error_data *wq_data = + container_of(work, struct adf_fatal_error_data, work); + struct adf_accel_dev *accel_dev = wq_data->accel_dev; + struct adf_hw_device_data *hw_device = accel_dev->hw_device; + + adf_error_notifier(accel_dev); + + if (!accel_dev->is_vf) { + /* Disable arbitration to stop processing of new requests */ + if (accel_dev->autoreset_on_error && hw_device->exit_arb) + hw_device->exit_arb(accel_dev); + if (accel_dev->pf.vf_info) + adf_pf2vf_notify_fatal_error(accel_dev); + adf_dev_autoreset(accel_dev); + } + + kfree(wq_data); +} + +int adf_notify_fatal_error(struct adf_accel_dev *accel_dev) +{ + struct adf_fatal_error_data *wq_data; + + wq_data = kzalloc(sizeof(*wq_data), GFP_ATOMIC); + if (!wq_data) + return -ENOMEM; + + wq_data->accel_dev = accel_dev; + INIT_WORK(&wq_data->work, adf_notify_fatal_error_worker); + adf_misc_wq_queue_work(&wq_data->work); + + return 0; +} + int adf_init_aer(void) { device_reset_wq = alloc_workqueue("qat_device_reset_wq", WQ_MEM_RECLAIM, 0); - return !device_reset_wq ? -EFAULT : 0; + if (!device_reset_wq) + return -EFAULT; + + device_sriov_wq = alloc_workqueue("qat_device_sriov_wq", 0, 0); + if (!device_sriov_wq) + return -EFAULT; + + return 0; } void adf_exit_aer(void) @@ -183,4 +292,8 @@ void adf_exit_aer(void) if (device_reset_wq) destroy_workqueue(device_reset_wq); device_reset_wq = NULL; + + if (device_sriov_wq) + destroy_workqueue(device_sriov_wq); + device_sriov_wq = NULL; } diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h b/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h index 322b76903a737..e015ad6cace2b 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h +++ b/drivers/crypto/intel/qat/qat_common/adf_cfg_strings.h @@ -49,5 +49,6 @@ ADF_ETRMGR_BANK "%d" ADF_ETRMGR_CORE_AFFINITY #define ADF_ACCEL_STR "Accelerator%d" #define ADF_HEARTBEAT_TIMER "HeartbeatTimer" +#define ADF_SRIOV_ENABLED "SriovEnabled" #endif diff --git a/drivers/crypto/intel/qat/qat_common/adf_clock.c b/drivers/crypto/intel/qat/qat_common/adf_clock.c index 01e0a389e462b..cf89f57de2a70 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_clock.c +++ b/drivers/crypto/intel/qat/qat_common/adf_clock.c @@ -83,6 +83,9 @@ static int measure_clock(struct adf_accel_dev *accel_dev, u32 *frequency) } delta_us = timespec_to_us(&ts3) - timespec_to_us(&ts1); + if (!delta_us) + return -EINVAL; + temp = (timestamp2 - timestamp1) * ME_CLK_DIVIDER * 10; temp = DIV_ROUND_CLOSEST_ULL(temp, delta_us); /* diff --git a/drivers/crypto/intel/qat/qat_common/adf_cnv_dbgfs.c b/drivers/crypto/intel/qat/qat_common/adf_cnv_dbgfs.c index 07119c487da01..627953a72d478 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_cnv_dbgfs.c +++ b/drivers/crypto/intel/qat/qat_common/adf_cnv_dbgfs.c @@ -16,7 +16,6 @@ #define CNV_ERR_INFO_MASK GENMASK(11, 0) #define CNV_ERR_TYPE_MASK GENMASK(15, 12) -#define CNV_SLICE_ERR_MASK GENMASK(7, 0) #define CNV_SLICE_ERR_SIGN_BIT_INDEX 7 #define CNV_DELTA_ERR_SIGN_BIT_INDEX 11 diff --git a/drivers/crypto/intel/qat/qat_common/adf_common_drv.h b/drivers/crypto/intel/qat/qat_common/adf_common_drv.h index f06188033a93f..57328249c89e7 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_common_drv.h +++ b/drivers/crypto/intel/qat/qat_common/adf_common_drv.h @@ -40,6 +40,7 @@ enum adf_event { ADF_EVENT_SHUTDOWN, ADF_EVENT_RESTARTING, ADF_EVENT_RESTARTED, + ADF_EVENT_FATAL_ERROR, }; struct service_hndl { @@ -60,6 +61,8 @@ int adf_dev_restart(struct adf_accel_dev *accel_dev); void adf_devmgr_update_class_index(struct adf_hw_device_data *hw_data); void adf_clean_vf_map(bool); +int adf_notify_fatal_error(struct adf_accel_dev *accel_dev); +void adf_error_notifier(struct adf_accel_dev *accel_dev); int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev, struct adf_accel_dev *pf); void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev, @@ -84,12 +87,14 @@ int adf_ae_stop(struct adf_accel_dev *accel_dev); extern const struct pci_error_handlers adf_err_handler; void adf_reset_sbr(struct adf_accel_dev *accel_dev); void adf_reset_flr(struct adf_accel_dev *accel_dev); +int adf_dev_autoreset(struct adf_accel_dev *accel_dev); void adf_dev_restore(struct adf_accel_dev *accel_dev); int adf_init_aer(void); void adf_exit_aer(void); int adf_init_arb(struct adf_accel_dev *accel_dev); void adf_exit_arb(struct adf_accel_dev *accel_dev); void adf_update_ring_arb(struct adf_etr_ring_data *ring); +int adf_disable_arb_thd(struct adf_accel_dev *accel_dev, u32 ae, u32 thr); int adf_dev_get(struct adf_accel_dev *accel_dev); void adf_dev_put(struct adf_accel_dev *accel_dev); @@ -188,6 +193,7 @@ bool adf_misc_wq_queue_delayed_work(struct delayed_work *work, #if defined(CONFIG_PCI_IOV) int adf_sriov_configure(struct pci_dev *pdev, int numvfs); void adf_disable_sriov(struct adf_accel_dev *accel_dev); +void adf_reenable_sriov(struct adf_accel_dev *accel_dev); void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask); void adf_disable_all_vf2pf_interrupts(struct adf_accel_dev *accel_dev); bool adf_recv_and_handle_pf2vf_msg(struct adf_accel_dev *accel_dev); @@ -208,6 +214,10 @@ static inline void adf_disable_sriov(struct adf_accel_dev *accel_dev) { } +static inline void adf_reenable_sriov(struct adf_accel_dev *accel_dev) +{ +} + static inline int adf_init_pf_wq(void) { return 0; diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c index 9985683056d5f..f752653ccb47e 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c +++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.c @@ -398,6 +398,9 @@ int adf_gen4_init_thd2arb_map(struct adf_accel_dev *accel_dev) ADF_GEN4_ADMIN_ACCELENGINES; if (srv_id == SVC_DCC) { + if (ae_cnt > ICP_QAT_HW_AE_DELIMITER) + return -EINVAL; + memcpy(thd2arb_map, thrd_to_arb_map_dcc, array_size(sizeof(*thd2arb_map), ae_cnt)); return 0; diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c index 048c246079390..2dd3772bf58a6 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c +++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_ras.c @@ -1007,8 +1007,7 @@ static bool adf_handle_spppar_err(struct adf_accel_dev *accel_dev, static bool adf_handle_ssmcpppar_err(struct adf_accel_dev *accel_dev, void __iomem *csr, u32 iastatssm) { - u32 reg = ADF_CSR_RD(csr, ADF_GEN4_SSMCPPERR); - u32 bits_num = BITS_PER_REG(reg); + u32 reg, bits_num = BITS_PER_REG(reg); bool reset_required = false; unsigned long errs_bits; u32 bit_iterator; @@ -1106,8 +1105,7 @@ static bool adf_handle_rf_parr_err(struct adf_accel_dev *accel_dev, static bool adf_handle_ser_err_ssmsh(struct adf_accel_dev *accel_dev, void __iomem *csr, u32 iastatssm) { - u32 reg = ADF_CSR_RD(csr, ADF_GEN4_SER_ERR_SSMSH); - u32 bits_num = BITS_PER_REG(reg); + u32 reg, bits_num = BITS_PER_REG(reg); bool reset_required = false; unsigned long errs_bits; u32 bit_iterator; diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.c b/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.c index 7fc7a77f6aed9..c7ad8cf07863b 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.c +++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_tl.c @@ -149,5 +149,6 @@ void adf_gen4_init_tl_data(struct adf_tl_hw_data *tl_data) tl_data->sl_exec_counters = sl_exec_counters; tl_data->rp_counters = rp_counters; tl_data->num_rp_counters = ARRAY_SIZE(rp_counters); + tl_data->max_sl_cnt = ADF_GEN4_TL_MAX_SLICES_PER_TYPE; } EXPORT_SYMBOL_GPL(adf_gen4_init_tl_data); diff --git a/drivers/crypto/intel/qat/qat_common/adf_heartbeat.c b/drivers/crypto/intel/qat/qat_common/adf_heartbeat.c index 13f48d2f6da88..b19aa1ef8eeed 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_heartbeat.c +++ b/drivers/crypto/intel/qat/qat_common/adf_heartbeat.c @@ -23,12 +23,6 @@ #define ADF_HB_EMPTY_SIG 0xA5A5A5A5 -/* Heartbeat counter pair */ -struct hb_cnt_pair { - __u16 resp_heartbeat_cnt; - __u16 req_heartbeat_cnt; -}; - static int adf_hb_check_polling_freq(struct adf_accel_dev *accel_dev) { u64 curr_time = adf_clock_get_current_time(); @@ -211,6 +205,19 @@ static int adf_hb_get_status(struct adf_accel_dev *accel_dev) return ret; } +static void adf_heartbeat_reset(struct adf_accel_dev *accel_dev) +{ + u64 curr_time = adf_clock_get_current_time(); + u64 time_since_reset = curr_time - accel_dev->heartbeat->last_hb_reset_time; + + if (time_since_reset < ADF_CFG_HB_RESET_MS) + return; + + accel_dev->heartbeat->last_hb_reset_time = curr_time; + if (adf_notify_fatal_error(accel_dev)) + dev_err(&GET_DEV(accel_dev), "Failed to notify fatal error\n"); +} + void adf_heartbeat_status(struct adf_accel_dev *accel_dev, enum adf_device_heartbeat_status *hb_status) { @@ -235,6 +242,7 @@ void adf_heartbeat_status(struct adf_accel_dev *accel_dev, "Heartbeat ERROR: QAT is not responding.\n"); *hb_status = HB_DEV_UNRESPONSIVE; hb->hb_failed_counter++; + adf_heartbeat_reset(accel_dev); return; } diff --git a/drivers/crypto/intel/qat/qat_common/adf_heartbeat.h b/drivers/crypto/intel/qat/qat_common/adf_heartbeat.h index b22e3cb29798e..16fdfb48b196a 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_heartbeat.h +++ b/drivers/crypto/intel/qat/qat_common/adf_heartbeat.h @@ -13,17 +13,26 @@ struct dentry; #define ADF_CFG_HB_TIMER_DEFAULT_MS 500 #define ADF_CFG_HB_COUNT_THRESHOLD 3 +#define ADF_CFG_HB_RESET_MS 5000 + enum adf_device_heartbeat_status { HB_DEV_UNRESPONSIVE = 0, HB_DEV_ALIVE, HB_DEV_UNSUPPORTED, }; +/* Heartbeat counter pair */ +struct hb_cnt_pair { + __u16 resp_heartbeat_cnt; + __u16 req_heartbeat_cnt; +}; + struct adf_heartbeat { unsigned int hb_sent_counter; unsigned int hb_failed_counter; unsigned int hb_timer; u64 last_hb_check_time; + u64 last_hb_reset_time; bool ctrs_cnt_checked; struct hb_dma_addr { dma_addr_t phy_addr; @@ -35,6 +44,9 @@ struct adf_heartbeat { struct dentry *cfg; struct dentry *sent; struct dentry *failed; +#ifdef CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION + struct dentry *inject_error; +#endif } dbgfs; }; @@ -51,6 +63,15 @@ void adf_heartbeat_status(struct adf_accel_dev *accel_dev, enum adf_device_heartbeat_status *hb_status); void adf_heartbeat_check_ctrs(struct adf_accel_dev *accel_dev); +#ifdef CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION +int adf_heartbeat_inject_error(struct adf_accel_dev *accel_dev); +#else +static inline int adf_heartbeat_inject_error(struct adf_accel_dev *accel_dev) +{ + return -EPERM; +} +#endif + #else static inline int adf_heartbeat_init(struct adf_accel_dev *accel_dev) { diff --git a/drivers/crypto/intel/qat/qat_common/adf_heartbeat_dbgfs.c b/drivers/crypto/intel/qat/qat_common/adf_heartbeat_dbgfs.c index 2661af6a2ef69..5cd6c2d6f90ac 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_heartbeat_dbgfs.c +++ b/drivers/crypto/intel/qat/qat_common/adf_heartbeat_dbgfs.c @@ -155,6 +155,43 @@ static const struct file_operations adf_hb_cfg_fops = { .write = adf_hb_cfg_write, }; +static ssize_t adf_hb_error_inject_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct adf_accel_dev *accel_dev = file->private_data; + size_t written_chars; + char buf[3]; + int ret; + + /* last byte left as string termination */ + if (count != 2) + return -EINVAL; + + written_chars = simple_write_to_buffer(buf, sizeof(buf) - 1, + ppos, user_buf, count); + if (buf[0] != '1') + return -EINVAL; + + ret = adf_heartbeat_inject_error(accel_dev); + if (ret) { + dev_err(&GET_DEV(accel_dev), + "Heartbeat error injection failed with status %d\n", + ret); + return ret; + } + + dev_info(&GET_DEV(accel_dev), "Heartbeat error injection enabled\n"); + + return written_chars; +} + +static const struct file_operations adf_hb_error_inject_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .write = adf_hb_error_inject_write, +}; + void adf_heartbeat_dbgfs_add(struct adf_accel_dev *accel_dev) { struct adf_heartbeat *hb = accel_dev->heartbeat; @@ -171,6 +208,17 @@ void adf_heartbeat_dbgfs_add(struct adf_accel_dev *accel_dev) &hb->hb_failed_counter, &adf_hb_stats_fops); hb->dbgfs.cfg = debugfs_create_file("config", 0600, hb->dbgfs.base_dir, accel_dev, &adf_hb_cfg_fops); + + if (IS_ENABLED(CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION)) { + struct dentry *inject_error __maybe_unused; + + inject_error = debugfs_create_file("inject_error", 0200, + hb->dbgfs.base_dir, accel_dev, + &adf_hb_error_inject_fops); +#ifdef CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION + hb->dbgfs.inject_error = inject_error; +#endif + } } EXPORT_SYMBOL_GPL(adf_heartbeat_dbgfs_add); @@ -189,6 +237,10 @@ void adf_heartbeat_dbgfs_rm(struct adf_accel_dev *accel_dev) hb->dbgfs.failed = NULL; debugfs_remove(hb->dbgfs.cfg); hb->dbgfs.cfg = NULL; +#ifdef CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION + debugfs_remove(hb->dbgfs.inject_error); + hb->dbgfs.inject_error = NULL; +#endif debugfs_remove(hb->dbgfs.base_dir); hb->dbgfs.base_dir = NULL; } diff --git a/drivers/crypto/intel/qat/qat_common/adf_heartbeat_inject.c b/drivers/crypto/intel/qat/qat_common/adf_heartbeat_inject.c new file mode 100644 index 0000000000000..a3b474bdef6c8 --- /dev/null +++ b/drivers/crypto/intel/qat/qat_common/adf_heartbeat_inject.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2023 Intel Corporation */ +#include + +#include "adf_admin.h" +#include "adf_common_drv.h" +#include "adf_heartbeat.h" + +#define MAX_HB_TICKS 0xFFFFFFFF + +static int adf_hb_set_timer_to_max(struct adf_accel_dev *accel_dev) +{ + struct adf_hw_device_data *hw_data = accel_dev->hw_device; + + accel_dev->heartbeat->hb_timer = 0; + + if (hw_data->stop_timer) + hw_data->stop_timer(accel_dev); + + return adf_send_admin_hb_timer(accel_dev, MAX_HB_TICKS); +} + +static void adf_set_hb_counters_fail(struct adf_accel_dev *accel_dev, u32 ae, + u32 thr) +{ + struct hb_cnt_pair *stats = accel_dev->heartbeat->dma.virt_addr; + struct adf_hw_device_data *hw_device = accel_dev->hw_device; + const size_t max_aes = hw_device->get_num_aes(hw_device); + const size_t hb_ctrs = hw_device->num_hb_ctrs; + size_t thr_id = ae * hb_ctrs + thr; + u16 num_rsp = stats[thr_id].resp_heartbeat_cnt; + + /* + * Inject live.req != live.rsp and live.rsp == last.rsp + * to trigger the heartbeat error detection + */ + stats[thr_id].req_heartbeat_cnt++; + stats += (max_aes * hb_ctrs); + stats[thr_id].resp_heartbeat_cnt = num_rsp; +} + +int adf_heartbeat_inject_error(struct adf_accel_dev *accel_dev) +{ + struct adf_hw_device_data *hw_device = accel_dev->hw_device; + const size_t max_aes = hw_device->get_num_aes(hw_device); + const size_t hb_ctrs = hw_device->num_hb_ctrs; + u32 rand, rand_ae, rand_thr; + unsigned long ae_mask; + int ret; + + ae_mask = hw_device->ae_mask; + + do { + /* Ensure we have a valid ae */ + get_random_bytes(&rand, sizeof(rand)); + rand_ae = rand % max_aes; + } while (!test_bit(rand_ae, &ae_mask)); + + get_random_bytes(&rand, sizeof(rand)); + rand_thr = rand % hb_ctrs; + + /* Increase the heartbeat timer to prevent FW updating HB counters */ + ret = adf_hb_set_timer_to_max(accel_dev); + if (ret) + return ret; + + /* Configure worker threads to stop processing any packet */ + ret = adf_disable_arb_thd(accel_dev, rand_ae, rand_thr); + if (ret) + return ret; + + /* Change HB counters memory to simulate a hang */ + adf_set_hb_counters_fail(accel_dev, rand_ae, rand_thr); + + return 0; +} diff --git a/drivers/crypto/intel/qat/qat_common/adf_hw_arbiter.c b/drivers/crypto/intel/qat/qat_common/adf_hw_arbiter.c index da69566992467..65bd26b25abce 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_hw_arbiter.c +++ b/drivers/crypto/intel/qat/qat_common/adf_hw_arbiter.c @@ -103,3 +103,28 @@ void adf_exit_arb(struct adf_accel_dev *accel_dev) csr_ops->write_csr_ring_srv_arb_en(csr, i, 0); } EXPORT_SYMBOL_GPL(adf_exit_arb); + +int adf_disable_arb_thd(struct adf_accel_dev *accel_dev, u32 ae, u32 thr) +{ + void __iomem *csr = accel_dev->transport->banks[0].csr_addr; + struct adf_hw_device_data *hw_data = accel_dev->hw_device; + const u32 *thd_2_arb_cfg; + struct arb_info info; + u32 ae_thr_map; + + if (ADF_AE_STRAND0_THREAD == thr || ADF_AE_STRAND1_THREAD == thr) + thr = ADF_AE_ADMIN_THREAD; + + hw_data->get_arb_info(&info); + thd_2_arb_cfg = hw_data->get_arb_mapping(accel_dev); + if (!thd_2_arb_cfg) + return -EFAULT; + + /* Disable scheduling for this particular AE and thread */ + ae_thr_map = *(thd_2_arb_cfg + ae); + ae_thr_map &= ~(GENMASK(3, 0) << (thr * BIT(2))); + + WRITE_CSR_ARB_WT2SAM(csr, info.arb_offset, info.wt2sam_offset, ae, + ae_thr_map); + return 0; +} diff --git a/drivers/crypto/intel/qat/qat_common/adf_init.c b/drivers/crypto/intel/qat/qat_common/adf_init.c index f43ae9111553f..74f0818c07034 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_init.c +++ b/drivers/crypto/intel/qat/qat_common/adf_init.c @@ -433,6 +433,18 @@ int adf_dev_restarted_notify(struct adf_accel_dev *accel_dev) return 0; } +void adf_error_notifier(struct adf_accel_dev *accel_dev) +{ + struct service_hndl *service; + + list_for_each_entry(service, &service_table, list) { + if (service->event_hld(accel_dev, ADF_EVENT_FATAL_ERROR)) + dev_err(&GET_DEV(accel_dev), + "Failed to send error event to %s.\n", + service->name); + } +} + static int adf_dev_shutdown_cache_cfg(struct adf_accel_dev *accel_dev) { char services[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; diff --git a/drivers/crypto/intel/qat/qat_common/adf_isr.c b/drivers/crypto/intel/qat/qat_common/adf_isr.c index 3557a0d6dea28..9d60fff5a76c7 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_isr.c +++ b/drivers/crypto/intel/qat/qat_common/adf_isr.c @@ -139,8 +139,13 @@ static bool adf_handle_ras_int(struct adf_accel_dev *accel_dev) if (ras_ops->handle_interrupt && ras_ops->handle_interrupt(accel_dev, &reset_required)) { - if (reset_required) + if (reset_required) { dev_err(&GET_DEV(accel_dev), "Fatal error, reset required\n"); + if (adf_notify_fatal_error(accel_dev)) + dev_err(&GET_DEV(accel_dev), + "Failed to notify fatal error\n"); + } + return true; } diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_msg.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_msg.h index 204a424389926..d1b3ef9cadacc 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_msg.h +++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_msg.h @@ -99,6 +99,8 @@ enum pf2vf_msgtype { ADF_PF2VF_MSGTYPE_RESTARTING = 0x01, ADF_PF2VF_MSGTYPE_VERSION_RESP = 0x02, ADF_PF2VF_MSGTYPE_BLKMSG_RESP = 0x03, + ADF_PF2VF_MSGTYPE_FATAL_ERROR = 0x04, + ADF_PF2VF_MSGTYPE_RESTARTED = 0x05, /* Values from 0x10 are Gen4 specific, message type is only 4 bits in Gen2 devices. */ ADF_PF2VF_MSGTYPE_RP_RESET_RESP = 0x10, }; @@ -112,6 +114,7 @@ enum vf2pf_msgtype { ADF_VF2PF_MSGTYPE_LARGE_BLOCK_REQ = 0x07, ADF_VF2PF_MSGTYPE_MEDIUM_BLOCK_REQ = 0x08, ADF_VF2PF_MSGTYPE_SMALL_BLOCK_REQ = 0x09, + ADF_VF2PF_MSGTYPE_RESTARTING_COMPLETE = 0x0a, /* Values from 0x10 are Gen4 specific, message type is only 4 bits in Gen2 devices. */ ADF_VF2PF_MSGTYPE_RP_RESET = 0x10, }; @@ -124,8 +127,10 @@ enum pfvf_compatibility_version { ADF_PFVF_COMPAT_FAST_ACK = 0x03, /* Ring to service mapping support for non-standard mappings */ ADF_PFVF_COMPAT_RING_TO_SVC_MAP = 0x04, + /* Fallback compat */ + ADF_PFVF_COMPAT_FALLBACK = 0x05, /* Reference to the latest version */ - ADF_PFVF_COMPAT_THIS_VERSION = 0x04, + ADF_PFVF_COMPAT_THIS_VERSION = 0x05, }; /* PF->VF Version Response */ diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c index 14c069f0d71a5..0e31f4b41844e 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c +++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c @@ -1,21 +1,83 @@ // SPDX-License-Identifier: (BSD-3-Clause OR GPL-2.0-only) /* Copyright(c) 2015 - 2021 Intel Corporation */ +#include #include #include "adf_accel_devices.h" #include "adf_pfvf_msg.h" #include "adf_pfvf_pf_msg.h" #include "adf_pfvf_pf_proto.h" +#define ADF_PF_WAIT_RESTARTING_COMPLETE_DELAY 100 +#define ADF_VF_SHUTDOWN_RETRY 100 + void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev) { struct adf_accel_vf_info *vf; struct pfvf_message msg = { .type = ADF_PF2VF_MSGTYPE_RESTARTING }; int i, num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev)); + dev_dbg(&GET_DEV(accel_dev), "pf2vf notify restarting\n"); for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) { - if (vf->init && adf_send_pf2vf_msg(accel_dev, i, msg)) + vf->restarting = false; + if (!vf->init) + continue; + if (adf_send_pf2vf_msg(accel_dev, i, msg)) dev_err(&GET_DEV(accel_dev), "Failed to send restarting msg to VF%d\n", i); + else if (vf->vf_compat_ver >= ADF_PFVF_COMPAT_FALLBACK) + vf->restarting = true; + } +} + +void adf_pf2vf_wait_for_restarting_complete(struct adf_accel_dev *accel_dev) +{ + int num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev)); + int i, retries = ADF_VF_SHUTDOWN_RETRY; + struct adf_accel_vf_info *vf; + bool vf_running; + + dev_dbg(&GET_DEV(accel_dev), "pf2vf wait for restarting complete\n"); + do { + vf_running = false; + for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) + if (vf->restarting) + vf_running = true; + if (!vf_running) + break; + msleep(ADF_PF_WAIT_RESTARTING_COMPLETE_DELAY); + } while (--retries); + + if (vf_running) + dev_warn(&GET_DEV(accel_dev), "Some VFs are still running\n"); +} + +void adf_pf2vf_notify_restarted(struct adf_accel_dev *accel_dev) +{ + struct pfvf_message msg = { .type = ADF_PF2VF_MSGTYPE_RESTARTED }; + int i, num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev)); + struct adf_accel_vf_info *vf; + + dev_dbg(&GET_DEV(accel_dev), "pf2vf notify restarted\n"); + for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) { + if (vf->init && vf->vf_compat_ver >= ADF_PFVF_COMPAT_FALLBACK && + adf_send_pf2vf_msg(accel_dev, i, msg)) + dev_err(&GET_DEV(accel_dev), + "Failed to send restarted msg to VF%d\n", i); + } +} + +void adf_pf2vf_notify_fatal_error(struct adf_accel_dev *accel_dev) +{ + struct pfvf_message msg = { .type = ADF_PF2VF_MSGTYPE_FATAL_ERROR }; + int i, num_vfs = pci_num_vf(accel_to_pci_dev(accel_dev)); + struct adf_accel_vf_info *vf; + + dev_dbg(&GET_DEV(accel_dev), "pf2vf notify fatal error\n"); + for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) { + if (vf->init && vf->vf_compat_ver >= ADF_PFVF_COMPAT_FALLBACK && + adf_send_pf2vf_msg(accel_dev, i, msg)) + dev_err(&GET_DEV(accel_dev), + "Failed to send fatal error msg to VF%d\n", i); } } diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.h index e8982d1ac8962..f203d88c919c2 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.h +++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.h @@ -5,7 +5,28 @@ #include "adf_accel_devices.h" +#if defined(CONFIG_PCI_IOV) void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev); +void adf_pf2vf_wait_for_restarting_complete(struct adf_accel_dev *accel_dev); +void adf_pf2vf_notify_restarted(struct adf_accel_dev *accel_dev); +void adf_pf2vf_notify_fatal_error(struct adf_accel_dev *accel_dev); +#else +static inline void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev) +{ +} + +static inline void adf_pf2vf_wait_for_restarting_complete(struct adf_accel_dev *accel_dev) +{ +} + +static inline void adf_pf2vf_notify_restarted(struct adf_accel_dev *accel_dev) +{ +} + +static inline void adf_pf2vf_notify_fatal_error(struct adf_accel_dev *accel_dev) +{ +} +#endif typedef int (*adf_pf2vf_blkmsg_provider)(struct adf_accel_dev *accel_dev, u8 *buffer, u8 compat); diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c index 388e58bcbcaf2..9ab93fbfefde9 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c +++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_proto.c @@ -291,6 +291,14 @@ static int adf_handle_vf2pf_msg(struct adf_accel_dev *accel_dev, u8 vf_nr, vf_info->init = false; } break; + case ADF_VF2PF_MSGTYPE_RESTARTING_COMPLETE: + { + dev_dbg(&GET_DEV(accel_dev), + "Restarting Complete received from VF%d\n", vf_nr); + vf_info->restarting = false; + vf_info->init = false; + } + break; case ADF_VF2PF_MSGTYPE_LARGE_BLOCK_REQ: case ADF_VF2PF_MSGTYPE_MEDIUM_BLOCK_REQ: case ADF_VF2PF_MSGTYPE_SMALL_BLOCK_REQ: diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.c index 1015155b63749..dc284a089c889 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.c +++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_proto.c @@ -308,6 +308,12 @@ static bool adf_handle_pf2vf_msg(struct adf_accel_dev *accel_dev, adf_pf2vf_handle_pf_restarting(accel_dev); return false; + case ADF_PF2VF_MSGTYPE_RESTARTED: + dev_dbg(&GET_DEV(accel_dev), "Restarted message received from PF\n"); + return true; + case ADF_PF2VF_MSGTYPE_FATAL_ERROR: + dev_err(&GET_DEV(accel_dev), "Fatal error received from PF\n"); + return true; case ADF_PF2VF_MSGTYPE_VERSION_RESP: case ADF_PF2VF_MSGTYPE_BLKMSG_RESP: case ADF_PF2VF_MSGTYPE_RP_RESET_RESP: diff --git a/drivers/crypto/intel/qat/qat_common/adf_rl.c b/drivers/crypto/intel/qat/qat_common/adf_rl.c index de1b214dba1f9..e10f0024f4b85 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_rl.c +++ b/drivers/crypto/intel/qat/qat_common/adf_rl.c @@ -788,6 +788,24 @@ static void clear_sla(struct adf_rl *rl_data, struct rl_sla *sla) sla_type_arr[node_id] = NULL; } +static void free_all_sla(struct adf_accel_dev *accel_dev) +{ + struct adf_rl *rl_data = accel_dev->rate_limiting; + int sla_id; + + mutex_lock(&rl_data->rl_lock); + + for (sla_id = 0; sla_id < RL_NODES_CNT_MAX; sla_id++) { + if (!rl_data->sla[sla_id]) + continue; + + kfree(rl_data->sla[sla_id]); + rl_data->sla[sla_id] = NULL; + } + + mutex_unlock(&rl_data->rl_lock); +} + /** * add_update_sla() - handles the creation and the update of an SLA * @accel_dev: pointer to acceleration device structure @@ -1107,7 +1125,7 @@ int adf_rl_start(struct adf_accel_dev *accel_dev) } if ((fw_caps & RL_CAPABILITY_MASK) != RL_CAPABILITY_VALUE) { - dev_info(&GET_DEV(accel_dev), "not supported\n"); + dev_info(&GET_DEV(accel_dev), "feature not supported by FW\n"); ret = -EOPNOTSUPP; goto ret_free; } @@ -1155,7 +1173,7 @@ void adf_rl_stop(struct adf_accel_dev *accel_dev) return; adf_sysfs_rl_rm(accel_dev); - adf_rl_remove_sla_all(accel_dev, true); + free_all_sla(accel_dev); } void adf_rl_exit(struct adf_accel_dev *accel_dev) diff --git a/drivers/crypto/intel/qat/qat_common/adf_sriov.c b/drivers/crypto/intel/qat/qat_common/adf_sriov.c index f44025bb6f995..87a70c00c41ee 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_sriov.c +++ b/drivers/crypto/intel/qat/qat_common/adf_sriov.c @@ -60,7 +60,6 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev) /* This ptr will be populated when VFs will be created */ vf_info->accel_dev = accel_dev; vf_info->vf_nr = i; - vf_info->vf_compat_ver = 0; mutex_init(&vf_info->pf2vf_lock); ratelimit_state_init(&vf_info->vf2pf_ratelimit, @@ -84,6 +83,32 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev) return pci_enable_sriov(pdev, totalvfs); } +void adf_reenable_sriov(struct adf_accel_dev *accel_dev) +{ + struct pci_dev *pdev = accel_to_pci_dev(accel_dev); + char cfg[ADF_CFG_MAX_VAL_LEN_IN_BYTES] = {0}; + unsigned long val = 0; + + if (adf_cfg_get_param_value(accel_dev, ADF_GENERAL_SEC, + ADF_SRIOV_ENABLED, cfg)) + return; + + if (!accel_dev->pf.vf_info) + return; + + if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_CY, + &val, ADF_DEC)) + return; + + if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC, ADF_NUM_DC, + &val, ADF_DEC)) + return; + + set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status); + dev_dbg(&pdev->dev, "Re-enabling SRIOV\n"); + adf_enable_sriov(accel_dev); +} + /** * adf_disable_sriov() - Disable SRIOV for the device * @accel_dev: Pointer to accel device. @@ -103,6 +128,7 @@ void adf_disable_sriov(struct adf_accel_dev *accel_dev) return; adf_pf2vf_notify_restarting(accel_dev); + adf_pf2vf_wait_for_restarting_complete(accel_dev); pci_disable_sriov(accel_to_pci_dev(accel_dev)); /* Disable VF to PF interrupts */ @@ -115,8 +141,10 @@ void adf_disable_sriov(struct adf_accel_dev *accel_dev) for (i = 0, vf = accel_dev->pf.vf_info; i < totalvfs; i++, vf++) mutex_destroy(&vf->pf2vf_lock); - kfree(accel_dev->pf.vf_info); - accel_dev->pf.vf_info = NULL; + if (!test_bit(ADF_STATUS_RESTARTING, &accel_dev->status)) { + kfree(accel_dev->pf.vf_info); + accel_dev->pf.vf_info = NULL; + } } EXPORT_SYMBOL_GPL(adf_disable_sriov); @@ -194,6 +222,10 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs) if (ret) return ret; + val = 1; + adf_cfg_add_key_value_param(accel_dev, ADF_GENERAL_SEC, ADF_SRIOV_ENABLED, + &val, ADF_DEC); + return numvfs; } EXPORT_SYMBOL_GPL(adf_sriov_configure); diff --git a/drivers/crypto/intel/qat/qat_common/adf_sysfs.c b/drivers/crypto/intel/qat/qat_common/adf_sysfs.c index d450dad32c9e4..4e7f70d4049d3 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_sysfs.c +++ b/drivers/crypto/intel/qat/qat_common/adf_sysfs.c @@ -204,6 +204,42 @@ static ssize_t pm_idle_enabled_store(struct device *dev, struct device_attribute } static DEVICE_ATTR_RW(pm_idle_enabled); +static ssize_t auto_reset_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + char *auto_reset; + struct adf_accel_dev *accel_dev; + + accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); + if (!accel_dev) + return -EINVAL; + + auto_reset = accel_dev->autoreset_on_error ? "on" : "off"; + + return sysfs_emit(buf, "%s\n", auto_reset); +} + +static ssize_t auto_reset_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct adf_accel_dev *accel_dev; + bool enabled = false; + int ret; + + ret = kstrtobool(buf, &enabled); + if (ret) + return ret; + + accel_dev = adf_devmgr_pci_to_accel_dev(to_pci_dev(dev)); + if (!accel_dev) + return -EINVAL; + + accel_dev->autoreset_on_error = enabled; + + return count; +} +static DEVICE_ATTR_RW(auto_reset); + static DEVICE_ATTR_RW(state); static DEVICE_ATTR_RW(cfg_services); @@ -291,6 +327,7 @@ static struct attribute *qat_attrs[] = { &dev_attr_pm_idle_enabled.attr, &dev_attr_rp2srv.attr, &dev_attr_num_rps.attr, + &dev_attr_auto_reset.attr, NULL, }; diff --git a/drivers/crypto/intel/qat/qat_common/adf_telemetry.c b/drivers/crypto/intel/qat/qat_common/adf_telemetry.c index 2ff714d11bd2f..74fb0c2ed2412 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_telemetry.c +++ b/drivers/crypto/intel/qat/qat_common/adf_telemetry.c @@ -41,6 +41,20 @@ static int validate_tl_data(struct adf_tl_hw_data *tl_data) return 0; } +static int validate_tl_slice_counters(struct icp_qat_fw_init_admin_slice_cnt *slice_count, + u8 max_slices_per_type) +{ + u8 *sl_counter = (u8 *)slice_count; + int i; + + for (i = 0; i < ADF_TL_SL_CNT_COUNT; i++) { + if (sl_counter[i] > max_slices_per_type) + return -EINVAL; + } + + return 0; +} + static int adf_tl_alloc_mem(struct adf_accel_dev *accel_dev) { struct adf_tl_hw_data *tl_data = &GET_TL_DATA(accel_dev); @@ -214,6 +228,13 @@ int adf_tl_run(struct adf_accel_dev *accel_dev, int state) return ret; } + ret = validate_tl_slice_counters(&telemetry->slice_cnt, tl_data->max_sl_cnt); + if (ret) { + dev_err(dev, "invalid value returned by FW\n"); + adf_send_admin_tl_stop(accel_dev); + return ret; + } + telemetry->hbuffs = state; atomic_set(&telemetry->state, state); diff --git a/drivers/crypto/intel/qat/qat_common/adf_telemetry.h b/drivers/crypto/intel/qat/qat_common/adf_telemetry.h index 9be81cd3b8860..e54a406cc1b4a 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_telemetry.h +++ b/drivers/crypto/intel/qat/qat_common/adf_telemetry.h @@ -40,6 +40,7 @@ struct adf_tl_hw_data { u8 num_dev_counters; u8 num_rp_counters; u8 max_rp; + u8 max_sl_cnt; }; struct adf_telemetry { diff --git a/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c b/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c index bf8c0ee629175..2ba4aa22e0927 100644 --- a/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c +++ b/drivers/crypto/intel/qat/qat_common/qat_comp_algs.c @@ -13,15 +13,6 @@ #include "qat_compression.h" #include "qat_algs_send.h" -#define QAT_RFC_1950_HDR_SIZE 2 -#define QAT_RFC_1950_FOOTER_SIZE 4 -#define QAT_RFC_1950_CM_DEFLATE 8 -#define QAT_RFC_1950_CM_DEFLATE_CINFO_32K 7 -#define QAT_RFC_1950_CM_MASK 0x0f -#define QAT_RFC_1950_CM_OFFSET 4 -#define QAT_RFC_1950_DICT_MASK 0x20 -#define QAT_RFC_1950_COMP_HDR 0x785e - static DEFINE_MUTEX(algs_lock); static unsigned int active_devs; diff --git a/drivers/crypto/marvell/octeontx2/cn10k_cpt.c b/drivers/crypto/marvell/octeontx2/cn10k_cpt.c index 79b4e74804f6d..6bfc59e677478 100644 --- a/drivers/crypto/marvell/octeontx2/cn10k_cpt.c +++ b/drivers/crypto/marvell/octeontx2/cn10k_cpt.c @@ -138,6 +138,10 @@ int cn10k_cpt_hw_ctx_init(struct pci_dev *pdev, return -ENOMEM; cptr_dma = dma_map_single(&pdev->dev, hctx, CN10K_CPT_HW_CTX_SIZE, DMA_BIDIRECTIONAL); + if (dma_mapping_error(&pdev->dev, cptr_dma)) { + kfree(hctx); + return -ENOMEM; + } cn10k_cpt_hw_ctx_set(hctx, 1); er_ctx->hw_ctx = hctx; diff --git a/drivers/crypto/starfive/jh7110-rsa.c b/drivers/crypto/starfive/jh7110-rsa.c index cf8bda7f0855d..7ec14b5b84905 100644 --- a/drivers/crypto/starfive/jh7110-rsa.c +++ b/drivers/crypto/starfive/jh7110-rsa.c @@ -273,7 +273,6 @@ static int starfive_rsa_enc_core(struct starfive_cryp_ctx *ctx, int enc) err_rsa_crypt: writel(STARFIVE_RSA_RESET, cryp->base + STARFIVE_PKA_CACR_OFFSET); - kfree(rctx->rsa_data); return ret; } diff --git a/drivers/crypto/xilinx/zynqmp-aes-gcm.c b/drivers/crypto/xilinx/zynqmp-aes-gcm.c index 3c205324b22b6..e614057188409 100644 --- a/drivers/crypto/xilinx/zynqmp-aes-gcm.c +++ b/drivers/crypto/xilinx/zynqmp-aes-gcm.c @@ -231,7 +231,10 @@ static int zynqmp_handle_aes_req(struct crypto_engine *engine, err = zynqmp_aes_aead_cipher(areq); } + local_bh_disable(); crypto_finalize_aead_request(engine, areq, err); + local_bh_enable(); + return 0; } diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 1a3e6aafbdcc3..af5cb818f84d6 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -530,13 +530,15 @@ static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport) if (kstrtou32(acpi_device_uid(hb), 0, &uid)) return -EINVAL; - rc = acpi_get_genport_coordinates(uid, &dport->hb_coord); + rc = acpi_get_genport_coordinates(uid, dport->hb_coord); if (rc < 0) return rc; /* Adjust back to picoseconds from nanoseconds */ - dport->hb_coord.read_latency *= 1000; - dport->hb_coord.write_latency *= 1000; + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + dport->hb_coord[i].read_latency *= 1000; + dport->hb_coord[i].write_latency *= 1000; + } return 0; } diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c index 08fd0baea7a0e..fbf167f9d59d4 100644 --- a/drivers/cxl/core/cdat.c +++ b/drivers/cxl/core/cdat.c @@ -162,15 +162,22 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port, static int cxl_port_perf_data_calculate(struct cxl_port *port, struct xarray *dsmas_xa) { - struct access_coordinate c; + struct access_coordinate ep_c; + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; struct dsmas_entry *dent; int valid_entries = 0; unsigned long index; int rc; - rc = cxl_endpoint_get_perf_coordinates(port, &c); + rc = cxl_endpoint_get_perf_coordinates(port, &ep_c); if (rc) { - dev_dbg(&port->dev, "Failed to retrieve perf coordinates.\n"); + dev_dbg(&port->dev, "Failed to retrieve ep perf coordinates.\n"); + return rc; + } + + rc = cxl_hb_get_perf_coordinates(port, coord); + if (rc) { + dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n"); return rc; } @@ -185,18 +192,19 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, xa_for_each(dsmas_xa, index, dent) { int qos_class; - dent->coord.read_latency = dent->coord.read_latency + - c.read_latency; - dent->coord.write_latency = dent->coord.write_latency + - c.write_latency; - dent->coord.read_bandwidth = min_t(int, c.read_bandwidth, - dent->coord.read_bandwidth); - dent->coord.write_bandwidth = min_t(int, c.write_bandwidth, - dent->coord.write_bandwidth); - + cxl_coordinates_combine(&dent->coord, &dent->coord, &ep_c); + /* + * Keeping the host bridge coordinates separate from the dsmas + * coordinates in order to allow calculation of access class + * 0 and 1 for region later. + */ + cxl_coordinates_combine(&coord[ACCESS_COORDINATE_LOCAL], + &coord[ACCESS_COORDINATE_LOCAL], + &dent->coord); dent->entries = 1; - rc = cxl_root->ops->qos_class(cxl_root, &dent->coord, 1, - &qos_class); + rc = cxl_root->ops->qos_class(cxl_root, + &coord[ACCESS_COORDINATE_LOCAL], + 1, &qos_class); if (rc != 1) continue; @@ -389,36 +397,38 @@ EXPORT_SYMBOL_NS_GPL(cxl_endpoint_parse_cdat, CXL); static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg, const unsigned long end) { + struct acpi_cdat_sslbis_table { + struct acpi_cdat_header header; + struct acpi_cdat_sslbis sslbis_header; + struct acpi_cdat_sslbe entries[]; + } *tbl = (struct acpi_cdat_sslbis_table *)header; + int size = sizeof(header->cdat) + sizeof(tbl->sslbis_header); struct acpi_cdat_sslbis *sslbis; - int size = sizeof(header->cdat) + sizeof(*sslbis); struct cxl_port *port = arg; struct device *dev = &port->dev; - struct acpi_cdat_sslbe *entry; int remain, entries, i; u16 len; len = le16_to_cpu((__force __le16)header->cdat.length); remain = len - size; - if (!remain || remain % sizeof(*entry) || + if (!remain || remain % sizeof(tbl->entries[0]) || (unsigned long)header + len > end) { dev_warn(dev, "Malformed SSLBIS table length: (%u)\n", len); return -EINVAL; } - /* Skip common header */ - sslbis = (struct acpi_cdat_sslbis *)((unsigned long)header + - sizeof(header->cdat)); - + sslbis = &tbl->sslbis_header; /* Unrecognized data type, we can skip */ if (sslbis->data_type > ACPI_HMAT_WRITE_BANDWIDTH) return 0; - entries = remain / sizeof(*entry); - entry = (struct acpi_cdat_sslbe *)((unsigned long)header + sizeof(*sslbis)); + entries = remain / sizeof(tbl->entries[0]); + if (struct_size(tbl, entries, entries) != len) + return -EINVAL; for (i = 0; i < entries; i++) { - u16 x = le16_to_cpu((__force __le16)entry->portx_id); - u16 y = le16_to_cpu((__force __le16)entry->porty_id); + u16 x = le16_to_cpu((__force __le16)tbl->entries[i].portx_id); + u16 y = le16_to_cpu((__force __le16)tbl->entries[i].porty_id); __le64 le_base; __le16 le_val; struct cxl_dport *dport; @@ -448,8 +458,8 @@ static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg, break; } - le_base = (__force __le64)sslbis->entry_base_unit; - le_val = (__force __le16)entry->latency_or_bandwidth; + le_base = (__force __le64)tbl->sslbis_header.entry_base_unit; + le_val = (__force __le16)tbl->entries[i].latency_or_bandwidth; if (check_mul_overflow(le64_to_cpu(le_base), le16_to_cpu(le_val), &val)) @@ -462,8 +472,6 @@ static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg, sslbis->data_type, val); } - - entry++; } return 0; @@ -484,4 +492,26 @@ void cxl_switch_parse_cdat(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL); +/** + * cxl_coordinates_combine - Combine the two input coordinates + * + * @out: Output coordinate of c1 and c2 combined + * @c1: input coordinates + * @c2: input coordinates + */ +void cxl_coordinates_combine(struct access_coordinate *out, + struct access_coordinate *c1, + struct access_coordinate *c2) +{ + if (c1->write_bandwidth && c2->write_bandwidth) + out->write_bandwidth = min(c1->write_bandwidth, + c2->write_bandwidth); + out->write_latency = c1->write_latency + c2->write_latency; + + if (c1->read_bandwidth && c2->read_bandwidth) + out->read_bandwidth = min(c1->read_bandwidth, + c2->read_bandwidth); + out->read_latency = c1->read_latency + c2->read_latency; +} + MODULE_IMPORT_NS(CXL); diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 9adda4795eb78..65185c9fa0013 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -915,7 +915,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, payload->handles[i++] = gen->hdr.handle; dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log, - le16_to_cpu(payload->handles[i])); + le16_to_cpu(payload->handles[i - 1])); if (i == max_handles) { payload->nr_recs = i; @@ -946,24 +946,22 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; struct device *dev = mds->cxlds.dev; struct cxl_get_event_payload *payload; - struct cxl_mbox_cmd mbox_cmd; u8 log_type = type; u16 nr_rec; mutex_lock(&mds->event.log_lock); payload = mds->event.buf; - mbox_cmd = (struct cxl_mbox_cmd) { - .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, - .payload_in = &log_type, - .size_in = sizeof(log_type), - .payload_out = payload, - .size_out = mds->payload_size, - .min_out = struct_size(payload, records, 0), - }; - do { int rc, i; + struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, + .payload_in = &log_type, + .size_in = sizeof(log_type), + .payload_out = payload, + .size_out = mds->payload_size, + .min_out = struct_size(payload, records, 0), + }; rc = cxl_internal_send_cmd(mds, &mbox_cmd); if (rc) { @@ -1296,7 +1294,6 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); struct cxl_mbox_poison_out *po; struct cxl_mbox_poison_in pi; - struct cxl_mbox_cmd mbox_cmd; int nr_records = 0; int rc; @@ -1308,16 +1305,16 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, pi.offset = cpu_to_le64(offset); pi.length = cpu_to_le64(len / CXL_POISON_LEN_MULT); - mbox_cmd = (struct cxl_mbox_cmd) { - .opcode = CXL_MBOX_OP_GET_POISON, - .size_in = sizeof(pi), - .payload_in = &pi, - .size_out = mds->payload_size, - .payload_out = po, - .min_out = struct_size(po, record, 0), - }; - do { + struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd){ + .opcode = CXL_MBOX_OP_GET_POISON, + .size_in = sizeof(pi), + .payload_in = &pi, + .size_out = mds->payload_size, + .payload_out = po, + .min_out = struct_size(po, record, 0), + }; + rc = cxl_internal_send_cmd(mds, &mbox_cmd); if (rc) break; diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index e9e6c81ce034a..e71cfd490d829 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -1034,3 +1034,32 @@ long cxl_pci_get_latency(struct pci_dev *pdev) return cxl_flit_size(pdev) * MEGA / bw; } + +static int __cxl_endpoint_decoder_reset_detected(struct device *dev, void *data) +{ + struct cxl_port *port = data; + struct cxl_decoder *cxld; + struct cxl_hdm *cxlhdm; + void __iomem *hdm; + u32 ctrl; + + if (!is_endpoint_decoder(dev)) + return 0; + + cxld = to_cxl_decoder(dev); + if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0) + return 0; + + cxlhdm = dev_get_drvdata(&port->dev); + hdm = cxlhdm->regs.hdm_decoder; + ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(cxld->id)); + + return !FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl); +} + +bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port) +{ + return device_for_each_child(&port->dev, port, + __cxl_endpoint_decoder_reset_detected); +} +EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_reset_detected, CXL); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index e59d9d37aa650..4ae441ef32174 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -2096,18 +2096,41 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd) } EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL); -static void combine_coordinates(struct access_coordinate *c1, - struct access_coordinate *c2) +/** + * cxl_hb_get_perf_coordinates - Retrieve performance numbers between initiator + * and host bridge + * + * @port: endpoint cxl_port + * @coord: output access coordinates + * + * Return: errno on failure, 0 on success. + */ +int cxl_hb_get_perf_coordinates(struct cxl_port *port, + struct access_coordinate *coord) { - if (c2->write_bandwidth) - c1->write_bandwidth = min(c1->write_bandwidth, - c2->write_bandwidth); - c1->write_latency += c2->write_latency; + struct cxl_port *iter = port; + struct cxl_dport *dport; + + if (!is_cxl_endpoint(port)) + return -EINVAL; + + dport = iter->parent_dport; + while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) { + iter = to_cxl_port(iter->dev.parent); + dport = iter->parent_dport; + } + + coord[ACCESS_COORDINATE_LOCAL] = + dport->hb_coord[ACCESS_COORDINATE_LOCAL]; + coord[ACCESS_COORDINATE_CPU] = + dport->hb_coord[ACCESS_COORDINATE_CPU]; - if (c2->read_bandwidth) - c1->read_bandwidth = min(c1->read_bandwidth, - c2->read_bandwidth); - c1->read_latency += c2->read_latency; + return 0; +} + +static bool parent_port_is_cxl_root(struct cxl_port *port) +{ + return is_cxl_root(to_cxl_port(port->dev.parent)); } /** @@ -2129,30 +2152,31 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, struct cxl_dport *dport; struct pci_dev *pdev; unsigned int bw; + bool is_cxl_root; if (!is_cxl_endpoint(port)) return -EINVAL; - dport = iter->parent_dport; - /* - * Exit the loop when the parent port of the current port is cxl root. - * The iterative loop starts at the endpoint and gathers the - * latency of the CXL link from the current iter to the next downstream - * port each iteration. If the parent is cxl root then there is - * nothing to gather. + * Exit the loop when the parent port of the current iter port is cxl + * root. The iterative loop starts at the endpoint and gathers the + * latency of the CXL link from the current device/port to the connected + * downstream port each iteration. */ - while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) { - combine_coordinates(&c, &dport->sw_coord); - c.write_latency += dport->link_latency; - c.read_latency += dport->link_latency; - - iter = to_cxl_port(iter->dev.parent); + do { dport = iter->parent_dport; - } + iter = to_cxl_port(iter->dev.parent); + is_cxl_root = parent_port_is_cxl_root(iter); - /* Augment with the generic port (host bridge) perf data */ - combine_coordinates(&c, &dport->hb_coord); + /* + * There's no valid access_coordinate for a root port since RPs do not + * have CDAT and therefore needs to be skipped. + */ + if (!is_cxl_root) + cxl_coordinates_combine(&c, &c, &dport->sw_coord); + c.write_latency += dport->link_latency; + c.read_latency += dport->link_latency; + } while (!is_cxl_root); /* Get the calculated PCI paths bandwidth */ pdev = to_pci_dev(port->uport_dev->parent); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 4c7fd2d5cccb2..54a825b866ab8 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -2187,15 +2187,6 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd, struct device *dev; int rc; - switch (mode) { - case CXL_DECODER_RAM: - case CXL_DECODER_PMEM: - break; - default: - dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode); - return ERR_PTR(-EINVAL); - } - cxlr = cxl_region_alloc(cxlrd, id); if (IS_ERR(cxlr)) return cxlr; @@ -2246,6 +2237,15 @@ static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd, { int rc; + switch (mode) { + case CXL_DECODER_RAM: + case CXL_DECODER_PMEM: + break; + default: + dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode); + return ERR_PTR(-EINVAL); + } + rc = memregion_alloc(GFP_KERNEL); if (rc < 0) return ERR_PTR(rc); @@ -2550,6 +2550,7 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) if (i == 0) { cxl_nvb = cxl_find_nvdimm_bridge(cxlmd); if (!cxl_nvb) { + kfree(cxlr_pmem); cxlr_pmem = ERR_PTR(-ENODEV); goto out; } diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c index 372786f809555..3c42f984eeafa 100644 --- a/drivers/cxl/core/regs.c +++ b/drivers/cxl/core/regs.c @@ -271,6 +271,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_map_device_regs, CXL); static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi, struct cxl_register_map *map) { + u8 reg_type = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK, reg_lo); int bar = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BIR_MASK, reg_lo); u64 offset = ((u64)reg_hi << 32) | (reg_lo & CXL_DVSEC_REG_LOCATOR_BLOCK_OFF_LOW_MASK); @@ -278,11 +279,11 @@ static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi, if (offset > pci_resource_len(pdev, bar)) { dev_warn(&pdev->dev, "BAR%d: %pr: too small (offset: %pa, type: %d)\n", bar, - &pdev->resource[bar], &offset, map->reg_type); + &pdev->resource[bar], &offset, reg_type); return false; } - map->reg_type = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK, reg_lo); + map->reg_type = reg_type; map->resource = pci_resource_start(pdev, bar) + offset; map->max_size = pci_resource_len(pdev, bar) - offset; return true; diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index bdf117a33744b..7c5cd069f10cc 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -253,8 +253,8 @@ TRACE_EVENT(cxl_generic_event, * DRAM Event Record * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 */ -#define CXL_DPA_FLAGS_MASK 0x3F -#define CXL_DPA_MASK (~CXL_DPA_FLAGS_MASK) +#define CXL_DPA_FLAGS_MASK GENMASK(1, 0) +#define CXL_DPA_MASK GENMASK_ULL(63, 6) #define CXL_DPA_VOLATILE BIT(0) #define CXL_DPA_NOT_REPAIRABLE BIT(1) @@ -646,18 +646,18 @@ u64 cxl_trace_hpa(struct cxl_region *cxlr, struct cxl_memdev *memdev, u64 dpa); TRACE_EVENT(cxl_poison, - TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *region, + TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *cxlr, const struct cxl_poison_record *record, u8 flags, __le64 overflow_ts, enum cxl_poison_trace_type trace_type), - TP_ARGS(cxlmd, region, record, flags, overflow_ts, trace_type), + TP_ARGS(cxlmd, cxlr, record, flags, overflow_ts, trace_type), TP_STRUCT__entry( __string(memdev, dev_name(&cxlmd->dev)) __string(host, dev_name(cxlmd->dev.parent)) __field(u64, serial) __field(u8, trace_type) - __string(region, region) + __string(region, cxlr ? dev_name(&cxlr->dev) : "") __field(u64, overflow_ts) __field(u64, hpa) __field(u64, dpa) @@ -677,10 +677,10 @@ TRACE_EVENT(cxl_poison, __entry->source = cxl_poison_record_source(record); __entry->trace_type = trace_type; __entry->flags = flags; - if (region) { - __assign_str(region, dev_name(®ion->dev)); - memcpy(__entry->uuid, ®ion->params.uuid, 16); - __entry->hpa = cxl_trace_hpa(region, cxlmd, + if (cxlr) { + __assign_str(region, dev_name(&cxlr->dev)); + memcpy(__entry->uuid, &cxlr->params.uuid, 16); + __entry->hpa = cxl_trace_hpa(cxlr, cxlmd, __entry->dpa); } else { __assign_str(region, ""); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 003feebab79b5..2624c775c5c93 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -671,7 +671,7 @@ struct cxl_dport { struct cxl_port *port; struct cxl_regs regs; struct access_coordinate sw_coord; - struct access_coordinate hb_coord; + struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX]; long link_latency; }; @@ -879,9 +879,17 @@ void cxl_switch_parse_cdat(struct cxl_port *port); int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, struct access_coordinate *coord); +int cxl_hb_get_perf_coordinates(struct cxl_port *port, + struct access_coordinate *coord); void cxl_memdev_update_perf(struct cxl_memdev *cxlmd); +void cxl_coordinates_combine(struct access_coordinate *out, + struct access_coordinate *c1, + struct access_coordinate *c2); + +bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port); + /* * Unit test builds overrides this to __weak, find the 'strong' version * of these symbols in tools/testing/cxl/. diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 2ff361e756d66..659f9d46b154c 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -957,11 +957,33 @@ static void cxl_error_resume(struct pci_dev *pdev) dev->driver ? "successful" : "failed"); } +static void cxl_reset_done(struct pci_dev *pdev) +{ + struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); + struct cxl_memdev *cxlmd = cxlds->cxlmd; + struct device *dev = &pdev->dev; + + /* + * FLR does not expect to touch the HDM decoders and related + * registers. SBR, however, will wipe all device configurations. + * Issue a warning if there was an active decoder before the reset + * that no longer exists. + */ + guard(device)(&cxlmd->dev); + if (cxlmd->endpoint && + cxl_endpoint_decoder_reset_detected(cxlmd->endpoint)) { + dev_crit(dev, "SBR happened without memory regions removal.\n"); + dev_crit(dev, "System may be unstable if regions hosted system memory.\n"); + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + } +} + static const struct pci_error_handlers cxl_error_handlers = { .error_detected = cxl_error_detected, .slot_reset = cxl_slot_reset, .resume = cxl_error_resume, .cor_error_detected = cxl_cor_error_detected, + .reset_done = cxl_reset_done, }; static struct pci_driver cxl_pci_driver = { diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c index 9c2a0c082a768..ed4b323886e43 100644 --- a/drivers/dma-buf/st-dma-fence-chain.c +++ b/drivers/dma-buf/st-dma-fence-chain.c @@ -84,11 +84,11 @@ static int sanitycheck(void *arg) return -ENOMEM; chain = mock_chain(NULL, f, 1); - if (!chain) + if (chain) + dma_fence_enable_sw_signaling(chain); + else err = -ENOMEM; - dma_fence_enable_sw_signaling(chain); - dma_fence_signal(f); dma_fence_put(f); diff --git a/drivers/dma-buf/st-dma-fence.c b/drivers/dma-buf/st-dma-fence.c index b7c6f7ea9e0c8..6a1bfcd0cc210 100644 --- a/drivers/dma-buf/st-dma-fence.c +++ b/drivers/dma-buf/st-dma-fence.c @@ -540,6 +540,12 @@ static int race_signal_callback(void *arg) t[i].before = pass; t[i].task = kthread_run(thread_signal_callback, &t[i], "dma-fence:%d", i); + if (IS_ERR(t[i].task)) { + ret = PTR_ERR(t[i].task); + while (--i >= 0) + kthread_stop_put(t[i].task); + return ret; + } get_task_struct(t[i].task); } diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c index 101394f16930f..237bce21d1e72 100644 --- a/drivers/dma-buf/sync_debug.c +++ b/drivers/dma-buf/sync_debug.c @@ -110,12 +110,12 @@ static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) seq_printf(s, "%s: %d\n", obj->name, obj->value); - spin_lock_irq(&obj->lock); + spin_lock(&obj->lock); /* Caller already disabled IRQ. */ list_for_each(pos, &obj->pt_list) { struct sync_pt *pt = container_of(pos, struct sync_pt, link); sync_print_fence(s, &pt->base, false); } - spin_unlock_irq(&obj->lock); + spin_unlock(&obj->lock); } static void sync_print_sync_file(struct seq_file *s, diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index e928f2ca0f1e9..9fc99cfbef08c 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -394,7 +394,7 @@ config LS2X_APB_DMA config MCF_EDMA tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs" - depends on M5441x || COMPILE_TEST + depends on M5441x || (COMPILE_TEST && FSL_EDMA=n) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help @@ -643,16 +643,16 @@ config TEGRA20_APB_DMA config TEGRA210_ADMA tristate "NVIDIA Tegra210 ADMA support" - depends on (ARCH_TEGRA_210_SOC || COMPILE_TEST) + depends on (ARCH_TEGRA || COMPILE_TEST) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help - Support for the NVIDIA Tegra210 ADMA controller driver. The - DMA controller has multiple DMA channels and is used to service - various audio clients in the Tegra210 audio processing engine - (APE). This DMA controller transfers data from memory to - peripheral and vice versa. It does not support memory to - memory data transfer. + Support for the NVIDIA Tegra210/Tegra186/Tegra194/Tegra234 ADMA + controller driver. The DMA controller has multiple DMA channels + and is used to service various audio clients in the Tegra210 + audio processing engine (APE). This DMA controller transfers + data from memory to peripheral and vice versa. It does not + support memory to memory data transfer. config TIMB_DMA tristate "Timberdale FPGA DMA support" diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c index 4e339c04fc1ea..d5a33e4a91b19 100644 --- a/drivers/dma/dma-axi-dmac.c +++ b/drivers/dma/dma-axi-dmac.c @@ -1134,8 +1134,8 @@ static void axi_dmac_remove(struct platform_device *pdev) { struct axi_dmac *dmac = platform_get_drvdata(pdev); - of_dma_controller_free(pdev->dev.of_node); free_irq(dmac->irq, dmac); + of_dma_controller_free(pdev->dev.of_node); tasklet_kill(&dmac->chan.vchan.task); dma_async_device_unregister(&dmac->dma_dev); clk_disable_unprepare(dmac->clk); diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index a86a81ff0caa6..321446fdddbd7 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -302,6 +302,7 @@ static struct axi_dma_desc *axi_desc_alloc(u32 num) kfree(desc); return NULL; } + desc->nr_hw_descs = num; return desc; } @@ -328,7 +329,7 @@ static struct axi_dma_lli *axi_desc_get(struct axi_dma_chan *chan, static void axi_desc_put(struct axi_dma_desc *desc) { struct axi_dma_chan *chan = desc->chan; - int count = atomic_read(&chan->descs_allocated); + int count = desc->nr_hw_descs; struct axi_dma_hw_desc *hw_desc; int descs_put; @@ -1139,9 +1140,6 @@ static void axi_chan_block_xfer_complete(struct axi_dma_chan *chan) /* Remove the completed descriptor from issued list before completing */ list_del(&vd->node); vchan_cookie_complete(vd); - - /* Submit queued descriptors after processing the completed ones */ - axi_chan_start_first_queued(chan); } out: diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h index 454904d996540..ac571b413b21c 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h @@ -104,6 +104,7 @@ struct axi_dma_desc { u32 completed_blocks; u32 length; u32 period_len; + u32 nr_hw_descs; }; struct axi_dma_chan_config { diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c index 78a938969d7d7..e3505e56784b1 100644 --- a/drivers/dma/idma64.c +++ b/drivers/dma/idma64.c @@ -171,6 +171,10 @@ static irqreturn_t idma64_irq(int irq, void *dev) u32 status_err; unsigned short i; + /* Since IRQ may be shared, check if DMA controller is powered on */ + if (status == GENMASK(31, 0)) + return IRQ_NONE; + dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status); /* Check if we have any interrupt from the DMA controller */ @@ -594,7 +598,9 @@ static int idma64_probe(struct idma64_chip *chip) idma64->dma.dev = chip->sysdev; - dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK); + ret = dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK); + if (ret) + return ret; ret = dma_async_device_register(&idma64->dma); if (ret) diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index e5a94a93a3cc4..86413707171f6 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -342,7 +342,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) if (!evl) return; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = status.tail; h = status.head; @@ -354,9 +354,8 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) set_bit(h, evl->bmap); h = (h + 1) % size; } - spin_unlock(&evl->lock); - drain_workqueue(wq->wq); + mutex_unlock(&evl->lock); } static int idxd_cdev_release(struct inode *node, struct file *filep) @@ -401,6 +400,18 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) int rc; dev_dbg(&pdev->dev, "%s called\n", __func__); + + /* + * Due to an erratum in some of the devices supported by the driver, + * direct user submission to the device can be unsafe. + * (See document INTEL-SA-01084) + * + * For the devices that exhibit this behavior, require that the user + * has CAP_SYS_RAWIO capabilities. + */ + if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO)) + return -EPERM; + rc = check_vma(wq, vma, __func__); if (rc < 0) return rc; @@ -415,6 +426,70 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_page_prot); } +static int idxd_submit_user_descriptor(struct idxd_user_context *ctx, + struct dsa_hw_desc __user *udesc) +{ + struct idxd_wq *wq = ctx->wq; + struct idxd_dev *idxd_dev = &wq->idxd->idxd_dev; + const uint64_t comp_addr_align = is_dsa_dev(idxd_dev) ? 0x20 : 0x40; + void __iomem *portal = idxd_wq_portal_addr(wq); + struct dsa_hw_desc descriptor __aligned(64); + int rc; + + rc = copy_from_user(&descriptor, udesc, sizeof(descriptor)); + if (rc) + return -EFAULT; + + /* + * DSA devices are capable of indirect ("batch") command submission. + * On devices where direct user submissions are not safe, we cannot + * allow this since there is no good way for us to verify these + * indirect commands. + */ + if (is_dsa_dev(idxd_dev) && descriptor.opcode == DSA_OPCODE_BATCH && + !wq->idxd->user_submission_safe) + return -EINVAL; + /* + * As per the programming specification, the completion address must be + * aligned to 32 or 64 bytes. If this is violated the hardware + * engine can get very confused (security issue). + */ + if (!IS_ALIGNED(descriptor.completion_addr, comp_addr_align)) + return -EINVAL; + + if (wq_dedicated(wq)) + iosubmit_cmds512(portal, &descriptor, 1); + else { + descriptor.priv = 0; + descriptor.pasid = ctx->pasid; + rc = idxd_enqcmds(wq, portal, &descriptor); + if (rc < 0) + return rc; + } + + return 0; +} + +static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t len, + loff_t *unused) +{ + struct dsa_hw_desc __user *udesc = (struct dsa_hw_desc __user *)buf; + struct idxd_user_context *ctx = filp->private_data; + ssize_t written = 0; + int i; + + for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) { + int rc = idxd_submit_user_descriptor(ctx, udesc + i); + + if (rc) + return written ? written : rc; + + written += sizeof(struct dsa_hw_desc); + } + + return written; +} + static __poll_t idxd_cdev_poll(struct file *filp, struct poll_table_struct *wait) { @@ -437,6 +512,7 @@ static const struct file_operations idxd_cdev_fops = { .open = idxd_cdev_open, .release = idxd_cdev_release, .mmap = idxd_cdev_mmap, + .write = idxd_cdev_write, .poll = idxd_cdev_poll, }; @@ -501,7 +577,6 @@ void idxd_wq_del_cdev(struct idxd_wq *wq) struct idxd_cdev *idxd_cdev; idxd_cdev = wq->idxd_cdev; - ida_destroy(&file_ida); wq->idxd_cdev = NULL; cdev_device_del(&idxd_cdev->cdev, cdev_dev(idxd_cdev)); put_device(cdev_dev(idxd_cdev)); diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c index f3f25ee676f30..ad4245cb301d5 100644 --- a/drivers/dma/idxd/debugfs.c +++ b/drivers/dma/idxd/debugfs.c @@ -66,7 +66,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d) if (!evl || !evl->log) return 0; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = evl_status.tail; @@ -87,7 +87,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d) dump_event_entry(idxd, s, i, &count, processed); } - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); return 0; } diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index ecfdf4a8f1f83..c41ef195eeb9f 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -775,7 +775,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) goto err_alloc; } - spin_lock(&evl->lock); + mutex_lock(&evl->lock); evl->log = addr; evl->dma = dma_addr; evl->log_size = size; @@ -796,7 +796,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) gencfg.evl_en = 1; iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); return 0; err_alloc: @@ -819,7 +819,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd) if (!gencfg.evl_en) return; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); gencfg.evl_en = 0; iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); @@ -836,7 +836,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd) evl_dma = evl->dma; evl->log = NULL; evl->size = IDXD_EVL_SIZE_MIN; - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); dma_free_coherent(dev, evl_log_size, evl_log, evl_dma); } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index d0f5db6cf1eda..eb73cabb4ad07 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -288,12 +288,13 @@ struct idxd_driver_data { int evl_cr_off; int cr_status_off; int cr_result_off; + bool user_submission_safe; load_device_defaults_fn_t load_device_defaults; }; struct idxd_evl { /* Lock to protect event log access. */ - spinlock_t lock; + struct mutex lock; void *log; dma_addr_t dma; /* Total size of event log = number of entries * entry size. */ @@ -374,6 +375,8 @@ struct idxd_device { struct dentry *dbgfs_dir; struct dentry *dbgfs_evl_file; + + bool user_submission_safe; }; static inline unsigned int evl_ent_size(struct idxd_device *idxd) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 4954adc6bb609..bbe1776d94d8c 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -47,6 +47,7 @@ static struct idxd_driver_data idxd_driver_data[] = { .align = 32, .dev_type = &dsa_device_type, .evl_cr_off = offsetof(struct dsa_evl_entry, cr), + .user_submission_safe = false, /* See INTEL-SA-01084 erratum */ .cr_status_off = offsetof(struct dsa_completion_record, status), .cr_result_off = offsetof(struct dsa_completion_record, result), }, @@ -57,6 +58,7 @@ static struct idxd_driver_data idxd_driver_data[] = { .align = 64, .dev_type = &iax_device_type, .evl_cr_off = offsetof(struct iax_evl_entry, cr), + .user_submission_safe = false, /* See INTEL-SA-01084 erratum */ .cr_status_off = offsetof(struct iax_completion_record, status), .cr_result_off = offsetof(struct iax_completion_record, error_code), .load_device_defaults = idxd_load_iaa_device_defaults, @@ -354,7 +356,7 @@ static int idxd_init_evl(struct idxd_device *idxd) if (!evl) return -ENOMEM; - spin_lock_init(&evl->lock); + mutex_init(&evl->lock); evl->size = IDXD_EVL_SIZE_MIN; idxd_name = dev_name(idxd_confdev(idxd)); @@ -774,6 +776,8 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n", idxd->hw.version); + idxd->user_submission_safe = data->user_submission_safe; + return 0; err_dev_register: diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index 348aa21389a9f..fc049c9c9892e 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -363,7 +363,7 @@ static void process_evl_entries(struct idxd_device *idxd) evl_status.bits = 0; evl_status.int_pending = 1; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); /* Clear interrupt pending bit */ iowrite32(evl_status.bits_upper32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32)); @@ -380,7 +380,7 @@ static void process_evl_entries(struct idxd_device *idxd) evl_status.head = h; iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET); - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); } irqreturn_t idxd_misc_thread(int vec, void *data) @@ -611,11 +611,13 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry) spin_unlock(&irq_entry->list_lock); - list_for_each_entry(desc, &flist, list) { + list_for_each_entry_safe(desc, n, &flist, list) { /* * Check against the original status as ABORT is software defined * and 0xff, which DSA_COMP_STATUS_MASK can mask out. */ + list_del(&desc->list); + if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) { idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, true); continue; diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c index fdda6d6042629..5e94247e1ea70 100644 --- a/drivers/dma/idxd/perfmon.c +++ b/drivers/dma/idxd/perfmon.c @@ -528,14 +528,11 @@ static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node) return 0; target = cpumask_any_but(cpu_online_mask, cpu); - /* migrate events if there is a valid target */ - if (target < nr_cpu_ids) + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &perfmon_dsa_cpu_mask); - else - target = -1; - - perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target); + perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target); + } return 0; } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 315c004f58e47..e16dbf9ab324c 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -6,9 +6,6 @@ #include /* PCI Config */ -#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 -#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe - #define DEVICE_VERSION_1 0x100 #define DEVICE_VERSION_2 0x200 diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 523ae0dff7d4a..3a5ce477a81ad 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1197,12 +1197,35 @@ static ssize_t wq_enqcmds_retries_store(struct device *dev, struct device_attrib static struct device_attribute dev_attr_wq_enqcmds_retries = __ATTR(enqcmds_retries, 0644, wq_enqcmds_retries_show, wq_enqcmds_retries_store); +static ssize_t op_cap_show_common(struct device *dev, char *buf, unsigned long *opcap_bmap) +{ + ssize_t pos; + int i; + + pos = 0; + for (i = IDXD_MAX_OPCAP_BITS/64 - 1; i >= 0; i--) { + unsigned long val = opcap_bmap[i]; + + /* On systems where direct user submissions are not safe, we need to clear out + * the BATCH capability from the capability mask in sysfs since we cannot support + * that command on such systems. + */ + if (i == DSA_OPCODE_BATCH/64 && !confdev_to_idxd(dev)->user_submission_safe) + clear_bit(DSA_OPCODE_BATCH % 64, &val); + + pos += sysfs_emit_at(buf, pos, "%*pb", 64, &val); + pos += sysfs_emit_at(buf, pos, "%c", i == 0 ? '\n' : ','); + } + + return pos; +} + static ssize_t wq_op_config_show(struct device *dev, struct device_attribute *attr, char *buf) { struct idxd_wq *wq = confdev_to_wq(dev); - return sysfs_emit(buf, "%*pb\n", IDXD_MAX_OPCAP_BITS, wq->opcap_bmap); + return op_cap_show_common(dev, buf, wq->opcap_bmap); } static int idxd_verify_supported_opcap(struct idxd_device *idxd, unsigned long *opmask) @@ -1455,7 +1478,7 @@ static ssize_t op_cap_show(struct device *dev, { struct idxd_device *idxd = confdev_to_idxd(dev); - return sysfs_emit(buf, "%*pb\n", IDXD_MAX_OPCAP_BITS, idxd->opcap_bmap); + return op_cap_show_common(dev, buf, idxd->opcap_bmap); } static DEVICE_ATTR_RO(op_cap); diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 9c364e92cb828..e8f45a7fded43 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -534,18 +534,6 @@ static int ioat_probe(struct ioatdma_device *ioat_dma) return err; } -static int ioat_register(struct ioatdma_device *ioat_dma) -{ - int err = dma_async_device_register(&ioat_dma->dma_dev); - - if (err) { - ioat_disable_interrupts(ioat_dma); - dma_pool_destroy(ioat_dma->completion_pool); - } - - return err; -} - static void ioat_dma_remove(struct ioatdma_device *ioat_dma) { struct dma_device *dma = &ioat_dma->dma_dev; @@ -1181,9 +1169,9 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca) ioat_chan->reg_base + IOAT_DCACTRL_OFFSET); } - err = ioat_register(ioat_dma); + err = dma_async_device_register(&ioat_dma->dma_dev); if (err) - return err; + goto err_disable_interrupts; ioat_kobject_add(ioat_dma, &ioat_ktype); @@ -1192,20 +1180,29 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca) /* disable relaxed ordering */ err = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &val16); - if (err) - return pcibios_err_to_errno(err); + if (err) { + err = pcibios_err_to_errno(err); + goto err_disable_interrupts; + } /* clear relaxed ordering enable */ val16 &= ~PCI_EXP_DEVCTL_RELAX_EN; err = pcie_capability_write_word(pdev, PCI_EXP_DEVCTL, val16); - if (err) - return pcibios_err_to_errno(err); + if (err) { + err = pcibios_err_to_errno(err); + goto err_disable_interrupts; + } if (ioat_dma->cap & IOAT_CAP_DPS) writeb(ioat_pending_level + 1, ioat_dma->reg_base + IOAT_PREFETCH_LIMIT_OFFSET); return 0; + +err_disable_interrupts: + ioat_disable_interrupts(ioat_dma); + dma_pool_destroy(ioat_dma->completion_pool); + return err; } static void ioat_shutdown(struct pci_dev *pdev) @@ -1350,6 +1347,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) void __iomem * const *iomap; struct device *dev = &pdev->dev; struct ioatdma_device *device; + unsigned int i; + u8 version; int err; err = pcim_enable_device(pdev); @@ -1363,6 +1362,10 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!iomap) return -ENOMEM; + version = readb(iomap[IOAT_MMIO_BAR] + IOAT_VER_OFFSET); + if (version < IOAT_VER_3_0) + return -ENODEV; + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) return err; @@ -1373,17 +1376,18 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); pci_set_drvdata(pdev, device); - device->version = readb(device->reg_base + IOAT_VER_OFFSET); + device->version = version; if (device->version >= IOAT_VER_3_4) ioat_dca_enabled = 0; - if (device->version >= IOAT_VER_3_0) { - if (is_skx_ioat(pdev)) - device->version = IOAT_VER_3_2; - err = ioat3_dma_probe(device, ioat_dca_enabled); - } else - return -ENODEV; + if (is_skx_ioat(pdev)) + device->version = IOAT_VER_3_2; + + err = ioat3_dma_probe(device, ioat_dca_enabled); if (err) { + for (i = 0; i < IOAT_MAX_CHANS; i++) + kfree(device->idx[i]); + kfree(device); dev_err(dev, "Intel(R) I/OAT DMA Engine init failed\n"); return -ENODEV; } @@ -1445,6 +1449,7 @@ module_init(ioat_init_module); static void __exit ioat_exit_module(void) { pci_unregister_driver(&ioat_pci_driver); + kmem_cache_destroy(ioat_sed_cache); kmem_cache_destroy(ioat_cache); } module_exit(ioat_exit_module); diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c index 4e76c4ec2d396..e001f4f7aa640 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -250,7 +250,7 @@ static void pchan_update(struct owl_dma_pchan *pchan, u32 reg, else regval &= ~val; - writel(val, pchan->base + reg); + writel(regval, pchan->base + reg); } static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data) @@ -274,7 +274,7 @@ static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state) else regval &= ~val; - writel(val, od->base + reg); + writel(regval, od->base + reg); } static void dma_writel(struct owl_dma *od, u32 reg, u32 data) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index c29744bfdf2c2..3cf0b38387ae5 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1053,9 +1053,6 @@ static bool _trigger(struct pl330_thread *thrd) thrd->req_running = idx; - if (desc->rqtype == DMA_MEM_TO_DEV || desc->rqtype == DMA_DEV_TO_MEM) - UNTIL(thrd, PL330_STATE_WFP); - return true; } diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index 88547a23825b1..3642508e88bb2 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -746,6 +746,9 @@ static int tegra_dma_get_residual(struct tegra_dma_channel *tdc) bytes_xfer = dma_desc->bytes_xfer + sg_req[dma_desc->sg_idx].len - (wcount * 4); + if (dma_desc->bytes_req == bytes_xfer) + return 0; + residual = dma_desc->bytes_req - (bytes_xfer % dma_desc->bytes_req); return residual; diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h index 98f5f6fb9ff9c..6ad08878e9386 100644 --- a/drivers/dma/xilinx/xdma-regs.h +++ b/drivers/dma/xilinx/xdma-regs.h @@ -117,6 +117,9 @@ struct xdma_hw_desc { CHAN_CTRL_IE_WRITE_ERROR | \ CHAN_CTRL_IE_DESC_ERROR) +/* bits of the channel status register */ +#define XDMA_CHAN_STATUS_BUSY BIT(0) + #define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START #define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH | \ diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 170017ff2aad6..ae6e06057aa1d 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -71,6 +71,8 @@ struct xdma_chan { enum dma_transfer_direction dir; struct dma_slave_config cfg; u32 irq; + struct completion last_interrupt; + bool stop_requested; }; /** @@ -376,6 +378,8 @@ static int xdma_xfer_start(struct xdma_chan *xchan) return ret; xchan->busy = true; + xchan->stop_requested = false; + reinit_completion(&xchan->last_interrupt); return 0; } @@ -387,7 +391,6 @@ static int xdma_xfer_start(struct xdma_chan *xchan) static int xdma_xfer_stop(struct xdma_chan *xchan) { int ret; - u32 val; struct xdma_device *xdev = xchan->xdev_hdl; /* clear run stop bit to prevent any further auto-triggering */ @@ -395,13 +398,7 @@ static int xdma_xfer_stop(struct xdma_chan *xchan) CHAN_CTRL_RUN_STOP); if (ret) return ret; - - /* Clear the channel status register */ - ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &val); - if (ret) - return ret; - - return 0; + return ret; } /** @@ -474,6 +471,8 @@ static int xdma_alloc_channels(struct xdma_device *xdev, xchan->xdev_hdl = xdev; xchan->base = base + i * XDMA_CHAN_STRIDE; xchan->dir = dir; + xchan->stop_requested = false; + init_completion(&xchan->last_interrupt); ret = xdma_channel_init(xchan); if (ret) @@ -521,6 +520,7 @@ static int xdma_terminate_all(struct dma_chan *chan) spin_lock_irqsave(&xdma_chan->vchan.lock, flags); xdma_chan->busy = false; + xdma_chan->stop_requested = true; vd = vchan_next_desc(&xdma_chan->vchan); if (vd) { list_del(&vd->node); @@ -542,17 +542,26 @@ static int xdma_terminate_all(struct dma_chan *chan) static void xdma_synchronize(struct dma_chan *chan) { struct xdma_chan *xdma_chan = to_xdma_chan(chan); + struct xdma_device *xdev = xdma_chan->xdev_hdl; + int st = 0; + + /* If the engine continues running, wait for the last interrupt */ + regmap_read(xdev->rmap, xdma_chan->base + XDMA_CHAN_STATUS, &st); + if (st & XDMA_CHAN_STATUS_BUSY) + wait_for_completion_timeout(&xdma_chan->last_interrupt, msecs_to_jiffies(1000)); vchan_synchronize(&xdma_chan->vchan); } /** - * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses - * @sw_desc: tx descriptor state container - * @src_addr: Value for a ->src_addr field of a first descriptor - * @dst_addr: Value for a ->dst_addr field of a first descriptor - * @size: Total size of a contiguous memory block - * @filled_descs_num: Number of filled hardware descriptors for corresponding sw_desc + * xdma_fill_descs() - Fill hardware descriptors for one contiguous memory chunk. + * More than one descriptor will be used if the size is bigger + * than XDMA_DESC_BLEN_MAX. + * @sw_desc: Descriptor container + * @src_addr: First value for the ->src_addr field + * @dst_addr: First value for the ->dst_addr field + * @size: Size of the contiguous memory block + * @filled_descs_num: Index of the first descriptor to take care of in @sw_desc */ static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr, u64 dst_addr, u32 size, u32 filled_descs_num) @@ -704,7 +713,7 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address, desc_num = 0; for (i = 0; i < periods; i++) { desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num); - addr += i * period_size; + addr += period_size; } tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags); @@ -878,6 +887,9 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id) spin_lock(&xchan->vchan.lock); + if (xchan->stop_requested) + complete(&xchan->last_interrupt); + /* get submitted request */ vd = vchan_next_desc(&xchan->vchan); if (!vd) diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index b82815e64d24e..eb0637d90342a 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -214,7 +214,8 @@ struct xilinx_dpdma_tx_desc { * @running: true if the channel is running * @first_frame: flag for the first frame of stream * @video_group: flag if multi-channel operation is needed for video channels - * @lock: lock to access struct xilinx_dpdma_chan + * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before + * @vchan.lock, if both are to be held. * @desc_pool: descriptor allocation pool * @err_task: error IRQ bottom half handler * @desc: References to descriptors being processed @@ -1097,12 +1098,14 @@ static void xilinx_dpdma_chan_vsync_irq(struct xilinx_dpdma_chan *chan) * Complete the active descriptor, if any, promote the pending * descriptor to active, and queue the next transfer, if any. */ + spin_lock(&chan->vchan.lock); if (chan->desc.active) vchan_cookie_complete(&chan->desc.active->vdesc); chan->desc.active = pending; chan->desc.pending = NULL; xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); out: spin_unlock_irqrestore(&chan->lock, flags); @@ -1264,10 +1267,12 @@ static void xilinx_dpdma_issue_pending(struct dma_chan *dchan) struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan); unsigned long flags; - spin_lock_irqsave(&chan->vchan.lock, flags); + spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); if (vchan_issue_pending(&chan->vchan)) xilinx_dpdma_chan_queue_transfer(chan); - spin_unlock_irqrestore(&chan->vchan.lock, flags); + spin_unlock(&chan->vchan.lock); + spin_unlock_irqrestore(&chan->lock, flags); } static int xilinx_dpdma_config(struct dma_chan *dchan, @@ -1495,7 +1500,9 @@ static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t) XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id); spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); spin_unlock_irqrestore(&chan->lock, flags); } diff --git a/drivers/dpll/Kconfig b/drivers/dpll/Kconfig index a4cae73f20d3d..20607ed542435 100644 --- a/drivers/dpll/Kconfig +++ b/drivers/dpll/Kconfig @@ -4,4 +4,4 @@ # config DPLL - bool + bool diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 7f686d179fc93..22c2f1375e867 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -29,6 +29,8 @@ static u32 dpll_pin_xa_id; WARN_ON_ONCE(!xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED)) #define ASSERT_DPLL_NOT_REGISTERED(d) \ WARN_ON_ONCE(xa_get_mark(&dpll_device_xa, (d)->id, DPLL_REGISTERED)) +#define ASSERT_DPLL_PIN_REGISTERED(p) \ + WARN_ON_ONCE(!xa_get_mark(&dpll_pin_xa, (p)->id, DPLL_REGISTERED)) struct dpll_device_registration { struct list_head list; @@ -40,6 +42,7 @@ struct dpll_pin_registration { struct list_head list; const struct dpll_pin_ops *ops; void *priv; + void *cookie; }; struct dpll_device *dpll_device_get_by_id(int id) @@ -52,12 +55,14 @@ struct dpll_device *dpll_device_get_by_id(int id) static struct dpll_pin_registration * dpll_pin_registration_find(struct dpll_pin_ref *ref, - const struct dpll_pin_ops *ops, void *priv) + const struct dpll_pin_ops *ops, void *priv, + void *cookie) { struct dpll_pin_registration *reg; list_for_each_entry(reg, &ref->registration_list, list) { - if (reg->ops == ops && reg->priv == priv) + if (reg->ops == ops && reg->priv == priv && + reg->cookie == cookie) return reg; } return NULL; @@ -65,7 +70,8 @@ dpll_pin_registration_find(struct dpll_pin_ref *ref, static int dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, - const struct dpll_pin_ops *ops, void *priv) + const struct dpll_pin_ops *ops, void *priv, + void *cookie) { struct dpll_pin_registration *reg; struct dpll_pin_ref *ref; @@ -76,7 +82,7 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, xa_for_each(xa_pins, i, ref) { if (ref->pin != pin) continue; - reg = dpll_pin_registration_find(ref, ops, priv); + reg = dpll_pin_registration_find(ref, ops, priv, cookie); if (reg) { refcount_inc(&ref->refcount); return 0; @@ -109,6 +115,7 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, } reg->ops = ops; reg->priv = priv; + reg->cookie = cookie; if (ref_exists) refcount_inc(&ref->refcount); list_add_tail(®->list, &ref->registration_list); @@ -117,7 +124,8 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, } static int dpll_xa_ref_pin_del(struct xarray *xa_pins, struct dpll_pin *pin, - const struct dpll_pin_ops *ops, void *priv) + const struct dpll_pin_ops *ops, void *priv, + void *cookie) { struct dpll_pin_registration *reg; struct dpll_pin_ref *ref; @@ -126,12 +134,12 @@ static int dpll_xa_ref_pin_del(struct xarray *xa_pins, struct dpll_pin *pin, xa_for_each(xa_pins, i, ref) { if (ref->pin != pin) continue; - reg = dpll_pin_registration_find(ref, ops, priv); + reg = dpll_pin_registration_find(ref, ops, priv, cookie); if (WARN_ON(!reg)) return -EINVAL; + list_del(®->list); + kfree(reg); if (refcount_dec_and_test(&ref->refcount)) { - list_del(®->list); - kfree(reg); xa_erase(xa_pins, i); WARN_ON(!list_empty(&ref->registration_list)); kfree(ref); @@ -144,7 +152,7 @@ static int dpll_xa_ref_pin_del(struct xarray *xa_pins, struct dpll_pin *pin, static int dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, - const struct dpll_pin_ops *ops, void *priv) + const struct dpll_pin_ops *ops, void *priv, void *cookie) { struct dpll_pin_registration *reg; struct dpll_pin_ref *ref; @@ -155,7 +163,7 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, xa_for_each(xa_dplls, i, ref) { if (ref->dpll != dpll) continue; - reg = dpll_pin_registration_find(ref, ops, priv); + reg = dpll_pin_registration_find(ref, ops, priv, cookie); if (reg) { refcount_inc(&ref->refcount); return 0; @@ -188,6 +196,7 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, } reg->ops = ops; reg->priv = priv; + reg->cookie = cookie; if (ref_exists) refcount_inc(&ref->refcount); list_add_tail(®->list, &ref->registration_list); @@ -197,7 +206,7 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, static void dpll_xa_ref_dpll_del(struct xarray *xa_dplls, struct dpll_device *dpll, - const struct dpll_pin_ops *ops, void *priv) + const struct dpll_pin_ops *ops, void *priv, void *cookie) { struct dpll_pin_registration *reg; struct dpll_pin_ref *ref; @@ -206,12 +215,12 @@ dpll_xa_ref_dpll_del(struct xarray *xa_dplls, struct dpll_device *dpll, xa_for_each(xa_dplls, i, ref) { if (ref->dpll != dpll) continue; - reg = dpll_pin_registration_find(ref, ops, priv); + reg = dpll_pin_registration_find(ref, ops, priv, cookie); if (WARN_ON(!reg)) return; + list_del(®->list); + kfree(reg); if (refcount_dec_and_test(&ref->refcount)) { - list_del(®->list); - kfree(reg); xa_erase(xa_dplls, i); WARN_ON(!list_empty(&ref->registration_list)); kfree(ref); @@ -440,7 +449,7 @@ static int dpll_pin_prop_dup(const struct dpll_pin_properties *src, sizeof(*src->freq_supported); dst->freq_supported = kmemdup(src->freq_supported, freq_size, GFP_KERNEL); - if (!src->freq_supported) + if (!dst->freq_supported) return -ENOMEM; } if (src->board_label) { @@ -592,14 +601,14 @@ EXPORT_SYMBOL_GPL(dpll_pin_put); static int __dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, - const struct dpll_pin_ops *ops, void *priv) + const struct dpll_pin_ops *ops, void *priv, void *cookie) { int ret; - ret = dpll_xa_ref_pin_add(&dpll->pin_refs, pin, ops, priv); + ret = dpll_xa_ref_pin_add(&dpll->pin_refs, pin, ops, priv, cookie); if (ret) return ret; - ret = dpll_xa_ref_dpll_add(&pin->dpll_refs, dpll, ops, priv); + ret = dpll_xa_ref_dpll_add(&pin->dpll_refs, dpll, ops, priv, cookie); if (ret) goto ref_pin_del; xa_set_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED); @@ -608,7 +617,7 @@ __dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, return ret; ref_pin_del: - dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv); + dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv, cookie); return ret; } @@ -640,7 +649,7 @@ dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, dpll->clock_id == pin->clock_id))) ret = -EINVAL; else - ret = __dpll_pin_register(dpll, pin, ops, priv); + ret = __dpll_pin_register(dpll, pin, ops, priv, NULL); mutex_unlock(&dpll_lock); return ret; @@ -649,10 +658,11 @@ EXPORT_SYMBOL_GPL(dpll_pin_register); static void __dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin, - const struct dpll_pin_ops *ops, void *priv) + const struct dpll_pin_ops *ops, void *priv, void *cookie) { - dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv); - dpll_xa_ref_dpll_del(&pin->dpll_refs, dpll, ops, priv); + ASSERT_DPLL_PIN_REGISTERED(pin); + dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv, cookie); + dpll_xa_ref_dpll_del(&pin->dpll_refs, dpll, ops, priv, cookie); if (xa_empty(&pin->dpll_refs)) xa_clear_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED); } @@ -677,7 +687,7 @@ void dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin, mutex_lock(&dpll_lock); dpll_pin_delete_ntf(pin); - __dpll_pin_unregister(dpll, pin, ops, priv); + __dpll_pin_unregister(dpll, pin, ops, priv, NULL); mutex_unlock(&dpll_lock); } EXPORT_SYMBOL_GPL(dpll_pin_unregister); @@ -713,12 +723,12 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, return -EINVAL; mutex_lock(&dpll_lock); - ret = dpll_xa_ref_pin_add(&pin->parent_refs, parent, ops, priv); + ret = dpll_xa_ref_pin_add(&pin->parent_refs, parent, ops, priv, pin); if (ret) goto unlock; refcount_inc(&pin->refcount); xa_for_each(&parent->dpll_refs, i, ref) { - ret = __dpll_pin_register(ref->dpll, pin, ops, priv); + ret = __dpll_pin_register(ref->dpll, pin, ops, priv, parent); if (ret) { stop = i; goto dpll_unregister; @@ -732,11 +742,12 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, dpll_unregister: xa_for_each(&parent->dpll_refs, i, ref) if (i < stop) { - __dpll_pin_unregister(ref->dpll, pin, ops, priv); + __dpll_pin_unregister(ref->dpll, pin, ops, priv, + parent); dpll_pin_delete_ntf(pin); } refcount_dec(&pin->refcount); - dpll_xa_ref_pin_del(&pin->parent_refs, parent, ops, priv); + dpll_xa_ref_pin_del(&pin->parent_refs, parent, ops, priv, pin); unlock: mutex_unlock(&dpll_lock); return ret; @@ -761,10 +772,10 @@ void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin, mutex_lock(&dpll_lock); dpll_pin_delete_ntf(pin); - dpll_xa_ref_pin_del(&pin->parent_refs, parent, ops, priv); + dpll_xa_ref_pin_del(&pin->parent_refs, parent, ops, priv, pin); refcount_dec(&pin->refcount); xa_for_each(&pin->dpll_refs, i, ref) - __dpll_pin_unregister(ref->dpll, pin, ops, priv); + __dpll_pin_unregister(ref->dpll, pin, ops, priv, parent); mutex_unlock(&dpll_lock); } EXPORT_SYMBOL_GPL(dpll_pin_on_pin_unregister); diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 537b9987a431c..fab73a12c9c33 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -80,7 +80,7 @@ int __amd64_read_pci_cfg_dword(struct pci_dev *pdev, int offset, amd64_warn("%s: error reading F%dx%03x.\n", func, PCI_FUNC(pdev->devfn), offset); - return err; + return pcibios_err_to_errno(err); } int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset, @@ -93,7 +93,7 @@ int __amd64_write_pci_cfg_dword(struct pci_dev *pdev, int offset, amd64_warn("%s: error writing to F%dx%03x.\n", func, PCI_FUNC(pdev->devfn), offset); - return err; + return pcibios_err_to_errno(err); } /* @@ -1024,8 +1024,10 @@ static int gpu_get_node_map(struct amd64_pvt *pvt) } ret = pci_read_config_dword(pdev, REG_LOCAL_NODE_TYPE_MAP, &tmp); - if (ret) + if (ret) { + ret = pcibios_err_to_errno(ret); goto out; + } gpu_node_map.node_count = FIELD_GET(LNTM_NODE_COUNT, tmp); gpu_node_map.base_node_id = FIELD_GET(LNTM_BASE_NODE_ID, tmp); diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 2b0ecdeba5cdc..9666caf2a6ab8 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -798,7 +798,7 @@ static int errcmd_enable_error_reporting(bool enable) rc = pci_read_config_word(imc->pdev, ERRCMD_OFFSET, &errcmd); if (rc) - return rc; + return pcibios_err_to_errno(rc); if (enable) errcmd |= ERRCMD_CE | ERRSTS_UE; @@ -807,7 +807,7 @@ static int errcmd_enable_error_reporting(bool enable) rc = pci_write_config_word(imc->pdev, ERRCMD_OFFSET, errcmd); if (rc) - return rc; + return pcibios_err_to_errno(rc); return 0; } diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 9c5b6f8bd8bd5..27996b7924c82 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -648,7 +648,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, memset(&res, 0, sizeof(res)); res.mce = mce; res.addr = mce->addr & MCI_ADDR_PHYSADDR; - if (!pfn_to_online_page(res.addr >> PAGE_SHIFT)) { + if (!pfn_to_online_page(res.addr >> PAGE_SHIFT) && !arch_is_platform_page(res.addr)) { pr_err("Invalid address 0x%llx in IA32_MC%d_ADDR\n", mce->addr, mce->bank); return NOTIFY_DONE; } diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c index 62caf454b5670..4d5b68b6be673 100644 --- a/drivers/edac/versal_edac.c +++ b/drivers/edac/versal_edac.c @@ -423,7 +423,7 @@ static void handle_error(struct mem_ctl_info *mci, struct ecc_status *stat) convert_to_physical(priv, pinf), pinf.burstpos); edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, - priv->ce_cnt, 0, 0, 0, 0, 0, -1, + 1, 0, 0, 0, 0, 0, -1, priv->message, ""); } @@ -436,7 +436,7 @@ static void handle_error(struct mem_ctl_info *mci, struct ecc_status *stat) convert_to_physical(priv, pinf), pinf.burstpos); edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, - priv->ue_cnt, 0, 0, 0, 0, 0, -1, + 1, 0, 0, 0, 0, 0, -1, priv->message, ""); } @@ -1006,8 +1006,7 @@ static int mc_probe(struct platform_device *pdev) } rc = xlnx_register_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1, - XPM_EVENT_ERROR_MASK_DDRMC_CR | XPM_EVENT_ERROR_MASK_DDRMC_NCR | - XPM_EVENT_ERROR_MASK_NOC_CR | XPM_EVENT_ERROR_MASK_NOC_NCR, + XPM_EVENT_ERROR_MASK_DDRMC_CR | XPM_EVENT_ERROR_MASK_DDRMC_NCR, false, err_callback, mci); if (rc) { if (rc == -EACCES) @@ -1044,8 +1043,6 @@ static int mc_remove(struct platform_device *pdev) xlnx_unregister_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1, XPM_EVENT_ERROR_MASK_DDRMC_CR | - XPM_EVENT_ERROR_MASK_NOC_CR | - XPM_EVENT_ERROR_MASK_NOC_NCR | XPM_EVENT_ERROR_MASK_DDRMC_NCR, err_callback, mci); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 5f869eacd19ab..3da94b3822923 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -116,7 +116,8 @@ config EXTCON_MAX77843 config EXTCON_MAX8997 tristate "Maxim MAX8997 EXTCON Support" - depends on MFD_MAX8997 && IRQ_DOMAIN + depends on MFD_MAX8997 + select IRQ_DOMAIN help If you say yes here you get support for the MUIC device of Maxim MAX8997 PMIC. The MAX8997 MUIC is a USB port accessory diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index b0d671db178a8..ea31ac7ac1ca9 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -148,10 +148,12 @@ packet_buffer_get(struct client *client, char __user *data, size_t user_length) if (atomic_read(&buffer->size) == 0) return -ENODEV; - /* FIXME: Check length <= user_length. */ + length = buffer->head->length; + + if (length > user_length) + return 0; end = buffer->data + buffer->capacity; - length = buffer->head->length; if (&buffer->head->data[length] < end) { if (copy_to_user(data, buffer->head->data, length)) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 7bc71f4be64a0..b9ae0340b8a70 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -1556,6 +1556,8 @@ static int handle_at_packet(struct context *context, #define HEADER_GET_DATA_LENGTH(q) (((q) >> 16) & 0xffff) #define HEADER_GET_EXTENDED_TCODE(q) (((q) >> 0) & 0xffff) +static u32 get_cycle_time(struct fw_ohci *ohci); + static void handle_local_rom(struct fw_ohci *ohci, struct fw_packet *packet, u32 csr) { @@ -1580,6 +1582,8 @@ static void handle_local_rom(struct fw_ohci *ohci, (void *) ohci->config_rom + i, length); } + // Timestamping on behalf of the hardware. + response.timestamp = cycle_time_to_ohci_tstamp(get_cycle_time(ohci)); fw_core_handle_response(&ohci->card, &response); } @@ -1628,6 +1632,8 @@ static void handle_local_lock(struct fw_ohci *ohci, fw_fill_response(&response, packet->header, RCODE_BUSY, NULL, 0); out: + // Timestamping on behalf of the hardware. + response.timestamp = cycle_time_to_ohci_tstamp(get_cycle_time(ohci)); fw_core_handle_response(&ohci->card, &response); } @@ -1670,8 +1676,6 @@ static void handle_local_request(struct context *ctx, struct fw_packet *packet) } } -static u32 get_cycle_time(struct fw_ohci *ohci); - static void at_context_transmit(struct context *ctx, struct fw_packet *packet) { unsigned long flags; @@ -2060,6 +2064,8 @@ static void bus_reset_work(struct work_struct *work) ohci->generation = generation; reg_write(ohci, OHCI1394_IntEventClear, OHCI1394_busReset); + if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS) + reg_write(ohci, OHCI1394_IntMaskSet, OHCI1394_busReset); if (ohci->quirks & QUIRK_RESET_PACKET) ohci->request_generation = generation; @@ -2125,12 +2131,14 @@ static irqreturn_t irq_handler(int irq, void *data) return IRQ_NONE; /* - * busReset and postedWriteErr must not be cleared yet + * busReset and postedWriteErr events must not be cleared yet * (OHCI 1.1 clauses 7.2.3.2 and 13.2.8.1) */ reg_write(ohci, OHCI1394_IntEventClear, event & ~(OHCI1394_busReset | OHCI1394_postedWriteErr)); log_irqs(ohci, event); + if (event & OHCI1394_busReset) + reg_write(ohci, OHCI1394_IntMaskClear, OHCI1394_busReset); if (event & OHCI1394_selfIDComplete) queue_work(selfid_workqueue, &ohci->bus_reset_work); diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index f2556a8e94015..9bc2e10381afd 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -790,7 +790,7 @@ static void ffa_notification_info_get(void) part_id = packed_id_list[ids_processed++]; - if (!ids_count[list]) { /* Global Notification */ + if (ids_count[list] == 1) { /* Global Notification */ __do_sched_recv_cb(part_id, 0, false); continue; } diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index 3505735185033..130d13e9cd6be 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -921,7 +921,7 @@ static int scmi_dbg_raw_mode_open(struct inode *inode, struct file *filp) rd->raw = raw; filp->private_data = rd; - return 0; + return nonseekable_open(inode, filp); } static int scmi_dbg_raw_mode_release(struct inode *inode, struct file *filp) @@ -950,6 +950,7 @@ static const struct file_operations scmi_dbg_raw_mode_reset_fops = { .open = scmi_dbg_raw_mode_open, .release = scmi_dbg_raw_mode_release, .write = scmi_dbg_raw_mode_reset_write, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -959,6 +960,7 @@ static const struct file_operations scmi_dbg_raw_mode_message_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_write, .poll = scmi_dbg_raw_mode_message_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -975,6 +977,7 @@ static const struct file_operations scmi_dbg_raw_mode_message_async_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_async_write, .poll = scmi_dbg_raw_mode_message_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -998,6 +1001,7 @@ static const struct file_operations scmi_dbg_raw_mode_notification_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_notif_read, .poll = scmi_test_dbg_raw_mode_notif_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -1021,6 +1025,7 @@ static const struct file_operations scmi_dbg_raw_mode_errors_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_errors_read, .poll = scmi_test_dbg_raw_mode_errors_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index 7611e9665038d..39936e1dd30e9 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -214,6 +214,13 @@ static int smc_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_smc *scmi_info = cinfo->transport_info; + /* + * Different protocols might share the same chan info, so a previous + * smc_chan_free call might have already freed the structure. + */ + if (!scmi_info) + return 0; + /* Ignore any possible further reception on the IRQ path */ if (scmi_info->irq > 0) free_irq(scmi_info->irq, scmi_info); diff --git a/drivers/firmware/dmi-id.c b/drivers/firmware/dmi-id.c index 5f3a3e913d28f..d19c78a78ae3a 100644 --- a/drivers/firmware/dmi-id.c +++ b/drivers/firmware/dmi-id.c @@ -169,9 +169,14 @@ static int dmi_dev_uevent(const struct device *dev, struct kobj_uevent_env *env) return 0; } +static void dmi_dev_release(struct device *dev) +{ + kfree(dev); +} + static struct class dmi_class = { .name = "dmi", - .dev_release = (void(*)(struct device *)) kfree, + .dev_release = dmi_dev_release, .dev_uevent = dmi_dev_uevent, }; diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index a2d0009560d0f..4f3486e6a84b2 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -25,6 +25,7 @@ subdir-$(CONFIG_EFI_STUB) += libstub obj-$(CONFIG_EFI_BOOTLOADER_CONTROL) += efibc.o obj-$(CONFIG_EFI_TEST) += test/ obj-$(CONFIG_EFI_DEV_PATH_PARSER) += dev-path-parser.o +obj-$(CONFIG_EFI) += secureboot.o obj-$(CONFIG_APPLE_PROPERTIES) += apple-properties.o obj-$(CONFIG_EFI_RCI2_TABLE) += rci2-table.o obj-$(CONFIG_EFI_EMBEDDED_FIRMWARE) += embedded-firmware.o diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index a00e07b853f22..7ee342a73e239 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -237,6 +238,13 @@ void __init efi_init(void) return; } + efi_set_secure_boot(efi_get__secure_boot()); + +#ifdef CONFIG_LOCK_DOWN_IN_SECURE_BOOT + if (efi_enabled(EFI_SECURE_BOOT)) + security_lock_kernel_down("EFI Secure Boot mode", LOCKDOWN_INTEGRITY_MAX); +#endif + reserve_regions(); /* * For memblock manipulation, the cap should come after the memblock_add(). diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 4fcda50acfa4a..cfd2b58a34940 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -33,6 +33,7 @@ #include #include #include +#include #include @@ -203,6 +204,8 @@ static bool generic_ops_supported(void) name_size = sizeof(name); + if (!efi.get_next_variable) + return false; status = efi.get_next_variable(&name_size, &name, &guid); if (status == EFI_UNSUPPORTED) return false; @@ -597,7 +600,8 @@ static const efi_config_table_type_t common_tables[] __initconst = { {EFI_MEMORY_ATTRIBUTES_TABLE_GUID, &efi_mem_attr_table, "MEMATTR" }, {LINUX_EFI_RANDOM_SEED_TABLE_GUID, &efi_rng_seed, "RNG" }, {LINUX_EFI_TPM_EVENT_LOG_GUID, &efi.tpm_log, "TPMEventLog" }, - {LINUX_EFI_TPM_FINAL_LOG_GUID, &efi.tpm_final_log, "TPMFinalLog" }, + {EFI_TCG2_FINAL_EVENTS_TABLE_GUID, &efi.tpm_final_log, "TPMFinalLog" }, + {EFI_CC_FINAL_EVENTS_TABLE_GUID, &efi.tpm_final_log, "CCFinalLog" }, {LINUX_EFI_MEMRESERVE_TABLE_GUID, &mem_reserve, "MEMRESERVE" }, {LINUX_EFI_INITRD_MEDIA_GUID, &initrd, "INITRD" }, {EFI_RT_PROPERTIES_TABLE_GUID, &rt_prop, "RTPROP" }, @@ -990,40 +994,101 @@ int efi_mem_type(unsigned long phys_addr) return -EINVAL; } +struct efi_error_code { + efi_status_t status; + int errno; + const char *description; +}; + +static const struct efi_error_code efi_error_codes[] = { + { EFI_SUCCESS, 0, "Success"}, +#if 0 + { EFI_LOAD_ERROR, -EPICK_AN_ERRNO, "Load Error"}, +#endif + { EFI_INVALID_PARAMETER, -EINVAL, "Invalid Parameter"}, + { EFI_UNSUPPORTED, -ENOSYS, "Unsupported"}, + { EFI_BAD_BUFFER_SIZE, -ENOSPC, "Bad Buffer Size"}, + { EFI_BUFFER_TOO_SMALL, -ENOSPC, "Buffer Too Small"}, + { EFI_NOT_READY, -EAGAIN, "Not Ready"}, + { EFI_DEVICE_ERROR, -EIO, "Device Error"}, + { EFI_WRITE_PROTECTED, -EROFS, "Write Protected"}, + { EFI_OUT_OF_RESOURCES, -ENOMEM, "Out of Resources"}, +#if 0 + { EFI_VOLUME_CORRUPTED, -EPICK_AN_ERRNO, "Volume Corrupt"}, + { EFI_VOLUME_FULL, -EPICK_AN_ERRNO, "Volume Full"}, + { EFI_NO_MEDIA, -EPICK_AN_ERRNO, "No Media"}, + { EFI_MEDIA_CHANGED, -EPICK_AN_ERRNO, "Media changed"}, +#endif + { EFI_NOT_FOUND, -ENOENT, "Not Found"}, +#if 0 + { EFI_ACCESS_DENIED, -EPICK_AN_ERRNO, "Access Denied"}, + { EFI_NO_RESPONSE, -EPICK_AN_ERRNO, "No Response"}, + { EFI_NO_MAPPING, -EPICK_AN_ERRNO, "No mapping"}, + { EFI_TIMEOUT, -EPICK_AN_ERRNO, "Time out"}, + { EFI_NOT_STARTED, -EPICK_AN_ERRNO, "Not started"}, + { EFI_ALREADY_STARTED, -EPICK_AN_ERRNO, "Already started"}, +#endif + { EFI_ABORTED, -EINTR, "Aborted"}, +#if 0 + { EFI_ICMP_ERROR, -EPICK_AN_ERRNO, "ICMP Error"}, + { EFI_TFTP_ERROR, -EPICK_AN_ERRNO, "TFTP Error"}, + { EFI_PROTOCOL_ERROR, -EPICK_AN_ERRNO, "Protocol Error"}, + { EFI_INCOMPATIBLE_VERSION, -EPICK_AN_ERRNO, "Incompatible Version"}, +#endif + { EFI_SECURITY_VIOLATION, -EACCES, "Security Policy Violation"}, +#if 0 + { EFI_CRC_ERROR, -EPICK_AN_ERRNO, "CRC Error"}, + { EFI_END_OF_MEDIA, -EPICK_AN_ERRNO, "End of Media"}, + { EFI_END_OF_FILE, -EPICK_AN_ERRNO, "End of File"}, + { EFI_INVALID_LANGUAGE, -EPICK_AN_ERRNO, "Invalid Languages"}, + { EFI_COMPROMISED_DATA, -EPICK_AN_ERRNO, "Compromised Data"}, + + // warnings + { EFI_WARN_UNKOWN_GLYPH, -EPICK_AN_ERRNO, "Warning Unknown Glyph"}, + { EFI_WARN_DELETE_FAILURE, -EPICK_AN_ERRNO, "Warning Delete Failure"}, + { EFI_WARN_WRITE_FAILURE, -EPICK_AN_ERRNO, "Warning Write Failure"}, + { EFI_WARN_BUFFER_TOO_SMALL, -EPICK_AN_ERRNO, "Warning Buffer Too Small"}, +#endif +}; + +static int +efi_status_cmp_bsearch(const void *key, const void *item) +{ + u64 status = (u64)(uintptr_t)key; + struct efi_error_code *code = (struct efi_error_code *)item; + + if (status < code->status) + return -1; + if (status > code->status) + return 1; + return 0; +} + int efi_status_to_err(efi_status_t status) { - int err; - - switch (status) { - case EFI_SUCCESS: - err = 0; - break; - case EFI_INVALID_PARAMETER: - err = -EINVAL; - break; - case EFI_OUT_OF_RESOURCES: - err = -ENOSPC; - break; - case EFI_DEVICE_ERROR: - err = -EIO; - break; - case EFI_WRITE_PROTECTED: - err = -EROFS; - break; - case EFI_SECURITY_VIOLATION: - err = -EACCES; - break; - case EFI_NOT_FOUND: - err = -ENOENT; - break; - case EFI_ABORTED: - err = -EINTR; - break; - default: - err = -EINVAL; - } + struct efi_error_code *found; + size_t num = sizeof(efi_error_codes) / sizeof(struct efi_error_code); - return err; + found = bsearch((void *)(uintptr_t)status, efi_error_codes, + sizeof(struct efi_error_code), num, + efi_status_cmp_bsearch); + if (!found) + return -EINVAL; + return found->errno; +} + +const char * +efi_status_to_str(efi_status_t status) +{ + struct efi_error_code *found; + size_t num = sizeof(efi_error_codes) / sizeof(struct efi_error_code); + + found = bsearch((void *)(uintptr_t)status, efi_error_codes, + sizeof(struct efi_error_code), num, + efi_status_cmp_bsearch); + if (!found) + return "Unknown error code"; + return found->description; } EXPORT_SYMBOL_GPL(efi_status_to_err); diff --git a/drivers/firmware/efi/fdtparams.c b/drivers/firmware/efi/fdtparams.c index 0ec83ba580972..562cf610447a4 100644 --- a/drivers/firmware/efi/fdtparams.c +++ b/drivers/firmware/efi/fdtparams.c @@ -16,16 +16,24 @@ enum { MMSIZE, DCSIZE, DCVERS, + SCBOOT, PARAMCOUNT }; +static u32 __secure_boot __initdata = efi_secureboot_mode_unset; +u32 __init efi_get__secure_boot(void) +{ + return __secure_boot; +} + static __initconst const char name[][22] = { [SYSTAB] = "System Table ", [MMBASE] = "MemMap Address ", [MMSIZE] = "MemMap Size ", [DCSIZE] = "MemMap Desc. Size ", [DCVERS] = "MemMap Desc. Version ", + [SCBOOT] = "Secure Boot Enabled ", }; static __initconst const struct { @@ -53,6 +61,7 @@ static __initconst const struct { [MMSIZE] = "linux,uefi-mmap-size", [DCSIZE] = "linux,uefi-mmap-desc-size", [DCVERS] = "linux,uefi-mmap-desc-ver", + [SCBOOT] = "linux,uefi-secure-boot", } } }; @@ -95,6 +104,7 @@ u64 __init efi_get_fdt_params(struct efi_memory_map_data *mm) [MMSIZE] = { &mm->size, sizeof(mm->size) }, [DCSIZE] = { &mm->desc_size, sizeof(mm->desc_size) }, [DCVERS] = { &mm->desc_version, sizeof(mm->desc_version) }, + [SCBOOT] = { &__secure_boot, sizeof(__secure_boot) }, }; BUILD_BUG_ON(ARRAY_SIZE(target) != ARRAY_SIZE(name)); diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index bfa30625f5d03..de659f6a815fd 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -11,6 +11,7 @@ #include #include +#include #include #include @@ -24,6 +25,8 @@ static bool efi_noinitrd; static bool efi_nosoftreserve; static bool efi_disable_pci_dma = IS_ENABLED(CONFIG_EFI_DISABLE_PCI_DMA); +int efi_mem_encrypt; + bool __pure __efi_soft_reserve_enabled(void) { return !efi_nosoftreserve; @@ -75,6 +78,12 @@ efi_status_t efi_parse_options(char const *cmdline) efi_noinitrd = true; } else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) { efi_no5lvl = true; + } else if (IS_ENABLED(CONFIG_ARCH_HAS_MEM_ENCRYPT) && + !strcmp(param, "mem_encrypt") && val) { + if (parse_option_str(val, "on")) + efi_mem_encrypt = 1; + else if (parse_option_str(val, "off")) + efi_mem_encrypt = -1; } else if (!strcmp(param, "efi") && val) { efi_nochunk = parse_option_str(val, "nochunk"); efi_novamap |= parse_option_str(val, "novamap"); @@ -193,7 +202,7 @@ void efi_apply_loadoptions_quirk(const void **load_options, u32 *load_options_si *load_options_size = load_option_unpacked.optional_data_size; } -enum efistub_event { +enum efistub_event_type { EFISTUB_EVT_INITRD, EFISTUB_EVT_LOAD_OPTIONS, EFISTUB_EVT_COUNT, @@ -219,54 +228,95 @@ static const struct { }, }; +static_assert(sizeof(efi_tcg2_event_t) == sizeof(efi_cc_event_t)); + +union efistub_event { + efi_tcg2_event_t tcg2_data; + efi_cc_event_t cc_data; +}; + +struct efistub_measured_event { + union efistub_event event_data; + TCG_PCClientTaggedEvent tagged_event __packed; +}; + static efi_status_t efi_measure_tagged_event(unsigned long load_addr, unsigned long load_size, - enum efistub_event event) + enum efistub_event_type event) { + union { + efi_status_t + (__efiapi *hash_log_extend_event)(void *, u64, efi_physical_addr_t, + u64, const union efistub_event *); + struct { u32 hash_log_extend_event; } mixed_mode; + } method; + struct efistub_measured_event *evt; + int size = struct_size(evt, tagged_event.tagged_event_data, + events[event].event_data_len); efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID; efi_tcg2_protocol_t *tcg2 = NULL; + union efistub_event ev; efi_status_t status; + void *protocol; efi_bs_call(locate_protocol, &tcg2_guid, NULL, (void **)&tcg2); if (tcg2) { - struct efi_measured_event { - efi_tcg2_event_t event_data; - efi_tcg2_tagged_event_t tagged_event; - u8 tagged_event_data[]; - } *evt; - int size = sizeof(*evt) + events[event].event_data_len; - - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, - (void **)&evt); - if (status != EFI_SUCCESS) - goto fail; - - evt->event_data = (struct efi_tcg2_event){ + ev.tcg2_data = (struct efi_tcg2_event){ .event_size = size, - .event_header.header_size = sizeof(evt->event_data.event_header), + .event_header.header_size = sizeof(ev.tcg2_data.event_header), .event_header.header_version = EFI_TCG2_EVENT_HEADER_VERSION, .event_header.pcr_index = events[event].pcr_index, .event_header.event_type = EV_EVENT_TAG, }; + protocol = tcg2; + method.hash_log_extend_event = + (void *)efi_table_attr(tcg2, hash_log_extend_event); + } else { + efi_guid_t cc_guid = EFI_CC_MEASUREMENT_PROTOCOL_GUID; + efi_cc_protocol_t *cc = NULL; - evt->tagged_event = (struct efi_tcg2_tagged_event){ - .tagged_event_id = events[event].event_id, - .tagged_event_data_size = events[event].event_data_len, - }; - - memcpy(evt->tagged_event_data, events[event].event_data, - events[event].event_data_len); + efi_bs_call(locate_protocol, &cc_guid, NULL, (void **)&cc); + if (!cc) + return EFI_UNSUPPORTED; - status = efi_call_proto(tcg2, hash_log_extend_event, 0, - load_addr, load_size, &evt->event_data); - efi_bs_call(free_pool, evt); + ev.cc_data = (struct efi_cc_event){ + .event_size = size, + .event_header.header_size = sizeof(ev.cc_data.event_header), + .event_header.header_version = EFI_CC_EVENT_HEADER_VERSION, + .event_header.event_type = EV_EVENT_TAG, + }; + status = efi_call_proto(cc, map_pcr_to_mr_index, + events[event].pcr_index, + &ev.cc_data.event_header.mr_index); if (status != EFI_SUCCESS) goto fail; - return EFI_SUCCESS; + + protocol = cc; + method.hash_log_extend_event = + (void *)efi_table_attr(cc, hash_log_extend_event); } - return EFI_UNSUPPORTED; + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, (void **)&evt); + if (status != EFI_SUCCESS) + goto fail; + + *evt = (struct efistub_measured_event) { + .event_data = ev, + .tagged_event.tagged_event_id = events[event].event_id, + .tagged_event.tagged_event_data_size = events[event].event_data_len, + }; + + memcpy(evt->tagged_event.tagged_event_data, events[event].event_data, + events[event].event_data_len); + + status = efi_fn_call(&method, hash_log_extend_event, protocol, 0, + load_addr, load_size, &evt->event_data); + efi_bs_call(free_pool, evt); + + if (status == EFI_SUCCESS) + return EFI_SUCCESS; + fail: efi_warn("Failed to measure data for event %d: 0x%lx\n", event, status); return status; diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c index f9c1e8a2bd1d3..958a680e0660d 100644 --- a/drivers/firmware/efi/libstub/efi-stub.c +++ b/drivers/firmware/efi/libstub/efi-stub.c @@ -167,7 +167,7 @@ efi_status_t efi_stub_common(efi_handle_t handle, si = setup_graphics(); - efi_retrieve_tpm2_eventlog(); + efi_retrieve_eventlog(); /* Ask the firmware to clear memory on unclean shutdown */ efi_enable_reset_attack_mitigation(); diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index c04b82ea40f21..e06d721d058d2 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -37,8 +37,8 @@ extern bool efi_no5lvl; extern bool efi_nochunk; extern bool efi_nokaslr; extern int efi_loglevel; +extern int efi_mem_encrypt; extern bool efi_novamap; - extern const efi_system_table_t *efi_system_table; typedef union efi_dxe_services_table efi_dxe_services_table_t; @@ -171,7 +171,7 @@ void efi_set_u64_split(u64 data, u32 *lo, u32 *hi) * the EFI memory map. Other related structures, e.g. x86 e820ext, need * to factor in this headroom requirement as well. */ -#define EFI_MMAP_NR_SLACK_SLOTS 8 +#define EFI_MMAP_NR_SLACK_SLOTS 16 typedef struct efi_generic_dev_path efi_device_path_protocol_t; @@ -843,14 +843,14 @@ struct efi_tcg2_event { /* u8[] event follows here */ } __packed; -struct efi_tcg2_tagged_event { - u32 tagged_event_id; - u32 tagged_event_data_size; - /* u8 tagged event data follows here */ -} __packed; +/* from TCG PC Client Platform Firmware Profile Specification */ +typedef struct tdTCG_PCClientTaggedEvent { + u32 tagged_event_id; + u32 tagged_event_data_size; + u8 tagged_event_data[]; +} TCG_PCClientTaggedEvent; typedef struct efi_tcg2_event efi_tcg2_event_t; -typedef struct efi_tcg2_tagged_event efi_tcg2_tagged_event_t; typedef union efi_tcg2_protocol efi_tcg2_protocol_t; union efi_tcg2_protocol { @@ -882,6 +882,87 @@ union efi_tcg2_protocol { } mixed_mode; }; +typedef struct { + u8 major; + u8 minor; +} efi_cc_version_t; + +typedef struct { + u8 type; + u8 sub_type; +} efi_cc_type_t; + +/* EFI CC type/subtype defines */ +#define EFI_CC_TYPE_NONE 0 +#define EFI_CC_TYPE_AMD_SEV 1 +#define EFI_CC_TYPE_INTEL_TDX 2 + +typedef u32 efi_cc_mr_index_t; + +struct efi_cc_event { + u32 event_size; + struct { + u32 header_size; + u16 header_version; + u32 mr_index; + u32 event_type; + } __packed event_header; + /* u8[] event follows here */ +} __packed; + +typedef struct efi_cc_event efi_cc_event_t; + +typedef u32 efi_cc_event_log_bitmap_t; +typedef u32 efi_cc_event_log_format_t; +typedef u32 efi_cc_event_algorithm_bitmap_t; + +typedef struct { + u8 size; + efi_cc_version_t structure_version; + efi_cc_version_t protocol_version; + efi_cc_event_algorithm_bitmap_t hash_algorithm_bitmap; + efi_cc_event_log_bitmap_t supported_event_logs; + efi_cc_type_t cc_type; +} efi_cc_boot_service_cap_t; + +#define EFI_CC_EVENT_HEADER_VERSION 1 + +#define EFI_CC_BOOT_HASH_ALG_SHA384 0x00000004 + +#define EFI_CC_EVENT_LOG_FORMAT_TCG_2 0x00000002 + +typedef union efi_cc_protocol efi_cc_protocol_t; + +union efi_cc_protocol { + struct { + efi_status_t + (__efiapi *get_capability)(efi_cc_protocol_t *, + efi_cc_boot_service_cap_t *); + + efi_status_t + (__efiapi *get_event_log)(efi_cc_protocol_t *, + efi_cc_event_log_format_t, + efi_physical_addr_t *, + efi_physical_addr_t *, + efi_bool_t *); + + efi_status_t + (__efiapi *hash_log_extend_event)(efi_cc_protocol_t *, u64, + efi_physical_addr_t, u64, + const efi_cc_event_t *); + + efi_status_t + (__efiapi *map_pcr_to_mr_index)(efi_cc_protocol_t *, u32, + efi_cc_mr_index_t *); + }; + struct { + u32 get_capability; + u32 get_event_log; + u32 hash_log_extend_event; + u32 map_pcr_to_mr_index; + } mixed_mode; +}; + struct riscv_efi_boot_protocol { u64 revision; @@ -1061,7 +1142,7 @@ static inline void efi_enable_reset_attack_mitigation(void) { } #endif -void efi_retrieve_tpm2_eventlog(void); +void efi_retrieve_eventlog(void); struct screen_info *alloc_screen_info(void); struct screen_info *__alloc_screen_info(void); diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 70e9789ff9de0..6c679da644dd6 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -132,6 +132,12 @@ static efi_status_t update_fdt(void *orig_fdt, unsigned long orig_fdt_size, } } + fdt_val32 = cpu_to_fdt32(efi_get_secureboot()); + status = fdt_setprop(fdt, node, "linux,uefi-secure-boot", + &fdt_val32, sizeof(fdt_val32)); + if (status) + goto fdt_set_fail; + /* Shrink the FDT back to its minimum size: */ fdt_pack(fdt); @@ -335,8 +341,8 @@ efi_status_t allocate_new_fdt_and_exit_boot(void *handle, fail: efi_free(fdt_size, fdt_addr); - - efi_bs_call(free_pool, priv.runtime_map); + if (!efi_novamap) + efi_bs_call(free_pool, priv.runtime_map); return EFI_LOAD_ERROR; } diff --git a/drivers/firmware/efi/libstub/loongarch.c b/drivers/firmware/efi/libstub/loongarch.c index 684c9354637c6..d0ef93551c44f 100644 --- a/drivers/firmware/efi/libstub/loongarch.c +++ b/drivers/firmware/efi/libstub/loongarch.c @@ -41,7 +41,7 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv) unsigned long __weak kernel_entry_address(unsigned long kernel_addr, efi_loaded_image_t *image) { - return *(unsigned long *)(kernel_addr + 8) - VMLINUX_LOAD_ADDRESS + kernel_addr; + return *(unsigned long *)(kernel_addr + 8) - PHYSADDR(VMLINUX_LOAD_ADDRESS) + kernel_addr; } efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image, diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index 4e96a855fdf47..c41e7b2091cdd 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -120,7 +120,7 @@ efi_status_t efi_random_alloc(unsigned long size, continue; } - target = round_up(md->phys_addr, align) + target_slot * align; + target = round_up(max_t(u64, md->phys_addr, alloc_min), align) + target_slot * align; pages = size / EFI_PAGE_SIZE; status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c index 7acbac16eae0b..df3182f2e63a5 100644 --- a/drivers/firmware/efi/libstub/tpm.c +++ b/drivers/firmware/efi/libstub/tpm.c @@ -47,39 +47,18 @@ void efi_enable_reset_attack_mitigation(void) #endif -void efi_retrieve_tpm2_eventlog(void) +static void efi_retrieve_tcg2_eventlog(int version, efi_physical_addr_t log_location, + efi_physical_addr_t log_last_entry, + efi_bool_t truncated, + struct efi_tcg2_final_events_table *final_events_table) { - efi_guid_t tcg2_guid = EFI_TCG2_PROTOCOL_GUID; efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID; efi_status_t status; - efi_physical_addr_t log_location = 0, log_last_entry = 0; struct linux_efi_tpm_eventlog *log_tbl = NULL; - struct efi_tcg2_final_events_table *final_events_table = NULL; unsigned long first_entry_addr, last_entry_addr; size_t log_size, last_entry_size; - efi_bool_t truncated; - int version = EFI_TCG2_EVENT_LOG_FORMAT_TCG_2; - efi_tcg2_protocol_t *tcg2_protocol = NULL; int final_events_size = 0; - status = efi_bs_call(locate_protocol, &tcg2_guid, NULL, - (void **)&tcg2_protocol); - if (status != EFI_SUCCESS) - return; - - status = efi_call_proto(tcg2_protocol, get_event_log, version, - &log_location, &log_last_entry, &truncated); - - if (status != EFI_SUCCESS || !log_location) { - version = EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2; - status = efi_call_proto(tcg2_protocol, get_event_log, version, - &log_location, &log_last_entry, - &truncated); - if (status != EFI_SUCCESS || !log_location) - return; - - } - first_entry_addr = (unsigned long) log_location; /* @@ -93,8 +72,10 @@ void efi_retrieve_tpm2_eventlog(void) * get_event_log only returns the address of the last entry. * We need to calculate its size to deduce the full size of * the logs. + * + * CC Event log also uses TCG2 format, handle it same as TPM2. */ - if (version == EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) { + if (version > EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2) { /* * The TCG2 log format has variable length entries, * and the information to decode the hash algorithms @@ -127,8 +108,6 @@ void efi_retrieve_tpm2_eventlog(void) * Figure out whether any events have already been logged to the * final events structure, and if so how much space they take up */ - if (version == EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) - final_events_table = get_efi_config_table(LINUX_EFI_TPM_FINAL_LOG_GUID); if (final_events_table && final_events_table->nr_events) { struct tcg_pcr_event2_head *header; int offset; @@ -165,3 +144,50 @@ void efi_retrieve_tpm2_eventlog(void) err_free: efi_bs_call(free_pool, log_tbl); } + +void efi_retrieve_eventlog(void) +{ + struct efi_tcg2_final_events_table *final_events_table = NULL; + efi_physical_addr_t log_location = 0, log_last_entry = 0; + efi_guid_t tpm2_guid = EFI_TCG2_PROTOCOL_GUID; + int version = EFI_TCG2_EVENT_LOG_FORMAT_TCG_2; + efi_tcg2_protocol_t *tpm2 = NULL; + efi_bool_t truncated; + efi_status_t status; + + status = efi_bs_call(locate_protocol, &tpm2_guid, NULL, (void **)&tpm2); + if (status == EFI_SUCCESS) { + status = efi_call_proto(tpm2, get_event_log, version, &log_location, + &log_last_entry, &truncated); + + if (status != EFI_SUCCESS || !log_location) { + version = EFI_TCG2_EVENT_LOG_FORMAT_TCG_1_2; + status = efi_call_proto(tpm2, get_event_log, version, + &log_location, &log_last_entry, + &truncated); + } else { + final_events_table = + get_efi_config_table(EFI_TCG2_FINAL_EVENTS_TABLE_GUID); + } + } else { + efi_guid_t cc_guid = EFI_CC_MEASUREMENT_PROTOCOL_GUID; + efi_cc_protocol_t *cc = NULL; + + status = efi_bs_call(locate_protocol, &cc_guid, NULL, (void **)&cc); + if (status != EFI_SUCCESS) + return; + + version = EFI_CC_EVENT_LOG_FORMAT_TCG_2; + status = efi_call_proto(cc, get_event_log, version, &log_location, + &log_last_entry, &truncated); + + final_events_table = + get_efi_config_table(EFI_CC_FINAL_EVENTS_TABLE_GUID); + } + + if (status != EFI_SUCCESS || !log_location) + return; + + efi_retrieve_tcg2_eventlog(version, log_location, log_last_entry, + truncated, final_events_table); +} diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 99429bc4b0c7e..1983fd3bf392e 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -21,6 +21,8 @@ #include "efistub.h" #include "x86-stub.h" +extern char _bss[], _ebss[]; + const efi_system_table_t *efi_system_table; const efi_dxe_services_table_t *efi_dxe_table; static efi_loaded_image_t *image = NULL; @@ -236,6 +238,15 @@ efi_status_t efi_adjust_memory_range_protection(unsigned long start, rounded_end = roundup(start + size, EFI_PAGE_SIZE); if (memattr != NULL) { + status = efi_call_proto(memattr, set_memory_attributes, + rounded_start, + rounded_end - rounded_start, + EFI_MEMORY_RO); + if (status != EFI_SUCCESS) { + efi_warn("Failed to set EFI_MEMORY_RO attribute\n"); + return status; + } + status = efi_call_proto(memattr, clear_memory_attributes, rounded_start, rounded_end - rounded_start, @@ -465,6 +476,9 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_status_t status; char *cmdline_ptr; + if (efi_is_native()) + memset(_bss, 0, _ebss - _bss); + efi_system_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ @@ -482,6 +496,7 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, hdr->vid_mode = 0xffff; hdr->type_of_loader = 0x21; + hdr->initrd_addr_max = INT_MAX; /* Convert unicode cmdline to ascii */ cmdline_ptr = efi_convert_cmdline(image, &options_size); @@ -761,6 +776,26 @@ static void error(char *str) efi_warn("Decompression failed: %s\n", str); } +static const char *cmdline_memmap_override; + +static efi_status_t parse_options(const char *cmdline) +{ + static const char opts[][14] = { + "mem=", "memmap=", "efi_fake_mem=", "hugepages=" + }; + + for (int i = 0; i < ARRAY_SIZE(opts); i++) { + const char *p = strstr(cmdline, opts[i]); + + if (p == cmdline || (p > cmdline && isspace(p[-1]))) { + cmdline_memmap_override = opts[i]; + break; + } + } + + return efi_parse_options(cmdline); +} + static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) { unsigned long virt_addr = LOAD_PHYSICAL_ADDR; @@ -792,6 +827,10 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) { efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n"); seed[0] = 0; + } else if (cmdline_memmap_override) { + efi_info("%s detected on the kernel command line - disabling physical KASLR\n", + cmdline_memmap_override); + seed[0] = 0; } boot_params_ptr->hdr.loadflags |= KASLR_FLAG; @@ -812,7 +851,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) *kernel_entry = addr + entry; - return efi_adjust_memory_range_protection(addr, kernel_total_size); + return efi_adjust_memory_range_protection(addr, kernel_text_size); } static void __noreturn enter_kernel(unsigned long kernel_addr, @@ -868,7 +907,7 @@ void __noreturn efi_stub_entry(efi_handle_t handle, } #ifdef CONFIG_CMDLINE_BOOL - status = efi_parse_options(CONFIG_CMDLINE); + status = parse_options(CONFIG_CMDLINE); if (status != EFI_SUCCESS) { efi_err("Failed to parse options\n"); goto fail; @@ -877,13 +916,16 @@ void __noreturn efi_stub_entry(efi_handle_t handle, if (!IS_ENABLED(CONFIG_CMDLINE_OVERRIDE)) { unsigned long cmdline_paddr = ((u64)hdr->cmd_line_ptr | ((u64)boot_params->ext_cmd_line_ptr << 32)); - status = efi_parse_options((char *)cmdline_paddr); + status = parse_options((char *)cmdline_paddr); if (status != EFI_SUCCESS) { efi_err("Failed to parse options\n"); goto fail; } } + if (efi_mem_encrypt > 0) + hdr->xloadflags |= XLF_MEM_ENCRYPTION; + status = efi_decompress_kernel(&kernel_entry); if (status != EFI_SUCCESS) { efi_err("Failed to decompress kernel\n"); @@ -923,7 +965,7 @@ void __noreturn efi_stub_entry(efi_handle_t handle, efi_random_get_seed(); - efi_retrieve_tpm2_eventlog(); + efi_retrieve_eventlog(); setup_graphics(boot_params); @@ -958,8 +1000,6 @@ void __noreturn efi_stub_entry(efi_handle_t handle, void efi_handover_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, struct boot_params *boot_params) { - extern char _bss[], _ebss[]; - memset(_bss, 0, _ebss - _bss); efi_stub_entry(handle, sys_table_arg, boot_params); } diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index 3365944f79654..34109fd86c55d 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -15,10 +15,6 @@ #include #include -#ifndef __efi_memmap_free -#define __efi_memmap_free(phys, size, flags) do { } while (0) -#endif - /** * __efi_memmap_init - Common code for mapping the EFI memory map * @data: EFI memory map data @@ -51,11 +47,6 @@ int __init __efi_memmap_init(struct efi_memory_map_data *data) return -ENOMEM; } - if (efi.memmap.flags & (EFI_MEMMAP_MEMBLOCK | EFI_MEMMAP_SLAB)) - __efi_memmap_free(efi.memmap.phys_map, - efi.memmap.desc_size * efi.memmap.nr_map, - efi.memmap.flags); - map.phys_map = data->phys_map; map.nr_map = data->size / data->desc_size; map.map_end = map.map + data->size; diff --git a/drivers/firmware/efi/secureboot.c b/drivers/firmware/efi/secureboot.c new file mode 100644 index 0000000000000..de0a3714a5d44 --- /dev/null +++ b/drivers/firmware/efi/secureboot.c @@ -0,0 +1,38 @@ +/* Core kernel secure boot support. + * + * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +/* + * Decide what to do when UEFI secure boot mode is enabled. + */ +void __init efi_set_secure_boot(enum efi_secureboot_mode mode) +{ + if (efi_enabled(EFI_BOOT)) { + switch (mode) { + case efi_secureboot_mode_disabled: + pr_info("Secure boot disabled\n"); + break; + case efi_secureboot_mode_enabled: + set_bit(EFI_SECURE_BOOT, &efi.flags); + pr_info("Secure boot enabled\n"); + break; + default: + pr_warn("Secure boot could not be determined (mode %u)\n", + mode); + break; + } + } +} diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c index 5b439d04079c8..50f6503fe49f5 100644 --- a/drivers/firmware/efi/unaccepted_memory.c +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -4,6 +4,7 @@ #include #include #include +#include #include /* Protects unaccepted memory bitmap and accepting_list */ @@ -149,6 +150,9 @@ void accept_memory(phys_addr_t start, phys_addr_t end) } list_del(&range.list); + + touch_softlockup_watchdog(); + spin_unlock_irqrestore(&unaccepted_memory_lock, flags); } diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index fbeeaee4ac856..23134ffc4dfc6 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -206,10 +206,12 @@ static int mpfs_auto_update_verify_image(struct fw_upload *fw_uploader) if (ret | response->resp_status) { dev_warn(priv->dev, "Verification of Upgrade Image failed!\n"); ret = ret ? ret : -EBADMSG; + goto free_message; } dev_info(priv->dev, "Verification of Upgrade Image passed!\n"); +free_message: devm_kfree(priv->dev, message); free_response: devm_kfree(priv->dev, response); diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index d9629ff878619..2328ca58bba61 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -497,10 +497,12 @@ int psci_cpu_suspend_enter(u32 state) static int psci_system_suspend(unsigned long unused) { + int err; phys_addr_t pa_cpu_resume = __pa_symbol(cpu_resume); - return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND), + err = invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND), pa_cpu_resume, 0, 0); + return psci_to_linux_errno(err); } static int psci_system_suspend_enter(suspend_state_t state) diff --git a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c index 32188f098ef34..bc550ad0dbe0c 100644 --- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c +++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c @@ -221,6 +221,19 @@ struct qsee_rsp_uefi_query_variable_info { * alignment of 8 bytes (64 bits) for GUIDs. Our definition of efi_guid_t, * however, has an alignment of 4 byte (32 bits). So far, this seems to work * fine here. See also the comment on the typedef of efi_guid_t. + * + * Note: It looks like uefisecapp is quite picky about how the memory passed to + * it is structured and aligned. In particular the request/response setup used + * for QSEE_CMD_UEFI_GET_VARIABLE. While qcom_qseecom_app_send(), in theory, + * accepts separate buffers/addresses for the request and response parts, in + * practice, however, it seems to expect them to be both part of a larger + * contiguous block. We initially allocated separate buffers for the request + * and response but this caused the QSEE_CMD_UEFI_GET_VARIABLE command to + * either not write any response to the response buffer or outright crash the + * device. Therefore, we now allocate a single contiguous block of DMA memory + * for both and properly align the data using the macros below. In particular, + * request and response structs are aligned at 8 byte (via __reqdata_offs()), + * following the driver that this has been reverse-engineered from. */ #define qcuefi_buf_align_fields(fields...) \ ({ \ @@ -244,6 +257,12 @@ struct qsee_rsp_uefi_query_variable_info { #define __array_offs(type, count, offset) \ __field_impl(sizeof(type) * (count), __alignof__(type), offset) +#define __array_offs_aligned(type, count, align, offset) \ + __field_impl(sizeof(type) * (count), align, offset) + +#define __reqdata_offs(size, offset) \ + __array_offs_aligned(u8, size, 8, offset) + #define __array(type, count) __array_offs(type, count, NULL) #define __field_offs(type, offset) __array_offs(type, 1, offset) #define __field(type) __array_offs(type, 1, NULL) @@ -277,10 +296,15 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e unsigned long buffer_size = *data_size; efi_status_t efi_status = EFI_SUCCESS; unsigned long name_length; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t guid_offs; size_t name_offs; size_t req_size; size_t rsp_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name || !guid) @@ -304,17 +328,19 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e __array(u8, buffer_size) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(rsp_size, &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(rsp_size, GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_GET_VARIABLE; req_data->data_size = buffer_size; @@ -332,7 +358,9 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e memcpy(((void *)req_data) + req_data->guid_offset, guid, req_data->guid_size); - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, rsp_size); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -407,9 +435,7 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e memcpy(data, ((void *)rsp_data) + rsp_data->data_offset, rsp_data->data_size); out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -422,10 +448,15 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e struct qsee_rsp_uefi_set_variable *rsp_data; efi_status_t efi_status = EFI_SUCCESS; unsigned long name_length; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t name_offs; size_t guid_offs; size_t data_offs; size_t req_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name || !guid) @@ -450,17 +481,19 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e __array_offs(u8, data_size, &data_offs) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(sizeof(*rsp_data), &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(sizeof(*rsp_data), GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_SET_VARIABLE; req_data->attributes = attributes; @@ -483,8 +516,9 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e if (data_size) memcpy(((void *)req_data) + req_data->data_offset, data, req_data->data_size); - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, - sizeof(*rsp_data)); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, sizeof(*rsp_data)); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -507,9 +541,7 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e } out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -521,10 +553,15 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, struct qsee_req_uefi_get_next_variable *req_data; struct qsee_rsp_uefi_get_next_variable *rsp_data; efi_status_t efi_status = EFI_SUCCESS; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t guid_offs; size_t name_offs; size_t req_size; size_t rsp_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name_size || !name || !guid) @@ -545,17 +582,19 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, __array(*name, *name_size / sizeof(*name)) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(rsp_size, &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(rsp_size, GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_GET_NEXT_VARIABLE; req_data->guid_offset = guid_offs; @@ -572,7 +611,9 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, goto out_free; } - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, rsp_size); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -645,9 +686,7 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, } out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -659,26 +698,34 @@ static efi_status_t qsee_uefi_query_variable_info(struct qcuefi_client *qcuefi, struct qsee_req_uefi_query_variable_info *req_data; struct qsee_rsp_uefi_query_variable_info *rsp_data; efi_status_t efi_status = EFI_SUCCESS; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; + size_t req_offs; + size_t rsp_offs; int status; - req_data = kzalloc(sizeof(*req_data), GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(sizeof(*req_data), &req_offs) + __reqdata_offs(sizeof(*rsp_data), &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(sizeof(*rsp_data), GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_QUERY_VARIABLE_INFO; req_data->attributes = attr; req_data->length = sizeof(*req_data); - status = qcom_qseecom_app_send(qcuefi->client, req_data, sizeof(*req_data), rsp_data, - sizeof(*rsp_data)); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, sizeof(*req_data), + cmd_buf_dma + rsp_offs, sizeof(*rsp_data)); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -711,9 +758,7 @@ static efi_status_t qsee_uefi_query_variable_info(struct qcuefi_client *qcuefi, *max_variable_size = rsp_data->max_variable_size; out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c index 520de9b5633ab..2ad85052b3f60 100644 --- a/drivers/firmware/qcom/qcom_scm.c +++ b/drivers/firmware/qcom/qcom_scm.c @@ -569,13 +569,14 @@ int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size, ret = qcom_scm_bw_enable(); if (ret) - return ret; + goto disable_clk; desc.args[1] = mdata_phys; ret = qcom_scm_call(__scm->dev, &desc, &res); - qcom_scm_bw_disable(); + +disable_clk: qcom_scm_clk_disable(); out: @@ -637,10 +638,12 @@ int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size) ret = qcom_scm_bw_enable(); if (ret) - return ret; + goto disable_clk; ret = qcom_scm_call(__scm->dev, &desc, &res); qcom_scm_bw_disable(); + +disable_clk: qcom_scm_clk_disable(); return ret ? : res.result[0]; @@ -672,10 +675,12 @@ int qcom_scm_pas_auth_and_reset(u32 peripheral) ret = qcom_scm_bw_enable(); if (ret) - return ret; + goto disable_clk; ret = qcom_scm_call(__scm->dev, &desc, &res); qcom_scm_bw_disable(); + +disable_clk: qcom_scm_clk_disable(); return ret ? : res.result[0]; @@ -706,11 +711,12 @@ int qcom_scm_pas_shutdown(u32 peripheral) ret = qcom_scm_bw_enable(); if (ret) - return ret; + goto disable_clk; ret = qcom_scm_call(__scm->dev, &desc, &res); - qcom_scm_bw_disable(); + +disable_clk: qcom_scm_clk_disable(); return ret ? : res.result[0]; @@ -1576,9 +1582,9 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_get_id); /** * qcom_scm_qseecom_app_send() - Send to and receive data from a given QSEE app. * @app_id: The ID of the target app. - * @req: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given ID and read back @@ -1589,33 +1595,13 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_get_id); * * Return: Zero on success, nonzero on failure. */ -int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, - size_t rsp_size) +int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { struct qcom_scm_qseecom_resp res = {}; struct qcom_scm_desc desc = {}; - dma_addr_t req_phys; - dma_addr_t rsp_phys; int status; - /* Map request buffer */ - req_phys = dma_map_single(__scm->dev, req, req_size, DMA_TO_DEVICE); - status = dma_mapping_error(__scm->dev, req_phys); - if (status) { - dev_err(__scm->dev, "qseecom: failed to map request buffer\n"); - return status; - } - - /* Map response buffer */ - rsp_phys = dma_map_single(__scm->dev, rsp, rsp_size, DMA_FROM_DEVICE); - status = dma_mapping_error(__scm->dev, rsp_phys); - if (status) { - dma_unmap_single(__scm->dev, req_phys, req_size, DMA_TO_DEVICE); - dev_err(__scm->dev, "qseecom: failed to map response buffer\n"); - return status; - } - - /* Set up SCM call data */ desc.owner = QSEECOM_TZ_OWNER_TZ_APPS; desc.svc = QSEECOM_TZ_SVC_APP_ID_PLACEHOLDER; desc.cmd = QSEECOM_TZ_CMD_APP_SEND; @@ -1623,18 +1609,13 @@ int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, QCOM_SCM_RW, QCOM_SCM_VAL, QCOM_SCM_RW, QCOM_SCM_VAL); desc.args[0] = app_id; - desc.args[1] = req_phys; + desc.args[1] = req; desc.args[2] = req_size; - desc.args[3] = rsp_phys; + desc.args[3] = rsp; desc.args[4] = rsp_size; - /* Perform call */ status = qcom_scm_qseecom_call(&desc, &res); - /* Unmap buffers */ - dma_unmap_single(__scm->dev, rsp_phys, rsp_size, DMA_FROM_DEVICE); - dma_unmap_single(__scm->dev, req_phys, req_size, DMA_TO_DEVICE); - if (status) return status; @@ -1649,7 +1630,7 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_send); * We do not yet support re-entrant calls via the qseecom interface. To prevent + any potential issues with this, only allow validated machines for now. */ -static const struct of_device_id qcom_scm_qseecom_allowlist[] = { +static const struct of_device_id qcom_scm_qseecom_allowlist[] __maybe_unused = { { .compatible = "lenovo,thinkpad-x13s", }, { } }; @@ -1738,7 +1719,7 @@ static int qcom_scm_qseecom_init(struct qcom_scm *scm) */ bool qcom_scm_is_available(void) { - return !!__scm; + return !!READ_ONCE(__scm); } EXPORT_SYMBOL_GPL(qcom_scm_is_available); @@ -1819,10 +1800,12 @@ static int qcom_scm_probe(struct platform_device *pdev) if (!scm) return -ENOMEM; + scm->dev = &pdev->dev; ret = qcom_scm_find_dload_address(&pdev->dev, &scm->dload_mode_addr); if (ret < 0) return ret; + init_completion(&scm->waitq_comp); mutex_init(&scm->scm_bw_lock); scm->path = devm_of_icc_get(&pdev->dev, NULL); @@ -1854,10 +1837,8 @@ static int qcom_scm_probe(struct platform_device *pdev) if (ret) return ret; - __scm = scm; - __scm->dev = &pdev->dev; - - init_completion(&__scm->waitq_comp); + /* Let all above stores be available after this */ + smp_store_release(&__scm, scm); irq = platform_get_irq_optional(pdev, 0); if (irq < 0) { diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c index 322aada20f742..ac34876a97f8b 100644 --- a/drivers/firmware/raspberrypi.c +++ b/drivers/firmware/raspberrypi.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -97,8 +98,8 @@ int rpi_firmware_property_list(struct rpi_firmware *fw, if (size & 3) return -EINVAL; - buf = dma_alloc_coherent(fw->cl.dev, PAGE_ALIGN(size), &bus_addr, - GFP_ATOMIC); + buf = dma_alloc_coherent(fw->chan->mbox->dev, PAGE_ALIGN(size), + &bus_addr, GFP_ATOMIC); if (!buf) return -ENOMEM; @@ -126,7 +127,7 @@ int rpi_firmware_property_list(struct rpi_firmware *fw, ret = -EINVAL; } - dma_free_coherent(fw->cl.dev, PAGE_ALIGN(size), buf, bus_addr); + dma_free_coherent(fw->chan->mbox->dev, PAGE_ALIGN(size), buf, bus_addr); return ret; } diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c index bbcdd9fed3fb6..4221fed70ad48 100644 --- a/drivers/firmware/tegra/bpmp-debugfs.c +++ b/drivers/firmware/tegra/bpmp-debugfs.c @@ -77,7 +77,7 @@ static const char *get_filename(struct tegra_bpmp *bpmp, root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL); if (!root_path_buf) - goto out; + return NULL; root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf, root_path_buf_len); diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c index 98b8fd16183e4..80cac3a5f9767 100644 --- a/drivers/fpga/dfl-pci.c +++ b/drivers/fpga/dfl-pci.c @@ -78,6 +78,7 @@ static void cci_pci_free_irq(struct pci_dev *pcidev) #define PCIE_DEVICE_ID_SILICOM_PAC_N5011 0x1001 #define PCIE_DEVICE_ID_INTEL_DFL 0xbcce /* PCI Subdevice ID for PCIE_DEVICE_ID_INTEL_DFL */ +#define PCIE_SUBDEVICE_ID_INTEL_D5005 0x138d #define PCIE_SUBDEVICE_ID_INTEL_N6000 0x1770 #define PCIE_SUBDEVICE_ID_INTEL_N6001 0x1771 #define PCIE_SUBDEVICE_ID_INTEL_C6100 0x17d4 @@ -101,6 +102,8 @@ static struct pci_device_id cci_pcie_id_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_PAC_D5005_VF),}, {PCI_DEVICE(PCI_VENDOR_ID_SILICOM_DENMARK, PCIE_DEVICE_ID_SILICOM_PAC_N5010),}, {PCI_DEVICE(PCI_VENDOR_ID_SILICOM_DENMARK, PCIE_DEVICE_ID_SILICOM_PAC_N5011),}, + {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL, + PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_D5005),}, {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL, PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_N6000),}, {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL_VF, diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index a024be2b84e29..83d35fbb82450 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -55,33 +55,26 @@ int fpga_bridge_disable(struct fpga_bridge *bridge) } EXPORT_SYMBOL_GPL(fpga_bridge_disable); -static struct fpga_bridge *__fpga_bridge_get(struct device *dev, +static struct fpga_bridge *__fpga_bridge_get(struct device *bridge_dev, struct fpga_image_info *info) { struct fpga_bridge *bridge; - int ret = -ENODEV; - bridge = to_fpga_bridge(dev); + bridge = to_fpga_bridge(bridge_dev); bridge->info = info; - if (!mutex_trylock(&bridge->mutex)) { - ret = -EBUSY; - goto err_dev; - } + if (!mutex_trylock(&bridge->mutex)) + return ERR_PTR(-EBUSY); - if (!try_module_get(dev->parent->driver->owner)) - goto err_ll_mod; + if (!try_module_get(bridge->br_ops_owner)) { + mutex_unlock(&bridge->mutex); + return ERR_PTR(-ENODEV); + } dev_dbg(&bridge->dev, "get\n"); return bridge; - -err_ll_mod: - mutex_unlock(&bridge->mutex); -err_dev: - put_device(dev); - return ERR_PTR(ret); } /** @@ -98,13 +91,18 @@ static struct fpga_bridge *__fpga_bridge_get(struct device *dev, struct fpga_bridge *of_fpga_bridge_get(struct device_node *np, struct fpga_image_info *info) { - struct device *dev; + struct fpga_bridge *bridge; + struct device *bridge_dev; - dev = class_find_device_by_of_node(&fpga_bridge_class, np); - if (!dev) + bridge_dev = class_find_device_by_of_node(&fpga_bridge_class, np); + if (!bridge_dev) return ERR_PTR(-ENODEV); - return __fpga_bridge_get(dev, info); + bridge = __fpga_bridge_get(bridge_dev, info); + if (IS_ERR(bridge)) + put_device(bridge_dev); + + return bridge; } EXPORT_SYMBOL_GPL(of_fpga_bridge_get); @@ -125,6 +123,7 @@ static int fpga_bridge_dev_match(struct device *dev, const void *data) struct fpga_bridge *fpga_bridge_get(struct device *dev, struct fpga_image_info *info) { + struct fpga_bridge *bridge; struct device *bridge_dev; bridge_dev = class_find_device(&fpga_bridge_class, NULL, dev, @@ -132,7 +131,11 @@ struct fpga_bridge *fpga_bridge_get(struct device *dev, if (!bridge_dev) return ERR_PTR(-ENODEV); - return __fpga_bridge_get(bridge_dev, info); + bridge = __fpga_bridge_get(bridge_dev, info); + if (IS_ERR(bridge)) + put_device(bridge_dev); + + return bridge; } EXPORT_SYMBOL_GPL(fpga_bridge_get); @@ -146,7 +149,7 @@ void fpga_bridge_put(struct fpga_bridge *bridge) dev_dbg(&bridge->dev, "put\n"); bridge->info = NULL; - module_put(bridge->dev.parent->driver->owner); + module_put(bridge->br_ops_owner); mutex_unlock(&bridge->mutex); put_device(&bridge->dev); } @@ -316,18 +319,19 @@ static struct attribute *fpga_bridge_attrs[] = { ATTRIBUTE_GROUPS(fpga_bridge); /** - * fpga_bridge_register - create and register an FPGA Bridge device + * __fpga_bridge_register - create and register an FPGA Bridge device * @parent: FPGA bridge device from pdev * @name: FPGA bridge name * @br_ops: pointer to structure of fpga bridge ops * @priv: FPGA bridge private data + * @owner: owner module containing the br_ops * * Return: struct fpga_bridge pointer or ERR_PTR() */ struct fpga_bridge * -fpga_bridge_register(struct device *parent, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv) +__fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, + void *priv, struct module *owner) { struct fpga_bridge *bridge; int id, ret; @@ -357,6 +361,7 @@ fpga_bridge_register(struct device *parent, const char *name, bridge->name = name; bridge->br_ops = br_ops; + bridge->br_ops_owner = owner; bridge->priv = priv; bridge->dev.groups = br_ops->groups; @@ -386,7 +391,7 @@ fpga_bridge_register(struct device *parent, const char *name, return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(fpga_bridge_register); +EXPORT_SYMBOL_GPL(__fpga_bridge_register); /** * fpga_bridge_unregister - unregister an FPGA bridge diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c index 06651389c5926..0f4035b089a2e 100644 --- a/drivers/fpga/fpga-mgr.c +++ b/drivers/fpga/fpga-mgr.c @@ -664,20 +664,16 @@ static struct attribute *fpga_mgr_attrs[] = { }; ATTRIBUTE_GROUPS(fpga_mgr); -static struct fpga_manager *__fpga_mgr_get(struct device *dev) +static struct fpga_manager *__fpga_mgr_get(struct device *mgr_dev) { struct fpga_manager *mgr; - mgr = to_fpga_manager(dev); + mgr = to_fpga_manager(mgr_dev); - if (!try_module_get(dev->parent->driver->owner)) - goto err_dev; + if (!try_module_get(mgr->mops_owner)) + mgr = ERR_PTR(-ENODEV); return mgr; - -err_dev: - put_device(dev); - return ERR_PTR(-ENODEV); } static int fpga_mgr_dev_match(struct device *dev, const void *data) @@ -693,12 +689,18 @@ static int fpga_mgr_dev_match(struct device *dev, const void *data) */ struct fpga_manager *fpga_mgr_get(struct device *dev) { - struct device *mgr_dev = class_find_device(&fpga_mgr_class, NULL, dev, - fpga_mgr_dev_match); + struct fpga_manager *mgr; + struct device *mgr_dev; + + mgr_dev = class_find_device(&fpga_mgr_class, NULL, dev, fpga_mgr_dev_match); if (!mgr_dev) return ERR_PTR(-ENODEV); - return __fpga_mgr_get(mgr_dev); + mgr = __fpga_mgr_get(mgr_dev); + if (IS_ERR(mgr)) + put_device(mgr_dev); + + return mgr; } EXPORT_SYMBOL_GPL(fpga_mgr_get); @@ -711,13 +713,18 @@ EXPORT_SYMBOL_GPL(fpga_mgr_get); */ struct fpga_manager *of_fpga_mgr_get(struct device_node *node) { - struct device *dev; + struct fpga_manager *mgr; + struct device *mgr_dev; - dev = class_find_device_by_of_node(&fpga_mgr_class, node); - if (!dev) + mgr_dev = class_find_device_by_of_node(&fpga_mgr_class, node); + if (!mgr_dev) return ERR_PTR(-ENODEV); - return __fpga_mgr_get(dev); + mgr = __fpga_mgr_get(mgr_dev); + if (IS_ERR(mgr)) + put_device(mgr_dev); + + return mgr; } EXPORT_SYMBOL_GPL(of_fpga_mgr_get); @@ -727,7 +734,7 @@ EXPORT_SYMBOL_GPL(of_fpga_mgr_get); */ void fpga_mgr_put(struct fpga_manager *mgr) { - module_put(mgr->dev.parent->driver->owner); + module_put(mgr->mops_owner); put_device(&mgr->dev); } EXPORT_SYMBOL_GPL(fpga_mgr_put); @@ -766,9 +773,10 @@ void fpga_mgr_unlock(struct fpga_manager *mgr) EXPORT_SYMBOL_GPL(fpga_mgr_unlock); /** - * fpga_mgr_register_full - create and register an FPGA Manager device + * __fpga_mgr_register_full - create and register an FPGA Manager device * @parent: fpga manager device from pdev * @info: parameters for fpga manager + * @owner: owner module containing the ops * * The caller of this function is responsible for calling fpga_mgr_unregister(). * Using devm_fpga_mgr_register_full() instead is recommended. @@ -776,7 +784,8 @@ EXPORT_SYMBOL_GPL(fpga_mgr_unlock); * Return: pointer to struct fpga_manager pointer or ERR_PTR() */ struct fpga_manager * -fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info) +__fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner) { const struct fpga_manager_ops *mops = info->mops; struct fpga_manager *mgr; @@ -804,6 +813,8 @@ fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *in mutex_init(&mgr->ref_mutex); + mgr->mops_owner = owner; + mgr->name = info->name; mgr->mops = info->mops; mgr->priv = info->priv; @@ -841,14 +852,15 @@ fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *in return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(fpga_mgr_register_full); +EXPORT_SYMBOL_GPL(__fpga_mgr_register_full); /** - * fpga_mgr_register - create and register an FPGA Manager device + * __fpga_mgr_register - create and register an FPGA Manager device * @parent: fpga manager device from pdev * @name: fpga manager name * @mops: pointer to structure of fpga manager ops * @priv: fpga manager private data + * @owner: owner module containing the ops * * The caller of this function is responsible for calling fpga_mgr_unregister(). * Using devm_fpga_mgr_register() instead is recommended. This simple @@ -859,8 +871,8 @@ EXPORT_SYMBOL_GPL(fpga_mgr_register_full); * Return: pointer to struct fpga_manager pointer or ERR_PTR() */ struct fpga_manager * -fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv) +__fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, struct module *owner) { struct fpga_manager_info info = { 0 }; @@ -868,9 +880,9 @@ fpga_mgr_register(struct device *parent, const char *name, info.mops = mops; info.priv = priv; - return fpga_mgr_register_full(parent, &info); + return __fpga_mgr_register_full(parent, &info, owner); } -EXPORT_SYMBOL_GPL(fpga_mgr_register); +EXPORT_SYMBOL_GPL(__fpga_mgr_register); /** * fpga_mgr_unregister - unregister an FPGA manager @@ -900,9 +912,10 @@ static void devm_fpga_mgr_unregister(struct device *dev, void *res) } /** - * devm_fpga_mgr_register_full - resource managed variant of fpga_mgr_register() + * __devm_fpga_mgr_register_full - resource managed variant of fpga_mgr_register() * @parent: fpga manager device from pdev * @info: parameters for fpga manager + * @owner: owner module containing the ops * * Return: fpga manager pointer on success, negative error code otherwise. * @@ -910,7 +923,8 @@ static void devm_fpga_mgr_unregister(struct device *dev, void *res) * function will be called automatically when the managing device is detached. */ struct fpga_manager * -devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info) +__devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner) { struct fpga_mgr_devres *dr; struct fpga_manager *mgr; @@ -919,7 +933,7 @@ devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_inf if (!dr) return ERR_PTR(-ENOMEM); - mgr = fpga_mgr_register_full(parent, info); + mgr = __fpga_mgr_register_full(parent, info, owner); if (IS_ERR(mgr)) { devres_free(dr); return mgr; @@ -930,14 +944,15 @@ devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_inf return mgr; } -EXPORT_SYMBOL_GPL(devm_fpga_mgr_register_full); +EXPORT_SYMBOL_GPL(__devm_fpga_mgr_register_full); /** - * devm_fpga_mgr_register - resource managed variant of fpga_mgr_register() + * __devm_fpga_mgr_register - resource managed variant of fpga_mgr_register() * @parent: fpga manager device from pdev * @name: fpga manager name * @mops: pointer to structure of fpga manager ops * @priv: fpga manager private data + * @owner: owner module containing the ops * * Return: fpga manager pointer on success, negative error code otherwise. * @@ -946,8 +961,9 @@ EXPORT_SYMBOL_GPL(devm_fpga_mgr_register_full); * device is detached. */ struct fpga_manager * -devm_fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv) +__devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, + struct module *owner) { struct fpga_manager_info info = { 0 }; @@ -955,9 +971,9 @@ devm_fpga_mgr_register(struct device *parent, const char *name, info.mops = mops; info.priv = priv; - return devm_fpga_mgr_register_full(parent, &info); + return __devm_fpga_mgr_register_full(parent, &info, owner); } -EXPORT_SYMBOL_GPL(devm_fpga_mgr_register); +EXPORT_SYMBOL_GPL(__devm_fpga_mgr_register); static void fpga_mgr_dev_release(struct device *dev) { diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c index b364a929425ce..753cd142503e0 100644 --- a/drivers/fpga/fpga-region.c +++ b/drivers/fpga/fpga-region.c @@ -53,7 +53,7 @@ static struct fpga_region *fpga_region_get(struct fpga_region *region) } get_device(dev); - if (!try_module_get(dev->parent->driver->owner)) { + if (!try_module_get(region->ops_owner)) { put_device(dev); mutex_unlock(®ion->mutex); return ERR_PTR(-ENODEV); @@ -75,7 +75,7 @@ static void fpga_region_put(struct fpga_region *region) dev_dbg(dev, "put\n"); - module_put(dev->parent->driver->owner); + module_put(region->ops_owner); put_device(dev); mutex_unlock(®ion->mutex); } @@ -181,14 +181,16 @@ static struct attribute *fpga_region_attrs[] = { ATTRIBUTE_GROUPS(fpga_region); /** - * fpga_region_register_full - create and register an FPGA Region device + * __fpga_region_register_full - create and register an FPGA Region device * @parent: device parent * @info: parameters for FPGA Region + * @owner: module containing the get_bridges function * * Return: struct fpga_region or ERR_PTR() */ struct fpga_region * -fpga_region_register_full(struct device *parent, const struct fpga_region_info *info) +__fpga_region_register_full(struct device *parent, const struct fpga_region_info *info, + struct module *owner) { struct fpga_region *region; int id, ret = 0; @@ -213,6 +215,7 @@ fpga_region_register_full(struct device *parent, const struct fpga_region_info * region->compat_id = info->compat_id; region->priv = info->priv; region->get_bridges = info->get_bridges; + region->ops_owner = owner; mutex_init(®ion->mutex); INIT_LIST_HEAD(®ion->bridge_list); @@ -241,13 +244,14 @@ fpga_region_register_full(struct device *parent, const struct fpga_region_info * return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(fpga_region_register_full); +EXPORT_SYMBOL_GPL(__fpga_region_register_full); /** - * fpga_region_register - create and register an FPGA Region device + * __fpga_region_register - create and register an FPGA Region device * @parent: device parent * @mgr: manager that programs this region * @get_bridges: optional function to get bridges to a list + * @owner: module containing the get_bridges function * * This simple version of the register function should be sufficient for most users. * The fpga_region_register_full() function is available for users that need to @@ -256,17 +260,17 @@ EXPORT_SYMBOL_GPL(fpga_region_register_full); * Return: struct fpga_region or ERR_PTR() */ struct fpga_region * -fpga_region_register(struct device *parent, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)) +__fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *), struct module *owner) { struct fpga_region_info info = { 0 }; info.mgr = mgr; info.get_bridges = get_bridges; - return fpga_region_register_full(parent, &info); + return __fpga_region_register_full(parent, &info, owner); } -EXPORT_SYMBOL_GPL(fpga_region_register); +EXPORT_SYMBOL_GPL(__fpga_region_register); /** * fpga_region_unregister - unregister an FPGA region diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 1301cec94f128..f1fc51ccaf65f 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -711,7 +711,8 @@ config GPIO_UNIPHIER Say yes here to support UniPhier GPIOs. config GPIO_VF610 - def_bool y + bool "VF610 GPIO support" + default y if SOC_VF610 depends on ARCH_MXC select GPIOLIB_IRQCHIP help @@ -1526,7 +1527,7 @@ config GPIO_TPS68470 are "output only" GPIOs. config GPIO_TQMX86 - tristate "TQ-Systems QTMX86 GPIO" + tristate "TQ-Systems TQMx86 GPIO" depends on MFD_TQMX86 || COMPILE_TEST depends on HAS_IOPORT_MAP select GPIOLIB_IRQCHIP @@ -1586,6 +1587,18 @@ endmenu menu "PCI GPIO expanders" depends on PCI +config GPIO_AAEON + tristate "AAEON GPIO support" + depends on ASUS_WMI + depends on UBUNTU_ODM_DRIVERS + select MFD_AAEON + help + Say yes here to support GPIO pins on Single Board Computers produced + by AAEON. + + This driver leverages the ASUS WMI interface to access device + resources. + config GPIO_AMD8111 tristate "AMD 8111 GPIO driver" depends on X86 || COMPILE_TEST diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index 9e40af196aae6..000f60b191c67 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_GPIO_104_IDI_48) += gpio-104-idi-48.o obj-$(CONFIG_GPIO_104_IDIO_16) += gpio-104-idio-16.o obj-$(CONFIG_GPIO_74X164) += gpio-74x164.o obj-$(CONFIG_GPIO_74XX_MMIO) += gpio-74xx-mmio.o +obj-$(CONFIG_GPIO_AAEON) += gpio-aaeon.o obj-$(CONFIG_GPIO_ADNP) += gpio-adnp.o obj-$(CONFIG_GPIO_ADP5520) += gpio-adp5520.o obj-$(CONFIG_GPIO_AGGREGATOR) += gpio-aggregator.o diff --git a/drivers/gpio/gpio-aaeon.c b/drivers/gpio/gpio-aaeon.c new file mode 100644 index 0000000000000..3183c45dd1946 --- /dev/null +++ b/drivers/gpio/gpio-aaeon.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AAEON GPIO driver + * Copyright (c) 2021, AAEON Ltd. + * + * Author: Edward Lin + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRVNAME "gpio_aaeon" +#define ASUS_NB_WMI_EVENT_GUID "0B3CBB35-E3C2-45ED-91C2-4C5A6D195D1C" +#define AAEON_WMI_MGMT_GUID "97845ED0-4E6D-11DE-8A39-0800200C9A66" + +#define GET_GPIO_NUMBER_ID 0x00010000 +#define GET_LEVEL_METHOD_ID 0x00010001 +#define SET_LEVEL_METHOD_ID 0x00010002 +#define GET_DIRECTION_METHOD_ID 0x00010003 +#define SET_DIRECTION_METHOD_ID 0x00010004 +#define GET_SIO_NUMBER_METHOD_ID 0xF0010 + +struct aaeon_gpio_bank { + struct gpio_chip chip; + unsigned int regbase; + struct aaeon_gpio_data *data; +}; + +struct aaeon_gpio_data { + int nr_bank; + struct aaeon_gpio_bank *bank; +}; + +static int aaeon_gpio_get_number(void); +static int aaeon_gpio_get_direction(struct gpio_chip *chip, + unsigned int offset); +static int aaeon_gpio_output_set_direction(struct gpio_chip *chip, + unsigned int offset, int value); +static int aaeon_gpio_input_set_direction(struct gpio_chip *chip, + unsigned int offset); +static int aaeon_gpio_get(struct gpio_chip *chip, + unsigned int offset); +static void aaeon_gpio_set(struct gpio_chip *chip, unsigned int offset, + int value); + +#define AAEON_GPIO_BANK(_base, _ngpio, _regbase) \ +{ \ + .chip = { \ + .label = DRVNAME, \ + .owner = THIS_MODULE, \ + .get_direction = aaeon_gpio_get_direction, \ + .direction_input = aaeon_gpio_input_set_direction, \ + .direction_output = aaeon_gpio_output_set_direction, \ + .get = aaeon_gpio_get, \ + .set = aaeon_gpio_set, \ + .base = _base, \ + .ngpio = _ngpio, \ + .can_sleep = true, \ + }, \ + .regbase = _regbase, \ +} + +static struct aaeon_gpio_bank aaeon_gpio_bank[] = { + AAEON_GPIO_BANK(0, 0, 0xF0), +}; + +static int aaeon_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) +{ + int err, retval; + u32 dev_id = 0x0; + + dev_id |= offset; + err = asus_wmi_evaluate_method(GET_DIRECTION_METHOD_ID, dev_id, + 0, &retval); + if (err) + return err; + + return retval; +} + +static int aaeon_gpio_input_set_direction(struct gpio_chip *chip, + unsigned int offset) +{ + int err, retval; + u32 dev_id; + + dev_id = BIT(16) | offset; + err = asus_wmi_evaluate_method(SET_DIRECTION_METHOD_ID, dev_id, + 0, &retval); + if (err) + return err; + + return retval; +} + +static int aaeon_gpio_output_set_direction(struct gpio_chip *chip, + unsigned int offset, int value) +{ + int err, retval; + u32 dev_id = 0x0; + + dev_id |= offset; + err = asus_wmi_evaluate_method(SET_DIRECTION_METHOD_ID, dev_id, + 0, &retval); + if (err) + return err; + + return retval; +} + +static int aaeon_gpio_get(struct gpio_chip *chip, unsigned int offset) +{ + int err, retval; + u32 dev_id = 0x0; + + dev_id |= offset; + err = asus_wmi_evaluate_method(GET_LEVEL_METHOD_ID, dev_id, 0, &retval); + if (err) + return err; + + return retval; +} + +static void aaeon_gpio_set(struct gpio_chip *chip, unsigned int offset, + int value) +{ + int retval; + u32 dev_id = offset; + + if (value) + dev_id = BIT(16) | dev_id; + + asus_wmi_evaluate_method(SET_LEVEL_METHOD_ID, dev_id, 0, &retval); +} + +static int aaeon_gpio_get_number(void) +{ + int err, retval; + + err = asus_wmi_evaluate_method(GET_GPIO_NUMBER_ID, + GET_SIO_NUMBER_METHOD_ID, + 0, &retval); + if (err) + return err; + + return retval; +} + +static int __init aaeon_gpio_probe(struct platform_device *pdev) +{ + int err, i; + int dio_number = 0; + struct aaeon_gpio_data *data; + struct aaeon_gpio_bank *bank; + + /* Prevent other drivers adding this platfom device */ + if (!wmi_has_guid(AAEON_WMI_MGMT_GUID)) { + pr_debug("AAEON Management GUID not found\n"); + return -ENODEV; + } + + dio_number = aaeon_gpio_get_number(); + if (dio_number < 0) + return -ENODEV; + + data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->nr_bank = ARRAY_SIZE(aaeon_gpio_bank); + data->bank = aaeon_gpio_bank; + platform_set_drvdata(pdev, data); + bank = &data->bank[0]; + bank->chip.parent = &pdev->dev; + bank->chip.ngpio = dio_number; + bank->data = data; + err = devm_gpiochip_add_data(&pdev->dev, &bank->chip, bank); + if (err) + pr_debug("Failed to register gpiochip %d: %d\n", i, err); + + return err; +} + +static struct platform_driver aaeon_gpio_driver = { + .driver = { + .name = "gpio-aaeon", + }, +}; + +module_platform_driver_probe(aaeon_gpio_driver, aaeon_gpio_probe); + +MODULE_ALIAS("platform:gpio-aaeon"); +MODULE_DESCRIPTION("AAEON GPIO Driver"); +MODULE_AUTHOR("Edward Lin "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c index 1ee62cd58582b..25db014494a4d 100644 --- a/drivers/gpio/gpio-crystalcove.c +++ b/drivers/gpio/gpio-crystalcove.c @@ -92,7 +92,7 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type) case 0x5e: return GPIOPANELCTL; default: - return -EOPNOTSUPP; + return -ENOTSUPP; } } diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c index 5ef8af8249806..c097e310c9e84 100644 --- a/drivers/gpio/gpio-lpc32xx.c +++ b/drivers/gpio/gpio-lpc32xx.c @@ -529,6 +529,7 @@ static const struct of_device_id lpc32xx_gpio_of_match[] = { { .compatible = "nxp,lpc3220-gpio", }, { }, }; +MODULE_DEVICE_TABLE(of, lpc32xx_gpio_of_match); static struct platform_driver lpc32xx_gpio_driver = { .driver = { diff --git a/drivers/gpio/gpio-npcm-sgpio.c b/drivers/gpio/gpio-npcm-sgpio.c index d31788b43abcc..2605706145434 100644 --- a/drivers/gpio/gpio-npcm-sgpio.c +++ b/drivers/gpio/gpio-npcm-sgpio.c @@ -434,7 +434,7 @@ static void npcm_sgpio_irq_handler(struct irq_desc *desc) struct gpio_chip *gc = irq_desc_get_handler_data(desc); struct irq_chip *ic = irq_desc_get_chip(desc); struct npcm_sgpio *gpio = gpiochip_get_data(gc); - unsigned int i, j, girq; + unsigned int i, j; unsigned long reg; chained_irq_enter(ic, desc); @@ -443,11 +443,9 @@ static void npcm_sgpio_irq_handler(struct irq_desc *desc) const struct npcm_sgpio_bank *bank = &npcm_sgpio_banks[i]; reg = ioread8(bank_reg(gpio, bank, EVENT_STS)); - for_each_set_bit(j, ®, 8) { - girq = irq_find_mapping(gc->irq.domain, - i * 8 + gpio->nout_sgpio + j); - generic_handle_domain_irq(gc->irq.domain, girq); - } + for_each_set_bit(j, ®, 8) + generic_handle_domain_irq(gc->irq.domain, + i * 8 + gpio->nout_sgpio + j); } chained_irq_exit(ic, desc); diff --git a/drivers/gpio/gpio-tangier.c b/drivers/gpio/gpio-tangier.c index b75e0b12087ac..4b29abafecf6a 100644 --- a/drivers/gpio/gpio-tangier.c +++ b/drivers/gpio/gpio-tangier.c @@ -195,7 +195,8 @@ static int tng_gpio_set_config(struct gpio_chip *chip, unsigned int offset, static void tng_irq_ack(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); void __iomem *gisr; u8 shift; @@ -227,7 +228,8 @@ static void tng_irq_unmask_mask(struct tng_gpio *priv, u32 gpio, bool unmask) static void tng_irq_mask(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); tng_irq_unmask_mask(priv, gpio, false); @@ -236,7 +238,8 @@ static void tng_irq_mask(struct irq_data *d) static void tng_irq_unmask(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); gpiochip_enable_irq(&priv->chip, gpio); diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index d87dd06db40d0..9130c691a2dd3 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -36,12 +36,6 @@ #define TEGRA186_GPIO_SCR_SEC_REN BIT(27) #define TEGRA186_GPIO_SCR_SEC_G1W BIT(9) #define TEGRA186_GPIO_SCR_SEC_G1R BIT(1) -#define TEGRA186_GPIO_FULL_ACCESS (TEGRA186_GPIO_SCR_SEC_WEN | \ - TEGRA186_GPIO_SCR_SEC_REN | \ - TEGRA186_GPIO_SCR_SEC_G1R | \ - TEGRA186_GPIO_SCR_SEC_G1W) -#define TEGRA186_GPIO_SCR_SEC_ENABLE (TEGRA186_GPIO_SCR_SEC_WEN | \ - TEGRA186_GPIO_SCR_SEC_REN) /* control registers */ #define TEGRA186_GPIO_ENABLE_CONFIG 0x00 @@ -177,10 +171,18 @@ static inline bool tegra186_gpio_is_accessible(struct tegra_gpio *gpio, unsigned value = __raw_readl(secure + TEGRA186_GPIO_SCR); - if ((value & TEGRA186_GPIO_SCR_SEC_ENABLE) == 0) - return true; + /* + * When SCR_SEC_[R|W]EN is unset, then we have full read/write access to all the + * registers for given GPIO pin. + * When SCR_SEC[R|W]EN is set, then there is need to further check the accompanying + * SCR_SEC_G1[R|W] bit to determine read/write access to all the registers for given + * GPIO pin. + */ - if ((value & TEGRA186_GPIO_FULL_ACCESS) == TEGRA186_GPIO_FULL_ACCESS) + if (((value & TEGRA186_GPIO_SCR_SEC_REN) == 0 || + ((value & TEGRA186_GPIO_SCR_SEC_REN) && (value & TEGRA186_GPIO_SCR_SEC_G1R))) && + ((value & TEGRA186_GPIO_SCR_SEC_WEN) == 0 || + ((value & TEGRA186_GPIO_SCR_SEC_WEN) && (value & TEGRA186_GPIO_SCR_SEC_G1W)))) return true; return false; diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index 3a28c1f273c39..f2e7e8754d95d 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -6,6 +6,7 @@ * Vadim V.Vlasov */ +#include #include #include #include @@ -28,16 +29,25 @@ #define TQMX86_GPIIC 3 /* GPI Interrupt Configuration Register */ #define TQMX86_GPIIS 4 /* GPI Interrupt Status Register */ +#define TQMX86_GPII_NONE 0 #define TQMX86_GPII_FALLING BIT(0) #define TQMX86_GPII_RISING BIT(1) +/* Stored in irq_type as a trigger type, but not actually valid as a register + * value, so the name doesn't use "GPII" + */ +#define TQMX86_INT_BOTH (BIT(0) | BIT(1)) #define TQMX86_GPII_MASK (BIT(0) | BIT(1)) #define TQMX86_GPII_BITS 2 +/* Stored in irq_type with GPII bits */ +#define TQMX86_INT_UNMASKED BIT(2) struct tqmx86_gpio_data { struct gpio_chip chip; void __iomem *io_base; int irq; + /* Lock must be held for accessing output and irq_type fields */ raw_spinlock_t spinlock; + DECLARE_BITMAP(output, TQMX86_NGPIO); u8 irq_type[TQMX86_NGPI]; }; @@ -64,15 +74,10 @@ static void tqmx86_gpio_set(struct gpio_chip *chip, unsigned int offset, { struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); unsigned long flags; - u8 val; raw_spin_lock_irqsave(&gpio->spinlock, flags); - val = tqmx86_gpio_read(gpio, TQMX86_GPIOD); - if (value) - val |= BIT(offset); - else - val &= ~BIT(offset); - tqmx86_gpio_write(gpio, val, TQMX86_GPIOD); + __assign_bit(offset, gpio->output, value); + tqmx86_gpio_write(gpio, bitmap_get_value8(gpio->output, 0), TQMX86_GPIOD); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); } @@ -107,21 +112,38 @@ static int tqmx86_gpio_get_direction(struct gpio_chip *chip, return GPIO_LINE_DIRECTION_OUT; } +static void tqmx86_gpio_irq_config(struct tqmx86_gpio_data *gpio, int offset) + __must_hold(&gpio->spinlock) +{ + u8 type = TQMX86_GPII_NONE, gpiic; + + if (gpio->irq_type[offset] & TQMX86_INT_UNMASKED) { + type = gpio->irq_type[offset] & TQMX86_GPII_MASK; + + if (type == TQMX86_INT_BOTH) + type = tqmx86_gpio_get(&gpio->chip, offset + TQMX86_NGPO) + ? TQMX86_GPII_FALLING + : TQMX86_GPII_RISING; + } + + gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); + gpiic &= ~(TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS)); + gpiic |= type << (offset * TQMX86_GPII_BITS); + tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); +} + static void tqmx86_gpio_irq_mask(struct irq_data *data) { unsigned int offset = (data->hwirq - TQMX86_NGPO); struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); unsigned long flags; - u8 gpiic, mask; - - mask = TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS); raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~mask; - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] &= ~TQMX86_INT_UNMASKED; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + gpiochip_disable_irq(&gpio->chip, irqd_to_hwirq(data)); } @@ -131,16 +153,12 @@ static void tqmx86_gpio_irq_unmask(struct irq_data *data) struct tqmx86_gpio_data *gpio = gpiochip_get_data( irq_data_get_irq_chip_data(data)); unsigned long flags; - u8 gpiic, mask; - - mask = TQMX86_GPII_MASK << (offset * TQMX86_GPII_BITS); gpiochip_enable_irq(&gpio->chip, irqd_to_hwirq(data)); + raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~mask; - gpiic |= gpio->irq_type[offset] << (offset * TQMX86_GPII_BITS); - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] |= TQMX86_INT_UNMASKED; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); } @@ -151,7 +169,7 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type) unsigned int offset = (data->hwirq - TQMX86_NGPO); unsigned int edge_type = type & IRQF_TRIGGER_MASK; unsigned long flags; - u8 new_type, gpiic; + u8 new_type; switch (edge_type) { case IRQ_TYPE_EDGE_RISING: @@ -161,19 +179,16 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type) new_type = TQMX86_GPII_FALLING; break; case IRQ_TYPE_EDGE_BOTH: - new_type = TQMX86_GPII_FALLING | TQMX86_GPII_RISING; + new_type = TQMX86_INT_BOTH; break; default: return -EINVAL; /* not supported */ } - gpio->irq_type[offset] = new_type; - raw_spin_lock_irqsave(&gpio->spinlock, flags); - gpiic = tqmx86_gpio_read(gpio, TQMX86_GPIIC); - gpiic &= ~((TQMX86_GPII_MASK) << (offset * TQMX86_GPII_BITS)); - gpiic |= new_type << (offset * TQMX86_GPII_BITS); - tqmx86_gpio_write(gpio, gpiic, TQMX86_GPIIC); + gpio->irq_type[offset] &= ~TQMX86_GPII_MASK; + gpio->irq_type[offset] |= new_type; + tqmx86_gpio_irq_config(gpio, offset); raw_spin_unlock_irqrestore(&gpio->spinlock, flags); return 0; @@ -184,8 +199,8 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc) struct gpio_chip *chip = irq_desc_get_handler_data(desc); struct tqmx86_gpio_data *gpio = gpiochip_get_data(chip); struct irq_chip *irq_chip = irq_desc_get_chip(desc); - unsigned long irq_bits; - int i = 0; + unsigned long irq_bits, flags; + int i; u8 irq_status; chained_irq_enter(irq_chip, desc); @@ -194,6 +209,34 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc) tqmx86_gpio_write(gpio, irq_status, TQMX86_GPIIS); irq_bits = irq_status; + + raw_spin_lock_irqsave(&gpio->spinlock, flags); + for_each_set_bit(i, &irq_bits, TQMX86_NGPI) { + /* + * Edge-both triggers are implemented by flipping the edge + * trigger after each interrupt, as the controller only supports + * either rising or falling edge triggers, but not both. + * + * Internally, the TQMx86 GPIO controller has separate status + * registers for rising and falling edge interrupts. GPIIC + * configures which bits from which register are visible in the + * interrupt status register GPIIS and defines what triggers the + * parent IRQ line. Writing to GPIIS always clears both rising + * and falling interrupt flags internally, regardless of the + * currently configured trigger. + * + * In consequence, we can cleanly implement the edge-both + * trigger in software by first clearing the interrupt and then + * setting the new trigger based on the current GPIO input in + * tqmx86_gpio_irq_config() - even if an edge arrives between + * reading the input and setting the trigger, we will have a new + * interrupt pending. + */ + if ((gpio->irq_type[i] & TQMX86_GPII_MASK) == TQMX86_INT_BOTH) + tqmx86_gpio_irq_config(gpio, i); + } + raw_spin_unlock_irqrestore(&gpio->spinlock, flags); + for_each_set_bit(i, &irq_bits, TQMX86_NGPI) generic_handle_domain_irq(gpio->chip.irq.domain, i + TQMX86_NGPO); @@ -277,6 +320,13 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) tqmx86_gpio_write(gpio, (u8)~TQMX86_DIR_INPUT_MASK, TQMX86_GPIODD); + /* + * Reading the previous output state is not possible with TQMx86 hardware. + * Initialize all outputs to 0 to have a defined state that matches the + * shadow register. + */ + tqmx86_gpio_write(gpio, 0, TQMX86_GPIOD); + chip = &gpio->chip; chip->label = "gpio-tqmx86"; chip->owner = THIS_MODULE; diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c index c18b6b47384f1..94ca9d03c0949 100644 --- a/drivers/gpio/gpio-wcove.c +++ b/drivers/gpio/gpio-wcove.c @@ -104,7 +104,7 @@ static inline int to_reg(int gpio, enum ctrl_register type) unsigned int reg = type == CTRL_IN ? GPIO_IN_CTRL_BASE : GPIO_OUT_CTRL_BASE; if (gpio >= WCOVE_GPIO_NUM) - return -EOPNOTSUPP; + return -ENOTSUPP; return reg + gpio; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index cd3e9657cc36d..551b604903e14 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -128,7 +128,24 @@ static bool acpi_gpio_deferred_req_irqs_done; static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) { - return device_match_acpi_handle(&gc->gpiodev->dev, data); + /* First check the actual GPIO device */ + if (device_match_acpi_handle(&gc->gpiodev->dev, data)) + return true; + + /* + * When the ACPI device is artificially split to the banks of GPIOs, + * where each of them is represented by a separate GPIO device, + * the firmware node of the physical device may not be shared among + * the banks as they may require different values for the same property, + * e.g., number of GPIOs in a certain bank. In such case the ACPI handle + * of a GPIO device is NULL and can not be used. Hence we have to check + * the parent device to be sure that there is no match before bailing + * out. + */ + if (gc->parent) + return device_match_acpi_handle(gc->parent, data); + + return false; } /** diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 2a88736629ef3..5cca9e8803495 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -734,6 +734,25 @@ static u32 line_event_id(int level) GPIO_V2_LINE_EVENT_FALLING_EDGE; } +static inline char *make_irq_label(const char *orig) +{ + char *new; + + if (!orig) + return NULL; + + new = kstrdup_and_replace(orig, '/', ':', GFP_KERNEL); + if (!new) + return ERR_PTR(-ENOMEM); + + return new; +} + +static inline void free_irq_label(const char *label) +{ + kfree(label); +} + #ifdef CONFIG_HTE static enum hte_return process_hw_ts_thread(void *p) @@ -1021,6 +1040,7 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us) { unsigned long irqflags; int ret, level, irq; + char *label; /* try hardware */ ret = gpiod_set_debounce(line->desc, debounce_period_us); @@ -1043,11 +1063,17 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us) if (irq < 0) return -ENXIO; + label = make_irq_label(line->req->label); + if (IS_ERR(label)) + return -ENOMEM; + irqflags = IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING; ret = request_irq(irq, debounce_irq_handler, irqflags, - line->req->label, line); - if (ret) + label, line); + if (ret) { + free_irq_label(label); return ret; + } line->irq = irq; } else { ret = hte_edge_setup(line, GPIO_V2_LINE_FLAG_EDGE_BOTH); @@ -1092,7 +1118,7 @@ static u32 gpio_v2_line_config_debounce_period(struct gpio_v2_line_config *lc, static void edge_detector_stop(struct line *line) { if (line->irq) { - free_irq(line->irq, line); + free_irq_label(free_irq(line->irq, line)); line->irq = 0; } @@ -1116,6 +1142,7 @@ static int edge_detector_setup(struct line *line, unsigned long irqflags = 0; u64 eflags; int irq, ret; + char *label; eflags = edflags & GPIO_V2_LINE_EDGE_FLAGS; if (eflags && !kfifo_initialized(&line->req->events)) { @@ -1152,11 +1179,17 @@ static int edge_detector_setup(struct line *line, IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING; irqflags |= IRQF_ONESHOT; + label = make_irq_label(line->req->label); + if (IS_ERR(label)) + return PTR_ERR(label); + /* Request a thread to read the events */ ret = request_threaded_irq(irq, edge_irq_handler, edge_irq_thread, - irqflags, line->req->label, line); - if (ret) + irqflags, label, line); + if (ret) { + free_irq_label(label); return ret; + } line->irq = irq; return 0; @@ -1166,6 +1199,8 @@ static int edge_detector_update(struct line *line, struct gpio_v2_line_config *lc, unsigned int line_idx, u64 edflags) { + u64 eflags; + int ret; u64 active_edflags = READ_ONCE(line->edflags); unsigned int debounce_period_us = gpio_v2_line_config_debounce_period(lc, line_idx); @@ -1177,6 +1212,18 @@ static int edge_detector_update(struct line *line, /* sw debounced and still will be...*/ if (debounce_period_us && READ_ONCE(line->sw_debounced)) { line_set_debounce_period(line, debounce_period_us); + /* + * ensure event fifo is initialised if edge detection + * is now enabled. + */ + eflags = edflags & GPIO_V2_LINE_EDGE_FLAGS; + if (eflags && !kfifo_initialized(&line->req->events)) { + ret = kfifo_alloc(&line->req->events, + line->req->event_buffer_size, + GFP_KERNEL); + if (ret) + return ret; + } return 0; } @@ -1979,7 +2026,7 @@ static void lineevent_free(struct lineevent_state *le) blocking_notifier_chain_unregister(&le->gdev->device_notifier, &le->device_unregistered_nb); if (le->irq) - free_irq(le->irq, le); + free_irq_label(free_irq(le->irq, le)); if (le->desc) gpiod_free(le->desc); kfree(le->label); @@ -2120,6 +2167,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) int fd; int ret; int irq, irqflags = 0; + char *label; if (copy_from_user(&eventreq, ip, sizeof(eventreq))) return -EFAULT; @@ -2204,15 +2252,23 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) if (ret) goto out_free_le; + label = make_irq_label(le->label); + if (IS_ERR(label)) { + ret = PTR_ERR(label); + goto out_free_le; + } + /* Request a thread to read the events */ ret = request_threaded_irq(irq, lineevent_irq_handler, lineevent_irq_thread, irqflags, - le->label, + label, le); - if (ret) + if (ret) { + free_irq_label(label); goto out_free_le; + } le->irq = irq; @@ -2758,11 +2814,11 @@ static int gpio_chrdev_release(struct inode *inode, struct file *file) struct gpio_chardev_data *cdev = file->private_data; struct gpio_device *gdev = cdev->gdev; - bitmap_free(cdev->watched_lines); blocking_notifier_chain_unregister(&gdev->device_notifier, &cdev->device_unregistered_nb); blocking_notifier_chain_unregister(&gdev->line_state_notifier, &cdev->lineinfo_changed_nb); + bitmap_free(cdev->watched_lines); gpio_device_put(gdev); kfree(cdev); diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index fe9ce6b19f15c..4987e62dcb3d1 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -158,7 +158,7 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, if (!dr) return ERR_PTR(-ENOMEM); - desc = fwnode_gpiod_get_index(fwnode, con_id, index, flags, label); + desc = gpiod_find_and_request(dev, fwnode, con_id, index, flags, label, false); if (IS_ERR(desc)) { devres_free(dr); return desc; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 75be4a3ca7f84..d9da0331e8340 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -2402,6 +2402,11 @@ char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset) } EXPORT_SYMBOL_GPL(gpiochip_dup_line_label); +static inline const char *function_name_or_default(const char *con_id) +{ + return con_id ?: "(default)"; +} + /** * gpiochip_request_own_desc - Allow GPIO chip to request its own descriptor * @gc: GPIO chip @@ -2430,10 +2435,11 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, enum gpiod_flags dflags) { struct gpio_desc *desc = gpiochip_get_desc(gc, hwnum); + const char *name = function_name_or_default(label); int ret; if (IS_ERR(desc)) { - chip_err(gc, "failed to get GPIO descriptor\n"); + chip_err(gc, "failed to get GPIO %s descriptor\n", name); return desc; } @@ -2443,8 +2449,8 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, ret = gpiod_configure_flags(desc, label, lflags, dflags); if (ret) { - chip_err(gc, "setup of own GPIO %s failed\n", label); gpiod_free_commit(desc); + chip_err(gc, "setup of own GPIO %s failed\n", name); return ERR_PTR(ret); } @@ -4119,34 +4125,33 @@ static struct gpio_desc *gpiod_find_by_fwnode(struct fwnode_handle *fwnode, enum gpiod_flags *flags, unsigned long *lookupflags) { + const char *name = function_name_or_default(con_id); struct gpio_desc *desc = ERR_PTR(-ENOENT); if (is_of_node(fwnode)) { - dev_dbg(consumer, "using DT '%pfw' for '%s' GPIO lookup\n", - fwnode, con_id); + dev_dbg(consumer, "using DT '%pfw' for '%s' GPIO lookup\n", fwnode, name); desc = of_find_gpio(to_of_node(fwnode), con_id, idx, lookupflags); } else if (is_acpi_node(fwnode)) { - dev_dbg(consumer, "using ACPI '%pfw' for '%s' GPIO lookup\n", - fwnode, con_id); + dev_dbg(consumer, "using ACPI '%pfw' for '%s' GPIO lookup\n", fwnode, name); desc = acpi_find_gpio(fwnode, con_id, idx, flags, lookupflags); } else if (is_software_node(fwnode)) { - dev_dbg(consumer, "using swnode '%pfw' for '%s' GPIO lookup\n", - fwnode, con_id); + dev_dbg(consumer, "using swnode '%pfw' for '%s' GPIO lookup\n", fwnode, name); desc = swnode_find_gpio(fwnode, con_id, idx, lookupflags); } return desc; } -static struct gpio_desc *gpiod_find_and_request(struct device *consumer, - struct fwnode_handle *fwnode, - const char *con_id, - unsigned int idx, - enum gpiod_flags flags, - const char *label, - bool platform_lookup_allowed) +struct gpio_desc *gpiod_find_and_request(struct device *consumer, + struct fwnode_handle *fwnode, + const char *con_id, + unsigned int idx, + enum gpiod_flags flags, + const char *label, + bool platform_lookup_allowed) { unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT; + const char *name = function_name_or_default(con_id); struct gpio_desc *desc; int ret; @@ -4162,7 +4167,7 @@ static struct gpio_desc *gpiod_find_and_request(struct device *consumer, } if (IS_ERR(desc)) { - dev_dbg(consumer, "No GPIO consumer %s found\n", con_id); + dev_dbg(consumer, "No GPIO consumer %s found\n", name); return desc; } @@ -4183,15 +4188,14 @@ static struct gpio_desc *gpiod_find_and_request(struct device *consumer, * * FIXME: Make this more sane and safe. */ - dev_info(consumer, - "nonexclusive access to GPIO for %s\n", con_id); + dev_info(consumer, "nonexclusive access to GPIO for %s\n", name); return desc; } ret = gpiod_configure_flags(desc, con_id, lookupflags, flags); if (ret < 0) { - dev_dbg(consumer, "setup of GPIO %s failed\n", con_id); gpiod_put(desc); + dev_dbg(consumer, "setup of GPIO %s failed\n", name); return ERR_PTR(ret); } @@ -4307,6 +4311,7 @@ EXPORT_SYMBOL_GPL(gpiod_get_optional); int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, unsigned long lflags, enum gpiod_flags dflags) { + const char *name = function_name_or_default(con_id); int ret; if (lflags & GPIO_ACTIVE_LOW) @@ -4350,7 +4355,7 @@ int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, /* No particular flag request, return here... */ if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) { - gpiod_dbg(desc, "no flags found for %s\n", con_id); + gpiod_dbg(desc, "no flags found for GPIO %s\n", name); return 0; } diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index a4a2520b5f31c..c6e5fb9aa2122 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -202,6 +202,14 @@ static inline int gpiod_request_user(struct gpio_desc *desc, const char *label) return ret; } +struct gpio_desc *gpiod_find_and_request(struct device *consumer, + struct fwnode_handle *fwnode, + const char *con_id, + unsigned int idx, + enum gpiod_flags flags, + const char *label, + bool platform_lookup_allowed); + int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, unsigned long lflags, enum gpiod_flags dflags); int gpio_set_debounce_timeout(struct gpio_desc *desc, unsigned int debounce); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 79827a6dcd7f5..ae040728db15d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -198,7 +198,7 @@ extern int amdgpu_smu_pptable_id; extern uint amdgpu_dc_feature_mask; extern uint amdgpu_dc_debug_mask; extern uint amdgpu_dc_visual_confirm; -extern uint amdgpu_dm_abm_level; +extern int amdgpu_dm_abm_level; extern int amdgpu_backlight; extern int amdgpu_damage_clips; extern struct amdgpu_mgpu_info mgpu_info; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 41db030ddc4ee..131983ed43465 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -146,7 +146,7 @@ int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev) { int ret; - if (!adev->kfd.init_complete) + if (!adev->kfd.init_complete || adev->kfd.client.dev) return 0; ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 231fd927dcfbe..f2cc45241fd97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -220,7 +220,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > kfd_mem_limit.max_ttm_mem_limit) || (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed > - vram_size - reserved_for_pt)) { + vram_size - reserved_for_pt - atomic64_read(&adev->vram_pin_size))) { ret = -ENOMEM; goto release; } @@ -1186,7 +1186,8 @@ static int reserve_bo_and_cond_vms(struct kgd_mem *mem, int ret; ctx->sync = &mem->sync; - drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); + drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT | + DRM_EXEC_IGNORE_DUPLICATES, 0); drm_exec_until_all_locked(&ctx->exec) { ctx->n_vms = 0; list_for_each_entry(entry, &mem->attachments, list) { @@ -1851,6 +1852,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( err_bo_create: amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags, xcp_id); err_reserve_limit: + amdgpu_sync_free(&(*mem)->sync); mutex_destroy(&(*mem)->lock); if (gobj) drm_gem_object_put(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index fb2681dd6b338..23651a9738cc8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -211,6 +211,7 @@ union igp_info { struct atom_integrated_system_info_v1_11 v11; struct atom_integrated_system_info_v1_12 v12; struct atom_integrated_system_info_v2_1 v21; + struct atom_integrated_system_info_v2_3 v23; }; union umc_info { @@ -359,6 +360,20 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev, if (vram_type) *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type); break; + case 3: + mem_channel_number = igp_info->v23.umachannelnumber; + if (!mem_channel_number) + mem_channel_number = 1; + mem_type = igp_info->v23.memorytype; + if (mem_type == LpDdr5MemType) + mem_channel_width = 32; + else + mem_channel_width = 64; + if (vram_width) + *vram_width = mem_channel_number * mem_channel_width; + if (vram_type) + *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type); + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 6adeddfb3d564..116d3756c9c35 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -819,7 +819,7 @@ static int amdgpu_cs_bo_validate(void *param, struct amdgpu_bo *bo) p->bytes_moved += ctx.bytes_moved; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - amdgpu_bo_in_cpu_visible_vram(bo)) + amdgpu_res_cpu_visible(adev, bo->tbo.resource)) p->bytes_moved_vis += ctx.bytes_moved; if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 94bdb5fa6ebc6..33f07e6cbc1d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4120,18 +4120,22 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->ip_blocks[i].status.hw = true; } } + } else if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) && + !amdgpu_device_has_display_hardware(adev)) { + r = psp_gpu_reset(adev); } else { - tmp = amdgpu_reset_method; - /* It should do a default reset when loading or reloading the driver, - * regardless of the module parameter reset_method. - */ - amdgpu_reset_method = AMD_RESET_METHOD_NONE; - r = amdgpu_asic_reset(adev); - amdgpu_reset_method = tmp; - if (r) { - dev_err(adev->dev, "asic reset on init failed\n"); - goto failed; - } + tmp = amdgpu_reset_method; + /* It should do a default reset when loading or reloading the driver, + * regardless of the module parameter reset_method. + */ + amdgpu_reset_method = AMD_RESET_METHOD_NONE; + r = amdgpu_asic_reset(adev); + amdgpu_reset_method = tmp; + } + + if (r) { + dev_err(adev->dev, "asic reset on init failed\n"); + goto failed; } } @@ -4524,6 +4528,8 @@ int amdgpu_device_prepare(struct drm_device *dev) if (r) goto unprepare; + flush_delayed_work(&adev->gfx.gfx_off_delay_work); + for (i = 0; i < adev->num_ip_blocks; i++) { if (!adev->ip_blocks[i].status.valid) continue; @@ -5786,13 +5792,18 @@ static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev, *speed = PCI_SPEED_UNKNOWN; *width = PCIE_LNK_WIDTH_UNKNOWN; - while ((parent = pci_upstream_bridge(parent))) { - /* skip upstream/downstream switches internal to dGPU*/ - if (parent->vendor == PCI_VENDOR_ID_ATI) - continue; - *speed = pcie_get_speed_cap(parent); - *width = pcie_get_width_cap(parent); - break; + if (amdgpu_device_pcie_dynamic_switching_supported(adev)) { + while ((parent = pci_upstream_bridge(parent))) { + /* skip upstream/downstream switches internal to dGPU*/ + if (parent->vendor == PCI_VENDOR_ID_ATI) + continue; + *speed = pcie_get_speed_cap(parent); + *width = pcie_get_width_cap(parent); + break; + } + } else { + /* use the current speeds rather than max if switching is not supported */ + pcie_bandwidth_available(adev->pdev, NULL, speed, width); } } @@ -6107,6 +6118,20 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev) struct amdgpu_reset_context reset_context; u32 memsize; struct list_head device_list; + struct amdgpu_hive_info *hive; + int hive_ras_recovery = 0; + struct amdgpu_ras *ras; + + /* PCI error slot reset should be skipped During RAS recovery */ + hive = amdgpu_get_xgmi_hive(adev); + if (hive) { + hive_ras_recovery = atomic_read(&hive->ras_recovery); + amdgpu_put_xgmi_hive(hive); + } + ras = amdgpu_ras_get_context(adev); + if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3)) && + ras && (atomic_read(&ras->in_recovery) || hive_ras_recovery)) + return PCI_ERS_RESULT_RECOVERED; DRM_INFO("PCI error: slot reset callback!!\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index c7d60dd0fb975..ff28265838ec0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -1278,11 +1278,10 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) * 0b10 : encode is disabled * 0b01 : decode is disabled */ - adev->vcn.vcn_config[adev->vcn.num_vcn_inst] = - ip->revision & 0xc0; - ip->revision &= ~0xc0; if (adev->vcn.num_vcn_inst < AMDGPU_MAX_VCN_INSTANCES) { + adev->vcn.vcn_config[adev->vcn.num_vcn_inst] = + ip->revision & 0xc0; adev->vcn.num_vcn_inst++; adev->vcn.inst_mask |= (1U << ip->instance_number); @@ -1293,6 +1292,7 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) adev->vcn.num_vcn_inst + 1, AMDGPU_MAX_VCN_INSTANCES); } + ip->revision &= ~0xc0; } if (le16_to_cpu(ip->hw_id) == SDMA0_HWID || le16_to_cpu(ip->hw_id) == SDMA1_HWID || @@ -1867,6 +1867,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block); break; case IP_VERSION(14, 0, 0): + case IP_VERSION(14, 0, 1): amdgpu_device_ip_block_add(adev, &smu_v14_0_ip_block); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 586f4d03039df..fa144e61815c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -849,12 +849,13 @@ module_param_named(visualconfirm, amdgpu_dc_visual_confirm, uint, 0444); * the ABM algorithm, with 1 being the least reduction and 4 being the most * reduction. * - * Defaults to 0, or disabled. Userspace can still override this level later - * after boot. + * Defaults to -1, or disabled. Userspace can only override this level after + * boot if it's set to auto. */ -uint amdgpu_dm_abm_level; -MODULE_PARM_DESC(abmlevel, "ABM level (0 = off (default), 1-4 = backlight reduction level) "); -module_param_named(abmlevel, amdgpu_dm_abm_level, uint, 0444); +int amdgpu_dm_abm_level = -1; +MODULE_PARM_DESC(abmlevel, + "ABM level (0 = off, 1-4 = backlight reduction level, -1 auto (default))"); +module_param_named(abmlevel, amdgpu_dm_abm_level, int, 0444); int amdgpu_backlight = -1; MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (default))"); @@ -2451,8 +2452,11 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) } for (i = 0; i < mgpu_info.num_dgpu; i++) { adev = mgpu_info.gpu_ins[i].adev; - if (!adev->kfd.init_complete) + if (!adev->kfd.init_complete) { + kgd2kfd_init_zone_device(adev); amdgpu_amdkfd_device_init(adev); + amdgpu_amdkfd_drm_client_create(adev); + } amdgpu_ttm_set_buffer_funcs_status(adev, true); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c index 5706b282a0c7e..c7df7fa3459f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c @@ -97,6 +97,10 @@ void amdgpu_show_fdinfo(struct drm_printer *p, struct drm_file *file) stats.requested_visible_vram/1024UL); drm_printf(p, "amd-requested-gtt:\t%llu KiB\n", stats.requested_gtt/1024UL); + drm_printf(p, "drm-shared-vram:\t%llu KiB\n", stats.vram_shared/1024UL); + drm_printf(p, "drm-shared-gtt:\t%llu KiB\n", stats.gtt_shared/1024UL); + drm_printf(p, "drm-shared-cpu:\t%llu KiB\n", stats.cpu_shared/1024UL); + for (hw_ip = 0; hw_ip < AMDGPU_HW_IP_NUM; ++hw_ip) { if (!usage[hw_ip]) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 55784a9f26c4c..9d2e306ab0c86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -684,12 +684,17 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring; struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst]; unsigned int ndw; - signed long r; + int r; uint32_t seq; - if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready || - !down_read_trylock(&adev->reset_domain->sem)) { + /* + * A GPU reset should flush all TLBs anyway, so no need to do + * this while one is ongoing. + */ + if (!down_read_trylock(&adev->reset_domain->sem)) + return 0; + if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) { if (adev->gmc.flush_tlb_needs_extra_type_2) adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, 2, all_hub, @@ -703,43 +708,40 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub, inst); - return 0; - } + r = 0; + } else { + /* 2 dwords flush + 8 dwords fence */ + ndw = kiq->pmf->invalidate_tlbs_size + 8; - /* 2 dwords flush + 8 dwords fence */ - ndw = kiq->pmf->invalidate_tlbs_size + 8; + if (adev->gmc.flush_tlb_needs_extra_type_2) + ndw += kiq->pmf->invalidate_tlbs_size; - if (adev->gmc.flush_tlb_needs_extra_type_2) - ndw += kiq->pmf->invalidate_tlbs_size; + if (adev->gmc.flush_tlb_needs_extra_type_0) + ndw += kiq->pmf->invalidate_tlbs_size; - if (adev->gmc.flush_tlb_needs_extra_type_0) - ndw += kiq->pmf->invalidate_tlbs_size; + spin_lock(&adev->gfx.kiq[inst].ring_lock); + amdgpu_ring_alloc(ring, ndw); + if (adev->gmc.flush_tlb_needs_extra_type_2) + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub); - spin_lock(&adev->gfx.kiq[inst].ring_lock); - amdgpu_ring_alloc(ring, ndw); - if (adev->gmc.flush_tlb_needs_extra_type_2) - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub); + if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0) + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub); - if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0) - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub); + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub); + r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); + if (r) { + amdgpu_ring_undo(ring); + spin_unlock(&adev->gfx.kiq[inst].ring_lock); + goto error_unlock_reset; + } - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub); - r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); - if (r) { - amdgpu_ring_undo(ring); + amdgpu_ring_commit(ring); spin_unlock(&adev->gfx.kiq[inst].ring_lock); - goto error_unlock_reset; - } - - amdgpu_ring_commit(ring); - spin_unlock(&adev->gfx.kiq[inst].ring_lock); - r = amdgpu_fence_wait_polling(ring, seq, usec_timeout); - if (r < 1) { - dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r); - r = -ETIME; - goto error_unlock_reset; + if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) { + dev_err(adev->dev, "timeout waiting for kiq fence\n"); + r = -ETIME; + } } - r = 0; error_unlock_reset: up_read(&adev->reset_domain->sem); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c index 55b65fc04b651..431ec72655ec8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c @@ -129,13 +129,25 @@ static const struct mmu_interval_notifier_ops amdgpu_hmm_hsa_ops = { */ int amdgpu_hmm_register(struct amdgpu_bo *bo, unsigned long addr) { + int r; + if (bo->kfd_bo) - return mmu_interval_notifier_insert(&bo->notifier, current->mm, + r = mmu_interval_notifier_insert(&bo->notifier, current->mm, addr, amdgpu_bo_size(bo), &amdgpu_hmm_hsa_ops); - return mmu_interval_notifier_insert(&bo->notifier, current->mm, addr, - amdgpu_bo_size(bo), - &amdgpu_hmm_gfx_ops); + else + r = mmu_interval_notifier_insert(&bo->notifier, current->mm, addr, + amdgpu_bo_size(bo), + &amdgpu_hmm_gfx_ops); + if (r) + /* + * Make sure amdgpu_hmm_unregister() doesn't call + * mmu_interval_notifier_remove() when the notifier isn't properly + * initialized. + */ + bo->notifier.mm = NULL; + + return r; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 71a5cf37b472d..0b8c6581b62c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -300,12 +300,15 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) dma_fence_set_error(finished, -ECANCELED); if (finished->error < 0) { - DRM_INFO("Skip scheduling IBs!\n"); + dev_dbg(adev->dev, "Skip scheduling IBs in ring(%s)", + ring->name); } else { r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job, &fence); if (r) - DRM_ERROR("Error scheduling IBs (%d)\n", r); + dev_err(adev->dev, + "Error scheduling IBs (%d) in ring(%s)", r, + ring->name); } job->job_run_counter++; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index da48b6da01072..420e5bc44e306 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1129,6 +1129,7 @@ void amdgpu_mes_remove_ring(struct amdgpu_device *adev, return; amdgpu_mes_remove_hw_queue(adev, ring->hw_queue_id); + del_timer_sync(&ring->fence_drv.fallback_timer); amdgpu_ring_fini(ring); kfree(ring); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 425cebcc5cbff..3af505e8cbbc3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -608,6 +608,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev, else amdgpu_bo_placement_from_domain(bo, bp->domain); if (bp->type == ttm_bo_type_kernel) + bo->tbo.priority = 2; + else if (!(bp->flags & AMDGPU_GEM_CREATE_DISCARDABLE)) bo->tbo.priority = 1; if (!bp->destroy) @@ -620,8 +622,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev, return r; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - bo->tbo.resource->mem_type == TTM_PL_VRAM && - amdgpu_bo_in_cpu_visible_vram(bo)) + amdgpu_res_cpu_visible(adev, bo->tbo.resource)) amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, ctx.bytes_moved); else @@ -1245,14 +1246,18 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, * amdgpu_bo_move_notify - notification about a memory move * @bo: pointer to a buffer object * @evict: if this move is evicting the buffer from the graphics address space + * @new_mem: new resource for backing the BO * * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs * bookkeeping. * TTM driver callback which is called when ttm moves a buffer. */ -void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) +void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, + bool evict, + struct ttm_resource *new_mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); + struct ttm_resource *old_mem = bo->resource; struct amdgpu_bo *abo; if (!amdgpu_bo_is_amdgpu_bo(bo)) @@ -1264,37 +1269,50 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) amdgpu_bo_kunmap(abo); if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach && - bo->resource->mem_type != TTM_PL_SYSTEM) + old_mem && old_mem->mem_type != TTM_PL_SYSTEM) dma_buf_move_notify(abo->tbo.base.dma_buf); - /* remember the eviction */ - if (evict) - atomic64_inc(&adev->num_evictions); + /* move_notify is called before move happens */ + trace_amdgpu_bo_move(abo, new_mem ? new_mem->mem_type : -1, + old_mem ? old_mem->mem_type : -1); } void amdgpu_bo_get_memory(struct amdgpu_bo *bo, struct amdgpu_mem_stats *stats) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct ttm_resource *res = bo->tbo.resource; uint64_t size = amdgpu_bo_size(bo); + struct drm_gem_object *obj; unsigned int domain; + bool shared; /* Abort if the BO doesn't currently have a backing store */ - if (!bo->tbo.resource) + if (!res) return; - domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); + obj = &bo->tbo.base; + shared = drm_gem_object_is_shared_for_memory_stats(obj); + + domain = amdgpu_mem_type_to_domain(res->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: stats->vram += size; - if (amdgpu_bo_in_cpu_visible_vram(bo)) + if (amdgpu_res_cpu_visible(adev, bo->tbo.resource)) stats->visible_vram += size; + if (shared) + stats->vram_shared += size; break; case AMDGPU_GEM_DOMAIN_GTT: stats->gtt += size; + if (shared) + stats->gtt_shared += size; break; case AMDGPU_GEM_DOMAIN_CPU: default: stats->cpu += size; + if (shared) + stats->cpu_shared += size; break; } @@ -1381,10 +1399,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* Remember that this BO was accessed by the CPU */ abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - if (bo->resource->mem_type != TTM_PL_VRAM) - return 0; - - if (amdgpu_bo_in_cpu_visible_vram(abo)) + if (amdgpu_res_cpu_visible(adev, bo->resource)) return 0; /* Can't move a pinned BO to visible VRAM */ @@ -1408,7 +1423,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* this should never happen */ if (bo->resource->mem_type == TTM_PL_VRAM && - !amdgpu_bo_in_cpu_visible_vram(abo)) + !amdgpu_res_cpu_visible(adev, bo->resource)) return VM_FAULT_SIGBUS; ttm_bo_move_to_lru_tail_unlocked(bo); @@ -1572,6 +1587,7 @@ uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, */ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct dma_buf_attachment *attachment; struct dma_buf *dma_buf; const char *placement; @@ -1580,10 +1596,11 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) if (dma_resv_trylock(bo->tbo.base.resv)) { unsigned int domain; + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: - if (amdgpu_bo_in_cpu_visible_vram(bo)) + if (amdgpu_res_cpu_visible(adev, bo->tbo.resource)) placement = "VRAM VISIBLE"; else placement = "VRAM"; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index a3ea8a82db23a..bc42ccbde659a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -138,12 +138,18 @@ struct amdgpu_bo_vm { struct amdgpu_mem_stats { /* current VRAM usage, includes visible VRAM */ uint64_t vram; + /* current shared VRAM usage, includes visible VRAM */ + uint64_t vram_shared; /* current visible VRAM usage */ uint64_t visible_vram; /* current GTT usage */ uint64_t gtt; + /* current shared GTT usage */ + uint64_t gtt_shared; /* current system memory usage */ uint64_t cpu; + /* current shared system memory usage */ + uint64_t cpu_shared; /* sum of evicted buffers, includes visible VRAM */ uint64_t evicted_vram; /* sum of evicted buffers due to CPU access */ @@ -244,28 +250,6 @@ static inline u64 amdgpu_bo_mmap_offset(struct amdgpu_bo *bo) return drm_vma_node_offset_addr(&bo->tbo.base.vma_node); } -/** - * amdgpu_bo_in_cpu_visible_vram - check if BO is (partly) in visible VRAM - */ -static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - struct amdgpu_res_cursor cursor; - - if (!bo->tbo.resource || bo->tbo.resource->mem_type != TTM_PL_VRAM) - return false; - - amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor); - while (cursor.remaining) { - if (cursor.start < adev->gmc.visible_vram_size) - return true; - - amdgpu_res_next(&cursor, cursor.size); - } - - return false; -} - /** * amdgpu_bo_explicit_sync - return whether the bo is explicitly synced */ @@ -344,7 +328,9 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, size_t buffer_size, uint32_t *metadata_size, uint64_t *flags); -void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict); +void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, + bool evict, + struct ttm_resource *new_mem); void amdgpu_bo_release_notify(struct ttm_buffer_object *bo); vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo); void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 5505d646f43aa..06f0a6534a94f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -524,46 +524,58 @@ static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf, { struct amdgpu_ring *ring = file_inode(f)->i_private; volatile u32 *mqd; - int r; + u32 *kbuf; + int r, i; uint32_t value, result; if (*pos & 3 || size & 3) return -EINVAL; - result = 0; + kbuf = kmalloc(ring->mqd_size, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; r = amdgpu_bo_reserve(ring->mqd_obj, false); if (unlikely(r != 0)) - return r; + goto err_free; r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&mqd); - if (r) { - amdgpu_bo_unreserve(ring->mqd_obj); - return r; - } + if (r) + goto err_unreserve; + /* + * Copy to local buffer to avoid put_user(), which might fault + * and acquire mmap_sem, under reservation_ww_class_mutex. + */ + for (i = 0; i < ring->mqd_size/sizeof(u32); i++) + kbuf[i] = mqd[i]; + + amdgpu_bo_kunmap(ring->mqd_obj); + amdgpu_bo_unreserve(ring->mqd_obj); + + result = 0; while (size) { if (*pos >= ring->mqd_size) - goto done; + break; - value = mqd[*pos/4]; + value = kbuf[*pos/4]; r = put_user(value, (uint32_t *)buf); if (r) - goto done; + goto err_free; buf += 4; result += 4; size -= 4; *pos += 4; } -done: - amdgpu_bo_kunmap(ring->mqd_obj); - mqd = NULL; - amdgpu_bo_unreserve(ring->mqd_obj); - if (r) - return r; - + kfree(kbuf); return result; + +err_unreserve: + amdgpu_bo_unreserve(ring->mqd_obj); +err_free: + kfree(kbuf); + return r; } static const struct file_operations amdgpu_debugfs_mqd_fops = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 75c9fd2c6c2a1..43ab165df4900 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -137,7 +137,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU); } else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) && - amdgpu_bo_in_cpu_visible_vram(abo)) { + amdgpu_res_cpu_visible(adev, bo->resource)) { /* Try evicting to the CPU inaccessible part of VRAM * first, but only set GTT as busy placement, so this @@ -408,40 +408,55 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, return r; } -/* - * amdgpu_mem_visible - Check that memory can be accessed by ttm_bo_move_memcpy +/** + * amdgpu_res_cpu_visible - Check that resource can be accessed by CPU + * @adev: amdgpu device + * @res: the resource to check * - * Called by amdgpu_bo_move() + * Returns: true if the full resource is CPU visible, false otherwise. */ -static bool amdgpu_mem_visible(struct amdgpu_device *adev, - struct ttm_resource *mem) +bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, + struct ttm_resource *res) { - u64 mem_size = (u64)mem->size; struct amdgpu_res_cursor cursor; - u64 end; - if (mem->mem_type == TTM_PL_SYSTEM || - mem->mem_type == TTM_PL_TT) + if (!res) + return false; + + if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT || + res->mem_type == AMDGPU_PL_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL) return true; - if (mem->mem_type != TTM_PL_VRAM) + + if (res->mem_type != TTM_PL_VRAM) return false; - amdgpu_res_first(mem, 0, mem_size, &cursor); - end = cursor.start + cursor.size; + amdgpu_res_first(res, 0, res->size, &cursor); while (cursor.remaining) { + if ((cursor.start + cursor.size) > adev->gmc.visible_vram_size) + return false; amdgpu_res_next(&cursor, cursor.size); + } - if (!cursor.remaining) - break; + return true; +} - /* ttm_resource_ioremap only supports contiguous memory */ - if (end != cursor.start) - return false; +/* + * amdgpu_res_copyable - Check that memory can be accessed by ttm_bo_move_memcpy + * + * Called by amdgpu_bo_move() + */ +static bool amdgpu_res_copyable(struct amdgpu_device *adev, + struct ttm_resource *mem) +{ + if (!amdgpu_res_cpu_visible(adev, mem)) + return false; - end = cursor.start + cursor.size; - } + /* ttm_resource_ioremap only supports contiguous memory */ + if (mem->mem_type == TTM_PL_VRAM && + !(mem->placement & TTM_PL_FLAG_CONTIGUOUS)) + return false; - return end <= adev->gmc.visible_vram_size; + return true; } /* @@ -471,14 +486,16 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL)) { + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if (old_mem->mem_type == TTM_PL_SYSTEM && (new_mem->mem_type == TTM_PL_TT || new_mem->mem_type == AMDGPU_PL_PREEMPT)) { + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if ((old_mem->mem_type == TTM_PL_TT || old_mem->mem_type == AMDGPU_PL_PREEMPT) && @@ -488,9 +505,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm); + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); - goto out; + return 0; } if (old_mem->mem_type == AMDGPU_PL_GDS || @@ -502,8 +520,9 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, new_mem->mem_type == AMDGPU_PL_OA || new_mem->mem_type == AMDGPU_PL_DOORBELL) { /* Nothing to save here */ + amdgpu_bo_move_notify(bo, evict, new_mem); ttm_bo_move_null(bo, new_mem); - goto out; + return 0; } if (bo->type == ttm_bo_type_device && @@ -515,27 +534,28 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; } - if (adev->mman.buffer_funcs_enabled) { - if (((old_mem->mem_type == TTM_PL_SYSTEM && - new_mem->mem_type == TTM_PL_VRAM) || - (old_mem->mem_type == TTM_PL_VRAM && - new_mem->mem_type == TTM_PL_SYSTEM))) { - hop->fpfn = 0; - hop->lpfn = 0; - hop->mem_type = TTM_PL_TT; - hop->flags = TTM_PL_FLAG_TEMPORARY; - return -EMULTIHOP; - } + if (adev->mman.buffer_funcs_enabled && + ((old_mem->mem_type == TTM_PL_SYSTEM && + new_mem->mem_type == TTM_PL_VRAM) || + (old_mem->mem_type == TTM_PL_VRAM && + new_mem->mem_type == TTM_PL_SYSTEM))) { + hop->fpfn = 0; + hop->lpfn = 0; + hop->mem_type = TTM_PL_TT; + hop->flags = TTM_PL_FLAG_TEMPORARY; + return -EMULTIHOP; + } + amdgpu_bo_move_notify(bo, evict, new_mem); + if (adev->mman.buffer_funcs_enabled) r = amdgpu_move_blit(bo, evict, new_mem, old_mem); - } else { + else r = -ENODEV; - } if (r) { /* Check that all memory is CPU accessible */ - if (!amdgpu_mem_visible(adev, old_mem) || - !amdgpu_mem_visible(adev, new_mem)) { + if (!amdgpu_res_copyable(adev, old_mem) || + !amdgpu_res_copyable(adev, new_mem)) { pr_err("Move buffer fallback to memcpy unavailable\n"); return r; } @@ -545,11 +565,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; } - trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type); -out: - /* update statistics */ + /* update statistics after the move */ + if (evict) + atomic64_inc(&adev->num_evictions); atomic64_add(bo->base.size, &adev->num_bytes_moved); - amdgpu_bo_move_notify(bo, evict); return 0; } @@ -562,7 +581,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(bdev); - size_t bus_size = (size_t)mem->size; switch (mem->mem_type) { case TTM_PL_SYSTEM: @@ -573,9 +591,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, break; case TTM_PL_VRAM: mem->bus.offset = mem->start << PAGE_SHIFT; - /* check if it's visible */ - if ((mem->bus.offset + bus_size) > adev->gmc.visible_vram_size) - return -EINVAL; if (adev->mman.aper_base_kaddr && mem->placement & TTM_PL_FLAG_CONTIGUOUS) @@ -869,6 +884,7 @@ static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev, amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages, gtt->ttm.dma_address, flags); } + gtt->bound = true; } /* @@ -1554,7 +1570,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo, static void amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo) { - amdgpu_bo_move_notify(bo, false); + amdgpu_bo_move_notify(bo, false, NULL); } static struct ttm_device_funcs amdgpu_bo_driver = { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 65ec82141a8e0..32cf6b6f6efd9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -139,6 +139,9 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start); +bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, + struct ttm_resource *res); + int amdgpu_ttm_init(struct amdgpu_device *adev); void amdgpu_ttm_fini(struct amdgpu_device *adev); void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c index bfbf59326ee12..1b5ef32108e14 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c @@ -766,6 +766,9 @@ static int umsch_mm_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (amdgpu_in_reset(adev) || adev->in_s0ix || adev->in_suspend) + return 0; + return umsch_mm_test(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 59acf424a078f..968ca2c84ef7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -743,7 +743,8 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t created = 0; uint32_t allocated = 0; uint32_t tmp, handle = 0; - uint32_t *size = &tmp; + uint32_t dummy = 0xffffffff; + uint32_t *size = &dummy; unsigned int idx; int i, r = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index b8fcb6c556989..5b50f7359199d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1559,6 +1559,37 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev, trace_amdgpu_vm_bo_map(bo_va, mapping); } +/* Validate operation parameters to prevent potential abuse */ +static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev, + struct amdgpu_bo *bo, + uint64_t saddr, + uint64_t offset, + uint64_t size) +{ + uint64_t tmp, lpfn; + + if (saddr & AMDGPU_GPU_PAGE_MASK + || offset & AMDGPU_GPU_PAGE_MASK + || size & AMDGPU_GPU_PAGE_MASK) + return -EINVAL; + + if (check_add_overflow(saddr, size, &tmp) + || check_add_overflow(offset, size, &tmp) + || size == 0 /* which also leads to end < begin */) + return -EINVAL; + + /* make sure object fit at this offset */ + if (bo && offset + size > amdgpu_bo_size(bo)) + return -EINVAL; + + /* Ensure last pfn not exceed max_pfn */ + lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT; + if (lpfn >= adev->vm_manager.max_pfn) + return -EINVAL; + + return 0; +} + /** * amdgpu_vm_bo_map - map bo inside a vm * @@ -1585,21 +1616,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; uint64_t eaddr; + int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr); if (tmp) { @@ -1652,17 +1676,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, uint64_t eaddr; int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; /* Allocate all the needed memory */ mapping = kmalloc(sizeof(*mapping), GFP_KERNEL); @@ -1676,7 +1692,7 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, } saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; mapping->start = saddr; mapping->last = eaddr; @@ -1763,10 +1779,14 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *before, *after, *tmp, *next; LIST_HEAD(removed); uint64_t eaddr; + int r; + + r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size); + if (r) + return r; - eaddr = saddr + size - 1; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; /* Allocate all the needed memory */ before = kzalloc(sizeof(*before), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c index b9a15d51eb5c3..ad44012cc01e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c @@ -390,6 +390,12 @@ static int vpe_hw_init(void *handle) struct amdgpu_vpe *vpe = &adev->vpe; int ret; + /* Power on VPE */ + ret = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VPE, + AMD_PG_STATE_UNGATE); + if (ret) + return ret; + ret = vpe_load_microcode(vpe); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c index d6f808acfb17b..fbb43ae7624f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c +++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c @@ -62,6 +62,11 @@ void aqua_vanjaram_doorbell_index_init(struct amdgpu_device *adev) adev->doorbell_index.max_assignment = AMDGPU_DOORBELL_LAYOUT1_MAX_ASSIGNMENT << 1; } +static bool aqua_vanjaram_xcp_vcn_shared(struct amdgpu_device *adev) +{ + return (adev->xcp_mgr->num_xcps > adev->vcn.num_vcn_inst); +} + static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, uint32_t inst_idx, struct amdgpu_ring *ring) { @@ -87,7 +92,7 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, case AMDGPU_RING_TYPE_VCN_ENC: case AMDGPU_RING_TYPE_VCN_JPEG: ip_blk = AMDGPU_XCP_VCN; - if (adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE) + if (aqua_vanjaram_xcp_vcn_shared(adev)) inst_mask = 1 << (inst_idx * 2); break; default: @@ -140,10 +145,12 @@ static int aqua_vanjaram_xcp_sched_list_update( aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id); - /* VCN is shared by two partitions under CPX MODE */ + /* VCN may be shared by two partitions under CPX MODE in certain + * configs. + */ if ((ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC || - ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) && - adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE) + ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) && + aqua_vanjaram_xcp_vcn_shared(adev)) aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id + 1); } diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index a33e890c70d90..ac51d19b518ca 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -313,7 +313,7 @@ static uint32_t atom_get_src_int(atom_exec_context *ctx, uint8_t attr, DEBUG("IMM 0x%02X\n", val); return val; } - return 0; + break; case ATOM_ARG_PLL: idx = U8(*ptr); (*ptr)++; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index dcdecb18b2306..42392a97daff2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -9194,7 +9194,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { 7 + /* PIPELINE_SYNC */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* VM_FLUSH */ + 4 + /* VM_FLUSH */ 8 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 4 + /* double SWITCH_BUFFER, @@ -9285,7 +9285,6 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = { 7 + /* gfx_v10_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v10_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v10_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v10_0_ring_emit_ib_compute */ .emit_ib = gfx_v10_0_ring_emit_ib_compute, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 4f3bfdc75b37d..6a6fc422e44da 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1630,7 +1630,7 @@ static void gfx_v11_0_setup_rb(struct amdgpu_device *adev) active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa)); } - active_rb_bitmap |= global_active_rb_bitmap; + active_rb_bitmap &= global_active_rb_bitmap; adev->gfx.config.backend_enable_mask = active_rb_bitmap; adev->gfx.config.num_rbs = hweight32(active_rb_bitmap); } @@ -6110,7 +6110,7 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_gfx = { 7 + /* PIPELINE_SYNC */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* VM_FLUSH */ + 4 + /* VM_FLUSH */ 8 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 5 + /* COND_EXEC */ @@ -6195,7 +6195,6 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_kiq = { 7 + /* gfx_v11_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v11_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v11_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v11_0_ring_emit_ib_compute */ .emit_ib = gfx_v11_0_ring_emit_ib_compute, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 3bc6943365a4f..153932c1f64f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -6991,7 +6991,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = { 7 + /* gfx_v9_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v9_0_ring_emit_vm_flush */ 8 + 8 + 8 + /* gfx_v9_0_ring_emit_fence x3 for user fence, vm fence */ 7 + /* gfx_v9_0_emit_mem_sync */ 5 + /* gfx_v9_0_emit_wave_limit for updating mmSPI_WCL_PIPE_PERCENT_GFX register */ @@ -7029,7 +7028,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = { 7 + /* gfx_v9_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v9_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v9_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v9_0_ring_emit_ib_compute */ .emit_fence = gfx_v9_0_ring_emit_fence_kiq, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 131cddbdda0dc..5a346607ed3ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -426,16 +426,16 @@ static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, static int gfx_v9_4_3_init_microcode(struct amdgpu_device *adev) { - const char *chip_name; + char ucode_prefix[15]; int r; - chip_name = "gc_9_4_3"; + amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); - r = gfx_v9_4_3_init_rlc_microcode(adev, chip_name); + r = gfx_v9_4_3_init_rlc_microcode(adev, ucode_prefix); if (r) return r; - r = gfx_v9_4_3_init_cp_compute_microcode(adev, chip_name); + r = gfx_v9_4_3_init_cp_compute_microcode(adev, ucode_prefix); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index c9c653cfc765b..3f1692194b7ad 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -570,6 +570,7 @@ static void gmc_v11_0_set_mmhub_funcs(struct amdgpu_device *adev) adev->mmhub.funcs = &mmhub_v3_0_2_funcs; break; case IP_VERSION(3, 3, 0): + case IP_VERSION(3, 3, 1): adev->mmhub.funcs = &mmhub_v3_3_funcs; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c index dc4812ecc98d6..238ea40c24500 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c @@ -98,16 +98,16 @@ mmhub_v3_3_print_l2_protection_fault_status(struct amdgpu_device *adev, switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) { case IP_VERSION(3, 3, 0): - mmhub_cid = mmhub_client_ids_v3_3[cid][rw]; + case IP_VERSION(3, 3, 1): + mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v3_3) ? + mmhub_client_ids_v3_3[cid][rw] : + cid == 0x140 ? "UMSCH" : NULL; break; default: mmhub_cid = NULL; break; } - if (!mmhub_cid && cid == 0x140) - mmhub_cid = "UMSCH"; - dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n", mmhub_cid ? mmhub_cid : "unknown", cid); dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n", diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 3d68dd5523c65..7487baa8ada67 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -2021,6 +2021,9 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev, DRM_DEBUG("IH: SDMA trap\n"); instance = sdma_v4_0_irq_id_to_seq(entry->client_id); + if (instance < 0) + return instance; + switch (entry->ring_id) { case 0: amdgpu_fence_process(&adev->sdma.instance[instance].ring); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 2d688dca26bed..328682cbb7e22 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -366,7 +366,8 @@ static void sdma_v4_4_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) u32 ref_and_mask = 0; const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg; - ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; + ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 + << (ring->me % adev->sdma.num_inst_per_aid); sdma_v4_4_2_wait_reg_mem(ring, 0, 1, adev->nbio.funcs->get_hdp_flush_done_offset(adev), @@ -429,16 +430,11 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev, struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES]; u32 doorbell_offset, doorbell; u32 rb_cntl, ib_cntl; - int i, unset = 0; + int i; for_each_inst(i, inst_mask) { sdma[i] = &adev->sdma.instance[i].ring; - if ((adev->mman.buffer_funcs_ring == sdma[i]) && unset != 1) { - amdgpu_ttm_set_buffer_funcs_status(adev, false); - unset = 1; - } - rb_cntl = RREG32_SDMA(i, regSDMA_GFX_RB_CNTL); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA_GFX_RB_CNTL, RB_ENABLE, 0); WREG32_SDMA(i, regSDMA_GFX_RB_CNTL, rb_cntl); @@ -485,20 +481,10 @@ static void sdma_v4_4_2_inst_rlc_stop(struct amdgpu_device *adev, static void sdma_v4_4_2_inst_page_stop(struct amdgpu_device *adev, uint32_t inst_mask) { - struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES]; u32 rb_cntl, ib_cntl; int i; - bool unset = false; for_each_inst(i, inst_mask) { - sdma[i] = &adev->sdma.instance[i].page; - - if ((adev->mman.buffer_funcs_ring == sdma[i]) && - (!unset)) { - amdgpu_ttm_set_buffer_funcs_status(adev, false); - unset = true; - } - rb_cntl = RREG32_SDMA(i, regSDMA_PAGE_RB_CNTL); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA_PAGE_RB_CNTL, RB_ENABLE, 0); @@ -948,13 +934,7 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev, r = amdgpu_ring_test_helper(page); if (r) return r; - - if (adev->mman.buffer_funcs_ring == page) - amdgpu_ttm_set_buffer_funcs_status(adev, true); } - - if (adev->mman.buffer_funcs_ring == ring) - amdgpu_ttm_set_buffer_funcs_status(adev, true); } return r; @@ -1621,19 +1601,9 @@ static int sdma_v4_4_2_set_ecc_irq_state(struct amdgpu_device *adev, u32 sdma_cntl; sdma_cntl = RREG32_SDMA(type, regSDMA_CNTL); - switch (state) { - case AMDGPU_IRQ_STATE_DISABLE: - sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, - DRAM_ECC_INT_ENABLE, 0); - WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl); - break; - /* sdma ecc interrupt is enabled by default - * driver doesn't need to do anything to - * enable the interrupt */ - case AMDGPU_IRQ_STATE_ENABLE: - default: - break; - } + sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, DRAM_ECC_INT_ENABLE, + state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0); + WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 0058f3f7cf6e4..46f9f58d845f8 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -292,17 +292,21 @@ static void sdma_v5_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) u32 ref_and_mask = 0; const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg; - ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; - - amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | - SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | - SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); - amdgpu_ring_write(ring, ref_and_mask); /* reference */ - amdgpu_ring_write(ring, ref_and_mask); /* mask */ - amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | - SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + if (ring->me > 1) { + amdgpu_asic_flush_hdp(adev, ring); + } else { + ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; + + amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | + SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | + SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); + amdgpu_ring_write(ring, ref_and_mask); /* reference */ + amdgpu_ring_write(ring, ref_and_mask); /* mask */ + amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | + SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + } } /** diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 4d7188912edfe..fd4505fa4f670 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -450,10 +450,8 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev) { switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(11, 0, 0): - return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC); case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): - return false; default: return true; } @@ -714,7 +712,10 @@ static int soc21_common_early_init(void *handle) AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_JPEG | AMD_PG_SUPPORT_GFX_PG; - adev->external_rev_id = adev->rev_id + 0x1; + if (adev->rev_id == 0) + adev->external_rev_id = 0x1; + else + adev->external_rev_id = adev->rev_id + 0x10; break; default: /* FIXME: not supported yet */ @@ -832,10 +833,35 @@ static int soc21_common_suspend(void *handle) return soc21_common_hw_fini(adev); } +static bool soc21_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg1, sol_reg2; + + /* Will reset for the following suspend abort cases. + * 1) Only reset dGPU side. + * 2) S3 suspend got aborted and TOS is active. + */ + if (!(adev->flags & AMD_IS_APU) && adev->in_s3 && + !adev->suspend_complete) { + sol_reg1 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81); + msleep(100); + sol_reg2 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81); + + return (sol_reg1 != sol_reg2); + } + + return false; +} + static int soc21_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (soc21_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend aborted, resetting..."); + soc21_asic_reset(adev); + } + return soc21_common_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c index 8e7b763cfdb7e..fd23cd348552b 100644 --- a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c @@ -225,6 +225,8 @@ static int umsch_mm_v4_0_ring_start(struct amdgpu_umsch_mm *umsch) WREG32_SOC15(VCN, 0, regVCN_UMSCH_RB_SIZE, ring->ring_size); + ring->wptr = 0; + data = RREG32_SOC15(VCN, 0, regVCN_RB_ENABLE); data &= ~(VCN_RB_ENABLE__AUDIO_RB_EN_MASK); WREG32_SOC15(VCN, 0, regVCN_RB_ENABLE, data); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 80e90fdef291d..88ad54f88d599 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -778,8 +778,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * nodes, but not more than args->num_of_nodes as that is * the amount of memory allocated by user */ - pa = kzalloc((sizeof(struct kfd_process_device_apertures) * - args->num_of_nodes), GFP_KERNEL); + pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures), + GFP_KERNEL); if (!pa) return -ENOMEM; @@ -1138,7 +1138,7 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep, goto err_unlock; } offset = dev->adev->rmmio_remap.bus_addr; - if (!offset) { + if (!offset || (PAGE_SIZE > 4096)) { err = -ENOMEM; goto err_unlock; } @@ -1522,7 +1522,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep, /* Find a KFD GPU device that supports the get_dmabuf_info query */ for (i = 0; kfd_topology_enum_kfd_devices(i, &dev) == 0; i++) - if (dev) + if (dev && !kfd_devcgroup_check_permission(dev)) break; if (!dev) return -EINVAL; @@ -1544,7 +1544,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep, if (xcp_id >= 0) args->gpu_id = dmabuf_adev->kfd.dev->nodes[xcp_id]->id; else - args->gpu_id = dmabuf_adev->kfd.dev->nodes[0]->id; + args->gpu_id = dev->id; args->flags = flags; /* Copy metadata buffer to user mode */ @@ -2306,7 +2306,7 @@ static int criu_restore_memory_of_gpu(struct kfd_process_device *pdd, return -EINVAL; } offset = pdd->dev->adev->rmmio_remap.bus_addr; - if (!offset) { + if (!offset || (PAGE_SIZE > 4096)) { pr_err("amdgpu_amdkfd_get_mmio_remap_phys_addr failed\n"); return -ENOMEM; } @@ -3347,6 +3347,9 @@ static int kfd_mmio_mmap(struct kfd_node *dev, struct kfd_process *process, if (vma->vm_end - vma->vm_start != PAGE_SIZE) return -EINVAL; + if (PAGE_SIZE > 4096) + return -EINVAL; + address = dev->adev->rmmio_remap.bus_addr; vm_flags_set(vma, VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 0a9cf9dfc2243..7d39982bf74e2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -405,15 +405,8 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf) f2g = &gfx_v11_kfd2kgd; break; case IP_VERSION(11, 0, 3): - if ((adev->pdev->device == 0x7460 && - adev->pdev->revision == 0x00) || - (adev->pdev->device == 0x7461 && - adev->pdev->revision == 0x00)) - /* Note: Compiler version is 11.0.5 while HW version is 11.0.3 */ - gfx_target_version = 110005; - else - /* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */ - gfx_target_version = 110001; + /* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */ + gfx_target_version = 110001; f2g = &gfx_v11_kfd2kgd; break; case IP_VERSION(11, 5, 0): @@ -944,7 +937,6 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) { struct kfd_node *node; int i; - int count; if (!kfd->init_complete) return; @@ -952,12 +944,10 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) /* for runtime suspend, skip locking kfd */ if (!run_pm) { mutex_lock(&kfd_processes_mutex); - count = ++kfd_locked; - mutex_unlock(&kfd_processes_mutex); - /* For first KFD device suspend all the KFD processes */ - if (count == 1) + if (++kfd_locked == 1) kfd_suspend_all_processes(); + mutex_unlock(&kfd_processes_mutex); } for (i = 0; i < kfd->num_nodes; i++) { @@ -968,7 +958,7 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) { - int ret, count, i; + int ret, i; if (!kfd->init_complete) return 0; @@ -982,12 +972,10 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) /* for runtime resume, skip unlocking kfd */ if (!run_pm) { mutex_lock(&kfd_processes_mutex); - count = --kfd_locked; - mutex_unlock(&kfd_processes_mutex); - - WARN_ONCE(count < 0, "KFD suspend / resume ref. error"); - if (count == 0) + if (--kfd_locked == 0) ret = kfd_resume_all_processes(); + WARN_ONCE(kfd_locked < 0, "KFD suspend / resume ref. error"); + mutex_unlock(&kfd_processes_mutex); } return ret; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index c0e71543389a9..c0ae1a97498b5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1997,6 +1997,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, dev_err(dev, "HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n"); while (halt_if_hws_hang) schedule(); + kfd_hws_hang(dqm); return -ETIME; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c index a7697ec8188e0..f85ca6cb90f56 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c @@ -336,7 +336,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, break; } kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23); - } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c index 2a65792fd1162..3ca9c160da7c2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c @@ -325,7 +325,8 @@ static void event_interrupt_wq_v11(struct kfd_node *dev, /* CP */ if (source_id == SOC15_INTSRC_CP_END_OF_PIPE) kfd_signal_event_interrupt(pasid, context_id0, 32); - else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) + else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0))) kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_CTXID0_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index 27cdaea405017..8a6729939ae55 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -385,7 +385,8 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, break; } kfd_signal_event_interrupt(pasid, sq_int_data, 24); - } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index bdc01ca9609a7..5c8d81bfce7ab 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -509,10 +509,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, start = start_mgr << PAGE_SHIFT; end = (last_mgr + 1) << PAGE_SHIFT; + r = amdgpu_amdkfd_reserve_mem_limit(node->adev, + prange->npages * PAGE_SIZE, + KFD_IOC_ALLOC_MEM_FLAGS_VRAM, + node->xcp ? node->xcp->id : 0); + if (r) { + dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r); + return -ENOSPC; + } + r = svm_range_vram_node_new(node, prange, true); if (r) { dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r); - return r; + goto out; } ttm_res_offset = (start_mgr - prange->start + prange->offset) << PAGE_SHIFT; @@ -545,6 +554,11 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, svm_range_vram_node_free(prange); } +out: + amdgpu_amdkfd_unreserve_mem_limit(node->adev, + prange->npages * PAGE_SIZE, + KFD_IOC_ALLOC_MEM_FLAGS_VRAM, + node->xcp ? node->xcp->id : 0); return r < 0 ? r : 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 80320b8603fc6..fedeba3e1250d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1473,7 +1473,7 @@ static inline void kfd_flush_tlb(struct kfd_process_device *pdd, static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev) { - return KFD_GC_VERSION(dev) > IP_VERSION(9, 4, 2) || + return KFD_GC_VERSION(dev) >= IP_VERSION(9, 4, 2) || (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) && dev->sdma_fw_version >= 18) || KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 717a60d7a4ea9..451bb058cc620 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -819,9 +819,9 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) mutex_lock(&kfd_processes_mutex); if (kfd_is_locked()) { - mutex_unlock(&kfd_processes_mutex); pr_debug("KFD is locked! Cannot create process"); - return ERR_PTR(-EINVAL); + process = ERR_PTR(-EINVAL); + goto out; } /* A prior open of /dev/kfd could have already created the process. */ @@ -829,6 +829,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) if (process) { pr_debug("Process already found\n"); } else { + /* If the process just called exec(3), it is possible that the + * cleanup of the kfd_process (following the release of the mm + * of the old process image) is still in the cleanup work queue. + * Make sure to drain any job before trying to recreate any + * resource for this process. + */ + flush_workqueue(kfd_process_wq); + process = create_process(thread); if (IS_ERR(process)) goto out; @@ -1922,6 +1930,8 @@ static int signal_eviction_fence(struct kfd_process *p) rcu_read_lock(); ef = dma_fence_get_rcu_safe(&p->ef); rcu_read_unlock(); + if (!ef) + return -EINVAL; ret = dma_fence_signal(ef); dma_fence_put(ef); @@ -1949,10 +1959,9 @@ static void evict_process_worker(struct work_struct *work) * they are responsible stopping the queues and scheduling * the restore work. */ - if (!signal_eviction_fence(p)) - queue_delayed_work(kfd_restore_wq, &p->restore_work, - msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)); - else + if (signal_eviction_fence(p) || + mod_delayed_work(kfd_restore_wq, &p->restore_work, + msecs_to_jiffies(PROCESS_RESTORE_TIME_MS))) kfd_process_restore_queues(p); pr_debug("Finished evicting pasid 0x%x\n", p->pasid); @@ -2011,9 +2020,9 @@ static void restore_process_worker(struct work_struct *work) if (ret) { pr_debug("Failed to restore BOs of pasid 0x%x, retry after %d ms\n", p->pasid, PROCESS_BACK_OFF_TIME_MS); - ret = queue_delayed_work(kfd_restore_wq, &p->restore_work, - msecs_to_jiffies(PROCESS_BACK_OFF_TIME_MS)); - WARN(!ret, "reschedule restore work failed\n"); + if (mod_delayed_work(kfd_restore_wq, &p->restore_work, + msecs_to_jiffies(PROCESS_RESTORE_TIME_MS))) + kfd_process_restore_queues(p); } } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index c50a0dc9c9c07..33205078202b5 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -3424,7 +3424,7 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, mm, KFD_MIGRATE_TRIGGER_PREFETCH); *migrated = !r; - return r; + return 0; } int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 1a9bbb04bd5e2..31cca58572ee7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -147,6 +147,9 @@ MODULE_FIRMWARE(FIRMWARE_NAVI12_DMCU); #define FIRMWARE_DCN_35_DMUB "amdgpu/dcn_3_5_dmcub.bin" MODULE_FIRMWARE(FIRMWARE_DCN_35_DMUB); +#define FIRMWARE_DCN_351_DMUB "amdgpu/dcn_3_5_1_dmcub.bin" +MODULE_FIRMWARE(FIRMWARE_DCN_351_DMUB); + /* Number of bytes in PSP header for firmware. */ #define PSP_HEADER_BYTES 0x100 @@ -1929,17 +1932,15 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev) adev->dm.hdcp_workqueue = NULL; } - if (adev->dm.dc) + if (adev->dm.dc) { dc_deinit_callbacks(adev->dm.dc); - - if (adev->dm.dc) dc_dmub_srv_destroy(&adev->dm.dc->ctx->dmub_srv); - - if (dc_enable_dmub_notifications(adev->dm.dc)) { - kfree(adev->dm.dmub_notify); - adev->dm.dmub_notify = NULL; - destroy_workqueue(adev->dm.delayed_hpd_wq); - adev->dm.delayed_hpd_wq = NULL; + if (dc_enable_dmub_notifications(adev->dm.dc)) { + kfree(adev->dm.dmub_notify); + adev->dm.dmub_notify = NULL; + destroy_workqueue(adev->dm.delayed_hpd_wq); + adev->dm.delayed_hpd_wq = NULL; + } } if (adev->dm.dmub_bo) @@ -3009,6 +3010,7 @@ static int dm_resume(void *handle) dc_stream_release(dm_new_crtc_state->stream); dm_new_crtc_state->stream = NULL; } + dm_new_crtc_state->base.color_mgmt_changed = true; } for_each_new_plane_in_state(dm->cached_state, plane, new_plane_state, i) { @@ -3027,6 +3029,10 @@ static int dm_resume(void *handle) /* Do mst topology probing after resuming cached state*/ drm_connector_list_iter_begin(ddev, &iter); drm_for_each_connector_iter(connector, &iter) { + + if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) + continue; + aconnector = to_amdgpu_dm_connector(connector); if (aconnector->dc_link->type != dc_connection_mst_branch || aconnector->mst_root) @@ -4778,6 +4784,9 @@ static int dm_init_microcode(struct amdgpu_device *adev) case IP_VERSION(3, 5, 0): fw_name_dmub = FIRMWARE_DCN_35_DMUB; break; + case IP_VERSION(3, 5, 1): + fw_name_dmub = FIRMWARE_DCN_351_DMUB; + break; default: /* ASIC doesn't support DMUB. */ return 0; @@ -5201,6 +5210,10 @@ static inline void fill_dc_dirty_rect(struct drm_plane *plane, * @new_plane_state: New state of @plane * @crtc_state: New state of CRTC connected to the @plane * @flip_addrs: DC flip tracking struct, which also tracts dirty rects + * @is_psr_su: Flag indicating whether Panel Self Refresh Selective Update (PSR SU) is enabled. + * If PSR SU is enabled and damage clips are available, only the regions of the screen + * that have changed will be updated. If PSR SU is not enabled, + * or if damage clips are not available, the entire screen will be updated. * @dirty_regions_changed: dirty regions changed * * For PSR SU, DC informs the DMUB uController of dirty rectangle regions @@ -5871,6 +5884,9 @@ get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector, &aconnector->base.probed_modes : &aconnector->base.modes; + if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_WRITEBACK) + return NULL; + if (aconnector->freesync_vid_base.clock != 0) return &aconnector->freesync_vid_base; @@ -6254,27 +6270,22 @@ create_stream_for_sink(struct drm_connector *connector, if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket); - else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT || - stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST || - stream->signal == SIGNAL_TYPE_EDP) { + + if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT || + stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST || + stream->signal == SIGNAL_TYPE_EDP) { // // should decide stream support vsc sdp colorimetry capability // before building vsc info packet // - stream->use_vsc_sdp_for_colorimetry = false; - if (aconnector->dc_sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { - stream->use_vsc_sdp_for_colorimetry = - aconnector->dc_sink->is_vsc_sdp_colorimetry_supported; - } else { - if (stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED) - stream->use_vsc_sdp_for_colorimetry = true; - } + stream->use_vsc_sdp_for_colorimetry = stream->link->dpcd_caps.dpcd_rev.raw >= 0x14 && + stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED; + if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) tf = TRANSFER_FUNC_GAMMA_22; mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf); + aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; - if (stream->link->psr_settings.psr_feature_enabled) - aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; } finish: dc_sink_release(sink); @@ -6409,10 +6420,82 @@ int amdgpu_dm_connector_atomic_get_property(struct drm_connector *connector, return ret; } +/** + * DOC: panel power savings + * + * The display manager allows you to set your desired **panel power savings** + * level (between 0-4, with 0 representing off), e.g. using the following:: + * + * # echo 3 > /sys/class/drm/card0-eDP-1/amdgpu/panel_power_savings + * + * Modifying this value can have implications on color accuracy, so tread + * carefully. + */ + +static ssize_t panel_power_savings_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct drm_connector *connector = dev_get_drvdata(device); + struct drm_device *dev = connector->dev; + u8 val; + + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); + val = to_dm_connector_state(connector->state)->abm_level == + ABM_LEVEL_IMMEDIATE_DISABLE ? 0 : + to_dm_connector_state(connector->state)->abm_level; + drm_modeset_unlock(&dev->mode_config.connection_mutex); + + return sysfs_emit(buf, "%u\n", val); +} + +static ssize_t panel_power_savings_store(struct device *device, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct drm_connector *connector = dev_get_drvdata(device); + struct drm_device *dev = connector->dev; + long val; + int ret; + + ret = kstrtol(buf, 0, &val); + + if (ret) + return ret; + + if (val < 0 || val > 4) + return -EINVAL; + + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); + to_dm_connector_state(connector->state)->abm_level = val ?: + ABM_LEVEL_IMMEDIATE_DISABLE; + drm_modeset_unlock(&dev->mode_config.connection_mutex); + + drm_kms_helper_hotplug_event(dev); + + return count; +} + +static DEVICE_ATTR_RW(panel_power_savings); + +static struct attribute *amdgpu_attrs[] = { + &dev_attr_panel_power_savings.attr, + NULL +}; + +static const struct attribute_group amdgpu_group = { + .name = "amdgpu", + .attrs = amdgpu_attrs +}; + static void amdgpu_dm_connector_unregister(struct drm_connector *connector) { struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && + amdgpu_dm_abm_level < 0) + sysfs_remove_group(&connector->kdev->kobj, &amdgpu_group); + drm_dp_aux_unregister(&amdgpu_dm_connector->dm_dp_aux.aux); } @@ -6474,9 +6557,12 @@ void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector) state->vcpi_slots = 0; state->pbn = 0; - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) - state->abm_level = amdgpu_dm_abm_level ?: - ABM_LEVEL_IMMEDIATE_DISABLE; + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + if (amdgpu_dm_abm_level <= 0) + state->abm_level = ABM_LEVEL_IMMEDIATE_DISABLE; + else + state->abm_level = amdgpu_dm_abm_level; + } __drm_atomic_helper_connector_reset(connector, &state->base); } @@ -6514,6 +6600,14 @@ amdgpu_dm_connector_late_register(struct drm_connector *connector) to_amdgpu_dm_connector(connector); int r; + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && + amdgpu_dm_abm_level < 0) { + r = sysfs_create_group(&connector->kdev->kobj, + &amdgpu_group); + if (r) + return r; + } + amdgpu_dm_register_backlight_device(amdgpu_dm_connector); if ((connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) || @@ -7548,7 +7642,8 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, aconnector->base.state->max_requested_bpc = aconnector->base.state->max_bpc; if (connector_type == DRM_MODE_CONNECTOR_eDP && - (dc_is_dmcu_initialized(adev->dm.dc) || adev->dm.dc->ctx->dmub_srv)) { + (dc_is_dmcu_initialized(adev->dm.dc) || + adev->dm.dc->ctx->dmub_srv) && amdgpu_dm_abm_level < 0) { drm_object_attach_property(&aconnector->base.base, adev->mode_info.abm_level_property, 0); } @@ -8630,10 +8725,10 @@ static void amdgpu_dm_commit_audio(struct drm_device *dev, if (!drm_atomic_crtc_needs_modeset(new_crtc_state)) continue; +notify: if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) continue; -notify: aconnector = to_amdgpu_dm_connector(connector); mutex_lock(&adev->dm.audio_lock); @@ -9003,9 +9098,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) trace_amdgpu_dm_atomic_commit_tail_begin(state); - if (dm->dc->caps.ips_support && dm->dc->idle_optimizations_allowed) - dc_allow_idle_optimizations(dm->dc, false); - drm_atomic_helper_update_legacy_modeset_state(dev, state); drm_dp_mst_atomic_wait_for_dependencies(state); @@ -11138,18 +11230,24 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, if (!adev->dm.freesync_module) goto update; - if (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT - || sink->sink_signal == SIGNAL_TYPE_EDP) { + if (edid && (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT || + sink->sink_signal == SIGNAL_TYPE_EDP)) { bool edid_check_required = false; - if (edid) { - edid_check_required = is_dp_capable_without_timing_msa( - adev->dm.dc, - amdgpu_dm_connector); + if (is_dp_capable_without_timing_msa(adev->dm.dc, + amdgpu_dm_connector)) { + if (edid->features & DRM_EDID_FEATURE_CONTINUOUS_FREQ) { + freesync_capable = true; + amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq; + amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq; + } else { + edid_check_required = edid->version > 1 || + (edid->version == 1 && + edid->revision > 1); + } } - if (edid_check_required == true && (edid->version > 1 || - (edid->version == 1 && edid->revision > 1))) { + if (edid_check_required) { for (i = 0; i < 4; i++) { timing = &edid->detailed_timings[i]; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 68a8463239127..5d499b99aba91 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -1483,7 +1483,7 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf, const uint32_t rd_buf_size = 10; struct pipe_ctx *pipe_ctx; ssize_t result = 0; - int i, r, str_len = 30; + int i, r, str_len = 10; rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL); @@ -1495,7 +1495,9 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1596,7 +1598,9 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1681,7 +1685,9 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1780,7 +1786,9 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1865,7 +1873,9 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -1964,7 +1974,9 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2045,7 +2057,9 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2141,7 +2155,9 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2220,7 +2236,9 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2276,7 +2294,9 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2347,7 +2367,9 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } @@ -2418,7 +2440,9 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf, for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink) break; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index c27063305a134..2c36f3d00ca25 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -363,7 +363,7 @@ void dm_helpers_dp_mst_send_payload_allocation( mst_state = to_drm_dp_mst_topology_state(mst_mgr->base.state); new_payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); - ret = drm_dp_add_payload_part2(mst_mgr, mst_state->base.state, new_payload); + ret = drm_dp_add_payload_part2(mst_mgr, new_payload); if (ret) { amdgpu_dm_set_mst_status(&aconnector->mst_status, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 941e96f100f4e..12b036d511d0c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -613,6 +613,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, &connector->base, dev->mode_config.tile_property, 0); + connector->colorspace_property = master->base.colorspace_property; + if (connector->colorspace_property) + drm_connector_attach_colorspace_property(connector); drm_connector_set_path_property(connector, pathprop); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index 1f08c6564c3bf..286ecd28cc6e6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -141,9 +141,8 @@ bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream) * amdgpu_dm_psr_enable() - enable psr f/w * @stream: stream state * - * Return: true if success */ -bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) +void amdgpu_dm_psr_enable(struct dc_stream_state *stream) { struct dc_link *link = stream->link; unsigned int vsync_rate_hz = 0; @@ -190,7 +189,10 @@ bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) if (link->psr_settings.psr_version < DC_PSR_VERSION_SU_1) power_opt |= psr_power_opt_z10_static_screen; - return dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt); + dc_link_set_psr_allow_active(link, &psr_enable, false, false, &power_opt); + + if (link->ctx->dc->caps.ips_support) + dc_allow_idle_optimizations(link->ctx->dc, true); } /* diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h index 6806b3c9c84ba..1fdfd183c0d91 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h @@ -32,7 +32,7 @@ #define AMDGPU_DM_PSR_ENTRY_DELAY 5 void amdgpu_dm_set_psr_caps(struct dc_link *link); -bool amdgpu_dm_psr_enable(struct dc_stream_state *stream); +void amdgpu_dm_psr_enable(struct dc_stream_state *stream); bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream); bool amdgpu_dm_psr_disable(struct dc_stream_state *stream); bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c index 16e72d623630c..08c494a7a21ba 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c @@ -76,10 +76,8 @@ static int amdgpu_dm_wb_encoder_atomic_check(struct drm_encoder *encoder, static int amdgpu_dm_wb_connector_get_modes(struct drm_connector *connector) { - struct drm_device *dev = connector->dev; - - return drm_add_modes_noedid(connector, dev->mode_config.max_width, - dev->mode_config.max_height); + /* Maximum resolution supported by DWB */ + return drm_add_modes_noedid(connector, 3840, 2160); } static int amdgpu_dm_wb_prepare_job(struct drm_writeback_connector *wb_connector, diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 05f392501c0ae..ab31643b10969 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -2948,6 +2948,7 @@ static enum bp_result construct_integrated_info( result = get_integrated_info_v2_1(bp, info); break; case 2: + case 3: result = get_integrated_info_v2_2(bp, info); break; default: diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index 644da46373209..5506cf9b3672f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -145,6 +145,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, */ clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; if (safe_to_lower) { + if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) { + dcn315_smu_set_dtbclk(clk_mgr, false); + clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en; + } /* check that we're not already in lower */ if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) { display_count = dcn315_get_active_display_cnt_wa(dc, context); @@ -160,6 +164,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, } } } else { + if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) { + dcn315_smu_set_dtbclk(clk_mgr, true); + clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en; + } /* check that we're not already in D0 */ if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_MISSION_MODE) { union display_idle_optimization_u idle_info = { 0 }; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 12f3e8aa46d8d..6ad4f4efec5dd 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -99,20 +99,25 @@ static int dcn316_get_active_display_cnt_wa( return display_count; } -static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) +static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, + bool safe_to_lower, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; for (i = 0; i < dc->res_pool->pipe_count; ++i) { - struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe = safe_to_lower + ? &context->res_ctx.pipe_ctx[i] + : &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; - if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || - dc_is_virtual_signal(pipe->stream->signal))) { + if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) || + !pipe->stream->link_enc)) { if (disable) { - pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); + if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc) + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); + reset_sync_context_for_pipe(dc, context, i); } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); @@ -207,11 +212,11 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn316_disable_otg_wa(clk_mgr_base, context, true); + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn316_disable_otg_wa(clk_mgr_base, context, false); + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index aadd07bc68c5d..39c63565baa9a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -216,6 +216,16 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) if (clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz > 1950) clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz = 1950; + /* DPPCLK */ + dcn32_init_single_clock(clk_mgr, PPCLK_DPPCLK, + &clk_mgr_base->bw_params->clk_table.entries[0].dppclk_mhz, + &num_entries_per_clk->num_dppclk_levels); + num_levels = num_entries_per_clk->num_dppclk_levels; + clk_mgr_base->bw_params->dc_mode_limit.dppclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DPPCLK); + //HW recommends limit of 1950 MHz in display clock for all DCN3.2.x + if (clk_mgr_base->bw_params->dc_mode_limit.dppclk_mhz > 1950) + clk_mgr_base->bw_params->dc_mode_limit.dppclk_mhz = 1950; + if (num_entries_per_clk->num_dcfclk_levels && num_entries_per_clk->num_dtbclk_levels && num_entries_per_clk->num_dispclk_levels) @@ -240,6 +250,10 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) = khz_to_mhz_ceil(clk_mgr_base->ctx->dc->debug.min_dpp_clk_khz); } + for (i = 0; i < num_levels; i++) + if (clk_mgr_base->bw_params->clk_table.entries[i].dppclk_mhz > 1950) + clk_mgr_base->bw_params->clk_table.entries[i].dppclk_mhz = 1950; + /* Get UCLK, update bounding box */ clk_mgr_base->funcs->get_memclk_states_from_smu(clk_mgr_base); @@ -682,8 +696,12 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, * since we calculate mode support based on softmax being the max UCLK * frequency. */ - dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, - dc->clk_mgr->bw_params->dc_mode_softmax_memclk); + if (dc->debug.disable_dc_mode_overwrite) { + dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz); + dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz); + } else + dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, + dc->clk_mgr->bw_params->dc_mode_softmax_memclk); } else { dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz); } @@ -716,8 +734,13 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, /* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */ if (clk_mgr_base->clks.p_state_change_support && (update_uclk || !clk_mgr_base->clks.prev_p_state_change_support) && - !dc->work_arounds.clock_update_disable_mask.uclk) + !dc->work_arounds.clock_update_disable_mask.uclk) { + if (dc->clk_mgr->dc_mode_softmax_enabled && dc->debug.disable_dc_mode_overwrite) + dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, + max((int)dc->clk_mgr->bw_params->dc_mode_softmax_memclk, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz))); + dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)); + } if (clk_mgr_base->clks.num_ways != new_clocks->num_ways && clk_mgr_base->clks.num_ways > new_clocks->num_ways) { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index e648902592358..9cbab880c6233 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -384,19 +384,6 @@ static void dcn35_enable_pme_wa(struct clk_mgr *clk_mgr_base) dcn35_smu_enable_pme_wa(clk_mgr); } -void dcn35_init_clocks(struct clk_mgr *clk_mgr) -{ - uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz; - - memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks)); - - // Assumption is that boot state always supports pstate - clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk - clk_mgr->clks.p_state_change_support = true; - clk_mgr->clks.prev_p_state_change_support = true; - clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN; - clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN; -} bool dcn35_are_clock_states_equal(struct dc_clocks *a, struct dc_clocks *b) @@ -421,7 +408,19 @@ static void dcn35_dump_clk_registers(struct clk_state_registers_and_bypass *regs struct clk_mgr_dcn35 *clk_mgr) { } +void dcn35_init_clocks(struct clk_mgr *clk_mgr) +{ + uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz; + memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks)); + + // Assumption is that boot state always supports pstate + clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk + clk_mgr->clks.p_state_change_support = true; + clk_mgr->clks.prev_p_state_change_support = true; + clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN; + clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN; +} static struct clk_bw_params dcn35_bw_params = { .vram_type = Ddr4MemType, .num_channels = 1, @@ -706,7 +705,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk clock_table->NumFclkLevelsEnabled; max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk); - num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS : + num_dcfclk = (clock_table->NumDcfClkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS : clock_table->NumDcfClkLevelsEnabled; for (i = 0; i < num_dcfclk; i++) { int j; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 2c424e435962d..040b5c2a57586 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -411,9 +411,14 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, * avoid conflicting with firmware updates. */ if (dc->ctx->dce_version > DCE_VERSION_MAX) - if (dc->optimized_required || dc->wm_optimized_required) + if (dc->optimized_required) return false; + if (!memcmp(&stream->adjust, adjust, sizeof(*adjust))) + return true; + + dc_exit_ips_for_hw_access(dc); + stream->adjust.v_total_max = adjust->v_total_max; stream->adjust.v_total_mid = adjust->v_total_mid; stream->adjust.v_total_mid_frame_num = adjust->v_total_mid_frame_num; @@ -454,6 +459,8 @@ bool dc_stream_get_last_used_drr_vtotal(struct dc *dc, int i = 0; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -484,6 +491,8 @@ bool dc_stream_get_crtc_position(struct dc *dc, bool ret = false; struct crtc_position position; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -603,6 +612,8 @@ bool dc_stream_configure_crc(struct dc *dc, struct dc_stream_state *stream, if (pipe == NULL) return false; + dc_exit_ips_for_hw_access(dc); + /* By default, capture the full frame */ param.windowa_x_start = 0; param.windowa_y_start = 0; @@ -662,6 +673,8 @@ bool dc_stream_get_crc(struct dc *dc, struct dc_stream_state *stream, struct pipe_ctx *pipe; struct timing_generator *tg; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { pipe = &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->stream == stream) @@ -686,6 +699,8 @@ void dc_stream_set_dyn_expansion(struct dc *dc, struct dc_stream_state *stream, int i; struct pipe_ctx *pipe_ctx; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream) { @@ -721,6 +736,8 @@ void dc_stream_set_dither_option(struct dc_stream_state *stream, if (option > DITHER_OPTION_MAX) return; + dc_exit_ips_for_hw_access(stream->ctx->dc); + stream->dither_option = option; memset(¶ms, 0, sizeof(params)); @@ -745,6 +762,8 @@ bool dc_stream_set_gamut_remap(struct dc *dc, const struct dc_stream_state *stre bool ret = false; struct pipe_ctx *pipes; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream) { pipes = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -762,6 +781,8 @@ bool dc_stream_program_csc_matrix(struct dc *dc, struct dc_stream_state *stream) bool ret = false; struct pipe_ctx *pipes; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream) { @@ -788,6 +809,8 @@ void dc_stream_set_static_screen_params(struct dc *dc, struct pipe_ctx *pipes_affected[MAX_PIPES]; int num_pipes_affected = 0; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < num_streams; i++) { struct dc_stream_state *stream = streams[i]; @@ -1282,6 +1305,54 @@ static void disable_vbios_mode_if_required( } } +/** + * wait_for_blank_complete - wait for all active OPPs to finish pending blank + * pattern updates + * + * @dc: [in] dc reference + * @context: [in] hardware context in use + */ +static void wait_for_blank_complete(struct dc *dc, + struct dc_state *context) +{ + struct pipe_ctx *opp_head; + struct dce_hwseq *hws = dc->hwseq; + int i; + + if (!hws->funcs.wait_for_blank_complete) + return; + + for (i = 0; i < MAX_PIPES; i++) { + opp_head = &context->res_ctx.pipe_ctx[i]; + + if (!resource_is_pipe_type(opp_head, OPP_HEAD) || + dc_state_get_pipe_subvp_type(context, opp_head) == SUBVP_PHANTOM) + continue; + + hws->funcs.wait_for_blank_complete(opp_head->stream_res.opp); + } +} + +static void wait_for_odm_update_pending_complete(struct dc *dc, struct dc_state *context) +{ + struct pipe_ctx *otg_master; + struct timing_generator *tg; + int i; + + for (i = 0; i < MAX_PIPES; i++) { + otg_master = &context->res_ctx.pipe_ctx[i]; + if (!resource_is_pipe_type(otg_master, OTG_MASTER) || + dc_state_get_pipe_subvp_type(context, otg_master) == SUBVP_PHANTOM) + continue; + tg = otg_master->stream_res.tg; + if (tg->funcs->wait_odm_doublebuffer_pending_clear) + tg->funcs->wait_odm_doublebuffer_pending_clear(tg); + } + + /* ODM update may require to reprogram blank pattern for each OPP */ + wait_for_blank_complete(dc, context); +} + static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) { int i; @@ -1733,6 +1804,9 @@ bool dc_validate_boot_timing(const struct dc *dc, return false; } + if (link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED) + return false; + if (dc->link_srv->edp_is_ilr_optimization_required(link, crtc_timing)) { DC_LOG_EVENT_LINK_TRAINING("Seamless boot disabled to optimize eDP link rate\n"); return false; @@ -1766,6 +1840,8 @@ void dc_enable_stereo( int i, j; struct pipe_ctx *pipe; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { if (context != NULL) { pipe = &context->res_ctx.pipe_ctx[i]; @@ -1785,6 +1861,8 @@ void dc_enable_stereo( void dc_trigger_sync(struct dc *dc, struct dc_state *context) { if (context->stream_count > 1 && !dc->debug.disable_timing_sync) { + dc_exit_ips_for_hw_access(dc); + enable_timing_multisync(dc, context); program_timing_sync(dc, context); } @@ -1969,6 +2047,11 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c context->stream_count == 0) { /* Must wait for no flips to be pending before doing optimize bw */ wait_for_no_pipes_pending(dc, context); + /* + * optimized dispclk depends on ODM setup. Need to wait for ODM + * update pending complete before optimizing bandwidth. + */ + wait_for_odm_update_pending_complete(dc, context); /* pplib is notified if disp_num changed */ dc->hwss.optimize_bandwidth(dc, context); /* Need to do otg sync again as otg could be out of sync due to otg @@ -2041,6 +2124,8 @@ enum dc_status dc_commit_streams(struct dc *dc, if (!streams_changed(dc, streams, stream_count)) return res; + dc_exit_ips_for_hw_access(dc); + DC_LOG_DC("%s: %d streams\n", __func__, stream_count); for (i = 0; i < stream_count; i++) { @@ -2227,7 +2312,6 @@ void dc_post_update_surfaces_to_stream(struct dc *dc) } dc->optimized_required = false; - dc->wm_optimized_required = false; } bool dc_set_generic_gpio_for_stereo(bool enable, @@ -2650,8 +2734,6 @@ enum surface_update_type dc_check_update_surfaces_for_stream( } else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) { dc->optimized_required = true; } - - dc->optimized_required |= dc->wm_optimized_required; } return type; @@ -2859,9 +2941,6 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->vrr_active_fixed) stream->vrr_active_fixed = *update->vrr_active_fixed; - if (update->crtc_timing_adjust) - stream->adjust = *update->crtc_timing_adjust; - if (update->dpms_off) stream->dpms_off = *update->dpms_off; @@ -3223,6 +3302,9 @@ static bool dc_dmub_should_send_dirty_rect_cmd(struct dc *dc, struct dc_stream_s if (stream->link->replay_settings.config.replay_supported) return true; + if (stream->ctx->dce_version >= DCN_VERSION_3_5 && stream->abm_level) + return true; + return false; } @@ -3376,6 +3458,8 @@ static void commit_planes_for_stream_fast(struct dc *dc, int i, j; struct pipe_ctx *top_pipe_to_program = NULL; struct dc_stream_status *stream_status = NULL; + dc_exit_ips_for_hw_access(dc); + dc_z10_restore(dc); top_pipe_to_program = resource_get_otg_master_for_stream( @@ -3444,7 +3528,7 @@ static void commit_planes_for_stream_fast(struct dc *dc, top_pipe_to_program->stream->update_flags.raw = 0; } -static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context) +static void wait_for_outstanding_hw_updates(struct dc *dc, struct dc_state *dc_context) { /* * This function calls HWSS to wait for any potentially double buffered @@ -3482,6 +3566,7 @@ static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state } } } + wait_for_odm_update_pending_complete(dc, dc_context); } static void commit_planes_for_stream(struct dc *dc, @@ -3503,6 +3588,8 @@ static void commit_planes_for_stream(struct dc *dc, // dc->current_state anymore, so we have to cache it before we apply // the new SubVP context subvp_prev_use = false; + dc_exit_ips_for_hw_access(dc); + dc_z10_restore(dc); if (update_type == UPDATE_TYPE_FULL) wait_for_outstanding_hw_updates(dc, context); @@ -4293,8 +4380,7 @@ static bool full_update_required(struct dc *dc, stream_update->mst_bw_update || stream_update->func_shaper || stream_update->lut3d_func || - stream_update->pending_test_pattern || - stream_update->crtc_timing_adjust)) + stream_update->pending_test_pattern)) return true; if (stream) { @@ -4384,6 +4470,8 @@ bool dc_update_planes_and_stream(struct dc *dc, bool is_plane_addition = 0; bool is_fast_update_only; + dc_exit_ips_for_hw_access(dc); + populate_fast_updates(fast_update, srf_updates, surface_count, stream_update); is_fast_update_only = fast_update_only(dc, fast_update, srf_updates, surface_count, stream_update, stream); @@ -4504,6 +4592,8 @@ void dc_commit_updates_for_stream(struct dc *dc, int i, j; struct dc_fast_update fast_update[MAX_SURFACES] = {0}; + dc_exit_ips_for_hw_access(dc); + populate_fast_updates(fast_update, srf_updates, surface_count, stream_update); stream_status = dc_stream_get_status(stream); context = dc->current_state; @@ -4688,6 +4778,8 @@ void dc_set_power_state( case DC_ACPI_CM_POWER_STATE_D0: dc_state_construct(dc, dc->current_state); + dc_exit_ips_for_hw_access(dc); + dc_z10_restore(dc); dc->hwss.init_hw(dc); @@ -4829,24 +4921,24 @@ void dc_allow_idle_optimizations(struct dc *dc, bool allow) dc->idle_optimizations_allowed = allow; } -bool dc_dmub_is_ips_idle_state(struct dc *dc) +void dc_exit_ips_for_hw_access(struct dc *dc) { - uint32_t idle_state = 0; + if (dc->caps.ips_support) + dc_allow_idle_optimizations(dc, false); +} +bool dc_dmub_is_ips_idle_state(struct dc *dc) +{ if (dc->debug.disable_idle_power_optimizations) return false; if (!dc->caps.ips_support || (dc->config.disable_ips == DMUB_IPS_DISABLE_ALL)) return false; - if (dc->hwss.get_idle_state) - idle_state = dc->hwss.get_idle_state(dc); - - if (!(idle_state & DMUB_IPS1_ALLOW_MASK) || - !(idle_state & DMUB_IPS2_ALLOW_MASK)) - return true; + if (!dc->ctx->dmub_srv) + return false; - return false; + return dc->ctx->dmub_srv->idle_allowed; } /* set min and max memory clock to lowest and highest DPM level, respectively */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index 180ac47868c22..61986e5cb4919 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -334,7 +334,8 @@ static void dc_state_free(struct kref *kref) void dc_state_release(struct dc_state *state) { - kref_put(&state->refcount, dc_state_free); + if (state != NULL) + kref_put(&state->refcount, dc_state_free); } /* * dc_state_add_stream() - Add a new dc_stream_state to a dc_state. @@ -435,6 +436,15 @@ bool dc_state_add_plane( goto out; } + if (stream_status->plane_count == 0 && dc->config.enable_windowed_mpo_odm) + /* ODM combine could prevent us from supporting more planes + * we will reset ODM slice count back to 1 when all planes have + * been removed to maximize the amount of planes supported when + * new planes are added. + */ + resource_update_pipes_for_stream_with_slice_count( + state, dc->current_state, dc->res_pool, stream, 1); + otg_master_pipe = resource_get_otg_master_for_stream( &state->res_ctx, stream); if (otg_master_pipe) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 54670e0b15189..51a970fcb5d05 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -423,6 +423,8 @@ bool dc_stream_add_writeback(struct dc *dc, return false; } + dc_exit_ips_for_hw_access(dc); + wb_info->dwb_params.out_transfer_func = stream->out_transfer_func; dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst]; @@ -493,6 +495,8 @@ bool dc_stream_fc_disable_writeback(struct dc *dc, return false; } + dc_exit_ips_for_hw_access(dc); + if (dwb->funcs->set_fc_enable) dwb->funcs->set_fc_enable(dwb, DWB_FRAME_CAPTURE_DISABLE); @@ -542,6 +546,8 @@ bool dc_stream_remove_writeback(struct dc *dc, return false; } + dc_exit_ips_for_hw_access(dc); + /* disable writeback */ if (dc->hwss.disable_writeback) { struct dwbc *dwb = dc->res_pool->dwbc[dwb_pipe_inst]; @@ -557,6 +563,8 @@ bool dc_stream_warmup_writeback(struct dc *dc, int num_dwb, struct dc_writeback_info *wb_info) { + dc_exit_ips_for_hw_access(dc); + if (dc->hwss.mmhubbub_warmup) return dc->hwss.mmhubbub_warmup(dc, num_dwb, wb_info); else @@ -569,6 +577,8 @@ uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream) struct resource_context *res_ctx = &dc->current_state->res_ctx; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg; @@ -597,6 +607,8 @@ bool dc_stream_send_dp_sdp(const struct dc_stream_state *stream, dc = stream->ctx->dc; res_ctx = &dc->current_state->res_ctx; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; @@ -628,6 +640,8 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream, struct resource_context *res_ctx = &dc->current_state->res_ctx; + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < MAX_PIPES; i++) { struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg; @@ -664,6 +678,8 @@ bool dc_stream_dmdata_status_done(struct dc *dc, struct dc_stream_state *stream) if (i == MAX_PIPES) return true; + dc_exit_ips_for_hw_access(dc); + return dc->hwss.dmdata_status_done(pipe); } @@ -698,6 +714,8 @@ bool dc_stream_set_dynamic_metadata(struct dc *dc, pipe_ctx->stream->dmdata_address = attr->address; + dc_exit_ips_for_hw_access(dc); + dc->hwss.program_dmdata_engine(pipe_ctx); if (hubp->funcs->dmdata_set_attributes != NULL && diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c index 19a2c7140ae84..19140fb65787c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c @@ -161,6 +161,8 @@ const struct dc_plane_status *dc_plane_get_status( break; } + dc_exit_ips_for_hw_access(dc); + for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index c9317ea0258ea..fc60fa5814fbe 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -987,6 +987,7 @@ struct dc_debug_options { bool psp_disabled_wa; unsigned int ips2_eval_delay_us; unsigned int ips2_entry_delay_us; + bool disable_dmub_reallow_idle; bool disable_timeout; bool disable_extblankadj; unsigned int static_screen_wait_frames; @@ -1037,7 +1038,6 @@ struct dc { /* Require to optimize clocks and bandwidth for added/removed planes */ bool optimized_required; - bool wm_optimized_required; bool idle_optimizations_allowed; bool enable_c20_dtm_b0; @@ -2325,6 +2325,7 @@ bool dc_is_plane_eligible_for_idle_optimizations(struct dc *dc, struct dc_plane_ struct dc_cursor_attributes *cursor_attr); void dc_allow_idle_optimizations(struct dc *dc, bool allow); +void dc_exit_ips_for_hw_access(struct dc *dc); bool dc_dmub_is_ips_idle_state(struct dc *dc); /* set min and max memory clock to lowest and highest DPM level, respectively */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index 363d522603a21..447dab3864019 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -1320,16 +1320,27 @@ void dc_dmub_srv_apply_idle_power_optimizations(const struct dc *dc, bool allow_ * Powering up the hardware requires notifying PMFW and DMCUB. * Clearing the driver idle allow requires a DMCUB command. * DMCUB commands requires the DMCUB to be powered up and restored. - * - * Exit out early to prevent an infinite loop of DMCUB commands - * triggering exit low power - use software state to track this. */ - dc_dmub_srv->idle_allowed = allow_idle; - if (!allow_idle) + if (!allow_idle) { dc_dmub_srv_exit_low_power_state(dc); - else + /* + * Idle is considered fully exited only after the sequence above + * fully completes. If we have a race of two threads exiting + * at the same time then it's safe to perform the sequence + * twice as long as we're not re-entering. + * + * Infinite command submission is avoided by using the + * dm_execute_dmub_cmd submission instead of the "wake" helpers. + */ + dc_dmub_srv->idle_allowed = false; + } else { + /* Consider idle as notified prior to the actual submission to + * prevent multiple entries. */ + dc_dmub_srv->idle_allowed = true; + dc_dmub_srv_notify_idle(dc, allow_idle); + } } bool dc_wake_and_execute_dmub_cmd(const struct dc_context *ctx, union dmub_rb_cmd *cmd, @@ -1364,7 +1375,7 @@ bool dc_wake_and_execute_dmub_cmd_list(const struct dc_context *ctx, unsigned in else result = dm_execute_dmub_cmd(ctx, cmd, wait_type); - if (result && reallow_idle) + if (result && reallow_idle && !ctx->dc->debug.disable_dmub_reallow_idle) dc_dmub_srv_apply_idle_power_optimizations(ctx->dc, true); return result; @@ -1413,7 +1424,7 @@ bool dc_wake_and_execute_gpint(const struct dc_context *ctx, enum dmub_gpint_com result = dc_dmub_execute_gpint(ctx, command_code, param, response, wait_type); - if (result && reallow_idle) + if (result && reallow_idle && !ctx->dc->debug.disable_dmub_reallow_idle) dc_dmub_srv_apply_idle_power_optimizations(ctx->dc, true); return result; diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index ee10941caa598..a23eebd9933b7 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -139,7 +139,6 @@ union stream_update_flags { uint32_t wb_update:1; uint32_t dsc_changed : 1; uint32_t mst_bw : 1; - uint32_t crtc_timing_adjust : 1; uint32_t fams_changed : 1; } bits; @@ -326,7 +325,6 @@ struct dc_stream_update { struct dc_3dlut *lut3d_func; struct test_pattern *pending_test_pattern; - struct dc_crtc_timing_adjust *crtc_timing_adjust; }; bool dc_is_stream_unchanged( diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 9900dda2eef5c..be2ac5c442a48 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -1085,9 +1085,9 @@ struct replay_settings { /* SMU optimization is enabled */ bool replay_smu_opt_enable; /* Current Coasting vtotal */ - uint16_t coasting_vtotal; + uint32_t coasting_vtotal; /* Coasting vtotal table */ - uint16_t coasting_vtotal_table[PR_COASTING_TYPE_NUM]; + uint32_t coasting_vtotal_table[PR_COASTING_TYPE_NUM]; /* Maximum link off frame count */ enum replay_link_off_frame_count_level link_off_frame_count_level; /* Replay pseudo vtotal for abm + ips on full screen video which can improve ips residency */ diff --git a/drivers/gpu/drm/amd/display/dc/dce110/Makefile b/drivers/gpu/drm/amd/display/dc/dce110/Makefile index f0777d61c2cbb..c307f040e48fc 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce110/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'controller' sub-component of DAL. # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce110/dce110_resource.o = -Wno-override-init DCE110 = dce110_timing_generator.o \ dce110_compressor.o dce110_opp_regamma_v.o \ diff --git a/drivers/gpu/drm/amd/display/dc/dce112/Makefile b/drivers/gpu/drm/amd/display/dc/dce112/Makefile index 7e92effec8944..683866797709b 100644 --- a/drivers/gpu/drm/amd/display/dc/dce112/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce112/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'controller' sub-component of DAL. # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce112/dce112_resource.o = -Wno-override-init DCE112 = dce112_compressor.o diff --git a/drivers/gpu/drm/amd/display/dc/dce120/Makefile b/drivers/gpu/drm/amd/display/dc/dce120/Makefile index 1e3ef68a452a5..8f508e6627480 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce120/Makefile @@ -24,7 +24,7 @@ # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce120/dce120_resource.o = -Wno-override-init DCE120 = dce120_timing_generator.o diff --git a/drivers/gpu/drm/amd/display/dc/dce60/Makefile b/drivers/gpu/drm/amd/display/dc/dce60/Makefile index fee331accc0e7..eede83ad91fa0 100644 --- a/drivers/gpu/drm/amd/display/dc/dce60/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce60/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'controller' sub-component of DAL. # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce60/dce60_resource.o = -Wno-override-init DCE60 = dce60_timing_generator.o dce60_hw_sequencer.o \ dce60_resource.o diff --git a/drivers/gpu/drm/amd/display/dc/dce80/Makefile b/drivers/gpu/drm/amd/display/dc/dce80/Makefile index 7eefffbdc9253..fba189d26652d 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dce80/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'controller' sub-component of DAL. # It provides the control and status of HW CRTC block. -CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = $(call cc-disable-warning, override-init) +CFLAGS_$(AMDDALPATH)/dc/dce80/dce80_resource.o = -Wno-override-init DCE80 = dce80_timing_generator.o diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c index 3538973bd0c6c..c0372aa4ec838 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c @@ -382,6 +382,11 @@ bool cm_helper_translate_curve_to_hw_format(struct dc_context *ctx, i += increment) { if (j == hw_points - 1) break; + if (i >= TRANSFER_FUNC_POINTS) { + DC_LOG_ERROR("Index out of bounds: i=%d, TRANSFER_FUNC_POINTS=%d\n", + i, TRANSFER_FUNC_POINTS); + return false; + } rgb_resulted[j].red = output_tf->tf_pts.red[i]; rgb_resulted[j].green = output_tf->tf_pts.green[i]; rgb_resulted[j].blue = output_tf->tf_pts.blue[i]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c index 0dec57679269b..86bfed5dea2e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c @@ -377,6 +377,7 @@ static const struct opp_funcs dcn10_opp_funcs = { .opp_set_disp_pattern_generator = NULL, .opp_program_dpg_dimensions = NULL, .dpg_is_blanked = NULL, + .dpg_is_pending = NULL, .opp_destroy = opp1_destroy }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c index 0784d01986610..fbf1b6370eb23 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c @@ -337,6 +337,19 @@ bool opp2_dpg_is_blanked(struct output_pixel_processor *opp) (double_buffer_pending == 0); } +bool opp2_dpg_is_pending(struct output_pixel_processor *opp) +{ + struct dcn20_opp *oppn20 = TO_DCN20_OPP(opp); + uint32_t double_buffer_pending; + uint32_t dpg_en; + + REG_GET(DPG_CONTROL, DPG_EN, &dpg_en); + + REG_GET(DPG_STATUS, DPG_DOUBLE_BUFFER_PENDING, &double_buffer_pending); + + return (dpg_en == 1 && double_buffer_pending == 1); +} + void opp2_program_left_edge_extra_pixel ( struct output_pixel_processor *opp, bool count) @@ -363,6 +376,7 @@ static struct opp_funcs dcn20_opp_funcs = { .opp_set_disp_pattern_generator = opp2_set_disp_pattern_generator, .opp_program_dpg_dimensions = opp2_program_dpg_dimensions, .dpg_is_blanked = opp2_dpg_is_blanked, + .dpg_is_pending = opp2_dpg_is_pending, .opp_dpg_set_blank_color = opp2_dpg_set_blank_color, .opp_destroy = opp1_destroy, .opp_program_left_edge_extra_pixel = opp2_program_left_edge_extra_pixel, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h index 3ab221bdd27dd..8f186abd558db 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h @@ -159,6 +159,8 @@ void opp2_program_dpg_dimensions( bool opp2_dpg_is_blanked(struct output_pixel_processor *opp); +bool opp2_dpg_is_pending(struct output_pixel_processor *opp); + void opp2_dpg_set_blank_color( struct output_pixel_processor *opp, const struct tg_color *color); diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c index 8e77db46a4090..6a71ba3dfc632 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c @@ -50,6 +50,7 @@ static struct opp_funcs dcn201_opp_funcs = { .opp_set_disp_pattern_generator = opp2_set_disp_pattern_generator, .opp_program_dpg_dimensions = opp2_program_dpg_dimensions, .dpg_is_blanked = opp2_dpg_is_blanked, + .dpg_is_pending = opp2_dpg_is_pending, .opp_dpg_set_blank_color = opp2_dpg_set_blank_color, .opp_destroy = opp1_destroy, .opp_program_left_edge_extra_pixel = opp2_program_left_edge_extra_pixel, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c index d1500b2238580..2f9da981a8bea 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c @@ -44,6 +44,36 @@ #define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0])) +void mpc3_mpc_init(struct mpc *mpc) +{ + struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc); + int opp_id; + + mpc1_mpc_init(mpc); + + for (opp_id = 0; opp_id < MAX_OPP; opp_id++) { + if (REG(MUX[opp_id])) + /* disable mpc out rate and flow control */ + REG_UPDATE_2(MUX[opp_id], MPC_OUT_RATE_CONTROL_DISABLE, + 1, MPC_OUT_FLOW_CONTROL_COUNT, 0); + } +} + +void mpc3_mpc_init_single_inst(struct mpc *mpc, unsigned int mpcc_id) +{ + struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc); + + mpc1_mpc_init_single_inst(mpc, mpcc_id); + + /* assuming mpc out mux is connected to opp with the same index at this + * point in time (e.g. transitioning from vbios to driver) + */ + if (mpcc_id < MAX_OPP && REG(MUX[mpcc_id])) + /* disable mpc out rate and flow control */ + REG_UPDATE_2(MUX[mpcc_id], MPC_OUT_RATE_CONTROL_DISABLE, + 1, MPC_OUT_FLOW_CONTROL_COUNT, 0); +} + bool mpc3_is_dwb_idle( struct mpc *mpc, int dwb_id) @@ -80,25 +110,6 @@ void mpc3_disable_dwb_mux( MPC_DWB0_MUX, 0xf); } -void mpc3_set_out_rate_control( - struct mpc *mpc, - int opp_id, - bool enable, - bool rate_2x_mode, - struct mpc_dwb_flow_control *flow_control) -{ - struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc); - - REG_UPDATE_2(MUX[opp_id], - MPC_OUT_RATE_CONTROL_DISABLE, !enable, - MPC_OUT_RATE_CONTROL, rate_2x_mode); - - if (flow_control) - REG_UPDATE_2(MUX[opp_id], - MPC_OUT_FLOW_CONTROL_MODE, flow_control->flow_ctrl_mode, - MPC_OUT_FLOW_CONTROL_COUNT, flow_control->flow_ctrl_cnt1); -} - enum dc_lut_mode mpc3_get_ogam_current(struct mpc *mpc, int mpcc_id) { /*Contrary to DCN2 and DCN1 wherein a single status register field holds this info; @@ -1386,8 +1397,8 @@ static const struct mpc_funcs dcn30_mpc_funcs = { .read_mpcc_state = mpc1_read_mpcc_state, .insert_plane = mpc1_insert_plane, .remove_mpcc = mpc1_remove_mpcc, - .mpc_init = mpc1_mpc_init, - .mpc_init_single_inst = mpc1_mpc_init_single_inst, + .mpc_init = mpc3_mpc_init, + .mpc_init_single_inst = mpc3_mpc_init_single_inst, .update_blending = mpc2_update_blending, .cursor_lock = mpc1_cursor_lock, .get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp, @@ -1404,7 +1415,6 @@ static const struct mpc_funcs dcn30_mpc_funcs = { .set_dwb_mux = mpc3_set_dwb_mux, .disable_dwb_mux = mpc3_disable_dwb_mux, .is_dwb_idle = mpc3_is_dwb_idle, - .set_out_rate_control = mpc3_set_out_rate_control, .set_gamut_remap = mpc3_set_gamut_remap, .program_shaper = mpc3_program_shaper, .acquire_rmu = mpcc3_acquire_rmu, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h index 5198f2167c7c8..d3b904517a22d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.h @@ -1007,6 +1007,13 @@ void dcn30_mpc_construct(struct dcn30_mpc *mpc30, int num_mpcc, int num_rmu); +void mpc3_mpc_init( + struct mpc *mpc); + +void mpc3_mpc_init_single_inst( + struct mpc *mpc, + unsigned int mpcc_id); + bool mpc3_program_shaper( struct mpc *mpc, const struct pwl_params *params, @@ -1074,13 +1081,6 @@ bool mpc3_is_dwb_idle( struct mpc *mpc, int dwb_id); -void mpc3_set_out_rate_control( - struct mpc *mpc, - int opp_id, - bool enable, - bool rate_2x_mode, - struct mpc_dwb_flow_control *flow_control); - void mpc3_power_on_ogam_lut( struct mpc *mpc, int mpcc_id, bool power_on); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c index 5b7ad38f85e08..65e45a0b4ff34 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c @@ -395,6 +395,12 @@ void dcn31_hpo_dp_link_enc_set_throttled_vcp_size( x), 25)); + // If y rounds up to integer, carry it over to x. + if (y >> 25) { + x += 1; + y = 0; + } + switch (stream_encoder_inst) { case 0: REG_SET_2(DP_DPHY_SYM32_VC_RATE_CNTL0, 0, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c index d761b0df28784..8a0460e863097 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c @@ -34,6 +34,7 @@ #include "dc_bios_types.h" #include "link_enc_cfg.h" +#include "dc_dmub_srv.h" #include "gpio_service_interface.h" #ifndef MIN @@ -61,6 +62,38 @@ #define AUX_REG_WRITE(reg_name, val) \ dm_write_reg(CTX, AUX_REG(reg_name), val) +static uint8_t phy_id_from_transmitter(enum transmitter t) +{ + uint8_t phy_id; + + switch (t) { + case TRANSMITTER_UNIPHY_A: + phy_id = 0; + break; + case TRANSMITTER_UNIPHY_B: + phy_id = 1; + break; + case TRANSMITTER_UNIPHY_C: + phy_id = 2; + break; + case TRANSMITTER_UNIPHY_D: + phy_id = 3; + break; + case TRANSMITTER_UNIPHY_E: + phy_id = 4; + break; + case TRANSMITTER_UNIPHY_F: + phy_id = 5; + break; + case TRANSMITTER_UNIPHY_G: + phy_id = 6; + break; + default: + phy_id = 0; + break; + } + return phy_id; +} void enc32_hw_init(struct link_encoder *enc) { @@ -117,38 +150,50 @@ void dcn32_link_encoder_enable_dp_output( } } -static bool dcn32_link_encoder_is_in_alt_mode(struct link_encoder *enc) +static bool query_dp_alt_from_dmub(struct link_encoder *enc, + union dmub_rb_cmd *cmd) { struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); - uint32_t dp_alt_mode_disable = 0; - bool is_usb_c_alt_mode = false; - if (enc->features.flags.bits.DP_IS_USB_C) { - /* if value == 1 alt mode is disabled, otherwise it is enabled */ - REG_GET(RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, &dp_alt_mode_disable); - is_usb_c_alt_mode = (dp_alt_mode_disable == 0); - } + memset(cmd, 0, sizeof(*cmd)); + cmd->query_dp_alt.header.type = DMUB_CMD__VBIOS; + cmd->query_dp_alt.header.sub_type = + DMUB_CMD__VBIOS_TRANSMITTER_QUERY_DP_ALT; + cmd->query_dp_alt.header.payload_bytes = sizeof(cmd->query_dp_alt.data); + cmd->query_dp_alt.data.phy_id = phy_id_from_transmitter(enc10->base.transmitter); + + if (!dc_wake_and_execute_dmub_cmd(enc->ctx, cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) + return false; - return is_usb_c_alt_mode; + return true; } -static void dcn32_link_encoder_get_max_link_cap(struct link_encoder *enc, +bool dcn32_link_encoder_is_in_alt_mode(struct link_encoder *enc) +{ + union dmub_rb_cmd cmd; + + if (!query_dp_alt_from_dmub(enc, &cmd)) + return false; + + return (cmd.query_dp_alt.data.is_dp_alt_disable == 0); +} + +void dcn32_link_encoder_get_max_link_cap(struct link_encoder *enc, struct dc_link_settings *link_settings) { - struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); - uint32_t is_in_usb_c_dp4_mode = 0; + union dmub_rb_cmd cmd; dcn10_link_encoder_get_max_link_cap(enc, link_settings); - /* in usb c dp2 mode, max lane count is 2 */ - if (enc->funcs->is_in_alt_mode && enc->funcs->is_in_alt_mode(enc)) { - REG_GET(RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, &is_in_usb_c_dp4_mode); - if (!is_in_usb_c_dp4_mode) - link_settings->lane_count = MIN(LANE_COUNT_TWO, link_settings->lane_count); - } + if (!query_dp_alt_from_dmub(enc, &cmd)) + return; + if (cmd.query_dp_alt.data.is_usb && + cmd.query_dp_alt.data.is_dp4 == 0) + link_settings->lane_count = MIN(LANE_COUNT_TWO, link_settings->lane_count); } + static const struct link_encoder_funcs dcn32_link_enc_funcs = { .read_state = link_enc2_read_state, .validate_output_with_stream = @@ -203,12 +248,12 @@ void dcn32_link_encoder_construct( enc10->base.hpd_source = init_data->hpd_source; enc10->base.connector = init_data->connector; + if (enc10->base.connector.id == CONNECTOR_ID_USBC) + enc10->base.features.flags.bits.DP_IS_USB_C = 1; enc10->base.preferred_engine = ENGINE_ID_UNKNOWN; enc10->base.features = *enc_features; - if (enc10->base.connector.id == CONNECTOR_ID_USBC) - enc10->base.features.flags.bits.DP_IS_USB_C = 1; enc10->base.transmitter = init_data->transmitter; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h index bbcfce06bec01..2d5f25290ed14 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h @@ -53,4 +53,9 @@ void dcn32_link_encoder_enable_dp_output( const struct dc_link_settings *link_settings, enum clock_source_id clock_source); +bool dcn32_link_encoder_is_in_alt_mode(struct link_encoder *enc); + +void dcn32_link_encoder_get_max_link_cap(struct link_encoder *enc, + struct dc_link_settings *link_settings); + #endif /* __DC_LINK_ENCODER__DCN32_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c index e789e654c3870..e408e859b3556 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c @@ -47,7 +47,7 @@ void mpc32_mpc_init(struct mpc *mpc) struct dcn30_mpc *mpc30 = TO_DCN30_MPC(mpc); int mpcc_id; - mpc1_mpc_init(mpc); + mpc3_mpc_init(mpc); if (mpc->ctx->dc->debug.enable_mem_low_power.bits.mpc) { if (mpc30->mpc_mask->MPCC_MCM_SHAPER_MEM_LOW_PWR_MODE && mpc30->mpc_mask->MPCC_MCM_3DLUT_MEM_LOW_PWR_MODE) { @@ -991,7 +991,7 @@ static const struct mpc_funcs dcn32_mpc_funcs = { .insert_plane = mpc1_insert_plane, .remove_mpcc = mpc1_remove_mpcc, .mpc_init = mpc32_mpc_init, - .mpc_init_single_inst = mpc1_mpc_init_single_inst, + .mpc_init_single_inst = mpc3_mpc_init_single_inst, .update_blending = mpc2_update_blending, .cursor_lock = mpc1_cursor_lock, .get_mpcc_for_dpp = mpc1_get_mpcc_for_dpp, @@ -1008,7 +1008,6 @@ static const struct mpc_funcs dcn32_mpc_funcs = { .set_dwb_mux = mpc3_set_dwb_mux, .disable_dwb_mux = mpc3_disable_dwb_mux, .is_dwb_idle = mpc3_is_dwb_idle, - .set_out_rate_control = mpc3_set_out_rate_control, .set_gamut_remap = mpc3_set_gamut_remap, .program_shaper = mpc32_program_shaper, .program_3dlut = mpc32_program_3dlut, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index 87760600e154d..f98def6c8c2d2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -782,3 +782,9 @@ void dcn32_update_dml_pipes_odm_policy_based_on_context(struct dc *dc, struct dc pipe_cnt++; } } + +void dcn32_override_min_req_dcfclk(struct dc *dc, struct dc_state *context) +{ + if (dcn32_subvp_in_use(dc, context) && context->bw_ctx.bw.dcn.clk.dcfclk_khz <= MIN_SUBVP_DCFCLK_KHZ) + context->bw_ctx.bw.dcn.clk.dcfclk_khz = MIN_SUBVP_DCFCLK_KHZ; +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c index 81e349d5835bb..da94e5309fbaf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c @@ -184,6 +184,8 @@ void dcn35_link_encoder_construct( enc10->base.hpd_source = init_data->hpd_source; enc10->base.connector = init_data->connector; + if (enc10->base.connector.id == CONNECTOR_ID_USBC) + enc10->base.features.flags.bits.DP_IS_USB_C = 1; enc10->base.preferred_engine = ENGINE_ID_UNKNOWN; @@ -238,8 +240,6 @@ void dcn35_link_encoder_construct( } enc10->base.features.flags.bits.HDMI_6GB_EN = 1; - if (enc10->base.connector.id == CONNECTOR_ID_USBC) - enc10->base.features.flags.bits.DP_IS_USB_C = 1; if (bp_funcs->get_connector_speed_cap_info) result = bp_funcs->get_connector_speed_cap_info(enc10->base.ctx->dc_bios, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index deb6d162a2d5c..7307b7b8d8ad7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -291,6 +291,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = { .do_urgent_latency_adjustment = false, .urgent_latency_adjustment_fabric_clock_component_us = 0, .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, + .dispclk_dppclk_vco_speed_mhz = 2400.0, .num_chans = 4, .dummy_pstate_latency_us = 10.0 }; @@ -438,6 +439,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = { .do_urgent_latency_adjustment = false, .urgent_latency_adjustment_fabric_clock_component_us = 0, .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, + .dispclk_dppclk_vco_speed_mhz = 2500.0, }; void dcn31_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index a0a65e0991041..ba76dd4a2ce29 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -2760,7 +2760,7 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk struct _vcs_dpi_voltage_scaling_st entry = {0}; struct clk_limit_table_entry max_clk_data = {0}; - unsigned int min_dcfclk_mhz = 199, min_fclk_mhz = 299; + unsigned int min_dcfclk_mhz = 399, min_fclk_mhz = 599; static const unsigned int num_dcfclk_stas = 5; unsigned int dcfclk_sta_targets[DC__VOLTAGE_STATES] = {199, 615, 906, 1324, 1564}; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index 1ba6933d2b361..a20f28a5d2e7b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -228,17 +228,13 @@ void dml2_init_socbb_params(struct dml2_context *dml2, const struct dc *in_dc, s break; case dml_project_dcn35: + case dml_project_dcn351: out->num_chans = 4; out->round_trip_ping_latency_dcfclk_cycles = 106; out->smn_latency_us = 2; out->dispclk_dppclk_vco_speed_mhz = 3600; break; - case dml_project_dcn351: - out->num_chans = 16; - out->round_trip_ping_latency_dcfclk_cycles = 1100; - out->smn_latency_us = 2; - break; } /* ---Overrides if available--- */ if (dml2->config.bbox_overrides.dram_num_chan) @@ -824,13 +820,25 @@ static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_stream_state *in) { + dml_uint_t width, height; + + if (in->timing.h_addressable > 3840) + width = 3840; + else + width = in->timing.h_addressable; // 4K max + + if (in->timing.v_addressable > 2160) + height = 2160; + else + height = in->timing.v_addressable; // 4K max + out->CursorBPP[location] = dml_cur_32bit; out->CursorWidth[location] = 256; out->GPUVMMinPageSizeKBytes[location] = 256; - out->ViewportWidth[location] = in->timing.h_addressable; - out->ViewportHeight[location] = in->timing.v_addressable; + out->ViewportWidth[location] = width; + out->ViewportHeight[location] = height; out->ViewportStationary[location] = false; out->ViewportWidthChroma[location] = 0; out->ViewportHeightChroma[location] = 0; @@ -849,7 +857,7 @@ static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned out->HTapsChroma[location] = 0; out->VTapsChroma[location] = 0; out->SourceScan[location] = dml_rotation_0; - out->ScalerRecoutWidth[location] = in->timing.h_addressable; + out->ScalerRecoutWidth[location] = width; out->LBBitPerPixel[location] = 57; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c index 2a58a7687bdb5..72cca367062e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c @@ -703,13 +703,8 @@ static inline struct dml2_context *dml2_allocate_memory(void) return (struct dml2_context *) kzalloc(sizeof(struct dml2_context), GFP_KERNEL); } -bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2) +static void dml2_init(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2) { - // Allocate Mode Lib Ctx - *dml2 = dml2_allocate_memory(); - - if (!(*dml2)) - return false; // Store config options (*dml2)->config = *config; @@ -737,9 +732,18 @@ bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options initialize_dml2_soc_bbox(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc); initialize_dml2_soc_states(*dml2, in_dc, &(*dml2)->v20.dml_core_ctx.soc, &(*dml2)->v20.dml_core_ctx.states); +} + +bool dml2_create(const struct dc *in_dc, const struct dml2_configuration_options *config, struct dml2_context **dml2) +{ + // Allocate Mode Lib Ctx + *dml2 = dml2_allocate_memory(); + + if (!(*dml2)) + return false; + + dml2_init(in_dc, config, dml2); - /*Initialize DML20 instance which calls dml2_core_create, and core_dcn3_populate_informative*/ - //dml2_initialize_instance(&(*dml_ctx)->v20.dml_init); return true; } @@ -779,3 +783,11 @@ bool dml2_create_copy(struct dml2_context **dst_dml2, return true; } + +void dml2_reinit(const struct dc *in_dc, + const struct dml2_configuration_options *config, + struct dml2_context **dml2) +{ + + dml2_init(in_dc, config, dml2); +} diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h index ee0eb184eb6d7..cc662d682fd4d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h @@ -214,6 +214,9 @@ void dml2_copy(struct dml2_context *dst_dml2, struct dml2_context *src_dml2); bool dml2_create_copy(struct dml2_context **dst_dml2, struct dml2_context *src_dml2); +void dml2_reinit(const struct dc *in_dc, + const struct dml2_configuration_options *config, + struct dml2_context **dml2); /* * dml2_validate - Determines if a display configuration is supported or not. diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index 0df6c55eb3260..6b10124e21b72 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -1050,7 +1050,12 @@ static bool setup_dsc_config( if (!is_dsc_possible) goto done; - dsc_cfg->num_slices_v = pic_height/slice_height; + if (slice_height > 0) { + dsc_cfg->num_slices_v = pic_height / slice_height; + } else { + is_dsc_possible = false; + goto done; + } if (target_bandwidth_kbps > 0) { is_dsc_possible = decide_dsc_target_bpp_x16( diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 01493c49bd7a0..12af6bb9fead7 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1185,7 +1185,8 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) if (dccg) { dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst); dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst); - dccg->funcs->set_dtbclk_dto(dccg, &dto_params); + if (dccg && dccg->funcs->set_dtbclk_dto) + dccg->funcs->set_dtbclk_dto(dccg, &dto_params); } } else if (dccg && dccg->funcs->disable_symclk_se) { dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c index 6dd479e8a3485..c45f84aa320ef 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c @@ -1840,6 +1840,9 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, { struct dpp *dpp = pipe_ctx->plane_res.dpp; + if (!stream) + return false; + if (dpp == NULL) return false; @@ -1862,8 +1865,8 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, } else dpp->funcs->dpp_program_regamma_pwl(dpp, NULL, OPP_REGAMMA_BYPASS); - if (stream != NULL && stream->ctx != NULL && - stream->out_transfer_func != NULL) { + if (stream->ctx && + stream->out_transfer_func) { log_tf(stream->ctx, stream->out_transfer_func, dpp->regamma_params.hw_points_num); @@ -3076,7 +3079,7 @@ void dcn10_prepare_bandwidth( context, false); - dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub, + dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub, &context->bw_ctx.bw.dcn.watermarks, dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000, true); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 931ac8ed7069d..868a086c72a2c 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -1392,6 +1392,11 @@ static void dcn20_detect_pipe_changes(struct dc_state *old_state, return; } + if (resource_is_pipe_type(new_pipe, OTG_MASTER) && + resource_is_odm_topology_changed(new_pipe, old_pipe)) + /* Detect odm changes */ + new_pipe->update_flags.bits.odm = 1; + /* Exit on unchanged, unused pipe */ if (!old_pipe->plane_state && !new_pipe->plane_state) return; @@ -1445,10 +1450,6 @@ static void dcn20_detect_pipe_changes(struct dc_state *old_state, /* Detect top pipe only changes */ if (resource_is_pipe_type(new_pipe, OTG_MASTER)) { - /* Detect odm changes */ - if (resource_is_odm_topology_changed(new_pipe, old_pipe)) - new_pipe->update_flags.bits.odm = 1; - /* Detect global sync changes */ if (old_pipe->pipe_dlg_param.vready_offset != new_pipe->pipe_dlg_param.vready_offset || old_pipe->pipe_dlg_param.vstartup_start != new_pipe->pipe_dlg_param.vstartup_start @@ -1891,19 +1892,20 @@ void dcn20_program_front_end_for_ctx( DC_LOGGER_INIT(dc->ctx->logger); unsigned int prev_hubp_count = 0; unsigned int hubp_count = 0; + struct pipe_ctx *pipe; if (resource_is_pipe_topology_changed(dc->current_state, context)) resource_log_pipe_topology_update(dc, context); if (dc->hwss.program_triplebuffer != NULL && dc->debug.enable_tri_buf) { for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + pipe = &context->res_ctx.pipe_ctx[i]; - if (!pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe && pipe_ctx->plane_state) { - ASSERT(!pipe_ctx->plane_state->triplebuffer_flips); + if (!pipe->top_pipe && !pipe->prev_odm_pipe && pipe->plane_state) { + ASSERT(!pipe->plane_state->triplebuffer_flips); /*turn off triple buffer for full update*/ dc->hwss.program_triplebuffer( - dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips); + dc, pipe, pipe->plane_state->triplebuffer_flips); } } } @@ -1978,12 +1980,22 @@ void dcn20_program_front_end_for_ctx( DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx); } + /* update ODM for blanked OTG master pipes */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + if (resource_is_pipe_type(pipe, OTG_MASTER) && + !resource_is_pipe_type(pipe, DPP_PIPE) && + pipe->update_flags.bits.odm && + hws->funcs.update_odm) + hws->funcs.update_odm(dc, context, pipe); + } + /* * Program all updated pipes, order matters for mpcc setup. Start with * top pipe and program all pipes that follow in order */ for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + pipe = &context->res_ctx.pipe_ctx[i]; if (pipe->plane_state && !pipe->top_pipe) { while (pipe) { @@ -2022,17 +2034,6 @@ void dcn20_program_front_end_for_ctx( context->stream_status[0].plane_count > 1) { pipe->plane_res.hubp->funcs->hubp_wait_pipe_read_start(pipe->plane_res.hubp); } - - /* when dynamic ODM is active, pipes must be reconfigured when all planes are - * disabled, as some transitions will leave software and hardware state - * mismatched. - */ - if (dc->debug.enable_single_display_2to1_odm_policy && - pipe->stream && - pipe->update_flags.bits.disable && - !pipe->prev_odm_pipe && - hws->funcs.update_odm) - hws->funcs.update_odm(dc, context, pipe); } } @@ -2159,10 +2160,10 @@ void dcn20_prepare_bandwidth( } /* program dchubbub watermarks: - * For assigning wm_optimized_required, use |= operator since we don't want + * For assigning optimized_required, use |= operator since we don't want * to clear the value if the optimize has not happened yet */ - dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub, + dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub, &context->bw_ctx.bw.dcn.watermarks, dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000, false); @@ -2175,10 +2176,10 @@ void dcn20_prepare_bandwidth( if (hubbub->funcs->program_compbuf_size) { if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) { compbuf_size_kb = context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes; - dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes); + dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes); } else { compbuf_size_kb = context->bw_ctx.bw.dcn.compbuf_size_kb; - dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb); + dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb); } hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, false); @@ -2344,7 +2345,7 @@ bool dcn20_wait_for_blank_complete( int counter; for (counter = 0; counter < 1000; counter++) { - if (opp->funcs->dpg_is_blanked(opp)) + if (!opp->funcs->dpg_is_pending(opp)) break; udelay(100); @@ -2355,7 +2356,7 @@ bool dcn20_wait_for_blank_complete( return false; } - return true; + return opp->funcs->dpg_is_blanked(opp); } bool dcn20_dmdata_status_done(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index c34c13e1e0a4e..55cf4c9e6aedf 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -663,10 +663,20 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) if (pipe_ctx == NULL) return; - if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) + if (dc_is_hdmi_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) { pipe_ctx->stream_res.stream_enc->funcs->set_avmute( pipe_ctx->stream_res.stream_enc, enable); + + /* Wait for two frame to make sure AV mute is sent out */ + if (enable) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } + } } void dcn30_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c index 3a9cc8ac0c079..093f4387553ce 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c @@ -69,29 +69,6 @@ #define FN(reg_name, field_name) \ hws->shifts->field_name, hws->masks->field_name -static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream, - int opp_cnt) -{ - bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing); - int flow_ctrl_cnt; - - if (opp_cnt >= 2) - hblank_halved = true; - - flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable - - stream->timing.h_border_left - - stream->timing.h_border_right; - - if (hblank_halved) - flow_ctrl_cnt /= 2; - - /* ODM combine 4:1 case */ - if (opp_cnt == 4) - flow_ctrl_cnt /= 2; - - return flow_ctrl_cnt; -} - static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) { struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc; @@ -183,10 +160,6 @@ void dcn314_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx struct pipe_ctx *odm_pipe; int opp_cnt = 0; int opp_inst[MAX_PIPES] = {0}; - bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing)); - struct mpc_dwb_flow_control flow_control; - struct mpc *mpc = dc->res_pool->mpc; - int i; opp_cnt = get_odm_config(pipe_ctx, opp_inst); @@ -199,20 +172,6 @@ void dcn314_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx pipe_ctx->stream_res.tg->funcs->set_odm_bypass( pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing); - rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1; - flow_control.flow_ctrl_mode = 0; - flow_control.flow_ctrl_cnt0 = 0x80; - flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt); - if (mpc->funcs->set_out_rate_control) { - for (i = 0; i < opp_cnt; ++i) { - mpc->funcs->set_out_rate_control( - mpc, opp_inst[i], - true, - rate_control_2x_pclk, - &flow_control); - } - } - for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) { odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control( odm_pipe->stream_res.opp, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index aa36d7a56ca8c..7668229438da2 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -966,29 +966,6 @@ void dcn32_init_hw(struct dc *dc) } } -static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream, - int opp_cnt) -{ - bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing); - int flow_ctrl_cnt; - - if (opp_cnt >= 2) - hblank_halved = true; - - flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable - - stream->timing.h_border_left - - stream->timing.h_border_right; - - if (hblank_halved) - flow_ctrl_cnt /= 2; - - /* ODM combine 4:1 case */ - if (opp_cnt == 4) - flow_ctrl_cnt /= 2; - - return flow_ctrl_cnt; -} - static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) { struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc; @@ -1103,10 +1080,6 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx * struct pipe_ctx *odm_pipe; int opp_cnt = 0; int opp_inst[MAX_PIPES] = {0}; - bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing)); - struct mpc_dwb_flow_control flow_control; - struct mpc *mpc = dc->res_pool->mpc; - int i; opp_cnt = get_odm_config(pipe_ctx, opp_inst); @@ -1119,20 +1092,6 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx * pipe_ctx->stream_res.tg->funcs->set_odm_bypass( pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing); - rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1; - flow_control.flow_ctrl_mode = 0; - flow_control.flow_ctrl_cnt0 = 0x80; - flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt); - if (mpc->funcs->set_out_rate_control) { - for (i = 0; i < opp_cnt; ++i) { - mpc->funcs->set_out_rate_control( - mpc, opp_inst[i], - true, - rate_control_2x_pclk, - &flow_control); - } - } - for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) { odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control( odm_pipe->stream_res.opp, @@ -1156,6 +1115,13 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx * dsc->funcs->dsc_disconnect(dsc); } } + + if (!resource_is_pipe_type(pipe_ctx, DPP_PIPE)) + /* + * blank pattern is generated by OPP, reprogram blank pattern + * due to OPP count change + */ + dc->hwseq->funcs.blank_pixel_data(dc, pipe_ctx, true); } unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div) @@ -1778,3 +1744,26 @@ void dcn32_prepare_bandwidth(struct dc *dc, context->bw_ctx.bw.dcn.clk.p_state_change_support = p_state_change_support; } } + +void dcn32_interdependent_update_lock(struct dc *dc, + struct dc_state *context, bool lock) +{ + unsigned int i; + struct pipe_ctx *pipe; + struct timing_generator *tg; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe = &context->res_ctx.pipe_ctx[i]; + tg = pipe->stream_res.tg; + + if (!resource_is_pipe_type(pipe, OTG_MASTER) || + !tg->funcs->is_tg_enabled(tg) || + dc_state_get_pipe_subvp_type(context, pipe) == SUBVP_PHANTOM) + continue; + + if (lock) + dc->hwss.pipe_control_lock(dc, pipe, true); + else + dc->hwss.pipe_control_lock(dc, pipe, false); + } +} diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h index 069e20bc87c0a..f55c11fc56ec7 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h @@ -129,4 +129,6 @@ bool dcn32_is_pipe_topology_transition_seamless(struct dc *dc, void dcn32_prepare_bandwidth(struct dc *dc, struct dc_state *context); +void dcn32_interdependent_update_lock(struct dc *dc, + struct dc_state *context, bool lock); #endif /* __DC_HWSS_DCN32_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c index e8ac94a005b83..03253faeaeac6 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c @@ -58,7 +58,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .disable_plane = dcn20_disable_plane, .disable_pixel_data = dcn20_disable_pixel_data, .pipe_control_lock = dcn20_pipe_control_lock, - .interdependent_update_lock = dcn10_lock_all_pipes, + .interdependent_update_lock = dcn32_interdependent_update_lock, .cursor_lock = dcn10_cursor_lock, .prepare_bandwidth = dcn32_prepare_bandwidth, .optimize_bandwidth = dcn20_optimize_bandwidth, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index 8b6c49622f3b6..f9dff06e59f5a 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -358,29 +358,6 @@ void dcn35_init_hw(struct dc *dc) } } -static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream, - int opp_cnt) -{ - bool hblank_halved = optc2_is_two_pixels_per_containter(&stream->timing); - int flow_ctrl_cnt; - - if (opp_cnt >= 2) - hblank_halved = true; - - flow_ctrl_cnt = stream->timing.h_total - stream->timing.h_addressable - - stream->timing.h_border_left - - stream->timing.h_border_right; - - if (hblank_halved) - flow_ctrl_cnt /= 2; - - /* ODM combine 4:1 case */ - if (opp_cnt == 4) - flow_ctrl_cnt /= 2; - - return flow_ctrl_cnt; -} - static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) { struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc; @@ -474,10 +451,6 @@ void dcn35_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx * struct pipe_ctx *odm_pipe; int opp_cnt = 0; int opp_inst[MAX_PIPES] = {0}; - bool rate_control_2x_pclk = (pipe_ctx->stream->timing.flags.INTERLACE || optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing)); - struct mpc_dwb_flow_control flow_control; - struct mpc *mpc = dc->res_pool->mpc; - int i; opp_cnt = get_odm_config(pipe_ctx, opp_inst); @@ -490,20 +463,6 @@ void dcn35_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx * pipe_ctx->stream_res.tg->funcs->set_odm_bypass( pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing); - rate_control_2x_pclk = rate_control_2x_pclk || opp_cnt > 1; - flow_control.flow_ctrl_mode = 0; - flow_control.flow_ctrl_cnt0 = 0x80; - flow_control.flow_ctrl_cnt1 = calc_mpc_flow_ctrl_cnt(pipe_ctx->stream, opp_cnt); - if (mpc->funcs->set_out_rate_control) { - for (i = 0; i < opp_cnt; ++i) { - mpc->funcs->set_out_rate_control( - mpc, opp_inst[i], - true, - rate_control_2x_pclk, - &flow_control); - } - } - for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) { odm_pipe->stream_res.opp->funcs->opp_pipe_clock_control( odm_pipe->stream_res.opp, @@ -679,22 +638,43 @@ void dcn35_power_down_on_boot(struct dc *dc) bool dcn35_apply_idle_power_optimizations(struct dc *dc, bool enable) { - struct dc_link *edp_links[MAX_NUM_EDP]; - int i, edp_num; if (dc->debug.dmcub_emulation) return true; if (enable) { - dc_get_edp_links(dc, edp_links, &edp_num); - if (edp_num == 0 || edp_num > 1) - return false; + uint32_t num_active_edp = 0; + int i; for (i = 0; i < dc->current_state->stream_count; ++i) { struct dc_stream_state *stream = dc->current_state->streams[i]; + struct dc_link *link = stream->link; + bool is_psr = link && !link->panel_config.psr.disable_psr && + (link->psr_settings.psr_version == DC_PSR_VERSION_1 || + link->psr_settings.psr_version == DC_PSR_VERSION_SU_1); + bool is_replay = link && link->replay_settings.replay_feature_enabled; + + /* Ignore streams that disabled. */ + if (stream->dpms_off) + continue; + + /* Active external displays block idle optimizations. */ + if (!dc_is_embedded_signal(stream->signal)) + return false; - if (!stream->dpms_off && !dc_is_embedded_signal(stream->signal)) + /* If not PWRSEQ0 can't enter idle optimizations */ + if (link && link->link_index != 0) return false; + + /* Check for panel power features required for idle optimizations. */ + if (!is_psr && !is_replay) + return false; + + num_active_edp += 1; } + + /* If more than one active eDP then disallow. */ + if (num_active_edp > 1) + return false; } // TODO: review other cases when idle optimization is allowed @@ -1019,8 +999,7 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context, if (pipe_ctx->plane_res.dpp) update_state->pg_pipe_res_update[PG_DPP][pipe_ctx->plane_res.hubp->inst] = false; - if ((pipe_ctx->plane_res.dpp || pipe_ctx->stream_res.opp) && - pipe_ctx->plane_res.mpcc_inst >= 0) + if (pipe_ctx->plane_res.dpp || pipe_ctx->stream_res.opp) update_state->pg_pipe_res_update[PG_MPCC][pipe_ctx->plane_res.mpcc_inst] = false; if (pipe_ctx->stream_res.dsc) @@ -1377,3 +1356,75 @@ void dcn35_set_drr(struct pipe_ctx **pipe_ctx, } } } + +static bool should_avoid_empty_tu(struct pipe_ctx *pipe_ctx) +{ + /* Calculate average pixel count per TU, return false if under ~2.00 to + * avoid empty TUs. This is only required for DPIA tunneling as empty TUs + * are legal to generate for native DP links. Assume TU size 64 as there + * is currently no scenario where it's reprogrammed from HW default. + * MTPs have no such limitation, so this does not affect MST use cases. + */ + unsigned int pix_clk_mhz; + unsigned int symclk_mhz; + unsigned int avg_pix_per_tu_x1000; + unsigned int tu_size_bytes = 64; + struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + struct dc_link_settings *link_settings = &pipe_ctx->link_config.dp_link_settings; + const struct dc *dc = pipe_ctx->stream->link->dc; + + if (pipe_ctx->stream->link->ep_type != DISPLAY_ENDPOINT_USB4_DPIA) + return false; + + // Not necessary for MST configurations + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) + return false; + + pix_clk_mhz = timing->pix_clk_100hz / 10000; + + // If this is true, can't block due to dynamic ODM + if (pix_clk_mhz > dc->clk_mgr->bw_params->clk_table.entries[0].dispclk_mhz) + return false; + + switch (link_settings->link_rate) { + case LINK_RATE_LOW: + symclk_mhz = 162; + break; + case LINK_RATE_HIGH: + symclk_mhz = 270; + break; + case LINK_RATE_HIGH2: + symclk_mhz = 540; + break; + case LINK_RATE_HIGH3: + symclk_mhz = 810; + break; + default: + // We shouldn't be tunneling any other rates, something is wrong + ASSERT(0); + return false; + } + + avg_pix_per_tu_x1000 = (1000 * pix_clk_mhz * tu_size_bytes) + / (symclk_mhz * link_settings->lane_count); + + // Add small empirically-decided margin to account for potential jitter + return (avg_pix_per_tu_x1000 < 2020); +} + +bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) +{ + struct dc *dc = pipe_ctx->stream->ctx->dc; + + if (!is_h_timing_divisible_by_2(pipe_ctx->stream)) + return false; + + if (should_avoid_empty_tu(pipe_ctx)) + return false; + + if (dc_is_dp_signal(pipe_ctx->stream->signal) && !dc->link_srv->dp_is_128b_132b_signal(pipe_ctx) && + dc->debug.enable_dp_dig_pixel_rate_div_policy) + return true; + + return false; +} diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h index fd66316e33de3..c26191138a72e 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h @@ -90,4 +90,6 @@ uint32_t dcn35_get_idle_state(const struct dc *dc); void dcn35_set_drr(struct pipe_ctx **pipe_ctx, int num_pipes, struct dc_crtc_timing_adjust adjust); +bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx); + #endif /* __DC_HWSS_DCN35_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c index a630aa77dcec0..d82082c5657c4 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c @@ -158,7 +158,7 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .setup_hpo_hw_control = dcn35_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .set_pixels_per_cycle = dcn32_set_pixels_per_cycle, - .is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy, + .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h index 7617fabbd16ee..0717920812d86 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h @@ -321,6 +321,9 @@ struct opp_funcs { bool (*dpg_is_blanked)( struct output_pixel_processor *opp); + bool (*dpg_is_pending)(struct output_pixel_processor *opp); + + void (*opp_dpg_set_blank_color)( struct output_pixel_processor *opp, const struct tg_color *color); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index 9a00a99317b29..cad3e5f148cf5 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -333,6 +333,7 @@ struct timing_generator_funcs { void (*init_odm)(struct timing_generator *tg); void (*wait_drr_doublebuffer_pending_clear)(struct timing_generator *tg); + void (*wait_odm_doublebuffer_pending_clear)(struct timing_generator *tg); }; #endif diff --git a/drivers/gpu/drm/amd/display/dc/inc/link.h b/drivers/gpu/drm/amd/display/dc/inc/link.h index 26fe81f213da5..bf29fc58ea6a6 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link.h @@ -285,12 +285,12 @@ struct link_service { enum replay_FW_Message_type msg, union dmub_replay_cmd_set *cmd_data); bool (*edp_set_coasting_vtotal)( - struct dc_link *link, uint16_t coasting_vtotal); + struct dc_link *link, uint32_t coasting_vtotal); bool (*edp_replay_residency)(const struct dc_link *link, unsigned int *residency, const bool is_start, const bool is_alpm); bool (*edp_set_replay_power_opt_and_coasting_vtotal)(struct dc_link *link, - const unsigned int *power_opts, uint16_t coasting_vtotal); + const unsigned int *power_opts, uint32_t coasting_vtotal); bool (*edp_wait_for_t12)(struct dc_link *link); bool (*edp_is_ilr_optimization_required)(struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c index 5491b707cec88..5a965c26bf209 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c @@ -270,7 +270,7 @@ static void set_usb4_req_bw_req(struct dc_link *link, int req_bw) /* Error check whether requested and allocated are equal */ req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity); - if (req_bw == link->dpia_bw_alloc_config.allocated_bw) { + if (req_bw && (req_bw == link->dpia_bw_alloc_config.allocated_bw)) { DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n", __func__, link->link_index); } @@ -341,6 +341,14 @@ bool link_dp_dpia_set_dptx_usb4_bw_alloc_support(struct dc_link *link) ret = true; init_usb4_bw_struct(link); link->dpia_bw_alloc_config.bw_alloc_enabled = true; + + /* + * During DP tunnel creation, CM preallocates BW and reduces estimated BW of other + * DPIA. CM release preallocation only when allocation is complete. Do zero alloc + * to make the CM to release preallocation and update estimated BW correctly for + * all DPIAs per host router + */ + link_dp_dpia_allocate_usb4_bandwidth_for_stream(link, 0); } } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index 046d3e2054153..d01b77fb9811a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -892,7 +892,8 @@ bool edp_set_replay_allow_active(struct dc_link *link, const bool *allow_active, /* Set power optimization flag */ if (power_opts && link->replay_settings.replay_power_opt_active != *power_opts) { - if (link->replay_settings.replay_feature_enabled && replay->funcs->replay_set_power_opt) { + if (replay != NULL && link->replay_settings.replay_feature_enabled && + replay->funcs->replay_set_power_opt) { replay->funcs->replay_set_power_opt(replay, *power_opts, panel_inst); link->replay_settings.replay_power_opt_active = *power_opts; } @@ -1033,7 +1034,7 @@ bool edp_send_replay_cmd(struct dc_link *link, return true; } -bool edp_set_coasting_vtotal(struct dc_link *link, uint16_t coasting_vtotal) +bool edp_set_coasting_vtotal(struct dc_link *link, uint32_t coasting_vtotal) { struct dc *dc = link->ctx->dc; struct dmub_replay *replay = dc->res_pool->replay; @@ -1072,7 +1073,7 @@ bool edp_replay_residency(const struct dc_link *link, } bool edp_set_replay_power_opt_and_coasting_vtotal(struct dc_link *link, - const unsigned int *power_opts, uint16_t coasting_vtotal) + const unsigned int *power_opts, uint32_t coasting_vtotal) { struct dc *dc = link->ctx->dc; struct dmub_replay *replay = dc->res_pool->replay; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h index 34e521af7bb48..a158c6234d422 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h @@ -59,12 +59,12 @@ bool edp_setup_replay(struct dc_link *link, bool edp_send_replay_cmd(struct dc_link *link, enum replay_FW_Message_type msg, union dmub_replay_cmd_set *cmd_data); -bool edp_set_coasting_vtotal(struct dc_link *link, uint16_t coasting_vtotal); +bool edp_set_coasting_vtotal(struct dc_link *link, uint32_t coasting_vtotal); bool edp_replay_residency(const struct dc_link *link, unsigned int *residency, const bool is_start, const bool is_alpm); bool edp_get_replay_state(const struct dc_link *link, uint64_t *state); bool edp_set_replay_power_opt_and_coasting_vtotal(struct dc_link *link, - const unsigned int *power_opts, uint16_t coasting_vtotal); + const unsigned int *power_opts, uint32_t coasting_vtotal); bool edp_wait_for_t12(struct dc_link *link); bool edp_is_ilr_optimization_required(struct dc_link *link, struct dc_crtc_timing *crtc_timing); diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h index ab81594a7fadc..6c2e84d3967fc 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h @@ -557,7 +557,8 @@ struct dcn_optc_registers { type OTG_CRC_DATA_STREAM_SPLIT_MODE;\ type OTG_CRC_DATA_FORMAT;\ type OTG_V_TOTAL_LAST_USED_BY_DRR;\ - type OTG_DRR_TIMING_DBUF_UPDATE_PENDING; + type OTG_DRR_TIMING_DBUF_UPDATE_PENDING;\ + type OTG_H_TIMING_DIV_MODE_DB_UPDATE_PENDING; #define TG_REG_FIELD_LIST_DCN3_2(type) \ type OTG_H_TIMING_DIV_MODE_MANUAL; diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c index 8234935433254..52eab8fccb7f1 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c @@ -122,6 +122,13 @@ void optc32_get_odm_combine_segments(struct timing_generator *tg, int *odm_combi } } +void optc32_wait_odm_doublebuffer_pending_clear(struct timing_generator *tg) +{ + struct optc *optc1 = DCN10TG_FROM_TG(tg); + + REG_WAIT(OTG_DOUBLE_BUFFER_CONTROL, OTG_H_TIMING_DIV_MODE_DB_UPDATE_PENDING, 0, 2, 50000); +} + void optc32_set_h_timing_div_manual_mode(struct timing_generator *optc, bool manual_mode) { struct optc *optc1 = DCN10TG_FROM_TG(optc); @@ -260,9 +267,6 @@ static void optc32_setup_manual_trigger(struct timing_generator *optc) OTG_V_TOTAL_MAX_SEL, 1, OTG_FORCE_LOCK_ON_EVENT, 0, OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */ - - // Setup manual flow control for EOF via TRIG_A - optc->funcs->setup_manual_trigger(optc); } } @@ -345,6 +349,7 @@ static struct timing_generator_funcs dcn32_tg_funcs = { .set_odm_bypass = optc32_set_odm_bypass, .set_odm_combine = optc32_set_odm_combine, .get_odm_combine_segments = optc32_get_odm_combine_segments, + .wait_odm_doublebuffer_pending_clear = optc32_wait_odm_doublebuffer_pending_clear, .set_h_timing_div_manual_mode = optc32_set_h_timing_div_manual_mode, .get_optc_source = optc2_get_optc_source, .set_out_mux = optc3_set_out_mux, diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h index 8ce3b178cab06..0c2c146955619 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h @@ -183,5 +183,6 @@ void optc32_set_h_timing_div_manual_mode(struct timing_generator *optc, bool man void optc32_get_odm_combine_segments(struct timing_generator *tg, int *odm_combine_segments); void optc32_set_odm_bypass(struct timing_generator *optc, const struct dc_crtc_timing *dc_crtc_timing); +void optc32_wait_odm_doublebuffer_pending_clear(struct timing_generator *tg); #endif /* __DC_OPTC_DCN32_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c index f9c5bc624be30..f81f6110913d3 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c @@ -2451,6 +2451,7 @@ static bool dcn20_resource_construct( dc->caps.post_blend_color_processing = true; dc->caps.force_dp_tps4_for_cp2520 = true; dc->caps.extended_aux_timeout_support = true; + dc->caps.dmcub_support = true; /* Color pipeline capabilities */ dc->caps.color.dpp.dcn_arch = 1; diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index 6f10052caeef0..9042378fa8dfb 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -1771,6 +1771,7 @@ static bool dml1_validate(struct dc *dc, struct dc_state *context, bool fast_val dc->res_pool->funcs->calculate_wm_and_dlg(dc, context, pipes, pipe_cnt, vlevel); dcn32_override_min_req_memclk(dc, context); + dcn32_override_min_req_dcfclk(dc, context); BW_VAL_TRACE_END_WATERMARKS(); @@ -1930,6 +1931,8 @@ static void dcn32_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw { DC_FP_START(); dcn32_update_bw_bounding_box_fpu(dc, bw_params); + if (dc->debug.using_dml2 && dc->current_state && dc->current_state->bw_ctx.dml2) + dml2_reinit(dc, &dc->dml2_options, &dc->current_state->bw_ctx.dml2); DC_FP_END(); } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h index 0c87b0fabba7d..2258c5c7212d8 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h @@ -42,6 +42,7 @@ #define SUBVP_ACTIVE_MARGIN_LIST_LEN 2 #define DCN3_2_MAX_SUBVP_PIXEL_RATE_MHZ 1800 #define DCN3_2_VMIN_DISPCLK_HZ 717000000 +#define MIN_SUBVP_DCFCLK_KHZ 400000 #define TO_DCN32_RES_POOL(pool)\ container_of(pool, struct dcn32_resource_pool, base) @@ -181,6 +182,8 @@ bool dcn32_subvp_vblank_admissable(struct dc *dc, struct dc_state *context, int void dcn32_update_dml_pipes_odm_policy_based_on_context(struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes); +void dcn32_override_min_req_dcfclk(struct dc *dc, struct dc_state *context); + /* definitions for run time init of reg offsets */ /* CLK SRC */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c index 74412e5f03fef..f4dd6443a3551 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c @@ -1581,6 +1581,8 @@ static void dcn321_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b { DC_FP_START(); dcn321_update_bw_bounding_box_fpu(dc, bw_params); + if (dc->debug.using_dml2 && dc->current_state && dc->current_state->bw_ctx.dml2) + dml2_reinit(dc, &dc->dml2_options, &dc->current_state->bw_ctx.dml2); DC_FP_END(); } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 5fdcda8f86026..78c315541f031 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -701,7 +701,7 @@ static const struct dc_plane_cap plane_cap = { // 6:1 downscaling ratio: 1000/6 = 166.666 .max_downscale_factor = { - .argb8888 = 167, + .argb8888 = 250, .nv12 = 167, .fp16 = 167 }, @@ -782,6 +782,7 @@ static const struct dc_debug_options debug_defaults_drv = { .psp_disabled_wa = true, .ips2_eval_delay_us = 2000, .ips2_entry_delay_us = 800, + .disable_dmub_reallow_idle = true, .static_screen_wait_frames = 2, }; diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index e699731ee68e9..bb1f69a54c148 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -3133,6 +3133,14 @@ struct dmub_cmd_replay_set_coasting_vtotal_data { * Currently the support is only for 0 or 1 */ uint8_t panel_inst; + /** + * 16-bit value dicated by driver that indicates the coasting vtotal high byte part. + */ + uint16_t coasting_vtotal_high; + /** + * Explicit padding to 4 byte boundary. + */ + uint8_t pad[2]; }; /** diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index 8c137d7c032e1..7c9805705fd38 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -513,6 +513,9 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp) hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); + if (!display) + return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND; + hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index; if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0) diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h index 5960dd760e91c..8ce6c22e5d041 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h @@ -57,10 +57,10 @@ void mod_stats_update_event(struct mod_stats *mod_stats, unsigned int length); void mod_stats_update_flip(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_vupdate(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_freesync(struct mod_stats *mod_stats, unsigned int v_total_min, diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index 738ee763f24a5..84f9b412a4f11 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -147,15 +147,12 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream, } /* VSC packet set to 4 for PSR-SU, or 2 for PSR1 */ - if (stream->link->psr_settings.psr_feature_enabled) { - if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) - vsc_packet_revision = vsc_packet_rev4; - else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) - vsc_packet_revision = vsc_packet_rev2; - } - - if (stream->link->replay_settings.config.replay_supported) + if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) + vsc_packet_revision = vsc_packet_rev4; + else if (stream->link->replay_settings.config.replay_supported) vsc_packet_revision = vsc_packet_rev4; + else if (stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) + vsc_packet_revision = vsc_packet_rev2; /* Update to revision 5 for extended colorimetry support */ if (stream->use_vsc_sdp_for_colorimetry) diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index e304e8435fb8f..2a3698fd2dc24 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -975,7 +975,7 @@ bool psr_su_set_dsc_slice_height(struct dc *dc, struct dc_link *link, void set_replay_coasting_vtotal(struct dc_link *link, enum replay_coasting_vtotal_type type, - uint16_t vtotal) + uint32_t vtotal) { link->replay_settings.coasting_vtotal_table[type] = vtotal; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h index bef4815e1703d..ff7e6f3cd6be2 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h @@ -56,7 +56,7 @@ bool dmub_init_abm_config(struct resource_pool *res_pool, void init_replay_config(struct dc_link *link, struct replay_config *pr_config); void set_replay_coasting_vtotal(struct dc_link *link, enum replay_coasting_vtotal_type type, - uint16_t vtotal); + uint32_t vtotal); void set_replay_ips_full_screen_video_src_vtotal(struct dc_link *link, uint16_t vtotal); void calculate_replay_link_off_frame_count(struct dc_link *link, uint16_t vtotal, uint16_t htotal); diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index fa7d6ced786f1..c618edc3f4ff2 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -1625,6 +1625,49 @@ struct atom_integrated_system_info_v2_2 uint32_t reserved4[189]; }; +struct uma_carveout_option { + char optionName[29]; //max length of string is 28chars + '\0'. Current design is for "minimum", "Medium", "High". This makes entire struct size 64bits + uint8_t memoryCarvedGb; //memory carved out with setting + uint8_t memoryRemainingGb; //memory remaining on system + union { + struct _flags { + uint8_t Auto : 1; + uint8_t Custom : 1; + uint8_t Reserved : 6; + } flags; + uint8_t all8; + } uma_carveout_option_flags; +}; + +struct atom_integrated_system_info_v2_3 { + struct atom_common_table_header table_header; + uint32_t vbios_misc; // enum of atom_system_vbiosmisc_def + uint32_t gpucapinfo; // enum of atom_system_gpucapinf_def + uint32_t system_config; + uint32_t cpucapinfo; + uint16_t gpuclk_ss_percentage; // unit of 0.001%, 1000 mean 1% + uint16_t gpuclk_ss_type; + uint16_t dpphy_override; // bit vector, enum of atom_sysinfo_dpphy_override_def + uint8_t memorytype; // enum of atom_dmi_t17_mem_type_def, APU memory type indication. + uint8_t umachannelnumber; // number of memory channels + uint8_t htc_hyst_limit; + uint8_t htc_tmp_limit; + uint8_t reserved1; // dp_ss_control + uint8_t gpu_package_id; + struct edp_info_table edp1_info; + struct edp_info_table edp2_info; + uint32_t reserved2[8]; + struct atom_external_display_connection_info extdispconninfo; + uint8_t UMACarveoutVersion; + uint8_t UMACarveoutIndexMax; + uint8_t UMACarveoutTypeDefault; + uint8_t UMACarveoutIndexDefault; + uint8_t UMACarveoutType; //Auto or Custom + uint8_t UMACarveoutIndex; + struct uma_carveout_option UMASizeControlOption[20]; + uint8_t reserved3[110]; +}; + // system_config enum atom_system_vbiosmisc_def{ INTEGRATED_SYSTEM_INFO__GET_EDID_CALLBACK_FUNC_SUPPORT = 0x01, diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 39c5e1dfa275a..b4698f9856006 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -4217,6 +4217,13 @@ static int amdgpu_od_set_init(struct amdgpu_device *adev) } } + /* + * If gpu_od is the only member in the list, that means gpu_od is an + * empty directory, so remove it. + */ + if (list_is_singular(&adev->pm.od_kobj_list)) + goto err_out; + return 0; err_out: diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 5cb4725c773f6..c8586cb7d0fec 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -164,6 +164,8 @@ static void sumo_construct_vid_mapping_table(struct amdgpu_device *adev, for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) { if (table[i].ulSupportedSCLK != 0) { + if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES) + continue; vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit = table[i].usVoltageID; vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit = diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 0ad947df777ab..ba1597b01a970 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -734,7 +734,7 @@ static int smu_early_init(void *handle) smu->adev = adev; smu->pm_enabled = !!amdgpu_dpm; smu->is_apu = false; - smu->smu_baco.state = SMU_BACO_STATE_EXIT; + smu->smu_baco.state = SMU_BACO_STATE_NONE; smu->smu_baco.platform_support = false; smu->user_dpm_profile.fan_mode = -1; @@ -1954,10 +1954,25 @@ static int smu_smc_hw_cleanup(struct smu_context *smu) return 0; } +static int smu_reset_mp1_state(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int ret = 0; + + if ((!adev->in_runpm) && (!adev->in_suspend) && + (!amdgpu_in_reset(adev)) && amdgpu_ip_version(adev, MP1_HWIP, 0) == + IP_VERSION(13, 0, 10) && + !amdgpu_device_has_display_hardware(adev)) + ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD); + + return ret; +} + static int smu_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct smu_context *smu = adev->powerplay.pp_handle; + int ret; if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) return 0; @@ -1975,7 +1990,15 @@ static int smu_hw_fini(void *handle) adev->pm.dpm_enabled = false; - return smu_smc_hw_cleanup(smu); + ret = smu_smc_hw_cleanup(smu); + if (ret) + return ret; + + ret = smu_reset_mp1_state(smu); + if (ret) + return ret; + + return 0; } static void smu_late_fini(void *handle) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 66e84defd0b6e..2aa4fea873147 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -424,6 +424,7 @@ enum smu_reset_mode { enum smu_baco_state { SMU_BACO_STATE_ENTER = 0, SMU_BACO_STATE_EXIT, + SMU_BACO_STATE_NONE, }; struct smu_baco_context { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index bcad42534da46..40ba7227cca58 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -1285,8 +1285,9 @@ static int arcturus_get_power_limit(struct smu_context *smu, { struct smu_11_0_powerplay_table *powerplay_table = (struct smu_11_0_powerplay_table *)smu->smu_table.power_play_table; + struct smu_11_0_overdrive_table *od_settings = smu->od_settings; PPTable_t *pptable = smu->smu_table.driver_pptable; - uint32_t power_limit, od_percent_upper, od_percent_lower; + uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; if (smu_v11_0_get_current_power_limit(smu, &power_limit)) { /* the last hope to figure out the ppt limit */ @@ -1303,12 +1304,16 @@ static int arcturus_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) - od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - else - od_percent_upper = 0; - - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + if (powerplay_table) { + if (smu->od_enabled && + od_settings->cap[SMU_11_0_ODCAP_POWER_LIMIT]) { + od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + } else if (od_settings->cap[SMU_11_0_ODCAP_POWER_LIMIT]) { + od_percent_upper = 0; + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + } + } dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); @@ -2272,8 +2277,8 @@ static uint16_t arcturus_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (uint16_t)(((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (uint16_t)(((esm_ctrl >> 8) & 0x7F) + 128); return smu_v11_0_get_current_pcie_link_speed(smu); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index ed189a3878ebe..836b1df799286 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2339,7 +2339,7 @@ static int navi10_get_power_limit(struct smu_context *smu, (struct smu_11_0_powerplay_table *)smu->smu_table.power_play_table; struct smu_11_0_overdrive_table *od_settings = smu->od_settings; PPTable_t *pptable = smu->smu_table.driver_pptable; - uint32_t power_limit, od_percent_upper, od_percent_lower; + uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; if (smu_v11_0_get_current_power_limit(smu, &power_limit)) { /* the last hope to figure out the ppt limit */ @@ -2356,13 +2356,16 @@ static int navi10_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled && - navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) - od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - else - od_percent_upper = 0; - - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + if (powerplay_table) { + if (smu->od_enabled && + navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) { + od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + } else if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) { + od_percent_upper = 0; + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + } + } dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index e2ad2b972ab0b..1f18b61884f3f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -617,6 +617,12 @@ static uint32_t sienna_cichlid_get_throttler_status_locked(struct smu_context *s return throttler_status; } +static bool sienna_cichlid_is_od_feature_supported(struct smu_11_0_7_overdrive_table *od_table, + enum SMU_11_0_7_ODFEATURE_CAP cap) +{ + return od_table->cap[cap]; +} + static int sienna_cichlid_get_power_limit(struct smu_context *smu, uint32_t *current_power_limit, uint32_t *default_power_limit, @@ -625,7 +631,8 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu, { struct smu_11_0_7_powerplay_table *powerplay_table = (struct smu_11_0_7_powerplay_table *)smu->smu_table.power_play_table; - uint32_t power_limit, od_percent_upper, od_percent_lower; + struct smu_11_0_7_overdrive_table *od_settings = smu->od_settings; + uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; uint16_t *table_member; GET_PPTABLE_MEMBER(SocketPowerLimitAc, &table_member); @@ -640,12 +647,16 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) - od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); - else - od_percent_upper = 0; - - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); + if (powerplay_table) { + if (smu->od_enabled && + sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_POWER_LIMIT)) { + od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); + } else if ((sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_POWER_LIMIT))) { + od_percent_upper = 0; + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); + } + } dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); @@ -1250,12 +1261,6 @@ static bool sienna_cichlid_is_support_fine_grained_dpm(struct smu_context *smu, return dpm_desc->SnapToDiscrete == 0; } -static bool sienna_cichlid_is_od_feature_supported(struct smu_11_0_7_overdrive_table *od_table, - enum SMU_11_0_7_ODFEATURE_CAP cap) -{ - return od_table->cap[cap]; -} - static void sienna_cichlid_get_od_setting_range(struct smu_11_0_7_overdrive_table *od_table, enum SMU_11_0_7_ODSETTING_ID setting, uint32_t *min, uint32_t *max) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index dd9bcbd630a1f..ca0d5a5b204ad 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1682,8 +1682,8 @@ static int aldebaran_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (((esm_ctrl >> 8) & 0x7F) + 128); return smu_v13_0_get_current_pcie_link_speed(smu); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 9b80f18ea6c35..67117ced7c6ae 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2356,7 +2356,7 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu, (struct smu_13_0_0_powerplay_table *)table_context->power_play_table; PPTable_t *pptable = table_context->driver_pptable; SkuTable_t *skutable = &pptable->SkuTable; - uint32_t power_limit, od_percent_upper, od_percent_lower; + uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC]; if (smu_v13_0_get_current_power_limit(smu, &power_limit)) @@ -2369,12 +2369,16 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) - od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); - else - od_percent_upper = 0; - - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); + if (powerplay_table) { + if (smu->od_enabled && + smu_v13_0_0_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) { + od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); + } else if (smu_v13_0_0_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) { + od_percent_upper = 0; + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); + } + } dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); @@ -2747,7 +2751,13 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu, switch (mp1_state) { case PP_MP1_STATE_UNLOAD: - ret = smu_cmn_set_mp1_state(smu, mp1_state); + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_PrepareMp1ForUnload, + 0x55, NULL); + + if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT) + ret = smu_v13_0_disable_pmfw_state(smu); + break; default: /* Ignore others */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index bb98156b2fa1d..2fb6c9cb0f143 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -226,8 +226,20 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en) struct amdgpu_device *adev = smu->adev; int ret = 0; - if (!en && !adev->in_s0ix) + if (!en && !adev->in_s0ix) { + if (adev->in_s4) { + /* Adds a GFX reset as workaround just before sending the + * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering + * an invalid state. + */ + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, + SMU_RESET_MODE_2, NULL); + if (ret) + return ret; + } + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); + } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 7e1941cf17964..ddb11eb8c3f53 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -2060,8 +2060,8 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu) /* TODO: confirm this on real target */ esm_ctrl = RREG32_PCIE(smnPCIE_ESM_CTRL); - if ((esm_ctrl >> 15) & 0x1FFFF) - return (((esm_ctrl >> 8) & 0x3F) + 128); + if ((esm_ctrl >> 15) & 0x1) + return (((esm_ctrl >> 8) & 0x7F) + 128); speed_level = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) & PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK) @@ -2205,6 +2205,17 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table return sizeof(*gpu_metrics); } +static void smu_v13_0_6_restore_pci_config(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int i; + + for (i = 0; i < 16; i++) + pci_write_config_dword(adev->pdev, i * 4, + adev->pdev->saved_config_space[i]); + pci_restore_msi_state(adev->pdev); +} + static int smu_v13_0_6_mode2_reset(struct smu_context *smu) { int ret = 0, index; @@ -2226,6 +2237,20 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu) /* Restore the config space saved during init */ amdgpu_device_load_pci_state(adev->pdev); + /* Certain platforms have switches which assign virtual BAR values to + * devices. OS uses the virtual BAR values and device behind the switch + * is assgined another BAR value. When device's config space registers + * are queried, switch returns the virtual BAR values. When mode-2 reset + * is performed, switch is unaware of it, and will continue to return + * the same virtual values to the OS.This affects + * pci_restore_config_space() API as it doesn't write the value saved if + * the current value read from config space is the same as what is + * saved. As a workaround, make sure the config space is restored + * always. + */ + if (!(adev->flags & AMD_IS_APU)) + smu_v13_0_6_restore_pci_config(smu); + dev_dbg(smu->adev->dev, "wait for reset ack\n"); do { ret = smu_cmn_wait_for_response(smu); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 3dc7b60cb0754..7318964f1f148 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2320,7 +2320,7 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu, (struct smu_13_0_7_powerplay_table *)table_context->power_play_table; PPTable_t *pptable = table_context->driver_pptable; SkuTable_t *skutable = &pptable->SkuTable; - uint32_t power_limit, od_percent_upper, od_percent_lower; + uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0; uint32_t msg_limit = skutable->MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC]; if (smu_v13_0_get_current_power_limit(smu, &power_limit)) @@ -2333,12 +2333,16 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) - od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); - else - od_percent_upper = 0; - - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); + if (powerplay_table) { + if (smu->od_enabled && + (smu_v13_0_7_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT))) { + od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); + } else if (smu_v13_0_7_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) { + od_percent_upper = 0; + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); + } + } dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c index f3e744172673c..f4e76b46ca327 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c @@ -259,7 +259,7 @@ komeda_component_get_avail_scaler(struct komeda_component *c, u32 avail_scalers; pipe_st = komeda_pipeline_get_state(c->pipeline, state); - if (!pipe_st) + if (IS_ERR_OR_NULL(pipe_st)) return NULL; avail_scalers = (pipe_st->active_comps & KOMEDA_PIPELINE_SCALERS) ^ diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c index 626709bec6f5f..2577f0cef8fcd 100644 --- a/drivers/gpu/drm/arm/malidp_mw.c +++ b/drivers/gpu/drm/arm/malidp_mw.c @@ -72,7 +72,10 @@ static void malidp_mw_connector_reset(struct drm_connector *connector) __drm_atomic_helper_connector_destroy_state(connector->state); kfree(connector->state); - __drm_atomic_helper_connector_reset(connector, &mw_state->base); + connector->state = NULL; + + if (mw_state) + __drm_atomic_helper_connector_reset(connector, &mw_state->base); } static enum drm_connector_status diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c index ebb6d8ebd44eb..1e9259416980e 100644 --- a/drivers/gpu/drm/ast/ast_dp.c +++ b/drivers/gpu/drm/ast/ast_dp.c @@ -180,6 +180,7 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on) { struct ast_device *ast = to_ast_device(dev); u8 video_on_off = on; + u32 i = 0; // Video On/Off ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xE3, (u8) ~AST_DP_VIDEO_ENABLE, on); @@ -192,6 +193,8 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on) ASTDP_MIRROR_VIDEO_ENABLE) != video_on_off) { // wait 1 ms mdelay(1); + if (++i > 200) + break; } } } diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 8be235144f6d9..6fc292393c674 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1277,17 +1277,6 @@ static int adv7511_probe(struct i2c_client *i2c) INIT_WORK(&adv7511->hpd_work, adv7511_hpd_work); - if (i2c->irq) { - init_waitqueue_head(&adv7511->wq); - - ret = devm_request_threaded_irq(dev, i2c->irq, NULL, - adv7511_irq_handler, - IRQF_ONESHOT, dev_name(dev), - adv7511); - if (ret) - goto err_unregister_cec; - } - adv7511_power_off(adv7511); i2c_set_clientdata(i2c, adv7511); @@ -1311,6 +1300,17 @@ static int adv7511_probe(struct i2c_client *i2c) adv7511_audio_init(dev, adv7511); + if (i2c->irq) { + init_waitqueue_head(&adv7511->wq); + + ret = devm_request_threaded_irq(dev, i2c->irq, NULL, + adv7511_irq_handler, + IRQF_ONESHOT, dev_name(dev), + adv7511); + if (ret) + goto err_unregister_audio; + } + if (adv7511->info->has_dsi) { ret = adv7533_attach_dsi(adv7511); if (ret) diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 29d91493b101a..c1191ef5e8e67 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -2076,10 +2076,8 @@ static int anx7625_setup_dsi_device(struct anx7625_data *ctx) }; host = of_find_mipi_dsi_host_by_node(ctx->pdata.mipi_host_node); - if (!host) { - DRM_DEV_ERROR(dev, "fail to find dsi host.\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "fail to find dsi host.\n"); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { @@ -2481,15 +2479,22 @@ static void anx7625_bridge_atomic_disable(struct drm_bridge *bridge, mutex_unlock(&ctx->aux_lock); } +static void +anx7625_audio_update_connector_status(struct anx7625_data *ctx, + enum drm_connector_status status); + static enum drm_connector_status anx7625_bridge_detect(struct drm_bridge *bridge) { struct anx7625_data *ctx = bridge_to_anx7625(bridge); struct device *dev = ctx->dev; + enum drm_connector_status status; DRM_DEV_DEBUG_DRIVER(dev, "drm bridge detect\n"); - return anx7625_sink_detect(ctx); + status = anx7625_sink_detect(ctx); + anx7625_audio_update_connector_status(ctx, status); + return status; } static struct edid *anx7625_bridge_get_edid(struct drm_bridge *bridge, diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c index 7d470527455b1..bab8844c6fefb 100644 --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c @@ -2057,6 +2057,9 @@ static void cdns_mhdp_atomic_enable(struct drm_bridge *bridge, mhdp_state = to_cdns_mhdp_bridge_state(new_state); mhdp_state->current_mode = drm_mode_duplicate(bridge->dev, mode); + if (!mhdp_state->current_mode) + return; + drm_mode_set_name(mhdp_state->current_mode); dev_dbg(mhdp->dev, "%s: Enabling mode %s\n", __func__, mode->name); diff --git a/drivers/gpu/drm/bridge/chipone-icn6211.c b/drivers/gpu/drm/bridge/chipone-icn6211.c index 82d23e4df09eb..ff3284b6b1a37 100644 --- a/drivers/gpu/drm/bridge/chipone-icn6211.c +++ b/drivers/gpu/drm/bridge/chipone-icn6211.c @@ -563,10 +563,8 @@ static int chipone_dsi_host_attach(struct chipone *icn) host = of_find_mipi_dsi_host_by_node(host_node); of_node_put(host_node); - if (!host) { - dev_err(dev, "failed to find dsi host\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n"); dsi = mipi_dsi_device_register_full(host, &info); if (IS_ERR(dsi)) { diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 273157428c827..0b5b98d3e5f6f 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -440,26 +440,24 @@ lt8912_connector_mode_valid(struct drm_connector *connector, static int lt8912_connector_get_modes(struct drm_connector *connector) { - struct edid *edid; - int ret = -1; - int num = 0; + const struct drm_edid *drm_edid; struct lt8912 *lt = connector_to_lt8912(connector); u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24; + int ret, num; - edid = drm_bridge_get_edid(lt->hdmi_port, connector); - if (edid) { - drm_connector_update_edid_property(connector, edid); - num = drm_add_edid_modes(connector, edid); - } else { - return ret; - } + drm_edid = drm_bridge_edid_read(lt->hdmi_port, connector); + drm_edid_connector_update(connector, drm_edid); + if (!drm_edid) + return 0; + + num = drm_edid_connector_add_modes(connector); ret = drm_display_info_set_bus_formats(&connector->display_info, &bus_format, 1); - if (ret) - num = ret; + if (ret < 0) + num = 0; - kfree(edid); + drm_edid_free(drm_edid); return num; } @@ -496,10 +494,8 @@ static int lt8912_attach_dsi(struct lt8912 *lt) }; host = of_find_mipi_dsi_host_by_node(lt->host_node); - if (!host) { - dev_err(dev, "failed to find dsi host\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n"); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 9663601ce0981..89bdd938757e1 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -760,10 +760,8 @@ static struct mipi_dsi_device *lt9611_attach_dsi(struct lt9611 *lt9611, int ret; host = of_find_mipi_dsi_host_by_node(dsi_node); - if (!host) { - dev_err(lt9611->dev, "failed to find dsi host\n"); - return ERR_PTR(-EPROBE_DEFER); - } + if (!host) + return ERR_PTR(dev_err_probe(lt9611->dev, -EPROBE_DEFER, "failed to find dsi host\n")); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c index e971b75e90ad0..b803899126d54 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c @@ -265,10 +265,8 @@ static struct mipi_dsi_device *lt9611uxc_attach_dsi(struct lt9611uxc *lt9611uxc, int ret; host = of_find_mipi_dsi_host_by_node(dsi_node); - if (!host) { - dev_err(dev, "failed to find dsi host\n"); - return ERR_PTR(-EPROBE_DEFER); - } + if (!host) + return ERR_PTR(dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n")); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c index 7f41525f7a6e6..3d6e8f096a5d4 100644 --- a/drivers/gpu/drm/bridge/panel.c +++ b/drivers/gpu/drm/bridge/panel.c @@ -358,9 +358,12 @@ EXPORT_SYMBOL(drm_panel_bridge_set_orientation); static void devm_drm_panel_bridge_release(struct device *dev, void *res) { - struct drm_bridge **bridge = res; + struct drm_bridge *bridge = *(struct drm_bridge **)res; - drm_panel_bridge_remove(*bridge); + if (!bridge) + return; + + drm_bridge_remove(bridge); } /** diff --git a/drivers/gpu/drm/bridge/tc358775.c b/drivers/gpu/drm/bridge/tc358775.c index 90a89d70d8328..c737670631929 100644 --- a/drivers/gpu/drm/bridge/tc358775.c +++ b/drivers/gpu/drm/bridge/tc358775.c @@ -454,10 +454,6 @@ static void tc_bridge_enable(struct drm_bridge *bridge) dev_dbg(tc->dev, "bus_formats %04x bpc %d\n", connector->display_info.bus_formats[0], tc->bpc); - /* - * Default hardware register settings of tc358775 configured - * with MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA jeida-24 format - */ if (connector->display_info.bus_formats[0] == MEDIA_BUS_FMT_RGB888_1X7X4_SPWG) { /* VESA-24 */ @@ -468,14 +464,15 @@ static void tc_bridge_enable(struct drm_bridge *bridge) d2l_write(tc->i2c, LV_MX1619, LV_MX(LVI_B6, LVI_B7, LVI_B1, LVI_B2)); d2l_write(tc->i2c, LV_MX2023, LV_MX(LVI_B3, LVI_B4, LVI_B5, LVI_L0)); d2l_write(tc->i2c, LV_MX2427, LV_MX(LVI_HS, LVI_VS, LVI_DE, LVI_R6)); - } else { /* MEDIA_BUS_FMT_RGB666_1X7X3_SPWG - JEIDA-18 */ - d2l_write(tc->i2c, LV_MX0003, LV_MX(LVI_R0, LVI_R1, LVI_R2, LVI_R3)); - d2l_write(tc->i2c, LV_MX0407, LV_MX(LVI_R4, LVI_L0, LVI_R5, LVI_G0)); - d2l_write(tc->i2c, LV_MX0811, LV_MX(LVI_G1, LVI_G2, LVI_L0, LVI_L0)); - d2l_write(tc->i2c, LV_MX1215, LV_MX(LVI_G3, LVI_G4, LVI_G5, LVI_B0)); - d2l_write(tc->i2c, LV_MX1619, LV_MX(LVI_L0, LVI_L0, LVI_B1, LVI_B2)); - d2l_write(tc->i2c, LV_MX2023, LV_MX(LVI_B3, LVI_B4, LVI_B5, LVI_L0)); - d2l_write(tc->i2c, LV_MX2427, LV_MX(LVI_HS, LVI_VS, LVI_DE, LVI_L0)); + } else { + /* JEIDA-18 and JEIDA-24 */ + d2l_write(tc->i2c, LV_MX0003, LV_MX(LVI_R2, LVI_R3, LVI_R4, LVI_R5)); + d2l_write(tc->i2c, LV_MX0407, LV_MX(LVI_R6, LVI_R1, LVI_R7, LVI_G2)); + d2l_write(tc->i2c, LV_MX0811, LV_MX(LVI_G3, LVI_G4, LVI_G0, LVI_G1)); + d2l_write(tc->i2c, LV_MX1215, LV_MX(LVI_G5, LVI_G6, LVI_G7, LVI_B2)); + d2l_write(tc->i2c, LV_MX1619, LV_MX(LVI_B0, LVI_B1, LVI_B3, LVI_B4)); + d2l_write(tc->i2c, LV_MX2023, LV_MX(LVI_B5, LVI_B6, LVI_B7, LVI_L0)); + d2l_write(tc->i2c, LV_MX2427, LV_MX(LVI_HS, LVI_VS, LVI_DE, LVI_R0)); } d2l_write(tc->i2c, VFUEN, VFUEN_EN); @@ -610,10 +607,8 @@ static int tc_attach_host(struct tc_data *tc) }; host = of_find_mipi_dsi_host_by_node(tc->host_node); - if (!host) { - dev_err(dev, "failed to find dsi host\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n"); dsi = devm_mipi_dsi_device_register_full(dev, host, &info); if (IS_ERR(dsi)) { diff --git a/drivers/gpu/drm/bridge/ti-dlpc3433.c b/drivers/gpu/drm/bridge/ti-dlpc3433.c index ca3348109bcd2..6b559e0713012 100644 --- a/drivers/gpu/drm/bridge/ti-dlpc3433.c +++ b/drivers/gpu/drm/bridge/ti-dlpc3433.c @@ -319,12 +319,11 @@ static int dlpc_host_attach(struct dlpc *dlpc) .channel = 0, .node = NULL, }; + int ret; host = of_find_mipi_dsi_host_by_node(dlpc->host_node); - if (!host) { - DRM_DEV_ERROR(dev, "failed to find dsi host\n"); - return -EPROBE_DEFER; - } + if (!host) + return dev_err_probe(dev, -EPROBE_DEFER, "failed to find dsi host\n"); dlpc->dsi = mipi_dsi_device_register_full(host, &info); if (IS_ERR(dlpc->dsi)) { @@ -336,7 +335,11 @@ static int dlpc_host_attach(struct dlpc *dlpc) dlpc->dsi->format = MIPI_DSI_FMT_RGB565; dlpc->dsi->lanes = dlpc->dsi_lanes; - return devm_mipi_dsi_attach(dev, dlpc->dsi); + ret = devm_mipi_dsi_attach(dev, dlpc->dsi); + if (ret) + DRM_DEV_ERROR(dev, "failed to attach dsi host\n"); + + return ret; } static int dlpc3433_probe(struct i2c_client *client) @@ -367,10 +370,8 @@ static int dlpc3433_probe(struct i2c_client *client) drm_bridge_add(&dlpc->bridge); ret = dlpc_host_attach(dlpc); - if (ret) { - DRM_DEV_ERROR(dev, "failed to attach dsi host\n"); + if (ret) goto err_remove_bridge; - } return 0; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 4814b7b6d1fd1..57a7ed13f9965 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -478,7 +478,6 @@ static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, dev_err(ctx->dev, "failed to lock PLL, ret=%i\n", ret); /* On failure, disable PLL again and exit. */ regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); - regulator_disable(ctx->vcc); return; } diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 62cc3893dca5d..1f6e929c2f6a3 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1591,7 +1591,6 @@ static int ti_sn_pwm_probe(struct auxiliary_device *adev, pdata->pchip.ops = &ti_sn_pwm_ops; pdata->pchip.npwm = 1; pdata->pchip.of_xlate = of_pwm_single_xlate; - pdata->pchip.of_pwm_n_cells = 1; devm_pm_runtime_enable(&adev->dev); diff --git a/drivers/gpu/drm/ci/gitlab-ci.yml b/drivers/gpu/drm/ci/gitlab-ci.yml index dac92cc2777cc..084e3ff8e3f42 100644 --- a/drivers/gpu/drm/ci/gitlab-ci.yml +++ b/drivers/gpu/drm/ci/gitlab-ci.yml @@ -1,6 +1,6 @@ variables: DRM_CI_PROJECT_PATH: &drm-ci-project-path mesa/mesa - DRM_CI_COMMIT_SHA: &drm-ci-commit-sha edfbf74df1d4d6ce54ffe24566108be0e1a98c3d + DRM_CI_COMMIT_SHA: &drm-ci-commit-sha 9d162de9a05155e1c4041857a5848842749164cf UPSTREAM_REPO: git://anongit.freedesktop.org/drm/drm TARGET_BRANCH: drm-next @@ -25,7 +25,9 @@ variables: # per-job artifact storage on MinIO JOB_ARTIFACTS_BASE: ${PIPELINE_ARTIFACTS_BASE}/${CI_JOB_ID} # default kernel for rootfs before injecting the current kernel tree - KERNEL_IMAGE_BASE: https://${S3_HOST}/mesa-lava/gfx-ci/linux/v6.4.12-for-mesa-ci-f6b4ad45f48d + KERNEL_REPO: "gfx-ci/linux" + KERNEL_TAG: "v6.6.4-for-mesa-ci-e4f4c500f7fb" + KERNEL_IMAGE_BASE: https://${S3_HOST}/mesa-lava/${KERNEL_REPO}/${KERNEL_TAG} LAVA_TAGS: subset-1-gfx LAVA_JOB_PRIORITY: 30 @@ -133,6 +135,11 @@ stages: - if: &is-pre-merge-for-marge '$GITLAB_USER_LOGIN == "marge-bot" && $CI_PIPELINE_SOURCE == "merge_request_event"' when: on_success +.never-post-merge-rules: + rules: + - if: *is-post-merge + when: never + # Rule to filter for only scheduled pipelines. .scheduled_pipeline-rules: rules: @@ -150,6 +157,7 @@ stages: .build-rules: rules: - !reference [.no_scheduled_pipelines-rules, rules] + - !reference [.never-post-merge-rules, rules] # Run automatically once all dependency jobs have passed - when: on_success @@ -157,6 +165,7 @@ stages: .container+build-rules: rules: - !reference [.no_scheduled_pipelines-rules, rules] + - !reference [.never-post-merge-rules, rules] - when: manual .ci-deqp-artifacts: @@ -175,6 +184,7 @@ stages: .container-rules: rules: - !reference [.no_scheduled_pipelines-rules, rules] + - !reference [.never-post-merge-rules, rules] # Run pipeline by default in the main project if any CI pipeline # configuration files were changed, to ensure docker images are up to date - if: *is-post-merge diff --git a/drivers/gpu/drm/ci/test.yml b/drivers/gpu/drm/ci/test.yml index 2c9a1838e7284..da381257e7e54 100644 --- a/drivers/gpu/drm/ci/test.yml +++ b/drivers/gpu/drm/ci/test.yml @@ -104,7 +104,10 @@ msm:apq8016: DRIVER_NAME: msm BM_DTB: https://${PIPELINE_ARTIFACTS_BASE}/arm64/apq8016-sbc-usb-host.dtb GPU_VERSION: apq8016 - BM_CMDLINE: "ip=dhcp console=ttyMSM0,115200n8 $BM_KERNEL_EXTRA_ARGS root=/dev/nfs rw nfsrootdebug nfsroot=,tcp,nfsvers=4.2 init=/init $BM_KERNELARGS" + # disabling unused clocks congests with the MDSS runtime PM trying to + # disable those clocks and causes boot to fail. + # Reproducer: DRM_MSM=y, DRM_I2C_ADV7511=m + BM_KERNEL_EXTRA_ARGS: clk_ignore_unused RUNNER_TAG: google-freedreno-db410c script: - ./install/bare-metal/fastboot.sh @@ -234,11 +237,11 @@ i915:cml: i915:tgl: extends: - .i915 - parallel: 8 + parallel: 5 variables: - DEVICE_TYPE: asus-cx9400-volteer + DEVICE_TYPE: acer-cp514-2h-1130g7-volteer GPU_VERSION: tgl - RUNNER_TAG: mesa-ci-x86-64-lava-asus-cx9400-volteer + RUNNER_TAG: mesa-ci-x86-64-lava-acer-cp514-2h-1130g7-volteer .amdgpu: extends: @@ -324,6 +327,7 @@ virtio_gpu:none: GPU_VERSION: none extends: - .test-gl + - .test-rules tags: - kvm script: diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index b1ca3a1100dab..fb80843e7f2df 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -532,6 +532,15 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, mutex_lock(&aux->hw_mutex); + /* + * If the device attached to the aux bus is powered down then there's + * no reason to attempt a transfer. Error out immediately. + */ + if (aux->powered_down) { + ret = -EBUSY; + goto unlock; + } + /* * The specification doesn't give any recommendation on how often to * retry native transactions. We used to retry 7 times like for @@ -599,6 +608,29 @@ int drm_dp_dpcd_probe(struct drm_dp_aux *aux, unsigned int offset) } EXPORT_SYMBOL(drm_dp_dpcd_probe); +/** + * drm_dp_dpcd_set_powered() - Set whether the DP device is powered + * @aux: DisplayPort AUX channel; for convenience it's OK to pass NULL here + * and the function will be a no-op. + * @powered: true if powered; false if not + * + * If the endpoint device on the DP AUX bus is known to be powered down + * then this function can be called to make future transfers fail immediately + * instead of needing to time out. + * + * If this function is never called then a device defaults to being powered. + */ +void drm_dp_dpcd_set_powered(struct drm_dp_aux *aux, bool powered) +{ + if (!aux) + return; + + mutex_lock(&aux->hw_mutex); + aux->powered_down = !powered; + mutex_unlock(&aux->hw_mutex); +} +EXPORT_SYMBOL(drm_dp_dpcd_set_powered); + /** * drm_dp_dpcd_read() - read a series of bytes from the DPCD * @aux: DisplayPort AUX channel (SST or MST) @@ -1858,6 +1890,9 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, struct drm_dp_aux_msg msg; int err = 0; + if (aux->powered_down) + return -EBUSY; + dp_aux_i2c_transfer_size = clamp(dp_aux_i2c_transfer_size, 1, DP_AUX_MAX_PAYLOAD_BYTES); memset(&msg, 0, sizeof(msg)); @@ -3982,6 +4017,13 @@ int drm_dp_bw_overhead(int lane_count, int hactive, u32 overhead = 1000000; int symbol_cycles; + if (lane_count == 0 || hactive == 0 || bpp_x16 == 0) { + DRM_DEBUG_KMS("Invalid BW overhead params: lane_count %d, hactive %d, bpp_x16 %d.%04d\n", + lane_count, hactive, + bpp_x16 >> 4, (bpp_x16 & 0xf) * 625); + return 0; + } + /* * DP Standard v2.1 2.6.4.1 * SSC downspread and ref clock variation margin: diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index f7c6b60629c2b..db2c698f97ff6 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3416,7 +3416,6 @@ EXPORT_SYMBOL(drm_dp_remove_payload_part2); /** * drm_dp_add_payload_part2() - Execute payload update part 2 * @mgr: Manager to use. - * @state: The global atomic state * @payload: The payload to update * * If @payload was successfully assigned a starting time slot by drm_dp_add_payload_part1(), this @@ -3425,14 +3424,13 @@ EXPORT_SYMBOL(drm_dp_remove_payload_part2); * Returns: 0 on success, negative error code on failure. */ int drm_dp_add_payload_part2(struct drm_dp_mst_topology_mgr *mgr, - struct drm_atomic_state *state, struct drm_dp_mst_atomic_payload *payload) { int ret = 0; /* Skip failed payloads */ if (payload->payload_allocation_status != DRM_DP_MST_PAYLOAD_ALLOCATION_DFP) { - drm_dbg_kms(state->dev, "Part 1 of payload creation for %s failed, skipping part 2\n", + drm_dbg_kms(mgr->dev, "Part 1 of payload creation for %s failed, skipping part 2\n", payload->port->connector->name); return -EIO; } diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index cee3188adf3d5..ac502ea20089b 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -27,8 +27,9 @@ #include #include -#include #include +#include +#include #include #include #include @@ -686,11 +687,17 @@ void drm_atomic_bridge_chain_post_disable(struct drm_bridge *bridge, */ list_for_each_entry_from(next, &encoder->bridge_chain, chain_node) { - if (next->pre_enable_prev_first) { + if (!next->pre_enable_prev_first) { next = list_prev_entry(next, chain_node); limit = next; break; } + + if (list_is_last(&next->chain_node, + &encoder->bridge_chain)) { + limit = next; + break; + } } /* Call these bridges in reverse order */ @@ -773,7 +780,7 @@ void drm_atomic_bridge_chain_pre_enable(struct drm_bridge *bridge, /* Found first bridge that does NOT * request prev to be enabled first */ - limit = list_prev_entry(next, chain_node); + limit = next; break; } } @@ -1206,6 +1213,47 @@ int drm_bridge_get_modes(struct drm_bridge *bridge, } EXPORT_SYMBOL_GPL(drm_bridge_get_modes); +/** + * drm_bridge_edid_read - read the EDID data of the connected display + * @bridge: bridge control structure + * @connector: the connector to read EDID for + * + * If the bridge supports output EDID retrieval, as reported by the + * DRM_BRIDGE_OP_EDID bridge ops flag, call &drm_bridge_funcs.edid_read to get + * the EDID and return it. Otherwise return NULL. + * + * If &drm_bridge_funcs.edid_read is not set, fall back to using + * drm_bridge_get_edid() and wrapping it in struct drm_edid. + * + * RETURNS: + * The retrieved EDID on success, or NULL otherwise. + */ +const struct drm_edid *drm_bridge_edid_read(struct drm_bridge *bridge, + struct drm_connector *connector) +{ + if (!(bridge->ops & DRM_BRIDGE_OP_EDID)) + return NULL; + + /* Transitional: Fall back to ->get_edid. */ + if (!bridge->funcs->edid_read) { + const struct drm_edid *drm_edid; + struct edid *edid; + + edid = drm_bridge_get_edid(bridge, connector); + if (!edid) + return NULL; + + drm_edid = drm_edid_alloc(edid, (edid->extensions + 1) * EDID_LENGTH); + + kfree(edid); + + return drm_edid; + } + + return bridge->funcs->edid_read(bridge, connector); +} +EXPORT_SYMBOL_GPL(drm_bridge_edid_read); + /** * drm_bridge_get_edid - get the EDID data of the connected display * @bridge: bridge control structure @@ -1215,6 +1263,8 @@ EXPORT_SYMBOL_GPL(drm_bridge_get_modes); * DRM_BRIDGE_OP_EDID bridge ops flag, call &drm_bridge_funcs.get_edid to * get the EDID and return it. Otherwise return NULL. * + * Deprecated. Prefer using drm_bridge_edid_read(). + * * RETURNS: * The retrieved EDID on success, or NULL otherwise. */ diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 871e4e2129d6d..0683a129b3628 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -777,6 +777,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, unsigned int total_modes_count = 0; struct drm_client_offset *offsets; unsigned int connector_count = 0; + /* points to modes protected by mode_config.mutex */ struct drm_display_mode **modes; struct drm_crtc **crtcs; int i, ret = 0; @@ -845,7 +846,6 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, drm_client_pick_crtcs(client, connectors, connector_count, crtcs, modes, 0, width, height); } - mutex_unlock(&dev->mode_config.mutex); drm_client_modeset_release(client); @@ -875,6 +875,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, modeset->y = offset->y; } } + mutex_unlock(&dev->mode_config.mutex); mutex_unlock(&client->modeset_mutex); out: diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index b0516505f7ae9..4d2df7f64dc51 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -2940,7 +2940,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, dev->mode_config.max_width, dev->mode_config.max_height); else - drm_dbg_kms(dev, "User-space requested a forced probe on [CONNECTOR:%d:%s] but is not the DRM master, demoting to read-only probe", + drm_dbg_kms(dev, "User-space requested a forced probe on [CONNECTOR:%d:%s] but is not the DRM master, demoting to read-only probe\n", connector->base.id, connector->name); } diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 69c68804023ff..9ef9a70a836c7 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -7345,7 +7345,7 @@ static void drm_parse_tiled_block(struct drm_connector *connector, static bool displayid_is_tiled_block(const struct displayid_iter *iter, const struct displayid_block *block) { - return (displayid_version(iter) == DISPLAY_ID_STRUCTURE_VER_12 && + return (displayid_version(iter) < DISPLAY_ID_STRUCTURE_VER_20 && block->tag == DATA_BLOCK_TILED_DISPLAY) || (displayid_version(iter) == DISPLAY_ID_STRUCTURE_VER_20 && block->tag == DATA_BLOCK_2_TILED_DISPLAY_TOPOLOGY); diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c index d647d89764cb9..b4659cd6285ab 100644 --- a/drivers/gpu/drm/drm_fbdev_generic.c +++ b/drivers/gpu/drm/drm_fbdev_generic.c @@ -113,7 +113,6 @@ static int drm_fbdev_generic_helper_fb_probe(struct drm_fb_helper *fb_helper, /* screen */ info->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST; info->screen_buffer = screen_buffer; - info->fix.smem_start = page_to_phys(vmalloc_to_page(info->screen_buffer)); info->fix.smem_len = screen_size; /* deferred I/O */ diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index e440f458b6633..93337543aac32 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -224,8 +224,8 @@ __drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane, __drm_atomic_helper_plane_duplicate_state(plane, &new_shadow_plane_state->base); - drm_format_conv_state_copy(&shadow_plane_state->fmtcnv_state, - &new_shadow_plane_state->fmtcnv_state); + drm_format_conv_state_copy(&new_shadow_plane_state->fmtcnv_state, + &shadow_plane_state->fmtcnv_state); } EXPORT_SYMBOL(__drm_gem_duplicate_shadow_plane_state); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index e435f986cd135..1ff0678be7c75 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -610,6 +610,9 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct return ret; } + if (is_cow_mapping(vma->vm_flags)) + return -EINVAL; + dma_resv_lock(shmem->base.resv, NULL); ret = drm_gem_shmem_get_pages(shmem); dma_resv_unlock(shmem->base.resv); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 843a6dbda93a0..52a93149363b4 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -654,7 +654,7 @@ EXPORT_SYMBOL(mipi_dsi_set_maximum_return_packet_size); * * Return: 0 on success or a negative error code on failure. */ -ssize_t mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable) +int mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable) { /* Note: Needs updating for non-default PPS or algorithm */ u8 tx[2] = { enable << 0, 0 }; @@ -679,8 +679,8 @@ EXPORT_SYMBOL(mipi_dsi_compression_mode); * * Return: 0 on success or a negative error code on failure. */ -ssize_t mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi, - const struct drm_dsc_picture_parameter_set *pps) +int mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi, + const struct drm_dsc_picture_parameter_set *pps) { struct mipi_dsi_msg msg = { .channel = dsi->channel, diff --git a/drivers/gpu/drm/drm_modeset_helper.c b/drivers/gpu/drm/drm_modeset_helper.c index f858dfedf2cfc..2c582020cb423 100644 --- a/drivers/gpu/drm/drm_modeset_helper.c +++ b/drivers/gpu/drm/drm_modeset_helper.c @@ -193,13 +193,22 @@ int drm_mode_config_helper_suspend(struct drm_device *dev) if (!dev) return 0; + /* + * Don't disable polling if it was never initialized + */ + if (dev->mode_config.poll_enabled) + drm_kms_helper_poll_disable(dev); - drm_kms_helper_poll_disable(dev); drm_fb_helper_set_suspend_unlocked(dev->fb_helper, 1); state = drm_atomic_helper_suspend(dev); if (IS_ERR(state)) { drm_fb_helper_set_suspend_unlocked(dev->fb_helper, 0); - drm_kms_helper_poll_enable(dev); + /* + * Don't enable polling if it was never initialized + */ + if (dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(dev); + return PTR_ERR(state); } @@ -239,7 +248,11 @@ int drm_mode_config_helper_resume(struct drm_device *dev) dev->mode_config.suspend_state = NULL; drm_fb_helper_set_suspend_unlocked(dev->fb_helper, 0); - drm_kms_helper_poll_enable(dev); + /* + * Don't enable polling if it is not initialized + */ + if (dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(dev); return ret; } diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index e814020bbcd3b..cfbe020de54e0 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -274,19 +274,24 @@ EXPORT_SYMBOL(drm_panel_disable); * The modes probed from the panel are automatically added to the connector * that the panel is attached to. * - * Return: The number of modes available from the panel on success or a - * negative error code on failure. + * Return: The number of modes available from the panel on success, or 0 on + * failure (no modes). */ int drm_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector) { if (!panel) - return -EINVAL; + return 0; - if (panel->funcs && panel->funcs->get_modes) - return panel->funcs->get_modes(panel, connector); + if (panel->funcs && panel->funcs->get_modes) { + int num; - return -EOPNOTSUPP; + num = panel->funcs->get_modes(panel, connector); + if (num > 0) + return num; + } + + return 0; } EXPORT_SYMBOL(drm_panel_get_modes); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 3d92f66e550c3..aa93129c3397e 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -117,6 +117,12 @@ static const struct drm_dmi_panel_orientation_data lcd1080x1920_leftside_up = { .orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP, }; +static const struct drm_dmi_panel_orientation_data lcd1080x1920_rightside_up = { + .width = 1080, + .height = 1920, + .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP, +}; + static const struct drm_dmi_panel_orientation_data lcd1200x1920_rightside_up = { .width = 1200, .height = 1920, @@ -279,6 +285,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1618-03") }, .driver_data = (void *)&lcd720x1280_rightside_up, + }, { /* GPD Win Mini */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1617-01") + }, + .driver_data = (void *)&lcd1080x1920_rightside_up, }, { /* I.T.Works TW891 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 7352bde299d54..03bd3c7bd0dc2 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -582,7 +582,12 @@ int drm_gem_map_attach(struct dma_buf *dma_buf, { struct drm_gem_object *obj = dma_buf->priv; - if (!obj->funcs->get_sg_table) + /* + * drm_gem_map_dma_buf() requires obj->get_sg_table(), but drivers + * that implement their own ->map_dma_buf() do not. + */ + if (dma_buf->ops->map_dma_buf == drm_gem_map_dma_buf && + !obj->funcs->get_sg_table) return -ENOSYS; return drm_gem_pin(obj); diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c index 23b4e9a3361d8..36433fa681f32 100644 --- a/drivers/gpu/drm/drm_probe_helper.c +++ b/drivers/gpu/drm/drm_probe_helper.c @@ -293,14 +293,17 @@ static void reschedule_output_poll_work(struct drm_device *dev) * Drivers can call this helper from their device resume implementation. It is * not an error to call this even when output polling isn't enabled. * + * If device polling was never initialized before, this call will trigger a + * warning and return. + * * Note that calls to enable and disable polling must be strictly ordered, which * is automatically the case when they're only call from suspend/resume * callbacks. */ void drm_kms_helper_poll_enable(struct drm_device *dev) { - if (!dev->mode_config.poll_enabled || !drm_kms_helper_poll || - dev->mode_config.poll_running) + if (drm_WARN_ON_ONCE(dev, !dev->mode_config.poll_enabled) || + !drm_kms_helper_poll || dev->mode_config.poll_running) return; if (drm_kms_helper_enable_hpd(dev) || @@ -419,6 +422,13 @@ static int drm_helper_probe_get_modes(struct drm_connector *connector) count = connector_funcs->get_modes(connector); + /* The .get_modes() callback should not return negative values. */ + if (count < 0) { + drm_err(connector->dev, ".get_modes() returned %pe\n", + ERR_PTR(count)); + count = 0; + } + /* * Fallback for when DDC probe failed in drm_get_edid() and thus skipped * override/firmware EDID. @@ -619,8 +629,12 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, 0); } - /* Re-enable polling in case the global poll config changed. */ - drm_kms_helper_poll_enable(dev); + /* + * Re-enable polling in case the global poll config changed but polling + * is still initialized. + */ + if (dev->mode_config.poll_enabled) + drm_kms_helper_poll_enable(dev); if (connector->status == connector_status_disconnected) { DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n", @@ -873,12 +887,18 @@ EXPORT_SYMBOL(drm_kms_helper_is_poll_worker); * not an error to call this even when output polling isn't enabled or already * disabled. Polling is re-enabled by calling drm_kms_helper_poll_enable(). * + * If however, the polling was never initialized, this call will trigger a + * warning and return + * * Note that calls to enable and disable polling must be strictly ordered, which * is automatically the case when they're only call from suspend/resume * callbacks. */ void drm_kms_helper_poll_disable(struct drm_device *dev) { + if (drm_WARN_ON(dev, !dev->mode_config.poll_enabled)) + return; + if (dev->mode_config.poll_running) drm_kms_helper_disable_hpd(dev); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 6228ce6032482..9a2965741dab3 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -494,7 +494,7 @@ static const struct drm_driver etnaviv_drm_driver = { .desc = "etnaviv DRM", .date = "20151214", .major = 1, - .minor = 3, + .minor = 4, }; /* diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 9b8445d2a128f..89cb6799b547f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -632,8 +632,8 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) /* Disable TX clock gating on affected core revisions. */ if (etnaviv_is_model_rev(gpu, GC4000, 0x5222) || etnaviv_is_model_rev(gpu, GC2000, 0x5108) || - etnaviv_is_model_rev(gpu, GC2000, 0x6202) || - etnaviv_is_model_rev(gpu, GC2000, 0x6203)) + etnaviv_is_model_rev(gpu, GC7000, 0x6202) || + etnaviv_is_model_rev(gpu, GC7000, 0x6203)) pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX; /* Disable SE and RA clock gating on affected core revisions. */ diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index 67201242438be..8665f2658d51b 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -265,6 +265,9 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) { struct etnaviv_chip_identity *ident = &gpu->identity; + const u32 product_id = ident->product_id; + const u32 customer_id = ident->customer_id; + const u32 eco_id = ident->eco_id; int i; for (i = 0; i < ARRAY_SIZE(etnaviv_chip_identities); i++) { @@ -278,6 +281,12 @@ bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) etnaviv_chip_identities[i].eco_id == ~0U)) { memcpy(ident, &etnaviv_chip_identities[i], sizeof(*ident)); + + /* Restore some id values as ~0U aka 'don't care' might been used. */ + ident->product_id = product_id; + ident->customer_id = customer_id; + ident->eco_id = eco_id; + return true; } } diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index 00382f28748ac..b1e9a702172f5 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -309,6 +309,7 @@ static int vidi_get_modes(struct drm_connector *connector) struct vidi_context *ctx = ctx_from_connector(connector); struct edid *edid; int edid_len; + int count; /* * the edid data comes from user side and it would be set @@ -316,19 +317,23 @@ static int vidi_get_modes(struct drm_connector *connector) */ if (!ctx->raw_edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "raw_edid is null.\n"); - return -EFAULT; + return 0; } edid_len = (1 + ctx->raw_edid->extensions) * EDID_LENGTH; edid = kmemdup(ctx->raw_edid, edid_len, GFP_KERNEL); if (!edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "failed to allocate edid\n"); - return -ENOMEM; + return 0; } drm_connector_update_edid_property(connector, edid); - return drm_add_edid_modes(connector, edid); + count = drm_add_edid_modes(connector, edid); + + kfree(edid); + + return count; } static const struct drm_connector_helper_funcs vidi_connector_helper_funcs = { diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 43bed6cbaaea0..6385202cd28bb 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector) int ret; if (!hdata->ddc_adpt) - return -ENODEV; + goto no_edid; edid = drm_get_edid(connector, hdata->ddc_adpt); if (!edid) - return -ENODEV; + goto no_edid; hdata->dvi_mode = !connector->display_info.is_hdmi; DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n", @@ -906,6 +906,9 @@ static int hdmi_get_modes(struct drm_connector *connector) kfree(edid); return ret; + +no_edid: + return drm_add_modes_noedid(connector, 640, 480); } static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock) diff --git a/drivers/gpu/drm/gma500/Makefile b/drivers/gpu/drm/gma500/Makefile index 4f302cd5e1a6c..58fed80c7392a 100644 --- a/drivers/gpu/drm/gma500/Makefile +++ b/drivers/gpu/drm/gma500/Makefile @@ -34,7 +34,6 @@ gma500_gfx-y += \ psb_intel_lvds.o \ psb_intel_modes.o \ psb_intel_sdvo.o \ - psb_lid.o \ psb_irq.o gma500_gfx-$(CONFIG_ACPI) += opregion.o diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c index dcfcd7b89d4a1..6dece8f0e380f 100644 --- a/drivers/gpu/drm/gma500/psb_device.c +++ b/drivers/gpu/drm/gma500/psb_device.c @@ -73,8 +73,7 @@ static int psb_backlight_setup(struct drm_device *dev) } psb_intel_lvds_set_brightness(dev, PSB_MAX_BRIGHTNESS); - /* This must occur after the backlight is properly initialised */ - psb_lid_timer_init(dev_priv); + return 0; } @@ -259,8 +258,6 @@ static int psb_chip_setup(struct drm_device *dev) static void psb_chip_teardown(struct drm_device *dev) { - struct drm_psb_private *dev_priv = to_drm_psb_private(dev); - psb_lid_timer_takedown(dev_priv); gma_intel_teardown_gmbus(dev); } diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index c5edfa4aa4ccd..83c17689c454f 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -162,7 +162,6 @@ #define PSB_NUM_VBLANKS 2 #define PSB_WATCHDOG_DELAY (HZ * 2) -#define PSB_LID_DELAY (HZ / 10) #define PSB_MAX_BRIGHTNESS 100 @@ -491,11 +490,7 @@ struct drm_psb_private { /* Hotplug handling */ struct work_struct hotplug_work; - /* LID-Switch */ - spinlock_t lid_lock; - struct timer_list lid_timer; struct psb_intel_opregion opregion; - u32 lid_last_state; /* Watchdog */ uint32_t apm_reg; @@ -591,10 +586,6 @@ struct psb_ops { int i2c_bus; /* I2C bus identifier for Moorestown */ }; -/* psb_lid.c */ -extern void psb_lid_timer_init(struct drm_psb_private *dev_priv); -extern void psb_lid_timer_takedown(struct drm_psb_private *dev_priv); - /* modesetting */ extern void psb_modeset_init(struct drm_device *dev); extern void psb_modeset_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/gma500/psb_lid.c b/drivers/gpu/drm/gma500/psb_lid.c deleted file mode 100644 index 58a7fe3926360..0000000000000 --- a/drivers/gpu/drm/gma500/psb_lid.c +++ /dev/null @@ -1,80 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/************************************************************************** - * Copyright (c) 2007, Intel Corporation. - * - * Authors: Thomas Hellstrom - **************************************************************************/ - -#include - -#include "psb_drv.h" -#include "psb_intel_reg.h" -#include "psb_reg.h" - -static void psb_lid_timer_func(struct timer_list *t) -{ - struct drm_psb_private *dev_priv = from_timer(dev_priv, t, lid_timer); - struct drm_device *dev = (struct drm_device *)&dev_priv->dev; - struct timer_list *lid_timer = &dev_priv->lid_timer; - unsigned long irq_flags; - u32 __iomem *lid_state = dev_priv->opregion.lid_state; - u32 pp_status; - - if (readl(lid_state) == dev_priv->lid_last_state) - goto lid_timer_schedule; - - if ((readl(lid_state)) & 0x01) { - /*lid state is open*/ - REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) | POWER_TARGET_ON); - do { - pp_status = REG_READ(PP_STATUS); - } while ((pp_status & PP_ON) == 0 && - (pp_status & PP_SEQUENCE_MASK) != 0); - - if (REG_READ(PP_STATUS) & PP_ON) { - /*FIXME: should be backlight level before*/ - psb_intel_lvds_set_brightness(dev, 100); - } else { - DRM_DEBUG("LVDS panel never powered up"); - return; - } - } else { - psb_intel_lvds_set_brightness(dev, 0); - - REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) & ~POWER_TARGET_ON); - do { - pp_status = REG_READ(PP_STATUS); - } while ((pp_status & PP_ON) == 0); - } - dev_priv->lid_last_state = readl(lid_state); - -lid_timer_schedule: - spin_lock_irqsave(&dev_priv->lid_lock, irq_flags); - if (!timer_pending(lid_timer)) { - lid_timer->expires = jiffies + PSB_LID_DELAY; - add_timer(lid_timer); - } - spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags); -} - -void psb_lid_timer_init(struct drm_psb_private *dev_priv) -{ - struct timer_list *lid_timer = &dev_priv->lid_timer; - unsigned long irq_flags; - - spin_lock_init(&dev_priv->lid_lock); - spin_lock_irqsave(&dev_priv->lid_lock, irq_flags); - - timer_setup(lid_timer, psb_lid_timer_func, 0); - - lid_timer->expires = jiffies + PSB_LID_DELAY; - - add_timer(lid_timer); - spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags); -} - -void psb_lid_timer_takedown(struct drm_psb_private *dev_priv) -{ - del_timer_sync(&dev_priv->lid_timer); -} - diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index c13f14edb5088..2d08baa91da08 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -33,9 +33,9 @@ endif subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror # Fine grained warnings disable -CFLAGS_i915_pci.o = $(call cc-disable-warning, override-init) -CFLAGS_display/intel_display_device.o = $(call cc-disable-warning, override-init) -CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init) +CFLAGS_i915_pci.o = -Wno-override-init +CFLAGS_display/intel_display_device.o = -Wno-override-init +CFLAGS_display/intel_fbdev.o = -Wno-override-init # Support compiling the display code separately for both i915 and xe # drivers. Define I915 when building i915. @@ -118,6 +118,7 @@ gt-y += \ gt/intel_ggtt_fencing.o \ gt/intel_gt.o \ gt/intel_gt_buffer_pool.o \ + gt/intel_gt_ccs_mode.o \ gt/intel_gt_clock_utils.o \ gt/intel_gt_debugfs.o \ gt/intel_gt_engines_debugfs.o \ diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c index dfe0b07a122d1..06ec04e667e32 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.c +++ b/drivers/gpu/drm/i915/display/g4x_dp.c @@ -717,7 +717,6 @@ static void g4x_enable_dp(struct intel_atomic_state *state, { intel_enable_dp(state, encoder, pipe_config, conn_state); intel_edp_backlight_on(pipe_config, conn_state); - encoder->audio_enable(encoder, pipe_config, conn_state); } static void vlv_enable_dp(struct intel_atomic_state *state, @@ -726,7 +725,6 @@ static void vlv_enable_dp(struct intel_atomic_state *state, const struct drm_connector_state *conn_state) { intel_edp_backlight_on(pipe_config, conn_state); - encoder->audio_enable(encoder, pipe_config, conn_state); } static void g4x_pre_enable_dp(struct intel_atomic_state *state, diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index eda4a8b885904..ac456a2275dba 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1155,7 +1155,6 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder) } intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP); - intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON); /* ensure all panel commands dispatched before enabling transcoder */ wait_for_cmds_dispatched_to_panel(encoder); @@ -1256,6 +1255,8 @@ static void gen11_dsi_enable(struct intel_atomic_state *state, /* step6d: enable dsi transcoder */ gen11_dsi_enable_transcoder(encoder); + intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON); + /* step7: enable backlight */ intel_backlight_enable(crtc_state, conn_state); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON); diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index 07e0c73204f30..40e7d862675ee 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -76,19 +76,6 @@ struct intel_audio_funcs { struct intel_crtc_state *crtc_state); }; -/* DP N/M table */ -#define LC_810M 810000 -#define LC_540M 540000 -#define LC_270M 270000 -#define LC_162M 162000 - -struct dp_aud_n_m { - int sample_rate; - int clock; - u16 m; - u16 n; -}; - struct hdmi_aud_ncts { int sample_rate; int clock; @@ -96,60 +83,6 @@ struct hdmi_aud_ncts { int cts; }; -/* Values according to DP 1.4 Table 2-104 */ -static const struct dp_aud_n_m dp_aud_n_m[] = { - { 32000, LC_162M, 1024, 10125 }, - { 44100, LC_162M, 784, 5625 }, - { 48000, LC_162M, 512, 3375 }, - { 64000, LC_162M, 2048, 10125 }, - { 88200, LC_162M, 1568, 5625 }, - { 96000, LC_162M, 1024, 3375 }, - { 128000, LC_162M, 4096, 10125 }, - { 176400, LC_162M, 3136, 5625 }, - { 192000, LC_162M, 2048, 3375 }, - { 32000, LC_270M, 1024, 16875 }, - { 44100, LC_270M, 784, 9375 }, - { 48000, LC_270M, 512, 5625 }, - { 64000, LC_270M, 2048, 16875 }, - { 88200, LC_270M, 1568, 9375 }, - { 96000, LC_270M, 1024, 5625 }, - { 128000, LC_270M, 4096, 16875 }, - { 176400, LC_270M, 3136, 9375 }, - { 192000, LC_270M, 2048, 5625 }, - { 32000, LC_540M, 1024, 33750 }, - { 44100, LC_540M, 784, 18750 }, - { 48000, LC_540M, 512, 11250 }, - { 64000, LC_540M, 2048, 33750 }, - { 88200, LC_540M, 1568, 18750 }, - { 96000, LC_540M, 1024, 11250 }, - { 128000, LC_540M, 4096, 33750 }, - { 176400, LC_540M, 3136, 18750 }, - { 192000, LC_540M, 2048, 11250 }, - { 32000, LC_810M, 1024, 50625 }, - { 44100, LC_810M, 784, 28125 }, - { 48000, LC_810M, 512, 16875 }, - { 64000, LC_810M, 2048, 50625 }, - { 88200, LC_810M, 1568, 28125 }, - { 96000, LC_810M, 1024, 16875 }, - { 128000, LC_810M, 4096, 50625 }, - { 176400, LC_810M, 3136, 28125 }, - { 192000, LC_810M, 2048, 16875 }, -}; - -static const struct dp_aud_n_m * -audio_config_dp_get_n_m(const struct intel_crtc_state *crtc_state, int rate) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(dp_aud_n_m); i++) { - if (rate == dp_aud_n_m[i].sample_rate && - crtc_state->port_clock == dp_aud_n_m[i].clock) - return &dp_aud_n_m[i]; - } - - return NULL; -} - static const struct { int clock; u32 config; @@ -387,47 +320,17 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { struct drm_i915_private *i915 = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = i915->display.audio.component; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - enum port port = encoder->port; - const struct dp_aud_n_m *nm; - int rate; - u32 tmp; - - rate = acomp ? acomp->aud_sample_rate[port] : 0; - nm = audio_config_dp_get_n_m(crtc_state, rate); - if (nm) - drm_dbg_kms(&i915->drm, "using Maud %u, Naud %u\n", nm->m, - nm->n); - else - drm_dbg_kms(&i915->drm, "using automatic Maud, Naud\n"); - - tmp = intel_de_read(i915, HSW_AUD_CFG(cpu_transcoder)); - tmp &= ~AUD_CONFIG_N_VALUE_INDEX; - tmp &= ~AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK; - tmp &= ~AUD_CONFIG_N_PROG_ENABLE; - tmp |= AUD_CONFIG_N_VALUE_INDEX; - - if (nm) { - tmp &= ~AUD_CONFIG_N_MASK; - tmp |= AUD_CONFIG_N(nm->n); - tmp |= AUD_CONFIG_N_PROG_ENABLE; - } - - intel_de_write(i915, HSW_AUD_CFG(cpu_transcoder), tmp); - - tmp = intel_de_read(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder)); - tmp &= ~AUD_CONFIG_M_MASK; - tmp &= ~AUD_M_CTS_M_VALUE_INDEX; - tmp &= ~AUD_M_CTS_M_PROG_ENABLE; - if (nm) { - tmp |= nm->m; - tmp |= AUD_M_CTS_M_VALUE_INDEX; - tmp |= AUD_M_CTS_M_PROG_ENABLE; - } + /* Enable time stamps. Let HW calculate Maud/Naud values */ + intel_de_rmw(i915, HSW_AUD_CFG(cpu_transcoder), + AUD_CONFIG_N_VALUE_INDEX | + AUD_CONFIG_PIXEL_CLOCK_HDMI_MASK | + AUD_CONFIG_UPPER_N_MASK | + AUD_CONFIG_LOWER_N_MASK | + AUD_CONFIG_N_PROG_ENABLE, + AUD_CONFIG_N_VALUE_INDEX); - intel_de_write(i915, HSW_AUD_M_CTS_ENABLE(cpu_transcoder), tmp); } static void @@ -1349,17 +1252,6 @@ static const struct component_ops i915_audio_component_bind_ops = { static void i915_audio_component_init(struct drm_i915_private *i915) { u32 aud_freq, aud_freq_init; - int ret; - - ret = component_add_typed(i915->drm.dev, - &i915_audio_component_bind_ops, - I915_COMPONENT_AUDIO); - if (ret < 0) { - drm_err(&i915->drm, - "failed to add audio component (%d)\n", ret); - /* continue with reduced functionality */ - return; - } if (DISPLAY_VER(i915) >= 9) { aud_freq_init = intel_de_read(i915, AUD_FREQ_CNTRL); @@ -1382,6 +1274,21 @@ static void i915_audio_component_init(struct drm_i915_private *i915) /* init with current cdclk */ intel_audio_cdclk_change_post(i915); +} + +static void i915_audio_component_register(struct drm_i915_private *i915) +{ + int ret; + + ret = component_add_typed(i915->drm.dev, + &i915_audio_component_bind_ops, + I915_COMPONENT_AUDIO); + if (ret < 0) { + drm_err(&i915->drm, + "failed to add audio component (%d)\n", ret); + /* continue with reduced functionality */ + return; + } i915->display.audio.component_registered = true; } @@ -1414,6 +1321,12 @@ void intel_audio_init(struct drm_i915_private *i915) i915_audio_component_init(i915); } +void intel_audio_register(struct drm_i915_private *i915) +{ + if (!i915->display.audio.lpe.platdev) + i915_audio_component_register(i915); +} + /** * intel_audio_deinit() - deinitialize the audio driver * @i915: the i915 drm device private data diff --git a/drivers/gpu/drm/i915/display/intel_audio.h b/drivers/gpu/drm/i915/display/intel_audio.h index 9327954b801e5..576c061d72a45 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.h +++ b/drivers/gpu/drm/i915/display/intel_audio.h @@ -28,6 +28,7 @@ void intel_audio_codec_get_config(struct intel_encoder *encoder, void intel_audio_cdclk_change_pre(struct drm_i915_private *dev_priv); void intel_audio_cdclk_change_post(struct drm_i915_private *dev_priv); void intel_audio_init(struct drm_i915_private *dev_priv); +void intel_audio_register(struct drm_i915_private *i915); void intel_audio_deinit(struct drm_i915_private *dev_priv); void intel_audio_sdp_split_update(const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index aa169b0055e97..c36633d7dda84 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1042,22 +1042,11 @@ parse_lfp_backlight(struct drm_i915_private *i915, panel->vbt.backlight.type = INTEL_BACKLIGHT_DISPLAY_DDI; panel->vbt.backlight.controller = 0; if (i915->display.vbt.version >= 191) { - size_t exp_size; + const struct lfp_backlight_control_method *method; - if (i915->display.vbt.version >= 236) - exp_size = sizeof(struct bdb_lfp_backlight_data); - else if (i915->display.vbt.version >= 234) - exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_234; - else - exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_191; - - if (get_blocksize(backlight_data) >= exp_size) { - const struct lfp_backlight_control_method *method; - - method = &backlight_data->backlight_control[panel_type]; - panel->vbt.backlight.type = method->type; - panel->vbt.backlight.controller = method->controller; - } + method = &backlight_data->backlight_control[panel_type]; + panel->vbt.backlight.type = method->type; + panel->vbt.backlight.controller = method->controller; } panel->vbt.backlight.pwm_freq_hz = entry->pwm_freq_hz; @@ -1952,16 +1941,12 @@ static int get_init_otp_deassert_fragment_len(struct drm_i915_private *i915, * these devices we split the init OTP sequence into a deassert sequence and * the actual init OTP part. */ -static void fixup_mipi_sequences(struct drm_i915_private *i915, - struct intel_panel *panel) +static void vlv_fixup_mipi_sequences(struct drm_i915_private *i915, + struct intel_panel *panel) { u8 *init_otp; int len; - /* Limit this to VLV for now. */ - if (!IS_VALLEYVIEW(i915)) - return; - /* Limit this to v1 vid-mode sequences */ if (panel->vbt.dsi.config->is_cmd_mode || panel->vbt.dsi.seq_version != 1) @@ -1997,6 +1982,41 @@ static void fixup_mipi_sequences(struct drm_i915_private *i915, panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] = init_otp + len - 1; } +/* + * Some machines (eg. Lenovo 82TQ) appear to have broken + * VBT sequences: + * - INIT_OTP is not present at all + * - what should be in INIT_OTP is in DISPLAY_ON + * - what should be in DISPLAY_ON is in BACKLIGHT_ON + * (along with the actual backlight stuff) + * + * To make those work we simply swap DISPLAY_ON and INIT_OTP. + * + * TODO: Do we need to limit this to specific machines, + * or examine the contents of the sequences to + * avoid false positives? + */ +static void icl_fixup_mipi_sequences(struct drm_i915_private *i915, + struct intel_panel *panel) +{ + if (!panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] && + panel->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]) { + drm_dbg_kms(&i915->drm, "Broken VBT: Swapping INIT_OTP and DISPLAY_ON sequences\n"); + + swap(panel->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP], + panel->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]); + } +} + +static void fixup_mipi_sequences(struct drm_i915_private *i915, + struct intel_panel *panel) +{ + if (DISPLAY_VER(i915) >= 11) + icl_fixup_mipi_sequences(i915, panel); + else if (IS_VALLEYVIEW(i915)) + vlv_fixup_mipi_sequences(i915, panel); +} + static void parse_mipi_sequence(struct drm_i915_private *i915, struct intel_panel *panel) @@ -3344,6 +3364,9 @@ bool intel_bios_encoder_supports_dp_dual_mode(const struct intel_bios_encoder_da { const struct child_device_config *child = &devdata->child; + if (!devdata) + return false; + if (!intel_bios_encoder_supports_dp(devdata) || !intel_bios_encoder_supports_hdmi(devdata)) return false; diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 7f2a50b4f4940..972ea887e2325 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -162,7 +162,9 @@ int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv, 1); if (ret < 0) { - drm_err(&dev_priv->drm, "Failed to disable qgv points (%d) points: 0x%x\n", ret, points_mask); + drm_err(&dev_priv->drm, + "Failed to disable qgv points (0x%x) points: 0x%x\n", + ret, points_mask); return ret; } @@ -290,8 +292,10 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv, struct intel_qgv_point *sp = &qi->points[i]; ret = intel_read_qgv_point_info(dev_priv, sp, i); - if (ret) + if (ret) { + drm_dbg_kms(&dev_priv->drm, "Could not read QGV %d info\n", i); return ret; + } drm_dbg_kms(&dev_priv->drm, "QGV %d: DCLK=%d tRP=%d tRDPRE=%d tRAS=%d tRCD=%d tRC=%d\n", @@ -659,6 +663,22 @@ static unsigned int adl_psf_bw(struct drm_i915_private *dev_priv, return bi->psf_bw[psf_gv_point]; } +static unsigned int icl_qgv_bw(struct drm_i915_private *i915, + int num_active_planes, int qgv_point) +{ + unsigned int idx; + + if (DISPLAY_VER(i915) >= 12) + idx = tgl_max_bw_index(i915, num_active_planes, qgv_point); + else + idx = icl_max_bw_index(i915, num_active_planes, qgv_point); + + if (idx >= ARRAY_SIZE(i915->display.bw.max)) + return 0; + + return i915->display.bw.max[idx].deratedbw[qgv_point]; +} + void intel_bw_init_hw(struct drm_i915_private *dev_priv) { if (!HAS_DISPLAY(dev_priv)) @@ -735,6 +755,7 @@ void intel_bw_crtc_update(struct intel_bw_state *bw_state, intel_bw_crtc_data_rate(crtc_state); bw_state->num_active_planes[crtc->pipe] = intel_bw_crtc_num_active_planes(crtc_state); + bw_state->force_check_qgv = true; drm_dbg_kms(&i915->drm, "pipe %c data rate %u num active planes %u\n", pipe_name(crtc->pipe), @@ -804,6 +825,80 @@ intel_atomic_get_bw_state(struct intel_atomic_state *state) return to_intel_bw_state(bw_state); } +static unsigned int icl_max_bw_qgv_point_mask(struct drm_i915_private *i915, + int num_active_planes) +{ + unsigned int num_qgv_points = i915->display.bw.max[0].num_qgv_points; + unsigned int max_bw_point = 0; + unsigned int max_bw = 0; + int i; + + for (i = 0; i < num_qgv_points; i++) { + unsigned int max_data_rate = + icl_qgv_bw(i915, num_active_planes, i); + + /* + * We need to know which qgv point gives us + * maximum bandwidth in order to disable SAGV + * if we find that we exceed SAGV block time + * with watermarks. By that moment we already + * have those, as it is calculated earlier in + * intel_atomic_check, + */ + if (max_data_rate > max_bw) { + max_bw_point = BIT(i); + max_bw = max_data_rate; + } + } + + return max_bw_point; +} + +static u16 icl_prepare_qgv_points_mask(struct drm_i915_private *i915, + unsigned int qgv_points, + unsigned int psf_points) +{ + return ~(ICL_PCODE_REQ_QGV_PT(qgv_points) | + ADLS_PCODE_REQ_PSF_PT(psf_points)) & icl_qgv_points_mask(i915); +} + +static unsigned int icl_max_bw_psf_gv_point_mask(struct drm_i915_private *i915) +{ + unsigned int num_psf_gv_points = i915->display.bw.max[0].num_psf_gv_points; + unsigned int max_bw_point_mask = 0; + unsigned int max_bw = 0; + int i; + + for (i = 0; i < num_psf_gv_points; i++) { + unsigned int max_data_rate = adl_psf_bw(i915, i); + + if (max_data_rate > max_bw) { + max_bw_point_mask = BIT(i); + max_bw = max_data_rate; + } else if (max_data_rate == max_bw) { + max_bw_point_mask |= BIT(i); + } + } + + return max_bw_point_mask; +} + +static void icl_force_disable_sagv(struct drm_i915_private *i915, + struct intel_bw_state *bw_state) +{ + unsigned int qgv_points = icl_max_bw_qgv_point_mask(i915, 0); + unsigned int psf_points = icl_max_bw_psf_gv_point_mask(i915); + + bw_state->qgv_points_mask = icl_prepare_qgv_points_mask(i915, + qgv_points, + psf_points); + + drm_dbg_kms(&i915->drm, "Forcing SAGV disable: mask 0x%x\n", + bw_state->qgv_points_mask); + + icl_pcode_restrict_qgv_points(i915, bw_state->qgv_points_mask); +} + static int mtl_find_qgv_points(struct drm_i915_private *i915, unsigned int data_rate, unsigned int num_active_planes, @@ -881,8 +976,6 @@ static int icl_find_qgv_points(struct drm_i915_private *i915, const struct intel_bw_state *old_bw_state, struct intel_bw_state *new_bw_state) { - unsigned int max_bw_point = 0; - unsigned int max_bw = 0; unsigned int num_psf_gv_points = i915->display.bw.max[0].num_psf_gv_points; unsigned int num_qgv_points = i915->display.bw.max[0].num_qgv_points; u16 psf_points = 0; @@ -895,31 +988,8 @@ static int icl_find_qgv_points(struct drm_i915_private *i915, return ret; for (i = 0; i < num_qgv_points; i++) { - unsigned int idx; - unsigned int max_data_rate; - - if (DISPLAY_VER(i915) >= 12) - idx = tgl_max_bw_index(i915, num_active_planes, i); - else - idx = icl_max_bw_index(i915, num_active_planes, i); - - if (idx >= ARRAY_SIZE(i915->display.bw.max)) - continue; - - max_data_rate = i915->display.bw.max[idx].deratedbw[i]; - - /* - * We need to know which qgv point gives us - * maximum bandwidth in order to disable SAGV - * if we find that we exceed SAGV block time - * with watermarks. By that moment we already - * have those, as it is calculated earlier in - * intel_atomic_check, - */ - if (max_data_rate > max_bw) { - max_bw_point = i; - max_bw = max_data_rate; - } + unsigned int max_data_rate = icl_qgv_bw(i915, + num_active_planes, i); if (max_data_rate >= data_rate) qgv_points |= BIT(i); @@ -963,20 +1033,18 @@ static int icl_find_qgv_points(struct drm_i915_private *i915, * cause. */ if (!intel_can_enable_sagv(i915, new_bw_state)) { - qgv_points = BIT(max_bw_point); - drm_dbg_kms(&i915->drm, "No SAGV, using single QGV point %d\n", - max_bw_point); + qgv_points = icl_max_bw_qgv_point_mask(i915, num_active_planes); + drm_dbg_kms(&i915->drm, "No SAGV, using single QGV point mask 0x%x\n", + qgv_points); } /* * We store the ones which need to be masked as that is what PCode * actually accepts as a parameter. */ - new_bw_state->qgv_points_mask = - ~(ICL_PCODE_REQ_QGV_PT(qgv_points) | - ADLS_PCODE_REQ_PSF_PT(psf_points)) & - icl_qgv_points_mask(i915); - + new_bw_state->qgv_points_mask = icl_prepare_qgv_points_mask(i915, + qgv_points, + psf_points); /* * If the actual mask had changed we need to make sure that * the commits are serialized(in case this is a nomodeset, nonblocking) @@ -1272,8 +1340,9 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) new_bw_state = intel_atomic_get_new_bw_state(state); if (new_bw_state && - intel_can_enable_sagv(i915, old_bw_state) != - intel_can_enable_sagv(i915, new_bw_state)) + (intel_can_enable_sagv(i915, old_bw_state) != + intel_can_enable_sagv(i915, new_bw_state) || + new_bw_state->force_check_qgv)) changed = true; /* @@ -1287,6 +1356,8 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) if (ret) return ret; + new_bw_state->force_check_qgv = false; + return 0; } @@ -1313,7 +1384,7 @@ static const struct intel_global_state_funcs intel_bw_funcs = { .atomic_destroy_state = intel_bw_destroy_state, }; -int intel_bw_init(struct drm_i915_private *dev_priv) +int intel_bw_init(struct drm_i915_private *i915) { struct intel_bw_state *state; @@ -1321,8 +1392,15 @@ int intel_bw_init(struct drm_i915_private *dev_priv) if (!state) return -ENOMEM; - intel_atomic_global_obj_init(dev_priv, &dev_priv->display.bw.obj, + intel_atomic_global_obj_init(i915, &i915->display.bw.obj, &state->base, &intel_bw_funcs); + /* + * Limit this only if we have SAGV. And for Display version 14 onwards + * sagv is handled though pmdemand requests + */ + if (intel_has_sagv(i915) && IS_DISPLAY_VER(i915, 11, 13)) + icl_force_disable_sagv(i915, state); + return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h index 59cb4fc5db76c..4d951a599de63 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.h +++ b/drivers/gpu/drm/i915/display/intel_bw.h @@ -47,6 +47,12 @@ struct intel_bw_state { */ u16 qgv_points_mask; + /* + * Flag to force the QGV comparison in atomic check right after the + * hw state readout + */ + bool force_check_qgv; + int min_cdclk[I915_MAX_PIPES]; unsigned int data_rate[I915_MAX_PIPES]; u8 num_active_planes[I915_MAX_PIPES]; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index c985ebb6831a3..7ba30d26f620c 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2512,7 +2512,8 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state) intel_atomic_get_old_cdclk_state(state); const struct intel_cdclk_state *new_cdclk_state = intel_atomic_get_new_cdclk_state(state); - enum pipe pipe = new_cdclk_state->pipe; + struct intel_cdclk_config cdclk_config; + enum pipe pipe; if (!intel_cdclk_changed(&old_cdclk_state->actual, &new_cdclk_state->actual)) @@ -2521,12 +2522,25 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state) if (IS_DG2(i915)) intel_cdclk_pcode_pre_notify(state); - if (pipe == INVALID_PIPE || - old_cdclk_state->actual.cdclk <= new_cdclk_state->actual.cdclk) { - drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + if (new_cdclk_state->disable_pipes) { + cdclk_config = new_cdclk_state->actual; + pipe = INVALID_PIPE; + } else { + if (new_cdclk_state->actual.cdclk >= old_cdclk_state->actual.cdclk) { + cdclk_config = new_cdclk_state->actual; + pipe = new_cdclk_state->pipe; + } else { + cdclk_config = old_cdclk_state->actual; + pipe = INVALID_PIPE; + } - intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); + cdclk_config.voltage_level = max(new_cdclk_state->actual.voltage_level, + old_cdclk_state->actual.voltage_level); } + + drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + + intel_set_cdclk(i915, &cdclk_config, pipe); } /** @@ -2544,7 +2558,7 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state) intel_atomic_get_old_cdclk_state(state); const struct intel_cdclk_state *new_cdclk_state = intel_atomic_get_new_cdclk_state(state); - enum pipe pipe = new_cdclk_state->pipe; + enum pipe pipe; if (!intel_cdclk_changed(&old_cdclk_state->actual, &new_cdclk_state->actual)) @@ -2553,12 +2567,15 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state) if (IS_DG2(i915)) intel_cdclk_pcode_post_notify(state); - if (pipe != INVALID_PIPE && - old_cdclk_state->actual.cdclk > new_cdclk_state->actual.cdclk) { - drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + if (!new_cdclk_state->disable_pipes && + new_cdclk_state->actual.cdclk < old_cdclk_state->actual.cdclk) + pipe = new_cdclk_state->pipe; + else + pipe = INVALID_PIPE; + + drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); - intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); - } + intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); } static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state) @@ -3036,6 +3053,7 @@ static struct intel_global_state *intel_cdclk_duplicate_state(struct intel_globa return NULL; cdclk_state->pipe = INVALID_PIPE; + cdclk_state->disable_pipes = false; return &cdclk_state->base; } @@ -3214,6 +3232,8 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) if (ret) return ret; + new_cdclk_state->disable_pipes = true; + drm_dbg_kms(&dev_priv->drm, "Modeset required for cdclk change\n"); } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index 48fd7d39e0cd9..71bc032bfef16 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -51,6 +51,9 @@ struct intel_cdclk_state { /* bitmask of active pipes */ u8 active_pipes; + + /* update cdclk with pipes disabled */ + bool disable_pipes; }; int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index 926e2de00eb58..2dde7ac88274d 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -35,12 +35,10 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev); - const struct drm_framebuffer *fb = plane_state->hw.fb; - struct drm_i915_gem_object *obj = intel_fb_obj(fb); u32 base; if (DISPLAY_INFO(dev_priv)->cursor_needs_physical) - base = i915_gem_object_get_dma_address(obj, 0); + base = plane_state->phys_dma_addr; else base = intel_plane_ggtt_offset(plane_state); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 12a29363e5dfe..31aa5d54fdf07 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -4229,7 +4229,12 @@ static bool m_n_equal(const struct intel_link_m_n *m_n_1, static bool crtcs_port_sync_compatible(const struct intel_crtc_state *crtc_state1, const struct intel_crtc_state *crtc_state2) { + /* + * FIXME the modeset sequence is currently wrong and + * can't deal with bigjoiner + port sync at the same time. + */ return crtc_state1->hw.active && crtc_state2->hw.active && + !crtc_state1->bigjoiner_pipes && !crtc_state2->bigjoiner_pipes && crtc_state1->output_types == crtc_state2->output_types && crtc_state1->output_format == crtc_state2->output_format && crtc_state1->lane_count == crtc_state2->lane_count && diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h index fe42688137863..9b1bce2624b9e 100644 --- a/drivers/gpu/drm/i915/display/intel_display_device.h +++ b/drivers/gpu/drm/i915/display/intel_display_device.h @@ -47,6 +47,7 @@ struct drm_printer; #define HAS_DPT(i915) (DISPLAY_VER(i915) >= 13) #define HAS_DSB(i915) (DISPLAY_INFO(i915)->has_dsb) #define HAS_DSC(__i915) (DISPLAY_RUNTIME_INFO(__i915)->has_dsc) +#define HAS_DSC_MST(__i915) (DISPLAY_VER(__i915) >= 12 && HAS_DSC(__i915)) #define HAS_FBC(i915) (DISPLAY_RUNTIME_INFO(i915)->fbc_mask != 0) #define HAS_FPGA_DBG_UNCLAIMED(i915) (DISPLAY_INFO(i915)->has_fpga_dbg) #define HAS_FW_BLC(i915) (DISPLAY_VER(i915) >= 3) diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c index 9df9097a0255a..9382d99248b64 100644 --- a/drivers/gpu/drm/i915/display/intel_display_driver.c +++ b/drivers/gpu/drm/i915/display/intel_display_driver.c @@ -394,6 +394,8 @@ void intel_display_driver_register(struct drm_i915_private *i915) intel_audio_init(i915); + intel_audio_register(i915); + intel_display_debugfs_register(i915); /* diff --git a/drivers/gpu/drm/i915/display/intel_display_trace.h b/drivers/gpu/drm/i915/display/intel_display_trace.h index 99bdb833591ce..7862e7cefe027 100644 --- a/drivers/gpu/drm/i915/display/intel_display_trace.h +++ b/drivers/gpu/drm/i915/display/intel_display_trace.h @@ -411,7 +411,7 @@ TRACE_EVENT(intel_fbc_activate, struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); __assign_str(dev, __dev_name_kms(plane)); - __assign_str(name, plane->base.name) + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); @@ -438,7 +438,7 @@ TRACE_EVENT(intel_fbc_deactivate, struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); __assign_str(dev, __dev_name_kms(plane)); - __assign_str(name, plane->base.name) + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); @@ -465,7 +465,7 @@ TRACE_EVENT(intel_fbc_nuke, struct intel_crtc *crtc = intel_crtc_for_pipe(to_i915(plane->base.dev), plane->pipe); __assign_str(dev, __dev_name_kms(plane)); - __assign_str(name, plane->base.name) + __assign_str(name, plane->base.name); __entry->pipe = crtc->pipe; __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index ac7fe6281afe3..1b754edb4ad7c 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -719,6 +719,7 @@ struct intel_plane_state { #define PLANE_HAS_FENCE BIT(0) struct intel_fb_view view; + u32 phys_dma_addr; /* for cursor_needs_physical */ /* Plane pxp decryption state */ bool decrypt; @@ -1715,8 +1716,15 @@ struct intel_psr { bool psr2_sel_fetch_cff_enabled; bool req_psr2_sdp_prior_scanline; u8 sink_sync_latency; - u8 io_wake_lines; - u8 fast_wake_lines; + + struct { + u8 io_wake_lines; + u8 fast_wake_lines; + + /* LNL and beyond */ + u8 check_entry_lines; + } alpm_parameters; + ktime_t last_entry_attempt; ktime_t last_exit; bool sink_not_reliable; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 94d2a15d8444a..4ebf899e4c40d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -434,6 +434,10 @@ bool intel_dp_can_bigjoiner(struct intel_dp *intel_dp) struct intel_encoder *encoder = &intel_dig_port->base; struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + /* eDP MSO is not compatible with joiner */ + if (intel_dp->mso_link_count) + return false; + return DISPLAY_VER(dev_priv) >= 12 || (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A); @@ -1422,7 +1426,8 @@ static bool intel_dp_source_supports_fec(struct intel_dp *intel_dp, if (DISPLAY_VER(dev_priv) >= 12) return true; - if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A) + if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A && + !intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST)) return true; return false; @@ -1915,8 +1920,9 @@ icl_dsc_compute_link_config(struct intel_dp *intel_dp, dsc_max_bpp = min(dsc_max_bpp, pipe_bpp - 1); for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp); i++) { - if (valid_dsc_bpp[i] < dsc_min_bpp || - valid_dsc_bpp[i] > dsc_max_bpp) + if (valid_dsc_bpp[i] < dsc_min_bpp) + continue; + if (valid_dsc_bpp[i] > dsc_max_bpp) break; ret = dsc_compute_link_config(intel_dp, @@ -2754,7 +2760,11 @@ intel_dp_drrs_compute_config(struct intel_connector *connector, intel_panel_downclock_mode(connector, &pipe_config->hw.adjusted_mode); int pixel_clock; - if (has_seamless_m_n(connector)) + /* + * FIXME all joined pipes share the same transcoder. + * Need to account for that when updating M/N live. + */ + if (has_seamless_m_n(connector) && !pipe_config->bigjoiner_pipes) pipe_config->update_m_n = true; if (!can_enable_drrs(connector, pipe_config, downclock_mode)) { @@ -6523,6 +6533,7 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, intel_connector->get_hw_state = intel_ddi_connector_get_hw_state; else intel_connector->get_hw_state = intel_connector_get_hw_state; + intel_connector->sync_state = intel_dp_connector_sync_state; if (!intel_edp_init_connector(intel_dp, intel_connector)) { intel_dp_aux_fini(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c index 2e2af71bcd5a8..375cce5bfc68c 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c @@ -142,9 +142,15 @@ static int intel_dp_aux_sync_len(void) return precharge + preamble; } -static int intel_dp_aux_fw_sync_len(void) +int intel_dp_aux_fw_sync_len(void) { - int precharge = 10; /* 10-16 */ + /* + * We faced some glitches on Dell Precision 5490 MTL laptop with panel: + * "Manufacturer: AUO, Model: 63898" when using HW default 18. Using 20 + * is fixing these problems with the panel. It is still within range + * mentioned in eDP specification. + */ + int precharge = 12; /* 10-16 */ int preamble = 8; return precharge + preamble; diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.h b/drivers/gpu/drm/i915/display/intel_dp_aux.h index 8447f3e601fe4..76d1f2ed7c2f4 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux.h +++ b/drivers/gpu/drm/i915/display/intel_dp_aux.h @@ -20,5 +20,6 @@ enum aux_ch intel_dp_aux_ch(struct intel_encoder *encoder); void intel_dp_aux_irq_handler(struct drm_i915_private *i915); u32 intel_dp_aux_pack(const u8 *src, int src_bytes); +int intel_dp_aux_fw_sync_len(void); #endif /* __INTEL_DP_AUX_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index a01a59f57ae55..e0f171012fcbf 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -1148,7 +1148,7 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state, if (first_mst_stream) intel_ddi_wait_for_fec_status(encoder, pipe_config, true); - drm_dp_add_payload_part2(&intel_dp->mst_mgr, &state->base, + drm_dp_add_payload_part2(&intel_dp->mst_mgr, drm_atomic_get_mst_payload_state(mst_state, connector->port)); if (DISPLAY_VER(dev_priv) >= 12) @@ -1338,7 +1338,7 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, return 0; } - if (DISPLAY_VER(dev_priv) >= 10 && + if (HAS_DSC_MST(dev_priv) && drm_dp_sink_supports_dsc(intel_connector->dp.dsc_dpcd)) { /* * TBD pass the connector BPC, diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index ef57dad1a9cb7..87deb135c9ccb 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -2509,7 +2509,7 @@ static void icl_wrpll_params_populate(struct skl_wrpll_params *params, static bool ehl_combo_pll_div_frac_wa_needed(struct drm_i915_private *i915) { - return (((IS_ELKHARTLAKE(i915) || IS_JASPERLAKE(i915)) && + return ((IS_ELKHARTLAKE(i915) && IS_DISPLAY_STEP(i915, STEP_B0, STEP_FOREVER)) || IS_TIGERLAKE(i915) || IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) && i915->display.dpll.ref_clks.nssc == 38400; @@ -3308,6 +3308,8 @@ static int icl_compute_tc_phy_dplls(struct intel_atomic_state *state, struct drm_i915_private *i915 = to_i915(state->base.dev); struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); struct icl_port_dpll *port_dpll = &crtc_state->icl_port_dplls[ICL_PORT_DPLL_DEFAULT]; struct skl_wrpll_params pll_params = {}; @@ -3326,7 +3328,11 @@ static int icl_compute_tc_phy_dplls(struct intel_atomic_state *state, return ret; /* this is mainly for the fastset check */ - icl_set_active_port_dpll(crtc_state, ICL_PORT_DPLL_MG_PHY); + if (old_crtc_state->shared_dpll && + old_crtc_state->shared_dpll->info->id == DPLL_ID_ICL_TBTPLL) + icl_set_active_port_dpll(crtc_state, ICL_PORT_DPLL_DEFAULT); + else + icl_set_active_port_dpll(crtc_state, ICL_PORT_DPLL_MG_PHY); crtc_state->port_clock = icl_ddi_mg_pll_get_freq(i915, NULL, &port_dpll->hw_state); @@ -4023,7 +4029,8 @@ static const struct intel_shared_dpll_funcs mg_pll_funcs = { static const struct dpll_info icl_plls[] = { { .name = "DPLL 0", .funcs = &combo_pll_funcs, .id = DPLL_ID_ICL_DPLL0, }, { .name = "DPLL 1", .funcs = &combo_pll_funcs, .id = DPLL_ID_ICL_DPLL1, }, - { .name = "TBT PLL", .funcs = &tbt_pll_funcs, .id = DPLL_ID_ICL_TBTPLL, }, + { .name = "TBT PLL", .funcs = &tbt_pll_funcs, .id = DPLL_ID_ICL_TBTPLL, + .flags = INTEL_DPLL_IS_ALT_PORT_DPLL, }, { .name = "MG PLL 1", .funcs = &mg_pll_funcs, .id = DPLL_ID_ICL_MGPLL1, }, { .name = "MG PLL 2", .funcs = &mg_pll_funcs, .id = DPLL_ID_ICL_MGPLL2, }, { .name = "MG PLL 3", .funcs = &mg_pll_funcs, .id = DPLL_ID_ICL_MGPLL3, }, @@ -4068,7 +4075,8 @@ static const struct intel_shared_dpll_funcs dkl_pll_funcs = { static const struct dpll_info tgl_plls[] = { { .name = "DPLL 0", .funcs = &combo_pll_funcs, .id = DPLL_ID_ICL_DPLL0, }, { .name = "DPLL 1", .funcs = &combo_pll_funcs, .id = DPLL_ID_ICL_DPLL1, }, - { .name = "TBT PLL", .funcs = &tbt_pll_funcs, .id = DPLL_ID_ICL_TBTPLL, }, + { .name = "TBT PLL", .funcs = &tbt_pll_funcs, .id = DPLL_ID_ICL_TBTPLL, + .flags = INTEL_DPLL_IS_ALT_PORT_DPLL, }, { .name = "TC PLL 1", .funcs = &dkl_pll_funcs, .id = DPLL_ID_ICL_MGPLL1, }, { .name = "TC PLL 2", .funcs = &dkl_pll_funcs, .id = DPLL_ID_ICL_MGPLL2, }, { .name = "TC PLL 3", .funcs = &dkl_pll_funcs, .id = DPLL_ID_ICL_MGPLL3, }, @@ -4141,7 +4149,8 @@ static const struct intel_dpll_mgr adls_pll_mgr = { static const struct dpll_info adlp_plls[] = { { .name = "DPLL 0", .funcs = &combo_pll_funcs, .id = DPLL_ID_ICL_DPLL0, }, { .name = "DPLL 1", .funcs = &combo_pll_funcs, .id = DPLL_ID_ICL_DPLL1, }, - { .name = "TBT PLL", .funcs = &tbt_pll_funcs, .id = DPLL_ID_ICL_TBTPLL, }, + { .name = "TBT PLL", .funcs = &tbt_pll_funcs, .id = DPLL_ID_ICL_TBTPLL, + .flags = INTEL_DPLL_IS_ALT_PORT_DPLL, }, { .name = "TC PLL 1", .funcs = &dkl_pll_funcs, .id = DPLL_ID_ICL_MGPLL1, }, { .name = "TC PLL 2", .funcs = &dkl_pll_funcs, .id = DPLL_ID_ICL_MGPLL2, }, { .name = "TC PLL 3", .funcs = &dkl_pll_funcs, .id = DPLL_ID_ICL_MGPLL3, }, @@ -4465,31 +4474,29 @@ verify_single_dpll_state(struct drm_i915_private *i915, struct intel_crtc *crtc, const struct intel_crtc_state *new_crtc_state) { - struct intel_dpll_hw_state dpll_hw_state; + struct intel_dpll_hw_state dpll_hw_state = {}; u8 pipe_mask; bool active; - memset(&dpll_hw_state, 0, sizeof(dpll_hw_state)); - - drm_dbg_kms(&i915->drm, "%s\n", pll->info->name); - active = intel_dpll_get_hw_state(i915, pll, &dpll_hw_state); if (!(pll->info->flags & INTEL_DPLL_ALWAYS_ON)) { I915_STATE_WARN(i915, !pll->on && pll->active_mask, - "pll in active use but not on in sw tracking\n"); + "%s: pll in active use but not on in sw tracking\n", + pll->info->name); I915_STATE_WARN(i915, pll->on && !pll->active_mask, - "pll is on but not used by any active pipe\n"); + "%s: pll is on but not used by any active pipe\n", + pll->info->name); I915_STATE_WARN(i915, pll->on != active, - "pll on state mismatch (expected %i, found %i)\n", - pll->on, active); + "%s: pll on state mismatch (expected %i, found %i)\n", + pll->info->name, pll->on, active); } if (!crtc) { I915_STATE_WARN(i915, pll->active_mask & ~pll->state.pipe_mask, - "more active pll users than references: 0x%x vs 0x%x\n", - pll->active_mask, pll->state.pipe_mask); + "%s: more active pll users than references: 0x%x vs 0x%x\n", + pll->info->name, pll->active_mask, pll->state.pipe_mask); return; } @@ -4498,21 +4505,30 @@ verify_single_dpll_state(struct drm_i915_private *i915, if (new_crtc_state->hw.active) I915_STATE_WARN(i915, !(pll->active_mask & pipe_mask), - "pll active mismatch (expected pipe %c in active mask 0x%x)\n", - pipe_name(crtc->pipe), pll->active_mask); + "%s: pll active mismatch (expected pipe %c in active mask 0x%x)\n", + pll->info->name, pipe_name(crtc->pipe), pll->active_mask); else I915_STATE_WARN(i915, pll->active_mask & pipe_mask, - "pll active mismatch (didn't expect pipe %c in active mask 0x%x)\n", - pipe_name(crtc->pipe), pll->active_mask); + "%s: pll active mismatch (didn't expect pipe %c in active mask 0x%x)\n", + pll->info->name, pipe_name(crtc->pipe), pll->active_mask); I915_STATE_WARN(i915, !(pll->state.pipe_mask & pipe_mask), - "pll enabled crtcs mismatch (expected 0x%x in 0x%x)\n", - pipe_mask, pll->state.pipe_mask); + "%s: pll enabled crtcs mismatch (expected 0x%x in 0x%x)\n", + pll->info->name, pipe_mask, pll->state.pipe_mask); I915_STATE_WARN(i915, pll->on && memcmp(&pll->state.hw_state, &dpll_hw_state, sizeof(dpll_hw_state)), - "pll hw state mismatch\n"); + "%s: pll hw state mismatch\n", + pll->info->name); +} + +static bool has_alt_port_dpll(const struct intel_shared_dpll *old_pll, + const struct intel_shared_dpll *new_pll) +{ + return old_pll && new_pll && old_pll != new_pll && + (old_pll->info->flags & INTEL_DPLL_IS_ALT_PORT_DPLL || + new_pll->info->flags & INTEL_DPLL_IS_ALT_PORT_DPLL); } void intel_shared_dpll_state_verify(struct intel_atomic_state *state, @@ -4534,11 +4550,15 @@ void intel_shared_dpll_state_verify(struct intel_atomic_state *state, struct intel_shared_dpll *pll = old_crtc_state->shared_dpll; I915_STATE_WARN(i915, pll->active_mask & pipe_mask, - "pll active mismatch (didn't expect pipe %c in active mask (0x%x))\n", - pipe_name(crtc->pipe), pll->active_mask); - I915_STATE_WARN(i915, pll->state.pipe_mask & pipe_mask, - "pll enabled crtcs mismatch (found pipe %c in enabled mask (0x%x))\n", - pipe_name(crtc->pipe), pll->state.pipe_mask); + "%s: pll active mismatch (didn't expect pipe %c in active mask (0x%x))\n", + pll->info->name, pipe_name(crtc->pipe), pll->active_mask); + + /* TC ports have both MG/TC and TBT PLL referenced simultaneously */ + I915_STATE_WARN(i915, !has_alt_port_dpll(old_crtc_state->shared_dpll, + new_crtc_state->shared_dpll) && + pll->state.pipe_mask & pipe_mask, + "%s: pll enabled crtcs mismatch (found pipe %c in enabled mask (0x%x))\n", + pll->info->name, pipe_name(crtc->pipe), pll->state.pipe_mask); } } diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h index 2e7ea0d8d3ffb..5cdec77cfd9d4 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h @@ -277,12 +277,16 @@ struct dpll_info { enum intel_display_power_domain power_domain; #define INTEL_DPLL_ALWAYS_ON (1 << 0) +#define INTEL_DPLL_IS_ALT_PORT_DPLL (1 << 1) /** * @flags: * * INTEL_DPLL_ALWAYS_ON * Inform the state checker that the DPLL is kept enabled even if * not in use by any CRTC. + * INTEL_DPLL_IS_ALT_PORT_DPLL + * Inform the state checker that the DPLL can be used as a fallback + * (for TC->TBT fallback). */ u32 flags; }; diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c index 482c28b5c2de5..54d9abeb2d8d6 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.c +++ b/drivers/gpu/drm/i915/display/intel_dsb.c @@ -340,6 +340,17 @@ static int intel_dsb_dewake_scanline(const struct intel_crtc_state *crtc_state) return max(0, vblank_start - intel_usecs_to_scanlines(adjusted_mode, latency)); } +static u32 dsb_chicken(struct intel_crtc *crtc) +{ + if (crtc->mode_flags & I915_MODE_FLAG_VRR) + return DSB_CTRL_WAIT_SAFE_WINDOW | + DSB_CTRL_NO_WAIT_VBLANK | + DSB_INST_WAIT_SAFE_WINDOW | + DSB_INST_NO_WAIT_VBLANK; + else + return 0; +} + static void _intel_dsb_commit(struct intel_dsb *dsb, u32 ctrl, int dewake_scanline) { @@ -361,6 +372,9 @@ static void _intel_dsb_commit(struct intel_dsb *dsb, u32 ctrl, intel_de_write_fw(dev_priv, DSB_CTRL(pipe, dsb->id), ctrl | DSB_ENABLE); + intel_de_write_fw(dev_priv, DSB_CHICKEN(pipe, dsb->id), + dsb_chicken(crtc)); + intel_de_write_fw(dev_priv, DSB_HEAD(pipe, dsb->id), intel_dsb_buffer_ggtt_offset(&dsb->dsb_buf)); diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c index 7b42aef37d2f7..b6df9baf481b6 100644 --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -255,6 +255,16 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state) return PTR_ERR(vma); plane_state->ggtt_vma = vma; + + /* + * Pre-populate the dma address before we enter the vblank + * evade critical section as i915_gem_object_get_dma_address() + * will trigger might_sleep() even if it won't actually sleep, + * which is the case when the fb has already been pinned. + */ + if (phys_cursor) + plane_state->phys_dma_addr = + i915_gem_object_get_dma_address(intel_fb_obj(fb), 0); } else { struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); diff --git a/drivers/gpu/drm/i915/display/intel_lpe_audio.c b/drivers/gpu/drm/i915/display/intel_lpe_audio.c index 5863763de5306..df48cfb2826e0 100644 --- a/drivers/gpu/drm/i915/display/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/display/intel_lpe_audio.c @@ -177,6 +177,14 @@ static int lpe_audio_irq_init(struct drm_i915_private *dev_priv) handle_simple_irq, "hdmi_lpe_audio_irq_handler"); + static const struct pci_device_id irq_quirk_ids[] = { + /* Dell Wyse 3040 */ + {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, 0x22b0, 0x1028, 0x07c1)}, + {} + }; + + if (pci_dev_present(irq_quirk_ids)) + return 0; return irq_set_chip_data(irq, dev_priv); } diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 4faaf4b3fc53b..0ab4e70462ea0 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -762,8 +762,8 @@ static u32 intel_psr2_get_tp_time(struct intel_dp *intel_dp) static int psr2_block_count_lines(struct intel_dp *intel_dp) { - return intel_dp->psr.io_wake_lines < 9 && - intel_dp->psr.fast_wake_lines < 9 ? 8 : 12; + return intel_dp->psr.alpm_parameters.io_wake_lines < 9 && + intel_dp->psr.alpm_parameters.fast_wake_lines < 9 ? 8 : 12; } static int psr2_block_count(struct intel_dp *intel_dp) @@ -800,6 +800,7 @@ static void dg2_activate_panel_replay(struct intel_dp *intel_dp) static void hsw_activate_psr2(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + struct intel_psr *psr = &intel_dp->psr; enum transcoder cpu_transcoder = intel_dp->psr.transcoder; u32 val = EDP_PSR2_ENABLE; u32 psr_val = 0; @@ -841,17 +842,18 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) */ int tmp; - tmp = map[intel_dp->psr.io_wake_lines - TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES]; + tmp = map[psr->alpm_parameters.io_wake_lines - + TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES]; val |= TGL_EDP_PSR2_IO_BUFFER_WAKE(tmp + TGL_EDP_PSR2_IO_BUFFER_WAKE_MIN_LINES); - tmp = map[intel_dp->psr.fast_wake_lines - TGL_EDP_PSR2_FAST_WAKE_MIN_LINES]; + tmp = map[psr->alpm_parameters.fast_wake_lines - TGL_EDP_PSR2_FAST_WAKE_MIN_LINES]; val |= TGL_EDP_PSR2_FAST_WAKE(tmp + TGL_EDP_PSR2_FAST_WAKE_MIN_LINES); } else if (DISPLAY_VER(dev_priv) >= 12) { - val |= TGL_EDP_PSR2_IO_BUFFER_WAKE(intel_dp->psr.io_wake_lines); - val |= TGL_EDP_PSR2_FAST_WAKE(intel_dp->psr.fast_wake_lines); + val |= TGL_EDP_PSR2_IO_BUFFER_WAKE(psr->alpm_parameters.io_wake_lines); + val |= TGL_EDP_PSR2_FAST_WAKE(psr->alpm_parameters.fast_wake_lines); } else if (DISPLAY_VER(dev_priv) >= 9) { - val |= EDP_PSR2_IO_BUFFER_WAKE(intel_dp->psr.io_wake_lines); - val |= EDP_PSR2_FAST_WAKE(intel_dp->psr.fast_wake_lines); + val |= EDP_PSR2_IO_BUFFER_WAKE(psr->alpm_parameters.io_wake_lines); + val |= EDP_PSR2_FAST_WAKE(psr->alpm_parameters.fast_wake_lines); } if (intel_dp->psr.req_psr2_sdp_prior_scanline) @@ -1101,26 +1103,76 @@ static bool _compute_psr2_sdp_prior_scanline_indication(struct intel_dp *intel_d return true; } -static bool _compute_psr2_wake_times(struct intel_dp *intel_dp, +static bool _lnl_compute_alpm_params(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + int check_entry_lines; + + if (DISPLAY_VER(i915) < 20) + return true; + + /* ALPM Entry Check = 2 + CEILING( 5us /tline ) */ + check_entry_lines = 2 + + intel_usecs_to_scanlines(&crtc_state->hw.adjusted_mode, 5); + + if (check_entry_lines > 15) + return false; + + if (i915->display.params.psr_safest_params) + check_entry_lines = 15; + + intel_dp->psr.alpm_parameters.check_entry_lines = check_entry_lines; + + return true; +} + +/* + * IO wake time for DISPLAY_VER < 12 is not directly mentioned in Bspec. There + * are 50 us io wake time and 32 us fast wake time. Clearly preharge pulses are + * not (improperly) included in 32 us fast wake time. 50 us - 32 us = 18 us. + */ +static int skl_io_buffer_wake_time(void) +{ + return 18; +} + +static int tgl_io_buffer_wake_time(void) +{ + return 10; +} + +static int io_buffer_wake_time(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + + if (DISPLAY_VER(i915) >= 12) + return tgl_io_buffer_wake_time(); + else + return skl_io_buffer_wake_time(); +} + +static bool _compute_alpm_params(struct intel_dp *intel_dp, + struct intel_crtc_state *crtc_state) { struct drm_i915_private *i915 = dp_to_i915(intel_dp); int io_wake_lines, io_wake_time, fast_wake_lines, fast_wake_time; + int tfw_exit_latency = 20; /* eDP spec */ + int phy_wake = 4; /* eDP spec */ + int preamble = 8; /* eDP spec */ + int precharge = intel_dp_aux_fw_sync_len() - preamble; u8 max_wake_lines; - if (DISPLAY_VER(i915) >= 12) { - io_wake_time = 42; - /* - * According to Bspec it's 42us, but based on testing - * it is not enough -> use 45 us. - */ - fast_wake_time = 45; + io_wake_time = max(precharge, io_buffer_wake_time(crtc_state)) + + preamble + phy_wake + tfw_exit_latency; + fast_wake_time = precharge + preamble + phy_wake + + tfw_exit_latency; + + if (DISPLAY_VER(i915) >= 12) + /* TODO: Check how we can use ALPM_CTL fast wake extended field */ max_wake_lines = 12; - } else { - io_wake_time = 50; - fast_wake_time = 32; + else max_wake_lines = 8; - } io_wake_lines = intel_usecs_to_scanlines( &crtc_state->hw.adjusted_mode, io_wake_time); @@ -1131,12 +1183,15 @@ static bool _compute_psr2_wake_times(struct intel_dp *intel_dp, fast_wake_lines > max_wake_lines) return false; + if (!_lnl_compute_alpm_params(intel_dp, crtc_state)) + return false; + if (i915->display.params.psr_safest_params) io_wake_lines = fast_wake_lines = max_wake_lines; /* According to Bspec lower limit should be set as 7 lines. */ - intel_dp->psr.io_wake_lines = max(io_wake_lines, 7); - intel_dp->psr.fast_wake_lines = max(fast_wake_lines, 7); + intel_dp->psr.alpm_parameters.io_wake_lines = max(io_wake_lines, 7); + intel_dp->psr.alpm_parameters.fast_wake_lines = max(fast_wake_lines, 7); return true; } @@ -1268,7 +1323,7 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, return false; } - if (!_compute_psr2_wake_times(intel_dp, crtc_state)) { + if (!_compute_alpm_params(intel_dp, crtc_state)) { drm_dbg_kms(&dev_priv->drm, "PSR2 not enabled, Unable to use long enough wake times\n"); return false; @@ -1368,6 +1423,17 @@ void intel_psr_compute_config(struct intel_dp *intel_dp, return; } + /* + * FIXME figure out what is wrong with PSR+bigjoiner and + * fix it. Presumably something related to the fact that + * PSR is a transcoder level feature. + */ + if (crtc_state->bigjoiner_pipes) { + drm_dbg_kms(&dev_priv->drm, + "PSR disabled due to bigjoiner\n"); + return; + } + if (CAN_PANEL_REPLAY(intel_dp)) crtc_state->has_panel_replay = true; else @@ -1504,6 +1570,21 @@ static void wm_optimization_wa(struct intel_dp *intel_dp, wa_16013835468_bit_get(intel_dp), 0); } +static void lnl_alpm_configure(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + enum transcoder cpu_transcoder = intel_dp->psr.transcoder; + struct intel_psr *psr = &intel_dp->psr; + + if (DISPLAY_VER(dev_priv) < 20) + return; + + intel_de_write(dev_priv, ALPM_CTL(cpu_transcoder), + ALPM_CTL_EXTENDED_FAST_WAKE_ENABLE | + ALPM_CTL_ALPM_ENTRY_CHECK(psr->alpm_parameters.check_entry_lines) | + ALPM_CTL_EXTENDED_FAST_WAKE_TIME(psr->alpm_parameters.fast_wake_lines)); +} + static void intel_psr_enable_source(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state) { @@ -1569,6 +1650,8 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp, intel_dp->psr.psr2_sel_fetch_enabled ? IGNORE_PSR2_HW_TRACKING : 0); + lnl_alpm_configure(intel_dp); + /* * Wa_16013835468 * Wa_14015648006 diff --git a/drivers/gpu/drm/i915/display/intel_psr_regs.h b/drivers/gpu/drm/i915/display/intel_psr_regs.h index efe4306b37e0c..83edb4764a822 100644 --- a/drivers/gpu/drm/i915/display/intel_psr_regs.h +++ b/drivers/gpu/drm/i915/display/intel_psr_regs.h @@ -290,4 +290,61 @@ _SEL_FETCH_PLANE_OFFSET_1_A - \ _SEL_FETCH_PLANE_BASE_1_A) +#define _ALPM_CTL_A 0x60950 +#define ALPM_CTL(tran) _MMIO_TRANS2(tran, _ALPM_CTL_A) +#define ALPM_CTL_ALPM_ENABLE REG_BIT(31) +#define ALPM_CTL_ALPM_AUX_LESS_ENABLE REG_BIT(30) +#define ALPM_CTL_LOBF_ENABLE REG_BIT(29) +#define ALPM_CTL_EXTENDED_FAST_WAKE_ENABLE REG_BIT(28) +#define ALPM_CTL_KEEP_FEC_ENABLE_FOR_AUX_WAKE_SLEEP REG_BIT(27) +#define ALPM_CTL_RESTORE_OCCURED REG_BIT(26) +#define ALPM_CTL_RESTORE_TO_SLEEP REG_BIT(25) +#define ALPM_CTL_RESTORE_TO_DEEP_SLEEP REG_BIT(24) +#define ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_MASK REG_GENMASK(23, 21) +#define ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_50_SYMBOLS REG_FIELD_PREP(ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_MASK, 0) +#define ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_128_SYMBOLS REG_FIELD_PREP(ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_MASK, 1) +#define ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_256_SYMBOLS REG_FIELD_PREP(ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_MASK, 2) +#define ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_512_SYMBOLS REG_FIELD_PREP(ALPM_CTL_AUX_LESS_SLEEP_HOLD_TIME_MASK, 3) +#define ALPM_CTL_AUX_WAKE_SLEEP_HOLD_ENABLE REG_BIT(20) +#define ALPM_CTL_ALPM_ENTRY_CHECK_MASK REG_GENMASK(19, 16) +#define ALPM_CTL_ALPM_ENTRY_CHECK(val) REG_FIELD_PREP(ALPM_CTL_ALPM_ENTRY_CHECK_MASK, val) +#define ALPM_CTL_EXTENDED_FAST_WAKE_TIME_MASK REG_GENMASK(13, 8) +#define ALPM_CTL_EXTENDED_FAST_WAKE_MIN_LINES 5 +#define ALPM_CTL_EXTENDED_FAST_WAKE_TIME(lines) REG_FIELD_PREP(ALPM_CTL_EXTENDED_FAST_WAKE_TIME_MASK, (lines) - ALPM_CTL_EXTENDED_FAST_WAKE_MIN_LINES) +#define ALPM_CTL_AUX_LESS_WAKE_TIME_MASK REG_GENMASK(5, 0) +#define ALPM_CTL_AUX_LESS_WAKE_TIME(val) REG_FIELD_PREP(ALPM_CTL_AUX_LESS_WAKE_TIME_MASK, val) + +#define _ALPM_CTL2_A 0x60954 +#define ALPM_CTL2(tran) _MMIO_TRANS2(tran, _ALPM_CTL2_A) +#define ALPM_CTL2_SWITCH_TO_ACTIVE_LATENCY_MASK REG_GENMASK(28, 24) +#define ALPM_CTL2_SWITCH_TO_ACTIVE_LATENCY(val) REG_FIELD_PREP(ALPM_CTL2_SWITCH_TO_ACTIVE_LATENCY_MASK, val) +#define ALPM_CTL2_AUX_LESS_WAKE_TIME_EXTENSION_MASK REG_GENMASK(19, 16) +#define ALPM_CTL2_AUX_LESS_WAKE_TIME_EXTENSION(val) REG_FIELD_PREP(ALPM_CTL2_AUX_LESS_WAKE_TIME_EXTENSION_MASK, val) +#define ALPM_CTL2_NUMBER_OF_LTTPR_MASK REG_GENMASK(15, 12) +#define ALPM_CTL2_NUMBER_OF_LTTPR(val) REG_FIELD_PREP(ALPM_CTL2_NUMBER_OF_LTTPR_MASK, val) +#define ALPM_CTL2_LTTPR_AUX_LESS_SLEEP_HOLD_TIME_MASK REG_GENMASK(10, 8) +#define ALPM_CTL2_LTTPR_AUX_LESS_SLEEP_HOLD_TIME(val) REG_FIELD_PREP(ALPM_CTL2_LTTPR_AUX_LESS_SLEEP_HOLD_TIME_MASK, val) +#define ALPM_CTL2_FEC_DECODE_EN_POSITION_AFTER_WAKE_SR REG_BIT(4) +#define ALPM_CTL2_NUMBER_AUX_LESS_ML_PHY_SLEEP_SEQUENCES_MASK REG_GENMASK(2, 0) +#define ALPM_CTL2_NUMBER_AUX_LESS_ML_PHY_SLEEP_SEQUENCES(val) REG_FIELD_PREP(ALPM_CTL2_NUMBER_AUX_LESS_ML_PHY_SLEEP_SEQUENCES_MASK, val) + +#define _PORT_ALPM_CTL_A 0x16fa2c +#define PORT_ALPM_CTL(tran) _MMIO_TRANS2(tran, _PORT_ALPM_CTL_A) +#define PORT_ALPM_CTL_ALPM_AUX_LESS_ENABLE REG_BIT(31) +#define PORT_ALPM_CTL_MAX_PHY_SWING_SETUP_MASK REG_GENMASK(23, 20) +#define PORT_ALPM_CTL_MAX_PHY_SWING_SETUP(val) REG_FIELD_PREP(PORT_ALPM_CTL_MAX_PHY_SWING_SETUP_MASK, val) +#define PORT_ALPM_CTL_MAX_PHY_SWING_HOLD_MASK REG_GENMASK(19, 16) +#define PORT_ALPM_CTL_MAX_PHY_SWING_HOLD(val) REG_FIELD_PREP(PORT_ALPM_CTL_MAX_PHY_SWING_HOLD_MASK, val) +#define PORT_ALPM_CTL_SILENCE_PERIOD_MASK REG_GENMASK(7, 0) +#define PORT_ALPM_CTL_SILENCE_PERIOD(val) REG_FIELD_PREP(PORT_ALPM_CTL_SILENCE_PERIOD_MASK, val) + +#define _PORT_ALPM_LFPS_CTL_A 0x16fa30 +#define PORT_ALPM_LFPS_CTL(tran) _MMIO_TRANS2(tran, _PORT_ALPM_LFPS_CTL_A) +#define PORT_ALPM_LFPS_CTL_LFPS_START_POLARITY REG_BIT(31) +#define PORT_ALPM_LFPS_CTL_LFPS_CYCLE_COUNT_MASK REG_GENMASK(27, 24) +#define ALPM_CTL_EXTENDED_FAST_WAKE_MIN_LINES 5 +#define ALPM_CTL_EXTENDED_FAST_WAKE_TIME(lines) REG_FIELD_PREP(ALPM_CTL_EXTENDED_FAST_WAKE_TIME_MASK, (lines) - ALPM_CTL_EXTENDED_FAST_WAKE_MIN_LINES) +#define ALPM_CTL_AUX_LESS_WAKE_TIME_MASK REG_GENMASK(5, 0) +#define ALPM_CTL_AUX_LESS_WAKE_TIME(val) REG_FIELD_PREP(ALPM_CTL_AUX_LESS_WAKE_TIME_MASK, val) + #endif /* __INTEL_PSR_REGS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 2915d7afe5ccc..cc978ee6d1309 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1830,8 +1830,6 @@ static void intel_disable_sdvo(struct intel_atomic_state *state, struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); u32 temp; - encoder->audio_disable(encoder, old_crtc_state, conn_state); - intel_sdvo_set_active_outputs(intel_sdvo, 0); if (0) intel_sdvo_set_encoder_power_state(intel_sdvo, @@ -1923,8 +1921,6 @@ static void intel_enable_sdvo(struct intel_atomic_state *state, intel_sdvo_set_encoder_power_state(intel_sdvo, DRM_MODE_DPMS_ON); intel_sdvo_set_active_outputs(intel_sdvo, intel_sdvo_connector->output_flag); - - encoder->audio_enable(encoder, pipe_config, conn_state); } static enum drm_mode_status diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index a9f44abfc9fc2..b50cd0dcabda9 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -897,11 +897,6 @@ struct lfp_brightness_level { u16 reserved; } __packed; -#define EXP_BDB_LFP_BL_DATA_SIZE_REV_191 \ - offsetof(struct bdb_lfp_backlight_data, brightness_level) -#define EXP_BDB_LFP_BL_DATA_SIZE_REV_234 \ - offsetof(struct bdb_lfp_backlight_data, brightness_precision_bits) - struct bdb_lfp_backlight_data { u8 entry_size; struct lfp_backlight_data_entry data[16]; diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index 5d905f932cb4b..f542ee1db1d97 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -117,6 +117,13 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state, const struct drm_display_info *info = &connector->base.display_info; int vmin, vmax; + /* + * FIXME all joined pipes share the same transcoder. + * Need to account for that during VRR toggle/push/etc. + */ + if (crtc_state->bigjoiner_pipes) + return; + if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) return; @@ -187,10 +194,11 @@ void intel_vrr_set_transcoder_timings(const struct intel_crtc_state *crtc_state) enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; /* - * TRANS_SET_CONTEXT_LATENCY with VRR enabled - * requires this chicken bit on ADL/DG2. + * This bit seems to have two meanings depending on the platform: + * TGL: generate VRR "safe window" for DSB vblank waits + * ADL/DG2: make TRANS_SET_CONTEXT_LATENCY effective with VRR */ - if (DISPLAY_VER(dev_priv) == 13) + if (IS_DISPLAY_VER(dev_priv, 12, 13)) intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder), 0, PIPE_VBLANK_WITH_DELAY); diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index 511dc1544854f..8bba6c2e50989 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -2290,6 +2290,9 @@ static u8 skl_get_plane_caps(struct drm_i915_private *i915, if (HAS_4TILE(i915)) caps |= INTEL_PLANE_CAP_TILING_4; + if (!IS_ENABLED(I915) && !HAS_FLAT_CCS(i915)) + return caps; + if (skl_plane_has_rc_ccs(i915, pipe, plane_id)) { caps |= INTEL_PLANE_CAP_CCS_RC; if (DISPLAY_VER(i915) >= 12) diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index 56588d6e24ae6..706f5afbbab4e 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -63,7 +63,7 @@ static bool skl_needs_memory_bw_wa(struct drm_i915_private *i915) return DISPLAY_VER(i915) == 9; } -static bool +bool intel_has_sagv(struct drm_i915_private *i915) { return HAS_SAGV(i915) && diff --git a/drivers/gpu/drm/i915/display/skl_watermark.h b/drivers/gpu/drm/i915/display/skl_watermark.h index fb0da36fd3ec3..4cca93cd83ad3 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.h +++ b/drivers/gpu/drm/i915/display/skl_watermark.h @@ -25,6 +25,7 @@ void intel_sagv_pre_plane_update(struct intel_atomic_state *state); void intel_sagv_post_plane_update(struct intel_atomic_state *state); bool intel_can_enable_sagv(struct drm_i915_private *i915, const struct intel_bw_state *bw_state); +bool intel_has_sagv(struct drm_i915_private *i915); u32 skl_ddb_dbuf_slice_mask(struct drm_i915_private *i915, const struct skl_ddb_entry *entry); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 3560a062d2872..5d7446a48ae79 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -284,7 +284,9 @@ bool i915_gem_object_has_iomem(const struct drm_i915_gem_object *obj); static inline bool i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj) { - return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE); + /* TODO: make DPT shrinkable when it has no bound vmas */ + return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE) && + !obj->is_dpt; } static inline bool diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 8c88075eeab23..adf37f97352b6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -944,7 +944,11 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, dsm_size = ALIGN_DOWN(lmem_size - dsm_base, SZ_1M); } - if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) { + if (i915_direct_stolen_access(i915)) { + drm_dbg(&i915->drm, "Using direct DSM access\n"); + io_start = intel_uncore_read64(uncore, GEN12_DSMBASE) & GEN12_BDSM_MASK; + io_size = dsm_size; + } else if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) { io_start = 0; io_size = 0; } else { diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 86a04afff64b3..e1bf13e3d3070 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -226,7 +226,7 @@ u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs) static int mtl_dummy_pipe_control(struct i915_request *rq) { /* Wa_14016712196 */ - if (IS_GFX_GT_IP_RANGE(rq->engine->gt, IP_VER(12, 70), IP_VER(12, 71)) || + if (IS_GFX_GT_IP_RANGE(rq->engine->gt, IP_VER(12, 70), IP_VER(12, 74)) || IS_DG2(rq->i915)) { u32 *cs; @@ -822,7 +822,7 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs) flags |= PIPE_CONTROL_FLUSH_L3; /* Wa_14016712196 */ - if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)) || IS_DG2(i915)) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)) || IS_DG2(i915)) /* dummy PIPE_CONTROL + depth flush */ cs = gen12_emit_pipe_control(cs, 0, PIPE_CONTROL_DEPTH_CACHE_FLUSH, 0); diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index fa46d2308b0ed..81bf2216371be 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -961,6 +961,9 @@ static int gen8_init_rsvd(struct i915_address_space *vm) struct i915_vma *vma; int ret; + if (!intel_gt_needs_wa_16018031267(vm->gt)) + return 0; + /* The memory will be used only by GPU. */ obj = i915_gem_object_create_lmem(i915, PAGE_SIZE, I915_BO_ALLOC_VOLATILE | diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index d650beb8ed22f..20b9b04ec1e0b 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -263,8 +263,13 @@ static void signal_irq_work(struct irq_work *work) i915_request_put(rq); } + /* Lazy irq enabling after HW submission */ if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers)) intel_breadcrumbs_arm_irq(b); + + /* And confirm that we still want irqs enabled before we yield */ + if (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) + intel_breadcrumbs_disarm_irq(b); } struct intel_breadcrumbs * @@ -315,13 +320,7 @@ void __intel_breadcrumbs_park(struct intel_breadcrumbs *b) return; /* Kick the work once more to drain the signalers, and disarm the irq */ - irq_work_sync(&b->irq_work); - while (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) { - local_irq_disable(); - signal_irq_work(&b->irq_work); - local_irq_enable(); - cond_resched(); - } + irq_work_queue(&b->irq_work); } void intel_breadcrumbs_free(struct kref *kref) @@ -404,7 +403,7 @@ static void insert_breadcrumb(struct i915_request *rq) * the request as it may have completed and raised the interrupt as * we were attaching it into the lists. */ - if (!b->irq_armed || __i915_request_is_complete(rq)) + if (!READ_ONCE(b->irq_armed) || __i915_request_is_complete(rq)) irq_work_queue(&b->irq_work); } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 40687806d22a6..e379eabeaa662 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -908,6 +908,29 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) info->engine_mask &= ~BIT(GSC0); } + /* + * Do not create the command streamer for CCS slices beyond the first. + * All the workload submitted to the first engine will be shared among + * all the slices. + * + * Once the user will be allowed to customize the CCS mode, then this + * check needs to be removed. + */ + if (IS_DG2(gt->i915)) { + u8 first_ccs = __ffs(CCS_MASK(gt)); + + /* + * Store the number of active cslices before + * changing the CCS engine configuration + */ + gt->ccs.cslices = CCS_MASK(gt); + + /* Mask off all the CCS engine */ + info->engine_mask &= ~GENMASK(CCS3, CCS0); + /* Put back in the first CCS engine */ + info->engine_mask |= BIT(_CCS(first_ccs)); + } + return info->engine_mask; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index 96bdb93a948d1..fb7bff27b45a3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -279,9 +279,6 @@ static int __engine_park(struct intel_wakeref *wf) intel_engine_park_heartbeat(engine); intel_breadcrumbs_park(engine->breadcrumbs); - /* Must be reset upon idling, or we may miss the busy wakeup. */ - GEM_BUG_ON(engine->sched_engine->queue_priority_hint != INT_MIN); - if (engine->park) engine->park(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 42aade0faf2d1..b061a0a0d6b08 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3272,6 +3272,9 @@ static void execlists_park(struct intel_engine_cs *engine) { cancel_timer(&engine->execlists.timer); cancel_timer(&engine->execlists.preempt); + + /* Reset upon idling, or we may delay the busy wakeup. */ + WRITE_ONCE(engine->sched_engine->queue_priority_hint, INT_MIN); } static void add_to_engine(struct i915_request *rq) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 21a7e3191c182..bce5d80253401 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -24,6 +24,7 @@ #include "intel_ring.h" #include "i915_drv.h" #include "i915_pci.h" +#include "i915_reg.h" #include "i915_request.h" #include "i915_scatterlist.h" #include "i915_utils.h" @@ -1152,13 +1153,20 @@ static unsigned int gen6_gttadr_offset(struct drm_i915_private *i915) static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) { struct drm_i915_private *i915 = ggtt->vm.i915; + struct intel_uncore *uncore = ggtt->vm.gt->uncore; struct pci_dev *pdev = to_pci_dev(i915->drm.dev); phys_addr_t phys_addr; u32 pte_flags; int ret; GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915)); - phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915); + + if (i915_direct_stolen_access(i915)) { + drm_dbg(&i915->drm, "Using direct GSM access\n"); + phys_addr = intel_uncore_read64(uncore, GEN12_GSMBASE) & GEN12_BDSM_MASK; + } else { + phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915); + } if (needs_wc_ggtt_mapping(i915)) ggtt->gsm = ioremap_wc(phys_addr, size); diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index a425db5ed3a22..6a2c2718bcc38 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -1024,6 +1024,12 @@ enum i915_map_type intel_gt_coherent_map_type(struct intel_gt *gt, return I915_MAP_WC; } +bool intel_gt_needs_wa_16018031267(struct intel_gt *gt) +{ + /* Wa_16018031267, Wa_16018063123 */ + return IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 55), IP_VER(12, 71)); +} + bool intel_gt_needs_wa_22016122933(struct intel_gt *gt) { return MEDIA_VER_FULL(gt->i915) == IP_VER(13, 0) && gt->type == GT_MEDIA; diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 608f5c8729285..003eb93b826fd 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -82,17 +82,18 @@ struct drm_printer; ##__VA_ARGS__); \ } while (0) -#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \ - IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 55), IP_VER(12, 71)) && \ - engine->class == COPY_ENGINE_CLASS && engine->instance == 0) - static inline bool gt_is_root(struct intel_gt *gt) { return !gt->info.id; } +bool intel_gt_needs_wa_16018031267(struct intel_gt *gt); bool intel_gt_needs_wa_22016122933(struct intel_gt *gt); +#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \ + intel_gt_needs_wa_16018031267(engine->gt) && \ + engine->class == COPY_ENGINE_CLASS && engine->instance == 0) + static inline struct intel_gt *uc_to_gt(struct intel_uc *uc) { return container_of(uc, struct intel_gt, uc); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c new file mode 100644 index 0000000000000..3c62a44e9106c --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ + +#include "i915_drv.h" +#include "intel_gt.h" +#include "intel_gt_ccs_mode.h" +#include "intel_gt_regs.h" + +unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt) +{ + int cslice; + u32 mode = 0; + int first_ccs = __ffs(CCS_MASK(gt)); + + if (!IS_DG2(gt->i915)) + return 0; + + /* Build the value for the fixed CCS load balancing */ + for (cslice = 0; cslice < I915_MAX_CCS; cslice++) { + if (gt->ccs.cslices & BIT(cslice)) + /* + * If available, assign the cslice + * to the first available engine... + */ + mode |= XEHP_CCS_MODE_CSLICE(cslice, first_ccs); + + else + /* + * ... otherwise, mark the cslice as + * unavailable if no CCS dispatches here + */ + mode |= XEHP_CCS_MODE_CSLICE(cslice, + XEHP_CCS_MODE_CSLICE_MASK); + } + + return mode; +} diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h new file mode 100644 index 0000000000000..55547f2ff426a --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#ifndef __INTEL_GT_CCS_MODE_H__ +#define __INTEL_GT_CCS_MODE_H__ + +struct intel_gt; + +unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt); + +#endif /* __INTEL_GT_CCS_MODE_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 50962cfd1353a..743fe35667227 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -1477,8 +1477,14 @@ #define ECOBITS_PPGTT_CACHE4B (0 << 8) #define GEN12_RCU_MODE _MMIO(0x14800) +#define XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE REG_BIT(1) #define GEN12_RCU_MODE_CCS_ENABLE REG_BIT(0) +#define XEHP_CCS_MODE _MMIO(0x14804) +#define XEHP_CCS_MODE_CSLICE_MASK REG_GENMASK(2, 0) /* CCS0-3 + rsvd */ +#define XEHP_CCS_MODE_CSLICE_WIDTH ilog2(XEHP_CCS_MODE_CSLICE_MASK + 1) +#define XEHP_CCS_MODE_CSLICE(cslice, ccs) (ccs << (cslice * XEHP_CCS_MODE_CSLICE_WIDTH)) + #define CHV_FUSE_GT _MMIO(VLV_GUNIT_BASE + 0x2168) #define CHV_FGT_DISABLE_SS0 (1 << 10) #define CHV_FGT_DISABLE_SS1 (1 << 11) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index def7dd0eb6f19..cfdd2ad5e9549 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -207,6 +207,14 @@ struct intel_gt { [MAX_ENGINE_INSTANCE + 1]; enum intel_submission_method submission_method; + struct { + /* + * Mask of the non fused CCS slices + * to be used for the load balancing + */ + intel_engine_mask_t cslices; + } ccs; + /* * Default address space (either GGTT or ppGTT depending on arch). * diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 3eacbc50caf8d..bc1b598d9a098 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -10,6 +10,7 @@ #include "intel_engine_regs.h" #include "intel_gpu_commands.h" #include "intel_gt.h" +#include "intel_gt_ccs_mode.h" #include "intel_gt_mcr.h" #include "intel_gt_print.h" #include "intel_gt_regs.h" @@ -51,7 +52,8 @@ * registers belonging to BCS, VCS or VECS should be implemented in * xcs_engine_wa_init(). Workarounds for registers not belonging to a specific * engine's MMIO range but that are part of of the common RCS/CCS reset domain - * should be implemented in general_render_compute_wa_init(). + * should be implemented in general_render_compute_wa_init(). The settings + * about the CCS load balancing should be added in ccs_engine_wa_mode(). * * - GT workarounds: the list of these WAs is applied whenever these registers * revert to their default values: on GPU reset, suspend/resume [1]_, etc. @@ -789,8 +791,13 @@ static void xelpg_ctx_gt_tuning_init(struct intel_engine_cs *engine, dg2_ctx_gt_tuning_init(engine, wal); - if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_B0, STEP_FOREVER) || - IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER)) + /* + * Due to Wa_16014892111, the DRAW_WATERMARK tuning must be done in + * gen12_emit_indirect_ctx_rcs() rather than here on some early + * steppings. + */ + if (!(IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0))) wa_add(wal, DRAW_WATERMARK, VERT_WM_VAL, 0x3FF, 0, false); } @@ -908,7 +915,7 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, if (engine->class != RENDER_CLASS) goto done; - if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71))) + if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 74))) xelpg_ctx_workarounds_init(engine, wal); else if (IS_PONTEVECCHIO(i915)) ; /* noop; none at this time */ @@ -1643,7 +1650,8 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) static void xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - /* Wa_14018778641 / Wa_18018781329 */ + /* Wa_14018575942 / Wa_18018781329 */ + wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB); /* Wa_22016670082 */ @@ -1710,7 +1718,7 @@ xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) */ static void gt_tuning_settings(struct intel_gt *gt, struct i915_wa_list *wal) { - if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) { + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74))) { wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS); } @@ -1743,7 +1751,7 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal) return; } - if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74))) xelpg_gt_workarounds_init(gt, wal); else if (IS_PONTEVECCHIO(i915)) pvc_gt_workarounds_init(gt, wal); @@ -2216,7 +2224,7 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) if (engine->gt->type == GT_MEDIA) ; /* none yet */ - else if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71))) + else if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 74))) xelpg_whitelist_build(engine); else if (IS_PONTEVECCHIO(i915)) pvc_whitelist_build(engine); @@ -2828,7 +2836,7 @@ add_render_compute_tuning_settings(struct intel_gt *gt, { struct drm_i915_private *i915 = gt->i915; - if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)) || IS_DG2(i915)) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74)) || IS_DG2(i915)) wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512); /* @@ -2844,6 +2852,30 @@ add_render_compute_tuning_settings(struct intel_gt *gt, wa_write_clr(wal, GEN8_GARBCNTL, GEN12_BUS_HASH_CTL_BIT_EXC); } +static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal) +{ + struct intel_gt *gt = engine->gt; + u32 mode; + + if (!IS_DG2(gt->i915)) + return; + + /* + * Wa_14019159160: This workaround, along with others, leads to + * significant challenges in utilizing load balancing among the + * CCS slices. Consequently, an architectural decision has been + * made to completely disable automatic CCS load balancing. + */ + wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE); + + /* + * After having disabled automatic load balancing we need to + * assign all slices to a single CCS. We will call it CCS mode 1 + */ + mode = intel_gt_apply_ccs_mode(gt); + wa_masked_en(wal, XEHP_CCS_MODE, mode); +} + /* * The workarounds in this function apply to shared registers in * the general render reset domain that aren't tied to a @@ -2881,7 +2913,8 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li } if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_B0, STEP_FOREVER) || - IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER)) + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER) || + IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 74), IP_VER(12, 74))) /* Wa_14017856879 */ wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN3, MTL_DISABLE_FIX_FOR_EOT_FLUSH); @@ -2993,8 +3026,10 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal * to a single RCS/CCS engine's workaround list since * they're reset as part of the general render domain reset. */ - if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) + if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) { general_render_compute_wa_init(engine, wal); + ccs_engine_wa_mode(engine, wal); + } if (engine->class == COMPUTE_CLASS) ccs_engine_wa_init(engine, wal); diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h index 58012edd4eb0e..4f4f53c42a9c5 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h @@ -29,9 +29,9 @@ */ #define GUC_KLV_LEN_MIN 1u -#define GUC_KLV_0_KEY (0xffff << 16) -#define GUC_KLV_0_LEN (0xffff << 0) -#define GUC_KLV_n_VALUE (0xffffffff << 0) +#define GUC_KLV_0_KEY (0xffffu << 16) +#define GUC_KLV_0_LEN (0xffffu << 0) +#define GUC_KLV_n_VALUE (0xffffffffu << 0) /** * DOC: GuC Self Config KLVs diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c index 0f79cb6585182..52332bb143395 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -184,7 +184,7 @@ static int guc_wait_ucode(struct intel_guc *guc) * in the seconds range. However, there is a limit on how long an * individual wait_for() can wait. So wrap it in a loop. */ - before_freq = intel_rps_read_actual_frequency(&uncore->gt->rps); + before_freq = intel_rps_read_actual_frequency(>->rps); before = ktime_get(); for (count = 0; count < GUC_LOAD_RETRY_LIMIT; count++) { ret = wait_for(guc_load_done(uncore, &status, &success), 1000); @@ -192,7 +192,7 @@ static int guc_wait_ucode(struct intel_guc *guc) break; guc_dbg(guc, "load still in progress, count = %d, freq = %dMHz, status = 0x%08X [0x%02X/%02X]\n", - count, intel_rps_read_actual_frequency(&uncore->gt->rps), status, + count, intel_rps_read_actual_frequency(>->rps), status, REG_FIELD_GET(GS_BOOTROM_MASK, status), REG_FIELD_GET(GS_UKERNEL_MASK, status)); } @@ -204,7 +204,7 @@ static int guc_wait_ucode(struct intel_guc *guc) u32 bootrom = REG_FIELD_GET(GS_BOOTROM_MASK, status); guc_info(guc, "load failed: status = 0x%08X, time = %lldms, freq = %dMHz, ret = %d\n", - status, delta_ms, intel_rps_read_actual_frequency(&uncore->gt->rps), ret); + status, delta_ms, intel_rps_read_actual_frequency(>->rps), ret); guc_info(guc, "load failed: status: Reset = %d, BootROM = 0x%02X, UKernel = 0x%02X, MIA = 0x%02X, Auth = 0x%02X\n", REG_FIELD_GET(GS_MIA_IN_RESET, status), bootrom, ukernel, @@ -254,11 +254,11 @@ static int guc_wait_ucode(struct intel_guc *guc) guc_warn(guc, "excessive init time: %lldms! [status = 0x%08X, count = %d, ret = %d]\n", delta_ms, status, count, ret); guc_warn(guc, "excessive init time: [freq = %dMHz, before = %dMHz, perf_limit_reasons = 0x%08X]\n", - intel_rps_read_actual_frequency(&uncore->gt->rps), before_freq, + intel_rps_read_actual_frequency(>->rps), before_freq, intel_uncore_read(uncore, intel_gt_perf_limit_reasons_reg(gt))); } else { guc_dbg(guc, "init took %lldms, freq = %dMHz, before = %dMHz, status = 0x%08X, count = %d, ret = %d\n", - delta_ms, intel_rps_read_actual_frequency(&uncore->gt->rps), + delta_ms, intel_rps_read_actual_frequency(>->rps), before_freq, status, count, ret); } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index ba9e07fc2b577..0945b177d5f97 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -6,6 +6,7 @@ #include #include "gt/intel_gt.h" +#include "gt/intel_rps.h" #include "intel_guc_reg.h" #include "intel_huc.h" #include "intel_huc_print.h" @@ -447,17 +448,68 @@ static const char *auth_mode_string(struct intel_huc *huc, return partial ? "clear media" : "all workloads"; } +/* + * Use a longer timeout for debug builds so that problems can be detected + * and analysed. But a shorter timeout for releases so that user's don't + * wait forever to find out there is a problem. Note that the only reason + * an end user should hit the timeout is in case of extreme thermal throttling. + * And a system that is that hot during boot is probably dead anyway! + */ +#if defined(CONFIG_DRM_I915_DEBUG_GEM) +#define HUC_LOAD_RETRY_LIMIT 20 +#else +#define HUC_LOAD_RETRY_LIMIT 3 +#endif + int intel_huc_wait_for_auth_complete(struct intel_huc *huc, enum intel_huc_authentication_type type) { struct intel_gt *gt = huc_to_gt(huc); - int ret; + struct intel_uncore *uncore = gt->uncore; + ktime_t before, after, delta; + int ret, count; + u64 delta_ms; + u32 before_freq; - ret = __intel_wait_for_register(gt->uncore, - huc->status[type].reg, - huc->status[type].mask, - huc->status[type].value, - 2, 50, NULL); + /* + * The KMD requests maximum frequency during driver load, however thermal + * throttling can force the frequency down to minimum (although the board + * really should never get that hot in real life!). IFWI issues have been + * seen to cause sporadic failures to grant the higher frequency. And at + * minimum frequency, the authentication time can be in the seconds range. + * Note that there is a limit on how long an individual wait_for() can wait. + * So wrap it in a loop. + */ + before_freq = intel_rps_read_actual_frequency(>->rps); + before = ktime_get(); + for (count = 0; count < HUC_LOAD_RETRY_LIMIT; count++) { + ret = __intel_wait_for_register(gt->uncore, + huc->status[type].reg, + huc->status[type].mask, + huc->status[type].value, + 2, 1000, NULL); + if (!ret) + break; + + huc_dbg(huc, "auth still in progress, count = %d, freq = %dMHz, status = 0x%08X\n", + count, intel_rps_read_actual_frequency(>->rps), + huc->status[type].reg.reg); + } + after = ktime_get(); + delta = ktime_sub(after, before); + delta_ms = ktime_to_ms(delta); + + if (delta_ms > 50) { + huc_warn(huc, "excessive auth time: %lldms! [status = 0x%08X, count = %d, ret = %d]\n", + delta_ms, huc->status[type].reg.reg, count, ret); + huc_warn(huc, "excessive auth time: [freq = %dMHz, before = %dMHz, perf_limit_reasons = 0x%08X]\n", + intel_rps_read_actual_frequency(>->rps), before_freq, + intel_uncore_read(uncore, intel_gt_perf_limit_reasons_reg(gt))); + } else { + huc_dbg(huc, "auth took %lldms, freq = %dMHz, before = %dMHz, status = 0x%08X, count = %d, ret = %d\n", + delta_ms, intel_rps_read_actual_frequency(>->rps), + before_freq, huc->status[type].reg.reg, count, ret); + } /* mark the load process as complete even if the wait failed */ delayed_huc_load_complete(huc); diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index c7d7c3b7ecc63..9967148aedf15 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -799,7 +799,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_cleanup_modeset2; ret = intel_pxp_init(i915); - if (ret != -ENODEV) + if (ret && ret != -ENODEV) drm_dbg(&i915->drm, "pxp init failed with %d\n", ret); ret = intel_display_driver_probe(i915); diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c index 8c3f443c8347e..c0662a022f59c 100644 --- a/drivers/gpu/drm/i915/i915_hwmon.c +++ b/drivers/gpu/drm/i915/i915_hwmon.c @@ -72,12 +72,13 @@ hwm_locked_with_pm_intel_uncore_rmw(struct hwm_drvdata *ddat, struct intel_uncore *uncore = ddat->uncore; intel_wakeref_t wakeref; - mutex_lock(&hwmon->hwmon_lock); + with_intel_runtime_pm(uncore->rpm, wakeref) { + mutex_lock(&hwmon->hwmon_lock); - with_intel_runtime_pm(uncore->rpm, wakeref) intel_uncore_rmw(uncore, reg, clear, set); - mutex_unlock(&hwmon->hwmon_lock); + mutex_unlock(&hwmon->hwmon_lock); + } } /* @@ -136,20 +137,21 @@ hwm_energy(struct hwm_drvdata *ddat, long *energy) else rgaddr = hwmon->rg.energy_status_all; - mutex_lock(&hwmon->hwmon_lock); + with_intel_runtime_pm(uncore->rpm, wakeref) { + mutex_lock(&hwmon->hwmon_lock); - with_intel_runtime_pm(uncore->rpm, wakeref) reg_val = intel_uncore_read(uncore, rgaddr); - if (reg_val >= ei->reg_val_prev) - ei->accum_energy += reg_val - ei->reg_val_prev; - else - ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val; - ei->reg_val_prev = reg_val; + if (reg_val >= ei->reg_val_prev) + ei->accum_energy += reg_val - ei->reg_val_prev; + else + ei->accum_energy += UINT_MAX - ei->reg_val_prev + reg_val; + ei->reg_val_prev = reg_val; - *energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY, - hwmon->scl_shift_energy); - mutex_unlock(&hwmon->hwmon_lock); + *energy = mul_u64_u32_shr(ei->accum_energy, SF_ENERGY, + hwmon->scl_shift_energy); + mutex_unlock(&hwmon->hwmon_lock); + } } static ssize_t @@ -404,6 +406,7 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val) /* Block waiting for GuC reset to complete when needed */ for (;;) { + wakeref = intel_runtime_pm_get(ddat->uncore->rpm); mutex_lock(&hwmon->hwmon_lock); prepare_to_wait(&ddat->waitq, &wait, TASK_INTERRUPTIBLE); @@ -417,14 +420,13 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val) } mutex_unlock(&hwmon->hwmon_lock); + intel_runtime_pm_put(ddat->uncore->rpm, wakeref); schedule(); } finish_wait(&ddat->waitq, &wait); if (ret) - goto unlock; - - wakeref = intel_runtime_pm_get(ddat->uncore->rpm); + goto exit; /* Disable PL1 limit and verify, because the limit cannot be disabled on all platforms */ if (val == PL1_DISABLE) { @@ -444,9 +446,8 @@ hwm_power_max_write(struct hwm_drvdata *ddat, long val) intel_uncore_rmw(ddat->uncore, hwmon->rg.pkg_rapl_limit, PKG_PWR_LIM_1_EN | PKG_PWR_LIM_1, nval); exit: - intel_runtime_pm_put(ddat->uncore->rpm, wakeref); -unlock: mutex_unlock(&hwmon->hwmon_lock); + intel_runtime_pm_put(ddat->uncore->rpm, wakeref); return ret; } @@ -792,7 +793,7 @@ void i915_hwmon_register(struct drm_i915_private *i915) if (!IS_DGFX(i915)) return; - hwmon = devm_kzalloc(dev, sizeof(*hwmon), GFP_KERNEL); + hwmon = kzalloc(sizeof(*hwmon), GFP_KERNEL); if (!hwmon) return; @@ -818,14 +819,12 @@ void i915_hwmon_register(struct drm_i915_private *i915) hwm_get_preregistration_info(i915); /* hwmon_dev points to device hwmon */ - hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat->name, - ddat, - &hwm_chip_info, - hwm_groups); - if (IS_ERR(hwmon_dev)) { - i915->hwmon = NULL; - return; - } + hwmon_dev = hwmon_device_register_with_info(dev, ddat->name, + ddat, + &hwm_chip_info, + hwm_groups); + if (IS_ERR(hwmon_dev)) + goto err; ddat->hwmon_dev = hwmon_dev; @@ -838,16 +837,36 @@ void i915_hwmon_register(struct drm_i915_private *i915) if (!hwm_gt_is_visible(ddat_gt, hwmon_energy, hwmon_energy_input, 0)) continue; - hwmon_dev = devm_hwmon_device_register_with_info(dev, ddat_gt->name, - ddat_gt, - &hwm_gt_chip_info, - NULL); + hwmon_dev = hwmon_device_register_with_info(dev, ddat_gt->name, + ddat_gt, + &hwm_gt_chip_info, + NULL); if (!IS_ERR(hwmon_dev)) ddat_gt->hwmon_dev = hwmon_dev; } + return; +err: + i915_hwmon_unregister(i915); } void i915_hwmon_unregister(struct drm_i915_private *i915) { - fetch_and_zero(&i915->hwmon); + struct i915_hwmon *hwmon = i915->hwmon; + struct intel_gt *gt; + int i; + + if (!hwmon) + return; + + for_each_gt(gt, i915, i) + if (hwmon->ddat_gt[i].hwmon_dev) + hwmon_device_unregister(hwmon->ddat_gt[i].hwmon_dev); + + if (hwmon->ddat.hwmon_dev) + hwmon_device_unregister(hwmon->ddat.hwmon_dev); + + mutex_destroy(&hwmon->hwmon_lock); + + kfree(i915->hwmon); + i915->hwmon = NULL; } diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 2d695818f0062..bd9d812b1afa7 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -3225,7 +3225,7 @@ u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915) struct intel_gt *gt = to_gt(i915); /* Wa_18013179988 */ - if (IS_DG2(i915) || IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) { + if (IS_DG2(i915) || IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 74))) { intel_wakeref_t wakeref; u32 reg, shift; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 27dc903f0553c..6eeeaed807746 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4597,7 +4597,7 @@ #define MTL_CHICKEN_TRANS(trans) _MMIO_TRANS((trans), \ _MTL_CHICKEN_TRANS_A, \ _MTL_CHICKEN_TRANS_B) -#define PIPE_VBLANK_WITH_DELAY REG_BIT(31) /* ADL/DG2 */ +#define PIPE_VBLANK_WITH_DELAY REG_BIT(31) /* tgl+ */ #define SKL_UNMASK_VBL_TO_PIPE_IN_SRD REG_BIT(30) /* skl+ */ #define HSW_FRAME_START_DELAY_MASK REG_GENMASK(28, 27) #define HSW_FRAME_START_DELAY(x) REG_FIELD_PREP(HSW_FRAME_START_DELAY_MASK, x) @@ -5412,6 +5412,9 @@ #define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16 #define GEN6_PCODE_DATA1 _MMIO(0x13812C) +#define MTL_PCODE_STOLEN_ACCESS _MMIO(0x138914) +#define STOLEN_ACCESS_ALLOWED 0x1 + /* IVYBRIDGE DPF */ #define GEN7_L3CDERRST1(slice) _MMIO(0xB008 + (slice) * 0x200) /* L3CD Error Status 1 */ #define GEN7_L3CDERRST1_ROW_MASK (0x7ff << 14) diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c index 29fd02bf5ea8c..6f9e7b354b544 100644 --- a/drivers/gpu/drm/i915/i915_utils.c +++ b/drivers/gpu/drm/i915/i915_utils.c @@ -8,6 +8,7 @@ #include #include "i915_drv.h" +#include "i915_reg.h" #include "i915_utils.h" #define FDO_BUG_MSG "Please file a bug on drm/i915; see " FDO_BUG_URL " for details." @@ -125,3 +126,19 @@ bool i915_vtd_active(struct drm_i915_private *i915) /* Running as a guest, we assume the host is enforcing VT'd */ return i915_run_as_guest(); } + +bool i915_direct_stolen_access(struct drm_i915_private *i915) +{ + /* + * Wa_22018444074 + * + * Access via BAR can hang MTL, go directly to GSM/DSM, + * except for VM guests which won't have access to it. + * + * Normally this would not work but on MTL the system firmware + * should have relaxed the access permissions sufficiently. + * 0x138914==0x1 indicates that the firmware has done its job. + */ + return IS_METEORLAKE(i915) && !i915_run_as_guest() && + intel_uncore_read(&i915->uncore, MTL_PCODE_STOLEN_ACCESS) == STOLEN_ACCESS_ALLOWED; +} diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index f98577967b7fc..b45ef0560611a 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -391,4 +391,6 @@ static inline bool i915_run_as_guest(void) bool i915_vtd_active(struct drm_i915_private *i915); +bool i915_direct_stolen_access(struct drm_i915_private *i915); + #endif /* !__I915_UTILS_H */ diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index d09aad34ba37f..b70715b1411d6 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -34,6 +34,7 @@ #include "gt/intel_engine.h" #include "gt/intel_engine_heartbeat.h" #include "gt/intel_gt.h" +#include "gt/intel_gt_pm.h" #include "gt/intel_gt_requests.h" #include "gt/intel_tlb.h" @@ -103,12 +104,42 @@ static inline struct i915_vma *active_to_vma(struct i915_active *ref) static int __i915_vma_active(struct i915_active *ref) { - return i915_vma_tryget(active_to_vma(ref)) ? 0 : -ENOENT; + struct i915_vma *vma = active_to_vma(ref); + + if (!i915_vma_tryget(vma)) + return -ENOENT; + + /* + * Exclude global GTT VMA from holding a GT wakeref + * while active, otherwise GPU never goes idle. + */ + if (!i915_vma_is_ggtt(vma)) { + /* + * Since we and our _retire() counterpart can be + * called asynchronously, storing a wakeref tracking + * handle inside struct i915_vma is not safe, and + * there is no other good place for that. Hence, + * use untracked variants of intel_gt_pm_get/put(). + */ + intel_gt_pm_get_untracked(vma->vm->gt); + } + + return 0; } static void __i915_vma_retire(struct i915_active *ref) { - i915_vma_put(active_to_vma(ref)); + struct i915_vma *vma = active_to_vma(ref); + + if (!i915_vma_is_ggtt(vma)) { + /* + * Since we can be called from atomic contexts, + * use an async variant of intel_gt_pm_put(). + */ + intel_gt_pm_put_async_untracked(vma->vm->gt); + } + + i915_vma_put(vma); } static struct i915_vma * @@ -1404,7 +1435,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, struct i915_vma_work *work = NULL; struct dma_fence *moving = NULL; struct i915_vma_resource *vma_res = NULL; - intel_wakeref_t wakeref = 0; + intel_wakeref_t wakeref; unsigned int bound; int err; @@ -1424,8 +1455,14 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (err) return err; - if (flags & PIN_GLOBAL) - wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); + /* + * In case of a global GTT, we must hold a runtime-pm wakeref + * while global PTEs are updated. In other cases, we hold + * the rpm reference while the VMA is active. Since runtime + * resume may require allocations, which are forbidden inside + * vm->mutex, get the first rpm wakeref outside of the mutex. + */ + wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); if (flags & vma->vm->bind_async_flags) { /* lock VM */ @@ -1561,8 +1598,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (work) dma_fence_work_commit_imm(&work->base); err_rpm: - if (wakeref) - intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); + intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref); if (moving) dma_fence_put(moving); diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c index 15492b69f6983..e3287f1de7741 100644 --- a/drivers/gpu/drm/i915/soc/intel_dram.c +++ b/drivers/gpu/drm/i915/soc/intel_dram.c @@ -681,6 +681,8 @@ void intel_dram_detect(struct drm_i915_private *i915) if (ret) return; + drm_dbg_kms(&i915->drm, "Num qgv points %u\n", dram_info->num_qgv_points); + drm_dbg_kms(&i915->drm, "DRAM channels: %u\n", dram_info->num_channels); drm_dbg_kms(&i915->drm, "Watermark level 0 adjustment needed: %s\n", diff --git a/drivers/gpu/drm/imagination/pvr_fw_mips.h b/drivers/gpu/drm/imagination/pvr_fw_mips.h index 408dbe63a90cf..a0c5c41c8aa24 100644 --- a/drivers/gpu/drm/imagination/pvr_fw_mips.h +++ b/drivers/gpu/drm/imagination/pvr_fw_mips.h @@ -7,13 +7,14 @@ #include "pvr_rogue_mips.h" #include +#include #include /* Forward declaration from pvr_gem.h. */ struct pvr_gem_object; -#define PVR_MIPS_PT_PAGE_COUNT ((ROGUE_MIPSFW_MAX_NUM_PAGETABLE_PAGES * ROGUE_MIPSFW_PAGE_SIZE_4K) \ - >> PAGE_SHIFT) +#define PVR_MIPS_PT_PAGE_COUNT DIV_ROUND_UP(ROGUE_MIPSFW_MAX_NUM_PAGETABLE_PAGES * ROGUE_MIPSFW_PAGE_SIZE_4K, PAGE_SIZE) + /** * struct pvr_fw_mips_data - MIPS-specific data */ diff --git a/drivers/gpu/drm/imagination/pvr_vm_mips.c b/drivers/gpu/drm/imagination/pvr_vm_mips.c index b7fef3c797e6c..4f99b4af871c0 100644 --- a/drivers/gpu/drm/imagination/pvr_vm_mips.c +++ b/drivers/gpu/drm/imagination/pvr_vm_mips.c @@ -46,7 +46,7 @@ pvr_vm_mips_init(struct pvr_device *pvr_dev) if (!mips_data) return -ENOMEM; - for (page_nr = 0; page_nr < ARRAY_SIZE(mips_data->pt_pages); page_nr++) { + for (page_nr = 0; page_nr < PVR_MIPS_PT_PAGE_COUNT; page_nr++) { mips_data->pt_pages[page_nr] = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!mips_data->pt_pages[page_nr]) { err = -ENOMEM; @@ -102,7 +102,7 @@ pvr_vm_mips_fini(struct pvr_device *pvr_dev) int page_nr; vunmap(mips_data->pt); - for (page_nr = ARRAY_SIZE(mips_data->pt_pages) - 1; page_nr >= 0; page_nr--) { + for (page_nr = PVR_MIPS_PT_PAGE_COUNT - 1; page_nr >= 0; page_nr--) { dma_unmap_page(from_pvr_device(pvr_dev)->dev, mips_data->pt_dma_addr[page_nr], PAGE_SIZE, DMA_TO_DEVICE); diff --git a/drivers/gpu/drm/imx/ipuv3/Kconfig b/drivers/gpu/drm/imx/ipuv3/Kconfig index bacf0655ebaf3..5d810ac02171d 100644 --- a/drivers/gpu/drm/imx/ipuv3/Kconfig +++ b/drivers/gpu/drm/imx/ipuv3/Kconfig @@ -35,7 +35,8 @@ config DRM_IMX_LDB config DRM_IMX_HDMI tristate "Freescale i.MX DRM HDMI" - select DRM_DW_HDMI - depends on DRM_IMX && OF + depends on DRM_DW_HDMI + depends on DRM_IMX + depends on OF help Choose this if you want to use HDMI on i.MX6. diff --git a/drivers/gpu/drm/imx/ipuv3/parallel-display.c b/drivers/gpu/drm/imx/ipuv3/parallel-display.c index 70349739dd89b..55dedd73f528c 100644 --- a/drivers/gpu/drm/imx/ipuv3/parallel-display.c +++ b/drivers/gpu/drm/imx/ipuv3/parallel-display.c @@ -72,14 +72,14 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) int ret; if (!mode) - return -EINVAL; + return 0; ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); if (ret) { drm_mode_destroy(connector->dev, mode); - return ret; + return 0; } drm_mode_copy(mode, &imxpd->mode); diff --git a/drivers/gpu/drm/ingenic/Kconfig b/drivers/gpu/drm/ingenic/Kconfig index b440e0cdc0579..dcc424d46c868 100644 --- a/drivers/gpu/drm/ingenic/Kconfig +++ b/drivers/gpu/drm/ingenic/Kconfig @@ -28,8 +28,8 @@ config DRM_INGENIC_IPU config DRM_INGENIC_DW_HDMI tristate "Ingenic specific support for Synopsys DW HDMI" + depends on DRM_DW_HDMI depends on MACH_JZ4780 - select DRM_DW_HDMI help Choose this option to enable Synopsys DesignWare HDMI based driver. If you want to enable HDMI on Ingenic JZ4780 based SoC, you should diff --git a/drivers/gpu/drm/lima/lima_bcast.c b/drivers/gpu/drm/lima/lima_bcast.c index fbc43f243c54d..6d000504e1a4e 100644 --- a/drivers/gpu/drm/lima/lima_bcast.c +++ b/drivers/gpu/drm/lima/lima_bcast.c @@ -43,6 +43,18 @@ void lima_bcast_suspend(struct lima_ip *ip) } +int lima_bcast_mask_irq(struct lima_ip *ip) +{ + bcast_write(LIMA_BCAST_BROADCAST_MASK, 0); + bcast_write(LIMA_BCAST_INTERRUPT_MASK, 0); + return 0; +} + +int lima_bcast_reset(struct lima_ip *ip) +{ + return lima_bcast_hw_init(ip); +} + int lima_bcast_init(struct lima_ip *ip) { int i; diff --git a/drivers/gpu/drm/lima/lima_bcast.h b/drivers/gpu/drm/lima/lima_bcast.h index 465ee587bceb2..cd08841e47879 100644 --- a/drivers/gpu/drm/lima/lima_bcast.h +++ b/drivers/gpu/drm/lima/lima_bcast.h @@ -13,4 +13,7 @@ void lima_bcast_fini(struct lima_ip *ip); void lima_bcast_enable(struct lima_device *dev, int num_pp); +int lima_bcast_mask_irq(struct lima_ip *ip); +int lima_bcast_reset(struct lima_ip *ip); + #endif diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index 4f9736e5f929b..7ea244d876ca6 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -75,29 +75,34 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm) } else { bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL); if (!bo->base.sgt) { - sg_free_table(&sgt); - return -ENOMEM; + ret = -ENOMEM; + goto err_out0; } } ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); - if (ret) { - sg_free_table(&sgt); - kfree(bo->base.sgt); - bo->base.sgt = NULL; - return ret; - } + if (ret) + goto err_out1; *bo->base.sgt = sgt; if (vm) { ret = lima_vm_map_bo(vm, bo, old_size >> PAGE_SHIFT); if (ret) - return ret; + goto err_out2; } bo->heap_size = new_size; return 0; + +err_out2: + dma_unmap_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); +err_out1: + kfree(bo->base.sgt); + bo->base.sgt = NULL; +err_out0: + sg_free_table(&sgt); + return ret; } int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file, diff --git a/drivers/gpu/drm/lima/lima_gp.c b/drivers/gpu/drm/lima/lima_gp.c index 8dd501b7a3d0d..6cf46b653e810 100644 --- a/drivers/gpu/drm/lima/lima_gp.c +++ b/drivers/gpu/drm/lima/lima_gp.c @@ -212,6 +212,13 @@ static void lima_gp_task_mmu_error(struct lima_sched_pipe *pipe) lima_sched_pipe_task_done(pipe); } +static void lima_gp_task_mask_irq(struct lima_sched_pipe *pipe) +{ + struct lima_ip *ip = pipe->processor[0]; + + gp_write(LIMA_GP_INT_MASK, 0); +} + static int lima_gp_task_recover(struct lima_sched_pipe *pipe) { struct lima_ip *ip = pipe->processor[0]; @@ -344,6 +351,7 @@ int lima_gp_pipe_init(struct lima_device *dev) pipe->task_error = lima_gp_task_error; pipe->task_mmu_error = lima_gp_task_mmu_error; pipe->task_recover = lima_gp_task_recover; + pipe->task_mask_irq = lima_gp_task_mask_irq; return 0; } diff --git a/drivers/gpu/drm/lima/lima_pp.c b/drivers/gpu/drm/lima/lima_pp.c index a5c95bed08c09..54b208a4a768e 100644 --- a/drivers/gpu/drm/lima/lima_pp.c +++ b/drivers/gpu/drm/lima/lima_pp.c @@ -408,6 +408,9 @@ static void lima_pp_task_error(struct lima_sched_pipe *pipe) lima_pp_hard_reset(ip); } + + if (pipe->bcast_processor) + lima_bcast_reset(pipe->bcast_processor); } static void lima_pp_task_mmu_error(struct lima_sched_pipe *pipe) @@ -416,6 +419,20 @@ static void lima_pp_task_mmu_error(struct lima_sched_pipe *pipe) lima_sched_pipe_task_done(pipe); } +static void lima_pp_task_mask_irq(struct lima_sched_pipe *pipe) +{ + int i; + + for (i = 0; i < pipe->num_processor; i++) { + struct lima_ip *ip = pipe->processor[i]; + + pp_write(LIMA_PP_INT_MASK, 0); + } + + if (pipe->bcast_processor) + lima_bcast_mask_irq(pipe->bcast_processor); +} + static struct kmem_cache *lima_pp_task_slab; static int lima_pp_task_slab_refcnt; @@ -447,6 +464,7 @@ int lima_pp_pipe_init(struct lima_device *dev) pipe->task_fini = lima_pp_task_fini; pipe->task_error = lima_pp_task_error; pipe->task_mmu_error = lima_pp_task_mmu_error; + pipe->task_mask_irq = lima_pp_task_mask_irq; return 0; } diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index c3bf8cda84982..5ba60fe756167 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -402,6 +402,13 @@ static enum drm_gpu_sched_stat lima_sched_timedout_job(struct drm_sched_job *job struct lima_sched_task *task = to_lima_task(job); struct lima_device *ldev = pipe->ldev; + /* + * The task might still finish while this timeout handler runs. + * To prevent a race condition on its completion, mask all irqs + * on the running core until the next hard reset completes. + */ + pipe->task_mask_irq(pipe); + if (!pipe->error) DRM_ERROR("lima job timeout\n"); diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h index 6a11764d87b38..edf205be43699 100644 --- a/drivers/gpu/drm/lima/lima_sched.h +++ b/drivers/gpu/drm/lima/lima_sched.h @@ -80,6 +80,7 @@ struct lima_sched_pipe { void (*task_error)(struct lima_sched_pipe *pipe); void (*task_mmu_error)(struct lima_sched_pipe *pipe); int (*task_recover)(struct lima_sched_pipe *pipe); + void (*task_mask_irq)(struct lima_sched_pipe *pipe); struct work_struct recover_work; }; diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 2136a596efa18..afc8905df828e 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -2095,7 +2095,7 @@ static ssize_t mtk_dp_aux_transfer(struct drm_dp_aux *mtk_aux, if (mtk_dp->bridge.type != DRM_MODE_CONNECTOR_eDP && !mtk_dp->train_info.cable_plugged_in) { - ret = -EAGAIN; + ret = -EIO; goto err; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index c729af3b98224..d398fa1871165 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -95,11 +95,13 @@ static void mtk_drm_crtc_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) struct drm_crtc *crtc = &mtk_crtc->base; unsigned long flags; - spin_lock_irqsave(&crtc->dev->event_lock, flags); - drm_crtc_send_vblank_event(crtc, mtk_crtc->event); - drm_crtc_vblank_put(crtc); - mtk_crtc->event = NULL; - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + if (mtk_crtc->event) { + spin_lock_irqsave(&crtc->dev->event_lock, flags); + drm_crtc_send_vblank_event(crtc, mtk_crtc->event); + drm_crtc_vblank_put(crtc); + mtk_crtc->event = NULL; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + } } static void mtk_drm_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) @@ -990,10 +992,10 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, mtk_crtc->mmsys_dev = priv->mmsys_dev; mtk_crtc->ddp_comp_nr = path_len; - mtk_crtc->ddp_comp = devm_kmalloc_array(dev, - mtk_crtc->ddp_comp_nr + (conn_routes ? 1 : 0), - sizeof(*mtk_crtc->ddp_comp), - GFP_KERNEL); + mtk_crtc->ddp_comp = devm_kcalloc(dev, + mtk_crtc->ddp_comp_nr + (conn_routes ? 1 : 0), + sizeof(*mtk_crtc->ddp_comp), + GFP_KERNEL); if (!mtk_crtc->ddp_comp) return -ENOMEM; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 4f2e3feabc0f8..1bf229615b018 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -38,6 +38,9 @@ static struct mtk_drm_gem_obj *mtk_drm_gem_init(struct drm_device *dev, size = round_up(size, PAGE_SIZE); + if (size == 0) + return ERR_PTR(-EINVAL); + mtk_gem_obj = kzalloc(sizeof(*mtk_gem_obj), GFP_KERNEL); if (!mtk_gem_obj) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index a2fdfc8ddb153..cd19885ee017f 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -71,8 +71,8 @@ #define DSI_PS_WC 0x3fff #define DSI_PS_SEL (3 << 16) #define PACKED_PS_16BIT_RGB565 (0 << 16) -#define LOOSELY_PS_18BIT_RGB666 (1 << 16) -#define PACKED_PS_18BIT_RGB666 (2 << 16) +#define PACKED_PS_18BIT_RGB666 (1 << 16) +#define LOOSELY_PS_24BIT_RGB666 (2 << 16) #define PACKED_PS_24BIT_RGB888 (3 << 16) #define DSI_VSA_NL 0x20 @@ -369,10 +369,10 @@ static void mtk_dsi_ps_control_vact(struct mtk_dsi *dsi) ps_bpp_mode |= PACKED_PS_24BIT_RGB888; break; case MIPI_DSI_FMT_RGB666: - ps_bpp_mode |= PACKED_PS_18BIT_RGB666; + ps_bpp_mode |= LOOSELY_PS_24BIT_RGB666; break; case MIPI_DSI_FMT_RGB666_PACKED: - ps_bpp_mode |= LOOSELY_PS_18BIT_RGB666; + ps_bpp_mode |= PACKED_PS_18BIT_RGB666; break; case MIPI_DSI_FMT_RGB565: ps_bpp_mode |= PACKED_PS_16BIT_RGB565; @@ -426,7 +426,7 @@ static void mtk_dsi_ps_control(struct mtk_dsi *dsi) dsi_tmp_buf_bpp = 3; break; case MIPI_DSI_FMT_RGB666: - tmp_reg = LOOSELY_PS_18BIT_RGB666; + tmp_reg = LOOSELY_PS_24BIT_RGB666; dsi_tmp_buf_bpp = 3; break; case MIPI_DSI_FMT_RGB666_PACKED: diff --git a/drivers/gpu/drm/meson/Kconfig b/drivers/gpu/drm/meson/Kconfig index 615fdd0ce41b4..5520b9e3f0107 100644 --- a/drivers/gpu/drm/meson/Kconfig +++ b/drivers/gpu/drm/meson/Kconfig @@ -13,9 +13,9 @@ config DRM_MESON config DRM_MESON_DW_HDMI tristate "HDMI Synopsys Controller support for Amlogic Meson Display" + depends on DRM_DW_HDMI depends on DRM_MESON default y if DRM_MESON - select DRM_DW_HDMI imply DRM_DW_HDMI_I2S_AUDIO config DRM_MESON_DW_MIPI_DSI diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c index 5a9538bc0e26f..5565f7777529f 100644 --- a/drivers/gpu/drm/meson/meson_dw_hdmi.c +++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c @@ -106,6 +106,8 @@ #define HHI_HDMI_CLK_CNTL 0x1cc /* 0x73 */ #define HHI_HDMI_PHY_CNTL0 0x3a0 /* 0xe8 */ #define HHI_HDMI_PHY_CNTL1 0x3a4 /* 0xe9 */ +#define PHY_CNTL1_INIT 0x03900000 +#define PHY_INVERT BIT(17) #define HHI_HDMI_PHY_CNTL2 0x3a8 /* 0xea */ #define HHI_HDMI_PHY_CNTL3 0x3ac /* 0xeb */ #define HHI_HDMI_PHY_CNTL4 0x3b0 /* 0xec */ @@ -130,6 +132,8 @@ struct meson_dw_hdmi_data { unsigned int addr); void (*dwc_write)(struct meson_dw_hdmi *dw_hdmi, unsigned int addr, unsigned int data); + u32 cntl0_init; + u32 cntl1_init; }; struct meson_dw_hdmi { @@ -384,26 +388,6 @@ static int dw_hdmi_phy_init(struct dw_hdmi *hdmi, void *data, dw_hdmi_bus_fmt_is_420(hdmi)) mode_is_420 = true; - /* Enable clocks */ - regmap_update_bits(priv->hhi, HHI_HDMI_CLK_CNTL, 0xffff, 0x100); - - /* Bring HDMITX MEM output of power down */ - regmap_update_bits(priv->hhi, HHI_MEM_PD_REG0, 0xff << 8, 0); - - /* Bring out of reset */ - dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_SW_RESET, 0); - - /* Enable internal pixclk, tmds_clk, spdif_clk, i2s_clk, cecclk */ - dw_hdmi_top_write_bits(dw_hdmi, HDMITX_TOP_CLK_CNTL, - 0x3, 0x3); - - /* Enable cec_clk and hdcp22_tmdsclk_en */ - dw_hdmi_top_write_bits(dw_hdmi, HDMITX_TOP_CLK_CNTL, - 0x3 << 4, 0x3 << 4); - - /* Enable normal output to PHY */ - dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_BIST_CNTL, BIT(12)); - /* TMDS pattern setup */ if (mode->clock > 340000 && !mode_is_420) { dw_hdmi->data->top_write(dw_hdmi, HDMITX_TOP_TMDS_CLK_PTTN_01, @@ -425,20 +409,6 @@ static int dw_hdmi_phy_init(struct dw_hdmi *hdmi, void *data, /* Setup PHY parameters */ meson_hdmi_phy_setup_mode(dw_hdmi, mode, mode_is_420); - /* Setup PHY */ - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - 0xffff << 16, 0x0390 << 16); - - /* BIT_INVERT */ - if (dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-gxl-dw-hdmi") || - dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-gxm-dw-hdmi") || - dw_hdmi_is_compatible(dw_hdmi, "amlogic,meson-g12a-dw-hdmi")) - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - BIT(17), 0); - else - regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, - BIT(17), BIT(17)); - /* Disable clock, fifo, fifo_wr */ regmap_update_bits(priv->hhi, HHI_HDMI_PHY_CNTL1, 0xf, 0); @@ -492,7 +462,9 @@ static void dw_hdmi_phy_disable(struct dw_hdmi *hdmi, DRM_DEBUG_DRIVER("\n"); - regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, 0); + /* Fallback to init mode */ + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL1, dw_hdmi->data->cntl1_init); + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, dw_hdmi->data->cntl0_init); } static enum drm_connector_status dw_hdmi_read_hpd(struct dw_hdmi *hdmi, @@ -610,11 +582,22 @@ static const struct regmap_config meson_dw_hdmi_regmap_config = { .fast_io = true, }; -static const struct meson_dw_hdmi_data meson_dw_hdmi_gx_data = { +static const struct meson_dw_hdmi_data meson_dw_hdmi_gxbb_data = { .top_read = dw_hdmi_top_read, .top_write = dw_hdmi_top_write, .dwc_read = dw_hdmi_dwc_read, .dwc_write = dw_hdmi_dwc_write, + .cntl0_init = 0x0, + .cntl1_init = PHY_CNTL1_INIT | PHY_INVERT, +}; + +static const struct meson_dw_hdmi_data meson_dw_hdmi_gxl_data = { + .top_read = dw_hdmi_top_read, + .top_write = dw_hdmi_top_write, + .dwc_read = dw_hdmi_dwc_read, + .dwc_write = dw_hdmi_dwc_write, + .cntl0_init = 0x0, + .cntl1_init = PHY_CNTL1_INIT, }; static const struct meson_dw_hdmi_data meson_dw_hdmi_g12a_data = { @@ -622,6 +605,8 @@ static const struct meson_dw_hdmi_data meson_dw_hdmi_g12a_data = { .top_write = dw_hdmi_g12a_top_write, .dwc_read = dw_hdmi_g12a_dwc_read, .dwc_write = dw_hdmi_g12a_dwc_write, + .cntl0_init = 0x000b4242, /* Bandgap */ + .cntl1_init = PHY_CNTL1_INIT, }; static void meson_dw_hdmi_init(struct meson_dw_hdmi *meson_dw_hdmi) @@ -656,6 +641,13 @@ static void meson_dw_hdmi_init(struct meson_dw_hdmi *meson_dw_hdmi) meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_CLK_CNTL, 0xff); + /* Enable normal output to PHY */ + meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_BIST_CNTL, BIT(12)); + + /* Setup PHY */ + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL1, meson_dw_hdmi->data->cntl1_init); + regmap_write(priv->hhi, HHI_HDMI_PHY_CNTL0, meson_dw_hdmi->data->cntl0_init); + /* Enable HDMI-TX Interrupt */ meson_dw_hdmi->data->top_write(meson_dw_hdmi, HDMITX_TOP_INTR_STAT_CLR, HDMITX_TOP_INTR_CORE); @@ -865,11 +857,11 @@ static const struct dev_pm_ops meson_dw_hdmi_pm_ops = { static const struct of_device_id meson_dw_hdmi_of_table[] = { { .compatible = "amlogic,meson-gxbb-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxbb_data }, { .compatible = "amlogic,meson-gxl-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxl_data }, { .compatible = "amlogic,meson-gxm-dw-hdmi", - .data = &meson_dw_hdmi_gx_data }, + .data = &meson_dw_hdmi_gxl_data }, { .compatible = "amlogic,meson-g12a-dw-hdmi", .data = &meson_dw_hdmi_g12a_data }, { } diff --git a/drivers/gpu/drm/meson/meson_dw_mipi_dsi.c b/drivers/gpu/drm/meson/meson_dw_mipi_dsi.c index a6bc1bdb3d0d8..a10cff3ca1fef 100644 --- a/drivers/gpu/drm/meson/meson_dw_mipi_dsi.c +++ b/drivers/gpu/drm/meson/meson_dw_mipi_dsi.c @@ -95,6 +95,7 @@ static int dw_mipi_dsi_phy_init(void *priv_data) return ret; } + clk_disable_unprepare(mipi_dsi->px_clk); ret = clk_set_rate(mipi_dsi->px_clk, mipi_dsi->mode->clock * 1000); if (ret) { @@ -103,6 +104,12 @@ static int dw_mipi_dsi_phy_init(void *priv_data) return ret; } + ret = clk_prepare_enable(mipi_dsi->px_clk); + if (ret) { + dev_err(mipi_dsi->dev, "Failed to enable DSI Pixel clock (ret %d)\n", ret); + return ret; + } + switch (mipi_dsi->dsi_device->format) { case MIPI_DSI_FMT_RGB888: dpi_data_format = DPI_COLOR_24BIT; diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c index 2a82119eb58ed..2a942dc6a6dc2 100644 --- a/drivers/gpu/drm/meson/meson_vclk.c +++ b/drivers/gpu/drm/meson/meson_vclk.c @@ -790,13 +790,13 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq, FREQ_1000_1001(params[i].pixel_freq)); DRM_DEBUG_DRIVER("i = %d phy_freq = %d alt = %d\n", i, params[i].phy_freq, - FREQ_1000_1001(params[i].phy_freq/10)*10); + FREQ_1000_1001(params[i].phy_freq/1000)*1000); /* Match strict frequency */ if (phy_freq == params[i].phy_freq && vclk_freq == params[i].vclk_freq) return MODE_OK; /* Match 1000/1001 variant */ - if (phy_freq == (FREQ_1000_1001(params[i].phy_freq/10)*10) && + if (phy_freq == (FREQ_1000_1001(params[i].phy_freq/1000)*1000) && vclk_freq == FREQ_1000_1001(params[i].vclk_freq)) return MODE_OK; } @@ -1070,7 +1070,7 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target, for (freq = 0 ; params[freq].pixel_freq ; ++freq) { if ((phy_freq == params[freq].phy_freq || - phy_freq == FREQ_1000_1001(params[freq].phy_freq/10)*10) && + phy_freq == FREQ_1000_1001(params[freq].phy_freq/1000)*1000) && (vclk_freq == params[freq].vclk_freq || vclk_freq == FREQ_1000_1001(params[freq].vclk_freq))) { if (vclk_freq != params[freq].vclk_freq) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index c9c55e2ea5849..74de2d50eead8 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -284,7 +284,7 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx); - get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0), + get_stats_counter(ring, REG_A7XX_RBBM_PERFCTR_CP(0), rbmemptr_stats(ring, index, cpcycles_start)); get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER, rbmemptr_stats(ring, index, alwayson_start)); @@ -330,7 +330,7 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_PKT7(ring, CP_SET_MARKER, 1); OUT_RING(ring, 0x00e); /* IB1LIST end */ - get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0), + get_stats_counter(ring, REG_A7XX_RBBM_PERFCTR_CP(0), rbmemptr_stats(ring, index, cpcycles_end)); get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER, rbmemptr_stats(ring, index, alwayson_end)); @@ -1292,9 +1292,12 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu) gpu->ubwc_config.ubwc_mode = 1; } - /* a618 is using the hw default values */ if (adreno_is_a618(gpu)) - return; + gpu->ubwc_config.highest_bank_bit = 14; + + if (adreno_is_a619(gpu)) + /* TODO: Should be 14 but causes corruption at e.g. 1920x1200 on DP */ + gpu->ubwc_config.highest_bank_bit = 13; if (adreno_is_a619_holi(gpu)) gpu->ubwc_config.highest_bank_bit = 13; @@ -2427,7 +2430,7 @@ static int a6xx_gmu_pm_resume(struct msm_gpu *gpu) msm_devfreq_resume(gpu); - adreno_is_a7xx(adreno_gpu) ? a7xx_llc_activate : a6xx_llc_activate(a6xx_gpu); + adreno_is_a7xx(adreno_gpu) ? a7xx_llc_activate(a6xx_gpu) : a6xx_llc_activate(a6xx_gpu); return ret; } @@ -2886,7 +2889,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) ret = a6xx_set_supported_hw(&pdev->dev, config->info); if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); + a6xx_llc_slices_destroy(a6xx_gpu); + kfree(a6xx_gpu); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index ef871239adb2a..68fae048a9a83 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -459,15 +459,15 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) &perf->core_clk_rate); debugfs_create_u32("enable_bw_release", 0600, entry, (u32 *)&perf->enable_bw_release); - debugfs_create_u32("threshold_low", 0600, entry, + debugfs_create_u32("threshold_low", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_low); - debugfs_create_u32("threshold_high", 0600, entry, + debugfs_create_u32("threshold_high", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_high); - debugfs_create_u32("min_core_ib", 0600, entry, + debugfs_create_u32("min_core_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_core_ib); - debugfs_create_u32("min_llcc_ib", 0600, entry, + debugfs_create_u32("min_llcc_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_llcc_ib); - debugfs_create_u32("min_dram_ib", 0600, entry, + debugfs_create_u32("min_dram_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_dram_ib); debugfs_create_file("perf_mode", 0600, entry, (u32 *)perf, &dpu_core_perf_mode_fops); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 6a4b489d44e51..aca689314ccea 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -226,6 +226,13 @@ bool dpu_encoder_is_widebus_enabled(const struct drm_encoder *drm_enc) return dpu_enc->wide_bus_en; } +bool dpu_encoder_is_dsc_enabled(const struct drm_encoder *drm_enc) +{ + const struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + + return dpu_enc->dsc ? true : false; +} + int dpu_encoder_get_crc_values_cnt(const struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc; @@ -1853,7 +1860,9 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, dsc_common_mode = 0; pic_width = dsc->pic_width; - dsc_common_mode = DSC_MODE_MULTIPLEX | DSC_MODE_SPLIT_PANEL; + dsc_common_mode = DSC_MODE_SPLIT_PANEL; + if (dpu_encoder_use_dsc_merge(enc_master->parent)) + dsc_common_mode |= DSC_MODE_MULTIPLEX; if (enc_master->intf_mode == INTF_MODE_VIDEO) dsc_common_mode |= DSC_MODE_VIDEO; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index 4c05fd5e9ed18..fe6b1d312a742 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -158,6 +158,13 @@ int dpu_encoder_get_vsync_count(struct drm_encoder *drm_enc); bool dpu_encoder_is_widebus_enabled(const struct drm_encoder *drm_enc); +/** + * dpu_encoder_is_dsc_enabled - indicate whether dsc is enabled + * for the encoder. + * @drm_enc: Pointer to previously created drm encoder structure + */ +bool dpu_encoder_is_dsc_enabled(const struct drm_encoder *drm_enc); + /** * dpu_encoder_get_crc_values_cnt - get number of physical encoders contained * in virtual encoder that can collect CRC values diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index a301e2833177a..44fb5083c1473 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -451,9 +451,6 @@ static void dpu_encoder_phys_cmd_enable_helper( _dpu_encoder_phys_cmd_pingpong_config(phys_enc); - if (!dpu_encoder_phys_cmd_is_master(phys_enc)) - return; - ctl = phys_enc->hw_ctl; ctl->ops.update_pending_flush_intf(ctl, phys_enc->hw_intf->idx); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index d0f56c5c4cce9..f02411b062c4c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -102,6 +102,7 @@ static void drm_mode_to_intf_timing_params( } timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent); + timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent); /* * for DP, divide the horizonal parameters by 2 when @@ -259,12 +260,14 @@ static void dpu_encoder_phys_vid_setup_timing_engine( mode.htotal >>= 1; mode.hsync_start >>= 1; mode.hsync_end >>= 1; + mode.hskew >>= 1; DPU_DEBUG_VIDENC(phys_enc, - "split_role %d, halve horizontal %d %d %d %d\n", + "split_role %d, halve horizontal %d %d %d %d %d\n", phys_enc->split_role, mode.hdisplay, mode.htotal, - mode.hsync_start, mode.hsync_end); + mode.hsync_start, mode.hsync_end, + mode.hskew); } drm_mode_to_intf_timing_params(phys_enc, &mode, &timing_params); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c index e9cdc7934a499..9016b3ade6bc3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c @@ -186,7 +186,7 @@ static int dpu_hw_cdm_enable(struct dpu_hw_cdm *ctx, struct dpu_hw_cdm_cfg *cdm) dpu_hw_cdm_setup_cdwn(ctx, cdm); if (cdm->output_type == CDM_CDWN_OUTPUT_HDMI) { - if (fmt->chroma_sample != DPU_CHROMA_H1V2) + if (fmt->chroma_sample == DPU_CHROMA_H1V2) return -EINVAL; /*unsupported format */ opmode = CDM_HDMI_PACK_OP_MODE_EN; opmode |= (fmt->chroma_sample << 1); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index e76565c3e6a43..e8a0b731d89e2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -532,6 +532,7 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, { struct dpu_hw_blk_reg_map *c = &ctx->hw; u32 intf_active = 0; + u32 dsc_active = 0; u32 wb_active = 0; u32 mode_sel = 0; @@ -547,6 +548,7 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE); wb_active = DPU_REG_READ(c, CTL_WB_ACTIVE); + dsc_active = DPU_REG_READ(c, CTL_DSC_ACTIVE); if (cfg->intf) intf_active |= BIT(cfg->intf - INTF_0); @@ -554,17 +556,18 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, if (cfg->wb) wb_active |= BIT(cfg->wb - WB_0); + if (cfg->dsc) + dsc_active |= cfg->dsc; + DPU_REG_WRITE(c, CTL_TOP, mode_sel); DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); DPU_REG_WRITE(c, CTL_WB_ACTIVE, wb_active); + DPU_REG_WRITE(c, CTL_DSC_ACTIVE, dsc_active); if (cfg->merge_3d) DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, BIT(cfg->merge_3d - MERGE_3D_0)); - if (cfg->dsc) - DPU_REG_WRITE(c, CTL_DSC_ACTIVE, cfg->dsc); - if (cfg->cdm) DPU_REG_WRITE(c, CTL_CDM_ACTIVE, cfg->cdm); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 946dd0135dffc..b85881aab0478 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -223,9 +223,11 @@ static void dpu_core_irq_callback_handler(struct dpu_kms *dpu_kms, unsigned int VERB("IRQ=[%d, %d]\n", DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); - if (!irq_entry->cb) + if (!irq_entry->cb) { DRM_ERROR("no registered cb, IRQ=[%d, %d]\n", DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); + return; + } atomic_inc(&irq_entry->count); @@ -525,14 +527,14 @@ int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int ret; if (!irq_cb) { - DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n", - DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb); + DPU_ERROR("IRQ=[%d, %d] NULL callback\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); return -EINVAL; } if (!dpu_core_irq_is_valid(irq_idx)) { - DPU_ERROR("invalid IRQ=[%d, %d]\n", - DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); + DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 6bba531d6dc41..965692ef7892c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -163,13 +163,8 @@ static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, hsync_ctl = (hsync_period << 16) | p->hsync_pulse_width; display_hctl = (hsync_end_x << 16) | hsync_start_x; - /* - * DATA_HCTL_EN controls data timing which can be different from - * video timing. It is recommended to enable it for all cases, except - * if compression is enabled in 1 pixel per clock mode - */ if (p->wide_bus_en) - intf_cfg2 |= INTF_CFG2_DATABUS_WIDEN | INTF_CFG2_DATA_HCTL_EN; + intf_cfg2 |= INTF_CFG2_DATABUS_WIDEN; data_width = p->width; @@ -229,6 +224,14 @@ static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, DPU_REG_WRITE(c, INTF_CONFIG, intf_cfg); DPU_REG_WRITE(c, INTF_PANEL_FORMAT, panel_format); if (ctx->cap->features & BIT(DPU_DATA_HCTL_EN)) { + /* + * DATA_HCTL_EN controls data timing which can be different from + * video timing. It is recommended to enable it for all cases, except + * if compression is enabled in 1 pixel per clock mode + */ + if (!(p->compression_en && !p->wide_bus_en)) + intf_cfg2 |= INTF_CFG2_DATA_HCTL_EN; + DPU_REG_WRITE(c, INTF_CONFIG2, intf_cfg2); DPU_REG_WRITE(c, INTF_DISPLAY_DATA_HCTL, display_data_hctl); DPU_REG_WRITE(c, INTF_ACTIVE_DATA_HCTL, active_data_hctl); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h index 0bd57a32144a6..6f4c87244f944 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -33,6 +33,7 @@ struct dpu_hw_intf_timing_params { u32 hsync_skew; bool wide_bus_en; + bool compression_en; }; struct dpu_hw_intf_prog_fetch { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 723cc1d821431..2330eb2a4e9c8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -374,6 +374,12 @@ static int dpu_kms_global_obj_init(struct dpu_kms *dpu_kms) return 0; } +static void dpu_kms_global_obj_fini(struct dpu_kms *dpu_kms) +{ + drm_atomic_private_obj_fini(&dpu_kms->global_state); + drm_modeset_lock_fini(&dpu_kms->global_state_lock); +} + static int dpu_kms_parse_data_bus_icc_path(struct dpu_kms *dpu_kms) { struct icc_path *path0; @@ -801,6 +807,8 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms) dpu_kms->hw_vbif[i] = NULL; } + dpu_kms_global_obj_fini(dpu_kms); + dpu_kms->catalog = NULL; dpu_kms->hw_mdp = NULL; diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index 03f4951c49f42..e67a80d56948c 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -35,6 +35,7 @@ struct dp_aux_private { bool no_send_stop; bool initted; bool is_edp; + bool enable_xfers; u32 offset; u32 segment; @@ -301,6 +302,17 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, goto exit; } + /* + * If we're using DP and an external display isn't connected then the + * transfer won't succeed. Return right away. If we don't do this we + * can end up with long timeouts if someone tries to access the DP AUX + * character device when no DP device is connected. + */ + if (!aux->is_edp && !aux->enable_xfers) { + ret = -ENXIO; + goto exit; + } + /* * For eDP it's important to give a reasonably long wait here for HPD * to be asserted. This is because the panel driver may have _just_ @@ -433,6 +445,14 @@ irqreturn_t dp_aux_isr(struct drm_dp_aux *dp_aux) return IRQ_HANDLED; } +void dp_aux_enable_xfers(struct drm_dp_aux *dp_aux, bool enabled) +{ + struct dp_aux_private *aux; + + aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + aux->enable_xfers = enabled; +} + void dp_aux_reconfig(struct drm_dp_aux *dp_aux) { struct dp_aux_private *aux; diff --git a/drivers/gpu/drm/msm/dp/dp_aux.h b/drivers/gpu/drm/msm/dp/dp_aux.h index 511305da4f66d..f3052cb43306b 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.h +++ b/drivers/gpu/drm/msm/dp/dp_aux.h @@ -12,6 +12,7 @@ int dp_aux_register(struct drm_dp_aux *dp_aux); void dp_aux_unregister(struct drm_dp_aux *dp_aux); irqreturn_t dp_aux_isr(struct drm_dp_aux *dp_aux); +void dp_aux_enable_xfers(struct drm_dp_aux *dp_aux, bool enabled); void dp_aux_init(struct drm_dp_aux *dp_aux); void dp_aux_deinit(struct drm_dp_aux *dp_aux); void dp_aux_reconfig(struct drm_dp_aux *dp_aux); diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index fb588fde298a2..780e9747be1fb 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1019,14 +1019,14 @@ static int dp_ctrl_update_vx_px(struct dp_ctrl_private *ctrl) if (ret) return ret; - if (voltage_swing_level >= DP_TRAIN_VOLTAGE_SWING_MAX) { + if (voltage_swing_level >= DP_TRAIN_LEVEL_MAX) { drm_dbg_dp(ctrl->drm_dev, "max. voltage swing level reached %d\n", voltage_swing_level); max_level_reached |= DP_TRAIN_MAX_SWING_REACHED; } - if (pre_emphasis_level >= DP_TRAIN_PRE_EMPHASIS_MAX) { + if (pre_emphasis_level >= DP_TRAIN_LEVEL_MAX) { drm_dbg_dp(ctrl->drm_dev, "max. pre-emphasis level reached %d\n", pre_emphasis_level); @@ -1117,7 +1117,7 @@ static int dp_ctrl_link_train_1(struct dp_ctrl_private *ctrl, } if (ctrl->link->phy_params.v_level >= - DP_TRAIN_VOLTAGE_SWING_MAX) { + DP_TRAIN_LEVEL_MAX) { DRM_ERROR_RATELIMITED("max v_level reached\n"); return -EAGAIN; } diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 4c72124ffb5d4..0840860336790 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -565,6 +565,8 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) int ret; struct platform_device *pdev = dp->dp_display.pdev; + dp_aux_enable_xfers(dp->aux, true); + mutex_lock(&dp->event_mutex); state = dp->hpd_state; @@ -598,6 +600,7 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) ret = dp_display_usbpd_configure_cb(&pdev->dev); if (ret) { /* link train failed */ dp->hpd_state = ST_DISCONNECTED; + pm_runtime_put_sync(&pdev->dev); } else { dp->hpd_state = ST_MAINLINK_READY; } @@ -629,6 +632,8 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) u32 state; struct platform_device *pdev = dp->dp_display.pdev; + dp_aux_enable_xfers(dp->aux, false); + mutex_lock(&dp->event_mutex); state = dp->hpd_state; @@ -655,6 +660,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) dp_display_host_phy_exit(dp); dp->hpd_state = ST_DISCONNECTED; dp_display_notify_disconnect(&dp->dp_display.pdev->dev); + pm_runtime_put_sync(&pdev->dev); mutex_unlock(&dp->event_mutex); return 0; } diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 49dfac1fd1ef2..ea911d9244be7 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -1109,6 +1109,7 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link) int dp_link_adjust_levels(struct dp_link *dp_link, u8 *link_status) { int i; + u8 max_p_level; int v_max = 0, p_max = 0; struct dp_link_private *link; @@ -1140,30 +1141,29 @@ int dp_link_adjust_levels(struct dp_link *dp_link, u8 *link_status) * Adjust the voltage swing and pre-emphasis level combination to within * the allowable range. */ - if (dp_link->phy_params.v_level > DP_TRAIN_VOLTAGE_SWING_MAX) { + if (dp_link->phy_params.v_level > DP_TRAIN_LEVEL_MAX) { drm_dbg_dp(link->drm_dev, "Requested vSwingLevel=%d, change to %d\n", dp_link->phy_params.v_level, - DP_TRAIN_VOLTAGE_SWING_MAX); - dp_link->phy_params.v_level = DP_TRAIN_VOLTAGE_SWING_MAX; + DP_TRAIN_LEVEL_MAX); + dp_link->phy_params.v_level = DP_TRAIN_LEVEL_MAX; } - if (dp_link->phy_params.p_level > DP_TRAIN_PRE_EMPHASIS_MAX) { + if (dp_link->phy_params.p_level > DP_TRAIN_LEVEL_MAX) { drm_dbg_dp(link->drm_dev, "Requested preEmphasisLevel=%d, change to %d\n", dp_link->phy_params.p_level, - DP_TRAIN_PRE_EMPHASIS_MAX); - dp_link->phy_params.p_level = DP_TRAIN_PRE_EMPHASIS_MAX; + DP_TRAIN_LEVEL_MAX); + dp_link->phy_params.p_level = DP_TRAIN_LEVEL_MAX; } - if ((dp_link->phy_params.p_level > DP_TRAIN_PRE_EMPHASIS_LVL_1) - && (dp_link->phy_params.v_level == - DP_TRAIN_VOLTAGE_SWING_LVL_2)) { + max_p_level = DP_TRAIN_LEVEL_MAX - dp_link->phy_params.v_level; + if (dp_link->phy_params.p_level > max_p_level) { drm_dbg_dp(link->drm_dev, "Requested preEmphasisLevel=%d, change to %d\n", dp_link->phy_params.p_level, - DP_TRAIN_PRE_EMPHASIS_LVL_1); - dp_link->phy_params.p_level = DP_TRAIN_PRE_EMPHASIS_LVL_1; + max_p_level); + dp_link->phy_params.p_level = max_p_level; } drm_dbg_dp(link->drm_dev, "adjusted: v_level=%d, p_level=%d\n", diff --git a/drivers/gpu/drm/msm/dp/dp_link.h b/drivers/gpu/drm/msm/dp/dp_link.h index 9dd4dd9265304..79c3a02b8dacd 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.h +++ b/drivers/gpu/drm/msm/dp/dp_link.h @@ -19,19 +19,7 @@ struct dp_link_info { unsigned long capabilities; }; -enum dp_link_voltage_level { - DP_TRAIN_VOLTAGE_SWING_LVL_0 = 0, - DP_TRAIN_VOLTAGE_SWING_LVL_1 = 1, - DP_TRAIN_VOLTAGE_SWING_LVL_2 = 2, - DP_TRAIN_VOLTAGE_SWING_MAX = DP_TRAIN_VOLTAGE_SWING_LVL_2, -}; - -enum dp_link_preemaphasis_level { - DP_TRAIN_PRE_EMPHASIS_LVL_0 = 0, - DP_TRAIN_PRE_EMPHASIS_LVL_1 = 1, - DP_TRAIN_PRE_EMPHASIS_LVL_2 = 2, - DP_TRAIN_PRE_EMPHASIS_MAX = DP_TRAIN_PRE_EMPHASIS_LVL_2, -}; +#define DP_TRAIN_LEVEL_MAX 3 struct dp_link_test_video { u32 test_video_pattern; diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index deeecdfd6c4e4..758a071150ecd 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -366,8 +366,8 @@ int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host) { int ret; - DBG("Set clk rates: pclk=%d, byteclk=%lu", - msm_host->mode->clock, msm_host->byte_clk_rate); + DBG("Set clk rates: pclk=%lu, byteclk=%lu", + msm_host->pixel_clk_rate, msm_host->byte_clk_rate); ret = dev_pm_opp_set_rate(&msm_host->pdev->dev, msm_host->byte_clk_rate); @@ -440,9 +440,9 @@ int dsi_link_clk_set_rate_v2(struct msm_dsi_host *msm_host) { int ret; - DBG("Set clk rates: pclk=%d, byteclk=%lu, esc_clk=%lu, dsi_src_clk=%lu", - msm_host->mode->clock, msm_host->byte_clk_rate, - msm_host->esc_clk_rate, msm_host->src_clk_rate); + DBG("Set clk rates: pclk=%lu, byteclk=%lu, esc_clk=%lu, dsi_src_clk=%lu", + msm_host->pixel_clk_rate, msm_host->byte_clk_rate, + msm_host->esc_clk_rate, msm_host->src_clk_rate); ret = clk_set_rate(msm_host->byte_clk, msm_host->byte_clk_rate); if (ret) { diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c index e3f61c39df69b..80166f702a0db 100644 --- a/drivers/gpu/drm/msm/msm_fb.c +++ b/drivers/gpu/drm/msm/msm_fb.c @@ -89,7 +89,7 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb, for (i = 0; i < n; i++) { ret = msm_gem_get_and_pin_iova(fb->obj[i], aspace, &msm_fb->iova[i]); - drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)", + drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)\n", fb->base.id, i, msm_fb->iova[i], ret); if (ret) return ret; @@ -176,7 +176,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, const struct msm_format *format; int ret, i, n; - drm_dbg_state(dev, "create framebuffer: mode_cmd=%p (%dx%d@%4.4s)", + drm_dbg_state(dev, "create framebuffer: mode_cmd=%p (%dx%d@%4.4s)\n", mode_cmd, mode_cmd->width, mode_cmd->height, (char *)&mode_cmd->pixel_format); @@ -232,7 +232,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, refcount_set(&msm_fb->dirtyfb, 1); - drm_dbg_state(dev, "create: FB ID: %d (%p)", fb->base.id, fb); + drm_dbg_state(dev, "create: FB ID: %d (%p)\n", fb->base.id, fb); return fb; diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 84c21ec2ceeae..af6a6fcb11736 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -149,7 +149,7 @@ int msm_crtc_enable_vblank(struct drm_crtc *crtc) struct msm_kms *kms = priv->kms; if (!kms) return -ENXIO; - drm_dbg_vbl(dev, "crtc=%u", crtc->base.id); + drm_dbg_vbl(dev, "crtc=%u\n", crtc->base.id); return vblank_ctrl_queue_work(priv, crtc, true); } @@ -160,7 +160,7 @@ void msm_crtc_disable_vblank(struct drm_crtc *crtc) struct msm_kms *kms = priv->kms; if (!kms) return; - drm_dbg_vbl(dev, "crtc=%u", crtc->base.id); + drm_dbg_vbl(dev, "crtc=%u\n", crtc->base.id); vblank_ctrl_queue_work(priv, crtc, false); } diff --git a/drivers/gpu/drm/mxsfb/lcdif_drv.c b/drivers/gpu/drm/mxsfb/lcdif_drv.c index 18de2f17e2491..6494e82707569 100644 --- a/drivers/gpu/drm/mxsfb/lcdif_drv.c +++ b/drivers/gpu/drm/mxsfb/lcdif_drv.c @@ -340,6 +340,9 @@ static int __maybe_unused lcdif_suspend(struct device *dev) if (ret) return ret; + if (pm_runtime_suspended(dev)) + return 0; + return lcdif_rpm_suspend(dev); } @@ -347,7 +350,8 @@ static int __maybe_unused lcdif_resume(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - lcdif_rpm_resume(dev); + if (!pm_runtime_suspended(dev)) + lcdif_rpm_resume(dev); return drm_mode_config_helper_resume(drm); } diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c index 13705c5f14973..4b7497a8755cd 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c @@ -68,7 +68,7 @@ nv04_display_fini(struct drm_device *dev, bool runtime, bool suspend) if (nv_two_heads(dev)) NVWriteCRTC(dev, 1, NV_PCRTC_INTR_EN_0, 0); - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); if (!suspend) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 8d37a694b7724..16c784da154cc 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -914,7 +914,7 @@ nv50_msto_cleanup(struct drm_atomic_state *state, msto->disabled = false; drm_dp_remove_payload_part2(mgr, new_mst_state, old_payload, new_payload); } else if (msto->enabled) { - drm_dp_add_payload_part2(mgr, state, new_payload); + drm_dp_add_payload_part2(mgr, new_payload); msto->enabled = false; } } @@ -2679,7 +2679,7 @@ nv50_display_fini(struct drm_device *dev, bool runtime, bool suspend) nv50_mstm_fini(nouveau_encoder(encoder)); } - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); } diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h index 6f5d376d8fcc1..a11d16a16c3b2 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h @@ -15,7 +15,9 @@ struct nvkm_gsp_mem { }; struct nvkm_gsp_radix3 { - struct nvkm_gsp_mem mem[3]; + struct nvkm_gsp_mem lvl0; + struct nvkm_gsp_mem lvl1; + struct sg_table lvl2; }; int nvkm_gsp_sg(struct nvkm_device *, u64 size, struct sg_table *); diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index 80f74ee0fc786..47e53e17b4e58 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -272,6 +272,9 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) getparam->value = (u64)ttm_resource_manager_usage(vram_mgr); break; } + case NOUVEAU_GETPARAM_HAS_VMA_TILEMODE: + getparam->value = 1; + break; default: NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param); return -EINVAL; diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 479effcf607e2..79cfab53f80e2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -23,6 +23,7 @@ */ #include "nouveau_drv.h" +#include "nouveau_bios.h" #include "nouveau_reg.h" #include "dispnv04/hw.h" #include "nouveau_encoder.h" @@ -1677,7 +1678,7 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf) */ if (nv_match_device(dev, 0x0201, 0x1462, 0x8851)) { if (*conn == 0xf2005014 && *conf == 0xffffffff) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, 1); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, DCB_OUTPUT_B); return false; } } @@ -1763,26 +1764,26 @@ fabricate_dcb_encoder_table(struct drm_device *dev, struct nvbios *bios) #ifdef __powerpc__ /* Apple iMac G4 NV17 */ if (of_machine_is_compatible("PowerMac4,5")) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, 1); - fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, 2); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, DCB_OUTPUT_B); + fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, DCB_OUTPUT_C); return; } #endif /* Make up some sane defaults */ fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, - bios->legacy.i2c_indices.crt, 1, 1); + bios->legacy.i2c_indices.crt, 1, DCB_OUTPUT_B); if (nv04_tv_identify(dev, bios->legacy.i2c_indices.tv) >= 0) fabricate_dcb_output(dcb, DCB_OUTPUT_TV, bios->legacy.i2c_indices.tv, - all_heads, 0); + all_heads, DCB_OUTPUT_A); else if (bios->tmds.output0_script_ptr || bios->tmds.output1_script_ptr) fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, bios->legacy.i2c_indices.panel, - all_heads, 1); + all_heads, DCB_OUTPUT_B); } static int diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 00cc7d1abaa39..eaa087a2ca63b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -241,28 +241,28 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, } nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG); - if (!nouveau_cli_uvmm(cli) || internal) { - /* for BO noVM allocs, don't assign kinds */ - if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { - nvbo->kind = (tile_flags & 0x0000ff00) >> 8; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } - nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; - } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { - nvbo->kind = (tile_flags & 0x00007f00) >> 8; - nvbo->comp = (tile_flags & 0x00030000) >> 16; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } - } else { - nvbo->zeta = (tile_flags & 0x00000007); + if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { + nvbo->kind = (tile_flags & 0x0000ff00) >> 8; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); + } + + nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; + } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { + nvbo->kind = (tile_flags & 0x00007f00) >> 8; + nvbo->comp = (tile_flags & 0x00030000) >> 16; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); } - nvbo->mode = tile_mode; + } else { + nvbo->zeta = (tile_flags & 0x00000007); + } + nvbo->mode = tile_mode; + if (!nouveau_cli_uvmm(cli) || internal) { /* Determine the desirable target GPU page size for the buffer. */ for (i = 0; i < vmm->page_nr; i++) { /* Because we cannot currently allow VMM maps to fail @@ -304,12 +304,6 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, } nvbo->page = vmm->page[pi].shift; } else { - /* reject other tile flags when in VM mode. */ - if (tile_mode) - return ERR_PTR(-EINVAL); - if (tile_flags & ~NOUVEAU_GEM_TILE_NONCONTIG) - return ERR_PTR(-EINVAL); - /* Determine the desirable target GPU page size for the buffer. */ for (i = 0; i < vmm->page_nr; i++) { /* Because we cannot currently allow VMM maps to fail @@ -1264,6 +1258,8 @@ nouveau_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *reg) drm_vma_node_unmap(&nvbo->bo.base.vma_node, bdev->dev_mapping); nouveau_ttm_io_mem_free_locked(drm, nvbo->bo.resource); + nvbo->bo.resource->bus.offset = 0; + nvbo->bo.resource->bus.addr = NULL; goto retry; } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index f28f9a8574586..60c32244211d0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -450,6 +450,9 @@ nouveau_display_hpd_resume(struct drm_device *dev) { struct nouveau_drm *drm = nouveau_drm(dev); + if (drm->headless) + return; + spin_lock_irq(&drm->hpd_lock); drm->hpd_pending = ~0; spin_unlock_irq(&drm->hpd_lock); @@ -635,7 +638,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime) } drm_connector_list_iter_end(&conn_iter); - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); drm_kms_helper_poll_disable(dev); @@ -729,6 +732,7 @@ nouveau_display_create(struct drm_device *dev) /* no display hw */ if (ret == -ENODEV) { ret = 0; + drm->headless = true; goto disp_create_err; } diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 12feecf71e752..6fb65b01d7780 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -378,9 +378,9 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) dma_addr_t *dma_addrs; struct nouveau_fence *fence; - src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); - dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); - dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL); + src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL); + dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL); + dma_addrs = kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL); migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, npages); @@ -406,11 +406,11 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) migrate_device_pages(src_pfns, dst_pfns, npages); nouveau_dmem_fence_done(&fence); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); + kvfree(src_pfns); + kvfree(dst_pfns); for (i = 0; i < npages; i++) dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); - kfree(dma_addrs); + kvfree(dma_addrs); } void diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 7de7707ec6a89..3f72bc38bd2c4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -225,12 +225,15 @@ nouveau_dp_detect(struct nouveau_connector *nv_connector, u8 *dpcd = nv_encoder->dp.dpcd; int ret = NOUVEAU_DP_NONE, hpd; - /* If we've already read the DPCD on an eDP device, we don't need to - * reread it as it won't change + /* eDP ports don't support hotplugging - so there's no point in probing eDP ports unless we + * haven't probed them once before. */ - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && - dpcd[DP_DPCD_REV] != 0) - return NOUVEAU_DP_SST; + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + if (connector->status == connector_status_connected) + return NOUVEAU_DP_SST; + else if (connector->status == connector_status_disconnected) + return NOUVEAU_DP_NONE; + } mutex_lock(&nv_encoder->dp.hpd_irq_lock); if (mstm) { diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index e239c6bf4afa4..25fca98a20bcd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -276,6 +276,7 @@ struct nouveau_drm { /* modesetting */ struct nvbios vbios; struct nouveau_display *display; + bool headless; struct work_struct hpd_work; spinlock_t hpd_lock; u32 hpd_pending; diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index 0a0a11dc9ec03..ee02cd833c5e4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -812,15 +812,15 @@ op_remap(struct drm_gpuva_op_remap *r, struct drm_gpuva_op_unmap *u = r->unmap; struct nouveau_uvma *uvma = uvma_from_va(u->va); u64 addr = uvma->va.va.addr; - u64 range = uvma->va.va.range; + u64 end = uvma->va.va.addr + uvma->va.va.range; if (r->prev) addr = r->prev->va.addr + r->prev->va.range; if (r->next) - range = r->next->va.addr - addr; + end = r->next->va.addr; - op_unmap_range(u, addr, range); + op_unmap_range(u, addr, end - addr); } static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c index 6a0a4d3b8902d..027867c2a8c5b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c @@ -1080,7 +1080,7 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize) ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); if (ret) { nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); - return PTR_ERR(ctrl); + return ret; } memcpy(data, ctrl->data, size); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c index 4bf486b571013..cb05f7f48a98b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c @@ -66,11 +66,16 @@ of_init(struct nvkm_bios *bios, const char *name) return ERR_PTR(-EINVAL); } +static void of_fini(void *p) +{ + kfree(p); +} + const struct nvbios_source nvbios_of = { .name = "OpenFirmware", .init = of_init, - .fini = (void(*)(void *))kfree, + .fini = of_fini, .read = of_read, .size = of_size, .rw = false, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c index 7bcbc4895ec22..271bfa038f5bc 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c @@ -25,6 +25,7 @@ #include #include +#include void gm107_devinit_disable(struct nvkm_devinit *init) @@ -33,10 +34,13 @@ gm107_devinit_disable(struct nvkm_devinit *init) u32 r021c00 = nvkm_rd32(device, 0x021c00); u32 r021c04 = nvkm_rd32(device, 0x021c04); - if (r021c00 & 0x00000001) - nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0); - if (r021c00 & 0x00000004) - nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2); + /* gsp only wants to enable/disable display */ + if (!nvkm_gsp_rm(device->gsp)) { + if (r021c00 & 0x00000001) + nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0); + if (r021c00 & 0x00000004) + nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2); + } if (r021c04 & 0x00000001) nvkm_subdev_disable(device, NVKM_ENGINE_DISP, 0); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index a73a5b5897904..49171d312f607 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -1112,7 +1112,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp) rpc->numEntries = NV_GSP_REG_NUM_ENTRIES; str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]); - strings = (char *)&rpc->entries[NV_GSP_REG_NUM_ENTRIES]; + strings = (char *)rpc + str_offset; for (i = 0; i < NV_GSP_REG_NUM_ENTRIES; i++) { int name_len = strlen(r535_registry_entries[i].name) + 1; @@ -1620,7 +1620,7 @@ r535_gsp_wpr_meta_init(struct nvkm_gsp *gsp) meta->magic = GSP_FW_WPR_META_MAGIC; meta->revision = GSP_FW_WPR_META_REVISION; - meta->sysmemAddrOfRadix3Elf = gsp->radix3.mem[0].addr; + meta->sysmemAddrOfRadix3Elf = gsp->radix3.lvl0.addr; meta->sizeOfRadix3Elf = gsp->fb.wpr2.elf.size; meta->sysmemAddrOfBootloader = gsp->boot.fw.addr; @@ -1914,8 +1914,9 @@ nvkm_gsp_sg(struct nvkm_device *device, u64 size, struct sg_table *sgt) static void nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3) { - for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) - nvkm_gsp_mem_dtor(gsp, &rx3->mem[i]); + nvkm_gsp_sg_free(gsp->subdev.device, &rx3->lvl2); + nvkm_gsp_mem_dtor(gsp, &rx3->lvl1); + nvkm_gsp_mem_dtor(gsp, &rx3->lvl0); } /** @@ -1951,36 +1952,60 @@ static int nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size, struct nvkm_gsp_radix3 *rx3) { - u64 addr; + struct sg_dma_page_iter sg_dma_iter; + struct scatterlist *sg; + size_t bufsize; + u64 *pte; + int ret, i, page_idx = 0; - for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) { - u64 *ptes; - size_t bufsize; - int ret, idx; + ret = nvkm_gsp_mem_ctor(gsp, GSP_PAGE_SIZE, &rx3->lvl0); + if (ret) + return ret; - bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE); - ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]); - if (ret) - return ret; + ret = nvkm_gsp_mem_ctor(gsp, GSP_PAGE_SIZE, &rx3->lvl1); + if (ret) + goto lvl1_fail; - ptes = rx3->mem[i].data; - if (i == 2) { - struct scatterlist *sgl; + // Allocate level 2 + bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE); + ret = nvkm_gsp_sg(gsp->subdev.device, bufsize, &rx3->lvl2); + if (ret) + goto lvl2_fail; - for_each_sgtable_dma_sg(sgt, sgl, idx) { - for (int j = 0; j < sg_dma_len(sgl) / GSP_PAGE_SIZE; j++) - *ptes++ = sg_dma_address(sgl) + (GSP_PAGE_SIZE * j); - } - } else { - for (int j = 0; j < size / GSP_PAGE_SIZE; j++) - *ptes++ = addr + GSP_PAGE_SIZE * j; + // Write the bus address of level 1 to level 0 + pte = rx3->lvl0.data; + *pte = rx3->lvl1.addr; + + // Write the bus address of each page in level 2 to level 1 + pte = rx3->lvl1.data; + for_each_sgtable_dma_page(&rx3->lvl2, &sg_dma_iter, 0) + *pte++ = sg_page_iter_dma_address(&sg_dma_iter); + + // Finally, write the bus address of each page in sgt to level 2 + for_each_sgtable_sg(&rx3->lvl2, sg, i) { + void *sgl_end; + + pte = sg_virt(sg); + sgl_end = (void *)pte + sg->length; + + for_each_sgtable_dma_page(sgt, &sg_dma_iter, page_idx) { + *pte++ = sg_page_iter_dma_address(&sg_dma_iter); + page_idx++; + + // Go to the next scatterlist for level 2 if we've reached the end + if ((void *)pte >= sgl_end) + break; } + } - size = rx3->mem[i].size; - addr = rx3->mem[i].addr; + if (ret) { +lvl2_fail: + nvkm_gsp_mem_dtor(gsp, &rx3->lvl1); +lvl1_fail: + nvkm_gsp_mem_dtor(gsp, &rx3->lvl0); } - return 0; + return ret; } int @@ -2012,7 +2037,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend) sr = gsp->sr.meta.data; sr->magic = GSP_FW_SR_META_MAGIC; sr->revision = GSP_FW_SR_META_REVISION; - sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.mem[0].addr; + sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.lvl0.addr; sr->sizeOfSuspendResumeData = len; mbox0 = lower_32_bits(gsp->sr.meta.addr); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index a7f3fc342d87e..dd5b5a17ece0b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -222,8 +222,11 @@ nv50_instobj_acquire(struct nvkm_memory *memory) void __iomem *map = NULL; /* Already mapped? */ - if (refcount_inc_not_zero(&iobj->maps)) + if (refcount_inc_not_zero(&iobj->maps)) { + /* read barrier match the wmb on refcount set */ + smp_rmb(); return iobj->map; + } /* Take the lock, and re-check that another thread hasn't * already mapped the object in the meantime. @@ -250,6 +253,8 @@ nv50_instobj_acquire(struct nvkm_memory *memory) iobj->base.memory.ptrs = &nv50_instobj_fast; else iobj->base.memory.ptrs = &nv50_instobj_slow; + /* barrier to ensure the ptrs are written before refcount is set */ + smp_wmb(); refcount_set(&iobj->maps, 1); } diff --git a/drivers/gpu/drm/omapdrm/Kconfig b/drivers/gpu/drm/omapdrm/Kconfig index b715301ec79f6..6c49270cb290a 100644 --- a/drivers/gpu/drm/omapdrm/Kconfig +++ b/drivers/gpu/drm/omapdrm/Kconfig @@ -4,7 +4,7 @@ config DRM_OMAP depends on DRM && OF depends on ARCH_OMAP2PLUS select DRM_KMS_HELPER - select FB_DMAMEM_HELPERS if DRM_FBDEV_EMULATION + select FB_DMAMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION select VIDEOMODE_HELPERS select HDMI default n diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index 6b08b137af1ad..523be34682caf 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -51,6 +51,10 @@ static void pan_worker(struct work_struct *work) omap_gem_roll(bo, fbi->var.yoffset * npages); } +FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(omap_fbdev, + drm_fb_helper_damage_range, + drm_fb_helper_damage_area) + static int omap_fbdev_pan_display(struct fb_var_screeninfo *var, struct fb_info *fbi) { @@ -78,11 +82,9 @@ static int omap_fbdev_pan_display(struct fb_var_screeninfo *var, static int omap_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) { - struct drm_fb_helper *helper = info->par; - struct drm_framebuffer *fb = helper->fb; - struct drm_gem_object *bo = drm_gem_fb_get_obj(fb, 0); + vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); - return drm_gem_mmap_obj(bo, omap_gem_mmap_size(bo), vma); + return fb_deferred_io_mmap(info, vma); } static void omap_fbdev_fb_destroy(struct fb_info *info) @@ -94,6 +96,7 @@ static void omap_fbdev_fb_destroy(struct fb_info *info) DBG(); + fb_deferred_io_cleanup(info); drm_fb_helper_fini(helper); omap_gem_unpin(bo); @@ -104,15 +107,19 @@ static void omap_fbdev_fb_destroy(struct fb_info *info) kfree(fbdev); } +/* + * For now, we cannot use FB_DEFAULT_DEFERRED_OPS and fb_deferred_io_mmap() + * because we use write-combine. + */ static const struct fb_ops omap_fb_ops = { .owner = THIS_MODULE, - __FB_DEFAULT_DMAMEM_OPS_RDWR, + __FB_DEFAULT_DEFERRED_OPS_RDWR(omap_fbdev), .fb_check_var = drm_fb_helper_check_var, .fb_set_par = drm_fb_helper_set_par, .fb_setcmap = drm_fb_helper_setcmap, .fb_blank = drm_fb_helper_blank, .fb_pan_display = omap_fbdev_pan_display, - __FB_DEFAULT_DMAMEM_OPS_DRAW, + __FB_DEFAULT_DEFERRED_OPS_DRAW(omap_fbdev), .fb_ioctl = drm_fb_helper_ioctl, .fb_mmap = omap_fbdev_fb_mmap, .fb_destroy = omap_fbdev_fb_destroy, @@ -213,6 +220,15 @@ static int omap_fbdev_create(struct drm_fb_helper *helper, fbi->fix.smem_start = dma_addr; fbi->fix.smem_len = bo->size; + /* deferred I/O */ + helper->fbdefio.delay = HZ / 20; + helper->fbdefio.deferred_io = drm_fb_helper_deferred_io; + + fbi->fbdefio = &helper->fbdefio; + ret = fb_deferred_io_init(fbi); + if (ret) + goto fail; + /* if we have DMM, then we can use it for scrolling by just * shuffling pages around in DMM rather than doing sw blit. */ @@ -238,8 +254,20 @@ static int omap_fbdev_create(struct drm_fb_helper *helper, return ret; } +static int omap_fbdev_dirty(struct drm_fb_helper *helper, struct drm_clip_rect *clip) +{ + if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2)) + return 0; + + if (helper->fb->funcs->dirty) + return helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1); + + return 0; +} + static const struct drm_fb_helper_funcs omap_fb_helper_funcs = { .fb_probe = omap_fbdev_create, + .fb_dirty = omap_fbdev_dirty, }; static struct drm_fb_helper *get_fb(struct fb_info *fbi) diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index 8f3783742208b..888297d0d3955 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -184,7 +184,7 @@ config DRM_PANEL_ILITEK_IL9322 config DRM_PANEL_ILITEK_ILI9341 tristate "Ilitek ILI9341 240x320 QVGA panels" - depends on OF && SPI + depends on SPI select DRM_KMS_HELPER select DRM_GEM_DMA_HELPER depends on BACKLIGHT_CLASS_DEVICE diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 4945a1e787eb3..0ffe8f8c01de8 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1871,6 +1871,8 @@ static int boe_panel_add(struct boe_panel *boe) gpiod_set_value(boe->enable_gpio, 0); + boe->base.prepare_prev_first = true; + drm_panel_init(&boe->base, dev, &boe_panel_funcs, DRM_MODE_CONNECTOR_DSI); err = of_drm_get_panel_orientation(dev->of_node, &boe->orientation); diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index a0b6f69b916f9..49b8a2484d92b 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -397,6 +397,7 @@ static int panel_edp_suspend(struct device *dev) { struct panel_edp *p = dev_get_drvdata(dev); + drm_dp_dpcd_set_powered(p->aux, false); gpiod_set_value_cansleep(p->enable_gpio, 0); regulator_disable(p->supply); p->unprepared_time = ktime_get_boottime(); @@ -413,8 +414,7 @@ static int panel_edp_unprepare(struct drm_panel *panel) if (!p->prepared) return 0; - pm_runtime_mark_last_busy(panel->dev); - ret = pm_runtime_put_autosuspend(panel->dev); + ret = pm_runtime_put_sync_suspend(panel->dev); if (ret < 0) return ret; p->prepared = false; @@ -454,6 +454,7 @@ static int panel_edp_prepare_once(struct panel_edp *p) } gpiod_set_value_cansleep(p->enable_gpio, 1); + drm_dp_dpcd_set_powered(p->aux, true); delay = p->desc->delay.hpd_reliable; if (p->no_hpd) @@ -490,6 +491,7 @@ static int panel_edp_prepare_once(struct panel_edp *p) return 0; error: + drm_dp_dpcd_set_powered(p->aux, false); gpiod_set_value_cansleep(p->enable_gpio, 0); regulator_disable(p->supply); p->unprepared_time = ktime_get_boottime(); diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index 3574681891e81..b933380b7eb78 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -22,8 +22,9 @@ #include #include #include +#include #include -#include +#include #include #include @@ -421,7 +422,7 @@ static int ili9341_dpi_prepare(struct drm_panel *panel) ili9341_dpi_init(ili); - return ret; + return 0; } static int ili9341_dpi_enable(struct drm_panel *panel) @@ -691,7 +692,7 @@ static int ili9341_dpi_probe(struct spi_device *spi, struct gpio_desc *dc, * Every new incarnation of this display must have a unique * data entry for the system in this driver. */ - ili->conf = of_device_get_match_data(dev); + ili->conf = device_get_match_data(dev); if (!ili->conf) { dev_err(dev, "missing device configuration\n"); return -ENODEV; @@ -714,18 +715,18 @@ static int ili9341_probe(struct spi_device *spi) reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(reset)) - dev_err(dev, "Failed to get gpio 'reset'\n"); + return dev_err_probe(dev, PTR_ERR(reset), "Failed to get gpio 'reset'\n"); dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW); if (IS_ERR(dc)) - dev_err(dev, "Failed to get gpio 'dc'\n"); + return dev_err_probe(dev, PTR_ERR(dc), "Failed to get gpio 'dc'\n"); if (!strcmp(id->name, "sf-tc240t-9370-t")) return ili9341_dpi_probe(spi, dc, reset); else if (!strcmp(id->name, "yx240qv29")) return ili9341_dbi_probe(spi, dc, reset); - return -1; + return -ENODEV; } static void ili9341_remove(struct spi_device *spi) diff --git a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c index 30919c872ac8d..8e0f5c3e3b98e 100644 --- a/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c +++ b/drivers/gpu/drm/panel/panel-leadtek-ltk050h3146w.c @@ -295,8 +295,6 @@ static int ltk050h3148w_init_sequence(struct ltk050h3146w *ctx) mipi_dsi_dcs_write_seq(dsi, 0xbd, 0x00); mipi_dsi_dcs_write_seq(dsi, 0xc6, 0xef); mipi_dsi_dcs_write_seq(dsi, 0xd4, 0x02); - mipi_dsi_dcs_write_seq(dsi, 0x11); - mipi_dsi_dcs_write_seq(dsi, 0x29); ret = mipi_dsi_dcs_set_tear_on(dsi, 1); if (ret < 0) { @@ -326,7 +324,8 @@ static const struct drm_display_mode ltk050h3148w_mode = { static const struct ltk050h3146w_desc ltk050h3148w_data = { .mode = <k050h3148w_mode, .init = ltk050h3148w_init_sequence, - .mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_VIDEO_BURST, + .mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | + MIPI_DSI_MODE_VIDEO_BURST, }; static int ltk050h3146w_init_sequence(struct ltk050h3146w *ctx) diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35950.c b/drivers/gpu/drm/panel/panel-novatek-nt35950.c index 648ce92014265..028fdac293f77 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35950.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35950.c @@ -556,10 +556,8 @@ static int nt35950_probe(struct mipi_dsi_device *dsi) } dsi_r_host = of_find_mipi_dsi_host_by_node(dsi_r); of_node_put(dsi_r); - if (!dsi_r_host) { - dev_err(dev, "Cannot get secondary DSI host\n"); - return -EPROBE_DEFER; - } + if (!dsi_r_host) + return dev_err_probe(dev, -EPROBE_DEFER, "Cannot get secondary DSI host\n"); nt->dsi[1] = mipi_dsi_device_register_full(dsi_r_host, info); if (!nt->dsi[1]) { diff --git a/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c b/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c index 5703f4712d96e..9c336c71562b9 100644 --- a/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c +++ b/drivers/gpu/drm/panel/panel-samsung-atna33xc20.c @@ -72,6 +72,7 @@ static int atana33xc20_suspend(struct device *dev) if (p->el3_was_on) atana33xc20_wait(p->el_on3_off_time, 150); + drm_dp_dpcd_set_powered(p->aux, false); ret = regulator_disable(p->supply); if (ret) return ret; @@ -93,6 +94,7 @@ static int atana33xc20_resume(struct device *dev) ret = regulator_enable(p->supply); if (ret) return ret; + drm_dp_dpcd_set_powered(p->aux, true); p->powered_on_time = ktime_get_boottime(); if (p->no_hpd) { @@ -107,19 +109,17 @@ static int atana33xc20_resume(struct device *dev) if (hpd_asserted < 0) ret = hpd_asserted; - if (ret) + if (ret) { dev_warn(dev, "Error waiting for HPD GPIO: %d\n", ret); - - return ret; - } - - if (p->aux->wait_hpd_asserted) { + goto error; + } + } else if (p->aux->wait_hpd_asserted) { ret = p->aux->wait_hpd_asserted(p->aux, HPD_MAX_US); - if (ret) + if (ret) { dev_warn(dev, "Controller error waiting for HPD: %d\n", ret); - - return ret; + goto error; + } } /* @@ -131,6 +131,12 @@ static int atana33xc20_resume(struct device *dev) * right times. */ return 0; + +error: + drm_dp_dpcd_set_powered(p->aux, false); + regulator_disable(p->supply); + + return ret; } static int atana33xc20_disable(struct drm_panel *panel) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index d493ee735c734..228c5c48e1588 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1367,6 +1367,23 @@ static const struct drm_display_mode boe_bp101wx1_100_mode = { .vtotal = 800 + 6 + 8 + 2, }; +static const struct panel_desc boe_bp082wx1_100 = { + .modes = &boe_bp101wx1_100_mode, + .num_modes = 1, + .bpc = 8, + .size = { + .width = 177, + .height = 110, + }, + .delay = { + .enable = 50, + .disable = 50, + }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, + .connector_type = DRM_MODE_CONNECTOR_LVDS, +}; + static const struct panel_desc boe_bp101wx1_100 = { .modes = &boe_bp101wx1_100_mode, .num_modes = 1, @@ -2547,6 +2564,9 @@ static const struct panel_desc innolux_g121x1_l03 = { .unprepare = 200, .disable = 400, }, + .bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, + .connector_type = DRM_MODE_CONNECTOR_LVDS, }; static const struct display_timing innolux_g156hce_l01_timings = { @@ -4345,6 +4365,9 @@ static const struct of_device_id platform_of_match[] = { }, { .compatible = "bananapi,s070wv20-ct16", .data = &bananapi_s070wv20_ct16, + }, { + .compatible = "boe,bp082wx1-100", + .data = &boe_bp082wx1_100, }, { .compatible = "boe,bp101wx1-100", .data = &boe_bp101wx1_100, diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c index 88e80fe98112d..28bfc48a91272 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c @@ -282,15 +282,15 @@ static const struct drm_display_mode et028013dma_mode = { static const struct drm_display_mode jt240mhqs_hwt_ek_e3_mode = { .clock = 6000, .hdisplay = 240, - .hsync_start = 240 + 28, - .hsync_end = 240 + 28 + 10, - .htotal = 240 + 28 + 10 + 10, + .hsync_start = 240 + 38, + .hsync_end = 240 + 38 + 10, + .htotal = 240 + 38 + 10 + 10, .vdisplay = 280, - .vsync_start = 280 + 8, - .vsync_end = 280 + 8 + 4, - .vtotal = 280 + 8 + 4 + 4, - .width_mm = 43, - .height_mm = 37, + .vsync_start = 280 + 48, + .vsync_end = 280 + 48 + 4, + .vtotal = 280 + 48 + 4 + 4, + .width_mm = 37, + .height_mm = 43, .flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC, }; @@ -643,7 +643,9 @@ static int st7789v_probe(struct spi_device *spi) if (ret) return dev_err_probe(dev, ret, "Failed to get backlight\n"); - of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation); + ret = of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation); + if (ret) + return dev_err_probe(&spi->dev, ret, "Failed to get orientation\n"); drm_panel_add(&ctx->panel); diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c index 775144695283f..b15ca56a09a74 100644 --- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c +++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c @@ -253,8 +253,6 @@ static void visionox_rm69299_remove(struct mipi_dsi_device *dsi) struct visionox_rm69299 *ctx = mipi_dsi_get_drvdata(dsi); mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_panel_remove(&ctx->panel); } diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index 9063ce2546422..fd8e44992184f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -441,19 +441,19 @@ void panfrost_gpu_power_off(struct panfrost_device *pfdev) gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO, - val, !val, 1, 1000); + val, !val, 1, 2000); if (ret) dev_err(pfdev->dev, "shader power transition timeout"); gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present); ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO, - val, !val, 1, 1000); + val, !val, 1, 2000); if (ret) dev_err(pfdev->dev, "tiler power transition timeout"); gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present); ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO, - val, !val, 0, 1000); + val, !val, 0, 2000); if (ret) dev_err(pfdev->dev, "l2 power transition timeout"); } diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index f38385fe76bbb..b91019cd5acb1 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -502,11 +502,18 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, mapping_set_unevictable(mapping); for (i = page_offset; i < page_offset + NUM_FAULT_PAGES; i++) { + /* Can happen if the last fault only partially filled this + * section of the pages array before failing. In that case + * we skip already filled pages. + */ + if (pages[i]) + continue; + pages[i] = shmem_read_mapping_page(mapping, i); if (IS_ERR(pages[i])) { ret = PTR_ERR(pages[i]); pages[i] = NULL; - goto err_pages; + goto err_unlock; } } @@ -514,7 +521,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, ret = sg_alloc_table_from_pages(sgt, pages + page_offset, NUM_FAULT_PAGES, 0, SZ_2M, GFP_KERNEL); if (ret) - goto err_pages; + goto err_unlock; ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0); if (ret) @@ -537,8 +544,6 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, err_map: sg_free_table(sgt); -err_pages: - drm_gem_shmem_put_pages(&bo->base); err_unlock: dma_resv_unlock(obj->resv); err_bo: diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 927e5f42e97d0..3e48cbb522a1c 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -813,7 +813,7 @@ int ni_init_microcode(struct radeon_device *rdev) err = 0; } else if (rdev->smc_fw->size != smc_req_size) { pr_err("ni_mc: Bogus length %zu in firmware \"%s\"\n", - rdev->mc_fw->size, fw_name); + rdev->smc_fw->size, fw_name); err = -EINVAL; } } diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h index 94947229888ba..b7f22597ee95e 100644 --- a/drivers/gpu/drm/radeon/pptable.h +++ b/drivers/gpu/drm/radeon/pptable.h @@ -424,7 +424,7 @@ typedef struct _ATOM_PPLIB_SUMO_CLOCK_INFO{ typedef struct _ATOM_PPLIB_STATE_V2 { //number of valid dpm levels in this state; Driver uses it to calculate the whole - //size of the state: sizeof(ATOM_PPLIB_STATE_V2) + (ucNumDPMLevels - 1) * sizeof(UCHAR) + //size of the state: struct_size(ATOM_PPLIB_STATE_V2, clockInfoIndex, ucNumDPMLevels) UCHAR ucNumDPMLevels; //a index to the array of nonClockInfos @@ -432,14 +432,14 @@ typedef struct _ATOM_PPLIB_STATE_V2 /** * Driver will read the first ucNumDPMLevels in this array */ - UCHAR clockInfoIndex[1]; + UCHAR clockInfoIndex[] __counted_by(ucNumDPMLevels); } ATOM_PPLIB_STATE_V2; typedef struct _StateArray{ //how many states we have UCHAR ucNumEntries; - ATOM_PPLIB_STATE_V2 states[1]; + ATOM_PPLIB_STATE_V2 states[] __counted_by(ucNumEntries); }StateArray; @@ -450,7 +450,7 @@ typedef struct _ClockInfoArray{ //sizeof(ATOM_PPLIB_CLOCK_INFO) UCHAR ucEntrySize; - UCHAR clockInfo[1]; + UCHAR clockInfo[] __counted_by(ucNumEntries); }ClockInfoArray; typedef struct _NonClockInfoArray{ @@ -460,7 +460,7 @@ typedef struct _NonClockInfoArray{ //sizeof(ATOM_PPLIB_NONCLOCK_INFO) UCHAR ucEntrySize; - ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[1]; + ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries); }NonClockInfoArray; typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 3596ea4a8b60f..fc7b0e8f1ca15 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -923,8 +923,12 @@ bool radeon_get_atom_connector_info_from_supported_devices_table(struct max_device = ATOM_MAX_SUPPORTED_DEVICE_INFO; for (i = 0; i < max_device; i++) { - ATOM_CONNECTOR_INFO_I2C ci = - supported_devices->info.asConnInfo[i]; + ATOM_CONNECTOR_INFO_I2C ci; + + if (frev > 1) + ci = supported_devices->info_2d1.asConnInfo[i]; + else + ci = supported_devices->info.asConnInfo[i]; bios_connectors[i].valid = false; diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c index d49c145db4370..f7f1ddc6cdd81 100644 --- a/drivers/gpu/drm/radeon/sumo_dpm.c +++ b/drivers/gpu/drm/radeon/sumo_dpm.c @@ -1621,6 +1621,8 @@ void sumo_construct_vid_mapping_table(struct radeon_device *rdev, for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) { if (table[i].ulSupportedSCLK != 0) { + if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES) + continue; vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit = table[i].usVoltageID; vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit = diff --git a/drivers/gpu/drm/renesas/rcar-du/Kconfig b/drivers/gpu/drm/renesas/rcar-du/Kconfig index 53c356aed5d52..2dc739db2ba33 100644 --- a/drivers/gpu/drm/renesas/rcar-du/Kconfig +++ b/drivers/gpu/drm/renesas/rcar-du/Kconfig @@ -25,8 +25,8 @@ config DRM_RCAR_CMM config DRM_RCAR_DW_HDMI tristate "R-Car Gen3 and RZ/G2 DU HDMI Encoder Support" depends on DRM && OF + depends on DRM_DW_HDMI depends on DRM_RCAR_DU || COMPILE_TEST - select DRM_DW_HDMI help Enable support for R-Car Gen3 or RZ/G2 internal HDMI encoder. diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig index 1bf3e2829cd07..0d5260e10f272 100644 --- a/drivers/gpu/drm/rockchip/Kconfig +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -7,7 +7,6 @@ config DRM_ROCKCHIP select DRM_PANEL select VIDEOMODE_HELPERS select DRM_ANALOGIX_DP if ROCKCHIP_ANALOGIX_DP - select DRM_DW_HDMI if ROCKCHIP_DW_HDMI select DRM_DW_MIPI_DSI if ROCKCHIP_DW_MIPI_DSI select GENERIC_PHY if ROCKCHIP_DW_MIPI_DSI select GENERIC_PHY_MIPI_DPHY if ROCKCHIP_DW_MIPI_DSI @@ -57,6 +56,7 @@ config ROCKCHIP_CDN_DP config ROCKCHIP_DW_HDMI bool "Rockchip specific extensions for Synopsys DW HDMI" + depends on DRM_DW_HDMI help This selects support for Rockchip SoC specific extensions for the Synopsys DesignWare HDMI driver. If you want to diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index e6fbe040ccf6a..b66c1ef5838fd 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -411,7 +411,7 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi, hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HBLANK_L, value & 0xFF); hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HBLANK_H, (value >> 8) & 0xFF); - value = mode->hsync_start - mode->hdisplay; + value = mode->htotal - mode->hsync_start; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HDELAY_L, value & 0xFF); hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HDELAY_H, (value >> 8) & 0xFF); @@ -426,7 +426,7 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi, value = mode->vtotal - mode->vdisplay; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_VBLANK, value & 0xFF); - value = mode->vsync_start - mode->vdisplay; + value = mode->vtotal - mode->vsync_start; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_VDELAY, value & 0xFF); value = mode->vsync_end - mode->vsync_start; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index fdd768bbd487c..62ebbdb16253d 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -706,6 +706,8 @@ static void vop2_setup_scale(struct vop2 *vop2, const struct vop2_win *win, const struct drm_format_info *info; u16 hor_scl_mode, ver_scl_mode; u16 hscl_filter_mode, vscl_filter_mode; + uint16_t cbcr_src_w = src_w; + uint16_t cbcr_src_h = src_h; u8 gt2 = 0; u8 gt4 = 0; u32 val; @@ -763,27 +765,27 @@ static void vop2_setup_scale(struct vop2 *vop2, const struct vop2_win *win, vop2_win_write(win, VOP2_WIN_YRGB_VSCL_FILTER_MODE, vscl_filter_mode); if (info->is_yuv) { - src_w /= info->hsub; - src_h /= info->vsub; + cbcr_src_w /= info->hsub; + cbcr_src_h /= info->vsub; gt4 = 0; gt2 = 0; - if (src_h >= (4 * dst_h)) { + if (cbcr_src_h >= (4 * dst_h)) { gt4 = 1; - src_h >>= 2; - } else if (src_h >= (2 * dst_h)) { + cbcr_src_h >>= 2; + } else if (cbcr_src_h >= (2 * dst_h)) { gt2 = 1; - src_h >>= 1; + cbcr_src_h >>= 1; } - hor_scl_mode = scl_get_scl_mode(src_w, dst_w); - ver_scl_mode = scl_get_scl_mode(src_h, dst_h); + hor_scl_mode = scl_get_scl_mode(cbcr_src_w, dst_w); + ver_scl_mode = scl_get_scl_mode(cbcr_src_h, dst_h); - val = vop2_scale_factor(src_w, dst_w); + val = vop2_scale_factor(cbcr_src_w, dst_w); vop2_win_write(win, VOP2_WIN_SCALE_CBCR_X, val); - val = vop2_scale_factor(src_h, dst_h); + val = vop2_scale_factor(cbcr_src_h, dst_h); vop2_win_write(win, VOP2_WIN_SCALE_CBCR_Y, val); vop2_win_write(win, VOP2_WIN_VSD_CBCR_GT4, gt4); diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index 59341654ec32b..77b76cff1adb9 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -576,8 +576,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, ret = -EINVAL; goto err_put_port; } else if (ret) { - DRM_DEV_ERROR(dev, "failed to find panel and bridge node\n"); - ret = -EPROBE_DEFER; + dev_err_probe(dev, ret, "failed to find panel and bridge node\n"); goto err_put_port; } if (lvds->panel) diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c index 48170694ac6b8..18efb3fe1c000 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c @@ -17,9 +17,7 @@ static const uint32_t formats_cluster[] = { DRM_FORMAT_XRGB2101010, - DRM_FORMAT_ARGB2101010, DRM_FORMAT_XBGR2101010, - DRM_FORMAT_ABGR2101010, DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, DRM_FORMAT_XBGR8888, diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 3c4f5a392b064..58c8161289fea 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -71,13 +71,19 @@ int drm_sched_entity_init(struct drm_sched_entity *entity, entity->guilty = guilty; entity->num_sched_list = num_sched_list; entity->priority = priority; + /* + * It's perfectly valid to initialize an entity without having a valid + * scheduler attached. It's just not valid to use the scheduler before it + * is initialized itself. + */ entity->sched_list = num_sched_list > 1 ? sched_list : NULL; RCU_INIT_POINTER(entity->last_scheduled, NULL); RB_CLEAR_NODE(&entity->rb_tree_node); - if (!sched_list[0]->sched_rq) { - /* Warn drivers not to do this and to fix their DRM - * calling order. + if (num_sched_list && !sched_list[0]->sched_rq) { + /* Since every entry covered by num_sched_list + * should be non-NULL and therefore we warn drivers + * not to do this and to fix their DRM calling order. */ pr_warn("%s: called with uninitialized scheduler\n", __func__); } else if (num_sched_list) { diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig index 4741d9f6544c2..5b19c7cb7b7eb 100644 --- a/drivers/gpu/drm/sun4i/Kconfig +++ b/drivers/gpu/drm/sun4i/Kconfig @@ -57,8 +57,8 @@ config DRM_SUN6I_DSI config DRM_SUN8I_DW_HDMI tristate "Support for Allwinner version of DesignWare HDMI" depends on DRM_SUN4I + depends on DRM_DW_HDMI default DRM_SUN4I - select DRM_DW_HDMI help Choose this option if you have an Allwinner SoC with the DesignWare HDMI controller. SoCs that support HDMI and diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index 152375f3de2e2..bae69d6967654 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -82,7 +82,8 @@ static int sun4i_hdmi_atomic_check(struct drm_encoder *encoder, return 0; } -static void sun4i_hdmi_disable(struct drm_encoder *encoder) +static void sun4i_hdmi_disable(struct drm_encoder *encoder, + struct drm_atomic_state *state) { struct sun4i_hdmi *hdmi = drm_encoder_to_sun4i_hdmi(encoder); u32 val; @@ -96,37 +97,17 @@ static void sun4i_hdmi_disable(struct drm_encoder *encoder) clk_disable_unprepare(hdmi->tmds_clk); } -static void sun4i_hdmi_enable(struct drm_encoder *encoder) +static void sun4i_hdmi_enable(struct drm_encoder *encoder, + struct drm_atomic_state *state) { struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct sun4i_hdmi *hdmi = drm_encoder_to_sun4i_hdmi(encoder); struct drm_display_info *display = &hdmi->connector.display_info; + unsigned int x, y; u32 val = 0; DRM_DEBUG_DRIVER("Enabling the HDMI Output\n"); - clk_prepare_enable(hdmi->tmds_clk); - - sun4i_hdmi_setup_avi_infoframes(hdmi, mode); - val |= SUN4I_HDMI_PKT_CTRL_TYPE(0, SUN4I_HDMI_PKT_AVI); - val |= SUN4I_HDMI_PKT_CTRL_TYPE(1, SUN4I_HDMI_PKT_END); - writel(val, hdmi->base + SUN4I_HDMI_PKT_CTRL_REG(0)); - - val = SUN4I_HDMI_VID_CTRL_ENABLE; - if (display->is_hdmi) - val |= SUN4I_HDMI_VID_CTRL_HDMI_MODE; - - writel(val, hdmi->base + SUN4I_HDMI_VID_CTRL_REG); -} - -static void sun4i_hdmi_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) -{ - struct sun4i_hdmi *hdmi = drm_encoder_to_sun4i_hdmi(encoder); - unsigned int x, y; - u32 val; - clk_set_rate(hdmi->mod_clk, mode->crtc_clock * 1000); clk_set_rate(hdmi->tmds_clk, mode->crtc_clock * 1000); @@ -178,6 +159,19 @@ static void sun4i_hdmi_mode_set(struct drm_encoder *encoder, val |= SUN4I_HDMI_VID_TIMING_POL_VSYNC; writel(val, hdmi->base + SUN4I_HDMI_VID_TIMING_POL_REG); + + clk_prepare_enable(hdmi->tmds_clk); + + sun4i_hdmi_setup_avi_infoframes(hdmi, mode); + val |= SUN4I_HDMI_PKT_CTRL_TYPE(0, SUN4I_HDMI_PKT_AVI); + val |= SUN4I_HDMI_PKT_CTRL_TYPE(1, SUN4I_HDMI_PKT_END); + writel(val, hdmi->base + SUN4I_HDMI_PKT_CTRL_REG(0)); + + val = SUN4I_HDMI_VID_CTRL_ENABLE; + if (display->is_hdmi) + val |= SUN4I_HDMI_VID_CTRL_HDMI_MODE; + + writel(val, hdmi->base + SUN4I_HDMI_VID_CTRL_REG); } static enum drm_mode_status sun4i_hdmi_mode_valid(struct drm_encoder *encoder, @@ -201,9 +195,8 @@ static enum drm_mode_status sun4i_hdmi_mode_valid(struct drm_encoder *encoder, static const struct drm_encoder_helper_funcs sun4i_hdmi_helper_funcs = { .atomic_check = sun4i_hdmi_atomic_check, - .disable = sun4i_hdmi_disable, - .enable = sun4i_hdmi_enable, - .mode_set = sun4i_hdmi_mode_set, + .atomic_disable = sun4i_hdmi_disable, + .atomic_enable = sun4i_hdmi_enable, .mode_valid = sun4i_hdmi_mode_valid, }; diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c index ef02d530f78d7..ae12d001a04bf 100644 --- a/drivers/gpu/drm/tegra/dpaux.c +++ b/drivers/gpu/drm/tegra/dpaux.c @@ -522,7 +522,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev) if (err < 0) { dev_err(dpaux->dev, "failed to request IRQ#%u: %d\n", dpaux->irq, err); - return err; + goto err_pm_disable; } disable_irq(dpaux->irq); @@ -542,7 +542,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev) */ err = tegra_dpaux_pad_config(dpaux, DPAUX_PADCTL_FUNC_I2C); if (err < 0) - return err; + goto err_pm_disable; #ifdef CONFIG_GENERIC_PINCONF dpaux->desc.name = dev_name(&pdev->dev); @@ -555,7 +555,8 @@ static int tegra_dpaux_probe(struct platform_device *pdev) dpaux->pinctrl = devm_pinctrl_register(&pdev->dev, &dpaux->desc, dpaux); if (IS_ERR(dpaux->pinctrl)) { dev_err(&pdev->dev, "failed to register pincontrol\n"); - return PTR_ERR(dpaux->pinctrl); + err = PTR_ERR(dpaux->pinctrl); + goto err_pm_disable; } #endif /* enable and clear all interrupts */ @@ -571,10 +572,15 @@ static int tegra_dpaux_probe(struct platform_device *pdev) err = devm_of_dp_aux_populate_ep_devices(&dpaux->aux); if (err < 0) { dev_err(dpaux->dev, "failed to populate AUX bus: %d\n", err); - return err; + goto err_pm_disable; } return 0; + +err_pm_disable: + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return err; } static void tegra_dpaux_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index fbfe92a816d4b..db606e151afc8 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -1544,9 +1544,11 @@ static int tegra_dsi_ganged_probe(struct tegra_dsi *dsi) np = of_parse_phandle(dsi->dev->of_node, "nvidia,ganged-mode", 0); if (np) { struct platform_device *gangster = of_find_device_by_node(np); + of_node_put(np); + if (!gangster) + return -EPROBE_DEFER; dsi->slave = platform_get_drvdata(gangster); - of_node_put(np); if (!dsi->slave) { put_device(&gangster->dev); @@ -1594,44 +1596,58 @@ static int tegra_dsi_probe(struct platform_device *pdev) if (!pdev->dev.pm_domain) { dsi->rst = devm_reset_control_get(&pdev->dev, "dsi"); - if (IS_ERR(dsi->rst)) - return PTR_ERR(dsi->rst); + if (IS_ERR(dsi->rst)) { + err = PTR_ERR(dsi->rst); + goto remove; + } } dsi->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(dsi->clk)) - return dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk), - "cannot get DSI clock\n"); + if (IS_ERR(dsi->clk)) { + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk), + "cannot get DSI clock\n"); + goto remove; + } dsi->clk_lp = devm_clk_get(&pdev->dev, "lp"); - if (IS_ERR(dsi->clk_lp)) - return dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_lp), - "cannot get low-power clock\n"); + if (IS_ERR(dsi->clk_lp)) { + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_lp), + "cannot get low-power clock\n"); + goto remove; + } dsi->clk_parent = devm_clk_get(&pdev->dev, "parent"); - if (IS_ERR(dsi->clk_parent)) - return dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_parent), - "cannot get parent clock\n"); + if (IS_ERR(dsi->clk_parent)) { + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_parent), + "cannot get parent clock\n"); + goto remove; + } dsi->vdd = devm_regulator_get(&pdev->dev, "avdd-dsi-csi"); - if (IS_ERR(dsi->vdd)) - return dev_err_probe(&pdev->dev, PTR_ERR(dsi->vdd), - "cannot get VDD supply\n"); + if (IS_ERR(dsi->vdd)) { + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->vdd), + "cannot get VDD supply\n"); + goto remove; + } err = tegra_dsi_setup_clocks(dsi); if (err < 0) { dev_err(&pdev->dev, "cannot setup clocks\n"); - return err; + goto remove; } regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); dsi->regs = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(dsi->regs)) - return PTR_ERR(dsi->regs); + if (IS_ERR(dsi->regs)) { + err = PTR_ERR(dsi->regs); + goto remove; + } dsi->mipi = tegra_mipi_request(&pdev->dev, pdev->dev.of_node); - if (IS_ERR(dsi->mipi)) - return PTR_ERR(dsi->mipi); + if (IS_ERR(dsi->mipi)) { + err = PTR_ERR(dsi->mipi); + goto remove; + } dsi->host.ops = &tegra_dsi_host_ops; dsi->host.dev = &pdev->dev; @@ -1659,9 +1675,12 @@ static int tegra_dsi_probe(struct platform_device *pdev) return 0; unregister: + pm_runtime_disable(&pdev->dev); mipi_dsi_host_unregister(&dsi->host); mipi_free: tegra_mipi_free(dsi->mipi); +remove: + tegra_output_remove(&dsi->output); return err; } diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c index a719af1dc9a57..46170753699dc 100644 --- a/drivers/gpu/drm/tegra/fb.c +++ b/drivers/gpu/drm/tegra/fb.c @@ -159,6 +159,7 @@ struct drm_framebuffer *tegra_fb_create(struct drm_device *drm, if (gem->size < size) { err = -EINVAL; + drm_gem_object_put(gem); goto unreference; } diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index a1fcee665023b..417fb884240a6 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -1856,12 +1856,14 @@ static int tegra_hdmi_probe(struct platform_device *pdev) return err; hdmi->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(hdmi->regs)) - return PTR_ERR(hdmi->regs); + if (IS_ERR(hdmi->regs)) { + err = PTR_ERR(hdmi->regs); + goto remove; + } err = platform_get_irq(pdev, 0); if (err < 0) - return err; + goto remove; hdmi->irq = err; @@ -1870,18 +1872,18 @@ static int tegra_hdmi_probe(struct platform_device *pdev) if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n", hdmi->irq, err); - return err; + goto remove; } platform_set_drvdata(pdev, hdmi); err = devm_pm_runtime_enable(&pdev->dev); if (err) - return err; + goto remove; err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev); if (err) - return err; + goto remove; INIT_LIST_HEAD(&hdmi->client.list); hdmi->client.ops = &hdmi_client_ops; @@ -1891,10 +1893,14 @@ static int tegra_hdmi_probe(struct platform_device *pdev) if (err < 0) { dev_err(&pdev->dev, "failed to register host1x client: %d\n", err); - return err; + goto remove; } return 0; + +remove: + tegra_output_remove(&hdmi->output); + return err; } static void tegra_hdmi_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index dc2dcb5ca1c89..d7d2389ac2f5a 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -142,8 +142,10 @@ int tegra_output_probe(struct tegra_output *output) GPIOD_IN, "HDMI hotplug detect"); if (IS_ERR(output->hpd_gpio)) { - if (PTR_ERR(output->hpd_gpio) != -ENOENT) - return PTR_ERR(output->hpd_gpio); + if (PTR_ERR(output->hpd_gpio) != -ENOENT) { + err = PTR_ERR(output->hpd_gpio); + goto put_i2c; + } output->hpd_gpio = NULL; } @@ -152,7 +154,7 @@ int tegra_output_probe(struct tegra_output *output) err = gpiod_to_irq(output->hpd_gpio); if (err < 0) { dev_err(output->dev, "gpiod_to_irq(): %d\n", err); - return err; + goto put_i2c; } output->hpd_irq = err; @@ -165,7 +167,7 @@ int tegra_output_probe(struct tegra_output *output) if (err < 0) { dev_err(output->dev, "failed to request IRQ#%u: %d\n", output->hpd_irq, err); - return err; + goto put_i2c; } output->connector.polled = DRM_CONNECTOR_POLL_HPD; @@ -179,6 +181,12 @@ int tegra_output_probe(struct tegra_output *output) } return 0; + +put_i2c: + if (output->ddc) + i2c_put_adapter(output->ddc); + + return err; } void tegra_output_remove(struct tegra_output *output) diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c index fc66bbd913b24..1e8ec50b759e4 100644 --- a/drivers/gpu/drm/tegra/rgb.c +++ b/drivers/gpu/drm/tegra/rgb.c @@ -225,26 +225,28 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc) rgb->clk = devm_clk_get(dc->dev, NULL); if (IS_ERR(rgb->clk)) { dev_err(dc->dev, "failed to get clock\n"); - return PTR_ERR(rgb->clk); + err = PTR_ERR(rgb->clk); + goto remove; } rgb->clk_parent = devm_clk_get(dc->dev, "parent"); if (IS_ERR(rgb->clk_parent)) { dev_err(dc->dev, "failed to get parent clock\n"); - return PTR_ERR(rgb->clk_parent); + err = PTR_ERR(rgb->clk_parent); + goto remove; } err = clk_set_parent(rgb->clk, rgb->clk_parent); if (err < 0) { dev_err(dc->dev, "failed to set parent clock: %d\n", err); - return err; + goto remove; } rgb->pll_d_out0 = clk_get_sys(NULL, "pll_d_out0"); if (IS_ERR(rgb->pll_d_out0)) { err = PTR_ERR(rgb->pll_d_out0); dev_err(dc->dev, "failed to get pll_d_out0: %d\n", err); - return err; + goto remove; } if (dc->soc->has_pll_d2_out0) { @@ -252,13 +254,19 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc) if (IS_ERR(rgb->pll_d2_out0)) { err = PTR_ERR(rgb->pll_d2_out0); dev_err(dc->dev, "failed to get pll_d2_out0: %d\n", err); - return err; + goto put_pll; } } dc->rgb = &rgb->output; return 0; + +put_pll: + clk_put(rgb->pll_d_out0); +remove: + tegra_output_remove(&rgb->output); + return err; } void tegra_dc_rgb_remove(struct tegra_dc *dc) diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index 484360c7e1f65..e48863a445564 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -260,30 +260,30 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test) KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, ps, ps, list, 0), - "buddy_alloc hit an error size=%u\n", + "buddy_alloc hit an error size=%lu\n", ps); } while (++i < n_pages); KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 3 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc didn't error size=%u\n", 3 * ps); + "buddy_alloc didn't error size=%lu\n", 3 * ps); drm_buddy_free_list(&mm, &middle); KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 3 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc didn't error size=%u\n", 3 * ps); + "buddy_alloc didn't error size=%lu\n", 3 * ps); KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 2 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc didn't error size=%u\n", 2 * ps); + "buddy_alloc didn't error size=%lu\n", 2 * ps); drm_buddy_free_list(&mm, &right); KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 3 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc didn't error size=%u\n", 3 * ps); + "buddy_alloc didn't error size=%lu\n", 3 * ps); /* * At this point we should have enough contiguous space for 2 blocks, * however they are never buddies (since we freed middle and right) so @@ -292,13 +292,13 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test) KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 2 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc hit an error size=%u\n", 2 * ps); + "buddy_alloc hit an error size=%lu\n", 2 * ps); drm_buddy_free_list(&mm, &left); KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, 3 * ps, ps, &allocated, DRM_BUDDY_CONTIGUOUS_ALLOCATION), - "buddy_alloc hit an error size=%u\n", 3 * ps); + "buddy_alloc hit an error size=%lu\n", 3 * ps); total = 0; list_for_each_entry(block, &allocated, link) diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c index 1eb0c304f9607..f37c0d7658656 100644 --- a/drivers/gpu/drm/tests/drm_mm_test.c +++ b/drivers/gpu/drm/tests/drm_mm_test.c @@ -157,7 +157,7 @@ static void drm_test_mm_init(struct kunit *test) /* After creation, it should all be one massive hole */ if (!assert_one_hole(test, &mm, 0, size)) { - KUNIT_FAIL(test, ""); + KUNIT_FAIL(test, "mm not one hole on creation"); goto out; } @@ -171,14 +171,14 @@ static void drm_test_mm_init(struct kunit *test) /* After filling the range entirely, there should be no holes */ if (!assert_no_holes(test, &mm)) { - KUNIT_FAIL(test, ""); + KUNIT_FAIL(test, "mm has holes when filled"); goto out; } /* And then after emptying it again, the massive hole should be back */ drm_mm_remove_node(&tmp); if (!assert_one_hole(test, &mm, 0, size)) { - KUNIT_FAIL(test, ""); + KUNIT_FAIL(test, "mm does not have single hole after emptying"); goto out; } diff --git a/drivers/gpu/drm/tidss/tidss_crtc.c b/drivers/gpu/drm/tidss/tidss_crtc.c index 5f838980c7a11..94f8e3178df58 100644 --- a/drivers/gpu/drm/tidss/tidss_crtc.c +++ b/drivers/gpu/drm/tidss/tidss_crtc.c @@ -265,6 +265,16 @@ static void tidss_crtc_atomic_disable(struct drm_crtc *crtc, reinit_completion(&tcrtc->framedone_completion); + /* + * If a layer is left enabled when the videoport is disabled, and the + * vid pipeline that was used for the layer is taken into use on + * another videoport, the DSS will report sync lost issues. Disable all + * the layers here as a work-around. + */ + for (u32 layer = 0; layer < tidss->feat->num_planes; layer++) + dispc_ovr_enable_layer(tidss->dispc, tcrtc->hw_videoport, layer, + false); + dispc_vp_disable(tidss->dispc, tcrtc->hw_videoport); if (!wait_for_completion_timeout(&tcrtc->framedone_completion, diff --git a/drivers/gpu/drm/tidss/tidss_plane.c b/drivers/gpu/drm/tidss/tidss_plane.c index e1c0ef0c3894c..68fed531f6a7f 100644 --- a/drivers/gpu/drm/tidss/tidss_plane.c +++ b/drivers/gpu/drm/tidss/tidss_plane.c @@ -213,7 +213,7 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss, drm_plane_helper_add(&tplane->plane, &tidss_plane_helper_funcs); - drm_plane_create_zpos_property(&tplane->plane, hw_plane_id, 0, + drm_plane_create_zpos_property(&tplane->plane, tidss->num_planes, 0, num_planes - 1); ret = drm_plane_create_color_properties(&tplane->plane, diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index edf10618fe2b2..f95b0406ca995 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -770,7 +770,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, * This function may sleep while waiting for space to become available. * Returns: * -EBUSY: No space available (only if no_wait == 1). - * -ENOMEM: Could not allocate memory for the buffer object, either due to + * -ENOSPC: Could not allocate space for the buffer object, either due to * fragmentation or concurrent allocators. * -ERESTARTSYS: An interruptible sleep was interrupted by a signal. */ @@ -830,7 +830,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, goto error; } - ret = -ENOMEM; + ret = -ENOSPC; if (!type_found) { pr_err(TTM_PFX "No compatible memory type found\n"); ret = -EINVAL; @@ -916,6 +916,9 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, return -EINVAL; ret = ttm_bo_move_buffer(bo, placement, ctx); + /* For backward compatibility with userspace */ + if (ret == -ENOSPC) + return -ENOMEM; if (ret) return ret; diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index fd9fd3d15101c..0b3f4267130c4 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -294,7 +294,13 @@ pgprot_t ttm_io_prot(struct ttm_buffer_object *bo, struct ttm_resource *res, enum ttm_caching caching; man = ttm_manager_type(bo->bdev, res->mem_type); - caching = man->use_tt ? bo->ttm->caching : res->bus.caching; + if (man->use_tt) { + caching = bo->ttm->caching; + if (bo->ttm->page_flags & TTM_TT_FLAG_DECRYPTED) + tmp = pgprot_decrypted(tmp); + } else { + caching = res->bus.caching; + } return ttm_prot_from_caching(caching, tmp); } @@ -337,6 +343,8 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo, .no_wait_gpu = false }; struct ttm_tt *ttm = bo->ttm; + struct ttm_resource_manager *man = + ttm_manager_type(bo->bdev, bo->resource->mem_type); pgprot_t prot; int ret; @@ -346,7 +354,8 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo, if (ret) return ret; - if (num_pages == 1 && ttm->caching == ttm_cached) { + if (num_pages == 1 && ttm->caching == ttm_cached && + !(man->use_tt && (ttm->page_flags & TTM_TT_FLAG_DECRYPTED))) { /* * We're mapping a single page, and the desired * page protection is consistent with the bo. diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 112438d965ffb..6e1fd6985ffcb 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -288,17 +288,23 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool, enum ttm_caching caching, unsigned int order) { - if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) + if (pool->use_dma_alloc) return &pool->caching[caching].orders[order]; #ifdef CONFIG_X86 switch (caching) { case ttm_write_combined: + if (pool->nid != NUMA_NO_NODE) + return &pool->caching[caching].orders[order]; + if (pool->use_dma32) return &global_dma32_write_combined[order]; return &global_write_combined[order]; case ttm_uncached: + if (pool->nid != NUMA_NO_NODE) + return &pool->caching[caching].orders[order]; + if (pool->use_dma32) return &global_dma32_uncached[order]; @@ -566,11 +572,17 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev, pool->use_dma_alloc = use_dma_alloc; pool->use_dma32 = use_dma32; - if (use_dma_alloc || nid != NUMA_NO_NODE) { - for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) - for (j = 0; j < NR_PAGE_ORDERS; ++j) - ttm_pool_type_init(&pool->caching[i].orders[j], - pool, i, j); + for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) { + for (j = 0; j < NR_PAGE_ORDERS; ++j) { + struct ttm_pool_type *pt; + + /* Initialize only pool types which are actually used */ + pt = ttm_pool_select_type(pool, i, j); + if (pt != &pool->caching[i].orders[j]) + continue; + + ttm_pool_type_init(pt, pool, i, j); + } } } EXPORT_SYMBOL(ttm_pool_init); @@ -599,10 +611,16 @@ void ttm_pool_fini(struct ttm_pool *pool) { unsigned int i, j; - if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) { - for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) - for (j = 0; j < NR_PAGE_ORDERS; ++j) - ttm_pool_type_fini(&pool->caching[i].orders[j]); + for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) { + for (j = 0; j < NR_PAGE_ORDERS; ++j) { + struct ttm_pool_type *pt; + + pt = ttm_pool_select_type(pool, i, j); + if (pt != &pool->caching[i].orders[j]) + continue; + + ttm_pool_type_fini(pt); + } } /* We removed the pool types from the LRU, but we need to also make sure diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index e0a77671edd6c..bf9601351fa35 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -31,11 +31,14 @@ #define pr_fmt(fmt) "[TTM] " fmt +#include #include #include #include #include #include +#include +#include #include #include @@ -60,6 +63,7 @@ static atomic_long_t ttm_dma32_pages_allocated; int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) { struct ttm_device *bdev = bo->bdev; + struct drm_device *ddev = bo->base.dev; uint32_t page_flags = 0; dma_resv_assert_held(bo->base.resv); @@ -81,6 +85,15 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) pr_err("Illegal buffer object type\n"); return -EINVAL; } + /* + * When using dma_alloc_coherent with memory encryption the + * mapped TT pages need to be decrypted or otherwise the drivers + * will end up sending encrypted mem to the gpu. + */ + if (bdev->pool.use_dma_alloc && cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { + page_flags |= TTM_TT_FLAG_DECRYPTED; + drm_info_once(ddev, "TT memory decryption enabled."); + } bo->ttm = bdev->funcs->ttm_tt_create(bo, page_flags); if (unlikely(bo->ttm == NULL)) diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index afc76390a197a..b8f9f2a3d2fb3 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -105,7 +105,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->bin_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_BIN]; - file->enabled_ns[V3D_BIN] += local_clock() - file->start_ns[V3D_BIN]; file->jobs_sent[V3D_BIN]++; v3d->queue[V3D_BIN].jobs_sent++; @@ -126,7 +125,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->render_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_RENDER]; - file->enabled_ns[V3D_RENDER] += local_clock() - file->start_ns[V3D_RENDER]; file->jobs_sent[V3D_RENDER]++; v3d->queue[V3D_RENDER].jobs_sent++; @@ -147,7 +145,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->csd_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_CSD]; - file->enabled_ns[V3D_CSD] += local_clock() - file->start_ns[V3D_CSD]; file->jobs_sent[V3D_CSD]++; v3d->queue[V3D_CSD].jobs_sent++; @@ -195,7 +192,6 @@ v3d_hub_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->tfu_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_TFU]; - file->enabled_ns[V3D_TFU] += local_clock() - file->start_ns[V3D_TFU]; file->jobs_sent[V3D_TFU]++; v3d->queue[V3D_TFU].jobs_sent++; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index f05e2c95a60d7..eff47465707be 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -508,7 +508,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, vc4_hdmi->ddc); cec_s_phys_addr_from_edid(vc4_hdmi->cec_adap, edid); if (!edid) - return -ENODEV; + return 0; drm_connector_update_edid_property(connector, edid); ret = drm_add_edid_modes(connector, edid); @@ -2739,6 +2739,8 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) index = 1; addr = of_get_address(dev->of_node, index, NULL, NULL); + if (!addr) + return -EINVAL; vc4_hdmi->audio.dma_data.addr = be32_to_cpup(addr) + mai_data->offset; vc4_hdmi->audio.dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 00e713faecd5a..5948e34f7f813 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -1505,9 +1505,6 @@ static int vc4_prepare_fb(struct drm_plane *plane, drm_gem_plane_helper_prepare_fb(plane, state); - if (plane->state->fb == state->fb) - return 0; - return vc4_bo_inc_usecnt(bo); } @@ -1516,7 +1513,7 @@ static void vc4_cleanup_fb(struct drm_plane *plane, { struct vc4_bo *bo; - if (plane->state->fb == state->fb || !state->fb) + if (!state->fb) return; bo = to_vc4_bo(&drm_fb_dma_get_gem_obj(state->fb, 0)->base); diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c index 3c99fb8b54e2d..e7441b227b3ce 100644 --- a/drivers/gpu/drm/vkms/vkms_composer.c +++ b/drivers/gpu/drm/vkms/vkms_composer.c @@ -123,6 +123,8 @@ static u16 apply_lut_to_channel_value(const struct vkms_color_lut *lut, u16 chan enum lut_channel channel) { s64 lut_index = get_lut_index(lut, channel_value); + u16 *floor_lut_value, *ceil_lut_value; + u16 floor_channel_value, ceil_channel_value; /* * This checks if `struct drm_color_lut` has any gap added by the compiler @@ -130,11 +132,15 @@ static u16 apply_lut_to_channel_value(const struct vkms_color_lut *lut, u16 chan */ static_assert(sizeof(struct drm_color_lut) == sizeof(__u16) * 4); - u16 *floor_lut_value = (__u16 *)&lut->base[drm_fixp2int(lut_index)]; - u16 *ceil_lut_value = (__u16 *)&lut->base[drm_fixp2int_ceil(lut_index)]; + floor_lut_value = (__u16 *)&lut->base[drm_fixp2int(lut_index)]; + if (drm_fixp2int(lut_index) == (lut->lut_length - 1)) + /* We're at the end of the LUT array, use same value for ceil and floor */ + ceil_lut_value = floor_lut_value; + else + ceil_lut_value = (__u16 *)&lut->base[drm_fixp2int_ceil(lut_index)]; - u16 floor_channel_value = floor_lut_value[channel]; - u16 ceil_channel_value = ceil_lut_value[channel]; + floor_channel_value = floor_lut_value[channel]; + ceil_channel_value = ceil_lut_value[channel]; return lerp_u16(floor_channel_value, ceil_channel_value, lut_index & DRM_FIXED_DECIMAL_MASK); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index c52c7bf1485b1..717d624e9a052 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -456,8 +456,10 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, .no_wait_gpu = false }; u32 j, initial_line = dst_offset / dst_stride; - struct vmw_bo_blit_line_data d; + struct vmw_bo_blit_line_data d = {0}; int ret = 0; + struct page **dst_pages = NULL; + struct page **src_pages = NULL; /* Buffer objects need to be either pinned or reserved: */ if (!(dst->pin_count)) @@ -477,12 +479,35 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, return ret; } + if (!src->ttm->pages && src->ttm->sg) { + src_pages = kvmalloc_array(src->ttm->num_pages, + sizeof(struct page *), GFP_KERNEL); + if (!src_pages) + return -ENOMEM; + ret = drm_prime_sg_to_page_array(src->ttm->sg, src_pages, + src->ttm->num_pages); + if (ret) + goto out; + } + if (!dst->ttm->pages && dst->ttm->sg) { + dst_pages = kvmalloc_array(dst->ttm->num_pages, + sizeof(struct page *), GFP_KERNEL); + if (!dst_pages) { + ret = -ENOMEM; + goto out; + } + ret = drm_prime_sg_to_page_array(dst->ttm->sg, dst_pages, + dst->ttm->num_pages); + if (ret) + goto out; + } + d.mapped_dst = 0; d.mapped_src = 0; d.dst_addr = NULL; d.src_addr = NULL; - d.dst_pages = dst->ttm->pages; - d.src_pages = src->ttm->pages; + d.dst_pages = dst->ttm->pages ? dst->ttm->pages : dst_pages; + d.src_pages = src->ttm->pages ? src->ttm->pages : src_pages; d.dst_num_pages = PFN_UP(dst->resource->size); d.src_num_pages = PFN_UP(src->resource->size); d.dst_prot = ttm_io_prot(dst, dst->resource, PAGE_KERNEL); @@ -504,6 +529,10 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, kunmap_atomic(d.src_addr); if (d.dst_addr) kunmap_atomic(d.dst_addr); + if (src_pages) + kvfree(src_pages); + if (dst_pages) + kvfree(dst_pages); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 2bfac3aad7b7d..ae796e0c64aa5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -204,6 +204,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, VMW_BO_DOMAIN_VRAM, VMW_BO_DOMAIN_VRAM); buf->places[0].lpfn = PFN_UP(bo->resource->size); + buf->busy_places[0].lpfn = PFN_UP(bo->resource->size); ret = ttm_bo_validate(bo, &buf->placement, &ctx); /* For some reason we didn't end up at the start of vram */ @@ -377,7 +378,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv, { struct ttm_operation_ctx ctx = { .interruptible = params->bo_type != ttm_bo_type_kernel, - .no_wait_gpu = false + .no_wait_gpu = false, + .resv = params->resv, }; struct ttm_device *bdev = &dev_priv->bdev; struct drm_device *vdev = &dev_priv->drm; @@ -394,8 +396,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv, vmw_bo_placement_set(vmw_bo, params->domain, params->busy_domain); ret = ttm_bo_init_reserved(bdev, &vmw_bo->tbo, params->bo_type, - &vmw_bo->placement, 0, &ctx, NULL, - NULL, destroy); + &vmw_bo->placement, 0, &ctx, + params->sg, params->resv, destroy); if (unlikely(ret)) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h index 0d496dc9c6af7..f349642e6190d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h @@ -55,6 +55,8 @@ struct vmw_bo_params { enum ttm_bo_type bo_type; size_t size; bool pin; + struct dma_resv *resv; + struct sg_table *sg; }; /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index d3e308fdfd5be..bea576434e475 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -666,11 +666,12 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_map_populate] = "Caching DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; - /* TTM currently doesn't fully support SEV encryption. */ - if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) - return -EINVAL; - - if (vmw_force_coherent) + /* + * When running with SEV we always want dma mappings, because + * otherwise ttm tt pool pages will bounce through swiotlb running + * out of available space. + */ + if (vmw_force_coherent || cc_platform_has(CC_ATTR_MEM_ENCRYPT)) dev_priv->map_mode = vmw_dma_alloc_coherent; else if (vmw_restrict_iommu) dev_priv->map_mode = vmw_dma_map_bind; @@ -955,13 +956,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) vmw_read(dev_priv, SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB); - /* - * Workaround for low memory 2D VMs to compensate for the - * allocation taken by fbdev - */ - if (!(dev_priv->capabilities & SVGA_CAP_3D)) - mem_size *= 3; - dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE; dev_priv->max_primary_mem = vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_MEM); @@ -1444,12 +1438,15 @@ static void vmw_debugfs_resource_managers_init(struct vmw_private *vmw) root, "system_ttm"); ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, TTM_PL_VRAM), root, "vram_ttm"); - ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR), - root, "gmr_ttm"); - ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB), - root, "mob_ttm"); - ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM), - root, "system_mob_ttm"); + if (vmw->has_gmr) + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR), + root, "gmr_ttm"); + if (vmw->has_mob) { + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB), + root, "mob_ttm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM), + root, "system_mob_ttm"); + } } static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val, @@ -1624,6 +1621,7 @@ static const struct drm_driver driver = { .prime_fd_to_handle = vmw_prime_fd_to_handle, .prime_handle_to_fd = vmw_prime_handle_to_fd, + .gem_prime_import_sg_table = vmw_prime_import_sg_table, .fops = &vmwgfx_driver_fops, .name = VMWGFX_DRIVER_NAME, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 3cd5090dedfc5..13423c7b0cbdb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1067,9 +1067,6 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf, int vmw_kms_write_svga(struct vmw_private *vmw_priv, unsigned width, unsigned height, unsigned pitch, unsigned bpp, unsigned depth); -bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv, - uint32_t pitch, - uint32_t height); int vmw_kms_present(struct vmw_private *dev_priv, struct drm_file *file_priv, struct vmw_framebuffer *vfb, @@ -1131,6 +1128,9 @@ extern int vmw_prime_handle_to_fd(struct drm_device *dev, struct drm_file *file_priv, uint32_t handle, uint32_t flags, int *prime_fd); +struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev, + struct dma_buf_attachment *attach, + struct sg_table *table); /* * MemoryOBject management - vmwgfx_mob.c diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 36987ef3fc300..5fef0b31c1179 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -447,7 +447,7 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv, vmw_res_type(ctx) == vmw_res_dx_context) { for (i = 0; i < cotable_max; ++i) { res = vmw_context_cotable(ctx, i); - if (IS_ERR(res)) + if (IS_ERR_OR_NULL(res)) continue; ret = vmw_execbuf_res_val_add(sw_context, res, @@ -1266,6 +1266,8 @@ static int vmw_cmd_dx_define_query(struct vmw_private *dev_priv, return -EINVAL; cotable_res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_DXQUERY); + if (IS_ERR_OR_NULL(cotable_res)) + return cotable_res ? PTR_ERR(cotable_res) : -EINVAL; ret = vmw_cotable_notify(cotable_res, cmd->body.queryId); return ret; @@ -2484,6 +2486,8 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv, return ret; res = vmw_context_cotable(ctx_node->ctx, vmw_view_cotables[view_type]); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->defined_id); if (unlikely(ret != 0)) return ret; @@ -2569,8 +2573,8 @@ static int vmw_cmd_dx_so_define(struct vmw_private *dev_priv, so_type = vmw_so_cmd_to_type(header->id); res = vmw_context_cotable(ctx_node->ctx, vmw_so_cotables[so_type]); - if (IS_ERR(res)) - return PTR_ERR(res); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; cmd = container_of(header, typeof(*cmd), header); ret = vmw_cotable_notify(res, cmd->defined_id); @@ -2689,6 +2693,8 @@ static int vmw_cmd_dx_define_shader(struct vmw_private *dev_priv, return -EINVAL; res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_DXSHADER); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->body.shaderId); if (ret) return ret; @@ -3010,6 +3016,8 @@ static int vmw_cmd_dx_define_streamoutput(struct vmw_private *dev_priv, } res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_STREAMOUTPUT); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->body.soid); if (ret) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 2a0cda3247031..5efc6a766f64e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -991,7 +991,7 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv, } event->event.base.type = DRM_VMW_EVENT_FENCE_SIGNALED; - event->event.base.length = sizeof(*event); + event->event.base.length = sizeof(event->event); event->event.user_data = user_data; ret = drm_event_reserve_init(dev, file_priv, &event->base, &event->event.base); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index 12787bb9c111d..d6bcaf078b1f4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -149,6 +149,38 @@ int vmw_gem_object_create_with_handle(struct vmw_private *dev_priv, return ret; } +struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev, + struct dma_buf_attachment *attach, + struct sg_table *table) +{ + int ret; + struct vmw_private *dev_priv = vmw_priv(dev); + struct drm_gem_object *gem = NULL; + struct vmw_bo *vbo; + struct vmw_bo_params params = { + .domain = (dev_priv->has_mob) ? VMW_BO_DOMAIN_SYS : VMW_BO_DOMAIN_VRAM, + .busy_domain = VMW_BO_DOMAIN_SYS, + .bo_type = ttm_bo_type_sg, + .size = attach->dmabuf->size, + .pin = false, + .resv = attach->dmabuf->resv, + .sg = table, + + }; + + dma_resv_lock(params.resv, NULL); + + ret = vmw_bo_create(dev_priv, ¶ms, &vbo); + if (ret != 0) + goto out_no_bo; + + vbo->tbo.base.funcs = &vmw_gem_object_funcs; + + gem = &vbo->tbo.base; +out_no_bo: + dma_resv_unlock(params.resv); + return gem; +} int vmw_gem_object_create_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index ceb4d3d3b965a..a0b47c9b33f55 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -64,8 +64,11 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, ttm_resource_init(bo, place, *res); id = ida_alloc_max(&gman->gmr_ida, gman->max_gmr_ids - 1, GFP_KERNEL); - if (id < 0) + if (id < 0) { + ttm_resource_fini(man, *res); + kfree(*res); return id; + } spin_lock(&gman->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 5fd0ccaa0b41b..11755d143e657 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -35,6 +35,7 @@ #include #include #include +#include void vmw_du_cleanup(struct vmw_display_unit *du) { @@ -184,13 +185,12 @@ static u32 vmw_du_cursor_mob_size(u32 w, u32 h) */ static u32 *vmw_du_cursor_plane_acquire_image(struct vmw_plane_state *vps) { - bool is_iomem; if (vps->surf) { if (vps->surf_mapped) return vmw_bo_map_and_cache(vps->surf->res.guest_memory_bo); return vps->surf->snooper.image; } else if (vps->bo) - return ttm_kmap_obj_virtual(&vps->bo->map, &is_iomem); + return vmw_bo_map_and_cache(vps->bo); return NULL; } @@ -216,7 +216,7 @@ static bool vmw_du_cursor_plane_has_changed(struct vmw_plane_state *old_vps, new_image = vmw_du_cursor_plane_acquire_image(new_vps); changed = false; - if (old_image && new_image) + if (old_image && new_image && old_image != new_image) changed = memcmp(old_image, new_image, size) != 0; return changed; @@ -272,6 +272,7 @@ static int vmw_du_get_cursor_mob(struct vmw_cursor_plane *vcp, u32 size = vmw_du_cursor_mob_size(vps->base.crtc_w, vps->base.crtc_h); u32 i; u32 cursor_max_dim, mob_max_size; + struct vmw_fence_obj *fence = NULL; int ret; if (!dev_priv->has_mob || @@ -313,7 +314,15 @@ static int vmw_du_get_cursor_mob(struct vmw_cursor_plane *vcp, if (ret != 0) goto teardown; - vmw_bo_fence_single(&vps->cursor.bo->tbo, NULL); + ret = vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL); + if (ret != 0) { + ttm_bo_unreserve(&vps->cursor.bo->tbo); + goto teardown; + } + + dma_fence_wait(&fence->base, false); + dma_fence_put(&fence->base); + ttm_bo_unreserve(&vps->cursor.bo->tbo); return 0; @@ -643,22 +652,12 @@ vmw_du_cursor_plane_cleanup_fb(struct drm_plane *plane, { struct vmw_cursor_plane *vcp = vmw_plane_to_vcp(plane); struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state); - bool is_iomem; if (vps->surf_mapped) { vmw_bo_unmap(vps->surf->res.guest_memory_bo); vps->surf_mapped = false; } - if (vps->bo && ttm_kmap_obj_virtual(&vps->bo->map, &is_iomem)) { - const int ret = ttm_bo_reserve(&vps->bo->tbo, true, false, NULL); - - if (likely(ret == 0)) { - ttm_bo_kunmap(&vps->bo->map); - ttm_bo_unreserve(&vps->bo->tbo); - } - } - vmw_du_cursor_plane_unmap_cm(vps); vmw_du_put_cursor_mob(vcp, vps); @@ -694,6 +693,10 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane, int ret = 0; if (vps->surf) { + if (vps->surf_mapped) { + vmw_bo_unmap(vps->surf->res.guest_memory_bo); + vps->surf_mapped = false; + } vmw_surface_unreference(&vps->surf); vps->surf = NULL; } @@ -930,6 +933,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane, int vmw_du_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { + struct vmw_private *vmw = vmw_priv(crtc->dev); struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc); struct vmw_display_unit *du = vmw_crtc_to_du(new_state->crtc); @@ -937,9 +941,13 @@ int vmw_du_crtc_atomic_check(struct drm_crtc *crtc, bool has_primary = new_state->plane_mask & drm_plane_mask(crtc->primary); - /* We always want to have an active plane with an active CRTC */ - if (has_primary != new_state->enable) - return -EINVAL; + /* + * This is fine in general, but broken userspace might expect + * some actual rendering so give a clue as why it's blank. + */ + if (new_state->enable && !has_primary) + drm_dbg_driver(&vmw->drm, + "CRTC without a primary plane will be blank.\n"); if (new_state->connector_mask != connector_mask && @@ -2149,13 +2157,12 @@ int vmw_kms_write_svga(struct vmw_private *vmw_priv, return 0; } +static bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv, - uint32_t pitch, - uint32_t height) + u64 pitch, + u64 height) { - return ((u64) pitch * (u64) height) < (u64) - ((dev_priv->active_display_unit == vmw_du_screen_target) ? - dev_priv->max_primary_mem : dev_priv->vram_size); + return (pitch * height) < (u64)dev_priv->vram_size; } /** @@ -2278,107 +2285,6 @@ vmw_du_connector_detect(struct drm_connector *connector, bool force) connector_status_connected : connector_status_disconnected); } -static struct drm_display_mode vmw_kms_connector_builtin[] = { - /* 640x480@60Hz */ - { DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656, - 752, 800, 0, 480, 489, 492, 525, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 800x600@60Hz */ - { DRM_MODE("800x600", DRM_MODE_TYPE_DRIVER, 40000, 800, 840, - 968, 1056, 0, 600, 601, 605, 628, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1024x768@60Hz */ - { DRM_MODE("1024x768", DRM_MODE_TYPE_DRIVER, 65000, 1024, 1048, - 1184, 1344, 0, 768, 771, 777, 806, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 1152x864@75Hz */ - { DRM_MODE("1152x864", DRM_MODE_TYPE_DRIVER, 108000, 1152, 1216, - 1344, 1600, 0, 864, 865, 868, 900, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1280x720@60Hz */ - { DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74500, 1280, 1344, - 1472, 1664, 0, 720, 723, 728, 748, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1280x768@60Hz */ - { DRM_MODE("1280x768", DRM_MODE_TYPE_DRIVER, 79500, 1280, 1344, - 1472, 1664, 0, 768, 771, 778, 798, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1280x800@60Hz */ - { DRM_MODE("1280x800", DRM_MODE_TYPE_DRIVER, 83500, 1280, 1352, - 1480, 1680, 0, 800, 803, 809, 831, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 1280x960@60Hz */ - { DRM_MODE("1280x960", DRM_MODE_TYPE_DRIVER, 108000, 1280, 1376, - 1488, 1800, 0, 960, 961, 964, 1000, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1280x1024@60Hz */ - { DRM_MODE("1280x1024", DRM_MODE_TYPE_DRIVER, 108000, 1280, 1328, - 1440, 1688, 0, 1024, 1025, 1028, 1066, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1360x768@60Hz */ - { DRM_MODE("1360x768", DRM_MODE_TYPE_DRIVER, 85500, 1360, 1424, - 1536, 1792, 0, 768, 771, 777, 795, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1440x1050@60Hz */ - { DRM_MODE("1400x1050", DRM_MODE_TYPE_DRIVER, 121750, 1400, 1488, - 1632, 1864, 0, 1050, 1053, 1057, 1089, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1440x900@60Hz */ - { DRM_MODE("1440x900", DRM_MODE_TYPE_DRIVER, 106500, 1440, 1520, - 1672, 1904, 0, 900, 903, 909, 934, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1600x1200@60Hz */ - { DRM_MODE("1600x1200", DRM_MODE_TYPE_DRIVER, 162000, 1600, 1664, - 1856, 2160, 0, 1200, 1201, 1204, 1250, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1680x1050@60Hz */ - { DRM_MODE("1680x1050", DRM_MODE_TYPE_DRIVER, 146250, 1680, 1784, - 1960, 2240, 0, 1050, 1053, 1059, 1089, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1792x1344@60Hz */ - { DRM_MODE("1792x1344", DRM_MODE_TYPE_DRIVER, 204750, 1792, 1920, - 2120, 2448, 0, 1344, 1345, 1348, 1394, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1853x1392@60Hz */ - { DRM_MODE("1856x1392", DRM_MODE_TYPE_DRIVER, 218250, 1856, 1952, - 2176, 2528, 0, 1392, 1393, 1396, 1439, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1920x1080@60Hz */ - { DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 173000, 1920, 2048, - 2248, 2576, 0, 1080, 1083, 1088, 1120, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1920x1200@60Hz */ - { DRM_MODE("1920x1200", DRM_MODE_TYPE_DRIVER, 193250, 1920, 2056, - 2256, 2592, 0, 1200, 1203, 1209, 1245, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1920x1440@60Hz */ - { DRM_MODE("1920x1440", DRM_MODE_TYPE_DRIVER, 234000, 1920, 2048, - 2256, 2600, 0, 1440, 1441, 1444, 1500, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 2560x1440@60Hz */ - { DRM_MODE("2560x1440", DRM_MODE_TYPE_DRIVER, 241500, 2560, 2608, - 2640, 2720, 0, 1440, 1443, 1448, 1481, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 2560x1600@60Hz */ - { DRM_MODE("2560x1600", DRM_MODE_TYPE_DRIVER, 348500, 2560, 2752, - 3032, 3504, 0, 1600, 1603, 1609, 1658, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 2880x1800@60Hz */ - { DRM_MODE("2880x1800", DRM_MODE_TYPE_DRIVER, 337500, 2880, 2928, - 2960, 3040, 0, 1800, 1803, 1809, 1852, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 3840x2160@60Hz */ - { DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 533000, 3840, 3888, - 3920, 4000, 0, 2160, 2163, 2168, 2222, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 3840x2400@60Hz */ - { DRM_MODE("3840x2400", DRM_MODE_TYPE_DRIVER, 592250, 3840, 3888, - 3920, 4000, 0, 2400, 2403, 2409, 2469, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* Terminate */ - { DRM_MODE("", 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) }, -}; - /** * vmw_guess_mode_timing - Provide fake timings for a * 60Hz vrefresh mode. @@ -2400,88 +2306,6 @@ void vmw_guess_mode_timing(struct drm_display_mode *mode) } -int vmw_du_connector_fill_modes(struct drm_connector *connector, - uint32_t max_width, uint32_t max_height) -{ - struct vmw_display_unit *du = vmw_connector_to_du(connector); - struct drm_device *dev = connector->dev; - struct vmw_private *dev_priv = vmw_priv(dev); - struct drm_display_mode *mode = NULL; - struct drm_display_mode *bmode; - struct drm_display_mode prefmode = { DRM_MODE("preferred", - DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) - }; - int i; - u32 assumed_bpp = 4; - - if (dev_priv->assume_16bpp) - assumed_bpp = 2; - - max_width = min(max_width, dev_priv->texture_max_width); - max_height = min(max_height, dev_priv->texture_max_height); - - /* - * For STDU extra limit for a mode on SVGA_REG_SCREENTARGET_MAX_WIDTH/ - * HEIGHT registers. - */ - if (dev_priv->active_display_unit == vmw_du_screen_target) { - max_width = min(max_width, dev_priv->stdu_max_width); - max_height = min(max_height, dev_priv->stdu_max_height); - } - - /* Add preferred mode */ - mode = drm_mode_duplicate(dev, &prefmode); - if (!mode) - return 0; - mode->hdisplay = du->pref_width; - mode->vdisplay = du->pref_height; - vmw_guess_mode_timing(mode); - drm_mode_set_name(mode); - - if (vmw_kms_validate_mode_vram(dev_priv, - mode->hdisplay * assumed_bpp, - mode->vdisplay)) { - drm_mode_probed_add(connector, mode); - } else { - drm_mode_destroy(dev, mode); - mode = NULL; - } - - if (du->pref_mode) { - list_del_init(&du->pref_mode->head); - drm_mode_destroy(dev, du->pref_mode); - } - - /* mode might be null here, this is intended */ - du->pref_mode = mode; - - for (i = 0; vmw_kms_connector_builtin[i].type != 0; i++) { - bmode = &vmw_kms_connector_builtin[i]; - if (bmode->hdisplay > max_width || - bmode->vdisplay > max_height) - continue; - - if (!vmw_kms_validate_mode_vram(dev_priv, - bmode->hdisplay * assumed_bpp, - bmode->vdisplay)) - continue; - - mode = drm_mode_duplicate(dev, bmode); - if (!mode) - return 0; - - drm_mode_probed_add(connector, mode); - } - - drm_connector_list_update(connector); - /* Move the prefered mode first, help apps pick the right mode. */ - drm_mode_sort(&connector->modes); - - return 1; -} - /** * vmw_kms_update_layout_ioctl - Handler for DRM_VMW_UPDATE_LAYOUT ioctl * @dev: drm device for the ioctl @@ -3022,3 +2846,84 @@ int vmw_du_helper_plane_update(struct vmw_du_update_plane *update) vmw_validation_unref_lists(&val_ctx); return ret; } + +/** + * vmw_connector_mode_valid - implements drm_connector_helper_funcs.mode_valid callback + * + * @connector: the drm connector, part of a DU container + * @mode: drm mode to check + * + * Returns MODE_OK on success, or a drm_mode_status error code. + */ +enum drm_mode_status vmw_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + enum drm_mode_status ret; + struct drm_device *dev = connector->dev; + struct vmw_private *dev_priv = vmw_priv(dev); + u32 assumed_cpp = 4; + + if (dev_priv->assume_16bpp) + assumed_cpp = 2; + + ret = drm_mode_validate_size(mode, dev_priv->texture_max_width, + dev_priv->texture_max_height); + if (ret != MODE_OK) + return ret; + + if (!vmw_kms_validate_mode_vram(dev_priv, + mode->hdisplay * assumed_cpp, + mode->vdisplay)) + return MODE_MEM; + + return MODE_OK; +} + +/** + * vmw_connector_get_modes - implements drm_connector_helper_funcs.get_modes callback + * + * @connector: the drm connector, part of a DU container + * + * Returns the number of added modes. + */ +int vmw_connector_get_modes(struct drm_connector *connector) +{ + struct vmw_display_unit *du = vmw_connector_to_du(connector); + struct drm_device *dev = connector->dev; + struct vmw_private *dev_priv = vmw_priv(dev); + struct drm_display_mode *mode = NULL; + struct drm_display_mode prefmode = { DRM_MODE("preferred", + DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) + }; + u32 max_width; + u32 max_height; + u32 num_modes; + + /* Add preferred mode */ + mode = drm_mode_duplicate(dev, &prefmode); + if (!mode) + return 0; + + mode->hdisplay = du->pref_width; + mode->vdisplay = du->pref_height; + vmw_guess_mode_timing(mode); + drm_mode_set_name(mode); + + drm_mode_probed_add(connector, mode); + drm_dbg_kms(dev, "preferred mode " DRM_MODE_FMT "\n", DRM_MODE_ARG(mode)); + + /* Probe connector for all modes not exceeding our geom limits */ + max_width = dev_priv->texture_max_width; + max_height = dev_priv->texture_max_height; + + if (dev_priv->active_display_unit == vmw_du_screen_target) { + max_width = min(dev_priv->stdu_max_width, max_width); + max_height = min(dev_priv->stdu_max_height, max_height); + } + + num_modes = 1 + drm_add_modes_noedid(connector, max_width, max_height); + + return num_modes; +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index db81e635dc061..19a843da87b78 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -243,10 +243,10 @@ struct vmw_framebuffer_bo { static const uint32_t __maybe_unused vmw_primary_plane_formats[] = { - DRM_FORMAT_XRGB1555, - DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGB565, + DRM_FORMAT_XRGB1555, }; static const uint32_t __maybe_unused vmw_cursor_plane_formats[] = { @@ -378,7 +378,6 @@ struct vmw_display_unit { unsigned pref_width; unsigned pref_height; bool pref_active; - struct drm_display_mode *pref_mode; /* * Gui positioning @@ -428,8 +427,6 @@ void vmw_du_connector_save(struct drm_connector *connector); void vmw_du_connector_restore(struct drm_connector *connector); enum drm_connector_status vmw_du_connector_detect(struct drm_connector *connector, bool force); -int vmw_du_connector_fill_modes(struct drm_connector *connector, - uint32_t max_width, uint32_t max_height); int vmw_kms_helper_dirty(struct vmw_private *dev_priv, struct vmw_framebuffer *framebuffer, const struct drm_clip_rect *clips, @@ -438,6 +435,9 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv, int num_clips, int increment, struct vmw_kms_dirty *dirty); +enum drm_mode_status vmw_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode); +int vmw_connector_get_modes(struct drm_connector *connector); void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv, struct drm_file *file_priv, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index a82fa97003705..c4db4aecca6c3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -304,7 +304,7 @@ static void vmw_ldu_connector_destroy(struct drm_connector *connector) static const struct drm_connector_funcs vmw_legacy_connector_funcs = { .dpms = vmw_du_connector_dpms, .detect = vmw_du_connector_detect, - .fill_modes = vmw_du_connector_fill_modes, + .fill_modes = drm_helper_probe_single_connector_modes, .destroy = vmw_ldu_connector_destroy, .reset = vmw_du_connector_reset, .atomic_duplicate_state = vmw_du_connector_duplicate_state, @@ -313,6 +313,8 @@ static const struct drm_connector_funcs vmw_legacy_connector_funcs = { static const struct drm_connector_helper_funcs vmw_ldu_connector_helper_funcs = { + .get_modes = vmw_connector_get_modes, + .mode_valid = vmw_connector_mode_valid }; static int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, @@ -449,7 +451,6 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit) ldu->base.pref_active = (unit == 0); ldu->base.pref_width = dev_priv->initial_width; ldu->base.pref_height = dev_priv->initial_height; - ldu->base.pref_mode = NULL; /* * Remove this after enabling atomic because property values can diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c index 2d72a5ee7c0c7..c99cad4449915 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c @@ -75,8 +75,12 @@ int vmw_prime_fd_to_handle(struct drm_device *dev, int fd, u32 *handle) { struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; + int ret = ttm_prime_fd_to_handle(tfile, fd, handle); - return ttm_prime_fd_to_handle(tfile, fd, handle); + if (ret) + ret = drm_gem_prime_fd_to_handle(dev, file_priv, fd, handle); + + return ret; } int vmw_prime_handle_to_fd(struct drm_device *dev, @@ -85,5 +89,12 @@ int vmw_prime_handle_to_fd(struct drm_device *dev, int *prime_fd) { struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; - return ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd); + int ret; + + if (handle > VMWGFX_NUM_MOB) + ret = ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd); + else + ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd); + + return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 556a403b7eb56..30c3ad27b6629 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -347,7 +347,7 @@ static void vmw_sou_connector_destroy(struct drm_connector *connector) static const struct drm_connector_funcs vmw_sou_connector_funcs = { .dpms = vmw_du_connector_dpms, .detect = vmw_du_connector_detect, - .fill_modes = vmw_du_connector_fill_modes, + .fill_modes = drm_helper_probe_single_connector_modes, .destroy = vmw_sou_connector_destroy, .reset = vmw_du_connector_reset, .atomic_duplicate_state = vmw_du_connector_duplicate_state, @@ -357,6 +357,8 @@ static const struct drm_connector_funcs vmw_sou_connector_funcs = { static const struct drm_connector_helper_funcs vmw_sou_connector_helper_funcs = { + .get_modes = vmw_connector_get_modes, + .mode_valid = vmw_connector_mode_valid }; @@ -826,7 +828,6 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit) sou->base.pref_active = (unit == 0); sou->base.pref_width = dev_priv->initial_width; sou->base.pref_height = dev_priv->initial_height; - sou->base.pref_mode = NULL; /* * Remove this after enabling atomic because property values can diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index ba0c0e12cfe9d..4ccab07faff08 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -41,7 +41,14 @@ #define vmw_connector_to_stdu(x) \ container_of(x, struct vmw_screen_target_display_unit, base.connector) - +/* + * Some renderers such as llvmpipe will align the width and height of their + * buffers to match their tile size. We need to keep this in mind when exposing + * modes to userspace so that this possible over-allocation will not exceed + * graphics memory. 64x64 pixels seems to be a reasonable upper bound for the + * tile size of current renderers. + */ +#define GPU_TILE_SIZE 64 enum stdu_content_type { SAME_AS_DISPLAY = 0, @@ -825,12 +832,46 @@ static void vmw_stdu_connector_destroy(struct drm_connector *connector) vmw_stdu_destroy(vmw_connector_to_stdu(connector)); } +static enum drm_mode_status +vmw_stdu_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + enum drm_mode_status ret; + struct drm_device *dev = connector->dev; + struct vmw_private *dev_priv = vmw_priv(dev); + u64 assumed_cpp = dev_priv->assume_16bpp ? 2 : 4; + /* Align width and height to account for GPU tile over-alignment */ + u64 required_mem = ALIGN(mode->hdisplay, GPU_TILE_SIZE) * + ALIGN(mode->vdisplay, GPU_TILE_SIZE) * + assumed_cpp; + required_mem = ALIGN(required_mem, PAGE_SIZE); + + ret = drm_mode_validate_size(mode, dev_priv->stdu_max_width, + dev_priv->stdu_max_height); + if (ret != MODE_OK) + return ret; + ret = drm_mode_validate_size(mode, dev_priv->texture_max_width, + dev_priv->texture_max_height); + if (ret != MODE_OK) + return ret; + + if (required_mem > dev_priv->max_primary_mem) + return MODE_MEM; + + if (required_mem > dev_priv->max_mob_pages * PAGE_SIZE) + return MODE_MEM; + + if (required_mem > dev_priv->max_mob_size) + return MODE_MEM; + + return MODE_OK; +} static const struct drm_connector_funcs vmw_stdu_connector_funcs = { .dpms = vmw_du_connector_dpms, .detect = vmw_du_connector_detect, - .fill_modes = vmw_du_connector_fill_modes, + .fill_modes = drm_helper_probe_single_connector_modes, .destroy = vmw_stdu_connector_destroy, .reset = vmw_du_connector_reset, .atomic_duplicate_state = vmw_du_connector_duplicate_state, @@ -840,6 +881,8 @@ static const struct drm_connector_funcs vmw_stdu_connector_funcs = { static const struct drm_connector_helper_funcs vmw_stdu_connector_helper_funcs = { + .get_modes = vmw_connector_get_modes, + .mode_valid = vmw_stdu_connector_mode_valid }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index af8562c95cc35..fcb87d83760ef 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -220,13 +220,18 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) switch (dev_priv->map_mode) { case vmw_dma_map_bind: case vmw_dma_map_populate: - vsgt->sgt = &vmw_tt->sgt; - ret = sg_alloc_table_from_pages_segment( - &vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0, - (unsigned long)vsgt->num_pages << PAGE_SHIFT, - dma_get_max_seg_size(dev_priv->drm.dev), GFP_KERNEL); - if (ret) - goto out_sg_alloc_fail; + if (vmw_tt->dma_ttm.page_flags & TTM_TT_FLAG_EXTERNAL) { + vsgt->sgt = vmw_tt->dma_ttm.sg; + } else { + vsgt->sgt = &vmw_tt->sgt; + ret = sg_alloc_table_from_pages_segment(&vmw_tt->sgt, + vsgt->pages, vsgt->num_pages, 0, + (unsigned long)vsgt->num_pages << PAGE_SHIFT, + dma_get_max_seg_size(dev_priv->drm.dev), + GFP_KERNEL); + if (ret) + goto out_sg_alloc_fail; + } ret = vmw_ttm_map_for_dma(vmw_tt); if (unlikely(ret != 0)) @@ -241,8 +246,9 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) return 0; out_map_fail: - sg_free_table(vmw_tt->vsgt.sgt); - vmw_tt->vsgt.sgt = NULL; + drm_warn(&dev_priv->drm, "VSG table map failed!"); + sg_free_table(vsgt->sgt); + vsgt->sgt = NULL; out_sg_alloc_fail: return ret; } @@ -388,15 +394,17 @@ static void vmw_ttm_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) static int vmw_ttm_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx) { - int ret; + bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0; - /* TODO: maybe completely drop this ? */ if (ttm_tt_is_populated(ttm)) return 0; - ret = ttm_pool_alloc(&bdev->pool, ttm, ctx); + if (external && ttm->sg) + return drm_prime_sg_to_dma_addr_array(ttm->sg, + ttm->dma_address, + ttm->num_pages); - return ret; + return ttm_pool_alloc(&bdev->pool, ttm, ctx); } static void vmw_ttm_unpopulate(struct ttm_device *bdev, @@ -404,6 +412,10 @@ static void vmw_ttm_unpopulate(struct ttm_device *bdev, { struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt, dma_ttm); + bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0; + + if (external) + return; vmw_ttm_unbind(bdev, ttm); @@ -422,6 +434,7 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, { struct vmw_ttm_tt *vmw_be; int ret; + bool external = bo->type == ttm_bo_type_sg; vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL); if (!vmw_be) @@ -430,7 +443,10 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, vmw_be->dev_priv = vmw_priv_from_ttm(bo->bdev); vmw_be->mob = NULL; - if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent) + if (external) + page_flags |= TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE; + + if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent || external) ret = ttm_sg_tt_init(&vmw_be->dma_ttm, bo, page_flags, ttm_cached); else diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index efcf0ab7a1a69..1c9e6906b06a2 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -42,7 +42,8 @@ generated_oob := $(obj)/generated/xe_wa_oob.c $(obj)/generated/xe_wa_oob.h quiet_cmd_wa_oob = GEN $(notdir $(generated_oob)) cmd_wa_oob = mkdir -p $(@D); $^ $(generated_oob) -$(generated_oob) &: $(obj)/xe_gen_wa_oob $(srctree)/$(src)/xe_wa_oob.rules +$(obj)/generated/%_wa_oob.c $(obj)/generated/%_wa_oob.h: $(obj)/xe_gen_wa_oob \ + $(srctree)/$(src)/xe_wa_oob.rules $(call cmd,wa_oob) uses_generated_oob := \ @@ -161,8 +162,8 @@ subdir-ccflags-$(CONFIG_DRM_XE_DISPLAY) += \ -Ddrm_i915_gem_object=xe_bo \ -Ddrm_i915_private=xe_device -CFLAGS_i915-display/intel_fbdev.o = $(call cc-disable-warning, override-init) -CFLAGS_i915-display/intel_display_device.o = $(call cc-disable-warning, override-init) +CFLAGS_i915-display/intel_fbdev.o = -Wno-override-init +CFLAGS_i915-display/intel_display_device.o = -Wno-override-init # Rule to build SOC code shared with i915 $(obj)/i915-soc/%.o: $(srctree)/drivers/gpu/drm/i915/soc/%.c FORCE diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h index 5d2a77b52db41..d9a81e6a4b85a 100644 --- a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h +++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h @@ -84,7 +84,8 @@ static inline struct drm_i915_private *kdev_to_i915(struct device *kdev) #define IS_ROCKETLAKE(dev_priv) IS_PLATFORM(dev_priv, XE_ROCKETLAKE) #define IS_DG1(dev_priv) IS_PLATFORM(dev_priv, XE_DG1) #define IS_ALDERLAKE_S(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_S) -#define IS_ALDERLAKE_P(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_P) +#define IS_ALDERLAKE_P(dev_priv) (IS_PLATFORM(dev_priv, XE_ALDERLAKE_P) || \ + IS_PLATFORM(dev_priv, XE_ALDERLAKE_N)) #define IS_XEHPSDV(dev_priv) (dev_priv && 0) #define IS_DG2(dev_priv) IS_PLATFORM(dev_priv, XE_DG2) #define IS_PONTEVECCHIO(dev_priv) IS_PLATFORM(dev_priv, XE_PVC) diff --git a/drivers/gpu/drm/xe/display/intel_fb_bo.c b/drivers/gpu/drm/xe/display/intel_fb_bo.c index b21da7b745a5e..a9c1f9885c6bb 100644 --- a/drivers/gpu/drm/xe/display/intel_fb_bo.c +++ b/drivers/gpu/drm/xe/display/intel_fb_bo.c @@ -31,7 +31,7 @@ int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb, ret = ttm_bo_reserve(&bo->ttm, true, false, NULL); if (ret) - return ret; + goto err; if (!(bo->flags & XE_BO_SCANOUT_BIT)) { /* @@ -42,12 +42,16 @@ int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb, */ if (XE_IOCTL_DBG(i915, !list_empty(&bo->ttm.base.gpuva.list))) { ttm_bo_unreserve(&bo->ttm); - return -EINVAL; + ret = -EINVAL; + goto err; } bo->flags |= XE_BO_SCANOUT_BIT; } ttm_bo_unreserve(&bo->ttm); + return 0; +err: + xe_bo_put(bo); return ret; } diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h index 5592774fc6903..81b8362e93406 100644 --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h @@ -120,7 +120,7 @@ #define RING_EXECLIST_STATUS_LO(base) XE_REG((base) + 0x234) #define RING_EXECLIST_STATUS_HI(base) XE_REG((base) + 0x234 + 4) -#define RING_CONTEXT_CONTROL(base) XE_REG((base) + 0x244) +#define RING_CONTEXT_CONTROL(base) XE_REG((base) + 0x244, XE_REG_OPTION_MASKED) #define CTX_CTRL_INHIBIT_SYN_CTX_SWITCH REG_BIT(3) #define CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT REG_BIT(0) diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index a6523df0f1d39..c347e2c29f81f 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -114,21 +114,21 @@ static void test_copy(struct xe_migrate *m, struct xe_bo *bo, region | XE_BO_NEEDS_CPU_ACCESS); if (IS_ERR(remote)) { - KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %li\n", - str, PTR_ERR(remote)); + KUNIT_FAIL(test, "Failed to allocate remote bo for %s: %pe\n", + str, remote); return; } err = xe_bo_validate(remote, NULL, false); if (err) { - KUNIT_FAIL(test, "Failed to validate system bo for %s: %li\n", + KUNIT_FAIL(test, "Failed to validate system bo for %s: %i\n", str, err); goto out_unlock; } err = xe_bo_vmap(remote); if (err) { - KUNIT_FAIL(test, "Failed to vmap system bo for %s: %li\n", + KUNIT_FAIL(test, "Failed to vmap system bo for %s: %i\n", str, err); goto out_unlock; } diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c index 7c124475c4289..a35e0781b7b95 100644 --- a/drivers/gpu/drm/xe/xe_bb.c +++ b/drivers/gpu/drm/xe/xe_bb.c @@ -96,7 +96,8 @@ struct xe_sched_job *xe_bb_create_job(struct xe_exec_queue *q, { u64 addr = xe_sa_bo_gpu_addr(bb->bo); - xe_gt_assert(q->gt, !(q->vm && q->vm->flags & XE_VM_FLAG_MIGRATION)); + xe_gt_assert(q->gt, !xe_sched_job_is_migration(q)); + xe_gt_assert(q->gt, q->width == 1); return __xe_bb_create_job(q, bb, &addr); } diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 4d3b80ec906d0..eb2c44a328278 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -140,9 +140,6 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo, .mem_type = XE_PL_TT, }; *c += 1; - - if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID) - bo->props.preferred_mem_type = XE_PL_TT; } } @@ -177,25 +174,15 @@ static void add_vram(struct xe_device *xe, struct xe_bo *bo, } places[*c] = place; *c += 1; - - if (bo->props.preferred_mem_type == XE_BO_PROPS_INVALID) - bo->props.preferred_mem_type = mem_type; } static void try_add_vram(struct xe_device *xe, struct xe_bo *bo, u32 bo_flags, u32 *c) { - if (bo->props.preferred_gt == XE_GT1) { - if (bo_flags & XE_BO_CREATE_VRAM1_BIT) - add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c); - if (bo_flags & XE_BO_CREATE_VRAM0_BIT) - add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c); - } else { - if (bo_flags & XE_BO_CREATE_VRAM0_BIT) - add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c); - if (bo_flags & XE_BO_CREATE_VRAM1_BIT) - add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c); - } + if (bo_flags & XE_BO_CREATE_VRAM0_BIT) + add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM0, c); + if (bo_flags & XE_BO_CREATE_VRAM1_BIT) + add_vram(xe, bo, bo->placements, bo_flags, XE_PL_VRAM1, c); } static void try_add_stolen(struct xe_device *xe, struct xe_bo *bo, @@ -219,17 +206,8 @@ static int __xe_bo_placement_for_flags(struct xe_device *xe, struct xe_bo *bo, { u32 c = 0; - bo->props.preferred_mem_type = XE_BO_PROPS_INVALID; - - /* The order of placements should indicate preferred location */ - - if (bo->props.preferred_mem_class == DRM_XE_MEM_REGION_CLASS_SYSMEM) { - try_add_system(xe, bo, bo_flags, &c); - try_add_vram(xe, bo, bo_flags, &c); - } else { - try_add_vram(xe, bo, bo_flags, &c); - try_add_system(xe, bo, bo_flags, &c); - } + try_add_vram(xe, bo, bo_flags, &c); + try_add_system(xe, bo, bo_flags, &c); try_add_stolen(xe, bo, bo_flags, &c); if (!c) @@ -1106,19 +1084,12 @@ static void xe_gem_object_close(struct drm_gem_object *obj, } } -static bool should_migrate_to_system(struct xe_bo *bo) -{ - struct xe_device *xe = xe_bo_device(bo); - - return xe_device_in_fault_mode(xe) && bo->props.cpu_atomic; -} - static vm_fault_t xe_gem_fault(struct vm_fault *vmf) { struct ttm_buffer_object *tbo = vmf->vma->vm_private_data; struct drm_device *ddev = tbo->base.dev; vm_fault_t ret; - int idx, r = 0; + int idx; ret = ttm_bo_vm_reserve(tbo, vmf); if (ret) @@ -1129,17 +1100,8 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf) trace_xe_bo_cpu_fault(bo); - if (should_migrate_to_system(bo)) { - r = xe_bo_migrate(bo, XE_PL_TT); - if (r == -EBUSY || r == -ERESTARTSYS || r == -EINTR) - ret = VM_FAULT_NOPAGE; - else if (r) - ret = VM_FAULT_SIGBUS; - } - if (!ret) - ret = ttm_bo_vm_fault_reserved(vmf, - vmf->vma->vm_page_prot, - TTM_BO_VM_NUM_PREFAULT); + ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot, + TTM_BO_VM_NUM_PREFAULT); drm_dev_exit(idx); } else { ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); @@ -1253,9 +1215,6 @@ struct xe_bo *___xe_bo_create_locked(struct xe_device *xe, struct xe_bo *bo, bo->flags = flags; bo->cpu_caching = cpu_caching; bo->ttm.base.funcs = &xe_gem_object_funcs; - bo->props.preferred_mem_class = XE_BO_PROPS_INVALID; - bo->props.preferred_gt = XE_BO_PROPS_INVALID; - bo->props.preferred_mem_type = XE_BO_PROPS_INVALID; bo->ttm.priority = XE_BO_PRIORITY_NORMAL; INIT_LIST_HEAD(&bo->pinned_link); #ifdef CONFIG_PROC_FS diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index 64c2249a4e407..81dca15315d5c 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -56,25 +56,6 @@ struct xe_bo { */ struct list_head client_link; #endif - /** @props: BO user controlled properties */ - struct { - /** @preferred_mem: preferred memory class for this BO */ - s16 preferred_mem_class; - /** @prefered_gt: preferred GT for this BO */ - s16 preferred_gt; - /** @preferred_mem_type: preferred memory type */ - s32 preferred_mem_type; - /** - * @cpu_atomic: the CPU expects to do atomics operations to - * this BO - */ - bool cpu_atomic; - /** - * @device_atomic: the device expects to do atomics operations - * to this BO - */ - bool device_atomic; - } props; /** @freed: List node for delayed put. */ struct llist_node freed; /** @created: Whether the bo has passed initial creation */ diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 5176c27e4b6a4..1554ba3cf3ce2 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -377,8 +377,14 @@ static int xe_set_dma_info(struct xe_device *xe) return err; } -/* - * Initialize MMIO resources that don't require any knowledge about tile count. +/** + * xe_device_probe_early: Device early probe + * @xe: xe device instance + * + * Initialize MMIO resources that don't require any + * knowledge about tile count. Also initialize pcode + * + * Return: 0 on success, error code on failure */ int xe_device_probe_early(struct xe_device *xe) { @@ -392,6 +398,10 @@ int xe_device_probe_early(struct xe_device *xe) if (err) return err; + err = xe_pcode_probe_early(xe); + if (err) + return err; + return 0; } @@ -454,11 +464,8 @@ int xe_device_probe(struct xe_device *xe) if (err) return err; - for_each_gt(gt, xe, id) { - err = xe_pcode_probe(gt); - if (err) - return err; - } + for_each_gt(gt, xe, id) + xe_pcode_init(gt); err = xe_display_init_noirq(xe); if (err) diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h index 08d8b72c77319..bf8efb44edf60 100644 --- a/drivers/gpu/drm/xe/xe_device.h +++ b/drivers/gpu/drm/xe/xe_device.h @@ -58,7 +58,7 @@ static inline struct xe_tile *xe_device_get_root_tile(struct xe_device *xe) static inline struct xe_gt *xe_tile_get_gt(struct xe_tile *tile, u8 gt_id) { - if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id > XE_MAX_GT_PER_TILE)) + if (drm_WARN_ON(&tile_to_xe(tile)->drm, gt_id >= XE_MAX_GT_PER_TILE)) gt_id = 0; return gt_id ? tile->media_gt : tile->primary_gt; @@ -79,7 +79,7 @@ static inline struct xe_gt *xe_device_get_gt(struct xe_device *xe, u8 gt_id) if (MEDIA_VER(xe) >= 13) { gt = xe_tile_get_gt(root_tile, gt_id); } else { - if (drm_WARN_ON(&xe->drm, gt_id > XE_MAX_TILES_PER_DEVICE)) + if (drm_WARN_ON(&xe->drm, gt_id >= XE_MAX_TILES_PER_DEVICE)) gt_id = 0; gt = xe->tiles[gt_id].primary_gt; diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c index e4db069f0db3f..6ec375c1c4b6c 100644 --- a/drivers/gpu/drm/xe/xe_display.c +++ b/drivers/gpu/drm/xe/xe_display.c @@ -108,11 +108,6 @@ int xe_display_create(struct xe_device *xe) xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0); drmm_mutex_init(&xe->drm, &xe->sb_lock); - drmm_mutex_init(&xe->drm, &xe->display.backlight.lock); - drmm_mutex_init(&xe->drm, &xe->display.audio.mutex); - drmm_mutex_init(&xe->drm, &xe->display.wm.wm_mutex); - drmm_mutex_init(&xe->drm, &xe->display.pps.mutex); - drmm_mutex_init(&xe->drm, &xe->display.hdcp.hdcp_mutex); xe->enabled_irq_mask = ~0; err = drmm_add_action_or_reset(&xe->drm, display_destroy, NULL); diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 17f26952e6656..2cd4ad2fcffa1 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -113,7 +113,6 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct drm_exec *exec = &vm_exec.exec; u32 i, num_syncs = 0, num_ufence = 0; struct xe_sched_job *job; - struct dma_fence *rebind_fence; struct xe_vm *vm; bool write_locked, skip_retry = false; ktime_t end = 0; @@ -196,6 +195,29 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_unlock_list; } + if (!args->num_batch_buffer) { + err = xe_vm_lock(vm, true); + if (err) + goto err_unlock_list; + + if (!xe_vm_in_lr_mode(vm)) { + struct dma_fence *fence; + + fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm); + if (IS_ERR(fence)) { + err = PTR_ERR(fence); + goto err_unlock_list; + } + for (i = 0; i < num_syncs; i++) + xe_sync_entry_signal(&syncs[i], NULL, fence); + xe_exec_queue_last_fence_set(q, vm, fence); + dma_fence_put(fence); + } + + xe_vm_unlock(vm); + goto err_unlock_list; + } + vm_exec.vm = &vm->gpuvm; vm_exec.num_fences = 1 + vm->xe->info.tile_count; vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; @@ -216,24 +238,6 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_exec; } - if (!args->num_batch_buffer) { - if (!xe_vm_in_lr_mode(vm)) { - struct dma_fence *fence; - - fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm); - if (IS_ERR(fence)) { - err = PTR_ERR(fence); - goto err_exec; - } - for (i = 0; i < num_syncs; i++) - xe_sync_entry_signal(&syncs[i], NULL, fence); - xe_exec_queue_last_fence_set(q, vm, fence); - dma_fence_put(fence); - } - - goto err_exec; - } - if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) { err = -EWOULDBLOCK; /* Aliased to -EAGAIN */ skip_retry = true; @@ -251,35 +255,11 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) * Rebind any invalidated userptr or evicted BOs in the VM, non-compute * VM mode only. */ - rebind_fence = xe_vm_rebind(vm, false); - if (IS_ERR(rebind_fence)) { - err = PTR_ERR(rebind_fence); + err = xe_vm_rebind(vm, false); + if (err) goto err_put_job; - } - - /* - * We store the rebind_fence in the VM so subsequent execs don't get - * scheduled before the rebinds of userptrs / evicted BOs is complete. - */ - if (rebind_fence) { - dma_fence_put(vm->rebind_fence); - vm->rebind_fence = rebind_fence; - } - if (vm->rebind_fence) { - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, - &vm->rebind_fence->flags)) { - dma_fence_put(vm->rebind_fence); - vm->rebind_fence = NULL; - } else { - dma_fence_get(vm->rebind_fence); - err = drm_sched_job_add_dependency(&job->drm, - vm->rebind_fence); - if (err) - goto err_put_job; - } - } - /* Wait behind munmap style rebinds */ + /* Wait behind rebinds */ if (!xe_vm_in_lr_mode(vm)) { err = drm_sched_job_add_resv_dependencies(&job->drm, xe_vm_resv(vm), diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 49223026c89fd..5093c56d60ab6 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -66,6 +66,8 @@ static struct xe_exec_queue *__xe_exec_queue_create(struct xe_device *xe, q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us; q->sched_props.preempt_timeout_us = hwe->eclass->sched_props.preempt_timeout_us; + q->sched_props.job_timeout_ms = + hwe->eclass->sched_props.job_timeout_ms; if (q->flags & EXEC_QUEUE_FLAG_KERNEL && q->flags & EXEC_QUEUE_FLAG_HIGH_PRIORITY) q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_KERNEL; @@ -403,7 +405,7 @@ find_hw_engine(struct xe_device *xe, { u32 idx; - if (eci.engine_class > ARRAY_SIZE(user_to_xe_engine_class)) + if (eci.engine_class >= ARRAY_SIZE(user_to_xe_engine_class)) return NULL; if (eci.gt_id >= xe->info.gt_count) diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 36f4901d8d7ee..22e1dffd0649f 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -132,6 +132,8 @@ struct xe_exec_queue { u32 timeslice_us; /** @preempt_timeout_us: preemption timeout in micro-seconds */ u32 preempt_timeout_us; + /** @job_timeout_ms: job timeout in milliseconds */ + u32 job_timeout_ms; /** @priority: priority of this exec queue */ enum xe_exec_queue_priority priority; } sched_props; @@ -157,6 +159,11 @@ struct xe_exec_queue { const struct xe_ring_ops *ring_ops; /** @entity: DRM sched entity for this exec queue (1 to 1 relationship) */ struct drm_sched_entity *entity; + /** + * @tlb_flush_seqno: The seqno of the last rebind tlb flush performed + * Protected by @vm's resv. Unused if @vm == NULL. + */ + u64 tlb_flush_seqno; /** @lrc: logical ring context for this exec queue */ struct xe_lrc lrc[]; }; diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 35474ddbaf97e..d23ee1397cf07 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -384,7 +384,9 @@ static int gt_fw_domain_init(struct xe_gt *gt) err); /* Initialize CCS mode sysfs after early initialization of HW engines */ - xe_gt_ccs_mode_sysfs_init(gt); + err = xe_gt_ccs_mode_sysfs_init(gt); + if (err) + goto err_force_wake; err = xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); XE_WARN_ON(err); diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c index 529fc286cd06c..396aeb5b99242 100644 --- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c +++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c @@ -167,25 +167,20 @@ static void xe_gt_ccs_mode_sysfs_fini(struct drm_device *drm, void *arg) * and it is expected that there are no open drm clients while doing so. * The number of available compute slices is exposed to user through a per-gt * 'num_cslices' sysfs interface. + * + * Returns: Returns error value for failure and 0 for success. */ -void xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt) +int xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); int err; if (!xe_gt_ccs_mode_enabled(gt)) - return; + return 0; err = sysfs_create_files(gt->sysfs, gt_ccs_mode_attrs); - if (err) { - drm_warn(&xe->drm, "Sysfs creation for ccs_mode failed err: %d\n", err); - return; - } + if (err) + return err; - err = drmm_add_action_or_reset(&xe->drm, xe_gt_ccs_mode_sysfs_fini, gt); - if (err) { - sysfs_remove_files(gt->sysfs, gt_ccs_mode_attrs); - drm_warn(&xe->drm, "%s: drmm_add_action_or_reset failed, err: %d\n", - __func__, err); - } + return drmm_add_action_or_reset(&xe->drm, xe_gt_ccs_mode_sysfs_fini, gt); } diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.h b/drivers/gpu/drm/xe/xe_gt_ccs_mode.h index f39975aaaab0d..f8779852cf0d2 100644 --- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.h +++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.h @@ -12,7 +12,7 @@ #include "xe_platform_types.h" void xe_gt_apply_ccs_mode(struct xe_gt *gt); -void xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt); +int xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt); static inline bool xe_gt_ccs_mode_enabled(const struct xe_gt *gt) { diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c index 9fcae65b64699..e7a39ad7adba0 100644 --- a/drivers/gpu/drm/xe/xe_gt_idle.c +++ b/drivers/gpu/drm/xe/xe_gt_idle.c @@ -126,6 +126,13 @@ static const struct attribute *gt_idle_attrs[] = { static void gt_idle_sysfs_fini(struct drm_device *drm, void *arg) { struct kobject *kobj = arg; + struct xe_gt *gt = kobj_to_gt(kobj->parent); + + if (gt_to_xe(gt)->info.skip_guc_pc) { + XE_WARN_ON(xe_force_wake_get(gt_to_fw(gt), XE_FW_GT)); + xe_gt_idle_disable_c6(gt); + xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); + } sysfs_remove_files(kobj, gt_idle_attrs); kobject_put(kobj); @@ -184,7 +191,7 @@ void xe_gt_idle_enable_c6(struct xe_gt *gt) void xe_gt_idle_disable_c6(struct xe_gt *gt) { xe_device_assert_mem_access(gt_to_xe(gt)); - xe_force_wake_assert_held(gt_to_fw(gt), XE_FORCEWAKE_ALL); + xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT); xe_mmio_write32(gt, PG_ENABLE, 0); xe_mmio_write32(gt, RC_CONTROL, 0); diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 73f08f1924df2..ab8536c4fd580 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type) static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma) { return BIT(tile->id) & vma->tile_present && - !(BIT(tile->id) & vma->usm.tile_invalidated); + !(BIT(tile->id) & vma->tile_invalidated); } static bool vma_matches(struct xe_vma *vma, u64 page_addr) @@ -146,10 +146,12 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) /* ASID to VM */ mutex_lock(&xe->usm.lock); vm = xa_load(&xe->usm.asid_to_vm, pf->asid); - if (vm) + if (vm && xe_vm_in_fault_mode(vm)) xe_vm_get(vm); + else + vm = NULL; mutex_unlock(&xe->usm.lock); - if (!vm || !xe_vm_in_fault_mode(vm)) + if (!vm) return -EINVAL; retry_userptr: @@ -224,7 +226,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) if (xe_vma_is_userptr(vma)) ret = xe_vma_userptr_check_repin(to_userptr_vma(vma)); - vma->usm.tile_invalidated &= ~BIT(tile->id); + vma->tile_invalidated &= ~BIT(tile->id); unlock_dma_resv: drm_exec_fini(&exec); diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c index d91702592520a..c5145e00ecf08 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.c +++ b/drivers/gpu/drm/xe/xe_guc_pc.c @@ -381,8 +381,6 @@ u32 xe_guc_pc_get_act_freq(struct xe_guc_pc *pc) struct xe_device *xe = gt_to_xe(gt); u32 freq; - xe_device_mem_access_get(gt_to_xe(gt)); - /* When in RC6, actual frequency reported will be 0. */ if (GRAPHICS_VERx100(xe) >= 1270) { freq = xe_mmio_read32(gt, MTL_MIRROR_TARGET_WP1); @@ -394,8 +392,6 @@ u32 xe_guc_pc_get_act_freq(struct xe_guc_pc *pc) freq = decode_freq(freq); - xe_device_mem_access_put(gt_to_xe(gt)); - return freq; } @@ -412,14 +408,13 @@ int xe_guc_pc_get_cur_freq(struct xe_guc_pc *pc, u32 *freq) struct xe_gt *gt = pc_to_gt(pc); int ret; - xe_device_mem_access_get(gt_to_xe(gt)); /* * GuC SLPC plays with cur freq request when GuCRC is enabled * Block RC6 for a more reliable read. */ ret = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); if (ret) - goto out; + return ret; *freq = xe_mmio_read32(gt, RPNSWREQ); @@ -427,9 +422,7 @@ int xe_guc_pc_get_cur_freq(struct xe_guc_pc *pc, u32 *freq) *freq = decode_freq(*freq); XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL)); -out: - xe_device_mem_access_put(gt_to_xe(gt)); - return ret; + return 0; } /** @@ -451,12 +444,7 @@ u32 xe_guc_pc_get_rp0_freq(struct xe_guc_pc *pc) */ u32 xe_guc_pc_get_rpe_freq(struct xe_guc_pc *pc) { - struct xe_gt *gt = pc_to_gt(pc); - struct xe_device *xe = gt_to_xe(gt); - - xe_device_mem_access_get(xe); pc_update_rp_values(pc); - xe_device_mem_access_put(xe); return pc->rpe_freq; } @@ -485,7 +473,6 @@ int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq) struct xe_gt *gt = pc_to_gt(pc); int ret; - xe_device_mem_access_get(pc_to_xe(pc)); mutex_lock(&pc->freq_lock); if (!pc->freq_ready) { /* Might be in the middle of a gt reset */ @@ -511,7 +498,6 @@ int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq) XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL)); out: mutex_unlock(&pc->freq_lock); - xe_device_mem_access_put(pc_to_xe(pc)); return ret; } @@ -528,7 +514,6 @@ int xe_guc_pc_set_min_freq(struct xe_guc_pc *pc, u32 freq) { int ret; - xe_device_mem_access_get(pc_to_xe(pc)); mutex_lock(&pc->freq_lock); if (!pc->freq_ready) { /* Might be in the middle of a gt reset */ @@ -544,8 +529,6 @@ int xe_guc_pc_set_min_freq(struct xe_guc_pc *pc, u32 freq) out: mutex_unlock(&pc->freq_lock); - xe_device_mem_access_put(pc_to_xe(pc)); - return ret; } @@ -561,7 +544,6 @@ int xe_guc_pc_get_max_freq(struct xe_guc_pc *pc, u32 *freq) { int ret; - xe_device_mem_access_get(pc_to_xe(pc)); mutex_lock(&pc->freq_lock); if (!pc->freq_ready) { /* Might be in the middle of a gt reset */ @@ -577,7 +559,6 @@ int xe_guc_pc_get_max_freq(struct xe_guc_pc *pc, u32 *freq) out: mutex_unlock(&pc->freq_lock); - xe_device_mem_access_put(pc_to_xe(pc)); return ret; } @@ -594,7 +575,6 @@ int xe_guc_pc_set_max_freq(struct xe_guc_pc *pc, u32 freq) { int ret; - xe_device_mem_access_get(pc_to_xe(pc)); mutex_lock(&pc->freq_lock); if (!pc->freq_ready) { /* Might be in the middle of a gt reset */ @@ -610,7 +590,6 @@ int xe_guc_pc_set_max_freq(struct xe_guc_pc *pc, u32 freq) out: mutex_unlock(&pc->freq_lock); - xe_device_mem_access_put(pc_to_xe(pc)); return ret; } @@ -623,8 +602,6 @@ enum xe_gt_idle_state xe_guc_pc_c_status(struct xe_guc_pc *pc) struct xe_gt *gt = pc_to_gt(pc); u32 reg, gt_c_state; - xe_device_mem_access_get(gt_to_xe(gt)); - if (GRAPHICS_VERx100(gt_to_xe(gt)) >= 1270) { reg = xe_mmio_read32(gt, MTL_MIRROR_TARGET_WP1); gt_c_state = REG_FIELD_GET(MTL_CC_MASK, reg); @@ -633,8 +610,6 @@ enum xe_gt_idle_state xe_guc_pc_c_status(struct xe_guc_pc *pc) gt_c_state = REG_FIELD_GET(RCN_MASK, reg); } - xe_device_mem_access_put(gt_to_xe(gt)); - switch (gt_c_state) { case GT_C6: return GT_IDLE_C6; @@ -654,9 +629,7 @@ u64 xe_guc_pc_rc6_residency(struct xe_guc_pc *pc) struct xe_gt *gt = pc_to_gt(pc); u32 reg; - xe_device_mem_access_get(gt_to_xe(gt)); reg = xe_mmio_read32(gt, GT_GFX_RC6); - xe_device_mem_access_put(gt_to_xe(gt)); return reg; } @@ -670,9 +643,7 @@ u64 xe_guc_pc_mc6_residency(struct xe_guc_pc *pc) struct xe_gt *gt = pc_to_gt(pc); u64 reg; - xe_device_mem_access_get(gt_to_xe(gt)); reg = xe_mmio_read32(gt, MTL_MEDIA_MC6); - xe_device_mem_access_put(gt_to_xe(gt)); return reg; } @@ -801,23 +772,19 @@ int xe_guc_pc_gucrc_disable(struct xe_guc_pc *pc) if (xe->info.skip_guc_pc) return 0; - xe_device_mem_access_get(pc_to_xe(pc)); - ret = pc_action_setup_gucrc(pc, XE_GUCRC_HOST_CONTROL); if (ret) - goto out; + return ret; ret = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); if (ret) - goto out; + return ret; xe_gt_idle_disable_c6(gt); XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL)); -out: - xe_device_mem_access_put(pc_to_xe(pc)); - return ret; + return 0; } static void pc_init_pcode_freq(struct xe_guc_pc *pc) @@ -870,11 +837,9 @@ int xe_guc_pc_start(struct xe_guc_pc *pc) xe_gt_assert(gt, xe_device_uc_enabled(xe)); - xe_device_mem_access_get(pc_to_xe(pc)); - ret = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); if (ret) - goto out_fail_force_wake; + return ret; if (xe->info.skip_guc_pc) { if (xe->info.platform != XE_PVC) @@ -914,8 +879,6 @@ int xe_guc_pc_start(struct xe_guc_pc *pc) out: XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL)); -out_fail_force_wake: - xe_device_mem_access_put(pc_to_xe(pc)); return ret; } @@ -928,12 +891,9 @@ int xe_guc_pc_stop(struct xe_guc_pc *pc) struct xe_device *xe = pc_to_xe(pc); int ret; - xe_device_mem_access_get(pc_to_xe(pc)); - if (xe->info.skip_guc_pc) { xe_gt_idle_disable_c6(pc_to_gt(pc)); - ret = 0; - goto out; + return 0; } mutex_lock(&pc->freq_lock); @@ -942,16 +902,14 @@ int xe_guc_pc_stop(struct xe_guc_pc *pc) ret = pc_action_shutdown(pc); if (ret) - goto out; + return ret; if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_NOT_RUNNING)) { drm_err(&pc_to_xe(pc)->drm, "GuC PC Shutdown failed\n"); - ret = -EIO; + return -EIO; } -out: - xe_device_mem_access_put(pc_to_xe(pc)); - return ret; + return 0; } /** @@ -960,15 +918,6 @@ int xe_guc_pc_stop(struct xe_guc_pc *pc) */ void xe_guc_pc_fini(struct xe_guc_pc *pc) { - struct xe_device *xe = pc_to_xe(pc); - - if (xe->info.skip_guc_pc) { - xe_device_mem_access_get(xe); - xe_gt_idle_disable_c6(pc_to_gt(pc)); - xe_device_mem_access_put(xe); - return; - } - XE_WARN_ON(xe_guc_pc_gucrc_disable(pc)); XE_WARN_ON(xe_guc_pc_stop(pc)); mutex_destroy(&pc->freq_lock); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index f22ae717b0b2d..c7aa09daa36ab 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -1216,7 +1216,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) init_waitqueue_head(&ge->suspend_wait); timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT : - q->hwe->eclass->sched_props.job_timeout_ms; + msecs_to_jiffies(q->sched_props.job_timeout_ms); err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops, get_submit_wq(guc), q->lrc[0].ring.size / MAX_JOB_SIZE_BYTES, 64, @@ -1253,6 +1253,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q) return 0; err_entity: + mutex_unlock(&guc->submission_state.lock); xe_sched_entity_fini(&ge->entity); err_sched: xe_sched_fini(&ge->sched); diff --git a/drivers/gpu/drm/xe/xe_huc.c b/drivers/gpu/drm/xe/xe_huc.c index eca109791c6ae..01b2d0bd26a30 100644 --- a/drivers/gpu/drm/xe/xe_huc.c +++ b/drivers/gpu/drm/xe/xe_huc.c @@ -53,7 +53,6 @@ static int huc_alloc_gsc_pkt(struct xe_huc *huc) struct xe_gt *gt = huc_to_gt(huc); struct xe_device *xe = gt_to_xe(gt); struct xe_bo *bo; - int err; /* we use a single object for both input and output */ bo = xe_bo_create_pin_map(xe, gt_to_tile(gt), NULL, @@ -66,13 +65,7 @@ static int huc_alloc_gsc_pkt(struct xe_huc *huc) huc->gsc_pkt = bo; - err = drmm_add_action_or_reset(&xe->drm, free_gsc_pkt, huc); - if (err) { - free_gsc_pkt(&xe->drm, huc); - return err; - } - - return 0; + return drmm_add_action_or_reset(&xe->drm, free_gsc_pkt, huc); } int xe_huc_init(struct xe_huc *huc) diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index 174ed2185481e..a6f43446c779a 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -288,7 +288,7 @@ xe_hwmon_power1_max_interval_show(struct device *dev, struct device_attribute *a * As y can be < 2, we compute tau4 = (4 | x) << y * and then add 2 when doing the final right shift to account for units */ - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; /* val in hwmon interface units (millisec) */ out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); @@ -328,7 +328,7 @@ xe_hwmon_power1_max_interval_store(struct device *dev, struct device_attribute * r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT); x = REG_FIELD_GET(PKG_MAX_WIN_X, r); y = REG_FIELD_GET(PKG_MAX_WIN_Y, r); - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); if (val > max_win) diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index b38319d2801e0..72f04a656e8b1 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -95,7 +95,6 @@ static void set_offsets(u32 *regs, #define REG16(x) \ (((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \ (((x) >> 2) & 0x7f) -#define END 0 { const u32 base = hwe->mmio_base; @@ -166,7 +165,7 @@ static const u8 gen12_xcs_offsets[] = { REG16(0x274), REG16(0x270), - END + 0 }; static const u8 dg2_xcs_offsets[] = { @@ -200,7 +199,7 @@ static const u8 dg2_xcs_offsets[] = { REG16(0x274), REG16(0x270), - END + 0 }; static const u8 gen12_rcs_offsets[] = { @@ -296,7 +295,7 @@ static const u8 gen12_rcs_offsets[] = { REG(0x084), NOP(1), - END + 0 }; static const u8 xehp_rcs_offsets[] = { @@ -337,7 +336,7 @@ static const u8 xehp_rcs_offsets[] = { LRI(1, 0), REG(0x0c8), - END + 0 }; static const u8 dg2_rcs_offsets[] = { @@ -380,7 +379,7 @@ static const u8 dg2_rcs_offsets[] = { LRI(1, 0), REG(0x0c8), - END + 0 }; static const u8 mtl_rcs_offsets[] = { @@ -423,7 +422,7 @@ static const u8 mtl_rcs_offsets[] = { LRI(1, 0), REG(0x0c8), - END + 0 }; #define XE2_CTX_COMMON \ @@ -469,7 +468,7 @@ static const u8 xe2_rcs_offsets[] = { LRI(1, 0), /* [0x47] */ REG(0x0c8), /* [0x48] R_PWR_CLK_STATE */ - END + 0 }; static const u8 xe2_bcs_offsets[] = { @@ -480,16 +479,15 @@ static const u8 xe2_bcs_offsets[] = { REG16(0x200), /* [0x42] BCS_SWCTRL */ REG16(0x204), /* [0x44] BLIT_CCTL */ - END + 0 }; static const u8 xe2_xcs_offsets[] = { XE2_CTX_COMMON, - END + 0 }; -#undef END #undef REG16 #undef REG #undef LRI @@ -525,9 +523,8 @@ static const u8 *reg_offsets(struct xe_device *xe, enum xe_engine_class class) static void set_context_control(u32 *regs, struct xe_hw_engine *hwe) { - regs[CTX_CONTEXT_CONTROL] = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH) | - _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) | - CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT; + regs[CTX_CONTEXT_CONTROL] = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH | + CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT); /* TODO: Timestamp */ } diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 70480c3056021..0f77305c47c88 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -32,7 +32,6 @@ #include "xe_sync.h" #include "xe_trace.h" #include "xe_vm.h" -#include "xe_wa.h" /** * struct xe_migrate - migrate context. @@ -216,7 +215,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, if (vm->flags & XE_VM_FLAG_64K && level == 1) flags = XE_PDE_64K; - entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (level - 1) * + entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (u64)(level - 1) * XE_PAGE_SIZE, pat_index); xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE * level, u64, entry | flags); @@ -224,7 +223,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, /* Write PDE's that point to our BO. */ for (i = 0; i < num_entries - num_level; i++) { - entry = vm->pt_ops->pde_encode_bo(bo, i * XE_PAGE_SIZE, + entry = vm->pt_ops->pde_encode_bo(bo, (u64)i * XE_PAGE_SIZE, pat_index); xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE + @@ -280,7 +279,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, #define VM_SA_UPDATE_UNIT_SIZE (XE_PAGE_SIZE / NUM_VMUSA_UNIT_PER_PAGE) #define NUM_VMUSA_WRITES_PER_UNIT (VM_SA_UPDATE_UNIT_SIZE / sizeof(u64)) drm_suballoc_manager_init(&m->vm_update_sa, - (map_ofs / XE_PAGE_SIZE - NUM_KERNEL_PDE) * + (size_t)(map_ofs / XE_PAGE_SIZE - NUM_KERNEL_PDE) * NUM_VMUSA_UNIT_PER_PAGE, 0); m->pt_bo = bo; @@ -288,10 +287,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, } /* - * Due to workaround 16017236439, odd instance hardware copy engines are - * faster than even instance ones. - * This function returns the mask involving all fast copy engines and the - * reserved copy engine to be used as logical mask for migrate engine. * Including the reserved copy engine is required to avoid deadlocks due to * migrate jobs servicing the faults gets stuck behind the job that faulted. */ @@ -305,8 +300,7 @@ static u32 xe_migrate_usm_logical_mask(struct xe_gt *gt) if (hwe->class != XE_ENGINE_CLASS_COPY) continue; - if (!XE_WA(gt, 16017236439) || - xe_gt_is_usm_hwe(gt, hwe) || hwe->instance & 1) + if (xe_gt_is_usm_hwe(gt, hwe)) logical_mask |= BIT(hwe->logical_instance); } @@ -357,6 +351,10 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile) if (!hwe || !logical_mask) return ERR_PTR(-EINVAL); + /* + * XXX: Currently only reserving 1 (likely slow) BCS instance on + * PVC, may want to revisit if performance is needed. + */ m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe, EXEC_QUEUE_FLAG_KERNEL | EXEC_QUEUE_FLAG_PERMANENT | @@ -479,7 +477,7 @@ static void emit_pte(struct xe_migrate *m, struct xe_vm *vm = m->q->vm; u16 pat_index; u32 ptes; - u64 ofs = at_pt * XE_PAGE_SIZE; + u64 ofs = (u64)at_pt * XE_PAGE_SIZE; u64 cur_ofs; /* Indirect access needs compression enabled uncached PAT index */ diff --git a/drivers/gpu/drm/xe/xe_pcode.c b/drivers/gpu/drm/xe/xe_pcode.c index b324dc2a5debe..81f4ae2ea08f3 100644 --- a/drivers/gpu/drm/xe/xe_pcode.c +++ b/drivers/gpu/drm/xe/xe_pcode.c @@ -10,6 +10,7 @@ #include +#include "xe_device.h" #include "xe_gt.h" #include "xe_mmio.h" #include "xe_pcode_api.h" @@ -43,8 +44,6 @@ static int pcode_mailbox_status(struct xe_gt *gt) [PCODE_ERROR_MASK] = {-EPROTO, "Unknown"}, }; - lockdep_assert_held(>->pcode.lock); - err = xe_mmio_read32(gt, PCODE_MAILBOX) & PCODE_ERROR_MASK; if (err) { drm_err(>_to_xe(gt)->drm, "PCODE Mailbox failed: %d %s", err, @@ -55,17 +54,15 @@ static int pcode_mailbox_status(struct xe_gt *gt) return 0; } -static int pcode_mailbox_rw(struct xe_gt *gt, u32 mbox, u32 *data0, u32 *data1, - unsigned int timeout_ms, bool return_data, - bool atomic) +static int __pcode_mailbox_rw(struct xe_gt *gt, u32 mbox, u32 *data0, u32 *data1, + unsigned int timeout_ms, bool return_data, + bool atomic) { int err; if (gt_to_xe(gt)->info.skip_pcode) return 0; - lockdep_assert_held(>->pcode.lock); - if ((xe_mmio_read32(gt, PCODE_MAILBOX) & PCODE_READY) != 0) return -EAGAIN; @@ -87,6 +84,18 @@ static int pcode_mailbox_rw(struct xe_gt *gt, u32 mbox, u32 *data0, u32 *data1, return pcode_mailbox_status(gt); } +static int pcode_mailbox_rw(struct xe_gt *gt, u32 mbox, u32 *data0, u32 *data1, + unsigned int timeout_ms, bool return_data, + bool atomic) +{ + if (gt_to_xe(gt)->info.skip_pcode) + return 0; + + lockdep_assert_held(>->pcode.lock); + + return __pcode_mailbox_rw(gt, mbox, data0, data1, timeout_ms, return_data, atomic); +} + int xe_pcode_write_timeout(struct xe_gt *gt, u32 mbox, u32 data, int timeout) { int err; @@ -109,15 +118,19 @@ int xe_pcode_read(struct xe_gt *gt, u32 mbox, u32 *val, u32 *val1) return err; } -static int xe_pcode_try_request(struct xe_gt *gt, u32 mbox, - u32 request, u32 reply_mask, u32 reply, - u32 *status, bool atomic, int timeout_us) +static int pcode_try_request(struct xe_gt *gt, u32 mbox, + u32 request, u32 reply_mask, u32 reply, + u32 *status, bool atomic, int timeout_us, bool locked) { int slept, wait = 10; for (slept = 0; slept < timeout_us; slept += wait) { - *status = pcode_mailbox_rw(gt, mbox, &request, NULL, 1, true, - atomic); + if (locked) + *status = pcode_mailbox_rw(gt, mbox, &request, NULL, 1, true, + atomic); + else + *status = __pcode_mailbox_rw(gt, mbox, &request, NULL, 1, true, + atomic); if ((*status == 0) && ((request & reply_mask) == reply)) return 0; @@ -158,8 +171,8 @@ int xe_pcode_request(struct xe_gt *gt, u32 mbox, u32 request, mutex_lock(>->pcode.lock); - ret = xe_pcode_try_request(gt, mbox, request, reply_mask, reply, &status, - false, timeout_base_ms * 1000); + ret = pcode_try_request(gt, mbox, request, reply_mask, reply, &status, + false, timeout_base_ms * 1000, true); if (!ret) goto out; @@ -177,8 +190,8 @@ int xe_pcode_request(struct xe_gt *gt, u32 mbox, u32 request, "PCODE timeout, retrying with preemption disabled\n"); drm_WARN_ON_ONCE(>_to_xe(gt)->drm, timeout_base_ms > 1); preempt_disable(); - ret = xe_pcode_try_request(gt, mbox, request, reply_mask, reply, &status, - true, timeout_base_ms * 1000); + ret = pcode_try_request(gt, mbox, request, reply_mask, reply, &status, + true, 50 * 1000, true); preempt_enable(); out: @@ -238,59 +251,71 @@ int xe_pcode_init_min_freq_table(struct xe_gt *gt, u32 min_gt_freq, } /** - * xe_pcode_init - Ensure PCODE is initialized - * @gt: gt instance + * xe_pcode_ready - Ensure PCODE is initialized + * @xe: xe instance + * @locked: true if lock held, false otherwise * - * This function ensures that PCODE is properly initialized. To be called during - * probe and resume paths. + * PCODE init mailbox is polled only on root gt of root tile + * as the root tile provides the initialization is complete only + * after all the tiles have completed the initialization. + * Called only on early probe without locks and with locks in + * resume path. * - * It returns 0 on success, and -error number on failure. + * Returns 0 on success, and -error number on failure. */ -int xe_pcode_init(struct xe_gt *gt) +int xe_pcode_ready(struct xe_device *xe, bool locked) { u32 status, request = DGFX_GET_INIT_STATUS; + struct xe_gt *gt = xe_root_mmio_gt(xe); int timeout_us = 180000000; /* 3 min */ int ret; - if (gt_to_xe(gt)->info.skip_pcode) + if (xe->info.skip_pcode) return 0; - if (!IS_DGFX(gt_to_xe(gt))) + if (!IS_DGFX(xe)) return 0; - mutex_lock(>->pcode.lock); - ret = xe_pcode_try_request(gt, DGFX_PCODE_STATUS, request, - DGFX_INIT_STATUS_COMPLETE, - DGFX_INIT_STATUS_COMPLETE, - &status, false, timeout_us); - mutex_unlock(>->pcode.lock); + if (locked) + mutex_lock(>->pcode.lock); + + ret = pcode_try_request(gt, DGFX_PCODE_STATUS, request, + DGFX_INIT_STATUS_COMPLETE, + DGFX_INIT_STATUS_COMPLETE, + &status, false, timeout_us, locked); + + if (locked) + mutex_unlock(>->pcode.lock); if (ret) - drm_err(>_to_xe(gt)->drm, + drm_err(&xe->drm, "PCODE initialization timedout after: 3 min\n"); return ret; } /** - * xe_pcode_probe - Prepare xe_pcode and also ensure PCODE is initialized. + * xe_pcode_init: initialize components of PCODE * @gt: gt instance * - * This function initializes the xe_pcode component, and when needed, it ensures - * that PCODE has properly performed its initialization and it is really ready - * to go. To be called once only during probe. - * - * It returns 0 on success, and -error number on failure. + * This function initializes the xe_pcode component. + * To be called once only during probe. */ -int xe_pcode_probe(struct xe_gt *gt) +void xe_pcode_init(struct xe_gt *gt) { drmm_mutex_init(>_to_xe(gt)->drm, >->pcode.lock); +} - if (gt_to_xe(gt)->info.skip_pcode) - return 0; - - if (!IS_DGFX(gt_to_xe(gt))) - return 0; - - return xe_pcode_init(gt); +/** + * xe_pcode_probe_early: initializes PCODE + * @xe: xe instance + * + * This function checks the initialization status of PCODE + * To be called once only during early probe without locks. + * + * Returns 0 on success, error code otherwise + */ +int xe_pcode_probe_early(struct xe_device *xe) +{ + return xe_pcode_ready(xe, false); } diff --git a/drivers/gpu/drm/xe/xe_pcode.h b/drivers/gpu/drm/xe/xe_pcode.h index 08cb1d047cba2..3f54c6d2a57d2 100644 --- a/drivers/gpu/drm/xe/xe_pcode.h +++ b/drivers/gpu/drm/xe/xe_pcode.h @@ -8,9 +8,11 @@ #include struct xe_gt; +struct xe_device; -int xe_pcode_probe(struct xe_gt *gt); -int xe_pcode_init(struct xe_gt *gt); +void xe_pcode_init(struct xe_gt *gt); +int xe_pcode_probe_early(struct xe_device *xe); +int xe_pcode_ready(struct xe_device *xe, bool locked); int xe_pcode_init_min_freq_table(struct xe_gt *gt, u32 min_gt_freq, u32 max_gt_freq); int xe_pcode_read(struct xe_gt *gt, u32 mbox, u32 *val, u32 *val1); diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index b429c2876a764..343b71216b797 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -54,13 +54,15 @@ int xe_pm_suspend(struct xe_device *xe) u8 id; int err; + drm_dbg(&xe->drm, "Suspending device\n"); + for_each_gt(gt, xe, id) xe_gt_suspend_prepare(gt); /* FIXME: Super racey... */ err = xe_bo_evict_all(xe); if (err) - return err; + goto err; xe_display_pm_suspend(xe); @@ -68,7 +70,7 @@ int xe_pm_suspend(struct xe_device *xe) err = xe_gt_suspend(gt); if (err) { xe_display_pm_resume(xe); - return err; + goto err; } } @@ -76,7 +78,11 @@ int xe_pm_suspend(struct xe_device *xe) xe_display_pm_suspend_late(xe); + drm_dbg(&xe->drm, "Device suspended\n"); return 0; +err: + drm_dbg(&xe->drm, "Device suspend failed %d\n", err); + return err; } /** @@ -92,14 +98,14 @@ int xe_pm_resume(struct xe_device *xe) u8 id; int err; + drm_dbg(&xe->drm, "Resuming device\n"); + for_each_tile(tile, xe, id) xe_wa_apply_tile_workarounds(tile); - for_each_gt(gt, xe, id) { - err = xe_pcode_init(gt); - if (err) - return err; - } + err = xe_pcode_ready(xe, true); + if (err) + return err; xe_display_pm_resume_early(xe); @@ -109,7 +115,7 @@ int xe_pm_resume(struct xe_device *xe) */ err = xe_bo_restore_kernel(xe); if (err) - return err; + goto err; xe_irq_resume(xe); @@ -120,9 +126,13 @@ int xe_pm_resume(struct xe_device *xe) err = xe_bo_restore_user(xe); if (err) - return err; + goto err; + drm_dbg(&xe->drm, "Device resumed\n"); return 0; +err: + drm_dbg(&xe->drm, "Device resume failed %d\n", err); + return err; } static bool xe_pm_pci_d3cold_capable(struct pci_dev *pdev) @@ -286,11 +296,9 @@ int xe_pm_runtime_resume(struct xe_device *xe) xe->d3cold.power_lost = xe_guc_in_reset(>->uc.guc); if (xe->d3cold.allowed && xe->d3cold.power_lost) { - for_each_gt(gt, xe, id) { - err = xe_pcode_init(gt); - if (err) - goto out; - } + err = xe_pcode_ready(xe, true); + if (err) + goto out; /* * This only restores pinned memory which is the memory diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 6653c045f3c92..c1a833b1cb3d3 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1255,11 +1255,13 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue * non-faulting LR, in particular on user-space batch buffer chaining, * it needs to be done here. */ - if ((rebind && !xe_vm_in_lr_mode(vm) && !vm->batch_invalidate_tlb) || - (!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) { + if ((!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) { ifence = kzalloc(sizeof(*ifence), GFP_KERNEL); if (!ifence) return ERR_PTR(-ENOMEM); + } else if (rebind && !xe_vm_in_lr_mode(vm)) { + /* We bump also if batch_invalidate_tlb is true */ + vm->tlb_flush_seqno++; } rfence = kzalloc(sizeof(*rfence), GFP_KERNEL); @@ -1298,7 +1300,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue } /* add shared fence now for pagetable delayed destroy */ - dma_resv_add_fence(xe_vm_resv(vm), fence, !rebind && + dma_resv_add_fence(xe_vm_resv(vm), fence, rebind || last_munmap_rebind ? DMA_RESV_USAGE_KERNEL : DMA_RESV_USAGE_BOOKKEEP); diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c index 7e924faeeea0b..1a6f2f51baae6 100644 --- a/drivers/gpu/drm/xe/xe_query.c +++ b/drivers/gpu/drm/xe/xe_query.c @@ -132,7 +132,7 @@ query_engine_cycles(struct xe_device *xe, return -EINVAL; eci = &resp.eci; - if (eci->gt_id > XE_MAX_GT_PER_TILE) + if (eci->gt_id >= XE_MAX_GT_PER_TILE) return -EINVAL; gt = xe_device_get_gt(xe, eci->gt_id); diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index 1e4c06eacd984..42a6e669bf27a 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -78,6 +78,16 @@ static int emit_store_imm_ggtt(u32 addr, u32 value, u32 *dw, int i) return i; } +static int emit_flush_dw(u32 *dw, int i) +{ + dw[i++] = MI_FLUSH_DW | MI_FLUSH_IMM_DW; + dw[i++] = 0; + dw[i++] = 0; + dw[i++] = 0; + + return i; +} + static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb, u32 *dw, int i) { @@ -227,10 +237,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc { u32 dw[MAX_JOB_SIZE_DW], i = 0; u32 ppgtt_flag = get_ppgtt_flag(job); - struct xe_vm *vm = job->q->vm; struct xe_gt *gt = job->q->gt; - if (vm && vm->batch_invalidate_tlb) { + if (job->ring_ops_flush_tlb) { dw[i++] = preparser_disable(true); i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), seqno, true, dw, i); @@ -242,10 +251,12 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); - if (job->user_fence.used) + if (job->user_fence.used) { + i = emit_flush_dw(dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr, job->user_fence.value, dw, i); + } i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i); @@ -278,7 +289,6 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, struct xe_gt *gt = job->q->gt; struct xe_device *xe = gt_to_xe(gt); bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE; - struct xe_vm *vm = job->q->vm; dw[i++] = preparser_disable(true); @@ -290,22 +300,24 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, i = emit_aux_table_inv(gt, VE0_AUX_INV, dw, i); } - if (vm && vm->batch_invalidate_tlb) + if (job->ring_ops_flush_tlb) i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), seqno, true, dw, i); dw[i++] = preparser_disable(false); - if (!vm || !vm->batch_invalidate_tlb) + if (!job->ring_ops_flush_tlb) i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), seqno, dw, i); i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); - if (job->user_fence.used) + if (job->user_fence.used) { + i = emit_flush_dw(dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr, job->user_fence.value, dw, i); + } i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i); @@ -325,7 +337,6 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job, struct xe_gt *gt = job->q->gt; struct xe_device *xe = gt_to_xe(gt); bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK); - struct xe_vm *vm = job->q->vm; u32 mask_flags = 0; dw[i++] = preparser_disable(true); @@ -335,7 +346,7 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job, mask_flags = PIPE_CONTROL_3D_ENGINE_FLAGS; /* See __xe_pt_bind_vma() for a discussion on TLB invalidations. */ - i = emit_pipe_invalidate(mask_flags, vm && vm->batch_invalidate_tlb, dw, i); + i = emit_pipe_invalidate(mask_flags, job->ring_ops_flush_tlb, dw, i); /* hsdes: 1809175790 */ if (has_aux_ccs(xe)) diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c index 4e2ccad0e52fa..d07b9ee0eaa55 100644 --- a/drivers/gpu/drm/xe/xe_sched_job.c +++ b/drivers/gpu/drm/xe/xe_sched_job.c @@ -250,6 +250,16 @@ bool xe_sched_job_completed(struct xe_sched_job *job) void xe_sched_job_arm(struct xe_sched_job *job) { + struct xe_exec_queue *q = job->q; + struct xe_vm *vm = q->vm; + + if (vm && !xe_sched_job_is_migration(q) && !xe_vm_in_lr_mode(vm) && + (vm->batch_invalidate_tlb || vm->tlb_flush_seqno != q->tlb_flush_seqno)) { + xe_vm_assert_held(vm); + q->tlb_flush_seqno = vm->tlb_flush_seqno; + job->ring_ops_flush_tlb = true; + } + drm_sched_job_arm(&job->drm); } diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h index 71213ba9735bc..46ead6345956b 100644 --- a/drivers/gpu/drm/xe/xe_sched_job_types.h +++ b/drivers/gpu/drm/xe/xe_sched_job_types.h @@ -39,6 +39,8 @@ struct xe_sched_job { } user_fence; /** @migrate_flush_flags: Additional flush flags for migration jobs */ u32 migrate_flush_flags; + /** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */ + bool ring_ops_flush_tlb; /** @batch_addr: batch buffer address of job */ u64 batch_addr[]; }; diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h index 4ddc55527f9ab..846f14507d5ff 100644 --- a/drivers/gpu/drm/xe/xe_trace.h +++ b/drivers/gpu/drm/xe/xe_trace.h @@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate, TP_ARGS(vma) ); -DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate, +DEFINE_EVENT(xe_vma, xe_vma_invalidate, TP_PROTO(struct xe_vma *vma), TP_ARGS(vma) ); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 3b21afe5b4883..a2024247bec1a 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -520,7 +520,6 @@ static void preempt_rebind_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work); struct drm_exec exec; - struct dma_fence *rebind_fence; unsigned int fence_count = 0; LIST_HEAD(preempt_fences); ktime_t end = 0; @@ -566,18 +565,11 @@ static void preempt_rebind_work_func(struct work_struct *w) if (err) goto out_unlock; - rebind_fence = xe_vm_rebind(vm, true); - if (IS_ERR(rebind_fence)) { - err = PTR_ERR(rebind_fence); + err = xe_vm_rebind(vm, true); + if (err) goto out_unlock; - } - if (rebind_fence) { - dma_fence_wait(rebind_fence, false); - dma_fence_put(rebind_fence); - } - - /* Wait on munmap style VM unbinds */ + /* Wait on rebinds and munmap style VM unbinds */ wait = dma_resv_wait_timeout(xe_vm_resv(vm), DMA_RESV_USAGE_KERNEL, false, MAX_SCHEDULE_TIMEOUT); @@ -706,6 +698,7 @@ int xe_vm_userptr_pin(struct xe_vm *vm) int err = 0; LIST_HEAD(tmp_evict); + xe_assert(vm->xe, !xe_vm_in_fault_mode(vm)); lockdep_assert_held_write(&vm->lock); /* Collect invalidated userptrs */ @@ -722,11 +715,27 @@ int xe_vm_userptr_pin(struct xe_vm *vm) list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list, userptr.repin_link) { err = xe_vma_userptr_pin_pages(uvma); - if (err < 0) - return err; + if (err == -EFAULT) { + list_del_init(&uvma->userptr.repin_link); + + /* Wait for pending binds */ + xe_vm_lock(vm, false); + dma_resv_wait_timeout(xe_vm_resv(vm), + DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); + + err = xe_vm_invalidate_vma(&uvma->vma); + xe_vm_unlock(vm); + if (err) + return err; + } else { + if (err < 0) + return err; - list_del_init(&uvma->userptr.repin_link); - list_move_tail(&uvma->vma.combined_links.rebind, &vm->rebind_list); + list_del_init(&uvma->userptr.repin_link); + list_move_tail(&uvma->vma.combined_links.rebind, + &vm->rebind_list); + } } return 0; @@ -754,14 +763,14 @@ xe_vm_bind_vma(struct xe_vma *vma, struct xe_exec_queue *q, struct xe_sync_entry *syncs, u32 num_syncs, bool first_op, bool last_op); -struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker) +int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker) { - struct dma_fence *fence = NULL; + struct dma_fence *fence; struct xe_vma *vma, *next; lockdep_assert_held(&vm->lock); if (xe_vm_in_lr_mode(vm) && !rebind_worker) - return NULL; + return 0; xe_vm_assert_held(vm); list_for_each_entry_safe(vma, next, &vm->rebind_list, @@ -769,17 +778,17 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker) xe_assert(vm->xe, vma->tile_present); list_del_init(&vma->combined_links.rebind); - dma_fence_put(fence); if (rebind_worker) trace_xe_vma_rebind_worker(vma); else trace_xe_vma_rebind_exec(vma); fence = xe_vm_bind_vma(vma, NULL, NULL, 0, false, false); if (IS_ERR(fence)) - return fence; + return PTR_ERR(fence); + dma_fence_put(fence); } - return fence; + return 0; } static void xe_vma_free(struct xe_vma *vma) @@ -1558,7 +1567,6 @@ static void vm_destroy_work_func(struct work_struct *w) XE_WARN_ON(vm->pt_root[id]); trace_xe_vm_free(vm); - dma_fence_put(vm->rebind_fence); kfree(vm); } @@ -2010,7 +2018,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma, return err; } - if (vma->tile_mask != (vma->tile_present & ~vma->usm.tile_invalidated)) { + if (vma->tile_mask != (vma->tile_present & ~vma->tile_invalidated)) { return xe_vm_bind(vm, vma, q, xe_vma_bo(vma), syncs, num_syncs, true, first_op, last_op); } else { @@ -3184,9 +3192,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) u8 id; int ret; - xe_assert(xe, xe_vm_in_fault_mode(xe_vma_vm(vma))); xe_assert(xe, !xe_vma_is_null(vma)); - trace_xe_vma_usm_invalidate(vma); + trace_xe_vma_invalidate(vma); /* Check that we don't race with page-table updates */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { @@ -3224,7 +3231,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) } } - vma->usm.tile_invalidated = vma->tile_mask; + vma->tile_invalidated = vma->tile_mask; return 0; } diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index 9654a0612fc25..40188a28c5471 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -207,7 +207,7 @@ int __xe_vm_userptr_needs_repin(struct xe_vm *vm); int xe_vm_userptr_check_repin(struct xe_vm *vm); -struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker); +int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker); int xe_vm_invalidate_vma(struct xe_vma *vma); diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 7300eea5394ba..4027da3a10b3a 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -83,11 +83,8 @@ struct xe_vma { struct work_struct destroy_work; }; - /** @usm: unified shared memory state */ - struct { - /** @tile_invalidated: VMA has been invalidated */ - u8 tile_invalidated; - } usm; + /** @tile_invalidated: VMA has been invalidated */ + u8 tile_invalidated; /** @tile_mask: Tile mask of where to create binding for this VMA */ u8 tile_mask; @@ -174,9 +171,6 @@ struct xe_vm { */ struct list_head rebind_list; - /** @rebind_fence: rebind fence from execbuf */ - struct dma_fence *rebind_fence; - /** * @destroy_work: worker to destroy VM, needed as a dma_fence signaling * from an irq context can be last put and the destroy needs to be able @@ -285,6 +279,11 @@ struct xe_vm { bool capture_once; } error_capture; + /** + * @tlb_flush_seqno: Required TLB flush seqno for the next exec. + * protected by the vm resv. + */ + u64 tlb_flush_seqno; /** @batch_invalidate_tlb: Always invalidate TLB before batch start */ bool batch_invalidate_tlb; /** @xef: XE file handle for tracking this VM's drm client */ diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c index 88eb33acd5f0d..face8d6b2a6fb 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c @@ -256,12 +256,12 @@ static int zynqmp_dpsub_probe(struct platform_device *pdev) if (ret) goto err_dp; + drm_bridge_add(dpsub->bridge); + if (dpsub->dma_enabled) { ret = zynqmp_dpsub_drm_init(dpsub); if (ret) goto err_disp; - } else { - drm_bridge_add(dpsub->bridge); } dev_info(&pdev->dev, "ZynqMP DisplayPort Subsystem driver probed"); @@ -288,9 +288,8 @@ static void zynqmp_dpsub_remove(struct platform_device *pdev) if (dpsub->drm) zynqmp_dpsub_drm_cleanup(dpsub); - else - drm_bridge_remove(dpsub->bridge); + drm_bridge_remove(dpsub->bridge); zynqmp_disp_remove(dpsub); zynqmp_dp_remove(dpsub); diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 84d042796d2e6..3937889fa912d 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -351,11 +351,6 @@ static int host1x_device_uevent(const struct device *dev, return 0; } -static int host1x_dma_configure(struct device *dev) -{ - return of_dma_configure(dev, dev->of_node, true); -} - static const struct dev_pm_ops host1x_device_pm_ops = { .suspend = pm_generic_suspend, .resume = pm_generic_resume, @@ -369,7 +364,6 @@ struct bus_type host1x_bus_type = { .name = "host1x", .match = host1x_device_match, .uevent = host1x_device_uevent, - .dma_configure = host1x_dma_configure, .pm = &host1x_device_pm_ops, }; @@ -458,8 +452,6 @@ static int host1x_device_add(struct host1x *host1x, device->dev.bus = &host1x_bus_type; device->dev.parent = host1x->dev; - of_dma_configure(&device->dev, host1x->dev->of_node, true); - device->dev.dma_parms = &device->dma_parms; dma_set_max_seg_size(&device->dev, UINT_MAX); diff --git a/drivers/greybus/interface.c b/drivers/greybus/interface.c index 9ec949a438ef6..52ef6be9d4499 100644 --- a/drivers/greybus/interface.c +++ b/drivers/greybus/interface.c @@ -694,6 +694,7 @@ static void gb_interface_release(struct device *dev) trace_gb_interface_release(intf); + cancel_work_sync(&intf->mode_switch_work); kfree(intf); } diff --git a/drivers/hid/amd-sfh-hid/Kconfig b/drivers/hid/amd-sfh-hid/Kconfig index af752dd3a3409..329de5e12c1a0 100644 --- a/drivers/hid/amd-sfh-hid/Kconfig +++ b/drivers/hid/amd-sfh-hid/Kconfig @@ -6,6 +6,7 @@ menu "AMD SFH HID Support" config AMD_SFH_HID tristate "AMD Sensor Fusion Hub" depends on HID + depends on X86 help If you say yes to this option, support will be included for the AMD Sensor Fusion Hub. diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_common.h b/drivers/hid/amd-sfh-hid/amd_sfh_common.h index a1950bc6e6cef..e5620d7db5690 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_common.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_common.h @@ -19,6 +19,9 @@ #define AMD_C2P_MSG(regno) (0x10500 + ((regno) * 4)) #define AMD_P2C_MSG(regno) (0x10680 + ((regno) * 4)) +#define AMD_C2P_MSG_V1(regno) (0x10900 + ((regno) * 4)) +#define AMD_P2C_MSG_V1(regno) (0x10500 + ((regno) * 4)) + #define SENSOR_ENABLED 4 #define SENSOR_DISABLED 5 @@ -53,6 +56,9 @@ struct amd_mp2_dev { /* mp2 active control status */ u32 mp2_acs; struct sfh_dev_status dev_en; + struct work_struct work; + u8 init_done; + u8 rver; }; struct amd_mp2_ops { @@ -79,4 +85,14 @@ void amd_sfh_clear_intr_v2(struct amd_mp2_dev *privdata); int amd_sfh_irq_init_v2(struct amd_mp2_dev *privdata); void amd_sfh_clear_intr(struct amd_mp2_dev *privdata); int amd_sfh_irq_init(struct amd_mp2_dev *privdata); + +static inline u64 amd_get_c2p_val(struct amd_mp2_dev *mp2, u32 idx) +{ + return mp2->rver == 1 ? AMD_C2P_MSG_V1(idx) : AMD_C2P_MSG(idx); +} + +static inline u64 amd_get_p2c_val(struct amd_mp2_dev *mp2, u32 idx) +{ + return mp2->rver == 1 ? AMD_P2C_MSG_V1(idx) : AMD_P2C_MSG(idx); +} #endif diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index 2530fa98b568b..9e97c26c4482e 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -35,15 +36,17 @@ static int sensor_mask_override = -1; module_param_named(sensor_mask, sensor_mask_override, int, 0444); MODULE_PARM_DESC(sensor_mask, "override the detected sensors mask"); +static bool intr_disable = true; + static int amd_sfh_wait_response_v2(struct amd_mp2_dev *mp2, u8 sid, u32 sensor_sts) { union cmd_response cmd_resp; - /* Get response with status within a max of 1600 ms timeout */ + /* Get response with status within a max of 10 seconds timeout */ if (!readl_poll_timeout(mp2->mmio + AMD_P2C_MSG(0), cmd_resp.resp, (cmd_resp.response_v2.response == sensor_sts && cmd_resp.response_v2.status == 0 && (sid == 0xff || - cmd_resp.response_v2.sensor_id == sid)), 500, 1600000)) + cmd_resp.response_v2.sensor_id == sid)), 500, 10000000)) return cmd_resp.response_v2.response; return SENSOR_DISABLED; @@ -55,7 +58,7 @@ static void amd_start_sensor_v2(struct amd_mp2_dev *privdata, struct amd_mp2_sen cmd_base.ul = 0; cmd_base.cmd_v2.cmd_id = ENABLE_SENSOR; - cmd_base.cmd_v2.intr_disable = 1; + cmd_base.cmd_v2.intr_disable = intr_disable; cmd_base.cmd_v2.period = info.period; cmd_base.cmd_v2.sensor_id = info.sensor_idx; cmd_base.cmd_v2.length = 16; @@ -73,7 +76,7 @@ static void amd_stop_sensor_v2(struct amd_mp2_dev *privdata, u16 sensor_idx) cmd_base.ul = 0; cmd_base.cmd_v2.cmd_id = DISABLE_SENSOR; - cmd_base.cmd_v2.intr_disable = 1; + cmd_base.cmd_v2.intr_disable = intr_disable; cmd_base.cmd_v2.period = 0; cmd_base.cmd_v2.sensor_id = sensor_idx; cmd_base.cmd_v2.length = 16; @@ -87,7 +90,7 @@ static void amd_stop_all_sensor_v2(struct amd_mp2_dev *privdata) union sfh_cmd_base cmd_base; cmd_base.cmd_v2.cmd_id = STOP_ALL_SENSORS; - cmd_base.cmd_v2.intr_disable = 1; + cmd_base.cmd_v2.intr_disable = intr_disable; cmd_base.cmd_v2.period = 0; cmd_base.cmd_v2.sensor_id = 0; @@ -96,9 +99,9 @@ static void amd_stop_all_sensor_v2(struct amd_mp2_dev *privdata) void amd_sfh_clear_intr_v2(struct amd_mp2_dev *privdata) { - if (readl(privdata->mmio + AMD_P2C_MSG(4))) { - writel(0, privdata->mmio + AMD_P2C_MSG(4)); - writel(0xf, privdata->mmio + AMD_P2C_MSG(5)); + if (readl(privdata->mmio + amd_get_p2c_val(privdata, 4))) { + writel(0, privdata->mmio + amd_get_p2c_val(privdata, 4)); + writel(0xf, privdata->mmio + amd_get_p2c_val(privdata, 5)); } } @@ -292,6 +295,26 @@ int amd_sfh_irq_init(struct amd_mp2_dev *privdata) return 0; } +static int mp2_disable_intr(const struct dmi_system_id *id) +{ + intr_disable = false; + return 0; +} + +static const struct dmi_system_id dmi_sfh_table[] = { + { + /* + * https://bugzilla.kernel.org/show_bug.cgi?id=218104 + */ + .callback = mp2_disable_intr, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook x360 435 G7"), + }, + }, + {} +}; + static const struct dmi_system_id dmi_nodevs[] = { { /* @@ -307,6 +330,48 @@ static const struct dmi_system_id dmi_nodevs[] = { { } }; +static void sfh1_1_init_work(struct work_struct *work) +{ + struct amd_mp2_dev *mp2 = container_of(work, struct amd_mp2_dev, work); + struct pci_dev *pdev = mp2->pdev; + int rc; + + rc = mp2->sfh1_1_ops->init(mp2); + if (rc) { + dev_err(&pdev->dev, "sfh1_1_init failed err %d\n", rc); + return; + } + + amd_sfh_clear_intr(mp2); + mp2->init_done = 1; +} + +static void sfh_init_work(struct work_struct *work) +{ + struct amd_mp2_dev *mp2 = container_of(work, struct amd_mp2_dev, work); + struct pci_dev *pdev = mp2->pdev; + int rc; + + rc = amd_sfh_hid_client_init(mp2); + if (rc) { + amd_sfh_clear_intr(mp2); + dev_err(&pdev->dev, "amd_sfh_hid_client_init failed err %d\n", rc); + return; + } + + amd_sfh_clear_intr(mp2); + mp2->init_done = 1; +} + +static void amd_sfh_remove(struct pci_dev *pdev) +{ + struct amd_mp2_dev *mp2 = pci_get_drvdata(pdev); + + flush_work(&mp2->work); + if (mp2->init_done) + mp2->mp2_ops->remove(mp2); +} + static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct amd_mp2_dev *privdata; @@ -315,6 +380,8 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i if (dmi_first_match(dmi_nodevs)) return -ENODEV; + dmi_check_system(dmi_sfh_table); + privdata = devm_kzalloc(&pdev->dev, sizeof(*privdata), GFP_KERNEL); if (!privdata) return -ENOMEM; @@ -343,10 +410,15 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i privdata->sfh1_1_ops = (const struct amd_sfh1_1_ops *)id->driver_data; if (privdata->sfh1_1_ops) { - rc = privdata->sfh1_1_ops->init(privdata); + if (boot_cpu_data.x86 >= 0x1A) + privdata->rver = 1; + + rc = devm_work_autocancel(&pdev->dev, &privdata->work, sfh1_1_init_work); if (rc) return rc; - goto init_done; + + schedule_work(&privdata->work); + return 0; } mp2_select_ops(privdata); @@ -357,33 +429,34 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i return rc; } - rc = amd_sfh_hid_client_init(privdata); + rc = devm_work_autocancel(&pdev->dev, &privdata->work, sfh_init_work); if (rc) { amd_sfh_clear_intr(privdata); - if (rc != -EOPNOTSUPP) - dev_err(&pdev->dev, "amd_sfh_hid_client_init failed\n"); return rc; } -init_done: - amd_sfh_clear_intr(privdata); - - return devm_add_action_or_reset(&pdev->dev, privdata->mp2_ops->remove, privdata); + schedule_work(&privdata->work); + return 0; } static void amd_sfh_shutdown(struct pci_dev *pdev) { struct amd_mp2_dev *mp2 = pci_get_drvdata(pdev); - if (mp2 && mp2->mp2_ops) - mp2->mp2_ops->stop_all(mp2); + if (mp2) { + flush_work(&mp2->work); + if (mp2->init_done) + mp2->mp2_ops->stop_all(mp2); + } } static int __maybe_unused amd_mp2_pci_resume(struct device *dev) { struct amd_mp2_dev *mp2 = dev_get_drvdata(dev); - mp2->mp2_ops->resume(mp2); + flush_work(&mp2->work); + if (mp2->init_done) + mp2->mp2_ops->resume(mp2); return 0; } @@ -392,7 +465,9 @@ static int __maybe_unused amd_mp2_pci_suspend(struct device *dev) { struct amd_mp2_dev *mp2 = dev_get_drvdata(dev); - mp2->mp2_ops->suspend(mp2); + flush_work(&mp2->work); + if (mp2->init_done) + mp2->mp2_ops->suspend(mp2); return 0; } @@ -414,6 +489,7 @@ static struct pci_driver amd_mp2_pci_driver = { .probe = amd_mp2_pci_probe, .driver.pm = &amd_mp2_pm_ops, .shutdown = amd_sfh_shutdown, + .remove = amd_sfh_remove, }; module_pci_driver(amd_mp2_pci_driver); diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h index 70add75fc5066..05e400a4a83e4 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h @@ -90,10 +90,10 @@ enum mem_use_type { struct hpd_status { union { struct { - u32 human_presence_report : 4; - u32 human_presence_actual : 4; - u32 probablity : 8; u32 object_distance : 16; + u32 probablity : 8; + u32 human_presence_actual : 4; + u32 human_presence_report : 4; } shpd; u32 val; }; diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c index 33fbdde8aff00..c8916afefa626 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_desc.c @@ -251,7 +251,7 @@ static u8 get_input_rep(u8 current_index, int sensor_idx, int report_id, break; case HPD_IDX: get_common_inputs(&hpd_input.common_property, report_id); - hpdstatus.val = readl(mp2->mmio + AMD_C2P_MSG(4)); + hpdstatus.val = readl(mp2->mmio + amd_get_c2p_val(mp2, 4)); hpd_input.human_presence = hpdstatus.shpd.presence; report_size = sizeof(hpd_input); memcpy(input_report, &hpd_input, sizeof(hpd_input)); diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c index 9dbe6f4cb2942..c2f9fc1f20a24 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c @@ -172,7 +172,7 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata) if (rc) goto cleanup; - writel(0, privdata->mmio + AMD_P2C_MSG(0)); + writel(0, privdata->mmio + amd_get_p2c_val(privdata, 0)); mp2_ops->start(privdata, info); status = amd_sfh_wait_for_response (privdata, cl_data->sensor_idx[i], ENABLE_SENSOR); @@ -227,6 +227,11 @@ static void amd_sfh_resume(struct amd_mp2_dev *mp2) struct amd_mp2_sensor_info info; int i, status; + if (!cl_data->is_any_sensor_enabled) { + amd_sfh_clear_intr(mp2); + return; + } + for (i = 0; i < cl_data->num_hid_devices; i++) { if (cl_data->sensor_sts[i] == SENSOR_DISABLED) { info.sensor_idx = cl_data->sensor_idx[i]; @@ -252,6 +257,11 @@ static void amd_sfh_suspend(struct amd_mp2_dev *mp2) struct amdtp_cl_data *cl_data = mp2->cl_data; int i, status; + if (!cl_data->is_any_sensor_enabled) { + amd_sfh_clear_intr(mp2); + return; + } + for (i = 0; i < cl_data->num_hid_devices; i++) { if (cl_data->sensor_idx[i] != HPD_IDX && cl_data->sensor_sts[i] == SENSOR_ENABLED) { @@ -298,7 +308,7 @@ static void amd_sfh_set_ops(struct amd_mp2_dev *mp2) int amd_sfh1_1_init(struct amd_mp2_dev *mp2) { - u32 phy_base = readl(mp2->mmio + AMD_C2P_MSG(22)); + u32 phy_base = readl(mp2->mmio + amd_get_c2p_val(mp2, 22)); struct device *dev = &mp2->pdev->dev; struct sfh_base_info binfo; int rc; diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c index ae36312bc2365..2de2668a02779 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c @@ -20,7 +20,7 @@ static int amd_sfh_wait_response(struct amd_mp2_dev *mp2, u8 sid, u32 cmd_id) struct sfh_cmd_response cmd_resp; /* Get response with status within a max of 10000 ms timeout */ - if (!readl_poll_timeout(mp2->mmio + AMD_P2C_MSG(0), cmd_resp.resp, + if (!readl_poll_timeout(mp2->mmio + amd_get_p2c_val(mp2, 0), cmd_resp.resp, (cmd_resp.response.response == 0 && cmd_resp.response.cmd_id == cmd_id && (sid == 0xff || cmd_resp.response.sensor_id == sid)), 500, 10000000)) @@ -39,7 +39,7 @@ static void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor cmd_base.cmd.sub_cmd_value = 1; cmd_base.cmd.sensor_id = info.sensor_idx; - writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG(0)); + writel(cmd_base.ul, privdata->mmio + amd_get_c2p_val(privdata, 0)); } static void amd_stop_sensor(struct amd_mp2_dev *privdata, u16 sensor_idx) @@ -52,8 +52,8 @@ static void amd_stop_sensor(struct amd_mp2_dev *privdata, u16 sensor_idx) cmd_base.cmd.sub_cmd_value = 1; cmd_base.cmd.sensor_id = sensor_idx; - writeq(0x0, privdata->mmio + AMD_C2P_MSG(1)); - writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG(0)); + writeq(0x0, privdata->mmio + amd_get_c2p_val(privdata, 1)); + writel(cmd_base.ul, privdata->mmio + amd_get_c2p_val(privdata, 0)); } static void amd_stop_all_sensor(struct amd_mp2_dev *privdata) @@ -66,7 +66,7 @@ static void amd_stop_all_sensor(struct amd_mp2_dev *privdata) /* 0xf indicates all sensors */ cmd_base.cmd.sensor_id = 0xf; - writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG(0)); + writel(cmd_base.ul, privdata->mmio + amd_get_c2p_val(privdata, 0)); } static struct amd_mp2_ops amd_sfh_ops = { diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 78cdfb8b9a7ae..88cbb2fe6ac8c 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -335,36 +335,20 @@ static int asus_raw_event(struct hid_device *hdev, if (drvdata->quirks & QUIRK_MEDION_E1239T) return asus_e1239t_event(drvdata, data, size); - if (drvdata->quirks & QUIRK_USE_KBD_BACKLIGHT) { + /* + * Skip these report ID, the device emits a continuous stream associated + * with the AURA mode it is in which looks like an 'echo'. + */ + if (report->id == FEATURE_KBD_LED_REPORT_ID1 || report->id == FEATURE_KBD_LED_REPORT_ID2) + return -1; + if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD) { /* - * Skip these report ID, the device emits a continuous stream associated - * with the AURA mode it is in which looks like an 'echo'. + * G713 and G733 send these codes on some keypresses, depending on + * the key pressed it can trigger a shutdown event if not caught. */ - if (report->id == FEATURE_KBD_LED_REPORT_ID1 || - report->id == FEATURE_KBD_LED_REPORT_ID2) { + if (data[0] == 0x02 && data[1] == 0x30) { return -1; - /* Additional report filtering */ - } else if (report->id == FEATURE_KBD_REPORT_ID) { - /* - * G14 and G15 send these codes on some keypresses with no - * discernable reason for doing so. We'll filter them out to avoid - * unmapped warning messages later. - */ - if (data[1] == 0xea || data[1] == 0xec || data[1] == 0x02 || - data[1] == 0x8a || data[1] == 0x9e) { - return -1; - } - } - if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD) { - /* - * G713 and G733 send these codes on some keypresses, depending on - * the key pressed it can trigger a shutdown event if not caught. - */ - if(data[0] == 0x02 && data[1] == 0x30) { - return -1; - } } - } if (drvdata->quirks & QUIRK_ROG_CLAYMORE_II_KEYBOARD) { @@ -1250,6 +1234,19 @@ static __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc, rdesc[205] = 0x01; } + /* match many more n-key devices */ + if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD && *rsize > 15) { + for (int i = 0; i < *rsize - 15; i++) { + /* offset to the count from 0x5a report part always 14 */ + if (rdesc[i] == 0x85 && rdesc[i + 1] == 0x5a && + rdesc[i + 14] == 0x95 && rdesc[i + 15] == 0x05) { + hid_info(hdev, "Fixing up Asus N-Key report descriptor\n"); + rdesc[i + 15] = 0x01; + break; + } + } + } + return rdesc; } @@ -1319,4 +1316,4 @@ static struct hid_driver asus_driver = { }; module_hid_driver(asus_driver); -MODULE_LICENSE("GPL"); \ No newline at end of file +MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index de7a477d66656..751a73ae7de75 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1448,7 +1448,6 @@ static void implement(const struct hid_device *hid, u8 *report, hid_warn(hid, "%s() called with too large value %d (n: %d)! (%s)\n", __func__, value, n, current->comm); - WARN_ON(1); value &= m; } } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 828a5c022c640..58111132ec528 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -430,6 +430,7 @@ #define I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V1 0x2BED #define I2C_DEVICE_ID_HP_SPECTRE_X360_14T_EA100_V2 0x2BEE #define I2C_DEVICE_ID_HP_ENVY_X360_15_EU0556NG 0x2D02 +#define I2C_DEVICE_ID_CHROMEBOOK_TROGDOR_POMPOM 0x2F81 #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 @@ -822,6 +823,7 @@ #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e #define USB_DEVICE_ID_LOGITECH_T651 0xb00c #define USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD 0xb309 +#define USB_DEVICE_ID_LOGITECH_CASA_TOUCHPAD 0xbb00 #define USB_DEVICE_ID_LOGITECH_C007 0xc007 #define USB_DEVICE_ID_LOGITECH_C077 0xc077 #define USB_DEVICE_ID_LOGITECH_RECEIVER 0xc101 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index c8b20d44b1472..e03d300d2bac4 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -411,6 +411,8 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15_EU0556NG), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_CHROMEBOOK_TROGDOR_POMPOM), + HID_BATTERY_QUIRK_AVOID_QUERY }, {} }; diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 149a3c74346b4..f86c1ea83a037 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -54,10 +54,10 @@ struct lenovo_drvdata { /* 0: Up * 1: Down (undecided) * 2: Scrolling - * 3: Patched firmware, disable workaround */ u8 middlebutton_state; bool fn_lock; + bool middleclick_workaround_cptkbd; }; #define map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c)) @@ -621,6 +621,36 @@ static ssize_t attr_sensitivity_store_cptkbd(struct device *dev, return count; } +static ssize_t attr_middleclick_workaround_show_cptkbd(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hid_device *hdev = to_hid_device(dev); + struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); + + return snprintf(buf, PAGE_SIZE, "%u\n", + cptkbd_data->middleclick_workaround_cptkbd); +} + +static ssize_t attr_middleclick_workaround_store_cptkbd(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + struct hid_device *hdev = to_hid_device(dev); + struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); + int value; + + if (kstrtoint(buf, 10, &value)) + return -EINVAL; + if (value < 0 || value > 1) + return -EINVAL; + + cptkbd_data->middleclick_workaround_cptkbd = !!value; + + return count; +} + static struct device_attribute dev_attr_fn_lock = __ATTR(fn_lock, S_IWUSR | S_IRUGO, @@ -632,10 +662,16 @@ static struct device_attribute dev_attr_sensitivity_cptkbd = attr_sensitivity_show_cptkbd, attr_sensitivity_store_cptkbd); +static struct device_attribute dev_attr_middleclick_workaround_cptkbd = + __ATTR(middleclick_workaround, S_IWUSR | S_IRUGO, + attr_middleclick_workaround_show_cptkbd, + attr_middleclick_workaround_store_cptkbd); + static struct attribute *lenovo_attributes_cptkbd[] = { &dev_attr_fn_lock.attr, &dev_attr_sensitivity_cptkbd.attr, + &dev_attr_middleclick_workaround_cptkbd.attr, NULL }; @@ -686,23 +722,7 @@ static int lenovo_event_cptkbd(struct hid_device *hdev, { struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); - if (cptkbd_data->middlebutton_state != 3) { - /* REL_X and REL_Y events during middle button pressed - * are only possible on patched, bug-free firmware - * so set middlebutton_state to 3 - * to never apply workaround anymore - */ - if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD && - cptkbd_data->middlebutton_state == 1 && - usage->type == EV_REL && - (usage->code == REL_X || usage->code == REL_Y)) { - cptkbd_data->middlebutton_state = 3; - /* send middle button press which was hold before */ - input_event(field->hidinput->input, - EV_KEY, BTN_MIDDLE, 1); - input_sync(field->hidinput->input); - } - + if (cptkbd_data->middleclick_workaround_cptkbd) { /* "wheel" scroll events */ if (usage->type == EV_REL && (usage->code == REL_WHEEL || usage->code == REL_HWHEEL)) { @@ -1166,6 +1186,7 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev) cptkbd_data->middlebutton_state = 0; cptkbd_data->fn_lock = true; cptkbd_data->sensitivity = 0x05; + cptkbd_data->middleclick_workaround_cptkbd = true; lenovo_features_set_cptkbd(hdev); ret = sysfs_create_group(&hdev->dev.kobj, &lenovo_attr_group_cptkbd); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index e6a8b6d8eab70..37958edec55f5 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -965,9 +965,7 @@ static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, } break; case REPORT_TYPE_MOUSE: - workitem->reports_supported |= STD_MOUSE | HIDPP; - if (djrcv_dev->type == recvr_type_mouse_only) - workitem->reports_supported |= MULTIMEDIA; + workitem->reports_supported |= STD_MOUSE | HIDPP | MULTIMEDIA; break; } } @@ -1286,8 +1284,10 @@ static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev, */ msleep(50); - if (retval) + if (retval) { + kfree(dj_report); return retval; + } } /* diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index f9cceaeffd081..da5ea5a23b087 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -944,9 +944,11 @@ static void mcp2221_hid_unregister(void *ptr) /* This is needed to be sure hid_hw_stop() isn't called twice by the subsystem */ static void mcp2221_remove(struct hid_device *hdev) { +#if IS_REACHABLE(CONFIG_IIO) struct mcp2221 *mcp = hid_get_drvdata(hdev); cancel_delayed_work_sync(&mcp->init_work); +#endif } #if IS_REACHABLE(CONFIG_IIO) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 3e91e4d6ba6fa..94ca12ee74956 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2082,6 +2082,12 @@ static const struct hid_device_id mt_devices[] = { USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X12_TAB) }, + /* Logitech devices */ + { .driver_data = MT_CLS_NSMU, + HID_DEVICE(BUS_BLUETOOTH, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_CASA_TOUCHPAD) }, + /* MosArt panels */ { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, MT_USB_DEVICE(USB_VENDOR_ID_ASUS, diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index ccc4032fb2b03..4b2c81b49b80e 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -481,10 +481,10 @@ static const struct joycon_ctlr_button_mapping n64con_button_mappings[] = { { BTN_TR, JC_BTN_R, }, { BTN_TR2, JC_BTN_LSTICK, }, /* ZR */ { BTN_START, JC_BTN_PLUS, }, - { BTN_FORWARD, JC_BTN_Y, }, /* C UP */ - { BTN_BACK, JC_BTN_ZR, }, /* C DOWN */ - { BTN_LEFT, JC_BTN_X, }, /* C LEFT */ - { BTN_RIGHT, JC_BTN_MINUS, }, /* C RIGHT */ + { BTN_SELECT, JC_BTN_Y, }, /* C UP */ + { BTN_X, JC_BTN_ZR, }, /* C DOWN */ + { BTN_Y, JC_BTN_X, }, /* C LEFT */ + { BTN_C, JC_BTN_MINUS, }, /* C RIGHT */ { BTN_MODE, JC_BTN_HOME, }, { BTN_Z, JC_BTN_CAP, }, { /* sentinel */ }, diff --git a/drivers/hid/hid-nvidia-shield.c b/drivers/hid/hid-nvidia-shield.c index 58b15750dbb0a..ff9078ad19611 100644 --- a/drivers/hid/hid-nvidia-shield.c +++ b/drivers/hid/hid-nvidia-shield.c @@ -283,7 +283,9 @@ static struct input_dev *shield_haptics_create( return haptics; input_set_capability(haptics, EV_FF, FF_RUMBLE); - input_ff_create_memless(haptics, NULL, play_effect); + ret = input_ff_create_memless(haptics, NULL, play_effect); + if (ret) + goto err; ret = input_register_device(haptics); if (ret) diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 2df1ab3c31cc5..d965382196c69 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -64,7 +64,6 @@ /* flags */ #define I2C_HID_STARTED 0 #define I2C_HID_RESET_PENDING 1 -#define I2C_HID_READ_PENDING 2 #define I2C_HID_PWR_ON 0x00 #define I2C_HID_PWR_SLEEP 0x01 @@ -190,15 +189,10 @@ static int i2c_hid_xfer(struct i2c_hid *ihid, msgs[n].len = recv_len; msgs[n].buf = recv_buf; n++; - - set_bit(I2C_HID_READ_PENDING, &ihid->flags); } ret = i2c_transfer(client->adapter, msgs, n); - if (recv_len) - clear_bit(I2C_HID_READ_PENDING, &ihid->flags); - if (ret != n) return ret < 0 ? ret : -EIO; @@ -556,9 +550,6 @@ static irqreturn_t i2c_hid_irq(int irq, void *dev_id) { struct i2c_hid *ihid = dev_id; - if (test_bit(I2C_HID_READ_PENDING, &ihid->flags)) - return IRQ_HANDLED; - i2c_hid_get_input(ihid); return IRQ_HANDLED; @@ -735,12 +726,15 @@ static int i2c_hid_parse(struct hid_device *hid) mutex_lock(&ihid->reset_lock); do { ret = i2c_hid_start_hwreset(ihid); - if (ret) + if (ret == 0) + ret = i2c_hid_finish_hwreset(ihid); + else msleep(1000); } while (tries-- > 0 && ret); + mutex_unlock(&ihid->reset_lock); if (ret) - goto abort_reset; + return ret; use_override = i2c_hid_get_dmi_hid_report_desc_override(client->name, &rsize); @@ -750,11 +744,8 @@ static int i2c_hid_parse(struct hid_device *hid) i2c_hid_dbg(ihid, "Using a HID report descriptor override\n"); } else { rdesc = kzalloc(rsize, GFP_KERNEL); - - if (!rdesc) { - ret = -ENOMEM; - goto abort_reset; - } + if (!rdesc) + return -ENOMEM; i2c_hid_dbg(ihid, "asking HID report descriptor\n"); @@ -763,23 +754,10 @@ static int i2c_hid_parse(struct hid_device *hid) rdesc, rsize); if (ret) { hid_err(hid, "reading report descriptor failed\n"); - goto abort_reset; + goto out; } } - /* - * Windows directly reads the report-descriptor after sending reset - * and then waits for resets completion afterwards. Some touchpads - * actually wait for the report-descriptor to be read before signalling - * reset completion. - */ - ret = i2c_hid_finish_hwreset(ihid); -abort_reset: - clear_bit(I2C_HID_RESET_PENDING, &ihid->flags); - mutex_unlock(&ihid->reset_lock); - if (ret) - goto out; - i2c_hid_dbg(ihid, "Report Descriptor: %*ph\n", rsize, rdesc); ret = hid_parse_report(hid, rdesc, rsize); diff --git a/drivers/hid/i2c-hid/i2c-hid-of-elan.c b/drivers/hid/i2c-hid/i2c-hid-of-elan.c index 5b91fb106cfc3..091e37933225a 100644 --- a/drivers/hid/i2c-hid/i2c-hid-of-elan.c +++ b/drivers/hid/i2c-hid/i2c-hid-of-elan.c @@ -31,6 +31,7 @@ struct i2c_hid_of_elan { struct regulator *vcc33; struct regulator *vccio; struct gpio_desc *reset_gpio; + bool no_reset_on_power_off; const struct elan_i2c_hid_chip_data *chip_data; }; @@ -40,17 +41,17 @@ static int elan_i2c_hid_power_up(struct i2chid_ops *ops) container_of(ops, struct i2c_hid_of_elan, ops); int ret; + gpiod_set_value_cansleep(ihid_elan->reset_gpio, 1); + if (ihid_elan->vcc33) { ret = regulator_enable(ihid_elan->vcc33); if (ret) - return ret; + goto err_deassert_reset; } ret = regulator_enable(ihid_elan->vccio); - if (ret) { - regulator_disable(ihid_elan->vcc33); - return ret; - } + if (ret) + goto err_disable_vcc33; if (ihid_elan->chip_data->post_power_delay_ms) msleep(ihid_elan->chip_data->post_power_delay_ms); @@ -60,6 +61,15 @@ static int elan_i2c_hid_power_up(struct i2chid_ops *ops) msleep(ihid_elan->chip_data->post_gpio_reset_on_delay_ms); return 0; + +err_disable_vcc33: + if (ihid_elan->vcc33) + regulator_disable(ihid_elan->vcc33); +err_deassert_reset: + if (ihid_elan->no_reset_on_power_off) + gpiod_set_value_cansleep(ihid_elan->reset_gpio, 0); + + return ret; } static void elan_i2c_hid_power_down(struct i2chid_ops *ops) @@ -67,7 +77,14 @@ static void elan_i2c_hid_power_down(struct i2chid_ops *ops) struct i2c_hid_of_elan *ihid_elan = container_of(ops, struct i2c_hid_of_elan, ops); - gpiod_set_value_cansleep(ihid_elan->reset_gpio, 1); + /* + * Do not assert reset when the hardware allows for it to remain + * deasserted regardless of the state of the (shared) power supply to + * avoid wasting power when the supply is left on. + */ + if (!ihid_elan->no_reset_on_power_off) + gpiod_set_value_cansleep(ihid_elan->reset_gpio, 1); + if (ihid_elan->chip_data->post_gpio_reset_off_delay_ms) msleep(ihid_elan->chip_data->post_gpio_reset_off_delay_ms); @@ -79,6 +96,7 @@ static void elan_i2c_hid_power_down(struct i2chid_ops *ops) static int i2c_hid_of_elan_probe(struct i2c_client *client) { struct i2c_hid_of_elan *ihid_elan; + int ret; ihid_elan = devm_kzalloc(&client->dev, sizeof(*ihid_elan), GFP_KERNEL); if (!ihid_elan) @@ -93,21 +111,38 @@ static int i2c_hid_of_elan_probe(struct i2c_client *client) if (IS_ERR(ihid_elan->reset_gpio)) return PTR_ERR(ihid_elan->reset_gpio); + ihid_elan->no_reset_on_power_off = of_property_read_bool(client->dev.of_node, + "no-reset-on-power-off"); + ihid_elan->vccio = devm_regulator_get(&client->dev, "vccio"); - if (IS_ERR(ihid_elan->vccio)) - return PTR_ERR(ihid_elan->vccio); + if (IS_ERR(ihid_elan->vccio)) { + ret = PTR_ERR(ihid_elan->vccio); + goto err_deassert_reset; + } ihid_elan->chip_data = device_get_match_data(&client->dev); if (ihid_elan->chip_data->main_supply_name) { ihid_elan->vcc33 = devm_regulator_get(&client->dev, ihid_elan->chip_data->main_supply_name); - if (IS_ERR(ihid_elan->vcc33)) - return PTR_ERR(ihid_elan->vcc33); + if (IS_ERR(ihid_elan->vcc33)) { + ret = PTR_ERR(ihid_elan->vcc33); + goto err_deassert_reset; + } } - return i2c_hid_core_probe(client, &ihid_elan->ops, - ihid_elan->chip_data->hid_descriptor_address, 0); + ret = i2c_hid_core_probe(client, &ihid_elan->ops, + ihid_elan->chip_data->hid_descriptor_address, 0); + if (ret) + goto err_deassert_reset; + + return 0; + +err_deassert_reset: + if (ihid_elan->no_reset_on_power_off) + gpiod_set_value_cansleep(ihid_elan->reset_gpio, 0); + + return ret; } static const struct elan_i2c_hid_chip_data elan_ekth6915_chip_data = { diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index a49c6affd7c4c..dd5fc60874ba1 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -948,6 +948,7 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev) if (!dev) return NULL; + dev->devc = &pdev->dev; ishtp_device_init(dev); init_waitqueue_head(&dev->wait_hw_ready); @@ -983,7 +984,6 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev) } dev->ops = &ish_hw_ops; - dev->devc = &pdev->dev; dev->mtu = IPC_PAYLOAD_SIZE - sizeof(struct ishtp_msg_hdr); return dev; } diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 65e7eeb2fa64e..ce5576ef3c861 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -172,6 +172,11 @@ static int ish_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* request and enable interrupt */ ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + dev_err(dev, "ISH: Failed to allocate IRQ vectors\n"); + return ret; + } + if (!pdev->msi_enabled && !pdev->msix_enabled) irq_flag = IRQF_SHARED; diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 00242107d62e0..862c47b191afe 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -16,6 +16,7 @@ config HYPERV config HYPERV_VTL_MODE bool "Enable Linux to boot in VTL context" depends on X86_64 && HYPERV + depends on SMP default n help Virtual Secure Mode (VSM) is a set of hypervisor capabilities and diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index adbf674355b2b..fb8cd8469328e 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -153,7 +153,9 @@ void vmbus_free_ring(struct vmbus_channel *channel) hv_ringbuffer_cleanup(&channel->inbound); if (channel->ringbuffer_page) { - __free_pages(channel->ringbuffer_page, + /* In a CoCo VM leak the memory if it didn't get re-encrypted */ + if (!channel->ringbuffer_gpadlhandle.decrypted) + __free_pages(channel->ringbuffer_page, get_order(channel->ringbuffer_pagecount << PAGE_SHIFT)); channel->ringbuffer_page = NULL; @@ -436,9 +438,18 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel, (atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1); ret = create_gpadl_header(type, kbuffer, size, send_offset, &msginfo); - if (ret) + if (ret) { + gpadl->decrypted = false; return ret; + } + /* + * Set the "decrypted" flag to true for the set_memory_decrypted() + * success case. In the failure case, the encryption state of the + * memory is unknown. Leave "decrypted" as true to ensure the + * memory will be leaked instead of going back on the free list. + */ + gpadl->decrypted = true; ret = set_memory_decrypted((unsigned long)kbuffer, PFN_UP(size)); if (ret) { @@ -527,9 +538,15 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel, kfree(msginfo); - if (ret) - set_memory_encrypted((unsigned long)kbuffer, - PFN_UP(size)); + if (ret) { + /* + * If set_memory_encrypted() fails, the decrypted flag is + * left as true so the memory is leaked instead of being + * put back on the free list. + */ + if (!set_memory_encrypted((unsigned long)kbuffer, PFN_UP(size))) + gpadl->decrypted = false; + } return ret; } @@ -850,6 +867,8 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, struct vmbus_gpadl *gpad if (ret) pr_warn("Fail to set mem host visibility in GPADL teardown %d.\n", ret); + gpadl->decrypted = ret; + return ret; } EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl); diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 3cabeeabb1cac..f001ae880e1db 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -237,8 +237,17 @@ int vmbus_connect(void) vmbus_connection.monitor_pages[0], 1); ret |= set_memory_decrypted((unsigned long) vmbus_connection.monitor_pages[1], 1); - if (ret) + if (ret) { + /* + * If set_memory_decrypted() fails, the encryption state + * of the memory is unknown. So leak the memory instead + * of risking returning decrypted memory to the free list. + * For simplicity, always handle both pages the same. + */ + vmbus_connection.monitor_pages[0] = NULL; + vmbus_connection.monitor_pages[1] = NULL; goto cleanup; + } /* * Set_memory_decrypted() will change the memory contents if @@ -337,13 +346,19 @@ void vmbus_disconnect(void) vmbus_connection.int_page = NULL; } - set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[0], 1); - set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[1], 1); + if (vmbus_connection.monitor_pages[0]) { + if (!set_memory_encrypted( + (unsigned long)vmbus_connection.monitor_pages[0], 1)) + hv_free_hyperv_page(vmbus_connection.monitor_pages[0]); + vmbus_connection.monitor_pages[0] = NULL; + } - hv_free_hyperv_page(vmbus_connection.monitor_pages[0]); - hv_free_hyperv_page(vmbus_connection.monitor_pages[1]); - vmbus_connection.monitor_pages[0] = NULL; - vmbus_connection.monitor_pages[1] = NULL; + if (vmbus_connection.monitor_pages[1]) { + if (!set_memory_encrypted( + (unsigned long)vmbus_connection.monitor_pages[1], 1)) + hv_free_hyperv_page(vmbus_connection.monitor_pages[1]); + vmbus_connection.monitor_pages[1] = NULL; + } } /* diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index a608264da87df..979bf293c372a 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -38,6 +38,18 @@ config HWMON_DEBUG_CHIP comment "Native drivers" +config SENSORS_AAEON + tristate "AAEON hwmon driver" + depends on X86 + depends on UBUNTU_ODM_DRIVERS + select MFD_AAEON + help + This hwmon driver adds support for reporting temperature or fan + speed and voltage on Single Board Computers produced by AAEON. + + This driver leverages the ASUS WMI interface to access device + resources. + config SENSORS_ABITUGURU tristate "Abit uGuru (rev 1 & 2)" depends on (X86 && DMI) || COMPILE_TEST diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index 47be39af5c038..8ffa48fca670e 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_SENSORS_HP_WMI) += hp-wmi-sensors.o # Native drivers # asb100, then w83781d go first, as they can override other drivers' addresses. +obj-$(CONFIG_SENSORS_AAEON) += hwmon-aaeon.o obj-$(CONFIG_SENSORS_ASB100) += asb100.o obj-$(CONFIG_SENSORS_W83627HF) += w83627hf.o obj-$(CONFIG_SENSORS_W83773G) += w83773g.o diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 703666b95bf49..6c8a9c863528e 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -883,6 +883,22 @@ static int acpi_power_meter_add(struct acpi_device *device) strcpy(acpi_device_class(device), ACPI_POWER_METER_CLASS); device->driver_data = resource; +#if IS_REACHABLE(CONFIG_ACPI_IPMI) + /* + * On Dell systems several methods of acpi_power_meter access + * variables in IPMI region, so wait until IPMI space handler is + * installed by acpi_ipmi and also wait until SMI is selected to make + * the space handler fully functional. + */ + if (dmi_match(DMI_SYS_VENDOR, "Dell Inc.")) { + struct acpi_device *ipi_device = acpi_dev_get_first_match_dev("IPI0001", NULL, -1); + + if (ipi_device && acpi_wait_for_acpi_ipmi()) + dev_warn(&device->dev, "Waiting for ACPI IPMI timeout"); + acpi_dev_put(ipi_device); + } +#endif + res = read_capabilities(resource); if (res) goto exit_free; diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c index 2a7a4b6b00942..9b02b304c2f5d 100644 --- a/drivers/hwmon/amc6821.c +++ b/drivers/hwmon/amc6821.c @@ -934,10 +934,21 @@ static const struct i2c_device_id amc6821_id[] = { MODULE_DEVICE_TABLE(i2c, amc6821_id); +static const struct of_device_id __maybe_unused amc6821_of_match[] = { + { + .compatible = "ti,amc6821", + .data = (void *)amc6821, + }, + { } +}; + +MODULE_DEVICE_TABLE(of, amc6821_of_match); + static struct i2c_driver amc6821_driver = { .class = I2C_CLASS_HWMON, .driver = { .name = "amc6821", + .of_match_table = of_match_ptr(amc6821_of_match), }, .probe = amc6821_probe, .id_table = amc6821_id, diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index b8fc8d1ef20df..30402de2c8890 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -39,13 +39,18 @@ static int force_tjmax; module_param_named(tjmax, force_tjmax, int, 0444); MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius"); -#define PKG_SYSFS_ATTR_NO 1 /* Sysfs attribute for package temp */ -#define BASE_SYSFS_ATTR_NO 2 /* Sysfs Base attr no for coretemp */ #define NUM_REAL_CORES 512 /* Number of Real cores per cpu */ #define CORETEMP_NAME_LENGTH 28 /* String Length of attrs */ -#define MAX_CORE_ATTRS 4 /* Maximum no of basic attrs */ -#define TOTAL_ATTRS (MAX_CORE_ATTRS + 1) -#define MAX_CORE_DATA (NUM_REAL_CORES + BASE_SYSFS_ATTR_NO) + +enum coretemp_attr_index { + ATTR_LABEL, + ATTR_CRIT_ALARM, + ATTR_TEMP, + ATTR_TJMAX, + ATTR_TTARGET, + MAX_CORE_ATTRS = ATTR_TJMAX + 1, /* Maximum no of basic attrs */ + TOTAL_ATTRS = ATTR_TTARGET + 1 /* Maximum no of possible attrs */ +}; #ifdef CONFIG_SMP #define for_each_sibling(i, cpu) \ @@ -65,19 +70,17 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius"); * @status_reg: One of IA32_THERM_STATUS or IA32_PACKAGE_THERM_STATUS, * from where the temperature values should be read. * @attr_size: Total number of pre-core attrs displayed in the sysfs. - * @is_pkg_data: If this is 1, the temp_data holds pkgtemp data. - * Otherwise, temp_data holds coretemp data. */ struct temp_data { int temp; int tjmax; unsigned long last_updated; unsigned int cpu; + int index; u32 cpu_core_id; u32 status_reg; int attr_size; - bool is_pkg_data; - struct sensor_device_attribute sd_attrs[TOTAL_ATTRS]; + struct device_attribute sd_attrs[TOTAL_ATTRS]; char attr_name[TOTAL_ATTRS][CORETEMP_NAME_LENGTH]; struct attribute *attrs[TOTAL_ATTRS + 1]; struct attribute_group attr_group; @@ -88,10 +91,11 @@ struct temp_data { struct platform_data { struct device *hwmon_dev; u16 pkg_id; - u16 cpu_map[NUM_REAL_CORES]; + int nr_cores; struct ida ida; struct cpumask cpumask; - struct temp_data *core_data[MAX_CORE_DATA]; + struct temp_data *pkg_data; + struct temp_data **core_data; struct device_attribute name_attr; }; @@ -143,6 +147,11 @@ static const struct tjmax_model tjmax_model_table[] = { */ }; +static bool is_pkg_temp_data(struct temp_data *tdata) +{ + return tdata->index < 0; +} + static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) { /* The 100C is default for both mobile and non mobile CPUs */ @@ -332,11 +341,10 @@ static struct platform_device **zone_devices; static ssize_t show_label(struct device *dev, struct device_attribute *devattr, char *buf) { - struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); struct platform_data *pdata = dev_get_drvdata(dev); - struct temp_data *tdata = pdata->core_data[attr->index]; + struct temp_data *tdata = container_of(devattr, struct temp_data, sd_attrs[ATTR_LABEL]); - if (tdata->is_pkg_data) + if (is_pkg_temp_data(tdata)) return sprintf(buf, "Package id %u\n", pdata->pkg_id); return sprintf(buf, "Core %u\n", tdata->cpu_core_id); @@ -346,9 +354,8 @@ static ssize_t show_crit_alarm(struct device *dev, struct device_attribute *devattr, char *buf) { u32 eax, edx; - struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); - struct platform_data *pdata = dev_get_drvdata(dev); - struct temp_data *tdata = pdata->core_data[attr->index]; + struct temp_data *tdata = container_of(devattr, struct temp_data, + sd_attrs[ATTR_CRIT_ALARM]); mutex_lock(&tdata->update_lock); rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx); @@ -360,9 +367,7 @@ static ssize_t show_crit_alarm(struct device *dev, static ssize_t show_tjmax(struct device *dev, struct device_attribute *devattr, char *buf) { - struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); - struct platform_data *pdata = dev_get_drvdata(dev); - struct temp_data *tdata = pdata->core_data[attr->index]; + struct temp_data *tdata = container_of(devattr, struct temp_data, sd_attrs[ATTR_TJMAX]); int tjmax; mutex_lock(&tdata->update_lock); @@ -375,9 +380,7 @@ static ssize_t show_tjmax(struct device *dev, static ssize_t show_ttarget(struct device *dev, struct device_attribute *devattr, char *buf) { - struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); - struct platform_data *pdata = dev_get_drvdata(dev); - struct temp_data *tdata = pdata->core_data[attr->index]; + struct temp_data *tdata = container_of(devattr, struct temp_data, sd_attrs[ATTR_TTARGET]); int ttarget; mutex_lock(&tdata->update_lock); @@ -393,9 +396,7 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *devattr, char *buf) { u32 eax, edx; - struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); - struct platform_data *pdata = dev_get_drvdata(dev); - struct temp_data *tdata = pdata->core_data[attr->index]; + struct temp_data *tdata = container_of(devattr, struct temp_data, sd_attrs[ATTR_TEMP]); int tjmax; mutex_lock(&tdata->update_lock); @@ -418,8 +419,7 @@ static ssize_t show_temp(struct device *dev, return sprintf(buf, "%d\n", tdata->temp); } -static int create_core_attrs(struct temp_data *tdata, struct device *dev, - int index) +static int create_core_attrs(struct temp_data *tdata, struct device *dev) { int i; static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev, @@ -436,16 +436,15 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev, * The attr number is always core id + 2 * The Pkgtemp will always show up as temp1_*, if available */ - int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2; + int attr_no = is_pkg_temp_data(tdata) ? 1 : tdata->cpu_core_id + 2; snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH, "temp%d_%s", attr_no, suffixes[i]); - sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr); - tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i]; - tdata->sd_attrs[i].dev_attr.attr.mode = 0444; - tdata->sd_attrs[i].dev_attr.show = rd_ptr[i]; - tdata->sd_attrs[i].index = index; - tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr; + sysfs_attr_init(&tdata->sd_attrs[i].attr); + tdata->sd_attrs[i].attr.name = tdata->attr_name[i]; + tdata->sd_attrs[i].attr.mode = 0444; + tdata->sd_attrs[i].show = rd_ptr[i]; + tdata->attrs[i] = &tdata->sd_attrs[i].attr; } tdata->attr_group.attrs = tdata->attrs; return sysfs_create_group(&dev->kobj, &tdata->attr_group); @@ -477,17 +476,44 @@ static struct platform_device *coretemp_get_pdev(unsigned int cpu) return NULL; } -static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag) +static struct temp_data * +init_temp_data(struct platform_data *pdata, unsigned int cpu, int pkg_flag) { struct temp_data *tdata; + if (!pdata->core_data) { + /* + * TODO: + * The information of actual possible cores in a package is broken for now. + * Will replace hardcoded NUM_REAL_CORES with actual per package core count + * when this information becomes available. + */ + pdata->nr_cores = NUM_REAL_CORES; + pdata->core_data = kcalloc(pdata->nr_cores, sizeof(struct temp_data *), + GFP_KERNEL); + if (!pdata->core_data) + return NULL; + } + tdata = kzalloc(sizeof(struct temp_data), GFP_KERNEL); if (!tdata) return NULL; + if (pkg_flag) { + pdata->pkg_data = tdata; + /* Use tdata->index as indicator of package temp data */ + tdata->index = -1; + } else { + tdata->index = ida_alloc_max(&pdata->ida, pdata->nr_cores - 1, GFP_KERNEL); + if (tdata->index < 0) { + kfree(tdata); + return NULL; + } + pdata->core_data[tdata->index] = tdata; + } + tdata->status_reg = pkg_flag ? MSR_IA32_PACKAGE_THERM_STATUS : MSR_IA32_THERM_STATUS; - tdata->is_pkg_data = pkg_flag; tdata->cpu = cpu; tdata->cpu_core_id = topology_core_id(cpu); tdata->attr_size = MAX_CORE_ATTRS; @@ -495,6 +521,36 @@ static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag) return tdata; } +static void destroy_temp_data(struct platform_data *pdata, struct temp_data *tdata) +{ + if (is_pkg_temp_data(tdata)) { + pdata->pkg_data = NULL; + kfree(pdata->core_data); + pdata->core_data = NULL; + pdata->nr_cores = 0; + } else { + pdata->core_data[tdata->index] = NULL; + ida_free(&pdata->ida, tdata->index); + } + kfree(tdata); +} + +static struct temp_data *get_temp_data(struct platform_data *pdata, int cpu) +{ + int i; + + /* cpu < 0 means get pkg temp_data */ + if (cpu < 0) + return pdata->pkg_data; + + for (i = 0; i < pdata->nr_cores; i++) { + if (pdata->core_data[i] && + pdata->core_data[i]->cpu_core_id == topology_core_id(cpu)) + return pdata->core_data[i]; + } + return NULL; +} + static int create_core_data(struct platform_device *pdev, unsigned int cpu, int pkg_flag) { @@ -502,37 +558,19 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, struct platform_data *pdata = platform_get_drvdata(pdev); struct cpuinfo_x86 *c = &cpu_data(cpu); u32 eax, edx; - int err, index; + int err; if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) return 0; - /* - * Get the index of tdata in pdata->core_data[] - * tdata for package: pdata->core_data[1] - * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1] - */ - if (pkg_flag) { - index = PKG_SYSFS_ATTR_NO; - } else { - index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL); - if (index < 0) - return index; - - pdata->cpu_map[index] = topology_core_id(cpu); - index += BASE_SYSFS_ATTR_NO; - } - - tdata = init_temp_data(cpu, pkg_flag); - if (!tdata) { - err = -ENOMEM; - goto ida_free; - } + tdata = init_temp_data(pdata, cpu, pkg_flag); + if (!tdata) + return -ENOMEM; /* Test if we can access the status register */ err = rdmsr_safe_on_cpu(cpu, tdata->status_reg, &eax, &edx); if (err) - goto exit_free; + goto err; /* Make sure tdata->tjmax is a valid indicator for dynamic/static tjmax */ get_tjmax(tdata, &pdev->dev); @@ -546,20 +584,15 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, if (get_ttarget(tdata, &pdev->dev) >= 0) tdata->attr_size++; - pdata->core_data[index] = tdata; - /* Create sysfs interfaces */ - err = create_core_attrs(tdata, pdata->hwmon_dev, index); + err = create_core_attrs(tdata, pdata->hwmon_dev); if (err) - goto exit_free; + goto err; return 0; -exit_free: - pdata->core_data[index] = NULL; - kfree(tdata); -ida_free: - if (!pkg_flag) - ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO); + +err: + destroy_temp_data(pdata, tdata); return err; } @@ -570,10 +603,8 @@ coretemp_add_core(struct platform_device *pdev, unsigned int cpu, int pkg_flag) dev_err(&pdev->dev, "Adding Core %u failed\n", cpu); } -static void coretemp_remove_core(struct platform_data *pdata, int indx) +static void coretemp_remove_core(struct platform_data *pdata, struct temp_data *tdata) { - struct temp_data *tdata = pdata->core_data[indx]; - /* if we errored on add then this is already gone */ if (!tdata) return; @@ -581,11 +612,7 @@ static void coretemp_remove_core(struct platform_data *pdata, int indx) /* Remove the sysfs attributes */ sysfs_remove_group(&pdata->hwmon_dev->kobj, &tdata->attr_group); - kfree(pdata->core_data[indx]); - pdata->core_data[indx] = NULL; - - if (indx >= BASE_SYSFS_ATTR_NO) - ida_free(&pdata->ida, indx - BASE_SYSFS_ATTR_NO); + destroy_temp_data(pdata, tdata); } static int coretemp_device_add(int zoneid) @@ -698,7 +725,7 @@ static int coretemp_cpu_offline(unsigned int cpu) struct platform_device *pdev = coretemp_get_pdev(cpu); struct platform_data *pd; struct temp_data *tdata; - int i, indx = -1, target; + int target; /* No need to tear down any interfaces for suspend */ if (cpuhp_tasks_frozen) @@ -709,18 +736,7 @@ static int coretemp_cpu_offline(unsigned int cpu) if (!pd->hwmon_dev) return 0; - for (i = 0; i < NUM_REAL_CORES; i++) { - if (pd->cpu_map[i] == topology_core_id(cpu)) { - indx = i + BASE_SYSFS_ATTR_NO; - break; - } - } - - /* Too many cores and this core is not populated, just return */ - if (indx < 0) - return 0; - - tdata = pd->core_data[indx]; + tdata = get_temp_data(pd, cpu); cpumask_clear_cpu(cpu, &pd->cpumask); @@ -731,7 +747,7 @@ static int coretemp_cpu_offline(unsigned int cpu) */ target = cpumask_any_and(&pd->cpumask, topology_sibling_cpumask(cpu)); if (target >= nr_cpu_ids) { - coretemp_remove_core(pd, indx); + coretemp_remove_core(pd, tdata); } else if (tdata && tdata->cpu == cpu) { mutex_lock(&tdata->update_lock); tdata->cpu = target; @@ -741,10 +757,10 @@ static int coretemp_cpu_offline(unsigned int cpu) /* * If all cores in this pkg are offline, remove the interface. */ - tdata = pd->core_data[PKG_SYSFS_ATTR_NO]; + tdata = get_temp_data(pd, -1); if (cpumask_empty(&pd->cpumask)) { if (tdata) - coretemp_remove_core(pd, PKG_SYSFS_ATTR_NO); + coretemp_remove_core(pd, tdata); hwmon_device_unregister(pd->hwmon_dev); pd->hwmon_dev = NULL; return 0; diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c index a284a02839fbb..3e63666a61bd6 100644 --- a/drivers/hwmon/corsair-cpro.c +++ b/drivers/hwmon/corsair-cpro.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #define USB_VENDOR_ID_CORSAIR 0x1b1c @@ -77,8 +78,11 @@ struct ccp_device { struct hid_device *hdev; struct device *hwmon_dev; + /* For reinitializing the completion below */ + spinlock_t wait_input_report_lock; struct completion wait_input_report; struct mutex mutex; /* whenever buffer is used, lock before send_usb_cmd */ + u8 *cmd_buffer; u8 *buffer; int target[6]; DECLARE_BITMAP(temp_cnct, NUM_TEMP_SENSORS); @@ -111,15 +115,23 @@ static int send_usb_cmd(struct ccp_device *ccp, u8 command, u8 byte1, u8 byte2, unsigned long t; int ret; - memset(ccp->buffer, 0x00, OUT_BUFFER_SIZE); - ccp->buffer[0] = command; - ccp->buffer[1] = byte1; - ccp->buffer[2] = byte2; - ccp->buffer[3] = byte3; - + memset(ccp->cmd_buffer, 0x00, OUT_BUFFER_SIZE); + ccp->cmd_buffer[0] = command; + ccp->cmd_buffer[1] = byte1; + ccp->cmd_buffer[2] = byte2; + ccp->cmd_buffer[3] = byte3; + + /* + * Disable raw event parsing for a moment to safely reinitialize the + * completion. Reinit is done because hidraw could have triggered + * the raw event parsing and marked the ccp->wait_input_report + * completion as done. + */ + spin_lock_bh(&ccp->wait_input_report_lock); reinit_completion(&ccp->wait_input_report); + spin_unlock_bh(&ccp->wait_input_report_lock); - ret = hid_hw_output_report(ccp->hdev, ccp->buffer, OUT_BUFFER_SIZE); + ret = hid_hw_output_report(ccp->hdev, ccp->cmd_buffer, OUT_BUFFER_SIZE); if (ret < 0) return ret; @@ -135,11 +147,12 @@ static int ccp_raw_event(struct hid_device *hdev, struct hid_report *report, u8 struct ccp_device *ccp = hid_get_drvdata(hdev); /* only copy buffer when requested */ - if (completion_done(&ccp->wait_input_report)) - return 0; - - memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size)); - complete(&ccp->wait_input_report); + spin_lock(&ccp->wait_input_report_lock); + if (!completion_done(&ccp->wait_input_report)) { + memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size)); + complete_all(&ccp->wait_input_report); + } + spin_unlock(&ccp->wait_input_report_lock); return 0; } @@ -492,7 +505,11 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) if (!ccp) return -ENOMEM; - ccp->buffer = devm_kmalloc(&hdev->dev, OUT_BUFFER_SIZE, GFP_KERNEL); + ccp->cmd_buffer = devm_kmalloc(&hdev->dev, OUT_BUFFER_SIZE, GFP_KERNEL); + if (!ccp->cmd_buffer) + return -ENOMEM; + + ccp->buffer = devm_kmalloc(&hdev->dev, IN_BUFFER_SIZE, GFP_KERNEL); if (!ccp->buffer) return -ENOMEM; @@ -510,7 +527,9 @@ static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) ccp->hdev = hdev; hid_set_drvdata(hdev, ccp); + mutex_init(&ccp->mutex); + spin_lock_init(&ccp->wait_input_report_lock); init_completion(&ccp->wait_input_report); hid_device_io_start(hdev); diff --git a/drivers/hwmon/hwmon-aaeon.c b/drivers/hwmon/hwmon-aaeon.c new file mode 100644 index 0000000000000..146da10309bbb --- /dev/null +++ b/drivers/hwmon/hwmon-aaeon.c @@ -0,0 +1,568 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AAEON HWMON driver + * Copyright (c) 2021, AAEON Ltd. + * + * Author: Edward Lin + * Author: Kunyang Fan + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRVNAME "hwmon-aaeon" + +#define AAEON_WMI_MGMT_GUID "97845ED0-4E6D-11DE-8A39-0800200C9A66" + +#define AAEON_VERSION_METHOD_ID 0x00000000 +#define HWM_INFORMATION_METHOD_ID 0x00030000 +#define HWM_METHOD_ID 0x00030001 + +#define BITMAP_TEMP_ARG 0x12 +#define BITMAP_FAN_ARG 0x13 +#define BITMAP_VOLTAGE_ARG 0x14 + +#define SENSOR_TEMP_NUMBER 0 +#define SENSOR_FAN_NUMBER 1 +#define SENSOR_VOLTAGE_NUMBER 2 +#define SENSOR_MAX_NUMBER 2 + +static ssize_t aaeon_show_sensor(struct device *dev, + struct device_attribute *devattr, char *buf); +static ssize_t aaeon_show_sensor_name(struct device *dev, + struct device_attribute *devattr, + char *buf); +static ssize_t aaeon_show_version(struct device *dev, + struct device_attribute *devattr, char *buf); +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, + char *buf); +static int aaeon_get_version(void); +static int aaeon_hwmon_probe(struct platform_device *pdev); +static int aaeon_hwmon_remove(struct platform_device *pdev); + +static const char * const temp_sensors_name_table[] = { + "CPU_Temp", + "SYS1_Temp", + "SYS2_Temp", +}; + +static const char * const temp_sensors_name_table_V3[] = { + "SYS_Temp", + "CPU_Temp", +}; + +static const char * const fan_sensors_name_table[] = { + "CPU_FAN", + "SYS1_FAN", + "SYS2_FAN", + "Chasis1_FAN", + "Chasis2_FAN", +}; + +static const char * const fan_sensors_name_table_V3[] = { + "Chasis_FAN", + "CPU_FAN", +}; + +static const char * const voltage_sensors_name_table[] = { + "VCORE_Voltage", + "VMEM_Voltage", + "+12_Voltage", + "+5_Voltage", + "+3.3_Voltage", + "+1.8_Voltage", + "5VSB_Voltage", + "3VSB_Voltage", + "VBAT_Voltage", +}; + +static const char * const voltage_sensors_name_table_V3[] = { + "VCORE_Voltage", + "+5_Voltage", + "AVCC_Voltage", + "+3.3_Voltage", + "+12_Voltage", + "VCOREREFIN_Voltage", + "VIN4_Voltage", + "3VSB_Voltage", + "VBAT_Voltage", +}; + +struct aaeon_hwmon_data { + struct device *hwmon_dev; + int bfpi_version; + u32 temp_bitmap; + u32 fan_bitmap; + u32 voltage_bitmap; + unsigned int sensors_number[SENSOR_MAX_NUMBER + 1]; + const char * const *temp_names; + const char * const *fan_names; + const char * const *voltage_names; +}; + +/* Temperature attributes */ +static struct sensor_device_attribute_2 temp_sys_nodes_atts[] = { + SENSOR_ATTR_2(temp1_input, 0444, aaeon_show_sensor, NULL, + SENSOR_TEMP_NUMBER, 0), + SENSOR_ATTR_2(temp1_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_TEMP_NUMBER, 0), + SENSOR_ATTR_2(temp2_input, 0444, aaeon_show_sensor, NULL, + SENSOR_TEMP_NUMBER, 1), + SENSOR_ATTR_2(temp2_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_TEMP_NUMBER, 1), + SENSOR_ATTR_2(temp3_input, 0444, aaeon_show_sensor, NULL, + SENSOR_TEMP_NUMBER, 2), + SENSOR_ATTR_2(temp3_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_TEMP_NUMBER, 2), +}; + +/* Cooler Fan attributes */ +static struct sensor_device_attribute_2 fan_sys_nodes_atts[] = { + SENSOR_ATTR_2(fan1_input, 0444, aaeon_show_sensor, NULL, + SENSOR_FAN_NUMBER, 0), + SENSOR_ATTR_2(fan1_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_FAN_NUMBER, 0), + SENSOR_ATTR_2(fan2_input, 0444, aaeon_show_sensor, NULL, + SENSOR_FAN_NUMBER, 1), + SENSOR_ATTR_2(fan2_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_FAN_NUMBER, 1), + SENSOR_ATTR_2(fan3_input, 0444, aaeon_show_sensor, NULL, + SENSOR_FAN_NUMBER, 2), + SENSOR_ATTR_2(fan3_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_FAN_NUMBER, 2), + SENSOR_ATTR_2(fan4_input, 0444, aaeon_show_sensor, NULL, + SENSOR_FAN_NUMBER, 3), + SENSOR_ATTR_2(fan4_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_FAN_NUMBER, 3), + SENSOR_ATTR_2(fan5_input, 0444, aaeon_show_sensor, NULL, + SENSOR_FAN_NUMBER, 4), + SENSOR_ATTR_2(fan5_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_FAN_NUMBER, 4), +}; + +/* Voltage attributes */ +static struct sensor_device_attribute_2 voltage_sys_nodes_atts[] = { + SENSOR_ATTR_2(in1_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 0), + SENSOR_ATTR_2(in1_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 0), + SENSOR_ATTR_2(in2_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 1), + SENSOR_ATTR_2(in2_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 1), + SENSOR_ATTR_2(in3_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 2), + SENSOR_ATTR_2(in3_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 2), + SENSOR_ATTR_2(in4_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 3), + SENSOR_ATTR_2(in4_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 3), + SENSOR_ATTR_2(in5_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 4), + SENSOR_ATTR_2(in5_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 4), + SENSOR_ATTR_2(in6_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 5), + SENSOR_ATTR_2(in6_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 5), + SENSOR_ATTR_2(in7_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 6), + SENSOR_ATTR_2(in7_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 6), + SENSOR_ATTR_2(in8_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 7), + SENSOR_ATTR_2(in8_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 7), + SENSOR_ATTR_2(in9_input, 0444, aaeon_show_sensor, NULL, + SENSOR_VOLTAGE_NUMBER, 8), + SENSOR_ATTR_2(in9_label, 0444, aaeon_show_sensor_name, NULL, + SENSOR_VOLTAGE_NUMBER, 8), + +}; + +static struct sensor_device_attribute_2 info_sys_nodes_atts[] = { + /* WMI version Information */ + SENSOR_ATTR_2(AAEON_VERSION, 0444, aaeon_show_version, NULL, 0, 0), +}; + +DEVICE_ATTR_RO(name); +static ssize_t name_show(struct device *dev, struct device_attribute *devattr, + char *buf) +{ + return sprintf(buf, "%s\n", DRVNAME); +} + +static ssize_t aaeon_show_version(struct device *dev, + struct device_attribute *devattr, char *buf) +{ + struct aaeon_hwmon_data *data = + (struct aaeon_hwmon_data *)dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", data->bfpi_version); +} + +static ssize_t aaeon_show_sensor_name(struct device *dev, + struct device_attribute *devattr, char *buf) +{ + u8 nr = to_sensor_dev_attr_2(devattr)->nr; + u8 index = to_sensor_dev_attr_2(devattr)->index; + struct aaeon_hwmon_data *data = + (struct aaeon_hwmon_data *)dev_get_drvdata(dev); + + if (nr > SENSOR_MAX_NUMBER || index >= data->sensors_number[nr]) { + pr_debug("Can not check the device"); + return -1; + } + + switch (nr) { + case SENSOR_TEMP_NUMBER: + return sprintf(buf, "%s\n", data->temp_names[index]); + case SENSOR_FAN_NUMBER: + return sprintf(buf, "%s\n", data->fan_names[index]); + case SENSOR_VOLTAGE_NUMBER: + return sprintf(buf, "%s\n", data->voltage_names[index]); + default: + break; + } + + return 0; +} + +static ssize_t aaeon_show_sensor(struct device *dev, + struct device_attribute *devattr, char *buf) +{ + u8 nr = to_sensor_dev_attr_2(devattr)->nr; + u8 index = to_sensor_dev_attr_2(devattr)->index; + u32 dev_id; + int retval, err; + struct aaeon_hwmon_data *data = + (struct aaeon_hwmon_data *)dev_get_drvdata(dev); + + if (nr > SENSOR_MAX_NUMBER || index >= data->sensors_number[nr]) { + pr_debug("Can not check the device"); + return -1; + } + + /* For the V3 version, index need offset */ + if (data->bfpi_version == 0x03 && nr != SENSOR_VOLTAGE_NUMBER) + index++; + + dev_id = (index << 12) | (nr << 8); + err = asus_wmi_evaluate_method(HWM_METHOD_ID, dev_id, 0, &retval); + if (err) + return err; + + /* For the V3 version, need to convert the raw value*/ + if (nr == SENSOR_VOLTAGE_NUMBER && data->bfpi_version == 0x03) { + switch (index) { + case 0: /* VCORE */ + retval = retval * 16; + break; + case 1: /* +5V */ + retval = (retval * 2008) / 50; + break; + case 2: /* AVCC */ + retval = retval * 16; + break; + case 3: /* +3.3V */ + retval = retval * 16; + break; + case 4: /* +12V */ + retval = retval * 96; + break; + case 5: /* VCOREREFIN */ + retval = (retval * 552) / 41; + break; + case 6: /* VIN4 */ + retval = retval * 8; + break; + case 7: /* 3VSB */ + retval = retval * 16; + break; + case 8: /* VBAT */ + retval = retval * 16; + break; + default: + break; + } + } else if (nr == SENSOR_TEMP_NUMBER && data->bfpi_version == 0x03) + retval = retval * 1000; + + return sprintf(buf, "%d\n", retval); +} + +static int aaeon_hwmon_create_sub_sysfs_fs(struct platform_device *pdev, + struct sensor_device_attribute_2 *attr, + int sensor_number, + u32 sensor_mask, + int bfpi_version) +{ + int i, err = 0; + + for (i = 0; i < sensor_number; i++) { + if (bfpi_version == 0x03 || sensor_mask & BIT(i)) { + err = device_create_file(&pdev->dev, &attr[2 * i].dev_attr); + if (err) + break; + err = device_create_file(&pdev->dev, &attr[2 * i + 1].dev_attr); + if (err) + break; + } + } + + return err; +} + +static int +aaeon_hwmon_create_sysfs_files(struct platform_device *pdev, struct aaeon_hwmon_data *data) +{ + int err; + + /* register sysfs interface files */ + err = device_create_file(&pdev->dev, &dev_attr_name); + if (err) + return err; + + /* registe sysfs to dump sensors BFPI version */ + err = device_create_file(&pdev->dev, &info_sys_nodes_atts[0].dev_attr); + if (err) + return err; + + /* create temperature name and value node */ + err = aaeon_hwmon_create_sub_sysfs_fs(pdev, temp_sys_nodes_atts, + data->sensors_number[SENSOR_TEMP_NUMBER], + data->temp_bitmap, data->bfpi_version); + if (err) + return err; + + /* create fan name and value node */ + err = aaeon_hwmon_create_sub_sysfs_fs(pdev, fan_sys_nodes_atts, + data->sensors_number[SENSOR_FAN_NUMBER], + data->fan_bitmap, data->bfpi_version); + if (err) + return err; + + /* create voltage name and value node */ + err = aaeon_hwmon_create_sub_sysfs_fs(pdev, voltage_sys_nodes_atts, + data->sensors_number[SENSOR_VOLTAGE_NUMBER], + data->voltage_bitmap, data->bfpi_version); + if (err) + return err; + + return 0; +} + +static void aaeon_hwmon_remove_sub_sysfs_fs(struct platform_device *pdev, + struct sensor_device_attribute_2 *attr, + int sensor_number, + u32 sensor_mask, + int bfpi_version) +{ + int i; + + for (i = 0; i < sensor_number; i++) { + if (bfpi_version == 0x03 || sensor_mask & BIT(i)) { + device_remove_file(&pdev->dev, &attr[2 * i].dev_attr); + device_remove_file(&pdev->dev, &attr[2 * i + 1].dev_attr); + } + } +} + +static void +aaeon_hwmon_remove_sysfs_files(struct platform_device *pdev, + struct aaeon_hwmon_data *data) +{ + /* degister sysfs interface files */ + device_remove_file(&pdev->dev, &dev_attr_name); + + /* degiste sysfs to dump sensors BFPI version */ + device_remove_file(&pdev->dev, &info_sys_nodes_atts[0].dev_attr); + + /* remove temperature name and value node */ + aaeon_hwmon_remove_sub_sysfs_fs(pdev, temp_sys_nodes_atts, + data->sensors_number[SENSOR_TEMP_NUMBER], + data->temp_bitmap, + data->bfpi_version); + + /* remove fan name and value node */ + aaeon_hwmon_remove_sub_sysfs_fs(pdev, fan_sys_nodes_atts, + data->sensors_number[SENSOR_FAN_NUMBER], + data->fan_bitmap, + data->bfpi_version); + + /* remove voltage name and value node */ + aaeon_hwmon_remove_sub_sysfs_fs(pdev, voltage_sys_nodes_atts, + data->sensors_number[SENSOR_VOLTAGE_NUMBER], + data->voltage_bitmap, + data->bfpi_version); +} + +static int aaeon_hwmon_remove(struct platform_device *pdev) +{ + struct aaeon_hwmon_data *data = platform_get_drvdata(pdev); + + if (data->hwmon_dev) + hwmon_device_unregister(data->hwmon_dev); + + aaeon_hwmon_remove_sysfs_files(pdev, data); + + return 0; +} + +static int aaeon_get_version(void) +{ + int err, retval; + u32 dev_id = 0x00; + + err = asus_wmi_evaluate_method(AAEON_VERSION_METHOD_ID, dev_id, 0, + &retval); + if (err) + return err; + + return retval; +} + +static int aaeon_hwmon_init_drv_data(struct aaeon_hwmon_data *data) +{ + int err; + + data->bfpi_version = aaeon_get_version(); + if (data->bfpi_version < 0) { + pr_debug("Error BFPI verion\n"); + return -1; + } + + if (data->bfpi_version == 0x03) { + /* set the number of bits in temp bitmap */ + data->sensors_number[SENSOR_TEMP_NUMBER] = + ARRAY_SIZE(temp_sensors_name_table_V3); + data->temp_names = temp_sensors_name_table_V3; + + /* set the number of bits in fan bitmap */ + data->sensors_number[SENSOR_FAN_NUMBER] = + ARRAY_SIZE(fan_sensors_name_table_V3); + data->fan_names = fan_sensors_name_table_V3; + + /* set the number of bits in voltage bitmap */ + data->sensors_number[SENSOR_VOLTAGE_NUMBER] = + ARRAY_SIZE(voltage_sensors_name_table_V3); + data->voltage_names = voltage_sensors_name_table_V3; + } else { + /* set the number of bits in temp bitmap */ + data->sensors_number[SENSOR_TEMP_NUMBER] = + ARRAY_SIZE(temp_sensors_name_table); + data->temp_names = temp_sensors_name_table; + + /* set the number of bits in fan bitmap */ + data->sensors_number[SENSOR_FAN_NUMBER] = + ARRAY_SIZE(fan_sensors_name_table); + data->fan_names = fan_sensors_name_table; + + /* set the number of bits in voltage bitmap */ + data->sensors_number[SENSOR_VOLTAGE_NUMBER] = + ARRAY_SIZE(voltage_sensors_name_table); + data->voltage_names = voltage_sensors_name_table; + } + + /* get temp supported bitmap */ + err = asus_wmi_evaluate_method(HWM_INFORMATION_METHOD_ID, + BITMAP_TEMP_ARG, 0, &data->temp_bitmap); + if (err) + return err; + + /* get fan supported bitmap */ + err = asus_wmi_evaluate_method(HWM_INFORMATION_METHOD_ID, + BITMAP_FAN_ARG, 0, &data->fan_bitmap); + if (err) + return err; + + /* get voltage supported bitmap */ + err = asus_wmi_evaluate_method(HWM_INFORMATION_METHOD_ID, + BITMAP_VOLTAGE_ARG, 0, &data->voltage_bitmap); + if (err) + return err; + + return 0; +} + +static int aaeon_hwmon_probe(struct platform_device *pdev) +{ + int err; + struct aaeon_hwmon_data *data; + + pr_debug("aaeon hwomon device probe (support V3)!\n"); + if (!wmi_has_guid(AAEON_WMI_MGMT_GUID)) { + pr_info("AAEON Management GUID not found\n"); + return -ENODEV; + } + + data = devm_kzalloc(&pdev->dev, sizeof(struct aaeon_hwmon_data), + GFP_KERNEL); + if (!data) + return -ENOMEM; + + err = aaeon_hwmon_init_drv_data(data); + if (err) { + pr_info("Error to get sensor support bitmap\n"); + goto exit; + } + + if (data->bfpi_version != 0x03 && data->temp_bitmap == 0 && + data->fan_bitmap == 0 && data->voltage_bitmap == 0) { + pr_debug("No sensors found\n"); + err = -ENODEV; + goto exit; + } + + platform_set_drvdata(pdev, data); + err = aaeon_hwmon_create_sysfs_files(pdev, data); + if (err) + goto exit; + + data->hwmon_dev = devm_hwmon_device_register_with_info(&pdev->dev, + "AAEON_HWM", + data, + NULL, + NULL); + if (IS_ERR(data->hwmon_dev)) { + err = PTR_ERR(data->hwmon_dev); + data->hwmon_dev = NULL; + goto exit_unregister_sysfs; + } + + return 0; + +exit_unregister_sysfs: + aaeon_hwmon_remove(pdev); +exit: + return err; +} + +static struct platform_driver aaeon_hwmon_driver = { + .driver = { + .name = DRVNAME, + .owner = THIS_MODULE, + }, + .probe = aaeon_hwmon_probe, + .remove = aaeon_hwmon_remove, +}; + +module_platform_driver_probe(aaeon_hwmon_driver, aaeon_hwmon_probe); + +MODULE_ALIAS("platform:hwmon-aaeon"); +MODULE_DESCRIPTION("AAEON Hardware Monitoring Driver"); +MODULE_AUTHOR("Edward Lin "); +MODULE_AUTHOR("Kunyang Fan "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwmon/intel-m10-bmc-hwmon.c b/drivers/hwmon/intel-m10-bmc-hwmon.c index 6500ca548f9c7..ca2dff1589251 100644 --- a/drivers/hwmon/intel-m10-bmc-hwmon.c +++ b/drivers/hwmon/intel-m10-bmc-hwmon.c @@ -429,7 +429,7 @@ static const struct m10bmc_sdata n6000bmc_curr_tbl[] = { }; static const struct m10bmc_sdata n6000bmc_power_tbl[] = { - { 0x724, 0x0, 0x0, 0x0, 0x0, 1, "Board Power" }, + { 0x724, 0x0, 0x0, 0x0, 0x0, 1000, "Board Power" }, }; static const struct hwmon_channel_info * const n6000bmc_hinfo[] = { diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c index 001799bc28ed6..b8548105cd67a 100644 --- a/drivers/hwmon/ltc2992.c +++ b/drivers/hwmon/ltc2992.c @@ -876,9 +876,11 @@ static int ltc2992_parse_dt(struct ltc2992_state *st) ret = fwnode_property_read_u32(child, "shunt-resistor-micro-ohms", &val); if (!ret) { - if (!val) + if (!val) { + fwnode_handle_put(child); return dev_err_probe(&st->client->dev, -EINVAL, "shunt resistor value cannot be zero\n"); + } st->r_sense_uohm[addr] = val; } } diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c index 8d9d422450e5c..d817c719b90bd 100644 --- a/drivers/hwmon/pmbus/ucd9000.c +++ b/drivers/hwmon/pmbus/ucd9000.c @@ -80,11 +80,11 @@ struct ucd9000_debugfs_entry { * It has been observed that the UCD90320 randomly fails register access when * doing another access right on the back of a register write. To mitigate this * make sure that there is a minimum delay between a write access and the - * following access. The 250us is based on experimental data. At a delay of - * 200us the issue seems to go away. Add a bit of extra margin to allow for + * following access. The 500 is based on experimental data. At a delay of + * 350us the issue seems to go away. Add a bit of extra margin to allow for * system to system differences. */ -#define UCD90320_WAIT_DELAY_US 250 +#define UCD90320_WAIT_DELAY_US 500 static inline void ucd90320_wait(const struct ucd9000_data *data) { diff --git a/drivers/hwmon/shtc1.c b/drivers/hwmon/shtc1.c index 1f96e94967ee8..439dd3dba5fc8 100644 --- a/drivers/hwmon/shtc1.c +++ b/drivers/hwmon/shtc1.c @@ -238,7 +238,7 @@ static int shtc1_probe(struct i2c_client *client) if (np) { data->setup.blocking_io = of_property_read_bool(np, "sensirion,blocking-io"); - data->setup.high_precision = !of_property_read_bool(np, "sensicon,low-precision"); + data->setup.high_precision = !of_property_read_bool(np, "sensirion,low-precision"); } else { if (client->dev.platform_data) data->setup = *(struct shtc1_platform_data *)dev->platform_data; diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index d7f0e231feb99..965bb6d4e1bf4 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -441,8 +441,26 @@ static void coresight_disable_helpers(struct coresight_device *csdev) } } +/* + * Helper function to call source_ops(csdev)->disable and also disable the + * helpers. + * + * There is an imbalance between coresight_enable_path() and + * coresight_disable_path(). Enabling also enables the source's helpers as part + * of the path, but disabling always skips the first item in the path (which is + * the source), so sources and their helpers don't get disabled as part of that + * function and we need the extra step here. + */ +void coresight_disable_source(struct coresight_device *csdev, void *data) +{ + if (source_ops(csdev)->disable) + source_ops(csdev)->disable(csdev, data); + coresight_disable_helpers(csdev); +} +EXPORT_SYMBOL_GPL(coresight_disable_source); + /** - * coresight_disable_source - Drop the reference count by 1 and disable + * coresight_disable_source_sysfs - Drop the reference count by 1 and disable * the device if there are no users left. * * @csdev: The coresight device to disable @@ -451,17 +469,15 @@ static void coresight_disable_helpers(struct coresight_device *csdev) * * Returns true if the device has been disabled. */ -bool coresight_disable_source(struct coresight_device *csdev, void *data) +static bool coresight_disable_source_sysfs(struct coresight_device *csdev, + void *data) { if (atomic_dec_return(&csdev->refcnt) == 0) { - if (source_ops(csdev)->disable) - source_ops(csdev)->disable(csdev, data); - coresight_disable_helpers(csdev); + coresight_disable_source(csdev, data); csdev->enable = false; } return !csdev->enable; } -EXPORT_SYMBOL_GPL(coresight_disable_source); /* * coresight_disable_path_from : Disable components in the given path beyond @@ -1204,7 +1220,7 @@ void coresight_disable(struct coresight_device *csdev) if (ret) goto out; - if (!csdev->enable || !coresight_disable_source(csdev, NULL)) + if (!csdev->enable || !coresight_disable_source_sysfs(csdev, NULL)) goto out; switch (csdev->subtype.source_subtype) { diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index a52cfcce25d6d..c0c60e6a1703e 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -589,7 +589,7 @@ static void etm_event_stop(struct perf_event *event, int mode) return; /* stop tracer */ - source_ops(csdev)->disable(csdev, event); + coresight_disable_source(csdev, event); /* tell the core */ event->hw.state = PERF_HES_STOPPED; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index ce1995a2827f0..30e8a235242d5 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -1200,6 +1200,7 @@ static void etm4_init_arch_data(void *info) struct etm4_init_arg *init_arg = info; struct etmv4_drvdata *drvdata; struct csdev_access *csa; + struct device *dev = init_arg->dev; int i; drvdata = dev_get_drvdata(init_arg->dev); @@ -1213,6 +1214,10 @@ static void etm4_init_arch_data(void *info) if (!etm4_init_csdev_access(drvdata, csa)) return; + if (!csa->io_mem || + fwnode_property_present(dev_fwnode(dev), "qcom,skip-power-up")) + drvdata->skip_power_up = true; + /* Detect the support for OS Lock before we actually use it */ etm_detect_os_lock(drvdata, csa); @@ -1239,6 +1244,8 @@ static void etm4_init_arch_data(void *info) drvdata->nr_event = FIELD_GET(TRCIDR0_NUMEVENT_MASK, etmidr0); /* QSUPP, bits[16:15] Q element support field */ drvdata->q_support = FIELD_GET(TRCIDR0_QSUPP_MASK, etmidr0); + if (drvdata->q_support) + drvdata->q_filt = !!(etmidr0 & TRCIDR0_QFILT); /* TSSIZE, bits[28:24] Global timestamp size field */ drvdata->ts_size = FIELD_GET(TRCIDR0_TSSIZE_MASK, etmidr0); @@ -1731,16 +1738,14 @@ static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) state->trcccctlr = etm4x_read32(csa, TRCCCCTLR); state->trcbbctlr = etm4x_read32(csa, TRCBBCTLR); state->trctraceidr = etm4x_read32(csa, TRCTRACEIDR); - state->trcqctlr = etm4x_read32(csa, TRCQCTLR); + if (drvdata->q_filt) + state->trcqctlr = etm4x_read32(csa, TRCQCTLR); state->trcvictlr = etm4x_read32(csa, TRCVICTLR); state->trcviiectlr = etm4x_read32(csa, TRCVIIECTLR); state->trcvissctlr = etm4x_read32(csa, TRCVISSCTLR); if (drvdata->nr_pe_cmp) state->trcvipcssctlr = etm4x_read32(csa, TRCVIPCSSCTLR); - state->trcvdctlr = etm4x_read32(csa, TRCVDCTLR); - state->trcvdsacctlr = etm4x_read32(csa, TRCVDSACCTLR); - state->trcvdarcctlr = etm4x_read32(csa, TRCVDARCCTLR); for (i = 0; i < drvdata->nrseqstate - 1; i++) state->trcseqevr[i] = etm4x_read32(csa, TRCSEQEVRn(i)); @@ -1757,7 +1762,8 @@ static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) state->trccntvr[i] = etm4x_read32(csa, TRCCNTVRn(i)); } - for (i = 0; i < drvdata->nr_resource * 2; i++) + /* Resource selector pair 0 is reserved */ + for (i = 2; i < drvdata->nr_resource * 2; i++) state->trcrsctlr[i] = etm4x_read32(csa, TRCRSCTLRn(i)); for (i = 0; i < drvdata->nr_ss_cmp; i++) { @@ -1842,8 +1848,10 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata) { int i; struct etmv4_save_state *state = drvdata->save_state; - struct csdev_access tmp_csa = CSDEV_ACCESS_IOMEM(drvdata->base); - struct csdev_access *csa = &tmp_csa; + struct csdev_access *csa = &drvdata->csdev->access; + + if (WARN_ON(!drvdata->csdev)) + return; etm4_cs_unlock(drvdata, csa); etm4x_relaxed_write32(csa, state->trcclaimset, TRCCLAIMSET); @@ -1862,16 +1870,14 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata) etm4x_relaxed_write32(csa, state->trcccctlr, TRCCCCTLR); etm4x_relaxed_write32(csa, state->trcbbctlr, TRCBBCTLR); etm4x_relaxed_write32(csa, state->trctraceidr, TRCTRACEIDR); - etm4x_relaxed_write32(csa, state->trcqctlr, TRCQCTLR); + if (drvdata->q_filt) + etm4x_relaxed_write32(csa, state->trcqctlr, TRCQCTLR); etm4x_relaxed_write32(csa, state->trcvictlr, TRCVICTLR); etm4x_relaxed_write32(csa, state->trcviiectlr, TRCVIIECTLR); etm4x_relaxed_write32(csa, state->trcvissctlr, TRCVISSCTLR); if (drvdata->nr_pe_cmp) etm4x_relaxed_write32(csa, state->trcvipcssctlr, TRCVIPCSSCTLR); - etm4x_relaxed_write32(csa, state->trcvdctlr, TRCVDCTLR); - etm4x_relaxed_write32(csa, state->trcvdsacctlr, TRCVDSACCTLR); - etm4x_relaxed_write32(csa, state->trcvdarcctlr, TRCVDARCCTLR); for (i = 0; i < drvdata->nrseqstate - 1; i++) etm4x_relaxed_write32(csa, state->trcseqevr[i], TRCSEQEVRn(i)); @@ -1888,7 +1894,8 @@ static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata) etm4x_relaxed_write32(csa, state->trccntvr[i], TRCCNTVRn(i)); } - for (i = 0; i < drvdata->nr_resource * 2; i++) + /* Resource selector pair 0 is reserved */ + for (i = 2; i < drvdata->nr_resource * 2; i++) etm4x_relaxed_write32(csa, state->trcrsctlr[i], TRCRSCTLRn(i)); for (i = 0; i < drvdata->nr_ss_cmp; i++) { @@ -2040,11 +2047,6 @@ static int etm4_add_coresight_dev(struct etm4_init_arg *init_arg) if (!drvdata->arch) return -EINVAL; - /* TRCPDCR is not accessible with system instructions. */ - if (!desc.access.io_mem || - fwnode_property_present(dev_fwnode(dev), "qcom,skip-power-up")) - drvdata->skip_power_up = true; - major = ETM_ARCH_MAJOR_VERSION(drvdata->arch); minor = ETM_ARCH_MINOR_VERSION(drvdata->arch); @@ -2217,6 +2219,9 @@ static int etm4_probe_platform_dev(struct platform_device *pdev) ret = etm4_probe(&pdev->dev); pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + return ret; } diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index da17b6c49b0f1..6b6760e49ed35 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -43,9 +43,6 @@ #define TRCVIIECTLR 0x084 #define TRCVISSCTLR 0x088 #define TRCVIPCSSCTLR 0x08C -#define TRCVDCTLR 0x0A0 -#define TRCVDSACCTLR 0x0A4 -#define TRCVDARCCTLR 0x0A8 /* Derived resources registers */ #define TRCSEQEVRn(n) (0x100 + (n * 4)) /* n = 0-2 */ #define TRCSEQRSTEVR 0x118 @@ -90,9 +87,6 @@ /* Address Comparator registers n = 0-15 */ #define TRCACVRn(n) (0x400 + (n * 8)) #define TRCACATRn(n) (0x480 + (n * 8)) -/* Data Value Comparator Value registers, n = 0-7 */ -#define TRCDVCVRn(n) (0x500 + (n * 16)) -#define TRCDVCMRn(n) (0x580 + (n * 16)) /* ContextID/Virtual ContextID comparators, n = 0-7 */ #define TRCCIDCVRn(n) (0x600 + (n * 8)) #define TRCVMIDCVRn(n) (0x640 + (n * 8)) @@ -141,6 +135,7 @@ #define TRCIDR0_TRCCCI BIT(7) #define TRCIDR0_RETSTACK BIT(9) #define TRCIDR0_NUMEVENT_MASK GENMASK(11, 10) +#define TRCIDR0_QFILT BIT(14) #define TRCIDR0_QSUPP_MASK GENMASK(16, 15) #define TRCIDR0_TSSIZE_MASK GENMASK(28, 24) @@ -272,9 +267,6 @@ /* List of registers accessible via System instructions */ #define ETM4x_ONLY_SYSREG_LIST(op, val) \ CASE_##op((val), TRCPROCSELR) \ - CASE_##op((val), TRCVDCTLR) \ - CASE_##op((val), TRCVDSACCTLR) \ - CASE_##op((val), TRCVDARCCTLR) \ CASE_##op((val), TRCOSLAR) #define ETM_COMMON_SYSREG_LIST(op, val) \ @@ -422,22 +414,6 @@ CASE_##op((val), TRCACATRn(13)) \ CASE_##op((val), TRCACATRn(14)) \ CASE_##op((val), TRCACATRn(15)) \ - CASE_##op((val), TRCDVCVRn(0)) \ - CASE_##op((val), TRCDVCVRn(1)) \ - CASE_##op((val), TRCDVCVRn(2)) \ - CASE_##op((val), TRCDVCVRn(3)) \ - CASE_##op((val), TRCDVCVRn(4)) \ - CASE_##op((val), TRCDVCVRn(5)) \ - CASE_##op((val), TRCDVCVRn(6)) \ - CASE_##op((val), TRCDVCVRn(7)) \ - CASE_##op((val), TRCDVCMRn(0)) \ - CASE_##op((val), TRCDVCMRn(1)) \ - CASE_##op((val), TRCDVCMRn(2)) \ - CASE_##op((val), TRCDVCMRn(3)) \ - CASE_##op((val), TRCDVCMRn(4)) \ - CASE_##op((val), TRCDVCMRn(5)) \ - CASE_##op((val), TRCDVCMRn(6)) \ - CASE_##op((val), TRCDVCMRn(7)) \ CASE_##op((val), TRCCIDCVRn(0)) \ CASE_##op((val), TRCCIDCVRn(1)) \ CASE_##op((val), TRCCIDCVRn(2)) \ @@ -907,9 +883,6 @@ struct etmv4_save_state { u32 trcviiectlr; u32 trcvissctlr; u32 trcvipcssctlr; - u32 trcvdctlr; - u32 trcvdsacctlr; - u32 trcvdarcctlr; u32 trcseqevr[ETM_MAX_SEQ_STATES]; u32 trcseqrstevr; @@ -982,6 +955,7 @@ struct etmv4_save_state { * @os_unlock: True if access to management registers is allowed. * @instrp0: Tracing of load and store instructions * as P0 elements is supported. + * @q_filt: Q element filtering support, if Q elements are supported. * @trcbb: Indicates if the trace unit supports branch broadcast tracing. * @trccond: If the trace unit supports conditional * instruction tracing. @@ -1045,6 +1019,7 @@ struct etmv4_drvdata { bool boot_enable; bool os_unlock; bool instrp0; + bool q_filt; bool trcbb; bool trccond; bool retstack; diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 767076e079701..30c051055e54b 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -233,6 +233,6 @@ void coresight_set_percpu_sink(int cpu, struct coresight_device *csdev); struct coresight_device *coresight_get_percpu_sink(int cpu); int coresight_enable_source(struct coresight_device *csdev, enum cs_mode mode, void *data); -bool coresight_disable_source(struct coresight_device *csdev, void *data); +void coresight_disable_source(struct coresight_device *csdev, void *data); #endif diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 147d338c191e7..8dad239aba2ce 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -289,6 +289,16 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7e24), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Meteor Lake-S CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xae24), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Meteor Lake-S */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7f26), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { /* Raptor Lake-S */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7a26), @@ -299,6 +309,26 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa76f), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Granite Rapids */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0963), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Granite Rapids SOC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3256), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Sapphire Rapids SOC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3456), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Lunar Lake */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa824), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { /* Alder Lake CPU */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f), diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c index c1b5fd2b89741..4bf04a9778407 100644 --- a/drivers/hwtracing/ptt/hisi_ptt.c +++ b/drivers/hwtracing/ptt/hisi_ptt.c @@ -998,6 +998,9 @@ static int hisi_ptt_pmu_event_init(struct perf_event *event) int ret; u32 val; + if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type) + return -ENOENT; + if (event->cpu < 0) { dev_dbg(event->pmu->dev, "Per-task mode not supported\n"); return -EOPNOTSUPP; @@ -1006,9 +1009,6 @@ static int hisi_ptt_pmu_event_init(struct perf_event *event) if (event->attach_state & PERF_ATTACH_TASK) return -EOPNOTSUPP; - if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type) - return -ENOENT; - ret = hisi_ptt_trace_valid_filter(hisi_ptt, event->attr.config); if (ret < 0) return ret; diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index 534fbefc7f6aa..20895d3915623 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -868,8 +868,11 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data, return -ENOMEM; stm->major = register_chrdev(0, stm_data->name, &stm_fops); - if (stm->major < 0) - goto err_free; + if (stm->major < 0) { + err = stm->major; + vfree(stm); + return err; + } device_initialize(&stm->dev); stm->dev.devt = MKDEV(stm->major, 0); @@ -913,10 +916,8 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data, err_device: unregister_chrdev(stm->major, stm_data->name); - /* matches device_initialize() above */ + /* calls stm_device_release() */ put_device(&stm->dev); -err_free: - vfree(stm); return err; } diff --git a/drivers/i2c/busses/i2c-at91-slave.c b/drivers/i2c/busses/i2c-at91-slave.c index d6eeea5166c04..131a67d9d4a68 100644 --- a/drivers/i2c/busses/i2c-at91-slave.c +++ b/drivers/i2c/busses/i2c-at91-slave.c @@ -106,8 +106,7 @@ static int at91_unreg_slave(struct i2c_client *slave) static u32 at91_twi_func(struct i2c_adapter *adapter) { - return I2C_FUNC_SLAVE | I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL - | I2C_FUNC_SMBUS_READ_BLOCK_DATA; + return I2C_FUNC_SLAVE; } static const struct i2c_algorithm at91_twi_algorithm_slave = { diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index de3f58b60dce5..6f7d753a8197c 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -633,6 +633,7 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id) if (hold_clear) { ctrl_reg &= ~CDNS_I2C_CR_HOLD; + ctrl_reg &= ~CDNS_I2C_CR_CLR_FIFO; /* * In case of Xilinx Zynq SOC, clear the HOLD bit before transfer size * register reaches '0'. This is an IP bug which causes transfer size diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index a7f6f3eafad7d..ae835000fd32a 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -318,7 +318,7 @@ struct dw_i2c_dev { #define AMD_UCSI_INTR_EN 0xd #define TXGBE_TX_FIFO_DEPTH 4 -#define TXGBE_RX_FIFO_DEPTH 0 +#define TXGBE_RX_FIFO_DEPTH 1 struct i2c_dw_semaphore_callbacks { int (*probe)(struct dw_i2c_dev *dev); diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c index 2e079cf20bb5b..78e2c47e3d7da 100644 --- a/drivers/i2c/busses/i2c-designware-slave.c +++ b/drivers/i2c/busses/i2c-designware-slave.c @@ -220,7 +220,7 @@ static const struct i2c_algorithm i2c_dw_algo = { void i2c_dw_configure_slave(struct dw_i2c_dev *dev) { - dev->functionality = I2C_FUNC_SLAVE | DW_IC_DEFAULT_FUNCTIONALITY; + dev->functionality = I2C_FUNC_SLAVE; dev->slave_cfg = DW_IC_CON_RX_FIFO_FULL_HLD_CTRL | DW_IC_CON_RESTART_EN | DW_IC_CON_STOP_DET_IFADDRESSED; diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 678b30e90492a..14473c223cfa7 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -99,6 +99,7 @@ struct lpi2c_imx_struct { __u8 *rx_buf; __u8 *tx_buf; struct completion complete; + unsigned long rate_per; unsigned int msglen; unsigned int delivered; unsigned int block_data; @@ -207,9 +208,7 @@ static int lpi2c_imx_config(struct lpi2c_imx_struct *lpi2c_imx) lpi2c_imx_set_mode(lpi2c_imx); - clk_rate = clk_get_rate(lpi2c_imx->clks[0].clk); - if (!clk_rate) - return -EINVAL; + clk_rate = lpi2c_imx->rate_per; if (lpi2c_imx->mode == HS || lpi2c_imx->mode == ULTRA_FAST) filt = 0; @@ -590,6 +589,20 @@ static int lpi2c_imx_probe(struct platform_device *pdev) if (ret) return ret; + /* + * Lock the parent clock rate to avoid getting parent clock upon + * each transfer + */ + ret = devm_clk_rate_exclusive_get(&pdev->dev, lpi2c_imx->clks[0].clk); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "can't lock I2C peripheral clock rate\n"); + + lpi2c_imx->rate_per = clk_get_rate(lpi2c_imx->clks[0].clk); + if (!lpi2c_imx->rate_per) + return dev_err_probe(&pdev->dev, -EINVAL, + "can't get I2C peripheral clock rate\n"); + pm_runtime_set_autosuspend_delay(&pdev->dev, I2C_PM_TIMEOUT); pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_get_noresume(&pdev->dev); diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index e106af83cef4d..350ccfbe86340 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -442,8 +442,8 @@ static int ocores_init(struct device *dev, struct ocores_i2c *i2c) oc_setreg(i2c, OCI2C_PREHIGH, prescale >> 8); /* Init the device */ - oc_setreg(i2c, OCI2C_CMD, OCI2C_CMD_IACK); oc_setreg(i2c, OCI2C_CONTROL, ctrl | OCI2C_CTRL_EN); + oc_setreg(i2c, OCI2C_CMD, OCI2C_CMD_IACK); return 0; } diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c index bbea521b05dda..a73f5bb9a1645 100644 --- a/drivers/i2c/busses/i2c-synquacer.c +++ b/drivers/i2c/busses/i2c-synquacer.c @@ -550,17 +550,13 @@ static int synquacer_i2c_probe(struct platform_device *pdev) device_property_read_u32(&pdev->dev, "socionext,pclk-rate", &i2c->pclkrate); - i2c->pclk = devm_clk_get(&pdev->dev, "pclk"); - if (PTR_ERR(i2c->pclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; - if (!IS_ERR_OR_NULL(i2c->pclk)) { - dev_dbg(&pdev->dev, "clock source %p\n", i2c->pclk); - - ret = clk_prepare_enable(i2c->pclk); - if (ret) - return dev_err_probe(&pdev->dev, ret, "failed to enable clock\n"); - i2c->pclkrate = clk_get_rate(i2c->pclk); - } + i2c->pclk = devm_clk_get_enabled(&pdev->dev, "pclk"); + if (IS_ERR(i2c->pclk)) + return dev_err_probe(&pdev->dev, PTR_ERR(i2c->pclk), + "failed to get and enable clock\n"); + + dev_dbg(&pdev->dev, "clock source %p\n", i2c->pclk); + i2c->pclkrate = clk_get_rate(i2c->pclk); if (i2c->pclkrate < SYNQUACER_I2C_MIN_CLK_RATE || i2c->pclkrate > SYNQUACER_I2C_MAX_CLK_RATE) @@ -615,8 +611,6 @@ static void synquacer_i2c_remove(struct platform_device *pdev) struct synquacer_i2c *i2c = platform_get_drvdata(pdev); i2c_del_adapter(&i2c->adapter); - if (!IS_ERR(i2c->pclk)) - clk_disable_unprepare(i2c->pclk); }; static const struct of_device_id synquacer_i2c_dt_ids[] __maybe_unused = { diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index d6037a3286690..14ae0cfc325ef 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -445,6 +445,11 @@ static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev) return i2c_find_device_by_fwnode(acpi_fwnode_handle(adev)); } +static struct i2c_adapter *i2c_acpi_find_adapter_by_adev(struct acpi_device *adev) +{ + return i2c_find_adapter_by_fwnode(acpi_fwnode_handle(adev)); +} + static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value, void *arg) { @@ -471,11 +476,17 @@ static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value, break; client = i2c_acpi_find_client_by_adev(adev); - if (!client) - break; + if (client) { + i2c_unregister_device(client); + put_device(&client->dev); + } + + adapter = i2c_acpi_find_adapter_by_adev(adev); + if (adapter) { + acpi_unbind_one(&adapter->dev); + put_device(&adapter->dev); + } - i2c_unregister_device(client); - put_device(&client->dev); break; } diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 3bd48d4b6318f..5e2cefb37e1a4 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2200,13 +2200,18 @@ static int i2c_check_for_quirks(struct i2c_adapter *adap, struct i2c_msg *msgs, * Returns negative errno, else the number of messages executed. * * Adapter lock must be held when calling this function. No debug logging - * takes place. adap->algo->master_xfer existence isn't checked. + * takes place. */ int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { unsigned long orig_jiffies; int ret, try; + if (!adap->algo->master_xfer) { + dev_dbg(&adap->dev, "I2C level transfers not supported\n"); + return -EOPNOTSUPP; + } + if (WARN_ON(!msgs || num < 1)) return -EINVAL; @@ -2273,11 +2278,6 @@ int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { int ret; - if (!adap->algo->master_xfer) { - dev_dbg(&adap->dev, "I2C level transfers not supported\n"); - return -EOPNOTSUPP; - } - /* REVISIT the fault reporting model here is weak: * * - When we get an error after receiving N bytes from a slave, diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index ef5751e91cc9e..276153e10f5a4 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1163,8 +1163,10 @@ static void dw_i3c_master_set_sir_enabled(struct dw_i3c_master *master, global = reg == 0xffffffff; reg &= ~BIT(idx); } else { - global = reg == 0; + bool hj_rejected = !!(readl(master->regs + DEVICE_CTRL) & DEV_CTRL_HOT_JOIN_NACK); + reg |= BIT(idx); + global = (reg == 0xffffffff) && hj_rejected; } writel(reg, master->regs + IBI_SIR_REQ_REJECT); diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index 5ee4db68988e2..bb299ce02cccb 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -415,6 +415,19 @@ static void svc_i3c_master_ibi_work(struct work_struct *work) int ret; mutex_lock(&master->lock); + /* + * IBIWON may be set before SVC_I3C_MCTRL_REQUEST_AUTO_IBI, causing + * readl_relaxed_poll_timeout() to return immediately. Consequently, + * ibitype will be 0 since it was last updated only after the 8th SCL + * cycle, leading to missed client IBI handlers. + * + * A typical scenario is when IBIWON occurs and bus arbitration is lost + * at svc_i3c_master_priv_xfers(). + * + * Clear SVC_I3C_MINT_IBIWON before sending SVC_I3C_MCTRL_REQUEST_AUTO_IBI. + */ + writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS); + /* Acknowledge the incoming interrupt with the AUTOIBI mechanism */ writel(SVC_I3C_MCTRL_REQUEST_AUTO_IBI | SVC_I3C_MCTRL_IBIRESP_AUTO, @@ -429,9 +442,6 @@ static void svc_i3c_master_ibi_work(struct work_struct *work) goto reenable_ibis; } - /* Clear the interrupt status */ - writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS); - status = readl(master->regs + SVC_I3C_MSTATUS); ibitype = SVC_I3C_MSTATUS_IBITYPE(status); ibiaddr = SVC_I3C_MSTATUS_IBIADDR(status); @@ -1080,7 +1090,7 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master, * and yield the above events handler. */ if (SVC_I3C_MSTATUS_IBIWON(reg)) { - ret = -ENXIO; + ret = -EAGAIN; *actual_len = 0; goto emit_stop; } diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig index 52eb46ef84c1b..9c351ffc7bed6 100644 --- a/drivers/iio/Kconfig +++ b/drivers/iio/Kconfig @@ -71,6 +71,15 @@ config IIO_TRIGGERED_EVENT help Provides helper functions for setting up triggered events. +config IIO_BACKEND + tristate + help + Framework to handle complex IIO aggregate devices. The typical + architecture that can make use of this framework is to have one + device as the frontend device which can be "linked" against one or + multiple backend devices. The framework then makes it easy to get + and control such backend devices. + source "drivers/iio/accel/Kconfig" source "drivers/iio/adc/Kconfig" source "drivers/iio/addac/Kconfig" diff --git a/drivers/iio/Makefile b/drivers/iio/Makefile index 9622347a1c1be..0ba0e1521ba4f 100644 --- a/drivers/iio/Makefile +++ b/drivers/iio/Makefile @@ -13,6 +13,7 @@ obj-$(CONFIG_IIO_GTS_HELPER) += industrialio-gts-helper.o obj-$(CONFIG_IIO_SW_DEVICE) += industrialio-sw-device.o obj-$(CONFIG_IIO_SW_TRIGGER) += industrialio-sw-trigger.o obj-$(CONFIG_IIO_TRIGGERED_EVENT) += industrialio-triggered-event.o +obj-$(CONFIG_IIO_BACKEND) += industrialio-backend.o obj-y += accel/ obj-y += adc/ diff --git a/drivers/iio/accel/mxc4005.c b/drivers/iio/accel/mxc4005.c index 82e8d0b390495..49e30b87732f5 100644 --- a/drivers/iio/accel/mxc4005.c +++ b/drivers/iio/accel/mxc4005.c @@ -5,6 +5,7 @@ * Copyright (c) 2014, Intel Corporation. */ +#include #include #include #include @@ -27,11 +28,16 @@ #define MXC4005_REG_ZOUT_UPPER 0x07 #define MXC4005_REG_ZOUT_LOWER 0x08 +#define MXC4005_REG_INT_MASK0 0x0A + #define MXC4005_REG_INT_MASK1 0x0B #define MXC4005_REG_INT_MASK1_BIT_DRDYE 0x01 +#define MXC4005_REG_INT_CLR0 0x00 + #define MXC4005_REG_INT_CLR1 0x01 #define MXC4005_REG_INT_CLR1_BIT_DRDYC 0x01 +#define MXC4005_REG_INT_CLR1_SW_RST 0x10 #define MXC4005_REG_CONTROL 0x0D #define MXC4005_REG_CONTROL_MASK_FSR GENMASK(6, 5) @@ -39,6 +45,9 @@ #define MXC4005_REG_DEVICE_ID 0x0E +/* Datasheet does not specify a reset time, this is a conservative guess */ +#define MXC4005_RESET_TIME_US 2000 + enum mxc4005_axis { AXIS_X, AXIS_Y, @@ -62,6 +71,8 @@ struct mxc4005_data { s64 timestamp __aligned(8); } scan; bool trigger_enabled; + unsigned int control; + unsigned int int_mask1; }; /* @@ -113,7 +124,9 @@ static bool mxc4005_is_readable_reg(struct device *dev, unsigned int reg) static bool mxc4005_is_writeable_reg(struct device *dev, unsigned int reg) { switch (reg) { + case MXC4005_REG_INT_CLR0: case MXC4005_REG_INT_CLR1: + case MXC4005_REG_INT_MASK0: case MXC4005_REG_INT_MASK1: case MXC4005_REG_CONTROL: return true; @@ -330,23 +343,20 @@ static int mxc4005_set_trigger_state(struct iio_trigger *trig, { struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig); struct mxc4005_data *data = iio_priv(indio_dev); + unsigned int val; int ret; mutex_lock(&data->mutex); - if (state) { - ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, - MXC4005_REG_INT_MASK1_BIT_DRDYE); - } else { - ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, - ~MXC4005_REG_INT_MASK1_BIT_DRDYE); - } + val = state ? MXC4005_REG_INT_MASK1_BIT_DRDYE : 0; + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, val); if (ret < 0) { mutex_unlock(&data->mutex); dev_err(data->dev, "failed to update reg_int_mask1"); return ret; } + data->int_mask1 = val; data->trigger_enabled = state; mutex_unlock(&data->mutex); @@ -382,6 +392,21 @@ static int mxc4005_chip_init(struct mxc4005_data *data) dev_dbg(data->dev, "MXC4005 chip id %02x\n", reg); + ret = regmap_write(data->regmap, MXC4005_REG_INT_CLR1, + MXC4005_REG_INT_CLR1_SW_RST); + if (ret < 0) + return dev_err_probe(data->dev, ret, "resetting chip\n"); + + fsleep(MXC4005_RESET_TIME_US); + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK0, 0); + if (ret < 0) + return dev_err_probe(data->dev, ret, "writing INT_MASK0\n"); + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, 0); + if (ret < 0) + return dev_err_probe(data->dev, ret, "writing INT_MASK1\n"); + return 0; } @@ -469,6 +494,58 @@ static int mxc4005_probe(struct i2c_client *client) return devm_iio_device_register(&client->dev, indio_dev); } +static int mxc4005_suspend(struct device *dev) +{ + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct mxc4005_data *data = iio_priv(indio_dev); + int ret; + + /* Save control to restore it on resume */ + ret = regmap_read(data->regmap, MXC4005_REG_CONTROL, &data->control); + if (ret < 0) + dev_err(data->dev, "failed to read reg_control\n"); + + return ret; +} + +static int mxc4005_resume(struct device *dev) +{ + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct mxc4005_data *data = iio_priv(indio_dev); + int ret; + + ret = regmap_write(data->regmap, MXC4005_REG_INT_CLR1, + MXC4005_REG_INT_CLR1_SW_RST); + if (ret) { + dev_err(data->dev, "failed to reset chip: %d\n", ret); + return ret; + } + + fsleep(MXC4005_RESET_TIME_US); + + ret = regmap_write(data->regmap, MXC4005_REG_CONTROL, data->control); + if (ret) { + dev_err(data->dev, "failed to restore control register\n"); + return ret; + } + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK0, 0); + if (ret) { + dev_err(data->dev, "failed to restore interrupt 0 mask\n"); + return ret; + } + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, data->int_mask1); + if (ret) { + dev_err(data->dev, "failed to restore interrupt 1 mask\n"); + return ret; + } + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(mxc4005_pm_ops, mxc4005_suspend, mxc4005_resume); + static const struct acpi_device_id mxc4005_acpi_match[] = { {"MXC4005", 0}, {"MXC6655", 0}, @@ -495,6 +572,7 @@ static struct i2c_driver mxc4005_driver = { .name = MXC4005_DRV_NAME, .acpi_match_table = ACPI_PTR(mxc4005_acpi_match), .of_match_table = mxc4005_of_match, + .pm = pm_sleep_ptr(&mxc4005_pm_ops), }, .probe = mxc4005_probe, .id_table = mxc4005_id, diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 3b73c509bd68e..02a55809cb6ab 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -291,7 +291,7 @@ config AD799X config AD9467 tristate "Analog Devices AD9467 High Speed ADC driver" depends on SPI - depends on ADI_AXI_ADC + select IIO_BACKEND help Say yes here to build support for Analog Devices: * AD9467 16-Bit, 200 MSPS/250 MSPS Analog-to-Digital Converter @@ -309,7 +309,7 @@ config ADI_AXI_ADC select IIO_BUFFER_HW_CONSUMER select IIO_BUFFER_DMAENGINE select REGMAP_MMIO - depends on OF + select IIO_BACKEND help Say yes here to build support for Analog Devices Generic AXI ADC IP core. The IP core is used for interfacing with diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index 6581fce4ba959..13e1bba45beff 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -17,13 +17,12 @@ #include +#include #include #include #include -#include - /* * ADI High-Speed ADC common spi interface registers * See Application-Note AN-877: @@ -102,15 +101,20 @@ #define AD9467_REG_VREF_MASK 0x0F struct ad9467_chip_info { - struct adi_axi_adc_chip_info axi_adc_info; - unsigned int default_output_mode; - unsigned int vref_mask; + const char *name; + unsigned int id; + const struct iio_chan_spec *channels; + unsigned int num_channels; + const unsigned int (*scale_table)[2]; + int num_scales; + unsigned long max_rate; + unsigned int default_output_mode; + unsigned int vref_mask; }; -#define to_ad9467_chip_info(_info) \ - container_of(_info, struct ad9467_chip_info, axi_adc_info) - struct ad9467_state { + const struct ad9467_chip_info *info; + struct iio_backend *back; struct spi_device *spi; struct clk *clk; unsigned int output_mode; @@ -151,10 +155,10 @@ static int ad9467_spi_write(struct spi_device *spi, unsigned int reg, return spi_write(spi, buf, ARRAY_SIZE(buf)); } -static int ad9467_reg_access(struct adi_axi_adc_conv *conv, unsigned int reg, +static int ad9467_reg_access(struct iio_dev *indio_dev, unsigned int reg, unsigned int writeval, unsigned int *readval) { - struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + struct ad9467_state *st = iio_priv(indio_dev); struct spi_device *spi = st->spi; int ret; @@ -191,10 +195,10 @@ static const unsigned int ad9467_scale_table[][2] = { {2300, 8}, {2400, 9}, {2500, 10}, }; -static void __ad9467_get_scale(struct adi_axi_adc_conv *conv, int index, +static void __ad9467_get_scale(struct ad9467_state *st, int index, unsigned int *val, unsigned int *val2) { - const struct adi_axi_adc_chip_info *info = conv->chip_info; + const struct ad9467_chip_info *info = st->info; const struct iio_chan_spec *chan = &info->channels[0]; unsigned int tmp; @@ -221,60 +225,52 @@ static void __ad9467_get_scale(struct adi_axi_adc_conv *conv, int index, } static const struct iio_chan_spec ad9434_channels[] = { - AD9467_CHAN(0, 0, 12, 'S'), + AD9467_CHAN(0, 0, 12, 's'), }; static const struct iio_chan_spec ad9467_channels[] = { - AD9467_CHAN(0, 0, 16, 'S'), + AD9467_CHAN(0, 0, 16, 's'), }; static const struct ad9467_chip_info ad9467_chip_tbl = { - .axi_adc_info = { - .name = "ad9467", - .id = CHIPID_AD9467, - .max_rate = 250000000UL, - .scale_table = ad9467_scale_table, - .num_scales = ARRAY_SIZE(ad9467_scale_table), - .channels = ad9467_channels, - .num_channels = ARRAY_SIZE(ad9467_channels), - }, + .name = "ad9467", + .id = CHIPID_AD9467, + .max_rate = 250000000UL, + .scale_table = ad9467_scale_table, + .num_scales = ARRAY_SIZE(ad9467_scale_table), + .channels = ad9467_channels, + .num_channels = ARRAY_SIZE(ad9467_channels), .default_output_mode = AD9467_DEF_OUTPUT_MODE, .vref_mask = AD9467_REG_VREF_MASK, }; static const struct ad9467_chip_info ad9434_chip_tbl = { - .axi_adc_info = { - .name = "ad9434", - .id = CHIPID_AD9434, - .max_rate = 500000000UL, - .scale_table = ad9434_scale_table, - .num_scales = ARRAY_SIZE(ad9434_scale_table), - .channels = ad9434_channels, - .num_channels = ARRAY_SIZE(ad9434_channels), - }, + .name = "ad9434", + .id = CHIPID_AD9434, + .max_rate = 500000000UL, + .scale_table = ad9434_scale_table, + .num_scales = ARRAY_SIZE(ad9434_scale_table), + .channels = ad9434_channels, + .num_channels = ARRAY_SIZE(ad9434_channels), .default_output_mode = AD9434_DEF_OUTPUT_MODE, .vref_mask = AD9434_REG_VREF_MASK, }; static const struct ad9467_chip_info ad9265_chip_tbl = { - .axi_adc_info = { - .name = "ad9265", - .id = CHIPID_AD9265, - .max_rate = 125000000UL, - .scale_table = ad9265_scale_table, - .num_scales = ARRAY_SIZE(ad9265_scale_table), - .channels = ad9467_channels, - .num_channels = ARRAY_SIZE(ad9467_channels), - }, + .name = "ad9265", + .id = CHIPID_AD9265, + .max_rate = 125000000UL, + .scale_table = ad9265_scale_table, + .num_scales = ARRAY_SIZE(ad9265_scale_table), + .channels = ad9467_channels, + .num_channels = ARRAY_SIZE(ad9467_channels), .default_output_mode = AD9265_DEF_OUTPUT_MODE, .vref_mask = AD9265_REG_VREF_MASK, }; -static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2) +static int ad9467_get_scale(struct ad9467_state *st, int *val, int *val2) { - const struct adi_axi_adc_chip_info *info = conv->chip_info; - const struct ad9467_chip_info *info1 = to_ad9467_chip_info(info); - struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + const struct ad9467_chip_info *info = st->info; unsigned int i, vref_val; int ret; @@ -282,7 +278,7 @@ static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2) if (ret < 0) return ret; - vref_val = ret & info1->vref_mask; + vref_val = ret & info->vref_mask; for (i = 0; i < info->num_scales; i++) { if (vref_val == info->scale_table[i][1]) @@ -292,15 +288,14 @@ static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2) if (i == info->num_scales) return -ERANGE; - __ad9467_get_scale(conv, i, val, val2); + __ad9467_get_scale(st, i, val, val2); return IIO_VAL_INT_PLUS_MICRO; } -static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2) +static int ad9467_set_scale(struct ad9467_state *st, int val, int val2) { - const struct adi_axi_adc_chip_info *info = conv->chip_info; - struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + const struct ad9467_chip_info *info = st->info; unsigned int scale_val[2]; unsigned int i; int ret; @@ -309,7 +304,7 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2) return -EINVAL; for (i = 0; i < info->num_scales; i++) { - __ad9467_get_scale(conv, i, &scale_val[0], &scale_val[1]); + __ad9467_get_scale(st, i, &scale_val[0], &scale_val[1]); if (scale_val[0] != val || scale_val[1] != val2) continue; @@ -326,15 +321,15 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2) return -EINVAL; } -static int ad9467_read_raw(struct adi_axi_adc_conv *conv, +static int ad9467_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val, int *val2, long m) { - struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + struct ad9467_state *st = iio_priv(indio_dev); switch (m) { case IIO_CHAN_INFO_SCALE: - return ad9467_get_scale(conv, val, val2); + return ad9467_get_scale(st, val, val2); case IIO_CHAN_INFO_SAMP_FREQ: *val = clk_get_rate(st->clk); @@ -344,17 +339,17 @@ static int ad9467_read_raw(struct adi_axi_adc_conv *conv, } } -static int ad9467_write_raw(struct adi_axi_adc_conv *conv, +static int ad9467_write_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int val, int val2, long mask) { - const struct adi_axi_adc_chip_info *info = conv->chip_info; - struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + struct ad9467_state *st = iio_priv(indio_dev); + const struct ad9467_chip_info *info = st->info; long r_clk; switch (mask) { case IIO_CHAN_INFO_SCALE: - return ad9467_set_scale(conv, val, val2); + return ad9467_set_scale(st, val, val2); case IIO_CHAN_INFO_SAMP_FREQ: r_clk = clk_round_rate(st->clk, val); if (r_clk < 0 || r_clk > info->max_rate) { @@ -369,13 +364,13 @@ static int ad9467_write_raw(struct adi_axi_adc_conv *conv, } } -static int ad9467_read_avail(struct adi_axi_adc_conv *conv, +static int ad9467_read_avail(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, const int **vals, int *type, int *length, long mask) { - const struct adi_axi_adc_chip_info *info = conv->chip_info; - struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + struct ad9467_state *st = iio_priv(indio_dev); + const struct ad9467_chip_info *info = st->info; switch (mask) { case IIO_CHAN_INFO_SCALE: @@ -389,6 +384,33 @@ static int ad9467_read_avail(struct adi_axi_adc_conv *conv, } } +static int ad9467_update_scan_mode(struct iio_dev *indio_dev, + const unsigned long *scan_mask) +{ + struct ad9467_state *st = iio_priv(indio_dev); + unsigned int c; + int ret; + + for (c = 0; c < st->info->num_channels; c++) { + if (test_bit(c, scan_mask)) + ret = iio_backend_chan_enable(st->back, c); + else + ret = iio_backend_chan_disable(st->back, c); + if (ret) + return ret; + } + + return 0; +} + +static const struct iio_info ad9467_info = { + .read_raw = ad9467_read_raw, + .write_raw = ad9467_write_raw, + .update_scan_mode = ad9467_update_scan_mode, + .debugfs_reg_access = ad9467_reg_access, + .read_avail = ad9467_read_avail, +}; + static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode) { int ret; @@ -401,10 +423,9 @@ static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode) AN877_ADC_TRANSFER_SYNC); } -static int ad9467_scale_fill(struct adi_axi_adc_conv *conv) +static int ad9467_scale_fill(struct ad9467_state *st) { - const struct adi_axi_adc_chip_info *info = conv->chip_info; - struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + const struct ad9467_chip_info *info = st->info; unsigned int i, val1, val2; st->scales = devm_kmalloc_array(&st->spi->dev, info->num_scales, @@ -413,7 +434,7 @@ static int ad9467_scale_fill(struct adi_axi_adc_conv *conv) return -ENOMEM; for (i = 0; i < info->num_scales; i++) { - __ad9467_get_scale(conv, i, &val1, &val2); + __ad9467_get_scale(st, i, &val1, &val2); st->scales[i][0] = val1; st->scales[i][1] = val2; } @@ -421,11 +442,27 @@ static int ad9467_scale_fill(struct adi_axi_adc_conv *conv) return 0; } -static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv) +static int ad9467_setup(struct ad9467_state *st) { - struct ad9467_state *st = adi_axi_adc_conv_priv(conv); + struct iio_backend_data_fmt data = { + .sign_extend = true, + .enable = true, + }; + unsigned int c, mode; + int ret; + + mode = st->info->default_output_mode | AN877_ADC_OUTPUT_MODE_TWOS_COMPLEMENT; + ret = ad9467_outputmode_set(st->spi, mode); + if (ret) + return ret; - return ad9467_outputmode_set(st->spi, st->output_mode); + for (c = 0; c < st->info->num_channels; c++) { + ret = iio_backend_data_format_set(st->back, c, &data); + if (ret) + return ret; + } + + return 0; } static int ad9467_reset(struct device *dev) @@ -443,25 +480,65 @@ static int ad9467_reset(struct device *dev) return 0; } +static int ad9467_iio_backend_get(struct ad9467_state *st) +{ + struct device *dev = &st->spi->dev; + struct device_node *__back; + + st->back = devm_iio_backend_get(dev, NULL); + if (!IS_ERR(st->back)) + return 0; + /* If not found, don't error out as we might have legacy DT property */ + if (PTR_ERR(st->back) != -ENOENT) + return PTR_ERR(st->back); + + /* + * if we don't get the backend using the normal API's, use the legacy + * 'adi,adc-dev' property. So we get all nodes with that property, and + * look for the one pointing at us. Then we directly lookup that fwnode + * on the backend list of registered devices. This is done so we don't + * make io-backends mandatory which would break DT ABI. + */ + for_each_node_with_property(__back, "adi,adc-dev") { + struct device_node *__me; + + __me = of_parse_phandle(__back, "adi,adc-dev", 0); + if (!__me) + continue; + + if (!device_match_of_node(dev, __me)) { + of_node_put(__me); + continue; + } + + of_node_put(__me); + st->back = __devm_iio_backend_get_from_fwnode_lookup(dev, + of_fwnode_handle(__back)); + of_node_put(__back); + return PTR_ERR_OR_ZERO(st->back); + } + + return -ENODEV; +} + static int ad9467_probe(struct spi_device *spi) { - const struct ad9467_chip_info *info; - struct adi_axi_adc_conv *conv; + struct iio_dev *indio_dev; struct ad9467_state *st; unsigned int id; int ret; - info = spi_get_device_match_data(spi); - if (!info) - return -ENODEV; - - conv = devm_adi_axi_adc_conv_register(&spi->dev, sizeof(*st)); - if (IS_ERR(conv)) - return PTR_ERR(conv); + indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st)); + if (!indio_dev) + return -ENOMEM; - st = adi_axi_adc_conv_priv(conv); + st = iio_priv(indio_dev); st->spi = spi; + st->info = spi_get_device_match_data(spi); + if (!st->info) + return -ENODEV; + st->clk = devm_clk_get_enabled(&spi->dev, "adc-clk"); if (IS_ERR(st->clk)) return PTR_ERR(st->clk); @@ -475,29 +552,39 @@ static int ad9467_probe(struct spi_device *spi) if (ret) return ret; - conv->chip_info = &info->axi_adc_info; - - ret = ad9467_scale_fill(conv); + ret = ad9467_scale_fill(st); if (ret) return ret; id = ad9467_spi_read(spi, AN877_ADC_REG_CHIP_ID); - if (id != conv->chip_info->id) { + if (id != st->info->id) { dev_err(&spi->dev, "Mismatch CHIP_ID, got 0x%X, expected 0x%X\n", - id, conv->chip_info->id); + id, st->info->id); return -ENODEV; } - conv->reg_access = ad9467_reg_access; - conv->write_raw = ad9467_write_raw; - conv->read_raw = ad9467_read_raw; - conv->read_avail = ad9467_read_avail; - conv->preenable_setup = ad9467_preenable_setup; + indio_dev->name = st->info->name; + indio_dev->channels = st->info->channels; + indio_dev->num_channels = st->info->num_channels; + indio_dev->info = &ad9467_info; - st->output_mode = info->default_output_mode | - AN877_ADC_OUTPUT_MODE_TWOS_COMPLEMENT; + ret = ad9467_iio_backend_get(st); + if (ret) + return ret; - return 0; + ret = devm_iio_backend_request_buffer(&spi->dev, st->back, indio_dev); + if (ret) + return ret; + + ret = devm_iio_backend_enable(&spi->dev, st->back); + if (ret) + return ret; + + ret = ad9467_setup(st); + if (ret) + return ret; + + return devm_iio_device_register(&spi->dev, indio_dev); } static const struct of_device_id ad9467_of_match[] = { @@ -529,4 +616,4 @@ module_spi_driver(ad9467_driver); MODULE_AUTHOR("Michael Hennerich "); MODULE_DESCRIPTION("Analog Devices AD9467 ADC driver"); MODULE_LICENSE("GPL v2"); -MODULE_IMPORT_NS(IIO_ADI_AXI); +MODULE_IMPORT_NS(IIO_BACKEND); diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c index c247ff1541d28..e3b2158829416 100644 --- a/drivers/iio/adc/adi-axi-adc.c +++ b/drivers/iio/adc/adi-axi-adc.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -17,13 +18,12 @@ #include #include -#include -#include -#include -#include - #include -#include + +#include +#include +#include +#include /* * Register definitions: @@ -44,6 +44,7 @@ #define ADI_AXI_REG_CHAN_CTRL_PN_SEL_OWR BIT(10) #define ADI_AXI_REG_CHAN_CTRL_IQCOR_EN BIT(9) #define ADI_AXI_REG_CHAN_CTRL_DCFILT_EN BIT(8) +#define ADI_AXI_REG_CHAN_CTRL_FMT_MASK GENMASK(6, 4) #define ADI_AXI_REG_CHAN_CTRL_FMT_SIGNEXT BIT(6) #define ADI_AXI_REG_CHAN_CTRL_FMT_TYPE BIT(5) #define ADI_AXI_REG_CHAN_CTRL_FMT_EN BIT(4) @@ -55,286 +56,100 @@ ADI_AXI_REG_CHAN_CTRL_FMT_EN | \ ADI_AXI_REG_CHAN_CTRL_ENABLE) -struct adi_axi_adc_core_info { - unsigned int version; -}; - struct adi_axi_adc_state { - struct mutex lock; - - struct adi_axi_adc_client *client; struct regmap *regmap; -}; - -struct adi_axi_adc_client { - struct list_head entry; - struct adi_axi_adc_conv conv; - struct adi_axi_adc_state *state; struct device *dev; - const struct adi_axi_adc_core_info *info; }; -static LIST_HEAD(registered_clients); -static DEFINE_MUTEX(registered_clients_lock); - -static struct adi_axi_adc_client *conv_to_client(struct adi_axi_adc_conv *conv) -{ - return container_of(conv, struct adi_axi_adc_client, conv); -} - -void *adi_axi_adc_conv_priv(struct adi_axi_adc_conv *conv) -{ - struct adi_axi_adc_client *cl = conv_to_client(conv); - - return (char *)cl + ALIGN(sizeof(struct adi_axi_adc_client), - IIO_DMA_MINALIGN); -} -EXPORT_SYMBOL_NS_GPL(adi_axi_adc_conv_priv, IIO_ADI_AXI); - -static int adi_axi_adc_config_dma_buffer(struct device *dev, - struct iio_dev *indio_dev) -{ - const char *dma_name; - - if (!device_property_present(dev, "dmas")) - return 0; - - if (device_property_read_string(dev, "dma-names", &dma_name)) - dma_name = "rx"; - - return devm_iio_dmaengine_buffer_setup(indio_dev->dev.parent, - indio_dev, dma_name); -} - -static int adi_axi_adc_read_raw(struct iio_dev *indio_dev, - struct iio_chan_spec const *chan, - int *val, int *val2, long mask) +static int axi_adc_enable(struct iio_backend *back) { - struct adi_axi_adc_state *st = iio_priv(indio_dev); - struct adi_axi_adc_conv *conv = &st->client->conv; - - if (!conv->read_raw) - return -EOPNOTSUPP; - - return conv->read_raw(conv, chan, val, val2, mask); -} - -static int adi_axi_adc_write_raw(struct iio_dev *indio_dev, - struct iio_chan_spec const *chan, - int val, int val2, long mask) -{ - struct adi_axi_adc_state *st = iio_priv(indio_dev); - struct adi_axi_adc_conv *conv = &st->client->conv; - - if (!conv->write_raw) - return -EOPNOTSUPP; - - return conv->write_raw(conv, chan, val, val2, mask); -} - -static int adi_axi_adc_read_avail(struct iio_dev *indio_dev, - struct iio_chan_spec const *chan, - const int **vals, int *type, int *length, - long mask) -{ - struct adi_axi_adc_state *st = iio_priv(indio_dev); - struct adi_axi_adc_conv *conv = &st->client->conv; - - if (!conv->read_avail) - return -EOPNOTSUPP; - - return conv->read_avail(conv, chan, vals, type, length, mask); -} - -static int adi_axi_adc_update_scan_mode(struct iio_dev *indio_dev, - const unsigned long *scan_mask) -{ - struct adi_axi_adc_state *st = iio_priv(indio_dev); - struct adi_axi_adc_conv *conv = &st->client->conv; - unsigned int i; + struct adi_axi_adc_state *st = iio_backend_get_priv(back); int ret; - for (i = 0; i < conv->chip_info->num_channels; i++) { - if (test_bit(i, scan_mask)) - ret = regmap_set_bits(st->regmap, - ADI_AXI_REG_CHAN_CTRL(i), - ADI_AXI_REG_CHAN_CTRL_ENABLE); - else - ret = regmap_clear_bits(st->regmap, - ADI_AXI_REG_CHAN_CTRL(i), - ADI_AXI_REG_CHAN_CTRL_ENABLE); - if (ret) - return ret; - } - - return 0; -} - -static struct adi_axi_adc_conv *adi_axi_adc_conv_register(struct device *dev, - size_t sizeof_priv) -{ - struct adi_axi_adc_client *cl; - size_t alloc_size; - - alloc_size = ALIGN(sizeof(struct adi_axi_adc_client), IIO_DMA_MINALIGN); - if (sizeof_priv) - alloc_size += ALIGN(sizeof_priv, IIO_DMA_MINALIGN); - - cl = kzalloc(alloc_size, GFP_KERNEL); - if (!cl) - return ERR_PTR(-ENOMEM); - - mutex_lock(®istered_clients_lock); - - cl->dev = get_device(dev); - - list_add_tail(&cl->entry, ®istered_clients); - - mutex_unlock(®istered_clients_lock); + ret = regmap_set_bits(st->regmap, ADI_AXI_REG_RSTN, + ADI_AXI_REG_RSTN_MMCM_RSTN); + if (ret) + return ret; - return &cl->conv; + fsleep(10000); + return regmap_set_bits(st->regmap, ADI_AXI_REG_RSTN, + ADI_AXI_REG_RSTN_RSTN | ADI_AXI_REG_RSTN_MMCM_RSTN); } -static void adi_axi_adc_conv_unregister(struct adi_axi_adc_conv *conv) +static void axi_adc_disable(struct iio_backend *back) { - struct adi_axi_adc_client *cl = conv_to_client(conv); - - mutex_lock(®istered_clients_lock); - - list_del(&cl->entry); - put_device(cl->dev); - - mutex_unlock(®istered_clients_lock); + struct adi_axi_adc_state *st = iio_backend_get_priv(back); - kfree(cl); + regmap_write(st->regmap, ADI_AXI_REG_RSTN, 0); } -static void devm_adi_axi_adc_conv_release(void *conv) +static int axi_adc_data_format_set(struct iio_backend *back, unsigned int chan, + const struct iio_backend_data_fmt *data) { - adi_axi_adc_conv_unregister(conv); + struct adi_axi_adc_state *st = iio_backend_get_priv(back); + u32 val; + + if (!data->enable) + return regmap_clear_bits(st->regmap, + ADI_AXI_REG_CHAN_CTRL(chan), + ADI_AXI_REG_CHAN_CTRL_FMT_EN); + + val = FIELD_PREP(ADI_AXI_REG_CHAN_CTRL_FMT_EN, true); + if (data->sign_extend) + val |= FIELD_PREP(ADI_AXI_REG_CHAN_CTRL_FMT_SIGNEXT, true); + if (data->type == IIO_BACKEND_OFFSET_BINARY) + val |= FIELD_PREP(ADI_AXI_REG_CHAN_CTRL_FMT_TYPE, true); + + return regmap_update_bits(st->regmap, ADI_AXI_REG_CHAN_CTRL(chan), + ADI_AXI_REG_CHAN_CTRL_FMT_MASK, val); } -struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev, - size_t sizeof_priv) +static int axi_adc_chan_enable(struct iio_backend *back, unsigned int chan) { - struct adi_axi_adc_conv *conv; - int ret; - - conv = adi_axi_adc_conv_register(dev, sizeof_priv); - if (IS_ERR(conv)) - return conv; - - ret = devm_add_action_or_reset(dev, devm_adi_axi_adc_conv_release, - conv); - if (ret) - return ERR_PTR(ret); + struct adi_axi_adc_state *st = iio_backend_get_priv(back); - return conv; + return regmap_set_bits(st->regmap, ADI_AXI_REG_CHAN_CTRL(chan), + ADI_AXI_REG_CHAN_CTRL_ENABLE); } -EXPORT_SYMBOL_NS_GPL(devm_adi_axi_adc_conv_register, IIO_ADI_AXI); - -static const struct iio_info adi_axi_adc_info = { - .read_raw = &adi_axi_adc_read_raw, - .write_raw = &adi_axi_adc_write_raw, - .update_scan_mode = &adi_axi_adc_update_scan_mode, - .read_avail = &adi_axi_adc_read_avail, -}; -static const struct adi_axi_adc_core_info adi_axi_adc_10_0_a_info = { - .version = ADI_AXI_PCORE_VER(10, 0, 'a'), -}; - -static struct adi_axi_adc_client *adi_axi_adc_attach_client(struct device *dev) +static int axi_adc_chan_disable(struct iio_backend *back, unsigned int chan) { - const struct adi_axi_adc_core_info *info; - struct adi_axi_adc_client *cl; - struct device_node *cln; - - info = of_device_get_match_data(dev); - if (!info) - return ERR_PTR(-ENODEV); - - cln = of_parse_phandle(dev->of_node, "adi,adc-dev", 0); - if (!cln) { - dev_err(dev, "No 'adi,adc-dev' node defined\n"); - return ERR_PTR(-ENODEV); - } + struct adi_axi_adc_state *st = iio_backend_get_priv(back); - mutex_lock(®istered_clients_lock); - - list_for_each_entry(cl, ®istered_clients, entry) { - if (!cl->dev) - continue; - - if (cl->dev->of_node != cln) - continue; - - if (!try_module_get(cl->dev->driver->owner)) { - mutex_unlock(®istered_clients_lock); - of_node_put(cln); - return ERR_PTR(-ENODEV); - } - - get_device(cl->dev); - cl->info = info; - mutex_unlock(®istered_clients_lock); - of_node_put(cln); - return cl; - } - - mutex_unlock(®istered_clients_lock); - of_node_put(cln); - - return ERR_PTR(-EPROBE_DEFER); + return regmap_clear_bits(st->regmap, ADI_AXI_REG_CHAN_CTRL(chan), + ADI_AXI_REG_CHAN_CTRL_ENABLE); } -static int adi_axi_adc_setup_channels(struct device *dev, - struct adi_axi_adc_state *st) +static struct iio_buffer *axi_adc_request_buffer(struct iio_backend *back, + struct iio_dev *indio_dev) { - struct adi_axi_adc_conv *conv = &st->client->conv; - int i, ret; + struct adi_axi_adc_state *st = iio_backend_get_priv(back); + struct iio_buffer *buffer; + const char *dma_name; + int ret; - if (conv->preenable_setup) { - ret = conv->preenable_setup(conv); - if (ret) - return ret; - } + if (device_property_read_string(st->dev, "dma-names", &dma_name)) + dma_name = "rx"; - for (i = 0; i < conv->chip_info->num_channels; i++) { - ret = regmap_write(st->regmap, ADI_AXI_REG_CHAN_CTRL(i), - ADI_AXI_REG_CHAN_CTRL_DEFAULTS); - if (ret) - return ret; + buffer = iio_dmaengine_buffer_alloc(st->dev, dma_name); + if (IS_ERR(buffer)) { + dev_err(st->dev, "Could not get DMA buffer, %ld\n", + PTR_ERR(buffer)); + return ERR_CAST(buffer); } - return 0; -} - -static int axi_adc_reset(struct adi_axi_adc_state *st) -{ - int ret; - - ret = regmap_write(st->regmap, ADI_AXI_REG_RSTN, 0); - if (ret) - return ret; - - mdelay(10); - ret = regmap_write(st->regmap, ADI_AXI_REG_RSTN, - ADI_AXI_REG_RSTN_MMCM_RSTN); + indio_dev->modes |= INDIO_BUFFER_HARDWARE; + ret = iio_device_attach_buffer(indio_dev, buffer); if (ret) - return ret; + return ERR_PTR(ret); - mdelay(10); - return regmap_write(st->regmap, ADI_AXI_REG_RSTN, - ADI_AXI_REG_RSTN_RSTN | ADI_AXI_REG_RSTN_MMCM_RSTN); + return buffer; } -static void adi_axi_adc_cleanup(void *data) +static void axi_adc_free_buffer(struct iio_backend *back, + struct iio_buffer *buffer) { - struct adi_axi_adc_client *cl = data; - - put_device(cl->dev); - module_put(cl->dev->driver->owner); + iio_dmaengine_buffer_free(buffer); } static const struct regmap_config axi_adc_regmap_config = { @@ -344,45 +159,52 @@ static const struct regmap_config axi_adc_regmap_config = { .max_register = 0x0800, }; +static const struct iio_backend_ops adi_axi_adc_generic = { + .enable = axi_adc_enable, + .disable = axi_adc_disable, + .data_format_set = axi_adc_data_format_set, + .chan_enable = axi_adc_chan_enable, + .chan_disable = axi_adc_chan_disable, + .request_buffer = axi_adc_request_buffer, + .free_buffer = axi_adc_free_buffer, +}; + static int adi_axi_adc_probe(struct platform_device *pdev) { - struct adi_axi_adc_conv *conv; - struct iio_dev *indio_dev; - struct adi_axi_adc_client *cl; + const unsigned int *expected_ver; struct adi_axi_adc_state *st; void __iomem *base; unsigned int ver; + struct clk *clk; int ret; - cl = adi_axi_adc_attach_client(&pdev->dev); - if (IS_ERR(cl)) - return PTR_ERR(cl); - - ret = devm_add_action_or_reset(&pdev->dev, adi_axi_adc_cleanup, cl); - if (ret) - return ret; - - indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*st)); - if (indio_dev == NULL) + st = devm_kzalloc(&pdev->dev, sizeof(*st), GFP_KERNEL); + if (!st) return -ENOMEM; - st = iio_priv(indio_dev); - st->client = cl; - cl->state = st; - mutex_init(&st->lock); - base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) return PTR_ERR(base); + st->dev = &pdev->dev; st->regmap = devm_regmap_init_mmio(&pdev->dev, base, &axi_adc_regmap_config); if (IS_ERR(st->regmap)) return PTR_ERR(st->regmap); - conv = &st->client->conv; + expected_ver = device_get_match_data(&pdev->dev); + if (!expected_ver) + return -ENODEV; - ret = axi_adc_reset(st); + clk = devm_clk_get_enabled(&pdev->dev, NULL); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + /* + * Force disable the core. Up to the frontend to enable us. And we can + * still read/write registers... + */ + ret = regmap_write(st->regmap, ADI_AXI_REG_RSTN, 0); if (ret) return ret; @@ -390,33 +212,19 @@ static int adi_axi_adc_probe(struct platform_device *pdev) if (ret) return ret; - if (cl->info->version > ver) { + if (ADI_AXI_PCORE_VER_MAJOR(ver) != ADI_AXI_PCORE_VER_MAJOR(*expected_ver)) { dev_err(&pdev->dev, - "IP core version is too old. Expected %d.%.2d.%c, Reported %d.%.2d.%c\n", - ADI_AXI_PCORE_VER_MAJOR(cl->info->version), - ADI_AXI_PCORE_VER_MINOR(cl->info->version), - ADI_AXI_PCORE_VER_PATCH(cl->info->version), + "Major version mismatch. Expected %d.%.2d.%c, Reported %d.%.2d.%c\n", + ADI_AXI_PCORE_VER_MAJOR(*expected_ver), + ADI_AXI_PCORE_VER_MINOR(*expected_ver), + ADI_AXI_PCORE_VER_PATCH(*expected_ver), ADI_AXI_PCORE_VER_MAJOR(ver), ADI_AXI_PCORE_VER_MINOR(ver), ADI_AXI_PCORE_VER_PATCH(ver)); return -ENODEV; } - indio_dev->info = &adi_axi_adc_info; - indio_dev->name = "adi-axi-adc"; - indio_dev->modes = INDIO_DIRECT_MODE; - indio_dev->num_channels = conv->chip_info->num_channels; - indio_dev->channels = conv->chip_info->channels; - - ret = adi_axi_adc_config_dma_buffer(&pdev->dev, indio_dev); - if (ret) - return ret; - - ret = adi_axi_adc_setup_channels(&pdev->dev, st); - if (ret) - return ret; - - ret = devm_iio_device_register(&pdev->dev, indio_dev); + ret = devm_iio_backend_register(&pdev->dev, &adi_axi_adc_generic, st); if (ret) return ret; @@ -428,6 +236,8 @@ static int adi_axi_adc_probe(struct platform_device *pdev) return 0; } +static unsigned int adi_axi_adc_10_0_a_info = ADI_AXI_PCORE_VER(10, 0, 'a'); + /* Match table for of_platform binding */ static const struct of_device_id adi_axi_adc_of_match[] = { { .compatible = "adi,axi-adc-10.0.a", .data = &adi_axi_adc_10_0_a_info }, @@ -447,3 +257,5 @@ module_platform_driver(adi_axi_adc_driver); MODULE_AUTHOR("Michael Hennerich "); MODULE_DESCRIPTION("Analog Devices Generic AXI ADC IP core driver"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_DMAENGINE_BUFFER); +MODULE_IMPORT_NS(IIO_BACKEND); diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c index dd94667a623bd..1c0042fbbb548 100644 --- a/drivers/iio/adc/rockchip_saradc.c +++ b/drivers/iio/adc/rockchip_saradc.c @@ -52,7 +52,7 @@ #define SARADC2_START BIT(4) #define SARADC2_SINGLE_MODE BIT(5) -#define SARADC2_CONV_CHANNELS GENMASK(15, 0) +#define SARADC2_CONV_CHANNELS GENMASK(3, 0) struct rockchip_saradc; @@ -102,12 +102,12 @@ static void rockchip_saradc_start_v2(struct rockchip_saradc *info, int chn) writel_relaxed(0xc, info->regs + SARADC_T_DAS_SOC); writel_relaxed(0x20, info->regs + SARADC_T_PD_SOC); val = FIELD_PREP(SARADC2_EN_END_INT, 1); - val |= val << 16; + val |= SARADC2_EN_END_INT << 16; writel_relaxed(val, info->regs + SARADC2_END_INT_EN); val = FIELD_PREP(SARADC2_START, 1) | FIELD_PREP(SARADC2_SINGLE_MODE, 1) | FIELD_PREP(SARADC2_CONV_CHANNELS, chn); - val |= val << 16; + val |= (SARADC2_START | SARADC2_SINGLE_MODE | SARADC2_CONV_CHANNELS) << 16; writel(val, info->regs + SARADC2_CONV_CON); } diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index b5d3c9cea5c4e..283c207571064 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -2234,6 +2234,7 @@ static int stm32_adc_generic_chan_init(struct iio_dev *indio_dev, if (vin[0] != val || vin[1] >= adc_info->max_channels) { dev_err(&indio_dev->dev, "Invalid channel in%d-in%d\n", vin[0], vin[1]); + ret = -EINVAL; goto err; } } else if (ret != -EINVAL) { diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c index 5f85ba38e6f6e..0d53c0a07b0d6 100644 --- a/drivers/iio/buffer/industrialio-buffer-dmaengine.c +++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c @@ -159,7 +159,7 @@ static const struct iio_dev_attr *iio_dmaengine_buffer_attrs[] = { * Once done using the buffer iio_dmaengine_buffer_free() should be used to * release it. */ -static struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, +struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, const char *channel) { struct dmaengine_buffer *dmaengine_buffer; @@ -210,6 +210,7 @@ static struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, kfree(dmaengine_buffer); return ERR_PTR(ret); } +EXPORT_SYMBOL_NS_GPL(iio_dmaengine_buffer_alloc, IIO_DMAENGINE_BUFFER); /** * iio_dmaengine_buffer_free() - Free dmaengine buffer @@ -217,7 +218,7 @@ static struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, * * Frees a buffer previously allocated with iio_dmaengine_buffer_alloc(). */ -static void iio_dmaengine_buffer_free(struct iio_buffer *buffer) +void iio_dmaengine_buffer_free(struct iio_buffer *buffer) { struct dmaengine_buffer *dmaengine_buffer = iio_buffer_to_dmaengine_buffer(buffer); @@ -227,6 +228,7 @@ static void iio_dmaengine_buffer_free(struct iio_buffer *buffer) iio_buffer_put(buffer); } +EXPORT_SYMBOL_NS_GPL(iio_dmaengine_buffer_free, IIO_DMAENGINE_BUFFER); static void __devm_iio_dmaengine_buffer_free(void *buffer) { @@ -288,7 +290,7 @@ int devm_iio_dmaengine_buffer_setup(struct device *dev, return iio_device_attach_buffer(indio_dev, buffer); } -EXPORT_SYMBOL_GPL(devm_iio_dmaengine_buffer_setup); +EXPORT_SYMBOL_NS_GPL(devm_iio_dmaengine_buffer_setup, IIO_DMAENGINE_BUFFER); MODULE_AUTHOR("Lars-Peter Clausen "); MODULE_DESCRIPTION("DMA buffer for the IIO framework"); diff --git a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c index 03823ee57f598..7b19c94ef87d9 100644 --- a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c +++ b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c @@ -60,11 +60,15 @@ EXPORT_SYMBOL_NS_GPL(inv_sensors_timestamp_init, IIO_INV_SENSORS_TIMESTAMP); int inv_sensors_timestamp_update_odr(struct inv_sensors_timestamp *ts, uint32_t period, bool fifo) { + uint32_t mult; + /* when FIFO is on, prevent odr change if one is already pending */ if (fifo && ts->new_mult != 0) return -EAGAIN; - ts->new_mult = period / ts->chip.clock_period; + mult = period / ts->chip.clock_period; + if (mult != ts->mult) + ts->new_mult = mult; return 0; } @@ -101,6 +105,9 @@ static bool inv_update_chip_period(struct inv_sensors_timestamp *ts, static void inv_align_timestamp_it(struct inv_sensors_timestamp *ts) { + const int64_t period_min = ts->min_period * ts->mult; + const int64_t period_max = ts->max_period * ts->mult; + int64_t add_max, sub_max; int64_t delta, jitter; int64_t adjust; @@ -108,11 +115,13 @@ static void inv_align_timestamp_it(struct inv_sensors_timestamp *ts) delta = ts->it.lo - ts->timestamp; /* adjust timestamp while respecting jitter */ + add_max = period_max - (int64_t)ts->period; + sub_max = period_min - (int64_t)ts->period; jitter = INV_SENSORS_TIMESTAMP_JITTER((int64_t)ts->period, ts->chip.jitter); if (delta > jitter) - adjust = jitter; + adjust = add_max; else if (delta < -jitter) - adjust = -jitter; + adjust = sub_max; else adjust = 0; diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index 076bc9ecfb499..4763402dbcd66 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -415,7 +415,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev, s64 tmp = *val * (3767897513LL / 25LL); *val = div_s64_rem(tmp, 1000000000LL, val2); - return IIO_VAL_INT_PLUS_MICRO; + return IIO_VAL_INT_PLUS_NANO; } mutex_lock(&st->lock); diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index 64be656f0b805..289b6c2bb2c28 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -1289,6 +1289,7 @@ static int adis16475_config_sync_mode(struct adis16475 *st) struct device *dev = &st->adis.spi->dev; const struct adis16475_sync *sync; u32 sync_mode; + u16 val; /* default to internal clk */ st->clk_freq = st->info->int_clk * 1000; @@ -1350,8 +1351,9 @@ static int adis16475_config_sync_mode(struct adis16475 *st) * I'm keeping this for simplicity and avoiding extra variables * in chip_info. */ + val = ADIS16475_SYNC_MODE(sync->sync_mode); ret = __adis_update_bits(&st->adis, ADIS16475_REG_MSG_CTRL, - ADIS16475_SYNC_MODE_MASK, sync->sync_mode); + ADIS16475_SYNC_MODE_MASK, val); if (ret) return ret; diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c index 183af482828f8..7d728d0aac903 100644 --- a/drivers/iio/imu/bmi323/bmi323_core.c +++ b/drivers/iio/imu/bmi323/bmi323_core.c @@ -1391,7 +1391,7 @@ static irqreturn_t bmi323_trigger_handler(int irq, void *p) &data->buffer.channels, ARRAY_SIZE(data->buffer.channels)); if (ret) - return IRQ_NONE; + goto out; } else { for_each_set_bit(bit, indio_dev->active_scan_mask, BMI323_CHAN_MAX) { @@ -1400,13 +1400,14 @@ static irqreturn_t bmi323_trigger_handler(int irq, void *p) &data->buffer.channels[index++], BMI323_BYTES_PER_SAMPLE); if (ret) - return IRQ_NONE; + goto out; } } iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer, iio_get_time_ns(indio_dev)); +out: iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c index f67bd5a39beb3..6d9cb010f628b 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c @@ -129,10 +129,6 @@ static int inv_icm42600_accel_update_scan_mode(struct iio_dev *indio_dev, /* update data FIFO write */ inv_sensors_timestamp_apply_odr(ts, 0, 0, 0); ret = inv_icm42600_buffer_set_fifo_en(st, fifo_en | st->fifo.en); - if (ret) - goto out_unlock; - - ret = inv_icm42600_buffer_update_watermark(st); out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c index 3df0a715e8856..fc80b4a97fda8 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c @@ -129,10 +129,6 @@ static int inv_icm42600_gyro_update_scan_mode(struct iio_dev *indio_dev, /* update data FIFO write */ inv_sensors_timestamp_apply_odr(ts, 0, 0, 0); ret = inv_icm42600_buffer_set_fifo_en(st, fifo_en | st->fifo.en); - if (ret) - goto out_unlock; - - ret = inv_icm42600_buffer_update_watermark(st); out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c new file mode 100644 index 0000000000000..2fea2bbbe47fd --- /dev/null +++ b/drivers/iio/industrialio-backend.c @@ -0,0 +1,418 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Framework to handle complex IIO aggregate devices. + * + * The typical architecture is to have one device as the frontend device which + * can be "linked" against one or multiple backend devices. All the IIO and + * userspace interface is expected to be registers/managed by the frontend + * device which will callback into the backends when needed (to get/set some + * configuration that it does not directly control). + * + * ------------------------------------------------------- + * ------------------ | ------------ ------------ ------- FPGA| + * | ADC |------------------------| | ADC CORE |---------| DMA CORE |------| RAM | | + * | (Frontend/IIO) | Serial Data (eg: LVDS) | |(backend) |---------| |------| | | + * | |------------------------| ------------ ------------ ------- | + * ------------------ ------------------------------------------------------- + * + * The framework interface is pretty simple: + * - Backends should register themselves with devm_iio_backend_register() + * - Frontend devices should get backends with devm_iio_backend_get() + * + * Also to note that the primary target for this framework are converters like + * ADC/DACs so iio_backend_ops will have some operations typical of converter + * devices. On top of that, this is "generic" for all IIO which means any kind + * of device can make use of the framework. That said, If the iio_backend_ops + * struct begins to grow out of control, we can always refactor things so that + * the industrialio-backend.c is only left with the really generic stuff. Then, + * we can build on top of it depending on the needs. + * + * Copyright (C) 2023-2024 Analog Devices Inc. + */ +#define dev_fmt(fmt) "iio-backend: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +struct iio_backend { + struct list_head entry; + const struct iio_backend_ops *ops; + struct device *dev; + struct module *owner; + void *priv; +}; + +/* + * Helper struct for requesting buffers. This ensures that we have all data + * that we need to free the buffer in a device managed action. + */ +struct iio_backend_buffer_pair { + struct iio_backend *back; + struct iio_buffer *buffer; +}; + +static LIST_HEAD(iio_back_list); +static DEFINE_MUTEX(iio_back_lock); + +/* + * Helper macros to call backend ops. Makes sure the option is supported. + */ +#define iio_backend_check_op(back, op) ({ \ + struct iio_backend *____back = back; \ + int ____ret = 0; \ + \ + if (!____back->ops->op) \ + ____ret = -EOPNOTSUPP; \ + \ + ____ret; \ +}) + +#define iio_backend_op_call(back, op, args...) ({ \ + struct iio_backend *__back = back; \ + int __ret; \ + \ + __ret = iio_backend_check_op(__back, op); \ + if (!__ret) \ + __ret = __back->ops->op(__back, ##args); \ + \ + __ret; \ +}) + +#define iio_backend_ptr_op_call(back, op, args...) ({ \ + struct iio_backend *__back = back; \ + void *ptr_err; \ + int __ret; \ + \ + __ret = iio_backend_check_op(__back, op); \ + if (__ret) \ + ptr_err = ERR_PTR(__ret); \ + else \ + ptr_err = __back->ops->op(__back, ##args); \ + \ + ptr_err; \ +}) + +#define iio_backend_void_op_call(back, op, args...) { \ + struct iio_backend *__back = back; \ + int __ret; \ + \ + __ret = iio_backend_check_op(__back, op); \ + if (!__ret) \ + __back->ops->op(__back, ##args); \ +} + +/** + * iio_backend_chan_enable - Enable a backend channel + * @back: Backend device + * @chan: Channel number + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int iio_backend_chan_enable(struct iio_backend *back, unsigned int chan) +{ + return iio_backend_op_call(back, chan_enable, chan); +} +EXPORT_SYMBOL_NS_GPL(iio_backend_chan_enable, IIO_BACKEND); + +/** + * iio_backend_chan_disable - Disable a backend channel + * @back: Backend device + * @chan: Channel number + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int iio_backend_chan_disable(struct iio_backend *back, unsigned int chan) +{ + return iio_backend_op_call(back, chan_disable, chan); +} +EXPORT_SYMBOL_NS_GPL(iio_backend_chan_disable, IIO_BACKEND); + +static void __iio_backend_disable(void *back) +{ + iio_backend_void_op_call(back, disable); +} + +/** + * devm_iio_backend_enable - Device managed backend enable + * @dev: Consumer device for the backend + * @back: Backend device + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int devm_iio_backend_enable(struct device *dev, struct iio_backend *back) +{ + int ret; + + ret = iio_backend_op_call(back, enable); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, __iio_backend_disable, back); +} +EXPORT_SYMBOL_NS_GPL(devm_iio_backend_enable, IIO_BACKEND); + +/** + * iio_backend_data_format_set - Configure the channel data format + * @back: Backend device + * @chan: Channel number + * @data: Data format + * + * Properly configure a channel with respect to the expected data format. A + * @struct iio_backend_data_fmt must be passed with the settings. + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int iio_backend_data_format_set(struct iio_backend *back, unsigned int chan, + const struct iio_backend_data_fmt *data) +{ + if (!data || data->type >= IIO_BACKEND_DATA_TYPE_MAX) + return -EINVAL; + + return iio_backend_op_call(back, data_format_set, chan, data); +} +EXPORT_SYMBOL_NS_GPL(iio_backend_data_format_set, IIO_BACKEND); + +static void iio_backend_free_buffer(void *arg) +{ + struct iio_backend_buffer_pair *pair = arg; + + iio_backend_void_op_call(pair->back, free_buffer, pair->buffer); +} + +/** + * devm_iio_backend_request_buffer - Device managed buffer request + * @dev: Consumer device for the backend + * @back: Backend device + * @indio_dev: IIO device + * + * Request an IIO buffer from the backend. The type of the buffer (typically + * INDIO_BUFFER_HARDWARE) is up to the backend to decide. This is because, + * normally, the backend dictates what kind of buffering we can get. + * + * The backend .free_buffer() hooks is automatically called on @dev detach. + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int devm_iio_backend_request_buffer(struct device *dev, + struct iio_backend *back, + struct iio_dev *indio_dev) +{ + struct iio_backend_buffer_pair *pair; + struct iio_buffer *buffer; + + pair = devm_kzalloc(dev, sizeof(*pair), GFP_KERNEL); + if (!pair) + return -ENOMEM; + + buffer = iio_backend_ptr_op_call(back, request_buffer, indio_dev); + if (IS_ERR(buffer)) + return PTR_ERR(buffer); + + /* weak reference should be all what we need */ + pair->back = back; + pair->buffer = buffer; + + return devm_add_action_or_reset(dev, iio_backend_free_buffer, pair); +} +EXPORT_SYMBOL_NS_GPL(devm_iio_backend_request_buffer, IIO_BACKEND); + +static void iio_backend_release(void *arg) +{ + struct iio_backend *back = arg; + + module_put(back->owner); +} + +static int __devm_iio_backend_get(struct device *dev, struct iio_backend *back) +{ + struct device_link *link; + int ret; + + /* + * Make sure the provider cannot be unloaded before the consumer module. + * Note that device_links would still guarantee that nothing is + * accessible (and breaks) but this makes it explicit that the consumer + * module must be also unloaded. + */ + if (!try_module_get(back->owner)) + return dev_err_probe(dev, -ENODEV, + "Cannot get module reference\n"); + + ret = devm_add_action_or_reset(dev, iio_backend_release, back); + if (ret) + return ret; + + link = device_link_add(dev, back->dev, DL_FLAG_AUTOREMOVE_CONSUMER); + if (!link) + return dev_err_probe(dev, -EINVAL, + "Could not link to supplier(%s)\n", + dev_name(back->dev)); + + dev_dbg(dev, "Found backend(%s) device\n", dev_name(back->dev)); + + return 0; +} + +/** + * devm_iio_backend_get - Device managed backend device get + * @dev: Consumer device for the backend + * @name: Backend name + * + * Get's the backend associated with @dev. + * + * RETURNS: + * A backend pointer, negative error pointer otherwise. + */ +struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name) +{ + struct fwnode_handle *fwnode; + struct iio_backend *back; + unsigned int index; + int ret; + + if (name) { + ret = device_property_match_string(dev, "io-backend-names", + name); + if (ret < 0) + return ERR_PTR(ret); + index = ret; + } else { + index = 0; + } + + fwnode = fwnode_find_reference(dev_fwnode(dev), "io-backends", index); + if (IS_ERR(fwnode)) { + dev_err_probe(dev, PTR_ERR(fwnode), + "Cannot get Firmware reference\n"); + return ERR_CAST(fwnode); + } + + guard(mutex)(&iio_back_lock); + list_for_each_entry(back, &iio_back_list, entry) { + if (!device_match_fwnode(back->dev, fwnode)) + continue; + + fwnode_handle_put(fwnode); + ret = __devm_iio_backend_get(dev, back); + if (ret) + return ERR_PTR(ret); + + return back; + } + + fwnode_handle_put(fwnode); + return ERR_PTR(-EPROBE_DEFER); +} +EXPORT_SYMBOL_NS_GPL(devm_iio_backend_get, IIO_BACKEND); + +/** + * __devm_iio_backend_get_from_fwnode_lookup - Device managed fwnode backend device get + * @dev: Consumer device for the backend + * @fwnode: Firmware node of the backend device + * + * Search the backend list for a device matching @fwnode. + * This API should not be used and it's only present for preventing the first + * user of this framework to break it's DT ABI. + * + * RETURNS: + * A backend pointer, negative error pointer otherwise. + */ +struct iio_backend * +__devm_iio_backend_get_from_fwnode_lookup(struct device *dev, + struct fwnode_handle *fwnode) +{ + struct iio_backend *back; + int ret; + + guard(mutex)(&iio_back_lock); + list_for_each_entry(back, &iio_back_list, entry) { + if (!device_match_fwnode(back->dev, fwnode)) + continue; + + ret = __devm_iio_backend_get(dev, back); + if (ret) + return ERR_PTR(ret); + + return back; + } + + return ERR_PTR(-EPROBE_DEFER); +} +EXPORT_SYMBOL_NS_GPL(__devm_iio_backend_get_from_fwnode_lookup, IIO_BACKEND); + +/** + * iio_backend_get_priv - Get driver private data + * @back: Backend device + */ +void *iio_backend_get_priv(const struct iio_backend *back) +{ + return back->priv; +} +EXPORT_SYMBOL_NS_GPL(iio_backend_get_priv, IIO_BACKEND); + +static void iio_backend_unregister(void *arg) +{ + struct iio_backend *back = arg; + + guard(mutex)(&iio_back_lock); + list_del(&back->entry); +} + +/** + * devm_iio_backend_register - Device managed backend device register + * @dev: Backend device being registered + * @ops: Backend ops + * @priv: Device private data + * + * @ops is mandatory. Not providing it results in -EINVAL. + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int devm_iio_backend_register(struct device *dev, + const struct iio_backend_ops *ops, void *priv) +{ + struct iio_backend *back; + + if (!ops) + return dev_err_probe(dev, -EINVAL, "No backend ops given\n"); + + /* + * Through device_links, we guarantee that a frontend device cannot be + * bound/exist if the backend driver is not around. Hence, we can bind + * the backend object lifetime with the device being passed since + * removing it will tear the frontend/consumer down. + */ + back = devm_kzalloc(dev, sizeof(*back), GFP_KERNEL); + if (!back) + return -ENOMEM; + + back->ops = ops; + back->owner = dev->driver->owner; + back->dev = dev; + back->priv = priv; + scoped_guard(mutex, &iio_back_lock) + list_add(&back->entry, &iio_back_list); + + return devm_add_action_or_reset(dev, iio_backend_unregister, back); +} +EXPORT_SYMBOL_NS_GPL(devm_iio_backend_register, IIO_BACKEND); + +MODULE_AUTHOR("Nuno Sa "); +MODULE_DESCRIPTION("Framework to handle complex IIO aggregate devices"); +MODULE_LICENSE("GPL"); diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 173dc00762a15..cc9f0d41f59b2 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1656,8 +1656,10 @@ struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv) return NULL; indio_dev = &iio_dev_opaque->indio_dev; - indio_dev->priv = (char *)iio_dev_opaque + - ALIGN(sizeof(struct iio_dev_opaque), IIO_DMA_MINALIGN); + + if (sizeof_priv) + indio_dev->priv = (char *)iio_dev_opaque + + ALIGN(sizeof(*iio_dev_opaque), IIO_DMA_MINALIGN); indio_dev->dev.parent = parent; indio_dev->dev.type = &iio_device_type; diff --git a/drivers/iio/industrialio-gts-helper.c b/drivers/iio/industrialio-gts-helper.c index 7653261d2dc2b..b51eb6cb766f3 100644 --- a/drivers/iio/industrialio-gts-helper.c +++ b/drivers/iio/industrialio-gts-helper.c @@ -34,24 +34,11 @@ static int iio_gts_get_gain(const u64 max, const u64 scale) { u64 full = max; - int tmp = 1; if (scale > full || !scale) return -EINVAL; - if (U64_MAX - full < scale) { - /* Risk of overflow */ - if (full - scale < scale) - return 1; - - full -= scale; - tmp++; - } - - while (full > scale * (u64)tmp) - tmp++; - - return tmp; + return div64_u64(full, scale); } /** diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index fe8734468ed35..0199d055e0ee1 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1233,6 +1233,7 @@ const struct bmp280_chip_info bmp380_chip_info = { .chip_id = bmp380_chip_ids, .num_chip_id = ARRAY_SIZE(bmp380_chip_ids), .regmap_config = &bmp380_regmap_config, + .spi_read_extra_byte = true, .start_up_time = 2000, .channels = bmp380_channels, .num_channels = 2, @@ -1393,12 +1394,12 @@ static int bmp580_read_temp(struct bmp280_data *data, int *val, int *val2) /* * Temperature is returned in Celsius degrees in fractional - * form down 2^16. We rescale by x1000 to return milli Celsius - * to respect IIO ABI. + * form down 2^16. We rescale by x1000 to return millidegrees + * Celsius to respect IIO ABI. */ - *val = raw_temp * 1000; - *val2 = 16; - return IIO_VAL_FRACTIONAL_LOG2; + raw_temp = sign_extend32(raw_temp, 23); + *val = ((s64)raw_temp * 1000) / (1 << 16); + return IIO_VAL_INT; } static int bmp580_read_press(struct bmp280_data *data, int *val, int *val2) diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c index a444d4b2978b5..4e19ea0b4d398 100644 --- a/drivers/iio/pressure/bmp280-spi.c +++ b/drivers/iio/pressure/bmp280-spi.c @@ -96,15 +96,10 @@ static int bmp280_spi_probe(struct spi_device *spi) chip_info = spi_get_device_match_data(spi); - switch (chip_info->chip_id[0]) { - case BMP380_CHIP_ID: - case BMP390_CHIP_ID: + if (chip_info->spi_read_extra_byte) bmp_regmap_bus = &bmp380_regmap_bus; - break; - default: + else bmp_regmap_bus = &bmp280_regmap_bus; - break; - } regmap = devm_regmap_init(&spi->dev, bmp_regmap_bus, @@ -127,7 +122,7 @@ static const struct of_device_id bmp280_of_spi_match[] = { { .compatible = "bosch,bmp180", .data = &bmp180_chip_info }, { .compatible = "bosch,bmp181", .data = &bmp180_chip_info }, { .compatible = "bosch,bmp280", .data = &bmp280_chip_info }, - { .compatible = "bosch,bme280", .data = &bmp280_chip_info }, + { .compatible = "bosch,bme280", .data = &bme280_chip_info }, { .compatible = "bosch,bmp380", .data = &bmp380_chip_info }, { .compatible = "bosch,bmp580", .data = &bmp580_chip_info }, { }, @@ -139,7 +134,7 @@ static const struct spi_device_id bmp280_spi_id[] = { { "bmp180", (kernel_ulong_t)&bmp180_chip_info }, { "bmp181", (kernel_ulong_t)&bmp180_chip_info }, { "bmp280", (kernel_ulong_t)&bmp280_chip_info }, - { "bme280", (kernel_ulong_t)&bmp280_chip_info }, + { "bme280", (kernel_ulong_t)&bme280_chip_info }, { "bmp380", (kernel_ulong_t)&bmp380_chip_info }, { "bmp580", (kernel_ulong_t)&bmp580_chip_info }, { } diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h index 4012387d79565..5812a344ed8e8 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -423,6 +423,7 @@ struct bmp280_chip_info { int num_chip_id; const struct regmap_config *regmap_config; + bool spi_read_extra_byte; const struct iio_chan_spec *channels; int num_channels; diff --git a/drivers/iio/pressure/dps310.c b/drivers/iio/pressure/dps310.c index 1ff091b2f764d..d0a516d56da47 100644 --- a/drivers/iio/pressure/dps310.c +++ b/drivers/iio/pressure/dps310.c @@ -730,7 +730,7 @@ static int dps310_read_pressure(struct dps310_data *data, int *val, int *val2, } } -static int dps310_calculate_temp(struct dps310_data *data) +static int dps310_calculate_temp(struct dps310_data *data, int *val) { s64 c0; s64 t; @@ -746,7 +746,9 @@ static int dps310_calculate_temp(struct dps310_data *data) t = c0 + ((s64)data->temp_raw * (s64)data->c1); /* Convert to milliCelsius and scale the temperature */ - return (int)div_s64(t * 1000LL, kt); + *val = (int)div_s64(t * 1000LL, kt); + + return 0; } static int dps310_read_temp(struct dps310_data *data, int *val, int *val2, @@ -768,11 +770,10 @@ static int dps310_read_temp(struct dps310_data *data, int *val, int *val2, if (rc) return rc; - rc = dps310_calculate_temp(data); - if (rc < 0) + rc = dps310_calculate_temp(data, val); + if (rc) return rc; - *val = rc; return IIO_VAL_INT; case IIO_CHAN_INFO_OVERSAMPLING_RATIO: diff --git a/drivers/iio/pressure/mprls0025pa.c b/drivers/iio/pressure/mprls0025pa.c index 30fb2de368210..e3f0de020a40c 100644 --- a/drivers/iio/pressure/mprls0025pa.c +++ b/drivers/iio/pressure/mprls0025pa.c @@ -323,6 +323,7 @@ static int mpr_probe(struct i2c_client *client) struct iio_dev *indio_dev; struct device *dev = &client->dev; s64 scale, offset; + u32 func; if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_READ_BYTE)) return dev_err_probe(dev, -EOPNOTSUPP, @@ -362,10 +363,11 @@ static int mpr_probe(struct i2c_client *client) return dev_err_probe(dev, ret, "honeywell,pmax-pascal could not be read\n"); ret = device_property_read_u32(dev, - "honeywell,transfer-function", &data->function); + "honeywell,transfer-function", &func); if (ret) return dev_err_probe(dev, ret, "honeywell,transfer-function could not be read\n"); + data->function = func - 1; if (data->function > MPR_FUNCTION_C) return dev_err_probe(dev, -EINVAL, "honeywell,transfer-function %d invalid\n", diff --git a/drivers/iio/temperature/mcp9600.c b/drivers/iio/temperature/mcp9600.c index 46845804292bf..7a3eef5d5e752 100644 --- a/drivers/iio/temperature/mcp9600.c +++ b/drivers/iio/temperature/mcp9600.c @@ -52,7 +52,8 @@ static int mcp9600_read(struct mcp9600_data *data, if (ret < 0) return ret; - *val = ret; + + *val = sign_extend32(ret, 15); return 0; } diff --git a/drivers/iio/temperature/mlx90635.c b/drivers/iio/temperature/mlx90635.c index 1f5c962c1818f..f7f88498ba0e8 100644 --- a/drivers/iio/temperature/mlx90635.c +++ b/drivers/iio/temperature/mlx90635.c @@ -947,9 +947,9 @@ static int mlx90635_probe(struct i2c_client *client) "failed to allocate regmap\n"); regmap_ee = devm_regmap_init_i2c(client, &mlx90635_regmap_ee); - if (IS_ERR(regmap)) - return dev_err_probe(&client->dev, PTR_ERR(regmap), - "failed to allocate regmap\n"); + if (IS_ERR(regmap_ee)) + return dev_err_probe(&client->dev, PTR_ERR(regmap_ee), + "failed to allocate EEPROM regmap\n"); mlx90635 = iio_priv(indio_dev); i2c_set_clientdata(client, indio_dev); diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index f253295795f0a..be0743dac3fff 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -348,16 +348,10 @@ static int dst_fetch_ha(const struct dst_entry *dst, static bool has_gateway(const struct dst_entry *dst, sa_family_t family) { - struct rtable *rt; - struct rt6_info *rt6; - - if (family == AF_INET) { - rt = container_of(dst, struct rtable, dst); - return rt->rt_uses_gateway; - } + if (family == AF_INET) + return dst_rtable(dst)->rt_uses_gateway; - rt6 = container_of(dst, struct rt6_info, dst); - return rt6->rt6i_flags & RTF_GATEWAY; + return dst_rt6_info(dst)->rt6i_flags & RTF_GATEWAY; } static int fetch_ha(const struct dst_entry *dst, struct rdma_dev_addr *dev_addr, diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index ff58058aeadca..07fb8d3c037f0 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -34,6 +34,7 @@ MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("InfiniBand CM"); MODULE_LICENSE("Dual BSD/GPL"); +#define CM_DESTROY_ID_WAIT_TIMEOUT 10000 /* msecs */ static const char * const ibcm_rej_reason_strs[] = { [IB_CM_REJ_NO_QP] = "no QP", [IB_CM_REJ_NO_EEC] = "no EEC", @@ -1025,13 +1026,26 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv) } } +static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id, + enum ib_cm_state old_state) +{ + struct cm_id_private *cm_id_priv; + + cm_id_priv = container_of(cm_id, struct cm_id_private, id); + pr_err("%s: cm_id=%p timed out. state %d -> %d, refcnt=%d\n", __func__, + cm_id, old_state, cm_id->state, refcount_read(&cm_id_priv->refcount)); +} + static void cm_destroy_id(struct ib_cm_id *cm_id, int err) { struct cm_id_private *cm_id_priv; + enum ib_cm_state old_state; struct cm_work *work; + int ret; cm_id_priv = container_of(cm_id, struct cm_id_private, id); spin_lock_irq(&cm_id_priv->lock); + old_state = cm_id->state; retest: switch (cm_id->state) { case IB_CM_LISTEN: @@ -1135,7 +1149,14 @@ static void cm_destroy_id(struct ib_cm_id *cm_id, int err) xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id)); cm_deref_id(cm_id_priv); - wait_for_completion(&cm_id_priv->comp); + do { + ret = wait_for_completion_timeout(&cm_id_priv->comp, + msecs_to_jiffies( + CM_DESTROY_ID_WAIT_TIMEOUT)); + if (!ret) /* timeout happened */ + cm_destroy_id_wait_timeout(cm_id, old_state); + } while (!ret); + while ((work = cm_dequeue_work(cm_id_priv)) != NULL) cm_free_work(work); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 1e2cd7c8716e8..64ace0b968f07 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -715,8 +715,10 @@ cma_validate_port(struct ib_device *device, u32 port, rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); if (!net_eq(dev_net(ndev), dev_addr->net) || - ndev->ifindex != bound_if_index) + ndev->ifindex != bound_if_index) { + rdma_put_gid_attr(sgid_attr); sgid_attr = ERR_PTR(-ENODEV); + } rcu_read_unlock(); goto out; } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 67bcea7a153c6..07cb6c5ffda00 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1730,7 +1730,7 @@ static int assign_client_id(struct ib_client *client) { int ret; - down_write(&clients_rwsem); + lockdep_assert_held(&clients_rwsem); /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in @@ -1739,14 +1739,11 @@ static int assign_client_id(struct ib_client *client) client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) - goto out; + return ret; highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); - -out: - up_write(&clients_rwsem); - return ret; + return 0; } static void remove_client_id(struct ib_client *client) @@ -1776,25 +1773,35 @@ int ib_register_client(struct ib_client *client) { struct ib_device *device; unsigned long index; + bool need_unreg = false; int ret; refcount_set(&client->uses, 1); init_completion(&client->uses_zero); + + /* + * The devices_rwsem is held in write mode to ensure that a racing + * ib_register_device() sees a consisent view of clients and devices. + */ + down_write(&devices_rwsem); + down_write(&clients_rwsem); ret = assign_client_id(client); if (ret) - return ret; + goto out; - down_read(&devices_rwsem); + need_unreg = true; xa_for_each_marked (&devices, index, device, DEVICE_REGISTERED) { ret = add_client_context(device, client); - if (ret) { - up_read(&devices_rwsem); - ib_unregister_client(client); - return ret; - } + if (ret) + goto out; } - up_read(&devices_rwsem); - return 0; + ret = 0; +out: + up_write(&clients_rwsem); + up_write(&devices_rwsem); + if (need_unreg && ret) + ib_unregister_client(client); + return ret; } EXPORT_SYMBOL(ib_register_client); diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index 9dca451ed5221..6974922e5609a 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -107,8 +107,6 @@ struct bnxt_re_gsi_context { struct bnxt_re_sqp_entries *sqp_tbl; }; -#define BNXT_RE_MIN_MSIX 2 -#define BNXT_RE_MAX_MSIX 9 #define BNXT_RE_AEQ_IDX 0 #define BNXT_RE_NQ_IDX 1 #define BNXT_RE_GEN_P5_MAX_VF 64 @@ -168,7 +166,7 @@ struct bnxt_re_dev { struct bnxt_qplib_rcfw rcfw; /* NQ */ - struct bnxt_qplib_nq nq[BNXT_RE_MAX_MSIX]; + struct bnxt_qplib_nq nq[BNXT_MAX_ROCE_MSIX]; /* Device Resources */ struct bnxt_qplib_dev_attr dev_attr; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 439d0c7c5d0ca..04258676d0726 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -1013,7 +1013,8 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) hwq_attr.stride = sizeof(struct sq_sge); hwq_attr.depth = bnxt_qplib_get_depth(sq); hwq_attr.aux_stride = psn_sz; - hwq_attr.aux_depth = bnxt_qplib_set_sq_size(sq, qp->wqe_mode); + hwq_attr.aux_depth = psn_sz ? bnxt_qplib_set_sq_size(sq, qp->wqe_mode) + : 0; /* Update msn tbl size */ if (BNXT_RE_HW_RETX(qp->dev_cap_flags) && psn_sz) { hwq_attr.aux_depth = roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c index 1b6d16af8c12b..2517c972c651a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cq.c +++ b/drivers/infiniband/hw/hns/hns_roce_cq.c @@ -151,7 +151,7 @@ static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) return ret; } - ret = xa_err(xa_store(&cq_table->array, hr_cq->cqn, hr_cq, GFP_KERNEL)); + ret = xa_err(xa_store_irq(&cq_table->array, hr_cq->cqn, hr_cq, GFP_KERNEL)); if (ret) { ibdev_err(ibdev, "failed to xa_store CQ, ret = %d.\n", ret); goto err_put; @@ -164,7 +164,7 @@ static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) return 0; err_xa: - xa_erase(&cq_table->array, hr_cq->cqn); + xa_erase_irq(&cq_table->array, hr_cq->cqn); err_put: hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn); @@ -183,7 +183,7 @@ static void free_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq) dev_err(dev, "DESTROY_CQ failed (%d) for CQN %06lx\n", ret, hr_cq->cqn); - xa_erase(&cq_table->array, hr_cq->cqn); + xa_erase_irq(&cq_table->array, hr_cq->cqn); /* Waiting interrupt process procedure carried out */ synchronize_irq(hr_dev->eq_table.eq[hr_cq->vector].irq); @@ -477,13 +477,6 @@ void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type) struct ib_event event; struct ib_cq *ibcq; - hr_cq = xa_load(&hr_dev->cq_table.array, - cqn & (hr_dev->caps.num_cqs - 1)); - if (!hr_cq) { - dev_warn(dev, "async event for bogus CQ 0x%06x\n", cqn); - return; - } - if (event_type != HNS_ROCE_EVENT_TYPE_CQ_ID_INVALID && event_type != HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR && event_type != HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW) { @@ -492,7 +485,16 @@ void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type) return; } - refcount_inc(&hr_cq->refcount); + xa_lock(&hr_dev->cq_table.array); + hr_cq = xa_load(&hr_dev->cq_table.array, + cqn & (hr_dev->caps.num_cqs - 1)); + if (hr_cq) + refcount_inc(&hr_cq->refcount); + xa_unlock(&hr_dev->cq_table.array); + if (!hr_cq) { + dev_warn(dev, "async event for bogus CQ 0x%06x\n", cqn); + return; + } ibcq = &hr_cq->ib_cq; if (ibcq->event_handler) { diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index b1fce5ddf6316..46f8a631093ba 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -585,6 +585,13 @@ struct hns_roce_work { u32 queue_num; }; +enum hns_roce_cong_type { + CONG_TYPE_DCQCN, + CONG_TYPE_LDCP, + CONG_TYPE_HC3, + CONG_TYPE_DIP, +}; + struct hns_roce_qp { struct ib_qp ibqp; struct hns_roce_wq rq; @@ -628,6 +635,7 @@ struct hns_roce_qp { struct list_head sq_node; /* all send qps are on a list */ struct hns_user_mmap_entry *dwqe_mmap_entry; u32 config; + enum hns_roce_cong_type cong_type; }; struct hns_roce_ib_iboe { @@ -699,13 +707,6 @@ struct hns_roce_eq_table { struct hns_roce_eq *eq; }; -enum cong_type { - CONG_TYPE_DCQCN, - CONG_TYPE_LDCP, - CONG_TYPE_HC3, - CONG_TYPE_DIP, -}; - struct hns_roce_caps { u64 fw_ver; u8 num_ports; @@ -835,7 +836,7 @@ struct hns_roce_caps { u16 default_aeq_period; u16 default_aeq_arm_st; u16 default_ceq_arm_st; - enum cong_type cong_type; + enum hns_roce_cong_type cong_type; }; enum hns_roce_device_state { diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h index 7d23d3c51da46..fea6d7d508b60 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.h +++ b/drivers/infiniband/hw/hns/hns_roce_hem.h @@ -61,16 +61,16 @@ enum { (sizeof(struct scatterlist) + sizeof(void *))) #define check_whether_bt_num_3(type, hop_num) \ - (type < HEM_TYPE_MTT && hop_num == 2) + ((type) < HEM_TYPE_MTT && (hop_num) == 2) #define check_whether_bt_num_2(type, hop_num) \ - ((type < HEM_TYPE_MTT && hop_num == 1) || \ - (type >= HEM_TYPE_MTT && hop_num == 2)) + (((type) < HEM_TYPE_MTT && (hop_num) == 1) || \ + ((type) >= HEM_TYPE_MTT && (hop_num) == 2)) #define check_whether_bt_num_1(type, hop_num) \ - ((type < HEM_TYPE_MTT && hop_num == HNS_ROCE_HOP_NUM_0) || \ - (type >= HEM_TYPE_MTT && hop_num == 1) || \ - (type >= HEM_TYPE_MTT && hop_num == HNS_ROCE_HOP_NUM_0)) + (((type) < HEM_TYPE_MTT && (hop_num) == HNS_ROCE_HOP_NUM_0) || \ + ((type) >= HEM_TYPE_MTT && (hop_num) == 1) || \ + ((type) >= HEM_TYPE_MTT && (hop_num) == HNS_ROCE_HOP_NUM_0)) struct hns_roce_hem_chunk { struct list_head list; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 8206daea6767d..f95ec4618fbed 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2105,7 +2105,7 @@ static void apply_func_caps(struct hns_roce_dev *hr_dev) caps->gmv_bt_num * (HNS_HW_PAGE_SIZE / caps->gmv_entry_sz)); - caps->gmv_entry_num = caps->gmv_bt_num * (PAGE_SIZE / + caps->gmv_entry_num = caps->gmv_bt_num * (HNS_HW_PAGE_SIZE / caps->gmv_entry_sz); } else { u32 func_num = max_t(u32, 1, hr_dev->func_num); @@ -3715,8 +3715,9 @@ static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp, wc->status == IB_WC_WR_FLUSH_ERR)) return; - ibdev_err(&hr_dev->ib_dev, "error cqe status 0x%x:\n", cqe_status); - print_hex_dump(KERN_ERR, "", DUMP_PREFIX_NONE, 16, 4, cqe, + ibdev_err_ratelimited(&hr_dev->ib_dev, "error cqe status 0x%x:\n", + cqe_status); + print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_NONE, 16, 4, cqe, cq->cqe_size, false); wc->vendor_err = hr_reg_read(cqe, CQE_SUB_STATUS); @@ -4745,12 +4746,15 @@ static int check_cong_type(struct ib_qp *ibqp, struct hns_roce_congestion_algorithm *cong_alg) { struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); - if (ibqp->qp_type == IB_QPT_UD) - hr_dev->caps.cong_type = CONG_TYPE_DCQCN; + if (ibqp->qp_type == IB_QPT_UD || ibqp->qp_type == IB_QPT_GSI) + hr_qp->cong_type = CONG_TYPE_DCQCN; + else + hr_qp->cong_type = hr_dev->caps.cong_type; /* different congestion types match different configurations */ - switch (hr_dev->caps.cong_type) { + switch (hr_qp->cong_type) { case CONG_TYPE_DCQCN: cong_alg->alg_sel = CONG_DCQCN; cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL; @@ -4778,8 +4782,8 @@ static int check_cong_type(struct ib_qp *ibqp, default: ibdev_warn(&hr_dev->ib_dev, "invalid type(%u) for congestion selection.\n", - hr_dev->caps.cong_type); - hr_dev->caps.cong_type = CONG_TYPE_DCQCN; + hr_qp->cong_type); + hr_qp->cong_type = CONG_TYPE_DCQCN; cong_alg->alg_sel = CONG_DCQCN; cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL; cong_alg->dip_vld = DIP_INVALID; @@ -4798,6 +4802,7 @@ static int fill_cong_field(struct ib_qp *ibqp, const struct ib_qp_attr *attr, struct hns_roce_congestion_algorithm cong_field; struct ib_device *ibdev = ibqp->device; struct hns_roce_dev *hr_dev = to_hr_dev(ibdev); + struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); u32 dip_idx = 0; int ret; @@ -4810,7 +4815,7 @@ static int fill_cong_field(struct ib_qp *ibqp, const struct ib_qp_attr *attr, return ret; hr_reg_write(context, QPC_CONG_ALGO_TMPL_ID, hr_dev->cong_algo_tmpl_id + - hr_dev->caps.cong_type * HNS_ROCE_CONG_SIZE); + hr_qp->cong_type * HNS_ROCE_CONG_SIZE); hr_reg_clear(qpc_mask, QPC_CONG_ALGO_TMPL_ID); hr_reg_write(&context->ext, QPCEX_CONG_ALG_SEL, cong_field.alg_sel); hr_reg_clear(&qpc_mask->ext, QPCEX_CONG_ALG_SEL); diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index b55fe6911f9f1..a33d3cedbc944 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -37,6 +37,7 @@ #include #include #include +#include "hnae3.h" #include "hns_roce_common.h" #include "hns_roce_device.h" #include "hns_roce_hem.h" diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 91cd580480fe2..0d42fd197c11e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -433,18 +433,18 @@ int hns_roce_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, struct ib_device *ibdev = &hr_dev->ib_dev; struct hns_roce_mr *mr = to_hr_mr(ibmr); struct hns_roce_mtr *mtr = &mr->pbl_mtr; - int ret = 0; + int ret, sg_num = 0; mr->npages = 0; mr->page_list = kvcalloc(mr->pbl_mtr.hem_cfg.buf_pg_count, sizeof(dma_addr_t), GFP_KERNEL); if (!mr->page_list) - return ret; + return sg_num; - ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, hns_roce_set_page); - if (ret < 1) { + sg_num = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, hns_roce_set_page); + if (sg_num < 1) { ibdev_err(ibdev, "failed to store sg pages %u %u, cnt = %d.\n", - mr->npages, mr->pbl_mtr.hem_cfg.buf_pg_count, ret); + mr->npages, mr->pbl_mtr.hem_cfg.buf_pg_count, sg_num); goto err_page_list; } @@ -455,17 +455,16 @@ int hns_roce_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, ret = hns_roce_mtr_map(hr_dev, mtr, mr->page_list, mr->npages); if (ret) { ibdev_err(ibdev, "failed to map sg mtr, ret = %d.\n", ret); - ret = 0; + sg_num = 0; } else { mr->pbl_mtr.hem_cfg.buf_pg_shift = (u32)ilog2(ibmr->page_size); - ret = mr->npages; } err_page_list: kvfree(mr->page_list); mr->page_list = NULL; - return ret; + return sg_num; } static void hns_roce_mw_free(struct hns_roce_dev *hr_dev, diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index 4abae94778544..8f48c6723e07e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -123,7 +123,7 @@ static int alloc_srqc(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq) return ret; } - ret = xa_err(xa_store(&srq_table->xa, srq->srqn, srq, GFP_KERNEL)); + ret = xa_err(xa_store_irq(&srq_table->xa, srq->srqn, srq, GFP_KERNEL)); if (ret) { ibdev_err(ibdev, "failed to store SRQC, ret = %d.\n", ret); goto err_put; @@ -136,7 +136,7 @@ static int alloc_srqc(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq) return 0; err_xa: - xa_erase(&srq_table->xa, srq->srqn); + xa_erase_irq(&srq_table->xa, srq->srqn); err_put: hns_roce_table_put(hr_dev, &srq_table->table, srq->srqn); @@ -154,7 +154,7 @@ static void free_srqc(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq) dev_err(hr_dev->dev, "DESTROY_SRQ failed (%d) for SRQN %06lx\n", ret, srq->srqn); - xa_erase(&srq_table->xa, srq->srqn); + xa_erase_irq(&srq_table->xa, srq->srqn); if (refcount_dec_and_test(&srq->refcount)) complete(&srq->free); diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 0b046c061742b..12704efb7b19a 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -719,7 +719,6 @@ static int irdma_setup_kmode_qp(struct irdma_device *iwdev, info->rq_pa + (ukinfo->rq_depth * IRDMA_QP_WQE_MIN_SIZE); ukinfo->sq_size = ukinfo->sq_depth >> ukinfo->sq_shift; ukinfo->rq_size = ukinfo->rq_depth >> ukinfo->rq_shift; - ukinfo->qp_id = iwqp->ibqp.qp_num; iwqp->max_send_wr = (ukinfo->sq_depth - IRDMA_SQ_RSVD) >> ukinfo->sq_shift; iwqp->max_recv_wr = (ukinfo->rq_depth - IRDMA_RQ_RSVD) >> ukinfo->rq_shift; @@ -944,7 +943,7 @@ static int irdma_create_qp(struct ib_qp *ibqp, iwqp->host_ctx.size = IRDMA_QP_CTX_SIZE; init_info.pd = &iwpd->sc_pd; - init_info.qp_uk_init_info.qp_id = iwqp->ibqp.qp_num; + init_info.qp_uk_init_info.qp_id = qp_num; if (!rdma_protocol_roce(&iwdev->ibdev, 1)) init_info.qp_uk_init_info.first_sq_wq = 1; iwqp->ctx_info.qp_compl_ctx = (uintptr_t)qp; diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c index 83ebd070535ab..89fcc09ded8a4 100644 --- a/drivers/infiniband/hw/mana/cq.c +++ b/drivers/infiniband/hw/mana/cq.c @@ -16,7 +16,7 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, int err; mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); - gc = mdev->gdma_dev->gdma_context; + gc = mdev_to_gc(mdev); if (udata->inlen < sizeof(ucmd)) return -EINVAL; @@ -39,37 +39,13 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, } cq->cqe = attr->cqe; - cq->umem = ib_umem_get(ibdev, ucmd.buf_addr, cq->cqe * COMP_ENTRY_SIZE, - IB_ACCESS_LOCAL_WRITE); - if (IS_ERR(cq->umem)) { - err = PTR_ERR(cq->umem); - ibdev_dbg(ibdev, "Failed to get umem for create cq, err %d\n", - err); - return err; - } - - err = mana_ib_gd_create_dma_region(mdev, cq->umem, &cq->gdma_region); + err = mana_ib_create_queue(mdev, ucmd.buf_addr, cq->cqe * COMP_ENTRY_SIZE, &cq->queue); if (err) { - ibdev_dbg(ibdev, - "Failed to create dma region for create cq, %d\n", - err); - goto err_release_umem; + ibdev_dbg(ibdev, "Failed to create queue for create cq, %d\n", err); + return err; } - ibdev_dbg(ibdev, - "mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n", - err, cq->gdma_region); - - /* - * The CQ ID is not known at this time. The ID is generated at create_qp - */ - cq->id = INVALID_QUEUE_ID; - return 0; - -err_release_umem: - ib_umem_release(cq->umem); - return err; } int mana_ib_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) @@ -78,32 +54,45 @@ int mana_ib_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) struct ib_device *ibdev = ibcq->device; struct mana_ib_dev *mdev; struct gdma_context *gc; - int err; mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); - gc = mdev->gdma_dev->gdma_context; - - err = mana_ib_gd_destroy_dma_region(mdev, cq->gdma_region); - if (err) { - ibdev_dbg(ibdev, - "Failed to destroy dma region, %d\n", err); - return err; - } + gc = mdev_to_gc(mdev); - if (cq->id != INVALID_QUEUE_ID) { - kfree(gc->cq_table[cq->id]); - gc->cq_table[cq->id] = NULL; + if (cq->queue.id != INVALID_QUEUE_ID) { + kfree(gc->cq_table[cq->queue.id]); + gc->cq_table[cq->queue.id] = NULL; } - ib_umem_release(cq->umem); + mana_ib_destroy_queue(mdev, &cq->queue); return 0; } -void mana_ib_cq_handler(void *ctx, struct gdma_queue *gdma_cq) +static void mana_ib_cq_handler(void *ctx, struct gdma_queue *gdma_cq) { struct mana_ib_cq *cq = ctx; if (cq->ibcq.comp_handler) cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); } + +int mana_ib_install_cq_cb(struct mana_ib_dev *mdev, struct mana_ib_cq *cq) +{ + struct gdma_context *gc = mdev_to_gc(mdev); + struct gdma_queue *gdma_cq; + + if (cq->queue.id >= gc->max_num_cqs) + return -EINVAL; + /* Create CQ table entry */ + WARN_ON(gc->cq_table[cq->queue.id]); + gdma_cq = kzalloc(sizeof(*gdma_cq), GFP_KERNEL); + if (!gdma_cq) + return -ENOMEM; + + gdma_cq->cq.context = cq; + gdma_cq->type = GDMA_CQ; + gdma_cq->cq.callback = mana_ib_cq_handler; + gdma_cq->id = cq->queue.id; + gc->cq_table[cq->queue.id] = gdma_cq; + return 0; +} diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c index faca092456fa3..4524c6b807487 100644 --- a/drivers/infiniband/hw/mana/main.c +++ b/drivers/infiniband/hw/mana/main.c @@ -8,13 +8,10 @@ void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd *pd, u32 port) { - struct gdma_dev *gd = &dev->gdma_dev->gdma_context->mana; struct mana_port_context *mpc; struct net_device *ndev; - struct mana_context *mc; - mc = gd->driver_data; - ndev = mc->ports[port]; + ndev = mana_ib_get_netdev(&dev->ib_dev, port); mpc = netdev_priv(ndev); mutex_lock(&pd->vport_mutex); @@ -31,14 +28,11 @@ void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd *pd, int mana_ib_cfg_vport(struct mana_ib_dev *dev, u32 port, struct mana_ib_pd *pd, u32 doorbell_id) { - struct gdma_dev *mdev = &dev->gdma_dev->gdma_context->mana; struct mana_port_context *mpc; - struct mana_context *mc; struct net_device *ndev; int err; - mc = mdev->driver_data; - ndev = mc->ports[port]; + ndev = mana_ib_get_netdev(&dev->ib_dev, port); mpc = netdev_priv(ndev); mutex_lock(&pd->vport_mutex); @@ -79,17 +73,17 @@ int mana_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata) struct gdma_create_pd_req req = {}; enum gdma_pd_flags flags = 0; struct mana_ib_dev *dev; - struct gdma_dev *mdev; + struct gdma_context *gc; int err; dev = container_of(ibdev, struct mana_ib_dev, ib_dev); - mdev = dev->gdma_dev; + gc = mdev_to_gc(dev); mana_gd_init_req_hdr(&req.hdr, GDMA_CREATE_PD, sizeof(req), sizeof(resp)); req.flags = flags; - err = mana_gd_send_request(mdev->gdma_context, sizeof(req), &req, + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); if (err || resp.hdr.status) { @@ -119,17 +113,17 @@ int mana_ib_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata) struct gdma_destory_pd_resp resp = {}; struct gdma_destroy_pd_req req = {}; struct mana_ib_dev *dev; - struct gdma_dev *mdev; + struct gdma_context *gc; int err; dev = container_of(ibdev, struct mana_ib_dev, ib_dev); - mdev = dev->gdma_dev; + gc = mdev_to_gc(dev); mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_PD, sizeof(req), sizeof(resp)); req.pd_handle = pd->pd_handle; - err = mana_gd_send_request(mdev->gdma_context, sizeof(req), &req, + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); if (err || resp.hdr.status) { @@ -206,13 +200,11 @@ int mana_ib_alloc_ucontext(struct ib_ucontext *ibcontext, struct ib_device *ibdev = ibcontext->device; struct mana_ib_dev *mdev; struct gdma_context *gc; - struct gdma_dev *dev; int doorbell_page; int ret; mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); - dev = mdev->gdma_dev; - gc = dev->gdma_context; + gc = mdev_to_gc(mdev); /* Allocate a doorbell page index */ ret = mana_gd_allocate_doorbell_page(gc, &doorbell_page); @@ -238,13 +230,56 @@ void mana_ib_dealloc_ucontext(struct ib_ucontext *ibcontext) int ret; mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); - gc = mdev->gdma_dev->gdma_context; + gc = mdev_to_gc(mdev); ret = mana_gd_destroy_doorbell_page(gc, mana_ucontext->doorbell); if (ret) ibdev_dbg(ibdev, "Failed to destroy doorbell page %d\n", ret); } +int mana_ib_create_queue(struct mana_ib_dev *mdev, u64 addr, u32 size, + struct mana_ib_queue *queue) +{ + struct ib_umem *umem; + int err; + + queue->umem = NULL; + queue->id = INVALID_QUEUE_ID; + queue->gdma_region = GDMA_INVALID_DMA_REGION; + + umem = ib_umem_get(&mdev->ib_dev, addr, size, IB_ACCESS_LOCAL_WRITE); + if (IS_ERR(umem)) { + err = PTR_ERR(umem); + ibdev_dbg(&mdev->ib_dev, "Failed to get umem, %d\n", err); + return err; + } + + err = mana_ib_create_zero_offset_dma_region(mdev, umem, &queue->gdma_region); + if (err) { + ibdev_dbg(&mdev->ib_dev, "Failed to create dma region, %d\n", err); + goto free_umem; + } + queue->umem = umem; + + ibdev_dbg(&mdev->ib_dev, + "create_dma_region ret %d gdma_region 0x%llx\n", + err, queue->gdma_region); + + return 0; +free_umem: + ib_umem_release(umem); + return err; +} + +void mana_ib_destroy_queue(struct mana_ib_dev *mdev, struct mana_ib_queue *queue) +{ + /* Ignore return code as there is not much we can do about it. + * The error message is printed inside. + */ + mana_ib_gd_destroy_dma_region(mdev, queue->gdma_region); + ib_umem_release(queue->umem); +} + static int mana_ib_gd_first_dma_region(struct mana_ib_dev *dev, struct gdma_context *gc, @@ -309,8 +344,8 @@ mana_ib_gd_add_dma_region(struct mana_ib_dev *dev, struct gdma_context *gc, return 0; } -int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, - mana_handle_t *gdma_region) +static int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, + mana_handle_t *gdma_region, unsigned long page_sz) { struct gdma_dma_region_add_pages_req *add_req = NULL; size_t num_pages_processed = 0, num_pages_to_handle; @@ -322,23 +357,14 @@ int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, size_t max_pgs_create_cmd; struct gdma_context *gc; size_t num_pages_total; - struct gdma_dev *mdev; - unsigned long page_sz; unsigned int tail = 0; u64 *page_addr_list; void *request_buf; int err; - mdev = dev->gdma_dev; - gc = mdev->gdma_context; + gc = mdev_to_gc(dev); hwc = gc->hwc.driver_data; - /* Hardware requires dma region to align to chosen page size */ - page_sz = ib_umem_find_best_pgsz(umem, PAGE_SZ_BM, 0); - if (!page_sz) { - ibdev_dbg(&dev->ib_dev, "failed to find page size.\n"); - return -ENOMEM; - } num_pages_total = ib_umem_num_dma_blocks(umem, page_sz); max_pgs_create_cmd = @@ -358,7 +384,7 @@ int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, sizeof(struct gdma_create_dma_region_resp)); create_req->length = umem->length; - create_req->offset_in_page = umem->address & (page_sz - 1); + create_req->offset_in_page = ib_umem_dma_offset(umem, page_sz); create_req->gdma_page_type = order_base_2(page_sz) - PAGE_SHIFT; create_req->page_count = num_pages_total; @@ -424,12 +450,39 @@ int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, return err; } +int mana_ib_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, + mana_handle_t *gdma_region, u64 virt) +{ + unsigned long page_sz; + + page_sz = ib_umem_find_best_pgsz(umem, PAGE_SZ_BM, virt); + if (!page_sz) { + ibdev_dbg(&dev->ib_dev, "Failed to find page size.\n"); + return -EINVAL; + } + + return mana_ib_gd_create_dma_region(dev, umem, gdma_region, page_sz); +} + +int mana_ib_create_zero_offset_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, + mana_handle_t *gdma_region) +{ + unsigned long page_sz; + + /* Hardware requires dma region to align to chosen page size */ + page_sz = ib_umem_find_best_pgoff(umem, PAGE_SZ_BM, 0); + if (!page_sz) { + ibdev_dbg(&dev->ib_dev, "Failed to find page size.\n"); + return -EINVAL; + } + + return mana_ib_gd_create_dma_region(dev, umem, gdma_region, page_sz); +} + int mana_ib_gd_destroy_dma_region(struct mana_ib_dev *dev, u64 gdma_region) { - struct gdma_dev *mdev = dev->gdma_dev; - struct gdma_context *gc; + struct gdma_context *gc = mdev_to_gc(dev); - gc = mdev->gdma_context; ibdev_dbg(&dev->ib_dev, "destroy dma region 0x%llx\n", gdma_region); return mana_gd_destroy_dma_region(gc, gdma_region); @@ -447,7 +500,7 @@ int mana_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma) int ret; mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); - gc = mdev->gdma_dev->gdma_context; + gc = mdev_to_gc(mdev); if (vma->vm_pgoff != 0) { ibdev_dbg(ibdev, "Unexpected vm_pgoff %lu\n", vma->vm_pgoff); @@ -531,7 +584,7 @@ int mana_ib_gd_query_adapter_caps(struct mana_ib_dev *dev) req.hdr.resp.msg_version = GDMA_MESSAGE_V3; req.hdr.dev_id = dev->gdma_dev->dev_id; - err = mana_gd_send_request(dev->gdma_dev->gdma_context, sizeof(req), + err = mana_gd_send_request(mdev_to_gc(dev), sizeof(req), &req, sizeof(resp), &resp); if (err) { diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h index 6bdc0f5498d5b..6acb5c281c368 100644 --- a/drivers/infiniband/hw/mana/mana_ib.h +++ b/drivers/infiniband/hw/mana/mana_ib.h @@ -45,6 +45,12 @@ struct mana_ib_adapter_caps { u32 max_inline_data_size; }; +struct mana_ib_queue { + struct ib_umem *umem; + u64 gdma_region; + u64 id; +}; + struct mana_ib_dev { struct ib_device ib_dev; struct gdma_dev *gdma_dev; @@ -82,10 +88,8 @@ struct mana_ib_mr { struct mana_ib_cq { struct ib_cq ibcq; - struct ib_umem *umem; + struct mana_ib_queue queue; int cqe; - u64 gdma_region; - u64 id; u32 comp_vector; }; @@ -142,12 +146,37 @@ struct mana_ib_query_adapter_caps_resp { u32 max_inline_data_size; }; /* HW Data */ -int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, - mana_handle_t *gdma_region); +static inline struct gdma_context *mdev_to_gc(struct mana_ib_dev *mdev) +{ + return mdev->gdma_dev->gdma_context; +} + +static inline struct net_device *mana_ib_get_netdev(struct ib_device *ibdev, u32 port) +{ + struct mana_ib_dev *mdev = container_of(ibdev, struct mana_ib_dev, ib_dev); + struct gdma_context *gc = mdev_to_gc(mdev); + struct mana_context *mc = gc->mana.driver_data; + + if (port < 1 || port > mc->num_ports) + return NULL; + return mc->ports[port - 1]; +} + +int mana_ib_install_cq_cb(struct mana_ib_dev *mdev, struct mana_ib_cq *cq); + +int mana_ib_create_zero_offset_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, + mana_handle_t *gdma_region); + +int mana_ib_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem, + mana_handle_t *gdma_region, u64 virt); int mana_ib_gd_destroy_dma_region(struct mana_ib_dev *dev, mana_handle_t gdma_region); +int mana_ib_create_queue(struct mana_ib_dev *mdev, u64 addr, u32 size, + struct mana_ib_queue *queue); +void mana_ib_destroy_queue(struct mana_ib_dev *mdev, struct mana_ib_queue *queue); + struct ib_wq *mana_ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); @@ -210,6 +239,4 @@ int mana_ib_query_gid(struct ib_device *ibdev, u32 port, int index, void mana_ib_disassociate_ucontext(struct ib_ucontext *ibcontext); int mana_ib_gd_query_adapter_caps(struct mana_ib_dev *mdev); - -void mana_ib_cq_handler(void *ctx, struct gdma_queue *gdma_cq); #endif diff --git a/drivers/infiniband/hw/mana/mr.c b/drivers/infiniband/hw/mana/mr.c index 351207c60eb65..13a49d8fd49d5 100644 --- a/drivers/infiniband/hw/mana/mr.c +++ b/drivers/infiniband/hw/mana/mr.c @@ -30,12 +30,9 @@ static int mana_ib_gd_create_mr(struct mana_ib_dev *dev, struct mana_ib_mr *mr, { struct gdma_create_mr_response resp = {}; struct gdma_create_mr_request req = {}; - struct gdma_dev *mdev = dev->gdma_dev; - struct gdma_context *gc; + struct gdma_context *gc = mdev_to_gc(dev); int err; - gc = mdev->gdma_context; - mana_gd_init_req_hdr(&req.hdr, GDMA_CREATE_MR, sizeof(req), sizeof(resp)); req.pd_handle = mr_params->pd_handle; @@ -77,12 +74,9 @@ static int mana_ib_gd_destroy_mr(struct mana_ib_dev *dev, u64 mr_handle) { struct gdma_destroy_mr_response resp = {}; struct gdma_destroy_mr_request req = {}; - struct gdma_dev *mdev = dev->gdma_dev; - struct gdma_context *gc; + struct gdma_context *gc = mdev_to_gc(dev); int err; - gc = mdev->gdma_context; - mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_MR, sizeof(req), sizeof(resp)); @@ -118,6 +112,7 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length, "start 0x%llx, iova 0x%llx length 0x%llx access_flags 0x%x", start, iova, length, access_flags); + access_flags &= ~IB_ACCESS_OPTIONAL; if (access_flags & ~VALID_MR_FLAGS) return ERR_PTR(-EINVAL); @@ -133,7 +128,7 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length, goto err_free; } - err = mana_ib_gd_create_dma_region(dev, mr->umem, &dma_region_handle); + err = mana_ib_create_dma_region(dev, mr->umem, &dma_region_handle, iova); if (err) { ibdev_dbg(ibdev, "Failed create dma region for user-mr, %d\n", err); @@ -141,7 +136,7 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length, } ibdev_dbg(ibdev, - "mana_ib_gd_create_dma_region ret %d gdma_region %llx\n", err, + "create_dma_region ret %d gdma_region %llx\n", err, dma_region_handle); mr_params.pd_handle = pd->pd_handle; @@ -164,8 +159,7 @@ struct ib_mr *mana_ib_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 length, return &mr->ibmr; err_dma_region: - mana_gd_destroy_dma_region(dev->gdma_dev->gdma_context, - dma_region_handle); + mana_gd_destroy_dma_region(mdev_to_gc(dev), dma_region_handle); err_umem: ib_umem_release(mr->umem); diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c index 21ac9fcadf3f2..d7485ee6a6854 100644 --- a/drivers/infiniband/hw/mana/qp.c +++ b/drivers/infiniband/hw/mana/qp.c @@ -17,12 +17,10 @@ static int mana_ib_cfg_vport_steering(struct mana_ib_dev *dev, struct mana_cfg_rx_steer_resp resp = {}; mana_handle_t *req_indir_tab; struct gdma_context *gc; - struct gdma_dev *mdev; u32 req_buf_size; int i, err; - gc = dev->gdma_dev->gdma_context; - mdev = &gc->mana; + gc = mdev_to_gc(dev); req_buf_size = sizeof(*req) + sizeof(mana_handle_t) * MANA_INDIRECT_TABLE_SIZE; @@ -39,7 +37,7 @@ static int mana_ib_cfg_vport_steering(struct mana_ib_dev *dev, req->rx_enable = 1; req->update_default_rxobj = 1; req->default_rxobj = default_rxobj; - req->hdr.dev_id = mdev->dev_id; + req->hdr.dev_id = gc->mana.dev_id; /* If there are more than 1 entries in indirection table, enable RSS */ if (log_ind_tbl_size) @@ -99,20 +97,17 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp); struct mana_ib_dev *mdev = container_of(pd->device, struct mana_ib_dev, ib_dev); + struct gdma_context *gc = mdev_to_gc(mdev); struct ib_rwq_ind_table *ind_tbl = attr->rwq_ind_tbl; struct mana_ib_create_qp_rss_resp resp = {}; struct mana_ib_create_qp_rss ucmd = {}; struct gdma_queue **gdma_cq_allocated; mana_handle_t *mana_ind_table; struct mana_port_context *mpc; - struct gdma_queue *gdma_cq; unsigned int ind_tbl_size; - struct mana_context *mc; struct net_device *ndev; - struct gdma_context *gc; struct mana_ib_cq *cq; struct mana_ib_wq *wq; - struct gdma_dev *gd; struct mana_eq *eq; struct ib_cq *ibcq; struct ib_wq *ibwq; @@ -120,10 +115,6 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, u32 port; int ret; - gc = mdev->gdma_dev->gdma_context; - gd = &gc->mana; - mc = gd->driver_data; - if (!udata || udata->inlen < sizeof(ucmd)) return -EINVAL; @@ -166,12 +157,12 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, /* IB ports start with 1, MANA start with 0 */ port = ucmd.port; - if (port < 1 || port > mc->num_ports) { + ndev = mana_ib_get_netdev(pd->device, port); + if (!ndev) { ibdev_dbg(&mdev->ib_dev, "Invalid port %u in creating qp\n", port); return -EINVAL; } - ndev = mc->ports[port - 1]; mpc = netdev_priv(ndev); ibdev_dbg(&mdev->ib_dev, "rx_hash_function %d port %d\n", @@ -206,10 +197,10 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, wq_spec.gdma_region = wq->gdma_region; wq_spec.queue_size = wq->wq_buf_size; - cq_spec.gdma_region = cq->gdma_region; + cq_spec.gdma_region = cq->queue.gdma_region; cq_spec.queue_size = cq->cqe * COMP_ENTRY_SIZE; cq_spec.modr_ctx_id = 0; - eq = &mc->eqs[cq->comp_vector % gc->max_num_queues]; + eq = &mpc->ac->eqs[cq->comp_vector % gc->max_num_queues]; cq_spec.attached_eq = eq->eq->id; ret = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_RQ, @@ -222,34 +213,26 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, /* The GDMA regions are now owned by the WQ object */ wq->gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_region = GDMA_INVALID_DMA_REGION; + cq->queue.gdma_region = GDMA_INVALID_DMA_REGION; wq->id = wq_spec.queue_index; - cq->id = cq_spec.queue_index; + cq->queue.id = cq_spec.queue_index; ibdev_dbg(&mdev->ib_dev, "ret %d rx_object 0x%llx wq id %llu cq id %llu\n", - ret, wq->rx_object, wq->id, cq->id); + ret, wq->rx_object, wq->id, cq->queue.id); - resp.entries[i].cqid = cq->id; + resp.entries[i].cqid = cq->queue.id; resp.entries[i].wqid = wq->id; mana_ind_table[i] = wq->rx_object; /* Create CQ table entry */ - WARN_ON(gc->cq_table[cq->id]); - gdma_cq = kzalloc(sizeof(*gdma_cq), GFP_KERNEL); - if (!gdma_cq) { - ret = -ENOMEM; + ret = mana_ib_install_cq_cb(mdev, cq); + if (ret) goto fail; - } - gdma_cq_allocated[i] = gdma_cq; - gdma_cq->cq.context = cq; - gdma_cq->type = GDMA_CQ; - gdma_cq->cq.callback = mana_ib_cq_handler; - gdma_cq->id = cq->id; - gc->cq_table[cq->id] = gdma_cq; + gdma_cq_allocated[i] = gc->cq_table[cq->queue.id]; } resp.num_entries = i; @@ -281,7 +264,7 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd, wq = container_of(ibwq, struct mana_ib_wq, ibwq); cq = container_of(ibcq, struct mana_ib_cq, ibcq); - gc->cq_table[cq->id] = NULL; + gc->cq_table[cq->queue.id] = NULL; kfree(gdma_cq_allocated[i]); mana_destroy_wq_obj(mpc, GDMA_RQ, wq->rx_object); @@ -306,14 +289,13 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, struct mana_ib_ucontext *mana_ucontext = rdma_udata_to_drv_context(udata, struct mana_ib_ucontext, ibucontext); - struct gdma_dev *gd = &mdev->gdma_dev->gdma_context->mana; + struct gdma_context *gc = mdev_to_gc(mdev); struct mana_ib_create_qp_resp resp = {}; struct mana_ib_create_qp ucmd = {}; struct gdma_queue *gdma_cq = NULL; struct mana_obj_spec wq_spec = {}; struct mana_obj_spec cq_spec = {}; struct mana_port_context *mpc; - struct mana_context *mc; struct net_device *ndev; struct ib_umem *umem; struct mana_eq *eq; @@ -321,8 +303,6 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, u32 port; int err; - mc = gd->driver_data; - if (!mana_ucontext || udata->inlen < sizeof(ucmd)) return -EINVAL; @@ -333,11 +313,6 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, return err; } - /* IB ports start with 1, MANA Ethernet ports start with 0 */ - port = ucmd.port; - if (port < 1 || port > mc->num_ports) - return -EINVAL; - if (attr->cap.max_send_wr > mdev->adapter_caps.max_qp_wr) { ibdev_dbg(&mdev->ib_dev, "Requested max_send_wr %d exceeding limit\n", @@ -352,11 +327,17 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, return -EINVAL; } - ndev = mc->ports[port - 1]; + port = ucmd.port; + ndev = mana_ib_get_netdev(ibpd->device, port); + if (!ndev) { + ibdev_dbg(&mdev->ib_dev, "Invalid port %u in creating qp\n", + port); + return -EINVAL; + } mpc = netdev_priv(ndev); ibdev_dbg(&mdev->ib_dev, "port %u ndev %p mpc %p\n", port, ndev, mpc); - err = mana_ib_cfg_vport(mdev, port - 1, pd, mana_ucontext->doorbell); + err = mana_ib_cfg_vport(mdev, port, pd, mana_ucontext->doorbell); if (err) return -ENODEV; @@ -376,8 +357,8 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, } qp->sq_umem = umem; - err = mana_ib_gd_create_dma_region(mdev, qp->sq_umem, - &qp->sq_gdma_region); + err = mana_ib_create_zero_offset_dma_region(mdev, qp->sq_umem, + &qp->sq_gdma_region); if (err) { ibdev_dbg(&mdev->ib_dev, "Failed to create dma region for create qp-raw, %d\n", @@ -386,18 +367,18 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, } ibdev_dbg(&mdev->ib_dev, - "mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n", + "create_dma_region ret %d gdma_region 0x%llx\n", err, qp->sq_gdma_region); /* Create a WQ on the same port handle used by the Ethernet */ wq_spec.gdma_region = qp->sq_gdma_region; wq_spec.queue_size = ucmd.sq_buf_size; - cq_spec.gdma_region = send_cq->gdma_region; + cq_spec.gdma_region = send_cq->queue.gdma_region; cq_spec.queue_size = send_cq->cqe * COMP_ENTRY_SIZE; cq_spec.modr_ctx_id = 0; - eq_vec = send_cq->comp_vector % gd->gdma_context->max_num_queues; - eq = &mc->eqs[eq_vec]; + eq_vec = send_cq->comp_vector % gc->max_num_queues; + eq = &mpc->ac->eqs[eq_vec]; cq_spec.attached_eq = eq->eq->id; err = mana_create_wq_obj(mpc, mpc->port_handle, GDMA_SQ, &wq_spec, @@ -411,31 +392,22 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, /* The GDMA regions are now owned by the WQ object */ qp->sq_gdma_region = GDMA_INVALID_DMA_REGION; - send_cq->gdma_region = GDMA_INVALID_DMA_REGION; + send_cq->queue.gdma_region = GDMA_INVALID_DMA_REGION; qp->sq_id = wq_spec.queue_index; - send_cq->id = cq_spec.queue_index; + send_cq->queue.id = cq_spec.queue_index; /* Create CQ table entry */ - WARN_ON(gd->gdma_context->cq_table[send_cq->id]); - gdma_cq = kzalloc(sizeof(*gdma_cq), GFP_KERNEL); - if (!gdma_cq) { - err = -ENOMEM; + err = mana_ib_install_cq_cb(mdev, send_cq); + if (err) goto err_destroy_wq_obj; - } - - gdma_cq->cq.context = send_cq; - gdma_cq->type = GDMA_CQ; - gdma_cq->cq.callback = mana_ib_cq_handler; - gdma_cq->id = send_cq->id; - gd->gdma_context->cq_table[send_cq->id] = gdma_cq; ibdev_dbg(&mdev->ib_dev, "ret %d qp->tx_object 0x%llx sq id %llu cq id %llu\n", err, - qp->tx_object, qp->sq_id, send_cq->id); + qp->tx_object, qp->sq_id, send_cq->queue.id); resp.sqid = qp->sq_id; - resp.cqid = send_cq->id; + resp.cqid = send_cq->queue.id; resp.tx_vp_offset = pd->tx_vp_offset; err = ib_copy_to_udata(udata, &resp, sizeof(resp)); @@ -450,7 +422,7 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, err_release_gdma_cq: kfree(gdma_cq); - gd->gdma_context->cq_table[send_cq->id] = NULL; + gc->cq_table[send_cq->queue.id] = NULL; err_destroy_wq_obj: mana_destroy_wq_obj(mpc, GDMA_SQ, qp->tx_object); @@ -462,7 +434,7 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd, ib_umem_release(umem); err_free_vport: - mana_ib_uncfg_vport(mdev, pd, port - 1); + mana_ib_uncfg_vport(mdev, pd, port); return err; } @@ -500,16 +472,13 @@ static int mana_ib_destroy_qp_rss(struct mana_ib_qp *qp, { struct mana_ib_dev *mdev = container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev); - struct gdma_dev *gd = &mdev->gdma_dev->gdma_context->mana; struct mana_port_context *mpc; - struct mana_context *mc; struct net_device *ndev; struct mana_ib_wq *wq; struct ib_wq *ibwq; int i; - mc = gd->driver_data; - ndev = mc->ports[qp->port - 1]; + ndev = mana_ib_get_netdev(qp->ibqp.device, qp->port); mpc = netdev_priv(ndev); for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) { @@ -527,15 +496,12 @@ static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct ib_udata *udata) { struct mana_ib_dev *mdev = container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev); - struct gdma_dev *gd = &mdev->gdma_dev->gdma_context->mana; struct ib_pd *ibpd = qp->ibqp.pd; struct mana_port_context *mpc; - struct mana_context *mc; struct net_device *ndev; struct mana_ib_pd *pd; - mc = gd->driver_data; - ndev = mc->ports[qp->port - 1]; + ndev = mana_ib_get_netdev(qp->ibqp.device, qp->port); mpc = netdev_priv(ndev); pd = container_of(ibpd, struct mana_ib_pd, ibpd); @@ -546,7 +512,7 @@ static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct ib_udata *udata) ib_umem_release(qp->sq_umem); } - mana_ib_uncfg_vport(mdev, pd, qp->port - 1); + mana_ib_uncfg_vport(mdev, pd, qp->port); return 0; } diff --git a/drivers/infiniband/hw/mana/wq.c b/drivers/infiniband/hw/mana/wq.c index 372d361510e0c..7c9c699625734 100644 --- a/drivers/infiniband/hw/mana/wq.c +++ b/drivers/infiniband/hw/mana/wq.c @@ -46,7 +46,7 @@ struct ib_wq *mana_ib_create_wq(struct ib_pd *pd, wq->wq_buf_size = ucmd.wq_buf_size; wq->rx_object = INVALID_MANA_HANDLE; - err = mana_ib_gd_create_dma_region(mdev, wq->umem, &wq->gdma_region); + err = mana_ib_create_zero_offset_dma_region(mdev, wq->umem, &wq->gdma_region); if (err) { ibdev_dbg(&mdev->ib_dev, "Failed to create dma region for create wq, %d\n", @@ -55,7 +55,7 @@ struct ib_wq *mana_ib_create_wq(struct ib_pd *pd, } ibdev_dbg(&mdev->ib_dev, - "mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n", + "create_dma_region ret %d gdma_region 0x%llx\n", err, wq->gdma_region); /* WQ ID is returned at wq_create time, doesn't know the value yet */ diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 0c3c4e64812c5..3e43687a7f6f7 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -188,7 +188,8 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num, mdev = dev->mdev; mdev_port_num = 1; } - if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) { + if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1 && + !mlx5_core_mp_enabled(mdev)) { /* set local port to one for Function-Per-Port HCA. */ mdev = dev->mdev; mdev_port_num = 1; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c2b557e642906..9fb8a544236d7 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3760,10 +3760,10 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) spin_lock_init(&dev->dm.lock); dev->dm.dev = mdev; return 0; -err: - mlx5r_macsec_dealloc_gids(dev); err_mp: mlx5_ib_cleanup_multiport_master(dev); +err: + mlx5r_macsec_dealloc_gids(dev); return err; } diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c index 96ffbbaf0a73d..5a22be14d958f 100644 --- a/drivers/infiniband/hw/mlx5/mem.c +++ b/drivers/infiniband/hw/mlx5/mem.c @@ -30,6 +30,7 @@ * SOFTWARE. */ +#include #include #include "mlx5_ib.h" #include @@ -108,7 +109,6 @@ static int post_send_nop(struct mlx5_ib_dev *dev, struct ib_qp *ibqp, u64 wr_id, __be32 mmio_wqe[16] = {}; unsigned long flags; unsigned int idx; - int i; if (unlikely(dev->mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)) return -EIO; @@ -148,10 +148,8 @@ static int post_send_nop(struct mlx5_ib_dev *dev, struct ib_qp *ibqp, u64 wr_id, * we hit doorbell */ wmb(); - for (i = 0; i < 8; i++) - mlx5_write64(&mmio_wqe[i * 2], - bf->bfreg->map + bf->offset + i * 8); - io_stop_wc(); + __iowrite64_copy(bf->bfreg->map + bf->offset, mmio_wqe, + sizeof(mmio_wqe) / 8); bf->offset ^= bf->buf_size; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index bbe79b86c7178..79ebafecca22a 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -643,9 +643,10 @@ struct mlx5_ib_mkey { unsigned int ndescs; struct wait_queue_head wait; refcount_t usecount; - /* User Mkey must hold either a rb_key or a cache_ent. */ + /* Cacheable user Mkey must hold either a rb_key or a cache_ent. */ struct mlx5r_cache_rb_key rb_key; struct mlx5_cache_ent *cache_ent; + u8 cacheable : 1; }; #define MLX5_IB_MTT_PRESENT (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index a8ee2ca1f4a17..d3c1f63791a2b 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -246,6 +246,7 @@ static void set_cache_mkc(struct mlx5_cache_ent *ent, void *mkc) MLX5_SET(mkc, mkc, access_mode_1_0, ent->rb_key.access_mode & 0x3); MLX5_SET(mkc, mkc, access_mode_4_2, (ent->rb_key.access_mode >> 2) & 0x7); + MLX5_SET(mkc, mkc, ma_translation_mode, !!ent->rb_key.ats); MLX5_SET(mkc, mkc, translations_octword_size, get_mkc_octo_size(ent->rb_key.access_mode, @@ -641,10 +642,8 @@ static int mlx5_cache_ent_insert(struct mlx5_mkey_cache *cache, new = &((*new)->rb_left); if (cmp < 0) new = &((*new)->rb_right); - if (cmp == 0) { - mutex_unlock(&cache->rb_lock); + if (cmp == 0) return -EEXIST; - } } /* Add new node and rebalance tree. */ @@ -719,6 +718,8 @@ static struct mlx5_ib_mr *_mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev, } mr->mmkey.cache_ent = ent; mr->mmkey.type = MLX5_MKEY_MR; + mr->mmkey.rb_key = ent->rb_key; + mr->mmkey.cacheable = true; init_waitqueue_head(&mr->mmkey.wait); return mr; } @@ -1158,6 +1159,7 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd, if (IS_ERR(mr)) return mr; mr->mmkey.rb_key = rb_key; + mr->mmkey.cacheable = true; return mr; } @@ -1570,7 +1572,8 @@ static bool can_use_umr_rereg_access(struct mlx5_ib_dev *dev, unsigned int diffs = current_access_flags ^ target_access_flags; if (diffs & ~(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_REMOTE_READ | IB_ACCESS_RELAXED_ORDERING)) + IB_ACCESS_REMOTE_READ | IB_ACCESS_RELAXED_ORDERING | + IB_ACCESS_REMOTE_ATOMIC)) return false; return mlx5r_umr_can_reconfig(dev, current_access_flags, target_access_flags); @@ -1835,6 +1838,23 @@ static int cache_ent_find_and_store(struct mlx5_ib_dev *dev, return ret; } +static int mlx5_revoke_mr(struct mlx5_ib_mr *mr) +{ + struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); + struct mlx5_cache_ent *ent = mr->mmkey.cache_ent; + + if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) + return 0; + + if (ent) { + spin_lock_irq(&ent->mkeys_queue.lock); + ent->in_use--; + mr->mmkey.cache_ent = NULL; + spin_unlock_irq(&ent->mkeys_queue.lock); + } + return destroy_mkey(dev, mr); +} + int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) { struct mlx5_ib_mr *mr = to_mmr(ibmr); @@ -1880,16 +1900,9 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) } /* Stop DMA */ - if (mr->umem && mlx5r_umr_can_load_pas(dev, mr->umem->length)) - if (mlx5r_umr_revoke_mr(mr) || - cache_ent_find_and_store(dev, mr)) - mr->mmkey.cache_ent = NULL; - - if (!mr->mmkey.cache_ent) { - rc = destroy_mkey(to_mdev(mr->ibmr.device), mr); - if (rc) - return rc; - } + rc = mlx5_revoke_mr(mr); + if (rc) + return rc; if (mr->umem) { bool is_odp = is_odp_mr(mr); diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index a056ea835da54..84be0c3d56995 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -199,17 +199,20 @@ int mlx5_ib_create_srq(struct ib_srq *ib_srq, int err; struct mlx5_srq_attr in = {}; __u32 max_srq_wqes = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz); + __u32 max_sge_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq) / + sizeof(struct mlx5_wqe_data_seg); if (init_attr->srq_type != IB_SRQT_BASIC && init_attr->srq_type != IB_SRQT_XRC && init_attr->srq_type != IB_SRQT_TM) return -EOPNOTSUPP; - /* Sanity check SRQ size before proceeding */ - if (init_attr->attr.max_wr >= max_srq_wqes) { - mlx5_ib_dbg(dev, "max_wr %d, cap %d\n", - init_attr->attr.max_wr, - max_srq_wqes); + /* Sanity check SRQ and sge size before proceeding */ + if (init_attr->attr.max_wr >= max_srq_wqes || + init_attr->attr.max_sge > max_sge_sz) { + mlx5_ib_dbg(dev, "max_wr %d,wr_cap %d,max_sge %d, sge_cap:%d\n", + init_attr->attr.max_wr, max_srq_wqes, + init_attr->attr.max_sge, max_sge_sz); return -EINVAL; } diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index 455e966eeff39..b27791029fa93 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -439,6 +439,7 @@ static int remove_device_files(struct super_block *sb, return PTR_ERR(dir); } simple_recursive_removal(dir, NULL); + dput(dir); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 54c723a6eddac..6f9ec8db014c7 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -33,6 +33,8 @@ void rxe_dealloc(struct ib_device *ib_dev) if (rxe->tfm) crypto_free_shash(rxe->tfm); + + mutex_destroy(&rxe->usdev_lock); } /* initialize rxe device parameters */ diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index d0bdc2d8adc82..acd2172bf092b 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -131,12 +131,12 @@ void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) { int must_sched; - skb_queue_tail(&qp->resp_pkts, skb); - - must_sched = skb_queue_len(&qp->resp_pkts) > 1; + must_sched = skb_queue_len(&qp->resp_pkts) > 0; if (must_sched != 0) rxe_counter_inc(SKB_TO_PKT(skb)->rxe, RXE_CNT_COMPLETER_SCHED); + skb_queue_tail(&qp->resp_pkts, skb); + if (must_sched) rxe_sched_task(&qp->comp.task); else diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index cd59666158b18..e5827064ab1e2 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -366,18 +366,10 @@ static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt) rxe_get(pkt->qp); atomic_inc(&pkt->qp->skb_out); - if (skb->protocol == htons(ETH_P_IP)) { + if (skb->protocol == htons(ETH_P_IP)) err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); - } else if (skb->protocol == htons(ETH_P_IPV6)) { + else err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); - } else { - rxe_dbg_qp(pkt->qp, "Unknown layer 3 protocol: %d\n", - skb->protocol); - atomic_dec(&pkt->qp->skb_out); - rxe_put(pkt->qp); - kfree_skb(skb); - return -EINVAL; - } if (unlikely(net_xmit_eval(err))) { rxe_dbg_qp(pkt->qp, "error sending packet: %d\n", err); diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index da470a925efc7..c02aa27fe5d81 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -354,6 +354,19 @@ static enum resp_states rxe_resp_check_length(struct rxe_qp *qp, * receive buffer later. For rmda operations additional * length checks are performed in check_rkey. */ + if ((qp_type(qp) == IB_QPT_GSI) || (qp_type(qp) == IB_QPT_UD)) { + unsigned int payload = payload_size(pkt); + unsigned int recv_buffer_len = 0; + int i; + + for (i = 0; i < qp->resp.wqe->dma.num_sge; i++) + recv_buffer_len += qp->resp.wqe->dma.sge[i].length; + if (payload + 40 > recv_buffer_len) { + rxe_dbg_qp(qp, "The receive buffer is too small for this UD packet.\n"); + return RESPST_ERR_LENGTH; + } + } + if (pkt->mask & RXE_PAYLOAD_MASK && ((qp_type(qp) == IB_QPT_RC) || (qp_type(qp) == IB_QPT_UC))) { unsigned int mtu = qp->mtu; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 48f86839d36a8..9f46b9f74825f 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -812,7 +812,7 @@ static void copy_inline_data_to_wqe(struct rxe_send_wqe *wqe, int i; for (i = 0; i < ibwr->num_sge; i++, sge++) { - memcpy(p, ib_virt_dma_to_page(sge->addr), sge->length); + memcpy(p, ib_virt_dma_to_ptr(sge->addr), sge->length); p += sge->length; } } @@ -888,6 +888,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, { int err = 0; unsigned long flags; + int good = 0; spin_lock_irqsave(&qp->sq.sq_lock, flags); while (ibwr) { @@ -895,12 +896,15 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, if (err) { *bad_wr = ibwr; break; + } else { + good++; } ibwr = ibwr->next; } spin_unlock_irqrestore(&qp->sq.sq_lock, flags); - if (!err) + /* kickoff processing of any posted wqes */ + if (good) rxe_sched_task(&qp->req.task); spin_lock_irqsave(&qp->state_lock, flags); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 4bd161e86f8dd..562df2b3ef187 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -184,8 +184,12 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) ppriv = ipoib_priv(pdev); - snprintf(intf_name, sizeof(intf_name), "%s.%04x", - ppriv->dev->name, pkey); + /* If you increase IFNAMSIZ, update snprintf below + * to allow longer names. + */ + BUILD_BUG_ON(IFNAMSIZ != 16); + snprintf(intf_name, sizeof(intf_name), "%.10s.%04x", ppriv->dev->name, + pkey); ndev = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); if (IS_ERR(ndev)) { diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c index d3c436ead6946..4aa80c9388f05 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c @@ -133,7 +133,7 @@ static ssize_t mpath_policy_store(struct device *dev, /* distinguish "mi" and "min-latency" with length */ len = strnlen(buf, NAME_MAX); - if (buf[len - 1] == '\n') + if (len && buf[len - 1] == '\n') len--; if (!strncasecmp(buf, "round-robin", 11) || diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 040234c01be4d..9632afbd727b6 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -3209,7 +3209,6 @@ static int srpt_add_one(struct ib_device *device) INIT_IB_EVENT_HANDLER(&sdev->event_handler, sdev->device, srpt_event_handler); - ib_register_event_handler(&sdev->event_handler); for (i = 1; i <= sdev->device->phys_port_cnt; i++) { sport = &sdev->port[i - 1]; @@ -3232,6 +3231,7 @@ static int srpt_add_one(struct ib_device *device) } } + ib_register_event_handler(&sdev->event_handler); spin_lock(&srpt_dev_lock); list_add_tail(&sdev->list, &srpt_dev_list); spin_unlock(&srpt_dev_lock); @@ -3242,7 +3242,6 @@ static int srpt_add_one(struct ib_device *device) err_port: srpt_unregister_mad_agent(sdev, i); - ib_unregister_event_handler(&sdev->event_handler); err_cm: if (sdev->cm_id) ib_destroy_cm_id(sdev->cm_id); diff --git a/drivers/input/input.c b/drivers/input/input.c index f71ea4fb173fd..3212c63dcf5ba 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1378,19 +1378,19 @@ static int input_print_modalias_bits(char *buf, int size, char name, const unsigned long *bm, unsigned int min_bit, unsigned int max_bit) { - int len = 0, i; + int bit = min_bit; + int len = 0; len += snprintf(buf, max(size, 0), "%c", name); - for (i = min_bit; i < max_bit; i++) - if (bm[BIT_WORD(i)] & BIT_MASK(i)) - len += snprintf(buf + len, max(size - len, 0), "%X,", i); + for_each_set_bit_from(bit, bm, max_bit) + len += snprintf(buf + len, max(size - len, 0), "%X,", bit); return len; } -static int input_print_modalias(char *buf, int size, const struct input_dev *id, - int add_cr) +static int input_print_modalias_parts(char *buf, int size, int full_len, + const struct input_dev *id) { - int len; + int len, klen, remainder, space; len = snprintf(buf, max(size, 0), "input:b%04Xv%04Xp%04Xe%04X-", @@ -1399,8 +1399,48 @@ static int input_print_modalias(char *buf, int size, const struct input_dev *id, len += input_print_modalias_bits(buf + len, size - len, 'e', id->evbit, 0, EV_MAX); - len += input_print_modalias_bits(buf + len, size - len, + + /* + * Calculate the remaining space in the buffer making sure we + * have place for the terminating 0. + */ + space = max(size - (len + 1), 0); + + klen = input_print_modalias_bits(buf + len, size - len, 'k', id->keybit, KEY_MIN_INTERESTING, KEY_MAX); + len += klen; + + /* + * If we have more data than we can fit in the buffer, check + * if we can trim key data to fit in the rest. We will indicate + * that key data is incomplete by adding "+" sign at the end, like + * this: * "k1,2,3,45,+,". + * + * Note that we shortest key info (if present) is "k+," so we + * can only try to trim if key data is longer than that. + */ + if (full_len && size < full_len + 1 && klen > 3) { + remainder = full_len - len; + /* + * We can only trim if we have space for the remainder + * and also for at least "k+," which is 3 more characters. + */ + if (remainder <= space - 3) { + /* + * We are guaranteed to have 'k' in the buffer, so + * we need at least 3 additional bytes for storing + * "+," in addition to the remainder. + */ + for (int i = size - 1 - remainder - 3; i >= 0; i--) { + if (buf[i] == 'k' || buf[i] == ',') { + strcpy(buf + i + 1, "+,"); + len = i + 3; /* Not counting '\0' */ + break; + } + } + } + } + len += input_print_modalias_bits(buf + len, size - len, 'r', id->relbit, 0, REL_MAX); len += input_print_modalias_bits(buf + len, size - len, @@ -1416,12 +1456,25 @@ static int input_print_modalias(char *buf, int size, const struct input_dev *id, len += input_print_modalias_bits(buf + len, size - len, 'w', id->swbit, 0, SW_MAX); - if (add_cr) - len += snprintf(buf + len, max(size - len, 0), "\n"); - return len; } +static int input_print_modalias(char *buf, int size, const struct input_dev *id) +{ + int full_len; + + /* + * Printing is done in 2 passes: first one figures out total length + * needed for the modalias string, second one will try to trim key + * data in case when buffer is too small for the entire modalias. + * If the buffer is too small regardless, it will fill as much as it + * can (without trimming key data) into the buffer and leave it to + * the caller to figure out what to do with the result. + */ + full_len = input_print_modalias_parts(NULL, 0, 0, id); + return input_print_modalias_parts(buf, size, full_len, id); +} + static ssize_t input_dev_show_modalias(struct device *dev, struct device_attribute *attr, char *buf) @@ -1429,7 +1482,9 @@ static ssize_t input_dev_show_modalias(struct device *dev, struct input_dev *id = to_input_dev(dev); ssize_t len; - len = input_print_modalias(buf, PAGE_SIZE, id, 1); + len = input_print_modalias(buf, PAGE_SIZE, id); + if (len < PAGE_SIZE - 2) + len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return min_t(int, len, PAGE_SIZE); } @@ -1641,6 +1696,23 @@ static int input_add_uevent_bm_var(struct kobj_uevent_env *env, return 0; } +/* + * This is a pretty gross hack. When building uevent data the driver core + * may try adding more environment variables to kobj_uevent_env without + * telling us, so we have no idea how much of the buffer we can use to + * avoid overflows/-ENOMEM elsewhere. To work around this let's artificially + * reduce amount of memory we will use for the modalias environment variable. + * + * The potential additions are: + * + * SEQNUM=18446744073709551615 - (%llu - 28 bytes) + * HOME=/ (6 bytes) + * PATH=/sbin:/bin:/usr/sbin:/usr/bin (34 bytes) + * + * 68 bytes total. Allow extra buffer - 96 bytes + */ +#define UEVENT_ENV_EXTRA_LEN 96 + static int input_add_uevent_modalias_var(struct kobj_uevent_env *env, const struct input_dev *dev) { @@ -1650,9 +1722,11 @@ static int input_add_uevent_modalias_var(struct kobj_uevent_env *env, return -ENOMEM; len = input_print_modalias(&env->buf[env->buflen - 1], - sizeof(env->buf) - env->buflen, - dev, 0); - if (len >= (sizeof(env->buf) - env->buflen)) + (int)sizeof(env->buf) - env->buflen - + UEVENT_ENV_EXTRA_LEN, + dev); + if (len >= ((int)sizeof(env->buf) - env->buflen - + UEVENT_ENV_EXTRA_LEN)) return -ENOMEM; env->buflen += len; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 14c828adebf78..c2de2f063cb8d 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -207,6 +207,7 @@ static const struct xpad_device { { 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 }, { 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 }, { 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 }, + { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE }, { 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX }, { 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX }, { 0x0c12, 0x8802, "Zeroplus Xbox Controller", 0, XTYPE_XBOX }, @@ -366,6 +367,8 @@ static const struct xpad_device { { 0x24c6, 0x5d04, "Razer Sabertooth", 0, XTYPE_XBOX360 }, { 0x24c6, 0xfafe, "Rock Candy Gamepad for Xbox 360", 0, XTYPE_XBOX360 }, { 0x2563, 0x058d, "OneXPlayer Gamepad", 0, XTYPE_XBOX360 }, + { 0x294b, 0x3303, "Snakebyte GAMEPAD BASE X", 0, XTYPE_XBOXONE }, + { 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE }, { 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE }, { 0x2dc8, 0x3106, "8BitDo Pro 2 Wired Controller", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 }, @@ -480,6 +483,7 @@ static const struct usb_device_id xpad_table[] = { { USB_DEVICE(0x0738, 0x4540) }, /* Mad Catz Beat Pad */ XPAD_XBOXONE_VENDOR(0x0738), /* Mad Catz FightStick TE 2 */ XPAD_XBOX360_VENDOR(0x07ff), /* Mad Catz Gamepad */ + XPAD_XBOXONE_VENDOR(0x0b05), /* ASUS controllers */ XPAD_XBOX360_VENDOR(0x0c12), /* Zeroplus X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x0e6f), /* 0x0e6f Xbox 360 controllers */ XPAD_XBOXONE_VENDOR(0x0e6f), /* 0x0e6f Xbox One controllers */ @@ -507,6 +511,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOXONE_VENDOR(0x24c6), /* PowerA controllers */ XPAD_XBOX360_VENDOR(0x2563), /* OneXPlayer Gamepad */ XPAD_XBOX360_VENDOR(0x260d), /* Dareu H101 */ + XPAD_XBOXONE_VENDOR(0x294b), /* Snakebyte */ XPAD_XBOX360_VENDOR(0x2c22), /* Qanba Controllers */ XPAD_XBOX360_VENDOR(0x2dc8), /* 8BitDo Pro 2 Wired Controller */ XPAD_XBOXONE_VENDOR(0x2dc8), /* 8BitDo Pro 2 Wired Controller for Xbox */ diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c index 6e8cc28debd97..80d16c92a08b3 100644 --- a/drivers/input/misc/ims-pcu.c +++ b/drivers/input/misc/ims-pcu.c @@ -42,8 +42,8 @@ struct ims_pcu_backlight { #define IMS_PCU_PART_NUMBER_LEN 15 #define IMS_PCU_SERIAL_NUMBER_LEN 8 #define IMS_PCU_DOM_LEN 8 -#define IMS_PCU_FW_VERSION_LEN (9 + 1) -#define IMS_PCU_BL_VERSION_LEN (9 + 1) +#define IMS_PCU_FW_VERSION_LEN 16 +#define IMS_PCU_BL_VERSION_LEN 16 #define IMS_PCU_BL_RESET_REASON_LEN (2 + 1) #define IMS_PCU_PCU_B_DEVICE_ID 5 diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c index 36aeeae776110..9ca5a743f19fe 100644 --- a/drivers/input/misc/iqs7222.c +++ b/drivers/input/misc/iqs7222.c @@ -620,6 +620,118 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = { }, }, }, + { + .prod_num = IQS7222_PROD_NUM_D, + .fw_major = 1, + .fw_minor = 2, + .touch_link = 1770, + .allow_offset = 9, + .event_offset = 10, + .comms_offset = 11, + .reg_grps = { + [IQS7222_REG_GRP_STAT] = { + .base = IQS7222_SYS_STATUS, + .num_row = 1, + .num_col = 7, + }, + [IQS7222_REG_GRP_CYCLE] = { + .base = 0x8000, + .num_row = 7, + .num_col = 2, + }, + [IQS7222_REG_GRP_GLBL] = { + .base = 0x8700, + .num_row = 1, + .num_col = 3, + }, + [IQS7222_REG_GRP_BTN] = { + .base = 0x9000, + .num_row = 14, + .num_col = 3, + }, + [IQS7222_REG_GRP_CHAN] = { + .base = 0xA000, + .num_row = 14, + .num_col = 4, + }, + [IQS7222_REG_GRP_FILT] = { + .base = 0xAE00, + .num_row = 1, + .num_col = 2, + }, + [IQS7222_REG_GRP_TPAD] = { + .base = 0xB000, + .num_row = 1, + .num_col = 24, + }, + [IQS7222_REG_GRP_GPIO] = { + .base = 0xC000, + .num_row = 3, + .num_col = 3, + }, + [IQS7222_REG_GRP_SYS] = { + .base = IQS7222_SYS_SETUP, + .num_row = 1, + .num_col = 12, + }, + }, + }, + { + .prod_num = IQS7222_PROD_NUM_D, + .fw_major = 1, + .fw_minor = 1, + .touch_link = 1774, + .allow_offset = 9, + .event_offset = 10, + .comms_offset = 11, + .reg_grps = { + [IQS7222_REG_GRP_STAT] = { + .base = IQS7222_SYS_STATUS, + .num_row = 1, + .num_col = 7, + }, + [IQS7222_REG_GRP_CYCLE] = { + .base = 0x8000, + .num_row = 7, + .num_col = 2, + }, + [IQS7222_REG_GRP_GLBL] = { + .base = 0x8700, + .num_row = 1, + .num_col = 3, + }, + [IQS7222_REG_GRP_BTN] = { + .base = 0x9000, + .num_row = 14, + .num_col = 3, + }, + [IQS7222_REG_GRP_CHAN] = { + .base = 0xA000, + .num_row = 14, + .num_col = 4, + }, + [IQS7222_REG_GRP_FILT] = { + .base = 0xAE00, + .num_row = 1, + .num_col = 2, + }, + [IQS7222_REG_GRP_TPAD] = { + .base = 0xB000, + .num_row = 1, + .num_col = 24, + }, + [IQS7222_REG_GRP_GPIO] = { + .base = 0xC000, + .num_row = 3, + .num_col = 3, + }, + [IQS7222_REG_GRP_SYS] = { + .base = IQS7222_SYS_SETUP, + .num_row = 1, + .num_col = 12, + }, + }, + }, { .prod_num = IQS7222_PROD_NUM_D, .fw_major = 0, diff --git a/drivers/input/misc/pm8xxx-vibrator.c b/drivers/input/misc/pm8xxx-vibrator.c index 5c288fe7accf1..79f478d3a9b37 100644 --- a/drivers/input/misc/pm8xxx-vibrator.c +++ b/drivers/input/misc/pm8xxx-vibrator.c @@ -13,7 +13,8 @@ #define VIB_MAX_LEVEL_mV (3100) #define VIB_MIN_LEVEL_mV (1200) -#define VIB_MAX_LEVELS (VIB_MAX_LEVEL_mV - VIB_MIN_LEVEL_mV) +#define VIB_PER_STEP_mV (100) +#define VIB_MAX_LEVELS (VIB_MAX_LEVEL_mV - VIB_MIN_LEVEL_mV + VIB_PER_STEP_mV) #define MAX_FF_SPEED 0xff @@ -117,10 +118,10 @@ static void pm8xxx_work_handler(struct work_struct *work) vib->active = true; vib->level = ((VIB_MAX_LEVELS * vib->speed) / MAX_FF_SPEED) + VIB_MIN_LEVEL_mV; - vib->level /= 100; + vib->level /= VIB_PER_STEP_mV; } else { vib->active = false; - vib->level = VIB_MIN_LEVEL_mV / 100; + vib->level = VIB_MIN_LEVEL_mV / VIB_PER_STEP_mV; } pm8xxx_vib_set(vib, vib->active); diff --git a/drivers/input/mouse/amimouse.c b/drivers/input/mouse/amimouse.c index cda0c3ff5a288..2fbbaeb76d708 100644 --- a/drivers/input/mouse/amimouse.c +++ b/drivers/input/mouse/amimouse.c @@ -132,7 +132,13 @@ static void __exit amimouse_remove(struct platform_device *pdev) input_unregister_device(dev); } -static struct platform_driver amimouse_driver = { +/* + * amimouse_remove() lives in .exit.text. For drivers registered via + * module_platform_driver_probe() this is ok because they cannot get unbound at + * runtime. So mark the driver struct with __refdata to prevent modpost + * triggering a section mismatch warning. + */ +static struct platform_driver amimouse_driver __refdata = { .remove_new = __exit_p(amimouse_remove), .driver = { .name = "amiga-mouse", diff --git a/drivers/input/mouse/cyapa.c b/drivers/input/mouse/cyapa.c index 5979deabe23d1..256f757a13267 100644 --- a/drivers/input/mouse/cyapa.c +++ b/drivers/input/mouse/cyapa.c @@ -1347,10 +1347,16 @@ static int cyapa_suspend(struct device *dev) u8 power_mode; int error; - error = mutex_lock_interruptible(&cyapa->state_sync_lock); + error = mutex_lock_interruptible(&cyapa->input->mutex); if (error) return error; + error = mutex_lock_interruptible(&cyapa->state_sync_lock); + if (error) { + mutex_unlock(&cyapa->input->mutex); + return error; + } + /* * Runtime PM is enable only when device is in operational mode and * users in use, so need check it before disable it to @@ -1385,6 +1391,8 @@ static int cyapa_suspend(struct device *dev) cyapa->irq_wake = (enable_irq_wake(client->irq) == 0); mutex_unlock(&cyapa->state_sync_lock); + mutex_unlock(&cyapa->input->mutex); + return 0; } @@ -1394,6 +1402,7 @@ static int cyapa_resume(struct device *dev) struct cyapa *cyapa = i2c_get_clientdata(client); int error; + mutex_lock(&cyapa->input->mutex); mutex_lock(&cyapa->state_sync_lock); if (device_may_wakeup(dev) && cyapa->irq_wake) { @@ -1412,6 +1421,7 @@ static int cyapa_resume(struct device *dev) enable_irq(client->irq); mutex_unlock(&cyapa->state_sync_lock); + mutex_unlock(&cyapa->input->mutex); return 0; } diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c index d272f1ec27ba5..c30afa29a9c71 100644 --- a/drivers/input/mouse/cypress_ps2.c +++ b/drivers/input/mouse/cypress_ps2.c @@ -387,7 +387,9 @@ static int cypress_set_input_params(struct input_dev *input, if (ret < 0) return ret; +#if ( CYPRESS_SIMULATED_MT != 1 ) __set_bit(INPUT_PROP_SEMI_MT, input->propbit); +#endif input_abs_set_res(input, ABS_X, cytp->tp_res_x); input_abs_set_res(input, ABS_Y, cytp->tp_res_y); @@ -473,6 +475,22 @@ static int cypress_parse_packet(struct psmouse *psmouse, ((packet[5] & 0x0f) << 8) | packet[7]; if (cytp->mode & CYTP_BIT_ABS_PRESSURE) report_data->contacts[1].z = report_data->contacts[0].z; +#if ( CYPRESS_SIMULATED_MT == 1 ) + /* simulate contact positions for >2 fingers */ + if ( report_data->contact_cnt >= 3 ) { + int i; + for ( i=1; icontact_cnt; i++ ) { + report_data->contacts[i].x = + report_data->contacts[0].x + + 100*(i)*((i%2)?-1:1); + report_data->contacts[i].y = + report_data->contacts[0].y; + if (cytp->mode & CYTP_BIT_ABS_PRESSURE) + report_data->contacts[i].z = + report_data->contacts[0].z; + } + } +#endif } report_data->left = (header_byte & BTN_LEFT_BIT) ? 1 : 0; diff --git a/drivers/input/mouse/cypress_ps2.h b/drivers/input/mouse/cypress_ps2.h index bb4979d06bf99..4d5028a43341e 100644 --- a/drivers/input/mouse/cypress_ps2.h +++ b/drivers/input/mouse/cypress_ps2.h @@ -131,7 +131,18 @@ #define RESP_REMOTE_BIT 0x40 #define RESP_SMBUS_BIT 0x80 -#define CYTP_MAX_MT_SLOTS 2 +/* + * CYPRESS_SIMULATED_MT + * set to 1 for simulated multitouch (up to 5 contact points) + * set to 0 for SEMI_MT (only 2 corner points, and count of fingers) + */ +#define CYPRESS_SIMULATED_MT 1 + +#if ( CYPRESS_SIMULATED_MT == 1 ) +# define CYTP_MAX_MT_SLOTS 5 +#else +# define CYTP_MAX_MT_SLOTS 2 +#endif struct cytp_contact { int x; diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index 42eaebb3bf5cc..ef9ea295f9e03 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -1196,7 +1196,11 @@ static int rmi_driver_probe(struct device *dev) } rmi_driver_set_input_params(rmi_dev, data->input); data->input->phys = devm_kasprintf(dev, GFP_KERNEL, - "%s/input0", dev_name(dev)); + "%s/input0", dev_name(dev)); + if (!data->input->phys) { + retval = -ENOMEM; + goto err; + } } retval = rmi_init_functions(data); diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 9fbb8d31575ae..7a9b0c3551981 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -178,6 +179,24 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id); static bool (*i8042_platform_filter)(unsigned char data, unsigned char str, struct serio *serio); +static int __init i8042_set_noaux(const struct dmi_system_id *dmi) +{ + i8042_noaux = true; + return 1; +} + +static const struct dmi_system_id i8042_quirks[] = { + { + .callback = i8042_set_noaux, + .ident = "Dell laptop", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision 5550"), + }, + }, + {}, +}; + void i8042_lock_chip(void) { mutex_lock(&i8042_mutex); @@ -621,7 +640,7 @@ static int i8042_enable_kbd_port(void) if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { i8042_ctr &= ~I8042_CTR_KBDINT; i8042_ctr |= I8042_CTR_KBDDIS; - pr_err("Failed to enable KBD port\n"); + pr_info("Failed to enable KBD port\n"); return -EIO; } @@ -640,7 +659,7 @@ static int i8042_enable_aux_port(void) if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { i8042_ctr &= ~I8042_CTR_AUXINT; i8042_ctr |= I8042_CTR_AUXDIS; - pr_err("Failed to enable AUX port\n"); + pr_info("Failed to enable AUX port\n"); return -EIO; } @@ -732,7 +751,7 @@ static int i8042_check_mux(void) i8042_ctr &= ~I8042_CTR_AUXINT; if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { - pr_err("Failed to disable AUX port, can't use MUX\n"); + pr_info("Failed to disable AUX port, can't use MUX\n"); return -EIO; } @@ -947,25 +966,28 @@ static int i8042_controller_selftest(void) { unsigned char param; int i = 0; + int ret; /* * We try this 5 times; on some really fragile systems this does not * take the first time... */ - do { + while (i++ < 5) { - if (i8042_command(¶m, I8042_CMD_CTL_TEST)) { - pr_err("i8042 controller selftest timeout\n"); - return -ENODEV; - } - - if (param == I8042_RET_CTL_TEST) + ret = i8042_command(¶m, I8042_CMD_CTL_TEST); + if (ret) + pr_info("i8042 controller selftest timeout (%d/5)\n", i); + else if (param == I8042_RET_CTL_TEST) return 0; + else + dbg("i8042 controller selftest: %#x != %#x\n", + param, I8042_RET_CTL_TEST); - dbg("i8042 controller selftest: %#x != %#x\n", - param, I8042_RET_CTL_TEST); msleep(50); - } while (i++ < 5); + } + + if (ret) + return -ENODEV; #ifdef CONFIG_X86 /* @@ -977,7 +999,7 @@ static int i8042_controller_selftest(void) pr_info("giving up on controller selftest, continuing anyway...\n"); return 0; #else - pr_err("i8042 controller selftest failed\n"); + pr_info("i8042 controller selftest failed\n"); return -EIO; #endif } @@ -1558,6 +1580,8 @@ static int i8042_probe(struct platform_device *dev) i8042_dritek_enable(); #endif + dmi_check_system(i8042_quirks); + if (!i8042_noaux) { error = i8042_setup_aux(); if (error && error != -ENODEV && error != -EBUSY) diff --git a/drivers/input/serio/ioc3kbd.c b/drivers/input/serio/ioc3kbd.c index 50552dc7b4f5e..676b0bda3d720 100644 --- a/drivers/input/serio/ioc3kbd.c +++ b/drivers/input/serio/ioc3kbd.c @@ -200,9 +200,16 @@ static void ioc3kbd_remove(struct platform_device *pdev) serio_unregister_port(d->aux); } +static const struct platform_device_id ioc3kbd_id_table[] = { + { "ioc3-kbd", }, + { } +}; +MODULE_DEVICE_TABLE(platform, ioc3kbd_id_table); + static struct platform_driver ioc3kbd_driver = { .probe = ioc3kbd_probe, .remove_new = ioc3kbd_remove, + .id_table = ioc3kbd_id_table, .driver = { .name = "ioc3-kbd", }, diff --git a/drivers/input/touchscreen/imagis.c b/drivers/input/touchscreen/imagis.c index 07111ca244556..55ecebe981445 100644 --- a/drivers/input/touchscreen/imagis.c +++ b/drivers/input/touchscreen/imagis.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include #include #include @@ -23,12 +24,9 @@ #define IST3038C_I2C_RETRY_COUNT 3 #define IST3038C_MAX_FINGER_NUM 10 #define IST3038C_X_MASK GENMASK(23, 12) -#define IST3038C_X_SHIFT 12 #define IST3038C_Y_MASK GENMASK(11, 0) #define IST3038C_AREA_MASK GENMASK(27, 24) -#define IST3038C_AREA_SHIFT 24 #define IST3038C_FINGER_COUNT_MASK GENMASK(15, 12) -#define IST3038C_FINGER_COUNT_SHIFT 12 #define IST3038C_FINGER_STATUS_MASK GENMASK(9, 0) struct imagis_ts { @@ -92,8 +90,7 @@ static irqreturn_t imagis_interrupt(int irq, void *dev_id) goto out; } - finger_count = (intr_message & IST3038C_FINGER_COUNT_MASK) >> - IST3038C_FINGER_COUNT_SHIFT; + finger_count = FIELD_GET(IST3038C_FINGER_COUNT_MASK, intr_message); if (finger_count > IST3038C_MAX_FINGER_NUM) { dev_err(&ts->client->dev, "finger count %d is more than maximum supported\n", @@ -101,7 +98,7 @@ static irqreturn_t imagis_interrupt(int irq, void *dev_id) goto out; } - finger_pressed = intr_message & IST3038C_FINGER_STATUS_MASK; + finger_pressed = FIELD_GET(IST3038C_FINGER_STATUS_MASK, intr_message); for (i = 0; i < finger_count; i++) { error = imagis_i2c_read_reg(ts, @@ -118,12 +115,11 @@ static irqreturn_t imagis_interrupt(int irq, void *dev_id) input_mt_report_slot_state(ts->input_dev, MT_TOOL_FINGER, finger_pressed & BIT(i)); touchscreen_report_pos(ts->input_dev, &ts->prop, - (finger_status & IST3038C_X_MASK) >> - IST3038C_X_SHIFT, - finger_status & IST3038C_Y_MASK, 1); + FIELD_GET(IST3038C_X_MASK, finger_status), + FIELD_GET(IST3038C_Y_MASK, finger_status), + true); input_report_abs(ts->input_dev, ABS_MT_TOUCH_MAJOR, - (finger_status & IST3038C_AREA_MASK) >> - IST3038C_AREA_SHIFT); + FIELD_GET(IST3038C_AREA_MASK, finger_status)); } input_mt_sync_frame(ts->input_dev); @@ -210,7 +206,7 @@ static int imagis_init_input_dev(struct imagis_ts *ts) input_set_capability(input_dev, EV_ABS, ABS_MT_POSITION_X); input_set_capability(input_dev, EV_ABS, ABS_MT_POSITION_Y); - input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0); + input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, 16, 0, 0); touchscreen_parse_properties(input_dev, true, &ts->prop); if (!ts->prop.max_x || !ts->prop.max_y) { diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 50bac2d79d9b5..68edb07d4443e 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -176,6 +176,8 @@ static struct icc_path *path_init(struct device *dev, struct icc_node *dst, path->num_nodes = num_nodes; + mutex_lock(&icc_bw_lock); + for (i = num_nodes - 1; i >= 0; i--) { node->provider->users++; hlist_add_head(&path->reqs[i].req_node, &node->req_list); @@ -186,6 +188,8 @@ static struct icc_path *path_init(struct device *dev, struct icc_node *dst, node = node->reverse; } + mutex_unlock(&icc_bw_lock); + return path; } @@ -792,12 +796,16 @@ void icc_put(struct icc_path *path) pr_err("%s: error (%d)\n", __func__, ret); mutex_lock(&icc_lock); + mutex_lock(&icc_bw_lock); + for (i = 0; i < path->num_nodes; i++) { node = path->reqs[i].node; hlist_del(&path->reqs[i].req_node); if (!WARN_ON(!node->provider->users)) node->provider->users--; } + + mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); kfree_const(path->name); diff --git a/drivers/interconnect/qcom/qcm2290.c b/drivers/interconnect/qcom/qcm2290.c index 96735800b13c0..ba4cc08684d63 100644 --- a/drivers/interconnect/qcom/qcm2290.c +++ b/drivers/interconnect/qcom/qcm2290.c @@ -164,7 +164,7 @@ static struct qcom_icc_node mas_snoc_bimc = { .name = "mas_snoc_bimc", .buswidth = 16, .qos.ap_owned = true, - .qos.qos_port = 2, + .qos.qos_port = 6, .qos.qos_mode = NOC_QOS_MODE_BYPASS, .mas_rpm_id = 164, .slv_rpm_id = -1, diff --git a/drivers/interconnect/qcom/x1e80100.c b/drivers/interconnect/qcom/x1e80100.c index cbaf4f9c41be6..06f0a6d6cbbc0 100644 --- a/drivers/interconnect/qcom/x1e80100.c +++ b/drivers/interconnect/qcom/x1e80100.c @@ -116,15 +116,6 @@ static struct qcom_icc_node xm_sdc2 = { .links = { X1E80100_SLAVE_A2NOC_SNOC }, }; -static struct qcom_icc_node ddr_perf_mode_master = { - .name = "ddr_perf_mode_master", - .id = X1E80100_MASTER_DDR_PERF_MODE, - .channels = 1, - .buswidth = 4, - .num_links = 1, - .links = { X1E80100_SLAVE_DDR_PERF_MODE }, -}; - static struct qcom_icc_node qup0_core_master = { .name = "qup0_core_master", .id = X1E80100_MASTER_QUP_CORE_0, @@ -832,14 +823,6 @@ static struct qcom_icc_node qns_a2noc_snoc = { .links = { X1E80100_MASTER_A2NOC_SNOC }, }; -static struct qcom_icc_node ddr_perf_mode_slave = { - .name = "ddr_perf_mode_slave", - .id = X1E80100_SLAVE_DDR_PERF_MODE, - .channels = 1, - .buswidth = 4, - .num_links = 0, -}; - static struct qcom_icc_node qup0_core_slave = { .name = "qup0_core_slave", .id = X1E80100_SLAVE_QUP_CORE_0, @@ -1591,12 +1574,6 @@ static struct qcom_icc_bcm bcm_acv = { .nodes = { &ebi }, }; -static struct qcom_icc_bcm bcm_acv_perf = { - .name = "ACV_PERF", - .num_nodes = 1, - .nodes = { &ddr_perf_mode_slave }, -}; - static struct qcom_icc_bcm bcm_ce0 = { .name = "CE0", .num_nodes = 1, @@ -1863,18 +1840,15 @@ static const struct qcom_icc_desc x1e80100_aggre2_noc = { }; static struct qcom_icc_bcm * const clk_virt_bcms[] = { - &bcm_acv_perf, &bcm_qup0, &bcm_qup1, &bcm_qup2, }; static struct qcom_icc_node * const clk_virt_nodes[] = { - [MASTER_DDR_PERF_MODE] = &ddr_perf_mode_master, [MASTER_QUP_CORE_0] = &qup0_core_master, [MASTER_QUP_CORE_1] = &qup1_core_master, [MASTER_QUP_CORE_2] = &qup2_core_master, - [SLAVE_DDR_PERF_MODE] = &ddr_perf_mode_slave, [SLAVE_QUP_CORE_0] = &qup0_core_slave, [SLAVE_QUP_CORE_1] = &qup1_core_slave, [SLAVE_QUP_CORE_2] = &qup2_core_slave, diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 9a29d742617e3..9dbb55e745bd9 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -196,7 +196,7 @@ source "drivers/iommu/iommufd/Kconfig" config IRQ_REMAP bool "Support for Interrupt Remapping" depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI - select DMAR_TABLE + select DMAR_TABLE if INTEL_IOMMU help Supports Interrupt remapping for IO-APIC and MSI devices. To use x2apic mode in the CPU's which support x2APIC enhancements or diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index c83bd0c2a1c92..63d1bd37fb073 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1677,8 +1677,17 @@ static void __init free_pci_segments(void) } } +static void __init free_sysfs(struct amd_iommu *iommu) +{ + if (iommu->iommu.dev) { + iommu_device_unregister(&iommu->iommu); + iommu_device_sysfs_remove(&iommu->iommu); + } +} + static void __init free_iommu_one(struct amd_iommu *iommu) { + free_sysfs(iommu); free_cwwb_sem(iommu); free_command_buffer(iommu); free_event_buffer(iommu); @@ -2068,6 +2077,9 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) /* Prevent binding other PCI device drivers to IOMMU devices */ iommu->dev->match_driver = false; + /* ACPI _PRT won't have an IRQ for IOMMU */ + iommu->dev->irq_managed = 1; + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, &iommu->cap); diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 4283dd8191f05..f945bf3253ce0 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2593,6 +2593,10 @@ static int amd_iommu_def_domain_type(struct device *dev) if (!dev_data) return 0; + /* Always use DMA domain for untrusted device */ + if (dev_is_pci(dev) && to_pci_dev(dev)->untrusted) + return IOMMU_DOMAIN_DMA; + /* * Do not identity map IOMMUv2 capable devices when: * - memory encryption is active, because some of those devices diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 0ffb1cf17e0b2..5071a8495a78c 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2398,8 +2398,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) return -EBUSY; } - arm_smmu_detach_dev(master); - mutex_lock(&smmu_domain->init_mutex); if (!smmu_domain->smmu) { @@ -2414,6 +2412,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) if (ret) return ret; + /* + * Prevent arm_smmu_share_asid() from trying to change the ASID + * of either the old or new domain while we are working on it. + * This allows the STE and the smmu_domain->devices list to + * be inconsistent during this routine. + */ + mutex_lock(&arm_smmu_asid_lock); + + arm_smmu_detach_dev(master); + master->domain = smmu_domain; /* @@ -2439,13 +2447,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) } } - /* - * Prevent SVA from concurrently modifying the CD or writing to - * the CD entry - */ - mutex_lock(&arm_smmu_asid_lock); ret = arm_smmu_write_ctx_desc(master, IOMMU_NO_PASID, &smmu_domain->cd); - mutex_unlock(&arm_smmu_asid_lock); if (ret) { master->domain = NULL; goto out_list_del; @@ -2455,13 +2457,15 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) arm_smmu_install_ste_for_dev(master); arm_smmu_enable_ats(master); - return 0; + goto out_unlock; out_list_del: spin_lock_irqsave(&smmu_domain->devices_lock, flags); list_del(&master->domain_head); spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); +out_unlock: + mutex_unlock(&arm_smmu_asid_lock); return ret; } @@ -3177,7 +3181,7 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) smmu->priq.q.irq = msi_get_virq(dev, PRIQ_MSI_INDEX); /* Add callback to free MSIs on teardown */ - devm_add_action(dev, arm_smmu_free_msis, dev); + devm_add_action_or_reset(dev, arm_smmu_free_msis, dev); } static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c index 87bf522b9d2ee..957d988b6d832 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c @@ -221,11 +221,9 @@ static irqreturn_t nvidia_smmu_context_fault(int irq, void *dev) unsigned int inst; irqreturn_t ret = IRQ_NONE; struct arm_smmu_device *smmu; - struct iommu_domain *domain = dev; - struct arm_smmu_domain *smmu_domain; + struct arm_smmu_domain *smmu_domain = dev; struct nvidia_smmu *nvidia; - smmu_domain = container_of(domain, struct arm_smmu_domain, domain); smmu = smmu_domain->smmu; nvidia = to_nvidia_smmu(smmu); diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 50ccc4f1ef81c..639efa0c40721 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1706,6 +1706,14 @@ static size_t iommu_dma_opt_mapping_size(void) return iova_rcache_range(); } +static size_t iommu_dma_max_mapping_size(struct device *dev) +{ + if (dev_is_untrusted(dev)) + return swiotlb_max_mapping_size(dev); + + return SIZE_MAX; +} + static const struct dma_map_ops iommu_dma_ops = { .flags = DMA_F_PCI_P2PDMA_SUPPORTED, .alloc = iommu_dma_alloc, @@ -1728,6 +1736,7 @@ static const struct dma_map_ops iommu_dma_ops = { .unmap_resource = iommu_dma_unmap_resource, .get_merge_boundary = iommu_dma_get_merge_boundary, .opt_mapping_size = iommu_dma_opt_mapping_size, + .max_mapping_size = iommu_dma_max_mapping_size, }; /* diff --git a/drivers/iommu/intel/Makefile b/drivers/iommu/intel/Makefile index 5dabf081a7793..5402b699a1229 100644 --- a/drivers/iommu/intel/Makefile +++ b/drivers/iommu/intel/Makefile @@ -5,5 +5,7 @@ obj-$(CONFIG_DMAR_TABLE) += trace.o cap_audit.o obj-$(CONFIG_DMAR_PERF) += perf.o obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o +ifdef CONFIG_INTEL_IOMMU obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o +endif obj-$(CONFIG_INTEL_IOMMU_PERF_EVENTS) += perfmon.o diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 23cb80d62a9ab..36d7427b12026 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1095,7 +1095,9 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->agaw = agaw; iommu->msagaw = msagaw; iommu->segment = drhd->segment; - + iommu->device_rbtree = RB_ROOT; + spin_lock_init(&iommu->device_rbtree_lock); + mutex_init(&iommu->iopf_lock); iommu->node = NUMA_NO_NODE; ver = readl(iommu->reg + DMAR_VER_REG); @@ -1271,6 +1273,8 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) { u32 fault; int head, tail; + struct device *dev; + u64 iqe_err, ite_sid; struct q_inval *qi = iommu->qi; int shift = qi_shift(iommu); @@ -1315,6 +1319,13 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) tail = readl(iommu->reg + DMAR_IQT_REG); tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH; + /* + * SID field is valid only when the ITE field is Set in FSTS_REG + * see Intel VT-d spec r4.1, section 11.4.9.9 + */ + iqe_err = dmar_readq(iommu->reg + DMAR_IQER_REG); + ite_sid = DMAR_IQER_REG_ITESID(iqe_err); + writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG); pr_info("Invalidation Time-out Error (ITE) cleared\n"); @@ -1324,6 +1335,19 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index) head = (head - 2 + QI_LENGTH) % QI_LENGTH; } while (head != tail); + /* + * If device was released or isn't present, no need to retry + * the ATS invalidate request anymore. + * + * 0 value of ite_sid means old VT-d device, no ite_sid value. + * see Intel VT-d spec r4.1, section 11.4.9.9 + */ + if (ite_sid) { + dev = device_rbtree_find(iommu, ite_sid); + if (!dev || !dev_is_pci(dev) || + !pci_device_is_present(to_pci_dev(dev))) + return -ETIMEDOUT; + } if (qi->desc_status[wait_index] == QI_ABORT) return -EAGAIN; } diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 11652e0bcab3a..c4c6240d14f98 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -38,6 +38,14 @@ #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY) #define IS_USB_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB) #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) +#define IS_INTEL_IPU(pdev) ((pdev)->vendor == PCI_VENDOR_ID_INTEL && \ + ((pdev)->device == 0xa75d || \ + (pdev)->device == 0x9a19 || \ + (pdev)->device == 0x9a39 || \ + (pdev)->device == 0x7d19 || \ + (pdev)->device == 0x4e19 || \ + (pdev)->device == 0x465d || \ + (pdev)->device == 0x1919)) #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e) #define IOAPIC_RANGE_START (0xfee00000) @@ -97,6 +105,81 @@ static phys_addr_t root_entry_uctp(struct root_entry *re) return re->hi & VTD_PAGE_MASK; } +static int device_rid_cmp_key(const void *key, const struct rb_node *node) +{ + struct device_domain_info *info = + rb_entry(node, struct device_domain_info, node); + const u16 *rid_lhs = key; + + if (*rid_lhs < PCI_DEVID(info->bus, info->devfn)) + return -1; + + if (*rid_lhs > PCI_DEVID(info->bus, info->devfn)) + return 1; + + return 0; +} + +static int device_rid_cmp(struct rb_node *lhs, const struct rb_node *rhs) +{ + struct device_domain_info *info = + rb_entry(lhs, struct device_domain_info, node); + u16 key = PCI_DEVID(info->bus, info->devfn); + + return device_rid_cmp_key(&key, rhs); +} + +/* + * Looks up an IOMMU-probed device using its source ID. + * + * Returns the pointer to the device if there is a match. Otherwise, + * returns NULL. + * + * Note that this helper doesn't guarantee that the device won't be + * released by the iommu subsystem after being returned. The caller + * should use its own synchronization mechanism to avoid the device + * being released during its use if its possibly the case. + */ +struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid) +{ + struct device_domain_info *info = NULL; + struct rb_node *node; + unsigned long flags; + + spin_lock_irqsave(&iommu->device_rbtree_lock, flags); + node = rb_find(&rid, &iommu->device_rbtree, device_rid_cmp_key); + if (node) + info = rb_entry(node, struct device_domain_info, node); + spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags); + + return info ? info->dev : NULL; +} + +static int device_rbtree_insert(struct intel_iommu *iommu, + struct device_domain_info *info) +{ + struct rb_node *curr; + unsigned long flags; + + spin_lock_irqsave(&iommu->device_rbtree_lock, flags); + curr = rb_find_add(&info->node, &iommu->device_rbtree, device_rid_cmp); + spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags); + if (WARN_ON(curr)) + return -EEXIST; + + return 0; +} + +static void device_rbtree_remove(struct device_domain_info *info) +{ + struct intel_iommu *iommu = info->iommu; + unsigned long flags; + + spin_lock_irqsave(&iommu->device_rbtree_lock, flags); + rb_erase(&info->node, &iommu->device_rbtree); + spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags); +} + /* * This domain is a statically identity mapping domain. * 1. This domain creats a static 1:1 mapping to all usable memory. @@ -148,12 +231,14 @@ int intel_iommu_enabled = 0; EXPORT_SYMBOL_GPL(intel_iommu_enabled); static int dmar_map_gfx = 1; +static int dmar_map_ipu = 1; static int intel_iommu_superpage = 1; static int iommu_identity_mapping; static int iommu_skip_te_disable; #define IDENTMAP_GFX 2 #define IDENTMAP_AZALIA 4 +#define IDENTMAP_IPU 8 const struct iommu_ops intel_iommu_ops; static const struct iommu_dirty_ops intel_dirty_ops; @@ -2412,6 +2497,9 @@ static int device_def_domain_type(struct device *dev) if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev)) return IOMMU_DOMAIN_IDENTITY; + + if ((iommu_identity_mapping & IDENTMAP_IPU) && IS_INTEL_IPU(pdev)) + return IOMMU_DOMAIN_IDENTITY; } return 0; @@ -2719,6 +2807,9 @@ static int __init init_dmars(void) if (!dmar_map_gfx) iommu_identity_mapping |= IDENTMAP_GFX; + if (!dmar_map_ipu) + iommu_identity_mapping |= IDENTMAP_IPU; + check_tylersburg_isoch(); ret = si_domain_init(hw_pass_through); @@ -3799,30 +3890,6 @@ static void domain_context_clear(struct device_domain_info *info) &domain_context_clear_one_cb, info); } -static void dmar_remove_one_dev_info(struct device *dev) -{ - struct device_domain_info *info = dev_iommu_priv_get(dev); - struct dmar_domain *domain = info->domain; - struct intel_iommu *iommu = info->iommu; - unsigned long flags; - - if (!dev_is_real_dma_subdevice(info->dev)) { - if (dev_is_pci(info->dev) && sm_supported(iommu)) - intel_pasid_tear_down_entry(iommu, info->dev, - IOMMU_NO_PASID, false); - - iommu_disable_pci_caps(info); - domain_context_clear(info); - } - - spin_lock_irqsave(&domain->lock, flags); - list_del(&info->link); - spin_unlock_irqrestore(&domain->lock, flags); - - domain_detach_iommu(domain, iommu); - info->domain = NULL; -} - /* * Clear the page table pointer in context or pasid table entries so that * all DMA requests without PASID from the device are blocked. If the page @@ -4330,26 +4397,45 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) } dev_iommu_priv_set(dev, info); + if (pdev && pci_ats_supported(pdev)) { + ret = device_rbtree_insert(iommu, info); + if (ret) + goto free; + } if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) { ret = intel_pasid_alloc_table(dev); if (ret) { dev_err(dev, "PASID table allocation failed\n"); - kfree(info); - return ERR_PTR(ret); + goto clear_rbtree; } } intel_iommu_debugfs_create_dev(info); return &iommu->iommu; +clear_rbtree: + device_rbtree_remove(info); +free: + kfree(info); + + return ERR_PTR(ret); } static void intel_iommu_release_device(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); + struct intel_iommu *iommu = info->iommu; + + mutex_lock(&iommu->iopf_lock); + if (dev_is_pci(dev) && pci_ats_supported(to_pci_dev(dev))) + device_rbtree_remove(info); + mutex_unlock(&iommu->iopf_lock); + + if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev) && + !context_copied(iommu, info->bus, info->devfn)) + intel_pasid_teardown_sm_context(dev); - dmar_remove_one_dev_info(dev); intel_pasid_free_table(dev); intel_iommu_debugfs_remove_dev(info); kfree(info); @@ -4855,6 +4941,7 @@ static const struct iommu_dirty_ops intel_dirty_ops = { const struct iommu_ops intel_iommu_ops = { .blocked_domain = &blocking_domain, + .release_domain = &blocking_domain, .capable = intel_iommu_capable, .hw_info = intel_iommu_hw_info, .domain_alloc = intel_iommu_domain_alloc, @@ -4896,6 +4983,18 @@ static void quirk_iommu_igfx(struct pci_dev *dev) dmar_map_gfx = 0; } +static void quirk_iommu_ipu(struct pci_dev *dev) +{ + if (!IS_INTEL_IPU(dev)) + return; + + if (risky_device(dev)) + return; + + pci_info(dev, "Passthrough IOMMU for integrated Intel IPU\n"); + dmar_map_ipu = 0; +} + /* G4x/GM45 integrated gfx dmar support is totally busted. */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_igfx); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_igfx); @@ -4931,6 +5030,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1632, quirk_iommu_igfx); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163A, quirk_iommu_igfx); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx); +/* disable IPU dmar support */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_iommu_ipu); + static void quirk_iommu_rwbf(struct pci_dev *dev) { if (risky_device(dev)) diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 4145c04cb1c68..cd267ba64eda1 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -719,9 +719,16 @@ struct intel_iommu { #endif struct iopf_queue *iopf_queue; unsigned char iopfq_name[16]; + /* Synchronization between fault report and iommu device release. */ + struct mutex iopf_lock; struct q_inval *qi; /* Queued invalidation info */ u32 iommu_state[MAX_SR_DMAR_REGS]; /* Store iommu states between suspend and resume.*/ + /* rb tree for all probed devices */ + struct rb_root device_rbtree; + /* protect the device_rbtree */ + spinlock_t device_rbtree_lock; + #ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ struct irq_domain *ir_domain; @@ -755,6 +762,8 @@ struct device_domain_info { struct intel_iommu *iommu; /* IOMMU used by this device */ struct dmar_domain *domain; /* pointer to domain */ struct pasid_table *pasid_table; /* pasid table */ + /* device tracking node(lookup by PCI RID) */ + struct rb_node node; #ifdef CONFIG_INTEL_IOMMU_DEBUGFS struct dentry *debugfs_dentry; /* pointer to device directory dentry */ #endif @@ -1081,6 +1090,7 @@ void free_pgtable_page(void *vaddr); void iommu_flush_write_buffer(struct intel_iommu *iommu); struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent, const struct iommu_user_data *user_data); +struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid); #ifdef CONFIG_INTEL_IOMMU_SVM void intel_svm_check(struct intel_iommu *iommu); diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 108158e2b907d..a51e895d9a178 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -214,6 +214,9 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu, if (!info || !info->ats_enabled) return; + if (pci_dev_is_disconnected(to_pci_dev(dev))) + return; + sid = info->bus << 8 | info->devfn; qdep = info->ats_qdep; pfsid = info->pfsid; @@ -667,3 +670,67 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev, return 0; } + +/* + * Interfaces to setup or teardown a pasid table to the scalable-mode + * context table entry: + */ + +static void device_pasid_table_teardown(struct device *dev, u8 bus, u8 devfn) +{ + struct device_domain_info *info = dev_iommu_priv_get(dev); + struct intel_iommu *iommu = info->iommu; + struct context_entry *context; + + spin_lock(&iommu->lock); + context = iommu_context_addr(iommu, bus, devfn, false); + if (!context) { + spin_unlock(&iommu->lock); + return; + } + + context_clear_entry(context); + __iommu_flush_cache(iommu, context, sizeof(*context)); + spin_unlock(&iommu->lock); + + /* + * Cache invalidation for changes to a scalable-mode context table + * entry. + * + * Section 6.5.3.3 of the VT-d spec: + * - Device-selective context-cache invalidation; + * - Domain-selective PASID-cache invalidation to affected domains + * (can be skipped if all PASID entries were not-present); + * - Domain-selective IOTLB invalidation to affected domains; + * - Global Device-TLB invalidation to affected functions. + * + * The iommu has been parked in the blocking state. All domains have + * been detached from the device or PASID. The PASID and IOTLB caches + * have been invalidated during the domain detach path. + */ + iommu->flush.flush_context(iommu, 0, PCI_DEVID(bus, devfn), + DMA_CCMD_MASK_NOBIT, DMA_CCMD_DEVICE_INVL); + devtlb_invalidation_with_pasid(iommu, dev, IOMMU_NO_PASID); +} + +static int pci_pasid_table_teardown(struct pci_dev *pdev, u16 alias, void *data) +{ + struct device *dev = data; + + if (dev == &pdev->dev) + device_pasid_table_teardown(dev, PCI_BUS_NUM(alias), alias & 0xff); + + return 0; +} + +void intel_pasid_teardown_sm_context(struct device *dev) +{ + struct device_domain_info *info = dev_iommu_priv_get(dev); + + if (!dev_is_pci(dev)) { + device_pasid_table_teardown(dev, info->bus, info->devfn); + return; + } + + pci_for_each_dma_alias(to_pci_dev(dev), pci_pasid_table_teardown, dev); +} diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 487ede039bdde..42fda97fd8516 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -318,4 +318,5 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, bool fault_ignore); void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu, struct device *dev, u32 pasid); +void intel_pasid_teardown_sm_context(struct device *dev); #endif /* __INTEL_PASID_H */ diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c index cf43e798eca49..44083d01852db 100644 --- a/drivers/iommu/intel/perfmon.c +++ b/drivers/iommu/intel/perfmon.c @@ -438,7 +438,7 @@ static int iommu_pmu_assign_event(struct iommu_pmu *iommu_pmu, iommu_pmu_set_filter(domain, event->attr.config1, IOMMU_PMU_FILTER_DOMAIN, idx, event->attr.config1); - iommu_pmu_set_filter(pasid, event->attr.config1, + iommu_pmu_set_filter(pasid, event->attr.config2, IOMMU_PMU_FILTER_PASID, idx, event->attr.config1); iommu_pmu_set_filter(ats, event->attr.config2, diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 40edd282903fb..4d269df0082fb 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -67,7 +67,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu) struct page *pages; int irq, ret; - pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, PRQ_ORDER); + pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO, PRQ_ORDER); if (!pages) { pr_warn("IOMMU: %s: Failed to allocate page request queue\n", iommu->name); @@ -650,7 +650,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) struct intel_iommu *iommu = d; struct page_req_dsc *req; int head, tail, handled; - struct pci_dev *pdev; + struct device *dev; u64 address; /* @@ -696,23 +696,24 @@ static irqreturn_t prq_event_thread(int irq, void *d) if (unlikely(req->lpig && !req->rd_req && !req->wr_req)) goto prq_advance; - pdev = pci_get_domain_bus_and_slot(iommu->segment, - PCI_BUS_NUM(req->rid), - req->rid & 0xff); /* * If prq is to be handled outside iommu driver via receiver of * the fault notifiers, we skip the page response here. */ - if (!pdev) + mutex_lock(&iommu->iopf_lock); + dev = device_rbtree_find(iommu, req->rid); + if (!dev) { + mutex_unlock(&iommu->iopf_lock); goto bad_req; + } - if (intel_svm_prq_report(iommu, &pdev->dev, req)) + if (intel_svm_prq_report(iommu, dev, req)) handle_bad_prq_event(iommu, req, QI_RESP_INVALID); else - trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1, + trace_prq_report(iommu, dev, req->qw_0, req->qw_1, req->priv_data[0], req->priv_data[1], iommu->prq_seq_number++); - pci_dev_put(pdev); + mutex_unlock(&iommu->iopf_lock); prq_advance: head = (head + sizeof(*req)) & PRQ_RING_MASK; } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d14413916f93a..e606d250d1d55 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -463,13 +463,24 @@ static void iommu_deinit_device(struct device *dev) /* * release_device() must stop using any attached domain on the device. - * If there are still other devices in the group they are not effected + * If there are still other devices in the group, they are not affected * by this callback. * - * The IOMMU driver must set the device to either an identity or - * blocking translation and stop using any domain pointer, as it is - * going to be freed. + * If the iommu driver provides release_domain, the core code ensures + * that domain is attached prior to calling release_device. Drivers can + * use this to enforce a translation on the idle iommu. Typically, the + * global static blocked_domain is a good choice. + * + * Otherwise, the iommu driver must set the device to either an identity + * or a blocking translation in release_device() and stop using any + * domain pointer, as it is going to be freed. + * + * Regardless, if a delayed attach never occurred, then the release + * should still avoid touching any hardware configuration either. */ + if (!dev->iommu->attach_deferred && ops->release_domain) + ops->release_domain->ops->attach_dev(ops->release_domain, dev); + if (ops->release_device) ops->release_device(dev); @@ -3499,15 +3510,26 @@ EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed); static int __iommu_set_group_pasid(struct iommu_domain *domain, struct iommu_group *group, ioasid_t pasid) { - struct group_device *device; - int ret = 0; + struct group_device *device, *last_gdev; + int ret; for_each_group_device(group, device) { ret = domain->ops->set_dev_pasid(domain, device->dev, pasid); if (ret) - break; + goto err_revert; } + return 0; + +err_revert: + last_gdev = device; + for_each_group_device(group, device) { + const struct iommu_ops *ops = dev_iommu_ops(device->dev); + + if (device == last_gdev) + break; + ops->remove_dev_pasid(device->dev, pasid); + } return ret; } @@ -3536,6 +3558,7 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, { /* Caller must be a probed driver on dev */ struct iommu_group *group = dev->iommu_group; + struct group_device *device; void *curr; int ret; @@ -3545,10 +3568,18 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, if (!group) return -ENODEV; - if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner) + if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner || + pasid == IOMMU_NO_PASID) return -EINVAL; mutex_lock(&group->mutex); + for_each_group_device(group, device) { + if (pasid >= device->dev->iommu->max_pasids) { + ret = -EINVAL; + goto out_unlock; + } + } + curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL); if (curr) { ret = xa_err(curr) ? : -EBUSY; @@ -3556,10 +3587,8 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, } ret = __iommu_set_group_pasid(domain, group, pasid); - if (ret) { - __iommu_remove_group_pasid(group, pasid); + if (ret) xa_erase(&group->pasid_array, pasid); - } out_unlock: mutex_unlock(&group->mutex); return ret; diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig index 99d4b075df49e..76656fe0470d7 100644 --- a/drivers/iommu/iommufd/Kconfig +++ b/drivers/iommu/iommufd/Kconfig @@ -37,6 +37,7 @@ config IOMMUFD_TEST depends on DEBUG_KERNEL depends on FAULT_INJECTION depends on RUNTIME_TESTING_MENU + select IOMMUFD_DRIVER default n help This is dangerous, do not enable unless running diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 83314b9d8f38b..ee59647c20501 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -99,7 +99,8 @@ int __init irq_remapping_prepare(void) if (disable_irq_remap) return -ENOSYS; - if (intel_irq_remap_ops.prepare() == 0) + if (IS_ENABLED(CONFIG_INTEL_IOMMU) && + intel_irq_remap_ops.prepare() == 0) remap_ops = &intel_irq_remap_ops; else if (IS_ENABLED(CONFIG_AMD_IOMMU) && amd_iommu_irq_ops.prepare() == 0) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 7abe9e85a5706..51d0eba8cbdf3 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -1789,6 +1789,7 @@ static const struct of_device_id mtk_iommu_of_ids[] = { { .compatible = "mediatek,mt8365-m4u", .data = &mt8365_data}, {} }; +MODULE_DEVICE_TABLE(of, mtk_iommu_of_ids); static struct platform_driver mtk_iommu_driver = { .probe = mtk_iommu_probe, diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 25b41222abaec..32cc8341d3726 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -599,6 +599,7 @@ static const struct of_device_id mtk_iommu_v1_of_ids[] = { { .compatible = "mediatek,mt2701-m4u", }, {} }; +MODULE_DEVICE_TABLE(of, mtk_iommu_v1_of_ids); static const struct component_master_ops mtk_iommu_v1_com_ops = { .bind = mtk_iommu_v1_bind, diff --git a/drivers/irqchip/irq-alpine-msi.c b/drivers/irqchip/irq-alpine-msi.c index 9c8b1349ee17b..a1430ab60a8a3 100644 --- a/drivers/irqchip/irq-alpine-msi.c +++ b/drivers/irqchip/irq-alpine-msi.c @@ -165,7 +165,7 @@ static int alpine_msix_middle_domain_alloc(struct irq_domain *domain, return 0; err_sgi: - irq_domain_free_irqs_parent(domain, virq, i - 1); + irq_domain_free_irqs_parent(domain, virq, i); alpine_msix_free_sgi(priv, sgi, nr_irqs); return err; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index b822752c42617..9913ce28fff1f 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1840,28 +1840,22 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); - int ret = 0; if (!info->map) return -EINVAL; - raw_spin_lock(&its_dev->event_map.vlpi_lock); - if (!its_dev->event_map.vm) { struct its_vlpi_map *maps; maps = kcalloc(its_dev->event_map.nr_lpis, sizeof(*maps), GFP_ATOMIC); - if (!maps) { - ret = -ENOMEM; - goto out; - } + if (!maps) + return -ENOMEM; its_dev->event_map.vm = info->map->vm; its_dev->event_map.vlpi_maps = maps; } else if (its_dev->event_map.vm != info->map->vm) { - ret = -EINVAL; - goto out; + return -EINVAL; } /* Get our private copy of the mapping information */ @@ -1893,46 +1887,32 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) its_dev->event_map.nr_vlpis++; } -out: - raw_spin_unlock(&its_dev->event_map.vlpi_lock); - return ret; + return 0; } static int its_vlpi_get(struct irq_data *d, struct its_cmd_info *info) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); struct its_vlpi_map *map; - int ret = 0; - - raw_spin_lock(&its_dev->event_map.vlpi_lock); map = get_vlpi_map(d); - if (!its_dev->event_map.vm || !map) { - ret = -EINVAL; - goto out; - } + if (!its_dev->event_map.vm || !map) + return -EINVAL; /* Copy our mapping information to the incoming request */ *info->map = *map; -out: - raw_spin_unlock(&its_dev->event_map.vlpi_lock); - return ret; + return 0; } static int its_vlpi_unmap(struct irq_data *d) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); - int ret = 0; - raw_spin_lock(&its_dev->event_map.vlpi_lock); - - if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d)) { - ret = -EINVAL; - goto out; - } + if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d)) + return -EINVAL; /* Drop the virtual mapping */ its_send_discard(its_dev, event); @@ -1956,9 +1936,7 @@ static int its_vlpi_unmap(struct irq_data *d) kfree(its_dev->event_map.vlpi_maps); } -out: - raw_spin_unlock(&its_dev->event_map.vlpi_lock); - return ret; + return 0; } static int its_vlpi_prop_update(struct irq_data *d, struct its_cmd_info *info) @@ -1986,6 +1964,8 @@ static int its_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) if (!is_v4(its_dev->its)) return -EINVAL; + guard(raw_spinlock_irq)(&its_dev->event_map.vlpi_lock); + /* Unmap request? */ if (!info) return its_vlpi_unmap(d); @@ -4561,13 +4541,8 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq irqd_set_resend_when_in_progress(irq_get_irq_data(virq + i)); } - if (err) { - if (i > 0) - its_vpe_irq_domain_free(domain, virq, i); - - its_lpi_free(bitmap, base, nr_ids); - its_free_prop_table(vprop_page); - } + if (err) + its_vpe_irq_domain_free(domain, virq, i); return err; } diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c index 6e1e1f011bb29..dd4d699170f4e 100644 --- a/drivers/irqchip/irq-loongson-pch-msi.c +++ b/drivers/irqchip/irq-loongson-pch-msi.c @@ -136,7 +136,7 @@ static int pch_msi_middle_domain_alloc(struct irq_domain *domain, err_hwirq: pch_msi_free_hwirq(priv, hwirq, nr_irqs); - irq_domain_free_irqs_parent(domain, virq, i - 1); + irq_domain_free_irqs_parent(domain, virq, i); return err; } diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c index 9494fc26259c3..8803facbb3a2e 100644 --- a/drivers/irqchip/irq-renesas-rzg2l.c +++ b/drivers/irqchip/irq-renesas-rzg2l.c @@ -85,10 +85,9 @@ static struct rzg2l_irqc_priv *irq_data_to_priv(struct irq_data *data) return data->domain->host_data; } -static void rzg2l_irq_eoi(struct irq_data *d) +static void rzg2l_clear_irq_int(struct rzg2l_irqc_priv *priv, unsigned int hwirq) { - unsigned int hw_irq = irqd_to_hwirq(d) - IRQC_IRQ_START; - struct rzg2l_irqc_priv *priv = irq_data_to_priv(d); + unsigned int hw_irq = hwirq - IRQC_IRQ_START; u32 bit = BIT(hw_irq); u32 iitsr, iscr; @@ -99,20 +98,30 @@ static void rzg2l_irq_eoi(struct irq_data *d) * ISCR can only be cleared if the type is falling-edge, rising-edge or * falling/rising-edge. */ - if ((iscr & bit) && (iitsr & IITSR_IITSEL_MASK(hw_irq))) + if ((iscr & bit) && (iitsr & IITSR_IITSEL_MASK(hw_irq))) { writel_relaxed(iscr & ~bit, priv->base + ISCR); + /* + * Enforce that the posted write is flushed to prevent that the + * just handled interrupt is raised again. + */ + readl_relaxed(priv->base + ISCR); + } } -static void rzg2l_tint_eoi(struct irq_data *d) +static void rzg2l_clear_tint_int(struct rzg2l_irqc_priv *priv, unsigned int hwirq) { - unsigned int hw_irq = irqd_to_hwirq(d) - IRQC_TINT_START; - struct rzg2l_irqc_priv *priv = irq_data_to_priv(d); - u32 bit = BIT(hw_irq); + u32 bit = BIT(hwirq - IRQC_TINT_START); u32 reg; reg = readl_relaxed(priv->base + TSCR); - if (reg & bit) + if (reg & bit) { writel_relaxed(reg & ~bit, priv->base + TSCR); + /* + * Enforce that the posted write is flushed to prevent that the + * just handled interrupt is raised again. + */ + readl_relaxed(priv->base + TSCR); + } } static void rzg2l_irqc_eoi(struct irq_data *d) @@ -122,9 +131,9 @@ static void rzg2l_irqc_eoi(struct irq_data *d) raw_spin_lock(&priv->lock); if (hw_irq >= IRQC_IRQ_START && hw_irq <= IRQC_IRQ_COUNT) - rzg2l_irq_eoi(d); + rzg2l_clear_irq_int(priv, hw_irq); else if (hw_irq >= IRQC_TINT_START && hw_irq < IRQC_NUM_IRQ) - rzg2l_tint_eoi(d); + rzg2l_clear_tint_int(priv, hw_irq); raw_spin_unlock(&priv->lock); irq_chip_eoi_parent(d); } @@ -172,8 +181,10 @@ static void rzg2l_irqc_irq_enable(struct irq_data *d) static int rzg2l_irq_set_type(struct irq_data *d, unsigned int type) { - unsigned int hw_irq = irqd_to_hwirq(d) - IRQC_IRQ_START; struct rzg2l_irqc_priv *priv = irq_data_to_priv(d); + unsigned int hwirq = irqd_to_hwirq(d); + u32 iitseln = hwirq - IRQC_IRQ_START; + bool clear_irq_int = false; u16 sense, tmp; switch (type & IRQ_TYPE_SENSE_MASK) { @@ -183,14 +194,17 @@ static int rzg2l_irq_set_type(struct irq_data *d, unsigned int type) case IRQ_TYPE_EDGE_FALLING: sense = IITSR_IITSEL_EDGE_FALLING; + clear_irq_int = true; break; case IRQ_TYPE_EDGE_RISING: sense = IITSR_IITSEL_EDGE_RISING; + clear_irq_int = true; break; case IRQ_TYPE_EDGE_BOTH: sense = IITSR_IITSEL_EDGE_BOTH; + clear_irq_int = true; break; default: @@ -199,21 +213,40 @@ static int rzg2l_irq_set_type(struct irq_data *d, unsigned int type) raw_spin_lock(&priv->lock); tmp = readl_relaxed(priv->base + IITSR); - tmp &= ~IITSR_IITSEL_MASK(hw_irq); - tmp |= IITSR_IITSEL(hw_irq, sense); + tmp &= ~IITSR_IITSEL_MASK(iitseln); + tmp |= IITSR_IITSEL(iitseln, sense); + if (clear_irq_int) + rzg2l_clear_irq_int(priv, hwirq); writel_relaxed(tmp, priv->base + IITSR); raw_spin_unlock(&priv->lock); return 0; } +static u32 rzg2l_disable_tint_and_set_tint_source(struct irq_data *d, struct rzg2l_irqc_priv *priv, + u32 reg, u32 tssr_offset, u8 tssr_index) +{ + u32 tint = (u32)(uintptr_t)irq_data_get_irq_chip_data(d); + u32 tien = reg & (TIEN << TSSEL_SHIFT(tssr_offset)); + + /* Clear the relevant byte in reg */ + reg &= ~(TSSEL_MASK << TSSEL_SHIFT(tssr_offset)); + /* Set TINT and leave TIEN clear */ + reg |= tint << TSSEL_SHIFT(tssr_offset); + writel_relaxed(reg, priv->base + TSSR(tssr_index)); + + return reg | tien; +} + static int rzg2l_tint_set_edge(struct irq_data *d, unsigned int type) { struct rzg2l_irqc_priv *priv = irq_data_to_priv(d); unsigned int hwirq = irqd_to_hwirq(d); u32 titseln = hwirq - IRQC_TINT_START; + u32 tssr_offset = TSSR_OFFSET(titseln); + u8 tssr_index = TSSR_INDEX(titseln); u8 index, sense; - u32 reg; + u32 reg, tssr; switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_RISING: @@ -235,10 +268,14 @@ static int rzg2l_tint_set_edge(struct irq_data *d, unsigned int type) } raw_spin_lock(&priv->lock); + tssr = readl_relaxed(priv->base + TSSR(tssr_index)); + tssr = rzg2l_disable_tint_and_set_tint_source(d, priv, tssr, tssr_offset, tssr_index); reg = readl_relaxed(priv->base + TITSR(index)); reg &= ~(IRQ_MASK << (titseln * TITSEL_WIDTH)); reg |= sense << (titseln * TITSEL_WIDTH); writel_relaxed(reg, priv->base + TITSR(index)); + rzg2l_clear_tint_int(priv, hwirq); + writel_relaxed(tssr, priv->base + TSSR(tssr_index)); raw_spin_unlock(&priv->lock); return 0; diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index e8d01b14ccdde..627beae9649a2 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -17,17 +17,19 @@ #include #include #include +#include static struct irq_domain *intc_domain; +static unsigned int riscv_intc_nr_irqs __ro_after_init = BITS_PER_LONG; +static unsigned int riscv_intc_custom_base __ro_after_init = BITS_PER_LONG; +static unsigned int riscv_intc_custom_nr_irqs __ro_after_init; static asmlinkage void riscv_intc_irq(struct pt_regs *regs) { unsigned long cause = regs->cause & ~CAUSE_IRQ_FLAG; - if (unlikely(cause >= BITS_PER_LONG)) - panic("unexpected interrupt cause"); - - generic_handle_domain_irq(intc_domain, cause); + if (generic_handle_domain_irq(intc_domain, cause)) + pr_warn_ratelimited("Failed to handle interrupt (cause: %ld)\n", cause); } /* @@ -47,6 +49,31 @@ static void riscv_intc_irq_unmask(struct irq_data *d) csr_set(CSR_IE, BIT(d->hwirq)); } +static void andes_intc_irq_mask(struct irq_data *d) +{ + /* + * Andes specific S-mode local interrupt causes (hwirq) + * are defined as (256 + n) and controlled by n-th bit + * of SLIE. + */ + unsigned int mask = BIT(d->hwirq % BITS_PER_LONG); + + if (d->hwirq < ANDES_SLI_CAUSE_BASE) + csr_clear(CSR_IE, mask); + else + csr_clear(ANDES_CSR_SLIE, mask); +} + +static void andes_intc_irq_unmask(struct irq_data *d) +{ + unsigned int mask = BIT(d->hwirq % BITS_PER_LONG); + + if (d->hwirq < ANDES_SLI_CAUSE_BASE) + csr_set(CSR_IE, mask); + else + csr_set(ANDES_CSR_SLIE, mask); +} + static void riscv_intc_irq_eoi(struct irq_data *d) { /* @@ -70,12 +97,21 @@ static struct irq_chip riscv_intc_chip = { .irq_eoi = riscv_intc_irq_eoi, }; +static struct irq_chip andes_intc_chip = { + .name = "RISC-V INTC", + .irq_mask = andes_intc_irq_mask, + .irq_unmask = andes_intc_irq_unmask, + .irq_eoi = riscv_intc_irq_eoi, +}; + static int riscv_intc_domain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq) { + struct irq_chip *chip = d->host_data; + irq_set_percpu_devid(irq); - irq_domain_set_info(d, irq, hwirq, &riscv_intc_chip, d->host_data, - handle_percpu_devid_irq, NULL, NULL); + irq_domain_set_info(d, irq, hwirq, chip, NULL, handle_percpu_devid_irq, + NULL, NULL); return 0; } @@ -93,6 +129,14 @@ static int riscv_intc_domain_alloc(struct irq_domain *domain, if (ret) return ret; + /* + * Only allow hwirq for which we have corresponding standard or + * custom interrupt enable register. + */ + if ((hwirq >= riscv_intc_nr_irqs && hwirq < riscv_intc_custom_base) || + (hwirq >= riscv_intc_custom_base + riscv_intc_custom_nr_irqs)) + return -EINVAL; + for (i = 0; i < nr_irqs; i++) { ret = riscv_intc_domain_map(domain, virq + i, hwirq + i); if (ret) @@ -113,12 +157,12 @@ static struct fwnode_handle *riscv_intc_hwnode(void) return intc_domain->fwnode; } -static int __init riscv_intc_init_common(struct fwnode_handle *fn) +static int __init riscv_intc_init_common(struct fwnode_handle *fn, + struct irq_chip *chip) { int rc; - intc_domain = irq_domain_create_linear(fn, BITS_PER_LONG, - &riscv_intc_domain_ops, NULL); + intc_domain = irq_domain_create_tree(fn, &riscv_intc_domain_ops, chip); if (!intc_domain) { pr_err("unable to add IRQ domain\n"); return -ENXIO; @@ -132,7 +176,11 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn) riscv_set_intc_hwnode_fn(riscv_intc_hwnode); - pr_info("%d local interrupts mapped\n", BITS_PER_LONG); + pr_info("%d local interrupts mapped\n", riscv_intc_nr_irqs); + if (riscv_intc_custom_nr_irqs) { + pr_info("%d custom local interrupts mapped\n", + riscv_intc_custom_nr_irqs); + } return 0; } @@ -140,8 +188,9 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn) static int __init riscv_intc_init(struct device_node *node, struct device_node *parent) { - int rc; + struct irq_chip *chip = &riscv_intc_chip; unsigned long hartid; + int rc; rc = riscv_of_parent_hartid(node, &hartid); if (rc < 0) { @@ -166,18 +215,26 @@ static int __init riscv_intc_init(struct device_node *node, return 0; } - return riscv_intc_init_common(of_node_to_fwnode(node)); + if (of_device_is_compatible(node, "andestech,cpu-intc")) { + riscv_intc_custom_base = ANDES_SLI_CAUSE_BASE; + riscv_intc_custom_nr_irqs = ANDES_RV_IRQ_LAST; + chip = &andes_intc_chip; + } + + return riscv_intc_init_common(of_node_to_fwnode(node), chip); } IRQCHIP_DECLARE(riscv, "riscv,cpu-intc", riscv_intc_init); +IRQCHIP_DECLARE(andes, "andestech,cpu-intc", riscv_intc_init); #ifdef CONFIG_ACPI static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, const unsigned long end) { - struct fwnode_handle *fn; struct acpi_madt_rintc *rintc; + struct fwnode_handle *fn; + int rc; rintc = (struct acpi_madt_rintc *)header; @@ -196,7 +253,11 @@ static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, return -ENOMEM; } - return riscv_intc_init_common(fn); + rc = riscv_intc_init_common(fn, &riscv_intc_chip); + if (rc) + irq_domain_free_fwnode(fn); + + return rc; } IRQCHIP_ACPI_DECLARE(riscv_intc, ACPI_MADT_TYPE_RINTC, NULL, diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index d721b254e1e45..27267ab6191f3 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -59,6 +59,18 @@ config LEDS_88PM860X This option enables support for on-chip LED drivers found on Marvell Semiconductor 88PM8606 PMIC. +config LEDS_AAEON + tristate "AAEON LED driver" + depends on X86 + depends on UBUNTU_ODM_DRIVERS + select MFD_AAEON + help + This led driver adds support for LED brightness control on Single + Board Computers produced by AAEON. + + This driver leverages the ASUS WMI interface to access device + resources. + config LEDS_AN30259A tristate "LED support for Panasonic AN30259A" depends on LEDS_CLASS && I2C && OF @@ -410,7 +422,6 @@ config LEDS_LP55XX_COMMON depends on OF depends on I2C select FW_LOADER - select FW_LOADER_USER_HELPER help This option supports common operations for LP5521/5523/55231/5562/8501 devices. diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index ce07dc295ff00..3d8138b8c24f3 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_LEDS_TRIGGERS) += led-triggers.o # LED Platform Drivers (keep this sorted, M-| sort) obj-$(CONFIG_LEDS_88PM860X) += leds-88pm860x.o +obj-$(CONFIG_LEDS_AAEON) += leds-aaeon.o obj-$(CONFIG_LEDS_ACER_A500) += leds-acer-a500.o obj-$(CONFIG_LEDS_ADP5520) += leds-adp5520.o obj-$(CONFIG_LEDS_AN30259A) += leds-an30259a.o diff --git a/drivers/leds/flash/leds-sgm3140.c b/drivers/leds/flash/leds-sgm3140.c index eb648ff54b4e5..db0ac6641954e 100644 --- a/drivers/leds/flash/leds-sgm3140.c +++ b/drivers/leds/flash/leds-sgm3140.c @@ -114,8 +114,11 @@ static int sgm3140_brightness_set(struct led_classdev *led_cdev, "failed to enable regulator: %d\n", ret); return ret; } + gpiod_set_value_cansleep(priv->flash_gpio, 0); gpiod_set_value_cansleep(priv->enable_gpio, 1); } else { + del_timer_sync(&priv->powerdown_timer); + gpiod_set_value_cansleep(priv->flash_gpio, 0); gpiod_set_value_cansleep(priv->enable_gpio, 0); ret = regulator_disable(priv->vin_regulator); if (ret) { diff --git a/drivers/leds/leds-aaeon.c b/drivers/leds/leds-aaeon.c new file mode 100644 index 0000000000000..10090a4bff654 --- /dev/null +++ b/drivers/leds/leds-aaeon.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AAEON LED driver + * + * Copyright (c) 2021, AAEON Ltd. + * + * Author: Kunyang Fan + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include + +#define DRVNAME "led_aaeon" +#define ASUS_NB_WMI_EVENT_GUID "0B3CBB35-E3C2-45ED-91C2-4C5A6D195D1C" +#define AAEON_WMI_MGMT_GUID "97845ED0-4E6D-11DE-8A39-0800200C9A66" + +#define GET_LED_NUMBER_ID 0x00060000 +#define GET_LED_METHOD_ID 0x00060001 +#define SET_LED_METHOD_ID 0x00060002 +#define GET_LED_NUMBER_METHOD_ID 0x10 + + +struct aaeon_led_data { + int id; + struct led_classdev cdev; +}; + +static int aaeon_led_get_number(void) +{ + int err, retval; + + err = asus_wmi_evaluate_method(GET_LED_NUMBER_ID, + GET_LED_NUMBER_METHOD_ID, + 0, &retval); + if (err) + return err; + + return retval; +} + +static enum led_brightness aaeon_led_brightness_get(struct led_classdev + *cdev) +{ + int err, brightness; + struct aaeon_led_data *led = + container_of(cdev, struct aaeon_led_data, cdev); + u32 arg0; + + arg0 = (u32)(led->id & 0xF); + err = asus_wmi_evaluate_method(GET_LED_METHOD_ID, arg0, 0, &brightness); + if (err) + return err; + + return brightness; +}; + +static void aaeon_led_brightness_set(struct led_classdev *cdev, + enum led_brightness brightness) +{ + int err, retval; + struct aaeon_led_data *led = + container_of(cdev, struct aaeon_led_data, cdev); + u32 arg0; + + arg0 = (u32)(led->id & 0xF); + if (brightness != LED_OFF) + arg0 |= BIT(16); + + err = asus_wmi_evaluate_method(SET_LED_METHOD_ID, arg0, 0, &retval); +}; + +static int __init aaeon_add_led_device(struct platform_device *pdev, + int id) +{ + struct aaeon_led_data *led; + + led = devm_kzalloc(&pdev->dev, sizeof(struct aaeon_led_data), GFP_KERNEL); + if (!led) + return -ENOMEM; + + led->id = id; + led->cdev.brightness_get = aaeon_led_brightness_get; + led->cdev.brightness_set = aaeon_led_brightness_set; + led->cdev.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "led:%d:", id); + + if (!led->cdev.name) + return -ENOMEM; + + return devm_led_classdev_register(&pdev->dev, &led->cdev); +} + +static int aaeon_led_probe(struct platform_device *pdev) +{ + int err = -ENODEV, i; + int led_number = 0; + + pr_debug("aaeon led device probe!\n"); + /* Prevent other drivers adding this platfom device */ + if (!wmi_has_guid(AAEON_WMI_MGMT_GUID)) { + pr_debug("AAEON Management GUID not found\n"); + return -ENODEV; + } + + /* Query the number of led devices board support */ + led_number = aaeon_led_get_number(); + + /* + * If the number is 0 or can't get the number of leds, + * no need to register any led device node. + */ + if (led_number <= 0) + return -ENODEV; + + for (i = 0; i < led_number; i++) { + err = aaeon_add_led_device(pdev, i); + if (err) + break; + } + + return err; +} + +static struct platform_driver aaeon_led_driver = { + .driver = { + .name = "leds-aaeon", + }, +}; + +module_platform_driver_probe(aaeon_led_driver, aaeon_led_probe); + +MODULE_ALIAS("platform:leds-aaeon"); +MODULE_DESCRIPTION("AAEON LED Driver"); +MODULE_AUTHOR("Kunyang Fan "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/leds/leds-aw2013.c b/drivers/leds/leds-aw2013.c index 91f44b23cb113..17235a5e576ae 100644 --- a/drivers/leds/leds-aw2013.c +++ b/drivers/leds/leds-aw2013.c @@ -405,6 +405,7 @@ static int aw2013_probe(struct i2c_client *client) chip->regulators); error: + mutex_unlock(&chip->mutex); mutex_destroy(&chip->mutex); return ret; } diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c index 4e3936a39d0ed..e1b414b403534 100644 --- a/drivers/leds/leds-pwm.c +++ b/drivers/leds/leds-pwm.c @@ -53,7 +53,13 @@ static int led_pwm_set(struct led_classdev *led_cdev, duty = led_dat->pwmstate.period - duty; led_dat->pwmstate.duty_cycle = duty; - led_dat->pwmstate.enabled = true; + /* + * Disabling a PWM doesn't guarantee that it emits the inactive level. + * So keep it on. Only for suspending the PWM should be disabled because + * otherwise it refuses to suspend. The possible downside is that the + * LED might stay (or even go) on. + */ + led_dat->pwmstate.enabled = !(led_cdev->flags & LED_SUSPENDED); return pwm_apply_might_sleep(led_dat->pwm, &led_dat->pwmstate); } diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index 8e5475819590e..df1b1d8468e60 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -504,12 +504,12 @@ static int netdev_trig_notify(struct notifier_block *nb, trigger_data->duplex = DUPLEX_UNKNOWN; switch (evt) { case NETDEV_CHANGENAME: - get_device_state(trigger_data); - fallthrough; case NETDEV_REGISTER: dev_put(trigger_data->net_dev); dev_hold(dev); trigger_data->net_dev = dev; + if (evt == NETDEV_CHANGENAME) + get_device_state(trigger_data); break; case NETDEV_UNREGISTER: dev_put(trigger_data->net_dev); diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c index db9270da5b8e9..b6ddf1d47cb4e 100644 --- a/drivers/macintosh/via-macii.c +++ b/drivers/macintosh/via-macii.c @@ -140,24 +140,19 @@ static int macii_probe(void) /* Initialize the driver */ static int macii_init(void) { - unsigned long flags; int err; - local_irq_save(flags); - err = macii_init_via(); if (err) - goto out; + return err; err = request_irq(IRQ_MAC_ADB, macii_interrupt, 0, "ADB", macii_interrupt); if (err) - goto out; + return err; macii_state = idle; -out: - local_irq_restore(flags); - return err; + return 0; } /* initialize the hardware */ diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c index ead2200f39ba0..033aff11f87cf 100644 --- a/drivers/mailbox/mtk-cmdq-mailbox.c +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -465,7 +465,7 @@ static void cmdq_mbox_shutdown(struct mbox_chan *chan) struct cmdq_task *task, *tmp; unsigned long flags; - WARN_ON(pm_runtime_get_sync(cmdq->mbox.dev)); + WARN_ON(pm_runtime_get_sync(cmdq->mbox.dev) < 0); spin_lock_irqsave(&thread->chan->lock, flags); if (list_empty(&thread->task_busy_list)) diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 2bba4d6aaaa28..463eb13bd0b2a 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -54,7 +54,7 @@ void bch_dump_bucket(struct btree_keys *b) int __bch_count_data(struct btree_keys *b) { unsigned int ret = 0; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k; if (b->ops->is_extents) @@ -67,7 +67,7 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...) { va_list args; struct bkey *k, *p = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; const char *err; for_each_key(b, k, &iter) { @@ -879,7 +879,7 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, unsigned int status = BTREE_INSERT_STATUS_NO_INSERT; struct bset *i = bset_tree_last(b)->data; struct bkey *m, *prev = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey preceding_key_on_stack = ZERO_KEY; struct bkey *preceding_key_p = &preceding_key_on_stack; @@ -895,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k, else preceding_key(k, &preceding_key_p); - m = bch_btree_iter_init(b, &iter, preceding_key_p); + m = bch_btree_iter_stack_init(b, &iter, preceding_key_p); - if (b->ops->insert_fixup(b, k, &iter, replace_key)) + if (b->ops->insert_fixup(b, k, &iter.iter, replace_key)) return status; status = BTREE_INSERT_STATUS_INSERT; @@ -1100,33 +1100,33 @@ void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, btree_iter_cmp)); } -static struct bkey *__bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search, - struct bset_tree *start) +static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search, + struct bset_tree *start) { struct bkey *ret = NULL; - iter->size = ARRAY_SIZE(iter->data); - iter->used = 0; + iter->iter.size = ARRAY_SIZE(iter->stack_data); + iter->iter.used = 0; #ifdef CONFIG_BCACHE_DEBUG - iter->b = b; + iter->iter.b = b; #endif for (; start <= bset_tree_last(b); start++) { ret = bch_bset_search(b, start, search); - bch_btree_iter_push(iter, ret, bset_bkey_last(start->data)); + bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data)); } return ret; } -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, struct bkey *search) { - return __bch_btree_iter_init(b, iter, search, b->set); + return __bch_btree_iter_stack_init(b, iter, search, b->set); } static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, @@ -1293,10 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, struct bset_sort_state *state) { size_t order = b->page_order, keys = 0; - struct btree_iter iter; + struct btree_iter_stack iter; int oldsize = bch_count_data(b); - __bch_btree_iter_init(b, &iter, NULL, &b->set[start]); + __bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]); if (start) { unsigned int i; @@ -1307,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start, order = get_order(__set_bytes(b->set->data, keys)); } - __btree_sort(b, &iter, start, order, false, state); + __btree_sort(b, &iter.iter, start, order, false, state); EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize); } @@ -1323,11 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new, struct bset_sort_state *state) { uint64_t start_time = local_clock(); - struct btree_iter iter; + struct btree_iter_stack iter; - bch_btree_iter_init(b, &iter, NULL); + bch_btree_iter_stack_init(b, &iter, NULL); - btree_mergesort(b, new->set->data, &iter, false, true); + btree_mergesort(b, new->set->data, &iter.iter, false, true); bch_time_stats_update(&state->time, start_time); diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index d795c84246b01..011f6062c4c04 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -321,7 +321,14 @@ struct btree_iter { #endif struct btree_iter_set { struct bkey *k, *end; - } data[MAX_BSETS]; + } data[]; +}; + +/* Fixed-size btree_iter that can be allocated on the stack */ + +struct btree_iter_stack { + struct btree_iter iter; + struct btree_iter_set stack_data[MAX_BSETS]; }; typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k); @@ -333,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter, void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, struct bkey *end); -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search); +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search); struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, const struct bkey *search); @@ -350,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b, return search ? __bch_bset_search(b, t, search) : t->data->start; } -#define for_each_key_filter(b, k, iter, filter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next_filter((iter), (b), filter));) +#define for_each_key_filter(b, k, stack_iter, filter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \ + filter));) -#define for_each_key(b, k, iter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next(iter));) +#define for_each_key(b, k, stack_iter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next(&((stack_iter)->iter)));) /* Sorting */ diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 196cdacce38f2..d011a7154d330 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1309,7 +1309,7 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc) uint8_t stale = 0; unsigned int keys = 0, good_keys = 0; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct bset_tree *t; gc->nodes++; @@ -1570,7 +1570,7 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op, static unsigned int btree_gc_count_keys(struct btree *b) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; unsigned int ret = 0; for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad) @@ -1611,17 +1611,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op, int ret = 0; bool should_rewrite; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct gc_merge_info r[GC_MERGE_NODES]; struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1; - bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done); + bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done); for (i = r; i < r + ARRAY_SIZE(r); i++) i->b = ERR_PTR(-EINTR); while (1) { - k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad); + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad); if (k) { r->b = bch_btree_node_get(b->c, op, k, b->level - 1, true, b); @@ -1911,7 +1912,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op) { int ret = 0; struct bkey *k, *p = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) bch_initial_mark_key(b->c, b->level, k); @@ -1919,10 +1920,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op) bch_initial_mark_key(b->c, b->level + 1, &b->key); if (b->level) { - bch_btree_iter_init(&b->keys, &iter, NULL); + bch_btree_iter_stack_init(&b->keys, &iter, NULL); do { - k = bch_btree_iter_next_filter(&iter, &b->keys, + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad); if (k) { btree_node_prefetch(b, k); @@ -1950,7 +1951,7 @@ static int bch_btree_check_thread(void *arg) struct btree_check_info *info = arg; struct btree_check_state *check_state = info->state; struct cache_set *c = check_state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; @@ -1959,8 +1960,8 @@ static int bch_btree_check_thread(void *arg) ret = 0; /* root node keys are checked before thread created */ - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -1978,7 +1979,7 @@ static int bch_btree_check_thread(void *arg) skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -2051,7 +2052,7 @@ int bch_btree_check(struct cache_set *c) int ret = 0; int i; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct btree_check_state check_state; /* check and mark root node keys */ @@ -2547,11 +2548,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op, if (b->level) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad))) { ret = bcache_btree(map_nodes_recurse, k, b, op, from, fn, flags); @@ -2580,11 +2581,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op, { int ret = MAP_CONTINUE; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) { + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad))) { ret = !b->level ? fn(op, b, k) : bcache_btree(map_keys_recurse, k, diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index dc3f50f697141..0676f863355a9 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1913,8 +1913,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) INIT_LIST_HEAD(&c->btree_cache_freed); INIT_LIST_HEAD(&c->data_buckets); - iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size + 1) * - sizeof(struct btree_iter_set); + iter_size = sizeof(struct btree_iter) + + ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) * + sizeof(struct btree_iter_set); c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL); if (!c->devices) diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index a438efb660699..c4633425acc4b 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -660,7 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c) unsigned int bytes = 0; struct bkey *k; struct btree *b; - struct btree_iter iter; + struct btree_iter_stack iter; goto lock_root; diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 8827a6f130ad7..792e070ccf38b 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -908,15 +908,15 @@ static int bch_dirty_init_thread(void *arg) struct dirty_init_thrd_info *info = arg; struct bch_dirty_init_state *state = info->state; struct cache_set *c = state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; k = p = NULL; prev_idx = 0; - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -930,7 +930,7 @@ static int bch_dirty_init_thread(void *arg) skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -979,7 +979,7 @@ void bch_sectors_dirty_init(struct bcache_device *d) int i; struct btree *b = NULL; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack iter; struct sectors_dirty_init op; struct cache_set *c = d->c; struct bch_dirty_init_state state; diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 13c65b7e1ed63..f5541b8f6320c 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1315,7 +1315,7 @@ static void use_dmio(struct dm_buffer *b, enum req_op op, sector_t sector, io_req.mem.ptr.vma = (char *)b->data + offset; } - r = dm_io(&io_req, 1, ®ion, NULL); + r = dm_io(&io_req, 1, ®ion, NULL, IOPRIO_DEFAULT); if (unlikely(r)) b->end_io(b, errno_to_blk_status(r)); } @@ -2167,7 +2167,7 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c) if (WARN_ON_ONCE(dm_bufio_in_request())) return -EINVAL; - return dm_io(&io_req, 1, &io_reg, NULL); + return dm_io(&io_req, 1, &io_reg, NULL, IOPRIO_DEFAULT); } EXPORT_SYMBOL_GPL(dm_bufio_issue_flush); @@ -2191,7 +2191,7 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c if (WARN_ON_ONCE(dm_bufio_in_request())) return -EINVAL; /* discards are optional */ - return dm_io(&io_req, 1, &io_reg, NULL); + return dm_io(&io_req, 1, &io_reg, NULL, IOPRIO_DEFAULT); } EXPORT_SYMBOL_GPL(dm_bufio_issue_discard); diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 5eabdb06c6498..2ac43d1f1b92c 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -154,8 +154,10 @@ static void delay_dtr(struct dm_target *ti) { struct delay_c *dc = ti->private; - if (dc->kdelayd_wq) + if (dc->kdelayd_wq) { + timer_shutdown_sync(&dc->delay_timer); destroy_workqueue(dc->kdelayd_wq); + } if (dc->read.dev) dm_put_device(ti, dc->read.dev); @@ -240,19 +242,18 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv) ret = delay_class_ctr(ti, &dc->flush, argv); if (ret) goto bad; - max_delay = max(max_delay, dc->write.delay); - max_delay = max(max_delay, dc->flush.delay); goto out; } ret = delay_class_ctr(ti, &dc->write, argv + 3); if (ret) goto bad; + max_delay = max(max_delay, dc->write.delay); + if (argc == 6) { ret = delay_class_ctr(ti, &dc->flush, argv + 3); if (ret) goto bad; - max_delay = max(max_delay, dc->flush.delay); goto out; } @@ -267,8 +268,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv) * In case of small requested delays, use kthread instead of * timers and workqueue to achieve better latency. */ - dc->worker = kthread_create(&flush_worker_fn, dc, - "dm-delay-flush-worker"); + dc->worker = kthread_run(&flush_worker_fn, dc, "dm-delay-flush-worker"); if (IS_ERR(dc->worker)) { ret = PTR_ERR(dc->worker); dc->worker = NULL; @@ -335,7 +335,7 @@ static void delay_presuspend(struct dm_target *ti) mutex_unlock(&delayed_bios_lock); if (!delay_is_fast(dc)) - del_timer_sync(&dc->delay_timer); + timer_delete(&dc->delay_timer); flush_delayed_bios(dc, true); } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 1fc901df84eb1..246ef6f6aae53 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -555,7 +555,7 @@ static int sync_rw_sb(struct dm_integrity_c *ic, blk_opf_t opf) } } - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) return r; @@ -1073,7 +1073,7 @@ static void rw_journal_sectors(struct dm_integrity_c *ic, blk_opf_t opf, io_loc.sector = ic->start + SB_SECTORS + sector; io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { dm_integrity_io_error(ic, (opf & REQ_OP_MASK) == REQ_OP_READ ? "reading journal" : "writing journal", r); @@ -1190,7 +1190,7 @@ static void copy_from_journal(struct dm_integrity_c *ic, unsigned int section, u io_loc.sector = target; io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { WARN_ONCE(1, "asynchronous dm_io failed: %d", r); fn(-1UL, data); @@ -1519,7 +1519,7 @@ static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_dat fr.io_reg.count = 0, fr.ic = ic; init_completion(&fr.comp); - r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL); + r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL, IOPRIO_DEFAULT); BUG_ON(r); } @@ -1699,7 +1699,6 @@ static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checks struct bio_vec bv; sector_t sector, logical_sector, area, offset; struct page *page; - void *buffer; get_area_and_offset(ic, dio->range.logical_sector, &area, &offset); dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset, @@ -1708,13 +1707,14 @@ static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checks logical_sector = dio->range.logical_sector; page = mempool_alloc(&ic->recheck_pool, GFP_NOIO); - buffer = page_to_virt(page); __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) { unsigned pos = 0; do { + sector_t alignment; char *mem; + char *buffer = page_to_virt(page); int r; struct dm_io_request io_req; struct dm_io_region io_loc; @@ -1727,7 +1727,15 @@ static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checks io_loc.sector = sector; io_loc.count = ic->sectors_per_block; - r = dm_io(&io_req, 1, &io_loc, NULL); + /* Align the bio to logical block size */ + alignment = dio->range.logical_sector | bio_sectors(bio) | (PAGE_SIZE >> SECTOR_SHIFT); + alignment &= -alignment; + io_loc.sector = round_down(io_loc.sector, alignment); + io_loc.count += sector - io_loc.sector; + buffer += (sector - io_loc.sector) << SECTOR_SHIFT; + io_loc.count = round_up(io_loc.count, alignment); + + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { dio->bi_status = errno_to_blk_status(r); goto free_ret; @@ -1848,12 +1856,12 @@ static void integrity_metadata(struct work_struct *w) r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset, checksums_ptr - checksums, dio->op == REQ_OP_READ ? TAG_CMP : TAG_WRITE); if (unlikely(r)) { + if (likely(checksums != checksums_onstack)) + kfree(checksums); if (r > 0) { - integrity_recheck(dio, checksums); + integrity_recheck(dio, checksums_onstack); goto skip_io; } - if (likely(checksums != checksums_onstack)) - kfree(checksums); goto error; } @@ -2806,7 +2814,7 @@ static void integrity_recalc(struct work_struct *w) io_loc.sector = get_data_sector(ic, area, offset); io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { dm_integrity_io_error(ic, "reading data", r); goto err; @@ -3484,6 +3492,7 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim limits->physical_block_size = ic->sectors_per_block << SECTOR_SHIFT; blk_limits_io_min(limits, ic->sectors_per_block << SECTOR_SHIFT); limits->dma_alignment = limits->logical_block_size - 1; + limits->discard_granularity = ic->sectors_per_block << SECTOR_SHIFT; } } @@ -4213,7 +4222,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv } else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) { log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval); } else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) { - if (val >= (uint64_t)UINT_MAX * 1000 / HZ) { + if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) { r = -EINVAL; ti->error = "Invalid bitmap_flush_interval argument"; goto bad; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index f053ce2458147..7409490259d1d 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -305,7 +305,7 @@ static void km_dp_init(struct dpages *dp, void *data) */ static void do_region(const blk_opf_t opf, unsigned int region, struct dm_io_region *where, struct dpages *dp, - struct io *io) + struct io *io, unsigned short ioprio) { struct bio *bio; struct page *page; @@ -354,6 +354,7 @@ static void do_region(const blk_opf_t opf, unsigned int region, &io->client->bios); bio->bi_iter.bi_sector = where->sector + (where->count - remaining); bio->bi_end_io = endio; + bio->bi_ioprio = ioprio; store_io_and_region_in_bio(bio, io, region); if (op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) { @@ -383,7 +384,7 @@ static void do_region(const blk_opf_t opf, unsigned int region, static void dispatch_io(blk_opf_t opf, unsigned int num_regions, struct dm_io_region *where, struct dpages *dp, - struct io *io, int sync) + struct io *io, int sync, unsigned short ioprio) { int i; struct dpages old_pages = *dp; @@ -400,7 +401,7 @@ static void dispatch_io(blk_opf_t opf, unsigned int num_regions, for (i = 0; i < num_regions; i++) { *dp = old_pages; if (where[i].count || (opf & REQ_PREFLUSH)) - do_region(opf, i, where + i, dp, io); + do_region(opf, i, where + i, dp, io, ioprio); } /* @@ -425,7 +426,7 @@ static void sync_io_complete(unsigned long error, void *context) static int sync_io(struct dm_io_client *client, unsigned int num_regions, struct dm_io_region *where, blk_opf_t opf, struct dpages *dp, - unsigned long *error_bits) + unsigned long *error_bits, unsigned short ioprio) { struct io *io; struct sync_io sio; @@ -447,7 +448,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, io->vma_invalidate_address = dp->vma_invalidate_address; io->vma_invalidate_size = dp->vma_invalidate_size; - dispatch_io(opf, num_regions, where, dp, io, 1); + dispatch_io(opf, num_regions, where, dp, io, 1, ioprio); wait_for_completion_io(&sio.wait); @@ -459,7 +460,8 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, static int async_io(struct dm_io_client *client, unsigned int num_regions, struct dm_io_region *where, blk_opf_t opf, - struct dpages *dp, io_notify_fn fn, void *context) + struct dpages *dp, io_notify_fn fn, void *context, + unsigned short ioprio) { struct io *io; @@ -479,7 +481,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions, io->vma_invalidate_address = dp->vma_invalidate_address; io->vma_invalidate_size = dp->vma_invalidate_size; - dispatch_io(opf, num_regions, where, dp, io, 0); + dispatch_io(opf, num_regions, where, dp, io, 0, ioprio); return 0; } @@ -521,7 +523,8 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp, } int dm_io(struct dm_io_request *io_req, unsigned int num_regions, - struct dm_io_region *where, unsigned long *sync_error_bits) + struct dm_io_region *where, unsigned long *sync_error_bits, + unsigned short ioprio) { int r; struct dpages dp; @@ -532,11 +535,11 @@ int dm_io(struct dm_io_request *io_req, unsigned int num_regions, if (!io_req->notify.fn) return sync_io(io_req->client, num_regions, where, - io_req->bi_opf, &dp, sync_error_bits); + io_req->bi_opf, &dp, sync_error_bits, ioprio); return async_io(io_req->client, num_regions, where, io_req->bi_opf, &dp, io_req->notify.fn, - io_req->notify.context); + io_req->notify.context, ioprio); } EXPORT_SYMBOL(dm_io); diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 36bcfdccae046..6ea75436a433a 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -578,9 +578,9 @@ static int run_io_job(struct kcopyd_job *job) io_job_start(job->kc->throttle); if (job->op == REQ_OP_READ) - r = dm_io(&io_req, 1, &job->source, NULL); + r = dm_io(&io_req, 1, &job->source, NULL, IOPRIO_DEFAULT); else - r = dm_io(&io_req, job->num_dests, job->dests, NULL); + r = dm_io(&io_req, job->num_dests, job->dests, NULL, IOPRIO_DEFAULT); return r; } diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index f9f84236dfcd7..f7f9c2100937b 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -300,7 +300,7 @@ static int rw_header(struct log_c *lc, enum req_op op) { lc->io_req.bi_opf = op; - return dm_io(&lc->io_req, 1, &lc->header_location, NULL); + return dm_io(&lc->io_req, 1, &lc->header_location, NULL, IOPRIO_DEFAULT); } static int flush_header(struct log_c *lc) @@ -313,7 +313,7 @@ static int flush_header(struct log_c *lc) lc->io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; - return dm_io(&lc->io_req, 1, &null_location, NULL); + return dm_io(&lc->io_req, 1, &null_location, NULL, IOPRIO_DEFAULT); } static int read_header(struct log_c *log) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index eb009d6bb03a1..d97355e9b9a6e 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -213,6 +213,7 @@ struct raid_dev { #define RT_FLAG_RS_IN_SYNC 6 #define RT_FLAG_RS_RESYNCING 7 #define RT_FLAG_RS_GROW 8 +#define RT_FLAG_RS_FROZEN 9 /* Array elements of 64 bit needed for rebuild/failed disk bits */ #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8) @@ -3240,11 +3241,12 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) rs->md.ro = 1; rs->md.in_sync = 1; - /* Keep array frozen until resume. */ - set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery); - /* Has to be held on running the array */ mddev_suspend_and_lock_nointr(&rs->md); + + /* Keep array frozen until resume. */ + md_frozen_sync_thread(&rs->md); + r = md_run(&rs->md); rs->md.in_sync = 0; /* Assume already marked dirty */ if (r) { @@ -3329,17 +3331,18 @@ static int raid_map(struct dm_target *ti, struct bio *bio) struct mddev *mddev = &rs->md; /* - * If we're reshaping to add disk(s)), ti->len and + * If we're reshaping to add disk(s), ti->len and * mddev->array_sectors will differ during the process * (ti->len > mddev->array_sectors), so we have to requeue * bios with addresses > mddev->array_sectors here or * there will occur accesses past EOD of the component * data images thus erroring the raid set. */ - if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) + if (unlikely(bio_has_data(bio) && bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; - md_handle_request(mddev, bio); + if (unlikely(!md_handle_request(mddev, bio))) + return DM_MAPIO_REQUEUE; return DM_MAPIO_SUBMITTED; } @@ -3718,21 +3721,33 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv, { struct raid_set *rs = ti->private; struct mddev *mddev = &rs->md; + int ret = 0; if (!mddev->pers || !mddev->pers->sync_request) return -EINVAL; - if (!strcasecmp(argv[0], "frozen")) - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - else - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags) || + test_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags)) + return -EBUSY; - if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) { - if (mddev->sync_thread) { - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_reap_sync_thread(mddev); - } - } else if (decipher_sync_action(mddev, mddev->recovery) != st_idle) + if (!strcasecmp(argv[0], "frozen")) { + ret = mddev_lock(mddev); + if (ret) + return ret; + + md_frozen_sync_thread(mddev); + mddev_unlock(mddev); + } else if (!strcasecmp(argv[0], "idle")) { + ret = mddev_lock(mddev); + if (ret) + return ret; + + md_idle_sync_thread(mddev); + mddev_unlock(mddev); + } + + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + if (decipher_sync_action(mddev, mddev->recovery) != st_idle) return -EBUSY; else if (!strcasecmp(argv[0], "resync")) ; /* MD_RECOVERY_NEEDED set below */ @@ -3791,15 +3806,46 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs)); } +static void raid_presuspend(struct dm_target *ti) +{ + struct raid_set *rs = ti->private; + struct mddev *mddev = &rs->md; + + /* + * From now on, disallow raid_message() to change sync_thread until + * resume, raid_postsuspend() is too late. + */ + set_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags); + + if (!reshape_interrupted(mddev)) + return; + + /* + * For raid456, if reshape is interrupted, IO across reshape position + * will never make progress, while caller will wait for IO to be done. + * Inform raid456 to handle those IO to prevent deadlock. + */ + if (mddev->pers && mddev->pers->prepare_suspend) + mddev->pers->prepare_suspend(mddev); +} + +static void raid_presuspend_undo(struct dm_target *ti) +{ + struct raid_set *rs = ti->private; + + clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags); +} + static void raid_postsuspend(struct dm_target *ti) { struct raid_set *rs = ti->private; if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { - /* Writes have to be stopped before suspending to avoid deadlocks. */ - if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery)) - md_stop_writes(&rs->md); - + /* + * sync_thread must be stopped during suspend, and writes have + * to be stopped before suspending to avoid deadlocks. + */ + md_stop_writes(&rs->md); mddev_suspend(&rs->md, false); } } @@ -4012,8 +4058,6 @@ static int raid_preresume(struct dm_target *ti) } /* Check for any resize/reshape on @rs and adjust/initiate */ - /* Be prepared for mddev_resume() in raid_resume() */ - set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) { set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); mddev->resync_min = mddev->recovery_cp; @@ -4047,7 +4091,9 @@ static void raid_resume(struct dm_target *ti) * Take this opportunity to check whether any failed * devices are reachable again. */ + mddev_lock_nointr(mddev); attempt_restore_of_faulty_devices(rs); + mddev_unlock(mddev); } if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { @@ -4055,10 +4101,13 @@ static void raid_resume(struct dm_target *ti) if (mddev->delta_disks < 0) rs_set_capacity(rs); + WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)); + WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); + clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags); mddev_lock_nointr(mddev); - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); mddev->ro = 0; mddev->in_sync = 0; + md_unfrozen_sync_thread(mddev); mddev_unlock_and_resume(mddev); } } @@ -4074,6 +4123,8 @@ static struct target_type raid_target = { .message = raid_message, .iterate_devices = raid_iterate_devices, .io_hints = raid_io_hints, + .presuspend = raid_presuspend, + .presuspend_undo = raid_presuspend_undo, .postsuspend = raid_postsuspend, .preresume = raid_preresume, .resume = raid_resume, diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index ddcb2bc4a6179..9511dae5b556a 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -278,7 +278,7 @@ static int mirror_flush(struct dm_target *ti) } error_bits = -1; - dm_io(&io_req, ms->nr_mirrors, io, &error_bits); + dm_io(&io_req, ms->nr_mirrors, io, &error_bits, IOPRIO_DEFAULT); if (unlikely(error_bits != 0)) { for (i = 0; i < ms->nr_mirrors; i++) if (test_bit(i, &error_bits)) @@ -554,7 +554,7 @@ static void read_async_bio(struct mirror *m, struct bio *bio) map_region(&io, m, bio); bio_set_m(bio, m); - BUG_ON(dm_io(&io_req, 1, &io, NULL)); + BUG_ON(dm_io(&io_req, 1, &io, NULL, IOPRIO_DEFAULT)); } static inline int region_in_sync(struct mirror_set *ms, region_t region, @@ -681,7 +681,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio) */ bio_set_m(bio, get_default_mirror(ms)); - BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL)); + BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL, IOPRIO_DEFAULT)); } static void do_writes(struct mirror_set *ms, struct bio_list *writes) diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 15649921f2a9b..568d10842b1f4 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -223,7 +223,7 @@ static void do_metadata(struct work_struct *work) { struct mdata_req *req = container_of(work, struct mdata_req, work); - req->result = dm_io(req->io_req, 1, req->where, NULL); + req->result = dm_io(req->io_req, 1, req->where, NULL, IOPRIO_DEFAULT); } /* @@ -247,7 +247,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, blk_opf_t opf, struct mdata_req req; if (!metadata) - return dm_io(&io_req, 1, &where, NULL); + return dm_io(&io_req, 1, &where, NULL, IOPRIO_DEFAULT); req.where = &where; req.io_req = &io_req; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index bf7a574499a34..0ace06d1bee38 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -684,8 +684,10 @@ static void dm_exception_table_exit(struct dm_exception_table *et, for (i = 0; i < size; i++) { slot = et->table + i; - hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) + hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) { kmem_cache_free(mem, ex); + cond_resched(); + } } kvfree(et->table); diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 1b591bfa90d5d..abc008bae9020 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -511,7 +511,7 @@ static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io, io_loc.bdev = v->data_dev->bdev; io_loc.sector = cur_block << (v->data_dev_block_bits - SECTOR_SHIFT); io_loc.count = 1 << (v->data_dev_block_bits - SECTOR_SHIFT); - r = dm_io(&io_req, 1, &io_loc, NULL); + r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); if (unlikely(r)) goto free_ret; diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index b463c28c39ad3..01ab141bc51e3 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -531,7 +531,7 @@ static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios) req.notify.context = &endio; /* writing via async dm-io (implied by notify.fn above) won't return an error */ - (void) dm_io(&req, 1, ®ion, NULL); + (void) dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); i = j; } @@ -568,7 +568,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc) req.notify.fn = NULL; req.notify.context = NULL; - r = dm_io(&req, 1, ®ion, NULL); + r = dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); if (unlikely(r)) writecache_error(wc, r, "error writing superblock"); } @@ -596,7 +596,7 @@ static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev) req.client = wc->dm_io; req.notify.fn = NULL; - r = dm_io(&req, 1, ®ion, NULL); + r = dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); if (unlikely(r)) writecache_error(wc, r, "error flushing metadata: %d", r); } @@ -990,7 +990,7 @@ static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors req.client = wc->dm_io; req.notify.fn = NULL; - return dm_io(&req, 1, ®ion, NULL); + return dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); } static void writecache_resume(struct dm_target *ti) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 8dcabf84d866e..0dc3650c7f4ca 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2945,6 +2945,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned int suspend static void __dm_internal_resume(struct mapped_device *md) { + int r; + struct dm_table *map; + BUG_ON(!md->internal_suspend_count); if (--md->internal_suspend_count) @@ -2953,12 +2956,23 @@ static void __dm_internal_resume(struct mapped_device *md) if (dm_suspended_md(md)) goto done; /* resume from nested suspend */ - /* - * NOTE: existing callers don't need to call dm_table_resume_targets - * (which may fail -- so best to avoid it for now by passing NULL map) - */ - (void) __dm_resume(md, NULL); - + map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock)); + r = __dm_resume(md, map); + if (r) { + /* + * If a preresume method of some target failed, we are in a + * tricky situation. We can't return an error to the caller. We + * can't fake success because then the "resume" and + * "postsuspend" methods would not be paired correctly, and it + * would break various targets, for example it would cause list + * corruption in the "origin" target. + * + * So, we fake normal suspend here, to make sure that the + * "resume" and "postsuspend" methods will be paired correctly. + */ + DMERR("Preresume method failed: %d", r); + set_bit(DMF_SUSPENDED, &md->flags); + } done: clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags); smp_mb__after_atomic(); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 9672f75c30503..dd8c1133f6c17 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -227,6 +227,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, struct block_device *bdev; struct mddev *mddev = bitmap->mddev; struct bitmap_storage *store = &bitmap->storage; + unsigned int bitmap_limit = (bitmap->storage.file_pages - pg_index) << + PAGE_SHIFT; loff_t sboff, offset = mddev->bitmap_info.offset; sector_t ps = pg_index * PAGE_SIZE / SECTOR_SIZE; unsigned int size = PAGE_SIZE; @@ -234,7 +236,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, sector_t doff; bdev = (rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev; - if (pg_index == store->file_pages - 1) { + /* we compare length (page numbers), not page offset. */ + if ((pg_index - store->sb_index) == store->file_pages - 1) { unsigned int last_page_size = store->bytes & (PAGE_SIZE - 1); if (last_page_size == 0) @@ -268,11 +271,9 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, if (size == 0) /* bitmap runs in to data */ return -EINVAL; - } else { - /* DATA METADATA BITMAP - no problems */ } - md_super_write(mddev, rdev, sboff + ps, (int) size, page); + md_super_write(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), page); return 0; } @@ -438,8 +439,8 @@ static void filemap_write_page(struct bitmap *bitmap, unsigned long pg_index, struct page *page = store->filemap[pg_index]; if (mddev_is_clustered(bitmap->mddev)) { - pg_index += bitmap->cluster_slot * - DIV_ROUND_UP(store->bytes, PAGE_SIZE); + /* go to node bitmap area starting point */ + pg_index += store->sb_index; } if (store->file) @@ -952,6 +953,7 @@ static void md_bitmap_file_set_bit(struct bitmap *bitmap, sector_t block) unsigned long index = file_page_index(store, chunk); unsigned long node_offset = 0; + index += store->sb_index; if (mddev_is_clustered(bitmap->mddev)) node_offset = bitmap->cluster_slot * store->file_pages; @@ -982,6 +984,7 @@ static void md_bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block) unsigned long index = file_page_index(store, chunk); unsigned long node_offset = 0; + index += store->sb_index; if (mddev_is_clustered(bitmap->mddev)) node_offset = bitmap->cluster_slot * store->file_pages; @@ -1424,7 +1427,7 @@ __acquires(bitmap->lock) sector_t chunk = offset >> bitmap->chunkshift; unsigned long page = chunk >> PAGE_COUNTER_SHIFT; unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT; - sector_t csize; + sector_t csize = ((sector_t)1) << bitmap->chunkshift; int err; if (page >= bitmap->pages) { @@ -1433,6 +1436,7 @@ __acquires(bitmap->lock) * End-of-device while looking for a whole page or * user set a huge number to sysfs bitmap_set_bits. */ + *blocks = csize - (offset & (csize - 1)); return NULL; } err = md_bitmap_checkpage(bitmap, page, create, 0); @@ -1441,8 +1445,7 @@ __acquires(bitmap->lock) bitmap->bp[page].map == NULL) csize = ((sector_t)1) << (bitmap->chunkshift + PAGE_COUNTER_SHIFT); - else - csize = ((sector_t)1) << bitmap->chunkshift; + *blocks = csize - (offset & (csize - 1)); if (err < 0) diff --git a/drivers/md/md.c b/drivers/md/md.c index 9e41a9aaba8b5..f54012d684414 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -99,18 +99,6 @@ static void mddev_detach(struct mddev *mddev); static void export_rdev(struct md_rdev *rdev, struct mddev *mddev); static void md_wakeup_thread_directly(struct md_thread __rcu *thread); -enum md_ro_state { - MD_RDWR, - MD_RDONLY, - MD_AUTO_READ, - MD_MAX_STATE -}; - -static bool md_is_rdwr(struct mddev *mddev) -{ - return (mddev->ro == MD_RDWR); -} - /* * Default number of read corrections we'll attempt on an rdev * before ejecting it from the array. We divide the read error @@ -378,7 +366,7 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio) return true; } -void md_handle_request(struct mddev *mddev, struct bio *bio) +bool md_handle_request(struct mddev *mddev, struct bio *bio) { check_suspended: if (is_suspended(mddev, bio)) { @@ -386,7 +374,7 @@ void md_handle_request(struct mddev *mddev, struct bio *bio) /* Bail out if REQ_NOWAIT is set for the bio */ if (bio->bi_opf & REQ_NOWAIT) { bio_wouldblock_error(bio); - return; + return true; } for (;;) { prepare_to_wait(&mddev->sb_wait, &__wait, @@ -402,10 +390,13 @@ void md_handle_request(struct mddev *mddev, struct bio *bio) if (!mddev->pers->make_request(mddev, bio)) { percpu_ref_put(&mddev->active_io); + if (!mddev->gendisk && mddev->pers->prepare_suspend) + return false; goto check_suspended; } percpu_ref_put(&mddev->active_io); + return true; } EXPORT_SYMBOL(md_handle_request); @@ -2566,6 +2557,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) fail: pr_warn("md: failed to register dev-%s for %s\n", b, mdname(mddev)); + mddev_destroy_serial_pool(mddev, rdev); return err; } @@ -4919,6 +4911,35 @@ static void stop_sync_thread(struct mddev *mddev, bool locked, bool check_seq) mddev_lock_nointr(mddev); } +void md_idle_sync_thread(struct mddev *mddev) +{ + lockdep_assert_held(&mddev->reconfig_mutex); + + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + stop_sync_thread(mddev, true, true); +} +EXPORT_SYMBOL_GPL(md_idle_sync_thread); + +void md_frozen_sync_thread(struct mddev *mddev) +{ + lockdep_assert_held(&mddev->reconfig_mutex); + + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + stop_sync_thread(mddev, true, false); +} +EXPORT_SYMBOL_GPL(md_frozen_sync_thread); + +void md_unfrozen_sync_thread(struct mddev *mddev) +{ + lockdep_assert_held(&mddev->reconfig_mutex); + + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); + sysfs_notify_dirent_safe(mddev->sysfs_action); +} +EXPORT_SYMBOL_GPL(md_unfrozen_sync_thread); + static void idle_sync_thread(struct mddev *mddev) { mutex_lock(&mddev->sync_mutex); @@ -6038,7 +6059,10 @@ int md_run(struct mddev *mddev) pr_warn("True protection against single-disk failure might be compromised.\n"); } - mddev->recovery = 0; + /* dm-raid expect sync_thread to be frozen until resume */ + if (mddev->gendisk) + mddev->recovery = 0; + /* may be over-ridden by personality */ mddev->resync_max_sectors = mddev->dev_sectors; @@ -6278,7 +6302,15 @@ static void md_clean(struct mddev *mddev) mddev->persistent = 0; mddev->level = LEVEL_NONE; mddev->clevel[0] = 0; - mddev->flags = 0; + /* + * Don't clear MD_CLOSING, or mddev can be opened again. + * 'hold_active != 0' means mddev is still in the creation + * process and will be used later. + */ + if (mddev->hold_active) + mddev->flags = 0; + else + mddev->flags &= BIT_ULL_MASK(MD_CLOSING); mddev->sb_flags = 0; mddev->ro = MD_RDWR; mddev->metadata_type[0] = 0; @@ -6315,7 +6347,6 @@ static void md_clean(struct mddev *mddev) static void __md_stop_writes(struct mddev *mddev) { - stop_sync_thread(mddev, true, false); del_timer_sync(&mddev->safemode_timer); if (mddev->pers && mddev->pers->quiesce) { @@ -6340,6 +6371,8 @@ static void __md_stop_writes(struct mddev *mddev) void md_stop_writes(struct mddev *mddev) { mddev_lock_nointr(mddev); + set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + stop_sync_thread(mddev, true, false); __md_stop_writes(mddev); mddev_unlock(mddev); } @@ -7624,7 +7657,6 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, int err = 0; void __user *argp = (void __user *)arg; struct mddev *mddev = NULL; - bool did_set_md_closing = false; if (!md_ioctl_valid(cmd)) return -ENOTTY; @@ -7708,7 +7740,6 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, err = -EBUSY; goto out; } - did_set_md_closing = true; mutex_unlock(&mddev->open_mutex); sync_blockdev(bdev); } @@ -7850,7 +7881,7 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode, mddev_unlock(mddev); out: - if(did_set_md_closing) + if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY)) clear_bit(MD_CLOSING, &mddev->flags); return err; } @@ -8737,6 +8768,23 @@ void md_account_bio(struct mddev *mddev, struct bio **bio) } EXPORT_SYMBOL_GPL(md_account_bio); +void md_free_cloned_bio(struct bio *bio) +{ + struct md_io_clone *md_io_clone = bio->bi_private; + struct bio *orig_bio = md_io_clone->orig_bio; + struct mddev *mddev = md_io_clone->mddev; + + if (bio->bi_status && !orig_bio->bi_status) + orig_bio->bi_status = bio->bi_status; + + if (md_io_clone->start_time) + bio_end_io_acct(orig_bio, md_io_clone->start_time); + + bio_put(bio); + percpu_ref_put(&mddev->active_io); +} +EXPORT_SYMBOL_GPL(md_free_cloned_bio); + /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before @@ -9270,9 +9318,14 @@ static bool md_spares_need_change(struct mddev *mddev) { struct md_rdev *rdev; - rdev_for_each(rdev, mddev) - if (rdev_removeable(rdev) || rdev_addable(rdev)) + rcu_read_lock(); + rdev_for_each_rcu(rdev, mddev) { + if (rdev_removeable(rdev) || rdev_addable(rdev)) { + rcu_read_unlock(); return true; + } + } + rcu_read_unlock(); return false; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 8d881cc597992..375ad4a2df71d 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -207,6 +207,7 @@ enum flag_bits { * check if there is collision between raid1 * serial bios. */ + Nonrot, /* non-rotational device (SSD) */ }; static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, @@ -558,6 +559,37 @@ enum recovery_flags { MD_RESYNCING_REMOTE, /* remote node is running resync thread */ }; +enum md_ro_state { + MD_RDWR, + MD_RDONLY, + MD_AUTO_READ, + MD_MAX_STATE +}; + +static inline bool md_is_rdwr(struct mddev *mddev) +{ + return (mddev->ro == MD_RDWR); +} + +static inline bool reshape_interrupted(struct mddev *mddev) +{ + /* reshape never start */ + if (mddev->reshape_position == MaxSector) + return false; + + /* interrupted */ + if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + return true; + + /* running reshape will be interrupted soon. */ + if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) || + test_bit(MD_RECOVERY_INTR, &mddev->recovery) || + test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) + return true; + + return false; +} + static inline int __must_check mddev_lock(struct mddev *mddev) { return mutex_lock_interruptible(&mddev->reconfig_mutex); @@ -617,6 +649,7 @@ struct md_personality int (*start_reshape) (struct mddev *mddev); void (*finish_reshape) (struct mddev *mddev); void (*update_reshape_pos) (struct mddev *mddev); + void (*prepare_suspend) (struct mddev *mddev); /* quiesce suspends or resumes internal processing. * 1 - stop new actions and wait for action io to complete * 0 - return to normal behaviour @@ -750,6 +783,7 @@ extern void md_finish_reshape(struct mddev *mddev); void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio, sector_t start, sector_t size); void md_account_bio(struct mddev *mddev, struct bio **bio); +void md_free_cloned_bio(struct bio *bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, @@ -778,9 +812,12 @@ extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); -extern void md_handle_request(struct mddev *mddev, struct bio *bio); +extern bool md_handle_request(struct mddev *mddev, struct bio *bio); extern int mddev_suspend(struct mddev *mddev, bool interruptible); extern void mddev_resume(struct mddev *mddev); +extern void md_idle_sync_thread(struct mddev *mddev); +extern void md_frozen_sync_thread(struct mddev *mddev); +extern void md_unfrozen_sync_thread(struct mddev *mddev); extern void md_reload_sb(struct mddev *mddev, int raid_disk); extern void md_update_sb(struct mddev *mddev, int force); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index c50a7abda744a..c3de0da626584 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -263,11 +263,12 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) default_layout == RAID0_ALT_MULTIZONE_LAYOUT) { conf->layout = default_layout; } else { - pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n", - mdname(mddev)); - pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n"); - err = -EOPNOTSUPP; - goto abort; + conf->layout = RAID0_ALT_MULTIZONE_LAYOUT; + pr_warn("md/raid0:%s: !!! DEFAULTING TO ALTERNATE LAYOUT !!!\n", + mdname(mddev)); + pr_warn("md/raid0: Please set raid0.default_layout to 1 or 2\n"); + pr_warn("md/raid0: Read the following page for more information:\n"); + pr_warn("md/raid0: https://wiki.ubuntu.com/Kernel/Raid0LayoutMigration\n"); } if (conf->layout == RAID0_ORIG_LAYOUT) { diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 286f8b16c7bde..4f3c35f1320d4 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -601,14 +601,12 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect const sector_t this_sector = r1_bio->sector; int sectors; int best_good_sectors; - int best_disk, best_dist_disk, best_pending_disk; - int has_nonrot_disk; + int best_disk, best_dist_disk, best_pending_disk, sequential_disk; int disk; sector_t best_dist; unsigned int min_pending; struct md_rdev *rdev; int choose_first; - int choose_next_idle; /* * Check if we can balance. We can balance on the whole @@ -619,12 +617,11 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect sectors = r1_bio->sectors; best_disk = -1; best_dist_disk = -1; + sequential_disk = -1; best_dist = MaxSector; best_pending_disk = -1; min_pending = UINT_MAX; best_good_sectors = 0; - has_nonrot_disk = 0; - choose_next_idle = 0; clear_bit(R1BIO_FailFast, &r1_bio->state); if ((conf->mddev->recovery_cp < this_sector + sectors) || @@ -640,7 +637,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect sector_t first_bad; int bad_sectors; unsigned int pending; - bool nonrot; rdev = conf->mirrors[disk].rdev; if (r1_bio->bios[disk] == IO_BLOCKED @@ -706,8 +702,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect /* At least two disks to choose from so failfast is OK */ set_bit(R1BIO_FailFast, &r1_bio->state); - nonrot = bdev_nonrot(rdev->bdev); - has_nonrot_disk |= nonrot; pending = atomic_read(&rdev->nr_pending); dist = abs(this_sector - conf->mirrors[disk].head_position); if (choose_first) { @@ -720,7 +714,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect int opt_iosize = bdev_io_opt(rdev->bdev) >> 9; struct raid1_info *mirror = &conf->mirrors[disk]; - best_disk = disk; /* * If buffered sequential IO size exceeds optimal * iosize, check if there is idle disk. If yes, choose @@ -734,20 +727,27 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect * small, but not a big deal since when the second disk * starts IO, the first disk is likely still busy. */ - if (nonrot && opt_iosize > 0 && + if (test_bit(Nonrot, &rdev->flags) && opt_iosize > 0 && mirror->seq_start != MaxSector && mirror->next_seq_sect > opt_iosize && mirror->next_seq_sect - opt_iosize >= mirror->seq_start) { - choose_next_idle = 1; - continue; + /* + * Add 'pending' to avoid choosing this disk if + * there is other idle disk. + */ + pending++; + /* + * If there is no other idle disk, this disk + * will be chosen. + */ + sequential_disk = disk; + } else { + best_disk = disk; + break; } - break; } - if (choose_next_idle) - continue; - if (min_pending > pending) { min_pending = pending; best_pending_disk = disk; @@ -759,6 +759,13 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect } } + /* + * sequential IO size exceeds optimal iosize, however, there is no other + * idle disk, so choose the sequential disk. + */ + if (best_disk == -1 && min_pending != 0) + best_disk = sequential_disk; + /* * If all disks are rotational, choose the closest disk. If any disk is * non-rotational, choose the disk with less pending request even the @@ -766,7 +773,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect * mixed ratation/non-rotational disks depending on workload. */ if (best_disk == -1) { - if (has_nonrot_disk || min_pending == 0) + if (READ_ONCE(conf->nonrot_disks) || min_pending == 0) best_disk = best_pending_disk; else best_disk = best_dist_disk; @@ -1467,7 +1474,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, for (j = 0; j < i; j++) if (r1_bio->bios[j]) rdev_dec_pending(conf->mirrors[j].rdev, mddev); - free_r1bio(r1_bio); + mempool_free(r1_bio, &conf->r1bio_pool); allow_barrier(conf, bio->bi_iter.bi_sector); if (bio->bi_opf & REQ_NOWAIT) { @@ -1760,6 +1767,52 @@ static int raid1_spare_active(struct mddev *mddev) return count; } +static bool raid1_add_conf(struct r1conf *conf, struct md_rdev *rdev, int disk, + bool replacement) +{ + struct raid1_info *info = conf->mirrors + disk; + + if (replacement) + info += conf->raid_disks; + + if (info->rdev) + return false; + + if (bdev_nonrot(rdev->bdev)) { + set_bit(Nonrot, &rdev->flags); + WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks + 1); + } + + rdev->raid_disk = disk; + info->head_position = 0; + info->seq_start = MaxSector; + WRITE_ONCE(info->rdev, rdev); + + return true; +} + +static bool raid1_remove_conf(struct r1conf *conf, int disk) +{ + struct raid1_info *info = conf->mirrors + disk; + struct md_rdev *rdev = info->rdev; + + if (!rdev || test_bit(In_sync, &rdev->flags) || + atomic_read(&rdev->nr_pending)) + return false; + + /* Only remove non-faulty devices if recovery is not possible. */ + if (!test_bit(Faulty, &rdev->flags) && + rdev->mddev->recovery_disabled != conf->recovery_disabled && + rdev->mddev->degraded < conf->raid_disks) + return false; + + if (test_and_clear_bit(Nonrot, &rdev->flags)) + WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks - 1); + + WRITE_ONCE(info->rdev, NULL); + return true; +} + static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) { struct r1conf *conf = mddev->private; @@ -1795,15 +1848,13 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); - p->head_position = 0; - rdev->raid_disk = mirror; + raid1_add_conf(conf, rdev, mirror, false); err = 0; /* As all devices are equivalent, we don't need a full recovery * if this was recently any drive of the array */ if (rdev->saved_raid_disk < 0) conf->fullsync = 1; - WRITE_ONCE(p->rdev, rdev); break; } if (test_bit(WantReplacement, &p->rdev->flags) && @@ -1813,13 +1864,11 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (err && repl_slot >= 0) { /* Add this device as a replacement */ - p = conf->mirrors + repl_slot; clear_bit(In_sync, &rdev->flags); set_bit(Replacement, &rdev->flags); - rdev->raid_disk = repl_slot; + raid1_add_conf(conf, rdev, repl_slot, true); err = 0; conf->fullsync = 1; - WRITE_ONCE(p[conf->raid_disks].rdev, rdev); } print_conf(conf); @@ -1836,27 +1885,20 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) if (unlikely(number >= conf->raid_disks)) goto abort; - if (rdev != p->rdev) - p = conf->mirrors + conf->raid_disks + number; + if (rdev != p->rdev) { + number += conf->raid_disks; + p = conf->mirrors + number; + } print_conf(conf); if (rdev == p->rdev) { - if (test_bit(In_sync, &rdev->flags) || - atomic_read(&rdev->nr_pending)) { - err = -EBUSY; - goto abort; - } - /* Only remove non-faulty devices if recovery - * is not possible. - */ - if (!test_bit(Faulty, &rdev->flags) && - mddev->recovery_disabled != conf->recovery_disabled && - mddev->degraded < conf->raid_disks) { + if (!raid1_remove_conf(conf, number)) { err = -EBUSY; goto abort; } - WRITE_ONCE(p->rdev, NULL); - if (conf->mirrors[conf->raid_disks + number].rdev) { + + if (number < conf->raid_disks && + conf->mirrors[conf->raid_disks + number].rdev) { /* We just removed a device that is being replaced. * Move down the replacement. We drain all IO before * doing this to avoid confusion. @@ -3006,23 +3048,17 @@ static struct r1conf *setup_conf(struct mddev *mddev) err = -EINVAL; spin_lock_init(&conf->device_lock); + conf->raid_disks = mddev->raid_disks; rdev_for_each(rdev, mddev) { int disk_idx = rdev->raid_disk; - if (disk_idx >= mddev->raid_disks - || disk_idx < 0) + + if (disk_idx >= conf->raid_disks || disk_idx < 0) continue; - if (test_bit(Replacement, &rdev->flags)) - disk = conf->mirrors + mddev->raid_disks + disk_idx; - else - disk = conf->mirrors + disk_idx; - if (disk->rdev) + if (!raid1_add_conf(conf, rdev, disk_idx, + test_bit(Replacement, &rdev->flags))) goto abort; - disk->rdev = rdev; - disk->head_position = 0; - disk->seq_start = MaxSector; } - conf->raid_disks = mddev->raid_disks; conf->mddev = mddev; INIT_LIST_HEAD(&conf->retry_list); INIT_LIST_HEAD(&conf->bio_end_io_list); diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index 14d4211a123a8..5300cbaa58a41 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -71,6 +71,7 @@ struct r1conf { * allow for replacements. */ int raid_disks; + int nonrot_disks; spinlock_t device_lock; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6a7a32f7fb912..40f951d0a7524 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -760,6 +760,7 @@ enum stripe_result { STRIPE_RETRY, STRIPE_SCHEDULE_AND_RETRY, STRIPE_FAIL, + STRIPE_WAIT_RESHAPE, }; struct stripe_request_ctx { @@ -2412,7 +2413,7 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) atomic_inc(&conf->active_stripes); raid5_release_stripe(sh); - conf->max_nr_stripes++; + WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes + 1); return 1; } @@ -2707,7 +2708,7 @@ static int drop_one_stripe(struct r5conf *conf) shrink_buffers(sh); free_stripe(conf->slab_cache, sh); atomic_dec(&conf->active_stripes); - conf->max_nr_stripes--; + WRITE_ONCE(conf->max_nr_stripes, conf->max_nr_stripes - 1); return 1; } @@ -5946,7 +5947,8 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, if (ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) { spin_unlock_irq(&conf->device_lock); - return STRIPE_SCHEDULE_AND_RETRY; + ret = STRIPE_SCHEDULE_AND_RETRY; + goto out; } } spin_unlock_irq(&conf->device_lock); @@ -6025,6 +6027,12 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, out_release: raid5_release_stripe(sh); +out: + if (ret == STRIPE_SCHEDULE_AND_RETRY && reshape_interrupted(mddev)) { + bi->bi_status = BLK_STS_RESOURCE; + ret = STRIPE_WAIT_RESHAPE; + pr_err_ratelimited("dm-raid456: io across reshape position while reshape can't make progress"); + } return ret; } @@ -6146,7 +6154,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) while (1) { res = make_stripe_request(mddev, conf, &ctx, logical_sector, bi); - if (res == STRIPE_FAIL) + if (res == STRIPE_FAIL || res == STRIPE_WAIT_RESHAPE) break; if (res == STRIPE_RETRY) @@ -6184,6 +6192,11 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) if (rw == WRITE) md_write_end(mddev); + if (res == STRIPE_WAIT_RESHAPE) { + md_free_cloned_bio(bi); + return false; + } + bio_endio(bi); return true; } @@ -6737,6 +6750,9 @@ static void raid5d(struct md_thread *thread) int batch_size, released; unsigned int offset; + if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) + break; + released = release_stripe_list(conf, conf->temp_inactive_list); if (released) clear_bit(R5_DID_ALLOC, &conf->cache_state); @@ -6820,7 +6836,7 @@ raid5_set_cache_size(struct mddev *mddev, int size) if (size <= 16 || size > 32768) return -EINVAL; - conf->min_nr_stripes = size; + WRITE_ONCE(conf->min_nr_stripes, size); mutex_lock(&conf->cache_size_mutex); while (size < conf->max_nr_stripes && drop_one_stripe(conf)) @@ -6832,7 +6848,7 @@ raid5_set_cache_size(struct mddev *mddev, int size) mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) if (!grow_one_stripe(conf, GFP_KERNEL)) { - conf->min_nr_stripes = conf->max_nr_stripes; + WRITE_ONCE(conf->min_nr_stripes, conf->max_nr_stripes); result = -ENOMEM; break; } @@ -7390,11 +7406,13 @@ static unsigned long raid5_cache_count(struct shrinker *shrink, struct shrink_control *sc) { struct r5conf *conf = shrink->private_data; + int max_stripes = READ_ONCE(conf->max_nr_stripes); + int min_stripes = READ_ONCE(conf->min_nr_stripes); - if (conf->max_nr_stripes < conf->min_nr_stripes) + if (max_stripes < min_stripes) /* unlikely, but not impossible */ return 0; - return conf->max_nr_stripes - conf->min_nr_stripes; + return max_stripes - min_stripes; } static struct r5conf *setup_conf(struct mddev *mddev) @@ -8909,6 +8927,18 @@ static int raid5_start(struct mddev *mddev) return r5l_start(conf->log); } +/* + * This is only used for dm-raid456, caller already frozen sync_thread, hence + * if rehsape is still in progress, io that is waiting for reshape can never be + * done now, hence wake up and handle those IO. + */ +static void raid5_prepare_suspend(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + + wake_up(&conf->wait_for_overlap); +} + static struct md_personality raid6_personality = { .name = "raid6", @@ -8932,6 +8962,7 @@ static struct md_personality raid6_personality = .quiesce = raid5_quiesce, .takeover = raid6_takeover, .change_consistency_policy = raid5_change_consistency_policy, + .prepare_suspend = raid5_prepare_suspend, }; static struct md_personality raid5_personality = { @@ -8956,6 +8987,7 @@ static struct md_personality raid5_personality = .quiesce = raid5_quiesce, .takeover = raid5_takeover, .change_consistency_policy = raid5_change_consistency_policy, + .prepare_suspend = raid5_prepare_suspend, }; static struct md_personality raid4_personality = @@ -8981,6 +9013,7 @@ static struct md_personality raid4_personality = .quiesce = raid5_quiesce, .takeover = raid4_takeover, .change_consistency_policy = raid5_change_consistency_policy, + .prepare_suspend = raid5_prepare_suspend, }; static int __init raid5_init(void) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 5741adf09a2ef..da09834990b87 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -490,6 +490,15 @@ int cec_thread_func(void *_adap) goto unlock; } + if (adap->transmit_in_progress && + adap->transmit_in_progress_aborted) { + if (adap->transmitting) + cec_data_cancel(adap->transmitting, + CEC_TX_STATUS_ABORTED, 0); + adap->transmit_in_progress = false; + adap->transmit_in_progress_aborted = false; + goto unlock; + } if (adap->transmit_in_progress && timeout) { /* * If we timeout, then log that. Normally this does @@ -771,6 +780,7 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, { struct cec_data *data; bool is_raw = msg_is_raw(msg); + int err; if (adap->devnode.unregistered) return -ENODEV; @@ -935,11 +945,13 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, * Release the lock and wait, retake the lock afterwards. */ mutex_unlock(&adap->lock); - wait_for_completion_killable(&data->c); - if (!data->completed) - cancel_delayed_work_sync(&data->work); + err = wait_for_completion_killable(&data->c); + cancel_delayed_work_sync(&data->work); mutex_lock(&adap->lock); + if (err) + adap->transmit_in_progress_aborted = true; + /* Cancel the transmit if it was interrupted */ if (!data->completed) { if (data->msg.tx_status & CEC_TX_STATUS_OK) @@ -1151,20 +1163,6 @@ void cec_received_msg_ts(struct cec_adapter *adap, if (valid_la && min_len) { /* These messages have special length requirements */ switch (cmd) { - case CEC_MSG_TIMER_STATUS: - if (msg->msg[2] & 0x10) { - switch (msg->msg[2] & 0xf) { - case CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE: - case CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE: - if (msg->len < 5) - valid_la = false; - break; - } - } else if ((msg->msg[2] & 0xf) == CEC_OP_PROG_ERROR_DUPLICATE) { - if (msg->len < 5) - valid_la = false; - } - break; case CEC_MSG_RECORD_ON: switch (msg->msg[2]) { case CEC_OP_RECORD_SRC_OWN: @@ -1589,9 +1587,12 @@ static int cec_config_thread_func(void *arg) */ static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) { - if (WARN_ON(adap->is_configuring || adap->is_configured)) + if (WARN_ON(adap->is_claiming_log_addrs || + adap->is_configuring || adap->is_configured)) return; + adap->is_claiming_log_addrs = true; + init_completion(&adap->config_completion); /* Ready to kick off the thread */ @@ -1606,6 +1607,7 @@ static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) wait_for_completion(&adap->config_completion); mutex_lock(&adap->lock); } + adap->is_claiming_log_addrs = false; } /* diff --git a/drivers/media/cec/core/cec-api.c b/drivers/media/cec/core/cec-api.c index 67dc79ef17050..3ef9153443044 100644 --- a/drivers/media/cec/core/cec-api.c +++ b/drivers/media/cec/core/cec-api.c @@ -178,7 +178,7 @@ static long cec_adap_s_log_addrs(struct cec_adapter *adap, struct cec_fh *fh, CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU | CEC_LOG_ADDRS_FL_CDC_ONLY; mutex_lock(&adap->lock); - if (!adap->is_configuring && + if (!adap->is_claiming_log_addrs && !adap->is_configuring && (!log_addrs.num_log_addrs || !adap->is_configured) && !cec_is_busy(adap, fh)) { err = __cec_s_log_addrs(adap, &log_addrs, block); @@ -664,6 +664,8 @@ static int cec_release(struct inode *inode, struct file *filp) list_del_init(&data->xfer_list); } mutex_unlock(&adap->lock); + + mutex_lock(&fh->lock); while (!list_empty(&fh->msgs)) { struct cec_msg_entry *entry = list_first_entry(&fh->msgs, struct cec_msg_entry, list); @@ -681,6 +683,7 @@ static int cec_release(struct inode *inode, struct file *filp) kfree(entry); } } + mutex_unlock(&fh->lock); kfree(fh); cec_put_device(devnode); diff --git a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c index a366566f22c3b..642c48e8c1f58 100644 --- a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c +++ b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c @@ -113,6 +113,7 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) { unsigned pat; unsigned plane; + int ret = 0; tpg->max_line_width = max_w; for (pat = 0; pat < TPG_MAX_PAT_LINES; pat++) { @@ -121,14 +122,18 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) tpg->lines[pat][plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->lines[pat][plane]) - return -ENOMEM; + if (!tpg->lines[pat][plane]) { + ret = -ENOMEM; + goto free_lines; + } if (plane == 0) continue; tpg->downsampled_lines[pat][plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->downsampled_lines[pat][plane]) - return -ENOMEM; + if (!tpg->downsampled_lines[pat][plane]) { + ret = -ENOMEM; + goto free_lines; + } } } for (plane = 0; plane < TPG_MAX_PLANES; plane++) { @@ -136,18 +141,45 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) tpg->contrast_line[plane] = vzalloc(array_size(pixelsz, max_w)); - if (!tpg->contrast_line[plane]) - return -ENOMEM; + if (!tpg->contrast_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } tpg->black_line[plane] = vzalloc(array_size(pixelsz, max_w)); - if (!tpg->black_line[plane]) - return -ENOMEM; + if (!tpg->black_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } tpg->random_line[plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->random_line[plane]) - return -ENOMEM; + if (!tpg->random_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } } return 0; + +free_contrast_line: + for (plane = 0; plane < TPG_MAX_PLANES; plane++) { + vfree(tpg->contrast_line[plane]); + vfree(tpg->black_line[plane]); + vfree(tpg->random_line[plane]); + tpg->contrast_line[plane] = NULL; + tpg->black_line[plane] = NULL; + tpg->random_line[plane] = NULL; + } +free_lines: + for (pat = 0; pat < TPG_MAX_PAT_LINES; pat++) + for (plane = 0; plane < TPG_MAX_PLANES; plane++) { + vfree(tpg->lines[pat][plane]); + tpg->lines[pat][plane] = NULL; + if (plane == 0) + continue; + vfree(tpg->downsampled_lines[pat][plane]); + tpg->downsampled_lines[pat][plane] = NULL; + } + return ret; } EXPORT_SYMBOL_GPL(tpg_alloc); diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 49f0eb7d0b9d3..733d0bc4b4cc3 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -490,6 +490,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); if (!dvbdevfops) { kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } @@ -498,6 +499,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, if (!new_node) { kfree(dvbdevfops); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } @@ -531,6 +533,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } list_del(&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); return -EINVAL; @@ -553,6 +556,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvb_media_device_free(dvbdev); list_del(&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return ret; } @@ -571,6 +575,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvb_media_device_free(dvbdev); list_del(&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c index 2638875924153..231b45632ad5a 100644 --- a/drivers/media/dvb-frontends/lgdt3306a.c +++ b/drivers/media/dvb-frontends/lgdt3306a.c @@ -2176,6 +2176,11 @@ static int lgdt3306a_probe(struct i2c_client *client) struct dvb_frontend *fe; int ret; + if (!client->dev.platform_data) { + dev_err(&client->dev, "platform data is mandatory\n"); + return -EINVAL; + } + config = kmemdup(client->dev.platform_data, sizeof(struct lgdt3306a_config), GFP_KERNEL); if (config == NULL) { diff --git a/drivers/media/dvb-frontends/mxl5xx.c b/drivers/media/dvb-frontends/mxl5xx.c index 4ebbcf05cc09e..91e9c378397c8 100644 --- a/drivers/media/dvb-frontends/mxl5xx.c +++ b/drivers/media/dvb-frontends/mxl5xx.c @@ -1381,57 +1381,57 @@ static int config_ts(struct mxl *state, enum MXL_HYDRA_DEMOD_ID_E demod_id, u32 nco_count_min = 0; u32 clk_type = 0; - struct MXL_REG_FIELD_T xpt_sync_polarity[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_sync_polarity[MXL_HYDRA_DEMOD_MAX] = { {0x90700010, 8, 1}, {0x90700010, 9, 1}, {0x90700010, 10, 1}, {0x90700010, 11, 1}, {0x90700010, 12, 1}, {0x90700010, 13, 1}, {0x90700010, 14, 1}, {0x90700010, 15, 1} }; - struct MXL_REG_FIELD_T xpt_clock_polarity[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_clock_polarity[MXL_HYDRA_DEMOD_MAX] = { {0x90700010, 16, 1}, {0x90700010, 17, 1}, {0x90700010, 18, 1}, {0x90700010, 19, 1}, {0x90700010, 20, 1}, {0x90700010, 21, 1}, {0x90700010, 22, 1}, {0x90700010, 23, 1} }; - struct MXL_REG_FIELD_T xpt_valid_polarity[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_valid_polarity[MXL_HYDRA_DEMOD_MAX] = { {0x90700014, 0, 1}, {0x90700014, 1, 1}, {0x90700014, 2, 1}, {0x90700014, 3, 1}, {0x90700014, 4, 1}, {0x90700014, 5, 1}, {0x90700014, 6, 1}, {0x90700014, 7, 1} }; - struct MXL_REG_FIELD_T xpt_ts_clock_phase[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_ts_clock_phase[MXL_HYDRA_DEMOD_MAX] = { {0x90700018, 0, 3}, {0x90700018, 4, 3}, {0x90700018, 8, 3}, {0x90700018, 12, 3}, {0x90700018, 16, 3}, {0x90700018, 20, 3}, {0x90700018, 24, 3}, {0x90700018, 28, 3} }; - struct MXL_REG_FIELD_T xpt_lsb_first[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_lsb_first[MXL_HYDRA_DEMOD_MAX] = { {0x9070000C, 16, 1}, {0x9070000C, 17, 1}, {0x9070000C, 18, 1}, {0x9070000C, 19, 1}, {0x9070000C, 20, 1}, {0x9070000C, 21, 1}, {0x9070000C, 22, 1}, {0x9070000C, 23, 1} }; - struct MXL_REG_FIELD_T xpt_sync_byte[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_sync_byte[MXL_HYDRA_DEMOD_MAX] = { {0x90700010, 0, 1}, {0x90700010, 1, 1}, {0x90700010, 2, 1}, {0x90700010, 3, 1}, {0x90700010, 4, 1}, {0x90700010, 5, 1}, {0x90700010, 6, 1}, {0x90700010, 7, 1} }; - struct MXL_REG_FIELD_T xpt_enable_output[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_enable_output[MXL_HYDRA_DEMOD_MAX] = { {0x9070000C, 0, 1}, {0x9070000C, 1, 1}, {0x9070000C, 2, 1}, {0x9070000C, 3, 1}, {0x9070000C, 4, 1}, {0x9070000C, 5, 1}, {0x9070000C, 6, 1}, {0x9070000C, 7, 1} }; - struct MXL_REG_FIELD_T xpt_err_replace_sync[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_err_replace_sync[MXL_HYDRA_DEMOD_MAX] = { {0x9070000C, 24, 1}, {0x9070000C, 25, 1}, {0x9070000C, 26, 1}, {0x9070000C, 27, 1}, {0x9070000C, 28, 1}, {0x9070000C, 29, 1}, {0x9070000C, 30, 1}, {0x9070000C, 31, 1} }; - struct MXL_REG_FIELD_T xpt_err_replace_valid[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_err_replace_valid[MXL_HYDRA_DEMOD_MAX] = { {0x90700014, 8, 1}, {0x90700014, 9, 1}, {0x90700014, 10, 1}, {0x90700014, 11, 1}, {0x90700014, 12, 1}, {0x90700014, 13, 1}, {0x90700014, 14, 1}, {0x90700014, 15, 1} }; - struct MXL_REG_FIELD_T xpt_continuous_clock[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_continuous_clock[MXL_HYDRA_DEMOD_MAX] = { {0x907001D4, 0, 1}, {0x907001D4, 1, 1}, {0x907001D4, 2, 1}, {0x907001D4, 3, 1}, {0x907001D4, 4, 1}, {0x907001D4, 5, 1}, {0x907001D4, 6, 1}, {0x907001D4, 7, 1} }; - struct MXL_REG_FIELD_T xpt_nco_clock_rate[MXL_HYDRA_DEMOD_MAX] = { + static const struct MXL_REG_FIELD_T xpt_nco_clock_rate[MXL_HYDRA_DEMOD_MAX] = { {0x90700044, 16, 80}, {0x90700044, 16, 81}, {0x90700044, 16, 82}, {0x90700044, 16, 83}, {0x90700044, 16, 84}, {0x90700044, 16, 85}, diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c index 48326434488c4..72540ef4e5f88 100644 --- a/drivers/media/dvb-frontends/stv0367.c +++ b/drivers/media/dvb-frontends/stv0367.c @@ -118,50 +118,32 @@ static const s32 stv0367cab_RF_LookUp2[RF_LOOKUP_TABLE2_SIZE][RF_LOOKUP_TABLE2_S } }; -static -int stv0367_writeregs(struct stv0367_state *state, u16 reg, u8 *data, int len) +static noinline_for_stack +int stv0367_writereg(struct stv0367_state *state, u16 reg, u8 data) { - u8 buf[MAX_XFER_SIZE]; + u8 buf[3] = { MSB(reg), LSB(reg), data }; struct i2c_msg msg = { .addr = state->config->demod_address, .flags = 0, .buf = buf, - .len = len + 2 + .len = 3, }; int ret; - if (2 + len > sizeof(buf)) { - printk(KERN_WARNING - "%s: i2c wr reg=%04x: len=%d is too big!\n", - KBUILD_MODNAME, reg, len); - return -EINVAL; - } - - - buf[0] = MSB(reg); - buf[1] = LSB(reg); - memcpy(buf + 2, data, len); - if (i2cdebug) printk(KERN_DEBUG "%s: [%02x] %02x: %02x\n", __func__, - state->config->demod_address, reg, buf[2]); + state->config->demod_address, reg, data); ret = i2c_transfer(state->i2c, &msg, 1); if (ret != 1) printk(KERN_ERR "%s: i2c write error! ([%02x] %02x: %02x)\n", - __func__, state->config->demod_address, reg, buf[2]); + __func__, state->config->demod_address, reg, data); return (ret != 1) ? -EREMOTEIO : 0; } -static int stv0367_writereg(struct stv0367_state *state, u16 reg, u8 data) -{ - u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ - - return stv0367_writeregs(state, reg, &tmp, 1); -} - -static u8 stv0367_readreg(struct stv0367_state *state, u16 reg) +static noinline_for_stack +u8 stv0367_readreg(struct stv0367_state *state, u16 reg) { u8 b0[] = { 0, 0 }; u8 b1[] = { 0 }; diff --git a/drivers/media/i2c/et8ek8/et8ek8_driver.c b/drivers/media/i2c/et8ek8/et8ek8_driver.c index f548b1bb75fb9..e932d25ca7b3a 100644 --- a/drivers/media/i2c/et8ek8/et8ek8_driver.c +++ b/drivers/media/i2c/et8ek8/et8ek8_driver.c @@ -1475,7 +1475,7 @@ static int et8ek8_probe(struct i2c_client *client) return ret; } -static void __exit et8ek8_remove(struct i2c_client *client) +static void et8ek8_remove(struct i2c_client *client) { struct v4l2_subdev *subdev = i2c_get_clientdata(client); struct et8ek8_sensor *sensor = to_et8ek8_sensor(subdev); @@ -1517,7 +1517,7 @@ static struct i2c_driver et8ek8_i2c_driver = { .of_match_table = et8ek8_of_table, }, .probe = et8ek8_probe, - .remove = __exit_p(et8ek8_remove), + .remove = et8ek8_remove, .id_table = et8ek8_id_table, }; diff --git a/drivers/media/i2c/imx290.c b/drivers/media/i2c/imx290.c index 9967f34774334..4150e6e4b9a63 100644 --- a/drivers/media/i2c/imx290.c +++ b/drivers/media/i2c/imx290.c @@ -150,10 +150,10 @@ #define IMX290_PIXEL_ARRAY_WIDTH 1945 #define IMX290_PIXEL_ARRAY_HEIGHT 1097 -#define IMX920_PIXEL_ARRAY_MARGIN_LEFT 12 -#define IMX920_PIXEL_ARRAY_MARGIN_RIGHT 13 -#define IMX920_PIXEL_ARRAY_MARGIN_TOP 8 -#define IMX920_PIXEL_ARRAY_MARGIN_BOTTOM 9 +#define IMX290_PIXEL_ARRAY_MARGIN_LEFT 12 +#define IMX290_PIXEL_ARRAY_MARGIN_RIGHT 13 +#define IMX290_PIXEL_ARRAY_MARGIN_TOP 8 +#define IMX290_PIXEL_ARRAY_MARGIN_BOTTOM 9 #define IMX290_PIXEL_ARRAY_RECORDING_WIDTH 1920 #define IMX290_PIXEL_ARRAY_RECORDING_HEIGHT 1080 @@ -1161,10 +1161,10 @@ static int imx290_get_selection(struct v4l2_subdev *sd, * The sensor moves the readout by 1 pixel based on flips to * keep the Bayer order the same. */ - sel->r.top = IMX920_PIXEL_ARRAY_MARGIN_TOP + sel->r.top = IMX290_PIXEL_ARRAY_MARGIN_TOP + (IMX290_PIXEL_ARRAY_RECORDING_HEIGHT - format->height) / 2 + imx290->vflip->val; - sel->r.left = IMX920_PIXEL_ARRAY_MARGIN_LEFT + sel->r.left = IMX290_PIXEL_ARRAY_MARGIN_LEFT + (IMX290_PIXEL_ARRAY_RECORDING_WIDTH - format->width) / 2 + imx290->hflip->val; sel->r.width = format->width; @@ -1183,8 +1183,8 @@ static int imx290_get_selection(struct v4l2_subdev *sd, return 0; case V4L2_SEL_TGT_CROP_DEFAULT: - sel->r.top = IMX920_PIXEL_ARRAY_MARGIN_TOP; - sel->r.left = IMX920_PIXEL_ARRAY_MARGIN_LEFT; + sel->r.top = IMX290_PIXEL_ARRAY_MARGIN_TOP; + sel->r.left = IMX290_PIXEL_ARRAY_MARGIN_LEFT; sel->r.width = IMX290_PIXEL_ARRAY_RECORDING_WIDTH; sel->r.height = IMX290_PIXEL_ARRAY_RECORDING_HEIGHT; diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c index 39d321e2b7f98..4577a8977c85a 100644 --- a/drivers/media/i2c/ov2680.c +++ b/drivers/media/i2c/ov2680.c @@ -1116,25 +1116,24 @@ static int ov2680_parse_dt(struct ov2680_dev *sensor) sensor->pixel_rate = sensor->link_freq[0] * 2; do_div(sensor->pixel_rate, 10); - /* Verify bus cfg */ - if (bus_cfg.bus.mipi_csi2.num_data_lanes != 1) { - ret = dev_err_probe(dev, -EINVAL, - "only a 1-lane CSI2 config is supported"); - goto out_free_bus_cfg; + if (!bus_cfg.nr_of_link_frequencies) { + dev_warn(dev, "Consider passing 'link-frequencies' in DT\n"); + goto skip_link_freq_validation; } for (i = 0; i < bus_cfg.nr_of_link_frequencies; i++) if (bus_cfg.link_frequencies[i] == sensor->link_freq[0]) break; - if (bus_cfg.nr_of_link_frequencies == 0 || - bus_cfg.nr_of_link_frequencies == i) { + if (bus_cfg.nr_of_link_frequencies == i) { ret = dev_err_probe(dev, -EINVAL, "supported link freq %lld not found\n", sensor->link_freq[0]); goto out_free_bus_cfg; } +skip_link_freq_validation: + ret = 0; out_free_bus_cfg: v4l2_fwnode_endpoint_free(&bus_cfg); return ret; diff --git a/drivers/media/i2c/ov2740.c b/drivers/media/i2c/ov2740.c index 552935ccb4a90..57906df7be4ec 100644 --- a/drivers/media/i2c/ov2740.c +++ b/drivers/media/i2c/ov2740.c @@ -768,14 +768,15 @@ static int ov2740_init_controls(struct ov2740 *ov2740) cur_mode = ov2740->cur_mode; size = ARRAY_SIZE(link_freq_menu_items); - ov2740->link_freq = v4l2_ctrl_new_int_menu(ctrl_hdlr, &ov2740_ctrl_ops, - V4L2_CID_LINK_FREQ, - size - 1, 0, - link_freq_menu_items); + ov2740->link_freq = + v4l2_ctrl_new_int_menu(ctrl_hdlr, &ov2740_ctrl_ops, + V4L2_CID_LINK_FREQ, size - 1, + ov2740->supported_modes->link_freq_index, + link_freq_menu_items); if (ov2740->link_freq) ov2740->link_freq->flags |= V4L2_CTRL_FLAG_READ_ONLY; - pixel_rate = to_pixel_rate(OV2740_LINK_FREQ_360MHZ_INDEX); + pixel_rate = to_pixel_rate(ov2740->supported_modes->link_freq_index); ov2740->pixel_rate = v4l2_ctrl_new_std(ctrl_hdlr, &ov2740_ctrl_ops, V4L2_CID_PIXEL_RATE, 0, pixel_rate, 1, pixel_rate); diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c index 2785935da497b..558152575d102 100644 --- a/drivers/media/i2c/tc358743.c +++ b/drivers/media/i2c/tc358743.c @@ -2091,9 +2091,6 @@ static int tc358743_probe(struct i2c_client *client) state->mbus_fmt_code = MEDIA_BUS_FMT_RGB888_1X24; sd->dev = &client->dev; - err = v4l2_async_register_subdev(sd); - if (err < 0) - goto err_hdl; mutex_init(&state->confctl_mutex); @@ -2151,6 +2148,10 @@ static int tc358743_probe(struct i2c_client *client) if (err) goto err_work_queues; + err = v4l2_async_register_subdev(sd); + if (err < 0) + goto err_work_queues; + v4l2_info(sd, "%s found @ 0x%x (%s)\n", client->name, client->addr << 1, client->adapter->name); diff --git a/drivers/media/mc/mc-devnode.c b/drivers/media/mc/mc-devnode.c index 680fbb3a93402..94abd042045da 100644 --- a/drivers/media/mc/mc-devnode.c +++ b/drivers/media/mc/mc-devnode.c @@ -246,15 +246,14 @@ int __must_check media_devnode_register(struct media_device *mdev, kobject_set_name(&devnode->cdev.kobj, "media%d", devnode->minor); /* Part 3: Add the media and char device */ + set_bit(MEDIA_FLAG_REGISTERED, &devnode->flags); ret = cdev_device_add(&devnode->cdev, &devnode->dev); if (ret < 0) { + clear_bit(MEDIA_FLAG_REGISTERED, &devnode->flags); pr_err("%s: cdev_device_add failed\n", __func__); goto cdev_add_error; } - /* Part 4: Activate this minor. The char device can now be used. */ - set_bit(MEDIA_FLAG_REGISTERED, &devnode->flags); - return 0; cdev_add_error: diff --git a/drivers/media/mc/mc-entity.c b/drivers/media/mc/mc-entity.c index 543a392f86357..96dd0f6ccd0d0 100644 --- a/drivers/media/mc/mc-entity.c +++ b/drivers/media/mc/mc-entity.c @@ -535,14 +535,15 @@ static int media_pipeline_walk_push(struct media_pipeline_walk *walk, /* * Move the top entry link cursor to the next link. If all links of the entry - * have been visited, pop the entry itself. + * have been visited, pop the entry itself. Return true if the entry has been + * popped. */ -static void media_pipeline_walk_pop(struct media_pipeline_walk *walk) +static bool media_pipeline_walk_pop(struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry; if (WARN_ON(walk->stack.top < 0)) - return; + return false; entry = media_pipeline_walk_top(walk); @@ -552,7 +553,7 @@ static void media_pipeline_walk_pop(struct media_pipeline_walk *walk) walk->stack.top); walk->stack.top--; - return; + return true; } entry->links = entry->links->next; @@ -560,6 +561,8 @@ static void media_pipeline_walk_pop(struct media_pipeline_walk *walk) dev_dbg(walk->mdev->dev, "media pipeline: moved entry %u to next link\n", walk->stack.top); + + return false; } /* Free all memory allocated while walking the pipeline. */ @@ -605,30 +608,30 @@ static int media_pipeline_explore_next_link(struct media_pipeline *pipe, struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry = media_pipeline_walk_top(walk); - struct media_pad *pad; + struct media_pad *origin; struct media_link *link; struct media_pad *local; struct media_pad *remote; + bool last_link; int ret; - pad = entry->pad; + origin = entry->pad; link = list_entry(entry->links, typeof(*link), list); - media_pipeline_walk_pop(walk); + last_link = media_pipeline_walk_pop(walk); + + if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) { + dev_dbg(walk->mdev->dev, + "media pipeline: skipping link (not data-link)\n"); + return 0; + } dev_dbg(walk->mdev->dev, "media pipeline: exploring link '%s':%u -> '%s':%u\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); - /* Skip links that are not enabled. */ - if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { - dev_dbg(walk->mdev->dev, - "media pipeline: skipping link (disabled)\n"); - return 0; - } - /* Get the local pad and remote pad. */ - if (link->source->entity == pad->entity) { + if (link->source->entity == origin->entity) { local = link->source; remote = link->sink; } else { @@ -640,25 +643,64 @@ static int media_pipeline_explore_next_link(struct media_pipeline *pipe, * Skip links that originate from a different pad than the incoming pad * that is not connected internally in the entity to the incoming pad. */ - if (pad != local && - !media_entity_has_pad_interdep(pad->entity, pad->index, local->index)) { + if (origin != local && + !media_entity_has_pad_interdep(origin->entity, origin->index, + local->index)) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (no route)\n"); - return 0; + goto done; } /* - * Add the local and remote pads of the link to the pipeline and push - * them to the stack, if they're not already present. + * Add the local pad of the link to the pipeline and push it to the + * stack, if not already present. */ ret = media_pipeline_add_pad(pipe, walk, local); if (ret) return ret; + /* Similarly, add the remote pad, but only if the link is enabled. */ + if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { + dev_dbg(walk->mdev->dev, + "media pipeline: skipping link (disabled)\n"); + goto done; + } + ret = media_pipeline_add_pad(pipe, walk, remote); if (ret) return ret; +done: + /* + * If we're done iterating over links, iterate over pads of the entity. + * This is necessary to discover pads that are not connected with any + * link. Those are dead ends from a pipeline exploration point of view, + * but are still part of the pipeline and need to be added to enable + * proper validation. + */ + if (!last_link) + return 0; + + dev_dbg(walk->mdev->dev, + "media pipeline: adding unconnected pads of '%s'\n", + local->entity->name); + + media_entity_for_each_pad(origin->entity, local) { + /* + * Skip the origin pad (already handled), pad that have links + * (already discovered through iterating over links) and pads + * not internally connected. + */ + if (origin == local || !local->num_links || + !media_entity_has_pad_interdep(origin->entity, origin->index, + local->index)) + continue; + + ret = media_pipeline_add_pad(pipe, walk, local); + if (ret) + return ret; + } + return 0; } @@ -770,7 +812,6 @@ __must_check int __media_pipeline_start(struct media_pad *pad, struct media_pad *pad = ppad->pad; struct media_entity *entity = pad->entity; bool has_enabled_link = false; - bool has_link = false; struct media_link *link; dev_dbg(mdev->dev, "Validating pad '%s':%u\n", pad->entity->name, @@ -800,7 +841,6 @@ __must_check int __media_pipeline_start(struct media_pad *pad, /* Record if the pad has links and enabled links. */ if (link->flags & MEDIA_LNK_FL_ENABLED) has_enabled_link = true; - has_link = true; /* * Validate the link if it's enabled and has the @@ -838,7 +878,7 @@ __must_check int __media_pipeline_start(struct media_pad *pad, * 3. If the pad has the MEDIA_PAD_FL_MUST_CONNECT flag set, * ensure that it has either no link or an enabled link. */ - if ((pad->flags & MEDIA_PAD_FL_MUST_CONNECT) && has_link && + if ((pad->flags & MEDIA_PAD_FL_MUST_CONNECT) && !has_enabled_link) { dev_dbg(mdev->dev, "Pad '%s':%u must be connected by an enabled link\n", @@ -1038,6 +1078,9 @@ static void __media_entity_remove_link(struct media_entity *entity, /* Remove the reverse links for a data link. */ if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == MEDIA_LNK_FL_DATA_LINK) { + link->source->num_links--; + link->sink->num_links--; + if (link->source->entity == entity) remote = link->sink->entity; else @@ -1092,6 +1135,11 @@ media_create_pad_link(struct media_entity *source, u16 source_pad, struct media_link *link; struct media_link *backlink; + if (flags & MEDIA_LNK_FL_LINK_TYPE) + return -EINVAL; + + flags |= MEDIA_LNK_FL_DATA_LINK; + if (WARN_ON(!source || !sink) || WARN_ON(source_pad >= source->num_pads) || WARN_ON(sink_pad >= sink->num_pads)) @@ -1107,7 +1155,7 @@ media_create_pad_link(struct media_entity *source, u16 source_pad, link->source = &source->pads[source_pad]; link->sink = &sink->pads[sink_pad]; - link->flags = flags & ~MEDIA_LNK_FL_INTERFACE_LINK; + link->flags = flags; /* Initialize graph object embedded at the new link */ media_gobj_create(source->graph_obj.mdev, MEDIA_GRAPH_LINK, @@ -1138,6 +1186,9 @@ media_create_pad_link(struct media_entity *source, u16 source_pad, sink->num_links++; source->num_links++; + link->source->num_links++; + link->sink->num_links++; + return 0; } EXPORT_SYMBOL_GPL(media_create_pad_link); diff --git a/drivers/media/pci/intel/ipu-bridge.c b/drivers/media/pci/intel/ipu-bridge.c index f980e3125a7b9..176d623d6e6fb 100644 --- a/drivers/media/pci/intel/ipu-bridge.c +++ b/drivers/media/pci/intel/ipu-bridge.c @@ -14,6 +14,8 @@ #include #include +#define ADEV_DEV(adev) ACPI_PTR(&((adev)->dev)) + /* * 92335fcf-3203-4472-af93-7b4453ac29da * @@ -58,8 +60,27 @@ static const struct ipu_sensor_config ipu_supported_sensors[] = { IPU_SENSOR_CONFIG("INT3537", 1, 437000000), /* Omnivision ov13b10 */ IPU_SENSOR_CONFIG("OVTIDB10", 1, 560000000), + IPU_SENSOR_CONFIG("OVTI13B1", 1, 560000000), /* GalaxyCore GC0310 */ IPU_SENSOR_CONFIG("INT0310", 0), + /* Omnivision ov01a10 */ + IPU_SENSOR_CONFIG("OVTI01A0", 1, 400000000), + /* Omnivision ov08x40 */ + IPU_SENSOR_CONFIG("OVTI08F4", 1, 400000000), + /* Himax hm11b1 */ + IPU_SENSOR_CONFIG("HIMX11B1", 1, 384000000), + /* Himax hm2170 */ + IPU_SENSOR_CONFIG("HIMX2170", 1, 384000000), + /* Himax hm2172 */ + IPU_SENSOR_CONFIG("HIMX2172", 1, 384000000), + /* Omnivision ov01a1s */ + IPU_SENSOR_CONFIG("OVTI01AS", 1, 400000000), + /* Omnivision ov02c10 */ + IPU_SENSOR_CONFIG("OVTI02C1", 1, 400000000), + /* Omnivision ov02e10 */ + IPU_SENSOR_CONFIG("OVTI02E1", 1, 360000000), + /* Omnivision ov08a10 */ + IPU_SENSOR_CONFIG("OVTI08A1", 1, 500000000), }; static const struct ipu_property_names prop_names = { @@ -84,6 +105,7 @@ static const char * const ipu_vcm_types[] = { "lc898212axb", }; +#if IS_ENABLED(CONFIG_ACPI) /* * Used to figure out IVSC acpi device by ipu_bridge_get_ivsc_acpi_dev() * instead of device and driver match to probe IVSC device. @@ -97,13 +119,13 @@ static const struct acpi_device_id ivsc_acpi_ids[] = { static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev) { - acpi_handle handle = acpi_device_handle(adev); - struct acpi_device *consumer, *ivsc_adev; unsigned int i; for (i = 0; i < ARRAY_SIZE(ivsc_acpi_ids); i++) { const struct acpi_device_id *acpi_id = &ivsc_acpi_ids[i]; + struct acpi_device *consumer, *ivsc_adev; + acpi_handle handle = acpi_device_handle(adev); for_each_acpi_dev_match(ivsc_adev, acpi_id->id, NULL, -1) /* camera sensor depends on IVSC in DSDT if exist */ for_each_acpi_consumer_dev(ivsc_adev, consumer) @@ -115,6 +137,12 @@ static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev return NULL; } +#else +static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev) +{ + return NULL; +} +#endif static int ipu_bridge_match_ivsc_dev(struct device *dev, const void *adev) { @@ -160,7 +188,7 @@ static int ipu_bridge_check_ivsc_dev(struct ipu_sensor *sensor, csi_dev = ipu_bridge_get_ivsc_csi_dev(adev); if (!csi_dev) { acpi_dev_put(adev); - dev_err(&adev->dev, "Failed to find MEI CSI dev\n"); + dev_err(ADEV_DEV(adev), "Failed to find MEI CSI dev\n"); return -ENODEV; } @@ -179,24 +207,25 @@ static int ipu_bridge_read_acpi_buffer(struct acpi_device *adev, char *id, acpi_status status; int ret = 0; - status = acpi_evaluate_object(adev->handle, id, NULL, &buffer); + status = acpi_evaluate_object(ACPI_PTR(adev->handle), + id, NULL, &buffer); if (ACPI_FAILURE(status)) return -ENODEV; obj = buffer.pointer; if (!obj) { - dev_err(&adev->dev, "Couldn't locate ACPI buffer\n"); + dev_err(ADEV_DEV(adev), "Couldn't locate ACPI buffer\n"); return -ENODEV; } if (obj->type != ACPI_TYPE_BUFFER) { - dev_err(&adev->dev, "Not an ACPI buffer\n"); + dev_err(ADEV_DEV(adev), "Not an ACPI buffer\n"); ret = -ENODEV; goto out_free_buff; } if (obj->buffer.length > size) { - dev_err(&adev->dev, "Given buffer is too small\n"); + dev_err(ADEV_DEV(adev), "Given buffer is too small\n"); ret = -EINVAL; goto out_free_buff; } @@ -217,7 +246,7 @@ static u32 ipu_bridge_parse_rotation(struct acpi_device *adev, case IPU_SENSOR_ROTATION_INVERTED: return 180; default: - dev_warn(&adev->dev, + dev_warn(ADEV_DEV(adev), "Unknown rotation %d. Assume 0 degree rotation\n", ssdb->degree); return 0; @@ -227,12 +256,14 @@ static u32 ipu_bridge_parse_rotation(struct acpi_device *adev, static enum v4l2_fwnode_orientation ipu_bridge_parse_orientation(struct acpi_device *adev) { enum v4l2_fwnode_orientation orientation; - struct acpi_pld_info *pld; - acpi_status status; + struct acpi_pld_info *pld = NULL; + acpi_status status = AE_ERROR; +#if IS_ENABLED(CONFIG_ACPI) status = acpi_get_physical_device_location(adev->handle, &pld); +#endif if (ACPI_FAILURE(status)) { - dev_warn(&adev->dev, "_PLD call failed, using default orientation\n"); + dev_warn(ADEV_DEV(adev), "_PLD call failed, using default orientation\n"); return V4L2_FWNODE_ORIENTATION_EXTERNAL; } @@ -250,7 +281,8 @@ static enum v4l2_fwnode_orientation ipu_bridge_parse_orientation(struct acpi_dev orientation = V4L2_FWNODE_ORIENTATION_EXTERNAL; break; default: - dev_warn(&adev->dev, "Unknown _PLD panel val %d\n", pld->panel); + dev_warn(ADEV_DEV(adev), "Unknown _PLD panel val %d\n", + pld->panel); orientation = V4L2_FWNODE_ORIENTATION_EXTERNAL; break; } @@ -269,12 +301,12 @@ int ipu_bridge_parse_ssdb(struct acpi_device *adev, struct ipu_sensor *sensor) return ret; if (ssdb.vcmtype > ARRAY_SIZE(ipu_vcm_types)) { - dev_warn(&adev->dev, "Unknown VCM type %d\n", ssdb.vcmtype); + dev_warn(ADEV_DEV(adev), "Unknown VCM type %d\n", ssdb.vcmtype); ssdb.vcmtype = 0; } if (ssdb.lanes > IPU_MAX_LANES) { - dev_err(&adev->dev, "Number of lanes in SSDB is invalid\n"); + dev_err(ADEV_DEV(adev), "Number of lanes in SSDB is invalid\n"); return -EINVAL; } @@ -462,8 +494,14 @@ static void ipu_bridge_create_connection_swnodes(struct ipu_bridge *bridge, sensor->ipu_properties); if (sensor->csi_dev) { + const char *device_hid = ""; + +#if IS_ENABLED(CONFIG_ACPI) + device_hid = acpi_device_hid(sensor->ivsc_adev); +#endif + snprintf(sensor->ivsc_name, sizeof(sensor->ivsc_name), "%s-%u", - acpi_device_hid(sensor->ivsc_adev), sensor->link); + device_hid, sensor->link); nodes[SWNODE_IVSC_HID] = NODE_SENSOR(sensor->ivsc_name, sensor->ivsc_properties); @@ -628,11 +666,15 @@ static int ipu_bridge_connect_sensor(const struct ipu_sensor_config *cfg, { struct fwnode_handle *fwnode, *primary; struct ipu_sensor *sensor; - struct acpi_device *adev; + struct acpi_device *adev = NULL; int ret; +#if IS_ENABLED(CONFIG_ACPI) for_each_acpi_dev_match(adev, cfg->hid, NULL, -1) { - if (!adev->status.enabled) +#else + while (true) { +#endif + if (!ACPI_PTR(adev->status.enabled)) continue; if (bridge->n_sensors >= IPU_MAX_PORTS) { @@ -668,7 +710,7 @@ static int ipu_bridge_connect_sensor(const struct ipu_sensor_config *cfg, goto err_free_swnodes; } - sensor->adev = acpi_dev_get(adev); + sensor->adev = ACPI_PTR(acpi_dev_get(adev)); primary = acpi_fwnode_handle(adev); primary->secondary = fwnode; @@ -724,11 +766,16 @@ static int ipu_bridge_ivsc_is_ready(void) unsigned int i; for (i = 0; i < ARRAY_SIZE(ipu_supported_sensors); i++) { +#if IS_ENABLED(CONFIG_ACPI) const struct ipu_sensor_config *cfg = &ipu_supported_sensors[i]; for_each_acpi_dev_match(sensor_adev, cfg->hid, NULL, -1) { - if (!sensor_adev->status.enabled) +#else + while (true) { + sensor_adev = NULL; +#endif + if (!ACPI_PTR(sensor_adev->status.enabled)) continue; adev = ipu_bridge_get_ivsc_acpi_dev(sensor_adev); diff --git a/drivers/media/pci/intel/ipu3/ipu3-cio2.c b/drivers/media/pci/intel/ipu3/ipu3-cio2.c index ed08bf4178f08..d5478779b3103 100644 --- a/drivers/media/pci/intel/ipu3/ipu3-cio2.c +++ b/drivers/media/pci/intel/ipu3/ipu3-cio2.c @@ -1789,11 +1789,6 @@ static int cio2_pci_probe(struct pci_dev *pci_dev, v4l2_async_nf_init(&cio2->notifier, &cio2->v4l2_dev); - /* Register notifier for subdevices we care */ - r = cio2_parse_firmware(cio2); - if (r) - goto fail_clean_notifier; - r = devm_request_irq(dev, pci_dev->irq, cio2_irq, IRQF_SHARED, CIO2_NAME, cio2); if (r) { @@ -1801,6 +1796,11 @@ static int cio2_pci_probe(struct pci_dev *pci_dev, goto fail_clean_notifier; } + /* Register notifier for subdevices we care */ + r = cio2_parse_firmware(cio2); + if (r) + goto fail_clean_notifier; + pm_runtime_put_noidle(dev); pm_runtime_allow(dev); diff --git a/drivers/media/pci/intel/ivsc/mei_csi.c b/drivers/media/pci/intel/ivsc/mei_csi.c index 15b905f66ab72..f936b0b6a9624 100644 --- a/drivers/media/pci/intel/ivsc/mei_csi.c +++ b/drivers/media/pci/intel/ivsc/mei_csi.c @@ -71,8 +71,8 @@ enum ivsc_privacy_status { }; enum csi_pads { - CSI_PAD_SOURCE, CSI_PAD_SINK, + CSI_PAD_SOURCE, CSI_NUM_PADS }; @@ -123,6 +123,8 @@ struct mei_csi { struct v4l2_ctrl_handler ctrl_handler; struct v4l2_ctrl *freq_ctrl; struct v4l2_ctrl *privacy_ctrl; + /* lock for v4l2 controls */ + struct mutex ctrl_lock; unsigned int remote_pad; /* start streaming or not */ int streaming; @@ -134,9 +136,6 @@ struct mei_csi { u32 nr_of_lanes; /* frequency of the CSI-2 link */ u64 link_freq; - - /* privacy status */ - enum ivsc_privacy_status status; }; static const struct v4l2_mbus_framefmt mei_csi_format_mbus_default = { @@ -188,7 +187,11 @@ static int mei_csi_send(struct mei_csi *csi, u8 *buf, size_t len) /* command response status */ ret = csi->cmd_response.status; - if (ret) { + if (ret == -1) { + /* notify privacy on instead of reporting error */ + ret = 0; + v4l2_ctrl_s_ctrl(csi->privacy_ctrl, 1); + } else if (ret) { ret = -EINVAL; goto out; } @@ -263,10 +266,9 @@ static void mei_csi_rx(struct mei_cl_device *cldev) switch (notif.cmd_id) { case CSI_PRIVACY_NOTIF: - if (notif.cont.cont < CSI_PRIVACY_MAX) { - csi->status = notif.cont.cont; - v4l2_ctrl_s_ctrl(csi->privacy_ctrl, csi->status); - } + if (notif.cont.cont < CSI_PRIVACY_MAX) + v4l2_ctrl_s_ctrl(csi->privacy_ctrl, + notif.cont.cont == CSI_PRIVACY_ON); break; case CSI_SET_OWNER: case CSI_SET_CONF: @@ -587,7 +589,7 @@ static int mei_csi_notify_bound(struct v4l2_async_notifier *notifier, csi->remote_pad = pad; return media_create_pad_link(&subdev->entity, pad, - &csi->subdev.entity, 1, + &csi->subdev.entity, CSI_PAD_SINK, MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE); } @@ -611,11 +613,13 @@ static int mei_csi_init_controls(struct mei_csi *csi) u32 max; int ret; + mutex_init(&csi->ctrl_lock); + ret = v4l2_ctrl_handler_init(&csi->ctrl_handler, 2); if (ret) return ret; - csi->ctrl_handler.lock = &csi->lock; + csi->ctrl_handler.lock = &csi->ctrl_lock; max = ARRAY_SIZE(link_freq_menu_items) - 1; csi->freq_ctrl = v4l2_ctrl_new_int_menu(&csi->ctrl_handler, @@ -794,6 +798,7 @@ static int mei_csi_probe(struct mei_cl_device *cldev, err_ctrl_handler: v4l2_ctrl_handler_free(&csi->ctrl_handler); + mutex_destroy(&csi->ctrl_lock); v4l2_async_nf_unregister(&csi->notifier); v4l2_async_nf_cleanup(&csi->notifier); @@ -813,6 +818,7 @@ static void mei_csi_remove(struct mei_cl_device *cldev) v4l2_async_nf_unregister(&csi->notifier); v4l2_async_nf_cleanup(&csi->notifier); v4l2_ctrl_handler_free(&csi->ctrl_handler); + mutex_destroy(&csi->ctrl_lock); v4l2_async_unregister_subdev(&csi->subdev); v4l2_subdev_cleanup(&csi->subdev); media_entity_cleanup(&csi->subdev.entity); diff --git a/drivers/media/pci/mgb4/mgb4_core.c b/drivers/media/pci/mgb4/mgb4_core.c index 5bfb8a06202e9..df6032d01faf2 100644 --- a/drivers/media/pci/mgb4/mgb4_core.c +++ b/drivers/media/pci/mgb4/mgb4_core.c @@ -642,9 +642,6 @@ static void mgb4_remove(struct pci_dev *pdev) struct mgb4_dev *mgbdev = pci_get_drvdata(pdev); int i; -#ifdef CONFIG_DEBUG_FS - debugfs_remove_recursive(mgbdev->debugfs); -#endif #if IS_REACHABLE(CONFIG_HWMON) hwmon_device_unregister(mgbdev->hwmon_dev); #endif @@ -659,6 +656,10 @@ static void mgb4_remove(struct pci_dev *pdev) if (mgbdev->vin[i]) mgb4_vin_free(mgbdev->vin[i]); +#ifdef CONFIG_DEBUG_FS + debugfs_remove_recursive(mgbdev->debugfs); +#endif + device_remove_groups(&mgbdev->pdev->dev, mgb4_pci_groups); free_spi(mgbdev); free_i2c(mgbdev); diff --git a/drivers/media/pci/ngene/ngene-core.c b/drivers/media/pci/ngene/ngene-core.c index 7481f553f9595..24ec576dc3bff 100644 --- a/drivers/media/pci/ngene/ngene-core.c +++ b/drivers/media/pci/ngene/ngene-core.c @@ -1488,7 +1488,9 @@ static int init_channel(struct ngene_channel *chan) } if (dev->ci.en && (io & NGENE_IO_TSOUT)) { - dvb_ca_en50221_init(adapter, dev->ci.en, 0, 1); + ret = dvb_ca_en50221_init(adapter, dev->ci.en, 0, 1); + if (ret != 0) + goto err; set_transfer(chan, 1); chan->dev->channel[2].DataFormatFlags = DF_SWAP32; set_transfer(&chan->dev->channel[2], 1); diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c index e4cf9d63e926d..364ce9e570182 100644 --- a/drivers/media/pci/sta2x11/sta2x11_vip.c +++ b/drivers/media/pci/sta2x11/sta2x11_vip.c @@ -757,7 +757,7 @@ static const struct video_device video_dev_template = { /** * vip_irq - interrupt routine * @irq: Number of interrupt ( not used, correct number is assumed ) - * @vip: local data structure containing all information + * @data: local data structure containing all information * * check for both frame interrupts set ( top and bottom ). * check FIFO overflow, but limit number of log messages after open. @@ -767,8 +767,9 @@ static const struct video_device video_dev_template = { * * IRQ_HANDLED, interrupt done. */ -static irqreturn_t vip_irq(int irq, struct sta2x11_vip *vip) +static irqreturn_t vip_irq(int irq, void *data) { + struct sta2x11_vip *vip = data; unsigned int status; status = reg_read(vip, DVP_ITS); @@ -1053,9 +1054,7 @@ static int sta2x11_vip_init_one(struct pci_dev *pdev, spin_lock_init(&vip->slock); - ret = request_irq(pdev->irq, - (irq_handler_t) vip_irq, - IRQF_SHARED, KBUILD_MODNAME, vip); + ret = request_irq(pdev->irq, vip_irq, IRQF_SHARED, KBUILD_MODNAME, vip); if (ret) { dev_err(&pdev->dev, "request_irq failed\n"); ret = -ENODEV; diff --git a/drivers/media/pci/ttpci/budget-av.c b/drivers/media/pci/ttpci/budget-av.c index 230b104a7cdf0..a47c5850ef875 100644 --- a/drivers/media/pci/ttpci/budget-av.c +++ b/drivers/media/pci/ttpci/budget-av.c @@ -1463,7 +1463,8 @@ static int budget_av_attach(struct saa7146_dev *dev, struct saa7146_pci_extensio budget_av->has_saa7113 = 1; err = saa7146_vv_init(dev, &vv_data); if (err != 0) { - /* fixme: proper cleanup here */ + ttpci_budget_deinit(&budget_av->budget); + kfree(budget_av); ERR("cannot init vv subsystem\n"); return err; } @@ -1472,9 +1473,10 @@ static int budget_av_attach(struct saa7146_dev *dev, struct saa7146_pci_extensio vv_data.vid_ops.vidioc_s_input = vidioc_s_input; if ((err = saa7146_register_device(&budget_av->vd, dev, "knc1", VFL_TYPE_VIDEO))) { - /* fixme: proper cleanup here */ - ERR("cannot register capture v4l2 device\n"); saa7146_vv_release(dev); + ttpci_budget_deinit(&budget_av->budget); + kfree(budget_av); + ERR("cannot register capture v4l2 device\n"); return err; } diff --git a/drivers/media/platform/cadence/cdns-csi2rx.c b/drivers/media/platform/cadence/cdns-csi2rx.c index fead5426830e8..5be75bd4add39 100644 --- a/drivers/media/platform/cadence/cdns-csi2rx.c +++ b/drivers/media/platform/cadence/cdns-csi2rx.c @@ -235,10 +235,6 @@ static int csi2rx_start(struct csi2rx_priv *csi2rx) writel(reg, csi2rx->base + CSI2RX_STATIC_CFG_REG); - ret = v4l2_subdev_call(csi2rx->source_subdev, video, s_stream, true); - if (ret) - goto err_disable_pclk; - /* Enable DPHY clk and data lanes. */ if (csi2rx->dphy) { reg = CSI2RX_DPHY_CL_EN | CSI2RX_DPHY_CL_RST; @@ -248,6 +244,13 @@ static int csi2rx_start(struct csi2rx_priv *csi2rx) } writel(reg, csi2rx->base + CSI2RX_DPHY_LANE_CTRL_REG); + + ret = csi2rx_configure_ext_dphy(csi2rx); + if (ret) { + dev_err(csi2rx->dev, + "Failed to configure external DPHY: %d\n", ret); + goto err_disable_pclk; + } } /* @@ -287,14 +290,9 @@ static int csi2rx_start(struct csi2rx_priv *csi2rx) reset_control_deassert(csi2rx->sys_rst); - if (csi2rx->dphy) { - ret = csi2rx_configure_ext_dphy(csi2rx); - if (ret) { - dev_err(csi2rx->dev, - "Failed to configure external DPHY: %d\n", ret); - goto err_disable_sysclk; - } - } + ret = v4l2_subdev_call(csi2rx->source_subdev, video, s_stream, true); + if (ret) + goto err_disable_sysclk; clk_disable_unprepare(csi2rx->p_clk); @@ -308,6 +306,10 @@ static int csi2rx_start(struct csi2rx_priv *csi2rx) clk_disable_unprepare(csi2rx->pixel_clk[i - 1]); } + if (csi2rx->dphy) { + writel(0, csi2rx->base + CSI2RX_DPHY_LANE_CTRL_REG); + phy_power_off(csi2rx->dphy); + } err_disable_pclk: clk_disable_unprepare(csi2rx->p_clk); @@ -468,7 +470,7 @@ static int csi2rx_async_bound(struct v4l2_async_notifier *notifier, struct csi2rx_priv *csi2rx = v4l2_subdev_to_csi2rx(subdev); csi2rx->source_pad = media_entity_get_fwnode_pad(&s_subdev->entity, - s_subdev->fwnode, + asd->match.fwnode, MEDIA_PAD_FL_SOURCE); if (csi2rx->source_pad < 0) { dev_err(csi2rx->dev, "Couldn't find output pad for subdev %s\n", diff --git a/drivers/media/platform/mediatek/mdp/mtk_mdp_vpu.c b/drivers/media/platform/mediatek/mdp/mtk_mdp_vpu.c index b065ccd069140..378a1cba0144f 100644 --- a/drivers/media/platform/mediatek/mdp/mtk_mdp_vpu.c +++ b/drivers/media/platform/mediatek/mdp/mtk_mdp_vpu.c @@ -26,7 +26,7 @@ static void mtk_mdp_vpu_handle_init_ack(const struct mdp_ipi_comm_ack *msg) vpu->inst_addr = msg->vpu_inst_addr; } -static void mtk_mdp_vpu_ipi_handler(const void *data, unsigned int len, +static void mtk_mdp_vpu_ipi_handler(void *data, unsigned int len, void *priv) { const struct mdp_ipi_comm_ack *msg = data; diff --git a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_scp.c b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_scp.c index 6bbe55de6ce9a..ff23b225db705 100644 --- a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_scp.c +++ b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_scp.c @@ -79,6 +79,8 @@ struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(void *priv, enum mtk_vcodec_fw_use } fw = devm_kzalloc(&plat_dev->dev, sizeof(*fw), GFP_KERNEL); + if (!fw) + return ERR_PTR(-ENOMEM); fw->type = SCP; fw->ops = &mtk_vcodec_rproc_msg; fw->scp = scp; diff --git a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c index 9f6e4b59455da..d7027d600208f 100644 --- a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c +++ b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c @@ -29,15 +29,7 @@ static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id, mtk_vcodec_ipi_handler handler, const char *name, void *priv) { - /* - * The handler we receive takes a void * as its first argument. We - * cannot change this because it needs to be passed down to the rproc - * subsystem when SCP is used. VPU takes a const argument, which is - * more constrained, so the conversion below is safe. - */ - ipi_handler_t handler_const = (ipi_handler_t)handler; - - return vpu_ipi_register(fw->pdev, id, handler_const, name, priv); + return vpu_ipi_register(fw->pdev, id, handler, name, priv); } static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, @@ -58,12 +50,12 @@ static void mtk_vcodec_vpu_reset_dec_handler(void *priv) dev_err(&dev->plat_dev->dev, "Watchdog timeout!!"); - mutex_lock(&dev->dev_mutex); + mutex_lock(&dev->dev_ctx_lock); list_for_each_entry(ctx, &dev->ctx_list, list) { ctx->state = MTK_STATE_ABORT; mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id); } - mutex_unlock(&dev->dev_mutex); + mutex_unlock(&dev->dev_ctx_lock); } static void mtk_vcodec_vpu_reset_enc_handler(void *priv) @@ -73,12 +65,12 @@ static void mtk_vcodec_vpu_reset_enc_handler(void *priv) dev_err(&dev->plat_dev->dev, "Watchdog timeout!!"); - mutex_lock(&dev->dev_mutex); + mutex_lock(&dev->dev_ctx_lock); list_for_each_entry(ctx, &dev->ctx_list, list) { ctx->state = MTK_STATE_ABORT; mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id); } - mutex_unlock(&dev->dev_mutex); + mutex_unlock(&dev->dev_ctx_lock); } static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = { diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c index f47c98faf068b..2073781ccadb1 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c @@ -268,7 +268,9 @@ static int fops_vcodec_open(struct file *file) ctx->dev->vdec_pdata->init_vdec_params(ctx); + mutex_lock(&dev->dev_ctx_lock); list_add(&ctx->list, &dev->ctx_list); + mutex_unlock(&dev->dev_ctx_lock); mtk_vcodec_dbgfs_create(ctx); mutex_unlock(&dev->dev_mutex); @@ -311,7 +313,9 @@ static int fops_vcodec_release(struct file *file) v4l2_ctrl_handler_free(&ctx->ctrl_hdl); mtk_vcodec_dbgfs_remove(dev, ctx->id); + mutex_lock(&dev->dev_ctx_lock); list_del_init(&ctx->list); + mutex_unlock(&dev->dev_ctx_lock); kfree(ctx); mutex_unlock(&dev->dev_mutex); return 0; @@ -404,6 +408,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) for (i = 0; i < MTK_VDEC_HW_MAX; i++) mutex_init(&dev->dec_mutex[i]); mutex_init(&dev->dev_mutex); + mutex_init(&dev->dev_ctx_lock); spin_lock_init(&dev->irqlock); snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s", diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h index 849b89dd205c2..85b2c0d3d8bcd 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h +++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h @@ -241,6 +241,7 @@ struct mtk_vcodec_dec_ctx { * * @dec_mutex: decoder hardware lock * @dev_mutex: video_device lock + * @dev_ctx_lock: the lock of context list * @decode_workqueue: decode work queue * * @irqlock: protect data access by irq handler and work thread @@ -282,6 +283,7 @@ struct mtk_vcodec_dec_dev { /* decoder hardware mutex lock */ struct mutex dec_mutex[MTK_VDEC_HW_MAX]; struct mutex dev_mutex; + struct mutex dev_ctx_lock; struct workqueue_struct *decode_workqueue; spinlock_t irqlock; diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c index 06ed47df693bf..21836dd6ef85a 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c @@ -869,7 +869,6 @@ static int vdec_hevc_slice_init(struct mtk_vcodec_dec_ctx *ctx) inst->vpu.codec_type = ctx->current_codec; inst->vpu.capture_type = ctx->capture_fourcc; - ctx->drv_handle = inst; err = vpu_dec_init(&inst->vpu); if (err) { mtk_vdec_err(ctx, "vdec_hevc init err=%d", err); @@ -898,6 +897,7 @@ static int vdec_hevc_slice_init(struct mtk_vcodec_dec_ctx *ctx) mtk_vdec_debug(ctx, "lat hevc instance >> %p, codec_type = 0x%x", inst, inst->vpu.codec_type); + ctx->drv_handle = inst; return 0; error_free_inst: kfree(inst); diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c index 82e57ae983d55..da6be556727bb 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c @@ -77,12 +77,14 @@ static bool vpu_dec_check_ap_inst(struct mtk_vcodec_dec_dev *dec_dev, struct vde struct mtk_vcodec_dec_ctx *ctx; int ret = false; + mutex_lock(&dec_dev->dev_ctx_lock); list_for_each_entry(ctx, &dec_dev->ctx_list, list) { if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) { ret = true; break; } } + mutex_unlock(&dec_dev->dev_ctx_lock); return ret; } diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c index 6319f24bc714b..3cb8a16222220 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c @@ -177,7 +177,9 @@ static int fops_vcodec_open(struct file *file) mtk_v4l2_venc_dbg(2, ctx, "Create instance [%d]@%p m2m_ctx=%p ", ctx->id, ctx, ctx->m2m_ctx); + mutex_lock(&dev->dev_ctx_lock); list_add(&ctx->list, &dev->ctx_list); + mutex_unlock(&dev->dev_ctx_lock); mutex_unlock(&dev->dev_mutex); mtk_v4l2_venc_dbg(0, ctx, "%s encoder [%d]", dev_name(&dev->plat_dev->dev), @@ -212,7 +214,9 @@ static int fops_vcodec_release(struct file *file) v4l2_fh_exit(&ctx->fh); v4l2_ctrl_handler_free(&ctx->ctrl_hdl); + mutex_lock(&dev->dev_ctx_lock); list_del_init(&ctx->list); + mutex_unlock(&dev->dev_ctx_lock); kfree(ctx); mutex_unlock(&dev->dev_mutex); return 0; @@ -294,6 +298,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) mutex_init(&dev->enc_mutex); mutex_init(&dev->dev_mutex); + mutex_init(&dev->dev_ctx_lock); spin_lock_init(&dev->irqlock); snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s", diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h index a042f607ed8d1..0bd85d0fb379a 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h +++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h @@ -178,6 +178,7 @@ struct mtk_vcodec_enc_ctx { * * @enc_mutex: encoder hardware lock. * @dev_mutex: video_device lock + * @dev_ctx_lock: the lock of context list * @encode_workqueue: encode work queue * * @enc_irq: h264 encoder irq resource @@ -205,6 +206,7 @@ struct mtk_vcodec_enc_dev { /* encoder hardware mutex lock */ struct mutex enc_mutex; struct mutex dev_mutex; + struct mutex dev_ctx_lock; struct workqueue_struct *encode_workqueue; int enc_irq; diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_pm.c b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_pm.c index a22b7dfc656e1..1a2b14a3e219c 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_pm.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_pm.c @@ -58,13 +58,15 @@ int mtk_vcodec_init_enc_clk(struct mtk_vcodec_enc_dev *mtkdev) return 0; } -void mtk_vcodec_enc_pw_on(struct mtk_vcodec_pm *pm) +int mtk_vcodec_enc_pw_on(struct mtk_vcodec_pm *pm) { int ret; ret = pm_runtime_resume_and_get(pm->dev); if (ret) dev_err(pm->dev, "pm_runtime_resume_and_get fail: %d", ret); + + return ret; } void mtk_vcodec_enc_pw_off(struct mtk_vcodec_pm *pm) diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_pm.h b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_pm.h index 157ea08ba9e36..2e28f25e36cc4 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_pm.h +++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_pm.h @@ -10,7 +10,7 @@ #include "mtk_vcodec_enc_drv.h" int mtk_vcodec_init_enc_clk(struct mtk_vcodec_enc_dev *dev); -void mtk_vcodec_enc_pw_on(struct mtk_vcodec_pm *pm); +int mtk_vcodec_enc_pw_on(struct mtk_vcodec_pm *pm); void mtk_vcodec_enc_pw_off(struct mtk_vcodec_pm *pm); void mtk_vcodec_enc_clock_on(struct mtk_vcodec_pm *pm); void mtk_vcodec_enc_clock_off(struct mtk_vcodec_pm *pm); diff --git a/drivers/media/platform/mediatek/vcodec/encoder/venc_drv_if.c b/drivers/media/platform/mediatek/vcodec/encoder/venc_drv_if.c index c402a686f3cb2..e83747b8d69ab 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/venc_drv_if.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/venc_drv_if.c @@ -64,7 +64,9 @@ int venc_if_encode(struct mtk_vcodec_enc_ctx *ctx, ctx->dev->curr_ctx = ctx; spin_unlock_irqrestore(&ctx->dev->irqlock, flags); - mtk_vcodec_enc_pw_on(&ctx->dev->pm); + ret = mtk_vcodec_enc_pw_on(&ctx->dev->pm); + if (ret) + goto venc_if_encode_pw_on_err; mtk_vcodec_enc_clock_on(&ctx->dev->pm); ret = ctx->enc_if->encode(ctx->drv_handle, opt, frm_buf, bs_buf, result); @@ -75,6 +77,7 @@ int venc_if_encode(struct mtk_vcodec_enc_ctx *ctx, ctx->dev->curr_ctx = NULL; spin_unlock_irqrestore(&ctx->dev->irqlock, flags); +venc_if_encode_pw_on_err: mtk_venc_unlock(ctx); return ret; } diff --git a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c index 84ad1cc6ad171..51bb7ee141b9e 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c @@ -47,12 +47,14 @@ static bool vpu_enc_check_ap_inst(struct mtk_vcodec_enc_dev *enc_dev, struct ven struct mtk_vcodec_enc_ctx *ctx; int ret = false; + mutex_lock(&enc_dev->dev_ctx_lock); list_for_each_entry(ctx, &enc_dev->ctx_list, list) { if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) { ret = true; break; } } + mutex_unlock(&enc_dev->dev_ctx_lock); return ret; } diff --git a/drivers/media/platform/mediatek/vpu/mtk_vpu.c b/drivers/media/platform/mediatek/vpu/mtk_vpu.c index 7243604a82a5b..724ae7c2ab3ba 100644 --- a/drivers/media/platform/mediatek/vpu/mtk_vpu.c +++ b/drivers/media/platform/mediatek/vpu/mtk_vpu.c @@ -635,7 +635,7 @@ int vpu_load_firmware(struct platform_device *pdev) } EXPORT_SYMBOL_GPL(vpu_load_firmware); -static void vpu_init_ipi_handler(const void *data, unsigned int len, void *priv) +static void vpu_init_ipi_handler(void *data, unsigned int len, void *priv) { struct mtk_vpu *vpu = priv; const struct vpu_run *run = data; diff --git a/drivers/media/platform/mediatek/vpu/mtk_vpu.h b/drivers/media/platform/mediatek/vpu/mtk_vpu.h index a56053ff135af..da05f3e740810 100644 --- a/drivers/media/platform/mediatek/vpu/mtk_vpu.h +++ b/drivers/media/platform/mediatek/vpu/mtk_vpu.h @@ -17,7 +17,7 @@ * VPU interfaces with other blocks by share memory and interrupt. */ -typedef void (*ipi_handler_t) (const void *data, +typedef void (*ipi_handler_t) (void *data, unsigned int len, void *priv); diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c index 575f173373887..93a55c97cd173 100644 --- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c +++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c @@ -161,7 +161,6 @@ mxc_isi_crossbar_xlate_streams(struct mxc_isi_crossbar *xbar, pad = media_pad_remote_pad_first(&xbar->pads[sink_pad]); sd = media_entity_to_v4l2_subdev(pad->entity); - if (!sd) { dev_dbg(xbar->isi->dev, "no entity connected to crossbar input %u\n", @@ -469,7 +468,8 @@ int mxc_isi_crossbar_init(struct mxc_isi_dev *isi) } for (i = 0; i < xbar->num_sinks; ++i) - xbar->pads[i].flags = MEDIA_PAD_FL_SINK; + xbar->pads[i].flags = MEDIA_PAD_FL_SINK + | MEDIA_PAD_FL_MUST_CONNECT; for (i = 0; i < xbar->num_sources; ++i) xbar->pads[i + xbar->num_sinks].flags = MEDIA_PAD_FL_SOURCE; diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-vin.h b/drivers/media/platform/renesas/rcar-vin/rcar-vin.h index 792336dada447..997a66318a293 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-vin.h +++ b/drivers/media/platform/renesas/rcar-vin/rcar-vin.h @@ -59,7 +59,7 @@ enum rvin_isp_id { #define RVIN_REMOTES_MAX \ (((unsigned int)RVIN_CSI_MAX) > ((unsigned int)RVIN_ISP_MAX) ? \ - RVIN_CSI_MAX : RVIN_ISP_MAX) + (unsigned int)RVIN_CSI_MAX : (unsigned int)RVIN_ISP_MAX) /** * enum rvin_dma_state - DMA states diff --git a/drivers/media/platform/sunxi/sun8i-a83t-mipi-csi2/Kconfig b/drivers/media/platform/sunxi/sun8i-a83t-mipi-csi2/Kconfig index 47a8c0fb7eb9f..99c401e653bc4 100644 --- a/drivers/media/platform/sunxi/sun8i-a83t-mipi-csi2/Kconfig +++ b/drivers/media/platform/sunxi/sun8i-a83t-mipi-csi2/Kconfig @@ -8,6 +8,7 @@ config VIDEO_SUN8I_A83T_MIPI_CSI2 select VIDEO_V4L2_SUBDEV_API select V4L2_FWNODE select REGMAP_MMIO + select GENERIC_PHY select GENERIC_PHY_MIPI_DPHY help Support for the Allwinner A83T MIPI CSI-2 controller and D-PHY. diff --git a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c index 954fabec27f63..a1c35a2b68ed9 100644 --- a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c +++ b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c @@ -66,6 +66,7 @@ static void deinterlace_device_run(void *priv) struct vb2_v4l2_buffer *src, *dst; unsigned int hstep, vstep; dma_addr_t addr; + int i; src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); dst = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx); @@ -160,6 +161,26 @@ static void deinterlace_device_run(void *priv) deinterlace_write(dev, DEINTERLACE_CH1_HORZ_FACT, hstep); deinterlace_write(dev, DEINTERLACE_CH1_VERT_FACT, vstep); + /* neutral filter coefficients */ + deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL, + DEINTERLACE_FRM_CTRL_COEF_ACCESS); + readl_poll_timeout(dev->base + DEINTERLACE_STATUS, val, + val & DEINTERLACE_STATUS_COEF_STATUS, 2, 40); + + for (i = 0; i < 32; i++) { + deinterlace_write(dev, DEINTERLACE_CH0_HORZ_COEF0 + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH0_VERT_COEF + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH1_HORZ_COEF0 + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH1_VERT_COEF + i * 4, + DEINTERLACE_IDENTITY_COEF); + } + + deinterlace_clr_set_bits(dev, DEINTERLACE_FRM_CTRL, + DEINTERLACE_FRM_CTRL_COEF_ACCESS, 0); + deinterlace_clr_set_bits(dev, DEINTERLACE_FIELD_CTRL, DEINTERLACE_FIELD_CTRL_FIELD_CNT_MSK, DEINTERLACE_FIELD_CTRL_FIELD_CNT(ctx->field)); @@ -248,7 +269,6 @@ static irqreturn_t deinterlace_irq(int irq, void *data) static void deinterlace_init(struct deinterlace_dev *dev) { u32 val; - int i; deinterlace_write(dev, DEINTERLACE_BYPASS, DEINTERLACE_BYPASS_CSC); @@ -284,27 +304,7 @@ static void deinterlace_init(struct deinterlace_dev *dev) deinterlace_clr_set_bits(dev, DEINTERLACE_CHROMA_DIFF, DEINTERLACE_CHROMA_DIFF_TH_MSK, - DEINTERLACE_CHROMA_DIFF_TH(5)); - - /* neutral filter coefficients */ - deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL, - DEINTERLACE_FRM_CTRL_COEF_ACCESS); - readl_poll_timeout(dev->base + DEINTERLACE_STATUS, val, - val & DEINTERLACE_STATUS_COEF_STATUS, 2, 40); - - for (i = 0; i < 32; i++) { - deinterlace_write(dev, DEINTERLACE_CH0_HORZ_COEF0 + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH0_VERT_COEF + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH1_HORZ_COEF0 + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH1_VERT_COEF + i * 4, - DEINTERLACE_IDENTITY_COEF); - } - - deinterlace_clr_set_bits(dev, DEINTERLACE_FRM_CTRL, - DEINTERLACE_FRM_CTRL_COEF_ACCESS, 0); + DEINTERLACE_CHROMA_DIFF_TH(31)); } static inline struct deinterlace_ctx *deinterlace_file2ctx(struct file *file) @@ -929,11 +929,18 @@ static int deinterlace_runtime_resume(struct device *device) return ret; } + ret = reset_control_deassert(dev->rstc); + if (ret) { + dev_err(dev->dev, "Failed to apply reset\n"); + + goto err_exclusive_rate; + } + ret = clk_prepare_enable(dev->bus_clk); if (ret) { dev_err(dev->dev, "Failed to enable bus clock\n"); - goto err_exclusive_rate; + goto err_rst; } ret = clk_prepare_enable(dev->mod_clk); @@ -950,23 +957,16 @@ static int deinterlace_runtime_resume(struct device *device) goto err_mod_clk; } - ret = reset_control_deassert(dev->rstc); - if (ret) { - dev_err(dev->dev, "Failed to apply reset\n"); - - goto err_ram_clk; - } - deinterlace_init(dev); return 0; -err_ram_clk: - clk_disable_unprepare(dev->ram_clk); err_mod_clk: clk_disable_unprepare(dev->mod_clk); err_bus_clk: clk_disable_unprepare(dev->bus_clk); +err_rst: + reset_control_assert(dev->rstc); err_exclusive_rate: clk_rate_exclusive_put(dev->mod_clk); @@ -977,11 +977,12 @@ static int deinterlace_runtime_suspend(struct device *device) { struct deinterlace_dev *dev = dev_get_drvdata(device); - reset_control_assert(dev->rstc); - clk_disable_unprepare(dev->ram_clk); clk_disable_unprepare(dev->mod_clk); clk_disable_unprepare(dev->bus_clk); + + reset_control_assert(dev->rstc); + clk_rate_exclusive_put(dev->mod_clk); return 0; diff --git a/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c b/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c index 59b30fc431440..c8c1fda73e530 100644 --- a/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c +++ b/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c @@ -762,15 +762,14 @@ static void ti_csi2rx_buffer_queue(struct vb2_buffer *vb) dev_warn(csi->dev, "Failed to drain DMA. Next frame might be bogus\n"); + spin_lock_irqsave(&dma->lock, flags); ret = ti_csi2rx_start_dma(csi, buf); if (ret) { - dev_err(csi->dev, "Failed to start DMA: %d\n", ret); - spin_lock_irqsave(&dma->lock, flags); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); dma->state = TI_CSI2RX_DMA_IDLE; spin_unlock_irqrestore(&dma->lock, flags); + dev_err(csi->dev, "Failed to start DMA: %d\n", ret); } else { - spin_lock_irqsave(&dma->lock, flags); list_add_tail(&buf->list, &dma->submitted); spin_unlock_irqrestore(&dma->lock, flags); } diff --git a/drivers/media/radio/radio-shark2.c b/drivers/media/radio/radio-shark2.c index f1c5c0a6a335c..e3e6aa87fe081 100644 --- a/drivers/media/radio/radio-shark2.c +++ b/drivers/media/radio/radio-shark2.c @@ -62,7 +62,7 @@ struct shark_device { #ifdef SHARK_USE_LEDS struct work_struct led_work; struct led_classdev leds[NO_LEDS]; - char led_names[NO_LEDS][32]; + char led_names[NO_LEDS][64]; atomic_t brightness[NO_LEDS]; unsigned long brightness_new; #endif diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index 57ded9ff3f043..29bc63021c5aa 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -1515,10 +1515,10 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) { struct xc4000_priv *priv = fe->tuner_priv; + mutex_lock(&priv->lock); *freq = priv->freq_hz + priv->freq_offset; if (debug) { - mutex_lock(&priv->lock); if ((priv->cur_fw.type & (BASE | FM | DTV6 | DTV7 | DTV78 | DTV8)) == BASE) { u16 snr = 0; @@ -1529,8 +1529,8 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) return 0; } } - mutex_unlock(&priv->lock); } + mutex_unlock(&priv->lock); dprintk(1, "%s()\n", __func__); diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c index 790787f0eba84..bcb24d8964981 100644 --- a/drivers/media/usb/b2c2/flexcop-usb.c +++ b/drivers/media/usb/b2c2/flexcop-usb.c @@ -515,7 +515,7 @@ static int flexcop_usb_init(struct flexcop_usb *fc_usb) alt = fc_usb->uintf->cur_altsetting; - if (alt->desc.bNumEndpoints < 1) + if (alt->desc.bNumEndpoints < 2) return -ENODEV; if (!usb_endpoint_is_isoc_in(&alt->endpoint[0].desc)) return -ENODEV; diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c index 4d037c92af7c5..bae76023cf71d 100644 --- a/drivers/media/usb/em28xx/em28xx-cards.c +++ b/drivers/media/usb/em28xx/em28xx-cards.c @@ -4094,6 +4094,10 @@ static int em28xx_usb_probe(struct usb_interface *intf, * topology will likely change after the load of the em28xx subdrivers. */ #ifdef CONFIG_MEDIA_CONTROLLER + /* + * No need to check the return value, the device will still be + * usable without media controller API. + */ retval = media_device_register(dev->media_dev); #endif diff --git a/drivers/media/usb/go7007/go7007-driver.c b/drivers/media/usb/go7007/go7007-driver.c index 0c24e29843048..eb03f98b2ef11 100644 --- a/drivers/media/usb/go7007/go7007-driver.c +++ b/drivers/media/usb/go7007/go7007-driver.c @@ -80,7 +80,7 @@ static int go7007_load_encoder(struct go7007 *go) const struct firmware *fw_entry; char fw_name[] = "go7007/go7007fw.bin"; void *bounce; - int fw_len, rv = 0; + int fw_len; u16 intr_val, intr_data; if (go->boot_fw == NULL) { @@ -109,9 +109,11 @@ static int go7007_load_encoder(struct go7007 *go) go7007_read_interrupt(go, &intr_val, &intr_data) < 0 || (intr_val & ~0x1) != 0x5a5a) { v4l2_err(go, "error transferring firmware\n"); - rv = -1; + kfree(go->boot_fw); + go->boot_fw = NULL; + return -1; } - return rv; + return 0; } MODULE_FIRMWARE("go7007/go7007fw.bin"); diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c index eeb85981e02b6..762c13e49bfa5 100644 --- a/drivers/media/usb/go7007/go7007-usb.c +++ b/drivers/media/usb/go7007/go7007-usb.c @@ -1201,7 +1201,9 @@ static int go7007_usb_probe(struct usb_interface *intf, u16 channel; /* read channel number from GPIO[1:0] */ - go7007_read_addr(go, 0x3c81, &channel); + if (go7007_read_addr(go, 0x3c81, &channel)) + goto allocfail; + channel &= 0x3; go->board_id = GO7007_BOARDID_ADLINK_MPG24; usb->board = board = &board_adlink_mpg24; diff --git a/drivers/media/usb/pvrusb2/pvrusb2-context.c b/drivers/media/usb/pvrusb2/pvrusb2-context.c index 1764674de98bc..73c95ba2328a4 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-context.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-context.c @@ -90,8 +90,10 @@ static void pvr2_context_destroy(struct pvr2_context *mp) } -static void pvr2_context_notify(struct pvr2_context *mp) +static void pvr2_context_notify(void *ptr) { + struct pvr2_context *mp = ptr; + pvr2_context_set_notify(mp,!0); } @@ -106,9 +108,7 @@ static void pvr2_context_check(struct pvr2_context *mp) pvr2_trace(PVR2_TRACE_CTXT, "pvr2_context %p (initialize)", mp); /* Finish hardware initialization */ - if (pvr2_hdw_initialize(mp->hdw, - (void (*)(void *))pvr2_context_notify, - mp)) { + if (pvr2_hdw_initialize(mp->hdw, pvr2_context_notify, mp)) { mp->video_stream.stream = pvr2_hdw_get_video_stream(mp->hdw); /* Trigger interface initialization. By doing this @@ -267,9 +267,9 @@ static void pvr2_context_exit(struct pvr2_context *mp) void pvr2_context_disconnect(struct pvr2_context *mp) { pvr2_hdw_disconnect(mp->hdw); - mp->disconnect_flag = !0; if (!pvr2_context_shutok()) pvr2_context_notify(mp); + mp->disconnect_flag = !0; } diff --git a/drivers/media/usb/pvrusb2/pvrusb2-dvb.c b/drivers/media/usb/pvrusb2/pvrusb2-dvb.c index 26811efe0fb58..9a9bae21c6147 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-dvb.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-dvb.c @@ -88,8 +88,10 @@ static int pvr2_dvb_feed_thread(void *data) return stat; } -static void pvr2_dvb_notify(struct pvr2_dvb_adapter *adap) +static void pvr2_dvb_notify(void *ptr) { + struct pvr2_dvb_adapter *adap = ptr; + wake_up(&adap->buffer_wait_data); } @@ -149,7 +151,7 @@ static int pvr2_dvb_stream_do_start(struct pvr2_dvb_adapter *adap) } pvr2_stream_set_callback(pvr->video_stream.stream, - (pvr2_stream_callback) pvr2_dvb_notify, adap); + pvr2_dvb_notify, adap); ret = pvr2_stream_set_buffer_count(stream, PVR2_DVB_BUFFER_COUNT); if (ret < 0) return ret; diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c index c04ab7258d645..d608b793fa847 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c @@ -1033,8 +1033,10 @@ static int pvr2_v4l2_open(struct file *file) } -static void pvr2_v4l2_notify(struct pvr2_v4l2_fh *fhp) +static void pvr2_v4l2_notify(void *ptr) { + struct pvr2_v4l2_fh *fhp = ptr; + wake_up(&fhp->wait_data); } @@ -1067,7 +1069,7 @@ static int pvr2_v4l2_iosetup(struct pvr2_v4l2_fh *fh) hdw = fh->channel.mc_head->hdw; sp = fh->pdi->stream->stream; - pvr2_stream_set_callback(sp,(pvr2_stream_callback)pvr2_v4l2_notify,fh); + pvr2_stream_set_callback(sp, pvr2_v4l2_notify, fh); pvr2_hdw_set_stream_type(hdw,fh->pdi->config); if ((ret = pvr2_hdw_set_streaming(hdw,!0)) < 0) return ret; return pvr2_ioread_set_enabled(fh->rhp,!0); @@ -1198,11 +1200,6 @@ static void pvr2_v4l2_dev_init(struct pvr2_v4l2_dev *dip, dip->minor_type = pvr2_v4l_type_video; nr_ptr = video_nr; caps |= V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_AUDIO; - if (!dip->stream) { - pr_err(KBUILD_MODNAME - ": Failed to set up pvrusb2 v4l video dev due to missing stream instance\n"); - return; - } break; case VFL_TYPE_VBI: dip->config = pvr2_config_vbi; diff --git a/drivers/media/usb/stk1160/stk1160-video.c b/drivers/media/usb/stk1160/stk1160-video.c index 366f0e4a5dc0d..e79c45db60ab5 100644 --- a/drivers/media/usb/stk1160/stk1160-video.c +++ b/drivers/media/usb/stk1160/stk1160-video.c @@ -99,7 +99,7 @@ void stk1160_buffer_done(struct stk1160 *dev) static inline void stk1160_copy_video(struct stk1160 *dev, u8 *src, int len) { - int linesdone, lineoff, lencopy; + int linesdone, lineoff, lencopy, offset; int bytesperline = dev->width * 2; struct stk1160_buffer *buf = dev->isoc_ctl.buf; u8 *dst = buf->mem; @@ -139,8 +139,13 @@ void stk1160_copy_video(struct stk1160 *dev, u8 *src, int len) * Check if we have enough space left in the buffer. * In that case, we force loop exit after copy. */ - if (lencopy > buf->bytesused - buf->length) { - lencopy = buf->bytesused - buf->length; + offset = dst - (u8 *)buf->mem; + if (offset > buf->length) { + dev_warn_ratelimited(dev->dev, "out of bounds offset\n"); + return; + } + if (lencopy > buf->length - offset) { + lencopy = buf->length - offset; remain = lencopy; } @@ -182,8 +187,13 @@ void stk1160_copy_video(struct stk1160 *dev, u8 *src, int len) * Check if we have enough space left in the buffer. * In that case, we force loop exit after copy. */ - if (lencopy > buf->bytesused - buf->length) { - lencopy = buf->bytesused - buf->length; + offset = dst - (u8 *)buf->mem; + if (offset > buf->length) { + dev_warn_ratelimited(dev->dev, "offset out of bounds\n"); + return; + } + if (lencopy > buf->length - offset) { + lencopy = buf->length - offset; remain = lencopy; } diff --git a/drivers/media/usb/usbtv/usbtv-video.c b/drivers/media/usb/usbtv/usbtv-video.c index 62a583040cd48..702f1c8bd2ab3 100644 --- a/drivers/media/usb/usbtv/usbtv-video.c +++ b/drivers/media/usb/usbtv/usbtv-video.c @@ -963,15 +963,8 @@ int usbtv_video_init(struct usbtv *usbtv) void usbtv_video_free(struct usbtv *usbtv) { - mutex_lock(&usbtv->vb2q_lock); - mutex_lock(&usbtv->v4l2_lock); - - usbtv_stop(usbtv); vb2_video_unregister_device(&usbtv->vdev); v4l2_device_disconnect(&usbtv->v4l2_dev); - mutex_unlock(&usbtv->v4l2_lock); - mutex_unlock(&usbtv->vb2q_lock); - v4l2_device_put(&usbtv->v4l2_dev); } diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index bbd90123a4e76..91a41aa3ced24 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -2232,6 +2233,9 @@ static int uvc_probe(struct usb_interface *intf, goto error; } + if (dev->quirks & UVC_QUIRK_NO_RESET_RESUME) + udev->quirks &= ~USB_QUIRK_RESET_RESUME; + uvc_dbg(dev, PROBE, "UVC device initialized\n"); usb_enable_autosuspend(udev); return 0; @@ -2574,6 +2578,33 @@ static const struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_RESTORE_CTRLS_ON_INIT) }, + /* Logitech Rally Bar Huddle */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x046d, + .idProduct = 0x087c, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_NO_RESET_RESUME) }, + /* Logitech Rally Bar */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x046d, + .idProduct = 0x089b, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_NO_RESET_RESUME) }, + /* Logitech Rally Bar Mini */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x046d, + .idProduct = 0x08d3, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_NO_RESET_RESUME) }, /* Chicony CNF7129 (Asus EEE 100HE) */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index 6fb0a78b1b009..88218693f6f0b 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -73,6 +73,7 @@ #define UVC_QUIRK_FORCE_Y8 0x00000800 #define UVC_QUIRK_FORCE_BPP 0x00001000 #define UVC_QUIRK_WAKE_AUTOSUSPEND 0x00002000 +#define UVC_QUIRK_NO_RESET_RESUME 0x00004000 /* Format flags */ #define UVC_FMT_FLAG_COMPRESSED 0x00000001 diff --git a/drivers/media/v4l2-core/v4l2-async.c b/drivers/media/v4l2-core/v4l2-async.c index 3ec323bd528b1..4bb073587817c 100644 --- a/drivers/media/v4l2-core/v4l2-async.c +++ b/drivers/media/v4l2-core/v4l2-async.c @@ -563,6 +563,7 @@ void v4l2_async_nf_init(struct v4l2_async_notifier *notifier, { INIT_LIST_HEAD(¬ifier->waiting_list); INIT_LIST_HEAD(¬ifier->done_list); + INIT_LIST_HEAD(¬ifier->notifier_entry); notifier->v4l2_dev = v4l2_dev; } EXPORT_SYMBOL(v4l2_async_nf_init); @@ -572,6 +573,7 @@ void v4l2_async_subdev_nf_init(struct v4l2_async_notifier *notifier, { INIT_LIST_HEAD(¬ifier->waiting_list); INIT_LIST_HEAD(¬ifier->done_list); + INIT_LIST_HEAD(¬ifier->notifier_entry); notifier->sd = sd; } EXPORT_SYMBOL_GPL(v4l2_async_subdev_nf_init); @@ -618,16 +620,10 @@ static int __v4l2_async_nf_register(struct v4l2_async_notifier *notifier) int v4l2_async_nf_register(struct v4l2_async_notifier *notifier) { - int ret; - if (WARN_ON(!notifier->v4l2_dev == !notifier->sd)) return -EINVAL; - ret = __v4l2_async_nf_register(notifier); - if (ret) - notifier->v4l2_dev = NULL; - - return ret; + return __v4l2_async_nf_register(notifier); } EXPORT_SYMBOL(v4l2_async_nf_register); @@ -639,7 +635,7 @@ __v4l2_async_nf_unregister(struct v4l2_async_notifier *notifier) v4l2_async_nf_unbind_all_subdevs(notifier); - list_del(¬ifier->notifier_entry); + list_del_init(¬ifier->notifier_entry); } void v4l2_async_nf_unregister(struct v4l2_async_notifier *notifier) diff --git a/drivers/media/v4l2-core/v4l2-cci.c b/drivers/media/v4l2-core/v4l2-cci.c index 10005c80f43b5..ee3475bed37fa 100644 --- a/drivers/media/v4l2-core/v4l2-cci.c +++ b/drivers/media/v4l2-core/v4l2-cci.c @@ -32,7 +32,7 @@ int cci_read(struct regmap *map, u32 reg, u64 *val, int *err) ret = regmap_bulk_read(map, reg, buf, len); if (ret) { - dev_err(regmap_get_device(map), "Error reading reg 0x%4x: %d\n", + dev_err(regmap_get_device(map), "Error reading reg 0x%04x: %d\n", reg, ret); goto out; } @@ -131,7 +131,7 @@ int cci_write(struct regmap *map, u32 reg, u64 val, int *err) ret = regmap_bulk_write(map, reg, buf, len); if (ret) - dev_err(regmap_get_device(map), "Error writing reg 0x%4x: %d\n", + dev_err(regmap_get_device(map), "Error writing reg 0x%04x: %d\n", reg, ret); out: diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index d13954bd31fd9..bae73b8c52ff5 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -1036,8 +1036,10 @@ int __video_register_device(struct video_device *vdev, vdev->dev.devt = MKDEV(VIDEO_MAJOR, vdev->minor); vdev->dev.parent = vdev->dev_parent; dev_set_name(&vdev->dev, "%s%d", name_base, vdev->num); + mutex_lock(&videodev_lock); ret = device_register(&vdev->dev); if (ret < 0) { + mutex_unlock(&videodev_lock); pr_err("%s: device_register failed\n", __func__); goto cleanup; } @@ -1057,6 +1059,7 @@ int __video_register_device(struct video_device *vdev, /* Part 6: Activate this minor. The char device can now be used. */ set_bit(V4L2_FL_REGISTERED, &vdev->flags); + mutex_unlock(&videodev_lock); return 0; diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 9e983176542be..75517134a5e94 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -1087,11 +1087,17 @@ static int v4l2_m2m_register_entity(struct media_device *mdev, entity->function = function; ret = media_entity_pads_init(entity, num_pads, pads); - if (ret) + if (ret) { + kfree(entity->name); + entity->name = NULL; return ret; + } ret = media_device_register_entity(mdev, entity); - if (ret) + if (ret) { + kfree(entity->name); + entity->name = NULL; return ret; + } return 0; } diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 4c6198c48dd61..19d20871afefa 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -412,15 +412,6 @@ static int call_s_stream(struct v4l2_subdev *sd, int enable) if (WARN_ON(!!sd->enabled_streams == !!enable)) return 0; -#if IS_REACHABLE(CONFIG_LEDS_CLASS) - if (!IS_ERR_OR_NULL(sd->privacy_led)) { - if (enable) - led_set_brightness(sd->privacy_led, - sd->privacy_led->max_brightness); - else - led_set_brightness(sd->privacy_led, 0); - } -#endif ret = sd->ops->video->s_stream(sd, enable); if (!enable && ret < 0) { @@ -428,9 +419,20 @@ static int call_s_stream(struct v4l2_subdev *sd, int enable) ret = 0; } - if (!ret) + if (!ret) { sd->enabled_streams = enable ? BIT(0) : 0; +#if IS_REACHABLE(CONFIG_LEDS_CLASS) + if (!IS_ERR_OR_NULL(sd->privacy_led)) { + if (enable) + led_set_brightness(sd->privacy_led, + sd->privacy_led->max_brightness); + else + led_set_brightness(sd->privacy_led, 0); + } +#endif + } + return ret; } @@ -732,6 +734,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, memset(&sel, 0, sizeof(sel)); sel.which = crop->which; sel.pad = crop->pad; + sel.stream = crop->stream; sel.target = V4L2_SEL_TGT_CROP; rval = v4l2_subdev_call( @@ -756,6 +759,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, memset(&sel, 0, sizeof(sel)); sel.which = crop->which; sel.pad = crop->pad; + sel.stream = crop->stream; sel.target = V4L2_SEL_TGT_CROP; sel.r = crop->rect; diff --git a/drivers/memory/tegra/tegra234.c b/drivers/memory/tegra/tegra234.c index abff87f917cb4..b8a7af2d36c11 100644 --- a/drivers/memory/tegra/tegra234.c +++ b/drivers/memory/tegra/tegra234.c @@ -121,7 +121,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_DLA1RDB, - .name = "dla0rdb", + .name = "dla1rdb", .sid = TEGRA234_SID_NVDLA1, .regs = { .sid = { @@ -407,7 +407,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_DLA1RDB1, - .name = "dla0rdb1", + .name = "dla1rdb1", .sid = TEGRA234_SID_NVDLA1, .regs = { .sid = { @@ -417,7 +417,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_DLA1WRB, - .name = "dla0wrb", + .name = "dla1wrb", .sid = TEGRA234_SID_NVDLA1, .regs = { .sid = { @@ -699,7 +699,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_DLA1RDA, - .name = "dla0rda", + .name = "dla1rda", .sid = TEGRA234_SID_NVDLA1, .regs = { .sid = { @@ -709,7 +709,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_DLA1FALRDB, - .name = "dla0falrdb", + .name = "dla1falrdb", .sid = TEGRA234_SID_NVDLA1, .regs = { .sid = { @@ -719,7 +719,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_DLA1WRA, - .name = "dla0wra", + .name = "dla1wra", .sid = TEGRA234_SID_NVDLA1, .regs = { .sid = { @@ -729,7 +729,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_DLA1FALWRB, - .name = "dla0falwrb", + .name = "dla1falwrb", .sid = TEGRA234_SID_NVDLA1, .regs = { .sid = { @@ -917,7 +917,7 @@ static const struct tegra_mc_client tegra234_mc_clients[] = { }, }, { .id = TEGRA234_MEMORY_CLIENT_DLA1RDA1, - .name = "dla0rda1", + .name = "dla1rda1", .sid = TEGRA234_SID_NVDLA1, .regs = { .sid = { diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index e7a6e45b9fac2..3425bba34632f 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1773,6 +1773,7 @@ config TWL4030_CORE bool "TI TWL4030/TWL5030/TWL6030/TPS659x0 Support" depends on I2C=y select IRQ_DOMAIN + select MFD_CORE select REGMAP_I2C help Say yes here if you have TWL4030 / TWL6030 family chip on your board. @@ -2218,6 +2219,18 @@ config MFD_QCOM_PM8008 under it in the device tree. Additional drivers must be enabled in order to use the functionality of the device. +config MFD_AAEON + tristate "AAEON WMI MFD devices" + depends on ASUS_WMI + depends on UBUNTU_ODM_DRIVERS + help + Say yes here to support mltiple IO devices on Single Board Computers + produced by AAEON. + + This driver leverages the ASUS WMI interface to access device + resources. + + menu "Multimedia Capabilities Port drivers" depends on ARCH_SA1100 diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index c66f07edcd0e6..df9cffad0606b 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -279,6 +279,7 @@ obj-$(CONFIG_MFD_INTEL_M10_BMC_PMCI) += intel-m10-bmc-pmci.o obj-$(CONFIG_MFD_ATC260X) += atc260x-core.o obj-$(CONFIG_MFD_ATC260X_I2C) += atc260x-i2c.o +obj-$(CONFIG_MFD_AAEON) += mfd-aaeon.o rsmu-i2c-objs := rsmu_core.o rsmu_i2c.o rsmu-spi-objs := rsmu_core.o rsmu_spi.o diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c index 0e52bd2ebd74b..fb5f988e61f37 100644 --- a/drivers/mfd/altera-sysmgr.c +++ b/drivers/mfd/altera-sysmgr.c @@ -109,7 +109,9 @@ struct regmap *altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np, dev = driver_find_device_by_of_node(&altr_sysmgr_driver.driver, (void *)sysmgr_np); - of_node_put(sysmgr_np); + if (property) + of_node_put(sysmgr_np); + if (!dev) return ERR_PTR(-EPROBE_DEFER); diff --git a/drivers/mfd/cs42l43.c b/drivers/mfd/cs42l43.c index 7b6d07cbe6fc6..1cea3f8f467d4 100644 --- a/drivers/mfd/cs42l43.c +++ b/drivers/mfd/cs42l43.c @@ -84,7 +84,7 @@ const struct reg_default cs42l43_reg_default[CS42L43_N_DEFAULTS] = { { CS42L43_DRV_CTRL_5, 0x136C00C0 }, { CS42L43_GPIO_CTRL1, 0x00000707 }, { CS42L43_GPIO_CTRL2, 0x00000000 }, - { CS42L43_GPIO_FN_SEL, 0x00000000 }, + { CS42L43_GPIO_FN_SEL, 0x00000004 }, { CS42L43_MCLK_SRC_SEL, 0x00000000 }, { CS42L43_SAMPLE_RATE1, 0x00000003 }, { CS42L43_SAMPLE_RATE2, 0x00000003 }, @@ -131,38 +131,38 @@ const struct reg_default cs42l43_reg_default[CS42L43_N_DEFAULTS] = { { CS42L43_ASP_TX_CH4_CTRL, 0x00170091 }, { CS42L43_ASP_TX_CH5_CTRL, 0x001700C1 }, { CS42L43_ASP_TX_CH6_CTRL, 0x001700F1 }, - { CS42L43_ASPTX1_INPUT, 0x00800000 }, - { CS42L43_ASPTX2_INPUT, 0x00800000 }, - { CS42L43_ASPTX3_INPUT, 0x00800000 }, - { CS42L43_ASPTX4_INPUT, 0x00800000 }, - { CS42L43_ASPTX5_INPUT, 0x00800000 }, - { CS42L43_ASPTX6_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP1_CH1_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP1_CH2_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP1_CH3_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP1_CH4_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP2_CH1_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP2_CH2_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP3_CH1_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP3_CH2_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP4_CH1_INPUT, 0x00800000 }, - { CS42L43_SWIRE_DP4_CH2_INPUT, 0x00800000 }, - { CS42L43_ASRC_INT1_INPUT1, 0x00800000 }, - { CS42L43_ASRC_INT2_INPUT1, 0x00800000 }, - { CS42L43_ASRC_INT3_INPUT1, 0x00800000 }, - { CS42L43_ASRC_INT4_INPUT1, 0x00800000 }, - { CS42L43_ASRC_DEC1_INPUT1, 0x00800000 }, - { CS42L43_ASRC_DEC2_INPUT1, 0x00800000 }, - { CS42L43_ASRC_DEC3_INPUT1, 0x00800000 }, - { CS42L43_ASRC_DEC4_INPUT1, 0x00800000 }, - { CS42L43_ISRC1INT1_INPUT1, 0x00800000 }, - { CS42L43_ISRC1INT2_INPUT1, 0x00800000 }, - { CS42L43_ISRC1DEC1_INPUT1, 0x00800000 }, - { CS42L43_ISRC1DEC2_INPUT1, 0x00800000 }, - { CS42L43_ISRC2INT1_INPUT1, 0x00800000 }, - { CS42L43_ISRC2INT2_INPUT1, 0x00800000 }, - { CS42L43_ISRC2DEC1_INPUT1, 0x00800000 }, - { CS42L43_ISRC2DEC2_INPUT1, 0x00800000 }, + { CS42L43_ASPTX1_INPUT, 0x00000000 }, + { CS42L43_ASPTX2_INPUT, 0x00000000 }, + { CS42L43_ASPTX3_INPUT, 0x00000000 }, + { CS42L43_ASPTX4_INPUT, 0x00000000 }, + { CS42L43_ASPTX5_INPUT, 0x00000000 }, + { CS42L43_ASPTX6_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP1_CH1_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP1_CH2_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP1_CH3_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP1_CH4_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP2_CH1_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP2_CH2_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP3_CH1_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP3_CH2_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP4_CH1_INPUT, 0x00000000 }, + { CS42L43_SWIRE_DP4_CH2_INPUT, 0x00000000 }, + { CS42L43_ASRC_INT1_INPUT1, 0x00000000 }, + { CS42L43_ASRC_INT2_INPUT1, 0x00000000 }, + { CS42L43_ASRC_INT3_INPUT1, 0x00000000 }, + { CS42L43_ASRC_INT4_INPUT1, 0x00000000 }, + { CS42L43_ASRC_DEC1_INPUT1, 0x00000000 }, + { CS42L43_ASRC_DEC2_INPUT1, 0x00000000 }, + { CS42L43_ASRC_DEC3_INPUT1, 0x00000000 }, + { CS42L43_ASRC_DEC4_INPUT1, 0x00000000 }, + { CS42L43_ISRC1INT1_INPUT1, 0x00000000 }, + { CS42L43_ISRC1INT2_INPUT1, 0x00000000 }, + { CS42L43_ISRC1DEC1_INPUT1, 0x00000000 }, + { CS42L43_ISRC1DEC2_INPUT1, 0x00000000 }, + { CS42L43_ISRC2INT1_INPUT1, 0x00000000 }, + { CS42L43_ISRC2INT2_INPUT1, 0x00000000 }, + { CS42L43_ISRC2DEC1_INPUT1, 0x00000000 }, + { CS42L43_ISRC2DEC2_INPUT1, 0x00000000 }, { CS42L43_EQ1MIX_INPUT1, 0x00800000 }, { CS42L43_EQ1MIX_INPUT2, 0x00800000 }, { CS42L43_EQ1MIX_INPUT3, 0x00800000 }, @@ -171,8 +171,8 @@ const struct reg_default cs42l43_reg_default[CS42L43_N_DEFAULTS] = { { CS42L43_EQ2MIX_INPUT2, 0x00800000 }, { CS42L43_EQ2MIX_INPUT3, 0x00800000 }, { CS42L43_EQ2MIX_INPUT4, 0x00800000 }, - { CS42L43_SPDIF1_INPUT1, 0x00800000 }, - { CS42L43_SPDIF2_INPUT1, 0x00800000 }, + { CS42L43_SPDIF1_INPUT1, 0x00000000 }, + { CS42L43_SPDIF2_INPUT1, 0x00000000 }, { CS42L43_AMP1MIX_INPUT1, 0x00800000 }, { CS42L43_AMP1MIX_INPUT2, 0x00800000 }, { CS42L43_AMP1MIX_INPUT3, 0x00800000 }, @@ -217,7 +217,7 @@ const struct reg_default cs42l43_reg_default[CS42L43_N_DEFAULTS] = { { CS42L43_CTRL_REG, 0x00000006 }, { CS42L43_FDIV_FRAC, 0x40000000 }, { CS42L43_CAL_RATIO, 0x00000080 }, - { CS42L43_SPI_CLK_CONFIG1, 0x00000000 }, + { CS42L43_SPI_CLK_CONFIG1, 0x00000001 }, { CS42L43_SPI_CONFIG1, 0x00000000 }, { CS42L43_SPI_CONFIG2, 0x00000000 }, { CS42L43_SPI_CONFIG3, 0x00000001 }, diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c index 4621d3950b8f9..8c00e0c695c5b 100644 --- a/drivers/mfd/intel-lpss-pci.c +++ b/drivers/mfd/intel-lpss-pci.c @@ -23,12 +23,22 @@ #include "intel-lpss.h" -/* Some DSDTs have an unused GEXP ACPI device conflicting with I2C4 resources */ -static const struct pci_device_id ignore_resource_conflicts_ids[] = { - /* Microsoft Surface Go (version 1) I2C4 */ - { PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, 0x9d64, 0x152d, 0x1182), }, - /* Microsoft Surface Go 2 I2C4 */ - { PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, 0x9d64, 0x152d, 0x1237), }, +static const struct pci_device_id quirk_ids[] = { + { + /* Microsoft Surface Go (version 1) I2C4 */ + PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, 0x9d64, 0x152d, 0x1182), + .driver_data = QUIRK_IGNORE_RESOURCE_CONFLICTS, + }, + { + /* Microsoft Surface Go 2 I2C4 */ + PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, 0x9d64, 0x152d, 0x1237), + .driver_data = QUIRK_IGNORE_RESOURCE_CONFLICTS, + }, + { + /* Dell XPS 9530 (2023) */ + PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, 0x51fb, 0x1028, 0x0beb), + .driver_data = QUIRK_CLOCK_DIVIDER_UNITY, + }, { } }; @@ -36,6 +46,7 @@ static int intel_lpss_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { const struct intel_lpss_platform_info *data = (void *)id->driver_data; + const struct pci_device_id *quirk_pci_info; struct intel_lpss_platform_info *info; int ret; @@ -55,8 +66,9 @@ static int intel_lpss_pci_probe(struct pci_dev *pdev, info->mem = pci_resource_n(pdev, 0); info->irq = pci_irq_vector(pdev, 0); - if (pci_match_id(ignore_resource_conflicts_ids, pdev)) - info->ignore_resource_conflicts = true; + quirk_pci_info = pci_match_id(quirk_ids, pdev); + if (quirk_pci_info) + info->quirks = quirk_pci_info->driver_data; pdev->d3cold_delay = 0; diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c index eff423f7dd284..2a9018112dfc8 100644 --- a/drivers/mfd/intel-lpss.c +++ b/drivers/mfd/intel-lpss.c @@ -300,6 +300,7 @@ static int intel_lpss_register_clock_divider(struct intel_lpss *lpss, { char name[32]; struct clk *tmp = *clk; + int ret; snprintf(name, sizeof(name), "%s-enable", devname); tmp = clk_register_gate(NULL, name, __clk_get_name(tmp), 0, @@ -316,6 +317,12 @@ static int intel_lpss_register_clock_divider(struct intel_lpss *lpss, return PTR_ERR(tmp); *clk = tmp; + if (lpss->info->quirks & QUIRK_CLOCK_DIVIDER_UNITY) { + ret = clk_set_rate(tmp, lpss->info->clk_rate); + if (ret) + return ret; + } + snprintf(name, sizeof(name), "%s-update", devname); tmp = clk_register_gate(NULL, name, __clk_get_name(tmp), CLK_SET_RATE_PARENT, lpss->priv, 31, 0, NULL); @@ -412,7 +419,7 @@ int intel_lpss_probe(struct device *dev, return ret; lpss->cell->swnode = info->swnode; - lpss->cell->ignore_resource_conflicts = info->ignore_resource_conflicts; + lpss->cell->ignore_resource_conflicts = info->quirks & QUIRK_IGNORE_RESOURCE_CONFLICTS; intel_lpss_init_dev(lpss); diff --git a/drivers/mfd/intel-lpss.h b/drivers/mfd/intel-lpss.h index c1d72b117ed5e..6f8f668f4c6f0 100644 --- a/drivers/mfd/intel-lpss.h +++ b/drivers/mfd/intel-lpss.h @@ -11,16 +11,28 @@ #ifndef __MFD_INTEL_LPSS_H #define __MFD_INTEL_LPSS_H +#include #include +/* + * Some DSDTs have an unused GEXP ACPI device conflicting with I2C4 resources. + * Set to ignore resource conflicts with ACPI declared SystemMemory regions. + */ +#define QUIRK_IGNORE_RESOURCE_CONFLICTS BIT(0) +/* + * Some devices have misconfigured clock divider due to a firmware bug. + * Set this to force the clock divider to 1:1 ratio. + */ +#define QUIRK_CLOCK_DIVIDER_UNITY BIT(1) + struct device; struct resource; struct software_node; struct intel_lpss_platform_info { struct resource *mem; - bool ignore_resource_conflicts; int irq; + unsigned int quirks; unsigned long clk_rate; const char *clk_con_id; const struct software_node *swnode; diff --git a/drivers/mfd/mfd-aaeon.c b/drivers/mfd/mfd-aaeon.c new file mode 100644 index 0000000000000..74211d01ce656 --- /dev/null +++ b/drivers/mfd/mfd-aaeon.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * UP Board main platform driver and FPGA configuration support + * + * Copyright (c) 2021, AAEON Ltd. + * + * Author: Kunyang_Fan + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define AAEON_WMI_MGMT_GUID "97845ED0-4E6D-11DE-8A39-0800200C9A66" + +#define WMI_REPORT_CAPABILITY_METHOD 0x00000000 +#define MAX_BFPI_VERSION 255 +#define GET_REVISION_ID 0x00 + +struct aaeon_wmi_priv { + const struct mfd_cell *cells; + size_t ncells; +}; + +static const struct mfd_cell aaeon_mfd_cells[] = { + { .name = "gpio-aaeon" }, + { .name = "hwmon-aaeon"}, + { .name = "leds-aaeon"}, + { .name = "wdt-aaeon"}, +}; + +static const struct aaeon_wmi_priv aaeon_wmi_priv_data = { + .cells = aaeon_mfd_cells, + .ncells = ARRAY_SIZE(aaeon_mfd_cells), +}; + +static int aaeon_wmi_check_device(void) +{ + int err; + int retval; + + err = asus_wmi_evaluate_method(WMI_REPORT_CAPABILITY_METHOD, GET_REVISION_ID, 0, + &retval); + if (err) + return -ENODEV; + if (retval < 3 || retval > MAX_BFPI_VERSION) + return -ENODEV; + + return 0; +} + +static int aaeon_wmi_probe(struct wmi_device *wdev, const void *context) +{ + struct aaeon_wmi_priv *priv; + + if (!wmi_has_guid(AAEON_WMI_MGMT_GUID)) { + dev_info(&wdev->dev, "AAEON Management GUID not found\n"); + return -ENODEV; + } + + if (aaeon_wmi_check_device()) + return -ENODEV; + + priv = (struct aaeon_wmi_priv *)context; + dev_set_drvdata(&wdev->dev, priv); + + return devm_mfd_add_devices(&wdev->dev, 0, priv->cells, + priv->ncells, NULL, 0, NULL); +} + +static const struct wmi_device_id aaeon_wmi_id_table[] = { + { AAEON_WMI_MGMT_GUID, (void *)&aaeon_wmi_priv_data }, + {} +}; + +static struct wmi_driver aaeon_wmi_driver = { + .driver = { + .name = "mfd-aaeon", + }, + .id_table = aaeon_wmi_id_table, + .probe = aaeon_wmi_probe, +}; + +module_wmi_driver(aaeon_wmi_driver); + +MODULE_DEVICE_TABLE(wmi, aaeon_wmi_id_table); +MODULE_AUTHOR("Kunyang Fan "); +MODULE_DESCRIPTION("AAEON Board WMI driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index c9550368d9ea5..7d0e91164cbaa 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -238,7 +238,9 @@ struct regmap *syscon_regmap_lookup_by_phandle(struct device_node *np, return ERR_PTR(-ENODEV); regmap = syscon_node_to_regmap(syscon_np); - of_node_put(syscon_np); + + if (property) + of_node_put(syscon_np); return regmap; } diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 1a64364700eb0..0ad2ff9065aad 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1002,7 +1002,7 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id) } else { pcr->card_removed |= SD_EXIST; pcr->card_inserted &= ~SD_EXIST; - if (PCI_PID(pcr) == PID_5261) { + if ((PCI_PID(pcr) == PID_5261) || (PCI_PID(pcr) == PID_5264)) { rtsx_pci_write_register(pcr, RTS5261_FW_STATUS, RTS5261_EXPRESS_LINK_FAIL_MASK, 0); pcr->extra_caps |= EXTRA_CAPS_SD_EXPRESS; diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 572333ead5fb8..4bd4f32bcdabb 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -758,15 +758,6 @@ static int at24_probe(struct i2c_client *client) } pm_runtime_enable(dev); - at24->nvmem = devm_nvmem_register(dev, &nvmem_config); - if (IS_ERR(at24->nvmem)) { - pm_runtime_disable(dev); - if (!pm_runtime_status_suspended(dev)) - regulator_disable(at24->vcc_reg); - return dev_err_probe(dev, PTR_ERR(at24->nvmem), - "failed to register nvmem\n"); - } - /* * Perform a one-byte test read to verify that the chip is functional, * unless powering on the device is to be avoided during probe (i.e. @@ -782,6 +773,15 @@ static int at24_probe(struct i2c_client *client) } } + at24->nvmem = devm_nvmem_register(dev, &nvmem_config); + if (IS_ERR(at24->nvmem)) { + pm_runtime_disable(dev); + if (!pm_runtime_status_suspended(dev)) + regulator_disable(at24->vcc_reg); + return dev_err_probe(dev, PTR_ERR(at24->nvmem), + "failed to register nvmem\n"); + } + /* If this a SPD EEPROM, probe for DDR3 thermal sensor */ if (cdata == &at24_data_spd) at24_probe_temp_sensor(client); diff --git a/drivers/misc/lkdtm/Makefile b/drivers/misc/lkdtm/Makefile index 95ef971b5e1cb..b28701138b4bc 100644 --- a/drivers/misc/lkdtm/Makefile +++ b/drivers/misc/lkdtm/Makefile @@ -19,7 +19,7 @@ KASAN_SANITIZE_rodata.o := n KCSAN_SANITIZE_rodata.o := n KCOV_INSTRUMENT_rodata.o := n OBJECT_FILES_NON_STANDARD_rodata.o := y -CFLAGS_REMOVE_rodata.o += $(CC_FLAGS_LTO) $(RETHUNK_CFLAGS) +CFLAGS_REMOVE_rodata.o += $(CC_FLAGS_LTO) $(RETHUNK_CFLAGS) $(CC_FLAGS_CFI) OBJCOPYFLAGS := OBJCOPYFLAGS_rodata_objcopy.o := \ diff --git a/drivers/misc/lkdtm/perms.c b/drivers/misc/lkdtm/perms.c index b93404d656509..5b861dbff27e9 100644 --- a/drivers/misc/lkdtm/perms.c +++ b/drivers/misc/lkdtm/perms.c @@ -61,7 +61,7 @@ static void *setup_function_descriptor(func_desc_t *fdesc, void *dst) return fdesc; } -static noinline void execute_location(void *dst, bool write) +static noinline __nocfi void execute_location(void *dst, bool write) { void (*func)(void); func_desc_t fdesc; diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c index 32af2b14ff344..34c9be437432a 100644 --- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c +++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c @@ -69,8 +69,10 @@ static int gp_aux_bus_probe(struct pci_dev *pdev, const struct pci_device_id *id aux_bus->aux_device_wrapper[1] = kzalloc(sizeof(*aux_bus->aux_device_wrapper[1]), GFP_KERNEL); - if (!aux_bus->aux_device_wrapper[1]) - return -ENOMEM; + if (!aux_bus->aux_device_wrapper[1]) { + retval = -ENOMEM; + goto err_aux_dev_add_0; + } retval = ida_alloc(&gp_client_ida, GFP_KERNEL); if (retval < 0) @@ -111,6 +113,7 @@ static int gp_aux_bus_probe(struct pci_dev *pdev, const struct pci_device_id *id err_aux_dev_add_1: auxiliary_device_uninit(&aux_bus->aux_device_wrapper[1]->aux_dev); + goto err_aux_dev_add_0; err_aux_dev_init_1: ida_free(&gp_client_ida, aux_bus->aux_device_wrapper[1]->aux_dev.id); @@ -120,6 +123,7 @@ static int gp_aux_bus_probe(struct pci_dev *pdev, const struct pci_device_id *id err_aux_dev_add_0: auxiliary_device_uninit(&aux_bus->aux_device_wrapper[0]->aux_dev); + goto err_ret; err_aux_dev_init_0: ida_free(&gp_client_ida, aux_bus->aux_device_wrapper[0]->aux_dev.id); @@ -127,6 +131,7 @@ static int gp_aux_bus_probe(struct pci_dev *pdev, const struct pci_device_id *id err_ida_alloc_0: kfree(aux_bus->aux_device_wrapper[0]); +err_ret: return retval; } diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index aac36750d2c54..c3a6657dcd4a2 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -115,6 +115,8 @@ #define MEI_DEV_ID_ARL_S 0x7F68 /* Arrow Lake Point S */ #define MEI_DEV_ID_ARL_H 0x7770 /* Arrow Lake Point H */ +#define MEI_DEV_ID_LNL_M 0xA870 /* Lunar Lake Point M */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 8cf636c540322..ac3ad92622766 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -24,6 +24,9 @@ #include "hw-me-regs.h" #include "hw-me.h" +static bool disable_msi; +module_param(disable_msi, bool, 0); + /* mei_pci_tbl - PCI Device ID Table */ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_82946GZ, MEI_ME_ICH_CFG)}, @@ -116,12 +119,14 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ADP_P, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ADP_N, MEI_ME_PCH15_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)}, + /* required last entry */ {0, } }; @@ -216,7 +221,8 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->mem_addr = pcim_iomap_table(pdev)[0]; hw->read_fws = mei_me_read_fws; - pci_enable_msi(pdev); + if (!disable_msi) + pci_enable_msi(pdev); hw->irq = pdev->irq; @@ -398,8 +404,10 @@ static int mei_me_pci_resume(struct device *device) } err = mei_restart(dev); - if (err) + if (err) { + free_irq(pdev->irq, dev); return err; + } /* Start timer if stopped in suspend */ schedule_delayed_work(&dev->timer_work, HZ); diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c index 8d303c6c00006..a59fb5a13bdc4 100644 --- a/drivers/misc/mei/platform-vsc.c +++ b/drivers/misc/mei/platform-vsc.c @@ -28,8 +28,8 @@ #define MEI_VSC_MAX_MSG_SIZE 512 -#define MEI_VSC_POLL_DELAY_US (50 * USEC_PER_MSEC) -#define MEI_VSC_POLL_TIMEOUT_US (200 * USEC_PER_MSEC) +#define MEI_VSC_POLL_DELAY_US (100 * USEC_PER_MSEC) +#define MEI_VSC_POLL_TIMEOUT_US (400 * USEC_PER_MSEC) #define mei_dev_to_vsc_hw(dev) ((struct mei_vsc_hw *)((dev)->hw)) @@ -401,24 +401,30 @@ static int mei_vsc_remove(struct platform_device *pdev) static int mei_vsc_suspend(struct device *dev) { - struct mei_device *mei_dev = dev_get_drvdata(dev); + struct mei_device *mei_dev; + int ret = 0; - mei_stop(mei_dev); + mei_dev = dev_get_drvdata(dev); + if (!mei_dev) + return -ENODEV; - return 0; + mutex_lock(&mei_dev->device_lock); + + if (!mei_write_is_idle(mei_dev)) + ret = -EAGAIN; + + mutex_unlock(&mei_dev->device_lock); + + return ret; } static int mei_vsc_resume(struct device *dev) { - struct mei_device *mei_dev = dev_get_drvdata(dev); - int ret; - - ret = mei_restart(mei_dev); - if (ret) - return ret; + struct mei_device *mei_dev; - /* start timer if stopped in suspend */ - schedule_delayed_work(&mei_dev->timer_work, HZ); + mei_dev = dev_get_drvdata(dev); + if (!mei_dev) + return -ENODEV; return 0; } diff --git a/drivers/misc/mei/vsc-fw-loader.c b/drivers/misc/mei/vsc-fw-loader.c index ffa4ccd96a104..596a9d695dfc1 100644 --- a/drivers/misc/mei/vsc-fw-loader.c +++ b/drivers/misc/mei/vsc-fw-loader.c @@ -252,7 +252,7 @@ static int vsc_get_sensor_name(struct vsc_fw_loader *fw_loader, { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER }; union acpi_object obj = { - .type = ACPI_TYPE_INTEGER, + .integer.type = ACPI_TYPE_INTEGER, .integer.value = 1, }; struct acpi_object_list arg_list = { diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c index 55f7db490d3bb..941f5b3df72f6 100644 --- a/drivers/misc/mei/vsc-tp.c +++ b/drivers/misc/mei/vsc-tp.c @@ -25,7 +25,8 @@ #define VSC_TP_ROM_BOOTUP_DELAY_MS 10 #define VSC_TP_ROM_XFER_POLL_TIMEOUT_US (500 * USEC_PER_MSEC) #define VSC_TP_ROM_XFER_POLL_DELAY_US (20 * USEC_PER_MSEC) -#define VSC_TP_WAIT_FW_ASSERTED_TIMEOUT (2 * HZ) +#define VSC_TP_WAIT_FW_POLL_TIMEOUT (2 * HZ) +#define VSC_TP_WAIT_FW_POLL_DELAY_US (20 * USEC_PER_MSEC) #define VSC_TP_MAX_XFER_COUNT 5 #define VSC_TP_PACKET_SYNC 0x31 @@ -93,6 +94,27 @@ static const struct acpi_gpio_mapping vsc_tp_acpi_gpios[] = { {} }; +static irqreturn_t vsc_tp_isr(int irq, void *data) +{ + struct vsc_tp *tp = data; + + atomic_inc(&tp->assert_cnt); + + wake_up(&tp->xfer_wait); + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t vsc_tp_thread_isr(int irq, void *data) +{ + struct vsc_tp *tp = data; + + if (tp->event_notify) + tp->event_notify(tp->event_notify_context); + + return IRQ_HANDLED; +} + /* wakeup firmware and wait for response */ static int vsc_tp_wakeup_request(struct vsc_tp *tp) { @@ -101,13 +123,15 @@ static int vsc_tp_wakeup_request(struct vsc_tp *tp) gpiod_set_value_cansleep(tp->wakeupfw, 0); ret = wait_event_timeout(tp->xfer_wait, - atomic_read(&tp->assert_cnt) && - gpiod_get_value_cansleep(tp->wakeuphost), - VSC_TP_WAIT_FW_ASSERTED_TIMEOUT); + atomic_read(&tp->assert_cnt), + VSC_TP_WAIT_FW_POLL_TIMEOUT); if (!ret) return -ETIMEDOUT; - return 0; + return read_poll_timeout(gpiod_get_value_cansleep, ret, ret, + VSC_TP_WAIT_FW_POLL_DELAY_US, + VSC_TP_WAIT_FW_POLL_TIMEOUT, false, + tp->wakeuphost); } static void vsc_tp_wakeup_release(struct vsc_tp *tp) @@ -307,12 +331,12 @@ int vsc_tp_rom_xfer(struct vsc_tp *tp, const void *obuf, void *ibuf, size_t len) return ret; } - ret = vsc_tp_dev_xfer(tp, tp->tx_buf, tp->rx_buf, len); + ret = vsc_tp_dev_xfer(tp, tp->tx_buf, ibuf ? tp->rx_buf : ibuf, len); if (ret) return ret; if (ibuf) - cpu_to_be32_array(ibuf, tp->rx_buf, words); + be32_to_cpu_array(ibuf, tp->rx_buf, words); return ret; } @@ -380,6 +404,37 @@ int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb, } EXPORT_SYMBOL_NS_GPL(vsc_tp_register_event_cb, VSC_TP); +/** + * vsc_tp_request_irq - request irq for vsc_tp device + * @tp: vsc_tp device handle + */ +int vsc_tp_request_irq(struct vsc_tp *tp) +{ + struct spi_device *spi = tp->spi; + struct device *dev = &spi->dev; + int ret; + + irq_set_status_flags(spi->irq, IRQ_DISABLE_UNLAZY); + ret = request_threaded_irq(spi->irq, vsc_tp_isr, vsc_tp_thread_isr, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + dev_name(dev), tp); + if (ret) + return ret; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(vsc_tp_request_irq, VSC_TP); + +/** + * vsc_tp_free_irq - free irq for vsc_tp device + * @tp: vsc_tp device handle + */ +void vsc_tp_free_irq(struct vsc_tp *tp) +{ + free_irq(tp->spi->irq, tp); +} +EXPORT_SYMBOL_NS_GPL(vsc_tp_free_irq, VSC_TP); + /** * vsc_tp_intr_synchronize - synchronize vsc_tp interrupt * @tp: vsc_tp device handle @@ -410,27 +465,6 @@ void vsc_tp_intr_disable(struct vsc_tp *tp) } EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_disable, VSC_TP); -static irqreturn_t vsc_tp_isr(int irq, void *data) -{ - struct vsc_tp *tp = data; - - atomic_inc(&tp->assert_cnt); - - wake_up(&tp->xfer_wait); - - return IRQ_WAKE_THREAD; -} - -static irqreturn_t vsc_tp_thread_isr(int irq, void *data) -{ - struct vsc_tp *tp = data; - - if (tp->event_notify) - tp->event_notify(tp->event_notify_context); - - return IRQ_HANDLED; -} - static int vsc_tp_match_any(struct acpi_device *adev, void *data) { struct acpi_device **__adev = data; @@ -482,10 +516,9 @@ static int vsc_tp_probe(struct spi_device *spi) tp->spi = spi; irq_set_status_flags(spi->irq, IRQ_DISABLE_UNLAZY); - ret = devm_request_threaded_irq(dev, spi->irq, vsc_tp_isr, - vsc_tp_thread_isr, - IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - dev_name(dev), tp); + ret = request_threaded_irq(spi->irq, vsc_tp_isr, vsc_tp_thread_isr, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + dev_name(dev), tp); if (ret) return ret; @@ -519,6 +552,8 @@ static int vsc_tp_probe(struct spi_device *spi) err_destroy_lock: mutex_destroy(&tp->mutex); + free_irq(spi->irq, tp); + return ret; } @@ -529,6 +564,21 @@ static void vsc_tp_remove(struct spi_device *spi) platform_device_unregister(tp->pdev); mutex_destroy(&tp->mutex); + + free_irq(spi->irq, tp); +} + +static void vsc_tp_shutdown(struct spi_device *spi) +{ + struct vsc_tp *tp = spi_get_drvdata(spi); + + platform_device_unregister(tp->pdev); + + mutex_destroy(&tp->mutex); + + vsc_tp_reset(tp); + + free_irq(spi->irq, tp); } static const struct acpi_device_id vsc_tp_acpi_ids[] = { @@ -543,6 +593,7 @@ MODULE_DEVICE_TABLE(acpi, vsc_tp_acpi_ids); static struct spi_driver vsc_tp_driver = { .probe = vsc_tp_probe, .remove = vsc_tp_remove, + .shutdown = vsc_tp_shutdown, .driver = { .name = "vsc-tp", .acpi_match_table = vsc_tp_acpi_ids, diff --git a/drivers/misc/mei/vsc-tp.h b/drivers/misc/mei/vsc-tp.h index f9513ddc3e409..14ca195cbddcc 100644 --- a/drivers/misc/mei/vsc-tp.h +++ b/drivers/misc/mei/vsc-tp.h @@ -37,6 +37,9 @@ int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen, int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb, void *context); +int vsc_tp_request_irq(struct vsc_tp *tp); +void vsc_tp_free_irq(struct vsc_tp *tp); + void vsc_tp_intr_enable(struct vsc_tp *tp); void vsc_tp_intr_disable(struct vsc_tp *tp); void vsc_tp_intr_synchronize(struct vsc_tp *tp); diff --git a/drivers/misc/pvpanic/pvpanic-pci.c b/drivers/misc/pvpanic/pvpanic-pci.c index 9ad20e82785bc..b21598a18f6da 100644 --- a/drivers/misc/pvpanic/pvpanic-pci.c +++ b/drivers/misc/pvpanic/pvpanic-pci.c @@ -44,8 +44,6 @@ static struct pci_driver pvpanic_pci_driver = { .name = "pvpanic-pci", .id_table = pvpanic_pci_id_tbl, .probe = pvpanic_pci_probe, - .driver = { - .dev_groups = pvpanic_dev_groups, - }, + .dev_groups = pvpanic_dev_groups, }; module_pci_driver(pvpanic_pci_driver); diff --git a/drivers/misc/vmw_vmci/vmci_datagram.c b/drivers/misc/vmw_vmci/vmci_datagram.c index f50d22882476f..a0ad1f3a69f7e 100644 --- a/drivers/misc/vmw_vmci/vmci_datagram.c +++ b/drivers/misc/vmw_vmci/vmci_datagram.c @@ -234,7 +234,8 @@ static int dg_dispatch_as_host(u32 context_id, struct vmci_datagram *dg) dg_info->in_dg_host_queue = true; dg_info->entry = dst_entry; - memcpy(&dg_info->msg, dg, dg_size); + dg_info->msg = *dg; + memcpy(&dg_info->msg_payload, dg + 1, dg->payload_size); INIT_WORK(&dg_info->work, dg_delayed_dispatch); schedule_work(&dg_info->work); @@ -377,7 +378,8 @@ int vmci_datagram_invoke_guest_handler(struct vmci_datagram *dg) dg_info->in_dg_host_queue = false; dg_info->entry = dst_entry; - memcpy(&dg_info->msg, dg, VMCI_DG_SIZE(dg)); + dg_info->msg = *dg; + memcpy(&dg_info->msg_payload, dg + 1, dg->payload_size); INIT_WORK(&dg_info->work, dg_delayed_dispatch); schedule_work(&dg_info->work); diff --git a/drivers/misc/vmw_vmci/vmci_event.c b/drivers/misc/vmw_vmci/vmci_event.c index 5d7ac07623c27..9a41ab65378de 100644 --- a/drivers/misc/vmw_vmci/vmci_event.c +++ b/drivers/misc/vmw_vmci/vmci_event.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -86,9 +87,12 @@ static void event_deliver(struct vmci_event_msg *event_msg) { struct vmci_subscription *cur; struct list_head *subscriber_list; + u32 sanitized_event, max_vmci_event; rcu_read_lock(); - subscriber_list = &subscriber_array[event_msg->event_data.event]; + max_vmci_event = ARRAY_SIZE(subscriber_array); + sanitized_event = array_index_nospec(event_msg->event_data.event, max_vmci_event); + subscriber_list = &subscriber_array[sanitized_event]; list_for_each_entry_rcu(cur, subscriber_list, node) { cur->callback(cur->id, &event_msg->event_data, cur->callback_data); diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c index 4f8d962bb5b2a..1300ccab3d21b 100644 --- a/drivers/misc/vmw_vmci/vmci_guest.c +++ b/drivers/misc/vmw_vmci/vmci_guest.c @@ -625,7 +625,8 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, if (!vmci_dev) { dev_err(&pdev->dev, "Can't allocate memory for VMCI device\n"); - return -ENOMEM; + error = -ENOMEM; + goto err_unmap_mmio_base; } vmci_dev->dev = &pdev->dev; @@ -642,7 +643,8 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, if (!vmci_dev->tx_buffer) { dev_err(&pdev->dev, "Can't allocate memory for datagram tx buffer\n"); - return -ENOMEM; + error = -ENOMEM; + goto err_unmap_mmio_base; } vmci_dev->data_buffer = dma_alloc_coherent(&pdev->dev, VMCI_DMA_DG_BUFFER_SIZE, @@ -893,6 +895,10 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, err_free_data_buffers: vmci_free_dg_buffers(vmci_dev); +err_unmap_mmio_base: + if (mmio_base != NULL) + pci_iounmap(pdev, mmio_base); + /* The rest are managed resources and will be freed by PCI core */ return error; } diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 32d49100dff51..3564a0f63c9c7 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -413,7 +413,7 @@ static struct mmc_blk_ioc_data *mmc_blk_ioctl_copy_from_user( struct mmc_blk_ioc_data *idata; int err; - idata = kmalloc(sizeof(*idata), GFP_KERNEL); + idata = kzalloc(sizeof(*idata), GFP_KERNEL); if (!idata) { err = -ENOMEM; goto out; @@ -488,7 +488,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, if (idata->flags & MMC_BLK_IOC_DROP) return 0; - if (idata->flags & MMC_BLK_IOC_SBC) + if (idata->flags & MMC_BLK_IOC_SBC && i > 0) prev_idata = idatas[i - 1]; /* @@ -874,10 +874,11 @@ static const struct block_device_operations mmc_bdops = { static int mmc_blk_part_switch_pre(struct mmc_card *card, unsigned int part_type) { - const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK; + const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if ((part_type & mask) == mask) { + if ((part_type & mask) == rpmb) { if (card->ext_csd.cmdq_en) { ret = mmc_cmdq_disable(card); if (ret) @@ -892,10 +893,11 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card, static int mmc_blk_part_switch_post(struct mmc_card *card, unsigned int part_type) { - const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK; + const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if ((part_type & mask) == mask) { + if ((part_type & mask) == rpmb) { mmc_retune_unpause(card->host); if (card->reenable_cmdq && !card->ext_csd.cmdq_en) ret = mmc_cmdq_enable(card); diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 39f45c2b6de8a..8791656e9e20d 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -221,6 +221,26 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, } EXPORT_SYMBOL(mmc_gpiod_request_cd); +/** + * mmc_gpiod_set_cd_config - set config for card-detection GPIO + * @host: mmc host + * @config: Generic pinconf config (from pinconf_to_config_packed()) + * + * This can be used by mmc host drivers to fixup a card-detection GPIO's config + * (e.g. set PIN_CONFIG_BIAS_PULL_UP) after acquiring the GPIO descriptor + * through mmc_gpiod_request_cd(). + * + * Returns: + * 0 on success, or a negative errno value on error. + */ +int mmc_gpiod_set_cd_config(struct mmc_host *host, unsigned long config) +{ + struct mmc_gpio *ctx = host->slot.handler_priv; + + return gpiod_set_config(ctx->cd_gpio, config); +} +EXPORT_SYMBOL(mmc_gpiod_set_cd_config); + bool mmc_can_gpio_cd(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c index ee3b1a4e08485..8fa6796787f4b 100644 --- a/drivers/mmc/host/davinci_mmc.c +++ b/drivers/mmc/host/davinci_mmc.c @@ -1344,7 +1344,7 @@ static int davinci_mmcsd_probe(struct platform_device *pdev) return ret; } -static void __exit davinci_mmcsd_remove(struct platform_device *pdev) +static void davinci_mmcsd_remove(struct platform_device *pdev) { struct mmc_davinci_host *host = platform_get_drvdata(pdev); @@ -1399,7 +1399,7 @@ static struct platform_driver davinci_mmcsd_driver = { .of_match_table = davinci_mmc_dt_ids, }, .probe = davinci_mmcsd_probe, - .remove_new = __exit_p(davinci_mmcsd_remove), + .remove_new = davinci_mmcsd_remove, .id_table = davinci_mmc_devtype, }; diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c index 9fb8995b43a1c..13fa8588e38c1 100644 --- a/drivers/mmc/host/omap.c +++ b/drivers/mmc/host/omap.c @@ -1119,10 +1119,25 @@ static void mmc_omap_set_power(struct mmc_omap_slot *slot, int power_on, host = slot->host; - if (slot->vsd) - gpiod_set_value(slot->vsd, power_on); - if (slot->vio) - gpiod_set_value(slot->vio, power_on); + if (power_on) { + if (slot->vsd) { + gpiod_set_value(slot->vsd, power_on); + msleep(1); + } + if (slot->vio) { + gpiod_set_value(slot->vio, power_on); + msleep(1); + } + } else { + if (slot->vio) { + gpiod_set_value(slot->vio, power_on); + msleep(50); + } + if (slot->vsd) { + gpiod_set_value(slot->vsd, power_on); + msleep(50); + } + } if (slot->pdata->set_power != NULL) slot->pdata->set_power(mmc_dev(slot->mmc), slot->id, power_on, @@ -1259,18 +1274,18 @@ static int mmc_omap_new_slot(struct mmc_omap_host *host, int id) slot->pdata = &host->pdata->slots[id]; /* Check for some optional GPIO controls */ - slot->vsd = gpiod_get_index_optional(host->dev, "vsd", - id, GPIOD_OUT_LOW); + slot->vsd = devm_gpiod_get_index_optional(host->dev, "vsd", + id, GPIOD_OUT_LOW); if (IS_ERR(slot->vsd)) return dev_err_probe(host->dev, PTR_ERR(slot->vsd), "error looking up VSD GPIO\n"); - slot->vio = gpiod_get_index_optional(host->dev, "vio", - id, GPIOD_OUT_LOW); + slot->vio = devm_gpiod_get_index_optional(host->dev, "vio", + id, GPIOD_OUT_LOW); if (IS_ERR(slot->vio)) return dev_err_probe(host->dev, PTR_ERR(slot->vio), "error looking up VIO GPIO\n"); - slot->cover = gpiod_get_index_optional(host->dev, "cover", - id, GPIOD_IN); + slot->cover = devm_gpiod_get_index_optional(host->dev, "cover", + id, GPIOD_IN); if (IS_ERR(slot->cover)) return dev_err_probe(host->dev, PTR_ERR(slot->cover), "error looking up cover switch GPIO\n"); @@ -1384,13 +1399,6 @@ static int mmc_omap_probe(struct platform_device *pdev) if (IS_ERR(host->virt_base)) return PTR_ERR(host->virt_base); - host->slot_switch = gpiod_get_optional(host->dev, "switch", - GPIOD_OUT_LOW); - if (IS_ERR(host->slot_switch)) - return dev_err_probe(host->dev, PTR_ERR(host->slot_switch), - "error looking up slot switch GPIO\n"); - - INIT_WORK(&host->slot_release_work, mmc_omap_slot_release_work); INIT_WORK(&host->send_stop_work, mmc_omap_send_stop_work); @@ -1409,6 +1417,12 @@ static int mmc_omap_probe(struct platform_device *pdev) host->dev = &pdev->dev; platform_set_drvdata(pdev, host); + host->slot_switch = devm_gpiod_get_optional(host->dev, "switch", + GPIOD_OUT_LOW); + if (IS_ERR(host->slot_switch)) + return dev_err_probe(host->dev, PTR_ERR(host->slot_switch), + "error looking up slot switch GPIO\n"); + host->id = pdev->id; host->irq = irq; host->phys_base = res->start; diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index acf5fc3ad7e41..eb8f427f9770d 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -80,6 +81,8 @@ struct sdhci_acpi_host { enum { DMI_QUIRK_RESET_SD_SIGNAL_VOLT_ON_SUSP = BIT(0), DMI_QUIRK_SD_NO_WRITE_PROTECT = BIT(1), + DMI_QUIRK_SD_CD_ACTIVE_HIGH = BIT(2), + DMI_QUIRK_SD_CD_ENABLE_PULL_UP = BIT(3), }; static inline void *sdhci_acpi_priv(struct sdhci_acpi_host *c) @@ -719,7 +722,28 @@ static const struct acpi_device_id sdhci_acpi_ids[] = { }; MODULE_DEVICE_TABLE(acpi, sdhci_acpi_ids); +/* Please keep this list sorted alphabetically */ static const struct dmi_system_id sdhci_acpi_quirks[] = { + { + /* + * The Acer Aspire Switch 10 (SW5-012) microSD slot always + * reports the card being write-protected even though microSD + * cards do not have a write-protect switch at all. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"), + }, + .driver_data = (void *)DMI_QUIRK_SD_NO_WRITE_PROTECT, + }, + { + /* Asus T100TA, needs pull-up for cd but DSDT GpioInt has NoPull set */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T100TA"), + }, + .driver_data = (void *)DMI_QUIRK_SD_CD_ENABLE_PULL_UP, + }, { /* * The Lenovo Miix 320-10ICR has a bug in the _PS0 method of @@ -736,15 +760,23 @@ static const struct dmi_system_id sdhci_acpi_quirks[] = { }, { /* - * The Acer Aspire Switch 10 (SW5-012) microSD slot always - * reports the card being write-protected even though microSD - * cards do not have a write-protect switch at all. + * Lenovo Yoga Tablet 2 Pro 1380F/L (13" Android version) this + * has broken WP reporting and an inverted CD signal. + * Note this has more or less the same BIOS as the Lenovo Yoga + * Tablet 2 830F/L or 1050F/L (8" and 10" Android), but unlike + * the 830 / 1050 models which share the same mainboard this + * model has a different mainboard and the inverted CD and + * broken WP are unique to this board. */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"), + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corp."), + DMI_MATCH(DMI_PRODUCT_NAME, "VALLEYVIEW C0 PLATFORM"), + DMI_MATCH(DMI_BOARD_NAME, "BYT-T FFD8"), + /* Full match so as to NOT match the 830/1050 BIOS */ + DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21.X64.0005.R00.1504101516"), }, - .driver_data = (void *)DMI_QUIRK_SD_NO_WRITE_PROTECT, + .driver_data = (void *)(DMI_QUIRK_SD_NO_WRITE_PROTECT | + DMI_QUIRK_SD_CD_ACTIVE_HIGH), }, { /* @@ -757,6 +789,17 @@ static const struct dmi_system_id sdhci_acpi_quirks[] = { }, .driver_data = (void *)DMI_QUIRK_SD_NO_WRITE_PROTECT, }, + { + /* + * The Toshiba WT10-A's microSD slot always reports the card being + * write-protected. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "TOSHIBA WT10-A"), + }, + .driver_data = (void *)DMI_QUIRK_SD_NO_WRITE_PROTECT, + }, {} /* Terminating entry */ }; @@ -866,12 +909,18 @@ static int sdhci_acpi_probe(struct platform_device *pdev) if (sdhci_acpi_flag(c, SDHCI_ACPI_SD_CD)) { bool v = sdhci_acpi_flag(c, SDHCI_ACPI_SD_CD_OVERRIDE_LEVEL); + if (quirks & DMI_QUIRK_SD_CD_ACTIVE_HIGH) + host->mmc->caps2 |= MMC_CAP2_CD_ACTIVE_HIGH; + err = mmc_gpiod_request_cd(host->mmc, NULL, 0, v, 0); if (err) { if (err == -EPROBE_DEFER) goto err_free; dev_warn(dev, "failed to setup card detect gpio\n"); c->use_runtime_pm = false; + } else if (quirks & DMI_QUIRK_SD_CD_ENABLE_PULL_UP) { + mmc_gpiod_set_cd_config(host->mmc, + PIN_CONF_PACKED(PIN_CONFIG_BIAS_PULL_UP, 20000)); } if (quirks & DMI_QUIRK_RESET_SD_SIGNAL_VOLT_ON_SUSP) diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 668e0aceeebac..e113b99a3eab5 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2694,6 +2694,11 @@ static __maybe_unused int sdhci_msm_runtime_suspend(struct device *dev) struct sdhci_host *host = dev_get_drvdata(dev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); + unsigned long flags; + + spin_lock_irqsave(&host->lock, flags); + host->runtime_suspended = true; + spin_unlock_irqrestore(&host->lock, flags); /* Drop the performance vote */ dev_pm_opp_set_rate(dev, 0); @@ -2708,6 +2713,7 @@ static __maybe_unused int sdhci_msm_runtime_resume(struct device *dev) struct sdhci_host *host = dev_get_drvdata(dev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); + unsigned long flags; int ret; ret = clk_bulk_prepare_enable(ARRAY_SIZE(msm_host->bulk_clks), @@ -2726,7 +2732,15 @@ static __maybe_unused int sdhci_msm_runtime_resume(struct device *dev) dev_pm_opp_set_rate(dev, msm_host->clk_rate); - return sdhci_msm_ice_resume(msm_host); + ret = sdhci_msm_ice_resume(msm_host); + if (ret) + return ret; + + spin_lock_irqsave(&host->lock, flags); + host->runtime_suspended = false; + spin_unlock_irqrestore(&host->lock, flags); + + return ret; } static const struct dev_pm_ops sdhci_msm_pm_ops = { diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index a1f57af6acfb0..60b42126a4edb 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -612,6 +612,7 @@ static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode) /* perform tuning */ sdhci_start_tuning(host); + host->tuning_loop_count = 128; host->tuning_err = __sdhci_execute_tuning(host, opcode); if (host->tuning_err) { /* disable auto-tuning upon tuning error */ @@ -933,6 +934,17 @@ static int dwcmshc_probe(struct platform_device *pdev) return err; } +static void dwcmshc_disable_card_clk(struct sdhci_host *host) +{ + u16 ctrl; + + ctrl = sdhci_readw(host, SDHCI_CLOCK_CONTROL); + if (ctrl & SDHCI_CLOCK_CARD_EN) { + ctrl &= ~SDHCI_CLOCK_CARD_EN; + sdhci_writew(host, ctrl, SDHCI_CLOCK_CONTROL); + } +} + static void dwcmshc_remove(struct platform_device *pdev) { struct sdhci_host *host = platform_get_drvdata(pdev); @@ -940,8 +952,14 @@ static void dwcmshc_remove(struct platform_device *pdev) struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host); struct rk35xx_priv *rk_priv = priv->priv; + pm_runtime_get_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + sdhci_remove_host(host, 0); + dwcmshc_disable_card_clk(host); + clk_disable_unprepare(pltfm_host->clk); clk_disable_unprepare(priv->bus_clk); if (rk_priv) @@ -1033,17 +1051,6 @@ static void dwcmshc_enable_card_clk(struct sdhci_host *host) } } -static void dwcmshc_disable_card_clk(struct sdhci_host *host) -{ - u16 ctrl; - - ctrl = sdhci_readw(host, SDHCI_CLOCK_CONTROL); - if (ctrl & SDHCI_CLOCK_CARD_EN) { - ctrl &= ~SDHCI_CLOCK_CARD_EN; - sdhci_writew(host, ctrl, SDHCI_CLOCK_CONTROL); - } -} - static int dwcmshc_runtime_suspend(struct device *dev) { struct sdhci_host *host = dev_get_drvdata(dev); diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index e78faef67d7ab..94076b0955719 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -1439,6 +1439,9 @@ static int __maybe_unused sdhci_omap_runtime_suspend(struct device *dev) struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host); + if (host->tuning_mode != SDHCI_TUNING_MODE_3) + mmc_retune_needed(host->mmc); + if (omap_host->con != -EINVAL) sdhci_runtime_suspend_host(host); diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index c79f73459915d..746f4cf7ab033 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -3439,12 +3439,18 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask) host->data->error = -EILSEQ; if (!mmc_op_tuning(SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND)))) sdhci_err_stats_inc(host, DAT_CRC); - } else if ((intmask & SDHCI_INT_DATA_CRC) && + } else if ((intmask & (SDHCI_INT_DATA_CRC | SDHCI_INT_TUNING_ERROR)) && SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND)) != MMC_BUS_TEST_R) { host->data->error = -EILSEQ; if (!mmc_op_tuning(SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND)))) sdhci_err_stats_inc(host, DAT_CRC); + if (intmask & SDHCI_INT_TUNING_ERROR) { + u16 ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2); + + ctrl2 &= ~SDHCI_CTRL_TUNED_CLK; + sdhci_writew(host, ctrl2, SDHCI_HOST_CONTROL2); + } } else if (intmask & SDHCI_INT_ADMA_ERROR) { pr_err("%s: ADMA error: 0x%08x\n", mmc_hostname(host->mmc), intmask); @@ -3979,7 +3985,7 @@ bool sdhci_cqe_irq(struct sdhci_host *host, u32 intmask, int *cmd_error, } else *cmd_error = 0; - if (intmask & (SDHCI_INT_DATA_END_BIT | SDHCI_INT_DATA_CRC)) { + if (intmask & (SDHCI_INT_DATA_END_BIT | SDHCI_INT_DATA_CRC | SDHCI_INT_TUNING_ERROR)) { *data_error = -EILSEQ; if (!mmc_op_tuning(SDHCI_GET_CMD(sdhci_readw(host, SDHCI_COMMAND)))) sdhci_err_stats_inc(host, DAT_CRC); diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index a20864fc06412..957c7a917ffb7 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -158,6 +158,7 @@ #define SDHCI_INT_BUS_POWER 0x00800000 #define SDHCI_INT_AUTO_CMD_ERR 0x01000000 #define SDHCI_INT_ADMA_ERROR 0x02000000 +#define SDHCI_INT_TUNING_ERROR 0x04000000 #define SDHCI_INT_NORMAL_MASK 0x00007FFF #define SDHCI_INT_ERROR_MASK 0xFFFF8000 @@ -169,7 +170,7 @@ SDHCI_INT_DATA_AVAIL | SDHCI_INT_SPACE_AVAIL | \ SDHCI_INT_DATA_TIMEOUT | SDHCI_INT_DATA_CRC | \ SDHCI_INT_DATA_END_BIT | SDHCI_INT_ADMA_ERROR | \ - SDHCI_INT_BLK_GAP) + SDHCI_INT_BLK_GAP | SDHCI_INT_TUNING_ERROR) #define SDHCI_INT_ALL_MASK ((unsigned int)-1) #define SDHCI_CQE_INT_ERR_MASK ( \ diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index d659c59422e1e..562034af653eb 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -143,16 +143,24 @@ struct sdhci_am654_data { struct regmap *base; int otap_del_sel[ARRAY_SIZE(td)]; int itap_del_sel[ARRAY_SIZE(td)]; + u32 itap_del_ena[ARRAY_SIZE(td)]; int clkbuf_sel; int trm_icp; int drv_strength; int strb_sel; u32 flags; u32 quirks; + bool dll_enable; #define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0) }; +struct window { + u8 start; + u8 end; + u8 length; +}; + struct sdhci_am654_driver_data { const struct sdhci_pltfm_data *pdata; u32 flags; @@ -232,11 +240,13 @@ static void sdhci_am654_setup_dll(struct sdhci_host *host, unsigned int clock) } static void sdhci_am654_write_itapdly(struct sdhci_am654_data *sdhci_am654, - u32 itapdly) + u32 itapdly, u32 enable) { /* Set ITAPCHGWIN before writing to ITAPDLY */ regmap_update_bits(sdhci_am654->base, PHY_CTRL4, ITAPCHGWIN_MASK, 1 << ITAPCHGWIN_SHIFT); + regmap_update_bits(sdhci_am654->base, PHY_CTRL4, ITAPDLYENA_MASK, + enable << ITAPDLYENA_SHIFT); regmap_update_bits(sdhci_am654->base, PHY_CTRL4, ITAPDLYSEL_MASK, itapdly << ITAPDLYSEL_SHIFT); regmap_update_bits(sdhci_am654->base, PHY_CTRL4, ITAPCHGWIN_MASK, 0); @@ -253,8 +263,8 @@ static void sdhci_am654_setup_delay_chain(struct sdhci_am654_data *sdhci_am654, mask = SELDLYTXCLK_MASK | SELDLYRXCLK_MASK; regmap_update_bits(sdhci_am654->base, PHY_CTRL5, mask, val); - sdhci_am654_write_itapdly(sdhci_am654, - sdhci_am654->itap_del_sel[timing]); + sdhci_am654_write_itapdly(sdhci_am654, sdhci_am654->itap_del_sel[timing], + sdhci_am654->itap_del_ena[timing]); } static void sdhci_am654_set_clock(struct sdhci_host *host, unsigned int clock) @@ -263,7 +273,6 @@ static void sdhci_am654_set_clock(struct sdhci_host *host, unsigned int clock) struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); unsigned char timing = host->mmc->ios.timing; u32 otap_del_sel; - u32 otap_del_ena; u32 mask, val; regmap_update_bits(sdhci_am654->base, PHY_CTRL1, ENDLL_MASK, 0); @@ -272,10 +281,9 @@ static void sdhci_am654_set_clock(struct sdhci_host *host, unsigned int clock) /* Setup DLL Output TAP delay */ otap_del_sel = sdhci_am654->otap_del_sel[timing]; - otap_del_ena = (timing > MMC_TIMING_UHS_SDR25) ? 1 : 0; mask = OTAPDLYENA_MASK | OTAPDLYSEL_MASK; - val = (otap_del_ena << OTAPDLYENA_SHIFT) | + val = (0x1 << OTAPDLYENA_SHIFT) | (otap_del_sel << OTAPDLYSEL_SHIFT); /* Write to STRBSEL for HS400 speed mode */ @@ -290,10 +298,21 @@ static void sdhci_am654_set_clock(struct sdhci_host *host, unsigned int clock) regmap_update_bits(sdhci_am654->base, PHY_CTRL4, mask, val); - if (timing > MMC_TIMING_UHS_SDR25 && clock >= CLOCK_TOO_SLOW_HZ) + if (timing > MMC_TIMING_UHS_SDR25 && clock >= CLOCK_TOO_SLOW_HZ) { sdhci_am654_setup_dll(host, clock); - else + sdhci_am654->dll_enable = true; + + if (timing == MMC_TIMING_MMC_HS400) { + sdhci_am654->itap_del_ena[timing] = 0x1; + sdhci_am654->itap_del_sel[timing] = sdhci_am654->itap_del_sel[timing - 1]; + } + + sdhci_am654_write_itapdly(sdhci_am654, sdhci_am654->itap_del_sel[timing], + sdhci_am654->itap_del_ena[timing]); + } else { sdhci_am654_setup_delay_chain(sdhci_am654, timing); + sdhci_am654->dll_enable = false; + } regmap_update_bits(sdhci_am654->base, PHY_CTRL5, CLKBUFSEL_MASK, sdhci_am654->clkbuf_sel); @@ -306,6 +325,8 @@ static void sdhci_j721e_4bit_set_clock(struct sdhci_host *host, struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); unsigned char timing = host->mmc->ios.timing; u32 otap_del_sel; + u32 itap_del_ena; + u32 itap_del_sel; u32 mask, val; /* Setup DLL Output TAP delay */ @@ -314,8 +335,19 @@ static void sdhci_j721e_4bit_set_clock(struct sdhci_host *host, mask = OTAPDLYENA_MASK | OTAPDLYSEL_MASK; val = (0x1 << OTAPDLYENA_SHIFT) | (otap_del_sel << OTAPDLYSEL_SHIFT); - regmap_update_bits(sdhci_am654->base, PHY_CTRL4, mask, val); + /* Setup Input TAP delay */ + itap_del_ena = sdhci_am654->itap_del_ena[timing]; + itap_del_sel = sdhci_am654->itap_del_sel[timing]; + + mask |= ITAPDLYENA_MASK | ITAPDLYSEL_MASK; + val |= (itap_del_ena << ITAPDLYENA_SHIFT) | + (itap_del_sel << ITAPDLYSEL_SHIFT); + + regmap_update_bits(sdhci_am654->base, PHY_CTRL4, ITAPCHGWIN_MASK, + 1 << ITAPCHGWIN_SHIFT); + regmap_update_bits(sdhci_am654->base, PHY_CTRL4, mask, val); + regmap_update_bits(sdhci_am654->base, PHY_CTRL4, ITAPCHGWIN_MASK, 0); regmap_update_bits(sdhci_am654->base, PHY_CTRL5, CLKBUFSEL_MASK, sdhci_am654->clkbuf_sel); @@ -408,40 +440,105 @@ static u32 sdhci_am654_cqhci_irq(struct sdhci_host *host, u32 intmask) return 0; } -#define ITAP_MAX 32 +#define ITAPDLY_LENGTH 32 +#define ITAPDLY_LAST_INDEX (ITAPDLY_LENGTH - 1) + +static u32 sdhci_am654_calculate_itap(struct sdhci_host *host, struct window + *fail_window, u8 num_fails, bool circular_buffer) +{ + u8 itap = 0, start_fail = 0, end_fail = 0, pass_length = 0; + u8 first_fail_start = 0, last_fail_end = 0; + struct device *dev = mmc_dev(host->mmc); + struct window pass_window = {0, 0, 0}; + int prev_fail_end = -1; + u8 i; + + if (!num_fails) + return ITAPDLY_LAST_INDEX >> 1; + + if (fail_window->length == ITAPDLY_LENGTH) { + dev_err(dev, "No passing ITAPDLY, return 0\n"); + return 0; + } + + first_fail_start = fail_window->start; + last_fail_end = fail_window[num_fails - 1].end; + + for (i = 0; i < num_fails; i++) { + start_fail = fail_window[i].start; + end_fail = fail_window[i].end; + pass_length = start_fail - (prev_fail_end + 1); + + if (pass_length > pass_window.length) { + pass_window.start = prev_fail_end + 1; + pass_window.length = pass_length; + } + prev_fail_end = end_fail; + } + + if (!circular_buffer) + pass_length = ITAPDLY_LAST_INDEX - last_fail_end; + else + pass_length = ITAPDLY_LAST_INDEX - last_fail_end + first_fail_start; + + if (pass_length > pass_window.length) { + pass_window.start = last_fail_end + 1; + pass_window.length = pass_length; + } + + if (!circular_buffer) + itap = pass_window.start + (pass_window.length >> 1); + else + itap = (pass_window.start + (pass_window.length >> 1)) % ITAPDLY_LENGTH; + + return (itap > ITAPDLY_LAST_INDEX) ? ITAPDLY_LAST_INDEX >> 1 : itap; +} + static int sdhci_am654_platform_execute_tuning(struct sdhci_host *host, u32 opcode) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); - int cur_val, prev_val = 1, fail_len = 0, pass_window = 0, pass_len; - u32 itap; + unsigned char timing = host->mmc->ios.timing; + struct window fail_window[ITAPDLY_LENGTH]; + u8 curr_pass, itap; + u8 fail_index = 0; + u8 prev_pass = 1; + + memset(fail_window, 0, sizeof(fail_window)); /* Enable ITAPDLY */ - regmap_update_bits(sdhci_am654->base, PHY_CTRL4, ITAPDLYENA_MASK, - 1 << ITAPDLYENA_SHIFT); + sdhci_am654->itap_del_ena[timing] = 0x1; + + for (itap = 0; itap < ITAPDLY_LENGTH; itap++) { + sdhci_am654_write_itapdly(sdhci_am654, itap, sdhci_am654->itap_del_ena[timing]); - for (itap = 0; itap < ITAP_MAX; itap++) { - sdhci_am654_write_itapdly(sdhci_am654, itap); + curr_pass = !mmc_send_tuning(host->mmc, opcode, NULL); - cur_val = !mmc_send_tuning(host->mmc, opcode, NULL); - if (cur_val && !prev_val) - pass_window = itap; + if (!curr_pass && prev_pass) + fail_window[fail_index].start = itap; - if (!cur_val) - fail_len++; + if (!curr_pass) { + fail_window[fail_index].end = itap; + fail_window[fail_index].length++; + } + + if (curr_pass && !prev_pass) + fail_index++; - prev_val = cur_val; + prev_pass = curr_pass; } - /* - * Having determined the length of the failing window and start of - * the passing window calculate the length of the passing window and - * set the final value halfway through it considering the range as a - * circular buffer - */ - pass_len = ITAP_MAX - fail_len; - itap = (pass_window + (pass_len >> 1)) % ITAP_MAX; - sdhci_am654_write_itapdly(sdhci_am654, itap); + + if (fail_window[fail_index].length != 0) + fail_index++; + + itap = sdhci_am654_calculate_itap(host, fail_window, fail_index, + sdhci_am654->dll_enable); + + sdhci_am654_write_itapdly(sdhci_am654, itap, sdhci_am654->itap_del_ena[timing]); + + /* Save ITAPDLY */ + sdhci_am654->itap_del_sel[timing] = itap; return 0; } @@ -590,9 +687,12 @@ static int sdhci_am654_get_otap_delay(struct sdhci_host *host, host->mmc->caps2 &= ~td[i].capability; } - if (td[i].itap_binding) - device_property_read_u32(dev, td[i].itap_binding, - &sdhci_am654->itap_del_sel[i]); + if (td[i].itap_binding) { + ret = device_property_read_u32(dev, td[i].itap_binding, + &sdhci_am654->itap_del_sel[i]); + if (!ret) + sdhci_am654->itap_del_ena[i] = 0x1; + } } return 0; diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index be7f18fd4836a..c253d176db691 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -259,6 +259,8 @@ static void tmio_mmc_reset_work(struct work_struct *work) else mrq->cmd->error = -ETIMEDOUT; + /* No new calls yet, but disallow concurrent tmio_mmc_done_work() */ + host->mrq = ERR_PTR(-EBUSY); host->cmd = NULL; host->data = NULL; diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c index 77d5f1d244899..860380931b6cd 100644 --- a/drivers/mmc/host/wmt-sdmmc.c +++ b/drivers/mmc/host/wmt-sdmmc.c @@ -883,7 +883,6 @@ static void wmt_mci_remove(struct platform_device *pdev) { struct mmc_host *mmc; struct wmt_mci_priv *priv; - struct resource *res; u32 reg_tmp; mmc = platform_get_drvdata(pdev); @@ -911,9 +910,6 @@ static void wmt_mci_remove(struct platform_device *pdev) clk_disable_unprepare(priv->clk_sdmmc); clk_put(priv->clk_sdmmc); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, resource_size(res)); - mmc_free_host(mmc); dev_info(&pdev->dev, "WMT MCI device removed\n"); diff --git a/drivers/mtd/maps/physmap-core.c b/drivers/mtd/maps/physmap-core.c index 746a27d15d440..96eb2e782c382 100644 --- a/drivers/mtd/maps/physmap-core.c +++ b/drivers/mtd/maps/physmap-core.c @@ -518,7 +518,7 @@ static int physmap_flash_probe(struct platform_device *dev) if (!info->maps[i].phys) info->maps[i].phys = res->start; - info->win_order = get_bitmask_order(resource_size(res)) - 1; + info->win_order = fls64(resource_size(res)) - 1; info->maps[i].size = BIT(info->win_order + (info->gpios ? info->gpios->ndescs : 0)); diff --git a/drivers/mtd/maps/sun_uflash.c b/drivers/mtd/maps/sun_uflash.c index f58cfb15d6e85..b69dade3f7ad0 100644 --- a/drivers/mtd/maps/sun_uflash.c +++ b/drivers/mtd/maps/sun_uflash.c @@ -47,7 +47,7 @@ struct map_info uflash_map_templ = { .bankwidth = UFLASH_BUSWIDTH, }; -int uflash_devinit(struct platform_device *op, struct device_node *dp) +static int uflash_devinit(struct platform_device *op, struct device_node *dp) { struct uflash_dev *up; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 5887feb347a4e..6d5c755411de0 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -900,7 +900,7 @@ static struct nvmem_device *mtd_otp_nvmem_register(struct mtd_info *mtd, config.name = compatible; config.id = NVMEM_DEVID_AUTO; config.owner = THIS_MODULE; - config.add_legacy_fixed_of_cells = true; + config.add_legacy_fixed_of_cells = !mtd_type_is_nand(mtd); config.type = NVMEM_TYPE_OTP; config.root_only = true; config.ignore_wp = true; @@ -956,8 +956,10 @@ static int mtd_otp_nvmem_add(struct mtd_info *mtd) if (mtd->_get_user_prot_info && mtd->_read_user_prot_reg) { size = mtd_otp_size(mtd, true); - if (size < 0) - return size; + if (size < 0) { + err = size; + goto err; + } if (size > 0) { nvmem = mtd_otp_nvmem_register(mtd, "user-otp", size, diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index 8faca43ae1ff9..b8e70fc64348e 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -625,7 +625,7 @@ enum { /* Only for v7.2 */ #define ACC_CONTROL_ECC_EXT_SHIFT 13 -static u8 brcmnand_status(struct brcmnand_host *host); +static int brcmnand_status(struct brcmnand_host *host); static inline bool brcmnand_non_mmio_ops(struct brcmnand_controller *ctrl) { @@ -1690,7 +1690,7 @@ static int brcmnand_waitfunc(struct nand_chip *chip) INTFC_FLASH_STATUS; } -static u8 brcmnand_status(struct brcmnand_host *host) +static int brcmnand_status(struct brcmnand_host *host) { struct nand_chip *chip = &host->chip; struct mtd_info *mtd = nand_to_mtd(chip); @@ -1701,7 +1701,7 @@ static u8 brcmnand_status(struct brcmnand_host *host) return brcmnand_waitfunc(chip); } -static u8 brcmnand_reset(struct brcmnand_host *host) +static int brcmnand_reset(struct brcmnand_host *host) { struct nand_chip *chip = &host->chip; @@ -2433,7 +2433,11 @@ static int brcmnand_exec_op(struct nand_chip *chip, if (brcmnand_op_is_status(op)) { status = op->instrs[1].ctx.data.buf.in; - *status = brcmnand_status(host); + ret = brcmnand_status(host); + if (ret < 0) + return ret; + + *status = ret & 0xFF; return 0; } diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 5243fab9face0..8db7fc4245711 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -53,7 +53,7 @@ static unsigned long doc_locations[] __initdata = { 0xe8000, 0xea000, 0xec000, 0xee000, #endif #endif - 0xffffffff }; +}; static struct mtd_info *doclist = NULL; @@ -1554,7 +1554,7 @@ static int __init init_nanddoc(void) if (ret < 0) return ret; } else { - for (i = 0; (doc_locations[i] != 0xffffffff); i++) { + for (i = 0; i < ARRAY_SIZE(doc_locations); i++) { doc_probe(doc_locations[i]); } } diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c index 488fd452611a6..677fcb03f9bef 100644 --- a/drivers/mtd/nand/raw/lpc32xx_mlc.c +++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c @@ -303,8 +303,9 @@ static int lpc32xx_nand_device_ready(struct nand_chip *nand_chip) return 0; } -static irqreturn_t lpc3xxx_nand_irq(int irq, struct lpc32xx_nand_host *host) +static irqreturn_t lpc3xxx_nand_irq(int irq, void *data) { + struct lpc32xx_nand_host *host = data; uint8_t sr; /* Clear interrupt flag by reading status */ @@ -780,7 +781,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) goto release_dma_chan; } - if (request_irq(host->irq, (irq_handler_t)&lpc3xxx_nand_irq, + if (request_irq(host->irq, &lpc3xxx_nand_irq, IRQF_TRIGGER_HIGH, DRV_NAME, host)) { dev_err(&pdev->dev, "Error requesting NAND IRQ\n"); res = -ENXIO; diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index cdb58aca59c08..2a96a87cf79ce 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -63,7 +63,7 @@ #define CMDRWGEN(cmd_dir, ran, bch, short_mode, page_size, pages) \ ( \ (cmd_dir) | \ - ((ran) << 19) | \ + (ran) | \ ((bch) << 14) | \ ((short_mode) << 13) | \ (((page_size) & 0x7f) << 6) | \ diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 3b3ce2926f5d1..2479fa98f9912 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -1211,21 +1211,36 @@ static int nand_lp_exec_read_page_op(struct nand_chip *chip, unsigned int page, return nand_exec_op(chip, &op); } +static unsigned int rawnand_last_page_of_lun(unsigned int pages_per_lun, unsigned int lun) +{ + /* lun is expected to be very small */ + return (lun * pages_per_lun) + pages_per_lun - 1; +} + static void rawnand_cap_cont_reads(struct nand_chip *chip) { struct nand_memory_organization *memorg; - unsigned int pages_per_lun, first_lun, last_lun; + unsigned int ppl, first_lun, last_lun; memorg = nanddev_get_memorg(&chip->base); - pages_per_lun = memorg->pages_per_eraseblock * memorg->eraseblocks_per_lun; - first_lun = chip->cont_read.first_page / pages_per_lun; - last_lun = chip->cont_read.last_page / pages_per_lun; + ppl = memorg->pages_per_eraseblock * memorg->eraseblocks_per_lun; + first_lun = chip->cont_read.first_page / ppl; + last_lun = chip->cont_read.last_page / ppl; /* Prevent sequential cache reads across LUN boundaries */ if (first_lun != last_lun) - chip->cont_read.pause_page = first_lun * pages_per_lun + pages_per_lun - 1; + chip->cont_read.pause_page = rawnand_last_page_of_lun(ppl, first_lun); else chip->cont_read.pause_page = chip->cont_read.last_page; + + if (chip->cont_read.first_page == chip->cont_read.pause_page) { + chip->cont_read.first_page++; + chip->cont_read.pause_page = min(chip->cont_read.last_page, + rawnand_last_page_of_lun(ppl, first_lun + 1)); + } + + if (chip->cont_read.first_page >= chip->cont_read.last_page) + chip->cont_read.ongoing = false; } static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int page, @@ -1292,12 +1307,11 @@ static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int p if (!chip->cont_read.ongoing) return 0; - if (page == chip->cont_read.pause_page && - page != chip->cont_read.last_page) { - chip->cont_read.first_page = chip->cont_read.pause_page + 1; - rawnand_cap_cont_reads(chip); - } else if (page == chip->cont_read.last_page) { + if (page == chip->cont_read.last_page) { chip->cont_read.ongoing = false; + } else if (page == chip->cont_read.pause_page) { + chip->cont_read.first_page++; + rawnand_cap_cont_reads(chip); } return 0; @@ -3466,30 +3480,36 @@ static void rawnand_enable_cont_reads(struct nand_chip *chip, unsigned int page, u32 readlen, int col) { struct mtd_info *mtd = nand_to_mtd(chip); - unsigned int end_page, end_col; + unsigned int first_page, last_page; chip->cont_read.ongoing = false; if (!chip->controller->supported_op.cont_read) return; - end_page = DIV_ROUND_UP(col + readlen, mtd->writesize); - end_col = (col + readlen) % mtd->writesize; + /* + * Don't bother making any calculations if the length is too small. + * Side effect: avoids possible integer underflows below. + */ + if (readlen < (2 * mtd->writesize)) + return; + /* Derive the page where continuous read should start (the first full page read) */ + first_page = page; if (col) - page++; + first_page++; - if (end_col && end_page) - end_page--; + /* Derive the page where continuous read should stop (the last full page read) */ + last_page = page + ((col + readlen) / mtd->writesize) - 1; - if (page + 1 > end_page) - return; - - chip->cont_read.first_page = page; - chip->cont_read.last_page = end_page; - chip->cont_read.ongoing = true; - - rawnand_cap_cont_reads(chip); + /* Configure and enable continuous read when suitable */ + if (first_page < last_page) { + chip->cont_read.first_page = first_page; + chip->cont_read.last_page = last_page; + chip->cont_read.ongoing = true; + /* May reset the ongoing flag */ + rawnand_cap_cont_reads(chip); + } } static void rawnand_cont_read_skip_first_page(struct nand_chip *chip, unsigned int page) @@ -3498,10 +3518,7 @@ static void rawnand_cont_read_skip_first_page(struct nand_chip *chip, unsigned i return; chip->cont_read.first_page++; - if (chip->cont_read.first_page == chip->cont_read.pause_page) - chip->cont_read.first_page++; - if (chip->cont_read.first_page >= chip->cont_read.last_page) - chip->cont_read.ongoing = false; + rawnand_cap_cont_reads(chip); } /** @@ -3577,7 +3594,8 @@ static int nand_do_read_ops(struct nand_chip *chip, loff_t from, oob = ops->oobbuf; oob_required = oob ? 1 : 0; - rawnand_enable_cont_reads(chip, page, readlen, col); + if (likely(ops->mode != MTD_OPS_RAW)) + rawnand_enable_cont_reads(chip, page, readlen, col); while (1) { struct mtd_ecc_stats ecc_stats = mtd->ecc_stats; @@ -5195,6 +5213,15 @@ static void rawnand_late_check_supported_ops(struct nand_chip *chip) if (!nand_has_exec_op(chip)) return; + /* + * For now, continuous reads can only be used with the core page helpers. + * This can be extended later. + */ + if (!(chip->ecc.read_page == nand_read_page_hwecc || + chip->ecc.read_page == nand_read_page_syndrome || + chip->ecc.read_page == nand_read_page_swecc)) + return; + rawnand_check_cont_read_support(chip); } diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c index 39076735a3fbb..9695f07b5eb26 100644 --- a/drivers/mtd/nand/raw/nand_hynix.c +++ b/drivers/mtd/nand/raw/nand_hynix.c @@ -402,7 +402,7 @@ static int hynix_nand_rr_init(struct nand_chip *chip) if (ret) pr_warn("failed to initialize read-retry infrastructure"); - return 0; + return ret; } static void hynix_nand_extract_oobsize(struct nand_chip *chip, diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index b079605c84d38..b8cff9240b286 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -2815,7 +2815,7 @@ static int qcom_misc_cmd_type_exec(struct nand_chip *chip, const struct nand_sub host->cfg0_raw & ~(7 << CW_PER_PAGE)); nandc_set_reg(chip, NAND_DEV0_CFG1, host->cfg1_raw); instrs = 3; - } else { + } else if (q_op.cmd_reg != OP_RESET_DEVICE) { return 0; } @@ -2830,9 +2830,8 @@ static int qcom_misc_cmd_type_exec(struct nand_chip *chip, const struct nand_sub nandc_set_reg(chip, NAND_EXEC_CMD, 1); write_reg_dma(nandc, NAND_FLASH_CMD, instrs, NAND_BAM_NEXT_SGL); - (q_op.cmd_reg == OP_BLOCK_ERASE) ? write_reg_dma(nandc, NAND_DEV0_CFG0, - 2, NAND_BAM_NEXT_SGL) : read_reg_dma(nandc, - NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); + if (q_op.cmd_reg == OP_BLOCK_ERASE) + write_reg_dma(nandc, NAND_DEV0_CFG0, 2, NAND_BAM_NEXT_SGL); write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); diff --git a/drivers/mtd/nand/spi/esmt.c b/drivers/mtd/nand/spi/esmt.c index 31c439a557b18..4597a82de23a4 100644 --- a/drivers/mtd/nand/spi/esmt.c +++ b/drivers/mtd/nand/spi/esmt.c @@ -104,7 +104,8 @@ static const struct mtd_ooblayout_ops f50l1g41lb_ooblayout = { static const struct spinand_info esmt_c8_spinand_table[] = { SPINAND_INFO("F50L1G41LB", - SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0x01), + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0x01, 0x7f, + 0x7f, 0x7f), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), NAND_ECCREQ(1, 512), SPINAND_INFO_OP_VARIANTS(&read_cache_variants, @@ -113,7 +114,8 @@ static const struct spinand_info esmt_c8_spinand_table[] = { 0, SPINAND_ECCINFO(&f50l1g41lb_ooblayout, NULL)), SPINAND_INFO("F50D1G41LB", - SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0x11), + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0x11, 0x7f, + 0x7f, 0x7f), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), NAND_ECCREQ(1, 512), SPINAND_INFO_OP_VARIANTS(&read_cache_variants, @@ -122,7 +124,8 @@ static const struct spinand_info esmt_c8_spinand_table[] = { 0, SPINAND_ECCINFO(&f50l1g41lb_ooblayout, NULL)), SPINAND_INFO("F50D2G41KA", - SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0x51), + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_ADDR, 0x51, 0x7f, + 0x7f, 0x7f), NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1), NAND_ECCREQ(8, 512), SPINAND_INFO_OP_VARIANTS(&read_cache_variants, diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 2a728c31e6b85..9a4940874be5b 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -85,9 +85,10 @@ size_t ubi_calc_fm_size(struct ubi_device *ubi) sizeof(struct ubi_fm_scan_pool) + sizeof(struct ubi_fm_scan_pool) + (ubi->peb_count * sizeof(struct ubi_fm_ec)) + - (sizeof(struct ubi_fm_eba) + - (ubi->peb_count * sizeof(__be32))) + - sizeof(struct ubi_fm_volhdr) * UBI_MAX_VOLUMES; + ((sizeof(struct ubi_fm_eba) + + sizeof(struct ubi_fm_volhdr)) * + (UBI_MAX_VOLUMES + UBI_INT_VOL_COUNT)) + + (ubi->peb_count * sizeof(__be32)); return roundup(size, ubi->leb_size); } diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c index f700f0e4f2ec4..6e5489e233dd2 100644 --- a/drivers/mtd/ubi/vtbl.c +++ b/drivers/mtd/ubi/vtbl.c @@ -791,6 +791,12 @@ int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai) * The number of supported volumes is limited by the eraseblock size * and by the UBI_MAX_VOLUMES constant. */ + + if (ubi->leb_size < UBI_VTBL_RECORD_SIZE) { + ubi_err(ubi, "LEB size too small for a volume record"); + return -EINVAL; + } + ubi->vtbl_slots = ubi->leb_size / UBI_VTBL_RECORD_SIZE; if (ubi->vtbl_slots > UBI_MAX_VOLUMES) ubi->vtbl_slots = UBI_MAX_VOLUMES; diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 7cab36f94782e..db55ffdb5792d 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -48,7 +48,9 @@ obj-$(CONFIG_MHI_NET) += mhi_net.o obj-$(CONFIG_ARCNET) += arcnet/ obj-$(CONFIG_CAIF) += caif/ obj-$(CONFIG_CAN) += can/ -obj-$(CONFIG_NET_DSA) += dsa/ +ifdef CONFIG_NET_DSA +obj-y += dsa/ +endif obj-$(CONFIG_ETHERNET) += ethernet/ obj-$(CONFIG_FDDI) += fddi/ obj-$(CONFIG_HIPPI) += hippi/ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index cd0683bcca038..a27824221e0f5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -6459,16 +6459,16 @@ static int __init bonding_init(void) if (res) goto out; + bond_create_debugfs(); + res = register_pernet_subsys(&bond_net_ops); if (res) - goto out; + goto err_net_ops; res = bond_netlink_init(); if (res) goto err_link; - bond_create_debugfs(); - for (i = 0; i < max_bonds; i++) { res = bond_create(&init_net, NULL); if (res) @@ -6483,10 +6483,11 @@ static int __init bonding_init(void) out: return res; err: - bond_destroy_debugfs(); bond_netlink_fini(); err_link: unregister_pernet_subsys(&bond_net_ops); +err_net_ops: + bond_destroy_debugfs(); goto out; } @@ -6495,11 +6496,11 @@ static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); - bond_destroy_debugfs(); - bond_netlink_fini(); unregister_pernet_subsys(&bond_net_ops); + bond_destroy_debugfs(); + #ifdef CONFIG_NET_POLL_CONTROLLER /* Make sure we don't have an imbalance on our netpoll blocking */ WARN_ON(atomic_read(&netpoll_block_tx)); diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 16ecc11c7f62a..2395b1225cc8a 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -418,6 +418,13 @@ static void m_can_config_endisable(struct m_can_classdev *cdev, bool enable) static inline void m_can_enable_all_interrupts(struct m_can_classdev *cdev) { + if (!cdev->net->irq) { + dev_dbg(cdev->dev, "Start hrtimer\n"); + hrtimer_start(&cdev->hrtimer, + ms_to_ktime(HRTIMER_POLL_INTERVAL_MS), + HRTIMER_MODE_REL_PINNED); + } + /* Only interrupt line 0 is used in this driver */ m_can_write(cdev, M_CAN_ILE, ILE_EINT0); } @@ -425,6 +432,11 @@ static inline void m_can_enable_all_interrupts(struct m_can_classdev *cdev) static inline void m_can_disable_all_interrupts(struct m_can_classdev *cdev) { m_can_write(cdev, M_CAN_ILE, 0x0); + + if (!cdev->net->irq) { + dev_dbg(cdev->dev, "Stop hrtimer\n"); + hrtimer_cancel(&cdev->hrtimer); + } } /* Retrieve internal timestamp counter from TSCV.TSC, and shift it to 32-bit @@ -1417,12 +1429,6 @@ static int m_can_start(struct net_device *dev) m_can_enable_all_interrupts(cdev); - if (!dev->irq) { - dev_dbg(cdev->dev, "Start hrtimer\n"); - hrtimer_start(&cdev->hrtimer, ms_to_ktime(HRTIMER_POLL_INTERVAL_MS), - HRTIMER_MODE_REL_PINNED); - } - return 0; } @@ -1577,11 +1583,6 @@ static void m_can_stop(struct net_device *dev) { struct m_can_classdev *cdev = netdev_priv(dev); - if (!dev->irq) { - dev_dbg(cdev->dev, "Stop hrtimer\n"); - hrtimer_cancel(&cdev->hrtimer); - } - /* disable all interrupts */ m_can_disable_all_interrupts(cdev); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 245dfb7a7a315..47b4e137c1a4f 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2185,6 +2185,8 @@ static int ksz_pirq_setup(struct ksz_device *dev, u8 p) return ksz_irq_common_setup(dev, pirq); } +static int ksz_parse_drive_strength(struct ksz_device *dev); + static int ksz_setup(struct dsa_switch *ds) { struct ksz_device *dev = ds->priv; @@ -2206,6 +2208,10 @@ static int ksz_setup(struct dsa_switch *ds) return ret; } + ret = ksz_parse_drive_strength(dev); + if (ret) + return ret; + /* set broadcast storm protection 10% rate */ regmap_update_bits(ksz_regmap_16(dev), regs[S_BROADCAST_CTRL], BROADCAST_STORM_RATE, @@ -2962,7 +2968,7 @@ phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit) else interface = PHY_INTERFACE_MODE_MII; } else if (val == bitval[P_RMII_SEL]) { - interface = PHY_INTERFACE_MODE_RGMII; + interface = PHY_INTERFACE_MODE_RMII; } else { interface = PHY_INTERFACE_MODE_RGMII; if (data8 & P_RGMII_ID_EG_ENABLE) @@ -4242,10 +4248,6 @@ int ksz_switch_register(struct ksz_device *dev) for (port_num = 0; port_num < dev->info->port_cnt; ++port_num) dev->ports[port_num].interface = PHY_INTERFACE_MODE_NA; if (dev->dev->of_node) { - ret = ksz_parse_drive_strength(dev); - if (ret) - return ret; - ret = of_get_phy_mode(dev->dev->of_node, &interface); if (ret == 0) dev->compat_interface = interface; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 3c1f657593a8f..e48ef9823c8ea 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -998,20 +998,217 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface) mutex_unlock(&priv->reg_mutex); } +/* In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL) + * of the Open Systems Interconnection basic reference model (OSI/RM) are + * described; the medium access control (MAC) and logical link control (LLC) + * sublayers. The MAC sublayer is the one facing the physical layer. + * + * In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A + * Bridge component comprises a MAC Relay Entity for interconnecting the Ports + * of the Bridge, at least two Ports, and higher layer entities with at least a + * Spanning Tree Protocol Entity included. + * + * Each Bridge Port also functions as an end station and shall provide the MAC + * Service to an LLC Entity. Each instance of the MAC Service is provided to a + * distinct LLC Entity that supports protocol identification, multiplexing, and + * demultiplexing, for protocol data unit (PDU) transmission and reception by + * one or more higher layer entities. + * + * It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC + * Entity associated with each Bridge Port is modeled as being directly + * connected to the attached Local Area Network (LAN). + * + * On the switch with CPU port architecture, CPU port functions as Management + * Port, and the Management Port functionality is provided by software which + * functions as an end station. Software is connected to an IEEE 802 LAN that is + * wholly contained within the system that incorporates the Bridge. Software + * provides access to the LLC Entity associated with each Bridge Port by the + * value of the source port field on the special tag on the frame received by + * software. + * + * We call frames that carry control information to determine the active + * topology and current extent of each Virtual Local Area Network (VLAN), i.e., + * spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration + * Protocol Data Units (MVRPDUs), and frames from other link constrained + * protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and + * Link Layer Discovery Protocol (LLDP), link-local frames. They are not + * forwarded by a Bridge. Permanently configured entries in the filtering + * database (FDB) ensure that such frames are discarded by the Forwarding + * Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail: + * + * Each of the reserved MAC addresses specified in Table 8-1 + * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be + * permanently configured in the FDB in C-VLAN components and ERs. + * + * Each of the reserved MAC addresses specified in Table 8-2 + * (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently + * configured in the FDB in S-VLAN components. + * + * Each of the reserved MAC addresses specified in Table 8-3 + * (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in + * TPMR components. + * + * The FDB entries for reserved MAC addresses shall specify filtering for all + * Bridge Ports and all VIDs. Management shall not provide the capability to + * modify or remove entries for reserved MAC addresses. + * + * The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of + * propagation of PDUs within a Bridged Network, as follows: + * + * The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no + * conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN) + * component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward. + * PDUs transmitted using this destination address, or any other addresses + * that appear in Table 8-1, Table 8-2, and Table 8-3 + * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can + * therefore travel no further than those stations that can be reached via a + * single individual LAN from the originating station. + * + * The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an + * address that no conformant S-VLAN component, C-VLAN component, or MAC + * Bridge can forward; however, this address is relayed by a TPMR component. + * PDUs using this destination address, or any of the other addresses that + * appear in both Table 8-1 and Table 8-2 but not in Table 8-3 + * (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by + * any TPMRs but will propagate no further than the nearest S-VLAN component, + * C-VLAN component, or MAC Bridge. + * + * The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address + * that no conformant C-VLAN component, MAC Bridge can forward; however, it is + * relayed by TPMR components and S-VLAN components. PDUs using this + * destination address, or any of the other addresses that appear in Table 8-1 + * but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]), + * will be relayed by TPMR components and S-VLAN components but will propagate + * no further than the nearest C-VLAN component or MAC Bridge. + * + * Because the LLC Entity associated with each Bridge Port is provided via CPU + * port, we must not filter these frames but forward them to CPU port. + * + * In a Bridge, the transmission Port is majorly decided by ingress and egress + * rules, FDB, and spanning tree Port State functions of the Forwarding Process. + * For link-local frames, only CPU port should be designated as destination port + * in the FDB, and the other functions of the Forwarding Process must not + * interfere with the decision of the transmission Port. We call this process + * trapping frames to CPU port. + * + * Therefore, on the switch with CPU port architecture, link-local frames must + * be trapped to CPU port, and certain link-local frames received by a Port of a + * Bridge comprising a TPMR component or an S-VLAN component must be excluded + * from it. + * + * A Bridge of the switch with CPU port architecture cannot comprise a Two-Port + * MAC Relay (TPMR) component as a TPMR component supports only a subset of the + * functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port + * doesn't count) of this architecture will either function as a standard MAC + * Bridge or a standard VLAN Bridge. + * + * Therefore, a Bridge of this architecture can only comprise S-VLAN components, + * C-VLAN components, or MAC Bridge components. Since there's no TPMR component, + * we don't need to relay PDUs using the destination addresses specified on the + * Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge + * section where they must be relayed by TPMR components. + * + * One option to trap link-local frames to CPU port is to add static FDB entries + * with CPU port designated as destination port. However, because that + * Independent VLAN Learning (IVL) is being used on every VID, each entry only + * applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC + * Bridge component or a C-VLAN component, there would have to be 16 times 4096 + * entries. This switch intellectual property can only hold a maximum of 2048 + * entries. Using this option, there also isn't a mechanism to prevent + * link-local frames from being discarded when the spanning tree Port State of + * the reception Port is discarding. + * + * The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4 + * registers. Whilst this applies to every VID, it doesn't contain all of the + * reserved MAC addresses without affecting the remaining Standard Group MAC + * Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the + * remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination + * addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF + * destination addresses which may be relayed by MAC Bridges or VLAN Bridges. + * The latter option provides better but not complete conformance. + * + * This switch intellectual property also does not provide a mechanism to trap + * link-local frames with specific destination addresses to CPU port by Bridge, + * to conform to the filtering rules for the distinct Bridge components. + * + * Therefore, regardless of the type of the Bridge component, link-local frames + * with these destination addresses will be trapped to CPU port: + * + * 01-80-C2-00-00-[00,01,02,03,0E] + * + * In a Bridge comprising a MAC Bridge component or a C-VLAN component: + * + * Link-local frames with these destination addresses won't be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] + * + * In a Bridge comprising an S-VLAN component: + * + * Link-local frames with these destination addresses will be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-00 + * + * Link-local frames with these destination addresses won't be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-[04,05,06,07,08,09,0A] + * + * To trap link-local frames to CPU port as conformant as this switch + * intellectual property can allow, link-local frames are made to be regarded as + * Bridge Protocol Data Units (BPDUs). This is because this switch intellectual + * property only lets the frames regarded as BPDUs bypass the spanning tree Port + * State function of the Forwarding Process. + * + * The only remaining interference is the ingress rules. When the reception Port + * has no PVID assigned on software, VLAN-untagged frames won't be allowed in. + * There doesn't seem to be a mechanism on the switch intellectual property to + * have link-local frames bypass this function of the Forwarding Process. + */ static void mt753x_trap_frames(struct mt7530_priv *priv) { - /* Trap BPDUs to the CPU port(s) */ - mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, - MT753X_BPDU_CPU_ONLY); - - /* Trap 802.1X PAE frames to the CPU port(s) */ - mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK, - MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY)); - - /* Trap LLDP frames with :0E MAC DA to the CPU port(s) */ - mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK, - MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); + /* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them + * VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_BPC, + MT753X_PAE_BPDU_FR | MT753X_PAE_EG_TAG_MASK | + MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK | + MT753X_BPDU_PORT_FW_MASK, + MT753X_PAE_BPDU_FR | + MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); + + /* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress + * them VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_RGAC1, + MT753X_R02_BPDU_FR | MT753X_R02_EG_TAG_MASK | + MT753X_R02_PORT_FW_MASK | MT753X_R01_BPDU_FR | + MT753X_R01_EG_TAG_MASK | MT753X_R01_PORT_FW_MASK, + MT753X_R02_BPDU_FR | + MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_R01_BPDU_FR | + MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); + + /* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress + * them VLAN-untagged. + */ + mt7530_rmw(priv, MT753X_RGAC2, + MT753X_R0E_BPDU_FR | MT753X_R0E_EG_TAG_MASK | + MT753X_R0E_PORT_FW_MASK | MT753X_R03_BPDU_FR | + MT753X_R03_EG_TAG_MASK | MT753X_R03_PORT_FW_MASK, + MT753X_R0E_BPDU_FR | + MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_R03_BPDU_FR | + MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); } static int @@ -1750,14 +1947,16 @@ mt7530_port_vlan_del(struct dsa_switch *ds, int port, static int mt753x_mirror_port_get(unsigned int id, u32 val) { - return (id == ID_MT7531) ? MT7531_MIRROR_PORT_GET(val) : - MIRROR_PORT(val); + return (id == ID_MT7531 || id == ID_MT7988) ? + MT7531_MIRROR_PORT_GET(val) : + MIRROR_PORT(val); } static int mt753x_mirror_port_set(unsigned int id, u32 val) { - return (id == ID_MT7531) ? MT7531_MIRROR_PORT_SET(val) : - MIRROR_PORT(val); + return (id == ID_MT7531 || id == ID_MT7988) ? + MT7531_MIRROR_PORT_SET(val) : + MIRROR_PORT(val); } static int mt753x_port_mirror_add(struct dsa_switch *ds, int port, @@ -2243,11 +2442,11 @@ mt7530_setup(struct dsa_switch *ds) */ if (priv->mcm) { reset_control_assert(priv->rstc); - usleep_range(1000, 1100); + usleep_range(5000, 5100); reset_control_deassert(priv->rstc); } else { gpiod_set_value_cansleep(priv->reset, 0); - usleep_range(1000, 1100); + usleep_range(5000, 5100); gpiod_set_value_cansleep(priv->reset, 1); } @@ -2272,8 +2471,6 @@ mt7530_setup(struct dsa_switch *ds) SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST | SYS_CTRL_REG_RST); - mt7530_pll_setup(priv); - /* Lower Tx driving for TRGMII path */ for (i = 0; i < NUM_TRGMII_CTRL; i++) mt7530_write(priv, MT7530_TRGMII_TD_ODT(i), @@ -2291,6 +2488,9 @@ mt7530_setup(struct dsa_switch *ds) priv->p6_interface = PHY_INTERFACE_MODE_NA; + if ((val & HWTRAP_XTAL_MASK) == HWTRAP_XTAL_40MHZ) + mt7530_pll_setup(priv); + mt753x_trap_frames(priv); /* Enable and reset MIB counters */ @@ -2320,6 +2520,9 @@ mt7530_setup(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Setup VLAN ID 0 for VLAN-unaware bridges */ ret = mt7530_setup_vlan0(priv); if (ret) @@ -2428,6 +2631,9 @@ mt7531_setup_common(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Flush the FDB table */ ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL); if (ret < 0) @@ -2449,11 +2655,11 @@ mt7531_setup(struct dsa_switch *ds) */ if (priv->mcm) { reset_control_assert(priv->rstc); - usleep_range(1000, 1100); + usleep_range(5000, 5100); reset_control_deassert(priv->rstc); } else { gpiod_set_value_cansleep(priv->reset, 0); - usleep_range(1000, 1100); + usleep_range(5000, 5100); gpiod_set_value_cansleep(priv->reset, 1); } @@ -2506,18 +2712,25 @@ mt7531_setup(struct dsa_switch *ds) priv->p5_interface = PHY_INTERFACE_MODE_NA; priv->p6_interface = PHY_INTERFACE_MODE_NA; - /* Enable PHY core PLL, since phy_device has not yet been created - * provided for phy_[read,write]_mmd_indirect is called, we provide - * our own mt7531_ind_mmd_phy_[read,write] to complete this - * function. + /* Enable Energy-Efficient Ethernet (EEE) and PHY core PLL, since + * phy_device has not yet been created provided for + * phy_[read,write]_mmd_indirect is called, we provide our own + * mt7531_ind_mmd_phy_[read,write] to complete this function. */ val = mt7531_ind_c45_phy_read(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2, CORE_PLL_GROUP4); - val |= MT7531_PHY_PLL_BYPASS_MODE; + val |= MT7531_RG_SYSPLL_DMY2 | MT7531_PHY_PLL_BYPASS_MODE; val &= ~MT7531_PHY_PLL_OFF; mt7531_ind_c45_phy_write(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2, CORE_PLL_GROUP4, val); + /* Disable EEE advertisement on the switch PHYs. */ + for (i = MT753X_CTRL_PHY_ADDR; + i < MT753X_CTRL_PHY_ADDR + MT7530_NUM_PHYS; i++) { + mt7531_ind_c45_phy_write(priv, i, MDIO_MMD_AN, MDIO_AN_EEE_ADV, + 0); + } + mt7531_setup_common(ds); /* Setup VLAN ID 0 for VLAN-unaware bridges */ diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 17e42d30fff4b..0ad52d3cbfebb 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -32,6 +32,10 @@ enum mt753x_id { #define SYSC_REG_RSTCTRL 0x34 #define RESET_MCM BIT(2) +/* Register for ARL global control */ +#define MT753X_AGC 0xc +#define LOCAL_EN BIT(7) + /* Registers to mac forward control for unknown frames */ #define MT7530_MFC 0x10 #define BC_FFP(x) (((x) & 0xff) << 24) @@ -65,14 +69,38 @@ enum mt753x_id { /* Registers for BPDU and PAE frame control*/ #define MT753X_BPC 0x24 -#define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) +#define MT753X_PAE_BPDU_FR BIT(25) +#define MT753X_PAE_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_PAE_EG_TAG(x) FIELD_PREP(MT753X_PAE_EG_TAG_MASK, x) #define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16) #define MT753X_PAE_PORT_FW(x) FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x) +#define MT753X_BPDU_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_BPDU_EG_TAG(x) FIELD_PREP(MT753X_BPDU_EG_TAG_MASK, x) +#define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) + +/* Register for :01 and :02 MAC DA frame control */ +#define MT753X_RGAC1 0x28 +#define MT753X_R02_BPDU_FR BIT(25) +#define MT753X_R02_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_R02_EG_TAG(x) FIELD_PREP(MT753X_R02_EG_TAG_MASK, x) +#define MT753X_R02_PORT_FW_MASK GENMASK(18, 16) +#define MT753X_R02_PORT_FW(x) FIELD_PREP(MT753X_R02_PORT_FW_MASK, x) +#define MT753X_R01_BPDU_FR BIT(9) +#define MT753X_R01_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_R01_EG_TAG(x) FIELD_PREP(MT753X_R01_EG_TAG_MASK, x) +#define MT753X_R01_PORT_FW_MASK GENMASK(2, 0) /* Register for :03 and :0E MAC DA frame control */ #define MT753X_RGAC2 0x2c +#define MT753X_R0E_BPDU_FR BIT(25) +#define MT753X_R0E_EG_TAG_MASK GENMASK(24, 22) +#define MT753X_R0E_EG_TAG(x) FIELD_PREP(MT753X_R0E_EG_TAG_MASK, x) #define MT753X_R0E_PORT_FW_MASK GENMASK(18, 16) #define MT753X_R0E_PORT_FW(x) FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x) +#define MT753X_R03_BPDU_FR BIT(9) +#define MT753X_R03_EG_TAG_MASK GENMASK(8, 6) +#define MT753X_R03_EG_TAG(x) FIELD_PREP(MT753X_R03_EG_TAG_MASK, x) +#define MT753X_R03_PORT_FW_MASK GENMASK(2, 0) enum mt753x_bpdu_port_fw { MT753X_BPDU_FOLLOW_MFC, @@ -253,6 +281,7 @@ enum mt7530_port_mode { enum mt7530_vlan_port_eg_tag { MT7530_VLAN_EG_DISABLED = 0, MT7530_VLAN_EG_CONSISTENT = 1, + MT7530_VLAN_EG_UNTAGGED = 4, }; enum mt7530_vlan_port_attr { @@ -605,6 +634,7 @@ enum mt7531_clk_skew { #define RG_SYSPLL_DDSFBK_EN BIT(12) #define RG_SYSPLL_BIAS_EN BIT(11) #define RG_SYSPLL_BIAS_LPF_EN BIT(10) +#define MT7531_RG_SYSPLL_DMY2 BIT(6) #define MT7531_PHY_PLL_OFF BIT(5) #define MT7531_PHY_PLL_BYPASS_MODE BIT(4) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 614cabb5c1b03..1da9538f0caf7 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -131,8 +131,8 @@ struct mii_bus *mv88e6xxx_default_mdio_bus(struct mv88e6xxx_chip *chip) { struct mv88e6xxx_mdio_bus *mdio_bus; - mdio_bus = list_first_entry(&chip->mdios, struct mv88e6xxx_mdio_bus, - list); + mdio_bus = list_first_entry_or_null(&chip->mdios, + struct mv88e6xxx_mdio_bus, list); if (!mdio_bus) return NULL; @@ -566,13 +566,61 @@ static void mv88e6xxx_translate_cmode(u8 cmode, unsigned long *supported) phy_interface_set_rgmii(supported); } -static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, - struct phylink_config *config) +static void +mv88e6250_setup_supported_interfaces(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { unsigned long *supported = config->supported_interfaces; + int err; + u16 reg; - /* Translate the default cmode */ - mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®); + if (err) { + dev_err(chip->dev, "p%d: failed to read port status\n", port); + return; + } + + switch (reg & MV88E6250_PORT_STS_PORTMODE_MASK) { + case MV88E6250_PORT_STS_PORTMODE_MII_10_HALF_PHY: + case MV88E6250_PORT_STS_PORTMODE_MII_100_HALF_PHY: + case MV88E6250_PORT_STS_PORTMODE_MII_10_FULL_PHY: + case MV88E6250_PORT_STS_PORTMODE_MII_100_FULL_PHY: + __set_bit(PHY_INTERFACE_MODE_REVMII, supported); + break; + + case MV88E6250_PORT_STS_PORTMODE_MII_HALF: + case MV88E6250_PORT_STS_PORTMODE_MII_FULL: + __set_bit(PHY_INTERFACE_MODE_MII, supported); + break; + + case MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL_PHY: + case MV88E6250_PORT_STS_PORTMODE_MII_200_RMII_FULL_PHY: + case MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_HALF_PHY: + case MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL_PHY: + __set_bit(PHY_INTERFACE_MODE_REVRMII, supported); + break; + + case MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL: + case MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL: + __set_bit(PHY_INTERFACE_MODE_RMII, supported); + break; + + case MV88E6250_PORT_STS_PORTMODE_MII_100_RGMII: + __set_bit(PHY_INTERFACE_MODE_RGMII, supported); + break; + + default: + dev_err(chip->dev, + "p%d: invalid port mode in status register: %04x\n", + port, reg); + } +} + +static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) +{ + if (!mv88e6xxx_phy_is_internal(chip, port)) + mv88e6250_setup_supported_interfaces(chip, port, config); config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100; } @@ -649,6 +697,18 @@ static void mv88e6352_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, } } +static void mv88e632x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) +{ + unsigned long *supported = config->supported_interfaces; + + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; +} + static void mv88e6341_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, struct phylink_config *config) { @@ -3075,6 +3135,7 @@ static int mv88e6xxx_software_reset(struct mv88e6xxx_chip *chip) static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) { struct gpio_desc *gpiod = chip->reset; + int err; /* If there is a GPIO connected to the reset pin, toggle it */ if (gpiod) { @@ -3083,17 +3144,26 @@ static void mv88e6xxx_hardware_reset(struct mv88e6xxx_chip *chip) * mid-byte, causing the first EEPROM read after the reset * from the wrong location resulting in the switch booting * to wrong mode and inoperable. + * For this reason, switch families with EEPROM support + * generally wait for EEPROM loads to complete as their pre- + * and post-reset handlers. */ - if (chip->info->ops->get_eeprom) - mv88e6xxx_g2_eeprom_wait(chip); + if (chip->info->ops->hardware_reset_pre) { + err = chip->info->ops->hardware_reset_pre(chip); + if (err) + dev_err(chip->dev, "pre-reset error: %d\n", err); + } gpiod_set_value_cansleep(gpiod, 1); usleep_range(10000, 20000); gpiod_set_value_cansleep(gpiod, 0); usleep_range(10000, 20000); - if (chip->info->ops->get_eeprom) - mv88e6xxx_g2_eeprom_wait(chip); + if (chip->info->ops->hardware_reset_post) { + err = chip->info->ops->hardware_reset_post(chip); + if (err) + dev_err(chip->dev, "post-reset error: %d\n", err); + } } } @@ -4320,6 +4390,8 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -4510,6 +4582,8 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .watchdog_ops = &mv88e6097_watchdog_ops, .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6352_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -4610,6 +4684,8 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .watchdog_ops = &mv88e6097_watchdog_ops, .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6352_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -4704,6 +4780,8 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -4762,6 +4840,8 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -4818,6 +4898,8 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -4877,6 +4959,8 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .watchdog_ops = &mv88e6097_watchdog_ops, .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6352_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -4930,6 +5014,8 @@ static const struct mv88e6xxx_ops mv88e6250_ops = { .watchdog_ops = &mv88e6250_watchdog_ops, .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6250_g1_wait_eeprom_done_prereset, + .hardware_reset_post = mv88e6xxx_g1_wait_eeprom_done, .reset = mv88e6250_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, @@ -4977,6 +5063,8 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -5036,13 +5124,15 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_get_caps = mv88e6185_phylink_get_caps, + .phylink_get_caps = mv88e632x_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6321_ops = { @@ -5082,13 +5172,15 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .set_egress_port = mv88e6095_g1_set_egress_port, .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_get_caps = mv88e6185_phylink_get_caps, + .phylink_get_caps = mv88e632x_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6341_ops = { @@ -5132,6 +5224,8 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -5287,6 +5381,8 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .watchdog_ops = &mv88e6097_watchdog_ops, .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6352_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -5349,6 +5445,8 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -5411,6 +5509,8 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .watchdog_ops = &mv88e6390_watchdog_ops, .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -5476,6 +5576,8 @@ static const struct mv88e6xxx_ops mv88e6393x_ops = { .watchdog_ops = &mv88e6393x_watchdog_ops, .mgmt_rsvd2cpu = mv88e6393x_port_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, + .hardware_reset_pre = mv88e6xxx_g2_eeprom_wait, + .hardware_reset_post = mv88e6xxx_g2_eeprom_wait, .reset = mv88e6352_g1_reset, .rmu_disable = mv88e6390_g1_rmu_disable, .atu_get_hash = mv88e6165_g1_atu_get_hash, @@ -5500,8 +5602,12 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .family = MV88E6XXX_FAMILY_6250, .name = "Marvell 88E6020", .num_databases = 64, - .num_ports = 4, + /* Ports 2-4 are not routed to pins + * => usable ports 0, 1, 5, 6 + */ + .num_ports = 7, .num_internal_phys = 2, + .invalid_port_mask = BIT(2) | BIT(3) | BIT(4), .max_vid = 4095, .port_base_addr = 0x8, .phy_base_addr = 0x0, @@ -5650,7 +5756,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6141, .family = MV88E6XXX_FAMILY_6341, .name = "Marvell 88E6141", - .num_databases = 4096, + .num_databases = 256, .num_macs = 2048, .num_ports = 6, .num_internal_phys = 5, @@ -6109,7 +6215,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6341, .family = MV88E6XXX_FAMILY_6341, .name = "Marvell 88E6341", - .num_databases = 4096, + .num_databases = 256, .num_macs = 2048, .num_internal_phys = 5, .num_ports = 6, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 85eb293381a7e..c34caf9815c5c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -487,6 +487,12 @@ struct mv88e6xxx_ops { int (*ppu_enable)(struct mv88e6xxx_chip *chip); int (*ppu_disable)(struct mv88e6xxx_chip *chip); + /* Additional handlers to run before and after hard reset, to make sure + * that the switch and EEPROM are in a good state. + */ + int (*hardware_reset_pre)(struct mv88e6xxx_chip *chip); + int (*hardware_reset_post)(struct mv88e6xxx_chip *chip); + /* Switch Software Reset */ int (*reset)(struct mv88e6xxx_chip *chip); diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 49444a72ff095..9820cd5967574 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -75,6 +75,95 @@ static int mv88e6xxx_g1_wait_init_ready(struct mv88e6xxx_chip *chip) return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } +static int mv88e6250_g1_eeprom_reload(struct mv88e6xxx_chip *chip) +{ + /* MV88E6185_G1_CTL1_RELOAD_EEPROM is also valid for 88E6250 */ + int bit = __bf_shf(MV88E6185_G1_CTL1_RELOAD_EEPROM); + u16 val; + int err; + + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &val); + if (err) + return err; + + val |= MV88E6185_G1_CTL1_RELOAD_EEPROM; + + err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL1, val); + if (err) + return err; + + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_CTL1, bit, 0); +} + +/* Returns 0 when done, -EBUSY when waiting, other negative codes on error */ +static int mv88e6xxx_g1_is_eeprom_done(struct mv88e6xxx_chip *chip) +{ + u16 val; + int err; + + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val); + if (err < 0) { + dev_err(chip->dev, "Error reading status"); + return err; + } + + /* If the switch is still resetting, it may not + * respond on the bus, and so MDIO read returns + * 0xffff. Differentiate between that, and waiting for + * the EEPROM to be done by bit 0 being set. + */ + if (val == 0xffff || !(val & BIT(MV88E6XXX_G1_STS_IRQ_EEPROM_DONE))) + return -EBUSY; + + return 0; +} + +/* As the EEInt (EEPROM done) flag clears on read if the status register, this + * function must be called directly after a hard reset or EEPROM ReLoad request, + * or the done condition may have been missed + */ +int mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip) +{ + const unsigned long timeout = jiffies + 1 * HZ; + int ret; + + /* Wait up to 1 second for the switch to finish reading the + * EEPROM. + */ + while (time_before(jiffies, timeout)) { + ret = mv88e6xxx_g1_is_eeprom_done(chip); + if (ret != -EBUSY) + return ret; + } + + dev_err(chip->dev, "Timeout waiting for EEPROM done"); + return -ETIMEDOUT; +} + +int mv88e6250_g1_wait_eeprom_done_prereset(struct mv88e6xxx_chip *chip) +{ + int ret; + + ret = mv88e6xxx_g1_is_eeprom_done(chip); + if (ret != -EBUSY) + return ret; + + /* Pre-reset, we don't know the state of the switch - when + * mv88e6xxx_g1_is_eeprom_done() returns -EBUSY, that may be because + * the switch is actually busy reading the EEPROM, or because + * MV88E6XXX_G1_STS_IRQ_EEPROM_DONE has been cleared by an unrelated + * status register read already. + * + * To account for the latter case, trigger another EEPROM reload for + * another chance at seeing the done flag. + */ + ret = mv88e6250_g1_eeprom_reload(chip); + if (ret) + return ret; + + return mv88e6xxx_g1_wait_eeprom_done(chip); +} + /* Offset 0x01: Switch MAC Address Register Bytes 0 & 1 * Offset 0x02: Switch MAC Address Register Bytes 2 & 3 * Offset 0x03: Switch MAC Address Register Bytes 4 & 5 diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 1095261f5b490..3dbb7a1b8fe11 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -282,6 +282,8 @@ int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); int mv88e6185_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6352_g1_reset(struct mv88e6xxx_chip *chip); int mv88e6250_g1_reset(struct mv88e6xxx_chip *chip); +int mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip); +int mv88e6250_g1_wait_eeprom_done_prereset(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_enable(struct mv88e6xxx_chip *chip); int mv88e6185_g1_ppu_disable(struct mv88e6xxx_chip *chip); diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index 86deeb347cbc1..ddadeb9bfdaee 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -25,10 +25,25 @@ #define MV88E6250_PORT_STS_PORTMODE_PHY_100_HALF 0x0900 #define MV88E6250_PORT_STS_PORTMODE_PHY_10_FULL 0x0a00 #define MV88E6250_PORT_STS_PORTMODE_PHY_100_FULL 0x0b00 -#define MV88E6250_PORT_STS_PORTMODE_MII_10_HALF 0x0c00 -#define MV88E6250_PORT_STS_PORTMODE_MII_100_HALF 0x0d00 -#define MV88E6250_PORT_STS_PORTMODE_MII_10_FULL 0x0e00 -#define MV88E6250_PORT_STS_PORTMODE_MII_100_FULL 0x0f00 +/* - Modes with PHY suffix use output instead of input clock + * - Modes without RMII or RGMII use MII + * - Modes without speed do not have a fixed speed specified in the manual + * ("DC to x MHz" - variable clock support?) + */ +#define MV88E6250_PORT_STS_PORTMODE_MII_DISABLED 0x0000 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_RGMII 0x0100 +#define MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL_PHY 0x0200 +#define MV88E6250_PORT_STS_PORTMODE_MII_200_RMII_FULL_PHY 0x0400 +#define MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL 0x0600 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL 0x0700 +#define MV88E6250_PORT_STS_PORTMODE_MII_HALF 0x0800 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_HALF_PHY 0x0900 +#define MV88E6250_PORT_STS_PORTMODE_MII_FULL 0x0a00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL_PHY 0x0b00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_HALF_PHY 0x0c00 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_HALF_PHY 0x0d00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_FULL_PHY 0x0e00 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_FULL_PHY 0x0f00 #define MV88E6XXX_PORT_STS_LINK 0x0800 #define MV88E6XXX_PORT_STS_DUPLEX 0x0400 #define MV88E6XXX_PORT_STS_SPEED_MASK 0x0300 diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 7a864329cb726..95d78b3181d1c 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -954,7 +954,7 @@ qca8k_mdio_register(struct qca8k_priv *priv) mdio = of_get_child_by_name(dev->of_node, "mdio"); if (mdio && !of_device_is_available(mdio)) - goto out; + goto out_put_node; bus = devm_mdiobus_alloc(dev); if (!bus) { @@ -988,7 +988,6 @@ qca8k_mdio_register(struct qca8k_priv *priv) out_put_node: of_node_put(mdio); -out: return err; } diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c index 811ebeeff4ed7..43ac68052baf9 100644 --- a/drivers/net/dsa/qca/qca8k-leds.c +++ b/drivers/net/dsa/qca/qca8k-leds.c @@ -431,8 +431,11 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d", priv->internal_mdio_bus->id, port_num); - if (!init_data.devicename) + if (!init_data.devicename) { + fwnode_handle_put(led); + fwnode_handle_put(leds); return -ENOMEM; + } ret = devm_led_classdev_register_ext(priv->dev, &port_led->cdev, &init_data); if (ret) @@ -441,6 +444,7 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p kfree(init_data.devicename); } + fwnode_handle_put(leds); return 0; } @@ -471,9 +475,13 @@ qca8k_setup_led_ctrl(struct qca8k_priv *priv) * the correct port for LED setup. */ ret = qca8k_parse_port_leds(priv, port, qca8k_port_to_phy(port_num)); - if (ret) + if (ret) { + fwnode_handle_put(port); + fwnode_handle_put(ports); return ret; + } } + fwnode_handle_put(ports); return 0; } diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c index e3b6a470ca67f..874e04cf2e0d2 100644 --- a/drivers/net/dsa/realtek/rtl8366rb.c +++ b/drivers/net/dsa/realtek/rtl8366rb.c @@ -182,7 +182,12 @@ #define RTL8366RB_LED_BLINKRATE_222MS 0x0004 #define RTL8366RB_LED_BLINKRATE_446MS 0x0005 +/* LED trigger event for each group */ #define RTL8366RB_LED_CTRL_REG 0x0431 +#define RTL8366RB_LED_CTRL_OFFSET(led_group) \ + (4 * (led_group)) +#define RTL8366RB_LED_CTRL_MASK(led_group) \ + (0xf << RTL8366RB_LED_CTRL_OFFSET(led_group)) #define RTL8366RB_LED_OFF 0x0 #define RTL8366RB_LED_DUP_COL 0x1 #define RTL8366RB_LED_LINK_ACT 0x2 @@ -199,6 +204,11 @@ #define RTL8366RB_LED_LINK_TX 0xd #define RTL8366RB_LED_MASTER 0xe #define RTL8366RB_LED_FORCE 0xf + +/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only + * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is + * RTL8366RB_LED_FORCE. Otherwise, it is ignored. + */ #define RTL8366RB_LED_0_1_CTRL_REG 0x0432 #define RTL8366RB_LED_1_OFFSET 6 #define RTL8366RB_LED_2_3_CTRL_REG 0x0433 @@ -998,28 +1008,20 @@ static int rtl8366rb_setup(struct dsa_switch *ds) */ if (priv->leds_disabled) { /* Turn everything off */ - regmap_update_bits(priv->map, - RTL8366RB_LED_0_1_CTRL_REG, - 0x0FFF, 0); - regmap_update_bits(priv->map, - RTL8366RB_LED_2_3_CTRL_REG, - 0x0FFF, 0); regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_CONTROL_REG, RTL8366RB_P4_RGMII_LED, 0); - val = RTL8366RB_LED_OFF; - } else { - /* TODO: make this configurable per LED */ - val = RTL8366RB_LED_FORCE; - } - for (i = 0; i < 4; i++) { - ret = regmap_update_bits(priv->map, - RTL8366RB_LED_CTRL_REG, - 0xf << (i * 4), - val << (i * 4)); - if (ret) - return ret; + + for (i = 0; i < RTL8366RB_NUM_LEDGROUPS; i++) { + val = RTL8366RB_LED_OFF << RTL8366RB_LED_CTRL_OFFSET(i); + ret = regmap_update_bits(priv->map, + RTL8366RB_LED_CTRL_REG, + RTL8366RB_LED_CTRL_MASK(i), + val); + if (ret) + return ret; + } } ret = rtl8366_reset_vlan(priv); @@ -1166,52 +1168,6 @@ rtl8366rb_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, } } -static void rb8366rb_set_port_led(struct realtek_priv *priv, - int port, bool enable) -{ - u16 val = enable ? 0x3f : 0; - int ret; - - if (priv->leds_disabled) - return; - - switch (port) { - case 0: - ret = regmap_update_bits(priv->map, - RTL8366RB_LED_0_1_CTRL_REG, - 0x3F, val); - break; - case 1: - ret = regmap_update_bits(priv->map, - RTL8366RB_LED_0_1_CTRL_REG, - 0x3F << RTL8366RB_LED_1_OFFSET, - val << RTL8366RB_LED_1_OFFSET); - break; - case 2: - ret = regmap_update_bits(priv->map, - RTL8366RB_LED_2_3_CTRL_REG, - 0x3F, val); - break; - case 3: - ret = regmap_update_bits(priv->map, - RTL8366RB_LED_2_3_CTRL_REG, - 0x3F << RTL8366RB_LED_3_OFFSET, - val << RTL8366RB_LED_3_OFFSET); - break; - case 4: - ret = regmap_update_bits(priv->map, - RTL8366RB_INTERRUPT_CONTROL_REG, - RTL8366RB_P4_RGMII_LED, - enable ? RTL8366RB_P4_RGMII_LED : 0); - break; - default: - dev_err(priv->dev, "no LED for port %d\n", port); - return; - } - if (ret) - dev_err(priv->dev, "error updating LED on port %d\n", port); -} - static int rtl8366rb_port_enable(struct dsa_switch *ds, int port, struct phy_device *phy) @@ -1225,7 +1181,6 @@ rtl8366rb_port_enable(struct dsa_switch *ds, int port, if (ret) return ret; - rb8366rb_set_port_led(priv, port, true); return 0; } @@ -1240,8 +1195,6 @@ rtl8366rb_port_disable(struct dsa_switch *ds, int port) BIT(port)); if (ret) return; - - rb8366rb_set_port_led(priv, port, false); } static int diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 833e55e4b9612..52ddb4ef259e9 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -94,7 +94,7 @@ int sja1110_pcs_mdio_read_c45(struct mii_bus *bus, int phy, int mmd, int reg) return tmp & 0xffff; } -int sja1110_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int reg, int mmd, +int sja1110_pcs_mdio_write_c45(struct mii_bus *bus, int phy, int mmd, int reg, u16 val) { struct sja1105_mdio_private *mdio_priv = bus->priv; diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 768454aa36d6c..946bba0701a4f 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -71,6 +71,7 @@ static int dummy_dev_init(struct net_device *dev) if (!dev->lstats) return -ENOMEM; + netdev_lockdep_set_classes(dev); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 633b321d7fdd9..276f6a8631fb1 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -90,8 +90,7 @@ static int ena_com_admin_init_sq(struct ena_com_admin_queue *admin_queue) struct ena_com_admin_sq *sq = &admin_queue->sq; u16 size = ADMIN_SQ_SIZE(admin_queue->q_depth); - sq->entries = dma_alloc_coherent(admin_queue->q_dmadev, size, - &sq->dma_addr, GFP_KERNEL); + sq->entries = dma_alloc_coherent(admin_queue->q_dmadev, size, &sq->dma_addr, GFP_KERNEL); if (!sq->entries) { netdev_err(ena_dev->net_device, "Memory allocation failed\n"); @@ -113,8 +112,7 @@ static int ena_com_admin_init_cq(struct ena_com_admin_queue *admin_queue) struct ena_com_admin_cq *cq = &admin_queue->cq; u16 size = ADMIN_CQ_SIZE(admin_queue->q_depth); - cq->entries = dma_alloc_coherent(admin_queue->q_dmadev, size, - &cq->dma_addr, GFP_KERNEL); + cq->entries = dma_alloc_coherent(admin_queue->q_dmadev, size, &cq->dma_addr, GFP_KERNEL); if (!cq->entries) { netdev_err(ena_dev->net_device, "Memory allocation failed\n"); @@ -136,8 +134,7 @@ static int ena_com_admin_init_aenq(struct ena_com_dev *ena_dev, ena_dev->aenq.q_depth = ENA_ASYNC_QUEUE_DEPTH; size = ADMIN_AENQ_SIZE(ENA_ASYNC_QUEUE_DEPTH); - aenq->entries = dma_alloc_coherent(ena_dev->dmadev, size, - &aenq->dma_addr, GFP_KERNEL); + aenq->entries = dma_alloc_coherent(ena_dev->dmadev, size, &aenq->dma_addr, GFP_KERNEL); if (!aenq->entries) { netdev_err(ena_dev->net_device, "Memory allocation failed\n"); @@ -155,14 +152,13 @@ static int ena_com_admin_init_aenq(struct ena_com_dev *ena_dev, aenq_caps = 0; aenq_caps |= ena_dev->aenq.q_depth & ENA_REGS_AENQ_CAPS_AENQ_DEPTH_MASK; - aenq_caps |= (sizeof(struct ena_admin_aenq_entry) - << ENA_REGS_AENQ_CAPS_AENQ_ENTRY_SIZE_SHIFT) & - ENA_REGS_AENQ_CAPS_AENQ_ENTRY_SIZE_MASK; + aenq_caps |= + (sizeof(struct ena_admin_aenq_entry) << ENA_REGS_AENQ_CAPS_AENQ_ENTRY_SIZE_SHIFT) & + ENA_REGS_AENQ_CAPS_AENQ_ENTRY_SIZE_MASK; writel(aenq_caps, ena_dev->reg_bar + ENA_REGS_AENQ_CAPS_OFF); if (unlikely(!aenq_handlers)) { - netdev_err(ena_dev->net_device, - "AENQ handlers pointer is NULL\n"); + netdev_err(ena_dev->net_device, "AENQ handlers pointer is NULL\n"); return -EINVAL; } @@ -189,14 +185,12 @@ static struct ena_comp_ctx *get_comp_ctxt(struct ena_com_admin_queue *admin_queu } if (unlikely(!admin_queue->comp_ctx)) { - netdev_err(admin_queue->ena_dev->net_device, - "Completion context is NULL\n"); + netdev_err(admin_queue->ena_dev->net_device, "Completion context is NULL\n"); return NULL; } if (unlikely(admin_queue->comp_ctx[command_id].occupied && capture)) { - netdev_err(admin_queue->ena_dev->net_device, - "Completion context is occupied\n"); + netdev_err(admin_queue->ena_dev->net_device, "Completion context is occupied\n"); return NULL; } @@ -226,8 +220,7 @@ static struct ena_comp_ctx *__ena_com_submit_admin_cmd(struct ena_com_admin_queu /* In case of queue FULL */ cnt = (u16)atomic_read(&admin_queue->outstanding_cmds); if (cnt >= admin_queue->q_depth) { - netdev_dbg(admin_queue->ena_dev->net_device, - "Admin queue is full.\n"); + netdev_dbg(admin_queue->ena_dev->net_device, "Admin queue is full.\n"); admin_queue->stats.out_of_space++; return ERR_PTR(-ENOSPC); } @@ -274,8 +267,7 @@ static int ena_com_init_comp_ctxt(struct ena_com_admin_queue *admin_queue) struct ena_comp_ctx *comp_ctx; u16 i; - admin_queue->comp_ctx = - devm_kzalloc(admin_queue->q_dmadev, size, GFP_KERNEL); + admin_queue->comp_ctx = devm_kzalloc(admin_queue->q_dmadev, size, GFP_KERNEL); if (unlikely(!admin_queue->comp_ctx)) { netdev_err(ena_dev->net_device, "Memory allocation failed\n"); return -ENOMEM; @@ -320,7 +312,6 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, struct ena_com_io_sq *io_sq) { size_t size; - int dev_node = 0; memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr)); @@ -333,23 +324,17 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, size = io_sq->desc_entry_size * io_sq->q_depth; if (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_HOST) { - dev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); io_sq->desc_addr.virt_addr = - dma_alloc_coherent(ena_dev->dmadev, size, - &io_sq->desc_addr.phys_addr, + dma_alloc_coherent(ena_dev->dmadev, size, &io_sq->desc_addr.phys_addr, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, dev_node); if (!io_sq->desc_addr.virt_addr) { io_sq->desc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, - &io_sq->desc_addr.phys_addr, - GFP_KERNEL); + &io_sq->desc_addr.phys_addr, GFP_KERNEL); } if (!io_sq->desc_addr.virt_addr) { - netdev_err(ena_dev->net_device, - "Memory allocation failed\n"); + netdev_err(ena_dev->net_device, "Memory allocation failed\n"); return -ENOMEM; } } @@ -362,21 +347,16 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, ENA_COM_BOUNCE_BUFFER_CNTRL_CNT; io_sq->bounce_buf_ctrl.next_to_use = 0; - size = io_sq->bounce_buf_ctrl.buffer_size * + size = (size_t)io_sq->bounce_buf_ctrl.buffer_size * io_sq->bounce_buf_ctrl.buffers_num; - dev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); - io_sq->bounce_buf_ctrl.base_buffer = - devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, dev_node); + io_sq->bounce_buf_ctrl.base_buffer = devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL); if (!io_sq->bounce_buf_ctrl.base_buffer) io_sq->bounce_buf_ctrl.base_buffer = devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL); if (!io_sq->bounce_buf_ctrl.base_buffer) { - netdev_err(ena_dev->net_device, - "Bounce buffer memory allocation failed\n"); + netdev_err(ena_dev->net_device, "Bounce buffer memory allocation failed\n"); return -ENOMEM; } @@ -410,7 +390,6 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev, struct ena_com_io_cq *io_cq) { size_t size; - int prev_node = 0; memset(&io_cq->cdesc_addr, 0x0, sizeof(io_cq->cdesc_addr)); @@ -422,16 +401,11 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev, size = io_cq->cdesc_entry_size_in_bytes * io_cq->q_depth; - prev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); io_cq->cdesc_addr.virt_addr = - dma_alloc_coherent(ena_dev->dmadev, size, - &io_cq->cdesc_addr.phys_addr, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, prev_node); + dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr, GFP_KERNEL); if (!io_cq->cdesc_addr.virt_addr) { io_cq->cdesc_addr.virt_addr = - dma_alloc_coherent(ena_dev->dmadev, size, - &io_cq->cdesc_addr.phys_addr, + dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr, GFP_KERNEL); } @@ -514,8 +488,8 @@ static int ena_com_comp_status_to_errno(struct ena_com_admin_queue *admin_queue, u8 comp_status) { if (unlikely(comp_status != 0)) - netdev_err(admin_queue->ena_dev->net_device, - "Admin command failed[%u]\n", comp_status); + netdev_err(admin_queue->ena_dev->net_device, "Admin command failed[%u]\n", + comp_status); switch (comp_status) { case ENA_ADMIN_SUCCESS: @@ -580,8 +554,7 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c } if (unlikely(comp_ctx->status == ENA_CMD_ABORTED)) { - netdev_err(admin_queue->ena_dev->net_device, - "Command was aborted\n"); + netdev_err(admin_queue->ena_dev->net_device, "Command was aborted\n"); spin_lock_irqsave(&admin_queue->q_lock, flags); admin_queue->stats.aborted_cmd++; spin_unlock_irqrestore(&admin_queue->q_lock, flags); @@ -589,8 +562,7 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c goto err; } - WARN(comp_ctx->status != ENA_CMD_COMPLETED, "Invalid comp status %d\n", - comp_ctx->status); + WARN(comp_ctx->status != ENA_CMD_COMPLETED, "Invalid comp status %d\n", comp_ctx->status); ret = ena_com_comp_status_to_errno(admin_queue, comp_ctx->comp_status); err: @@ -634,8 +606,7 @@ static int ena_com_set_llq(struct ena_com_dev *ena_dev) sizeof(resp)); if (unlikely(ret)) - netdev_err(ena_dev->net_device, - "Failed to set LLQ configurations: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to set LLQ configurations: %d\n", ret); return ret; } @@ -658,8 +629,7 @@ static int ena_com_config_llq_info(struct ena_com_dev *ena_dev, llq_default_cfg->llq_header_location; } else { netdev_err(ena_dev->net_device, - "Invalid header location control, supported: 0x%x\n", - supported_feat); + "Invalid header location control, supported: 0x%x\n", supported_feat); return -EINVAL; } @@ -681,8 +651,8 @@ static int ena_com_config_llq_info(struct ena_com_dev *ena_dev, netdev_err(ena_dev->net_device, "Default llq stride ctrl is not supported, performing fallback, default: 0x%x, supported: 0x%x, used: 0x%x\n", - llq_default_cfg->llq_stride_ctrl, - supported_feat, llq_info->desc_stride_ctrl); + llq_default_cfg->llq_stride_ctrl, supported_feat, + llq_info->desc_stride_ctrl); } } else { llq_info->desc_stride_ctrl = 0; @@ -704,8 +674,7 @@ static int ena_com_config_llq_info(struct ena_com_dev *ena_dev, llq_info->desc_list_entry_size = 256; } else { netdev_err(ena_dev->net_device, - "Invalid entry_size_ctrl, supported: 0x%x\n", - supported_feat); + "Invalid entry_size_ctrl, supported: 0x%x\n", supported_feat); return -EINVAL; } @@ -750,8 +719,8 @@ static int ena_com_config_llq_info(struct ena_com_dev *ena_dev, netdev_err(ena_dev->net_device, "Default llq num descs before header is not supported, performing fallback, default: 0x%x, supported: 0x%x, used: 0x%x\n", - llq_default_cfg->llq_num_decs_before_header, - supported_feat, llq_info->descs_num_before_header); + llq_default_cfg->llq_num_decs_before_header, supported_feat, + llq_info->descs_num_before_header); } /* Check for accelerated queue supported */ llq_accel_mode_get = llq_features->accel_mode.u.get; @@ -767,8 +736,7 @@ static int ena_com_config_llq_info(struct ena_com_dev *ena_dev, rc = ena_com_set_llq(ena_dev); if (rc) - netdev_err(ena_dev->net_device, - "Cannot set LLQ configuration: %d\n", rc); + netdev_err(ena_dev->net_device, "Cannot set LLQ configuration: %d\n", rc); return rc; } @@ -780,8 +748,7 @@ static int ena_com_wait_and_process_admin_cq_interrupts(struct ena_comp_ctx *com int ret; wait_for_completion_timeout(&comp_ctx->wait_event, - usecs_to_jiffies( - admin_queue->completion_timeout)); + usecs_to_jiffies(admin_queue->completion_timeout)); /* In case the command wasn't completed find out the root cause. * There might be 2 kinds of errors @@ -797,8 +764,7 @@ static int ena_com_wait_and_process_admin_cq_interrupts(struct ena_comp_ctx *com if (comp_ctx->status == ENA_CMD_COMPLETED) { netdev_err(admin_queue->ena_dev->net_device, "The ena device sent a completion but the driver didn't receive a MSI-X interrupt (cmd %d), autopolling mode is %s\n", - comp_ctx->cmd_opcode, - admin_queue->auto_polling ? "ON" : "OFF"); + comp_ctx->cmd_opcode, admin_queue->auto_polling ? "ON" : "OFF"); /* Check if fallback to polling is enabled */ if (admin_queue->auto_polling) admin_queue->polling = true; @@ -867,15 +833,13 @@ static u32 ena_com_reg_bar_read32(struct ena_com_dev *ena_dev, u16 offset) if (unlikely(i == timeout)) { netdev_err(ena_dev->net_device, "Reading reg failed for timeout. expected: req id[%u] offset[%u] actual: req id[%u] offset[%u]\n", - mmio_read->seq_num, offset, read_resp->req_id, - read_resp->reg_off); + mmio_read->seq_num, offset, read_resp->req_id, read_resp->reg_off); ret = ENA_MMIO_READ_TIMEOUT; goto err; } if (read_resp->reg_off != offset) { - netdev_err(ena_dev->net_device, - "Read failure: wrong offset provided\n"); + netdev_err(ena_dev->net_device, "Read failure: wrong offset provided\n"); ret = ENA_MMIO_READ_TIMEOUT; } else { ret = read_resp->reg_val; @@ -934,8 +898,7 @@ static int ena_com_destroy_io_sq(struct ena_com_dev *ena_dev, sizeof(destroy_resp)); if (unlikely(ret && (ret != -ENODEV))) - netdev_err(ena_dev->net_device, - "Failed to destroy io sq error: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to destroy io sq error: %d\n", ret); return ret; } @@ -949,8 +912,7 @@ static void ena_com_io_queue_free(struct ena_com_dev *ena_dev, if (io_cq->cdesc_addr.virt_addr) { size = io_cq->cdesc_entry_size_in_bytes * io_cq->q_depth; - dma_free_coherent(ena_dev->dmadev, size, - io_cq->cdesc_addr.virt_addr, + dma_free_coherent(ena_dev->dmadev, size, io_cq->cdesc_addr.virt_addr, io_cq->cdesc_addr.phys_addr); io_cq->cdesc_addr.virt_addr = NULL; @@ -959,8 +921,7 @@ static void ena_com_io_queue_free(struct ena_com_dev *ena_dev, if (io_sq->desc_addr.virt_addr) { size = io_sq->desc_entry_size * io_sq->q_depth; - dma_free_coherent(ena_dev->dmadev, size, - io_sq->desc_addr.virt_addr, + dma_free_coherent(ena_dev->dmadev, size, io_sq->desc_addr.virt_addr, io_sq->desc_addr.phys_addr); io_sq->desc_addr.virt_addr = NULL; @@ -985,8 +946,7 @@ static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout, val = ena_com_reg_bar_read32(ena_dev, ENA_REGS_DEV_STS_OFF); if (unlikely(val == ENA_MMIO_READ_TIMEOUT)) { - netdev_err(ena_dev->net_device, - "Reg read timeout occurred\n"); + netdev_err(ena_dev->net_device, "Reg read timeout occurred\n"); return -ETIME; } @@ -1026,8 +986,7 @@ static int ena_com_get_feature_ex(struct ena_com_dev *ena_dev, int ret; if (!ena_com_check_supported_feature_id(ena_dev, feature_id)) { - netdev_dbg(ena_dev->net_device, "Feature %d isn't supported\n", - feature_id); + netdev_dbg(ena_dev->net_device, "Feature %d isn't supported\n", feature_id); return -EOPNOTSUPP; } @@ -1064,8 +1023,7 @@ static int ena_com_get_feature_ex(struct ena_com_dev *ena_dev, if (unlikely(ret)) netdev_err(ena_dev->net_device, - "Failed to submit get_feature command %d error: %d\n", - feature_id, ret); + "Failed to submit get_feature command %d error: %d\n", feature_id, ret); return ret; } @@ -1104,13 +1062,11 @@ static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev) { struct ena_rss *rss = &ena_dev->rss; - if (!ena_com_check_supported_feature_id(ena_dev, - ENA_ADMIN_RSS_HASH_FUNCTION)) + if (!ena_com_check_supported_feature_id(ena_dev, ENA_ADMIN_RSS_HASH_FUNCTION)) return -EOPNOTSUPP; - rss->hash_key = - dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key), - &rss->hash_key_dma_addr, GFP_KERNEL); + rss->hash_key = dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key), + &rss->hash_key_dma_addr, GFP_KERNEL); if (unlikely(!rss->hash_key)) return -ENOMEM; @@ -1123,8 +1079,8 @@ static void ena_com_hash_key_destroy(struct ena_com_dev *ena_dev) struct ena_rss *rss = &ena_dev->rss; if (rss->hash_key) - dma_free_coherent(ena_dev->dmadev, sizeof(*rss->hash_key), - rss->hash_key, rss->hash_key_dma_addr); + dma_free_coherent(ena_dev->dmadev, sizeof(*rss->hash_key), rss->hash_key, + rss->hash_key_dma_addr); rss->hash_key = NULL; } @@ -1132,9 +1088,8 @@ static int ena_com_hash_ctrl_init(struct ena_com_dev *ena_dev) { struct ena_rss *rss = &ena_dev->rss; - rss->hash_ctrl = - dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_ctrl), - &rss->hash_ctrl_dma_addr, GFP_KERNEL); + rss->hash_ctrl = dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_ctrl), + &rss->hash_ctrl_dma_addr, GFP_KERNEL); if (unlikely(!rss->hash_ctrl)) return -ENOMEM; @@ -1147,8 +1102,8 @@ static void ena_com_hash_ctrl_destroy(struct ena_com_dev *ena_dev) struct ena_rss *rss = &ena_dev->rss; if (rss->hash_ctrl) - dma_free_coherent(ena_dev->dmadev, sizeof(*rss->hash_ctrl), - rss->hash_ctrl, rss->hash_ctrl_dma_addr); + dma_free_coherent(ena_dev->dmadev, sizeof(*rss->hash_ctrl), rss->hash_ctrl, + rss->hash_ctrl_dma_addr); rss->hash_ctrl = NULL; } @@ -1177,15 +1132,13 @@ static int ena_com_indirect_table_allocate(struct ena_com_dev *ena_dev, tbl_size = (1ULL << log_size) * sizeof(struct ena_admin_rss_ind_table_entry); - rss->rss_ind_tbl = - dma_alloc_coherent(ena_dev->dmadev, tbl_size, - &rss->rss_ind_tbl_dma_addr, GFP_KERNEL); + rss->rss_ind_tbl = dma_alloc_coherent(ena_dev->dmadev, tbl_size, &rss->rss_ind_tbl_dma_addr, + GFP_KERNEL); if (unlikely(!rss->rss_ind_tbl)) goto mem_err1; tbl_size = (1ULL << log_size) * sizeof(u16); - rss->host_rss_ind_tbl = - devm_kzalloc(ena_dev->dmadev, tbl_size, GFP_KERNEL); + rss->host_rss_ind_tbl = devm_kzalloc(ena_dev->dmadev, tbl_size, GFP_KERNEL); if (unlikely(!rss->host_rss_ind_tbl)) goto mem_err2; @@ -1197,8 +1150,7 @@ static int ena_com_indirect_table_allocate(struct ena_com_dev *ena_dev, tbl_size = (1ULL << log_size) * sizeof(struct ena_admin_rss_ind_table_entry); - dma_free_coherent(ena_dev->dmadev, tbl_size, rss->rss_ind_tbl, - rss->rss_ind_tbl_dma_addr); + dma_free_coherent(ena_dev->dmadev, tbl_size, rss->rss_ind_tbl, rss->rss_ind_tbl_dma_addr); rss->rss_ind_tbl = NULL; mem_err1: rss->tbl_log_size = 0; @@ -1261,8 +1213,7 @@ static int ena_com_create_io_sq(struct ena_com_dev *ena_dev, &create_cmd.sq_ba, io_sq->desc_addr.phys_addr); if (unlikely(ret)) { - netdev_err(ena_dev->net_device, - "Memory address set failed\n"); + netdev_err(ena_dev->net_device, "Memory address set failed\n"); return ret; } } @@ -1273,8 +1224,7 @@ static int ena_com_create_io_sq(struct ena_com_dev *ena_dev, (struct ena_admin_acq_entry *)&cmd_completion, sizeof(cmd_completion)); if (unlikely(ret)) { - netdev_err(ena_dev->net_device, - "Failed to create IO SQ. error: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to create IO SQ. error: %d\n", ret); return ret; } @@ -1292,8 +1242,7 @@ static int ena_com_create_io_sq(struct ena_com_dev *ena_dev, cmd_completion.llq_descriptors_offset); } - netdev_dbg(ena_dev->net_device, "Created sq[%u], depth[%u]\n", - io_sq->idx, io_sq->q_depth); + netdev_dbg(ena_dev->net_device, "Created sq[%u], depth[%u]\n", io_sq->idx, io_sq->q_depth); return ret; } @@ -1420,8 +1369,7 @@ int ena_com_create_io_cq(struct ena_com_dev *ena_dev, (struct ena_admin_acq_entry *)&cmd_completion, sizeof(cmd_completion)); if (unlikely(ret)) { - netdev_err(ena_dev->net_device, - "Failed to create IO CQ. error: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to create IO CQ. error: %d\n", ret); return ret; } @@ -1440,8 +1388,7 @@ int ena_com_create_io_cq(struct ena_com_dev *ena_dev, (u32 __iomem *)((uintptr_t)ena_dev->reg_bar + cmd_completion.numa_node_register_offset); - netdev_dbg(ena_dev->net_device, "Created cq[%u], depth[%u]\n", - io_cq->idx, io_cq->q_depth); + netdev_dbg(ena_dev->net_device, "Created cq[%u], depth[%u]\n", io_cq->idx, io_cq->q_depth); return ret; } @@ -1451,8 +1398,7 @@ int ena_com_get_io_handlers(struct ena_com_dev *ena_dev, u16 qid, struct ena_com_io_cq **io_cq) { if (qid >= ENA_TOTAL_NUM_QUEUES) { - netdev_err(ena_dev->net_device, - "Invalid queue number %d but the max is %d\n", qid, + netdev_err(ena_dev->net_device, "Invalid queue number %d but the max is %d\n", qid, ENA_TOTAL_NUM_QUEUES); return -EINVAL; } @@ -1492,8 +1438,7 @@ void ena_com_wait_for_abort_completion(struct ena_com_dev *ena_dev) spin_lock_irqsave(&admin_queue->q_lock, flags); while (atomic_read(&admin_queue->outstanding_cmds) != 0) { spin_unlock_irqrestore(&admin_queue->q_lock, flags); - ena_delay_exponential_backoff_us(exp++, - ena_dev->ena_min_poll_delay_us); + ena_delay_exponential_backoff_us(exp++, ena_dev->ena_min_poll_delay_us); spin_lock_irqsave(&admin_queue->q_lock, flags); } spin_unlock_irqrestore(&admin_queue->q_lock, flags); @@ -1519,8 +1464,7 @@ int ena_com_destroy_io_cq(struct ena_com_dev *ena_dev, sizeof(destroy_resp)); if (unlikely(ret && (ret != -ENODEV))) - netdev_err(ena_dev->net_device, - "Failed to destroy IO CQ. error: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to destroy IO CQ. error: %d\n", ret); return ret; } @@ -1588,8 +1532,7 @@ int ena_com_set_aenq_config(struct ena_com_dev *ena_dev, u32 groups_flag) sizeof(resp)); if (unlikely(ret)) - netdev_err(ena_dev->net_device, - "Failed to config AENQ ret: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to config AENQ ret: %d\n", ret); return ret; } @@ -1610,8 +1553,7 @@ int ena_com_get_dma_width(struct ena_com_dev *ena_dev) netdev_dbg(ena_dev->net_device, "ENA dma width: %d\n", width); if ((width < 32) || width > ENA_MAX_PHYS_ADDR_SIZE_BITS) { - netdev_err(ena_dev->net_device, "DMA width illegal value: %d\n", - width); + netdev_err(ena_dev->net_device, "DMA width illegal value: %d\n", width); return -EINVAL; } @@ -1633,19 +1575,16 @@ int ena_com_validate_version(struct ena_com_dev *ena_dev) ctrl_ver = ena_com_reg_bar_read32(ena_dev, ENA_REGS_CONTROLLER_VERSION_OFF); - if (unlikely((ver == ENA_MMIO_READ_TIMEOUT) || - (ctrl_ver == ENA_MMIO_READ_TIMEOUT))) { + if (unlikely((ver == ENA_MMIO_READ_TIMEOUT) || (ctrl_ver == ENA_MMIO_READ_TIMEOUT))) { netdev_err(ena_dev->net_device, "Reg read timeout occurred\n"); return -ETIME; } dev_info(ena_dev->dmadev, "ENA device version: %d.%d\n", - (ver & ENA_REGS_VERSION_MAJOR_VERSION_MASK) >> - ENA_REGS_VERSION_MAJOR_VERSION_SHIFT, + (ver & ENA_REGS_VERSION_MAJOR_VERSION_MASK) >> ENA_REGS_VERSION_MAJOR_VERSION_SHIFT, ver & ENA_REGS_VERSION_MINOR_VERSION_MASK); - dev_info(ena_dev->dmadev, - "ENA controller version: %d.%d.%d implementation version %d\n", + dev_info(ena_dev->dmadev, "ENA controller version: %d.%d.%d implementation version %d\n", (ctrl_ver & ENA_REGS_CONTROLLER_VERSION_MAJOR_VERSION_MASK) >> ENA_REGS_CONTROLLER_VERSION_MAJOR_VERSION_SHIFT, (ctrl_ver & ENA_REGS_CONTROLLER_VERSION_MINOR_VERSION_MASK) >> @@ -1694,20 +1633,17 @@ void ena_com_admin_destroy(struct ena_com_dev *ena_dev) size = ADMIN_SQ_SIZE(admin_queue->q_depth); if (sq->entries) - dma_free_coherent(ena_dev->dmadev, size, sq->entries, - sq->dma_addr); + dma_free_coherent(ena_dev->dmadev, size, sq->entries, sq->dma_addr); sq->entries = NULL; size = ADMIN_CQ_SIZE(admin_queue->q_depth); if (cq->entries) - dma_free_coherent(ena_dev->dmadev, size, cq->entries, - cq->dma_addr); + dma_free_coherent(ena_dev->dmadev, size, cq->entries, cq->dma_addr); cq->entries = NULL; size = ADMIN_AENQ_SIZE(aenq->q_depth); if (ena_dev->aenq.entries) - dma_free_coherent(ena_dev->dmadev, size, aenq->entries, - aenq->dma_addr); + dma_free_coherent(ena_dev->dmadev, size, aenq->entries, aenq->dma_addr); aenq->entries = NULL; } @@ -1733,10 +1669,8 @@ int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev) struct ena_com_mmio_read *mmio_read = &ena_dev->mmio_read; spin_lock_init(&mmio_read->lock); - mmio_read->read_resp = - dma_alloc_coherent(ena_dev->dmadev, - sizeof(*mmio_read->read_resp), - &mmio_read->read_resp_dma_addr, GFP_KERNEL); + mmio_read->read_resp = dma_alloc_coherent(ena_dev->dmadev, sizeof(*mmio_read->read_resp), + &mmio_read->read_resp_dma_addr, GFP_KERNEL); if (unlikely(!mmio_read->read_resp)) goto err; @@ -1767,8 +1701,8 @@ void ena_com_mmio_reg_read_request_destroy(struct ena_com_dev *ena_dev) writel(0x0, ena_dev->reg_bar + ENA_REGS_MMIO_RESP_LO_OFF); writel(0x0, ena_dev->reg_bar + ENA_REGS_MMIO_RESP_HI_OFF); - dma_free_coherent(ena_dev->dmadev, sizeof(*mmio_read->read_resp), - mmio_read->read_resp, mmio_read->read_resp_dma_addr); + dma_free_coherent(ena_dev->dmadev, sizeof(*mmio_read->read_resp), mmio_read->read_resp, + mmio_read->read_resp_dma_addr); mmio_read->read_resp = NULL; } @@ -1800,8 +1734,7 @@ int ena_com_admin_init(struct ena_com_dev *ena_dev, } if (!(dev_sts & ENA_REGS_DEV_STS_READY_MASK)) { - netdev_err(ena_dev->net_device, - "Device isn't ready, abort com init\n"); + netdev_err(ena_dev->net_device, "Device isn't ready, abort com init\n"); return -ENODEV; } @@ -1878,8 +1811,7 @@ int ena_com_create_io_queue(struct ena_com_dev *ena_dev, int ret; if (ctx->qid >= ENA_TOTAL_NUM_QUEUES) { - netdev_err(ena_dev->net_device, - "Qid (%d) is bigger than max num of queues (%d)\n", + netdev_err(ena_dev->net_device, "Qid (%d) is bigger than max num of queues (%d)\n", ctx->qid, ENA_TOTAL_NUM_QUEUES); return -EINVAL; } @@ -1905,8 +1837,7 @@ int ena_com_create_io_queue(struct ena_com_dev *ena_dev, if (ctx->direction == ENA_COM_IO_QUEUE_DIRECTION_TX) /* header length is limited to 8 bits */ - io_sq->tx_max_header_size = - min_t(u32, ena_dev->tx_max_header_size, SZ_256); + io_sq->tx_max_header_size = min_t(u32, ena_dev->tx_max_header_size, SZ_256); ret = ena_com_init_io_sq(ena_dev, ctx, io_sq); if (ret) @@ -1938,8 +1869,7 @@ void ena_com_destroy_io_queue(struct ena_com_dev *ena_dev, u16 qid) struct ena_com_io_cq *io_cq; if (qid >= ENA_TOTAL_NUM_QUEUES) { - netdev_err(ena_dev->net_device, - "Qid (%d) is bigger than max num of queues (%d)\n", + netdev_err(ena_dev->net_device, "Qid (%d) is bigger than max num of queues (%d)\n", qid, ENA_TOTAL_NUM_QUEUES); return; } @@ -1983,8 +1913,7 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev, if (rc) return rc; - if (get_resp.u.max_queue_ext.version != - ENA_FEATURE_MAX_QUEUE_EXT_VER) + if (get_resp.u.max_queue_ext.version != ENA_FEATURE_MAX_QUEUE_EXT_VER) return -EINVAL; memcpy(&get_feat_ctx->max_queue_ext, &get_resp.u.max_queue_ext, @@ -2025,18 +1954,15 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev, rc = ena_com_get_feature(ena_dev, &get_resp, ENA_ADMIN_HW_HINTS, 0); if (!rc) - memcpy(&get_feat_ctx->hw_hints, &get_resp.u.hw_hints, - sizeof(get_resp.u.hw_hints)); + memcpy(&get_feat_ctx->hw_hints, &get_resp.u.hw_hints, sizeof(get_resp.u.hw_hints)); else if (rc == -EOPNOTSUPP) - memset(&get_feat_ctx->hw_hints, 0x0, - sizeof(get_feat_ctx->hw_hints)); + memset(&get_feat_ctx->hw_hints, 0x0, sizeof(get_feat_ctx->hw_hints)); else return rc; rc = ena_com_get_feature(ena_dev, &get_resp, ENA_ADMIN_LLQ, 0); if (!rc) - memcpy(&get_feat_ctx->llq, &get_resp.u.llq, - sizeof(get_resp.u.llq)); + memcpy(&get_feat_ctx->llq, &get_resp.u.llq, sizeof(get_resp.u.llq)); else if (rc == -EOPNOTSUPP) memset(&get_feat_ctx->llq, 0x0, sizeof(get_feat_ctx->llq)); else @@ -2084,8 +2010,7 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *ena_dev, void *data) aenq_common = &aenq_e->aenq_common_desc; /* Go over all the events */ - while ((READ_ONCE(aenq_common->flags) & - ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK) == phase) { + while ((READ_ONCE(aenq_common->flags) & ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK) == phase) { /* Make sure the phase bit (ownership) is as expected before * reading the rest of the descriptor. */ @@ -2094,8 +2019,7 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *ena_dev, void *data) timestamp = (u64)aenq_common->timestamp_low | ((u64)aenq_common->timestamp_high << 32); - netdev_dbg(ena_dev->net_device, - "AENQ! Group[%x] Syndrome[%x] timestamp: [%llus]\n", + netdev_dbg(ena_dev->net_device, "AENQ! Group[%x] Syndrome[%x] timestamp: [%llus]\n", aenq_common->group, aenq_common->syndrome, timestamp); /* Handle specific event*/ @@ -2124,8 +2048,7 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *ena_dev, void *data) /* write the aenq doorbell after all AENQ descriptors were read */ mb(); - writel_relaxed((u32)aenq->head, - ena_dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF); + writel_relaxed((u32)aenq->head, ena_dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF); } int ena_com_dev_reset(struct ena_com_dev *ena_dev, @@ -2137,15 +2060,13 @@ int ena_com_dev_reset(struct ena_com_dev *ena_dev, stat = ena_com_reg_bar_read32(ena_dev, ENA_REGS_DEV_STS_OFF); cap = ena_com_reg_bar_read32(ena_dev, ENA_REGS_CAPS_OFF); - if (unlikely((stat == ENA_MMIO_READ_TIMEOUT) || - (cap == ENA_MMIO_READ_TIMEOUT))) { + if (unlikely((stat == ENA_MMIO_READ_TIMEOUT) || (cap == ENA_MMIO_READ_TIMEOUT))) { netdev_err(ena_dev->net_device, "Reg read32 timeout occurred\n"); return -ETIME; } if ((stat & ENA_REGS_DEV_STS_READY_MASK) == 0) { - netdev_err(ena_dev->net_device, - "Device isn't ready, can't reset device\n"); + netdev_err(ena_dev->net_device, "Device isn't ready, can't reset device\n"); return -EINVAL; } @@ -2168,8 +2089,7 @@ int ena_com_dev_reset(struct ena_com_dev *ena_dev, rc = wait_for_reset_state(ena_dev, timeout, ENA_REGS_DEV_STS_RESET_IN_PROGRESS_MASK); if (rc != 0) { - netdev_err(ena_dev->net_device, - "Reset indication didn't turn on\n"); + netdev_err(ena_dev->net_device, "Reset indication didn't turn on\n"); return rc; } @@ -2177,8 +2097,7 @@ int ena_com_dev_reset(struct ena_com_dev *ena_dev, writel(0, ena_dev->reg_bar + ENA_REGS_DEV_CTL_OFF); rc = wait_for_reset_state(ena_dev, timeout, 0); if (rc != 0) { - netdev_err(ena_dev->net_device, - "Reset indication didn't turn off\n"); + netdev_err(ena_dev->net_device, "Reset indication didn't turn off\n"); return rc; } @@ -2215,8 +2134,7 @@ static int ena_get_dev_stats(struct ena_com_dev *ena_dev, sizeof(*get_resp)); if (unlikely(ret)) - netdev_err(ena_dev->net_device, - "Failed to get stats. error: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to get stats. error: %d\n", ret); return ret; } @@ -2228,8 +2146,7 @@ int ena_com_get_eni_stats(struct ena_com_dev *ena_dev, int ret; if (!ena_com_get_cap(ena_dev, ENA_ADMIN_ENI_STATS)) { - netdev_err(ena_dev->net_device, - "Capability %d isn't supported\n", + netdev_err(ena_dev->net_device, "Capability %d isn't supported\n", ENA_ADMIN_ENI_STATS); return -EOPNOTSUPP; } @@ -2266,8 +2183,7 @@ int ena_com_set_dev_mtu(struct ena_com_dev *ena_dev, u32 mtu) int ret; if (!ena_com_check_supported_feature_id(ena_dev, ENA_ADMIN_MTU)) { - netdev_dbg(ena_dev->net_device, "Feature %d isn't supported\n", - ENA_ADMIN_MTU); + netdev_dbg(ena_dev->net_device, "Feature %d isn't supported\n", ENA_ADMIN_MTU); return -EOPNOTSUPP; } @@ -2286,8 +2202,7 @@ int ena_com_set_dev_mtu(struct ena_com_dev *ena_dev, u32 mtu) sizeof(resp)); if (unlikely(ret)) - netdev_err(ena_dev->net_device, - "Failed to set mtu %d. error: %d\n", mtu, ret); + netdev_err(ena_dev->net_device, "Failed to set mtu %d. error: %d\n", mtu, ret); return ret; } @@ -2301,8 +2216,7 @@ int ena_com_get_offload_settings(struct ena_com_dev *ena_dev, ret = ena_com_get_feature(ena_dev, &resp, ENA_ADMIN_STATELESS_OFFLOAD_CONFIG, 0); if (unlikely(ret)) { - netdev_err(ena_dev->net_device, - "Failed to get offload capabilities %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to get offload capabilities %d\n", ret); return ret; } @@ -2320,8 +2234,7 @@ int ena_com_set_hash_function(struct ena_com_dev *ena_dev) struct ena_admin_get_feat_resp get_resp; int ret; - if (!ena_com_check_supported_feature_id(ena_dev, - ENA_ADMIN_RSS_HASH_FUNCTION)) { + if (!ena_com_check_supported_feature_id(ena_dev, ENA_ADMIN_RSS_HASH_FUNCTION)) { netdev_dbg(ena_dev->net_device, "Feature %d isn't supported\n", ENA_ADMIN_RSS_HASH_FUNCTION); return -EOPNOTSUPP; @@ -2334,8 +2247,7 @@ int ena_com_set_hash_function(struct ena_com_dev *ena_dev) return ret; if (!(get_resp.u.flow_hash_func.supported_func & BIT(rss->hash_func))) { - netdev_err(ena_dev->net_device, - "Func hash %d isn't supported by device, abort\n", + netdev_err(ena_dev->net_device, "Func hash %d isn't supported by device, abort\n", rss->hash_func); return -EOPNOTSUPP; } @@ -2365,8 +2277,7 @@ int ena_com_set_hash_function(struct ena_com_dev *ena_dev) (struct ena_admin_acq_entry *)&resp, sizeof(resp)); if (unlikely(ret)) { - netdev_err(ena_dev->net_device, - "Failed to set hash function %d. error: %d\n", + netdev_err(ena_dev->net_device, "Failed to set hash function %d. error: %d\n", rss->hash_func, ret); return -EINVAL; } @@ -2398,16 +2309,15 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev, return rc; if (!(BIT(func) & get_resp.u.flow_hash_func.supported_func)) { - netdev_err(ena_dev->net_device, - "Flow hash function %d isn't supported\n", func); + netdev_err(ena_dev->net_device, "Flow hash function %d isn't supported\n", func); return -EOPNOTSUPP; } if ((func == ENA_ADMIN_TOEPLITZ) && key) { if (key_len != sizeof(hash_key->key)) { netdev_err(ena_dev->net_device, - "key len (%u) doesn't equal the supported size (%zu)\n", - key_len, sizeof(hash_key->key)); + "key len (%u) doesn't equal the supported size (%zu)\n", key_len, + sizeof(hash_key->key)); return -EINVAL; } memcpy(hash_key->key, key, key_len); @@ -2495,8 +2405,7 @@ int ena_com_set_hash_ctrl(struct ena_com_dev *ena_dev) struct ena_admin_set_feat_resp resp; int ret; - if (!ena_com_check_supported_feature_id(ena_dev, - ENA_ADMIN_RSS_HASH_INPUT)) { + if (!ena_com_check_supported_feature_id(ena_dev, ENA_ADMIN_RSS_HASH_INPUT)) { netdev_dbg(ena_dev->net_device, "Feature %d isn't supported\n", ENA_ADMIN_RSS_HASH_INPUT); return -EOPNOTSUPP; @@ -2527,8 +2436,7 @@ int ena_com_set_hash_ctrl(struct ena_com_dev *ena_dev) (struct ena_admin_acq_entry *)&resp, sizeof(resp)); if (unlikely(ret)) - netdev_err(ena_dev->net_device, - "Failed to set hash input. error: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to set hash input. error: %d\n", ret); return ret; } @@ -2605,8 +2513,7 @@ int ena_com_fill_hash_ctrl(struct ena_com_dev *ena_dev, int rc; if (proto >= ENA_ADMIN_RSS_PROTO_NUM) { - netdev_err(ena_dev->net_device, "Invalid proto num (%u)\n", - proto); + netdev_err(ena_dev->net_device, "Invalid proto num (%u)\n", proto); return -EINVAL; } @@ -2658,8 +2565,7 @@ int ena_com_indirect_table_set(struct ena_com_dev *ena_dev) struct ena_admin_set_feat_resp resp; int ret; - if (!ena_com_check_supported_feature_id( - ena_dev, ENA_ADMIN_RSS_INDIRECTION_TABLE_CONFIG)) { + if (!ena_com_check_supported_feature_id(ena_dev, ENA_ADMIN_RSS_INDIRECTION_TABLE_CONFIG)) { netdev_dbg(ena_dev->net_device, "Feature %d isn't supported\n", ENA_ADMIN_RSS_INDIRECTION_TABLE_CONFIG); return -EOPNOTSUPP; @@ -2699,8 +2605,7 @@ int ena_com_indirect_table_set(struct ena_com_dev *ena_dev) sizeof(resp)); if (unlikely(ret)) - netdev_err(ena_dev->net_device, - "Failed to set indirect table. error: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to set indirect table. error: %d\n", ret); return ret; } @@ -2779,9 +2684,8 @@ int ena_com_allocate_host_info(struct ena_com_dev *ena_dev) { struct ena_host_attribute *host_attr = &ena_dev->host_attr; - host_attr->host_info = - dma_alloc_coherent(ena_dev->dmadev, SZ_4K, - &host_attr->host_info_dma_addr, GFP_KERNEL); + host_attr->host_info = dma_alloc_coherent(ena_dev->dmadev, SZ_4K, + &host_attr->host_info_dma_addr, GFP_KERNEL); if (unlikely(!host_attr->host_info)) return -ENOMEM; @@ -2827,8 +2731,7 @@ void ena_com_delete_debug_area(struct ena_com_dev *ena_dev) if (host_attr->debug_area_virt_addr) { dma_free_coherent(ena_dev->dmadev, host_attr->debug_area_size, - host_attr->debug_area_virt_addr, - host_attr->debug_area_dma_addr); + host_attr->debug_area_virt_addr, host_attr->debug_area_dma_addr); host_attr->debug_area_virt_addr = NULL; } } @@ -2877,8 +2780,7 @@ int ena_com_set_host_attributes(struct ena_com_dev *ena_dev) sizeof(resp)); if (unlikely(ret)) - netdev_err(ena_dev->net_device, - "Failed to set host attributes: %d\n", ret); + netdev_err(ena_dev->net_device, "Failed to set host attributes: %d\n", ret); return ret; } @@ -2896,8 +2798,7 @@ static int ena_com_update_nonadaptive_moderation_interval(struct ena_com_dev *en u32 *intr_moder_interval) { if (!intr_delay_resolution) { - netdev_err(ena_dev->net_device, - "Illegal interrupt delay granularity value\n"); + netdev_err(ena_dev->net_device, "Illegal interrupt delay granularity value\n"); return -EFAULT; } @@ -2935,14 +2836,12 @@ int ena_com_init_interrupt_moderation(struct ena_com_dev *ena_dev) if (rc) { if (rc == -EOPNOTSUPP) { - netdev_dbg(ena_dev->net_device, - "Feature %d isn't supported\n", + netdev_dbg(ena_dev->net_device, "Feature %d isn't supported\n", ENA_ADMIN_INTERRUPT_MODERATION); rc = 0; } else { netdev_err(ena_dev->net_device, - "Failed to get interrupt moderation admin cmd. rc: %d\n", - rc); + "Failed to get interrupt moderation admin cmd. rc: %d\n", rc); } /* no moderation supported, disable adaptive support */ @@ -2990,8 +2889,7 @@ int ena_com_config_dev_mode(struct ena_com_dev *ena_dev, (llq_info->descs_num_before_header * sizeof(struct ena_eth_io_tx_desc)); if (unlikely(ena_dev->tx_max_header_size == 0)) { - netdev_err(ena_dev->net_device, - "The size of the LLQ entry is smaller than needed\n"); + netdev_err(ena_dev->net_device, "The size of the LLQ entry is smaller than needed\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index 3c5081d9d25d6..d52173a69b8f8 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -46,7 +46,7 @@ /*****************************************************************************/ /* ENA adaptive interrupt moderation settings */ -#define ENA_INTR_INITIAL_TX_INTERVAL_USECS 64 +#define ENA_INTR_INITIAL_TX_INTERVAL_USECS 0 #define ENA_INTR_INITIAL_RX_INTERVAL_USECS 0 #define ENA_DEFAULT_INTR_DELAY_RESOLUTION 1 diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index f9f886289b970..4c6e07aa4bbb5 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -18,8 +18,7 @@ static struct ena_eth_io_rx_cdesc_base *ena_com_get_next_rx_cdesc( cdesc = (struct ena_eth_io_rx_cdesc_base *)(io_cq->cdesc_addr.virt_addr + (head_masked * io_cq->cdesc_entry_size_in_bytes)); - desc_phase = (READ_ONCE(cdesc->status) & - ENA_ETH_IO_RX_CDESC_BASE_PHASE_MASK) >> + desc_phase = (READ_ONCE(cdesc->status) & ENA_ETH_IO_RX_CDESC_BASE_PHASE_MASK) >> ENA_ETH_IO_RX_CDESC_BASE_PHASE_SHIFT; if (desc_phase != expected_phase) @@ -65,8 +64,8 @@ static int ena_com_write_bounce_buffer_to_dev(struct ena_com_io_sq *io_sq, io_sq->entries_in_tx_burst_left--; netdev_dbg(ena_com_io_sq_to_ena_dev(io_sq)->net_device, - "Decreasing entries_in_tx_burst_left of queue %d to %d\n", - io_sq->qid, io_sq->entries_in_tx_burst_left); + "Decreasing entries_in_tx_burst_left of queue %d to %d\n", io_sq->qid, + io_sq->entries_in_tx_burst_left); } /* Make sure everything was written into the bounce buffer before @@ -75,8 +74,8 @@ static int ena_com_write_bounce_buffer_to_dev(struct ena_com_io_sq *io_sq, wmb(); /* The line is completed. Copy it to dev */ - __iowrite64_copy(io_sq->desc_addr.pbuf_dev_addr + dst_offset, - bounce_buffer, (llq_info->desc_list_entry_size) / 8); + __iowrite64_copy(io_sq->desc_addr.pbuf_dev_addr + dst_offset, bounce_buffer, + (llq_info->desc_list_entry_size) / 8); io_sq->tail++; @@ -102,16 +101,14 @@ static int ena_com_write_header_to_bounce(struct ena_com_io_sq *io_sq, header_offset = llq_info->descs_num_before_header * io_sq->desc_entry_size; - if (unlikely((header_offset + header_len) > - llq_info->desc_list_entry_size)) { + if (unlikely((header_offset + header_len) > llq_info->desc_list_entry_size)) { netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, "Trying to write header larger than llq entry can accommodate\n"); return -EFAULT; } if (unlikely(!bounce_buffer)) { - netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, - "Bounce buffer is NULL\n"); + netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, "Bounce buffer is NULL\n"); return -EFAULT; } @@ -129,8 +126,7 @@ static void *get_sq_desc_llq(struct ena_com_io_sq *io_sq) bounce_buffer = pkt_ctrl->curr_bounce_buf; if (unlikely(!bounce_buffer)) { - netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, - "Bounce buffer is NULL\n"); + netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, "Bounce buffer is NULL\n"); return NULL; } @@ -233,31 +229,43 @@ static struct ena_eth_io_rx_cdesc_base * idx * io_cq->cdesc_entry_size_in_bytes); } -static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq, - u16 *first_cdesc_idx) +static int ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq, + u16 *first_cdesc_idx, + u16 *num_descs) { + u16 count = io_cq->cur_rx_pkt_cdesc_count, head_masked; struct ena_eth_io_rx_cdesc_base *cdesc; - u16 count = 0, head_masked; u32 last = 0; do { + u32 status; + cdesc = ena_com_get_next_rx_cdesc(io_cq); if (!cdesc) break; + status = READ_ONCE(cdesc->status); ena_com_cq_inc_head(io_cq); + if (unlikely((status & ENA_ETH_IO_RX_CDESC_BASE_FIRST_MASK) >> + ENA_ETH_IO_RX_CDESC_BASE_FIRST_SHIFT && count != 0)) { + struct ena_com_dev *dev = ena_com_io_cq_to_ena_dev(io_cq); + + netdev_err(dev->net_device, + "First bit is on in descriptor #%d on q_id: %d, req_id: %u\n", + count, io_cq->qid, cdesc->req_id); + return -EFAULT; + } count++; - last = (READ_ONCE(cdesc->status) & - ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK) >> - ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT; + last = (status & ENA_ETH_IO_RX_CDESC_BASE_LAST_MASK) >> + ENA_ETH_IO_RX_CDESC_BASE_LAST_SHIFT; } while (!last); if (last) { *first_cdesc_idx = io_cq->cur_rx_pkt_cdesc_start_idx; - count += io_cq->cur_rx_pkt_cdesc_count; head_masked = io_cq->head & (io_cq->q_depth - 1); + *num_descs = count; io_cq->cur_rx_pkt_cdesc_count = 0; io_cq->cur_rx_pkt_cdesc_start_idx = head_masked; @@ -265,11 +273,11 @@ static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq, "ENA q_id: %d packets were completed. first desc idx %u descs# %d\n", io_cq->qid, *first_cdesc_idx, count); } else { - io_cq->cur_rx_pkt_cdesc_count += count; - count = 0; + io_cq->cur_rx_pkt_cdesc_count = count; + *num_descs = 0; } - return count; + return 0; } static int ena_com_create_meta(struct ena_com_io_sq *io_sq, @@ -369,9 +377,8 @@ static void ena_com_rx_set_flags(struct ena_com_io_cq *io_cq, netdev_dbg(ena_com_io_cq_to_ena_dev(io_cq)->net_device, "l3_proto %d l4_proto %d l3_csum_err %d l4_csum_err %d hash %d frag %d cdesc_status %x\n", - ena_rx_ctx->l3_proto, ena_rx_ctx->l4_proto, - ena_rx_ctx->l3_csum_err, ena_rx_ctx->l4_csum_err, - ena_rx_ctx->hash, ena_rx_ctx->frag, cdesc->status); + ena_rx_ctx->l3_proto, ena_rx_ctx->l4_proto, ena_rx_ctx->l3_csum_err, + ena_rx_ctx->l4_csum_err, ena_rx_ctx->hash, ena_rx_ctx->frag, cdesc->status); } /*****************************************************************************/ @@ -403,13 +410,12 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq, if (unlikely(header_len > io_sq->tx_max_header_size)) { netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, - "Header size is too large %d max header: %d\n", - header_len, io_sq->tx_max_header_size); + "Header size is too large %d max header: %d\n", header_len, + io_sq->tx_max_header_size); return -EINVAL; } - if (unlikely(io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV && - !buffer_to_push)) { + if (unlikely(io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV && !buffer_to_push)) { netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, "Push header wasn't provided in LLQ mode\n"); return -EINVAL; @@ -546,23 +552,25 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq, u16 cdesc_idx = 0; u16 nb_hw_desc; u16 i = 0; + int rc; WARN(io_cq->direction != ENA_COM_IO_QUEUE_DIRECTION_RX, "wrong Q type"); - nb_hw_desc = ena_com_cdesc_rx_pkt_get(io_cq, &cdesc_idx); + rc = ena_com_cdesc_rx_pkt_get(io_cq, &cdesc_idx, &nb_hw_desc); + if (unlikely(rc != 0)) + return -EFAULT; + if (nb_hw_desc == 0) { ena_rx_ctx->descs = nb_hw_desc; return 0; } netdev_dbg(ena_com_io_cq_to_ena_dev(io_cq)->net_device, - "Fetch rx packet: queue %d completed desc: %d\n", io_cq->qid, - nb_hw_desc); + "Fetch rx packet: queue %d completed desc: %d\n", io_cq->qid, nb_hw_desc); if (unlikely(nb_hw_desc > ena_rx_ctx->max_bufs)) { netdev_err(ena_com_io_cq_to_ena_dev(io_cq)->net_device, - "Too many RX cdescs (%d) > MAX(%d)\n", nb_hw_desc, - ena_rx_ctx->max_bufs); + "Too many RX cdescs (%d) > MAX(%d)\n", nb_hw_desc, ena_rx_ctx->max_bufs); return -ENOSPC; } @@ -586,8 +594,8 @@ int ena_com_rx_pkt(struct ena_com_io_cq *io_cq, io_sq->next_to_comp += nb_hw_desc; netdev_dbg(ena_com_io_cq_to_ena_dev(io_cq)->net_device, - "[%s][QID#%d] Updating SQ head to: %d\n", __func__, - io_sq->qid, io_sq->next_to_comp); + "[%s][QID#%d] Updating SQ head to: %d\n", __func__, io_sq->qid, + io_sq->next_to_comp); /* Get rx flags from the last pkt */ ena_com_rx_set_flags(io_cq, ena_rx_ctx, cdesc); @@ -624,8 +632,8 @@ int ena_com_add_single_rx_desc(struct ena_com_io_sq *io_sq, desc->req_id = req_id; netdev_dbg(ena_com_io_sq_to_ena_dev(io_sq)->net_device, - "[%s] Adding single RX desc, Queue: %u, req_id: %u\n", - __func__, io_sq->qid, req_id); + "[%s] Adding single RX desc, Queue: %u, req_id: %u\n", __func__, io_sq->qid, + req_id); desc->buff_addr_lo = (u32)ena_buf->paddr; desc->buff_addr_hi = diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h index 372b259279eca..6eba034646525 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h @@ -145,8 +145,8 @@ static inline bool ena_com_is_doorbell_needed(struct ena_com_io_sq *io_sq, } netdev_dbg(ena_com_io_sq_to_ena_dev(io_sq)->net_device, - "Queue: %d num_descs: %d num_entries_needed: %d\n", - io_sq->qid, num_descs, num_entries_needed); + "Queue: %d num_descs: %d num_entries_needed: %d\n", io_sq->qid, num_descs, + num_entries_needed); return num_entries_needed > io_sq->entries_in_tx_burst_left; } @@ -157,15 +157,14 @@ static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq) u16 tail = io_sq->tail; netdev_dbg(ena_com_io_sq_to_ena_dev(io_sq)->net_device, - "Write submission queue doorbell for queue: %d tail: %d\n", - io_sq->qid, tail); + "Write submission queue doorbell for queue: %d tail: %d\n", io_sq->qid, tail); writel(tail, io_sq->db_addr); if (is_llq_max_tx_burst_exists(io_sq)) { netdev_dbg(ena_com_io_sq_to_ena_dev(io_sq)->net_device, - "Reset available entries in tx burst for queue %d to %d\n", - io_sq->qid, max_entries_in_tx_burst); + "Reset available entries in tx burst for queue %d to %d\n", io_sq->qid, + max_entries_in_tx_burst); io_sq->entries_in_tx_burst_left = max_entries_in_tx_burst; } @@ -248,8 +247,8 @@ static inline int ena_com_tx_comp_req_id_get(struct ena_com_io_cq *io_cq, *req_id = READ_ONCE(cdesc->req_id); if (unlikely(*req_id >= io_cq->q_depth)) { - netdev_err(ena_com_io_cq_to_ena_dev(io_cq)->net_device, - "Invalid req id %d\n", cdesc->req_id); + netdev_err(ena_com_io_cq_to_ena_dev(io_cq)->net_device, "Invalid req id %d\n", + cdesc->req_id); return -EINVAL; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 1c0a7828d397b..0ea0f5e73aa6b 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -116,11 +116,9 @@ int ena_xmit_common(struct ena_adapter *adapter, if (unlikely(rc)) { netif_err(adapter, tx_queued, adapter->netdev, "Failed to prepare tx bufs\n"); - ena_increase_stat(&ring->tx_stats.prepare_ctx_err, 1, - &ring->syncp); + ena_increase_stat(&ring->tx_stats.prepare_ctx_err, 1, &ring->syncp); if (rc != -ENOMEM) - ena_reset_device(adapter, - ENA_REGS_RESET_DRIVER_INVALID_STATE); + ena_reset_device(adapter, ENA_REGS_RESET_DRIVER_INVALID_STATE); return rc; } @@ -485,8 +483,7 @@ static struct page *ena_alloc_map_page(struct ena_ring *rx_ring, */ page = dev_alloc_page(); if (!page) { - ena_increase_stat(&rx_ring->rx_stats.page_alloc_fail, 1, - &rx_ring->syncp); + ena_increase_stat(&rx_ring->rx_stats.page_alloc_fail, 1, &rx_ring->syncp); return ERR_PTR(-ENOSPC); } @@ -545,8 +542,8 @@ static void ena_unmap_rx_buff_attrs(struct ena_ring *rx_ring, struct ena_rx_buffer *rx_info, unsigned long attrs) { - dma_unmap_page_attrs(rx_ring->dev, rx_info->dma_addr, ENA_PAGE_SIZE, - DMA_BIDIRECTIONAL, attrs); + dma_unmap_page_attrs(rx_ring->dev, rx_info->dma_addr, ENA_PAGE_SIZE, DMA_BIDIRECTIONAL, + attrs); } static void ena_free_rx_page(struct ena_ring *rx_ring, @@ -696,8 +693,11 @@ void ena_unmap_tx_buff(struct ena_ring *tx_ring, static void ena_free_tx_bufs(struct ena_ring *tx_ring) { bool print_once = true; + bool is_xdp_ring; u32 i; + is_xdp_ring = ENA_IS_XDP_INDEX(tx_ring->adapter, tx_ring->qid); + for (i = 0; i < tx_ring->ring_size; i++) { struct ena_tx_buffer *tx_info = &tx_ring->tx_buffer_info[i]; @@ -717,10 +717,15 @@ static void ena_free_tx_bufs(struct ena_ring *tx_ring) ena_unmap_tx_buff(tx_ring, tx_info); - dev_kfree_skb_any(tx_info->skb); + if (is_xdp_ring) + xdp_return_frame(tx_info->xdpf); + else + dev_kfree_skb_any(tx_info->skb); } - netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev, - tx_ring->qid)); + + if (!is_xdp_ring) + netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->qid)); } static void ena_free_all_tx_bufs(struct ena_adapter *adapter) @@ -819,8 +824,7 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget) &req_id); if (rc) { if (unlikely(rc == -EINVAL)) - handle_invalid_req_id(tx_ring, req_id, NULL, - false); + handle_invalid_req_id(tx_ring, req_id, NULL, false); break; } @@ -1046,8 +1050,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, DMA_FROM_DEVICE); if (!reuse_rx_buf_page) - ena_unmap_rx_buff_attrs(rx_ring, rx_info, - DMA_ATTR_SKIP_CPU_SYNC); + ena_unmap_rx_buff_attrs(rx_ring, rx_info, DMA_ATTR_SKIP_CPU_SYNC); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, page_offset + buf_offset, len, buf_len); @@ -1320,9 +1323,10 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, adapter = netdev_priv(rx_ring->netdev); if (rc == -ENOSPC) { - ena_increase_stat(&rx_ring->rx_stats.bad_desc_num, 1, - &rx_ring->syncp); + ena_increase_stat(&rx_ring->rx_stats.bad_desc_num, 1, &rx_ring->syncp); ena_reset_device(adapter, ENA_REGS_RESET_TOO_MANY_RX_DESCS); + } else if (rc == -EFAULT) { + ena_reset_device(adapter, ENA_REGS_RESET_RX_DESCRIPTOR_MALFORMED); } else { ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1, &rx_ring->syncp); @@ -1811,8 +1815,7 @@ static int ena_rss_configure(struct ena_adapter *adapter) if (!ena_dev->rss.tbl_log_size) { rc = ena_rss_init_default(adapter); if (rc && (rc != -EOPNOTSUPP)) { - netif_err(adapter, ifup, adapter->netdev, - "Failed to init RSS rc: %d\n", rc); + netif_err(adapter, ifup, adapter->netdev, "Failed to init RSS rc: %d\n", rc); return rc; } } @@ -2670,22 +2673,6 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) -{ - u16 qid; - /* we suspect that this is good for in--kernel network services that - * want to loop incoming skb rx to tx in normal user generated traffic, - * most probably we will not get to this - */ - if (skb_rx_queue_recorded(skb)) - qid = skb_get_rx_queue(skb); - else - qid = netdev_pick_tx(dev, skb, NULL); - - return qid; -} - static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pdev) { struct device *dev = &pdev->dev; @@ -2764,8 +2751,7 @@ static void ena_config_debug_area(struct ena_adapter *adapter) rc = ena_com_set_host_attributes(adapter->ena_dev); if (rc) { if (rc == -EOPNOTSUPP) - netif_warn(adapter, drv, adapter->netdev, - "Cannot set host attributes\n"); + netif_warn(adapter, drv, adapter->netdev, "Cannot set host attributes\n"); else netif_err(adapter, drv, adapter->netdev, "Cannot set host attributes\n"); @@ -2863,7 +2849,6 @@ static const struct net_device_ops ena_netdev_ops = { .ndo_open = ena_open, .ndo_stop = ena_close, .ndo_start_xmit = ena_start_xmit, - .ndo_select_queue = ena_select_queue, .ndo_get_stats64 = ena_get_stats64, .ndo_tx_timeout = ena_tx_timeout, .ndo_change_mtu = ena_change_mtu, @@ -3438,10 +3423,11 @@ static void check_for_missing_completions(struct ena_adapter *adapter) { struct ena_ring *tx_ring; struct ena_ring *rx_ring; - int i, budget, rc; + int qid, budget, rc; int io_queue_count; io_queue_count = adapter->xdp_num_queues + adapter->num_io_queues; + /* Make sure the driver doesn't turn the device in other process */ smp_rmb(); @@ -3454,27 +3440,29 @@ static void check_for_missing_completions(struct ena_adapter *adapter) if (adapter->missing_tx_completion_to == ENA_HW_HINTS_NO_TIMEOUT) return; - budget = ENA_MONITORED_TX_QUEUES; + budget = min_t(u32, io_queue_count, ENA_MONITORED_TX_QUEUES); - for (i = adapter->last_monitored_tx_qid; i < io_queue_count; i++) { - tx_ring = &adapter->tx_ring[i]; - rx_ring = &adapter->rx_ring[i]; + qid = adapter->last_monitored_tx_qid; + + while (budget) { + qid = (qid + 1) % io_queue_count; + + tx_ring = &adapter->tx_ring[qid]; + rx_ring = &adapter->rx_ring[qid]; rc = check_missing_comp_in_tx_queue(adapter, tx_ring); if (unlikely(rc)) return; - rc = !ENA_IS_XDP_INDEX(adapter, i) ? + rc = !ENA_IS_XDP_INDEX(adapter, qid) ? check_for_rx_interrupt_queue(adapter, rx_ring) : 0; if (unlikely(rc)) return; budget--; - if (!budget) - break; } - adapter->last_monitored_tx_qid = i % io_queue_count; + adapter->last_monitored_tx_qid = qid; } /* trigger napi schedule after 2 consecutive detections */ @@ -3762,8 +3750,8 @@ static int ena_rss_init_default(struct ena_adapter *adapter) } } - rc = ena_com_fill_hash_function(ena_dev, ENA_ADMIN_TOEPLITZ, NULL, - ENA_HASH_KEY_SIZE, 0xFFFFFFFF); + rc = ena_com_fill_hash_function(ena_dev, ENA_ADMIN_TOEPLITZ, NULL, ENA_HASH_KEY_SIZE, + 0xFFFFFFFF); if (unlikely(rc && (rc != -EOPNOTSUPP))) { dev_err(dev, "Cannot fill hash function\n"); goto err_fill_indir; diff --git a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h index 1e007a41a5256..23466d62fbc5c 100644 --- a/drivers/net/ethernet/amazon/ena/ena_regs_defs.h +++ b/drivers/net/ethernet/amazon/ena/ena_regs_defs.h @@ -21,6 +21,7 @@ enum ena_regs_reset_reason_types { ENA_REGS_RESET_USER_TRIGGER = 12, ENA_REGS_RESET_GENERIC = 13, ENA_REGS_RESET_MISS_INTERRUPT = 14, + ENA_REGS_RESET_RX_DESCRIPTOR_MALFORMED = 16, }; /* ena_registers offsets */ diff --git a/drivers/net/ethernet/amazon/ena/ena_xdp.c b/drivers/net/ethernet/amazon/ena/ena_xdp.c index fc1c4ef73ba32..34d73c72f7803 100644 --- a/drivers/net/ethernet/amazon/ena/ena_xdp.c +++ b/drivers/net/ethernet/amazon/ena/ena_xdp.c @@ -89,7 +89,7 @@ int ena_xdp_xmit_frame(struct ena_ring *tx_ring, rc = ena_xdp_tx_map_frame(tx_ring, tx_info, xdpf, &ena_tx_ctx); if (unlikely(rc)) - return rc; + goto err; ena_tx_ctx.req_id = req_id; @@ -112,7 +112,9 @@ int ena_xdp_xmit_frame(struct ena_ring *tx_ring, error_unmap_dma: ena_unmap_tx_buff(tx_ring, tx_info); +err: tx_info->xdpf = NULL; + return rc; } diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 7658a72867675..dd4f0965bbe64 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -595,6 +595,16 @@ void pdsc_fw_up(struct pdsc *pdsc) pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY); } +void pdsc_pci_reset_thread(struct work_struct *work) +{ + struct pdsc *pdsc = container_of(work, struct pdsc, pci_reset_work); + struct pci_dev *pdev = pdsc->pdev; + + pci_dev_get(pdev); + pci_reset_function(pdev); + pci_dev_put(pdev); +} + static void pdsc_check_pci_health(struct pdsc *pdsc) { u8 fw_status; @@ -609,8 +619,8 @@ static void pdsc_check_pci_health(struct pdsc *pdsc) if (fw_status != PDS_RC_BAD_PCI) return; - pdsc_reset_prepare(pdsc->pdev); - pdsc_reset_done(pdsc->pdev); + /* prevent deadlock between pdsc_reset_prepare and pdsc_health_thread */ + queue_work(pdsc->wq, &pdsc->pci_reset_work); } void pdsc_health_thread(struct work_struct *work) diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index 110c4b826b22d..401ff56eba0dc 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -197,6 +197,7 @@ struct pdsc { struct pdsc_qcq notifyqcq; u64 last_eid; struct pdsc_viftype *viftype_status; + struct work_struct pci_reset_work; }; /** enum pds_core_dbell_bits - bitwise composition of dbell values. @@ -283,9 +284,6 @@ int pdsc_devcmd_init(struct pdsc *pdsc); int pdsc_devcmd_reset(struct pdsc *pdsc); int pdsc_dev_init(struct pdsc *pdsc); -void pdsc_reset_prepare(struct pci_dev *pdev); -void pdsc_reset_done(struct pci_dev *pdev); - int pdsc_intr_alloc(struct pdsc *pdsc, char *name, irq_handler_t handler, void *data); void pdsc_intr_free(struct pdsc *pdsc, int index); @@ -315,5 +313,6 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw, void pdsc_fw_down(struct pdsc *pdsc); void pdsc_fw_up(struct pdsc *pdsc); +void pdsc_pci_reset_thread(struct work_struct *work); #endif /* _PDSC_H_ */ diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index e65a1632df505..bfb79c5aac391 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -229,6 +229,9 @@ int pdsc_devcmd_reset(struct pdsc *pdsc) .reset.opcode = PDS_CORE_CMD_RESET, }; + if (!pdsc_is_fw_running(pdsc)) + return 0; + return pdsc_devcmd(pdsc, &cmd, &comp, pdsc->devcmd_timeout); } diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index 0050c5894563b..a375d612d2875 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -238,6 +238,7 @@ static int pdsc_init_pf(struct pdsc *pdsc) snprintf(wq_name, sizeof(wq_name), "%s.%d", PDS_CORE_DRV_NAME, pdsc->uid); pdsc->wq = create_singlethread_workqueue(wq_name); INIT_WORK(&pdsc->health_work, pdsc_health_thread); + INIT_WORK(&pdsc->pci_reset_work, pdsc_pci_reset_thread); timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0); pdsc->wdtimer_period = PDSC_WATCHDOG_SECS * HZ; @@ -468,7 +469,7 @@ static void pdsc_restart_health_thread(struct pdsc *pdsc) mod_timer(&pdsc->wdtimer, jiffies + 1); } -void pdsc_reset_prepare(struct pci_dev *pdev) +static void pdsc_reset_prepare(struct pci_dev *pdev) { struct pdsc *pdsc = pci_get_drvdata(pdev); @@ -477,10 +478,11 @@ void pdsc_reset_prepare(struct pci_dev *pdev) pdsc_unmap_bars(pdsc); pci_release_regions(pdev); - pci_disable_device(pdev); + if (pci_is_enabled(pdev)) + pci_disable_device(pdev); } -void pdsc_reset_done(struct pci_dev *pdev) +static void pdsc_reset_done(struct pci_dev *pdev) { struct pdsc *pdsc = pci_get_drvdata(pdev); struct device *dev = pdsc->dev; diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index 6ad1366270f79..529172a87ae50 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -391,7 +391,9 @@ static void umac_reset(struct bcmasp_intf *intf) umac_wl(intf, 0x0, UMC_CMD); umac_wl(intf, UMC_CMD_SW_RESET, UMC_CMD); usleep_range(10, 100); - umac_wl(intf, 0x0, UMC_CMD); + /* We hold the umac in reset and bring it out of + * reset when phy link is up. + */ } static void umac_set_hw_addr(struct bcmasp_intf *intf, @@ -411,6 +413,8 @@ static void umac_enable_set(struct bcmasp_intf *intf, u32 mask, u32 reg; reg = umac_rl(intf, UMC_CMD); + if (reg & UMC_CMD_SW_RESET) + return; if (enable) reg |= mask; else @@ -429,13 +433,10 @@ static void umac_init(struct bcmasp_intf *intf) umac_wl(intf, 0x800, UMC_FRM_LEN); umac_wl(intf, 0xffff, UMC_PAUSE_CNTRL); umac_wl(intf, 0x800, UMC_RX_MAX_PKT_SZ); - umac_enable_set(intf, UMC_CMD_PROMISC, 1); } -static int bcmasp_tx_poll(struct napi_struct *napi, int budget) +static int bcmasp_tx_reclaim(struct bcmasp_intf *intf) { - struct bcmasp_intf *intf = - container_of(napi, struct bcmasp_intf, tx_napi); struct bcmasp_intf_stats64 *stats = &intf->stats64; struct device *kdev = &intf->parent->pdev->dev; unsigned long read, released = 0; @@ -478,10 +479,16 @@ static int bcmasp_tx_poll(struct napi_struct *napi, int budget) DESC_RING_COUNT); } - /* Ensure all descriptors have been written to DRAM for the hardware - * to see updated contents. - */ - wmb(); + return released; +} + +static int bcmasp_tx_poll(struct napi_struct *napi, int budget) +{ + struct bcmasp_intf *intf = + container_of(napi, struct bcmasp_intf, tx_napi); + int released = 0; + + released = bcmasp_tx_reclaim(intf); napi_complete(&intf->tx_napi); @@ -656,6 +663,12 @@ static void bcmasp_adj_link(struct net_device *dev) UMC_CMD_HD_EN | UMC_CMD_RX_PAUSE_IGNORE | UMC_CMD_TX_PAUSE_IGNORE); reg |= cmd_bits; + if (reg & UMC_CMD_SW_RESET) { + reg &= ~UMC_CMD_SW_RESET; + umac_wl(intf, reg, UMC_CMD); + udelay(2); + reg |= UMC_CMD_TX_EN | UMC_CMD_RX_EN | UMC_CMD_PROMISC; + } umac_wl(intf, reg, UMC_CMD); intf->eee.eee_active = phy_init_eee(phydev, 0) >= 0; @@ -787,6 +800,7 @@ static int bcmasp_init_tx(struct bcmasp_intf *intf) intf->tx_spb_index = 0; intf->tx_spb_clean_index = 0; + memset(intf->tx_cbs, 0, sizeof(struct bcmasp_tx_cb) * DESC_RING_COUNT); netif_napi_add_tx(intf->ndev, &intf->tx_napi, bcmasp_tx_poll); @@ -897,6 +911,8 @@ static void bcmasp_netif_deinit(struct net_device *dev) } while (timeout-- > 0); tx_spb_dma_wl(intf, 0x0, TX_SPB_DMA_FIFO_CTRL); + bcmasp_tx_reclaim(intf); + umac_enable_set(intf, UMC_CMD_TX_EN, 0); phy_stop(dev->phydev); @@ -1063,9 +1079,6 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect) umac_init(intf); - /* Disable the UniMAC RX/TX */ - umac_enable_set(intf, (UMC_CMD_RX_EN | UMC_CMD_TX_EN), 0); - umac_set_hw_addr(intf, dev->dev_addr); intf->old_duplex = -1; @@ -1085,9 +1098,6 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect) bcmasp_enable_rx(intf, 1); - /* Turn on UniMAC TX/RX */ - umac_enable_set(intf, (UMC_CMD_RX_EN | UMC_CMD_TX_EN), 1); - intf->crc_fwd = !!(umac_rl(intf, UMC_CMD) & UMC_CMD_CRC_FWD); bcmasp_netif_start(dev); @@ -1324,7 +1334,14 @@ static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf) if (intf->wolopts & WAKE_FILTER) bcmasp_netfilt_suspend(intf); - /* UniMAC receive needs to be turned on */ + /* Bring UniMAC out of reset if needed and enable RX */ + reg = umac_rl(intf, UMC_CMD); + if (reg & UMC_CMD_SW_RESET) + reg &= ~UMC_CMD_SW_RESET; + + reg |= UMC_CMD_RX_EN | UMC_CMD_PROMISC; + umac_wl(intf, reg, UMC_CMD); + umac_enable_set(intf, UMC_CMD_RX_EN, 1); if (intf->parent->wol_irq > 0) { diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 3e4fb3c3e8342..1be6d14030bcf 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2009,12 +2009,14 @@ static int b44_set_pauseparam(struct net_device *dev, bp->flags |= B44_FLAG_TX_PAUSE; else bp->flags &= ~B44_FLAG_TX_PAUSE; - if (bp->flags & B44_FLAG_PAUSE_AUTO) { - b44_halt(bp); - b44_init_rings(bp); - b44_init_hw(bp, B44_FULL_RESET); - } else { - __b44_set_flow_ctrl(bp, bp->flags); + if (netif_running(dev)) { + if (bp->flags & B44_FLAG_PAUSE_AUTO) { + b44_halt(bp); + b44_init_rings(bp); + b44_init_hw(bp, B44_FULL_RESET); + } else { + __b44_set_flow_ctrl(bp, bp->flags); + } } spin_unlock_irq(&bp->lock); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index e2a4e1088b7f4..9580ab83d387c 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1262,7 +1262,7 @@ enum { struct bnx2x_fw_stats_req { struct stats_query_header hdr; - struct stats_query_entry query[FP_SB_MAX_E1x+ + struct stats_query_entry query[FP_SB_MAX_E2 + BNX2X_FIRST_QUEUE_QUERY_IDX]; }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index e9c1e1bb55806..528441b28c4ef 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -147,10 +147,11 @@ void bnx2x_fill_fw_str(struct bnx2x *bp, char *buf, size_t buf_len) phy_fw_ver[0] = '\0'; bnx2x_get_ext_phy_fw_version(&bp->link_params, - phy_fw_ver, PHY_FW_VER_LEN); - strscpy(buf, bp->fw_ver, buf_len); - snprintf(buf + strlen(bp->fw_ver), 32 - strlen(bp->fw_ver), - "bc %d.%d.%d%s%s", + phy_fw_ver, sizeof(phy_fw_ver)); + /* This may become truncated. */ + scnprintf(buf, buf_len, + "%sbc %d.%d.%d%s%s", + bp->fw_ver, (bp->common.bc_ver & 0xff0000) >> 16, (bp->common.bc_ver & 0xff00) >> 8, (bp->common.bc_ver & 0xff), diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index d8b1824c334d3..0bc1367fd6492 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1002,9 +1002,6 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid, static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp, struct bnx2x_alloc_pool *pool) { - if (!pool->page) - return; - put_page(pool->page); pool->page = NULL; @@ -1015,6 +1012,9 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, { int i; + if (!fp->page_pool.page) + return; + if (fp->mode == TPA_MODE_DISABLED) return; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 81d232e6d05fe..0bc7690cdee16 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1132,7 +1132,7 @@ static void bnx2x_get_drvinfo(struct net_device *dev, } memset(version, 0, sizeof(version)); - bnx2x_fill_fw_str(bp, version, ETHTOOL_FWVERS_LEN); + bnx2x_fill_fw_str(bp, version, sizeof(version)); strlcat(info->fw_version, version, sizeof(info->fw_version)); strscpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info)); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 02808513ffe45..ea310057fe3af 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -6163,8 +6163,8 @@ static void bnx2x_link_int_ack(struct link_params *params, static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len) { - str[0] = '\0'; - (*len)--; + if (*len) + str[0] = '\0'; return 0; } @@ -6173,7 +6173,7 @@ static int bnx2x_format_ver(u32 num, u8 *str, u16 *len) u16 ret; if (*len < 10) { - /* Need more than 10chars for this format */ + /* Need more than 10 chars for this format */ bnx2x_null_format_ver(num, str, len); return -EINVAL; } @@ -6188,8 +6188,8 @@ static int bnx2x_3_seq_format_ver(u32 num, u8 *str, u16 *len) { u16 ret; - if (*len < 10) { - /* Need more than 10chars for this format */ + if (*len < 9) { + /* Need more than 9 chars for this format */ bnx2x_null_format_ver(num, str, len); return -EINVAL; } @@ -6208,7 +6208,7 @@ int bnx2x_get_ext_phy_fw_version(struct link_params *params, u8 *version, int status = 0; u8 *ver_p = version; u16 remain_len = len; - if (version == NULL || params == NULL) + if (version == NULL || params == NULL || len == 0) return -EINVAL; bp = params->bp; @@ -11546,7 +11546,7 @@ static int bnx2x_7101_format_ver(u32 spirom_ver, u8 *str, u16 *len) str[2] = (spirom_ver & 0xFF0000) >> 16; str[3] = (spirom_ver & 0xFF000000) >> 24; str[4] = '\0'; - *len -= 5; + *len -= 4; return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 39845d556bafc..b056d788863df 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -687,9 +687,6 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; tx_dma_error: - if (BNXT_TX_PTP_IS_SET(lflags)) - atomic_inc(&bp->ptp_cfg->tx_avail); - last_frag = i; /* start back at beginning and unmap skb */ @@ -711,6 +708,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_free: dev_kfree_skb_any(skb); tx_kick_pending: + if (BNXT_TX_PTP_IS_SET(lflags)) + atomic_inc(&bp->ptp_cfg->tx_avail); if (txr->kick_pending) bnxt_txr_db_kick(bp, txr, txr->tx_prod); txr->tx_buf_ring[txr->tx_prod].skb = NULL; @@ -1735,7 +1734,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping); if (!skb) { bnxt_abort_tpa(cpr, idx, agg_bufs); - cpr->sw_stats.rx.rx_oom_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; return NULL; } } else { @@ -1745,7 +1744,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, GFP_ATOMIC); if (!new_data) { bnxt_abort_tpa(cpr, idx, agg_bufs); - cpr->sw_stats.rx.rx_oom_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; return NULL; } @@ -1761,7 +1760,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, if (!skb) { skb_free_frag(data); bnxt_abort_tpa(cpr, idx, agg_bufs); - cpr->sw_stats.rx.rx_oom_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; return NULL; } skb_reserve(skb, bp->rx_offset); @@ -1772,7 +1771,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true); if (!skb) { /* Page reuse already handled by bnxt_rx_pages(). */ - cpr->sw_stats.rx.rx_oom_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; return NULL; } } @@ -2051,11 +2050,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp, cp_cons, agg_bufs, false); - if (!frag_len) { - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; - } + if (!frag_len) + goto oom_next_rx; } xdp_active = true; } @@ -2078,9 +2074,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, else bnxt_xdp_buff_frags_free(rxr, &xdp); } - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; + goto oom_next_rx; } } else { u32 payload; @@ -2091,29 +2085,21 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, payload = 0; skb = bp->rx_skb_func(bp, rxr, cons, data, data_ptr, dma_addr, payload | len); - if (!skb) { - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; - } + if (!skb) + goto oom_next_rx; } if (agg_bufs) { if (!xdp_active) { skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false); - if (!skb) { - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; - } + if (!skb) + goto oom_next_rx; } else { skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1); if (!skb) { /* we should be able to free the old skb here */ bnxt_xdp_buff_frags_free(rxr, &xdp); - cpr->sw_stats.rx.rx_oom_discards += 1; - rc = -ENOMEM; - goto next_rx; + goto oom_next_rx; } } } @@ -2191,6 +2177,11 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, *raw_cons = tmp_raw_cons; return rc; + +oom_next_rx: + cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1; + rc = -ENOMEM; + goto next_rx; } /* In netpoll mode, if we are using a combined completion ring, we need to @@ -2237,7 +2228,7 @@ static int bnxt_force_rx_discard(struct bnxt *bp, } rc = bnxt_rx_pkt(bp, cpr, raw_cons, event); if (rc && rc != -EBUSY) - cpr->sw_stats.rx.rx_netpoll_discards += 1; + cpr->bnapi->cp_ring.sw_stats.rx.rx_netpoll_discards += 1; return rc; } @@ -8906,7 +8897,7 @@ static void bnxt_try_map_fw_health_reg(struct bnxt *bp) BNXT_FW_HEALTH_WIN_BASE + BNXT_GRC_REG_CHIP_NUM); } - if (!BNXT_CHIP_P5(bp)) + if (!BNXT_CHIP_P5_PLUS(bp)) return; status_loc = BNXT_GRC_REG_STATUS_P5 | @@ -11526,6 +11517,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* VF-reps may need to be re-opened after the PF is re-opened */ if (BNXT_PF(bp)) bnxt_vf_reps_open(bp); + if (bp->ptp_cfg) + atomic_set(&bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS); bnxt_ptp_init_rtc(bp, true); bnxt_ptp_cfg_tstamp_filters(bp); return 0; @@ -12774,6 +12767,16 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) bnxt_rtnl_unlock_sp(bp); } +static void bnxt_fw_fatal_close(struct bnxt *bp) +{ + bnxt_tx_disable(bp); + bnxt_disable_napi(bp); + bnxt_disable_int_sync(bp); + bnxt_free_irq(bp); + bnxt_clear_int_mode(bp); + pci_disable_device(bp->pdev); +} + static void bnxt_fw_reset_close(struct bnxt *bp) { bnxt_ulp_stop(bp); @@ -12787,12 +12790,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp) pci_read_config_word(bp->pdev, PCI_SUBSYSTEM_ID, &val); if (val == 0xffff) bp->fw_reset_min_dsecs = 0; - bnxt_tx_disable(bp); - bnxt_disable_napi(bp); - bnxt_disable_int_sync(bp); - bnxt_free_irq(bp); - bnxt_clear_int_mode(bp); - pci_disable_device(bp->pdev); + bnxt_fw_fatal_close(bp); } __bnxt_close_nic(bp, true, false); bnxt_vf_reps_free(bp); @@ -15038,6 +15036,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, { struct net_device *netdev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(netdev); + bool abort = false; netdev_info(netdev, "PCI I/O error detected\n"); @@ -15046,16 +15045,27 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, bnxt_ulp_stop(bp); - if (state == pci_channel_io_perm_failure) { + if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + netdev_err(bp->dev, "Firmware reset already in progress\n"); + abort = true; + } + + if (abort || state == pci_channel_io_perm_failure) { rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; } - if (state == pci_channel_io_frozen) + /* Link is not reliable anymore if state is pci_channel_io_frozen + * so we disable bus master to prevent any potential bad DMAs before + * freeing kernel memory. + */ + if (state == pci_channel_io_frozen) { set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state); + bnxt_fw_fatal_close(bp); + } if (netif_running(netdev)) - bnxt_close(netdev); + __bnxt_close_nic(bp, true, true); if (pci_is_enabled(pdev)) pci_disable_device(pdev); @@ -15139,6 +15149,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) } reset_exit: + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); bnxt_clear_reservations(bp, true); rtnl_unlock(); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 47338b48ca203..6b8d6a7f850af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1399,6 +1399,57 @@ struct bnxt_l2_filter { atomic_t refcnt; }; +/* Compat version of hwrm_port_phy_qcfg_output capped at 96 bytes. The + * first 95 bytes are identical to hwrm_port_phy_qcfg_output in bnxt_hsi.h. + * The last valid byte in the compat version is different. + */ +struct hwrm_port_phy_qcfg_output_compat { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 link; + u8 active_fec_signal_mode; + __le16 link_speed; + u8 duplex_cfg; + u8 pause; + __le16 support_speeds; + __le16 force_link_speed; + u8 auto_mode; + u8 auto_pause; + __le16 auto_link_speed; + __le16 auto_link_speed_mask; + u8 wirespeed; + u8 lpbk; + u8 force_pause; + u8 module_status; + __le32 preemphasis; + u8 phy_maj; + u8 phy_min; + u8 phy_bld; + u8 phy_type; + u8 media_type; + u8 xcvr_pkg_type; + u8 eee_config_phy_addr; + u8 parallel_detect; + __le16 link_partner_adv_speeds; + u8 link_partner_adv_auto_mode; + u8 link_partner_adv_pause; + __le16 adv_eee_link_speed_mask; + __le16 link_partner_adv_eee_link_speed_mask; + __le32 xcvr_identifier_type_tx_lpi_timer; + __le16 fec_cfg; + u8 duplex_state; + u8 option_flags; + char phy_vendor_name[16]; + char phy_vendor_partnumber[16]; + __le16 support_pam4_speeds; + __le16 force_pam4_link_speed; + __le16 auto_pam4_link_speed_mask; + u8 link_partner_pam4_adv_speeds; + u8 valid; +}; + struct bnxt_link_info { u8 phy_type; u8 media_type; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c index 1df3d56cc4b51..d2fd2d04ed474 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c @@ -680,7 +680,7 @@ static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx) req_type); else if (rc && rc != HWRM_ERR_CODE_PF_UNAVAILABLE) hwrm_err(bp, ctx, "hwrm req_type 0x%x seq id 0x%x error 0x%x\n", - req_type, token->seq_id, rc); + req_type, le16_to_cpu(ctx->req->seq_id), rc); rc = __hwrm_to_stderr(rc); exit: if (token) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 175192ebaa773..22898d3d088b0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -950,8 +950,11 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, struct hwrm_fwd_resp_input *req; int rc; - if (BNXT_FWD_RESP_SIZE_ERR(msg_size)) + if (BNXT_FWD_RESP_SIZE_ERR(msg_size)) { + netdev_warn_once(bp->dev, "HWRM fwd response too big (%d bytes)\n", + msg_size); return -EINVAL; + } rc = hwrm_req_init(bp, req, HWRM_FWD_RESP); if (!rc) { @@ -1085,7 +1088,7 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf) rc = bnxt_hwrm_exec_fwd_resp( bp, vf, sizeof(struct hwrm_port_phy_qcfg_input)); } else { - struct hwrm_port_phy_qcfg_output phy_qcfg_resp = {0}; + struct hwrm_port_phy_qcfg_output_compat phy_qcfg_resp = {}; struct hwrm_port_phy_qcfg_input *phy_qcfg_req; phy_qcfg_req = @@ -1096,6 +1099,11 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf) mutex_unlock(&bp->link_lock); phy_qcfg_resp.resp_len = cpu_to_le16(sizeof(phy_qcfg_resp)); phy_qcfg_resp.seq_id = phy_qcfg_req->seq_id; + /* New SPEEDS2 fields are beyond the legacy structure, so + * clear the SPEEDS2_SUPPORTED flag. + */ + phy_qcfg_resp.option_flags &= + ~PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED; phy_qcfg_resp.valid = 1; if (vf->flags & BNXT_VF_LINK_UP) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 93f9bd55020f2..195c02dc06830 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -210,6 +210,9 @@ void bnxt_ulp_start(struct bnxt *bp, int err) if (err) return; + if (edev->ulp_tbl->msix_requested) + bnxt_fill_msix_vecs(bp, edev->msix_entries); + if (aux_priv) { struct auxiliary_device *adev; @@ -392,12 +395,13 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp) if (!edev) goto aux_dev_uninit; + aux_priv->edev = edev; + ulp = kzalloc(sizeof(*ulp), GFP_KERNEL); if (!ulp) goto aux_dev_uninit; edev->ulp_tbl = ulp; - aux_priv->edev = edev; bp->edev = edev; bnxt_set_edev_info(edev, bp); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 2d7ae71287b14..cefb9f34d57b0 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2,7 +2,7 @@ /* * Broadcom GENET (Gigabit Ethernet) controller driver * - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #define pr_fmt(fmt) "bcmgenet: " fmt @@ -2469,14 +2469,18 @@ static void umac_enable_set(struct bcmgenet_priv *priv, u32 mask, bool enable) { u32 reg; + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); - if (reg & CMD_SW_RESET) + if (reg & CMD_SW_RESET) { + spin_unlock_bh(&priv->reg_lock); return; + } if (enable) reg |= mask; else reg &= ~mask; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); /* UniMAC stops on a packet boundary, wait for a full-size packet * to be processed @@ -2492,8 +2496,10 @@ static void reset_umac(struct bcmgenet_priv *priv) udelay(10); /* issue soft reset and disable MAC while updating its registers */ + spin_lock_bh(&priv->reg_lock); bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD); udelay(2); + spin_unlock_bh(&priv->reg_lock); } static void bcmgenet_intr_disable(struct bcmgenet_priv *priv) @@ -3282,7 +3288,7 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, } /* Returns a reusable dma control register value */ -static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) +static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx) { unsigned int i; u32 reg; @@ -3307,6 +3313,14 @@ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) udelay(10); bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH); + if (flush_rx) { + reg = bcmgenet_rbuf_ctrl_get(priv); + bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0)); + udelay(10); + bcmgenet_rbuf_ctrl_set(priv, reg); + udelay(10); + } + return dma_ctrl; } @@ -3328,7 +3342,9 @@ static void bcmgenet_netif_start(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); /* Start the network engine */ + netif_addr_lock_bh(dev); bcmgenet_set_rx_mode(dev); + netif_addr_unlock_bh(dev); bcmgenet_enable_rx_napi(priv); umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true); @@ -3370,8 +3386,8 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_set_hw_addr(priv, dev->dev_addr); - /* Disable RX/TX DMA and flush TX queues */ - dma_ctrl = bcmgenet_dma_disable(priv); + /* Disable RX/TX DMA and flush TX and RX queues */ + dma_ctrl = bcmgenet_dma_disable(priv, true); /* Reinitialize TDMA and RDMA and SW housekeeping */ ret = bcmgenet_init_dma(priv); @@ -3589,16 +3605,19 @@ static void bcmgenet_set_rx_mode(struct net_device *dev) * 3. The number of filters needed exceeds the number filters * supported by the hardware. */ + spin_lock(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) || (nfilter > MAX_MDF_FILTER)) { reg |= CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock(&priv->reg_lock); bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL); return; } else { reg &= ~CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock(&priv->reg_lock); } /* update MDF filter */ @@ -3997,6 +4016,7 @@ static int bcmgenet_probe(struct platform_device *pdev) goto err; } + spin_lock_init(&priv->reg_lock); spin_lock_init(&priv->lock); /* Set default pause parameters */ @@ -4237,7 +4257,7 @@ static int bcmgenet_resume(struct device *d) bcmgenet_hfb_create_rxnfc_filter(priv, rule); /* Disable RX/TX DMA and flush TX queues */ - dma_ctrl = bcmgenet_dma_disable(priv); + dma_ctrl = bcmgenet_dma_disable(priv, false); /* Reinitialize TDMA and RDMA and SW housekeeping */ ret = bcmgenet_init_dma(priv); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 1985c0ec4da2a..28e2c94ef835c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #ifndef __BCMGENET_H__ @@ -573,6 +573,8 @@ struct bcmgenet_rxnfc_rule { /* device context */ struct bcmgenet_priv { void __iomem *base; + /* reg_lock: lock to serialize access to shared registers */ + spinlock_t reg_lock; enum bcmgenet_version version; struct net_device *dev; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index 7a41cad5788f4..1248792d7fd4d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -2,7 +2,7 @@ /* * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support * - * Copyright (c) 2014-2020 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #define pr_fmt(fmt) "bcmgenet_wol: " fmt @@ -151,6 +151,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, } /* Can't suspend with WoL if MAC is still in reset */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); if (reg & CMD_SW_RESET) reg &= ~CMD_SW_RESET; @@ -158,6 +159,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, /* disable RX */ reg &= ~CMD_RX_EN; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); mdelay(10); if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) { @@ -203,6 +205,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, } /* Enable CRC forward */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); priv->crc_fwd_en = 1; reg |= CMD_CRC_FWD; @@ -210,6 +213,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, /* Receiver must be enabled for WOL MP detection */ reg |= CMD_RX_EN; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); reg = UMAC_IRQ_MPD_R; if (hfb_enable) @@ -256,7 +260,9 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, } /* Disable CRC Forward */ + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); reg &= ~CMD_CRC_FWD; bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 97ea76d443abe..e7c659cd39746 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -2,7 +2,7 @@ /* * Broadcom GENET MDIO routines * - * Copyright (c) 2014-2017 Broadcom + * Copyright (c) 2014-2024 Broadcom */ #include @@ -75,6 +75,7 @@ static void bcmgenet_mac_config(struct net_device *dev) reg |= RGMII_LINK; bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + spin_lock_bh(&priv->reg_lock); reg = bcmgenet_umac_readl(priv, UMAC_CMD); reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) | CMD_HD_EN | @@ -87,6 +88,7 @@ static void bcmgenet_mac_config(struct net_device *dev) reg |= CMD_TX_EN | CMD_RX_EN; } bcmgenet_umac_writel(priv, reg, UMAC_CMD); + spin_unlock_bh(&priv->reg_lock); priv->eee.eee_active = phy_init_eee(phydev, 0) >= 0; bcmgenet_eee_enable_set(dev, @@ -274,6 +276,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) * block for the interface to work, unconditionally clear the * Out-of-band disable since we do not need it. */ + mutex_lock(&phydev->lock); reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); reg &= ~OOB_DISABLE; if (priv->ext_phy) { @@ -285,6 +288,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) reg |= RGMII_MODE_EN; } bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + mutex_unlock(&phydev->lock); if (init) dev_info(kdev, "configuring instance for %s\n", phy_name); diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c index 7246e13dd559f..97291bfbeea58 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c +++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c @@ -312,7 +312,7 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf, void *kern_buf; /* Copy the user space buf */ - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); @@ -372,7 +372,7 @@ bnad_debugfs_write_regwr(struct file *file, const char __user *buf, void *kern_buf; /* Copy the user space buf */ - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c index aa6c0dfb6f1ca..e26b4ed33dc83 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c @@ -272,13 +272,12 @@ lio_vf_rep_copy_packet(struct octeon_device *oct, pg_info->page_offset; memcpy(skb->data, va, MIN_SKB_SIZE); skb_put(skb, MIN_SKB_SIZE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + pg_info->page, + pg_info->page_offset + MIN_SKB_SIZE, + len - MIN_SKB_SIZE, + LIO_RXBUFFER_SZ); } - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - pg_info->page, - pg_info->page_offset + MIN_SKB_SIZE, - len - MIN_SKB_SIZE, - LIO_RXBUFFER_SZ); } else { struct octeon_skb_page_info *pg_info = ((struct octeon_skb_page_info *)(skb->cb)); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index b5ff2e1a9975f..2285f2e87e689 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2684,12 +2684,12 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) lb->loopback = 1; q = &adap->sge.ethtxq[pi->first_qset]; - __netif_tx_lock(q->txq, smp_processor_id()); + __netif_tx_lock_bh(q->txq); reclaim_completed_tx(adap, &q->q, -1, true); credits = txq_avail(&q->q) - ndesc; if (unlikely(credits < 0)) { - __netif_tx_unlock(q->txq); + __netif_tx_unlock_bh(q->txq); return -ENOMEM; } @@ -2724,7 +2724,7 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) init_completion(&lb->completion); txq_advance(&q->q, ndesc); cxgb4_ring_tx_db(adap, &q->q, ndesc); - __netif_tx_unlock(q->txq); + __netif_tx_unlock_bh(q->txq); /* wait for the pkt to return */ ret = wait_for_completion_timeout(&lb->completion, 10 * HZ); diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 37bd38d772e80..cccf0db2fb4e5 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1117,18 +1117,30 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, pp->request = nla_get_u8(port[IFLA_PORT_REQUEST]); if (port[IFLA_PORT_PROFILE]) { + if (nla_len(port[IFLA_PORT_PROFILE]) != PORT_PROFILE_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_NAME; memcpy(pp->name, nla_data(port[IFLA_PORT_PROFILE]), PORT_PROFILE_MAX); } if (port[IFLA_PORT_INSTANCE_UUID]) { + if (nla_len(port[IFLA_PORT_INSTANCE_UUID]) != PORT_UUID_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_INSTANCE; memcpy(pp->instance_uuid, nla_data(port[IFLA_PORT_INSTANCE_UUID]), PORT_UUID_MAX); } if (port[IFLA_PORT_HOST_UUID]) { + if (nla_len(port[IFLA_PORT_HOST_UUID]) != PORT_UUID_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_HOST; memcpy(pp->host_uuid, nla_data(port[IFLA_PORT_HOST_UUID]), PORT_UUID_MAX); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 705c3eb19cd3f..d1fbadbf86d4a 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1107,10 +1107,13 @@ static void gmac_tx_irq_enable(struct net_device *netdev, { struct gemini_ethernet_port *port = netdev_priv(netdev); struct gemini_ethernet *geth = port->geth; + unsigned long flags; u32 val, mask; netdev_dbg(netdev, "%s device %d\n", __func__, netdev->dev_id); + spin_lock_irqsave(&geth->irq_lock, flags); + mask = GMAC0_IRQ0_TXQ0_INTS << (6 * netdev->dev_id + txq); if (en) @@ -1119,6 +1122,8 @@ static void gmac_tx_irq_enable(struct net_device *netdev, val = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG); val = en ? val | mask : val & ~mask; writel(val, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG); + + spin_unlock_irqrestore(&geth->irq_lock, flags); } static void gmac_tx_irq(struct net_device *netdev, unsigned int txq_num) @@ -1415,15 +1420,19 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) union gmac_rxdesc_3 word3; struct page *page = NULL; unsigned int page_offs; + unsigned long flags; unsigned short r, w; union dma_rwptr rw; dma_addr_t mapping; int frag_nr = 0; + spin_lock_irqsave(&geth->irq_lock, flags); rw.bits32 = readl(ptr_reg); /* Reset interrupt as all packages until here are taken into account */ writel(DEFAULT_Q0_INT_BIT << netdev->dev_id, geth->base + GLOBAL_INTERRUPT_STATUS_1_REG); + spin_unlock_irqrestore(&geth->irq_lock, flags); + r = rw.bits.rptr; w = rw.bits.wptr; @@ -1726,10 +1735,9 @@ static irqreturn_t gmac_irq(int irq, void *data) gmac_update_hw_stats(netdev); if (val & (GMAC0_RX_OVERRUN_INT_BIT << (netdev->dev_id * 8))) { + spin_lock(&geth->irq_lock); writel(GMAC0_RXDERR_INT_BIT << (netdev->dev_id * 8), geth->base + GLOBAL_INTERRUPT_STATUS_4_REG); - - spin_lock(&geth->irq_lock); u64_stats_update_begin(&port->ir_stats_syncp); ++port->stats.rx_fifo_errors; u64_stats_update_end(&port->ir_stats_syncp); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index bfdbdab443ae0..5e6e1f7196f87 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2769,7 +2769,7 @@ static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog, if (priv->min_num_stack_tx_queues + num_xdp_tx_queues > priv->num_tx_rings) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Reserving %d XDP TXQs does not leave a minimum of %d for stack (total %d)", + "Reserving %d XDP TXQs leaves under %d for stack (total %d)", num_xdp_tx_queues, priv->min_num_stack_tx_queues, priv->num_tx_rings); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 432523b2c7892..eec38f1e17360 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2406,8 +2406,6 @@ static int fec_enet_mii_probe(struct net_device *ndev) fep->link = 0; fep->full_duplex = 0; - phy_dev->mac_managed_pm = true; - phy_attached_info(phy_dev); return 0; @@ -2419,10 +2417,12 @@ static int fec_enet_mii_init(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); bool suppress_preamble = false; + struct phy_device *phydev; struct device_node *node; int err = -ENXIO; u32 mii_speed, holdtime; u32 bus_freq; + int addr; /* * The i.MX28 dual fec interfaces are not equal. @@ -2536,6 +2536,13 @@ static int fec_enet_mii_init(struct platform_device *pdev) goto err_out_free_mdiobus; of_node_put(node); + /* find all the PHY devices on the bus and set mac_managed_pm to true */ + for (addr = 0; addr < PHY_MAX_ADDR; addr++) { + phydev = mdiobus_get_phy(fep->mii_bus, addr); + if (phydev) + phydev->mac_managed_pm = true; + } + mii_cnt++; /* save fec0 mii_bus */ @@ -3671,29 +3678,6 @@ fec_set_mac_address(struct net_device *ndev, void *p) return 0; } -#ifdef CONFIG_NET_POLL_CONTROLLER -/** - * fec_poll_controller - FEC Poll controller function - * @dev: The FEC network adapter - * - * Polled functionality used by netconsole and others in non interrupt mode - * - */ -static void fec_poll_controller(struct net_device *dev) -{ - int i; - struct fec_enet_private *fep = netdev_priv(dev); - - for (i = 0; i < FEC_IRQ_NUM; i++) { - if (fep->irq[i] > 0) { - disable_irq(fep->irq[i]); - fec_enet_interrupt(fep->irq[i], dev); - enable_irq(fep->irq[i]); - } - } -} -#endif - static inline void fec_enet_set_netdev_features(struct net_device *netdev, netdev_features_t features) { @@ -4000,9 +3984,6 @@ static const struct net_device_ops fec_netdev_ops = { .ndo_tx_timeout = fec_timeout, .ndo_set_mac_address = fec_set_mac_address, .ndo_eth_ioctl = phy_do_ioctl_running, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = fec_poll_controller, -#endif .ndo_set_features = fec_set_features, .ndo_bpf = fec_enet_bpf, .ndo_xdp_xmit = fec_enet_xdp_xmit, @@ -4153,6 +4134,14 @@ static int fec_enet_init(struct net_device *ndev) return ret; } +static void fec_enet_deinit(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + netif_napi_del(&fep->napi); + fec_enet_free_queue(ndev); +} + #ifdef CONFIG_OF static int fec_reset_phy(struct platform_device *pdev) { @@ -4547,6 +4536,7 @@ fec_probe(struct platform_device *pdev) fec_enet_mii_remove(fep); failed_mii_init: failed_irq: + fec_enet_deinit(ndev); failed_init: fec_ptp_stop(pdev); failed_reset: @@ -4610,6 +4600,7 @@ fec_drv_remove(struct platform_device *pdev) pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + fec_enet_deinit(ndev); free_netdev(ndev); } diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 181d9bfbee220..e32f6724f5681 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -104,14 +104,13 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable) struct timespec64 ts; u64 ns; - if (fep->pps_enable == enable) - return 0; - - fep->pps_channel = DEFAULT_PPS_CHANNEL; - fep->reload_period = PPS_OUPUT_RELOAD_PERIOD; - spin_lock_irqsave(&fep->tmreg_lock, flags); + if (fep->pps_enable == enable) { + spin_unlock_irqrestore(&fep->tmreg_lock, flags); + return 0; + } + if (enable) { /* clear capture or output compare interrupt status if have. */ @@ -532,6 +531,9 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp, int ret = 0; if (rq->type == PTP_CLK_REQ_PPS) { + fep->pps_channel = DEFAULT_PPS_CHANNEL; + fep->reload_period = PPS_OUPUT_RELOAD_PERIOD; + ret = fec_ptp_enable_pps(fep, on); return ret; diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index f281e42a7ef96..3d60ea25711fc 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -506,11 +506,13 @@ static void gve_rx_skb_hash(struct sk_buff *skb, skb_set_hash(skb, le32_to_cpu(compl_desc->hash), hash_type); } -static void gve_rx_free_skb(struct gve_rx_ring *rx) +static void gve_rx_free_skb(struct napi_struct *napi, struct gve_rx_ring *rx) { if (!rx->ctx.skb_head) return; + if (rx->ctx.skb_head == napi->skb) + napi->skb = NULL; dev_kfree_skb_any(rx->ctx.skb_head); rx->ctx.skb_head = NULL; rx->ctx.skb_tail = NULL; @@ -783,7 +785,7 @@ int gve_rx_poll_dqo(struct gve_notify_block *block, int budget) err = gve_rx_dqo(napi, rx, compl_desc, rx->q_num); if (err < 0) { - gve_rx_free_skb(rx); + gve_rx_free_skb(napi, rx); u64_stats_update_begin(&rx->statss); if (err == -ENOMEM) rx->rx_skb_alloc_fail++; @@ -826,7 +828,7 @@ int gve_rx_poll_dqo(struct gve_notify_block *block, int budget) /* gve_rx_complete_skb() will consume skb if successful */ if (gve_rx_complete_skb(rx, napi, compl_desc, feat) != 0) { - gve_rx_free_skb(rx); + gve_rx_free_skb(napi, rx); u64_stats_update_begin(&rx->statss); rx->rx_desc_err_dropped_pkt++; u64_stats_update_end(&rx->statss); diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index f59c4710f1188..c40a7bb749bba 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -501,28 +501,18 @@ static int gve_prep_tso(struct sk_buff *skb) if (unlikely(skb_shinfo(skb)->gso_size < GVE_TX_MIN_TSO_MSS_DQO)) return -1; + if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + return -EINVAL; + /* Needed because we will modify header. */ err = skb_cow_head(skb, 0); if (err < 0) return err; tcp = tcp_hdr(skb); - - /* Remove payload length from checksum. */ paylen = skb->len - skb_transport_offset(skb); - - switch (skb_shinfo(skb)->gso_type) { - case SKB_GSO_TCPV4: - case SKB_GSO_TCPV6: - csum_replace_by_diff(&tcp->check, - (__force __wsum)htonl(paylen)); - - /* Compute length of segmentation header. */ - header_len = skb_tcp_all_headers(skb); - break; - default: - return -EINVAL; - } + csum_replace_by_diff(&tcp->check, (__force __wsum)htonl(paylen)); + header_len = skb_tcp_all_headers(skb); if (unlikely(header_len > GVE_TX_MAX_HDR_SIZE_DQO)) return -EINVAL; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index d7e175a9cb49b..2f7195ba4902b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -895,7 +895,7 @@ struct hnae3_handle { struct hnae3_roce_private_info rinfo; }; - u32 numa_node_mask; /* for multi-chip support */ + nodemask_t numa_node_mask; /* for multi-chip support */ enum hnae3_port_base_vlan_state port_base_vlan_state; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index f3c9395d8351c..618f66d9586b3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -85,7 +85,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, hclge_comm_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_TX_STATS, true); - desc.data[0] = cpu_to_le32(tqp->index & 0x1ff); + desc.data[0] = cpu_to_le32(tqp->index); ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c index 3b6dbf158b98d..f72dc0cee30e5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c @@ -76,7 +76,7 @@ static int hns3_dcbnl_ieee_delapp(struct net_device *ndev, struct dcb_app *app) if (hns3_nic_resetting(ndev)) return -EBUSY; - if (h->kinfo.dcb_ops->ieee_setapp) + if (h->kinfo.dcb_ops->ieee_delapp) return h->kinfo.dcb_ops->ieee_delapp(h, app); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index f1695c889d3a0..31a5d1597fc7b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3539,6 +3539,9 @@ static int hns3_alloc_ring_buffers(struct hns3_enet_ring *ring) ret = hns3_alloc_and_attach_buffer(ring, i); if (ret) goto out_buffer_fail; + + if (!(i % HNS3_RESCHED_BD_NUM)) + cond_resched(); } return 0; @@ -5111,6 +5114,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv) } u64_stats_init(&priv->ring[i].syncp); + cond_resched(); } return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index acd756b0c7c9a..d36c4ed16d8dd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -214,6 +214,8 @@ enum hns3_nic_state { #define HNS3_CQ_MODE_EQE 1U #define HNS3_CQ_MODE_CQE 0U +#define HNS3_RESCHED_BD_NUM 1024 + enum hns3_pkt_l2t_type { HNS3_L2_TYPE_UNICAST, HNS3_L2_TYPE_MULTICAST, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 999a0ee162a64..941cb529d671f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -78,6 +78,9 @@ static const struct hns3_stats hns3_rxq_stats[] = { #define HNS3_NIC_LB_TEST_NO_MEM_ERR 1 #define HNS3_NIC_LB_TEST_TX_CNT_ERR 2 #define HNS3_NIC_LB_TEST_RX_CNT_ERR 3 +#define HNS3_NIC_LB_TEST_UNEXECUTED 4 + +static int hns3_get_sset_count(struct net_device *netdev, int stringset); static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) { @@ -418,18 +421,26 @@ static void hns3_do_external_lb(struct net_device *ndev, static void hns3_self_test(struct net_device *ndev, struct ethtool_test *eth_test, u64 *data) { + int cnt = hns3_get_sset_count(ndev, ETH_SS_TEST); struct hns3_nic_priv *priv = netdev_priv(ndev); struct hnae3_handle *h = priv->ae_handle; int st_param[HNAE3_LOOP_NONE][2]; bool if_running = netif_running(ndev); + int i; + + /* initialize the loopback test result, avoid marking an unexcuted + * loopback test as PASS. + */ + for (i = 0; i < cnt; i++) + data[i] = HNS3_NIC_LB_TEST_UNEXECUTED; if (hns3_nic_resetting(ndev)) { netdev_err(ndev, "dev resetting!"); - return; + goto failure; } if (!(eth_test->flags & ETH_TEST_FL_OFFLINE)) - return; + goto failure; if (netif_msg_ifdown(h)) netdev_info(ndev, "self test start\n"); @@ -451,6 +462,10 @@ static void hns3_self_test(struct net_device *ndev, if (netif_msg_ifdown(h)) netdev_info(ndev, "self test end\n"); + return; + +failure: + eth_test->flags |= ETH_TEST_FL_FAILED; } static void hns3_update_limit_promisc_mode(struct net_device *netdev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 5ea9e59569eff..09e007d3d1dac 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1524,6 +1524,9 @@ static int hclge_configure(struct hclge_dev *hdev) cfg.default_speed, ret); return ret; } + hdev->hw.mac.req_speed = hdev->hw.mac.speed; + hdev->hw.mac.req_autoneg = AUTONEG_ENABLE; + hdev->hw.mac.req_duplex = DUPLEX_FULL; hclge_parse_link_mode(hdev, cfg.speed_ability); @@ -1753,7 +1756,8 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps) nic->pdev = hdev->pdev; nic->ae_algo = &ae_algo; - nic->numa_node_mask = hdev->numa_node_mask; + bitmap_copy(nic->numa_node_mask.bits, hdev->numa_node_mask.bits, + MAX_NUMNODES); nic->kinfo.io_base = hdev->hw.hw.io_base; ret = hclge_knic_setup(vport, num_tqps, @@ -2445,7 +2449,8 @@ static int hclge_init_roce_base_info(struct hclge_vport *vport) roce->pdev = nic->pdev; roce->ae_algo = nic->ae_algo; - roce->numa_node_mask = nic->numa_node_mask; + bitmap_copy(roce->numa_node_mask.bits, nic->numa_node_mask.bits, + MAX_NUMNODES); return 0; } @@ -2890,7 +2895,10 @@ static int hclge_mac_init(struct hclge_dev *hdev) int ret; hdev->support_sfp_query = true; - hdev->hw.mac.duplex = HCLGE_MAC_FULL; + + if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + hdev->hw.mac.duplex = HCLGE_MAC_FULL; + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, hdev->hw.mac.duplex, hdev->hw.mac.lane_num); if (ret) @@ -3021,9 +3029,7 @@ static void hclge_push_link_status(struct hclge_dev *hdev) static void hclge_update_link_status(struct hclge_dev *hdev) { - struct hnae3_handle *rhandle = &hdev->vport[0].roce; struct hnae3_handle *handle = &hdev->vport[0].nic; - struct hnae3_client *rclient = hdev->roce_client; struct hnae3_client *client = hdev->nic_client; int state; int ret; @@ -3047,8 +3053,15 @@ static void hclge_update_link_status(struct hclge_dev *hdev) client->ops->link_status_change(handle, state); hclge_config_mac_tnl_int(hdev, state); - if (rclient && rclient->ops->link_status_change) - rclient->ops->link_status_change(rhandle, state); + + if (test_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state)) { + struct hnae3_handle *rhandle = &hdev->vport[0].roce; + struct hnae3_client *rclient = hdev->roce_client; + + if (rclient && rclient->ops->link_status_change) + rclient->ops->link_status_change(rhandle, + state); + } hclge_push_link_status(hdev); } @@ -3326,9 +3339,9 @@ hclge_set_phy_link_ksettings(struct hnae3_handle *handle, return ret; } - hdev->hw.mac.autoneg = cmd->base.autoneg; - hdev->hw.mac.speed = cmd->base.speed; - hdev->hw.mac.duplex = cmd->base.duplex; + hdev->hw.mac.req_autoneg = cmd->base.autoneg; + hdev->hw.mac.req_speed = cmd->base.speed; + hdev->hw.mac.req_duplex = cmd->base.duplex; linkmode_copy(hdev->hw.mac.advertising, cmd->link_modes.advertising); return 0; @@ -3361,9 +3374,9 @@ static int hclge_tp_port_init(struct hclge_dev *hdev) if (!hnae3_dev_phy_imp_supported(hdev)) return 0; - cmd.base.autoneg = hdev->hw.mac.autoneg; - cmd.base.speed = hdev->hw.mac.speed; - cmd.base.duplex = hdev->hw.mac.duplex; + cmd.base.autoneg = hdev->hw.mac.req_autoneg; + cmd.base.speed = hdev->hw.mac.req_speed; + cmd.base.duplex = hdev->hw.mac.req_duplex; linkmode_copy(cmd.link_modes.advertising, hdev->hw.mac.advertising); return hclge_set_phy_link_ksettings(&hdev->vport->nic, &cmd); @@ -7936,8 +7949,7 @@ static void hclge_set_timer_task(struct hnae3_handle *handle, bool enable) /* Set the DOWN flag here to disable link updating */ set_bit(HCLGE_STATE_DOWN, &hdev->state); - /* flush memory to make sure DOWN is seen by service task */ - smp_mb__before_atomic(); + smp_mb__after_atomic(); /* flush memory to make sure DOWN is seen by service task */ hclge_flush_link_update(hdev); } } @@ -9890,6 +9902,7 @@ static int hclge_set_vlan_protocol_type(struct hclge_dev *hdev) static int hclge_init_vlan_filter(struct hclge_dev *hdev) { struct hclge_vport *vport; + bool enable = true; int ret; int i; @@ -9909,8 +9922,12 @@ static int hclge_init_vlan_filter(struct hclge_dev *hdev) vport->cur_vlan_fltr_en = true; } + if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, hdev->ae_dev->caps) && + !test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, hdev->ae_dev->caps)) + enable = false; + return hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, - HCLGE_FILTER_FE_INGRESS, true, 0); + HCLGE_FILTER_FE_INGRESS, enable, 0); } static int hclge_init_vlan_type(struct hclge_dev *hdev) @@ -11220,6 +11237,12 @@ static int hclge_init_client_instance(struct hnae3_client *client, return ret; } +static bool hclge_uninit_need_wait(struct hclge_dev *hdev) +{ + return test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGE_STATE_LINK_UPDATING, &hdev->state); +} + static void hclge_uninit_client_instance(struct hnae3_client *client, struct hnae3_ae_dev *ae_dev) { @@ -11228,7 +11251,7 @@ static void hclge_uninit_client_instance(struct hnae3_client *client, if (hdev->roce_client) { clear_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state); - while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + while (hclge_uninit_need_wait(hdev)) msleep(HCLGE_WAIT_RESET_DONE); hdev->roce_client->ops->uninit_instance(&vport->roce, 0); @@ -11606,14 +11629,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) if (ret) goto out; - ret = hclge_devlink_init(hdev); - if (ret) - goto err_pci_uninit; - /* Firmware command queue initialize */ ret = hclge_comm_cmd_queue_init(hdev->pdev, &hdev->hw.hw); if (ret) - goto err_devlink_uninit; + goto err_pci_uninit; /* Firmware command initialize */ ret = hclge_comm_cmd_init(hdev->ae_dev, &hdev->hw.hw, &hdev->fw_version, @@ -11741,7 +11760,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) ret = hclge_update_port_info(hdev); if (ret) - goto err_mdiobus_unreg; + goto err_ptp_uninit; INIT_KFIFO(hdev->mac_tnl_log); @@ -11781,6 +11800,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) dev_warn(&pdev->dev, "failed to wake on lan init, ret = %d\n", ret); + ret = hclge_devlink_init(hdev); + if (ret) + goto err_ptp_uninit; + hclge_state_init(hdev); hdev->last_reset_time = jiffies; @@ -11788,9 +11811,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) HCLGE_DRIVER_NAME); hclge_task_schedule(hdev, round_jiffies_relative(HZ)); - return 0; +err_ptp_uninit: + hclge_ptp_uninit(hdev); err_mdiobus_unreg: if (hdev->hw.mac.phydev) mdiobus_unregister(hdev->hw.mac.mdio_bus); @@ -11800,8 +11824,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) pci_free_irq_vectors(pdev); err_cmd_uninit: hclge_comm_cmd_uninit(hdev->ae_dev, &hdev->hw.hw); -err_devlink_uninit: - hclge_devlink_uninit(hdev); err_pci_uninit: pcim_iounmap(pdev, hdev->hw.hw.io_base); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 51979cf712623..d4a146c53c5e9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -270,11 +270,14 @@ struct hclge_mac { u8 media_type; /* port media type, e.g. fibre/copper/backplane */ u8 mac_addr[ETH_ALEN]; u8 autoneg; + u8 req_autoneg; u8 duplex; + u8 req_duplex; u8 support_autoneg; u8 speed_type; /* 0: sfp speed, 1: active speed */ u8 lane_num; u32 speed; + u32 req_speed; u32 max_speed; u32 speed_ability; /* speed ability supported by current media */ u32 module_type; /* sub media type, e.g. kr/cr/sr/lr */ @@ -882,7 +885,7 @@ struct hclge_dev { u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */ u16 num_alloc_vport; /* Num vports this driver supports */ - u32 numa_node_mask; + nodemask_t numa_node_mask; u16 rx_buf_len; u16 num_tx_desc; /* desc num of per tx queue */ u16 num_rx_desc; /* desc num of per rx queue */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 4b0d07ca2505e..a44659906ca0e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -1077,12 +1077,13 @@ static void hclge_mbx_request_handling(struct hclge_mbx_ops_param *param) hdev = param->vport->back; cmd_func = hclge_mbx_ops_list[param->req->msg.code]; - if (cmd_func) - ret = cmd_func(param); - else + if (!cmd_func) { dev_err(&hdev->pdev->dev, "un-supported mailbox message, code = %u\n", param->req->msg.code); + return; + } + ret = cmd_func(param); /* PF driver should not reply IMP */ if (hnae3_get_bit(param->req->mbx_need_resp, HCLGE_MBX_NEED_RESP_B) && diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index 80a2a0073d97a..507d7ce26d831 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -108,7 +108,7 @@ void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb, u64 ns = nsec; u32 sec_h; - if (!test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags)) + if (!hdev->ptp || !test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags)) return; /* Since the BD does not have enough space for the higher 16 bits of diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h index 8510b88d49820..f3cd5a376eca9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h @@ -24,7 +24,7 @@ TRACE_EVENT(hclge_pf_mbx_get, __field(u8, code) __field(u8, subcode) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __string(devname, hdev->vport[0].nic.kinfo.netdev->name) __array(u32, mbx_data, PF_GET_MBX_LEN) ), @@ -33,7 +33,7 @@ TRACE_EVENT(hclge_pf_mbx_get, __entry->code = req->msg.code; __entry->subcode = req->msg.subcode; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + __assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_vf_to_pf_cmd)); ), @@ -56,7 +56,7 @@ TRACE_EVENT(hclge_pf_mbx_send, __field(u8, vfid) __field(u16, code) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __string(devname, hdev->vport[0].nic.kinfo.netdev->name) __array(u32, mbx_data, PF_SEND_MBX_LEN) ), @@ -64,7 +64,7 @@ TRACE_EVENT(hclge_pf_mbx_send, __entry->vfid = req->dest_vfid; __entry->code = le16_to_cpu(req->msg.code); __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + __assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_pf_to_vf_cmd)); ), diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 0aa9beefd1c7e..43ee20eb03d1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -412,7 +412,8 @@ static int hclgevf_set_handle_info(struct hclgevf_dev *hdev) nic->ae_algo = &ae_algovf; nic->pdev = hdev->pdev; - nic->numa_node_mask = hdev->numa_node_mask; + bitmap_copy(nic->numa_node_mask.bits, hdev->numa_node_mask.bits, + MAX_NUMNODES); nic->flags |= HNAE3_SUPPORT_VF; nic->kinfo.io_base = hdev->hw.hw.io_base; @@ -2082,8 +2083,8 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev) roce->pdev = nic->pdev; roce->ae_algo = nic->ae_algo; - roce->numa_node_mask = nic->numa_node_mask; - + bitmap_copy(roce->numa_node_mask.bits, nic->numa_node_mask.bits, + MAX_NUMNODES); return 0; } @@ -2180,8 +2181,7 @@ static void hclgevf_set_timer_task(struct hnae3_handle *handle, bool enable) } else { set_bit(HCLGEVF_STATE_DOWN, &hdev->state); - /* flush memory to make sure DOWN is seen by service task */ - smp_mb__before_atomic(); + smp_mb__after_atomic(); /* flush memory to make sure DOWN is seen by service task */ hclgevf_flush_link_update(hdev); } } @@ -2845,10 +2845,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) if (ret) return ret; - ret = hclgevf_devlink_init(hdev); - if (ret) - goto err_devlink_init; - ret = hclge_comm_cmd_queue_init(hdev->pdev, &hdev->hw.hw); if (ret) goto err_cmd_queue_init; @@ -2941,6 +2937,10 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) hclgevf_init_rxd_adv_layout(hdev); + ret = hclgevf_devlink_init(hdev); + if (ret) + goto err_config; + set_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state); hdev->last_reset_time = jiffies; @@ -2960,8 +2960,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) err_cmd_init: hclge_comm_cmd_uninit(hdev->ae_dev, &hdev->hw.hw); err_cmd_queue_init: - hclgevf_devlink_uninit(hdev); -err_devlink_init: hclgevf_pci_uninit(hdev); clear_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state); return ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index a73f2bf3a56a6..cccef32284616 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -236,7 +236,7 @@ struct hclgevf_dev { u16 rss_size_max; /* HW defined max RSS task queue */ u16 num_alloc_vport; /* num vports this driver supports */ - u32 numa_node_mask; + nodemask_t numa_node_mask; u16 rx_buf_len; u16 num_tx_desc; /* desc num of per tx queue */ u16 num_rx_desc; /* desc num of per rx queue */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h index 5d4895bb57a17..b259e95dd53c2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h @@ -23,7 +23,7 @@ TRACE_EVENT(hclge_vf_mbx_get, __field(u8, vfid) __field(u16, code) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->nic.kinfo.netdev->name) + __string(devname, hdev->nic.kinfo.netdev->name) __array(u32, mbx_data, VF_GET_MBX_LEN) ), @@ -31,7 +31,7 @@ TRACE_EVENT(hclge_vf_mbx_get, __entry->vfid = req->dest_vfid; __entry->code = le16_to_cpu(req->msg.code); __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->nic.kinfo.netdev->name); + __assign_str(devname, hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_pf_to_vf_cmd)); ), @@ -55,7 +55,7 @@ TRACE_EVENT(hclge_vf_mbx_send, __field(u8, code) __field(u8, subcode) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->nic.kinfo.netdev->name) + __string(devname, hdev->nic.kinfo.netdev->name) __array(u32, mbx_data, VF_SEND_MBX_LEN) ), @@ -64,7 +64,7 @@ TRACE_EVENT(hclge_vf_mbx_send, __entry->code = req->msg.code; __entry->subcode = req->msg.subcode; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->nic.kinfo.netdev->name); + __assign_str(devname, hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_vf_to_pf_cmd)); ), diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 1fef6bb5a5fbc..4b6e7536170ab 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -628,6 +628,7 @@ struct e1000_phy_info { u32 id; u32 reset_delay_us; /* in usec */ u32 revision; + u32 retry_count; enum e1000_media_type media_type; @@ -644,6 +645,7 @@ struct e1000_phy_info { bool polarity_correction; bool speed_downgraded; bool autoneg_wait_to_complete; + bool retry_enabled; }; struct e1000_nvm_info { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 19e450a5bd314..ce227b56cf724 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -222,11 +222,18 @@ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw) if (hw->mac.type >= e1000_pch_lpt) { /* Only unforce SMBus if ME is not active */ if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) { + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + /* Unforce SMBus mode in PHY */ e1e_rphy_locked(hw, CV_SMB_CTRL, &phy_reg); phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS; e1e_wphy_locked(hw, CV_SMB_CTRL, phy_reg); + e1000e_enable_phy_retry(hw); + /* Unforce SMBus mode in MAC */ mac_reg = er32(CTRL_EXT); mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; @@ -310,6 +317,11 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) goto out; } + /* There is no guarantee that the PHY is accessible at this time + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + /* The MAC-PHY interconnect may be in SMBus mode. If the PHY is * inaccessible and resetting the PHY is not blocked, toggle the * LANPHYPC Value bit to force the interconnect to PCIe mode. @@ -380,6 +392,8 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) break; } + e1000e_enable_phy_retry(hw); + hw->phy.ops.release(hw); if (!ret_val) { @@ -449,6 +463,11 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) phy->id = e1000_phy_unknown; + if (hw->mac.type == e1000_pch_mtp) { + phy->retry_count = 2; + e1000e_enable_phy_retry(hw); + } + ret_val = e1000_init_phy_workarounds_pchlan(hw); if (ret_val) return ret_val; @@ -1089,6 +1108,46 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) return 0; } +/** + * e1000e_force_smbus - Force interfaces to transition to SMBUS mode. + * @hw: pointer to the HW structure + * + * Force the MAC and the PHY to SMBUS mode. Assumes semaphore already + * acquired. + * + * Return: 0 on success, negative errno on failure. + **/ +static s32 e1000e_force_smbus(struct e1000_hw *hw) +{ + u16 smb_ctrl = 0; + u32 ctrl_ext; + s32 ret_val; + + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + + /* Force SMBus mode in the PHY */ + ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &smb_ctrl); + if (ret_val) { + e1000e_enable_phy_retry(hw); + return ret_val; + } + + smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS; + e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, smb_ctrl); + + e1000e_enable_phy_retry(hw); + + /* Force SMBus mode in the MAC */ + ctrl_ext = er32(CTRL_EXT); + ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, ctrl_ext); + + return 0; +} + /** * e1000_enable_ulp_lpt_lp - configure Ultra Low Power mode for LynxPoint-LP * @hw: pointer to the HW structure @@ -1146,17 +1205,13 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) if (ret_val) goto out; - /* Force SMBus mode in PHY */ - ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); - if (ret_val) - goto release; - phy_reg |= CV_SMB_CTRL_FORCE_SMBUS; - e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); - - /* Force SMBus mode in MAC */ - mac_reg = er32(CTRL_EXT); - mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS; - ew32(CTRL_EXT, mac_reg); + if (hw->mac.type != e1000_pch_mtp) { + ret_val = e1000e_force_smbus(hw); + if (ret_val) { + e_dbg("Failed to force SMBUS: %d\n", ret_val); + goto release; + } + } /* Si workaround for ULP entry flow on i127/rev6 h/w. Enable * LPLU and disable Gig speed when entering ULP @@ -1218,6 +1273,13 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) } release: + if (hw->mac.type == e1000_pch_mtp) { + ret_val = e1000e_force_smbus(hw); + if (ret_val) + e_dbg("Failed to force SMBUS over MTL system: %d\n", + ret_val); + } + hw->phy.ops.release(hw); out: if (ret_val) @@ -1313,6 +1375,11 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force) /* Toggle LANPHYPC Value bit */ e1000_toggle_lanphypc_pch_lpt(hw); + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + /* Unforce SMBus mode in PHY */ ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); if (ret_val) { @@ -1333,6 +1400,8 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force) phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS; e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); + e1000e_enable_phy_retry(hw); + /* Unforce SMBus mode in MAC */ mac_reg = er32(CTRL_EXT); mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index af5d9d97a0d6c..cc8c531ec3dff 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6688,14 +6688,14 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (adapter->hw.phy.type == e1000_phy_igp_3) { e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw); } else if (hw->mac.type >= e1000_pch_lpt) { - if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) + if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) { /* ULP does not support wake from unicast, multicast * or broadcast. */ retval = e1000_enable_ulp_lpt_lp(hw, !runtime); - - if (retval) - return retval; + if (retval) + return retval; + } } /* Ensure that the appropriate bits are set in LPI_CTRL diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 5e329156d1bae..f7ae0e0aa4a4f 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -107,6 +107,16 @@ s32 e1000e_phy_reset_dsp(struct e1000_hw *hw) return e1e_wphy(hw, M88E1000_PHY_GEN_CONTROL, 0); } +void e1000e_disable_phy_retry(struct e1000_hw *hw) +{ + hw->phy.retry_enabled = false; +} + +void e1000e_enable_phy_retry(struct e1000_hw *hw) +{ + hw->phy.retry_enabled = true; +} + /** * e1000e_read_phy_reg_mdic - Read MDI control register * @hw: pointer to the HW structure @@ -118,55 +128,73 @@ s32 e1000e_phy_reset_dsp(struct e1000_hw *hw) **/ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) { + u32 i, mdic = 0, retry_counter, retry_max; struct e1000_phy_info *phy = &hw->phy; - u32 i, mdic = 0; + bool success; if (offset > MAX_PHY_REG_ADDRESS) { e_dbg("PHY Address %d is out of range\n", offset); return -E1000_ERR_PARAM; } + retry_max = phy->retry_enabled ? phy->retry_count : 0; + /* Set up Op-code, Phy Address, and register offset in the MDI * Control register. The MAC will take care of interfacing with the * PHY to retrieve the desired data. */ - mdic = ((offset << E1000_MDIC_REG_SHIFT) | - (phy->addr << E1000_MDIC_PHY_SHIFT) | - (E1000_MDIC_OP_READ)); + for (retry_counter = 0; retry_counter <= retry_max; retry_counter++) { + success = true; - ew32(MDIC, mdic); + mdic = ((offset << E1000_MDIC_REG_SHIFT) | + (phy->addr << E1000_MDIC_PHY_SHIFT) | + (E1000_MDIC_OP_READ)); - /* Poll the ready bit to see if the MDI read completed - * Increasing the time out as testing showed failures with - * the lower time out - */ - for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { - udelay(50); - mdic = er32(MDIC); - if (mdic & E1000_MDIC_READY) - break; - } - if (!(mdic & E1000_MDIC_READY)) { - e_dbg("MDI Read PHY Reg Address %d did not complete\n", offset); - return -E1000_ERR_PHY; - } - if (mdic & E1000_MDIC_ERROR) { - e_dbg("MDI Read PHY Reg Address %d Error\n", offset); - return -E1000_ERR_PHY; - } - if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { - e_dbg("MDI Read offset error - requested %d, returned %d\n", - offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); - return -E1000_ERR_PHY; + ew32(MDIC, mdic); + + /* Poll the ready bit to see if the MDI read completed + * Increasing the time out as testing showed failures with + * the lower time out + */ + for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { + udelay(50); + mdic = er32(MDIC); + if (mdic & E1000_MDIC_READY) + break; + } + if (!(mdic & E1000_MDIC_READY)) { + e_dbg("MDI Read PHY Reg Address %d did not complete\n", + offset); + success = false; + } + if (mdic & E1000_MDIC_ERROR) { + e_dbg("MDI Read PHY Reg Address %d Error\n", offset); + success = false; + } + if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { + e_dbg("MDI Read offset error - requested %d, returned %d\n", + offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); + success = false; + } + + /* Allow some time after each MDIC transaction to avoid + * reading duplicate data in the next MDIC transaction. + */ + if (hw->mac.type == e1000_pch2lan) + udelay(100); + + if (success) { + *data = (u16)mdic; + return 0; + } + + if (retry_counter != retry_max) { + e_dbg("Perform retry on PHY transaction...\n"); + mdelay(10); + } } - *data = (u16)mdic; - /* Allow some time after each MDIC transaction to avoid - * reading duplicate data in the next MDIC transaction. - */ - if (hw->mac.type == e1000_pch2lan) - udelay(100); - return 0; + return -E1000_ERR_PHY; } /** @@ -179,56 +207,72 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) **/ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) { + u32 i, mdic = 0, retry_counter, retry_max; struct e1000_phy_info *phy = &hw->phy; - u32 i, mdic = 0; + bool success; if (offset > MAX_PHY_REG_ADDRESS) { e_dbg("PHY Address %d is out of range\n", offset); return -E1000_ERR_PARAM; } + retry_max = phy->retry_enabled ? phy->retry_count : 0; + /* Set up Op-code, Phy Address, and register offset in the MDI * Control register. The MAC will take care of interfacing with the * PHY to retrieve the desired data. */ - mdic = (((u32)data) | - (offset << E1000_MDIC_REG_SHIFT) | - (phy->addr << E1000_MDIC_PHY_SHIFT) | - (E1000_MDIC_OP_WRITE)); + for (retry_counter = 0; retry_counter <= retry_max; retry_counter++) { + success = true; - ew32(MDIC, mdic); + mdic = (((u32)data) | + (offset << E1000_MDIC_REG_SHIFT) | + (phy->addr << E1000_MDIC_PHY_SHIFT) | + (E1000_MDIC_OP_WRITE)); - /* Poll the ready bit to see if the MDI read completed - * Increasing the time out as testing showed failures with - * the lower time out - */ - for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { - udelay(50); - mdic = er32(MDIC); - if (mdic & E1000_MDIC_READY) - break; - } - if (!(mdic & E1000_MDIC_READY)) { - e_dbg("MDI Write PHY Reg Address %d did not complete\n", offset); - return -E1000_ERR_PHY; - } - if (mdic & E1000_MDIC_ERROR) { - e_dbg("MDI Write PHY Red Address %d Error\n", offset); - return -E1000_ERR_PHY; - } - if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { - e_dbg("MDI Write offset error - requested %d, returned %d\n", - offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); - return -E1000_ERR_PHY; - } + ew32(MDIC, mdic); - /* Allow some time after each MDIC transaction to avoid - * reading duplicate data in the next MDIC transaction. - */ - if (hw->mac.type == e1000_pch2lan) - udelay(100); + /* Poll the ready bit to see if the MDI read completed + * Increasing the time out as testing showed failures with + * the lower time out + */ + for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) { + udelay(50); + mdic = er32(MDIC); + if (mdic & E1000_MDIC_READY) + break; + } + if (!(mdic & E1000_MDIC_READY)) { + e_dbg("MDI Write PHY Reg Address %d did not complete\n", + offset); + success = false; + } + if (mdic & E1000_MDIC_ERROR) { + e_dbg("MDI Write PHY Reg Address %d Error\n", offset); + success = false; + } + if (FIELD_GET(E1000_MDIC_REG_MASK, mdic) != offset) { + e_dbg("MDI Write offset error - requested %d, returned %d\n", + offset, FIELD_GET(E1000_MDIC_REG_MASK, mdic)); + success = false; + } - return 0; + /* Allow some time after each MDIC transaction to avoid + * reading duplicate data in the next MDIC transaction. + */ + if (hw->mac.type == e1000_pch2lan) + udelay(100); + + if (success) + return 0; + + if (retry_counter != retry_max) { + e_dbg("Perform retry on PHY transaction...\n"); + mdelay(10); + } + } + + return -E1000_ERR_PHY; } /** diff --git a/drivers/net/ethernet/intel/e1000e/phy.h b/drivers/net/ethernet/intel/e1000e/phy.h index c48777d095235..049bb325b4b14 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.h +++ b/drivers/net/ethernet/intel/e1000e/phy.h @@ -51,6 +51,8 @@ s32 e1000e_read_phy_reg_bm2(struct e1000_hw *hw, u32 offset, u16 *data); s32 e1000e_write_phy_reg_bm2(struct e1000_hw *hw, u32 offset, u16 data); void e1000_power_up_phy_copper(struct e1000_hw *hw); void e1000_power_down_phy_copper(struct e1000_hw *hw); +void e1000e_disable_phy_retry(struct e1000_hw *hw); +void e1000e_enable_phy_retry(struct e1000_hw *hw); s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data); s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data); s32 e1000_read_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 *data); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 9b701615c7c62..4d2b05de6c634 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -908,6 +908,7 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; + bool in_busy_poll; int irq_num; /* IRQ assigned to this q_vector */ } ____cacheline_internodealigned_in_smp; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 89a3401d20ab4..f3c1df46f699c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1257,8 +1257,11 @@ int i40e_count_filters(struct i40e_vsi *vsi) int bkt; int cnt = 0; - hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) - ++cnt; + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_ACTIVE) + ++cnt; + } return cnt; } @@ -3915,6 +3918,12 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; + /* Set ITR for software interrupts triggered after exiting + * busy-loop polling. + */ + wr32(hw, I40E_PFINT_ITRN(I40E_SW_ITR, vector - 1), + I40E_ITR_20K); + wr32(hw, I40E_PFINT_RATEN(vector - 1), i40e_intrl_usec_to_reg(vsi->int_rate_limit)); @@ -16177,8 +16186,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK, rd32(&pf->hw, I40E_PRTGL_SAH)); if (val < MAX_FRAME_SIZE_DEFAULT) - dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n", - pf->hw.port, val); + dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n", + pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out @@ -16724,7 +16733,7 @@ static int __init i40e_init_module(void) * since we need to be able to guarantee forward progress even under * memory pressure. */ - i40e_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, i40e_driver_name); + i40e_wq = alloc_workqueue("%s", 0, 0, i40e_driver_name); if (!i40e_wq) { pr_err("%s: Failed to create workqueue\n", i40e_driver_name); return -ENOMEM; diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 14ab642cafdb2..432afbb642013 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -333,8 +333,11 @@ #define I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT 3 #define I40E_PFINT_DYN_CTLN_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) #define I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT 5 +#define I40E_PFINT_DYN_CTLN_INTERVAL_MASK I40E_MASK(0xFFF, I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT) #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT 24 #define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_SHIFT) +#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT 25 +#define I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_PFINT_DYN_CTLN_SW_ITR_INDX_SHIFT) #define I40E_PFINT_ICR0 0x00038780 /* Reset: CORER */ #define I40E_PFINT_ICR0_INTEVENT_SHIFT 0 #define I40E_PFINT_ICR0_INTEVENT_MASK I40E_MASK(0x1, I40E_PFINT_ICR0_INTEVENT_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 0d7177083708f..1a12b732818ee 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2630,7 +2630,22 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, return failure ? budget : (int)total_rx_packets; } -static inline u32 i40e_buildreg_itr(const int type, u16 itr) +/** + * i40e_buildreg_itr - build a value for writing to I40E_PFINT_DYN_CTLN register + * @itr_idx: interrupt throttling index + * @interval: interrupt throttling interval value in usecs + * @force_swint: force software interrupt + * + * The function builds a value for I40E_PFINT_DYN_CTLN register that + * is used to update interrupt throttling interval for specified ITR index + * and optionally enforces a software interrupt. If the @itr_idx is equal + * to I40E_ITR_NONE then no interval change is applied and only @force_swint + * parameter is taken into account. If the interval change and enforced + * software interrupt are not requested then the built value just enables + * appropriate vector interrupt. + **/ +static u32 i40e_buildreg_itr(enum i40e_dyn_idx itr_idx, u16 interval, + bool force_swint) { u32 val; @@ -2644,23 +2659,33 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) * an event in the PBA anyway so we need to rely on the automask * to hold pending events for us until the interrupt is re-enabled * - * The itr value is reported in microseconds, and the register - * value is recorded in 2 microsecond units. For this reason we - * only need to shift by the interval shift - 1 instead of the - * full value. + * We have to shift the given value as it is reported in microseconds + * and the register value is recorded in 2 microsecond units. */ - itr &= I40E_ITR_MASK; + interval >>= 1; + /* 1. Enable vector interrupt + * 2. Update the interval for the specified ITR index + * (I40E_ITR_NONE in the register is used to indicate that + * no interval update is requested) + */ val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | - (itr << (I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT - 1)); + FIELD_PREP(I40E_PFINT_DYN_CTLN_ITR_INDX_MASK, itr_idx) | + FIELD_PREP(I40E_PFINT_DYN_CTLN_INTERVAL_MASK, interval); + + /* 3. Enforce software interrupt trigger if requested + * (These software interrupts rate is limited by ITR2 that is + * set to 20K interrupts per second) + */ + if (force_swint) + val |= I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK | + I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK | + FIELD_PREP(I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK, + I40E_SW_ITR); return val; } -/* a small macro to shorten up some long lines */ -#define INTREG I40E_PFINT_DYN_CTLN - /* The act of updating the ITR will cause it to immediately trigger. In order * to prevent this from throwing off adaptive update statistics we defer the * update so that it can only happen so often. So after either Tx or Rx are @@ -2679,8 +2704,10 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { + enum i40e_dyn_idx itr_idx = I40E_ITR_NONE; struct i40e_hw *hw = &vsi->back->hw; - u32 intval; + u16 interval = 0; + u32 itr_val; /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!test_bit(I40E_FLAG_MSIX_ENA, vsi->back->flags)) { @@ -2702,8 +2729,8 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ if (q_vector->rx.target_itr < q_vector->rx.current_itr) { /* Rx ITR needs to be reduced, this is highest priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, - q_vector->rx.target_itr); + itr_idx = I40E_RX_ITR; + interval = q_vector->rx.target_itr; q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || @@ -2712,25 +2739,36 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* Tx ITR needs to be reduced, this is second priority * Tx ITR needs to be increased more than Rx, fourth priority */ - intval = i40e_buildreg_itr(I40E_TX_ITR, - q_vector->tx.target_itr); + itr_idx = I40E_TX_ITR; + interval = q_vector->tx.target_itr; q_vector->tx.current_itr = q_vector->tx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { /* Rx ITR needs to be increased, third priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, - q_vector->rx.target_itr); + itr_idx = I40E_RX_ITR; + interval = q_vector->rx.target_itr; q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else { /* No ITR update, lowest priority */ - intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); if (q_vector->itr_countdown) q_vector->itr_countdown--; } - if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), intval); + /* Do not update interrupt control register if VSI is down */ + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + return; + + /* Update ITR interval if necessary and enforce software interrupt + * if we are exiting busy poll. + */ + if (q_vector->in_busy_poll) { + itr_val = i40e_buildreg_itr(itr_idx, interval, true); + q_vector->in_busy_poll = false; + } else { + itr_val = i40e_buildreg_itr(itr_idx, interval, false); + } + wr32(hw, I40E_PFINT_DYN_CTLN(q_vector->reg_idx), itr_val); } /** @@ -2845,6 +2883,8 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) */ if (likely(napi_complete_done(napi, work_done))) i40e_update_enable_itr(vsi, q_vector); + else + q_vector->in_busy_poll = true; return min(work_done, budget - 1); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index abf15067eb5de..2cdc7de6301c1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -68,6 +68,7 @@ enum i40e_dyn_idx { /* these are indexes into ITRN registers */ #define I40E_RX_ITR I40E_IDX_ITR0 #define I40E_TX_ITR I40E_IDX_ITR1 +#define I40E_SW_ITR I40E_IDX_ITR2 /* Supported RSS offloads */ #define I40E_DEFAULT_RSS_HENA ( \ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index b34c717708874..37e77163da4cd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1628,8 +1628,8 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) { struct i40e_hw *hw = &pf->hw; struct i40e_vf *vf; - int i, v; u32 reg; + int i; /* If we don't have any VFs, then there is nothing to reset */ if (!pf->num_alloc_vfs) @@ -1640,11 +1640,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) return false; /* Begin reset on all VFs at once */ - for (v = 0; v < pf->num_alloc_vfs; v++) { - vf = &pf->vf[v]; + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is being reset no need to trigger reset again */ if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) - i40e_trigger_vf_reset(&pf->vf[v], flr); + i40e_trigger_vf_reset(vf, flr); } /* HW requires some time to make sure it can flush the FIFO for a VF @@ -1653,14 +1652,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) * the VFs using a simple iterator that increments once that VF has * finished resetting. */ - for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + for (i = 0, vf = &pf->vf[0]; i < 10 && vf < &pf->vf[pf->num_alloc_vfs]; ++i) { usleep_range(10000, 20000); /* Check each VF in sequence, beginning with the VF to fail * the previous check. */ - while (v < pf->num_alloc_vfs) { - vf = &pf->vf[v]; + while (vf < &pf->vf[pf->num_alloc_vfs]) { if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) { reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) @@ -1670,7 +1668,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* If the current VF has finished resetting, move on * to the next VF in sequence. */ - v++; + ++vf; } } @@ -1680,39 +1678,39 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* Display a warning if at least one VF didn't manage to reset in * time, but continue on with the operation. */ - if (v < pf->num_alloc_vfs) + if (vf < &pf->vf[pf->num_alloc_vfs]) dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", - pf->vf[v].vf_id); + vf->vf_id); usleep_range(10000, 20000); /* Begin disabling all the rings associated with VFs, but do not wait * between each VF. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_stop_rings_no_wait(pf->vsi[vf->lan_vsi_idx]); } /* Now that we've notified HW to disable all of the VF rings, wait * until they finish. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_wait_queues_disabled(pf->vsi[vf->lan_vsi_idx]); } /* Hw may need up to 50ms to finish disabling the RX queues. We @@ -1721,12 +1719,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) mdelay(50); /* Finish the reset on each VF */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_cleanup_reset_vf(&pf->vf[v]); + i40e_cleanup_reset_vf(vf); } i40e_flush(hw); @@ -3143,11 +3141,12 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) /* Allow to delete VF primary MAC only if it was not set * administratively by PF or if VF is trusted. */ - if (ether_addr_equal(addr, vf->default_lan_addr.addr) && - i40e_can_vf_change_mac(vf)) - was_unimac_deleted = true; - else - continue; + if (ether_addr_equal(addr, vf->default_lan_addr.addr)) { + if (i40e_can_vf_change_mac(vf)) + was_unimac_deleted = true; + else + continue; + } if (i40e_del_mac_filter(vsi, al->list[i].addr)) { ret = -EINVAL; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 335fd13e86f71..1ff381361c29d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3511,6 +3511,34 @@ static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) spin_unlock_bh(&adapter->cloud_filter_list_lock); } +/** + * iavf_is_tc_config_same - Compare the mqprio TC config with the + * TC config already configured on this adapter. + * @adapter: board private structure + * @mqprio_qopt: TC config received from kernel. + * + * This function compares the TC config received from the kernel + * with the config already configured on the adapter. + * + * Return: True if configuration is same, false otherwise. + **/ +static bool iavf_is_tc_config_same(struct iavf_adapter *adapter, + struct tc_mqprio_qopt *mqprio_qopt) +{ + struct virtchnl_channel_info *ch = &adapter->ch_config.ch_info[0]; + int i; + + if (adapter->num_tc != mqprio_qopt->num_tc) + return false; + + for (i = 0; i < adapter->num_tc; i++) { + if (ch[i].count != mqprio_qopt->count[i] || + ch[i].offset != mqprio_qopt->offset[i]) + return false; + } + return true; +} + /** * __iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure @@ -3568,7 +3596,7 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data) if (ret) return ret; /* Return if same TC config is requested */ - if (adapter->num_tc == num_tc) + if (iavf_is_tc_config_same(adapter, &mqprio_qopt->qopt)) return 0; adapter->num_tc = num_tc; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 367b613d92c05..ef501cb86f9b4 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -412,7 +412,6 @@ struct ice_vsi { struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; struct ice_tx_ring **xdp_rings; /* XDP ring array */ - unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ @@ -748,6 +747,25 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) ring->flags |= ICE_TX_FLAGS_RING_XDP; } +/** + * ice_get_xp_from_qid - get ZC XSK buffer pool bound to a queue ID + * @vsi: pointer to VSI + * @qid: index of a queue to look at XSK buff pool presence + * + * Return: A pointer to xsk_buff_pool structure if there is a buffer pool + * attached and configured as zero-copy, NULL otherwise. + */ +static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi, + u16 qid) +{ + struct xsk_buff_pool *pool = xsk_get_pool_from_qid(vsi->netdev, qid); + + if (!ice_is_xdp_ena_vsi(vsi)) + return NULL; + + return (pool && pool->dev) ? pool : NULL; +} + /** * ice_xsk_pool - get XSK buffer pool bound to a ring * @ring: Rx ring to use @@ -760,10 +778,7 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index; - if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) - return NULL; - - return xsk_get_pool_from_qid(vsi->netdev, qid); + return ice_get_xp_from_qid(vsi, qid); } /** @@ -788,12 +803,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid) if (!ring) return; - if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) { - ring->xsk_pool = NULL; - return; - } - - ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid); + ring->xsk_pool = ice_get_xp_from_qid(vsi, qid); } /** @@ -921,9 +931,17 @@ int ice_down(struct ice_vsi *vsi); int ice_down_up(struct ice_vsi *vsi); int ice_vsi_cfg_lan(struct ice_vsi *vsi); struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); + +enum ice_xdp_cfg { + ICE_XDP_CFG_FULL, /* Fully apply new config in .ndo_bpf() */ + ICE_XDP_CFG_PART, /* Save/use part of config in VSI rebuild */ +}; + int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); -int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog); -int ice_destroy_xdp_rings(struct ice_vsi *vsi); +int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, + enum ice_xdp_cfg cfg_type); +int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type); +void ice_map_xdp_rings(struct ice_vsi *vsi); int ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 8040317c95617..1f3e7a6903e56 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -593,8 +593,9 @@ struct ice_aqc_recipe_data_elem { struct ice_aqc_recipe_to_profile { __le16 profile_id; u8 rsvd[6]; - DECLARE_BITMAP(recipe_assoc, ICE_MAX_NUM_RECIPES); + __le64 recipe_assoc; }; +static_assert(sizeof(struct ice_aqc_recipe_to_profile) == 16); /* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3) */ diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index c979192e44d10..9d23a436d2a6a 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -536,7 +536,7 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) * * Return 0 on success and a negative value on error. */ -int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) +static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); u32 num_bufs = ICE_RX_DESC_UNUSED(ring); @@ -631,6 +631,62 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) return 0; } +int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) +{ + if (q_idx >= vsi->num_rxq) + return -EINVAL; + + return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]); +} + +/** + * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length + * @vsi: VSI + */ +static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) +{ + if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { + vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; + vsi->rx_buf_len = ICE_RXBUF_1664; +#if (PAGE_SIZE < 8192) + } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && + (vsi->netdev->mtu <= ETH_DATA_LEN)) { + vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; + vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; +#endif + } else { + vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; + vsi->rx_buf_len = ICE_RXBUF_3072; + } +} + +/** + * ice_vsi_cfg_rxqs - Configure the VSI for Rx + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Rx VSI for operation. + */ +int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) +{ + u16 i; + + if (vsi->type == ICE_VSI_VF) + goto setup_rings; + + ice_vsi_cfg_frame_size(vsi); +setup_rings: + /* set up individual rings */ + ice_for_each_rxq(vsi, i) { + int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]); + + if (err) + return err; + } + + return 0; +} + /** * __ice_vsi_get_qs - helper function for assigning queues from PF to VSI * @qs_cfg: gathered variables needed for pf->vsi queues assignment @@ -804,6 +860,9 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) } rx_rings_rem -= rx_rings_per_v; } + + if (ice_is_xdp_ena_vsi(vsi)) + ice_map_xdp_rings(vsi); } /** @@ -826,7 +885,7 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi) * @ring: Tx ring to be configured * @qg_buf: queue group buffer */ -int +static int ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_aqc_add_tx_qgrp *qg_buf) { @@ -897,6 +956,80 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, return 0; } +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, + u16 q_idx) +{ + DEFINE_RAW_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); + + if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx]) + return -EINVAL; + + qg_buf->num_txqs = 1; + + return ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); +} + +/** + * ice_vsi_cfg_txqs - Configure the VSI for Tx + * @vsi: the VSI being configured + * @rings: Tx ring array to be configured + * @count: number of Tx ring array elements + * + * Return 0 on success and a negative value on error + * Configure the Tx VSI for operation. + */ +static int +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) +{ + DEFINE_RAW_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); + int err = 0; + u16 q_idx; + + qg_buf->num_txqs = 1; + + for (q_idx = 0; q_idx < count; q_idx++) { + err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); + if (err) + break; + } + + return err; +} + +/** + * ice_vsi_cfg_lan_txqs - Configure the VSI for Tx + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Tx VSI for operation. + */ +int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) +{ + return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); +} + +/** + * ice_vsi_cfg_xdp_txqs - Configure Tx queues dedicated for XDP in given VSI + * @vsi: the VSI being configured + * + * Return 0 on success and a negative value on error + * Configure the Tx queues dedicated for XDP in given VSI for operation. + */ +int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) +{ + int ret; + int i; + + ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); + if (ret) + return ret; + + ice_for_each_rxq(vsi, i) + ice_tx_xsk_pool(vsi, i); + + return 0; +} + /** * ice_cfg_itr - configure the initial interrupt throttle values * @hw: pointer to the HW structure diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h index 17321ba75602d..b711bc921928d 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.h +++ b/drivers/net/ethernet/intel/ice/ice_base.h @@ -6,7 +6,8 @@ #include "ice.h" -int ice_vsi_cfg_rxq(struct ice_rx_ring *ring); +int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx); +int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg); int ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait); @@ -14,9 +15,10 @@ int ice_vsi_wait_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx); int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi); void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi); void ice_vsi_free_q_vectors(struct ice_vsi *vsi); -int -ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, - struct ice_aqc_add_tx_qgrp *qg_buf); +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, + u16 q_idx); +int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi); +int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi); void ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector); void ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 10c32cd80fff6..3017e7c4423b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -3103,6 +3103,16 @@ ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high) case ICE_PHY_TYPE_HIGH_100G_AUI2: speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB; break; + case ICE_PHY_TYPE_HIGH_200G_CR4_PAM4: + case ICE_PHY_TYPE_HIGH_200G_SR4: + case ICE_PHY_TYPE_HIGH_200G_FR4: + case ICE_PHY_TYPE_HIGH_200G_LR4: + case ICE_PHY_TYPE_HIGH_200G_DR4: + case ICE_PHY_TYPE_HIGH_200G_KR4_PAM4: + case ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC: + case ICE_PHY_TYPE_HIGH_200G_AUI4: + speed_phy_type_high = ICE_AQ_LINK_SPEED_200GB; + break; default: speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN; break; @@ -4700,7 +4710,7 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd) { - DEFINE_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); + DEFINE_RAW_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); u16 i, buf_size = __struct_size(qg_list); struct ice_q_ctx *q_ctx; int status = -ENOENT; @@ -4922,7 +4932,7 @@ int ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, u16 *q_id) { - DEFINE_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); + DEFINE_RAW_FLEX(struct ice_aqc_dis_txq_item, qg_list, q_id, 1); u16 qg_size = __struct_size(qg_list); struct ice_hw *hw; int status = 0; diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index 8b7504a9df316..109d6daa8dd2e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -1329,6 +1329,7 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, for (i = 0; i < count; i++) { bool last = false; + int try_cnt = 0; int status; bh = (struct ice_buf_hdr *)(bufs + start + i); @@ -1336,8 +1337,26 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, if (indicate_last) last = ice_is_last_download_buffer(bh, i, count); - status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, - &offset, &info, NULL); + while (1) { + status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, + last, &offset, &info, + NULL); + if (hw->adminq.sq_last_status != ICE_AQ_RC_ENOSEC && + hw->adminq.sq_last_status != ICE_AQ_RC_EBADSIG) + break; + + try_cnt++; + + if (try_cnt == 5) + break; + + msleep(20); + } + + if (try_cnt) + dev_dbg(ice_hw_to_dev(hw), + "ice_aq_download_pkg number of retries: %d\n", + try_cnt); /* Save AQ status from download package */ if (status) { @@ -1424,14 +1443,14 @@ ice_dwnld_sign_and_cfg_segs(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, goto exit; } - conf_idx = le32_to_cpu(seg->signed_seg_idx); - start = le32_to_cpu(seg->signed_buf_start); count = le32_to_cpu(seg->signed_buf_count); - state = ice_download_pkg_sig_seg(hw, seg); - if (state) + if (state || !count) goto exit; + conf_idx = le32_to_cpu(seg->signed_seg_idx); + start = le32_to_cpu(seg->signed_buf_start); + state = ice_download_pkg_config_seg(hw, pkg_hdr, conf_idx, start, count); @@ -1934,8 +1953,8 @@ static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw, */ static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) { - DEFINE_FLEX(struct ice_aqc_get_pkg_info_resp, pkg_info, pkg_info, - ICE_PKG_CNT); + DEFINE_RAW_FLEX(struct ice_aqc_get_pkg_info_resp, pkg_info, pkg_info, + ICE_PKG_CNT); u16 size = __struct_size(pkg_info); u32 i; @@ -1986,8 +2005,8 @@ static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, struct ice_seg **seg) { - DEFINE_FLEX(struct ice_aqc_get_pkg_info_resp, pkg, pkg_info, - ICE_PKG_CNT); + DEFINE_RAW_FLEX(struct ice_aqc_get_pkg_info_resp, pkg, pkg_info, + ICE_PKG_CNT); u16 size = __struct_size(pkg); enum ice_ddp_state state; u32 i; diff --git a/drivers/net/ethernet/intel/ice/ice_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c index c2bfba6b9ead6..66aa9759c8e7e 100644 --- a/drivers/net/ethernet/intel/ice/ice_debugfs.c +++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c @@ -174,7 +174,7 @@ ice_debugfs_module_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 8) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -260,7 +260,7 @@ ice_debugfs_nr_messages_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 4) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -335,7 +335,7 @@ ice_debugfs_enable_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 2) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -431,7 +431,7 @@ ice_debugfs_log_size_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 5) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index a19b06f18e400..eb604ed3b6cbb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3514,7 +3514,6 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) struct ice_pf *pf = vsi->back; int new_rx = 0, new_tx = 0; bool locked = false; - u32 curr_combined; int ret = 0; /* do not support changing channels in Safe Mode */ @@ -3536,22 +3535,8 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) return -EOPNOTSUPP; } - curr_combined = ice_get_combined_cnt(vsi); - - /* these checks are for cases where user didn't specify a particular - * value on cmd line but we get non-zero value anyway via - * get_channels(); look at ethtool.c in ethtool repository (the user - * space part), particularly, do_schannels() routine - */ - if (ch->rx_count == vsi->num_rxq - curr_combined) - ch->rx_count = 0; - if (ch->tx_count == vsi->num_txq - curr_combined) - ch->tx_count = 0; - if (ch->combined_count == curr_combined) - ch->combined_count = 0; - - if (!(ch->combined_count || (ch->rx_count && ch->tx_count))) { - netdev_err(dev, "Please specify at least 1 Rx and 1 Tx channel\n"); + if (ch->rx_count && ch->tx_count) { + netdev_err(dev, "Dedicated RX or TX channels cannot be used simultaneously\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 467372d541d21..f0e76f0a6d603 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -491,7 +491,7 @@ static void ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport, u16 vsi_num, u8 tc) { - DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_move_elem, buf, teid, 1); struct device *dev = ice_pf_to_dev(lag->pf); u16 numq, valq, num_moved, qbuf_size; u16 buf_size = __struct_size(buf); @@ -849,7 +849,7 @@ static void ice_lag_reclaim_vf_tc(struct ice_lag *lag, struct ice_hw *src_hw, u16 vsi_num, u8 tc) { - DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_move_elem, buf, teid, 1); struct device *dev = ice_pf_to_dev(lag->pf); u16 numq, valq, num_moved, qbuf_size; u16 buf_size = __struct_size(buf); @@ -1873,7 +1873,7 @@ static void ice_lag_move_vf_nodes_tc_sync(struct ice_lag *lag, struct ice_hw *dest_hw, u16 vsi_num, u8 tc) { - DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_move_elem, buf, teid, 1); struct device *dev = ice_pf_to_dev(lag->pf); u16 numq, valq, num_moved, qbuf_size; u16 buf_size = __struct_size(buf); @@ -2041,7 +2041,7 @@ int ice_init_lag(struct ice_pf *pf) /* associate recipes to profiles */ for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) { err = ice_aq_get_recipe_to_profile(&pf->hw, n, - (u8 *)&recipe_bits, NULL); + &recipe_bits, NULL); if (err) continue; @@ -2049,7 +2049,7 @@ int ice_init_lag(struct ice_pf *pf) recipe_bits |= BIT(lag->pf_recipe) | BIT(lag->lport_recipe); ice_aq_map_recipe_to_profile(&pf->hw, n, - (u8 *)&recipe_bits, NULL); + recipe_bits, NULL); } } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index fc23dbe302b46..962c8edce8a9d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -117,14 +117,8 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->q_vectors) goto err_vectors; - vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL); - if (!vsi->af_xdp_zc_qps) - goto err_zc_qps; - return 0; -err_zc_qps: - devm_kfree(dev, vsi->q_vectors); err_vectors: devm_kfree(dev, vsi->rxq_map); err_rxq_map: @@ -328,8 +322,6 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); - bitmap_free(vsi->af_xdp_zc_qps); - vsi->af_xdp_zc_qps = NULL; /* free the ring and vector containers */ devm_kfree(dev, vsi->q_vectors); vsi->q_vectors = NULL; @@ -1671,27 +1663,6 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) } } -/** - * ice_vsi_cfg_frame_size - setup max frame size and Rx buffer length - * @vsi: VSI - */ -static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) -{ - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; - vsi->rx_buf_len = ICE_RXBUF_1664; -#if (PAGE_SIZE < 8192) - } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && - (vsi->netdev->mtu <= ETH_DATA_LEN)) { - vsi->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; - vsi->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; -#endif - } else { - vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - vsi->rx_buf_len = ICE_RXBUF_3072; - } -} - /** * ice_pf_state_is_nominal - checks the PF for nominal state * @pf: pointer to PF to check @@ -1795,114 +1766,6 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, wr32(hw, QRXFLXP_CNTXT(pf_q), regval); } -int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) -{ - if (q_idx >= vsi->num_rxq) - return -EINVAL; - - return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]); -} - -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx) -{ - DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); - - if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx]) - return -EINVAL; - - qg_buf->num_txqs = 1; - - return ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); -} - -/** - * ice_vsi_cfg_rxqs - Configure the VSI for Rx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Rx VSI for operation. - */ -int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) -{ - u16 i; - - if (vsi->type == ICE_VSI_VF) - goto setup_rings; - - ice_vsi_cfg_frame_size(vsi); -setup_rings: - /* set up individual rings */ - ice_for_each_rxq(vsi, i) { - int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]); - - if (err) - return err; - } - - return 0; -} - -/** - * ice_vsi_cfg_txqs - Configure the VSI for Tx - * @vsi: the VSI being configured - * @rings: Tx ring array to be configured - * @count: number of Tx ring array elements - * - * Return 0 on success and a negative value on error - * Configure the Tx VSI for operation. - */ -static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) -{ - DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); - int err = 0; - u16 q_idx; - - qg_buf->num_txqs = 1; - - for (q_idx = 0; q_idx < count; q_idx++) { - err = ice_vsi_cfg_txq(vsi, rings[q_idx], qg_buf); - if (err) - break; - } - - return err; -} - -/** - * ice_vsi_cfg_lan_txqs - Configure the VSI for Tx - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Tx VSI for operation. - */ -int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi) -{ - return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, vsi->num_txq); -} - -/** - * ice_vsi_cfg_xdp_txqs - Configure Tx queues dedicated for XDP in given VSI - * @vsi: the VSI being configured - * - * Return 0 on success and a negative value on error - * Configure the Tx queues dedicated for XDP in given VSI for operation. - */ -int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) -{ - int ret; - int i; - - ret = ice_vsi_cfg_txqs(vsi, vsi->xdp_rings, vsi->num_xdp_txq); - if (ret) - return ret; - - ice_for_each_rxq(vsi, i) - ice_tx_xsk_pool(vsi, i); - - return 0; -} - /** * ice_intrl_usec_to_reg - convert interrupt rate limit to register value * @intrl: interrupt rate limit in usecs @@ -2423,22 +2286,23 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) if (ret) goto unroll_vector_base; - ice_vsi_map_rings_to_vectors(vsi); - - /* Associate q_vector rings to napi */ - ice_vsi_set_napi_queues(vsi); - - vsi->stat_offsets_loaded = false; - if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) goto unroll_vector_base; - ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); + ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog, + ICE_XDP_CFG_PART); if (ret) goto unroll_vector_base; } + ice_vsi_map_rings_to_vectors(vsi); + + /* Associate q_vector rings to napi */ + ice_vsi_set_napi_queues(vsi); + + vsi->stat_offsets_loaded = false; + /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ if (vsi->type != ICE_VSI_CTRL) /* Do not exit if configuring RSS had an issue, at @@ -2585,7 +2449,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi) /* return value check can be skipped here, it always returns * 0 if reset is in progress */ - ice_destroy_xdp_rings(vsi); + ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_PART); ice_vsi_clear_rings(vsi); ice_vsi_free_q_vectors(vsi); @@ -3238,7 +3102,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) { struct ice_vsi_cfg_params params = {}; struct ice_coalesce_stored *coalesce; - int prev_num_q_vectors = 0; + int prev_num_q_vectors; struct ice_pf *pf; int ret; @@ -3252,13 +3116,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; - coalesce = kcalloc(vsi->num_q_vectors, - sizeof(struct ice_coalesce_stored), GFP_KERNEL); - if (!coalesce) - return -ENOMEM; - - prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); - ret = ice_vsi_realloc_stat_arrays(vsi); if (ret) goto err_vsi_cfg; @@ -3268,6 +3125,13 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) if (ret) goto err_vsi_cfg; + coalesce = kcalloc(vsi->num_q_vectors, + sizeof(struct ice_coalesce_stored), GFP_KERNEL); + if (!coalesce) + return -ENOMEM; + + prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); + ret = ice_vsi_cfg_tc_lan(pf, vsi); if (ret) { if (vsi_flags & ICE_VSI_FLAG_INIT) { @@ -3286,8 +3150,8 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) err_vsi_cfg_tc_lan: ice_vsi_decfg(vsi); -err_vsi_cfg: kfree(coalesce); +err_vsi_cfg: return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index bfcfc582a4c04..b5a1ed7cc4b17 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -54,14 +54,6 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf); void ice_update_eth_stats(struct ice_vsi *vsi); -int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx); - -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx); - -int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); - -int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi); - void ice_vsi_cfg_msix(struct ice_vsi *vsi); int ice_vsi_start_all_rx_rings(struct ice_vsi *vsi); @@ -72,8 +64,6 @@ int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num); -int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi); - int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index df6a68ab747ee..4f5580e2d61e7 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -803,6 +803,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } switch (vsi->port_info->phy.link_info.link_speed) { + case ICE_AQ_LINK_SPEED_200GB: + speed = "200 G"; + break; case ICE_AQ_LINK_SPEED_100GB: speed = "100 G"; break; @@ -2668,17 +2671,72 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog) bpf_prog_put(old_prog); } +static struct ice_tx_ring *ice_xdp_ring_from_qid(struct ice_vsi *vsi, int qid) +{ + struct ice_q_vector *q_vector; + struct ice_tx_ring *ring; + + if (static_key_enabled(&ice_xdp_locking_key)) + return vsi->xdp_rings[qid % vsi->num_xdp_txq]; + + q_vector = vsi->rx_rings[qid]->q_vector; + ice_for_each_tx_ring(ring, q_vector->tx) + if (ice_ring_is_xdp(ring)) + return ring; + + return NULL; +} + +/** + * ice_map_xdp_rings - Map XDP rings to interrupt vectors + * @vsi: the VSI with XDP rings being configured + * + * Map XDP rings to interrupt vectors and perform the configuration steps + * dependent on the mapping. + */ +void ice_map_xdp_rings(struct ice_vsi *vsi) +{ + int xdp_rings_rem = vsi->num_xdp_txq; + int v_idx, q_idx; + + /* follow the logic from ice_vsi_map_rings_to_vectors */ + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; + int xdp_rings_per_v, q_id, q_base; + + xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem, + vsi->num_q_vectors - v_idx); + q_base = vsi->num_xdp_txq - xdp_rings_rem; + + for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) { + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id]; + + xdp_ring->q_vector = q_vector; + xdp_ring->next = q_vector->tx.tx_ring; + q_vector->tx.tx_ring = xdp_ring; + } + xdp_rings_rem -= xdp_rings_per_v; + } + + ice_for_each_rxq(vsi, q_idx) { + vsi->rx_rings[q_idx]->xdp_ring = ice_xdp_ring_from_qid(vsi, + q_idx); + ice_tx_xsk_pool(vsi, q_idx); + } +} + /** * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP * @vsi: VSI to bring up Tx rings used by XDP * @prog: bpf program that will be assigned to VSI + * @cfg_type: create from scratch or restore the existing configuration * * Return 0 on success and negative value on error */ -int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) +int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, + enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; - int xdp_rings_rem = vsi->num_xdp_txq; struct ice_pf *pf = vsi->back; struct ice_qs_cfg xdp_qs_cfg = { .qs_mutex = &pf->avail_q_mutex, @@ -2691,8 +2749,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) .mapping_mode = ICE_VSI_MAP_CONTIG }; struct device *dev; - int i, v_idx; - int status; + int status, i; dev = ice_pf_to_dev(pf); vsi->xdp_rings = devm_kcalloc(dev, vsi->num_xdp_txq, @@ -2711,49 +2768,15 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) if (ice_xdp_alloc_setup_rings(vsi)) goto clear_xdp_rings; - /* follow the logic from ice_vsi_map_rings_to_vectors */ - ice_for_each_q_vector(vsi, v_idx) { - struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - int xdp_rings_per_v, q_id, q_base; - - xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem, - vsi->num_q_vectors - v_idx); - q_base = vsi->num_xdp_txq - xdp_rings_rem; - - for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) { - struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id]; - - xdp_ring->q_vector = q_vector; - xdp_ring->next = q_vector->tx.tx_ring; - q_vector->tx.tx_ring = xdp_ring; - } - xdp_rings_rem -= xdp_rings_per_v; - } - - ice_for_each_rxq(vsi, i) { - if (static_key_enabled(&ice_xdp_locking_key)) { - vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; - } else { - struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector; - struct ice_tx_ring *ring; - - ice_for_each_tx_ring(ring, q_vector->tx) { - if (ice_ring_is_xdp(ring)) { - vsi->rx_rings[i]->xdp_ring = ring; - break; - } - } - } - ice_tx_xsk_pool(vsi, i); - } - /* omit the scheduler update if in reset path; XDP queues will be * taken into account at the end of ice_vsi_rebuild, where * ice_cfg_vsi_lan is being called */ - if (ice_is_reset_in_progress(pf->state)) + if (cfg_type == ICE_XDP_CFG_PART) return 0; + ice_map_xdp_rings(vsi); + /* tell the Tx scheduler that right now we have * additional queues */ @@ -2803,22 +2826,21 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) /** * ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings * @vsi: VSI to remove XDP rings + * @cfg_type: disable XDP permanently or allow it to be restored later * * Detach XDP rings from irq vectors, clean up the PF bitmap and free * resources */ -int ice_destroy_xdp_rings(struct ice_vsi *vsi) +int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; int i, v_idx; /* q_vectors are freed in reset path so there's no point in detaching - * rings; in case of rebuild being triggered not from reset bits - * in pf->state won't be set, so additionally check first q_vector - * against NULL + * rings */ - if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) + if (cfg_type == ICE_XDP_CFG_PART) goto free_qmap; ice_for_each_q_vector(vsi, v_idx) { @@ -2859,7 +2881,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi) if (static_key_enabled(&ice_xdp_locking_key)) static_branch_dec(&ice_xdp_locking_key); - if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) + if (cfg_type == ICE_XDP_CFG_PART) return 0; ice_vsi_assign_bpf_prog(vsi, NULL); @@ -2970,7 +2992,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) { NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP"); } else { - xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); + xdp_ring_err = ice_prepare_xdp_rings(vsi, prog, + ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); } @@ -2981,7 +3004,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_features_clear_redirect_target(vsi->netdev); - xdp_ring_err = ice_destroy_xdp_rings(vsi); + xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); /* reallocate Rx queues that were used for zero-copy */ @@ -5495,7 +5518,7 @@ static int __maybe_unused ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); - ice_unplug_aux_dev(pf); + ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { @@ -5575,6 +5598,11 @@ static int __maybe_unused ice_resume(struct device *dev) if (ret) dev_err(dev, "Cannot restore interrupt scheme: %d\n", ret); + ret = ice_init_rdma(pf); + if (ret) + dev_err(dev, "Reinitialize RDMA during resume failed: %d\n", + ret); + clear_bit(ICE_DOWN, pf->state); /* Now perform PF reset and rebuild */ reset_type = ICE_RESET_PFR; @@ -6737,6 +6765,7 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) { struct rtnl_link_stats64 *net_stats, *stats_prev; struct rtnl_link_stats64 *vsi_stats; + struct ice_pf *pf = vsi->back; u64 pkts, bytes; int i; @@ -6782,21 +6811,18 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) net_stats = &vsi->net_stats; stats_prev = &vsi->net_stats_prev; - /* clear prev counters after reset */ - if (vsi_stats->tx_packets < stats_prev->tx_packets || - vsi_stats->rx_packets < stats_prev->rx_packets) { - stats_prev->tx_packets = 0; - stats_prev->tx_bytes = 0; - stats_prev->rx_packets = 0; - stats_prev->rx_bytes = 0; + /* Update netdev counters, but keep in mind that values could start at + * random value after PF reset. And as we increase the reported stat by + * diff of Prev-Cur, we need to be sure that Prev is valid. If it's not, + * let's skip this round. + */ + if (likely(pf->stat_prev_loaded)) { + net_stats->tx_packets += vsi_stats->tx_packets - stats_prev->tx_packets; + net_stats->tx_bytes += vsi_stats->tx_bytes - stats_prev->tx_bytes; + net_stats->rx_packets += vsi_stats->rx_packets - stats_prev->rx_packets; + net_stats->rx_bytes += vsi_stats->rx_bytes - stats_prev->rx_bytes; } - /* update netdev counters */ - net_stats->tx_packets += vsi_stats->tx_packets - stats_prev->tx_packets; - net_stats->tx_bytes += vsi_stats->tx_bytes - stats_prev->tx_bytes; - net_stats->rx_packets += vsi_stats->rx_packets - stats_prev->rx_packets; - net_stats->rx_bytes += vsi_stats->rx_bytes - stats_prev->rx_bytes; - stats_prev->tx_packets = vsi_stats->tx_packets; stats_prev->tx_bytes = vsi_stats->tx_bytes; stats_prev->rx_packets = vsi_stats->rx_packets; diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index d4e05d2cb30c4..8510a02afedcc 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -375,11 +375,25 @@ ice_read_nvm_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u1 * * Read the specified word from the copy of the Shadow RAM found in the * specified NVM module. + * + * Note that the Shadow RAM copy is always located after the CSS header, and + * is aligned to 64-byte (32-word) offsets. */ static int ice_read_nvm_sr_copy(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u16 *data) { - return ice_read_nvm_module(hw, bank, ICE_NVM_SR_COPY_WORD_OFFSET + offset, data); + u32 sr_copy; + + switch (bank) { + case ICE_ACTIVE_FLASH_BANK: + sr_copy = roundup(hw->flash.banks.active_css_hdr_len, 32); + break; + case ICE_INACTIVE_FLASH_BANK: + sr_copy = roundup(hw->flash.banks.inactive_css_hdr_len, 32); + break; + } + + return ice_read_nvm_module(hw, bank, sr_copy + offset, data); } /** @@ -441,8 +455,7 @@ int ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, u16 module_type) { - u16 pfa_len, pfa_ptr; - u16 next_tlv; + u16 pfa_len, pfa_ptr, next_tlv, max_tlv; int status; status = ice_read_sr_word(hw, ICE_SR_PFA_PTR, &pfa_ptr); @@ -455,11 +468,23 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, ice_debug(hw, ICE_DBG_INIT, "Failed to read PFA length.\n"); return status; } + + /* The Preserved Fields Area contains a sequence of Type-Length-Value + * structures which define its contents. The PFA length includes all + * of the TLVs, plus the initial length word itself, *and* one final + * word at the end after all of the TLVs. + */ + if (check_add_overflow(pfa_ptr, pfa_len - 1, &max_tlv)) { + dev_warn(ice_hw_to_dev(hw), "PFA starts at offset %u. PFA length of %u caused 16-bit arithmetic overflow.\n", + pfa_ptr, pfa_len); + return -EINVAL; + } + /* Starting with first TLV after PFA length, iterate through the list * of TLVs to find the requested one. */ next_tlv = pfa_ptr + 1; - while (next_tlv < pfa_ptr + pfa_len) { + while (next_tlv < max_tlv) { u16 tlv_sub_module_type; u16 tlv_len; @@ -483,10 +508,13 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, } return -EINVAL; } - /* Check next TLV, i.e. current TLV pointer + length + 2 words - * (for current TLV's type and length) - */ - next_tlv = next_tlv + tlv_len + 2; + + if (check_add_overflow(next_tlv, 2, &next_tlv) || + check_add_overflow(next_tlv, tlv_len, &next_tlv)) { + dev_warn(ice_hw_to_dev(hw), "TLV of type %u and length 0x%04x caused 16-bit arithmetic overflow. The PFA starts at 0x%04x and has length of 0x%04x\n", + tlv_sub_module_type, tlv_len, pfa_ptr, pfa_len); + return -EINVAL; + } } /* Module does not exist */ return -ENOENT; @@ -1010,6 +1038,72 @@ static int ice_determine_active_flash_banks(struct ice_hw *hw) return 0; } +/** + * ice_get_nvm_css_hdr_len - Read the CSS header length from the NVM CSS header + * @hw: pointer to the HW struct + * @bank: whether to read from the active or inactive flash bank + * @hdr_len: storage for header length in words + * + * Read the CSS header length from the NVM CSS header and add the Authentication + * header size, and then convert to words. + * + * Return: zero on success, or a negative error code on failure. + */ +static int +ice_get_nvm_css_hdr_len(struct ice_hw *hw, enum ice_bank_select bank, + u32 *hdr_len) +{ + u16 hdr_len_l, hdr_len_h; + u32 hdr_len_dword; + int status; + + status = ice_read_nvm_module(hw, bank, ICE_NVM_CSS_HDR_LEN_L, + &hdr_len_l); + if (status) + return status; + + status = ice_read_nvm_module(hw, bank, ICE_NVM_CSS_HDR_LEN_H, + &hdr_len_h); + if (status) + return status; + + /* CSS header length is in DWORD, so convert to words and add + * authentication header size + */ + hdr_len_dword = hdr_len_h << 16 | hdr_len_l; + *hdr_len = (hdr_len_dword * 2) + ICE_NVM_AUTH_HEADER_LEN; + + return 0; +} + +/** + * ice_determine_css_hdr_len - Discover CSS header length for the device + * @hw: pointer to the HW struct + * + * Determine the size of the CSS header at the start of the NVM module. This + * is useful for locating the Shadow RAM copy in the NVM, as the Shadow RAM is + * always located just after the CSS header. + * + * Return: zero on success, or a negative error code on failure. + */ +static int ice_determine_css_hdr_len(struct ice_hw *hw) +{ + struct ice_bank_info *banks = &hw->flash.banks; + int status; + + status = ice_get_nvm_css_hdr_len(hw, ICE_ACTIVE_FLASH_BANK, + &banks->active_css_hdr_len); + if (status) + return status; + + status = ice_get_nvm_css_hdr_len(hw, ICE_INACTIVE_FLASH_BANK, + &banks->inactive_css_hdr_len); + if (status) + return status; + + return 0; +} + /** * ice_init_nvm - initializes NVM setting * @hw: pointer to the HW struct @@ -1056,6 +1150,12 @@ int ice_init_nvm(struct ice_hw *hw) return status; } + status = ice_determine_css_hdr_len(hw); + if (status) { + ice_debug(hw, ICE_DBG_NVM, "Failed to determine Shadow RAM copy offsets.\n"); + return status; + } + status = ice_get_nvm_ver_info(hw, ICE_ACTIVE_FLASH_BANK, &flash->nvm); if (status) { ice_debug(hw, ICE_DBG_INIT, "Failed to read NVM info.\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index d174a4eeb899c..a1525992d14bc 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -237,7 +237,7 @@ static int ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, u32 node_teid) { - DEFINE_FLEX(struct ice_aqc_delete_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_delete_elem, buf, teid, 1); u16 buf_size = __struct_size(buf); u16 num_groups_removed = 0; int status; @@ -2219,7 +2219,7 @@ int ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, u16 num_items, u32 *list) { - DEFINE_FLEX(struct ice_aqc_move_elem, buf, teid, 1); + DEFINE_RAW_FLEX(struct ice_aqc_move_elem, buf, teid, 1); u16 buf_len = __struct_size(buf); struct ice_sched_node *node; u16 i, grps_movd = 0; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index f84bab80ca423..1472385eb68eb 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1812,7 +1812,7 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type, enum ice_adminq_opc opc) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); u16 buf_len = __struct_size(sw_buf); struct ice_aqc_res_elem *vsi_ele; int status; @@ -1825,7 +1825,8 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || lkup_type == ICE_SW_LKUP_PROMISC_VLAN || - lkup_type == ICE_SW_LKUP_DFLT) { + lkup_type == ICE_SW_LKUP_DFLT || + lkup_type == ICE_SW_LKUP_LAST) { sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP); } else if (lkup_type == ICE_SW_LKUP_VLAN) { if (opc == ice_aqc_opc_alloc_res) @@ -2025,12 +2026,12 @@ ice_update_recipe_lkup_idx(struct ice_hw *hw, * ice_aq_map_recipe_to_profile - Map recipe to packet profile * @hw: pointer to the HW struct * @profile_id: package profile ID to associate the recipe with - * @r_bitmap: Recipe bitmap filled in and need to be returned as response + * @r_assoc: Recipe bitmap filled in and need to be returned as response * @cd: pointer to command details structure or NULL * Recipe to profile association (0x0291) */ int -ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc, struct ice_sq_cd *cd) { struct ice_aqc_recipe_to_profile *cmd; @@ -2042,7 +2043,7 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, /* Set the recipe ID bit in the bitmask to let the device know which * profile we are associating the recipe to */ - memcpy(cmd->recipe_assoc, r_bitmap, sizeof(cmd->recipe_assoc)); + cmd->recipe_assoc = cpu_to_le64(r_assoc); return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); } @@ -2051,12 +2052,12 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * ice_aq_get_recipe_to_profile - Map recipe to packet profile * @hw: pointer to the HW struct * @profile_id: package profile ID to associate the recipe with - * @r_bitmap: Recipe bitmap filled in and need to be returned as response + * @r_assoc: Recipe bitmap filled in and need to be returned as response * @cd: pointer to command details structure or NULL * Associate profile ID with given recipe (0x0293) */ int -ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc, struct ice_sq_cd *cd) { struct ice_aqc_recipe_to_profile *cmd; @@ -2069,7 +2070,7 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); if (!status) - memcpy(r_bitmap, cmd->recipe_assoc, sizeof(cmd->recipe_assoc)); + *r_assoc = le64_to_cpu(cmd->recipe_assoc); return status; } @@ -2081,7 +2082,7 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, */ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, sw_buf, elem, 1); u16 buf_len = __struct_size(sw_buf); int status; @@ -2108,6 +2109,7 @@ int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) static void ice_get_recp_to_prof_map(struct ice_hw *hw) { DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + u64 recp_assoc; u16 i; for (i = 0; i < hw->switch_info->max_used_prof_index + 1; i++) { @@ -2115,8 +2117,9 @@ static void ice_get_recp_to_prof_map(struct ice_hw *hw) bitmap_zero(profile_to_recipe[i], ICE_MAX_NUM_RECIPES); bitmap_zero(r_bitmap, ICE_MAX_NUM_RECIPES); - if (ice_aq_get_recipe_to_profile(hw, i, (u8 *)r_bitmap, NULL)) + if (ice_aq_get_recipe_to_profile(hw, i, &recp_assoc, NULL)) continue; + bitmap_from_arr64(r_bitmap, &recp_assoc, ICE_MAX_NUM_RECIPES); bitmap_copy(profile_to_recipe[i], r_bitmap, ICE_MAX_NUM_RECIPES); for_each_set_bit(j, r_bitmap, ICE_MAX_NUM_RECIPES) @@ -2757,7 +2760,8 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || lkup_type == ICE_SW_LKUP_PROMISC_VLAN || - lkup_type == ICE_SW_LKUP_DFLT) + lkup_type == ICE_SW_LKUP_DFLT || + lkup_type == ICE_SW_LKUP_LAST) rule_type = remove ? ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR : ICE_AQC_SW_RULES_T_VSI_LIST_SET; else if (lkup_type == ICE_SW_LKUP_VLAN) @@ -4418,7 +4422,7 @@ int ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 *counter_id) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); u16 buf_len = __struct_size(buf); int status; @@ -4446,7 +4450,7 @@ int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); u16 buf_len = __struct_size(buf); int status; @@ -4476,7 +4480,7 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, */ int ice_share_res(struct ice_hw *hw, u16 type, u8 shared, u16 res_id) { - DEFINE_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); + DEFINE_RAW_FLEX(struct ice_aqc_alloc_free_res_elem, buf, elem, 1); u16 buf_len = __struct_size(buf); u16 res_type; int status; @@ -5390,22 +5394,24 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, */ list_for_each_entry(fvit, &rm->fv_list, list_entry) { DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + u64 recp_assoc; u16 j; status = ice_aq_get_recipe_to_profile(hw, fvit->profile_id, - (u8 *)r_bitmap, NULL); + &recp_assoc, NULL); if (status) goto err_unroll; + bitmap_from_arr64(r_bitmap, &recp_assoc, ICE_MAX_NUM_RECIPES); bitmap_or(r_bitmap, r_bitmap, rm->r_bitmap, ICE_MAX_NUM_RECIPES); status = ice_acquire_change_lock(hw, ICE_RES_WRITE); if (status) goto err_unroll; + bitmap_to_arr64(&recp_assoc, r_bitmap, ICE_MAX_NUM_RECIPES); status = ice_aq_map_recipe_to_profile(hw, fvit->profile_id, - (u8 *)r_bitmap, - NULL); + recp_assoc, NULL); ice_release_change_lock(hw); if (status) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index db7e501b7e0a4..89ffa1b51b5ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -424,10 +424,10 @@ int ice_aq_add_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 num_recipes, struct ice_sq_cd *cd); int -ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc, struct ice_sq_cd *cd); int -ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc, struct ice_sq_cd *cd); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index b890410a2bc0b..688ccb0615ab9 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -28,6 +28,8 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified) * - Tunnel flag (present if tunnel) */ + if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) + lkups_cnt++; if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; @@ -363,6 +365,11 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, /* Always add direction metadata */ ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); + if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { + ice_rule_add_src_vsi_metadata(&list[i]); + i++; + } + rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type); if (tc_fltr->tunnel_type != TNL_LAST) { i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); @@ -772,7 +779,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) int ret; int i; - if (!flags || (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT)) { + if (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)"); return -EOPNOTSUPP; } @@ -820,6 +827,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) /* specify the cookie as filter_rule_id */ rule_info.fltr_rule_id = fltr->cookie; + rule_info.src_vsi = vsi->idx; ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); if (ret == -EEXIST) { @@ -1481,7 +1489,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index a508e917ce5ff..b549a2ff6628e 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -480,6 +480,8 @@ struct ice_bank_info { u32 orom_size; /* Size of OROM bank */ u32 netlist_ptr; /* Pointer to 1st Netlist bank */ u32 netlist_size; /* Size of Netlist bank */ + u32 active_css_hdr_len; /* Active CSS header length */ + u32 inactive_css_hdr_len; /* Inactive CSS header length */ enum ice_flash_bank nvm_bank; /* Active NVM bank */ enum ice_flash_bank orom_bank; /* Active OROM bank */ enum ice_flash_bank netlist_bank; /* Active Netlist bank */ @@ -1083,17 +1085,13 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_SR_SECTOR_SIZE_IN_WORDS 0x800 /* CSS Header words */ +#define ICE_NVM_CSS_HDR_LEN_L 0x02 +#define ICE_NVM_CSS_HDR_LEN_H 0x03 #define ICE_NVM_CSS_SREV_L 0x14 #define ICE_NVM_CSS_SREV_H 0x15 -/* Length of CSS header section in words */ -#define ICE_CSS_HEADER_LENGTH 330 - -/* Offset of Shadow RAM copy in the NVM bank area. */ -#define ICE_NVM_SR_COPY_WORD_OFFSET roundup(ICE_CSS_HEADER_LENGTH, 32) - -/* Size in bytes of Option ROM trailer */ -#define ICE_NVM_OROM_TRAILER_LENGTH (2 * ICE_CSS_HEADER_LENGTH) +/* Length of Authentication header section in words */ +#define ICE_NVM_AUTH_HEADER_LEN 0x08 /* The Link Topology Netlist section is stored as a series of words. It is * stored in the NVM as a TLV, with the first two words containing the type diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 2ffdae9a82dfb..15ade19de55a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -863,6 +863,11 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return 0; } + if (flags & ICE_VF_RESET_LOCK) + mutex_lock(&vf->cfg_lock); + else + lockdep_assert_held(&vf->cfg_lock); + lag = pf->lag; mutex_lock(&pf->lag_mutex); if (lag && lag->bonded && lag->primary) { @@ -874,11 +879,6 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) act_prt = ICE_LAG_INVALID_PORT; } - if (flags & ICE_VF_RESET_LOCK) - mutex_lock(&vf->cfg_lock); - else - lockdep_assert_held(&vf->cfg_lock); - if (ice_is_vf_disabled(vf)) { vsi = ice_get_vf_vsi(vf); if (!vsi) { @@ -963,14 +963,14 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) ice_mbx_clear_malvf(&vf->mbx_info); out_unlock: - if (flags & ICE_VF_RESET_LOCK) - mutex_unlock(&vf->cfg_lock); - if (lag && lag->bonded && lag->primary && act_prt != ICE_LAG_INVALID_PORT) ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); mutex_unlock(&pf->lag_mutex); + if (flags & ICE_VF_RESET_LOCK) + mutex_unlock(&vf->cfg_lock); + return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index 80dc4bcdd3a41..b3e1bdcb80f84 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -26,24 +26,22 @@ static void ice_port_vlan_on(struct ice_vsi *vsi) struct ice_vsi_vlan_ops *vlan_ops; struct ice_pf *pf = vsi->back; - if (ice_is_dvm_ena(&pf->hw)) { - vlan_ops = &vsi->outer_vlan_ops; - - /* setup outer VLAN ops */ - vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + /* setup inner VLAN ops */ + vlan_ops = &vsi->inner_vlan_ops; - /* setup inner VLAN ops */ - vlan_ops = &vsi->inner_vlan_ops; + if (ice_is_dvm_ena(&pf->hw)) { vlan_ops->add_vlan = noop_vlan_arg; vlan_ops->del_vlan = noop_vlan_arg; vlan_ops->ena_stripping = ice_vsi_ena_inner_stripping; vlan_ops->dis_stripping = ice_vsi_dis_inner_stripping; vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; - } else { - vlan_ops = &vsi->inner_vlan_ops; + /* setup outer VLAN ops */ + vlan_ops = &vsi->outer_vlan_ops; + vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; + } else { vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 6f2328a049bf1..1ff9818b4c84f 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -499,7 +499,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->rss_lut_size = ICE_LUT_VSI_SIZE; vfres->max_mtu = ice_vc_get_max_frame_size(vf); - vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; + vfres->vsi_res[0].vsi_id = ICE_VF_VSI_ID; vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; ether_addr_copy(vfres->vsi_res[0].default_mac_addr, @@ -545,27 +545,20 @@ static void ice_vc_reset_vf_msg(struct ice_vf *vf) */ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) { - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = ice_find_vsi(pf, vsi_id); - - return (vsi && (vsi->vf == vf)); + return vsi_id == ICE_VF_VSI_ID; } /** * ice_vc_isvalid_q_id - * @vf: pointer to the VF info - * @vsi_id: VSI ID + * @vsi: VSI to check queue ID against * @qid: VSI relative queue ID * * check for the valid queue ID */ -static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) +static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid) { - struct ice_vsi *vsi = ice_find_vsi(vf->pf, vsi_id); /* allocated Tx and Rx queues should be always equal for VF VSI */ - return (vsi && (qid < vsi->alloc_txq)); + return qid < vsi->alloc_txq; } /** @@ -1323,7 +1316,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) */ q_map = vqs->rx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1345,7 +1338,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1450,7 +1443,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1476,7 +1469,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); } else if (q_map) { for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1532,7 +1525,7 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { vsi_q_id = vsi_q_id_idx; - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + if (!ice_vc_isvalid_q_id(vsi, vsi_q_id)) return VIRTCHNL_STATUS_ERR_PARAM; q_vector->num_ring_rx++; @@ -1546,7 +1539,7 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { vsi_q_id = vsi_q_id_idx; - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + if (!ice_vc_isvalid_q_id(vsi, vsi_q_id)) return VIRTCHNL_STATUS_ERR_PARAM; q_vector->num_ring_tx++; @@ -1703,7 +1696,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) qpi->txq.headwb_enabled || !ice_vc_isvalid_ring_len(qpi->txq.ring_len) || !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) || - !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { + !ice_vc_isvalid_q_id(vsi, qpi->txq.queue_id)) { goto error_param; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index 60dfbe05980aa..3a41158691532 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -19,6 +19,15 @@ #define ICE_MAX_MACADDR_PER_VF 18 #define ICE_FLEX_DESC_RXDID_MAX_NUM 64 +/* VFs only get a single VSI. For ice hardware, the VF does not need to know + * its VSI index. However, the virtchnl interface requires a VSI number, + * mainly due to legacy hardware. + * + * Since the VF doesn't need this information, report a static value to the VF + * instead of leaking any information about the PF or hardware setup. + */ +#define ICE_VF_VSI_ID 1 + struct ice_virtchnl_ops { int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); int (*get_vf_res_msg)(struct ice_vf *vf, u8 *msg); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index f001553e1a1a0..8e4ff3af86c68 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -94,9 +94,6 @@ ice_vc_fdir_param_check(struct ice_vf *vf, u16 vsi_id) if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF)) return -EINVAL; - if (vsi_id != vf->lan_vsi_num) - return -EINVAL; - if (!ice_vc_isvalid_vsi_id(vf, vsi_id)) return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 2e9ad27cb9d13..6e8f2aab60801 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -45,14 +45,15 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return -EINVAL; err = ice_fltr_add_vlan(vsi, vlan); - if (err && err != -EEXIST) { + if (!err) + vsi->num_vlan++; + else if (err == -EEXIST) + err = 0; + else dev_err(ice_pf_to_dev(vsi->back), "Failure Adding VLAN %d on VSI %i, status %d\n", vlan->vid, vsi->vsi_num, err); - return err; - } - vsi->num_vlan++; - return 0; + return err; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 2eecd0f39aa69..86a865788e345 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -218,42 +218,28 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) */ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) { - DEFINE_FLEX(struct ice_aqc_add_tx_qgrp, qg_buf, txqs, 1); - u16 size = __struct_size(qg_buf); struct ice_q_vector *q_vector; - struct ice_tx_ring *tx_ring; - struct ice_rx_ring *rx_ring; int err; - if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq) - return -EINVAL; - - qg_buf->num_txqs = 1; - - tx_ring = vsi->tx_rings[q_idx]; - rx_ring = vsi->rx_rings[q_idx]; - q_vector = rx_ring->q_vector; - - err = ice_vsi_cfg_txq(vsi, tx_ring, qg_buf); + err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx); if (err) return err; if (ice_is_xdp_ena_vsi(vsi)) { struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; - memset(qg_buf, 0, size); - qg_buf->num_txqs = 1; - err = ice_vsi_cfg_txq(vsi, xdp_ring, qg_buf); + err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx); if (err) return err; ice_set_ring_xdp(xdp_ring); ice_tx_xsk_pool(vsi, q_idx); } - err = ice_vsi_cfg_rxq(rx_ring); + err = ice_vsi_cfg_single_rxq(vsi, q_idx); if (err) return err; + q_vector = vsi->rx_rings[q_idx]->q_vector; ice_qvec_cfg_msix(vsi, q_vector); err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true); @@ -283,7 +269,6 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid) if (!pool) return -EINVAL; - clear_bit(qid, vsi->af_xdp_zc_qps); xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR); return 0; @@ -314,8 +299,6 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) if (err) return err; - set_bit(qid, vsi->af_xdp_zc_qps); - return 0; } @@ -363,11 +346,13 @@ ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present) int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) { struct ice_rx_ring *rx_ring; - unsigned long q; + uint i; + + ice_for_each_rxq(vsi, i) { + rx_ring = vsi->rx_rings[i]; + if (!rx_ring->xsk_pool) + continue; - for_each_set_bit(q, vsi->af_xdp_zc_qps, - max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) { - rx_ring = vsi->rx_rings[q]; if (ice_realloc_rx_xdp_bufs(rx_ring, zc)) return -ENOMEM; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index 986d429d11755..1885ba618981d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -222,14 +222,19 @@ static int idpf_set_channels(struct net_device *netdev, struct ethtool_channels *ch) { struct idpf_vport_config *vport_config; - u16 combined, num_txq, num_rxq; unsigned int num_req_tx_q; unsigned int num_req_rx_q; struct idpf_vport *vport; + u16 num_txq, num_rxq; struct device *dev; int err = 0; u16 idx; + if (ch->rx_count && ch->tx_count) { + netdev_err(netdev, "Dedicated RX or TX channels cannot be used simultaneously\n"); + return -EINVAL; + } + idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); @@ -239,20 +244,6 @@ static int idpf_set_channels(struct net_device *netdev, num_txq = vport_config->user_config.num_req_tx_qs; num_rxq = vport_config->user_config.num_req_rx_qs; - combined = min(num_txq, num_rxq); - - /* these checks are for cases where user didn't specify a particular - * value on cmd line but we get non-zero value anyway via - * get_channels(); look at ethtool.c in ethtool repository (the user - * space part), particularly, do_schannels() routine - */ - if (ch->combined_count == combined) - ch->combined_count = 0; - if (ch->combined_count && ch->rx_count == num_rxq - combined) - ch->rx_count = 0; - if (ch->combined_count && ch->tx_count == num_txq - combined) - ch->tx_count = 0; - num_req_tx_q = ch->combined_count + ch->tx_count; num_req_rx_q = ch->combined_count + ch->rx_count; @@ -376,7 +367,8 @@ static int idpf_set_ringparam(struct net_device *netdev, new_tx_count); if (new_tx_count == vport->txq_desc_count && - new_rx_count == vport->rxq_desc_count) + new_rx_count == vport->rxq_desc_count && + kring->tcp_data_split == idpf_vport_get_hsplit(vport)) goto unlock_mutex; if (!idpf_vport_set_hsplit(vport, kring->tcp_data_split)) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 58179bd733ff0..f769a9fc1084c 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -1419,6 +1419,7 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) } idpf_rx_init_buf_tail(vport); + idpf_vport_intr_ena(vport); err = idpf_send_config_queues_msg(vport); if (err) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 2f8ad79ae3f04..b16fa9d8a8c58 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -2940,6 +2940,8 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq, rx_ptype = le16_get_bits(rx_desc->ptype_err_fflags0, VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M); + skb->protocol = eth_type_trans(skb, rxq->vport->netdev); + decoded = rxq->vport->rx_ptype_lkup[rx_ptype]; /* If we don't know the ptype we can't do anything else with it. Just * pass it up the stack as-is. @@ -2950,8 +2952,6 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq, /* process RSS/hash */ idpf_rx_hash(rxq, skb, rx_desc, &decoded); - skb->protocol = eth_type_trans(skb, rxq->vport->netdev); - if (le16_get_bits(rx_desc->hdrlen_flags, VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M)) return idpf_rx_rsc(rxq, skb, rx_desc, &decoded); @@ -3746,9 +3746,9 @@ static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport) */ void idpf_vport_intr_deinit(struct idpf_vport *vport) { + idpf_vport_intr_dis_irq_all(vport); idpf_vport_intr_napi_dis_all(vport); idpf_vport_intr_napi_del_all(vport); - idpf_vport_intr_dis_irq_all(vport); idpf_vport_intr_rel_irq(vport); } @@ -4179,7 +4179,6 @@ int idpf_vport_intr_init(struct idpf_vport *vport) idpf_vport_intr_map_vector_to_qs(vport); idpf_vport_intr_napi_add_all(vport); - idpf_vport_intr_napi_ena_all(vport); err = vport->adapter->dev_ops.reg_ops.intr_reg_init(vport); if (err) @@ -4193,17 +4192,20 @@ int idpf_vport_intr_init(struct idpf_vport *vport) if (err) goto unroll_vectors_alloc; - idpf_vport_intr_ena_irq_all(vport); - return 0; unroll_vectors_alloc: - idpf_vport_intr_napi_dis_all(vport); idpf_vport_intr_napi_del_all(vport); return err; } +void idpf_vport_intr_ena(struct idpf_vport *vport) +{ + idpf_vport_intr_napi_ena_all(vport); + idpf_vport_intr_ena_irq_all(vport); +} + /** * idpf_config_rss - Send virtchnl messages to configure RSS * @vport: virtual port diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index df76493faa756..85a1466890d43 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -988,6 +988,7 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport); void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector); void idpf_vport_intr_deinit(struct idpf_vport *vport); int idpf_vport_intr_init(struct idpf_vport *vport); +void idpf_vport_intr_ena(struct idpf_vport *vport); enum pkt_hash_types idpf_ptype_to_htype(const struct idpf_rx_ptype_decoded *decoded); int idpf_config_rss(struct idpf_vport *vport); int idpf_init_rss(struct idpf_vport *vport); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index cebb44f51d5f5..7662c42e35c11 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6985,44 +6985,31 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) static void igb_tsync_interrupt(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - u32 ack = 0, tsicr = rd32(E1000_TSICR); + u32 tsicr = rd32(E1000_TSICR); struct ptp_clock_event event; if (tsicr & TSINTR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) ptp_clock_event(adapter->ptp_clock, &event); - ack |= TSINTR_SYS_WRAP; } if (tsicr & E1000_TSICR_TXTS) { /* retrieve hardware timestamp */ schedule_work(&adapter->ptp_tx_work); - ack |= E1000_TSICR_TXTS; } - if (tsicr & TSINTR_TT0) { + if (tsicr & TSINTR_TT0) igb_perout(adapter, 0); - ack |= TSINTR_TT0; - } - if (tsicr & TSINTR_TT1) { + if (tsicr & TSINTR_TT1) igb_perout(adapter, 1); - ack |= TSINTR_TT1; - } - if (tsicr & TSINTR_AUTT0) { + if (tsicr & TSINTR_AUTT0) igb_extts(adapter, 0); - ack |= TSINTR_AUTT0; - } - if (tsicr & TSINTR_AUTT1) { + if (tsicr & TSINTR_AUTT1) igb_extts(adapter, 1); - ack |= TSINTR_AUTT1; - } - - /* acknowledge the interrupts */ - wr32(E1000_TSICR, ack); } static irqreturn_t igb_msix_other(int irq, void *data) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 81c21a893ede9..d98a681622537 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1642,10 +1642,6 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { - /* FIXME: add support for retrieving timestamps from - * the other timer registers before skipping the - * timestamping request. - */ unsigned long flags; u32 tstamp_flags; @@ -5302,25 +5298,22 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, static void igc_tsync_interrupt(struct igc_adapter *adapter) { - u32 ack, tsauxc, sec, nsec, tsicr; struct igc_hw *hw = &adapter->hw; + u32 tsauxc, sec, nsec, tsicr; struct ptp_clock_event event; struct timespec64 ts; tsicr = rd32(IGC_TSICR); - ack = 0; if (tsicr & IGC_TSICR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_SYS_WRAP; } if (tsicr & IGC_TSICR_TXTS) { /* retrieve hardware timestamp */ igc_ptp_tx_tstamp_event(adapter); - ack |= IGC_TSICR_TXTS; } if (tsicr & IGC_TSICR_TT0) { @@ -5334,7 +5327,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) wr32(IGC_TSAUXC, tsauxc); adapter->perout[0].start = ts; spin_unlock(&adapter->tmreg_lock); - ack |= IGC_TSICR_TT0; } if (tsicr & IGC_TSICR_TT1) { @@ -5348,7 +5340,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) wr32(IGC_TSAUXC, tsauxc); adapter->perout[1].start = ts; spin_unlock(&adapter->tmreg_lock); - ack |= IGC_TSICR_TT1; } if (tsicr & IGC_TSICR_AUTT0) { @@ -5358,7 +5349,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) event.index = 0; event.timestamp = sec * NSEC_PER_SEC + nsec; ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_AUTT0; } if (tsicr & IGC_TSICR_AUTT1) { @@ -5368,11 +5358,7 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) event.index = 1; event.timestamp = sec * NSEC_PER_SEC + nsec; ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_AUTT1; } - - /* acknowledge the interrupts */ - wr32(IGC_TSICR, ack); } /** @@ -6833,6 +6819,9 @@ static int igc_probe(struct pci_dev *pdev, memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops)); memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops)); + if (pci_is_thunderbolt_attached(pdev)) + msleep(600); + /* Initialize skew-specific constants */ err = ei->get_invariants(hw); if (err) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 13a6fca31004a..866024f2b9eeb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -914,7 +914,13 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) goto err_out; } - xs = kzalloc(sizeof(*xs), GFP_KERNEL); + algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); + if (unlikely(!algo)) { + err = -ENOENT; + goto err_out; + } + + xs = kzalloc(sizeof(*xs), GFP_ATOMIC); if (unlikely(!xs)) { err = -ENOMEM; goto err_out; @@ -930,14 +936,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4)); xs->xso.dev = adapter->netdev; - algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); - if (unlikely(!algo)) { - err = -ENOENT; - goto err_xs; - } - aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8; - xs->aead = kzalloc(aead_len, GFP_KERNEL); + xs->aead = kzalloc(aead_len, GFP_ATOMIC); if (unlikely(!xs->aead)) { err = -ENOMEM; goto err_xs; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 61b9774b3d31e..c24a72d1e2737 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -3673,9 +3673,7 @@ struct ixgbe_info { #define IXGBE_KRM_LINK_S1(P) ((P) ? 0x8200 : 0x4200) #define IXGBE_KRM_LINK_CTRL_1(P) ((P) ? 0x820C : 0x420C) #define IXGBE_KRM_AN_CNTL_1(P) ((P) ? 0x822C : 0x422C) -#define IXGBE_KRM_AN_CNTL_4(P) ((P) ? 0x8238 : 0x4238) #define IXGBE_KRM_AN_CNTL_8(P) ((P) ? 0x8248 : 0x4248) -#define IXGBE_KRM_PCS_KX_AN(P) ((P) ? 0x9918 : 0x5918) #define IXGBE_KRM_SGMII_CTRL(P) ((P) ? 0x82A0 : 0x42A0) #define IXGBE_KRM_LP_BASE_PAGE_HIGH(P) ((P) ? 0x836C : 0x436C) #define IXGBE_KRM_DSP_TXFFE_STATE_4(P) ((P) ? 0x8634 : 0x4634) @@ -3685,7 +3683,6 @@ struct ixgbe_info { #define IXGBE_KRM_PMD_FLX_MASK_ST20(P) ((P) ? 0x9054 : 0x5054) #define IXGBE_KRM_TX_COEFF_CTRL_1(P) ((P) ? 0x9520 : 0x5520) #define IXGBE_KRM_RX_ANA_CTL(P) ((P) ? 0x9A00 : 0x5A00) -#define IXGBE_KRM_FLX_TMRS_CTRL_ST31(P) ((P) ? 0x9180 : 0x5180) #define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA ~(0x3 << 20) #define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR BIT(20) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index c1adc94a5a657..f806fbf25ec7c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1722,59 +1722,9 @@ static s32 ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed) return -EINVAL; } - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* change mode enforcement rules to hybrid */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_FLX_TMRS_CTRL_ST31(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= 0x0400; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_FLX_TMRS_CTRL_ST31(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* manually control the config */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= 0x20002240; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* move the AN base page values */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_PCS_KX_AN(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= 0x1; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_PCS_KX_AN(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* set the AN37 over CB mode */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_AN_CNTL_4(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= 0x20000000; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_AN_CNTL_4(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); - - /* restart AN manually */ - (void)mac->ops.read_iosf_sb_reg(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); - reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART; - - (void)mac->ops.write_iosf_sb_reg(hw, - IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + status = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); /* Toggle port SW reset by AN reset. */ status = ixgbe_restart_an_internal_phy_x550em(hw); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 23adf53c2aa1c..cebc79a710ec2 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4013,7 +4013,10 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, } } - skb = build_skb(data, frag_size); + if (frag_size) + skb = build_skb(data, frag_size); + else + skb = slab_build_skb(data); if (!skb) { netdev_warn(port->dev, "skb build failed\n"); goto err_drop_frame; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 6c70c84986904..b86f3224f0b78 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -808,6 +808,11 @@ static int cgx_lmac_enadis_pause_frm(void *cgxd, int lmac_id, if (!is_lmac_valid(cgx, lmac_id)) return -ENODEV; + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; + cfg |= rx_pause ? CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK : 0x0; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK; cfg |= rx_pause ? CGX_SMUX_RX_FRM_CTL_CTL_BCK : 0x0; @@ -1338,7 +1343,7 @@ static irqreturn_t cgx_fwi_event_handler(int irq, void *data) /* Release thread waiting for completion */ lmac->cmd_pend = false; - wake_up_interruptible(&lmac->wq_cmd_cmplt); + wake_up(&lmac->wq_cmd_cmplt); break; case CGX_EVT_ASYNC: if (cgx_event_is_linkevent(event)) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c index b92264d0a77e7..1e5aa53975040 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c @@ -214,11 +214,12 @@ int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid) } EXPORT_SYMBOL(otx2_mbox_busy_poll_for_rsp); -void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) +static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data) { struct otx2_mbox_dev *mdev = &mbox->dev[devid]; struct mbox_hdr *tx_hdr, *rx_hdr; void *hw_mbase = mdev->hwbase; + u64 intr_val; tx_hdr = hw_mbase + mbox->tx_start; rx_hdr = hw_mbase + mbox->rx_start; @@ -254,14 +255,52 @@ void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) spin_unlock(&mdev->mbox_lock); + /* Check if interrupt pending */ + intr_val = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + intr_val |= data; /* The interrupt should be fired after num_msgs is written * to the shared memory */ - writeq(1, (void __iomem *)mbox->reg_base + + writeq(intr_val, (void __iomem *)mbox->reg_base + (mbox->trigger | (devid << mbox->tr_shift))); } + +void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid) +{ + otx2_mbox_msg_send_data(mbox, devid, MBOX_DOWN_MSG); +} EXPORT_SYMBOL(otx2_mbox_msg_send); +void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid) +{ + otx2_mbox_msg_send_data(mbox, devid, MBOX_UP_MSG); +} +EXPORT_SYMBOL(otx2_mbox_msg_send_up); + +bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid) +{ + u64 data; + + data = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + /* If data is non-zero wait for ~1ms and return to caller + * whether data has changed to zero or not after the wait. + */ + if (!data) + return true; + + usleep_range(950, 1000); + + data = readq((void __iomem *)mbox->reg_base + + (mbox->trigger | (devid << mbox->tr_shift))); + + return data == 0; +} +EXPORT_SYMBOL(otx2_mbox_wait_for_zero); + struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid, int size, int size_rsp) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index edeb0f7373121..98e203a0e26b6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -16,6 +16,9 @@ #define MBOX_SIZE SZ_64K +#define MBOX_DOWN_MSG 1 +#define MBOX_UP_MSG 2 + /* AF/PF: PF initiated, PF/VF VF initiated */ #define MBOX_DOWN_RX_START 0 #define MBOX_DOWN_RX_SIZE (46 * SZ_1K) @@ -101,6 +104,7 @@ int otx2_mbox_regions_init(struct otx2_mbox *mbox, void __force **hwbase, struct pci_dev *pdev, void __force *reg_base, int direction, int ndevs, unsigned long *bmap); void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid); +void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid); int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid); int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid); struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid, @@ -118,6 +122,8 @@ static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox, return otx2_mbox_alloc_msg_rsp(mbox, devid, size, 0); } +bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid); + /* Mailbox message types */ #define MBOX_MSG_MASK 0xFFFF #define MBOX_MSG_INVALID 0xFFFE diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c index dfd23580e3b8e..d39d86e694ccf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c @@ -121,13 +121,17 @@ int mcs_add_intr_wq_entry(struct mcs *mcs, struct mcs_intr_event *event) static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu) { struct mcs_intr_info *req; - int err, pf; + int pf; pf = rvu_get_pf(event->pcifunc); + mutex_lock(&rvu->mbox_lock); + req = otx2_mbox_alloc_msg_mcs_intr_notify(rvu, pf); - if (!req) + if (!req) { + mutex_unlock(&rvu->mbox_lock); return -ENOMEM; + } req->mcs_id = event->mcs_id; req->intr_mask = event->intr_mask; @@ -135,10 +139,11 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu) req->hdr.pcifunc = event->pcifunc; req->lmac_id = event->lmac_id; - otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pf); - err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pf); - if (err) - dev_warn(rvu->dev, "MCS notification to pf %d failed\n", pf); + otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pf); + + otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf); + + mutex_unlock(&rvu->mbox_lock); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 5c1d04a3c559b..6a911ea0cff9b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2117,7 +2117,7 @@ MBOX_MESSAGES } } -static void __rvu_mbox_handler(struct rvu_work *mwork, int type) +static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll) { struct rvu *rvu = mwork->rvu; int offset, err, id, devid; @@ -2184,6 +2184,9 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type) } mw->mbox_wrk[devid].num_msgs = 0; + if (poll) + otx2_mbox_wait_for_zero(mbox, devid); + /* Send mbox responses to VF/PF */ otx2_mbox_msg_send(mbox, devid); } @@ -2191,15 +2194,18 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type) static inline void rvu_afpf_mbox_handler(struct work_struct *work) { struct rvu_work *mwork = container_of(work, struct rvu_work, work); + struct rvu *rvu = mwork->rvu; - __rvu_mbox_handler(mwork, TYPE_AFPF); + mutex_lock(&rvu->mbox_lock); + __rvu_mbox_handler(mwork, TYPE_AFPF, true); + mutex_unlock(&rvu->mbox_lock); } static inline void rvu_afvf_mbox_handler(struct work_struct *work) { struct rvu_work *mwork = container_of(work, struct rvu_work, work); - __rvu_mbox_handler(mwork, TYPE_AFVF); + __rvu_mbox_handler(mwork, TYPE_AFVF, false); } static void __rvu_mbox_up_handler(struct rvu_work *mwork, int type) @@ -2374,6 +2380,8 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, } } + mutex_init(&rvu->mbox_lock); + mbox_regions = kcalloc(num, sizeof(void *), GFP_KERNEL); if (!mbox_regions) { err = -ENOMEM; @@ -2523,10 +2531,9 @@ static void rvu_queue_work(struct mbox_wq_info *mw, int first, } } -static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) +static irqreturn_t rvu_mbox_pf_intr_handler(int irq, void *rvu_irq) { struct rvu *rvu = (struct rvu *)rvu_irq; - int vfs = rvu->vfs; u64 intr; intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT); @@ -2540,6 +2547,18 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) rvu_queue_work(&rvu->afpf_wq_info, 0, rvu->hw->total_pfs, intr); + return IRQ_HANDLED; +} + +static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) +{ + struct rvu *rvu = (struct rvu *)rvu_irq; + int vfs = rvu->vfs; + u64 intr; + + /* Sync with mbox memory region */ + rmb(); + /* Handle VF interrupts */ if (vfs > 64) { intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(1)); @@ -2881,7 +2900,7 @@ static int rvu_register_interrupts(struct rvu *rvu) /* Register mailbox interrupt handler */ sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], "RVUAF Mbox"); ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_MBOX), - rvu_mbox_intr_handler, 0, + rvu_mbox_pf_intr_handler, 0, &rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], rvu); if (ret) { dev_err(rvu->dev, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 43be37dd1f325..d44a400e1b502 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -570,6 +570,8 @@ struct rvu { spinlock_t mcs_intrq_lock; /* CPT interrupt lock */ spinlock_t cpt_intr_lock; + + struct mutex mbox_lock; /* Serialize mbox up and down msgs */ }; static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 38acdc7a73bbe..e9bf9231b0185 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -160,6 +160,8 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) continue; lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { + if (iter >= MAX_LMAC_COUNT) + continue; lmac = cgx_get_lmacid(rvu_cgx_pdata(cgx, rvu), iter); rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac); @@ -232,7 +234,7 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) struct cgx_link_user_info *linfo; struct cgx_link_info_msg *msg; unsigned long pfmap; - int err, pfid; + int pfid; linfo = &event->link_uinfo; pfmap = cgxlmac_to_pfmap(rvu, event->cgx_id, event->lmac_id); @@ -255,16 +257,22 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) continue; } + mutex_lock(&rvu->mbox_lock); + /* Send mbox message to PF */ msg = otx2_mbox_alloc_msg_cgx_link_event(rvu, pfid); - if (!msg) + if (!msg) { + mutex_unlock(&rvu->mbox_lock); continue; + } + msg->link_info = *linfo; - otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pfid); - err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pfid); - if (err) - dev_warn(rvu->dev, "notification to pf %d failed\n", - pfid); + + otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pfid); + + otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pfid); + + mutex_unlock(&rvu->mbox_lock); } while (pfmap); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index e6d7914ce61c4..e7eca8141e8c7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -999,12 +999,10 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, u16 pcifunc; int ret, lf; - cmd_buf = memdup_user(buffer, count + 1); + cmd_buf = memdup_user_nul(buffer, count); if (IS_ERR(cmd_buf)) return -ENOMEM; - cmd_buf[count] = '\0'; - cmd_buf_tmp = strchr(cmd_buf, '\n'); if (cmd_buf_tmp) { *cmd_buf_tmp = '\0'; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 1e6fbd98423dc..96c04f7d93f8b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1235,8 +1235,8 @@ static int rvu_af_dl_dwrr_mtu_get(struct devlink *devlink, u32 id, enum rvu_af_dl_param_id { RVU_AF_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, RVU_AF_DEVLINK_PARAM_ID_DWRR_MTU, - RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE, RVU_AF_DEVLINK_PARAM_ID_NPC_MCAM_ZONE_PERCENT, + RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE, RVU_AF_DEVLINK_PARAM_ID_NIX_MAXLF, }; @@ -1434,15 +1434,6 @@ static const struct devlink_param rvu_af_dl_params[] = { BIT(DEVLINK_PARAM_CMODE_RUNTIME), rvu_af_dl_dwrr_mtu_get, rvu_af_dl_dwrr_mtu_set, rvu_af_dl_dwrr_mtu_validate), -}; - -static const struct devlink_param rvu_af_dl_param_exact_match[] = { - DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE, - "npc_exact_feature_disable", DEVLINK_PARAM_TYPE_STRING, - BIT(DEVLINK_PARAM_CMODE_RUNTIME), - rvu_af_npc_exact_feature_get, - rvu_af_npc_exact_feature_disable, - rvu_af_npc_exact_feature_validate), DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_MCAM_ZONE_PERCENT, "npc_mcam_high_zone_percent", DEVLINK_PARAM_TYPE_U8, BIT(DEVLINK_PARAM_CMODE_RUNTIME), @@ -1457,6 +1448,15 @@ static const struct devlink_param rvu_af_dl_param_exact_match[] = { rvu_af_dl_nix_maxlf_validate), }; +static const struct devlink_param rvu_af_dl_param_exact_match[] = { + DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE, + "npc_exact_feature_disable", DEVLINK_PARAM_TYPE_STRING, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + rvu_af_npc_exact_feature_get, + rvu_af_npc_exact_feature_disable, + rvu_af_npc_exact_feature_validate), +}; + /* Devlink switch mode */ static int rvu_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 66203a90f052b..42db213fb69a6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4721,18 +4721,18 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw) */ rvu_write64(rvu, blkaddr, NIX_AF_CFG, rvu_read64(rvu, blkaddr, NIX_AF_CFG) | 0x40ULL); + } - /* Set chan/link to backpressure TL3 instead of TL2 */ - rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01); + /* Set chan/link to backpressure TL3 instead of TL2 */ + rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01); - /* Disable SQ manager's sticky mode operation (set TM6 = 0) - * This sticky mode is known to cause SQ stalls when multiple - * SQs are mapped to same SMQ and transmitting pkts at a time. - */ - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS); - cfg &= ~BIT_ULL(15); - rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg); - } + /* Disable SQ manager's sticky mode operation (set TM6 = 0) + * This sticky mode is known to cause SQ stalls when multiple + * SQs are mapped to same SMQ and transmitting pkts at a time. + */ + cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS); + cfg &= ~BIT_ULL(15); + rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg); ltdefs = rvu->kpu.lt_def; /* Calibrate X2P bus to check if CGX/LBK links are fine */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 516adb50f9f6b..72e6e7a2e6194 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -1657,7 +1657,7 @@ static int npc_fwdb_detect_load_prfl_img(struct rvu *rvu, uint64_t prfl_sz, struct npc_coalesced_kpu_prfl *img_data = NULL; int i = 0, rc = -EINVAL; void __iomem *kpu_prfl_addr; - u16 offset; + u32 offset; img_data = (struct npc_coalesced_kpu_prfl __force *)rvu->kpu_prfl_addr; if (le64_to_cpu(img_data->signature) == KPU_SIGN && @@ -2181,7 +2181,6 @@ void rvu_npc_freemem(struct rvu *rvu) kfree(pkind->rsrc.bmap); npc_mcam_rsrcs_deinit(rvu); - kfree(mcam->counters.bmap); if (rvu->kpu_prfl_addr) iounmap(rvu->kpu_prfl_addr); else @@ -2520,7 +2519,17 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc, * - when available free entries are less. * Lower priority ones out of avaialble free entries are always * chosen when 'high vs low' question arises. + * + * For a VF base MCAM match rule is set by its PF. And all the + * further MCAM rules installed by VF on its own are + * concatenated with the base rule set by its PF. Hence PF entries + * should be at lower priority compared to VF entries. Otherwise + * base rule is hit always and rules installed by VF will be of + * no use. Hence if the request is from PF then allocate low + * priority entries. */ + if (!(pcifunc & RVU_PFVF_FUNC_MASK)) + goto lprio_alloc; /* Get the search range for priority allocation request */ if (req->priority) { @@ -2529,17 +2538,6 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc, goto alloc; } - /* For a VF base MCAM match rule is set by its PF. And all the - * further MCAM rules installed by VF on its own are - * concatenated with the base rule set by its PF. Hence PF entries - * should be at lower priority compared to VF entries. Otherwise - * base rule is hit always and rules installed by VF will be of - * no use. Hence if the request is from PF and NOT a priority - * allocation request then allocate low priority entries. - */ - if (!(pcifunc & RVU_PFVF_FUNC_MASK)) - goto lprio_alloc; - /* Find out the search range for non-priority allocation request * * Get MCAM free entry count in middle zone. @@ -2569,6 +2567,18 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc, reverse = true; start = 0; end = mcam->bmap_entries; + /* Ensure PF requests are always at bottom and if PF requests + * for higher/lower priority entry wrt reference entry then + * honour that criteria and start search for entries from bottom + * and not in mid zone. + */ + if (!(pcifunc & RVU_PFVF_FUNC_MASK) && + req->priority == NPC_MCAM_HIGHER_PRIO) + end = req->ref_entry; + + if (!(pcifunc & RVU_PFVF_FUNC_MASK) && + req->priority == NPC_MCAM_LOWER_PRIO) + start = req->ref_entry; } alloc: diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 5664f768cb0cd..64a97a0a10ed6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -9,10 +9,9 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ otx2_devlink.o qos_sq.o qos.o -rvu_nicvf-y := otx2_vf.o otx2_devlink.o +rvu_nicvf-y := otx2_vf.o rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o -rvu_nicvf-$(CONFIG_DCB) += otx2_dcbnl.o rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 02d0b707aea5b..a85ac039d779b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1592,7 +1592,7 @@ int otx2_detach_resources(struct mbox *mbox) detach->partial = false; /* Send detach request to AF */ - otx2_mbox_msg_send(&mbox->mbox, 0); + otx2_sync_mbox_msg(mbox); mutex_unlock(&mbox->lock); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 06910307085ef..7e16a341ec588 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -815,7 +815,7 @@ static inline int otx2_sync_mbox_up_msg(struct mbox *mbox, int devid) if (!otx2_mbox_nonempty(&mbox->mbox_up, devid)) return 0; - otx2_mbox_msg_send(&mbox->mbox_up, devid); + otx2_mbox_msg_send_up(&mbox->mbox_up, devid); err = otx2_mbox_wait_for_rsp(&mbox->mbox_up, devid); if (err) return err; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index 28fb643d2917f..aa01110f04a33 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -54,6 +54,7 @@ int otx2_pfc_txschq_config(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_config); static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio) { @@ -122,6 +123,7 @@ int otx2_pfc_txschq_alloc(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_alloc); static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio) { @@ -260,6 +262,7 @@ int otx2_pfc_txschq_update(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_update); int otx2_pfc_txschq_stop(struct otx2_nic *pfvf) { @@ -282,6 +285,7 @@ int otx2_pfc_txschq_stop(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_stop); int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf) { @@ -321,6 +325,7 @@ int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf) mutex_unlock(&pfvf->mbox.lock); return err; } +EXPORT_SYMBOL(otx2_config_priority_flow_ctrl); void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx, bool pfc_enable) @@ -385,6 +390,7 @@ void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx, "Updating BPIDs in CQ and Aura contexts of RQ%d failed with err %d\n", qidx, err); } +EXPORT_SYMBOL(otx2_update_bpid_in_rqctx); static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) { @@ -472,3 +478,4 @@ int otx2_dcbnl_set_ops(struct net_device *dev) return 0; } +EXPORT_SYMBOL(otx2_dcbnl_set_ops); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 4e1130496573e..05956bf03c05d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -112,6 +112,7 @@ int otx2_register_dl(struct otx2_nic *pfvf) devlink_free(dl); return err; } +EXPORT_SYMBOL(otx2_register_dl); void otx2_unregister_dl(struct otx2_nic *pfvf) { @@ -123,3 +124,4 @@ void otx2_unregister_dl(struct otx2_nic *pfvf) ARRAY_SIZE(otx2_dl_params)); devlink_free(dl); } +EXPORT_SYMBOL(otx2_unregister_dl); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index e5fe67e738655..3f46d5e0fb2ec 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -292,8 +292,8 @@ static int otx2_pf_flr_init(struct otx2_nic *pf, int num_vfs) return 0; } -static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq, - int first, int mdevs, u64 intr, int type) +static void otx2_queue_vf_work(struct mbox *mw, struct workqueue_struct *mbox_wq, + int first, int mdevs, u64 intr) { struct otx2_mbox_dev *mdev; struct otx2_mbox *mbox; @@ -307,40 +307,26 @@ static void otx2_queue_work(struct mbox *mw, struct workqueue_struct *mbox_wq, mbox = &mw->mbox; mdev = &mbox->dev[i]; - if (type == TYPE_PFAF) - otx2_sync_mbox_bbuf(mbox, i); hdr = mdev->mbase + mbox->rx_start; /* The hdr->num_msgs is set to zero immediately in the interrupt - * handler to ensure that it holds a correct value next time - * when the interrupt handler is called. - * pf->mbox.num_msgs holds the data for use in pfaf_mbox_handler - * pf>mbox.up_num_msgs holds the data for use in - * pfaf_mbox_up_handler. + * handler to ensure that it holds a correct value next time + * when the interrupt handler is called. pf->mw[i].num_msgs + * holds the data for use in otx2_pfvf_mbox_handler and + * pf->mw[i].up_num_msgs holds the data for use in + * otx2_pfvf_mbox_up_handler. */ if (hdr->num_msgs) { mw[i].num_msgs = hdr->num_msgs; hdr->num_msgs = 0; - if (type == TYPE_PFAF) - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), - sizeof(u64))); - queue_work(mbox_wq, &mw[i].mbox_wrk); } mbox = &mw->mbox_up; mdev = &mbox->dev[i]; - if (type == TYPE_PFAF) - otx2_sync_mbox_bbuf(mbox, i); hdr = mdev->mbase + mbox->rx_start; if (hdr->num_msgs) { mw[i].up_num_msgs = hdr->num_msgs; hdr->num_msgs = 0; - if (type == TYPE_PFAF) - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), - sizeof(u64))); - queue_work(mbox_wq, &mw[i].mbox_up_wrk); } } @@ -356,8 +342,10 @@ static void otx2_forward_msg_pfvf(struct otx2_mbox_dev *mdev, /* Msgs are already copied, trigger VF's mbox irq */ smp_wmb(); + otx2_mbox_wait_for_zero(pfvf_mbox, devid); + offset = pfvf_mbox->trigger | (devid << pfvf_mbox->tr_shift); - writeq(1, (void __iomem *)pfvf_mbox->reg_base + offset); + writeq(MBOX_DOWN_MSG, (void __iomem *)pfvf_mbox->reg_base + offset); /* Restore VF's mbox bounce buffer region address */ src_mdev->mbase = bbuf_base; @@ -547,7 +535,7 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work) end: offset = mbox->rx_start + msg->next_msgoff; if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1)) - __otx2_mbox_reset(mbox, 0); + __otx2_mbox_reset(mbox, vf_idx); mdev->msgs_acked++; } } @@ -564,8 +552,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) if (vfs > 64) { intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(1)); otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr); - otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr, - TYPE_PFVF); + otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr); if (intr) trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); vfs = 64; @@ -574,7 +561,7 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0)); otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(0), intr); - otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF); + otx2_queue_vf_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr); if (intr) trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); @@ -597,8 +584,9 @@ static int otx2_pfvf_mbox_init(struct otx2_nic *pf, int numvfs) if (!pf->mbox_pfvf) return -ENOMEM; - pf->mbox_pfvf_wq = alloc_ordered_workqueue("otx2_pfvf_mailbox", - WQ_HIGHPRI | WQ_MEM_RECLAIM); + pf->mbox_pfvf_wq = alloc_workqueue("otx2_pfvf_mailbox", + WQ_UNBOUND | WQ_HIGHPRI | + WQ_MEM_RECLAIM, 0); if (!pf->mbox_pfvf_wq) return -ENOMEM; @@ -821,20 +809,22 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work) struct mbox *af_mbox; struct otx2_nic *pf; int offset, id; + u16 num_msgs; af_mbox = container_of(work, struct mbox, mbox_wrk); mbox = &af_mbox->mbox; mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + num_msgs = rsp_hdr->num_msgs; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); pf = af_mbox->pfvf; - for (id = 0; id < af_mbox->num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2_process_pfaf_mbox_msg(pf, msg); offset = mbox->rx_start + msg->next_msgoff; - if (mdev->msgs_acked == (af_mbox->num_msgs - 1)) + if (mdev->msgs_acked == (num_msgs - 1)) __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } @@ -945,12 +935,14 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) int offset, id, devid = 0; struct mbox_hdr *rsp_hdr; struct mbox_msghdr *msg; + u16 num_msgs; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + num_msgs = rsp_hdr->num_msgs; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < af_mbox->up_num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); devid = msg->pcifunc & RVU_PFVF_FUNC_MASK; @@ -959,10 +951,11 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) otx2_process_mbox_msg_up(pf, msg); offset = mbox->rx_start + msg->next_msgoff; } - if (devid) { + /* Forward to VF iff VFs are really present */ + if (devid && pci_num_vf(pf->pdev)) { otx2_forward_vf_mbox_msgs(pf, &pf->mbox.mbox_up, MBOX_DIR_PFVF_UP, devid - 1, - af_mbox->up_num_msgs); + num_msgs); return; } @@ -972,16 +965,49 @@ static void otx2_pfaf_mbox_up_handler(struct work_struct *work) static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq) { struct otx2_nic *pf = (struct otx2_nic *)pf_irq; - struct mbox *mbox; + struct mbox *mw = &pf->mbox; + struct otx2_mbox_dev *mdev; + struct otx2_mbox *mbox; + struct mbox_hdr *hdr; + u64 mbox_data; /* Clear the IRQ */ otx2_write64(pf, RVU_PF_INT, BIT_ULL(0)); - mbox = &pf->mbox; - trace_otx2_msg_interrupt(mbox->mbox.pdev, "AF to PF", BIT_ULL(0)); + mbox_data = otx2_read64(pf, RVU_PF_PFAF_MBOX0); + + if (mbox_data & MBOX_UP_MSG) { + mbox_data &= ~MBOX_UP_MSG; + otx2_write64(pf, RVU_PF_PFAF_MBOX0, mbox_data); + + mbox = &mw->mbox_up; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(pf->mbox_wq, &mw->mbox_up_wrk); + + trace_otx2_msg_interrupt(pf->pdev, "UP message from AF to PF", + BIT_ULL(0)); + } + + if (mbox_data & MBOX_DOWN_MSG) { + mbox_data &= ~MBOX_DOWN_MSG; + otx2_write64(pf, RVU_PF_PFAF_MBOX0, mbox_data); + + mbox = &mw->mbox; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(pf->mbox_wq, &mw->mbox_wrk); - otx2_queue_work(mbox, pf->mbox_wq, 0, 1, 1, TYPE_PFAF); + trace_otx2_msg_interrupt(pf->pdev, "DOWN reply from AF to PF", + BIT_ULL(0)); + } return IRQ_HANDLED; } @@ -1907,7 +1933,7 @@ int otx2_open(struct net_device *netdev) * mcam entries are enabled to receive the packets. Hence disable the * packet I/O. */ - if (err == EIO) + if (err == -EIO) goto err_disable_rxtx; else if (err) goto err_tx_stop_queues; @@ -3087,6 +3113,7 @@ static void otx2_vf_link_event_task(struct work_struct *work) struct otx2_vf_config *config; struct cgx_link_info_msg *req; struct mbox_msghdr *msghdr; + struct delayed_work *dwork; struct otx2_nic *pf; int vf_idx; @@ -3095,10 +3122,24 @@ static void otx2_vf_link_event_task(struct work_struct *work) vf_idx = config - config->pf->vf_configs; pf = config->pf; + if (config->intf_down) + return; + + mutex_lock(&pf->mbox.lock); + + dwork = &config->link_event_work; + + if (!otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx)) { + schedule_delayed_work(dwork, msecs_to_jiffies(100)); + mutex_unlock(&pf->mbox.lock); + return; + } + msghdr = otx2_mbox_alloc_msg_rsp(&pf->mbox_pfvf[0].mbox_up, vf_idx, sizeof(*req), sizeof(struct msg_rsp)); if (!msghdr) { dev_err(pf->dev, "Failed to create VF%d link event\n", vf_idx); + mutex_unlock(&pf->mbox.lock); return; } @@ -3107,7 +3148,11 @@ static void otx2_vf_link_event_task(struct work_struct *work) req->hdr.sig = OTX2_MBOX_REQ_SIG; memcpy(&req->link_info, &pf->linfo, sizeof(req->link_info)); + otx2_mbox_wait_for_zero(&pf->mbox_pfvf[0].mbox_up, vf_idx); + otx2_sync_mbox_up_msg(&pf->mbox_pfvf[0], vf_idx); + + mutex_unlock(&pf->mbox.lock); } static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 4fd44b6eecea6..60ee7ae2c4097 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -688,6 +688,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_match_control match; + u32 val; flow_rule_match_control(rule, &match); if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { @@ -696,12 +697,14 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, } if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { + val = match.key->flags & FLOW_DIS_IS_FRAGMENT; if (ntohs(flow_spec->etype) == ETH_P_IP) { - flow_spec->ip_flag = IPV4_FLAG_MORE; + flow_spec->ip_flag = val ? IPV4_FLAG_MORE : 0; flow_mask->ip_flag = IPV4_FLAG_MORE; req->features |= BIT_ULL(NPC_IPFRAG_IPV4); } else if (ntohs(flow_spec->etype) == ETH_P_IPV6) { - flow_spec->next_header = IPPROTO_FRAGMENT; + flow_spec->next_header = val ? + IPPROTO_FRAGMENT : 0; flow_mask->next_header = 0xff; req->features |= BIT_ULL(NPC_IPFRAG_IPV6); } else { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index f828d32737af0..04a49b9b545f3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -1171,8 +1171,11 @@ bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, if (skb_shinfo(skb)->gso_size && !is_hw_tso_supported(pfvf, skb)) { /* Insert vlan tag before giving pkt to tso */ - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tag_present(skb)) { skb = __vlan_hwaccel_push_inside(skb); + if (!skb) + return true; + } otx2_sq_append_tso(pfvf, sq, skb, qidx); return true; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 35e06048356f4..cf0aa16d75407 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -89,16 +89,20 @@ static void otx2vf_vfaf_mbox_handler(struct work_struct *work) struct otx2_mbox *mbox; struct mbox *af_mbox; int offset, id; + u16 num_msgs; af_mbox = container_of(work, struct mbox, mbox_wrk); mbox = &af_mbox->mbox; mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (af_mbox->num_msgs == 0) + num_msgs = rsp_hdr->num_msgs; + + if (num_msgs == 0) return; + offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < af_mbox->num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2vf_process_vfaf_mbox_msg(af_mbox->pfvf, msg); offset = mbox->rx_start + msg->next_msgoff; @@ -151,6 +155,7 @@ static void otx2vf_vfaf_mbox_up_handler(struct work_struct *work) struct mbox *vf_mbox; struct otx2_nic *vf; int offset, id; + u16 num_msgs; vf_mbox = container_of(work, struct mbox, mbox_up_wrk); vf = vf_mbox->pfvf; @@ -158,12 +163,14 @@ static void otx2vf_vfaf_mbox_up_handler(struct work_struct *work) mdev = &mbox->dev[0]; rsp_hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (vf_mbox->up_num_msgs == 0) + num_msgs = rsp_hdr->num_msgs; + + if (num_msgs == 0) return; offset = mbox->rx_start + ALIGN(sizeof(*rsp_hdr), MBOX_MSG_ALIGN); - for (id = 0; id < vf_mbox->up_num_msgs; id++) { + for (id = 0; id < num_msgs; id++) { msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2vf_process_mbox_msg_up(vf, msg); offset = mbox->rx_start + msg->next_msgoff; @@ -178,40 +185,48 @@ static irqreturn_t otx2vf_vfaf_mbox_intr_handler(int irq, void *vf_irq) struct otx2_mbox_dev *mdev; struct otx2_mbox *mbox; struct mbox_hdr *hdr; + u64 mbox_data; /* Clear the IRQ */ otx2_write64(vf, RVU_VF_INT, BIT_ULL(0)); + mbox_data = otx2_read64(vf, RVU_VF_VFPF_MBOX0); + /* Read latest mbox data */ smp_rmb(); - /* Check for PF => VF response messages */ - mbox = &vf->mbox.mbox; - mdev = &mbox->dev[0]; - otx2_sync_mbox_bbuf(mbox, 0); + if (mbox_data & MBOX_DOWN_MSG) { + mbox_data &= ~MBOX_DOWN_MSG; + otx2_write64(vf, RVU_VF_VFPF_MBOX0, mbox_data); + + /* Check for PF => VF response messages */ + mbox = &vf->mbox.mbox; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); - trace_otx2_msg_interrupt(mbox->pdev, "PF to VF", BIT_ULL(0)); + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(vf->mbox_wq, &vf->mbox.mbox_wrk); - hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (hdr->num_msgs) { - vf->mbox.num_msgs = hdr->num_msgs; - hdr->num_msgs = 0; - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), sizeof(u64))); - queue_work(vf->mbox_wq, &vf->mbox.mbox_wrk); + trace_otx2_msg_interrupt(mbox->pdev, "DOWN reply from PF to VF", + BIT_ULL(0)); } - /* Check for PF => VF notification messages */ - mbox = &vf->mbox.mbox_up; - mdev = &mbox->dev[0]; - otx2_sync_mbox_bbuf(mbox, 0); - hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); - if (hdr->num_msgs) { - vf->mbox.up_num_msgs = hdr->num_msgs; - hdr->num_msgs = 0; - memset(mbox->hwbase + mbox->rx_start, 0, - ALIGN(sizeof(struct mbox_hdr), sizeof(u64))); - queue_work(vf->mbox_wq, &vf->mbox.mbox_up_wrk); + if (mbox_data & MBOX_UP_MSG) { + mbox_data &= ~MBOX_UP_MSG; + otx2_write64(vf, RVU_VF_VFPF_MBOX0, mbox_data); + + /* Check for PF => VF notification messages */ + mbox = &vf->mbox.mbox_up; + mdev = &mbox->dev[0]; + otx2_sync_mbox_bbuf(mbox, 0); + + hdr = (struct mbox_hdr *)(mdev->mbase + mbox->rx_start); + if (hdr->num_msgs) + queue_work(vf->mbox_wq, &vf->mbox.mbox_up_wrk); + + trace_otx2_msg_interrupt(mbox->pdev, "UP message from PF to VF", + BIT_ULL(0)); } return IRQ_HANDLED; @@ -760,8 +775,8 @@ static void otx2vf_remove(struct pci_dev *pdev) otx2_mcam_flow_del(vf); otx2_shutdown_tc(vf); otx2_shutdown_qos(vf); - otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); + otx2vf_disable_mbox_intr(vf); free_percpu(vf->hw.lmt_info); if (test_bit(CN10K_LMTST, &vf->hw.cap_flag)) qmem_free(vf->dev, vf->dync_lmt); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c index 1e77bbf5d22a1..6cddb4da85b71 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c @@ -382,6 +382,7 @@ static void otx2_qos_read_txschq_cfg_tl(struct otx2_qos_node *parent, otx2_qos_read_txschq_cfg_tl(node, cfg); cnt = cfg->static_node_pos[node->level]; cfg->schq_contig_list[node->level][cnt] = node->schq; + cfg->schq_index_used[node->level][cnt] = true; cfg->schq_contig[node->level]++; cfg->static_node_pos[node->level]++; otx2_qos_read_txschq_cfg_schq(node, cfg); @@ -1406,7 +1407,10 @@ static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid, otx2_qos_read_txschq_cfg(pfvf, node, old_cfg); /* delete the txschq nodes allocated for this node */ + otx2_qos_disable_sq(pfvf, qid); + otx2_qos_free_hw_node_schq(pfvf, node); otx2_qos_free_sw_node_schq(pfvf, node); + pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; /* mark this node as htb inner node */ WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER); @@ -1553,6 +1557,7 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force dwrr_del_node = true; /* destroy the leaf node */ + otx2_qos_disable_sq(pfvf, qid); otx2_qos_destroy_node(pfvf, node); pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index de123350bd46b..41d9b0684be74 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -110,16 +110,16 @@ static const struct mtk_reg_map mt7986_reg_map = { .tx_irq_mask = 0x461c, .tx_irq_status = 0x4618, .pdma = { - .rx_ptr = 0x6100, - .rx_cnt_cfg = 0x6104, - .pcrx_ptr = 0x6108, - .glo_cfg = 0x6204, - .rst_idx = 0x6208, - .delay_irq = 0x620c, - .irq_status = 0x6220, - .irq_mask = 0x6228, - .adma_rx_dbg0 = 0x6238, - .int_grp = 0x6250, + .rx_ptr = 0x4100, + .rx_cnt_cfg = 0x4104, + .pcrx_ptr = 0x4108, + .glo_cfg = 0x4204, + .rst_idx = 0x4208, + .delay_irq = 0x420c, + .irq_status = 0x4220, + .irq_mask = 0x4228, + .adma_rx_dbg0 = 0x4238, + .int_grp = 0x4250, }, .qdma = { .qtx_cfg = 0x4400, @@ -677,8 +677,7 @@ static int mtk_mac_finish(struct phylink_config *config, unsigned int mode, mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); mcr_new = mcr_cur; mcr_new |= MAC_MCR_IPG_CFG | MAC_MCR_FORCE_MODE | - MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_LINK | - MAC_MCR_RX_FIFO_CLR_DIS; + MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_RX_FIFO_CLR_DIS; /* Only update control register when needed! */ if (mcr_new != mcr_cur) @@ -694,7 +693,7 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode, phylink_config); u32 mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); - mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN); + mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK); mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } @@ -803,7 +802,7 @@ static void mtk_mac_link_up(struct phylink_config *config, if (rx_pause) mcr |= MAC_MCR_FORCE_RX_FC; - mcr |= MAC_MCR_TX_EN | MAC_MCR_RX_EN; + mcr |= MAC_MCR_TX_EN | MAC_MCR_RX_EN | MAC_MCR_FORCE_LINK; mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } @@ -1108,7 +1107,7 @@ static bool mtk_rx_get_desc(struct mtk_eth *eth, struct mtk_rx_dma_v2 *rxd, rxd->rxd1 = READ_ONCE(dma_rxd->rxd1); rxd->rxd3 = READ_ONCE(dma_rxd->rxd3); rxd->rxd4 = READ_ONCE(dma_rxd->rxd4); - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { rxd->rxd5 = READ_ONCE(dma_rxd->rxd5); rxd->rxd6 = READ_ONCE(dma_rxd->rxd6); } @@ -1132,51 +1131,57 @@ static int mtk_init_fq_dma(struct mtk_eth *eth) { const struct mtk_soc_data *soc = eth->soc; dma_addr_t phy_ring_tail; - int cnt = MTK_QDMA_RING_SIZE; + int cnt = soc->tx.fq_dma_size; dma_addr_t dma_addr; - int i; + int i, j, len; if (MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM)) eth->scratch_ring = eth->sram_base; else eth->scratch_ring = dma_alloc_coherent(eth->dma_dev, - cnt * soc->txrx.txd_size, + cnt * soc->tx.desc_size, ð->phy_scratch_ring, GFP_KERNEL); + if (unlikely(!eth->scratch_ring)) return -ENOMEM; - eth->scratch_head = kcalloc(cnt, MTK_QDMA_PAGE_SIZE, GFP_KERNEL); - if (unlikely(!eth->scratch_head)) - return -ENOMEM; + phy_ring_tail = eth->phy_scratch_ring + soc->tx.desc_size * (cnt - 1); - dma_addr = dma_map_single(eth->dma_dev, - eth->scratch_head, cnt * MTK_QDMA_PAGE_SIZE, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(eth->dma_dev, dma_addr))) - return -ENOMEM; + for (j = 0; j < DIV_ROUND_UP(soc->tx.fq_dma_size, MTK_FQ_DMA_LENGTH); j++) { + len = min_t(int, cnt - j * MTK_FQ_DMA_LENGTH, MTK_FQ_DMA_LENGTH); + eth->scratch_head[j] = kcalloc(len, MTK_QDMA_PAGE_SIZE, GFP_KERNEL); - phy_ring_tail = eth->phy_scratch_ring + soc->txrx.txd_size * (cnt - 1); + if (unlikely(!eth->scratch_head[j])) + return -ENOMEM; - for (i = 0; i < cnt; i++) { - dma_addr_t addr = dma_addr + i * MTK_QDMA_PAGE_SIZE; - struct mtk_tx_dma_v2 *txd; + dma_addr = dma_map_single(eth->dma_dev, + eth->scratch_head[j], len * MTK_QDMA_PAGE_SIZE, + DMA_FROM_DEVICE); - txd = eth->scratch_ring + i * soc->txrx.txd_size; - txd->txd1 = addr; - if (i < cnt - 1) - txd->txd2 = eth->phy_scratch_ring + - (i + 1) * soc->txrx.txd_size; + if (unlikely(dma_mapping_error(eth->dma_dev, dma_addr))) + return -ENOMEM; - txd->txd3 = TX_DMA_PLEN0(MTK_QDMA_PAGE_SIZE); - if (MTK_HAS_CAPS(soc->caps, MTK_36BIT_DMA)) - txd->txd3 |= TX_DMA_PREP_ADDR64(addr); - txd->txd4 = 0; - if (mtk_is_netsys_v2_or_greater(eth)) { - txd->txd5 = 0; - txd->txd6 = 0; - txd->txd7 = 0; - txd->txd8 = 0; + for (i = 0; i < cnt; i++) { + struct mtk_tx_dma_v2 *txd; + + txd = eth->scratch_ring + (j * MTK_FQ_DMA_LENGTH + i) * soc->tx.desc_size; + txd->txd1 = dma_addr + i * MTK_QDMA_PAGE_SIZE; + if (j * MTK_FQ_DMA_LENGTH + i < cnt) + txd->txd2 = eth->phy_scratch_ring + + (j * MTK_FQ_DMA_LENGTH + i + 1) * soc->tx.desc_size; + + txd->txd3 = TX_DMA_PLEN0(MTK_QDMA_PAGE_SIZE); + if (MTK_HAS_CAPS(soc->caps, MTK_36BIT_DMA)) + txd->txd3 |= TX_DMA_PREP_ADDR64(dma_addr + i * MTK_QDMA_PAGE_SIZE); + + txd->txd4 = 0; + if (mtk_is_netsys_v2_or_greater(eth)) { + txd->txd5 = 0; + txd->txd6 = 0; + txd->txd7 = 0; + txd->txd8 = 0; + } } } @@ -1417,7 +1422,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, if (itxd == ring->last_free) return -ENOMEM; - itx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->txrx.txd_size); + itx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->tx.desc_size); memset(itx_buf, 0, sizeof(*itx_buf)); txd_info.addr = dma_map_single(eth->dma_dev, skb->data, txd_info.size, @@ -1458,7 +1463,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, memset(&txd_info, 0, sizeof(struct mtk_tx_dma_desc_info)); txd_info.size = min_t(unsigned int, frag_size, - soc->txrx.dma_max_len); + soc->tx.dma_max_len); txd_info.qid = queue; txd_info.last = i == skb_shinfo(skb)->nr_frags - 1 && !(frag_size - txd_info.size); @@ -1471,7 +1476,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, mtk_tx_set_dma_desc(dev, txd, &txd_info); tx_buf = mtk_desc_to_tx_buf(ring, txd, - soc->txrx.txd_size); + soc->tx.desc_size); if (new_desc) memset(tx_buf, 0, sizeof(*tx_buf)); tx_buf->data = (void *)MTK_DMA_DUMMY_DESC; @@ -1514,7 +1519,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, } else { int next_idx; - next_idx = NEXT_DESP_IDX(txd_to_idx(ring, txd, soc->txrx.txd_size), + next_idx = NEXT_DESP_IDX(txd_to_idx(ring, txd, soc->tx.desc_size), ring->dma_size); mtk_w32(eth, next_idx, MT7628_TX_CTX_IDX0); } @@ -1523,7 +1528,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, err_dma: do { - tx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->txrx.txd_size); + tx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->tx.desc_size); /* unmap dma */ mtk_tx_unmap(eth, tx_buf, NULL, false); @@ -1548,7 +1553,7 @@ static int mtk_cal_txd_req(struct mtk_eth *eth, struct sk_buff *skb) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; nfrags += DIV_ROUND_UP(skb_frag_size(frag), - eth->soc->txrx.dma_max_len); + eth->soc->tx.dma_max_len); } } else { nfrags += skb_shinfo(skb)->nr_frags; @@ -1655,7 +1660,7 @@ static struct mtk_rx_ring *mtk_get_rx_ring(struct mtk_eth *eth) ring = ð->rx_ring[i]; idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size); - rxd = ring->dma + idx * eth->soc->txrx.rxd_size; + rxd = ring->dma + idx * eth->soc->rx.desc_size; if (rxd->rxd2 & RX_DMA_DONE) { ring->calc_idx_update = true; return ring; @@ -1823,7 +1828,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, } htxd = txd; - tx_buf = mtk_desc_to_tx_buf(ring, txd, soc->txrx.txd_size); + tx_buf = mtk_desc_to_tx_buf(ring, txd, soc->tx.desc_size); memset(tx_buf, 0, sizeof(*tx_buf)); htx_buf = tx_buf; @@ -1842,7 +1847,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, goto unmap; tx_buf = mtk_desc_to_tx_buf(ring, txd, - soc->txrx.txd_size); + soc->tx.desc_size); memset(tx_buf, 0, sizeof(*tx_buf)); n_desc++; } @@ -1880,7 +1885,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, } else { int idx; - idx = txd_to_idx(ring, txd, soc->txrx.txd_size); + idx = txd_to_idx(ring, txd, soc->tx.desc_size); mtk_w32(eth, NEXT_DESP_IDX(idx, ring->dma_size), MT7628_TX_CTX_IDX0); } @@ -1891,7 +1896,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, unmap: while (htxd != txd) { - tx_buf = mtk_desc_to_tx_buf(ring, htxd, soc->txrx.txd_size); + tx_buf = mtk_desc_to_tx_buf(ring, htxd, soc->tx.desc_size); mtk_tx_unmap(eth, tx_buf, NULL, false); htxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; @@ -2022,14 +2027,14 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, goto rx_done; idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size); - rxd = ring->dma + idx * eth->soc->txrx.rxd_size; + rxd = ring->dma + idx * eth->soc->rx.desc_size; data = ring->data[idx]; if (!mtk_rx_get_desc(eth, &trxd, rxd)) break; /* find out which mac the packet come from. values start at 1 */ - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { u32 val = RX_DMA_GET_SPORT_V2(trxd.rxd5); switch (val) { @@ -2141,7 +2146,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, skb->dev = netdev; bytes += skb->len; - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { reason = FIELD_GET(MTK_RXD5_PPE_CPU_REASON, trxd.rxd5); hash = trxd.rxd5 & MTK_RXD5_FOE_ENTRY; if (hash != MTK_RXD5_FOE_ENTRY) @@ -2157,7 +2162,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, rxdcsum = &trxd.rxd4; } - if (*rxdcsum & eth->soc->txrx.rx_dma_l4_valid) + if (*rxdcsum & eth->soc->rx.dma_l4_valid) skb->ip_summed = CHECKSUM_UNNECESSARY; else skb_checksum_none_assert(skb); @@ -2281,7 +2286,7 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget, break; tx_buf = mtk_desc_to_tx_buf(ring, desc, - eth->soc->txrx.txd_size); + eth->soc->tx.desc_size); if (!tx_buf->data) break; @@ -2332,7 +2337,7 @@ static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget, } mtk_tx_unmap(eth, tx_buf, &bq, true); - desc = ring->dma + cpu * eth->soc->txrx.txd_size; + desc = ring->dma + cpu * eth->soc->tx.desc_size; ring->last_free = desc; atomic_inc(&ring->free_count); @@ -2422,7 +2427,7 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget) do { int rx_done; - mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, + mtk_w32(eth, eth->soc->rx.irq_done_mask, reg_map->pdma.irq_status); rx_done = mtk_poll_rx(napi, budget - rx_done_total, eth); rx_done_total += rx_done; @@ -2438,10 +2443,10 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget) return budget; } while (mtk_r32(eth, reg_map->pdma.irq_status) & - eth->soc->txrx.rx_irq_done_mask); + eth->soc->rx.irq_done_mask); if (napi_complete_done(napi, rx_done_total)) - mtk_rx_irq_enable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_enable(eth, eth->soc->rx.irq_done_mask); return rx_done_total; } @@ -2450,7 +2455,7 @@ static int mtk_tx_alloc(struct mtk_eth *eth) { const struct mtk_soc_data *soc = eth->soc; struct mtk_tx_ring *ring = ð->tx_ring; - int i, sz = soc->txrx.txd_size; + int i, sz = soc->tx.desc_size; struct mtk_tx_dma_v2 *txd; int ring_size; u32 ofs, val; @@ -2458,7 +2463,7 @@ static int mtk_tx_alloc(struct mtk_eth *eth) if (MTK_HAS_CAPS(soc->caps, MTK_QDMA)) ring_size = MTK_QDMA_RING_SIZE; else - ring_size = MTK_DMA_SIZE; + ring_size = soc->tx.dma_size; ring->buf = kcalloc(ring_size, sizeof(*ring->buf), GFP_KERNEL); @@ -2466,8 +2471,8 @@ static int mtk_tx_alloc(struct mtk_eth *eth) goto no_tx_mem; if (MTK_HAS_CAPS(soc->caps, MTK_SRAM)) { - ring->dma = eth->sram_base + ring_size * sz; - ring->phys = eth->phy_scratch_ring + ring_size * (dma_addr_t)sz; + ring->dma = eth->sram_base + soc->tx.fq_dma_size * sz; + ring->phys = eth->phy_scratch_ring + soc->tx.fq_dma_size * (dma_addr_t)sz; } else { ring->dma = dma_alloc_coherent(eth->dma_dev, ring_size * sz, &ring->phys, GFP_KERNEL); @@ -2573,14 +2578,14 @@ static void mtk_tx_clean(struct mtk_eth *eth) } if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && ring->dma) { dma_free_coherent(eth->dma_dev, - ring->dma_size * soc->txrx.txd_size, + ring->dma_size * soc->tx.desc_size, ring->dma, ring->phys); ring->dma = NULL; } if (ring->dma_pdma) { dma_free_coherent(eth->dma_dev, - ring->dma_size * soc->txrx.txd_size, + ring->dma_size * soc->tx.desc_size, ring->dma_pdma, ring->phys_pdma); ring->dma_pdma = NULL; } @@ -2589,6 +2594,7 @@ static void mtk_tx_clean(struct mtk_eth *eth) static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) { const struct mtk_reg_map *reg_map = eth->soc->reg_map; + const struct mtk_soc_data *soc = eth->soc; struct mtk_rx_ring *ring; int rx_data_len, rx_dma_size, tx_ring_size; int i; @@ -2596,7 +2602,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) tx_ring_size = MTK_QDMA_RING_SIZE; else - tx_ring_size = MTK_DMA_SIZE; + tx_ring_size = soc->tx.dma_size; if (rx_flag == MTK_RX_FLAGS_QDMA) { if (ring_no) @@ -2611,7 +2617,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) rx_dma_size = MTK_HW_LRO_DMA_SIZE; } else { rx_data_len = ETH_DATA_LEN; - rx_dma_size = MTK_DMA_SIZE; + rx_dma_size = soc->rx.dma_size; } ring->frag_size = mtk_max_frag_size(rx_data_len); @@ -2635,15 +2641,15 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM) || rx_flag != MTK_RX_FLAGS_NORMAL) { ring->dma = dma_alloc_coherent(eth->dma_dev, - rx_dma_size * eth->soc->txrx.rxd_size, - &ring->phys, GFP_KERNEL); + rx_dma_size * eth->soc->rx.desc_size, + &ring->phys, GFP_KERNEL); } else { struct mtk_tx_ring *tx_ring = ð->tx_ring; ring->dma = tx_ring->dma + tx_ring_size * - eth->soc->txrx.txd_size * (ring_no + 1); + eth->soc->tx.desc_size * (ring_no + 1); ring->phys = tx_ring->phys + tx_ring_size * - eth->soc->txrx.txd_size * (ring_no + 1); + eth->soc->tx.desc_size * (ring_no + 1); } if (!ring->dma) @@ -2654,7 +2660,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) dma_addr_t dma_addr; void *data; - rxd = ring->dma + i * eth->soc->txrx.rxd_size; + rxd = ring->dma + i * eth->soc->rx.desc_size; if (ring->page_pool) { data = mtk_page_pool_get_buff(ring->page_pool, &dma_addr, GFP_KERNEL); @@ -2691,7 +2697,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) rxd->rxd3 = 0; rxd->rxd4 = 0; - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { rxd->rxd5 = 0; rxd->rxd6 = 0; rxd->rxd7 = 0; @@ -2745,7 +2751,7 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_ if (!ring->data[i]) continue; - rxd = ring->dma + i * eth->soc->txrx.rxd_size; + rxd = ring->dma + i * eth->soc->rx.desc_size; if (!rxd->rxd1) continue; @@ -2762,7 +2768,7 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_ if (!in_sram && ring->dma) { dma_free_coherent(eth->dma_dev, - ring->dma_size * eth->soc->txrx.rxd_size, + ring->dma_size * eth->soc->rx.desc_size, ring->dma, ring->phys); ring->dma = NULL; } @@ -3125,7 +3131,7 @@ static void mtk_dma_free(struct mtk_eth *eth) netdev_reset_queue(eth->netdev[i]); if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) { dma_free_coherent(eth->dma_dev, - MTK_QDMA_RING_SIZE * soc->txrx.txd_size, + MTK_QDMA_RING_SIZE * soc->tx.desc_size, eth->scratch_ring, eth->phy_scratch_ring); eth->scratch_ring = NULL; eth->phy_scratch_ring = 0; @@ -3140,7 +3146,10 @@ static void mtk_dma_free(struct mtk_eth *eth) mtk_rx_clean(eth, ð->rx_ring[i], false); } - kfree(eth->scratch_head); + for (i = 0; i < DIV_ROUND_UP(soc->tx.fq_dma_size, MTK_FQ_DMA_LENGTH); i++) { + kfree(eth->scratch_head[i]); + eth->scratch_head[i] = NULL; + } } static bool mtk_hw_reset_check(struct mtk_eth *eth) @@ -3175,7 +3184,7 @@ static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth) eth->rx_events++; if (likely(napi_schedule_prep(ð->rx_napi))) { - mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask); __napi_schedule(ð->rx_napi); } @@ -3201,9 +3210,9 @@ static irqreturn_t mtk_handle_irq(int irq, void *_eth) const struct mtk_reg_map *reg_map = eth->soc->reg_map; if (mtk_r32(eth, reg_map->pdma.irq_mask) & - eth->soc->txrx.rx_irq_done_mask) { + eth->soc->rx.irq_done_mask) { if (mtk_r32(eth, reg_map->pdma.irq_status) & - eth->soc->txrx.rx_irq_done_mask) + eth->soc->rx.irq_done_mask) mtk_handle_irq_rx(irq, _eth); } if (mtk_r32(eth, reg_map->tx_irq_mask) & MTK_TX_DONE_INT) { @@ -3221,10 +3230,10 @@ static void mtk_poll_controller(struct net_device *dev) struct mtk_eth *eth = mac->hw; mtk_tx_irq_disable(eth, MTK_TX_DONE_INT); - mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask); mtk_handle_irq_rx(eth->irq[2], dev); mtk_tx_irq_enable(eth, MTK_TX_DONE_INT); - mtk_rx_irq_enable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_enable(eth, eth->soc->rx.irq_done_mask); } #endif @@ -3388,7 +3397,7 @@ static int mtk_open(struct net_device *dev) napi_enable(ð->tx_napi); napi_enable(ð->rx_napi); mtk_tx_irq_enable(eth, MTK_TX_DONE_INT); - mtk_rx_irq_enable(eth, soc->txrx.rx_irq_done_mask); + mtk_rx_irq_enable(eth, soc->rx.irq_done_mask); refcount_set(ð->dma_refcnt, 1); } else @@ -3472,7 +3481,7 @@ static int mtk_stop(struct net_device *dev) mtk_gdm_config(eth, MTK_GDMA_DROP_ALL); mtk_tx_irq_disable(eth, MTK_TX_DONE_INT); - mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask); napi_disable(ð->tx_napi); napi_disable(ð->rx_napi); @@ -3894,7 +3903,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) else mtk_hw_reset(eth); - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { /* Set FE to PDMAv2 if necessary */ val = mtk_r32(eth, MTK_FE_GLO_MISC); mtk_w32(eth, val | BIT(4), MTK_FE_GLO_MISC); @@ -3948,9 +3957,9 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) /* FE int grouping */ mtk_w32(eth, MTK_TX_DONE_INT, reg_map->pdma.int_grp); - mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, reg_map->pdma.int_grp + 4); + mtk_w32(eth, eth->soc->rx.irq_done_mask, reg_map->pdma.int_grp + 4); mtk_w32(eth, MTK_TX_DONE_INT, reg_map->qdma.int_grp); - mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, reg_map->qdma.int_grp + 4); + mtk_w32(eth, eth->soc->rx.irq_done_mask, reg_map->qdma.int_grp + 4); mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP); if (mtk_is_netsys_v3_or_greater(eth)) { @@ -5040,11 +5049,18 @@ static const struct mtk_soc_data mt2701_data = { .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, .version = 1, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), + .fq_dma_size = MTK_DMA_SIZE(2K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, + .dma_size = MTK_DMA_SIZE(2K), .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5060,11 +5076,18 @@ static const struct mtk_soc_data mt7621_data = { .offload_version = 1, .hash_offset = 2, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), + .fq_dma_size = MTK_DMA_SIZE(2K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, + .dma_size = MTK_DMA_SIZE(2K), .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5082,11 +5105,18 @@ static const struct mtk_soc_data mt7622_data = { .hash_offset = 2, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), + .fq_dma_size = MTK_DMA_SIZE(2K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, + .dma_size = MTK_DMA_SIZE(2K), .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5103,11 +5133,18 @@ static const struct mtk_soc_data mt7623_data = { .hash_offset = 2, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, .disable_pll_modes = true, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), + .fq_dma_size = MTK_DMA_SIZE(2K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, + .dma_size = MTK_DMA_SIZE(2K), .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5122,11 +5159,18 @@ static const struct mtk_soc_data mt7629_data = { .required_pctl = false, .has_accounting = true, .version = 1, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), + .fq_dma_size = MTK_DMA_SIZE(2K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, + .dma_size = MTK_DMA_SIZE(2K), .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5144,13 +5188,20 @@ static const struct mtk_soc_data mt7981_data = { .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V2_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma_v2), - .rxd_size = sizeof(struct mtk_rx_dma_v2), - .rx_irq_done_mask = MTK_RX_DONE_INT_V2, - .rx_dma_l4_valid = RX_DMA_L4_VALID_V2, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma_v2), .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, .dma_len_offset = 8, + .dma_size = MTK_DMA_SIZE(2K), + .fq_dma_size = MTK_DMA_SIZE(2K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID_V2, + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), }, }; @@ -5166,13 +5217,20 @@ static const struct mtk_soc_data mt7986_data = { .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V2_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma_v2), - .rxd_size = sizeof(struct mtk_rx_dma_v2), - .rx_irq_done_mask = MTK_RX_DONE_INT_V2, - .rx_dma_l4_valid = RX_DMA_L4_VALID_V2, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma_v2), .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, .dma_len_offset = 8, + .dma_size = MTK_DMA_SIZE(2K), + .fq_dma_size = MTK_DMA_SIZE(2K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID_V2, + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), }, }; @@ -5188,13 +5246,20 @@ static const struct mtk_soc_data mt7988_data = { .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V3_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma_v2), - .rxd_size = sizeof(struct mtk_rx_dma_v2), - .rx_irq_done_mask = MTK_RX_DONE_INT_V2, - .rx_dma_l4_valid = RX_DMA_L4_VALID_V2, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma_v2), .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, .dma_len_offset = 8, + .dma_size = MTK_DMA_SIZE(2K), + .fq_dma_size = MTK_DMA_SIZE(4K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma_v2), + .irq_done_mask = MTK_RX_DONE_INT_V2, + .dma_l4_valid = RX_DMA_L4_VALID_V2, + .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, + .dma_len_offset = 8, + .dma_size = MTK_DMA_SIZE(2K), }, }; @@ -5205,13 +5270,19 @@ static const struct mtk_soc_data rt5350_data = { .required_clks = MT7628_CLKS_BITMAP, .required_pctl = false, .version = 1, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID_PDMA, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID_PDMA, .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, + .dma_size = MTK_DMA_SIZE(2K), }, }; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 9ae3b8a71d0e6..a25c33b9a4f34 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -32,7 +32,9 @@ #define MTK_TX_DMA_BUF_LEN 0x3fff #define MTK_TX_DMA_BUF_LEN_V2 0xffff #define MTK_QDMA_RING_SIZE 2048 -#define MTK_DMA_SIZE 512 +#define MTK_DMA_SIZE(x) (SZ_##x) +#define MTK_FQ_DMA_HEAD 32 +#define MTK_FQ_DMA_LENGTH 2048 #define MTK_RX_ETH_HLEN (ETH_HLEN + ETH_FCS_LEN) #define MTK_RX_HLEN (NET_SKB_PAD + MTK_RX_ETH_HLEN + NET_IP_ALIGN) #define MTK_DMA_DUMMY_DESC 0xffffffff @@ -327,8 +329,8 @@ /* QDMA descriptor txd3 */ #define TX_DMA_OWNER_CPU BIT(31) #define TX_DMA_LS0 BIT(30) -#define TX_DMA_PLEN0(x) (((x) & eth->soc->txrx.dma_max_len) << eth->soc->txrx.dma_len_offset) -#define TX_DMA_PLEN1(x) ((x) & eth->soc->txrx.dma_max_len) +#define TX_DMA_PLEN0(x) (((x) & eth->soc->tx.dma_max_len) << eth->soc->tx.dma_len_offset) +#define TX_DMA_PLEN1(x) ((x) & eth->soc->tx.dma_max_len) #define TX_DMA_SWC BIT(14) #define TX_DMA_PQID GENMASK(3, 0) #define TX_DMA_ADDR64_MASK GENMASK(3, 0) @@ -348,8 +350,8 @@ /* QDMA descriptor rxd2 */ #define RX_DMA_DONE BIT(31) #define RX_DMA_LSO BIT(30) -#define RX_DMA_PREP_PLEN0(x) (((x) & eth->soc->txrx.dma_max_len) << eth->soc->txrx.dma_len_offset) -#define RX_DMA_GET_PLEN0(x) (((x) >> eth->soc->txrx.dma_len_offset) & eth->soc->txrx.dma_max_len) +#define RX_DMA_PREP_PLEN0(x) (((x) & eth->soc->rx.dma_max_len) << eth->soc->rx.dma_len_offset) +#define RX_DMA_GET_PLEN0(x) (((x) >> eth->soc->rx.dma_len_offset) & eth->soc->rx.dma_max_len) #define RX_DMA_VTAG BIT(15) #define RX_DMA_ADDR64_MASK GENMASK(3, 0) #if IS_ENABLED(CONFIG_64BIT) @@ -1153,10 +1155,9 @@ struct mtk_reg_map { * @foe_entry_size Foe table entry size. * @has_accounting Bool indicating support for accounting of * offloaded flows. - * @txd_size Tx DMA descriptor size. - * @rxd_size Rx DMA descriptor size. - * @rx_irq_done_mask Rx irq done register mask. - * @rx_dma_l4_valid Rx DMA valid register mask. + * @desc_size Tx/Rx DMA descriptor size. + * @irq_done_mask Rx irq done register mask. + * @dma_l4_valid Rx DMA valid register mask. * @dma_max_len Max DMA tx/rx buffer length. * @dma_len_offset Tx/Rx DMA length field offset. */ @@ -1174,13 +1175,20 @@ struct mtk_soc_data { bool has_accounting; bool disable_pll_modes; struct { - u32 txd_size; - u32 rxd_size; - u32 rx_irq_done_mask; - u32 rx_dma_l4_valid; + u32 desc_size; u32 dma_max_len; u32 dma_len_offset; - } txrx; + u32 dma_size; + u32 fq_dma_size; + } tx; + struct { + u32 desc_size; + u32 irq_done_mask; + u32 dma_l4_valid; + u32 dma_max_len; + u32 dma_len_offset; + u32 dma_size; + } rx; }; #define MTK_DMA_MONITOR_TIMEOUT msecs_to_jiffies(1000) @@ -1261,7 +1269,7 @@ struct mtk_eth { struct napi_struct rx_napi; void *scratch_ring; dma_addr_t phy_scratch_ring; - void *scratch_head; + void *scratch_head[MTK_FQ_DMA_HEAD]; struct clk *clks[MTK_CLK_MAX]; struct mii_bus *mii_bus; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index b2a5d9c3733d4..6ce0db3a1a920 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -994,7 +994,7 @@ void mtk_ppe_start(struct mtk_ppe *ppe) MTK_PPE_KEEPALIVE_DISABLE) | FIELD_PREP(MTK_PPE_TB_CFG_HASH_MODE, 1) | FIELD_PREP(MTK_PPE_TB_CFG_SCAN_MODE, - MTK_PPE_SCAN_MODE_KEEPALIVE_AGE) | + MTK_PPE_SCAN_MODE_CHECK_AGE) | FIELD_PREP(MTK_PPE_TB_CFG_ENTRY_NUM, MTK_PPE_ENTRIES_SHIFT); if (mtk_is_netsys_v2_or_greater(ppe->eth)) @@ -1090,17 +1090,21 @@ int mtk_ppe_stop(struct mtk_ppe *ppe) mtk_ppe_cache_enable(ppe, false); - /* disable offload engine */ - ppe_clear(ppe, MTK_PPE_GLO_CFG, MTK_PPE_GLO_CFG_EN); - ppe_w32(ppe, MTK_PPE_FLOW_CFG, 0); - /* disable aging */ val = MTK_PPE_TB_CFG_AGE_NON_L4 | MTK_PPE_TB_CFG_AGE_UNBIND | MTK_PPE_TB_CFG_AGE_TCP | MTK_PPE_TB_CFG_AGE_UDP | - MTK_PPE_TB_CFG_AGE_TCP_FIN; + MTK_PPE_TB_CFG_AGE_TCP_FIN | + MTK_PPE_TB_CFG_SCAN_MODE; ppe_clear(ppe, MTK_PPE_TB_CFG, val); - return mtk_ppe_wait_busy(ppe); + if (mtk_ppe_wait_busy(ppe)) + return -ETIMEDOUT; + + /* disable offload engine */ + ppe_clear(ppe, MTK_PPE_GLO_CFG, MTK_PPE_GLO_CFG_EN); + ppe_w32(ppe, MTK_PPE_FLOW_CFG, 0); + + return 0; } diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index c895e265ae0eb..61334a71058c7 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1074,13 +1074,13 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) static void mtk_wed_stop(struct mtk_wed_device *dev) { + mtk_wed_dma_disable(dev); mtk_wed_set_ext_int(dev, false); wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER, 0); wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, 0); wdma_w32(dev, MTK_WDMA_INT_MASK, 0); wdma_w32(dev, MTK_WDMA_INT_GRP2, 0); - wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0); if (!mtk_wed_get_rx_capa(dev)) return; @@ -1093,7 +1093,6 @@ static void mtk_wed_deinit(struct mtk_wed_device *dev) { mtk_wed_stop(dev); - mtk_wed_dma_disable(dev); wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WDMA_INT_AGENT_EN | @@ -2605,9 +2604,6 @@ mtk_wed_irq_get(struct mtk_wed_device *dev, u32 mask) static void mtk_wed_irq_set_mask(struct mtk_wed_device *dev, u32 mask) { - if (!dev->running) - return; - mtk_wed_set_ext_int(dev, !!mask); wed_w32(dev, MTK_WED_INT_MASK, mask); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 4957412ff1f65..20768ef2e9d2b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -969,19 +969,32 @@ static void cmd_work_handler(struct work_struct *work) bool poll_cmd = ent->polling; struct mlx5_cmd_layout *lay; struct mlx5_core_dev *dev; - unsigned long cb_timeout; - struct semaphore *sem; + unsigned long timeout; unsigned long flags; int alloc_ret; int cmd_mode; + complete(&ent->handling); + dev = container_of(cmd, struct mlx5_core_dev, cmd); - cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); + timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); - complete(&ent->handling); - sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem; - down(sem); if (!ent->page_queue) { + if (down_timeout(&cmd->vars.sem, timeout)) { + mlx5_core_warn(dev, "%s(0x%x) timed out while waiting for a slot.\n", + mlx5_command_str(ent->op), ent->op); + if (ent->callback) { + ent->callback(-EBUSY, ent->context); + mlx5_free_cmd_msg(dev, ent->out); + free_msg(dev, ent->in); + cmd_ent_put(ent); + } else { + ent->ret = -EBUSY; + complete(&ent->done); + } + complete(&ent->slotted); + return; + } alloc_ret = cmd_alloc_index(cmd, ent); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); @@ -994,10 +1007,11 @@ static void cmd_work_handler(struct work_struct *work) ent->ret = -EAGAIN; complete(&ent->done); } - up(sem); + up(&cmd->vars.sem); return; } } else { + down(&cmd->vars.pages_sem); ent->idx = cmd->vars.max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); clear_bit(ent->idx, &cmd->vars.bitmask); @@ -1005,6 +1019,8 @@ static void cmd_work_handler(struct work_struct *work) spin_unlock_irqrestore(&cmd->alloc_lock, flags); } + complete(&ent->slotted); + lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); @@ -1023,7 +1039,7 @@ static void cmd_work_handler(struct work_struct *work) ent->ts1 = ktime_get_ns(); cmd_mode = cmd->mode; - if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, cb_timeout)) + if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, timeout)) cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); @@ -1143,6 +1159,9 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) ent->ret = -ECANCELED; goto out_err; } + + wait_for_completion(&ent->slotted); + if (cmd->mode == CMD_MODE_POLLING || ent->polling) wait_for_completion(&ent->done); else if (!wait_for_completion_timeout(&ent->done, timeout)) @@ -1157,6 +1176,9 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) } else if (err == -ECANCELED) { mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n", mlx5_command_str(ent->op), ent->op); + } else if (err == -EBUSY) { + mlx5_core_warn(dev, "%s(0x%x) timeout while waiting for command semaphore.\n", + mlx5_command_str(ent->op), ent->op); } mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n", err, deliv_status_to_str(ent->status), ent->status); @@ -1208,6 +1230,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, ent->polling = force_polling; init_completion(&ent->handling); + init_completion(&ent->slotted); if (!callback) init_completion(&ent->done); @@ -1225,7 +1248,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, return 0; /* mlx5_cmd_comp_handler() will put(ent) */ err = wait_func(dev, ent); - if (err == -ETIMEDOUT || err == -ECANCELED) + if (err == -ETIMEDOUT || err == -ECANCELED || err == -EBUSY) goto out_free; ds = ent->ts2 - ent->ts1; @@ -1611,6 +1634,9 @@ static int cmd_comp_notifier(struct notifier_block *nb, dev = container_of(cmd, struct mlx5_core_dev, cmd); eqe = data; + if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + return NOTIFY_DONE; + mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false); return NOTIFY_OK; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index 86f1854698b4e..883c044852f1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -95,9 +95,15 @@ static inline void mlx5e_ptp_metadata_fifo_push(struct mlx5e_ptp_metadata_fifo * } static inline u8 +mlx5e_ptp_metadata_fifo_peek(struct mlx5e_ptp_metadata_fifo *fifo) +{ + return fifo->data[fifo->mask & fifo->cc]; +} + +static inline void mlx5e_ptp_metadata_fifo_pop(struct mlx5e_ptp_metadata_fifo *fifo) { - return fifo->data[fifo->mask & fifo->cc++]; + fifo->cc++; } static inline void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 34adf8c3f81a0..922bc5b7c10e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -83,24 +83,25 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs, txq_ix = mlx5e_qid_from_qos(chs, node_qid); - WARN_ON(node_qid > priv->htb_max_qos_sqs); - if (node_qid == priv->htb_max_qos_sqs) { - struct mlx5e_sq_stats *stats, **stats_list = NULL; - - if (priv->htb_max_qos_sqs == 0) { - stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev), - sizeof(*stats_list), - GFP_KERNEL); - if (!stats_list) - return -ENOMEM; - } + WARN_ON(node_qid >= mlx5e_htb_cur_leaf_nodes(priv->htb)); + if (!priv->htb_qos_sq_stats) { + struct mlx5e_sq_stats **stats_list; + + stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev), + sizeof(*stats_list), GFP_KERNEL); + if (!stats_list) + return -ENOMEM; + + WRITE_ONCE(priv->htb_qos_sq_stats, stats_list); + } + + if (!priv->htb_qos_sq_stats[node_qid]) { + struct mlx5e_sq_stats *stats; + stats = kzalloc(sizeof(*stats), GFP_KERNEL); - if (!stats) { - kvfree(stats_list); + if (!stats) return -ENOMEM; - } - if (stats_list) - WRITE_ONCE(priv->htb_qos_sq_stats, stats_list); + WRITE_ONCE(priv->htb_qos_sq_stats[node_qid], stats); /* Order htb_max_qos_sqs increment after writing the array pointer. * Pairs with smp_load_acquire in en_stats.c. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c index f675b1926340f..f66bbc8464645 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c @@ -57,6 +57,7 @@ int mlx5e_selq_init(struct mlx5e_selq *selq, struct mutex *state_lock) void mlx5e_selq_cleanup(struct mlx5e_selq *selq) { + mutex_lock(selq->state_lock); WARN_ON_ONCE(selq->is_prepared); kvfree(selq->standby); @@ -67,6 +68,7 @@ void mlx5e_selq_cleanup(struct mlx5e_selq *selq) kvfree(selq->standby); selq->standby = NULL; + mutex_unlock(selq->state_lock); } void mlx5e_selq_prepare_params(struct mlx5e_selq *selq, struct mlx5e_params *params) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 82e6abbc17342..c969b8e709804 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -28,8 +28,10 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5_core_dev *mdev) { - /* AF_XDP doesn't support frames larger than PAGE_SIZE. */ - if (xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) { + /* AF_XDP doesn't support frames larger than PAGE_SIZE, + * and xsk->chunk_size is limited to 65535 bytes. + */ + if ((size_t)xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) { mlx5_core_err(mdev, "XSK chunk size %u out of bounds [%u, %lu]\n", xsk->chunk_size, MLX5E_MIN_XSK_CHUNK_SIZE, PAGE_SIZE); return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h index caa34b9c161e5..33e32584b07f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -102,8 +102,14 @@ static inline void mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb) { int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr); + struct udphdr *udphdr; - udp_hdr(skb)->len = htons(payload_len); + if (skb->encapsulation) + udphdr = (struct udphdr *)skb_inner_transport_header(skb); + else + udphdr = udp_hdr(skb); + + udphdr->len = htons(payload_len); } struct mlx5e_accel_tx_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 41a2543a52cda..e51b03d4c717f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -750,8 +750,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, err_fs_ft: if (rx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); - mlx5_del_flow_rules(rx->status.rule); - mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); + mlx5_ipsec_rx_status_destroy(ipsec, rx); err_add: mlx5_destroy_flow_table(rx->ft.status); err_fs_ft_status: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 2ed99772f168a..e1a241d3b418c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -98,18 +98,11 @@ mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features) if (!x || !x->xso.offload_handle) goto out_disable; - if (xo->inner_ipproto) { - /* Cannot support tunnel packet over IPsec tunnel mode - * because we cannot offload three IP header csum - */ - if (x->props.mode == XFRM_MODE_TUNNEL) - goto out_disable; - - /* Only support UDP or TCP L4 checksum */ - if (xo->inner_ipproto != IPPROTO_UDP && - xo->inner_ipproto != IPPROTO_TCP) - goto out_disable; - } + /* Only support UDP or TCP L4 checksum */ + if (xo->inner_ipproto && + xo->inner_ipproto != IPPROTO_UDP && + xo->inner_ipproto != IPPROTO_TCP) + goto out_disable; return features; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index b2cabd6ab86cb..cc9bcc4200324 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -1640,6 +1640,7 @@ static const struct macsec_ops macsec_offload_ops = { .mdo_add_secy = mlx5e_macsec_add_secy, .mdo_upd_secy = mlx5e_macsec_upd_secy, .mdo_del_secy = mlx5e_macsec_del_secy, + .rx_uses_md_dst = true, }; bool mlx5e_macsec_handle_tx_skb(struct mlx5e_macsec *macsec, struct sk_buff *skb) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index e66f486faafe1..415fec7763bd2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -45,6 +45,10 @@ struct arfs_table { struct hlist_head rules_hash[ARFS_HASH_SIZE]; }; +enum { + MLX5E_ARFS_STATE_ENABLED, +}; + enum arfs_type { ARFS_IPV4_TCP, ARFS_IPV6_TCP, @@ -59,6 +63,7 @@ struct mlx5e_arfs_tables { spinlock_t arfs_lock; int last_filter_id; struct workqueue_struct *wq; + unsigned long state; }; struct arfs_tuple { @@ -169,6 +174,8 @@ int mlx5e_arfs_enable(struct mlx5e_flow_steering *fs) return err; } } + set_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + return 0; } @@ -454,6 +461,8 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs) int i; int j; + clear_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + spin_lock_bh(&arfs->arfs_lock); mlx5e_for_each_arfs_rule(rule, htmp, arfs->arfs_tables, i, j) { hlist_del_init(&rule->hlist); @@ -626,17 +635,8 @@ static void arfs_handle_work(struct work_struct *work) struct mlx5_flow_handle *rule; arfs = mlx5e_fs_get_arfs(priv->fs); - mutex_lock(&priv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - spin_lock_bh(&arfs->arfs_lock); - hlist_del(&arfs_rule->hlist); - spin_unlock_bh(&arfs->arfs_lock); - - mutex_unlock(&priv->state_lock); - kfree(arfs_rule); - goto out; - } - mutex_unlock(&priv->state_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) + return; if (!arfs_rule->rule) { rule = arfs_add_rule(priv, arfs_rule); @@ -752,6 +752,11 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, return -EPROTONOSUPPORT; spin_lock_bh(&arfs->arfs_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) { + spin_unlock_bh(&arfs->arfs_lock); + return -EPERM; + } + arfs_rule = arfs_find_rule(arfs_t, &fk); if (arfs_rule) { if (arfs_rule->rxq == rxq_index || work_busy(&arfs_rule->arfs_work)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index cc51ce16df14a..93461b0c5703b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -451,6 +451,23 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, mutex_lock(&priv->state_lock); + /* If RXFH is configured, changing the channels number is allowed only if + * it does not require resizing the RSS table. This is because the previous + * configuration may no longer be compatible with the new RSS table. + */ + if (netif_is_rxfh_configured(priv->netdev)) { + int cur_rqt_size = mlx5e_rqt_size(priv->mdev, cur_params->num_channels); + int new_rqt_size = mlx5e_rqt_size(priv->mdev, count); + + if (new_rqt_size != cur_rqt_size) { + err = -EINVAL; + netdev_err(priv->netdev, + "%s: RXFH is configured, block changing channels number that affects RSS table size (new: %d, current: %d)\n", + __func__, new_rqt_size, cur_rqt_size); + goto out; + } + } + /* Don't allow changing the number of channels if HTB offload is active, * because the numeration of the QoS SQs will change, while per-queue * qdiscs are attached. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c8e8f512803ef..07a9f2b251638 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3769,7 +3769,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) mlx5e_fold_sw_stats64(priv, stats); } - stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer; + stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer; stats->rx_length_errors = PPORT_802_3_GET(pstats, a_in_range_length_errors) + @@ -4717,7 +4717,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, /* Verify if UDP port is being offloaded by HW */ if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port)) - return features; + return vxlan_features_check(skb, features); #if IS_ENABLED(CONFIG_GENEVE) /* Support Geneve offload for default UDP port */ @@ -4743,7 +4743,6 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, struct mlx5e_priv *priv = netdev_priv(netdev); features = vlan_features_check(skb, features); - features = vxlan_features_check(skb, features); /* Validate if the tunneled packet is being offloaded by HW */ if (skb->encapsulation && @@ -5695,9 +5694,7 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) kfree(priv->tx_rates); kfree(priv->txq2sq); destroy_workqueue(priv->wq); - mutex_lock(&priv->state_lock); mlx5e_selq_cleanup(&priv->selq); - mutex_unlock(&priv->state_lock); free_cpumask_var(priv->scratchpad.cpumask); for (i = 0; i < priv->htb_max_qos_sqs; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 2fa076b23fbea..0964b16ca5619 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -153,7 +153,11 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb, int *hopbyhop) *hopbyhop = 0; if (skb->encapsulation) { - ihs = skb_inner_tcp_all_headers(skb); + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + ihs = skb_inner_transport_offset(skb) + + sizeof(struct udphdr); + else + ihs = skb_inner_tcp_all_headers(skb); stats->tso_inner_packets++; stats->tso_inner_bytes += skb->len - ihs; } else { @@ -398,6 +402,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) { u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata); + mlx5e_ptp_metadata_fifo_pop(&sq->ptpsq->metadata_freelist); + mlx5e_skb_cb_hwtstamp_init(skb); mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, metadata_index); @@ -496,9 +502,6 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, err_drop: stats->dropped++; - if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) - mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist, - be32_to_cpu(eseg->flow_table_metadata)); dev_kfree_skb_any(skb); mlx5e_tx_flush(sq); } @@ -657,7 +660,7 @@ static void mlx5e_cqe_ts_id_eseg(struct mlx5e_ptpsq *ptpsq, struct sk_buff *skb, { if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) eseg->flow_table_metadata = - cpu_to_be32(mlx5e_ptp_metadata_fifo_pop(&ptpsq->metadata_freelist)); + cpu_to_be32(mlx5e_ptp_metadata_fifo_peek(&ptpsq->metadata_freelist)); } static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 1b9bc32efd6fa..c5ea1d1d2b035 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1874,7 +1874,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_ "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n", addr, vid, vport_num); NL_SET_ERR_MSG_FMT_MOD(extack, - "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n", + "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)\n", addr, vid, vport_num); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 3047d7015c525..1789800faaeb6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1868,6 +1868,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) if (err) goto abort; + dev->priv.eswitch = esw; err = esw_offloads_init(esw); if (err) goto reps_err; @@ -1892,11 +1893,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; else esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; - if (MLX5_ESWITCH_MANAGER(dev) && - mlx5_esw_vport_match_metadata_supported(esw)) - esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA; - - dev->priv.eswitch = esw; BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head); esw_info(dev, @@ -1908,6 +1904,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) reps_err: mlx5_esw_vports_cleanup(esw); + dev->priv.eswitch = NULL; abort: if (esw->work_queue) destroy_workqueue(esw->work_queue); @@ -1926,7 +1923,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw_info(esw->dev, "cleanup\n"); - esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); WARN_ON(refcount_read(&esw->qos.refcnt)); mutex_destroy(&esw->state_lock); @@ -1937,6 +1933,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) mutex_destroy(&esw->offloads.encap_tbl_lock); mutex_destroy(&esw->offloads.decap_tbl_lock); esw_offloads_cleanup(esw); + esw->dev->priv.eswitch = NULL; mlx5_esw_vports_cleanup(esw); debugfs_remove_recursive(esw->debugfs_root); devl_params_unregister(priv_to_devlink(esw->dev), mlx5_eswitch_params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 349e28a6dd8df..ef55674876cb4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -833,7 +833,7 @@ int mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw, int max_slaves); void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw); -int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw); +int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw); bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev); void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev); @@ -925,7 +925,7 @@ mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, static inline int mlx5_eswitch_get_npeers(struct mlx5_eswitch *esw) { return 0; } static inline int -mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) +mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index baaae628b0a0f..58529d1a98b37 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2476,6 +2476,10 @@ int esw_offloads_init(struct mlx5_eswitch *esw) if (err) return err; + if (MLX5_ESWITCH_MANAGER(esw->dev) && + mlx5_esw_vport_match_metadata_supported(esw)) + esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA; + err = devl_params_register(priv_to_devlink(esw->dev), esw_devlink_params, ARRAY_SIZE(esw_devlink_params)); @@ -2497,6 +2501,16 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw) esw_offloads_cleanup_reps(esw); } +static int __esw_offloads_load_rep(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, u8 rep_type) +{ + if (atomic_cmpxchg(&rep->rep_data[rep_type].state, + REP_REGISTERED, REP_LOADED) == REP_REGISTERED) + return esw->offloads.rep_ops[rep_type]->load(esw->dev, rep); + + return 0; +} + static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, u8 rep_type) { @@ -2521,13 +2535,11 @@ static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num) int err; rep = mlx5_eswitch_get_rep(esw, vport_num); - for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) - if (atomic_cmpxchg(&rep->rep_data[rep_type].state, - REP_REGISTERED, REP_LOADED) == REP_REGISTERED) { - err = esw->offloads.rep_ops[rep_type]->load(esw->dev, rep); - if (err) - goto err_reps; - } + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { + err = __esw_offloads_load_rep(esw, rep, rep_type); + if (err) + goto err_reps; + } return 0; @@ -3272,7 +3284,7 @@ static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw) esw_vport_destroy_offloads_acl_tables(esw, vport); } -int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) +int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw) { struct mlx5_eswitch_rep *rep; unsigned long i; @@ -3285,13 +3297,13 @@ int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) return 0; - ret = mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK); + ret = __esw_offloads_load_rep(esw, rep, REP_IB); if (ret) return ret; mlx5_esw_for_each_rep(esw, i, rep) { if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED) - mlx5_esw_offloads_rep_load(esw, rep->vport); + __esw_offloads_load_rep(esw, rep, REP_IB); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index e6bfa7e4f146c..cf085a478e3e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1664,6 +1664,16 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft, return err; } +static bool mlx5_pkt_reformat_cmp(struct mlx5_pkt_reformat *p1, + struct mlx5_pkt_reformat *p2) +{ + return p1->owner == p2->owner && + (p1->owner == MLX5_FLOW_RESOURCE_OWNER_FW ? + p1->id == p2->id : + mlx5_fs_dr_action_get_pkt_reformat_id(p1) == + mlx5_fs_dr_action_get_pkt_reformat_id(p2)); +} + static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, struct mlx5_flow_destination *d2) { @@ -1675,8 +1685,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ? (d1->vport.vhca_id == d2->vport.vhca_id) : true) && ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ? - (d1->vport.pkt_reformat->id == - d2->vport.pkt_reformat->id) : true)) || + mlx5_pkt_reformat_cmp(d1->vport.pkt_reformat, + d2->vport.pkt_reformat) : true)) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && d1->ft == d2->ft) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR && @@ -1808,8 +1818,9 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, } trace_mlx5_fs_set_fte(fte, false); + /* Link newly added rules into the tree. */ for (i = 0; i < handle->num_rules; i++) { - if (refcount_read(&handle->rule[i]->node.refcount) == 1) { + if (!handle->rule[i]->node.parent) { tree_add_node(&handle->rule[i]->node, &fte->node); trace_mlx5_fs_add_rule(handle->rule[i]); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 58f4c0d0fafa2..70898f0a9866c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -373,6 +373,10 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) do { if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) break; + if (pci_channel_offline(dev->pdev)) { + mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n"); + return -EACCES; + } cond_resched(); } while (!time_after(jiffies, end)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index b5c709bba1553..4ad88be1ecb5e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -248,6 +248,10 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev) do { if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) break; + if (pci_channel_offline(dev->pdev)) { + mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n"); + goto unlock; + } msleep(20); } while (!time_after(jiffies, end)); @@ -317,6 +321,10 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev) mlx5_core_warn(dev, "device is being removed, stop waiting for PCI\n"); return -ENODEV; } + if (pci_channel_offline(dev->pdev)) { + mlx5_core_err(dev, "PCI channel offline, stop waiting for PCI\n"); + return -EACCES; + } msleep(100); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index d14459e5c04fc..58a452d20daf7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -703,8 +703,10 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev) return err; } - if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) + if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) { mlx5_lag_port_sel_destroy(ldev); + ldev->buckets = 1; + } if (mlx5_lag_has_drop_rule(ldev)) mlx5_lag_drop_rule_cleanup(ldev); @@ -718,6 +720,7 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) struct mlx5_core_dev *dev; u8 mode; #endif + bool roce_support; int i; for (i = 0; i < ldev->ports; i++) @@ -744,6 +747,11 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) if (mlx5_sriov_is_enabled(ldev->pf[i].dev)) return false; #endif + roce_support = mlx5_get_roce_state(ldev->pf[MLX5_LAG_P1].dev); + for (i = 1; i < ldev->ports; i++) + if (mlx5_get_roce_state(ldev->pf[i].dev) != roce_support) + return false; + return true; } @@ -812,7 +820,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev) if (shared_fdb) for (i = 0; i < ldev->ports; i++) if (!(ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) - mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); } static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) @@ -911,8 +919,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) } else if (roce_lag) { dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); - for (i = 1; i < ldev->ports; i++) - mlx5_nic_vport_enable_roce(ldev->pf[i].dev); + for (i = 1; i < ldev->ports; i++) { + if (mlx5_get_roce_state(ldev->pf[i].dev)) + mlx5_nic_vport_enable_roce(ldev->pf[i].dev); + } } else if (shared_fdb) { int i; @@ -920,7 +930,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) mlx5_rescan_drivers_locked(dev0); for (i = 0; i < ldev->ports; i++) { - err = mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); if (err) break; } @@ -931,7 +941,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) mlx5_deactivate_lag(ldev); mlx5_lag_add_devices(ldev); for (i = 0; i < ldev->ports; i++) - mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); mlx5_core_err(dev0, "Failed to enable lag\n"); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index 82889f30506ea..571ea26edd0ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -99,7 +99,7 @@ static int enable_mpesw(struct mlx5_lag *ldev) dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); for (i = 0; i < ldev->ports; i++) { - err = mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); if (err) goto err_rescan_drivers; } @@ -113,7 +113,7 @@ static int enable_mpesw(struct mlx5_lag *ldev) err_add_devices: mlx5_lag_add_devices(ldev); for (i = 0; i < ldev->ports; i++) - mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); mlx5_mpesw_metadata_cleanup(ldev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index 101b3bb908638..e12bc4cd80661 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -88,9 +88,13 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev, &dest, 1); if (IS_ERR(lag_definer->rules[idx])) { err = PTR_ERR(lag_definer->rules[idx]); - while (i--) - while (j--) + do { + while (j--) { + idx = i * ldev->buckets + j; mlx5_del_flow_rules(lag_definer->rules[idx]); + } + j = ldev->buckets; + } while (i--); goto destroy_fg; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c index 6b774e0c27665..d0b595ba61101 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c @@ -74,6 +74,10 @@ int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev) ret = -EBUSY; goto pci_unlock; } + if (pci_channel_offline(dev->pdev)) { + ret = -EACCES; + goto pci_unlock; + } /* Check if semaphore is already locked */ ret = vsc_read(dev, VSC_SEMAPHORE_OFFSET, &lock_val); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index bccf6e53556c6..74d3c80a29b81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1298,6 +1298,9 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) if (!err) mlx5_function_disable(dev, boot); + else + mlx5_stop_health_poll(dev, boot); + return err; } @@ -1480,6 +1483,14 @@ int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev) if (err) goto err_register; + err = mlx5_crdump_enable(dev); + if (err) + mlx5_core_err(dev, "mlx5_crdump_enable failed with error code %d\n", err); + + err = mlx5_hwmon_dev_register(dev); + if (err) + mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err); + mutex_unlock(&dev->intf_state_mutex); return 0; @@ -1505,7 +1516,10 @@ int mlx5_init_one(struct mlx5_core_dev *dev) int err; devl_lock(devlink); + devl_register(devlink); err = mlx5_init_one_devl_locked(dev); + if (err) + devl_unregister(devlink); devl_unlock(devlink); return err; } @@ -1517,6 +1531,8 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev) devl_lock(devlink); mutex_lock(&dev->intf_state_mutex); + mlx5_hwmon_dev_unregister(dev); + mlx5_crdump_disable(dev); mlx5_unregister_device(dev); if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { @@ -1534,6 +1550,7 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev) mlx5_function_teardown(dev, true); out: mutex_unlock(&dev->intf_state_mutex); + devl_unregister(devlink); devl_unlock(devlink); } @@ -1666,6 +1683,8 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev) struct devlink *devlink = priv_to_devlink(dev); int err; + devl_lock(devlink); + devl_register(devlink); dev->state = MLX5_DEVICE_STATE_UP; err = mlx5_function_enable(dev, true, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); if (err) { @@ -1679,20 +1698,21 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev) goto query_hca_caps_err; } - devl_lock(devlink); err = mlx5_devlink_params_register(priv_to_devlink(dev)); - devl_unlock(devlink); if (err) { mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err); goto query_hca_caps_err; } + devl_unlock(devlink); return 0; query_hca_caps_err: mlx5_function_disable(dev, true); out: dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; + devl_unregister(devlink); + devl_unlock(devlink); return err; } @@ -1702,6 +1722,7 @@ void mlx5_uninit_one_light(struct mlx5_core_dev *dev) devl_lock(devlink); mlx5_devlink_params_unregister(priv_to_devlink(dev)); + devl_unregister(devlink); devl_unlock(devlink); if (dev->state != MLX5_DEVICE_STATE_UP) return; @@ -1943,16 +1964,7 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_init_one; } - err = mlx5_crdump_enable(dev); - if (err) - dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); - - err = mlx5_hwmon_dev_register(dev); - if (err) - mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err); - pci_save_state(pdev); - devlink_register(devlink); return 0; err_init_one: @@ -1973,16 +1985,9 @@ static void remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(dev); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); - /* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using - * devlink notify APIs. - * Hence, we must drain them before unregistering the devlink. - */ mlx5_drain_fw_reset(dev); mlx5_drain_health_wq(dev); - devlink_unregister(devlink); mlx5_sriov_disable(pdev, false); - mlx5_hwmon_dev_unregister(dev); - mlx5_crdump_disable(dev); mlx5_uninit_one(dev); mlx5_pci_close(dev); mlx5_mdev_uninit(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 4dcf995cb1a20..6bac8ad70ba60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -19,6 +19,7 @@ #define MLX5_IRQ_CTRL_SF_MAX 8 /* min num of vectors for SFs to be enabled */ #define MLX5_IRQ_VEC_COMP_BASE_SF 2 +#define MLX5_IRQ_VEC_COMP_BASE 1 #define MLX5_EQ_SHARE_IRQ_MAX_COMP (8) #define MLX5_EQ_SHARE_IRQ_MAX_CTRL (UINT_MAX) @@ -246,6 +247,7 @@ static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) return; } + vecidx -= MLX5_IRQ_VEC_COMP_BASE; snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx); } @@ -585,7 +587,7 @@ struct mlx5_irq *mlx5_irq_request_vector(struct mlx5_core_dev *dev, u16 cpu, struct mlx5_irq_table *table = mlx5_irq_table_get(dev); struct mlx5_irq_pool *pool = table->pcif_pool; struct irq_affinity_desc af_desc; - int offset = 1; + int offset = MLX5_IRQ_VEC_COMP_BASE; if (!pool->xa_num_irqs.max) offset = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 169c2c68ed5c2..b2986175d9afe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -60,6 +60,13 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto remap_err; } + /* Peer devlink logic expects to work on unregistered devlink instance. */ + err = mlx5_core_peer_devlink_set(sf_dev, devlink); + if (err) { + mlx5_core_warn(mdev, "mlx5_core_peer_devlink_set err=%d\n", err); + goto peer_devlink_set_err; + } + if (MLX5_ESWITCH_MANAGER(sf_dev->parent_mdev)) err = mlx5_init_one_light(mdev); else @@ -69,21 +76,10 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto init_one_err; } - err = mlx5_core_peer_devlink_set(sf_dev, devlink); - if (err) { - mlx5_core_warn(mdev, "mlx5_core_peer_devlink_set err=%d\n", err); - goto peer_devlink_set_err; - } - - devlink_register(devlink); return 0; -peer_devlink_set_err: - if (mlx5_dev_is_lightweight(sf_dev->mdev)) - mlx5_uninit_one_light(sf_dev->mdev); - else - mlx5_uninit_one(sf_dev->mdev); init_one_err: +peer_devlink_set_err: iounmap(mdev->iseg); remap_err: mlx5_mdev_uninit(mdev); @@ -95,24 +91,28 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia static void mlx5_sf_dev_remove(struct auxiliary_device *adev) { struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); - struct devlink *devlink = priv_to_devlink(sf_dev->mdev); + struct mlx5_core_dev *mdev = sf_dev->mdev; + struct devlink *devlink; - mlx5_drain_health_wq(sf_dev->mdev); - devlink_unregister(devlink); - if (mlx5_dev_is_lightweight(sf_dev->mdev)) - mlx5_uninit_one_light(sf_dev->mdev); + devlink = priv_to_devlink(mdev); + set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state); + mlx5_drain_health_wq(mdev); + if (mlx5_dev_is_lightweight(mdev)) + mlx5_uninit_one_light(mdev); else - mlx5_uninit_one(sf_dev->mdev); - iounmap(sf_dev->mdev->iseg); - mlx5_mdev_uninit(sf_dev->mdev); + mlx5_uninit_one(mdev); + iounmap(mdev->iseg); + mlx5_mdev_uninit(mdev); mlx5_devlink_free(devlink); } static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev) { struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); + struct mlx5_core_dev *mdev = sf_dev->mdev; - mlx5_unload_one(sf_dev->mdev, false); + set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state); + mlx5_unload_one(mdev, false); } static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = { diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 3d09fa54598f1..ba303868686a7 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "mlxbf_gige.h" @@ -139,13 +140,10 @@ static int mlxbf_gige_open(struct net_device *netdev) control |= MLXBF_GIGE_CONTROL_PORT_EN; writeq(control, priv->base + MLXBF_GIGE_CONTROL); - err = mlxbf_gige_request_irqs(priv); - if (err) - return err; mlxbf_gige_cache_stats(priv); err = mlxbf_gige_clean_port(priv); if (err) - goto free_irqs; + return err; /* Clear driver's valid_polarity to match hardware, * since the above call to clean_port() resets the @@ -157,7 +155,7 @@ static int mlxbf_gige_open(struct net_device *netdev) err = mlxbf_gige_tx_init(priv); if (err) - goto free_irqs; + goto phy_deinit; err = mlxbf_gige_rx_init(priv); if (err) goto tx_deinit; @@ -166,6 +164,10 @@ static int mlxbf_gige_open(struct net_device *netdev) napi_enable(&priv->napi); netif_start_queue(netdev); + err = mlxbf_gige_request_irqs(priv); + if (err) + goto napi_deinit; + /* Set bits in INT_EN that we care about */ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | @@ -182,11 +184,17 @@ static int mlxbf_gige_open(struct net_device *netdev) return 0; +napi_deinit: + netif_stop_queue(netdev); + napi_disable(&priv->napi); + netif_napi_del(&priv->napi); + mlxbf_gige_rx_deinit(priv); + tx_deinit: mlxbf_gige_tx_deinit(priv); -free_irqs: - mlxbf_gige_free_irqs(priv); +phy_deinit: + phy_stop(phydev); return err; } @@ -485,8 +493,13 @@ static void mlxbf_gige_shutdown(struct platform_device *pdev) { struct mlxbf_gige *priv = platform_get_drvdata(pdev); - writeq(0, priv->base + MLXBF_GIGE_INT_EN); - mlxbf_gige_clean_port(priv); + rtnl_lock(); + netif_device_detach(priv->netdev); + + if (netif_running(priv->netdev)) + dev_close(priv->netdev); + + rtnl_unlock(); } static const struct acpi_device_id __maybe_unused mlxbf_gige_acpi_match[] = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e4d7739bd7c88..4a79c0d7e7ad8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -849,7 +849,7 @@ static void mlxsw_emad_rx_listener_func(struct sk_buff *skb, u16 local_port, static const struct mlxsw_listener mlxsw_emad_rx_listener = MLXSW_RXL(mlxsw_emad_rx_listener_func, ETHEMAD, TRAP_TO_CPU, false, - EMAD, DISCARD); + EMAD, FORWARD); static int mlxsw_emad_tlv_enable(struct mlxsw_core *mlxsw_core) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index faa63ea9b83e1..1915fa41c6224 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -95,7 +95,7 @@ struct mlxsw_afa_set { */ has_trap:1, has_police:1; - unsigned int ref_count; + refcount_t ref_count; struct mlxsw_afa_set *next; /* Pointer to the next set. */ struct mlxsw_afa_set *prev; /* Pointer to the previous set, * note that set may have multiple @@ -120,7 +120,7 @@ struct mlxsw_afa_fwd_entry { struct rhash_head ht_node; struct mlxsw_afa_fwd_entry_ht_key ht_key; u32 kvdl_index; - unsigned int ref_count; + refcount_t ref_count; }; static const struct rhashtable_params mlxsw_afa_fwd_entry_ht_params = { @@ -282,7 +282,7 @@ static struct mlxsw_afa_set *mlxsw_afa_set_create(bool is_first) /* Need to initialize the set to pass by default */ mlxsw_afa_set_goto_set(set, MLXSW_AFA_SET_GOTO_BINDING_CMD_TERM, 0); set->ht_key.is_first = is_first; - set->ref_count = 1; + refcount_set(&set->ref_count, 1); return set; } @@ -330,7 +330,7 @@ static void mlxsw_afa_set_unshare(struct mlxsw_afa *mlxsw_afa, static void mlxsw_afa_set_put(struct mlxsw_afa *mlxsw_afa, struct mlxsw_afa_set *set) { - if (--set->ref_count) + if (!refcount_dec_and_test(&set->ref_count)) return; if (set->shared) mlxsw_afa_set_unshare(mlxsw_afa, set); @@ -350,7 +350,7 @@ static struct mlxsw_afa_set *mlxsw_afa_set_get(struct mlxsw_afa *mlxsw_afa, set = rhashtable_lookup_fast(&mlxsw_afa->set_ht, &orig_set->ht_key, mlxsw_afa_set_ht_params); if (set) { - set->ref_count++; + refcount_inc(&set->ref_count); mlxsw_afa_set_put(mlxsw_afa, orig_set); } else { set = orig_set; @@ -564,7 +564,7 @@ mlxsw_afa_fwd_entry_create(struct mlxsw_afa *mlxsw_afa, u16 local_port) if (!fwd_entry) return ERR_PTR(-ENOMEM); fwd_entry->ht_key.local_port = local_port; - fwd_entry->ref_count = 1; + refcount_set(&fwd_entry->ref_count, 1); err = rhashtable_insert_fast(&mlxsw_afa->fwd_entry_ht, &fwd_entry->ht_node, @@ -607,7 +607,7 @@ mlxsw_afa_fwd_entry_get(struct mlxsw_afa *mlxsw_afa, u16 local_port) fwd_entry = rhashtable_lookup_fast(&mlxsw_afa->fwd_entry_ht, &ht_key, mlxsw_afa_fwd_entry_ht_params); if (fwd_entry) { - fwd_entry->ref_count++; + refcount_inc(&fwd_entry->ref_count); return fwd_entry; } return mlxsw_afa_fwd_entry_create(mlxsw_afa, local_port); @@ -616,7 +616,7 @@ mlxsw_afa_fwd_entry_get(struct mlxsw_afa *mlxsw_afa, u16 local_port) static void mlxsw_afa_fwd_entry_put(struct mlxsw_afa *mlxsw_afa, struct mlxsw_afa_fwd_entry *fwd_entry) { - if (--fwd_entry->ref_count) + if (!refcount_dec_and_test(&fwd_entry->ref_count)) return; mlxsw_afa_fwd_entry_destroy(mlxsw_afa, fwd_entry); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c index 0d5e6f9b466ec..947500f8ed714 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -5,6 +5,7 @@ #include #include #include +#include #include "item.h" #include "core_acl_flex_keys.h" @@ -107,7 +108,7 @@ EXPORT_SYMBOL(mlxsw_afk_destroy); struct mlxsw_afk_key_info { struct list_head list; - unsigned int ref_count; + refcount_t ref_count; unsigned int blocks_count; int element_to_block[MLXSW_AFK_ELEMENT_MAX]; /* index is element, value * is index inside "blocks" @@ -334,7 +335,7 @@ mlxsw_afk_key_info_create(struct mlxsw_afk *mlxsw_afk, if (err) goto err_picker; list_add(&key_info->list, &mlxsw_afk->key_info_list); - key_info->ref_count = 1; + refcount_set(&key_info->ref_count, 1); return key_info; err_picker: @@ -356,7 +357,7 @@ mlxsw_afk_key_info_get(struct mlxsw_afk *mlxsw_afk, key_info = mlxsw_afk_key_info_find(mlxsw_afk, elusage); if (key_info) { - key_info->ref_count++; + refcount_inc(&key_info->ref_count); return key_info; } return mlxsw_afk_key_info_create(mlxsw_afk, elusage); @@ -365,7 +366,7 @@ EXPORT_SYMBOL(mlxsw_afk_key_info_get); void mlxsw_afk_key_info_put(struct mlxsw_afk_key_info *key_info) { - if (--key_info->ref_count) + if (!refcount_dec_and_test(&key_info->ref_count)) return; mlxsw_afk_key_info_destroy(key_info); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index 53b150b7ae4e7..6c06b05927608 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -1357,24 +1357,20 @@ static struct mlxsw_linecards_event_ops mlxsw_env_event_ops = { .got_inactive = mlxsw_env_got_inactive, }; -static int mlxsw_env_max_module_eeprom_len_query(struct mlxsw_env *mlxsw_env) +static void mlxsw_env_max_module_eeprom_len_query(struct mlxsw_env *mlxsw_env) { char mcam_pl[MLXSW_REG_MCAM_LEN]; - bool mcia_128b_supported; + bool mcia_128b_supported = false; int err; mlxsw_reg_mcam_pack(mcam_pl, MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES); err = mlxsw_reg_query(mlxsw_env->core, MLXSW_REG(mcam), mcam_pl); - if (err) - return err; - - mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_MCIA_128B, - &mcia_128b_supported); + if (!err) + mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_MCIA_128B, + &mcia_128b_supported); mlxsw_env->max_eeprom_len = mcia_128b_supported ? 128 : 48; - - return 0; } int mlxsw_env_init(struct mlxsw_core *mlxsw_core, @@ -1445,15 +1441,11 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, if (err) goto err_type_set; - err = mlxsw_env_max_module_eeprom_len_query(env); - if (err) - goto err_eeprom_len_query; - + mlxsw_env_max_module_eeprom_len_query(env); env->line_cards[0]->active = true; return 0; -err_eeprom_len_query: err_type_set: mlxsw_env_module_event_disable(env, 0); err_mlxsw_env_module_event_enable: diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index af99bf17eb36d..f42a1b1c93687 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1530,7 +1530,7 @@ mlxsw_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id) { struct pci_dev *pdev = mlxsw_pci->pdev; char mcam_pl[MLXSW_REG_MCAM_LEN]; - bool pci_reset_supported; + bool pci_reset_supported = false; u32 sys_status; int err; @@ -1548,11 +1548,9 @@ mlxsw_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id) mlxsw_reg_mcam_pack(mcam_pl, MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES); err = mlxsw_reg_query(mlxsw_pci->core, MLXSW_REG(mcam), mcam_pl); - if (err) - return err; - - mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET, - &pci_reset_supported); + if (!err) + mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET, + &pci_reset_supported); if (pci_reset_supported) { pci_dbg(pdev, "Starting PCI reset flow\n"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 7c59c8a135840..b01b000bc71c1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -55,7 +56,7 @@ struct mlxsw_sp_acl_ruleset { struct rhash_head ht_node; /* Member of acl HT */ struct mlxsw_sp_acl_ruleset_ht_key ht_key; struct rhashtable rule_ht; - unsigned int ref_count; + refcount_t ref_count; unsigned int min_prio; unsigned int max_prio; unsigned long priv[]; @@ -99,7 +100,7 @@ static bool mlxsw_sp_acl_ruleset_is_singular(const struct mlxsw_sp_acl_ruleset *ruleset) { /* We hold a reference on ruleset ourselves */ - return ruleset->ref_count == 2; + return refcount_read(&ruleset->ref_count) == 2; } int mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp, @@ -176,7 +177,7 @@ mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp, ruleset = kzalloc(alloc_size, GFP_KERNEL); if (!ruleset) return ERR_PTR(-ENOMEM); - ruleset->ref_count = 1; + refcount_set(&ruleset->ref_count, 1); ruleset->ht_key.block = block; ruleset->ht_key.chain_index = chain_index; ruleset->ht_key.ops = ops; @@ -222,13 +223,13 @@ static void mlxsw_sp_acl_ruleset_destroy(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_acl_ruleset_ref_inc(struct mlxsw_sp_acl_ruleset *ruleset) { - ruleset->ref_count++; + refcount_inc(&ruleset->ref_count); } static void mlxsw_sp_acl_ruleset_ref_dec(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset) { - if (--ruleset->ref_count) + if (!refcount_dec_and_test(&ruleset->ref_count)) return; mlxsw_sp_acl_ruleset_destroy(mlxsw_sp, ruleset); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 50ea1eff02b2f..92a406f02eae7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -9,6 +9,8 @@ #include #include #include +#include +#include #include #include @@ -57,41 +59,43 @@ int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_acl_tcam_region_id_get(struct mlxsw_sp_acl_tcam *tcam, u16 *p_id) { - u16 id; + int id; - id = find_first_zero_bit(tcam->used_regions, tcam->max_regions); - if (id < tcam->max_regions) { - __set_bit(id, tcam->used_regions); - *p_id = id; - return 0; - } - return -ENOBUFS; + id = ida_alloc_max(&tcam->used_regions, tcam->max_regions - 1, + GFP_KERNEL); + if (id < 0) + return id; + + *p_id = id; + + return 0; } static void mlxsw_sp_acl_tcam_region_id_put(struct mlxsw_sp_acl_tcam *tcam, u16 id) { - __clear_bit(id, tcam->used_regions); + ida_free(&tcam->used_regions, id); } static int mlxsw_sp_acl_tcam_group_id_get(struct mlxsw_sp_acl_tcam *tcam, u16 *p_id) { - u16 id; + int id; - id = find_first_zero_bit(tcam->used_groups, tcam->max_groups); - if (id < tcam->max_groups) { - __set_bit(id, tcam->used_groups); - *p_id = id; - return 0; - } - return -ENOBUFS; + id = ida_alloc_max(&tcam->used_groups, tcam->max_groups - 1, + GFP_KERNEL); + if (id < 0) + return id; + + *p_id = id; + + return 0; } static void mlxsw_sp_acl_tcam_group_id_put(struct mlxsw_sp_acl_tcam *tcam, u16 id) { - __clear_bit(id, tcam->used_groups); + ida_free(&tcam->used_groups, id); } struct mlxsw_sp_acl_tcam_pattern { @@ -155,7 +159,7 @@ struct mlxsw_sp_acl_tcam_vregion { struct mlxsw_sp_acl_tcam_rehash_ctx ctx; } rehash; struct mlxsw_sp *mlxsw_sp; - unsigned int ref_count; + refcount_t ref_count; }; struct mlxsw_sp_acl_tcam_vchunk; @@ -176,7 +180,7 @@ struct mlxsw_sp_acl_tcam_vchunk { unsigned int priority; /* Priority within the vregion and group */ struct mlxsw_sp_acl_tcam_vgroup *vgroup; struct mlxsw_sp_acl_tcam_vregion *vregion; - unsigned int ref_count; + refcount_t ref_count; }; struct mlxsw_sp_acl_tcam_entry { @@ -714,7 +718,9 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) rehash.dw.work); int credits = MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS; + mutex_lock(&vregion->lock); mlxsw_sp_acl_tcam_vregion_rehash(vregion->mlxsw_sp, vregion, &credits); + mutex_unlock(&vregion->lock); if (credits < 0) /* Rehash gone out of credits so it was interrupted. * Schedule the work as soon as possible to continue. @@ -724,6 +730,17 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion); } +static void +mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(struct mlxsw_sp_acl_tcam_rehash_ctx *ctx) +{ + /* The entry markers are relative to the current chunk and therefore + * needs to be reset together with the chunk marker. + */ + ctx->current_vchunk = NULL; + ctx->start_ventry = NULL; + ctx->stop_ventry = NULL; +} + static void mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(struct mlxsw_sp_acl_tcam_vchunk *vchunk) { @@ -746,7 +763,7 @@ mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(struct mlxsw_sp_acl_tcam_vregion *v * the current chunk pointer to make sure all chunks * are properly migrated. */ - vregion->rehash.ctx.current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(&vregion->rehash.ctx); } static struct mlxsw_sp_acl_tcam_vregion * @@ -769,7 +786,7 @@ mlxsw_sp_acl_tcam_vregion_create(struct mlxsw_sp *mlxsw_sp, vregion->tcam = tcam; vregion->mlxsw_sp = mlxsw_sp; vregion->vgroup = vgroup; - vregion->ref_count = 1; + refcount_set(&vregion->ref_count, 1); vregion->key_info = mlxsw_afk_key_info_get(afk, elusage); if (IS_ERR(vregion->key_info)) { @@ -819,10 +836,14 @@ mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam = vregion->tcam; if (vgroup->vregion_rehash_enabled && ops->region_rehash_hints_get) { + struct mlxsw_sp_acl_tcam_rehash_ctx *ctx = &vregion->rehash.ctx; + mutex_lock(&tcam->lock); list_del(&vregion->tlist); mutex_unlock(&tcam->lock); - cancel_delayed_work_sync(&vregion->rehash.dw); + if (cancel_delayed_work_sync(&vregion->rehash.dw) && + ctx->hints_priv) + ops->region_rehash_hints_put(ctx->hints_priv); } mlxsw_sp_acl_tcam_vgroup_vregion_detach(mlxsw_sp, vregion); if (vregion->region2) @@ -856,7 +877,7 @@ mlxsw_sp_acl_tcam_vregion_get(struct mlxsw_sp *mlxsw_sp, */ return ERR_PTR(-EOPNOTSUPP); } - vregion->ref_count++; + refcount_inc(&vregion->ref_count); return vregion; } @@ -871,7 +892,7 @@ static void mlxsw_sp_acl_tcam_vregion_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_vregion *vregion) { - if (--vregion->ref_count) + if (!refcount_dec_and_test(&vregion->ref_count)) return; mlxsw_sp_acl_tcam_vregion_destroy(mlxsw_sp, vregion); } @@ -924,7 +945,7 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, INIT_LIST_HEAD(&vchunk->ventry_list); vchunk->priority = priority; vchunk->vgroup = vgroup; - vchunk->ref_count = 1; + refcount_set(&vchunk->ref_count, 1); vregion = mlxsw_sp_acl_tcam_vregion_get(mlxsw_sp, vgroup, priority, elusage); @@ -1008,7 +1029,7 @@ mlxsw_sp_acl_tcam_vchunk_get(struct mlxsw_sp *mlxsw_sp, if (WARN_ON(!mlxsw_afk_key_info_subset(vchunk->vregion->key_info, elusage))) return ERR_PTR(-EINVAL); - vchunk->ref_count++; + refcount_inc(&vchunk->ref_count); return vchunk; } return mlxsw_sp_acl_tcam_vchunk_create(mlxsw_sp, vgroup, @@ -1019,7 +1040,7 @@ static void mlxsw_sp_acl_tcam_vchunk_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_vchunk *vchunk) { - if (--vchunk->ref_count) + if (!refcount_dec_and_test(&vchunk->ref_count)) return; mlxsw_sp_acl_tcam_vchunk_destroy(mlxsw_sp, vchunk); } @@ -1153,8 +1174,14 @@ mlxsw_sp_acl_tcam_ventry_activity_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_ventry *ventry, bool *activity) { - return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, - ventry->entry, activity); + struct mlxsw_sp_acl_tcam_vregion *vregion = ventry->vchunk->vregion; + int err; + + mutex_lock(&vregion->lock); + err = mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, ventry->entry, + activity); + mutex_unlock(&vregion->lock); + return err; } static int @@ -1188,6 +1215,8 @@ mlxsw_sp_acl_tcam_vchunk_migrate_start(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_chunk *new_chunk; + WARN_ON(vchunk->chunk2); + new_chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region); if (IS_ERR(new_chunk)) return PTR_ERR(new_chunk); @@ -1206,7 +1235,7 @@ mlxsw_sp_acl_tcam_vchunk_migrate_end(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2); vchunk->chunk2 = NULL; - ctx->current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); } static int @@ -1229,6 +1258,9 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, return 0; } + if (list_empty(&vchunk->ventry_list)) + goto out; + /* If the migration got interrupted, we have the ventry to start from * stored in context. */ @@ -1238,6 +1270,8 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, ventry = list_first_entry(&vchunk->ventry_list, typeof(*ventry), list); + WARN_ON(ventry->vchunk != vchunk); + list_for_each_entry_from(ventry, &vchunk->ventry_list, list) { /* During rollback, once we reach the ventry that failed * to migrate, we are done. @@ -1278,6 +1312,7 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, } } +out: mlxsw_sp_acl_tcam_vchunk_migrate_end(mlxsw_sp, vchunk, ctx); return 0; } @@ -1291,6 +1326,9 @@ mlxsw_sp_acl_tcam_vchunk_migrate_all(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_vchunk *vchunk; int err; + if (list_empty(&vregion->vchunk_list)) + return 0; + /* If the migration got interrupted, we have the vchunk * we are working on stored in context. */ @@ -1319,16 +1357,17 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, int err, err2; trace_mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion); - mutex_lock(&vregion->lock); err = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion, ctx, credits); if (err) { + if (ctx->this_is_rollback) + return err; /* In case migration was not successful, we need to swap * so the original region pointer is assigned again * to vregion->region. */ swap(vregion->region, vregion->region2); - ctx->current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); ctx->this_is_rollback = true; err2 = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion, ctx, credits); @@ -1339,7 +1378,6 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, /* Let the rollback to be continued later on. */ } } - mutex_unlock(&vregion->lock); trace_mlxsw_sp_acl_tcam_vregion_migrate_end(mlxsw_sp, vregion); return err; } @@ -1388,6 +1426,7 @@ mlxsw_sp_acl_tcam_vregion_rehash_start(struct mlxsw_sp *mlxsw_sp, ctx->hints_priv = hints_priv; ctx->this_is_rollback = false; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); return 0; @@ -1440,7 +1479,8 @@ mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion, ctx, credits); if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n"); + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n"); + return; } if (*credits >= 0) @@ -1548,19 +1588,11 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, if (max_tcam_regions < max_regions) max_regions = max_tcam_regions; - tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL); - if (!tcam->used_regions) { - err = -ENOMEM; - goto err_alloc_used_regions; - } + ida_init(&tcam->used_regions); tcam->max_regions = max_regions; max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS); - tcam->used_groups = bitmap_zalloc(max_groups, GFP_KERNEL); - if (!tcam->used_groups) { - err = -ENOMEM; - goto err_alloc_used_groups; - } + ida_init(&tcam->used_groups); tcam->max_groups = max_groups; tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUP_SIZE); @@ -1574,10 +1606,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, return 0; err_tcam_init: - bitmap_free(tcam->used_groups); -err_alloc_used_groups: - bitmap_free(tcam->used_regions); -err_alloc_used_regions: + ida_destroy(&tcam->used_groups); + ida_destroy(&tcam->used_regions); mlxsw_sp_acl_tcam_rehash_params_unregister(mlxsw_sp); err_rehash_params_register: mutex_destroy(&tcam->lock); @@ -1590,8 +1620,8 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; ops->fini(mlxsw_sp, tcam->priv); - bitmap_free(tcam->used_groups); - bitmap_free(tcam->used_regions); + ida_destroy(&tcam->used_groups); + ida_destroy(&tcam->used_regions); mlxsw_sp_acl_tcam_rehash_params_unregister(mlxsw_sp); mutex_destroy(&tcam->lock); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index 462bf448497d3..79a1d86065125 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -6,15 +6,16 @@ #include #include +#include #include "reg.h" #include "spectrum.h" #include "core_acl_flex_keys.h" struct mlxsw_sp_acl_tcam { - unsigned long *used_regions; /* bit array */ + struct ida used_regions; unsigned int max_regions; - unsigned long *used_groups; /* bit array */ + struct ida used_groups; unsigned int max_groups; unsigned int max_group_size; struct mutex lock; /* guards vregion list */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 7164f9e6370fb..87617df694ab2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -501,7 +501,7 @@ struct mlxsw_sp_rt6 { struct mlxsw_sp_lpm_tree { u8 id; /* tree ID */ - unsigned int ref_count; + refcount_t ref_count; enum mlxsw_sp_l3proto proto; unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT]; struct mlxsw_sp_prefix_usage prefix_usage; @@ -578,7 +578,7 @@ mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp) for (i = 0; i < mlxsw_sp->router->lpm.tree_count; i++) { lpm_tree = &mlxsw_sp->router->lpm.trees[i]; - if (lpm_tree->ref_count == 0) + if (refcount_read(&lpm_tree->ref_count) == 0) return lpm_tree; } return NULL; @@ -654,7 +654,7 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, sizeof(lpm_tree->prefix_usage)); memset(&lpm_tree->prefix_ref_count, 0, sizeof(lpm_tree->prefix_ref_count)); - lpm_tree->ref_count = 1; + refcount_set(&lpm_tree->ref_count, 1); return lpm_tree; err_left_struct_set: @@ -678,7 +678,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < mlxsw_sp->router->lpm.tree_count; i++) { lpm_tree = &mlxsw_sp->router->lpm.trees[i]; - if (lpm_tree->ref_count != 0 && + if (refcount_read(&lpm_tree->ref_count) && lpm_tree->proto == proto && mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage, prefix_usage)) { @@ -691,14 +691,15 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree) { - lpm_tree->ref_count++; + refcount_inc(&lpm_tree->ref_count); } static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_lpm_tree *lpm_tree) { - if (--lpm_tree->ref_count == 0) - mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree); + if (!refcount_dec_and_test(&lpm_tree->ref_count)) + return; + mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree); } #define MLXSW_SP_LPM_TREE_MIN 1 /* tree 0 is reserved */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index af50ff9e5f267..ce49c9514f911 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -539,7 +539,7 @@ mlxsw_sp_span_gretap6_route(const struct net_device *to_dev, if (!dst || dst->error) goto out; - rt6 = container_of(dst, struct rt6_info, dst); + rt6 = dst_rt6_info(dst); dev = dst->dev; *saddrp = fl6.saddr; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 6c749c148148d..6397ff0dc951c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -61,7 +61,7 @@ struct mlxsw_sp_bridge_port { struct mlxsw_sp_bridge_device *bridge_device; struct list_head list; struct list_head vlans_list; - unsigned int ref_count; + refcount_t ref_count; u8 stp_state; unsigned long flags; bool mrouter; @@ -495,7 +495,7 @@ mlxsw_sp_bridge_port_create(struct mlxsw_sp_bridge_device *bridge_device, BR_MCAST_FLOOD; INIT_LIST_HEAD(&bridge_port->vlans_list); list_add(&bridge_port->list, &bridge_device->ports_list); - bridge_port->ref_count = 1; + refcount_set(&bridge_port->ref_count, 1); err = switchdev_bridge_port_offload(brport_dev, mlxsw_sp_port->dev, NULL, NULL, NULL, false, extack); @@ -531,7 +531,7 @@ mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge, bridge_port = mlxsw_sp_bridge_port_find(bridge, brport_dev); if (bridge_port) { - bridge_port->ref_count++; + refcount_inc(&bridge_port->ref_count); return bridge_port; } @@ -558,7 +558,7 @@ static void mlxsw_sp_bridge_port_put(struct mlxsw_sp_bridge *bridge, { struct mlxsw_sp_bridge_device *bridge_device; - if (--bridge_port->ref_count != 0) + if (!refcount_dec_and_test(&bridge_port->ref_count)) return; bridge_device = bridge_port->bridge_device; mlxsw_sp_bridge_port_destroy(bridge_port); diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index e5ec0a363aff8..31f75b4a67fd7 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -368,7 +368,6 @@ union ks8851_tx_hdr { * @rdfifo: FIFO read callback * @wrfifo: FIFO write callback * @start_xmit: start_xmit() implementation callback - * @rx_skb: rx_skb() implementation callback * @flush_tx_work: flush_tx_work() implementation callback * * The @statelock is used to protect information in the structure which may @@ -423,8 +422,6 @@ struct ks8851_net { struct sk_buff *txp, bool irq); netdev_tx_t (*start_xmit)(struct sk_buff *skb, struct net_device *dev); - void (*rx_skb)(struct ks8851_net *ks, - struct sk_buff *skb); void (*flush_tx_work)(struct ks8851_net *ks); }; diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 0bf13b38b8f5b..6453c92f0fa7c 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -231,25 +231,16 @@ static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt) rxpkt[12], rxpkt[13], rxpkt[14], rxpkt[15]); } -/** - * ks8851_rx_skb - receive skbuff - * @ks: The device state. - * @skb: The skbuff - */ -static void ks8851_rx_skb(struct ks8851_net *ks, struct sk_buff *skb) -{ - ks->rx_skb(ks, skb); -} - /** * ks8851_rx_pkts - receive packets from the host * @ks: The device information. + * @rxq: Queue of packets received in this function. * * This is called from the IRQ work queue when the system detects that there * are packets in the receive queue. Find out how many packets there are and * read them from the FIFO. */ -static void ks8851_rx_pkts(struct ks8851_net *ks) +static void ks8851_rx_pkts(struct ks8851_net *ks, struct sk_buff_head *rxq) { struct sk_buff *skb; unsigned rxfc; @@ -309,7 +300,7 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) ks8851_dbg_dumpkkt(ks, rxpkt); skb->protocol = eth_type_trans(skb, ks->netdev); - ks8851_rx_skb(ks, skb); + __skb_queue_tail(rxq, skb); ks->netdev->stats.rx_packets++; ks->netdev->stats.rx_bytes += rxlen; @@ -336,31 +327,25 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) static irqreturn_t ks8851_irq(int irq, void *_ks) { struct ks8851_net *ks = _ks; - unsigned handled = 0; + struct sk_buff_head rxq; unsigned long flags; unsigned int status; + struct sk_buff *skb; ks8851_lock(ks, &flags); status = ks8851_rdreg16(ks, KS_ISR); + ks8851_wrreg16(ks, KS_ISR, status); netif_dbg(ks, intr, ks->netdev, "%s: status 0x%04x\n", __func__, status); - if (status & IRQ_LCI) - handled |= IRQ_LCI; - if (status & IRQ_LDI) { u16 pmecr = ks8851_rdreg16(ks, KS_PMECR); pmecr &= ~PMECR_WKEVT_MASK; ks8851_wrreg16(ks, KS_PMECR, pmecr | PMECR_WKEVT_LINK); - - handled |= IRQ_LDI; } - if (status & IRQ_RXPSI) - handled |= IRQ_RXPSI; - if (status & IRQ_TXI) { unsigned short tx_space = ks8851_rdreg16(ks, KS_TXMIR); @@ -372,27 +357,20 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) if (netif_queue_stopped(ks->netdev)) netif_wake_queue(ks->netdev); spin_unlock(&ks->statelock); - - handled |= IRQ_TXI; } - if (status & IRQ_RXI) - handled |= IRQ_RXI; - if (status & IRQ_SPIBEI) { netdev_err(ks->netdev, "%s: spi bus error\n", __func__); - handled |= IRQ_SPIBEI; } - ks8851_wrreg16(ks, KS_ISR, handled); - if (status & IRQ_RXI) { /* the datasheet says to disable the rx interrupt during * packet read-out, however we're masking the interrupt * from the device so do not bother masking just the RX * from the device. */ - ks8851_rx_pkts(ks); + __skb_queue_head_init(&rxq); + ks8851_rx_pkts(ks, &rxq); } /* if something stopped the rx process, probably due to wanting @@ -416,6 +394,10 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) if (status & IRQ_LCI) mii_check_link(&ks->mii); + if (status & IRQ_RXI) + while ((skb = __skb_dequeue(&rxq))) + netif_rx(skb); + return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c index 2a7f298542670..381b9cd285ebd 100644 --- a/drivers/net/ethernet/micrel/ks8851_par.c +++ b/drivers/net/ethernet/micrel/ks8851_par.c @@ -210,16 +210,6 @@ static void ks8851_wrfifo_par(struct ks8851_net *ks, struct sk_buff *txp, iowrite16_rep(ksp->hw_addr, txp->data, len / 2); } -/** - * ks8851_rx_skb_par - receive skbuff - * @ks: The device state. - * @skb: The skbuff - */ -static void ks8851_rx_skb_par(struct ks8851_net *ks, struct sk_buff *skb) -{ - netif_rx(skb); -} - static unsigned int ks8851_rdreg16_par_txqcr(struct ks8851_net *ks) { return ks8851_rdreg16_par(ks, KS_TXQCR); @@ -298,7 +288,6 @@ static int ks8851_probe_par(struct platform_device *pdev) ks->rdfifo = ks8851_rdfifo_par; ks->wrfifo = ks8851_wrfifo_par; ks->start_xmit = ks8851_start_xmit_par; - ks->rx_skb = ks8851_rx_skb_par; #define STD_IRQ (IRQ_LCI | /* Link Change */ \ IRQ_RXI | /* RX done */ \ diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 54f2eac11a631..55f6f9f6d030e 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -298,16 +298,6 @@ static unsigned int calc_txlen(unsigned int len) return ALIGN(len + 4, 4); } -/** - * ks8851_rx_skb_spi - receive skbuff - * @ks: The device state - * @skb: The skbuff - */ -static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb) -{ - netif_rx(skb); -} - /** * ks8851_tx_work - process tx packet(s) * @work: The work strucutre what was scheduled. @@ -435,7 +425,6 @@ static int ks8851_probe_spi(struct spi_device *spi) ks->rdfifo = ks8851_rdfifo_spi; ks->wrfifo = ks8851_wrfifo_spi; ks->start_xmit = ks8851_start_xmit_spi; - ks->rx_skb = ks8851_rx_skb_spi; ks->flush_tx_work = ks8851_flush_tx_work_spi; #define STD_IRQ (IRQ_LCI | /* Link Change */ \ diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index a2b3f4433ca8f..60671f33fd718 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1148,8 +1148,12 @@ static void lan743x_ethtool_get_wol(struct net_device *netdev, if (netdev->phydev) phy_ethtool_get_wol(netdev->phydev, wol); - wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | - WAKE_MAGIC | WAKE_PHY | WAKE_ARP; + if (wol->supported != adapter->phy_wol_supported) + netif_warn(adapter, drv, adapter->netdev, + "PHY changed its supported WOL! old=%x, new=%x\n", + adapter->phy_wol_supported, wol->supported); + + wol->supported |= MAC_SUPPORTED_WAKES; if (adapter->is_pci11x1x) wol->supported |= WAKE_MAGICSECURE; @@ -1164,7 +1168,39 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, { struct lan743x_adapter *adapter = netdev_priv(netdev); + /* WAKE_MAGICSEGURE is a modifier of and only valid together with + * WAKE_MAGIC + */ + if ((wol->wolopts & WAKE_MAGICSECURE) && !(wol->wolopts & WAKE_MAGIC)) + return -EINVAL; + + if (netdev->phydev) { + struct ethtool_wolinfo phy_wol; + int ret; + + phy_wol.wolopts = wol->wolopts & adapter->phy_wol_supported; + + /* If WAKE_MAGICSECURE was requested, filter out WAKE_MAGIC + * for PHYs that do not support WAKE_MAGICSECURE + */ + if (wol->wolopts & WAKE_MAGICSECURE && + !(adapter->phy_wol_supported & WAKE_MAGICSECURE)) + phy_wol.wolopts &= ~WAKE_MAGIC; + + ret = phy_ethtool_set_wol(netdev->phydev, &phy_wol); + if (ret && (ret != -EOPNOTSUPP)) + return ret; + + if (ret == -EOPNOTSUPP) + adapter->phy_wolopts = 0; + else + adapter->phy_wolopts = phy_wol.wolopts; + } else { + adapter->phy_wolopts = 0; + } + adapter->wolopts = 0; + wol->wolopts &= ~adapter->phy_wolopts; if (wol->wolopts & WAKE_UCAST) adapter->wolopts |= WAKE_UCAST; if (wol->wolopts & WAKE_MCAST) @@ -1185,10 +1221,10 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, memset(adapter->sopass, 0, sizeof(u8) * SOPASS_MAX); } + wol->wolopts = adapter->wolopts | adapter->phy_wolopts; device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts); - return netdev->phydev ? phy_ethtool_set_wol(netdev->phydev, wol) - : -ENETDOWN; + return 0; } #endif /* CONFIG_PM */ diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 45e209a7d0831..6f690d96d41e3 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -25,6 +25,8 @@ #define PCS_POWER_STATE_DOWN 0x6 #define PCS_POWER_STATE_UP 0x4 +#define RFE_RD_FIFO_TH_3_DWORDS 0x3 + static void pci11x1x_strap_get_status(struct lan743x_adapter *adapter) { u32 chip_rev; @@ -3109,6 +3111,17 @@ static int lan743x_netdev_open(struct net_device *netdev) if (ret) goto close_tx; } + +#ifdef CONFIG_PM + if (adapter->netdev->phydev) { + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + + phy_ethtool_get_wol(netdev->phydev, &wol); + adapter->phy_wol_supported = wol.supported; + adapter->phy_wolopts = wol.wolopts; + } +#endif + return 0; close_tx: @@ -3272,6 +3285,21 @@ static void lan743x_full_cleanup(struct lan743x_adapter *adapter) lan743x_pci_cleanup(adapter); } +static void pci11x1x_set_rfe_rd_fifo_threshold(struct lan743x_adapter *adapter) +{ + u16 rev = adapter->csr.id_rev & ID_REV_CHIP_REV_MASK_; + + if (rev == ID_REV_CHIP_REV_PCI11X1X_B0_) { + u32 misc_ctl; + + misc_ctl = lan743x_csr_read(adapter, MISC_CTL_0); + misc_ctl &= ~MISC_CTL_0_RFE_READ_FIFO_MASK_; + misc_ctl |= FIELD_PREP(MISC_CTL_0_RFE_READ_FIFO_MASK_, + RFE_RD_FIFO_TH_3_DWORDS); + lan743x_csr_write(adapter, MISC_CTL_0, misc_ctl); + } +} + static int lan743x_hardware_init(struct lan743x_adapter *adapter, struct pci_dev *pdev) { @@ -3287,6 +3315,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, pci11x1x_strap_get_status(adapter); spin_lock_init(&adapter->eth_syslock_spinlock); mutex_init(&adapter->sgmii_rw_lock); + pci11x1x_set_rfe_rd_fifo_threshold(adapter); } else { adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS; adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS; @@ -3550,7 +3579,7 @@ static void lan743x_pm_set_wol(struct lan743x_adapter *adapter) /* clear wake settings */ pmtctl = lan743x_csr_read(adapter, PMT_CTL); - pmtctl |= PMT_CTL_WUPS_MASK_; + pmtctl |= PMT_CTL_WUPS_MASK_ | PMT_CTL_RES_CLR_WKP_MASK_; pmtctl &= ~(PMT_CTL_GPIO_WAKEUP_EN_ | PMT_CTL_EEE_WAKEUP_EN_ | PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_ | PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_ | PMT_CTL_ETH_PHY_WAKE_EN_); @@ -3562,10 +3591,9 @@ static void lan743x_pm_set_wol(struct lan743x_adapter *adapter) pmtctl |= PMT_CTL_ETH_PHY_D3_COLD_OVR_ | PMT_CTL_ETH_PHY_D3_OVR_; - if (adapter->wolopts & WAKE_PHY) { - pmtctl |= PMT_CTL_ETH_PHY_EDPD_PLL_CTL_; + if (adapter->phy_wolopts) pmtctl |= PMT_CTL_ETH_PHY_WAKE_EN_; - } + if (adapter->wolopts & WAKE_MAGIC) { wucsr |= MAC_WUCSR_MPEN_; macrx |= MAC_RX_RXEN_; @@ -3661,7 +3689,7 @@ static int lan743x_pm_suspend(struct device *dev) lan743x_csr_write(adapter, MAC_WUCSR2, 0); lan743x_csr_write(adapter, MAC_WK_SRC, 0xFFFFFFFF); - if (adapter->wolopts) + if (adapter->wolopts || adapter->phy_wolopts) lan743x_pm_set_wol(adapter); if (adapter->is_pci11x1x) { @@ -3685,6 +3713,7 @@ static int lan743x_pm_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct lan743x_adapter *adapter = netdev_priv(netdev); + u32 data; int ret; pci_set_power_state(pdev, PCI_D0); @@ -3703,6 +3732,30 @@ static int lan743x_pm_resume(struct device *dev) return ret; } + ret = lan743x_csr_read(adapter, MAC_WK_SRC); + netif_dbg(adapter, drv, adapter->netdev, + "Wakeup source : 0x%08X\n", ret); + + /* Clear the wol configuration and status bits. Note that + * the status bits are "Write One to Clear (W1C)" + */ + data = MAC_WUCSR_EEE_TX_WAKE_ | MAC_WUCSR_EEE_RX_WAKE_ | + MAC_WUCSR_RFE_WAKE_FR_ | MAC_WUCSR_PFDA_FR_ | MAC_WUCSR_WUFR_ | + MAC_WUCSR_MPR_ | MAC_WUCSR_BCAST_FR_; + lan743x_csr_write(adapter, MAC_WUCSR, data); + + data = MAC_WUCSR2_NS_RCD_ | MAC_WUCSR2_ARP_RCD_ | + MAC_WUCSR2_IPV6_TCPSYN_RCD_ | MAC_WUCSR2_IPV4_TCPSYN_RCD_; + lan743x_csr_write(adapter, MAC_WUCSR2, data); + + data = MAC_WK_SRC_ETH_PHY_WK_ | MAC_WK_SRC_IPV6_TCPSYN_RCD_WK_ | + MAC_WK_SRC_IPV4_TCPSYN_RCD_WK_ | MAC_WK_SRC_EEE_TX_WK_ | + MAC_WK_SRC_EEE_RX_WK_ | MAC_WK_SRC_RFE_FR_WK_ | + MAC_WK_SRC_PFDA_FR_WK_ | MAC_WK_SRC_MP_FR_WK_ | + MAC_WK_SRC_BCAST_FR_WK_ | MAC_WK_SRC_WU_FR_WK_ | + MAC_WK_SRC_WK_FR_SAVED_; + lan743x_csr_write(adapter, MAC_WK_SRC, data); + /* open netdev when netdev is at running state while resume. * For instance, it is true when system wakesup after pm-suspend * However, it is false when system wakes up after suspend GUI menu @@ -3711,9 +3764,6 @@ static int lan743x_pm_resume(struct device *dev) lan743x_netdev_open(netdev); netif_device_attach(netdev); - ret = lan743x_csr_read(adapter, MAC_WK_SRC); - netif_info(adapter, drv, adapter->netdev, - "Wakeup source : 0x%08X\n", ret); return 0; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index be79cb0ae5af3..3b2585a384e2c 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -26,6 +26,7 @@ #define ID_REV_CHIP_REV_MASK_ (0x0000FFFF) #define ID_REV_CHIP_REV_A0_ (0x00000000) #define ID_REV_CHIP_REV_B0_ (0x00000010) +#define ID_REV_CHIP_REV_PCI11X1X_B0_ (0x000000B0) #define FPGA_REV (0x04) #define FPGA_REV_GET_MINOR_(fpga_rev) (((fpga_rev) >> 8) & 0x000000FF) @@ -60,6 +61,7 @@ #define PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_ BIT(18) #define PMT_CTL_GPIO_WAKEUP_EN_ BIT(15) #define PMT_CTL_EEE_WAKEUP_EN_ BIT(13) +#define PMT_CTL_RES_CLR_WKP_MASK_ GENMASK(9, 8) #define PMT_CTL_READY_ BIT(7) #define PMT_CTL_ETH_PHY_RST_ BIT(4) #define PMT_CTL_WOL_EN_ BIT(3) @@ -226,12 +228,31 @@ #define MAC_WUCSR (0x140) #define MAC_MP_SO_EN_ BIT(21) #define MAC_WUCSR_RFE_WAKE_EN_ BIT(14) +#define MAC_WUCSR_EEE_TX_WAKE_ BIT(13) +#define MAC_WUCSR_EEE_RX_WAKE_ BIT(11) +#define MAC_WUCSR_RFE_WAKE_FR_ BIT(9) +#define MAC_WUCSR_PFDA_FR_ BIT(7) +#define MAC_WUCSR_WUFR_ BIT(6) +#define MAC_WUCSR_MPR_ BIT(5) +#define MAC_WUCSR_BCAST_FR_ BIT(4) #define MAC_WUCSR_PFDA_EN_ BIT(3) #define MAC_WUCSR_WAKE_EN_ BIT(2) #define MAC_WUCSR_MPEN_ BIT(1) #define MAC_WUCSR_BCST_EN_ BIT(0) #define MAC_WK_SRC (0x144) +#define MAC_WK_SRC_ETH_PHY_WK_ BIT(17) +#define MAC_WK_SRC_IPV6_TCPSYN_RCD_WK_ BIT(16) +#define MAC_WK_SRC_IPV4_TCPSYN_RCD_WK_ BIT(15) +#define MAC_WK_SRC_EEE_TX_WK_ BIT(14) +#define MAC_WK_SRC_EEE_RX_WK_ BIT(13) +#define MAC_WK_SRC_RFE_FR_WK_ BIT(12) +#define MAC_WK_SRC_PFDA_FR_WK_ BIT(11) +#define MAC_WK_SRC_MP_FR_WK_ BIT(10) +#define MAC_WK_SRC_BCAST_FR_WK_ BIT(9) +#define MAC_WK_SRC_WU_FR_WK_ BIT(8) +#define MAC_WK_SRC_WK_FR_SAVED_ BIT(7) + #define MAC_MP_SO_HI (0x148) #define MAC_MP_SO_LO (0x14C) @@ -294,6 +315,10 @@ #define RFE_INDX(index) (0x580 + (index << 2)) #define MAC_WUCSR2 (0x600) +#define MAC_WUCSR2_NS_RCD_ BIT(7) +#define MAC_WUCSR2_ARP_RCD_ BIT(6) +#define MAC_WUCSR2_IPV6_TCPSYN_RCD_ BIT(5) +#define MAC_WUCSR2_IPV4_TCPSYN_RCD_ BIT(4) #define SGMII_ACC (0x720) #define SGMII_ACC_SGMII_BZY_ BIT(31) @@ -311,6 +336,9 @@ #define SGMII_CTL_LINK_STATUS_SOURCE_ BIT(8) #define SGMII_CTL_SGMII_POWER_DN_ BIT(1) +#define MISC_CTL_0 (0x920) +#define MISC_CTL_0_RFE_READ_FIFO_MASK_ GENMASK(6, 4) + /* Vendor Specific SGMII MMD details */ #define SR_VSMMD_PCS_ID1 0x0004 #define SR_VSMMD_PCS_ID2 0x0005 @@ -1014,6 +1042,8 @@ enum lan743x_sgmii_lsd { LINK_2500_SLAVE }; +#define MAC_SUPPORTED_WAKES (WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | \ + WAKE_MAGIC | WAKE_ARP) struct lan743x_adapter { struct net_device *netdev; struct mii_bus *mdiobus; @@ -1021,6 +1051,8 @@ struct lan743x_adapter { #ifdef CONFIG_PM u32 wolopts; u8 sopass[SOPASS_MAX]; + u32 phy_wolopts; + u32 phy_wol_supported; #endif struct pci_dev *pdev; struct lan743x_csr csr; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 2635ef8958c80..6695ed661ef83 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -474,14 +474,14 @@ static int lan966x_port_hwtstamp_set(struct net_device *dev, cfg->source != HWTSTAMP_SOURCE_PHYLIB) return -EOPNOTSUPP; + if (cfg->source == HWTSTAMP_SOURCE_NETDEV && !port->lan966x->ptp) + return -EOPNOTSUPP; + err = lan966x_ptp_setup_traps(port, cfg); if (err) return err; if (cfg->source == HWTSTAMP_SOURCE_NETDEV) { - if (!port->lan966x->ptp) - return -EOPNOTSUPP; - err = lan966x_ptp_hwtstamp_set(port, cfg, extack); if (err) { lan966x_ptp_del_traps(port); @@ -1087,8 +1087,6 @@ static int lan966x_probe(struct platform_device *pdev) platform_set_drvdata(pdev, lan966x); lan966x->dev = &pdev->dev; - lan966x->debugfs_root = debugfs_create_dir("lan966x", NULL); - if (!device_get_mac_address(&pdev->dev, mac_addr)) { ether_addr_copy(lan966x->base_mac, mac_addr); } else { @@ -1179,6 +1177,8 @@ static int lan966x_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, -ENODEV, "no ethernet-ports child found\n"); + lan966x->debugfs_root = debugfs_create_dir("lan966x", NULL); + /* init switch */ lan966x_init(lan966x); lan966x_stats_init(lan966x); @@ -1257,6 +1257,8 @@ static int lan966x_probe(struct platform_device *pdev) destroy_workqueue(lan966x->stats_queue); mutex_destroy(&lan966x->stats_lock); + debugfs_remove_recursive(lan966x->debugfs_root); + return err; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 3a1b1a1f5a195..60dd2fd603a85 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -731,7 +731,7 @@ static int sparx5_port_pcs_low_set(struct sparx5 *sparx5, bool sgmii = false, inband_aneg = false; int err; - if (port->conf.inband) { + if (conf->inband) { if (conf->portmode == PHY_INTERFACE_MODE_SGMII || conf->portmode == PHY_INTERFACE_MODE_QSGMII) inband_aneg = true; /* Cisco-SGMII in-band-aneg */ @@ -948,7 +948,7 @@ int sparx5_port_pcs_set(struct sparx5 *sparx5, if (err) return -EINVAL; - if (port->conf.inband) { + if (conf->inband) { /* Enable/disable 1G counters in ASM */ spx5_rmw(ASM_PORT_CFG_CSC_STAT_DIS_SET(high_speed_dev), ASM_PORT_CFG_CSC_STAT_DIS, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 523e0c470894f..55f255a3c9db6 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -36,6 +36,27 @@ struct sparx5_tc_flower_template { u16 l3_proto; /* protocol specified in the template */ }; +/* SparX-5 VCAP fragment types: + * 0 = no fragment, 1 = initial fragment, + * 2 = suspicious fragment, 3 = valid follow-up fragment + */ +enum { /* key / mask */ + FRAG_NOT = 0x03, /* 0 / 3 */ + FRAG_SOME = 0x11, /* 1 / 1 */ + FRAG_FIRST = 0x13, /* 1 / 3 */ + FRAG_LATER = 0x33, /* 3 / 3 */ + FRAG_INVAL = 0xff, /* invalid */ +}; + +/* Flower fragment flag to VCAP fragment type mapping */ +static const u8 sparx5_vcap_frag_map[4][4] = { /* is_frag */ + { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_FIRST }, /* 0/0 */ + { FRAG_NOT, FRAG_NOT, FRAG_INVAL, FRAG_INVAL }, /* 0/1 */ + { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_INVAL }, /* 1/0 */ + { FRAG_SOME, FRAG_LATER, FRAG_INVAL, FRAG_FIRST } /* 1/1 */ + /* 0/0 0/1 1/0 1/1 <-- first_frag */ +}; + static int sparx5_tc_flower_es0_tpid(struct vcap_tc_flower_parse_usage *st) { @@ -145,29 +166,27 @@ sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) flow_rule_match_control(st->frule, &mt); if (mt.mask->flags) { - if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { - if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { - value = 1; /* initial fragment */ - mask = 0x3; - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } - } - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } + u8 is_frag_key = !!(mt.key->flags & FLOW_DIS_IS_FRAGMENT); + u8 is_frag_mask = !!(mt.mask->flags & FLOW_DIS_IS_FRAGMENT); + u8 is_frag_idx = (is_frag_key << 1) | is_frag_mask; + + u8 first_frag_key = !!(mt.key->flags & FLOW_DIS_FIRST_FRAG); + u8 first_frag_mask = !!(mt.mask->flags & FLOW_DIS_FIRST_FRAG); + u8 first_frag_idx = (first_frag_key << 1) | first_frag_mask; + + /* Lookup verdict based on the 2 + 2 input bits */ + u8 vdt = sparx5_vcap_frag_map[is_frag_idx][first_frag_idx]; + + if (vdt == FRAG_INVAL) { + NL_SET_ERR_MSG_MOD(st->fco->common.extack, + "Match on invalid fragment flag combination"); + return -EINVAL; } + /* Extract VCAP fragment key and mask from verdict */ + value = (vdt >> 4) & 0x3; + mask = vdt & 0x3; + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_FRAGMENT_TYPE, value, mask); diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 2729a2c5acf9c..ca814fe8a775b 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -848,7 +848,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, } if (!wait_for_completion_timeout(&ctx->comp_event, - (msecs_to_jiffies(hwc->hwc_timeout) * HZ))) { + (msecs_to_jiffies(hwc->hwc_timeout)))) { dev_err(hwc->dev, "HWC: Request timed out!\n"); err = -ETIMEDOUT; goto out; diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 59287c6e6cee6..d8af5e7e15b4d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -601,7 +601,7 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; - *datasize = ALIGN(mtu + ETH_HLEN, MANA_RX_DATA_ALIGN); + *datasize = mtu + ETH_HLEN; } static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c index 361d7c495e2d8..2c7bd6e80d993 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c @@ -337,6 +337,11 @@ static void nfp_fl_lag_do_work(struct work_struct *work) acti_netdevs = kmalloc_array(entry->slave_cnt, sizeof(*acti_netdevs), GFP_KERNEL); + if (!acti_netdevs) { + schedule_delayed_work(&lag->work, + NFP_FL_LAG_DELAY); + continue; + } /* Include sanity check in the loop. It may be that a bond has * changed between processing the last notification and the diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index fcb44ceeb6aa5..1294e249ce66d 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -296,10 +296,8 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) if (ret) return ret; - if (qcq->napi.poll) - napi_enable(&qcq->napi); - if (qcq->flags & IONIC_QCQ_F_INTR) { + napi_enable(&qcq->napi); irq_set_affinity_hint(qcq->intr.vector, &qcq->intr.affinity_mask); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, @@ -3391,9 +3389,12 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) napi_enable(&qcq->napi); - if (qcq->flags & IONIC_QCQ_F_INTR) + if (qcq->flags & IONIC_QCQ_F_INTR) { + irq_set_affinity_hint(qcq->intr.vector, + &qcq->intr.affinity_mask); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); + } qcq->flags |= IONIC_QCQ_F_INITED; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index c278f8893042b..8159b4c315b5d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1206,7 +1206,6 @@ static void qed_slowpath_task(struct work_struct *work) static int qed_slowpath_wq_start(struct qed_dev *cdev) { struct qed_hwfn *hwfn; - char name[NAME_SIZE]; int i; if (IS_VF(cdev)) @@ -1215,11 +1214,11 @@ static int qed_slowpath_wq_start(struct qed_dev *cdev) for_each_hwfn(cdev, i) { hwfn = &cdev->hwfns[i]; - snprintf(name, NAME_SIZE, "slowpath-%02x:%02x.%02x", - cdev->pdev->bus->number, - PCI_SLOT(cdev->pdev->devfn), hwfn->abs_pf_id); + hwfn->slowpath_wq = alloc_workqueue("slowpath-%02x:%02x.%02x", + 0, 0, cdev->pdev->bus->number, + PCI_SLOT(cdev->pdev->devfn), + hwfn->abs_pf_id); - hwfn->slowpath_wq = alloc_workqueue(name, 0, 0); if (!hwfn->slowpath_wq) { DP_NOTICE(hwfn, "Cannot create slowpath workqueue\n"); return -ENOMEM; diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index a5ac21a0ee33f..cb6b33a228ea2 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1868,8 +1868,8 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, struct flow_cls_offload *f) { struct qede_arfs_fltr_node *n; - int min_hlen, rc = -EINVAL; struct qede_arfs_tuple t; + int min_hlen, rc; __qede_lock(edev); @@ -1879,7 +1879,8 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, } /* parse flower attribute and prepare filter */ - if (qede_parse_flow_attr(edev, proto, f->rule, &t)) + rc = qede_parse_flow_attr(edev, proto, f->rule, &t); + if (rc) goto unlock; /* Validate profile mode and number of filters */ @@ -1888,11 +1889,13 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, DP_NOTICE(edev, "Filter configuration invalidated, filter mode=0x%x, configured mode=0x%x, filter count=0x%x\n", t.mode, edev->arfs->mode, edev->arfs->filter_count); + rc = -EINVAL; goto unlock; } /* parse tc actions and get the vf_id */ - if (qede_parse_actions(edev, &f->rule->action, f->common.extack)) + rc = qede_parse_actions(edev, &f->rule->action, f->common.extack); + if (rc) goto unlock; if (qede_flow_find_fltr(edev, &t)) { @@ -1998,10 +2001,9 @@ static int qede_flow_spec_to_rule(struct qede_dev *edev, if (IS_ERR(flow)) return PTR_ERR(flow); - if (qede_parse_flow_attr(edev, proto, flow->rule, t)) { - err = -EINVAL; + err = qede_parse_flow_attr(edev, proto, flow->rule, t); + if (err) goto err_out; - } /* Make sure location is valid and filter isn't already set */ err = qede_flow_spec_validate(edev, &flow->rule->action, t, diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index 1822f2ad8f0dd..2ac1b1b96e6a4 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -111,10 +111,8 @@ qcaspi_info_show(struct seq_file *s, void *what) seq_printf(s, "IRQ : %d\n", qca->spi_dev->irq); - seq_printf(s, "INTR REQ : %u\n", - qca->intr_req); - seq_printf(s, "INTR SVC : %u\n", - qca->intr_svc); + seq_printf(s, "INTR : %lx\n", + qca->intr); seq_printf(s, "SPI max speed : %lu\n", (unsigned long)qca->spi_dev->max_speed_hz); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 5f3c11fb3fa27..b697a9e6face6 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -48,6 +48,8 @@ #define MAX_DMA_BURST_LEN 5000 +#define SPI_INTR 0 + /* Modules parameters */ #define QCASPI_CLK_SPEED_MIN 1000000 #define QCASPI_CLK_SPEED_MAX 16000000 @@ -592,14 +594,14 @@ qcaspi_spi_thread(void *data) continue; } - if ((qca->intr_req == qca->intr_svc) && + if (!test_bit(SPI_INTR, &qca->intr) && !qca->txr.skb[qca->txr.head]) schedule(); set_current_state(TASK_RUNNING); - netdev_dbg(qca->net_dev, "have work to do. int: %d, tx_skb: %p\n", - qca->intr_req - qca->intr_svc, + netdev_dbg(qca->net_dev, "have work to do. int: %lu, tx_skb: %p\n", + qca->intr, qca->txr.skb[qca->txr.head]); qcaspi_qca7k_sync(qca, QCASPI_EVENT_UPDATE); @@ -613,8 +615,7 @@ qcaspi_spi_thread(void *data) msleep(QCASPI_QCA7K_REBOOT_TIME_MS); } - if (qca->intr_svc != qca->intr_req) { - qca->intr_svc = qca->intr_req; + if (test_and_clear_bit(SPI_INTR, &qca->intr)) { start_spi_intr_handling(qca, &intr_cause); if (intr_cause & SPI_INT_CPU_ON) { @@ -676,7 +677,7 @@ qcaspi_intr_handler(int irq, void *data) { struct qcaspi *qca = data; - qca->intr_req++; + set_bit(SPI_INTR, &qca->intr); if (qca->spi_thread) wake_up_process(qca->spi_thread); @@ -692,8 +693,7 @@ qcaspi_netdev_open(struct net_device *dev) if (!qca) return -EINVAL; - qca->intr_req = 1; - qca->intr_svc = 0; + set_bit(SPI_INTR, &qca->intr); qca->sync = QCASPI_SYNC_UNKNOWN; qcafrm_fsm_init_spi(&qca->frm_handle); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index 3067356106f0b..58ad910068d4b 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -93,8 +93,7 @@ struct qcaspi { struct qcafrm_handle frm_handle; struct sk_buff *rx_skb; - unsigned int intr_req; - unsigned int intr_svc; + unsigned long intr; u16 reset_count; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h index 81567fcf39579..1ef39928757bd 100644 --- a/drivers/net/ethernet/realtek/r8169.h +++ b/drivers/net/ethernet/realtek/r8169.h @@ -72,6 +72,7 @@ enum mac_version { }; struct rtl8169_private; +struct r8169_led_classdev; void r8169_apply_firmware(struct rtl8169_private *tp); u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp); @@ -83,4 +84,5 @@ void r8169_get_led_name(struct rtl8169_private *tp, int idx, char *buf, int buf_len); int rtl8168_get_led_mode(struct rtl8169_private *tp); int rtl8168_led_mod_ctrl(struct rtl8169_private *tp, u16 mask, u16 val); -void rtl8168_init_leds(struct net_device *ndev); +struct r8169_led_classdev *rtl8168_init_leds(struct net_device *ndev); +void r8169_remove_leds(struct r8169_led_classdev *leds); diff --git a/drivers/net/ethernet/realtek/r8169_leds.c b/drivers/net/ethernet/realtek/r8169_leds.c index 007d077edcad7..1c97f3cca22a1 100644 --- a/drivers/net/ethernet/realtek/r8169_leds.c +++ b/drivers/net/ethernet/realtek/r8169_leds.c @@ -138,20 +138,31 @@ static void rtl8168_setup_ldev(struct r8169_led_classdev *ldev, led_cdev->hw_control_get_device = r8169_led_hw_control_get_device; /* ignore errors */ - devm_led_classdev_register(&ndev->dev, led_cdev); + led_classdev_register(&ndev->dev, led_cdev); } -void rtl8168_init_leds(struct net_device *ndev) +struct r8169_led_classdev *rtl8168_init_leds(struct net_device *ndev) { - /* bind resource mgmt to netdev */ - struct device *dev = &ndev->dev; struct r8169_led_classdev *leds; int i; - leds = devm_kcalloc(dev, RTL8168_NUM_LEDS, sizeof(*leds), GFP_KERNEL); + leds = kcalloc(RTL8168_NUM_LEDS + 1, sizeof(*leds), GFP_KERNEL); if (!leds) - return; + return NULL; for (i = 0; i < RTL8168_NUM_LEDS; i++) rtl8168_setup_ldev(leds + i, ndev, i); + + return leds; +} + +void r8169_remove_leds(struct r8169_led_classdev *leds) +{ + if (!leds) + return; + + for (struct r8169_led_classdev *l = leds; l->ndev; l++) + led_classdev_unregister(&l->led); + + kfree(leds); } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index dd73df6b17b06..151007f43b6a2 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -634,6 +635,8 @@ struct rtl8169_private { const char *fw_name; struct rtl_fw *rtl_fw; + struct r8169_led_classdev *leds; + u32 ocp_base; }; @@ -1255,17 +1258,40 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp) RTL_W8(tp, IBCR0, RTL_R8(tp, IBCR0) & ~0x01); } +static void rtl_dash_loop_wait(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long usecs, int n, bool high) +{ + if (!tp->dash_enabled) + return; + rtl_loop_wait(tp, c, usecs, n, high); +} + +static void rtl_dash_loop_wait_high(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long d, int n) +{ + rtl_dash_loop_wait(tp, c, d, n, true); +} + +static void rtl_dash_loop_wait_low(struct rtl8169_private *tp, + const struct rtl_cond *c, + unsigned long d, int n) +{ + rtl_dash_loop_wait(tp, c, d, n, false); +} + static void rtl8168dp_driver_start(struct rtl8169_private *tp) { r8168dp_oob_notify(tp, OOB_CMD_DRIVER_START); - rtl_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10000, 10); } static void rtl8168ep_driver_start(struct rtl8169_private *tp) { r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); + rtl_dash_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); } static void rtl8168_driver_start(struct rtl8169_private *tp) @@ -1279,7 +1305,7 @@ static void rtl8168_driver_start(struct rtl8169_private *tp) static void rtl8168dp_driver_stop(struct rtl8169_private *tp) { r8168dp_oob_notify(tp, OOB_CMD_DRIVER_STOP); - rtl_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10000, 10); } static void rtl8168ep_driver_stop(struct rtl8169_private *tp) @@ -1287,7 +1313,7 @@ static void rtl8168ep_driver_stop(struct rtl8169_private *tp) rtl8168ep_stop_cmac(tp); r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10); + rtl_dash_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10000, 10); } static void rtl8168_driver_stop(struct rtl8169_private *tp) @@ -4196,11 +4222,11 @@ static void rtl8169_doorbell(struct rtl8169_private *tp) static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct net_device *dev) { - unsigned int frags = skb_shinfo(skb)->nr_frags; struct rtl8169_private *tp = netdev_priv(dev); unsigned int entry = tp->cur_tx % NUM_TX_DESC; struct TxDesc *txd_first, *txd_last; bool stop_queue, door_bell; + unsigned int frags; u32 opts[2]; if (unlikely(!rtl_tx_slots_avail(tp))) { @@ -4223,6 +4249,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, txd_first = tp->TxDescArray + entry; + frags = skb_shinfo(skb)->nr_frags; if (frags) { if (rtl8169_xmit_frags(tp, skb, opts, entry)) goto err_dma_1; @@ -4516,10 +4543,8 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING); } - if (napi_schedule_prep(&tp->napi)) { - rtl_irq_disable(tp); - __napi_schedule(&tp->napi); - } + rtl_irq_disable(tp); + napi_schedule(&tp->napi); out: rtl_ack_events(tp, status); @@ -4907,6 +4932,9 @@ static void rtl_remove_one(struct pci_dev *pdev) cancel_work_sync(&tp->wk.work); + if (IS_ENABLED(CONFIG_R8169_LEDS)) + r8169_remove_leds(tp->leds); + unregister_netdev(tp->dev); if (tp->dash_type != RTL_DASH_NONE) @@ -5027,6 +5055,15 @@ static int r8169_mdio_register(struct rtl8169_private *tp) struct mii_bus *new_bus; int ret; + /* On some boards with this chip version the BIOS is buggy and misses + * to reset the PHY page selector. This results in the PHY ID read + * accessing registers on a different page, returning a more or + * less random value. Fix this by resetting the page selector first. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_25 || + tp->mac_version == RTL_GIGA_MAC_VER_26) + r8169_mdio_write(tp, 0x1f, 0); + new_bus = devm_mdiobus_alloc(&pdev->dev); if (!new_bus) return -ENOMEM; @@ -5164,11 +5201,87 @@ static void rtl_init_mac_address(struct rtl8169_private *tp) rtl_rar_set(tp, mac_addr); } +static bool rtl_aspm_dell_workaround(struct rtl8169_private *tp) +{ + static const struct dmi_system_id sysids[] = { + { + .ident = "Dell", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 16 5640"), + DMI_MATCH(DMI_PRODUCT_SKU, "0CA0"), + }, + }, + { + .ident = "Dell", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 14 3440"), + DMI_MATCH(DMI_PRODUCT_SKU, "0CA5"), + }, + }, + { + .ident = "Dell", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 14 3440"), + DMI_MATCH(DMI_PRODUCT_SKU, "0CA6"), + }, + }, + { + .ident = "Dell", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3450"), + DMI_MATCH(DMI_PRODUCT_SKU, "0C99"), + }, + }, + { + .ident = "Dell", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3450"), + DMI_MATCH(DMI_PRODUCT_SKU, "0C97"), + }, + }, + { + .ident = "Dell", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3550"), + DMI_MATCH(DMI_PRODUCT_SKU, "0C9A"), + }, + }, + { + .ident = "Dell", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3550"), + DMI_MATCH(DMI_PRODUCT_SKU, "0C98"), + }, + }, + {} + }; + + if (tp->mac_version == RTL_GIGA_MAC_VER_46 && dmi_check_system(sysids)) + return true; + + return false; +} + /* register is set if system vendor successfully tested ASPM 1.2 */ static bool rtl_aspm_is_safe(struct rtl8169_private *tp) { + /* definition of 0xc0b2, + * 0: L1 + * 1: ASPM L1.0 + * 2: ASPM L0s + * 3: CLKEREQ + * 4-7: Reserved + */ if (tp->mac_version >= RTL_GIGA_MAC_VER_61 && - r8168_mac_ocp_read(tp, 0xc0b2) & 0xf) + r8168_mac_ocp_read(tp, 0xc0b2) & 0xf || + rtl_aspm_dell_workaround(tp)) return true; return false; @@ -5359,7 +5472,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (IS_ENABLED(CONFIG_R8169_LEDS) && tp->mac_version > RTL_GIGA_MAC_VER_06 && tp->mac_version < RTL_GIGA_MAC_VER_61) - rtl8168_init_leds(dev); + tp->leds = rtl8168_init_leds(dev); netdev_info(dev, "%s, %pM, XID %03x, IRQ %d\n", rtl_chip_infos[chipset].name, dev->dev_addr, xid, tp->irq); diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index e0f8276cffedd..fd59155a70e1f 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -1060,8 +1060,10 @@ struct ravb_private { struct ravb_desc *desc_bat; dma_addr_t rx_desc_dma[NUM_RX_QUEUE]; dma_addr_t tx_desc_dma[NUM_TX_QUEUE]; - struct ravb_rx_desc *gbeth_rx_ring; - struct ravb_ex_rx_desc *rx_ring[NUM_RX_QUEUE]; + union { + struct ravb_rx_desc *desc; + struct ravb_ex_rx_desc *ex_desc; + } rx_ring[NUM_RX_QUEUE]; struct ravb_tx_desc *tx_ring[NUM_TX_QUEUE]; void *tx_align[NUM_TX_QUEUE]; struct sk_buff *rx_1st_skb; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index f7566cfa45ca3..853c2a0d4e259 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -250,11 +250,11 @@ static void ravb_rx_ring_free_gbeth(struct net_device *ndev, int q) unsigned int ring_size; unsigned int i; - if (!priv->gbeth_rx_ring) + if (!priv->rx_ring[q].desc) return; for (i = 0; i < priv->num_rx_ring[q]; i++) { - struct ravb_rx_desc *desc = &priv->gbeth_rx_ring[i]; + struct ravb_rx_desc *desc = &priv->rx_ring[q].desc[i]; if (!dma_mapping_error(ndev->dev.parent, le32_to_cpu(desc->dptr))) @@ -264,9 +264,9 @@ static void ravb_rx_ring_free_gbeth(struct net_device *ndev, int q) DMA_FROM_DEVICE); } ring_size = sizeof(struct ravb_rx_desc) * (priv->num_rx_ring[q] + 1); - dma_free_coherent(ndev->dev.parent, ring_size, priv->gbeth_rx_ring, + dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q].desc, priv->rx_desc_dma[q]); - priv->gbeth_rx_ring = NULL; + priv->rx_ring[q].desc = NULL; } static void ravb_rx_ring_free_rcar(struct net_device *ndev, int q) @@ -275,11 +275,11 @@ static void ravb_rx_ring_free_rcar(struct net_device *ndev, int q) unsigned int ring_size; unsigned int i; - if (!priv->rx_ring[q]) + if (!priv->rx_ring[q].ex_desc) return; for (i = 0; i < priv->num_rx_ring[q]; i++) { - struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i]; + struct ravb_ex_rx_desc *desc = &priv->rx_ring[q].ex_desc[i]; if (!dma_mapping_error(ndev->dev.parent, le32_to_cpu(desc->dptr))) @@ -290,9 +290,9 @@ static void ravb_rx_ring_free_rcar(struct net_device *ndev, int q) } ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1); - dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q], + dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q].ex_desc, priv->rx_desc_dma[q]); - priv->rx_ring[q] = NULL; + priv->rx_ring[q].ex_desc = NULL; } /* Free skb's and DMA buffers for Ethernet AVB */ @@ -344,11 +344,11 @@ static void ravb_rx_ring_format_gbeth(struct net_device *ndev, int q) unsigned int i; rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q]; - memset(priv->gbeth_rx_ring, 0, rx_ring_size); + memset(priv->rx_ring[q].desc, 0, rx_ring_size); /* Build RX ring buffer */ for (i = 0; i < priv->num_rx_ring[q]; i++) { /* RX descriptor */ - rx_desc = &priv->gbeth_rx_ring[i]; + rx_desc = &priv->rx_ring[q].desc[i]; rx_desc->ds_cc = cpu_to_le16(GBETH_RX_DESC_DATA_SIZE); dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, GBETH_RX_BUFF_MAX, @@ -361,7 +361,7 @@ static void ravb_rx_ring_format_gbeth(struct net_device *ndev, int q) rx_desc->dptr = cpu_to_le32(dma_addr); rx_desc->die_dt = DT_FEMPTY; } - rx_desc = &priv->gbeth_rx_ring[i]; + rx_desc = &priv->rx_ring[q].desc[i]; rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]); rx_desc->die_dt = DT_LINKFIX; /* type */ } @@ -374,11 +374,11 @@ static void ravb_rx_ring_format_rcar(struct net_device *ndev, int q) dma_addr_t dma_addr; unsigned int i; - memset(priv->rx_ring[q], 0, rx_ring_size); + memset(priv->rx_ring[q].ex_desc, 0, rx_ring_size); /* Build RX ring buffer */ for (i = 0; i < priv->num_rx_ring[q]; i++) { /* RX descriptor */ - rx_desc = &priv->rx_ring[q][i]; + rx_desc = &priv->rx_ring[q].ex_desc[i]; rx_desc->ds_cc = cpu_to_le16(RX_BUF_SZ); dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, RX_BUF_SZ, @@ -391,7 +391,7 @@ static void ravb_rx_ring_format_rcar(struct net_device *ndev, int q) rx_desc->dptr = cpu_to_le32(dma_addr); rx_desc->die_dt = DT_FEMPTY; } - rx_desc = &priv->rx_ring[q][i]; + rx_desc = &priv->rx_ring[q].ex_desc[i]; rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]); rx_desc->die_dt = DT_LINKFIX; /* type */ } @@ -446,10 +446,10 @@ static void *ravb_alloc_rx_desc_gbeth(struct net_device *ndev, int q) ring_size = sizeof(struct ravb_rx_desc) * (priv->num_rx_ring[q] + 1); - priv->gbeth_rx_ring = dma_alloc_coherent(ndev->dev.parent, ring_size, - &priv->rx_desc_dma[q], - GFP_KERNEL); - return priv->gbeth_rx_ring; + priv->rx_ring[q].desc = dma_alloc_coherent(ndev->dev.parent, ring_size, + &priv->rx_desc_dma[q], + GFP_KERNEL); + return priv->rx_ring[q].desc; } static void *ravb_alloc_rx_desc_rcar(struct net_device *ndev, int q) @@ -459,10 +459,11 @@ static void *ravb_alloc_rx_desc_rcar(struct net_device *ndev, int q) ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1); - priv->rx_ring[q] = dma_alloc_coherent(ndev->dev.parent, ring_size, - &priv->rx_desc_dma[q], - GFP_KERNEL); - return priv->rx_ring[q]; + priv->rx_ring[q].ex_desc = dma_alloc_coherent(ndev->dev.parent, + ring_size, + &priv->rx_desc_dma[q], + GFP_KERNEL); + return priv->rx_ring[q].ex_desc; } /* Init skb and descriptor buffer for Ethernet AVB */ @@ -780,12 +781,15 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) int limit; int i; - entry = priv->cur_rx[q] % priv->num_rx_ring[q]; limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; stats = &priv->stats[q]; - desc = &priv->gbeth_rx_ring[entry]; - for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) { + for (i = 0; i < limit; i++, priv->cur_rx[q]++) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->rx_ring[q].desc[entry]; + if (rx_packets == *quota || desc->die_dt == DT_FEMPTY) + break; + /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; @@ -849,15 +853,12 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) break; } } - - entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->gbeth_rx_ring[entry]; } /* Refill the RX ring buffers. */ for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; - desc = &priv->gbeth_rx_ring[entry]; + desc = &priv->rx_ring[q].desc[entry]; desc->ds_cc = cpu_to_le16(GBETH_RX_DESC_DATA_SIZE); if (!priv->rx_skb[q][entry]) { @@ -893,30 +894,29 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - int entry = priv->cur_rx[q] % priv->num_rx_ring[q]; - int boguscnt = (priv->dirty_rx[q] + priv->num_rx_ring[q]) - - priv->cur_rx[q]; struct net_device_stats *stats = &priv->stats[q]; struct ravb_ex_rx_desc *desc; + unsigned int limit, i; struct sk_buff *skb; dma_addr_t dma_addr; struct timespec64 ts; + int rx_packets = 0; u8 desc_status; u16 pkt_len; - int limit; + int entry; + + limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; + for (i = 0; i < limit; i++, priv->cur_rx[q]++) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->rx_ring[q].ex_desc[entry]; + if (rx_packets == *quota || desc->die_dt == DT_FEMPTY) + break; - boguscnt = min(boguscnt, *quota); - limit = boguscnt; - desc = &priv->rx_ring[q][entry]; - while (desc->die_dt != DT_FEMPTY) { /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; - if (--boguscnt < 0) - break; - /* We use 0-byte descriptors to mark the DMA mapping errors */ if (!pkt_len) continue; @@ -962,18 +962,15 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) if (ndev->features & NETIF_F_RXCSUM) ravb_rx_csum(skb); napi_gro_receive(&priv->napi[q], skb); - stats->rx_packets++; + rx_packets++; stats->rx_bytes += pkt_len; } - - entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q][entry]; } /* Refill the RX ring buffers. */ for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q][entry]; + desc = &priv->rx_ring[q].ex_desc[entry]; desc->ds_cc = cpu_to_le16(RX_BUF_SZ); if (!priv->rx_skb[q][entry]) { @@ -998,9 +995,9 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) desc->die_dt = DT_FEMPTY; } - *quota -= limit - (++boguscnt); - - return boguscnt <= 0; + stats->rx_packets += rx_packets; + *quota -= rx_packets; + return *quota == 0; } /* Packet receive function for Ethernet AVB */ @@ -1284,25 +1281,16 @@ static int ravb_poll(struct napi_struct *napi, int budget) struct net_device *ndev = napi->dev; struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - bool gptp = info->gptp || info->ccc_gac; - struct ravb_rx_desc *desc; unsigned long flags; int q = napi - priv->napi; int mask = BIT(q); int quota = budget; - unsigned int entry; + bool unmask; - if (!gptp) { - entry = priv->cur_rx[q] % priv->num_rx_ring[q]; - desc = &priv->gbeth_rx_ring[entry]; - } /* Processing RX Descriptor Ring */ /* Clear RX interrupt */ ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0); - if (gptp || desc->die_dt != DT_FEMPTY) { - if (ravb_rx(ndev, "a, q)) - goto out; - } + unmask = !ravb_rx(ndev, "a, q); /* Processing TX Descriptor Ring */ spin_lock_irqsave(&priv->lock, flags); @@ -1312,6 +1300,18 @@ static int ravb_poll(struct napi_struct *napi, int budget) netif_wake_subqueue(ndev, q); spin_unlock_irqrestore(&priv->lock, flags); + /* Receive error message handling */ + priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; + if (info->nc_queues) + priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; + if (priv->rx_over_errors != ndev->stats.rx_over_errors) + ndev->stats.rx_over_errors = priv->rx_over_errors; + if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) + ndev->stats.rx_fifo_errors = priv->rx_fifo_errors; + + if (!unmask) + goto out; + napi_complete(napi); /* Re-enable RX/TX interrupts */ @@ -1325,14 +1325,6 @@ static int ravb_poll(struct napi_struct *napi, int budget) } spin_unlock_irqrestore(&priv->lock, flags); - /* Receive error message handling */ - priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; - if (info->nc_queues) - priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; - if (priv->rx_over_errors != ndev->stats.rx_over_errors) - ndev->stats.rx_over_errors = priv->rx_over_errors; - if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) - ndev->stats.rx_fifo_errors = priv->rx_fifo_errors; out: return budget - quota; } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 475e1e8c1d35f..0786eb0da3914 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -50,7 +50,7 @@ * the macros available to do this only define GCC 8. */ __diag_push(); -__diag_ignore(GCC, 8, "-Woverride-init", +__diag_ignore_all("-Woverride-init", "logic to initialize all and then override some is OK"); static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = { SH_ETH_OFFSET_DEFAULTS, diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 46eee747c6992..45ef5ac0788a8 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -156,8 +156,8 @@ static inline void mcf_outsw(void *a, unsigned char *p, int l) writew(*wp++, a); } -#define SMC_inw(a, r) _swapw(readw((a) + (r))) -#define SMC_outw(lp, v, a, r) writew(_swapw(v), (a) + (r)) +#define SMC_inw(a, r) ioread16be((a) + (r)) +#define SMC_outw(lp, v, a, r) iowrite16be(v, (a) + (r)) #define SMC_insw(a, r, p, l) mcf_insw(a + r, p, l) #define SMC_outsw(a, r, p, l) mcf_outsw(a + r, p, l) diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 85dcda51df052..4ec61f1ee71a2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -165,9 +165,9 @@ config DWMAC_STARFIVE help Support for ethernet controllers on StarFive RISC-V SoCs - This selects the StarFive platform specific glue layer support for - the stmmac device driver. This driver is used for StarFive JH7110 - ethernet controller. + This selects the StarFive platform specific glue layer support + for the stmmac device driver. This driver is used for the + StarFive JH7100 and JH7110 ethernet controllers. config DWMAC_STI tristate "STi GMAC support" diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 5ba606a596e77..618d455b457c7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -225,6 +225,8 @@ struct stmmac_extra_stats { unsigned long mtl_est_hlbf; unsigned long mtl_est_btre; unsigned long mtl_est_btrlm; + unsigned long max_sdu_txq_drop[MTL_MAX_TX_QUEUES]; + unsigned long mtl_est_txq_hlbf[MTL_MAX_TX_QUEUES]; /* per queue statistics */ struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES]; struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES]; @@ -550,6 +552,7 @@ extern const struct stmmac_hwtimestamp stmmac_ptp; extern const struct stmmac_mode_ops dwmac4_ring_mode_ops; struct mac_link { + u32 caps; u32 speed_mask; u32 speed10; u32 speed100; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 31631e3f89d0a..51ff53120307a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -93,6 +93,7 @@ struct ethqos_emac_driver_data { bool has_emac_ge_3; const char *link_clk_name; bool has_integrated_pcs; + u32 dma_addr_width; struct dwmac4_addrs dwmac4_addrs; }; @@ -272,6 +273,7 @@ static const struct ethqos_emac_driver_data emac_v4_0_0_data = { .has_emac_ge_3 = true, .link_clk_name = "phyaux", .has_integrated_pcs = true, + .dma_addr_width = 36, .dwmac4_addrs = { .dma_chan = 0x00008100, .dma_chan_offset = 0x1000, @@ -816,6 +818,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->flags |= STMMAC_FLAG_RX_CLK_RUNS_IN_LPI; if (data->has_integrated_pcs) plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS; + if (data->dma_addr_width) + plat_dat->host_dma_width = data->dma_addr_width; if (ethqos->serdes_phy) { plat_dat->serdes_powerup = qcom_ethqos_serdes_powerup; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c index 5d630affb4d15..4e1076faee0cd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c @@ -15,13 +15,20 @@ #include "stmmac_platform.h" -#define STARFIVE_DWMAC_PHY_INFT_RGMII 0x1 -#define STARFIVE_DWMAC_PHY_INFT_RMII 0x4 -#define STARFIVE_DWMAC_PHY_INFT_FIELD 0x7U +#define STARFIVE_DWMAC_PHY_INFT_RGMII 0x1 +#define STARFIVE_DWMAC_PHY_INFT_RMII 0x4 +#define STARFIVE_DWMAC_PHY_INFT_FIELD 0x7U + +#define JH7100_SYSMAIN_REGISTER49_DLYCHAIN 0xc8 + +struct starfive_dwmac_data { + unsigned int gtxclk_dlychain; +}; struct starfive_dwmac { struct device *dev; struct clk *clk_tx; + const struct starfive_dwmac_data *data; }; static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) @@ -67,6 +74,8 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat) case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: mode = STARFIVE_DWMAC_PHY_INFT_RGMII; break; @@ -89,6 +98,14 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat) if (err) return dev_err_probe(dwmac->dev, err, "error setting phy mode\n"); + if (dwmac->data) { + err = regmap_write(regmap, JH7100_SYSMAIN_REGISTER49_DLYCHAIN, + dwmac->data->gtxclk_dlychain); + if (err) + return dev_err_probe(dwmac->dev, err, + "error selecting gtxclk delay chain\n"); + } + return 0; } @@ -114,6 +131,8 @@ static int starfive_dwmac_probe(struct platform_device *pdev) if (!dwmac) return -ENOMEM; + dwmac->data = device_get_match_data(&pdev->dev); + dwmac->clk_tx = devm_clk_get_enabled(&pdev->dev, "tx"); if (IS_ERR(dwmac->clk_tx)) return dev_err_probe(&pdev->dev, PTR_ERR(dwmac->clk_tx), @@ -144,8 +163,13 @@ static int starfive_dwmac_probe(struct platform_device *pdev) return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); } +static const struct starfive_dwmac_data jh7100_data = { + .gtxclk_dlychain = 4, +}; + static const struct of_device_id starfive_dwmac_match[] = { - { .compatible = "starfive,jh7110-dwmac" }, + { .compatible = "starfive,jh7100-dwmac", .data = &jh7100_data }, + { .compatible = "starfive,jh7110-dwmac" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, starfive_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index b21d99faa2d04..e1b761dcfa1dd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1096,6 +1096,8 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv) priv->dev->priv_flags |= IFF_UNICAST_FLT; + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; /* The loopback bit seems to be re-set when link change * Simply mask it each time * Speed 10/100/1000 are set in BIT(2)/BIT(3) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 3927609abc441..8555299443f4e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -539,6 +539,8 @@ int dwmac1000_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; mac->link.duplex = GMAC_CONTROL_DM; mac->link.speed10 = GMAC_CONTROL_PS; mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index a6e8d7bd95886..7667d103cd0eb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -175,6 +175,8 @@ int dwmac100_setup(struct stmmac_priv *priv) dev_info(priv->device, "\tDWMAC100\n"); mac->pcsr = priv->ioaddr; + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; mac->link.duplex = MAC_CONTROL_F; mac->link.speed10 = 0; mac->link.speed100 = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 6b6d0de096197..a38226d7cc6a9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -70,7 +70,10 @@ static void dwmac4_core_init(struct mac_device_info *hw, static void dwmac4_phylink_get_caps(struct stmmac_priv *priv) { - priv->phylink_config.mac_capabilities |= MAC_2500FD; + if (priv->plat->tx_queues_to_use > 1) + priv->hw->link.caps &= ~(MAC_10HD | MAC_100HD | MAC_1000HD); + else + priv->hw->link.caps |= (MAC_10HD | MAC_100HD | MAC_1000HD); } static void dwmac4_rx_queue_enable(struct mac_device_info *hw, @@ -92,19 +95,41 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 base_register; - u32 value; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; - if (queue >= 4) - queue -= 4; + ctrl2 = readl(ioaddr + GMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + GMAC_RXQ_CTRL3); - value = readl(ioaddr + base_register); + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << GMAC_RXQCTRL_PSRQX_SHIFT(i)) & + GMAC_RXQCTRL_PSRQX_MASK(i)); - value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue); - value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & GMAC_RXQCTRL_PSRQX_MASK(queue); - writel(value, ioaddr + base_register); + + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + } else { + queue -= 4; + + ctrl3 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + GMAC_RXQCTRL_PSRQX_MASK(queue); + + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + } } static void dwmac4_tx_queue_priority(struct mac_device_info *hw, @@ -1356,6 +1381,8 @@ int dwmac4_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; mac->link.duplex = GMAC_CONFIG_DM; mac->link.speed10 = GMAC_CONFIG_PS; mac->link.speed100 = GMAC_CONFIG_FES | GMAC_CONFIG_PS; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 1af2f89a0504a..f8e7775bb6336 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -47,14 +47,6 @@ static void dwxgmac2_core_init(struct mac_device_info *hw, writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN); } -static void xgmac_phylink_get_caps(struct stmmac_priv *priv) -{ - priv->phylink_config.mac_capabilities |= MAC_2500FD | MAC_5000FD | - MAC_10000FD | MAC_25000FD | - MAC_40000FD | MAC_50000FD | - MAC_100000FD; -} - static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable) { u32 tx = readl(ioaddr + XGMAC_TX_CONFIG); @@ -105,17 +97,41 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 value, reg; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3; - if (queue >= 4) + ctrl2 = readl(ioaddr + XGMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + XGMAC_RXQ_CTRL3); + + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << XGMAC_PSRQ_SHIFT(i)) & + XGMAC_PSRQ(i)); + + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); + + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + } else { queue -= 4; - value = readl(ioaddr + reg); - value &= ~XGMAC_PSRQ(queue); - value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue); + ctrl3 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); - writel(value, ioaddr + reg); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + } } static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio, @@ -1516,7 +1532,6 @@ static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg * const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, - .phylink_get_caps = xgmac_phylink_get_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxgmac2_rx_queue_enable, @@ -1577,7 +1592,6 @@ static void dwxlgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode, const struct stmmac_ops dwxlgmac2_ops = { .core_init = dwxgmac2_core_init, - .phylink_get_caps = xgmac_phylink_get_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxlgmac2_rx_queue_enable, @@ -1637,6 +1651,9 @@ int dwxgmac2_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_1000FD | MAC_2500FD | MAC_5000FD | + MAC_10000FD; mac->link.duplex = 0; mac->link.speed10 = XGMAC_CONFIG_SS_10_MII; mac->link.speed100 = XGMAC_CONFIG_SS_100_MII; @@ -1674,6 +1691,11 @@ int dwxlgmac2_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_1000FD | MAC_2500FD | MAC_5000FD | + MAC_10000FD | MAC_25000FD | + MAC_40000FD | MAC_50000FD | + MAC_100000FD; mac->link.duplex = 0; mac->link.speed1000 = XLGMAC_CONFIG_SS_1000; mac->link.speed2500 = XLGMAC_CONFIG_SS_2500; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index f155e4841c62b..1db1359d154f3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -260,6 +260,8 @@ struct stmmac_priv { struct stmmac_extra_stats xstats ____cacheline_aligned_in_smp; struct stmmac_safety_stats sstats; struct plat_stmmacenet_data *plat; + /* Protect est parameters */ + struct mutex est_lock; struct dma_features dma_cap; struct stmmac_counters mmc; int hw_cap_support; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c index 4da6ccc17c205..c9693f77e1f61 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c @@ -81,6 +81,7 @@ static void est_irq_status(struct stmmac_priv *priv, struct net_device *dev, u32 status, value, feqn, hbfq, hbfs, btrl, btrl_max; void __iomem *est_addr = priv->estaddr; u32 txqcnt_mask = BIT(txqcnt) - 1; + int i; status = readl(est_addr + EST_STATUS); @@ -125,6 +126,11 @@ static void est_irq_status(struct stmmac_priv *priv, struct net_device *dev, x->mtl_est_hlbf++; + for (i = 0; i < txqcnt; i++) { + if (feqn & BIT(i)) + x->mtl_est_txq_hlbf[i]++; + } + /* Clear Interrupt */ writel(feqn, est_addr + EST_FRM_SZ_ERR); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index f05bd757dfe52..5ef52ef2698fb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -218,6 +218,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv) { u32 num_snapshot, ts_status, tsync_int; struct ptp_clock_event event; + u32 acr_value, channel; unsigned long flags; u64 ptp_time; int i; @@ -243,12 +244,15 @@ static void timestamp_interrupt(struct stmmac_priv *priv) num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >> GMAC_TIMESTAMP_ATSNS_SHIFT; + acr_value = readl(priv->ptpaddr + PTP_ACR); + channel = ilog2(FIELD_GET(PTP_ACR_MASK, acr_value)); + for (i = 0; i < num_snapshot; i++) { read_lock_irqsave(&priv->ptp_lock, flags); get_ptptime(priv->ptpaddr, &ptp_time); read_unlock_irqrestore(&priv->ptp_lock, flags); event.type = PTP_CLOCK_EXTTS; - event.index = 0; + event.index = channel; event.timestamp = ptp_time; ptp_clock_event(priv->ptp_clock, &event); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7c6aef033a456..12f4c0da838da 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1198,17 +1198,6 @@ static int stmmac_init_phy(struct net_device *dev) return ret; } -static void stmmac_set_half_duplex(struct stmmac_priv *priv) -{ - /* Half-Duplex can only work with single tx queue */ - if (priv->plat->tx_queues_to_use > 1) - priv->phylink_config.mac_capabilities &= - ~(MAC_10HD | MAC_100HD | MAC_1000HD); - else - priv->phylink_config.mac_capabilities |= - (MAC_10HD | MAC_100HD | MAC_1000HD); -} - static int stmmac_phy_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data; @@ -1236,15 +1225,11 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) xpcs_get_interfaces(priv->hw->xpcs, priv->phylink_config.supported_interfaces); - priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | - MAC_10FD | MAC_100FD | - MAC_1000FD; - - stmmac_set_half_duplex(priv); - /* Get the MAC specific capabilities */ stmmac_mac_phylink_get_caps(priv); + priv->phylink_config.mac_capabilities = priv->hw->link.caps; + max_speed = priv->plat->max_speed; if (max_speed) phylink_limit_mac_speed(&priv->phylink_config, max_speed); @@ -2506,6 +2491,13 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) if (!xsk_tx_peek_desc(pool, &xdp_desc)) break; + if (priv->plat->est && priv->plat->est->enable && + priv->plat->est->max_sdu[queue] && + xdp_desc.len > priv->plat->est->max_sdu[queue]) { + priv->xstats.max_sdu_txq_drop[queue]++; + continue; + } + if (likely(priv->extend_desc)) tx_desc = (struct dma_desc *)(tx_q->dma_etx + entry); else if (tx_q->tbs & STMMAC_TBS_AVAIL) @@ -4500,6 +4492,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return stmmac_tso_xmit(skb, dev); } + if (priv->plat->est && priv->plat->est->enable && + priv->plat->est->max_sdu[queue] && + skb->len > priv->plat->est->max_sdu[queue]){ + priv->xstats.max_sdu_txq_drop[queue]++; + goto max_sdu_err; + } + if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) { netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, @@ -4717,6 +4716,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) dma_map_err: netdev_err(priv->dev, "Tx DMA map failed\n"); +max_sdu_err: dev_kfree_skb(skb); priv->xstats.tx_dropped++; return NETDEV_TX_OK; @@ -4873,6 +4873,13 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue, if (stmmac_tx_avail(priv, queue) < STMMAC_TX_THRESH(priv)) return STMMAC_XDP_CONSUMED; + if (priv->plat->est && priv->plat->est->enable && + priv->plat->est->max_sdu[queue] && + xdpf->len > priv->plat->est->max_sdu[queue]) { + priv->xstats.max_sdu_txq_drop[queue]++; + return STMMAC_XDP_CONSUMED; + } + if (likely(priv->extend_desc)) tx_desc = (struct dma_desc *)(tx_q->dma_etx + entry); else if (tx_q->tbs & STMMAC_TBS_AVAIL) @@ -7286,6 +7293,7 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) { struct stmmac_priv *priv = netdev_priv(dev); int ret = 0, i; + int max_speed; if (netif_running(dev)) stmmac_release(dev); @@ -7299,7 +7307,14 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) priv->rss.table[i] = ethtool_rxfh_indir_default(i, rx_cnt); - stmmac_set_half_duplex(priv); + stmmac_mac_phylink_get_caps(priv); + + priv->phylink_config.mac_capabilities = priv->hw->link.caps; + + max_speed = priv->plat->max_speed; + if (max_speed) + phylink_limit_mac_speed(&priv->phylink_config, max_speed); + stmmac_napi_add(dev); if (netif_running(dev)) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index e04830a3a1fb1..0c5aab6dd7a73 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -70,11 +70,11 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) /* If EST is enabled, disabled it before adjust ptp time. */ if (priv->plat->est && priv->plat->est->enable) { est_rst = true; - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); priv->plat->est->enable = false; stmmac_est_configure(priv, priv, priv->plat->est, priv->plat->clk_ptp_rate); - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); } write_lock_irqsave(&priv->ptp_lock, flags); @@ -87,7 +87,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) ktime_t current_time_ns, basetime; u64 cycle_time; - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); current_time_ns = timespec64_to_ktime(current_time); time.tv_nsec = priv->plat->est->btr_reserve[0]; @@ -104,7 +104,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) priv->plat->est->enable = true; ret = stmmac_est_configure(priv, priv, priv->plat->est, priv->plat->clk_ptp_rate); - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); if (ret) netdev_err(priv->dev, "failed to configure EST\n"); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 26fa33e5ec34f..7d240a2b54a85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -343,10 +343,11 @@ static int tc_setup_cbs(struct stmmac_priv *priv, struct tc_cbs_qopt_offload *qopt) { u32 tx_queues_count = priv->plat->tx_queues_to_use; + s64 port_transmit_rate_kbps; u32 queue = qopt->queue; - u32 ptr, speed_div; u32 mode_to_use; u64 value; + u32 ptr; int ret; /* Queue 0 is not AVB capable */ @@ -355,30 +356,30 @@ static int tc_setup_cbs(struct stmmac_priv *priv, if (!priv->dma_cap.av) return -EOPNOTSUPP; - /* Port Transmit Rate and Speed Divider */ - switch (priv->speed) { - case SPEED_10000: - ptr = 32; - speed_div = 10000000; - break; - case SPEED_5000: - ptr = 32; - speed_div = 5000000; - break; - case SPEED_2500: - ptr = 8; - speed_div = 2500000; - break; - case SPEED_1000: - ptr = 8; - speed_div = 1000000; - break; - case SPEED_100: - ptr = 4; - speed_div = 100000; - break; - default: - return -EOPNOTSUPP; + port_transmit_rate_kbps = qopt->idleslope - qopt->sendslope; + + if (qopt->enable) { + /* Port Transmit Rate and Speed Divider */ + switch (div_s64(port_transmit_rate_kbps, 1000)) { + case SPEED_10000: + case SPEED_5000: + ptr = 32; + break; + case SPEED_2500: + case SPEED_1000: + ptr = 8; + break; + case SPEED_100: + ptr = 4; + break; + default: + netdev_err(priv->dev, + "Invalid portTransmitRate %lld (idleSlope - sendSlope)\n", + port_transmit_rate_kbps); + return -EINVAL; + } + } else { + ptr = 0; } mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; @@ -398,10 +399,10 @@ static int tc_setup_cbs(struct stmmac_priv *priv, } /* Final adjustments for HW */ - value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div); + value = div_s64(qopt->idleslope * 1024ll * ptr, port_transmit_rate_kbps); priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0); - value = div_s64(-qopt->sendslope * 1024ll * ptr, speed_div); + value = div_s64(-qopt->sendslope * 1024ll * ptr, port_transmit_rate_kbps); priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0); value = qopt->hicredit * 1024ll * 8; @@ -915,8 +916,30 @@ struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time, return time; } -static int tc_setup_taprio(struct stmmac_priv *priv, - struct tc_taprio_qopt_offload *qopt) +static void tc_taprio_map_maxsdu_txq(struct stmmac_priv *priv, + struct tc_taprio_qopt_offload *qopt) +{ + struct plat_stmmacenet_data *plat = priv->plat; + u32 num_tc = qopt->mqprio.qopt.num_tc; + u32 offset, count, i, j; + + /* QueueMaxSDU received from the driver corresponds to the Linux traffic + * class. Map queueMaxSDU per Linux traffic class to DWMAC Tx queues. + */ + for (i = 0; i < num_tc; i++) { + if (!qopt->max_sdu[i]) + continue; + + offset = qopt->mqprio.qopt.offset[i]; + count = qopt->mqprio.qopt.count[i]; + + for (j = offset; j < offset + count; j++) + plat->est->max_sdu[j] = qopt->max_sdu[i] + ETH_HLEN - ETH_TLEN; + } +} + +static int tc_taprio_configure(struct stmmac_priv *priv, + struct tc_taprio_qopt_offload *qopt) { u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep; struct plat_stmmacenet_data *plat = priv->plat; @@ -968,8 +991,6 @@ static int tc_setup_taprio(struct stmmac_priv *priv, if (qopt->cmd == TAPRIO_CMD_DESTROY) goto disable; - else if (qopt->cmd != TAPRIO_CMD_REPLACE) - return -EOPNOTSUPP; if (qopt->num_entries >= dep) return -EINVAL; @@ -984,17 +1005,19 @@ static int tc_setup_taprio(struct stmmac_priv *priv, if (!plat->est) return -ENOMEM; - mutex_init(&priv->plat->est->lock); + mutex_init(&priv->est_lock); } else { + mutex_lock(&priv->est_lock); memset(plat->est, 0, sizeof(*plat->est)); + mutex_unlock(&priv->est_lock); } size = qopt->num_entries; - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); priv->plat->est->gcl_size = size; priv->plat->est->enable = qopt->cmd == TAPRIO_CMD_REPLACE; - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); for (i = 0; i < size; i++) { s64 delta_ns = qopt->entries[i].interval; @@ -1025,7 +1048,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->gcl[i] = delta_ns | (gates << wid); } - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); /* Adjust for real system time */ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); current_time_ns = timespec64_to_ktime(current_time); @@ -1045,8 +1068,10 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->ter = qopt->cycle_time_extension; + tc_taprio_map_maxsdu_txq(priv, qopt); + if (fpe && !priv->dma_cap.fpesel) { - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); return -EOPNOTSUPP; } @@ -1057,7 +1082,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, ret = stmmac_est_configure(priv, priv, priv->plat->est, priv->plat->clk_ptp_rate); - mutex_unlock(&priv->plat->est->lock); + mutex_unlock(&priv->est_lock); if (ret) { netdev_err(priv->dev, "failed to configure EST\n"); goto disable; @@ -1074,11 +1099,16 @@ static int tc_setup_taprio(struct stmmac_priv *priv, disable: if (priv->plat->est) { - mutex_lock(&priv->plat->est->lock); + mutex_lock(&priv->est_lock); priv->plat->est->enable = false; stmmac_est_configure(priv, priv, priv->plat->est, priv->plat->clk_ptp_rate); - mutex_unlock(&priv->plat->est->lock); + /* Reset taprio status */ + for (i = 0; i < priv->plat->tx_queues_to_use; i++) { + priv->xstats.max_sdu_txq_drop[i] = 0; + priv->xstats.mtl_est_txq_hlbf[i] = 0; + } + mutex_unlock(&priv->est_lock); } priv->plat->fpe_cfg->enable = false; @@ -1095,6 +1125,57 @@ static int tc_setup_taprio(struct stmmac_priv *priv, return ret; } +static void tc_taprio_stats(struct stmmac_priv *priv, + struct tc_taprio_qopt_offload *qopt) +{ + u64 window_drops = 0; + int i = 0; + + for (i = 0; i < priv->plat->tx_queues_to_use; i++) + window_drops += priv->xstats.max_sdu_txq_drop[i] + + priv->xstats.mtl_est_txq_hlbf[i]; + qopt->stats.window_drops = window_drops; + + /* Transmission overrun doesn't happen for stmmac, hence always 0 */ + qopt->stats.tx_overruns = 0; +} + +static void tc_taprio_queue_stats(struct stmmac_priv *priv, + struct tc_taprio_qopt_offload *qopt) +{ + struct tc_taprio_qopt_queue_stats *q_stats = &qopt->queue_stats; + int queue = qopt->queue_stats.queue; + + q_stats->stats.window_drops = priv->xstats.max_sdu_txq_drop[queue] + + priv->xstats.mtl_est_txq_hlbf[queue]; + + /* Transmission overrun doesn't happen for stmmac, hence always 0 */ + q_stats->stats.tx_overruns = 0; +} + +static int tc_setup_taprio(struct stmmac_priv *priv, + struct tc_taprio_qopt_offload *qopt) +{ + int err = 0; + + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + case TAPRIO_CMD_DESTROY: + err = tc_taprio_configure(priv, qopt); + break; + case TAPRIO_CMD_STATS: + tc_taprio_stats(priv, qopt); + break; + case TAPRIO_CMD_QUEUE_STATS: + tc_taprio_queue_stats(priv, qopt); + break; + default: + err = -EOPNOTSUPP; + } + + return err; +} + static int tc_setup_etf(struct stmmac_priv *priv, struct tc_etf_qopt_offload *qopt) { @@ -1126,6 +1207,7 @@ static int tc_query_caps(struct stmmac_priv *priv, return -EOPNOTSUPP; caps->gate_mask_per_txq = true; + caps->supports_queue_max_sdu = true; return 0; } diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 9bd1df8308d24..d3a2fbb14140e 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -949,17 +949,6 @@ static irqreturn_t gem_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void gem_poll_controller(struct net_device *dev) -{ - struct gem *gp = netdev_priv(dev); - - disable_irq(gp->pdev->irq); - gem_interrupt(gp->pdev->irq, dev); - enable_irq(gp->pdev->irq); -} -#endif - static void gem_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct gem *gp = netdev_priv(dev); @@ -2839,9 +2828,6 @@ static const struct net_device_ops gem_netdev_ops = { .ndo_change_mtu = gem_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = gem_set_mac_address, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = gem_poll_controller, -#endif }; static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2939a21ca74f3..1d00e21808c1c 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2793,6 +2793,8 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { + struct am65_cpsw_rx_chn *rx_chan = &common->rx_chns; + struct am65_cpsw_tx_chn *tx_chan = common->tx_chns; struct device *dev = common->dev; struct am65_cpsw_port *port; int ret = 0, i; @@ -2805,6 +2807,22 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) if (ret) return ret; + /* The DMA Channels are not guaranteed to be in a clean state. + * Reset and disable them to ensure that they are back to the + * clean state and ready to be used. + */ + for (i = 0; i < common->tx_ch_num; i++) { + k3_udma_glue_reset_tx_chn(tx_chan[i].tx_chn, &tx_chan[i], + am65_cpsw_nuss_tx_cleanup); + k3_udma_glue_disable_tx_chn(tx_chan[i].tx_chn); + } + + for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++) + k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i, rx_chan, + am65_cpsw_nuss_rx_cleanup, !!i); + + k3_udma_glue_disable_rx_chn(rx_chan->rx_chn); + ret = am65_cpsw_nuss_register_devlink(common); if (ret) return ret; diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index c66618d91c28f..f89716b1cfb64 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -784,6 +784,11 @@ static bool am65_cpts_match_tx_ts(struct am65_cpts *cpts, struct am65_cpts_skb_cb_data *skb_cb = (struct am65_cpts_skb_cb_data *)skb->cb; + if ((ptp_classify_raw(skb) & PTP_CLASS_V1) && + ((mtype_seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK) == + (skb_cb->skb_mtype_seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK))) + mtype_seqid = skb_cb->skb_mtype_seqid; + if (mtype_seqid == skb_cb->skb_mtype_seqid) { u64 ns = event->timestamp; diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c index 6df53ab17fbc5..902a2717785cb 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c +++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c @@ -360,7 +360,7 @@ void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr) { const u8 mask_addr[] = { 0, 0, 0, 0, 0, 0, }; - rx_class_ft1_set_start_len(miig_rt, slice, 0, 6); + rx_class_ft1_set_start_len(miig_rt, slice, ETH_ALEN, ETH_ALEN); rx_class_ft1_set_da(miig_rt, slice, 0, mac_addr); rx_class_ft1_set_da_mask(miig_rt, slice, 0, mask_addr); rx_class_ft1_cfg_set_type(miig_rt, slice, 0, FT1_CFG_TYPE_EQ); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 411898a4f38ca..3fa49448a74bb 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -421,12 +421,14 @@ static int prueth_init_rx_chns(struct prueth_emac *emac, if (!i) fdqring_id = k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn, i); - rx_chn->irq[i] = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i); - if (rx_chn->irq[i] <= 0) { - ret = rx_chn->irq[i]; + ret = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i); + if (ret <= 0) { + if (!ret) + ret = -ENXIO; netdev_err(ndev, "Failed to get rx dma irq"); goto fail; } + rx_chn->irq[i] = ret; } return 0; @@ -2154,7 +2156,12 @@ static int prueth_probe(struct platform_device *pdev) prueth->registered_netdevs[PRUETH_MAC0] = prueth->emac[PRUETH_MAC0]->ndev; - emac_phy_connect(prueth->emac[PRUETH_MAC0]); + ret = emac_phy_connect(prueth->emac[PRUETH_MAC0]); + if (ret) { + dev_err(dev, + "can't connect to MII0 PHY, error -%d", ret); + goto netdev_unregister; + } phy_attached_info(prueth->emac[PRUETH_MAC0]->ndev->phydev); } @@ -2166,7 +2173,12 @@ static int prueth_probe(struct platform_device *pdev) } prueth->registered_netdevs[PRUETH_MAC1] = prueth->emac[PRUETH_MAC1]->ndev; - emac_phy_connect(prueth->emac[PRUETH_MAC1]); + ret = emac_phy_connect(prueth->emac[PRUETH_MAC1]); + if (ret) { + dev_err(dev, + "can't connect to MII1 PHY, error %d", ret); + goto netdev_unregister; + } phy_attached_info(prueth->emac[PRUETH_MAC1]->ndev->phydev); } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 1db754615cca3..c09a6f7445754 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1958,7 +1958,7 @@ int wx_sw_init(struct wx *wx) return -ENOMEM; } - wx->msix_in_use = false; + bitmap_zero(wx->state, WX_STATE_NBITS); return 0; } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 8706223a6e5aa..c87afe5de1dd8 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -1598,7 +1598,7 @@ static void wx_set_num_queues(struct wx *wx) */ static int wx_acquire_msix_vectors(struct wx *wx) { - struct irq_affinity affd = {0, }; + struct irq_affinity affd = { .pre_vectors = 1 }; int nvecs, i; /* We start by asking for one vector per queue pair */ @@ -1614,14 +1614,12 @@ static int wx_acquire_msix_vectors(struct wx *wx) /* One for non-queue interrupts */ nvecs += 1; - if (!wx->msix_in_use) { - wx->msix_entry = kcalloc(1, sizeof(struct msix_entry), - GFP_KERNEL); - if (!wx->msix_entry) { - kfree(wx->msix_q_entries); - wx->msix_q_entries = NULL; - return -ENOMEM; - } + wx->msix_entry = kcalloc(1, sizeof(struct msix_entry), + GFP_KERNEL); + if (!wx->msix_entry) { + kfree(wx->msix_q_entries); + wx->msix_q_entries = NULL; + return -ENOMEM; } nvecs = pci_alloc_irq_vectors_affinity(wx->pdev, nvecs, @@ -1931,10 +1929,8 @@ void wx_reset_interrupt_capability(struct wx *wx) if (pdev->msix_enabled) { kfree(wx->msix_q_entries); wx->msix_q_entries = NULL; - if (!wx->msix_in_use) { - kfree(wx->msix_entry); - wx->msix_entry = NULL; - } + kfree(wx->msix_entry); + wx->msix_entry = NULL; } pci_free_irq_vectors(wx->pdev); } @@ -2694,15 +2690,63 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features) wx->rss_enabled = false; } - if (changed & - (NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_STAG_RX)) + netdev->features = features; + + if (wx->mac.type == wx_mac_sp && changed & NETIF_F_HW_VLAN_CTAG_RX) + wx->do_reset(netdev); + else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER)) wx_set_rx_mode(netdev); - return 1; + return 0; } EXPORT_SYMBOL(wx_set_features); +#define NETIF_VLAN_STRIPPING_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_HW_VLAN_STAG_RX) + +#define NETIF_VLAN_INSERTION_FEATURES (NETIF_F_HW_VLAN_CTAG_TX | \ + NETIF_F_HW_VLAN_STAG_TX) + +#define NETIF_VLAN_FILTERING_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ + NETIF_F_HW_VLAN_STAG_FILTER) + +netdev_features_t wx_fix_features(struct net_device *netdev, + netdev_features_t features) +{ + netdev_features_t changed = netdev->features ^ features; + struct wx *wx = netdev_priv(netdev); + + if (changed & NETIF_VLAN_STRIPPING_FEATURES) { + if ((features & NETIF_VLAN_STRIPPING_FEATURES) != NETIF_VLAN_STRIPPING_FEATURES && + (features & NETIF_VLAN_STRIPPING_FEATURES) != 0) { + features &= ~NETIF_VLAN_STRIPPING_FEATURES; + features |= netdev->features & NETIF_VLAN_STRIPPING_FEATURES; + wx_err(wx, "802.1Q and 802.1ad VLAN stripping must be either both on or both off."); + } + } + + if (changed & NETIF_VLAN_INSERTION_FEATURES) { + if ((features & NETIF_VLAN_INSERTION_FEATURES) != NETIF_VLAN_INSERTION_FEATURES && + (features & NETIF_VLAN_INSERTION_FEATURES) != 0) { + features &= ~NETIF_VLAN_INSERTION_FEATURES; + features |= netdev->features & NETIF_VLAN_INSERTION_FEATURES; + wx_err(wx, "802.1Q and 802.1ad VLAN insertion must be either both on or both off."); + } + } + + if (changed & NETIF_VLAN_FILTERING_FEATURES) { + if ((features & NETIF_VLAN_FILTERING_FEATURES) != NETIF_VLAN_FILTERING_FEATURES && + (features & NETIF_VLAN_FILTERING_FEATURES) != 0) { + features &= ~NETIF_VLAN_FILTERING_FEATURES; + features |= netdev->features & NETIF_VLAN_FILTERING_FEATURES; + wx_err(wx, "802.1Q and 802.1ad VLAN filtering must be either both on or both off."); + } + } + + return features; +} +EXPORT_SYMBOL(wx_fix_features); + void wx_set_ring(struct wx *wx, u32 new_tx_count, u32 new_rx_count, struct wx_ring *temp_ring) { diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h index ec909e876720c..c41b29ea812ff 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h @@ -30,6 +30,8 @@ int wx_setup_resources(struct wx *wx); void wx_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats); int wx_set_features(struct net_device *netdev, netdev_features_t features); +netdev_features_t wx_fix_features(struct net_device *netdev, + netdev_features_t features); void wx_set_ring(struct wx *wx, u32 new_tx_count, u32 new_rx_count, struct wx_ring *temp_ring); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index b4dc4f3411174..5aaf7b1fa2db9 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -982,8 +982,13 @@ struct wx_hw_stats { u64 qmprc; }; +enum wx_state { + WX_STATE_RESETTING, + WX_STATE_NBITS, /* must be last */ +}; struct wx { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + DECLARE_BITMAP(state, WX_STATE_NBITS); void *priv; u8 __iomem *hw_addr; @@ -1047,7 +1052,6 @@ struct wx { unsigned int queues_per_pool; struct msix_entry *msix_q_entries; struct msix_entry *msix_entry; - bool msix_in_use; struct wx_ring_feature ring_feature[RING_F_ARRAY_SIZE]; /* misc interrupt status block */ @@ -1072,6 +1076,8 @@ struct wx { u64 hw_csum_rx_good; u64 hw_csum_rx_error; u64 alloc_rx_buff_failed; + + void (*do_reset)(struct net_device *netdev); }; #define WX_INTR_ALL (~0ULL) @@ -1132,4 +1138,19 @@ static inline struct wx *phylink_to_wx(struct phylink_config *config) return container_of(config, struct wx, phylink_config); } +static inline int wx_set_state_reset(struct wx *wx) +{ + u8 timeout = 50; + + while (test_and_set_bit(WX_STATE_RESETTING, wx->state)) { + timeout--; + if (!timeout) + return -EBUSY; + + usleep_range(1000, 2000); + } + + return 0; +} + #endif /* _WX_TYPE_H_ */ diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c index 786a652ae64f3..46a5a3e952021 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c @@ -52,7 +52,7 @@ static int ngbe_set_ringparam(struct net_device *netdev, struct wx *wx = netdev_priv(netdev); u32 new_rx_count, new_tx_count; struct wx_ring *temp_ring; - int i; + int i, err = 0; new_tx_count = clamp_t(u32, ring->tx_pending, WX_MIN_TXD, WX_MAX_TXD); new_tx_count = ALIGN(new_tx_count, WX_REQ_TX_DESCRIPTOR_MULTIPLE); @@ -64,6 +64,10 @@ static int ngbe_set_ringparam(struct net_device *netdev, new_rx_count == wx->rx_ring_count) return 0; + err = wx_set_state_reset(wx); + if (err) + return err; + if (!netif_running(wx->netdev)) { for (i = 0; i < wx->num_tx_queues; i++) wx->tx_ring[i]->count = new_tx_count; @@ -72,14 +76,16 @@ static int ngbe_set_ringparam(struct net_device *netdev, wx->tx_ring_count = new_tx_count; wx->rx_ring_count = new_rx_count; - return 0; + goto clear_reset; } /* allocate temporary buffer to store rings in */ i = max_t(int, wx->num_tx_queues, wx->num_rx_queues); temp_ring = kvmalloc_array(i, sizeof(struct wx_ring), GFP_KERNEL); - if (!temp_ring) - return -ENOMEM; + if (!temp_ring) { + err = -ENOMEM; + goto clear_reset; + } ngbe_down(wx); @@ -89,7 +95,9 @@ static int ngbe_set_ringparam(struct net_device *netdev, wx_configure(wx); ngbe_up(wx); - return 0; +clear_reset: + clear_bit(WX_STATE_RESETTING, wx->state); + return err; } static int ngbe_set_channels(struct net_device *dev, diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index fdd6b4f70b7a5..e894e01d030d1 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -499,6 +499,7 @@ static const struct net_device_ops ngbe_netdev_ops = { .ndo_start_xmit = wx_xmit_frame, .ndo_set_rx_mode = wx_set_rx_mode, .ndo_set_features = wx_set_features, + .ndo_fix_features = wx_fix_features, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = wx_set_mac, .ndo_get_stats64 = wx_get_stats64, diff --git a/drivers/net/ethernet/wangxun/txgbe/Makefile b/drivers/net/ethernet/wangxun/txgbe/Makefile index 7507f762edfe5..42718875277c8 100644 --- a/drivers/net/ethernet/wangxun/txgbe/Makefile +++ b/drivers/net/ethernet/wangxun/txgbe/Makefile @@ -9,4 +9,5 @@ obj-$(CONFIG_TXGBE) += txgbe.o txgbe-objs := txgbe_main.o \ txgbe_hw.o \ txgbe_phy.o \ + txgbe_irq.o \ txgbe_ethtool.o diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c index db675512ce4dc..31fde3fa7c6b5 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c @@ -19,7 +19,7 @@ static int txgbe_set_ringparam(struct net_device *netdev, struct wx *wx = netdev_priv(netdev); u32 new_rx_count, new_tx_count; struct wx_ring *temp_ring; - int i; + int i, err = 0; new_tx_count = clamp_t(u32, ring->tx_pending, WX_MIN_TXD, WX_MAX_TXD); new_tx_count = ALIGN(new_tx_count, WX_REQ_TX_DESCRIPTOR_MULTIPLE); @@ -31,6 +31,10 @@ static int txgbe_set_ringparam(struct net_device *netdev, new_rx_count == wx->rx_ring_count) return 0; + err = wx_set_state_reset(wx); + if (err) + return err; + if (!netif_running(wx->netdev)) { for (i = 0; i < wx->num_tx_queues; i++) wx->tx_ring[i]->count = new_tx_count; @@ -39,14 +43,16 @@ static int txgbe_set_ringparam(struct net_device *netdev, wx->tx_ring_count = new_tx_count; wx->rx_ring_count = new_rx_count; - return 0; + goto clear_reset; } /* allocate temporary buffer to store rings in */ i = max_t(int, wx->num_tx_queues, wx->num_rx_queues); temp_ring = kvmalloc_array(i, sizeof(struct wx_ring), GFP_KERNEL); - if (!temp_ring) - return -ENOMEM; + if (!temp_ring) { + err = -ENOMEM; + goto clear_reset; + } txgbe_down(wx); @@ -55,7 +61,9 @@ static int txgbe_set_ringparam(struct net_device *netdev, txgbe_up(wx); - return 0; +clear_reset: + clear_bit(WX_STATE_RESETTING, wx->state); + return err; } static int txgbe_set_channels(struct net_device *dev, diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c new file mode 100644 index 0000000000000..b3e3605d1edb3 --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2015 - 2024 Beijing WangXun Technology Co., Ltd. */ + +#include +#include + +#include "../libwx/wx_type.h" +#include "../libwx/wx_lib.h" +#include "../libwx/wx_hw.h" +#include "txgbe_type.h" +#include "txgbe_phy.h" +#include "txgbe_irq.h" + +/** + * txgbe_irq_enable - Enable default interrupt generation settings + * @wx: pointer to private structure + * @queues: enable irqs for queues + **/ +void txgbe_irq_enable(struct wx *wx, bool queues) +{ + wr32(wx, WX_PX_MISC_IEN, TXGBE_PX_MISC_IEN_MASK); + + /* unmask interrupt */ + wx_intr_enable(wx, TXGBE_INTR_MISC); + if (queues) + wx_intr_enable(wx, TXGBE_INTR_QALL(wx)); +} + +/** + * txgbe_intr - msi/legacy mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t txgbe_intr(int __always_unused irq, void *data) +{ + struct wx_q_vector *q_vector; + struct wx *wx = data; + struct pci_dev *pdev; + u32 eicr; + + q_vector = wx->q_vector[0]; + pdev = wx->pdev; + + eicr = wx_misc_isb(wx, WX_ISB_VEC0); + if (!eicr) { + /* shared interrupt alert! + * the interrupt that we masked before the ICR read. + */ + if (netif_running(wx->netdev)) + txgbe_irq_enable(wx, true); + return IRQ_NONE; /* Not our interrupt */ + } + wx->isb_mem[WX_ISB_VEC0] = 0; + if (!(pdev->msi_enabled)) + wr32(wx, WX_PX_INTA, 1); + + wx->isb_mem[WX_ISB_MISC] = 0; + /* would disable interrupts here but it is auto disabled */ + napi_schedule_irqoff(&q_vector->napi); + + /* re-enable link(maybe) and non-queue interrupts, no flush. + * txgbe_poll will re-enable the queue interrupts + */ + if (netif_running(wx->netdev)) + txgbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +/** + * txgbe_request_msix_irqs - Initialize MSI-X interrupts + * @wx: board private structure + * + * Allocate MSI-X vectors and request interrupts from the kernel. + **/ +static int txgbe_request_msix_irqs(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + int vector, err; + + for (vector = 0; vector < wx->num_q_vectors; vector++) { + struct wx_q_vector *q_vector = wx->q_vector[vector]; + struct msix_entry *entry = &wx->msix_q_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-TxRx-%d", netdev->name, entry->entry); + else + /* skip this unused q_vector */ + continue; + + err = request_irq(entry->vector, wx_msix_clean_rings, 0, + q_vector->name, q_vector); + if (err) { + wx_err(wx, "request_irq failed for MSIX interrupt %s Error: %d\n", + q_vector->name, err); + goto free_queue_irqs; + } + } + + return 0; + +free_queue_irqs: + while (vector) { + vector--; + free_irq(wx->msix_q_entries[vector].vector, + wx->q_vector[vector]); + } + wx_reset_interrupt_capability(wx); + return err; +} + +/** + * txgbe_request_irq - initialize interrupts + * @wx: board private structure + * + * Attempt to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +int txgbe_request_irq(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + struct pci_dev *pdev = wx->pdev; + int err; + + if (pdev->msix_enabled) + err = txgbe_request_msix_irqs(wx); + else if (pdev->msi_enabled) + err = request_irq(wx->pdev->irq, &txgbe_intr, 0, + netdev->name, wx); + else + err = request_irq(wx->pdev->irq, &txgbe_intr, IRQF_SHARED, + netdev->name, wx); + + if (err) + wx_err(wx, "request_irq failed, Error %d\n", err); + + return err; +} + +static int txgbe_request_gpio_irq(struct txgbe *txgbe) +{ + txgbe->gpio_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_GPIO); + return request_threaded_irq(txgbe->gpio_irq, NULL, + txgbe_gpio_irq_handler, + IRQF_ONESHOT, "txgbe-gpio-irq", txgbe); +} + +static int txgbe_request_link_irq(struct txgbe *txgbe) +{ + txgbe->link_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_LINK); + return request_threaded_irq(txgbe->link_irq, NULL, + txgbe_link_irq_handler, + IRQF_ONESHOT, "txgbe-link-irq", txgbe); +} + +static const struct irq_chip txgbe_irq_chip = { + .name = "txgbe-misc-irq", +}; + +static int txgbe_misc_irq_domain_map(struct irq_domain *d, + unsigned int irq, + irq_hw_number_t hwirq) +{ + struct txgbe *txgbe = d->host_data; + + irq_set_chip_data(irq, txgbe); + irq_set_chip(irq, &txgbe->misc.chip); + irq_set_nested_thread(irq, true); + irq_set_noprobe(irq); + + return 0; +} + +static const struct irq_domain_ops txgbe_misc_irq_domain_ops = { + .map = txgbe_misc_irq_domain_map, +}; + +static irqreturn_t txgbe_misc_irq_handle(int irq, void *data) +{ + struct txgbe *txgbe = data; + struct wx *wx = txgbe->wx; + unsigned int nhandled = 0; + unsigned int sub_irq; + u32 eicr; + + eicr = wx_misc_isb(wx, WX_ISB_MISC); + if (eicr & TXGBE_PX_MISC_GPIO) { + sub_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_GPIO); + handle_nested_irq(sub_irq); + nhandled++; + } + if (eicr & (TXGBE_PX_MISC_ETH_LK | TXGBE_PX_MISC_ETH_LKDN | + TXGBE_PX_MISC_ETH_AN)) { + sub_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_LINK); + handle_nested_irq(sub_irq); + nhandled++; + } + + wx_intr_enable(wx, TXGBE_INTR_MISC); + return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); +} + +static void txgbe_del_irq_domain(struct txgbe *txgbe) +{ + int hwirq, virq; + + for (hwirq = 0; hwirq < txgbe->misc.nirqs; hwirq++) { + virq = irq_find_mapping(txgbe->misc.domain, hwirq); + irq_dispose_mapping(virq); + } + + irq_domain_remove(txgbe->misc.domain); +} + +void txgbe_free_misc_irq(struct txgbe *txgbe) +{ + free_irq(txgbe->gpio_irq, txgbe); + free_irq(txgbe->link_irq, txgbe); + free_irq(txgbe->misc.irq, txgbe); + txgbe_del_irq_domain(txgbe); +} + +int txgbe_setup_misc_irq(struct txgbe *txgbe) +{ + struct wx *wx = txgbe->wx; + int hwirq, err; + + txgbe->misc.nirqs = 2; + txgbe->misc.domain = irq_domain_add_simple(NULL, txgbe->misc.nirqs, 0, + &txgbe_misc_irq_domain_ops, txgbe); + if (!txgbe->misc.domain) + return -ENOMEM; + + for (hwirq = 0; hwirq < txgbe->misc.nirqs; hwirq++) + irq_create_mapping(txgbe->misc.domain, hwirq); + + txgbe->misc.chip = txgbe_irq_chip; + if (wx->pdev->msix_enabled) + txgbe->misc.irq = wx->msix_entry->vector; + else + txgbe->misc.irq = wx->pdev->irq; + + err = request_threaded_irq(txgbe->misc.irq, NULL, + txgbe_misc_irq_handle, + IRQF_ONESHOT, + wx->netdev->name, txgbe); + if (err) + goto del_misc_irq; + + err = txgbe_request_gpio_irq(txgbe); + if (err) + goto free_msic_irq; + + err = txgbe_request_link_irq(txgbe); + if (err) + goto free_gpio_irq; + + return 0; + +free_gpio_irq: + free_irq(txgbe->gpio_irq, txgbe); +free_msic_irq: + free_irq(txgbe->misc.irq, txgbe); +del_misc_irq: + txgbe_del_irq_domain(txgbe); + + return err; +} diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.h new file mode 100644 index 0000000000000..b77945e7a0f26 --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2015 - 2024 Beijing WangXun Technology Co., Ltd. */ + +void txgbe_irq_enable(struct wx *wx, bool queues); +int txgbe_request_irq(struct wx *wx); +void txgbe_free_misc_irq(struct txgbe *txgbe); +int txgbe_setup_misc_irq(struct txgbe *txgbe); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 3b151c410a5c2..8c7a74981b907 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -17,6 +17,7 @@ #include "txgbe_type.h" #include "txgbe_hw.h" #include "txgbe_phy.h" +#include "txgbe_irq.h" #include "txgbe_ethtool.h" char txgbe_driver_name[] = "txgbe"; @@ -76,137 +77,11 @@ static int txgbe_enumerate_functions(struct wx *wx) return physfns; } -/** - * txgbe_irq_enable - Enable default interrupt generation settings - * @wx: pointer to private structure - * @queues: enable irqs for queues - **/ -static void txgbe_irq_enable(struct wx *wx, bool queues) -{ - wr32(wx, WX_PX_MISC_IEN, TXGBE_PX_MISC_IEN_MASK); - - /* unmask interrupt */ - wx_intr_enable(wx, TXGBE_INTR_MISC); - if (queues) - wx_intr_enable(wx, TXGBE_INTR_QALL(wx)); -} - -/** - * txgbe_intr - msi/legacy mode Interrupt Handler - * @irq: interrupt number - * @data: pointer to a network interface device structure - **/ -static irqreturn_t txgbe_intr(int __always_unused irq, void *data) -{ - struct wx_q_vector *q_vector; - struct wx *wx = data; - struct pci_dev *pdev; - u32 eicr; - - q_vector = wx->q_vector[0]; - pdev = wx->pdev; - - eicr = wx_misc_isb(wx, WX_ISB_VEC0); - if (!eicr) { - /* shared interrupt alert! - * the interrupt that we masked before the ICR read. - */ - if (netif_running(wx->netdev)) - txgbe_irq_enable(wx, true); - return IRQ_NONE; /* Not our interrupt */ - } - wx->isb_mem[WX_ISB_VEC0] = 0; - if (!(pdev->msi_enabled)) - wr32(wx, WX_PX_INTA, 1); - - wx->isb_mem[WX_ISB_MISC] = 0; - /* would disable interrupts here but it is auto disabled */ - napi_schedule_irqoff(&q_vector->napi); - - /* re-enable link(maybe) and non-queue interrupts, no flush. - * txgbe_poll will re-enable the queue interrupts - */ - if (netif_running(wx->netdev)) - txgbe_irq_enable(wx, false); - - return IRQ_HANDLED; -} - -/** - * txgbe_request_msix_irqs - Initialize MSI-X interrupts - * @wx: board private structure - * - * Allocate MSI-X vectors and request interrupts from the kernel. - **/ -static int txgbe_request_msix_irqs(struct wx *wx) -{ - struct net_device *netdev = wx->netdev; - int vector, err; - - for (vector = 0; vector < wx->num_q_vectors; vector++) { - struct wx_q_vector *q_vector = wx->q_vector[vector]; - struct msix_entry *entry = &wx->msix_q_entries[vector]; - - if (q_vector->tx.ring && q_vector->rx.ring) - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "%s-TxRx-%d", netdev->name, entry->entry); - else - /* skip this unused q_vector */ - continue; - - err = request_irq(entry->vector, wx_msix_clean_rings, 0, - q_vector->name, q_vector); - if (err) { - wx_err(wx, "request_irq failed for MSIX interrupt %s Error: %d\n", - q_vector->name, err); - goto free_queue_irqs; - } - } - - return 0; - -free_queue_irqs: - while (vector) { - vector--; - free_irq(wx->msix_q_entries[vector].vector, - wx->q_vector[vector]); - } - wx_reset_interrupt_capability(wx); - return err; -} - -/** - * txgbe_request_irq - initialize interrupts - * @wx: board private structure - * - * Attempt to configure interrupts using the best available - * capabilities of the hardware and kernel. - **/ -static int txgbe_request_irq(struct wx *wx) -{ - struct net_device *netdev = wx->netdev; - struct pci_dev *pdev = wx->pdev; - int err; - - if (pdev->msix_enabled) - err = txgbe_request_msix_irqs(wx); - else if (pdev->msi_enabled) - err = request_irq(wx->pdev->irq, &txgbe_intr, 0, - netdev->name, wx); - else - err = request_irq(wx->pdev->irq, &txgbe_intr, IRQF_SHARED, - netdev->name, wx); - - if (err) - wx_err(wx, "request_irq failed, Error %d\n", err); - - return err; -} - static void txgbe_up_complete(struct wx *wx) { struct net_device *netdev = wx->netdev; + txgbe_reinit_gpio_intr(wx); wx_control_hw(wx, true); wx_configure_vectors(wx); @@ -394,6 +269,8 @@ static int txgbe_sw_init(struct wx *wx) wx->tx_work_limit = TXGBE_DEFAULT_TX_WORK; wx->rx_work_limit = TXGBE_DEFAULT_RX_WORK; + wx->do_reset = txgbe_do_reset; + return 0; } @@ -518,6 +395,7 @@ static void txgbe_shutdown(struct pci_dev *pdev) int txgbe_setup_tc(struct net_device *dev, u8 tc) { struct wx *wx = netdev_priv(dev); + struct txgbe *txgbe = wx->priv; /* Hardware has to reinitialize queues and interrupts to * match packet buffer alignment. Unfortunately, the @@ -528,6 +406,7 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc) else txgbe_reset(wx); + txgbe_free_misc_irq(txgbe); wx_clear_interrupt_scheme(wx); if (tc) @@ -536,6 +415,7 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc) netdev_reset_tc(dev); wx_init_interrupt_scheme(wx); + txgbe_setup_misc_irq(txgbe); if (netif_running(dev)) txgbe_open(dev); @@ -543,6 +423,34 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc) return 0; } +static void txgbe_reinit_locked(struct wx *wx) +{ + int err = 0; + + netif_trans_update(wx->netdev); + + err = wx_set_state_reset(wx); + if (err) { + wx_err(wx, "wait device reset timeout\n"); + return; + } + + txgbe_down(wx); + txgbe_up(wx); + + clear_bit(WX_STATE_RESETTING, wx->state); +} + +void txgbe_do_reset(struct net_device *netdev) +{ + struct wx *wx = netdev_priv(netdev); + + if (netif_running(netdev)) + txgbe_reinit_locked(wx); + else + txgbe_reset(wx); +} + static const struct net_device_ops txgbe_netdev_ops = { .ndo_open = txgbe_open, .ndo_stop = txgbe_close, @@ -550,6 +458,7 @@ static const struct net_device_ops txgbe_netdev_ops = { .ndo_start_xmit = wx_xmit_frame, .ndo_set_rx_mode = wx_set_rx_mode, .ndo_set_features = wx_set_features, + .ndo_fix_features = wx_fix_features, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = wx_set_mac, .ndo_get_stats64 = wx_get_stats64, @@ -751,10 +660,14 @@ static int txgbe_probe(struct pci_dev *pdev, txgbe->wx = wx; wx->priv = txgbe; - err = txgbe_init_phy(txgbe); + err = txgbe_setup_misc_irq(txgbe); if (err) goto err_release_hw; + err = txgbe_init_phy(txgbe); + if (err) + goto err_free_misc_irq; + err = register_netdev(netdev); if (err) goto err_remove_phy; @@ -781,6 +694,8 @@ static int txgbe_probe(struct pci_dev *pdev, err_remove_phy: txgbe_remove_phy(txgbe); +err_free_misc_irq: + txgbe_free_misc_irq(txgbe); err_release_hw: wx_clear_interrupt_scheme(wx); wx_control_hw(wx, false); @@ -813,6 +728,7 @@ static void txgbe_remove(struct pci_dev *pdev) unregister_netdev(netdev); txgbe_remove_phy(txgbe); + txgbe_free_misc_irq(txgbe); pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c index 1b84d495d14e8..93295916b1d2b 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -292,6 +292,21 @@ static int txgbe_phylink_init(struct txgbe *txgbe) return 0; } +irqreturn_t txgbe_link_irq_handler(int irq, void *data) +{ + struct txgbe *txgbe = data; + struct wx *wx = txgbe->wx; + u32 status; + bool up; + + status = rd32(wx, TXGBE_CFG_PORT_ST); + up = !!(status & TXGBE_CFG_PORT_ST_LINK_UP); + + phylink_mac_change(wx->phylink, up); + + return IRQ_HANDLED; +} + static int txgbe_gpio_get(struct gpio_chip *chip, unsigned int offset) { struct wx *wx = gpiochip_get_data(chip); @@ -437,7 +452,7 @@ static int txgbe_gpio_set_type(struct irq_data *d, unsigned int type) } static const struct irq_chip txgbe_gpio_irq_chip = { - .name = "txgbe_gpio_irq", + .name = "txgbe-gpio-irq", .irq_ack = txgbe_gpio_irq_ack, .irq_mask = txgbe_gpio_irq_mask, .irq_unmask = txgbe_gpio_irq_unmask, @@ -446,29 +461,25 @@ static const struct irq_chip txgbe_gpio_irq_chip = { GPIOCHIP_IRQ_RESOURCE_HELPERS, }; -static void txgbe_irq_handler(struct irq_desc *desc) +irqreturn_t txgbe_gpio_irq_handler(int irq, void *data) { - struct irq_chip *chip = irq_desc_get_chip(desc); - struct wx *wx = irq_desc_get_handler_data(desc); - struct txgbe *txgbe = wx->priv; + struct txgbe *txgbe = data; + struct wx *wx = txgbe->wx; irq_hw_number_t hwirq; unsigned long gpioirq; struct gpio_chip *gc; unsigned long flags; - u32 eicr; - - eicr = wx_misc_isb(wx, WX_ISB_MISC); - - chained_irq_enter(chip, desc); gpioirq = rd32(wx, WX_GPIO_INTSTATUS); gc = txgbe->gpio; for_each_set_bit(hwirq, &gpioirq, gc->ngpio) { int gpio = irq_find_mapping(gc->irq.domain, hwirq); + struct irq_data *d = irq_get_irq_data(gpio); u32 irq_type = irq_get_trigger_type(gpio); - generic_handle_domain_irq(gc->irq.domain, hwirq); + txgbe_gpio_irq_ack(d); + handle_nested_irq(gpio); if ((irq_type & IRQ_TYPE_SENSE_MASK) == IRQ_TYPE_EDGE_BOTH) { raw_spin_lock_irqsave(&wx->gpio_lock, flags); @@ -477,17 +488,34 @@ static void txgbe_irq_handler(struct irq_desc *desc) } } - chained_irq_exit(chip, desc); + return IRQ_HANDLED; +} + +void txgbe_reinit_gpio_intr(struct wx *wx) +{ + struct txgbe *txgbe = wx->priv; + irq_hw_number_t hwirq; + unsigned long gpioirq; + struct gpio_chip *gc; + unsigned long flags; + + /* for gpio interrupt pending before irq enable */ + gpioirq = rd32(wx, WX_GPIO_INTSTATUS); - if (eicr & (TXGBE_PX_MISC_ETH_LK | TXGBE_PX_MISC_ETH_LKDN | - TXGBE_PX_MISC_ETH_AN)) { - u32 reg = rd32(wx, TXGBE_CFG_PORT_ST); + gc = txgbe->gpio; + for_each_set_bit(hwirq, &gpioirq, gc->ngpio) { + int gpio = irq_find_mapping(gc->irq.domain, hwirq); + struct irq_data *d = irq_get_irq_data(gpio); + u32 irq_type = irq_get_trigger_type(gpio); - phylink_mac_change(wx->phylink, !!(reg & TXGBE_CFG_PORT_ST_LINK_UP)); - } + txgbe_gpio_irq_ack(d); - /* unmask interrupt */ - wx_intr_enable(wx, TXGBE_INTR_MISC); + if ((irq_type & IRQ_TYPE_SENSE_MASK) == IRQ_TYPE_EDGE_BOTH) { + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + txgbe_toggle_trigger(gc, hwirq); + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); + } + } } static int txgbe_gpio_init(struct txgbe *txgbe) @@ -524,19 +552,6 @@ static int txgbe_gpio_init(struct txgbe *txgbe) girq = &gc->irq; gpio_irq_chip_set_chip(girq, &txgbe_gpio_irq_chip); - girq->parent_handler = txgbe_irq_handler; - girq->parent_handler_data = wx; - girq->num_parents = 1; - girq->parents = devm_kcalloc(dev, girq->num_parents, - sizeof(*girq->parents), GFP_KERNEL); - if (!girq->parents) - return -ENOMEM; - - /* now only suuported on MSI-X interrupt */ - if (!wx->msix_entry) - return -EPERM; - - girq->parents[0] = wx->msix_entry->vector; girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_bad_irq; @@ -754,8 +769,6 @@ int txgbe_init_phy(struct txgbe *txgbe) goto err_unregister_i2c; } - wx->msix_in_use = true; - return 0; err_unregister_i2c: @@ -788,5 +801,4 @@ void txgbe_remove_phy(struct txgbe *txgbe) phylink_destroy(txgbe->wx->phylink); xpcs_destroy(txgbe->xpcs); software_node_unregister_node_group(txgbe->nodes.group); - txgbe->wx->msix_in_use = false; } diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h index 1ab592124986a..8a026d804fe24 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h @@ -4,6 +4,9 @@ #ifndef _TXGBE_PHY_H_ #define _TXGBE_PHY_H_ +irqreturn_t txgbe_gpio_irq_handler(int irq, void *data); +void txgbe_reinit_gpio_intr(struct wx *wx); +irqreturn_t txgbe_link_irq_handler(int irq, void *data); int txgbe_init_phy(struct txgbe *txgbe); void txgbe_remove_phy(struct txgbe *txgbe); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index 270a6fd9ad0b0..f434a7865cb7b 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -5,6 +5,7 @@ #define _TXGBE_TYPE_H_ #include +#include /* Device IDs */ #define TXGBE_DEV_ID_SP1000 0x1001 @@ -133,6 +134,7 @@ extern char txgbe_driver_name[]; void txgbe_down(struct wx *wx); void txgbe_up(struct wx *wx); int txgbe_setup_tc(struct net_device *dev, u8 tc); +void txgbe_do_reset(struct net_device *netdev); #define NODE_PROP(_NAME, _PROP) \ (const struct software_node) { \ @@ -169,15 +171,31 @@ struct txgbe_nodes { const struct software_node *group[SWNODE_MAX + 1]; }; +enum txgbe_misc_irqs { + TXGBE_IRQ_GPIO = 0, + TXGBE_IRQ_LINK, + TXGBE_IRQ_MAX +}; + +struct txgbe_irq { + struct irq_chip chip; + struct irq_domain *domain; + int nirqs; + int irq; +}; + struct txgbe { struct wx *wx; struct txgbe_nodes nodes; + struct txgbe_irq misc; struct dw_xpcs *xpcs; struct platform_device *sfp_dev; struct platform_device *i2c_dev; struct clk_lookup *clock; struct clk *clk; struct gpio_chip *gpio; + unsigned int gpio_irq; + unsigned int link_irq; }; #endif /* _TXGBE_TYPE_H_ */ diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 9df39cf8b0975..1072e2210aed3 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1443,7 +1443,7 @@ static int temac_probe(struct platform_device *pdev) } /* map device registers */ - lp->regs = devm_platform_ioremap_resource_byname(pdev, 0); + lp->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(lp->regs)) { dev_err(&pdev->dev, "could not map TEMAC registers\n"); return -ENOMEM; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index c4ed36c718974..bcab3f36272ed 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -349,6 +349,7 @@ static int geneve_init(struct net_device *dev) gro_cells_destroy(&geneve->gro_cells); return err; } + netdev_lockdep_set_classes(dev); return 0; } @@ -818,6 +819,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { + bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); const struct ip_tunnel_key *key = &info->key; @@ -829,7 +831,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!pskb_inet_may_pull(skb)) + if (!skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs4) @@ -910,7 +912,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, } err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr), - geneve->cfg.inner_proto_inherit); + inner_proto_inherit); if (unlikely(err)) return err; @@ -926,6 +928,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { + bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); const struct ip_tunnel_key *key = &info->key; @@ -936,7 +939,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!pskb_inet_may_pull(skb)) + if (!skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs6) @@ -998,7 +1001,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr), - geneve->cfg.inner_proto_inherit); + inner_proto_inherit); if (unlikely(err)) return err; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 2b5357d94ff56..63f932256c9f5 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1111,11 +1111,12 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, static void gtp_dellink(struct net_device *dev, struct list_head *head) { struct gtp_dev *gtp = netdev_priv(dev); + struct hlist_node *next; struct pdp_ctx *pctx; int i; for (i = 0; i < gtp->hash_size; i++) - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid) pdp_context_delete(pctx); list_del_rcu(>p->list); diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index a6fcbda64ecc6..2b6ec979a62f2 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -154,8 +154,11 @@ static void free_netvsc_device(struct rcu_head *head) int i; kfree(nvdev->extension); - vfree(nvdev->recv_buf); - vfree(nvdev->send_buf); + + if (!nvdev->recv_buf_gpadl_handle.decrypted) + vfree(nvdev->recv_buf); + if (!nvdev->send_buf_gpadl_handle.decrypted) + vfree(nvdev->send_buf); bitmap_free(nvdev->send_section_map); for (i = 0; i < VRSS_CHANNEL_MAX; i++) { diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 2d5b021b4ea60..fef4eff7753a7 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -439,7 +439,7 @@ static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - err = ip_local_out(net, skb->sk, skb); + err = ip_local_out(net, NULL, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else @@ -494,7 +494,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); - err = ip6_local_out(dev_net(dev), skb->sk, skb); + err = ip6_local_out(dev_net(dev), NULL, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index f6d53e63ef4ec..f6eab66c26608 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -144,6 +144,7 @@ static int loopback_dev_init(struct net_device *dev) dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); if (!dev->lstats) return -ENOMEM; + netdev_lockdep_set_classes(dev); return 0; } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 7f5426285c61b..ac3f6801c940c 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -999,10 +999,12 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) struct metadata_dst *md_dst; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; + bool is_macsec_md_dst; rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); md_dst = skb_metadata_dst(skb); + is_macsec_md_dst = md_dst && md_dst->type == METADATA_MACSEC; list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; @@ -1013,14 +1015,42 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) * the SecTAG, so we have to deduce which port to deliver to. */ if (macsec_is_offloaded(macsec) && netif_running(ndev)) { - struct macsec_rx_sc *rx_sc = NULL; + const struct macsec_ops *ops; - if (md_dst && md_dst->type == METADATA_MACSEC) - rx_sc = find_rx_sc(&macsec->secy, md_dst->u.macsec_info.sci); + ops = macsec_get_ops(macsec, NULL); - if (md_dst && md_dst->type == METADATA_MACSEC && !rx_sc) + if (ops->rx_uses_md_dst && !is_macsec_md_dst) continue; + if (is_macsec_md_dst) { + struct macsec_rx_sc *rx_sc; + + /* All drivers that implement MACsec offload + * support using skb metadata destinations must + * indicate that they do so. + */ + DEBUG_NET_WARN_ON_ONCE(!ops->rx_uses_md_dst); + rx_sc = find_rx_sc(&macsec->secy, + md_dst->u.macsec_info.sci); + if (!rx_sc) + continue; + /* device indicated macsec offload occurred */ + skb->dev = ndev; + skb->pkt_type = PACKET_HOST; + eth_skb_pkt_type(skb, ndev); + ret = RX_HANDLER_ANOTHER; + goto out; + } + + /* This datapath is insecure because it is unable to + * enforce isolation of broadcast/multicast traffic and + * unicast traffic with promiscuous mode on the macsec + * netdev. Since the core stack has no mechanism to + * check that the hardware did indeed receive MACsec + * traffic, it is possible that the response handling + * done by the MACsec port was to a plaintext packet. + * This violates the MACsec protocol standard. + */ if (ether_addr_equal_64bits(hdr->h_dest, ndev->dev_addr)) { /* exact match, divert skb to this port */ @@ -1036,14 +1066,10 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) break; nskb->dev = ndev; - if (ether_addr_equal_64bits(hdr->h_dest, - ndev->broadcast)) - nskb->pkt_type = PACKET_BROADCAST; - else - nskb->pkt_type = PACKET_MULTICAST; + eth_skb_pkt_type(nskb, ndev); __netif_rx(nskb); - } else if (rx_sc || ndev->flags & IFF_PROMISC) { + } else if (ndev->flags & IFF_PROMISC) { skb->dev = ndev; skb->pkt_type = PACKET_HOST; ret = RX_HANDLER_ANOTHER; diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 39171380ccf29..5cc794a2a789d 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -55,6 +55,7 @@ static void netkit_prep_forward(struct sk_buff *skb, bool xnet) skb_scrub_packet(skb, xnet); skb->priority = 0; nf_skip_egress(skb, true); + skb_reset_mac_header(skb); } static struct netkit *netkit_priv(const struct net_device *dev) @@ -78,6 +79,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) skb_orphan_frags(skb, GFP_ATOMIC))) goto drop; netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer))); + eth_skb_pkt_type(skb, peer); skb->dev = peer; entry = rcu_dereference(nk->active); if (entry) @@ -85,7 +87,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) switch (ret) { case NETKIT_NEXT: case NETKIT_PASS: - skb->protocol = eth_type_trans(skb, skb->dev); + eth_skb_pull_mac(skb); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { dev_sw_netstats_tx_add(dev, 1, len); @@ -155,6 +157,16 @@ static void netkit_set_multicast(struct net_device *dev) /* Nothing to do, we receive whatever gets pushed to us! */ } +static int netkit_set_macaddr(struct net_device *dev, void *sa) +{ + struct netkit *nk = netkit_priv(dev); + + if (nk->mode != NETKIT_L2) + return -EOPNOTSUPP; + + return eth_mac_addr(dev, sa); +} + static void netkit_set_headroom(struct net_device *dev, int headroom) { struct netkit *nk = netkit_priv(dev), *nk2; @@ -198,6 +210,7 @@ static const struct net_device_ops netkit_netdev_ops = { .ndo_start_xmit = netkit_xmit, .ndo_set_rx_mode = netkit_set_multicast, .ndo_set_rx_headroom = netkit_set_headroom, + .ndo_set_mac_address = netkit_set_macaddr, .ndo_get_iflink = netkit_get_iflink, .ndo_get_peer_dev = netkit_peer_dev, .ndo_get_stats64 = netkit_get_stats, @@ -300,9 +313,11 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], if (!attr) return 0; - NL_SET_ERR_MSG_ATTR(extack, attr, - "Setting Ethernet address is not supported"); - return -EOPNOTSUPP; + if (nla_len(attr) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(attr))) + return -EADDRNOTAVAIL; + return 0; } static struct rtnl_link_ops netkit_link_ops; @@ -365,6 +380,9 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, strscpy(ifname, "nk%d", IFNAMSIZ); ifname_assign_type = NET_NAME_ENUM; } + if (mode != NETKIT_L2 && + (tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS])) + return -EOPNOTSUPP; net = rtnl_link_get_net(src_net, tbp); if (IS_ERR(net)) @@ -379,7 +397,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, netif_inherit_tso_max(peer, dev); - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) eth_hw_addr_random(peer); if (ifmp && dev->ifindex) peer->ifindex = ifmp->ifi_index; @@ -402,7 +420,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, if (err < 0) goto err_configure_peer; - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 31f0beba638a2..03d6a6aef77cd 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -293,7 +293,7 @@ static int xpcs_soft_reset(struct dw_xpcs *xpcs, dev = MDIO_MMD_VEND2; break; default: - return -1; + return -EINVAL; } ret = xpcs_write(xpcs, dev, MDIO_CTRL1, MDIO_CTRL1_RESET); @@ -891,7 +891,7 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, return ret; break; default: - return -1; + return -EINVAL; } if (compat->pma_config) { diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index a62442a55774c..fdb89a505de3d 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -1503,7 +1503,7 @@ static int at8031_parse_dt(struct phy_device *phydev) static int at8031_probe(struct phy_device *phydev) { - struct at803x_priv *priv = phydev->priv; + struct at803x_priv *priv; int mode_cfg; int ccr; int ret; @@ -1512,6 +1512,8 @@ static int at8031_probe(struct phy_device *phydev) if (ret) return ret; + priv = phydev->priv; + /* Only supported on AR8031/AR8033, the AR8030/AR8035 use strapping * options. */ diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index b7cb71817780c..29e1cbea6dc0c 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -380,7 +380,7 @@ static int dp83822_config_init(struct phy_device *phydev) { struct dp83822_private *dp83822 = phydev->priv; struct device *dev = &phydev->mdio.dev; - int rgmii_delay; + int rgmii_delay = 0; s32 rx_int_delay; s32 tx_int_delay; int err = 0; @@ -390,30 +390,33 @@ static int dp83822_config_init(struct phy_device *phydev) rx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, true); - if (rx_int_delay <= 0) - rgmii_delay = 0; - else - rgmii_delay = DP83822_RX_CLK_SHIFT; + /* Set DP83822_RX_CLK_SHIFT to enable rx clk internal delay */ + if (rx_int_delay > 0) + rgmii_delay |= DP83822_RX_CLK_SHIFT; tx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, false); + + /* Set DP83822_TX_CLK_SHIFT to disable tx clk internal delay */ if (tx_int_delay <= 0) - rgmii_delay &= ~DP83822_TX_CLK_SHIFT; - else rgmii_delay |= DP83822_TX_CLK_SHIFT; - if (rgmii_delay) { - err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_RCSR, rgmii_delay); - if (err) - return err; - } + err = phy_modify_mmd(phydev, DP83822_DEVADDR, MII_DP83822_RCSR, + DP83822_RX_CLK_SHIFT | DP83822_TX_CLK_SHIFT, rgmii_delay); + if (err) + return err; + + err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); - phy_set_bits_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); + if (err) + return err; } else { - phy_clear_bits_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); + err = phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); + + if (err) + return err; } if (dp83822->fx_enabled) { diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index fa8c6fdcf3018..d7aaefb5226b6 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -695,7 +695,8 @@ static int dp83869_configure_mode(struct phy_device *phydev, phy_ctrl_val = dp83869->mode; if (phydev->interface == PHY_INTERFACE_MODE_MII) { if (dp83869->mode == DP83869_100M_MEDIA_CONVERT || - dp83869->mode == DP83869_RGMII_100_BASE) { + dp83869->mode == DP83869_RGMII_100_BASE || + dp83869->mode == DP83869_RGMII_COPPER_ETHERNET) { phy_ctrl_val |= DP83869_OP_MODE_MII; } else { phydev_err(phydev, "selected op-mode is not valid with MII mode\n"); diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c index 326c9770a6dcc..c706429b225a2 100644 --- a/drivers/net/phy/dp83tg720.c +++ b/drivers/net/phy/dp83tg720.c @@ -17,6 +17,11 @@ #define DP83TG720S_PHY_RESET 0x1f #define DP83TG720S_HW_RESET BIT(15) +#define DP83TG720S_LPS_CFG3 0x18c +/* Power modes are documented as bit fields but used as values */ +/* Power Mode 0 is Normal mode */ +#define DP83TG720S_LPS_CFG3_PWR_MODE_0 BIT(0) + #define DP83TG720S_RGMII_DELAY_CTRL 0x602 /* In RGMII mode, Enable or disable the internal delay for RXD */ #define DP83TG720S_RGMII_RX_CLK_SEL BIT(1) @@ -31,11 +36,20 @@ static int dp83tg720_config_aneg(struct phy_device *phydev) { + int ret; + /* Autoneg is not supported and this PHY supports only one speed. * We need to care only about master/slave configuration if it was * changed by user. */ - return genphy_c45_pma_baset1_setup_master_slave(phydev); + ret = genphy_c45_pma_baset1_setup_master_slave(phydev); + if (ret) + return ret; + + /* Re-read role configuration to make changes visible even if + * the link is in administrative down state. + */ + return genphy_c45_pma_baset1_read_master_slave(phydev); } static int dp83tg720_read_status(struct phy_device *phydev) @@ -64,6 +78,8 @@ static int dp83tg720_read_status(struct phy_device *phydev) return ret; /* After HW reset we need to restore master/slave configuration. + * genphy_c45_pma_baset1_read_master_slave() call will be done + * by the dp83tg720_config_aneg() function. */ ret = dp83tg720_config_aneg(phydev); if (ret) @@ -154,10 +170,24 @@ static int dp83tg720_config_init(struct phy_device *phydev) */ usleep_range(1000, 2000); - if (phy_interface_is_rgmii(phydev)) - return dp83tg720_config_rgmii_delay(phydev); + if (phy_interface_is_rgmii(phydev)) { + ret = dp83tg720_config_rgmii_delay(phydev); + if (ret) + return ret; + } + + /* In case the PHY is bootstrapped in managed mode, we need to + * wake it. + */ + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_LPS_CFG3, + DP83TG720S_LPS_CFG3_PWR_MODE_0); + if (ret) + return ret; - return 0; + /* Make role configuration visible for ethtool on init and after + * rest. + */ + return genphy_c45_pma_baset1_read_master_slave(phydev); } static struct phy_driver dp83tg720_driver[] = { diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index eba652a4c1d88..fc55f19994fcd 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -312,6 +313,16 @@ struct marvell_priv { s8 pair; }; +static const struct dmi_system_id skip_config_led_tbl[] = { + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Dell EMC"), + DMI_MATCH(DMI_BOARD_NAME, "0d370eed-89ca-4dc0-a365-e9904c4c62bb"), + }, + }, + {} +}; + static int marvell_read_page(struct phy_device *phydev) { return __phy_read(phydev, MII_MARVELL_PHY_PAGE); @@ -759,6 +770,9 @@ static void marvell_config_led(struct phy_device *phydev) u16 def_config; int err; + if (dmi_check_system(skip_config_led_tbl)) + return; + switch (MARVELL_PHY_FAMILY_ID(phydev->phy_id)) { /* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */ case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1121R): diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c index 0f3a1538a8b8e..f4f9412d0cd7e 100644 --- a/drivers/net/phy/mediatek-ge-soc.c +++ b/drivers/net/phy/mediatek-ge-soc.c @@ -216,6 +216,9 @@ #define MTK_PHY_LED_ON_LINK1000 BIT(0) #define MTK_PHY_LED_ON_LINK100 BIT(1) #define MTK_PHY_LED_ON_LINK10 BIT(2) +#define MTK_PHY_LED_ON_LINK (MTK_PHY_LED_ON_LINK10 |\ + MTK_PHY_LED_ON_LINK100 |\ + MTK_PHY_LED_ON_LINK1000) #define MTK_PHY_LED_ON_LINKDOWN BIT(3) #define MTK_PHY_LED_ON_FDX BIT(4) /* Full duplex */ #define MTK_PHY_LED_ON_HDX BIT(5) /* Half duplex */ @@ -231,6 +234,12 @@ #define MTK_PHY_LED_BLINK_100RX BIT(3) #define MTK_PHY_LED_BLINK_10TX BIT(4) #define MTK_PHY_LED_BLINK_10RX BIT(5) +#define MTK_PHY_LED_BLINK_RX (MTK_PHY_LED_BLINK_10RX |\ + MTK_PHY_LED_BLINK_100RX |\ + MTK_PHY_LED_BLINK_1000RX) +#define MTK_PHY_LED_BLINK_TX (MTK_PHY_LED_BLINK_10TX |\ + MTK_PHY_LED_BLINK_100TX |\ + MTK_PHY_LED_BLINK_1000TX) #define MTK_PHY_LED_BLINK_COLLISION BIT(6) #define MTK_PHY_LED_BLINK_RX_CRC_ERR BIT(7) #define MTK_PHY_LED_BLINK_RX_IDLE_ERR BIT(8) @@ -1247,11 +1256,9 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, if (blink < 0) return -EIO; - if ((on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 | - MTK_PHY_LED_ON_LINK10)) || - (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX | - MTK_PHY_LED_BLINK_10RX | MTK_PHY_LED_BLINK_1000TX | - MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX))) + if ((on & (MTK_PHY_LED_ON_LINK | MTK_PHY_LED_ON_FDX | MTK_PHY_LED_ON_HDX | + MTK_PHY_LED_ON_LINKDOWN)) || + (blink & (MTK_PHY_LED_BLINK_RX | MTK_PHY_LED_BLINK_TX))) set_bit(bit_netdev, &priv->led_state); else clear_bit(bit_netdev, &priv->led_state); @@ -1269,7 +1276,7 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, if (!rules) return 0; - if (on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 | MTK_PHY_LED_ON_LINK10)) + if (on & MTK_PHY_LED_ON_LINK) *rules |= BIT(TRIGGER_NETDEV_LINK); if (on & MTK_PHY_LED_ON_LINK10) @@ -1287,10 +1294,10 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, if (on & MTK_PHY_LED_ON_HDX) *rules |= BIT(TRIGGER_NETDEV_HALF_DUPLEX); - if (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX | MTK_PHY_LED_BLINK_10RX)) + if (blink & MTK_PHY_LED_BLINK_RX) *rules |= BIT(TRIGGER_NETDEV_RX); - if (blink & (MTK_PHY_LED_BLINK_1000TX | MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX)) + if (blink & MTK_PHY_LED_BLINK_TX) *rules |= BIT(TRIGGER_NETDEV_TX); return 0; @@ -1323,15 +1330,19 @@ static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index, on |= MTK_PHY_LED_ON_LINK1000; if (rules & BIT(TRIGGER_NETDEV_RX)) { - blink |= MTK_PHY_LED_BLINK_10RX | - MTK_PHY_LED_BLINK_100RX | - MTK_PHY_LED_BLINK_1000RX; + blink |= (on & MTK_PHY_LED_ON_LINK) ? + (((on & MTK_PHY_LED_ON_LINK10) ? MTK_PHY_LED_BLINK_10RX : 0) | + ((on & MTK_PHY_LED_ON_LINK100) ? MTK_PHY_LED_BLINK_100RX : 0) | + ((on & MTK_PHY_LED_ON_LINK1000) ? MTK_PHY_LED_BLINK_1000RX : 0)) : + MTK_PHY_LED_BLINK_RX; } if (rules & BIT(TRIGGER_NETDEV_TX)) { - blink |= MTK_PHY_LED_BLINK_10TX | - MTK_PHY_LED_BLINK_100TX | - MTK_PHY_LED_BLINK_1000TX; + blink |= (on & MTK_PHY_LED_ON_LINK) ? + (((on & MTK_PHY_LED_ON_LINK10) ? MTK_PHY_LED_BLINK_10TX : 0) | + ((on & MTK_PHY_LED_ON_LINK100) ? MTK_PHY_LED_BLINK_100TX : 0) | + ((on & MTK_PHY_LED_ON_LINK1000) ? MTK_PHY_LED_BLINK_1000TX : 0)) : + MTK_PHY_LED_BLINK_TX; } if (blink || on) @@ -1344,9 +1355,7 @@ static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index, MTK_PHY_LED0_ON_CTRL, MTK_PHY_LED_ON_FDX | MTK_PHY_LED_ON_HDX | - MTK_PHY_LED_ON_LINK10 | - MTK_PHY_LED_ON_LINK100 | - MTK_PHY_LED_ON_LINK1000, + MTK_PHY_LED_ON_LINK, on); if (ret) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index dad720138baaf..5d2f7a0514a92 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -770,6 +770,17 @@ static int ksz8061_config_init(struct phy_device *phydev) { int ret; + /* Chip can be powered down by the bootstrap code. */ + ret = phy_read(phydev, MII_BMCR); + if (ret < 0) + return ret; + if (ret & BMCR_PDOWN) { + ret = phy_write(phydev, MII_BMCR, ret & ~BMCR_PDOWN); + if (ret < 0) + return ret; + usleep_range(1000, 2000); + } + ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A); if (ret) return ret; @@ -1843,7 +1854,7 @@ static const struct ksz9477_errata_write ksz9477_errata_writes[] = { {0x1c, 0x20, 0xeeee}, }; -static int ksz9477_config_init(struct phy_device *phydev) +static int ksz9477_phy_errata(struct phy_device *phydev) { int err; int i; @@ -1871,16 +1882,30 @@ static int ksz9477_config_init(struct phy_device *phydev) return err; } + err = genphy_restart_aneg(phydev); + if (err) + return err; + + return err; +} + +static int ksz9477_config_init(struct phy_device *phydev) +{ + int err; + + /* Only KSZ9897 family of switches needs this fix. */ + if ((phydev->phy_id & 0xf) == 1) { + err = ksz9477_phy_errata(phydev); + if (err) + return err; + } + /* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes * in this switch shall be regarded as broken. */ if (phydev->dev_flags & MICREL_NO_EEE) phydev->eee_broken_modes = -1; - err = genphy_restart_aneg(phydev); - if (err) - return err; - return kszphy_config_init(phydev); } @@ -1989,6 +2014,71 @@ static int kszphy_resume(struct phy_device *phydev) return 0; } +static int ksz9477_resume(struct phy_device *phydev) +{ + int ret; + + /* No need to initialize registers if not powered down. */ + ret = phy_read(phydev, MII_BMCR); + if (ret < 0) + return ret; + if (!(ret & BMCR_PDOWN)) + return 0; + + genphy_resume(phydev); + + /* After switching from power-down to normal mode, an internal global + * reset is automatically generated. Wait a minimum of 1 ms before + * read/write access to the PHY registers. + */ + usleep_range(1000, 2000); + + /* Only KSZ9897 family of switches needs this fix. */ + if ((phydev->phy_id & 0xf) == 1) { + ret = ksz9477_phy_errata(phydev); + if (ret) + return ret; + } + + /* Enable PHY Interrupts */ + if (phy_interrupt_is_valid(phydev)) { + phydev->interrupts = PHY_INTERRUPT_ENABLED; + if (phydev->drv->config_intr) + phydev->drv->config_intr(phydev); + } + + return 0; +} + +static int ksz8061_resume(struct phy_device *phydev) +{ + int ret; + + /* This function can be called twice when the Ethernet device is on. */ + ret = phy_read(phydev, MII_BMCR); + if (ret < 0) + return ret; + if (!(ret & BMCR_PDOWN)) + return 0; + + genphy_resume(phydev); + usleep_range(1000, 2000); + + /* Re-program the value after chip is reset. */ + ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A); + if (ret) + return ret; + + /* Enable PHY Interrupts */ + if (phy_interrupt_is_valid(phydev)) { + phydev->interrupts = PHY_INTERRUPT_ENABLED; + if (phydev->drv->config_intr) + phydev->drv->config_intr(phydev); + } + + return 0; +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -2416,6 +2506,7 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct lan8814_ptp_rx_ts *rx_ts, *tmp; int txcfg = 0, rxcfg = 0; int pkt_ts_enable; + int tx_mod; ptp_priv->hwts_tx_type = config->tx_type; ptp_priv->rx_filter = config->rx_filter; @@ -2462,9 +2553,14 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_RX_TIMESTAMP_EN, pkt_ts_enable); lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_TIMESTAMP_EN, pkt_ts_enable); - if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) + tx_mod = lanphy_read_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD); + if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) { lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD, - PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + tx_mod | PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + } else if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ON) { + lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD, + tx_mod & ~PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); + } if (config->rx_filter != HWTSTAMP_FILTER_NONE) lan8814_config_ts_intr(ptp_priv->phydev, true); @@ -2522,7 +2618,7 @@ static void lan8814_txtstamp(struct mii_timestamper *mii_ts, } } -static void lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) +static bool lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) { struct ptp_header *ptp_header; u32 type; @@ -2532,7 +2628,11 @@ static void lan8814_get_sig_rx(struct sk_buff *skb, u16 *sig) ptp_header = ptp_parse_header(skb, type); skb_pull_inline(skb, ETH_HLEN); + if (!ptp_header) + return false; + *sig = (__force u16)(ntohs(ptp_header->sequence_id)); + return true; } static bool lan8814_match_rx_skb(struct kszphy_ptp_priv *ptp_priv, @@ -2544,7 +2644,8 @@ static bool lan8814_match_rx_skb(struct kszphy_ptp_priv *ptp_priv, bool ret = false; u16 skb_sig; - lan8814_get_sig_rx(skb, &skb_sig); + if (!lan8814_get_sig_rx(skb, &skb_sig)) + return ret; /* Iterate over all RX timestamps and match it with the received skbs */ spin_lock_irqsave(&ptp_priv->rx_ts_lock, flags); @@ -2824,7 +2925,7 @@ static int lan8814_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm) return 0; } -static void lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) +static bool lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) { struct ptp_header *ptp_header; u32 type; @@ -2832,7 +2933,11 @@ static void lan8814_get_sig_tx(struct sk_buff *skb, u16 *sig) type = ptp_classify_raw(skb); ptp_header = ptp_parse_header(skb, type); + if (!ptp_header) + return false; + *sig = (__force u16)(ntohs(ptp_header->sequence_id)); + return true; } static void lan8814_match_tx_skb(struct kszphy_ptp_priv *ptp_priv, @@ -2846,7 +2951,8 @@ static void lan8814_match_tx_skb(struct kszphy_ptp_priv *ptp_priv, spin_lock_irqsave(&ptp_priv->tx_queue.lock, flags); skb_queue_walk_safe(&ptp_priv->tx_queue, skb, skb_tmp) { - lan8814_get_sig_tx(skb, &skb_sig); + if (!lan8814_get_sig_tx(skb, &skb_sig)) + continue; if (memcmp(&skb_sig, &seq_id, sizeof(seq_id))) continue; @@ -2900,7 +3006,8 @@ static bool lan8814_match_skb(struct kszphy_ptp_priv *ptp_priv, spin_lock_irqsave(&ptp_priv->rx_queue.lock, flags); skb_queue_walk_safe(&ptp_priv->rx_queue, skb, skb_tmp) { - lan8814_get_sig_rx(skb, &skb_sig); + if (!lan8814_get_sig_rx(skb, &skb_sig)) + continue; if (memcmp(&skb_sig, &rx_ts->seq_id, sizeof(rx_ts->seq_id))) continue; @@ -3458,7 +3565,7 @@ static int lan8841_config_intr(struct phy_device *phydev) if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { err = phy_read(phydev, LAN8814_INTS); - if (err) + if (err < 0) return err; /* Enable / disable interrupts. It is OK to enable PTP interrupt @@ -3474,6 +3581,14 @@ static int lan8841_config_intr(struct phy_device *phydev) return err; err = phy_read(phydev, LAN8814_INTS); + if (err < 0) + return err; + + /* Getting a positive value doesn't mean that is an error, it + * just indicates what was the status. Therefore make sure to + * clear the value and say that there is no error. + */ + err = 0; } return err; @@ -4618,7 +4733,8 @@ static int lan8841_suspend(struct phy_device *phydev) struct kszphy_priv *priv = phydev->priv; struct kszphy_ptp_priv *ptp_priv = &priv->ptp_priv; - ptp_cancel_worker_sync(ptp_priv->ptp_clock); + if (ptp_priv->ptp_clock) + ptp_cancel_worker_sync(ptp_priv->ptp_clock); return genphy_suspend(phydev); } @@ -4755,10 +4871,11 @@ static struct phy_driver ksphy_driver[] = { /* PHY_BASIC_FEATURES */ .probe = kszphy_probe, .config_init = ksz8061_config_init, + .soft_reset = genphy_soft_reset, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .suspend = kszphy_suspend, - .resume = kszphy_resume, + .resume = ksz8061_resume, }, { .phy_id = PHY_ID_KSZ9021, .phy_id_mask = 0x000ffffe, @@ -4912,7 +5029,7 @@ static struct phy_driver ksphy_driver[] = { .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = ksz9477_resume, .get_features = ksz9477_get_features, } }; diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index ea1073adc5a16..034f5c4d03377 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -107,6 +107,7 @@ struct gpy_priv { u8 fw_major; u8 fw_minor; + u32 wolopts; /* It takes 3 seconds to fully switch out of loopback mode before * it can safely re-enter loopback mode. Record the time when @@ -221,6 +222,15 @@ static int gpy_hwmon_register(struct phy_device *phydev) } #endif +static int gpy_ack_interrupt(struct phy_device *phydev) +{ + int ret; + + /* Clear all pending interrupts */ + ret = phy_read(phydev, PHY_ISTAT); + return ret < 0 ? ret : 0; +} + static int gpy_mbox_read(struct phy_device *phydev, u32 addr) { struct gpy_priv *priv = phydev->priv; @@ -262,16 +272,8 @@ static int gpy_mbox_read(struct phy_device *phydev, u32 addr) static int gpy_config_init(struct phy_device *phydev) { - int ret; - - /* Mask all interrupts */ - ret = phy_write(phydev, PHY_IMASK, 0); - if (ret) - return ret; - - /* Clear all pending interrupts */ - ret = phy_read(phydev, PHY_ISTAT); - return ret < 0 ? ret : 0; + /* Nothing to configure. Configuration Requirement Placeholder */ + return 0; } static int gpy_probe(struct phy_device *phydev) @@ -619,11 +621,23 @@ static int gpy_read_status(struct phy_device *phydev) static int gpy_config_intr(struct phy_device *phydev) { + struct gpy_priv *priv = phydev->priv; u16 mask = 0; + int ret; + + ret = gpy_ack_interrupt(phydev); + if (ret) + return ret; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) mask = PHY_IMASK_MASK; + if (priv->wolopts & WAKE_MAGIC) + mask |= PHY_IMASK_WOL; + + if (priv->wolopts & WAKE_PHY) + mask |= PHY_IMASK_LSTC; + return phy_write(phydev, PHY_IMASK, mask); } @@ -670,6 +684,7 @@ static int gpy_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) { struct net_device *attach_dev = phydev->attached_dev; + struct gpy_priv *priv = phydev->priv; int ret; if (wol->wolopts & WAKE_MAGIC) { @@ -717,6 +732,8 @@ static int gpy_set_wol(struct phy_device *phydev, ret = phy_read(phydev, PHY_ISTAT); if (ret < 0) return ret; + + priv->wolopts |= WAKE_MAGIC; } else { /* Disable magic packet matching */ ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, @@ -724,6 +741,13 @@ static int gpy_set_wol(struct phy_device *phydev, WOL_EN); if (ret < 0) return ret; + + /* Disable the WOL interrupt */ + ret = phy_clear_bits(phydev, PHY_IMASK, PHY_IMASK_WOL); + if (ret < 0) + return ret; + + priv->wolopts &= ~WAKE_MAGIC; } if (wol->wolopts & WAKE_PHY) { @@ -740,9 +764,11 @@ static int gpy_set_wol(struct phy_device *phydev, if (ret & (PHY_IMASK_MASK & ~PHY_IMASK_LSTC)) phy_trigger_machine(phydev); + priv->wolopts |= WAKE_PHY; return 0; } + priv->wolopts &= ~WAKE_PHY; /* Disable the link state change interrupt */ return phy_clear_bits(phydev, PHY_IMASK, PHY_IMASK_LSTC); } @@ -750,18 +776,10 @@ static int gpy_set_wol(struct phy_device *phydev, static void gpy_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) { - int ret; + struct gpy_priv *priv = phydev->priv; wol->supported = WAKE_MAGIC | WAKE_PHY; - wol->wolopts = 0; - - ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, VPSPEC2_WOL_CTL); - if (ret & WOL_EN) - wol->wolopts |= WAKE_MAGIC; - - ret = phy_read(phydev, PHY_IMASK); - if (ret & PHY_IMASK_LSTC) - wol->wolopts |= WAKE_PHY; + wol->wolopts = priv->wolopts; } static int gpy_loopback(struct phy_device *phydev, bool enable) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 3611ea64875ef..8efa2a136faa9 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1413,6 +1413,11 @@ int phy_sfp_probe(struct phy_device *phydev, } EXPORT_SYMBOL(phy_sfp_probe); +static bool phy_drv_supports_irq(struct phy_driver *phydrv) +{ + return phydrv->config_intr && phydrv->handle_interrupt; +} + /** * phy_attach_direct - attach a network device to a given PHY device pointer * @dev: network device to attach @@ -1527,6 +1532,9 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (phydev->dev_flags & PHY_F_NO_IRQ) phydev->irq = PHY_POLL; + if (!phy_drv_supports_irq(phydev->drv) && phy_interrupt_is_valid(phydev)) + phydev->irq = PHY_POLL; + /* Port is set to PORT_TP by default and the actual PHY driver will set * it to different value depending on the PHY configuration. If we have * the generic PHY driver we can't figure it out, thus set the old @@ -2706,8 +2714,8 @@ EXPORT_SYMBOL(genphy_resume); int genphy_loopback(struct phy_device *phydev, bool enable) { if (enable) { - u16 val, ctl = BMCR_LOOPBACK; - int ret; + u16 ctl = BMCR_LOOPBACK; + int ret, val; ctl |= mii_bmcr_encode_fixed(phydev->speed, phydev->duplex); @@ -2959,7 +2967,7 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, if (delay < 0) return delay; - if (delay && size == 0) + if (size == 0) return delay; if (delay < delay_values[0] || delay > delay_values[size - 1]) { @@ -2992,11 +3000,6 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, } EXPORT_SYMBOL(phy_get_internal_delay); -static bool phy_drv_supports_irq(struct phy_driver *phydrv) -{ - return phydrv->config_intr && phydrv->handle_interrupt; -} - static int phy_led_set_brightness(struct led_classdev *led_cdev, enum led_brightness value) { diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index f75c9eb3958ef..e4b759690c441 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -502,6 +502,9 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK_F("Walsun", "HXSX-ATRC-1", sfp_fixup_fs_10gt), SFP_QUIRK_F("Walsun", "HXSX-ATRI-1", sfp_fixup_fs_10gt), + // OEM SFP-GE-T is a 1000Base-T module with broken TX_FAULT indicator + SFP_QUIRK_F("OEM", "SFP-GE-T", sfp_fixup_ignore_tx_fault), + SFP_QUIRK_F("OEM", "SFP-10G-T", sfp_fixup_rollball_cc), SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g), SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc), @@ -2418,8 +2421,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event) /* Handle remove event globally, it resets this state machine */ if (event == SFP_E_REMOVE) { - if (sfp->sm_mod_state > SFP_MOD_PROBE) - sfp_sm_mod_remove(sfp); + sfp_sm_mod_remove(sfp); sfp_sm_mod_next(sfp, SFP_MOD_EMPTY, 0); return; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8f95a562b8d0c..86515f0c2b6c1 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2132,14 +2132,16 @@ static ssize_t tun_put_user(struct tun_struct *tun, tun_is_little_endian(tun), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); - pr_err("unexpected GSO type: " - "0x%x, gso_size %d, hdr_len %d\n", - sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), - tun16_to_cpu(tun, gso.hdr_len)); - print_hex_dump(KERN_ERR, "tun: ", - DUMP_PREFIX_NONE, - 16, 1, skb->head, - min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + + if (net_ratelimit()) { + netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), + tun16_to_cpu(tun, gso.hdr_len)); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + } WARN_ON_ONCE(1); return -EINVAL; } diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index 7b8afa589a53c..284375f662f1e 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -1141,17 +1141,15 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb) continue; } - /* Clone SKB */ - new_skb = skb_clone(skb, GFP_ATOMIC); + new_skb = netdev_alloc_skb_ip_align(dev->net, pkt_len); if (!new_skb) goto err; - new_skb->len = pkt_len; + skb_put(new_skb, pkt_len); + memcpy(new_skb->data, skb->data, pkt_len); skb_pull(new_skb, AQ_RX_HW_PAD); - skb_set_tail_pointer(new_skb, new_skb->len); - new_skb->truesize = SKB_TRUESIZE(new_skb->len); if (aqc111_data->rx_checksum) aqc111_rx_checksum(new_skb, pkt_desc); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index d837c18874161..53f6efc22f5c9 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1273,6 +1273,8 @@ static void ax88179_get_mac_addr(struct usbnet *dev) if (is_valid_ether_addr(mac)) { eth_hw_addr_set(dev->net, mac); + if (!is_local_ether_addr(mac)) + dev->net->addr_assign_type = NET_ADDR_PERM; } else { netdev_info(dev->net, "invalid MAC address, using random\n"); eth_hw_addr_random(dev->net); @@ -1315,6 +1317,8 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) netif_set_tso_max_size(dev->net, 16384); + ax88179_reset(dev); + return 0; } @@ -1452,21 +1456,16 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* Skip IP alignment pseudo header */ skb_pull(skb, 2); - skb->truesize = SKB_TRUESIZE(pkt_len_plus_padd); ax88179_rx_checksum(skb, pkt_hdr); return 1; } - ax_skb = skb_clone(skb, GFP_ATOMIC); + ax_skb = netdev_alloc_skb_ip_align(dev->net, pkt_len); if (!ax_skb) return 0; - skb_trim(ax_skb, pkt_len); + skb_put(ax_skb, pkt_len); + memcpy(ax_skb->data, skb->data + 2, pkt_len); - /* Skip IP alignment pseudo header */ - skb_pull(ax_skb, 2); - - skb->truesize = pkt_len_plus_padd + - SKB_DATA_ALIGN(sizeof(struct sk_buff)); ax88179_rx_checksum(ax_skb, pkt_hdr); usbnet_skb_return(dev, ax_skb); @@ -1674,6 +1673,27 @@ static int ax88179_reset(struct usbnet *dev) return 0; } +static int ax88179_net_reset(struct usbnet *dev) +{ + u16 tmp16; + + ax88179_read_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PHYSR, + 2, &tmp16); + if (tmp16) { + ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, + 2, 2, &tmp16); + if (!(tmp16 & AX_MEDIUM_RECEIVE_EN)) { + tmp16 |= AX_MEDIUM_RECEIVE_EN; + ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, + 2, 2, &tmp16); + } + } else { + ax88179_reset(dev); + } + + return 0; +} + static int ax88179_stop(struct usbnet *dev) { u16 tmp16; @@ -1693,7 +1713,7 @@ static const struct driver_info ax88179_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1706,7 +1726,7 @@ static const struct driver_info ax88178a_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1719,7 +1739,7 @@ static const struct driver_info cypress_GX3_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1732,7 +1752,7 @@ static const struct driver_info dlink_dub1312_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1745,7 +1765,7 @@ static const struct driver_info sitecom_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1758,7 +1778,7 @@ static const struct driver_info samsung_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1771,7 +1791,7 @@ static const struct driver_info lenovo_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1784,7 +1804,7 @@ static const struct driver_info belkin_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1797,7 +1817,7 @@ static const struct driver_info toshiba_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1810,7 +1830,7 @@ static const struct driver_info mct_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1823,7 +1843,7 @@ static const struct driver_info at_umc2000_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1836,7 +1856,7 @@ static const struct driver_info at_umc200_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1849,7 +1869,7 @@ static const struct driver_info at_umc2000sp_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index e2e181378f412..a5469cf5cf670 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1368,6 +1368,9 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a9, 0)}, /* Telit FN920C04 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ @@ -1431,6 +1434,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ {QMI_QUIRK_SET_DTR(0x1546, 0x1312, 4)}, /* u-blox LARA-R6 01B */ {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ + {QMI_QUIRK_SET_DTR(0x33f8, 0x0104, 4)}, /* Rolling RW101 RMNET */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 0d0672d2a6545..51fe00c2b896e 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -10078,7 +10078,7 @@ static int rtl8152_cfgselector_choose_configuration(struct usb_device *udev) * driver supports it. */ if (__rtl_get_hw_ver(udev) == RTL_VER_UNKNOWN) - return 0; + return -ENODEV; /* The vendor mode is not always config #1, so to find it out. */ c = udev->config; diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 97afd7335d868..01a3b2417a540 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -778,7 +778,8 @@ static int rtl8150_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *ecmd) { rtl8150_t *dev = netdev_priv(netdev); - short lpa, bmcr; + short lpa = 0; + short bmcr = 0; u32 supported; supported = (SUPPORTED_10baseT_Half | diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 2fa46baa589e5..8e82184be5e7d 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -879,7 +879,7 @@ static int smsc95xx_start_rx_path(struct usbnet *dev) static int smsc95xx_reset(struct usbnet *dev) { struct smsc95xx_priv *pdata = dev->driver_priv; - u32 read_buf, write_buf, burst_cap; + u32 read_buf, burst_cap; int ret = 0, timeout; netif_dbg(dev, ifup, dev->net, "entering smsc95xx_reset\n"); @@ -1003,10 +1003,13 @@ static int smsc95xx_reset(struct usbnet *dev) return ret; netif_dbg(dev, ifup, dev->net, "ID_REV = 0x%08x\n", read_buf); + ret = smsc95xx_read_reg(dev, LED_GPIO_CFG, &read_buf); + if (ret < 0) + return ret; /* Configure GPIO pins as LED outputs */ - write_buf = LED_GPIO_CFG_SPD_LED | LED_GPIO_CFG_LNK_LED | - LED_GPIO_CFG_FDX_LED; - ret = smsc95xx_write_reg(dev, LED_GPIO_CFG, write_buf); + read_buf |= LED_GPIO_CFG_SPD_LED | LED_GPIO_CFG_LNK_LED | + LED_GPIO_CFG_FDX_LED; + ret = smsc95xx_write_reg(dev, LED_GPIO_CFG, read_buf); if (ret < 0) return ret; @@ -1810,9 +1813,11 @@ static int smsc95xx_reset_resume(struct usb_interface *intf) static void smsc95xx_rx_csum_offload(struct sk_buff *skb) { - skb->csum = *(u16 *)(skb_tail_pointer(skb) - 2); + u16 *csum_ptr = (u16 *)(skb_tail_pointer(skb) - 2); + + skb->csum = (__force __wsum)get_unaligned(csum_ptr); skb->ip_summed = CHECKSUM_COMPLETE; - skb_trim(skb, skb->len - 2); + skb_trim(skb, skb->len - 2); /* remove csum */ } static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) @@ -1870,25 +1875,22 @@ static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (dev->net->features & NETIF_F_RXCSUM) smsc95xx_rx_csum_offload(skb); skb_trim(skb, skb->len - 4); /* remove fcs */ - skb->truesize = size + sizeof(struct sk_buff); return 1; } - ax_skb = skb_clone(skb, GFP_ATOMIC); + ax_skb = netdev_alloc_skb_ip_align(dev->net, size); if (unlikely(!ax_skb)) { netdev_warn(dev->net, "Error allocating skb\n"); return 0; } - ax_skb->len = size; - ax_skb->data = packet; - skb_set_tail_pointer(ax_skb, size); + skb_put(ax_skb, size); + memcpy(ax_skb->data, packet, size); if (dev->net->features & NETIF_F_RXCSUM) smsc95xx_rx_csum_offload(ax_skb); skb_trim(ax_skb, ax_skb->len - 4); /* remove fcs */ - ax_skb->truesize = size + sizeof(struct sk_buff); usbnet_skb_return(dev, ax_skb); } diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 3164451e1010c..0a662e42ed965 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -421,19 +421,15 @@ static int sr9700_rx_fixup(struct usbnet *dev, struct sk_buff *skb) skb_pull(skb, 3); skb->len = len; skb_set_tail_pointer(skb, len); - skb->truesize = len + sizeof(struct sk_buff); return 2; } - /* skb_clone is used for address align */ - sr_skb = skb_clone(skb, GFP_ATOMIC); + sr_skb = netdev_alloc_skb_ip_align(dev->net, len); if (!sr_skb) return 0; - sr_skb->len = len; - sr_skb->data = skb->data + 3; - skb_set_tail_pointer(sr_skb, len); - sr_skb->truesize = len + sizeof(struct sk_buff); + skb_put(sr_skb, len); + memcpy(sr_skb->data, skb->data + 3, len); usbnet_skb_return(dev, sr_skb); skb_pull(skb, len + SR_RX_OVERHEAD); diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 143bd4ab160df..57947a5590cca 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -737,7 +737,9 @@ static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) data->eeprom_len = SR9800_EEPROM_LEN; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + goto out; /* LED Setting Rule : * AABB:CCDD diff --git a/drivers/net/veth.c b/drivers/net/veth.c index cd4a6fe458f95..5146aa6989acc 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1483,6 +1483,7 @@ static void veth_free_queues(struct net_device *dev) static int veth_dev_init(struct net_device *dev) { + netdev_lockdep_set_classes(dev); return veth_alloc_queues(dev); } @@ -1533,8 +1534,6 @@ static netdev_features_t veth_fix_features(struct net_device *dev, if (peer_priv->_xdp_prog) features &= ~NETIF_F_GSO_SOFTWARE; } - if (priv->_xdp_prog) - features |= NETIF_F_GRO; return features; } @@ -1638,14 +1637,6 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, } if (!old_prog) { - if (!veth_gro_requested(dev)) { - /* user-space did not require GRO, but adding - * XDP is supposed to get GRO working - */ - dev->features |= NETIF_F_GRO; - netdev_features_change(dev); - } - peer->hw_features &= ~NETIF_F_GSO_SOFTWARE; peer->max_mtu = max_mtu; } @@ -1661,14 +1652,6 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (dev->flags & IFF_UP) veth_disable_xdp(dev); - /* if user-space did not require GRO, since adding XDP - * enabled it, clear it now - */ - if (!veth_gro_requested(dev)) { - dev->features &= ~NETIF_F_GRO; - netdev_features_change(dev); - } - if (peer) { peer->hw_features |= NETIF_F_GSO_SOFTWARE; peer->max_mtu = ETH_MAX_MTU; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d7ce4a1011ea2..1074dd1e96c8e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1209,6 +1209,10 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, if (unlikely(hdr->hdr.gso_type)) goto err_xdp; + /* Partially checksummed packets must be dropped. */ + if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) + goto err_xdp; + buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -1526,6 +1530,10 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi, if (unlikely(hdr->hdr.gso_type)) return NULL; + /* Partially checksummed packets must be dropped. */ + if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) + return NULL; + /* Now XDP core assumes frag size is PAGE_SIZE, but buffers * with headroom may add hole in truesize, which * make their length exceed PAGE_SIZE. So we disabled the @@ -1792,6 +1800,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, struct net_device *dev = vi->dev; struct sk_buff *skb; struct virtio_net_common_hdr *hdr; + u8 flags; if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); @@ -1800,6 +1809,15 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, return; } + /* 1. Save the flags early, as the XDP program might overwrite them. + * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID + * stay valid after XDP processing. + * 2. XDP doesn't work with partially checksummed packets (refer to + * virtnet_xdp_set()), so packets marked as + * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP processing. + */ + flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; + if (vi->mergeable_rx_bufs) skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); @@ -1815,7 +1833,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report) virtio_skb_set_hash(&hdr->hash_v1_hdr, skb); - if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) + if (flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; if (virtio_net_hdr_to_skb(skb, &hdr->hdr, @@ -3550,10 +3568,10 @@ static void virtnet_rx_dim_work(struct work_struct *work) if (err) pr_debug("%s: Failed to send dim parameters on rxq%d\n", dev->name, qnum); - dim->state = DIM_START_MEASURE; } } + dim->state = DIM_START_MEASURE; rtnl_unlock(); } @@ -3768,6 +3786,7 @@ static int virtnet_set_rxfh(struct net_device *dev, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); + bool update = false; int i; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && @@ -3775,13 +3794,28 @@ static int virtnet_set_rxfh(struct net_device *dev, return -EOPNOTSUPP; if (rxfh->indir) { + if (!vi->has_rss) + return -EOPNOTSUPP; + for (i = 0; i < vi->rss_indir_table_size; ++i) vi->ctrl->rss.indirection_table[i] = rxfh->indir[i]; + update = true; } - if (rxfh->key) + + if (rxfh->key) { + /* If either _F_HASH_REPORT or _F_RSS are negotiated, the + * device provides hash calculation capabilities, that is, + * hash_key is configured. + */ + if (!vi->has_rss && !vi->has_rss_hash_report) + return -EOPNOTSUPP; + memcpy(vi->ctrl->rss.key, rxfh->key, vi->rss_key_size); + update = true; + } - virtnet_commit_rss_command(vi); + if (update) + virtnet_commit_rss_command(vi); return 0; } @@ -4640,8 +4674,16 @@ static int virtnet_probe(struct virtio_device *vdev) dev->features |= dev->hw_features & NETIF_F_ALL_TSO; /* (!csum && gso) case will be fixed by register_netdev() */ } - if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM)) - dev->features |= NETIF_F_RXCSUM; + + /* 1. With VIRTIO_NET_F_GUEST_CSUM negotiation, the driver doesn't + * need to calculate checksums for partially checksummed packets, + * as they're considered valid by the upper layer. + * 2. Without VIRTIO_NET_F_GUEST_CSUM negotiation, the driver only + * receives fully checksummed packets. The device may assist in + * validating these packets' checksums, so the driver won't have to. + */ + dev->features |= NETIF_F_RXCSUM; + if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)) dev->features |= NETIF_F_GRO_HW; @@ -4686,13 +4728,15 @@ static int virtnet_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT)) vi->has_rss_hash_report = true; - if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) + if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) { vi->has_rss = true; - if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_indir_table_size = virtio_cread16(vdev, offsetof(struct virtio_net_config, rss_max_indirection_table_length)); + } + + if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_key_size = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 0578864792b60..beebe09eb88ff 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2034,8 +2034,8 @@ vmxnet3_rq_destroy_all_rxdataring(struct vmxnet3_adapter *adapter) rq->data_ring.base, rq->data_ring.basePA); rq->data_ring.base = NULL; - rq->data_ring.desc_size = 0; } + rq->data_ring.desc_size = 0; } } diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c index 80ddaff759d47..a6c787454a1ae 100644 --- a/drivers/net/vmxnet3/vmxnet3_xdp.c +++ b/drivers/net/vmxnet3/vmxnet3_xdp.c @@ -382,12 +382,12 @@ vmxnet3_process_xdp(struct vmxnet3_adapter *adapter, page = rbi->page; dma_sync_single_for_cpu(&adapter->pdev->dev, page_pool_get_dma_addr(page) + - rq->page_pool->p.offset, rcd->len, + rq->page_pool->p.offset, rbi->len, page_pool_get_dma_dir(rq->page_pool)); - xdp_init_buff(&xdp, rbi->len, &rq->xdp_rxq); + xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq); xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset, - rcd->len, false); + rbi->len, false); xdp_buff_clear_frags_flag(&xdp); xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index bb95ce43cd97d..c3af9ad5e1547 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -653,7 +653,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, skb->dev = dev; rcu_read_lock(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -860,7 +860,7 @@ static int vrf_rt6_create(struct net_device *dev) static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct rtable *rt = (struct rtable *)dst; + struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 16106e088c630..95a924adf1761 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -71,6 +72,167 @@ static inline bool vxlan_collect_metadata(struct vxlan_sock *vs) ip_tunnel_collect_metadata(); } +static struct ip_fan_map *vxlan_fan_find_map(struct vxlan_dev *vxlan, __be32 daddr) +{ + struct ip_fan_map *fan_map; + + rcu_read_lock(); + list_for_each_entry_rcu(fan_map, &vxlan->fan.fan_maps, list) { + if (fan_map->overlay == + (daddr & inet_make_mask(fan_map->overlay_prefix))) { + rcu_read_unlock(); + return fan_map; + } + } + rcu_read_unlock(); + + return NULL; +} + +static void vxlan_fan_flush_map(struct vxlan_dev *vxlan) +{ + struct ip_fan_map *fan_map; + + list_for_each_entry_rcu(fan_map, &vxlan->fan.fan_maps, list) { + list_del_rcu(&fan_map->list); + kfree_rcu(fan_map, rcu); + } +} + +static int vxlan_fan_del_map(struct vxlan_dev *vxlan, __be32 overlay) +{ + struct ip_fan_map *fan_map; + + fan_map = vxlan_fan_find_map(vxlan, overlay); + if (!fan_map) + return -ENOENT; + + list_del_rcu(&fan_map->list); + kfree_rcu(fan_map, rcu); + + return 0; +} + +static int vxlan_fan_add_map(struct vxlan_dev *vxlan, struct ifla_fan_map *map) +{ + __be32 overlay_mask, underlay_mask; + struct ip_fan_map *fan_map; + + overlay_mask = inet_make_mask(map->overlay_prefix); + underlay_mask = inet_make_mask(map->underlay_prefix); + + netdev_dbg(vxlan->dev, "vfam: map: o %x/%d u %x/%d om %x um %x\n", + map->overlay, map->overlay_prefix, + map->underlay, map->underlay_prefix, + overlay_mask, underlay_mask); + + if ((map->overlay & ~overlay_mask) || (map->underlay & ~underlay_mask)) + return -EINVAL; + + if (!(map->overlay & overlay_mask) && (map->underlay & underlay_mask)) + return -EINVAL; + + /* Special case: overlay 0 and underlay 0: flush all mappings */ + if (!map->overlay && !map->underlay) { + vxlan_fan_flush_map(vxlan); + return 0; + } + + /* Special case: overlay set and underlay 0: clear map for overlay */ + if (!map->underlay) + return vxlan_fan_del_map(vxlan, map->overlay); + + if (vxlan_fan_find_map(vxlan, map->overlay)) + return -EEXIST; + + fan_map = kmalloc(sizeof(*fan_map), GFP_KERNEL); + fan_map->underlay = map->underlay; + fan_map->overlay = map->overlay; + fan_map->underlay_prefix = map->underlay_prefix; + fan_map->overlay_mask = ntohl(overlay_mask); + fan_map->overlay_prefix = map->overlay_prefix; + + list_add_tail_rcu(&fan_map->list, &vxlan->fan.fan_maps); + + return 0; +} + +static int vxlan_parse_fan_map(struct nlattr *data[], struct vxlan_dev *vxlan) +{ + struct ifla_fan_map *map; + struct nlattr *attr; + int rem, rv; + + nla_for_each_nested(attr, data[IFLA_IPTUN_FAN_MAP], rem) { + map = nla_data(attr); + rv = vxlan_fan_add_map(vxlan, map); + if (rv) + return rv; + } + + return 0; +} + +static int vxlan_fan_build_rdst(struct vxlan_dev *vxlan, struct sk_buff *skb, + struct vxlan_rdst *fan_rdst) +{ + struct ip_fan_map *f_map; + union vxlan_addr *va; + u32 daddr, underlay; + struct arphdr *arp; + void *arp_ptr; + struct ethhdr *eth; + struct iphdr *iph; + + eth = eth_hdr(skb); + switch (eth->h_proto) { + case htons(ETH_P_IP): + iph = ip_hdr(skb); + if (!iph) + return -EINVAL; + daddr = iph->daddr; + break; + case htons(ETH_P_ARP): + arp = arp_hdr(skb); + if (!arp) + return -EINVAL; + arp_ptr = arp + 1; + netdev_dbg(vxlan->dev, + "vfbr: arp sha %pM sip %pI4 tha %pM tip %pI4\n", + arp_ptr, arp_ptr + skb->dev->addr_len, + arp_ptr + skb->dev->addr_len + 4, + arp_ptr + (skb->dev->addr_len * 2) + 4); + arp_ptr += (skb->dev->addr_len * 2) + 4; + memcpy(&daddr, arp_ptr, 4); + break; + default: + netdev_dbg(vxlan->dev, "vfbr: unknown eth p %x\n", eth->h_proto); + return -EINVAL; + } + + f_map = vxlan_fan_find_map(vxlan, daddr); + if (!f_map) + return -EINVAL; + + daddr = ntohl(daddr); + underlay = ntohl(f_map->underlay); + if (!underlay) + return -EINVAL; + + memset(fan_rdst, 0, sizeof(*fan_rdst)); + va = &fan_rdst->remote_ip; + va->sa.sa_family = AF_INET; + fan_rdst->remote_vni = vxlan->default_dst.remote_vni; + va->sin.sin_addr.s_addr = htonl(underlay | + ((daddr & ~f_map->overlay_mask) >> + (32 - f_map->overlay_prefix - + (32 - f_map->underlay_prefix)))); + netdev_dbg(vxlan->dev, "vfbr: daddr %x ul %x dst %x\n", + daddr, underlay, va->sin.sin_addr.s_addr); + + return 0; +} + /* Find VXLAN socket based on network namespace, address family, UDP port, * enabled unshareable flags and socket device binding (see l3mdev with * non-default VRF). @@ -1446,6 +1608,10 @@ static bool vxlan_snoop(struct net_device *dev, struct vxlan_fdb *f; u32 ifindex = 0; + /* Ignore packets from invalid src-address */ + if (!is_valid_ether_addr(src_mac)) + return true; + #if IS_ENABLED(CONFIG_IPV6) if (src_ip->sa.sa_family == AF_INET6 && (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)) @@ -1670,6 +1836,7 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) bool raw_proto = false; void *oiph; __be32 vni = 0; + int nh; /* Need UDP and VXLAN header to be present */ if (!pskb_may_pull(skb, VXLAN_HLEN)) @@ -1758,12 +1925,28 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_HOST; } - oiph = skb_network_header(skb); + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(vxlan->dev, rx_length_errors); + DEV_STATS_INC(vxlan->dev, rx_errors); + vxlan_vnifilter_count(vxlan, vni, vninode, + VXLAN_VNI_STATS_RX_ERRORS, 0); + goto drop; + } + + /* Get the outer header. */ + oiph = skb->head + nh; + if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { - ++vxlan->dev->stats.rx_frame_errors; - ++vxlan->dev->stats.rx_errors; + DEV_STATS_INC(vxlan->dev, rx_frame_errors); + DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; @@ -1833,7 +2016,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) goto out; if (!pskb_may_pull(skb, arp_hdr_len(dev))) { - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); + vxlan_vnifilter_count(vxlan, vni, NULL, + VXLAN_VNI_STATS_TX_DROPS, 0); goto out; } parp = arp_hdr(skb); @@ -1889,7 +2074,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) reply->pkt_type = PACKET_HOST; if (netif_rx(reply) == NET_RX_DROP) { - dev->stats.rx_dropped++; + dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2048,7 +2233,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) goto out; if (netif_rx(reply) == NET_RX_DROP) { - dev->stats.rx_dropped++; + dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2259,7 +2444,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, len); } else { drop: - dev->stats.rx_dropped++; + dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } @@ -2291,7 +2476,7 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, addr_family, dst_port, vxlan->cfg.flags); if (!dst_vxlan) { - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb(skb); @@ -2433,6 +2618,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; } + if (fan_has_map(&vxlan->fan) && rt->rt_flags & RTCF_LOCAL) { + netdev_dbg(dev, "discard fan to localhost %pI4\n", + &rdst->remote_ip.sin.sin_addr.s_addr); + ip_rt_put(rt); + goto tx_free; + } + if (!info) { /* Bypass encapsulation if the destination is local */ err = encap_bypass_if_local(skb, dev, vxlan, AF_INET, @@ -2505,7 +2697,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } if (!info) { - u32 rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags; + u32 rt6i_flags = dst_rt6_info(ndst)->rt6i_flags; err = encap_bypass_if_local(skb, dev, vxlan, AF_INET6, dst_port, ifindex, vni, @@ -2555,7 +2747,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; drop: - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); return; @@ -2563,12 +2755,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, tx_error: rcu_read_unlock(); if (err == -ELOOP) - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_release(ndst); - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); +tx_free: kfree_skb(skb); } @@ -2600,7 +2793,7 @@ static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, return; drop: - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); @@ -2638,7 +2831,7 @@ static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, return NETDEV_TX_OK; drop: - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); @@ -2716,6 +2909,20 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_unlock(); } + if (fan_has_map(&vxlan->fan)) { + struct vxlan_rdst fan_rdst; + + netdev_dbg(vxlan->dev, "vxlan_xmit p %x d %pM\n", + eth->h_proto, eth->h_dest); + if (vxlan_fan_build_rdst(vxlan, skb, &fan_rdst)) { + dev->stats.tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; + } + vxlan_xmit_one(skb, dev, vni, &fan_rdst, 0); + return NETDEV_TX_OK; + } + eth = eth_hdr(skb); f = vxlan_find_mac(vxlan, eth->h_dest, vni); did_rsc = false; @@ -2735,7 +2942,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); - dev->stats.tx_dropped++; + dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb(skb); @@ -2855,6 +3062,7 @@ static int vxlan_init(struct net_device *dev) if (err) goto err_gro_cells_destroy; + netdev_lockdep_set_classes(dev); return 0; err_gro_cells_destroy: @@ -3325,6 +3533,8 @@ static void vxlan_setup(struct net_device *dev) spin_lock_init(&vxlan->hash_lock[h]); INIT_HLIST_HEAD(&vxlan->fdb_head[h]); } + + INIT_LIST_HEAD(&vxlan->fan.fan_maps); } static void vxlan_ether_setup(struct net_device *dev) @@ -3344,6 +3554,22 @@ static void vxlan_raw_setup(struct net_device *dev) dev->netdev_ops = &vxlan_netdev_raw_ops; } +/* Validate Ubuntu FAN payload. + * + * This is required to bypass the strict length validation enforced for the + * attribute types >= IFLA_VXLAN_LOCALBYPASS in vxlan_policy. + * + * In this way we can continue to use the same allocated ID for + * IFLA_VXLAN_FAN_MAP, without breaking the existing user-space and also + * future kernel ABIs that may add new attribute types to vxlan_policy. + */ +static int fan_map_validate_entry(const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + /* Accept any payload for Ubuntu FAN */ + return 0; +} + static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_UNSPEC] = { .strict_start_type = IFLA_VXLAN_LOCALBYPASS }, [IFLA_VXLAN_ID] = { .type = NLA_U32 }, @@ -3378,6 +3604,9 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), + [IFLA_VXLAN_FAN_MAP] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + fan_map_validate_entry, + sizeof(struct ifla_fan_map) * 256), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], @@ -4055,6 +4284,12 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], conf->remote_ip.sa.sa_family = AF_INET6; } + if (data[IFLA_VXLAN_FAN_MAP]) { + err = vxlan_parse_fan_map(data, vxlan); + if (err) + return err; + } + if (data[IFLA_VXLAN_LOCAL]) { if (changelink && (conf->saddr.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL], "New local address family does not match old"); @@ -4440,6 +4675,7 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(0) + /* IFLA_VXLAN_GPE */ nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ + nla_total_size(sizeof(struct ip_fan_map) * 256) + 0; } @@ -4486,6 +4722,26 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) } } + if (fan_has_map(&vxlan->fan)) { + struct nlattr *fan_nest; + struct ip_fan_map *fan_map; + + fan_nest = nla_nest_start(skb, IFLA_VXLAN_FAN_MAP); + if (!fan_nest) + goto nla_put_failure; + list_for_each_entry_rcu(fan_map, &vxlan->fan.fan_maps, list) { + struct ifla_fan_map map; + + map.underlay = fan_map->underlay; + map.underlay_prefix = fan_map->underlay_prefix; + map.overlay = fan_map->overlay; + map.overlay_prefix = fan_map->overlay_prefix; + if (nla_put(skb, IFLA_FAN_MAPPING, sizeof(map), &map)) + goto nla_put_failure; + } + nla_nest_end(skb, fan_nest); + } + if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT, !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) || @@ -4826,6 +5082,22 @@ static __net_init int vxlan_init_net(struct net *net) NULL); } +#ifdef CONFIG_SYSCTL +static struct ctl_table_header *vxlan_fan_header; +static unsigned int vxlan_fan_version = 4; + +static struct ctl_table vxlan_fan_sysctls[] = { + { + .procname = "vxlan", + .data = &vxlan_fan_version, + .maxlen = sizeof(vxlan_fan_version), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + {}, +}; +#endif /* CONFIG_SYSCTL */ + static void vxlan_destroy_tunnels(struct net *net, struct list_head *head) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); @@ -4903,7 +5175,20 @@ static int __init vxlan_init_module(void) vxlan_vnifilter_init(); +#ifdef CONFIG_SYSCTL + vxlan_fan_header = register_net_sysctl(&init_net, "net/fan", + vxlan_fan_sysctls); + if (!vxlan_fan_header) { + rc = -ENOMEM; + goto sysctl_failed; + } +#endif /* CONFIG_SYSCTL */ + return 0; +#ifdef CONFIG_SYSCTL +sysctl_failed: + rtnl_link_unregister(&vxlan_link_ops); +#endif /* CONFIG_SYSCTL */ out4: unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); out3: @@ -4917,6 +5202,9 @@ late_initcall(vxlan_init_module); static void __exit vxlan_cleanup_module(void) { +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(vxlan_fan_header); +#endif /* CONFIG_SYSCTL */ vxlan_vnifilter_uninit(); rtnl_link_unregister(&vxlan_link_ops); unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index e220d761b1f27..f7055180ba4aa 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -164,8 +164,8 @@ get_peer(struct wg_peer *peer, struct sk_buff *skb, struct dump_ctx *ctx) if (!allowedips_node) goto no_allowedips; if (!ctx->allowedips_seq) - ctx->allowedips_seq = peer->device->peer_allowedips.seq; - else if (ctx->allowedips_seq != peer->device->peer_allowedips.seq) + ctx->allowedips_seq = ctx->wg->peer_allowedips.seq; + else if (ctx->allowedips_seq != ctx->wg->peer_allowedips.seq) goto no_allowedips; allowedips_nest = nla_nest_start(skb, WGPEER_A_ALLOWEDIPS); @@ -255,17 +255,17 @@ static int wg_get_device_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!peers_nest) goto out; ret = 0; - /* If the last cursor was removed via list_del_init in peer_remove, then + lockdep_assert_held(&wg->device_update_lock); + /* If the last cursor was removed in peer_remove or peer_remove_all, then * we just treat this the same as there being no more peers left. The * reason is that seq_nr should indicate to userspace that this isn't a * coherent dump anyway, so they'll try again. */ if (list_empty(&wg->peer_list) || - (ctx->next_peer && list_empty(&ctx->next_peer->peer_list))) { + (ctx->next_peer && ctx->next_peer->is_dead)) { nla_nest_cancel(skb, peers_nest); goto out; } - lockdep_assert_held(&wg->device_update_lock); peer = list_prepare_entry(ctx->next_peer, &wg->peer_list, peer_list); list_for_each_entry_continue(peer, &wg->peer_list, peer_list) { if (get_peer(peer, skb, ctx)) { diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index a176653c88616..db01ec03bda00 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -251,7 +251,7 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) if (unlikely(!READ_ONCE(keypair->receiving.is_valid) || wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) || - keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) { + READ_ONCE(keypair->receiving_counter.counter) >= REJECT_AFTER_MESSAGES)) { WRITE_ONCE(keypair->receiving.is_valid, false); return false; } @@ -318,7 +318,7 @@ static bool counter_validate(struct noise_replay_counter *counter, u64 their_cou for (i = 1; i <= top; ++i) counter->backtrack[(i + index_current) & ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0; - counter->counter = their_counter; + WRITE_ONCE(counter->counter, their_counter); } index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1; @@ -463,7 +463,7 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget) net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n", peer->device->dev->name, PACKET_CB(skb)->nonce, - keypair->receiving_counter.counter); + READ_ONCE(keypair->receiving_counter.counter)); goto next; } diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c index a742cec44e3db..91ddbe6136e00 100644 --- a/drivers/net/wireless/ath/ar5523/ar5523.c +++ b/drivers/net/wireless/ath/ar5523/ar5523.c @@ -1590,6 +1590,20 @@ static int ar5523_probe(struct usb_interface *intf, struct ar5523 *ar; int error = -ENOMEM; + static const u8 bulk_ep_addr[] = { + AR5523_CMD_TX_PIPE | USB_DIR_OUT, + AR5523_DATA_TX_PIPE | USB_DIR_OUT, + AR5523_CMD_RX_PIPE | USB_DIR_IN, + AR5523_DATA_RX_PIPE | USB_DIR_IN, + 0}; + + if (!usb_check_bulk_endpoints(intf, bulk_ep_addr)) { + dev_err(&dev->dev, + "Could not find all expected endpoints\n"); + error = -ENODEV; + goto out; + } + /* * Load firmware if the device requires it. This will return * -ENXIO on success and we'll get called back afer the usb diff --git a/drivers/net/wireless/ath/ath.h b/drivers/net/wireless/ath/ath.h index f02a308a9ffc5..34654f710d8a1 100644 --- a/drivers/net/wireless/ath/ath.h +++ b/drivers/net/wireless/ath/ath.h @@ -171,8 +171,10 @@ struct ath_common { unsigned int clockrate; spinlock_t cc_lock; - struct ath_cycle_counters cc_ani; - struct ath_cycle_counters cc_survey; + struct_group(cc, + struct ath_cycle_counters cc_ani; + struct ath_cycle_counters cc_survey; + ); struct ath_regulatory regulatory; struct ath_regulatory reg_world_copy; diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig index e6ea884cafc19..4f385f4a8cef2 100644 --- a/drivers/net/wireless/ath/ath10k/Kconfig +++ b/drivers/net/wireless/ath/ath10k/Kconfig @@ -45,6 +45,7 @@ config ATH10K_SNOC depends on ATH10K depends on ARCH_QCOM || COMPILE_TEST depends on QCOM_SMEM + depends on QCOM_RPROC_COMMON || QCOM_RPROC_COMMON=n select QCOM_SCM select QCOM_QMI_HELPERS help diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 0032f8aa892ff..4e3736d7aff77 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -720,6 +720,9 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .max_spatial_stream = 4, .fw = { .dir = WCN3990_HW_1_0_FW_DIR, + .board = WCN3990_HW_1_0_BOARD_DATA_FILE, + .board_size = WCN3990_BOARD_DATA_SZ, + .board_ext_size = WCN3990_BOARD_EXT_DATA_SZ, }, .sw_decrypt_mcast_mgmt = true, .rx_desc_ops = &wcn3990_rx_desc_ops, diff --git a/drivers/net/wireless/ath/ath10k/debugfs_sta.c b/drivers/net/wireless/ath/ath10k/debugfs_sta.c index 394bf3c32abff..0f6de862c3a9b 100644 --- a/drivers/net/wireless/ath/ath10k/debugfs_sta.c +++ b/drivers/net/wireless/ath/ath10k/debugfs_sta.c @@ -439,7 +439,7 @@ ath10k_dbg_sta_write_peer_debug_trigger(struct file *file, } out: mutex_unlock(&ar->conf_mutex); - return count; + return ret ?: count; } static const struct file_operations fops_peer_debug_trigger = { diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h index 93c0730919966..9aa2d821b5078 100644 --- a/drivers/net/wireless/ath/ath10k/hw.h +++ b/drivers/net/wireless/ath/ath10k/hw.h @@ -133,6 +133,7 @@ enum qca9377_chip_id_rev { /* WCN3990 1.0 definitions */ #define WCN3990_HW_1_0_DEV_VERSION ATH10K_HW_WCN3990 #define WCN3990_HW_1_0_FW_DIR ATH10K_FW_DIR "/WCN3990/hw1.0" +#define WCN3990_HW_1_0_BOARD_DATA_FILE "board.bin" #define ATH10K_FW_FILE_BASE "firmware" #define ATH10K_FW_API_MAX 6 diff --git a/drivers/net/wireless/ath/ath10k/targaddrs.h b/drivers/net/wireless/ath/ath10k/targaddrs.h index ec556bb88d658..ba37e6c7ced08 100644 --- a/drivers/net/wireless/ath/ath10k/targaddrs.h +++ b/drivers/net/wireless/ath/ath10k/targaddrs.h @@ -491,4 +491,7 @@ struct host_interest { #define QCA4019_BOARD_DATA_SZ 12064 #define QCA4019_BOARD_EXT_DATA_SZ 0 +#define WCN3990_BOARD_DATA_SZ 26328 +#define WCN3990_BOARD_EXT_DATA_SZ 0 + #endif /* __TARGADDRS_H__ */ diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c index 6b6aa3c367448..0ce08e9a0a3d2 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c @@ -851,6 +851,10 @@ ath10k_wmi_tlv_op_pull_mgmt_tx_compl_ev(struct ath10k *ar, struct sk_buff *skb, } ev = tb[WMI_TLV_TAG_STRUCT_MGMT_TX_COMPL_EVENT]; + if (!ev) { + kfree(tb); + return -EPROTO; + } arg->desc_id = ev->desc_id; arg->status = ev->status; diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 88befe92f95dc..24f1ab2785214 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -1763,12 +1763,32 @@ void ath10k_wmi_put_wmi_channel(struct ath10k *ar, struct wmi_channel *ch, int ath10k_wmi_wait_for_service_ready(struct ath10k *ar) { - unsigned long time_left; + unsigned long time_left, i; time_left = wait_for_completion_timeout(&ar->wmi.service_ready, WMI_SERVICE_READY_TIMEOUT_HZ); - if (!time_left) - return -ETIMEDOUT; + if (!time_left) { + /* Sometimes the PCI HIF doesn't receive interrupt + * for the service ready message even if the buffer + * was completed. PCIe sniffer shows that it's + * because the corresponding CE ring doesn't fires + * it. Workaround here by polling CE rings once. + */ + ath10k_warn(ar, "failed to receive service ready completion, polling..\n"); + + for (i = 0; i < CE_COUNT; i++) + ath10k_hif_send_complete_check(ar, i, 1); + + time_left = wait_for_completion_timeout(&ar->wmi.service_ready, + WMI_SERVICE_READY_TIMEOUT_HZ); + if (!time_left) { + ath10k_warn(ar, "polling timed out\n"); + return -ETIMEDOUT; + } + + ath10k_warn(ar, "service ready completion received, continuing normally\n"); + } + return 0; } diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index 0c6ecbb9a0661..65c866e432fad 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -589,7 +589,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .coldboot_cal_ftm = true, .cbcal_restart_fw = false, .fw_mem_mode = 0, - .num_vdevs = 16 + 1, + .num_vdevs = 3, .num_peers = 512, .supports_suspend = false, .hal_desc_sz = sizeof(struct hal_rx_desc_qcn9074), diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index 02e160d831bed..cd829ec70d76b 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -918,6 +918,7 @@ struct ath11k_base { * This may or may not be used during the runtime */ struct ieee80211_regdomain *new_regd[MAX_RADIOS]; + struct cur_regulatory_info *reg_info_store; /* Current DFS Regulatory */ enum ath11k_dfs_region dfs_region; diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index b13525bbbb808..a46b8e677cd1f 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -1234,14 +1234,7 @@ static int ath11k_mac_vif_setup_ps(struct ath11k_vif *arvif) enable_ps = arvif->ps; - if (!arvif->is_started) { - /* mac80211 can update vif powersave state while disconnected. - * Firmware doesn't behave nicely and consumes more power than - * necessary if PS is disabled on a non-started vdev. Hence - * force-enable PS for non-running vdevs. - */ - psmode = WMI_STA_PS_MODE_ENABLED; - } else if (enable_ps) { + if (enable_ps) { psmode = WMI_STA_PS_MODE_ENABLED; param = WMI_STA_PS_PARAM_INACTIVITY_TIME; @@ -2297,6 +2290,8 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, mcs_160_map = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); mcs_80_map = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); + /* Initialize rx_mcs_160 to 9 which is an invalid value */ + rx_mcs_160 = 9; if (support_160) { for (i = 7; i >= 0; i--) { u8 mcs_160 = (mcs_160_map >> (2 * i)) & 3; @@ -2308,6 +2303,8 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, } } + /* Initialize rx_mcs_80 to 9 which is an invalid value */ + rx_mcs_80 = 9; for (i = 7; i >= 0; i--) { u8 mcs_80 = (mcs_80_map >> (2 * i)) & 3; @@ -3026,7 +3023,14 @@ static void ath11k_bss_assoc(struct ieee80211_hw *hw, rcu_read_unlock(); + if (!ath11k_mac_vif_recalc_sta_he_txbf(ar, vif, &he_cap)) { + ath11k_warn(ar->ab, "failed to recalc he txbf for vdev %i on bss %pM\n", + arvif->vdev_id, bss_conf->bssid); + return; + } + peer_arg.is_assoc = true; + ret = ath11k_wmi_send_peer_assoc_cmd(ar, &peer_arg); if (ret) { ath11k_warn(ar->ab, "failed to run peer assoc for %pM vdev %i: %d\n", @@ -3049,12 +3053,6 @@ static void ath11k_bss_assoc(struct ieee80211_hw *hw, return; } - if (!ath11k_mac_vif_recalc_sta_he_txbf(ar, vif, &he_cap)) { - ath11k_warn(ar->ab, "failed to recalc he txbf for vdev %i on bss %pM\n", - arvif->vdev_id, bss_conf->bssid); - return; - } - WARN_ON(arvif->is_up); arvif->aid = vif->cfg.aid; diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index 6835c14b82cc9..337590236485f 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -106,7 +106,7 @@ static struct mhi_controller_config ath11k_mhi_config_qca6390 = { .max_channels = 128, .timeout_ms = 2000, .use_bounce_buf = false, - .buf_len = 0, + .buf_len = 8192, .num_channels = ARRAY_SIZE(ath11k_mhi_channels_qca6390), .ch_cfg = ath11k_mhi_channels_qca6390, .num_events = ARRAY_SIZE(ath11k_mhi_events_qca6390), diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c index b4fd4d2107c71..d4fd3509e608c 100644 --- a/drivers/net/wireless/ath/ath11k/reg.c +++ b/drivers/net/wireless/ath/ath11k/reg.c @@ -618,25 +618,68 @@ ath11k_reg_update_weather_radar_band(struct ath11k_base *ab, *rule_idx = i; } +enum wmi_reg_6ghz_ap_type +ath11k_reg_ap_pwr_convert(enum ieee80211_ap_reg_power power_type) +{ + switch (power_type) { + case IEEE80211_REG_LPI_AP: + return WMI_REG_INDOOR_AP; + case IEEE80211_REG_SP_AP: + return WMI_REG_STANDARD_POWER_AP; + case IEEE80211_REG_VLP_AP: + return WMI_REG_VERY_LOW_POWER_AP; + default: + return WMI_REG_MAX_AP_TYPE; + } +} + struct ieee80211_regdomain * ath11k_reg_build_regd(struct ath11k_base *ab, - struct cur_regulatory_info *reg_info, bool intersect) + struct cur_regulatory_info *reg_info, bool intersect, + enum wmi_vdev_type vdev_type, + enum ieee80211_ap_reg_power power_type) { struct ieee80211_regdomain *tmp_regd, *default_regd, *new_regd = NULL; - struct cur_reg_rule *reg_rule; + struct cur_reg_rule *reg_rule, *reg_rule_6ghz; u8 i = 0, j = 0, k = 0; u8 num_rules; u16 max_bw; - u32 flags; + u32 flags, reg_6ghz_number, max_bw_6ghz; char alpha2[3]; num_rules = reg_info->num_5ghz_reg_rules + reg_info->num_2ghz_reg_rules; - /* FIXME: Currently taking reg rules for 6 GHz only from Indoor AP mode list. - * This can be updated after complete 6 GHz regulatory support is added. - */ - if (reg_info->is_ext_reg_event) - num_rules += reg_info->num_6ghz_rules_ap[WMI_REG_INDOOR_AP]; + if (reg_info->is_ext_reg_event) { + if (vdev_type == WMI_VDEV_TYPE_STA) { + enum wmi_reg_6ghz_ap_type ap_type; + + ap_type = ath11k_reg_ap_pwr_convert(power_type); + + if (ap_type == WMI_REG_MAX_AP_TYPE) + ap_type = WMI_REG_INDOOR_AP; + + reg_6ghz_number = reg_info->num_6ghz_rules_client + [ap_type][WMI_REG_DEFAULT_CLIENT]; + + if (reg_6ghz_number == 0) { + ap_type = WMI_REG_INDOOR_AP; + reg_6ghz_number = reg_info->num_6ghz_rules_client + [ap_type][WMI_REG_DEFAULT_CLIENT]; + } + + reg_rule_6ghz = reg_info->reg_rules_6ghz_client_ptr + [ap_type][WMI_REG_DEFAULT_CLIENT]; + max_bw_6ghz = reg_info->max_bw_6ghz_client + [ap_type][WMI_REG_DEFAULT_CLIENT]; + } else { + reg_6ghz_number = reg_info->num_6ghz_rules_ap[WMI_REG_INDOOR_AP]; + reg_rule_6ghz = + reg_info->reg_rules_6ghz_ap_ptr[WMI_REG_INDOOR_AP]; + max_bw_6ghz = reg_info->max_bw_6ghz_ap[WMI_REG_INDOOR_AP]; + } + + num_rules += reg_6ghz_number; + } if (!num_rules) goto ret; @@ -683,13 +726,10 @@ ath11k_reg_build_regd(struct ath11k_base *ab, * per other BW rule flags we pass from here */ flags = NL80211_RRF_AUTO_BW; - } else if (reg_info->is_ext_reg_event && - reg_info->num_6ghz_rules_ap[WMI_REG_INDOOR_AP] && - (k < reg_info->num_6ghz_rules_ap[WMI_REG_INDOOR_AP])) { - reg_rule = reg_info->reg_rules_6ghz_ap_ptr[WMI_REG_INDOOR_AP] + - k++; - max_bw = min_t(u16, reg_rule->max_bw, - reg_info->max_bw_6ghz_ap[WMI_REG_INDOOR_AP]); + } else if (reg_info->is_ext_reg_event && reg_6ghz_number && + k < reg_6ghz_number) { + reg_rule = reg_rule_6ghz + k++; + max_bw = min_t(u16, reg_rule->max_bw, max_bw_6ghz); flags = NL80211_RRF_AUTO_BW; } else { break; @@ -758,6 +798,159 @@ ath11k_reg_build_regd(struct ath11k_base *ab, return new_regd; } +static bool ath11k_reg_is_world_alpha(char *alpha) +{ + if (alpha[0] == '0' && alpha[1] == '0') + return true; + + if (alpha[0] == 'n' && alpha[1] == 'a') + return true; + + return false; +} + +static enum wmi_vdev_type ath11k_reg_get_ar_vdev_type(struct ath11k *ar) +{ + struct ath11k_vif *arvif; + + /* Currently each struct ath11k maps to one struct ieee80211_hw/wiphy + * and one struct ieee80211_regdomain, so it could only store one group + * reg rules. It means multi-interface concurrency in the same ath11k is + * not support for the regdomain. So get the vdev type of the first entry + * now. After concurrency support for the regdomain, this should change. + */ + arvif = list_first_entry_or_null(&ar->arvifs, struct ath11k_vif, list); + if (arvif) + return arvif->vdev_type; + + return WMI_VDEV_TYPE_UNSPEC; +} + +int ath11k_reg_handle_chan_list(struct ath11k_base *ab, + struct cur_regulatory_info *reg_info, + enum ieee80211_ap_reg_power power_type) +{ + struct ieee80211_regdomain *regd; + bool intersect = false; + int pdev_idx; + struct ath11k *ar; + enum wmi_vdev_type vdev_type; + + ath11k_dbg(ab, ATH11K_DBG_WMI, "event reg handle chan list"); + + if (reg_info->status_code != REG_SET_CC_STATUS_PASS) { + /* In case of failure to set the requested ctry, + * fw retains the current regd. We print a failure info + * and return from here. + */ + ath11k_warn(ab, "Failed to set the requested Country regulatory setting\n"); + return -EINVAL; + } + + pdev_idx = reg_info->phy_id; + + /* Avoid default reg rule updates sent during FW recovery if + * it is already available + */ + spin_lock_bh(&ab->base_lock); + if (test_bit(ATH11K_FLAG_RECOVERY, &ab->dev_flags) && + ab->default_regd[pdev_idx]) { + spin_unlock_bh(&ab->base_lock); + goto retfail; + } + spin_unlock_bh(&ab->base_lock); + + if (pdev_idx >= ab->num_radios) { + /* Process the event for phy0 only if single_pdev_only + * is true. If pdev_idx is valid but not 0, discard the + * event. Otherwise, it goes to fallback. In either case + * ath11k_reg_reset_info() needs to be called to avoid + * memory leak issue. + */ + ath11k_reg_reset_info(reg_info); + + if (ab->hw_params.single_pdev_only && + pdev_idx < ab->hw_params.num_rxmda_per_pdev) + return 0; + goto fallback; + } + + /* Avoid multiple overwrites to default regd, during core + * stop-start after mac registration. + */ + if (ab->default_regd[pdev_idx] && !ab->new_regd[pdev_idx] && + !memcmp((char *)ab->default_regd[pdev_idx]->alpha2, + (char *)reg_info->alpha2, 2)) + goto retfail; + + /* Intersect new rules with default regd if a new country setting was + * requested, i.e a default regd was already set during initialization + * and the regd coming from this event has a valid country info. + */ + if (ab->default_regd[pdev_idx] && + !ath11k_reg_is_world_alpha((char *) + ab->default_regd[pdev_idx]->alpha2) && + !ath11k_reg_is_world_alpha((char *)reg_info->alpha2)) + intersect = true; + + ar = ab->pdevs[pdev_idx].ar; + vdev_type = ath11k_reg_get_ar_vdev_type(ar); + + ath11k_dbg(ab, ATH11K_DBG_WMI, + "wmi handle chan list power type %d vdev type %d intersect %d\n", + power_type, vdev_type, intersect); + + regd = ath11k_reg_build_regd(ab, reg_info, intersect, vdev_type, power_type); + if (!regd) { + ath11k_warn(ab, "failed to build regd from reg_info\n"); + goto fallback; + } + + if (power_type == IEEE80211_REG_UNSET_AP) { + ath11k_reg_reset_info(&ab->reg_info_store[pdev_idx]); + ab->reg_info_store[pdev_idx] = *reg_info; + } + + spin_lock_bh(&ab->base_lock); + if (ab->default_regd[pdev_idx]) { + /* The initial rules from FW after WMI Init is to build + * the default regd. From then on, any rules updated for + * the pdev could be due to user reg changes. + * Free previously built regd before assigning the newly + * generated regd to ar. NULL pointer handling will be + * taken care by kfree itself. + */ + ar = ab->pdevs[pdev_idx].ar; + kfree(ab->new_regd[pdev_idx]); + ab->new_regd[pdev_idx] = regd; + queue_work(ab->workqueue, &ar->regd_update_work); + } else { + /* This regd would be applied during mac registration and is + * held constant throughout for regd intersection purpose + */ + ab->default_regd[pdev_idx] = regd; + } + ab->dfs_region = reg_info->dfs_region; + spin_unlock_bh(&ab->base_lock); + + return 0; + +fallback: + /* Fallback to older reg (by sending previous country setting + * again if fw has succeeded and we failed to process here. + * The Regdomain should be uniform across driver and fw. Since the + * FW has processed the command and sent a success status, we expect + * this function to succeed as well. If it doesn't, CTRY needs to be + * reverted at the fw and the old SCAN_CHAN_LIST cmd needs to be sent. + */ + /* TODO: This is rare, but still should also be handled */ + WARN_ON(1); + +retfail: + + return -EINVAL; +} + void ath11k_regd_update_work(struct work_struct *work) { struct ath11k *ar = container_of(work, struct ath11k, @@ -781,10 +974,36 @@ void ath11k_reg_init(struct ath11k *ar) ar->hw->wiphy->reg_notifier = ath11k_reg_notifier; } +void ath11k_reg_reset_info(struct cur_regulatory_info *reg_info) +{ + int i, j; + + if (!reg_info) + return; + + kfree(reg_info->reg_rules_2ghz_ptr); + kfree(reg_info->reg_rules_5ghz_ptr); + + for (i = 0; i < WMI_REG_CURRENT_MAX_AP_TYPE; i++) { + kfree(reg_info->reg_rules_6ghz_ap_ptr[i]); + + for (j = 0; j < WMI_REG_MAX_CLIENT_TYPE; j++) + kfree(reg_info->reg_rules_6ghz_client_ptr[i][j]); + } + + memset(reg_info, 0, sizeof(*reg_info)); +} + void ath11k_reg_free(struct ath11k_base *ab) { int i; + for (i = 0; i < ab->num_radios; i++) + ath11k_reg_reset_info(&ab->reg_info_store[i]); + + kfree(ab->reg_info_store); + ab->reg_info_store = NULL; + for (i = 0; i < ab->hw_params.max_radios; i++) { kfree(ab->default_regd[i]); kfree(ab->new_regd[i]); diff --git a/drivers/net/wireless/ath/ath11k/reg.h b/drivers/net/wireless/ath/ath11k/reg.h index f28902f85e419..64edb794260ab 100644 --- a/drivers/net/wireless/ath/ath11k/reg.h +++ b/drivers/net/wireless/ath/ath11k/reg.h @@ -30,11 +30,20 @@ enum ath11k_dfs_region { /* ATH11K Regulatory API's */ void ath11k_reg_init(struct ath11k *ar); +void ath11k_reg_reset_info(struct cur_regulatory_info *reg_info); void ath11k_reg_free(struct ath11k_base *ab); void ath11k_regd_update_work(struct work_struct *work); struct ieee80211_regdomain * ath11k_reg_build_regd(struct ath11k_base *ab, - struct cur_regulatory_info *reg_info, bool intersect); + struct cur_regulatory_info *reg_info, bool intersect, + enum wmi_vdev_type vdev_type, + enum ieee80211_ap_reg_power power_type); int ath11k_regd_update(struct ath11k *ar); int ath11k_reg_update_chan_list(struct ath11k *ar, bool wait); +enum wmi_reg_6ghz_ap_type +ath11k_reg_ap_pwr_convert(enum ieee80211_ap_reg_power power_type); +int ath11k_reg_handle_chan_list(struct ath11k_base *ab, + struct cur_regulatory_info *reg_info, + enum ieee80211_ap_reg_power power_type); + #endif diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 8a65fa04b48d9..442afda7ec885 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -4749,6 +4749,14 @@ static int ath11k_wmi_tlv_ext_soc_hal_reg_caps_parse(struct ath11k_base *soc, soc->pdevs[0].pdev_id = 0; } + if (!soc->reg_info_store) { + soc->reg_info_store = kcalloc(soc->num_radios, + sizeof(*soc->reg_info_store), + GFP_ATOMIC); + if (!soc->reg_info_store) + return -ENOMEM; + } + return 0; } @@ -7060,32 +7068,15 @@ static void ath11k_wmi_htc_tx_complete(struct ath11k_base *ab, wake_up(&wmi->tx_ce_desc_wq); } -static bool ath11k_reg_is_world_alpha(char *alpha) -{ - if (alpha[0] == '0' && alpha[1] == '0') - return true; - - if (alpha[0] == 'n' && alpha[1] == 'a') - return true; - - return false; -} - -static int ath11k_reg_chan_list_event(struct ath11k_base *ab, - struct sk_buff *skb, +static int ath11k_reg_chan_list_event(struct ath11k_base *ab, struct sk_buff *skb, enum wmi_reg_chan_list_cmd_type id) { - struct cur_regulatory_info *reg_info = NULL; - struct ieee80211_regdomain *regd = NULL; - bool intersect = false; - int ret = 0, pdev_idx, i, j; - struct ath11k *ar; + struct cur_regulatory_info *reg_info; + int ret; reg_info = kzalloc(sizeof(*reg_info), GFP_ATOMIC); - if (!reg_info) { - ret = -ENOMEM; - goto fallback; - } + if (!reg_info) + return -ENOMEM; if (id == WMI_REG_CHAN_LIST_CC_ID) ret = ath11k_pull_reg_chan_list_update_ev(ab, skb, reg_info); @@ -7093,118 +7084,22 @@ static int ath11k_reg_chan_list_event(struct ath11k_base *ab, ret = ath11k_pull_reg_chan_list_ext_update_ev(ab, skb, reg_info); if (ret) { - ath11k_warn(ab, "failed to extract regulatory info from received event\n"); - goto fallback; - } - - ath11k_dbg(ab, ATH11K_DBG_WMI, "event reg chan list id %d", id); - - if (reg_info->status_code != REG_SET_CC_STATUS_PASS) { - /* In case of failure to set the requested ctry, - * fw retains the current regd. We print a failure info - * and return from here. - */ - ath11k_warn(ab, "Failed to set the requested Country regulatory setting\n"); - goto mem_free; - } - - pdev_idx = reg_info->phy_id; - - /* Avoid default reg rule updates sent during FW recovery if - * it is already available - */ - spin_lock(&ab->base_lock); - if (test_bit(ATH11K_FLAG_RECOVERY, &ab->dev_flags) && - ab->default_regd[pdev_idx]) { - spin_unlock(&ab->base_lock); + ath11k_warn(ab, "failed to extract regulatory info\n"); goto mem_free; } - spin_unlock(&ab->base_lock); - if (pdev_idx >= ab->num_radios) { - /* Process the event for phy0 only if single_pdev_only - * is true. If pdev_idx is valid but not 0, discard the - * event. Otherwise, it goes to fallback. - */ - if (ab->hw_params.single_pdev_only && - pdev_idx < ab->hw_params.num_rxmda_per_pdev) - goto mem_free; - else - goto fallback; - } - - /* Avoid multiple overwrites to default regd, during core - * stop-start after mac registration. - */ - if (ab->default_regd[pdev_idx] && !ab->new_regd[pdev_idx] && - !memcmp((char *)ab->default_regd[pdev_idx]->alpha2, - (char *)reg_info->alpha2, 2)) + ret = ath11k_reg_handle_chan_list(ab, reg_info, IEEE80211_REG_UNSET_AP); + if (ret) { + ath11k_warn(ab, "failed to process regulatory info %d\n", ret); goto mem_free; - - /* Intersect new rules with default regd if a new country setting was - * requested, i.e a default regd was already set during initialization - * and the regd coming from this event has a valid country info. - */ - if (ab->default_regd[pdev_idx] && - !ath11k_reg_is_world_alpha((char *) - ab->default_regd[pdev_idx]->alpha2) && - !ath11k_reg_is_world_alpha((char *)reg_info->alpha2)) - intersect = true; - - regd = ath11k_reg_build_regd(ab, reg_info, intersect); - if (!regd) { - ath11k_warn(ab, "failed to build regd from reg_info\n"); - goto fallback; - } - - spin_lock(&ab->base_lock); - if (ab->default_regd[pdev_idx]) { - /* The initial rules from FW after WMI Init is to build - * the default regd. From then on, any rules updated for - * the pdev could be due to user reg changes. - * Free previously built regd before assigning the newly - * generated regd to ar. NULL pointer handling will be - * taken care by kfree itself. - */ - ar = ab->pdevs[pdev_idx].ar; - kfree(ab->new_regd[pdev_idx]); - ab->new_regd[pdev_idx] = regd; - queue_work(ab->workqueue, &ar->regd_update_work); - } else { - /* This regd would be applied during mac registration and is - * held constant throughout for regd intersection purpose - */ - ab->default_regd[pdev_idx] = regd; } - ab->dfs_region = reg_info->dfs_region; - spin_unlock(&ab->base_lock); - goto mem_free; + kfree(reg_info); + return 0; -fallback: - /* Fallback to older reg (by sending previous country setting - * again if fw has succeeded and we failed to process here. - * The Regdomain should be uniform across driver and fw. Since the - * FW has processed the command and sent a success status, we expect - * this function to succeed as well. If it doesn't, CTRY needs to be - * reverted at the fw and the old SCAN_CHAN_LIST cmd needs to be sent. - */ - /* TODO: This is rare, but still should also be handled */ - WARN_ON(1); mem_free: - if (reg_info) { - kfree(reg_info->reg_rules_2ghz_ptr); - kfree(reg_info->reg_rules_5ghz_ptr); - if (reg_info->is_ext_reg_event) { - for (i = 0; i < WMI_REG_CURRENT_MAX_AP_TYPE; i++) - kfree(reg_info->reg_rules_6ghz_ap_ptr[i]); - - for (j = 0; j < WMI_REG_CURRENT_MAX_AP_TYPE; j++) - for (i = 0; i < WMI_REG_MAX_CLIENT_TYPE; i++) - kfree(reg_info->reg_rules_6ghz_client_ptr[j][i]); - } - kfree(reg_info); - } + ath11k_reg_reset_info(reg_info); + kfree(reg_info); return ret; } diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h index ff0a9a92beeb0..cd2098d78e861 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.h +++ b/drivers/net/wireless/ath/ath11k/wmi.h @@ -4951,6 +4951,7 @@ struct ath11k_targ_cap { }; enum wmi_vdev_type { + WMI_VDEV_TYPE_UNSPEC = 0, WMI_VDEV_TYPE_AP = 1, WMI_VDEV_TYPE_STA = 2, WMI_VDEV_TYPE_IBSS = 3, diff --git a/drivers/net/wireless/ath/ath12k/Makefile b/drivers/net/wireless/ath/ath12k/Makefile index 62c52e733b5e5..0d723e85cf6b9 100644 --- a/drivers/net/wireless/ath/ath12k/Makefile +++ b/drivers/net/wireless/ath/ath12k/Makefile @@ -19,7 +19,8 @@ ath12k-y += core.o \ hw.o \ mhi.o \ pci.o \ - dp_mon.o + dp_mon.o \ + fw.o ath12k-$(CONFIG_ATH12K_TRACING) += trace.o diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c index 6c01b282fcd33..95012477e88f9 100644 --- a/drivers/net/wireless/ath/ath12k/core.c +++ b/drivers/net/wireless/ath/ath12k/core.c @@ -14,6 +14,7 @@ #include "dp_rx.h" #include "debug.h" #include "hif.h" +#include "fw.h" unsigned int ath12k_debug_mask; module_param_named(debug_mask, ath12k_debug_mask, uint, 0644); @@ -114,11 +115,26 @@ static int ath12k_core_create_board_name(struct ath12k_base *ab, char *name, scnprintf(variant, sizeof(variant), ",variant=%s", ab->qmi.target.bdf_ext); - scnprintf(name, name_len, - "bus=%s,qmi-chip-id=%d,qmi-board-id=%d%s", - ath12k_bus_str(ab->hif.bus), - ab->qmi.target.chip_id, - ab->qmi.target.board_id, variant); + switch (ab->id.bdf_search) { + case ATH12K_BDF_SEARCH_BUS_AND_BOARD: + scnprintf(name, name_len, + "bus=%s,vendor=%04x,device=%04x,subsystem-vendor=%04x,subsystem-device=%04x,qmi-chip-id=%d,qmi-board-id=%d%s", + ath12k_bus_str(ab->hif.bus), + ab->id.vendor, ab->id.device, + ab->id.subsystem_vendor, + ab->id.subsystem_device, + ab->qmi.target.chip_id, + ab->qmi.target.board_id, + variant); + break; + default: + scnprintf(name, name_len, + "bus=%s,qmi-chip-id=%d,qmi-board-id=%d%s", + ath12k_bus_str(ab->hif.bus), + ab->qmi.target.chip_id, + ab->qmi.target.board_id, variant); + break; + } ath12k_dbg(ab, ATH12K_DBG_BOOT, "boot using board name '%s'\n", name); @@ -356,7 +372,7 @@ int ath12k_core_fetch_board_data_api_1(struct ath12k_base *ab, return 0; } -#define BOARD_NAME_SIZE 100 +#define BOARD_NAME_SIZE 200 int ath12k_core_fetch_bdf(struct ath12k_base *ab, struct ath12k_board_data *bd) { char boardname[BOARD_NAME_SIZE]; @@ -963,7 +979,6 @@ static void ath12k_core_reset(struct work_struct *work) ATH12K_RECOVER_START_TIMEOUT_HZ); ath12k_hif_power_down(ab); - ath12k_qmi_free_resource(ab); ath12k_hif_power_up(ab); ath12k_dbg(ab, ATH12K_DBG_BOOT, "reset started\n"); @@ -979,6 +994,8 @@ int ath12k_core_pre_init(struct ath12k_base *ab) return ret; } + ath12k_fw_map(ab); + return 0; } @@ -1007,6 +1024,7 @@ void ath12k_core_deinit(struct ath12k_base *ab) ath12k_hif_power_down(ab); ath12k_mac_destroy(ab); ath12k_core_soc_destroy(ab); + ath12k_fw_unmap(ab); } void ath12k_core_free(struct ath12k_base *ab) diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h index 8458dc292821a..30b30240f5ba9 100644 --- a/drivers/net/wireless/ath/ath12k/core.h +++ b/drivers/net/wireless/ath/ath12k/core.h @@ -13,6 +13,7 @@ #include #include #include +#include #include "qmi.h" #include "htc.h" #include "wmi.h" @@ -24,6 +25,7 @@ #include "hal_rx.h" #include "reg.h" #include "dbring.h" +#include "fw.h" #define SM(_v, _f) (((_v) << _f##_LSB) & _f##_MASK) @@ -55,6 +57,11 @@ #define ATH12K_RECONFIGURE_TIMEOUT_HZ (10 * HZ) #define ATH12K_RECOVER_START_TIMEOUT_HZ (20 * HZ) +enum ath12k_bdf_search { + ATH12K_BDF_SEARCH_DEFAULT, + ATH12K_BDF_SEARCH_BUS_AND_BOARD, +}; + enum wme_ac { WME_AC_BE, WME_AC_BK, @@ -420,7 +427,7 @@ struct ath12k_sta { }; #define ATH12K_MIN_5G_FREQ 4150 -#define ATH12K_MIN_6G_FREQ 5945 +#define ATH12K_MIN_6G_FREQ 5925 #define ATH12K_MAX_6G_FREQ 7115 #define ATH12K_NUM_CHANS 100 #define ATH12K_MAX_5G_CHAN 173 @@ -793,6 +800,26 @@ struct ath12k_base { /* true means radio is on */ bool rfkill_radio_on; + struct { + enum ath12k_bdf_search bdf_search; + u32 vendor; + u32 device; + u32 subsystem_vendor; + u32 subsystem_device; + } id; + + struct { + u32 api_version; + + const struct firmware *fw; + const u8 *amss_data; + size_t amss_len; + const u8 *m3_data; + size_t m3_len; + + DECLARE_BITMAP(fw_features, ATH12K_FW_FEATURE_COUNT); + } fw; + /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; diff --git a/drivers/net/wireless/ath/ath12k/fw.c b/drivers/net/wireless/ath/ath12k/fw.c new file mode 100644 index 0000000000000..fbcf40c97792c --- /dev/null +++ b/drivers/net/wireless/ath/ath12k/fw.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: BSD-3-Clause-Clear +/* + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include "core.h" + +#include "debug.h" + +static int ath12k_fw_request_firmware_api_n(struct ath12k_base *ab, + const char *name) +{ + size_t magic_len, len, ie_len; + int ie_id, i, index, bit, ret; + struct ath12k_fw_ie *hdr; + const u8 *data; + __le32 *timestamp; + + ab->fw.fw = ath12k_core_firmware_request(ab, name); + if (IS_ERR(ab->fw.fw)) { + ret = PTR_ERR(ab->fw.fw); + ath12k_dbg(ab, ATH12K_DBG_BOOT, "failed to load %s: %d\n", name, ret); + ab->fw.fw = NULL; + return ret; + } + + data = ab->fw.fw->data; + len = ab->fw.fw->size; + + /* magic also includes the null byte, check that as well */ + magic_len = strlen(ATH12K_FIRMWARE_MAGIC) + 1; + + if (len < magic_len) { + ath12k_err(ab, "firmware image too small to contain magic: %zu\n", + len); + ret = -EINVAL; + goto err; + } + + if (memcmp(data, ATH12K_FIRMWARE_MAGIC, magic_len) != 0) { + ath12k_err(ab, "Invalid firmware magic\n"); + ret = -EINVAL; + goto err; + } + + /* jump over the padding */ + magic_len = ALIGN(magic_len, 4); + + /* make sure there's space for padding */ + if (magic_len > len) { + ath12k_err(ab, "No space for padding after magic\n"); + ret = -EINVAL; + goto err; + } + + len -= magic_len; + data += magic_len; + + /* loop elements */ + while (len > sizeof(struct ath12k_fw_ie)) { + hdr = (struct ath12k_fw_ie *)data; + + ie_id = le32_to_cpu(hdr->id); + ie_len = le32_to_cpu(hdr->len); + + len -= sizeof(*hdr); + data += sizeof(*hdr); + + if (len < ie_len) { + ath12k_err(ab, "Invalid length for FW IE %d (%zu < %zu)\n", + ie_id, len, ie_len); + ret = -EINVAL; + goto err; + } + + switch (ie_id) { + case ATH12K_FW_IE_TIMESTAMP: + if (ie_len != sizeof(u32)) + break; + + timestamp = (__le32 *)data; + + ath12k_dbg(ab, ATH12K_DBG_BOOT, "found fw timestamp %d\n", + le32_to_cpup(timestamp)); + break; + case ATH12K_FW_IE_FEATURES: + ath12k_dbg(ab, ATH12K_DBG_BOOT, + "found firmware features ie (%zd B)\n", + ie_len); + + for (i = 0; i < ATH12K_FW_FEATURE_COUNT; i++) { + index = i / 8; + bit = i % 8; + + if (index == ie_len) + break; + + if (data[index] & (1 << bit)) + __set_bit(i, ab->fw.fw_features); + } + + ath12k_dbg_dump(ab, ATH12K_DBG_BOOT, "features", "", + ab->fw.fw_features, + sizeof(ab->fw.fw_features)); + break; + case ATH12K_FW_IE_AMSS_IMAGE: + ath12k_dbg(ab, ATH12K_DBG_BOOT, + "found fw image ie (%zd B)\n", + ie_len); + + ab->fw.amss_data = data; + ab->fw.amss_len = ie_len; + break; + case ATH12K_FW_IE_M3_IMAGE: + ath12k_dbg(ab, ATH12K_DBG_BOOT, + "found m3 image ie (%zd B)\n", + ie_len); + + ab->fw.m3_data = data; + ab->fw.m3_len = ie_len; + break; + default: + ath12k_warn(ab, "Unknown FW IE: %u\n", ie_id); + break; + } + + /* jump over the padding */ + ie_len = ALIGN(ie_len, 4); + + /* make sure there's space for padding */ + if (ie_len > len) + break; + + len -= ie_len; + data += ie_len; + } + + return 0; + +err: + release_firmware(ab->fw.fw); + ab->fw.fw = NULL; + return ret; +} + +void ath12k_fw_map(struct ath12k_base *ab) +{ + int ret; + + ret = ath12k_fw_request_firmware_api_n(ab, ATH12K_FW_API2_FILE); + if (ret == 0) + ab->fw.api_version = 2; + else + ab->fw.api_version = 1; + + ath12k_dbg(ab, ATH12K_DBG_BOOT, "using fw api %d\n", + ab->fw.api_version); +} + +void ath12k_fw_unmap(struct ath12k_base *ab) +{ + release_firmware(ab->fw.fw); + memset(&ab->fw, 0, sizeof(ab->fw)); +} diff --git a/drivers/net/wireless/ath/ath12k/fw.h b/drivers/net/wireless/ath/ath12k/fw.h new file mode 100644 index 0000000000000..d91d95fc57405 --- /dev/null +++ b/drivers/net/wireless/ath/ath12k/fw.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: BSD-3-Clause-Clear */ +/* + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef ATH12K_FW_H +#define ATH12K_FW_H + +#define ATH12K_FW_API2_FILE "firmware-2.bin" +#define ATH12K_FIRMWARE_MAGIC "QCOM-ATH12K-FW" + +enum ath12k_fw_ie_type { + ATH12K_FW_IE_TIMESTAMP = 0, + ATH12K_FW_IE_FEATURES = 1, + ATH12K_FW_IE_AMSS_IMAGE = 2, + ATH12K_FW_IE_M3_IMAGE = 3, +}; + +enum ath12k_fw_features { + /* keep last */ + ATH12K_FW_FEATURE_COUNT, +}; + +void ath12k_fw_map(struct ath12k_base *ab); +void ath12k_fw_unmap(struct ath12k_base *ab); + +#endif /* ATH12K_FW_H */ diff --git a/drivers/net/wireless/ath/ath12k/hal.c b/drivers/net/wireless/ath/ath12k/hal.c index a489369d80687..1bdab8604db94 100644 --- a/drivers/net/wireless/ath/ath12k/hal.c +++ b/drivers/net/wireless/ath/ath12k/hal.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include #include "hal_tx.h" @@ -449,8 +449,8 @@ static u8 *ath12k_hw_qcn9274_rx_desc_mpdu_start_addr2(struct hal_rx_desc *desc) static bool ath12k_hw_qcn9274_rx_desc_is_da_mcbc(struct hal_rx_desc *desc) { - return __le16_to_cpu(desc->u.qcn9274.msdu_end.info5) & - RX_MSDU_END_INFO5_DA_IS_MCBC; + return __le32_to_cpu(desc->u.qcn9274.mpdu_start.info6) & + RX_MPDU_START_INFO6_MCAST_BCAST; } static void ath12k_hw_qcn9274_rx_desc_get_dot11_hdr(struct hal_rx_desc *desc, diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index 88cec54c6c2e6..d67ee0312c1d9 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -5269,7 +5269,7 @@ ath12k_mac_get_vdev_stats_id(struct ath12k_vif *arvif) do { if (ab->free_vdev_stats_id_map & (1LL << vdev_stats_id)) { vdev_stats_id++; - if (vdev_stats_id <= ATH12K_INVAL_VDEV_STATS_ID) { + if (vdev_stats_id >= ATH12K_MAX_VDEV_STATS_ID) { vdev_stats_id = ATH12K_INVAL_VDEV_STATS_ID; break; } @@ -5911,14 +5911,24 @@ ath12k_mac_check_down_grade_phy_mode(struct ath12k *ar, enum nl80211_band band, enum nl80211_iftype type) { - struct ieee80211_sta_eht_cap *eht_cap; + struct ieee80211_sta_eht_cap *eht_cap = NULL; enum wmi_phy_mode down_mode; + int n = ar->mac.sbands[band].n_iftype_data; + int i; + struct ieee80211_sband_iftype_data *data; if (mode < MODE_11BE_EHT20) return mode; - eht_cap = &ar->mac.iftype[band][type].eht_cap; - if (eht_cap->has_eht) + data = ar->mac.iftype[band]; + for (i = 0; i < n; i++) { + if (data[i].types_mask & BIT(type)) { + eht_cap = &data[i].eht_cap; + break; + } + } + + if (eht_cap && eht_cap->has_eht) return mode; switch (mode) { @@ -7198,7 +7208,7 @@ static int ath12k_mac_setup_channels_rates(struct ath12k *ar, } if (supported_bands & WMI_HOST_WLAN_5G_CAP) { - if (reg_cap->high_5ghz_chan >= ATH12K_MAX_6G_FREQ) { + if (reg_cap->high_5ghz_chan >= ATH12K_MIN_6G_FREQ) { channels = kmemdup(ath12k_6ghz_channels, sizeof(ath12k_6ghz_channels), GFP_KERNEL); if (!channels) { diff --git a/drivers/net/wireless/ath/ath12k/mhi.c b/drivers/net/wireless/ath/ath12k/mhi.c index d5441ddb374b0..b7b31978a434d 100644 --- a/drivers/net/wireless/ath/ath12k/mhi.c +++ b/drivers/net/wireless/ath/ath12k/mhi.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2020-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include #include +#include #include "core.h" #include "debug.h" @@ -364,17 +365,24 @@ int ath12k_mhi_register(struct ath12k_pci *ab_pci) if (!mhi_ctrl) return -ENOMEM; - ath12k_core_create_firmware_path(ab, ATH12K_AMSS_FILE, - ab_pci->amss_path, - sizeof(ab_pci->amss_path)); - ab_pci->mhi_ctrl = mhi_ctrl; mhi_ctrl->cntrl_dev = ab->dev; - mhi_ctrl->fw_image = ab_pci->amss_path; mhi_ctrl->regs = ab->mem; mhi_ctrl->reg_len = ab->mem_len; mhi_ctrl->rddm_size = ab->hw_params->rddm_size; + if (ab->fw.amss_data && ab->fw.amss_len > 0) { + /* use MHI firmware file from firmware-N.bin */ + mhi_ctrl->fw_data = ab->fw.amss_data; + mhi_ctrl->fw_sz = ab->fw.amss_len; + } else { + /* use the old separate mhi.bin MHI firmware file */ + ath12k_core_create_firmware_path(ab, ATH12K_AMSS_FILE, + ab_pci->amss_path, + sizeof(ab_pci->amss_path)); + mhi_ctrl->fw_image = ab_pci->amss_path; + } + ret = ath12k_mhi_get_msi(ab_pci); if (ret) { ath12k_err(ab, "failed to get msi for mhi\n"); diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c index f0d2e2d8719c0..76438b3afd55b 100644 --- a/drivers/net/wireless/ath/ath12k/pci.c +++ b/drivers/net/wireless/ath/ath12k/pci.c @@ -1310,6 +1310,15 @@ static int ath12k_pci_probe(struct pci_dev *pdev, goto err_free_core; } + ath12k_dbg(ab, ATH12K_DBG_BOOT, "pci probe %04x:%04x %04x:%04x\n", + pdev->vendor, pdev->device, + pdev->subsystem_vendor, pdev->subsystem_device); + + ab->id.vendor = pdev->vendor; + ab->id.device = pdev->device; + ab->id.subsystem_vendor = pdev->subsystem_vendor; + ab->id.subsystem_device = pdev->subsystem_device; + switch (pci_dev->device) { case QCN9274_DEVICE_ID: ab_pci->msi_config = &ath12k_msi_config[0]; @@ -1333,6 +1342,7 @@ static int ath12k_pci_probe(struct pci_dev *pdev, } break; case WCN7850_DEVICE_ID: + ab->id.bdf_search = ATH12K_BDF_SEARCH_BUS_AND_BOARD; ab_pci->msi_config = &ath12k_msi_config[0]; ab->static_window_map = false; ab_pci->pci_ops = &ath12k_pci_ops_wcn7850; diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c index 77a132f6bbd1b..03984be0d7a1c 100644 --- a/drivers/net/wireless/ath/ath12k/qmi.c +++ b/drivers/net/wireless/ath/ath12k/qmi.c @@ -2149,8 +2149,9 @@ static void ath12k_qmi_free_target_mem_chunk(struct ath12k_base *ab) for (i = 0; i < ab->qmi.mem_seg_count; i++) { if (!ab->qmi.target_mem[i].v.addr) continue; + dma_free_coherent(ab->dev, - ab->qmi.target_mem[i].size, + ab->qmi.target_mem[i].prev_size, ab->qmi.target_mem[i].v.addr, ab->qmi.target_mem[i].paddr); ab->qmi.target_mem[i].v.addr = NULL; @@ -2176,6 +2177,20 @@ static int ath12k_qmi_alloc_target_mem_chunk(struct ath12k_base *ab) case M3_DUMP_REGION_TYPE: case PAGEABLE_MEM_REGION_TYPE: case CALDB_MEM_REGION_TYPE: + /* Firmware reloads in recovery/resume. + * In such cases, no need to allocate memory for FW again. + */ + if (chunk->v.addr) { + if (chunk->prev_type == chunk->type && + chunk->prev_size == chunk->size) + goto this_chunk_done; + + /* cannot reuse the existing chunk */ + dma_free_coherent(ab->dev, chunk->prev_size, + chunk->v.addr, chunk->paddr); + chunk->v.addr = NULL; + } + chunk->v.addr = dma_alloc_coherent(ab->dev, chunk->size, &chunk->paddr, @@ -2194,6 +2209,10 @@ static int ath12k_qmi_alloc_target_mem_chunk(struct ath12k_base *ab) chunk->type, chunk->size); return -ENOMEM; } + + chunk->prev_type = chunk->type; + chunk->prev_size = chunk->size; +this_chunk_done: break; default: ath12k_warn(ab, "memory type %u not supported\n", @@ -2494,53 +2513,78 @@ static int ath12k_qmi_load_bdf_qmi(struct ath12k_base *ab, return ret; } +static void ath12k_qmi_m3_free(struct ath12k_base *ab) +{ + struct m3_mem_region *m3_mem = &ab->qmi.m3_mem; + + if (!m3_mem->vaddr) + return; + + dma_free_coherent(ab->dev, m3_mem->size, + m3_mem->vaddr, m3_mem->paddr); + m3_mem->vaddr = NULL; + m3_mem->size = 0; +} + static int ath12k_qmi_m3_load(struct ath12k_base *ab) { struct m3_mem_region *m3_mem = &ab->qmi.m3_mem; - const struct firmware *fw; + const struct firmware *fw = NULL; + const void *m3_data; char path[100]; + size_t m3_len; int ret; - if (m3_mem->vaddr || m3_mem->size) - return 0; + if (ab->fw.m3_data && ab->fw.m3_len > 0) { + /* firmware-N.bin had a m3 firmware file so use that */ + m3_data = ab->fw.m3_data; + m3_len = ab->fw.m3_len; + } else { + /* No m3 file in firmware-N.bin so try to request old + * separate m3.bin. + */ + fw = ath12k_core_firmware_request(ab, ATH12K_M3_FILE); + if (IS_ERR(fw)) { + ret = PTR_ERR(fw); + ath12k_core_create_firmware_path(ab, ATH12K_M3_FILE, + path, sizeof(path)); + ath12k_err(ab, "failed to load %s: %d\n", path, ret); + return ret; + } - fw = ath12k_core_firmware_request(ab, ATH12K_M3_FILE); - if (IS_ERR(fw)) { - ret = PTR_ERR(fw); - ath12k_core_create_firmware_path(ab, ATH12K_M3_FILE, - path, sizeof(path)); - ath12k_err(ab, "failed to load %s: %d\n", path, ret); - return ret; + m3_data = fw->data; + m3_len = fw->size; + } + + /* In recovery/resume cases, M3 buffer is not freed, try to reuse that */ + if (m3_mem->vaddr) { + if (m3_mem->size >= m3_len) + goto skip_m3_alloc; + + /* Old buffer is too small, free and reallocate */ + ath12k_qmi_m3_free(ab); } m3_mem->vaddr = dma_alloc_coherent(ab->dev, - fw->size, &m3_mem->paddr, + m3_len, &m3_mem->paddr, GFP_KERNEL); if (!m3_mem->vaddr) { ath12k_err(ab, "failed to allocate memory for M3 with size %zu\n", fw->size); - release_firmware(fw); - return -ENOMEM; + ret = -ENOMEM; + goto out; } - memcpy(m3_mem->vaddr, fw->data, fw->size); - m3_mem->size = fw->size; - release_firmware(fw); +skip_m3_alloc: + memcpy(m3_mem->vaddr, m3_data, m3_len); + m3_mem->size = m3_len; - return 0; -} - -static void ath12k_qmi_m3_free(struct ath12k_base *ab) -{ - struct m3_mem_region *m3_mem = &ab->qmi.m3_mem; + ret = 0; - if (!m3_mem->vaddr) - return; +out: + release_firmware(fw); - dma_free_coherent(ab->dev, m3_mem->size, - m3_mem->vaddr, m3_mem->paddr); - m3_mem->vaddr = NULL; - m3_mem->size = 0; + return ret; } static int ath12k_qmi_wlanfw_m3_info_send(struct ath12k_base *ab) @@ -2941,6 +2985,9 @@ static const struct qmi_msg_handler ath12k_qmi_msg_handlers[] = { .decoded_size = sizeof(struct qmi_wlanfw_fw_ready_ind_msg_v01), .fn = ath12k_qmi_msg_fw_ready_cb, }, + + /* end of list */ + {}, }; static int ath12k_qmi_ops_new_server(struct qmi_handle *qmi_hdl, diff --git a/drivers/net/wireless/ath/ath12k/qmi.h b/drivers/net/wireless/ath/ath12k/qmi.h index e25bbaa125e83..641b43a9bc019 100644 --- a/drivers/net/wireless/ath/ath12k/qmi.h +++ b/drivers/net/wireless/ath/ath12k/qmi.h @@ -97,6 +97,8 @@ struct ath12k_qmi_event_msg { struct target_mem_chunk { u32 size; u32 type; + u32 prev_size; + u32 prev_type; dma_addr_t paddr; union { void __iomem *ioaddr; diff --git a/drivers/net/wireless/ath/ath12k/reg.c b/drivers/net/wireless/ath/ath12k/reg.c index f924bc13ccff5..29542c46b0941 100644 --- a/drivers/net/wireless/ath/ath12k/reg.c +++ b/drivers/net/wireless/ath/ath12k/reg.c @@ -103,7 +103,7 @@ int ath12k_reg_update_chan_list(struct ath12k *ar) bands = hw->wiphy->bands; for (band = 0; band < NUM_NL80211_BANDS; band++) { - if (!bands[band]) + if (!(ar->mac.sbands[band].channels && bands[band])) continue; for (i = 0; i < bands[band]->n_channels; i++) { @@ -129,7 +129,7 @@ int ath12k_reg_update_chan_list(struct ath12k *ar) ch = arg->channel; for (band = 0; band < NUM_NL80211_BANDS; band++) { - if (!bands[band]) + if (!(ar->mac.sbands[band].channels && bands[band])) continue; for (i = 0; i < bands[band]->n_channels; i++) { diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 11cc3005c0f98..035d8f247e23e 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -1836,7 +1836,7 @@ static void ath12k_wmi_copy_peer_flags(struct wmi_peer_assoc_complete_cmd *cmd, if (arg->bw_160) cmd->peer_flags |= cpu_to_le32(WMI_PEER_160MHZ); if (arg->bw_320) - cmd->peer_flags |= cpu_to_le32(WMI_PEER_EXT_320MHZ); + cmd->peer_flags_ext |= cpu_to_le32(WMI_PEER_EXT_320MHZ); /* Typically if STBC is enabled for VHT it should be enabled * for HT as well diff --git a/drivers/net/wireless/ath/ath9k/antenna.c b/drivers/net/wireless/ath/ath9k/antenna.c index 988222cea9dfe..acc84e6711b0e 100644 --- a/drivers/net/wireless/ath/ath9k/antenna.c +++ b/drivers/net/wireless/ath/ath9k/antenna.c @@ -643,7 +643,7 @@ static void ath_ant_try_scan(struct ath_ant_comb *antcomb, conf->main_lna_conf = ATH_ANT_DIV_COMB_LNA1; conf->alt_lna_conf = ATH_ANT_DIV_COMB_LNA1_PLUS_LNA2; } else if (antcomb->rssi_sub > - antcomb->rssi_lna1) { + antcomb->rssi_lna2) { /* set to A-B */ conf->main_lna_conf = ATH_ANT_DIV_COMB_LNA1; conf->alt_lna_conf = ATH_ANT_DIV_COMB_LNA1_MINUS_LNA2; diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 237f4ec2cffd7..6c33e898b3000 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -306,7 +306,6 @@ struct ath9k_htc_tx { DECLARE_BITMAP(tx_slot, MAX_TX_BUF_NUM); struct timer_list cleanup_timer; spinlock_t tx_lock; - bool initialized; }; struct ath9k_htc_tx_ctl { @@ -515,6 +514,7 @@ struct ath9k_htc_priv { unsigned long ps_usecount; bool ps_enabled; bool ps_idle; + bool initialized; #ifdef CONFIG_MAC80211_LEDS enum led_brightness brightness; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 0aa5bdeb44a1b..3633f9eb2c559 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -966,6 +966,10 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev, htc_handle->drv_priv = priv; + /* Allow ath9k_wmi_event_tasklet() to operate. */ + smp_wmb(); + priv->initialized = true; + return 0; err_init: diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c index efcaeccb055aa..ce9c04e418b8d 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c @@ -815,10 +815,6 @@ int ath9k_tx_init(struct ath9k_htc_priv *priv) skb_queue_head_init(&priv->tx.data_vo_queue); skb_queue_head_init(&priv->tx.tx_failed); - /* Allow ath9k_wmi_event_tasklet(WMI_TXSTATUS_EVENTID) to operate. */ - smp_wmb(); - priv->tx.initialized = true; - return 0; } diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index c48ff0ffbfefb..3e697521ca135 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -135,8 +135,7 @@ void ath9k_ps_wakeup(struct ath_softc *sc) if (power_mode != ATH9K_PM_AWAKE) { spin_lock(&common->cc_lock); ath_hw_cycle_counters_update(common); - memset(&common->cc_survey, 0, sizeof(common->cc_survey)); - memset(&common->cc_ani, 0, sizeof(common->cc_ani)); + memset(&common->cc, 0, sizeof(common->cc)); spin_unlock(&common->cc_lock); } diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c index 1476b42b52a91..805ad31edba2b 100644 --- a/drivers/net/wireless/ath/ath9k/wmi.c +++ b/drivers/net/wireless/ath/ath9k/wmi.c @@ -155,6 +155,12 @@ void ath9k_wmi_event_tasklet(struct tasklet_struct *t) } spin_unlock_irqrestore(&wmi->wmi_lock, flags); + /* Check if ath9k_htc_probe_device() completed. */ + if (!data_race(priv->initialized)) { + kfree_skb(skb); + continue; + } + hdr = (struct wmi_cmd_hdr *) skb->data; cmd_id = be16_to_cpu(hdr->command_id); wmi_event = skb_pull(skb, sizeof(struct wmi_cmd_hdr)); @@ -169,10 +175,6 @@ void ath9k_wmi_event_tasklet(struct tasklet_struct *t) &wmi->drv_priv->fatal_work); break; case WMI_TXSTATUS_EVENTID: - /* Check if ath9k_tx_init() completed. */ - if (!data_race(priv->tx.initialized)) - break; - spin_lock_bh(&priv->tx.tx_lock); if (priv->tx.flags & ATH9K_HTC_OP_TX_DRAIN) { spin_unlock_bh(&priv->tx.tx_lock); diff --git a/drivers/net/wireless/ath/carl9170/tx.c b/drivers/net/wireless/ath/carl9170/tx.c index 6bb9aa2bfe654..88ef6e023f826 100644 --- a/drivers/net/wireless/ath/carl9170/tx.c +++ b/drivers/net/wireless/ath/carl9170/tx.c @@ -280,7 +280,8 @@ static void carl9170_tx_release(struct kref *ref) * carl9170_tx_fill_rateinfo() has filled the rate information * before we get to this point. */ - memset_after(&txinfo->status, 0, rates); + memset(&txinfo->pad, 0, sizeof(txinfo->pad)); + memset(&txinfo->rate_driver_data, 0, sizeof(txinfo->rate_driver_data)); if (atomic_read(&ar->tx_total_queued)) ar->tx_schedule = true; diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c index c4edf83559410..a3e03580cd9ff 100644 --- a/drivers/net/wireless/ath/carl9170/usb.c +++ b/drivers/net/wireless/ath/carl9170/usb.c @@ -1069,6 +1069,38 @@ static int carl9170_usb_probe(struct usb_interface *intf, ar->usb_ep_cmd_is_bulk = true; } + /* Verify that all expected endpoints are present */ + if (ar->usb_ep_cmd_is_bulk) { + u8 bulk_ep_addr[] = { + AR9170_USB_EP_RX | USB_DIR_IN, + AR9170_USB_EP_TX | USB_DIR_OUT, + AR9170_USB_EP_CMD | USB_DIR_OUT, + 0}; + u8 int_ep_addr[] = { + AR9170_USB_EP_IRQ | USB_DIR_IN, + 0}; + if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) || + !usb_check_int_endpoints(intf, int_ep_addr)) + err = -ENODEV; + } else { + u8 bulk_ep_addr[] = { + AR9170_USB_EP_RX | USB_DIR_IN, + AR9170_USB_EP_TX | USB_DIR_OUT, + 0}; + u8 int_ep_addr[] = { + AR9170_USB_EP_IRQ | USB_DIR_IN, + AR9170_USB_EP_CMD | USB_DIR_OUT, + 0}; + if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) || + !usb_check_int_endpoints(intf, int_ep_addr)) + err = -ENODEV; + } + + if (err) { + carl9170_free(ar); + return err; + } + usb_set_intfdata(intf, ar); SET_IEEE80211_DEV(ar->hw, &intf->dev); diff --git a/drivers/net/wireless/broadcom/b43/b43.h b/drivers/net/wireless/broadcom/b43/b43.h index 67b4bac048e58..c0d8fc0b22fb2 100644 --- a/drivers/net/wireless/broadcom/b43/b43.h +++ b/drivers/net/wireless/broadcom/b43/b43.h @@ -1082,6 +1082,22 @@ static inline bool b43_using_pio_transfers(struct b43_wldev *dev) return dev->__using_pio_transfers; } +static inline void b43_wake_queue(struct b43_wldev *dev, int queue_prio) +{ + if (dev->qos_enabled) + ieee80211_wake_queue(dev->wl->hw, queue_prio); + else + ieee80211_wake_queue(dev->wl->hw, 0); +} + +static inline void b43_stop_queue(struct b43_wldev *dev, int queue_prio) +{ + if (dev->qos_enabled) + ieee80211_stop_queue(dev->wl->hw, queue_prio); + else + ieee80211_stop_queue(dev->wl->hw, 0); +} + /* Message printing */ __printf(2, 3) void b43info(struct b43_wl *wl, const char *fmt, ...); __printf(2, 3) void b43err(struct b43_wl *wl, const char *fmt, ...); diff --git a/drivers/net/wireless/broadcom/b43/dma.c b/drivers/net/wireless/broadcom/b43/dma.c index 760d1a28edc6c..6ac7dcebfff9d 100644 --- a/drivers/net/wireless/broadcom/b43/dma.c +++ b/drivers/net/wireless/broadcom/b43/dma.c @@ -1399,7 +1399,7 @@ int b43_dma_tx(struct b43_wldev *dev, struct sk_buff *skb) should_inject_overflow(ring)) { /* This TX ring is full. */ unsigned int skb_mapping = skb_get_queue_mapping(skb); - ieee80211_stop_queue(dev->wl->hw, skb_mapping); + b43_stop_queue(dev, skb_mapping); dev->wl->tx_queue_stopped[skb_mapping] = true; ring->stopped = true; if (b43_debug(dev, B43_DBG_DMAVERBOSE)) { @@ -1570,7 +1570,7 @@ void b43_dma_handle_txstatus(struct b43_wldev *dev, } else { /* If the driver queue is running wake the corresponding * mac80211 queue. */ - ieee80211_wake_queue(dev->wl->hw, ring->queue_prio); + b43_wake_queue(dev, ring->queue_prio); if (b43_debug(dev, B43_DBG_DMAVERBOSE)) { b43dbg(dev->wl, "Woke up TX ring %d\n", ring->index); } diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c index 92ca0b2ca286d..effb6c23f8257 100644 --- a/drivers/net/wireless/broadcom/b43/main.c +++ b/drivers/net/wireless/broadcom/b43/main.c @@ -2587,7 +2587,8 @@ static void b43_request_firmware(struct work_struct *work) start_ieee80211: wl->hw->queues = B43_QOS_QUEUE_NUM; - if (!modparam_qos || dev->fw.opensource) + if (!modparam_qos || dev->fw.opensource || + dev->dev->chip_id == BCMA_CHIP_ID_BCM4331) wl->hw->queues = 1; err = ieee80211_register_hw(wl->hw); @@ -3603,7 +3604,7 @@ static void b43_tx_work(struct work_struct *work) err = b43_dma_tx(dev, skb); if (err == -ENOSPC) { wl->tx_queue_stopped[queue_num] = true; - ieee80211_stop_queue(wl->hw, queue_num); + b43_stop_queue(dev, queue_num); skb_queue_head(&wl->tx_queue[queue_num], skb); break; } @@ -3627,6 +3628,7 @@ static void b43_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb) { struct b43_wl *wl = hw_to_b43_wl(hw); + u16 skb_queue_mapping; if (unlikely(skb->len < 2 + 2 + 6)) { /* Too short, this can't be a valid frame. */ @@ -3635,12 +3637,12 @@ static void b43_op_tx(struct ieee80211_hw *hw, } B43_WARN_ON(skb_shinfo(skb)->nr_frags); - skb_queue_tail(&wl->tx_queue[skb->queue_mapping], skb); - if (!wl->tx_queue_stopped[skb->queue_mapping]) { + skb_queue_mapping = skb_get_queue_mapping(skb); + skb_queue_tail(&wl->tx_queue[skb_queue_mapping], skb); + if (!wl->tx_queue_stopped[skb_queue_mapping]) ieee80211_queue_work(wl->hw, &wl->tx_work); - } else { - ieee80211_stop_queue(wl->hw, skb->queue_mapping); - } + else + b43_stop_queue(wl->current_dev, skb_queue_mapping); } static void b43_qos_params_upload(struct b43_wldev *dev, diff --git a/drivers/net/wireless/broadcom/b43/pio.c b/drivers/net/wireless/broadcom/b43/pio.c index 0cf70fdb60a6a..e41f2f5b4c266 100644 --- a/drivers/net/wireless/broadcom/b43/pio.c +++ b/drivers/net/wireless/broadcom/b43/pio.c @@ -525,7 +525,7 @@ int b43_pio_tx(struct b43_wldev *dev, struct sk_buff *skb) if (total_len > (q->buffer_size - q->buffer_used)) { /* Not enough memory on the queue. */ err = -EBUSY; - ieee80211_stop_queue(dev->wl->hw, skb_get_queue_mapping(skb)); + b43_stop_queue(dev, skb_get_queue_mapping(skb)); q->stopped = true; goto out; } @@ -552,7 +552,7 @@ int b43_pio_tx(struct b43_wldev *dev, struct sk_buff *skb) if (((q->buffer_size - q->buffer_used) < roundup(2 + 2 + 6, 4)) || (q->free_packet_slots == 0)) { /* The queue is full. */ - ieee80211_stop_queue(dev->wl->hw, skb_get_queue_mapping(skb)); + b43_stop_queue(dev, skb_get_queue_mapping(skb)); q->stopped = true; } @@ -587,7 +587,7 @@ void b43_pio_handle_txstatus(struct b43_wldev *dev, list_add(&pack->list, &q->packets_list); if (q->stopped) { - ieee80211_wake_queue(dev->wl->hw, q->queue_prio); + b43_wake_queue(dev, q->queue_prio); q->stopped = false; } } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/core.c index ac3a36fa3640c..a963c242975ac 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/core.c @@ -7,21 +7,16 @@ #include #include #include +#include #include "vops.h" -static int brcmf_bca_attach(struct brcmf_pub *drvr) +static void brcmf_bca_feat_attach(struct brcmf_if *ifp) { - pr_err("%s: executing\n", __func__); - return 0; -} - -static void brcmf_bca_detach(struct brcmf_pub *drvr) -{ - pr_err("%s: executing\n", __func__); + /* SAE support not confirmed so disabling for now */ + ifp->drvr->feat_flags &= ~BIT(BRCMF_FEAT_SAE); } const struct brcmf_fwvid_ops brcmf_bca_ops = { - .attach = brcmf_bca_attach, - .detach = brcmf_bca_detach, + .feat_attach = brcmf_bca_feat_attach, }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 28d6a30cc0106..625b7cb37f47b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -32,6 +32,7 @@ #include "vendor.h" #include "bus.h" #include "common.h" +#include "fwvid.h" #define BRCMF_SCAN_IE_LEN_MAX 2048 @@ -1179,8 +1180,7 @@ s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg, scan_request = cfg->scan_request; cfg->scan_request = NULL; - if (timer_pending(&cfg->escan_timeout)) - del_timer_sync(&cfg->escan_timeout); + timer_delete_sync(&cfg->escan_timeout); if (fw_abort) { /* Do a scan abort to stop the driver's scan engine */ @@ -1687,52 +1687,39 @@ static u16 brcmf_map_fw_linkdown_reason(const struct brcmf_event_msg *e) return reason; } -static int brcmf_set_pmk(struct brcmf_if *ifp, const u8 *pmk_data, u16 pmk_len) +int brcmf_set_wsec(struct brcmf_if *ifp, const u8 *key, u16 key_len, u16 flags) { struct brcmf_pub *drvr = ifp->drvr; struct brcmf_wsec_pmk_le pmk; int err; + if (key_len > sizeof(pmk.key)) { + bphy_err(drvr, "key must be less than %zu bytes\n", + sizeof(pmk.key)); + return -EINVAL; + } + memset(&pmk, 0, sizeof(pmk)); - /* pass pmk directly */ - pmk.key_len = cpu_to_le16(pmk_len); - pmk.flags = cpu_to_le16(0); - memcpy(pmk.key, pmk_data, pmk_len); + /* pass key material directly */ + pmk.key_len = cpu_to_le16(key_len); + pmk.flags = cpu_to_le16(flags); + memcpy(pmk.key, key, key_len); - /* store psk in firmware */ + /* store key material in firmware */ err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SET_WSEC_PMK, &pmk, sizeof(pmk)); if (err < 0) bphy_err(drvr, "failed to change PSK in firmware (len=%u)\n", - pmk_len); + key_len); return err; } +BRCMF_EXPORT_SYMBOL_GPL(brcmf_set_wsec); -static int brcmf_set_sae_password(struct brcmf_if *ifp, const u8 *pwd_data, - u16 pwd_len) +static int brcmf_set_pmk(struct brcmf_if *ifp, const u8 *pmk_data, u16 pmk_len) { - struct brcmf_pub *drvr = ifp->drvr; - struct brcmf_wsec_sae_pwd_le sae_pwd; - int err; - - if (pwd_len > BRCMF_WSEC_MAX_SAE_PASSWORD_LEN) { - bphy_err(drvr, "sae_password must be less than %d\n", - BRCMF_WSEC_MAX_SAE_PASSWORD_LEN); - return -EINVAL; - } - - sae_pwd.key_len = cpu_to_le16(pwd_len); - memcpy(sae_pwd.key, pwd_data, pwd_len); - - err = brcmf_fil_iovar_data_set(ifp, "sae_password", &sae_pwd, - sizeof(sae_pwd)); - if (err < 0) - bphy_err(drvr, "failed to set SAE password in firmware (len=%u)\n", - pwd_len); - - return err; + return brcmf_set_wsec(ifp, pmk_data, pmk_len, 0); } static void brcmf_link_down(struct brcmf_cfg80211_vif *vif, u16 reason, @@ -2503,8 +2490,7 @@ brcmf_cfg80211_connect(struct wiphy *wiphy, struct net_device *ndev, bphy_err(drvr, "failed to clean up user-space RSNE\n"); goto done; } - err = brcmf_set_sae_password(ifp, sme->crypto.sae_pwd, - sme->crypto.sae_pwd_len); + err = brcmf_fwvid_set_sae_password(ifp, &sme->crypto); if (!err && sme->crypto.psk) err = brcmf_set_pmk(ifp, sme->crypto.psk, BRCMF_WSEC_MAX_PSK_LEN); @@ -4322,6 +4308,9 @@ brcmf_pmksa_v3_op(struct brcmf_if *ifp, struct cfg80211_pmksa *pmksa, int ret; pmk_op = kzalloc(sizeof(*pmk_op), GFP_KERNEL); + if (!pmk_op) + return -ENOMEM; + pmk_op->version = cpu_to_le16(BRCMF_PMKSA_VER_3); if (!pmksa) { @@ -5254,8 +5243,7 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev, if (crypto->sae_pwd) { brcmf_dbg(INFO, "using SAE offload\n"); profile->use_fwauth |= BIT(BRCMF_PROFILE_FWAUTH_SAE); - err = brcmf_set_sae_password(ifp, crypto->sae_pwd, - crypto->sae_pwd_len); + err = brcmf_fwvid_set_sae_password(ifp, crypto); if (err < 0) goto exit; } @@ -5362,10 +5350,12 @@ static int brcmf_cfg80211_stop_ap(struct wiphy *wiphy, struct net_device *ndev, msleep(400); if (profile->use_fwauth != BIT(BRCMF_PROFILE_FWAUTH_NONE)) { + struct cfg80211_crypto_settings crypto = {}; + if (profile->use_fwauth & BIT(BRCMF_PROFILE_FWAUTH_PSK)) brcmf_set_pmk(ifp, NULL, 0); if (profile->use_fwauth & BIT(BRCMF_PROFILE_FWAUTH_SAE)) - brcmf_set_sae_password(ifp, NULL, 0); + brcmf_fwvid_set_sae_password(ifp, &crypto); profile->use_fwauth = BIT(BRCMF_PROFILE_FWAUTH_NONE); } @@ -8437,6 +8427,7 @@ void brcmf_cfg80211_detach(struct brcmf_cfg80211_info *cfg) brcmf_btcoex_detach(cfg); wiphy_unregister(cfg->wiphy); wl_deinit_priv(cfg); + cancel_work_sync(&cfg->escan_timeout_work); brcmf_free_wiphy(cfg->wiphy); kfree(cfg); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h index 0e1fa3f0dea2c..dc3a6a537507d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.h @@ -468,4 +468,6 @@ void brcmf_set_mpc(struct brcmf_if *ndev, int mpc); void brcmf_abort_scanning(struct brcmf_cfg80211_info *cfg); void brcmf_cfg80211_free_netdev(struct net_device *ndev); +int brcmf_set_wsec(struct brcmf_if *ifp, const u8 *key, u16 key_len, u16 flags); + #endif /* BRCMFMAC_CFG80211_H */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c index b75652ba9359f..bec5748310b9c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/core.c @@ -7,21 +7,36 @@ #include #include #include +#include #include "vops.h" -static int brcmf_cyw_attach(struct brcmf_pub *drvr) +static int brcmf_cyw_set_sae_pwd(struct brcmf_if *ifp, + struct cfg80211_crypto_settings *crypto) { - pr_err("%s: executing\n", __func__); - return 0; -} + struct brcmf_pub *drvr = ifp->drvr; + struct brcmf_wsec_sae_pwd_le sae_pwd; + u16 pwd_len = crypto->sae_pwd_len; + int err; -static void brcmf_cyw_detach(struct brcmf_pub *drvr) -{ - pr_err("%s: executing\n", __func__); + if (pwd_len > BRCMF_WSEC_MAX_SAE_PASSWORD_LEN) { + bphy_err(drvr, "sae_password must be less than %d\n", + BRCMF_WSEC_MAX_SAE_PASSWORD_LEN); + return -EINVAL; + } + + sae_pwd.key_len = cpu_to_le16(pwd_len); + memcpy(sae_pwd.key, crypto->sae_pwd, pwd_len); + + err = brcmf_fil_iovar_data_set(ifp, "sae_password", &sae_pwd, + sizeof(sae_pwd)); + if (err < 0) + bphy_err(drvr, "failed to set SAE password in firmware (len=%u)\n", + pwd_len); + + return err; } const struct brcmf_fwvid_ops brcmf_cyw_ops = { - .attach = brcmf_cyw_attach, - .detach = brcmf_cyw_detach, + .set_sae_password = brcmf_cyw_set_sae_pwd, }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c index 86ff174936a9a..c3a602197662b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c @@ -82,6 +82,15 @@ static const struct dmi_system_id dmi_platform_data[] = { }, .driver_data = (void *)&acepc_t8_data, }, + { + /* ACEPC W5 Pro Cherry Trail Z8350 HDMI stick, same wifi as the T8 */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "T3 MRD"), + DMI_MATCH(DMI_CHASSIS_TYPE, "3"), + DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), + }, + .driver_data = (void *)&acepc_t8_data, + }, { /* Chuwi Hi8 Pro with D2D3_Hi8Pro.233 BIOS */ .matches = { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c index 6d10c9efbe93d..909a34a1ab503 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c @@ -13,6 +13,7 @@ #include "debug.h" #include "fwil.h" #include "fwil_types.h" +#include "fwvid.h" #include "feature.h" #include "common.h" @@ -339,6 +340,8 @@ void brcmf_feat_attach(struct brcmf_pub *drvr) brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_FWSUP, "sup_wpa"); brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_SCAN_V2, "scan_ver"); + brcmf_fwvid_feat_attach(ifp); + if (drvr->settings->feature_disable) { brcmf_dbg(INFO, "Features: 0x%02x, disable: 0x%02x\n", ifp->drvr->feat_flags, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c index 72fe8bce6eaf5..a9514d72f770b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c @@ -239,6 +239,7 @@ brcmf_fil_iovar_data_set(struct brcmf_if *ifp, const char *name, const void *dat mutex_unlock(&drvr->proto_block); return err; } +BRCMF_EXPORT_SYMBOL_GPL(brcmf_fil_iovar_data_set); s32 brcmf_fil_iovar_data_get(struct brcmf_if *ifp, const char *name, void *data, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h index 9d248ba1c0b2b..e74a23e11830c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h @@ -584,7 +584,7 @@ struct brcmf_wsec_key_le { struct brcmf_wsec_pmk_le { __le16 key_len; __le16 flags; - u8 key[2 * BRCMF_WSEC_MAX_PSK_LEN + 1]; + u8 key[BRCMF_WSEC_MAX_SAE_PASSWORD_LEN]; }; /** diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.c index 86eafdb405419..b427782554b59 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.c @@ -89,8 +89,7 @@ int brcmf_fwvid_register_vendor(enum brcmf_fwvendor fwvid, struct module *vmod, if (fwvid >= BRCMF_FWVENDOR_NUM) return -ERANGE; - if (WARN_ON(!vmod) || WARN_ON(!vops) || - WARN_ON(!vops->attach) || WARN_ON(!vops->detach)) + if (WARN_ON(!vmod) || WARN_ON(!vops)) return -EINVAL; if (WARN_ON(fwvid_list[fwvid].vmod)) @@ -150,7 +149,7 @@ static inline int brcmf_fwvid_request_module(enum brcmf_fwvendor fwvid) } #endif -int brcmf_fwvid_attach_ops(struct brcmf_pub *drvr) +int brcmf_fwvid_attach(struct brcmf_pub *drvr) { enum brcmf_fwvendor fwvid = drvr->bus_if->fwvid; int ret; @@ -175,7 +174,7 @@ int brcmf_fwvid_attach_ops(struct brcmf_pub *drvr) return ret; } -void brcmf_fwvid_detach_ops(struct brcmf_pub *drvr) +void brcmf_fwvid_detach(struct brcmf_pub *drvr) { enum brcmf_fwvendor fwvid = drvr->bus_if->fwvid; @@ -187,9 +186,10 @@ void brcmf_fwvid_detach_ops(struct brcmf_pub *drvr) mutex_lock(&fwvid_list_lock); - drvr->vops = NULL; - list_del(&drvr->bus_if->list); - + if (drvr->vops) { + drvr->vops = NULL; + list_del(&drvr->bus_if->list); + } mutex_unlock(&fwvid_list_lock); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.h index 43df58bb70ad3..dac22534d0334 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwvid.h @@ -6,12 +6,14 @@ #define FWVID_H_ #include "firmware.h" +#include "cfg80211.h" struct brcmf_pub; +struct brcmf_if; struct brcmf_fwvid_ops { - int (*attach)(struct brcmf_pub *drvr); - void (*detach)(struct brcmf_pub *drvr); + void (*feat_attach)(struct brcmf_if *ifp); + int (*set_sae_password)(struct brcmf_if *ifp, struct cfg80211_crypto_settings *crypto); }; /* exported functions */ @@ -20,28 +22,29 @@ int brcmf_fwvid_register_vendor(enum brcmf_fwvendor fwvid, struct module *mod, int brcmf_fwvid_unregister_vendor(enum brcmf_fwvendor fwvid, struct module *mod); /* core driver functions */ -int brcmf_fwvid_attach_ops(struct brcmf_pub *drvr); -void brcmf_fwvid_detach_ops(struct brcmf_pub *drvr); +int brcmf_fwvid_attach(struct brcmf_pub *drvr); +void brcmf_fwvid_detach(struct brcmf_pub *drvr); const char *brcmf_fwvid_vendor_name(struct brcmf_pub *drvr); -static inline int brcmf_fwvid_attach(struct brcmf_pub *drvr) +static inline void brcmf_fwvid_feat_attach(struct brcmf_if *ifp) { - int ret; + const struct brcmf_fwvid_ops *vops = ifp->drvr->vops; - ret = brcmf_fwvid_attach_ops(drvr); - if (ret) - return ret; + if (!vops->feat_attach) + return; - return drvr->vops->attach(drvr); + vops->feat_attach(ifp); } -static inline void brcmf_fwvid_detach(struct brcmf_pub *drvr) +static inline int brcmf_fwvid_set_sae_password(struct brcmf_if *ifp, + struct cfg80211_crypto_settings *crypto) { - if (!drvr->vops) - return; + const struct brcmf_fwvid_ops *vops = ifp->drvr->vops; + + if (!vops || !vops->set_sae_password) + return -EOPNOTSUPP; - drvr->vops->detach(drvr); - brcmf_fwvid_detach_ops(drvr); + return vops->set_sae_password(ifp, crypto); } #endif /* FWVID_H_ */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index d7fb88bb6ae1a..06698a714b523 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1675,6 +1675,15 @@ struct brcmf_random_seed_footer { #define BRCMF_RANDOM_SEED_MAGIC 0xfeedc0de #define BRCMF_RANDOM_SEED_LENGTH 0x100 +static noinline_for_stack void +brcmf_pcie_provide_random_bytes(struct brcmf_pciedev_info *devinfo, u32 address) +{ + u8 randbuf[BRCMF_RANDOM_SEED_LENGTH]; + + get_random_bytes(randbuf, BRCMF_RANDOM_SEED_LENGTH); + memcpy_toio(devinfo->tcm + address, randbuf, BRCMF_RANDOM_SEED_LENGTH); +} + static int brcmf_pcie_download_fw_nvram(struct brcmf_pciedev_info *devinfo, const struct firmware *fw, void *nvram, u32 nvram_len) @@ -1717,7 +1726,6 @@ static int brcmf_pcie_download_fw_nvram(struct brcmf_pciedev_info *devinfo, .length = cpu_to_le32(rand_len), .magic = cpu_to_le32(BRCMF_RANDOM_SEED_MAGIC), }; - void *randbuf; /* Some Apple chips/firmwares expect a buffer of random * data to be present before NVRAM @@ -1729,10 +1737,7 @@ static int brcmf_pcie_download_fw_nvram(struct brcmf_pciedev_info *devinfo, sizeof(footer)); address -= rand_len; - randbuf = kzalloc(rand_len, GFP_KERNEL); - get_random_bytes(randbuf, rand_len); - memcpy_toio(devinfo->tcm + address, randbuf, rand_len); - kfree(randbuf); + brcmf_pcie_provide_random_bytes(devinfo, address); } } else { brcmf_dbg(PCIE, "No matching NVRAM file found %s\n", diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/core.c index 5573a47766ad5..fd593b93ad404 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/core.c @@ -7,21 +7,17 @@ #include #include #include +#include #include "vops.h" -static int brcmf_wcc_attach(struct brcmf_pub *drvr) +static int brcmf_wcc_set_sae_pwd(struct brcmf_if *ifp, + struct cfg80211_crypto_settings *crypto) { - pr_debug("%s: executing\n", __func__); - return 0; -} - -static void brcmf_wcc_detach(struct brcmf_pub *drvr) -{ - pr_debug("%s: executing\n", __func__); + return brcmf_set_wsec(ifp, crypto->sae_pwd, crypto->sae_pwd_len, + BRCMF_WSEC_PASSPHRASE); } const struct brcmf_fwvid_ops brcmf_wcc_ops = { - .attach = brcmf_wcc_attach, - .detach = brcmf_wcc_detach, + .set_sae_password = brcmf_wcc_set_sae_pwd, }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c index ccc621b8ed9f2..4a1fe982a948e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c @@ -383,8 +383,9 @@ struct shared_phy *wlc_phy_shared_attach(struct shared_phy_params *shp) return sh; } -static void wlc_phy_timercb_phycal(struct brcms_phy *pi) +static void wlc_phy_timercb_phycal(void *ptr) { + struct brcms_phy *pi = ptr; uint delay = 5; if (PHY_PERICAL_MPHASE_PENDING(pi)) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c index a0de5db0cd646..b723817915365 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c @@ -57,12 +57,11 @@ void wlc_phy_shim_detach(struct phy_shim_info *physhim) } struct wlapi_timer *wlapi_init_timer(struct phy_shim_info *physhim, - void (*fn)(struct brcms_phy *pi), + void (*fn)(void *pi), void *arg, const char *name) { return (struct wlapi_timer *) - brcms_init_timer(physhim->wl, (void (*)(void *))fn, - arg, name); + brcms_init_timer(physhim->wl, fn, arg, name); } void wlapi_free_timer(struct wlapi_timer *t) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h index dd8774717adee..27d0934e600ed 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h @@ -131,7 +131,7 @@ void wlc_phy_shim_detach(struct phy_shim_info *physhim); /* PHY to WL utility functions */ struct wlapi_timer *wlapi_init_timer(struct phy_shim_info *physhim, - void (*fn)(struct brcms_phy *pi), + void (*fn)(void *pi), void *arg, const char *name); void wlapi_free_timer(struct wlapi_timer *t); void wlapi_add_timer(struct wlapi_timer *t, uint ms, int periodic); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c index 134635c70ce85..73cbb120a49b4 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c @@ -299,3 +299,9 @@ MODULE_FIRMWARE(IWL_MA_B_HR_B_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_B_GF_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_B_GF4_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_B_MR_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); + +MODULE_FIRMWARE("iwlwifi-so-a0-gf-a0.pnvm"); +MODULE_FIRMWARE("iwlwifi-so-a0-gf4-a0.pnvm"); +MODULE_FIRMWARE("iwlwifi-ty-a0-gf-a0.pnvm"); +MODULE_FIRMWARE("iwlwifi-ma-b0-gf-a0.pnvm"); +MODULE_FIRMWARE("iwlwifi-ma-b0-gf4-a0.pnvm"); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c index 82da957adcf6e..1b6249561cd58 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c @@ -179,3 +179,5 @@ MODULE_FIRMWARE(IWL_BZ_A_FM_C_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_BZ_A_FM4_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_GL_B_FM_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_GL_C_FM_C_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); + +MODULE_FIRMWARE("iwlwifi-gl-c0-fm-c0.pnvm"); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c index 80eb9b4995389..156c428547497 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include #include @@ -33,6 +33,10 @@ #define IWL_SC_A_GF_A_FW_PRE "iwlwifi-sc-a0-gf-a0" #define IWL_SC_A_GF4_A_FW_PRE "iwlwifi-sc-a0-gf4-a0" #define IWL_SC_A_WH_A_FW_PRE "iwlwifi-sc-a0-wh-a0" +#define IWL_SC2_A_FM_C_FW_PRE "iwlwifi-sc2-a0-fm-c0" +#define IWL_SC2_A_WH_A_FW_PRE "iwlwifi-sc2-a0-wh-a0" +#define IWL_SC2F_A_FM_C_FW_PRE "iwlwifi-sc2f-a0-fm-c0" +#define IWL_SC2F_A_WH_A_FW_PRE "iwlwifi-sc2f-a0-wh-a0" #define IWL_SC_A_FM_B_FW_MODULE_FIRMWARE(api) \ IWL_SC_A_FM_B_FW_PRE "-" __stringify(api) ".ucode" @@ -48,6 +52,14 @@ IWL_SC_A_GF4_A_FW_PRE "-" __stringify(api) ".ucode" #define IWL_SC_A_WH_A_FW_MODULE_FIRMWARE(api) \ IWL_SC_A_WH_A_FW_PRE "-" __stringify(api) ".ucode" +#define IWL_SC2_A_FM_C_FW_MODULE_FIRMWARE(api) \ + IWL_SC2_A_FM_C_FW_PRE "-" __stringify(api) ".ucode" +#define IWL_SC2_A_WH_A_FW_MODULE_FIRMWARE(api) \ + IWL_SC2_A_WH_A_FW_PRE "-" __stringify(api) ".ucode" +#define IWL_SC2F_A_FM_C_FW_MODULE_FIRMWARE(api) \ + IWL_SC2F_A_FM_C_FW_PRE "-" __stringify(api) ".ucode" +#define IWL_SC2F_A_WH_A_FW_MODULE_FIRMWARE(api) \ + IWL_SC2F_A_WH_A_FW_PRE "-" __stringify(api) ".ucode" static const struct iwl_base_params iwl_sc_base_params = { .eeprom_size = OTP_LOW_IMAGE_SIZE_32K, @@ -124,6 +136,9 @@ static const struct iwl_base_params iwl_sc_base_params = { #define IWL_DEVICE_SC \ IWL_DEVICE_BZ_COMMON, \ + .uhb_supported = true, \ + .features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM, \ + .num_rbds = IWL_NUM_RBDS_SC_EHT, \ .ht_params = &iwl_22000_ht_params /* @@ -149,10 +164,21 @@ const char iwl_sc_name[] = "Intel(R) TBD Sc device"; const struct iwl_cfg iwl_cfg_sc = { .fw_name_mac = "sc", - .uhb_supported = true, IWL_DEVICE_SC, - .features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM, - .num_rbds = IWL_NUM_RBDS_SC_EHT, +}; + +const char iwl_sc2_name[] = "Intel(R) TBD Sc2 device"; + +const struct iwl_cfg iwl_cfg_sc2 = { + .fw_name_mac = "sc2", + IWL_DEVICE_SC, +}; + +const char iwl_sc2f_name[] = "Intel(R) TBD Sc2f device"; + +const struct iwl_cfg iwl_cfg_sc2f = { + .fw_name_mac = "sc2f", + IWL_DEVICE_SC, }; MODULE_FIRMWARE(IWL_SC_A_FM_B_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); @@ -162,3 +188,7 @@ MODULE_FIRMWARE(IWL_SC_A_HR_B_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_SC_A_GF_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_SC_A_GF4_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_SC_A_WH_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_SC2_A_FM_C_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_SC2_A_WH_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_SC2F_A_FM_C_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_SC2F_A_WH_A_FW_MODULE_FIRMWARE(IWL_SC_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index dcc4810cb3247..e161b44539069 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -767,7 +767,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) * from index 1, so the maximum value allowed here is * ACPI_SAR_PROFILES_NUM - 1. */ - if (n_profiles <= 0 || n_profiles >= ACPI_SAR_PROFILE_NUM) { + if (n_profiles >= ACPI_SAR_PROFILE_NUM) { ret = -EINVAL; goto out_free; } @@ -1296,7 +1296,6 @@ void iwl_acpi_get_phy_filters(struct iwl_fw_runtime *fwrt, if (IS_ERR(data)) return; - /* try to read wtas table revision 1 or revision 0*/ wifi_pkg = iwl_acpi_get_wifi_pkg(fwrt->dev, data, ACPI_WPFC_WIFI_DATA_SIZE, &tbl_rev); @@ -1306,13 +1305,14 @@ void iwl_acpi_get_phy_filters(struct iwl_fw_runtime *fwrt, if (tbl_rev != 0) goto out_free; - BUILD_BUG_ON(ARRAY_SIZE(filters->filter_cfg_chains) != ACPI_WPFC_WIFI_DATA_SIZE); + BUILD_BUG_ON(ARRAY_SIZE(filters->filter_cfg_chains) != + ACPI_WPFC_WIFI_DATA_SIZE - 1); for (i = 0; i < ARRAY_SIZE(filters->filter_cfg_chains); i++) { - if (wifi_pkg->package.elements[i].type != ACPI_TYPE_INTEGER) - return; + if (wifi_pkg->package.elements[i + 1].type != ACPI_TYPE_INTEGER) + goto out_free; tmp.filter_cfg_chains[i] = - cpu_to_le32(wifi_pkg->package.elements[i].integer.value); + cpu_to_le32(wifi_pkg->package.elements[i + 1].integer.value); } IWL_DEBUG_RADIO(fwrt, "Loaded WPFC filter config from ACPI\n"); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h index e9277f6f35821..39106ccb4b9b6 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h @@ -56,7 +56,7 @@ #define ACPI_EWRD_WIFI_DATA_SIZE_REV2 ((ACPI_SAR_PROFILE_NUM - 1) * \ ACPI_SAR_NUM_CHAINS_REV2 * \ ACPI_SAR_NUM_SUB_BANDS_REV2 + 3) -#define ACPI_WPFC_WIFI_DATA_SIZE 4 /* 4 filter config words */ +#define ACPI_WPFC_WIFI_DATA_SIZE 5 /* domain and 4 filter config words */ /* revision 0 and 1 are identical, except for the semantics in the FW */ #define ACPI_GEO_NUM_BANDS_REV0 2 diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h index 040d83fa5424a..bae4f2238e98b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h @@ -385,6 +385,33 @@ struct iwl_dev_tx_power_cmd_v7 { __le32 timer_period; __le32 flags; } __packed; /* TX_REDUCED_POWER_API_S_VER_7 */ + +/** + * struct iwl_dev_tx_power_cmd_v8 - TX power reduction command version 8 + * @per_chain: per chain restrictions + * @enable_ack_reduction: enable or disable close range ack TX power + * reduction. + * @per_chain_restriction_changed: is per_chain_restriction has changed + * from last command. used if set_mode is + * IWL_TX_POWER_MODE_SET_SAR_TIMER. + * note: if not changed, the command is used for keep alive only. + * @reserved: reserved (padding) + * @timer_period: timer in milliseconds. if expires FW will change to default + * BIOS values. relevant if setMode is IWL_TX_POWER_MODE_SET_SAR_TIMER + * @flags: reduce power flags. + * @tpc_vlp_backoff_level: user backoff of UNII5,7 VLP channels in USA. + * Not in use. + */ +struct iwl_dev_tx_power_cmd_v8 { + __le16 per_chain[IWL_NUM_CHAIN_TABLES_V2][IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS_V2]; + u8 enable_ack_reduction; + u8 per_chain_restriction_changed; + u8 reserved[2]; + __le32 timer_period; + __le32 flags; + __le32 tpc_vlp_backoff_level; +} __packed; /* TX_REDUCED_POWER_API_S_VER_8 */ + /** * struct iwl_dev_tx_power_cmd - TX power reduction command (multiversion) * @common: common part of the command @@ -392,6 +419,8 @@ struct iwl_dev_tx_power_cmd_v7 { * @v4: version 4 part of the command * @v5: version 5 part of the command * @v6: version 6 part of the command + * @v7: version 7 part of the command + * @v8: version 8 part of the command */ struct iwl_dev_tx_power_cmd { struct iwl_dev_tx_power_common common; @@ -401,6 +430,7 @@ struct iwl_dev_tx_power_cmd { struct iwl_dev_tx_power_cmd_v5 v5; struct iwl_dev_tx_power_cmd_v6 v6; struct iwl_dev_tx_power_cmd_v7 v7; + struct iwl_dev_tx_power_cmd_v8 v8; }; }; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index 80fda056e46a6..59f7a75c7201d 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -3074,8 +3074,6 @@ static void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt, u8 wk_idx) struct iwl_fw_dbg_params params = {0}; struct iwl_fwrt_dump_data *dump_data = &fwrt->dump.wks[wk_idx].dump_data; - u32 policy; - u32 time_point; if (!test_bit(wk_idx, &fwrt->dump.active_wks)) return; @@ -3106,13 +3104,16 @@ static void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt, u8 wk_idx) iwl_fw_dbg_stop_restart_recording(fwrt, ¶ms, false); - policy = le32_to_cpu(dump_data->trig->apply_policy); - time_point = le32_to_cpu(dump_data->trig->time_point); + if (iwl_trans_dbg_ini_valid(fwrt->trans)) { + u32 policy = le32_to_cpu(dump_data->trig->apply_policy); + u32 time_point = le32_to_cpu(dump_data->trig->time_point); - if (policy & IWL_FW_INI_APPLY_POLICY_DUMP_COMPLETE_CMD) { - IWL_DEBUG_FW_INFO(fwrt, "WRT: sending dump complete\n"); - iwl_send_dbg_dump_complete_cmd(fwrt, time_point, 0); + if (policy & IWL_FW_INI_APPLY_POLICY_DUMP_COMPLETE_CMD) { + IWL_DEBUG_FW_INFO(fwrt, "WRT: sending dump complete\n"); + iwl_send_dbg_dump_complete_cmd(fwrt, time_point, 0); + } } + if (fwrt->trans->dbg.last_tp_resetfw == IWL_FW_INI_RESET_FW_MODE_STOP_FW_ONLY) iwl_force_nmi(fwrt->trans); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c index 650e4bde9c17b..56ee0ceed78ab 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c @@ -255,21 +255,27 @@ static u8 *iwl_get_pnvm_image(struct iwl_trans *trans_p, size_t *len) struct pnvm_sku_package *package; u8 *image = NULL; - /* First attempt to get the PNVM from BIOS */ - package = iwl_uefi_get_pnvm(trans_p, len); - if (!IS_ERR_OR_NULL(package)) { - if (*len >= sizeof(*package)) { - /* we need only the data */ - *len -= sizeof(*package); - image = kmemdup(package->data, *len, GFP_KERNEL); + /* Get PNVM from BIOS for non-Intel SKU */ + if (trans_p->sku_id[2]) { + package = iwl_uefi_get_pnvm(trans_p, len); + if (!IS_ERR_OR_NULL(package)) { + if (*len >= sizeof(*package)) { + /* we need only the data */ + *len -= sizeof(*package); + image = kmemdup(package->data, + *len, GFP_KERNEL); + } + /* + * free package regardless of whether kmemdup + * succeeded + */ + kfree(package); + if (image) + return image; } - /* free package regardless of whether kmemdup succeeded */ - kfree(package); - if (image) - return image; } - /* If it's not available, try from the filesystem */ + /* If it's not available, or for Intel SKU, try from the filesystem */ if (iwl_pnvm_get_from_fs(trans_p, &image, len)) return NULL; return image; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h index 357727774db90..baabb8e321f8d 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h @@ -173,9 +173,9 @@ struct iwl_fw_runtime { struct iwl_sar_offset_mapping_cmd sgom_table; bool sgom_enabled; u8 reduced_power_flags; - bool uats_enabled; struct iwl_uats_table_cmd uats_table; #endif + bool uats_enabled; }; void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans, diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index ae6f1cd4d6605..e99d691362a86 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -2,7 +2,7 @@ /* * Copyright (C) 2005-2014, 2018-2021 Intel Corporation * Copyright (C) 2016-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #ifndef __IWL_CONFIG_H__ #define __IWL_CONFIG_H__ @@ -418,6 +418,8 @@ struct iwl_cfg { #define IWL_CFG_MAC_TYPE_BZ 0x46 #define IWL_CFG_MAC_TYPE_GL 0x47 #define IWL_CFG_MAC_TYPE_SC 0x48 +#define IWL_CFG_MAC_TYPE_SC2 0x49 +#define IWL_CFG_MAC_TYPE_SC2F 0x4A #define IWL_CFG_RF_TYPE_TH 0x105 #define IWL_CFG_RF_TYPE_TH1 0x108 @@ -527,6 +529,8 @@ extern const char iwl_ax231_name[]; extern const char iwl_ax411_name[]; extern const char iwl_bz_name[]; extern const char iwl_sc_name[]; +extern const char iwl_sc2_name[]; +extern const char iwl_sc2f_name[]; #if IS_ENABLED(CONFIG_IWLDVM) extern const struct iwl_cfg iwl5300_agn_cfg; extern const struct iwl_cfg iwl5100_agn_cfg; @@ -632,6 +636,8 @@ extern const struct iwl_cfg iwl_cfg_bz; extern const struct iwl_cfg iwl_cfg_gl; extern const struct iwl_cfg iwl_cfg_sc; +extern const struct iwl_cfg iwl_cfg_sc2; +extern const struct iwl_cfg iwl_cfg_sc2f; #endif /* CONFIG_IWLMVM */ #endif /* __IWL_CONFIG_H__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 72075720969c0..3442dfab50b53 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -103,6 +103,12 @@ static int iwl_dbg_tlv_alloc_debug_info(struct iwl_trans *trans, if (le32_to_cpu(tlv->length) != sizeof(*debug_info)) return -EINVAL; + /* we use this as a string, ensure input was NUL terminated */ + if (strnlen(debug_info->debug_cfg_name, + sizeof(debug_info->debug_cfg_name)) == + sizeof(debug_info->debug_cfg_name)) + return -EINVAL; + IWL_DEBUG_FW(trans, "WRT: Loading debug cfg: %s\n", debug_info->debug_cfg_name); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index abf8001bdac17..2d63e022f4e2d 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1838,8 +1838,8 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans) err_fw: #ifdef CONFIG_IWLWIFI_DEBUGFS debugfs_remove_recursive(drv->dbgfs_drv); - iwl_dbg_tlv_free(drv->trans); #endif + iwl_dbg_tlv_free(drv->trans); kfree(drv); err: return ERR_PTR(ret); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index 2f6774ec37b22..501a8cc2134cf 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -2097,7 +2097,7 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans, !!(mac_flags & NVM_MAC_SKU_FLAGS_BAND_5_2_ENABLED); nvm->sku_cap_mimo_disabled = !!(mac_flags & NVM_MAC_SKU_FLAGS_MIMO_DISABLED); - if (CSR_HW_RFID_TYPE(trans->hw_rf_id) == IWL_CFG_RF_TYPE_FM) + if (CSR_HW_RFID_TYPE(trans->hw_rf_id) >= IWL_CFG_RF_TYPE_FM) nvm->sku_cap_11be_enable = true; /* Initialize PHY sku data */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 05b64176859e8..2a08369238f23 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -461,12 +461,10 @@ static int iwl_mvm_wowlan_config_rsc_tsc(struct iwl_mvm *mvm, struct wowlan_key_rsc_v5_data data = {}; int i; - data.rsc = kmalloc(sizeof(*data.rsc), GFP_KERNEL); + data.rsc = kzalloc(sizeof(*data.rsc), GFP_KERNEL); if (!data.rsc) return -ENOMEM; - memset(data.rsc, 0xff, sizeof(*data.rsc)); - for (i = 0; i < ARRAY_SIZE(data.rsc->mcast_key_id_map); i++) data.rsc->mcast_key_id_map[i] = IWL_MCAST_KEY_MAP_INVALID; @@ -2200,7 +2198,10 @@ static void iwl_mvm_convert_gtk_v3(struct iwl_wowlan_status_data *status, static void iwl_mvm_convert_igtk(struct iwl_wowlan_status_data *status, struct iwl_wowlan_igtk_status *data) { + int i; + BUILD_BUG_ON(sizeof(status->igtk.key) < sizeof(data->key)); + BUILD_BUG_ON(sizeof(status->igtk.ipn) != sizeof(data->ipn)); if (!data->key_len) return; @@ -2212,7 +2213,10 @@ static void iwl_mvm_convert_igtk(struct iwl_wowlan_status_data *status, + WOWLAN_IGTK_MIN_INDEX; memcpy(status->igtk.key, data->key, sizeof(data->key)); - memcpy(status->igtk.ipn, data->ipn, sizeof(data->ipn)); + + /* mac80211 expects big endian for memcmp() to work, convert */ + for (i = 0; i < sizeof(data->ipn); i++) + status->igtk.ipn[i] = data->ipn[sizeof(data->ipn) - i - 1]; } static void iwl_mvm_convert_bigtk(struct iwl_wowlan_status_data *status, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c index e8b881596baf1..34b8771d1edac 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c @@ -735,7 +735,9 @@ void iwl_mvm_vif_dbgfs_add_link(struct iwl_mvm *mvm, struct ieee80211_vif *vif) { struct dentry *dbgfs_dir = vif->debugfs_dir; struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - char buf[100]; + char buf[3 * 3 + 11 + (NL80211_WIPHY_NAME_MAXLEN + 1) + + (7 + IFNAMSIZ + 1) + 6 + 1]; + char name[7 + IFNAMSIZ + 1]; /* this will happen in monitor mode */ if (!dbgfs_dir) @@ -748,10 +750,11 @@ void iwl_mvm_vif_dbgfs_add_link(struct iwl_mvm *mvm, struct ieee80211_vif *vif) * find * netdev:wlan0 -> ../../../ieee80211/phy0/netdev:wlan0/iwlmvm/ */ - snprintf(buf, 100, "../../../%pd3/iwlmvm", dbgfs_dir); + snprintf(name, sizeof(name), "%pd", dbgfs_dir); + snprintf(buf, sizeof(buf), "../../../%pd3/iwlmvm", dbgfs_dir); - mvmvif->dbgfs_slink = debugfs_create_symlink(dbgfs_dir->d_name.name, - mvm->debugfs_dir, buf); + mvmvif->dbgfs_slink = + debugfs_create_symlink(name, mvm->debugfs_dir, buf); } void iwl_mvm_vif_dbgfs_rm_link(struct iwl_mvm *mvm, struct ieee80211_vif *vif) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index 233ae81884a0e..ae0eb585b61ee 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -53,6 +53,8 @@ int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (!pasn) return -ENOBUFS; + iwl_mvm_ftm_remove_pasn_sta(mvm, addr); + pasn->cipher = iwl_mvm_cipher_to_location_cipher(cipher); switch (pasn->cipher) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 1252084662c6f..5c0eda0ea0166 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -93,20 +93,10 @@ void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm, { struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_mfu_assert_dump_notif *mfu_dump_notif = (void *)pkt->data; - __le32 *dump_data = mfu_dump_notif->data; - int n_words = le32_to_cpu(mfu_dump_notif->data_size) / sizeof(__le32); - int i; if (mfu_dump_notif->index_num == 0) IWL_INFO(mvm, "MFUART assert id 0x%x occurred\n", le32_to_cpu(mfu_dump_notif->assert_id)); - - for (i = 0; i < n_words; i++) - IWL_DEBUG_INFO(mvm, - "MFUART assert dump, dword %u: 0x%08x\n", - le16_to_cpu(mfu_dump_notif->index_num) * - n_words + i, - le32_to_cpu(dump_data[i])); } static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait, @@ -901,13 +891,15 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b) int ret; u16 len = 0; u32 n_subbands; - u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, - IWL_FW_CMD_VER_UNKNOWN); - if (cmd_ver == 7) { + u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, 3); + + if (cmd_ver >= 7) { len = sizeof(cmd.v7); n_subbands = IWL_NUM_SUB_BANDS_V2; per_chain = cmd.v7.per_chain[0][0]; cmd.v7.flags = cpu_to_le32(mvm->fwrt.reduced_power_flags); + if (cmd_ver == 8) + len = sizeof(cmd.v8); } else if (cmd_ver == 6) { len = sizeof(cmd.v6); n_subbands = IWL_NUM_SUB_BANDS_V2; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 53e26c3c3a9af..2b3e1c752ccd7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -354,7 +354,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) if (mvm->mld_api_is_used && mvm->nvm_data->sku_cap_11be_enable && !iwlwifi_mod_params.disable_11ax && !iwlwifi_mod_params.disable_11be) - hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO; + hw->wiphy->flags |= WIPHY_FLAG_DISABLE_WEXT; /* With MLD FW API, it tracks timing by itself, * no need for any timing from the host @@ -1383,7 +1383,9 @@ int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (tx_power == IWL_DEFAULT_MAX_TX_POWER) cmd.common.pwr_restriction = cpu_to_le16(IWL_DEV_MAX_TX_POWER); - if (cmd_ver == 7) + if (cmd_ver == 8) + len = sizeof(cmd.v8); + else if (cmd_ver == 7) len = sizeof(cmd.v7); else if (cmd_ver == 6) len = sizeof(cmd.v6); @@ -1547,6 +1549,17 @@ static int iwl_mvm_alloc_bcast_mcast_sta(struct iwl_mvm *mvm, IWL_STA_MULTICAST); } +void iwl_mvm_mac_init_mvmvif(struct iwl_mvm *mvm, struct iwl_mvm_vif *mvmvif) +{ + lockdep_assert_held(&mvm->mutex); + + if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) + return; + + INIT_DELAYED_WORK(&mvmvif->csa_work, + iwl_mvm_channel_switch_disconnect_wk); +} + static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { @@ -1557,6 +1570,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw, mutex_lock(&mvm->mutex); + iwl_mvm_mac_init_mvmvif(mvm, mvmvif); + mvmvif->mvm = mvm; /* the first link always points to the default one */ @@ -1632,8 +1647,6 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw, mvm->p2p_device_vif = vif; iwl_mvm_tcm_add_vif(mvm, vif); - INIT_DELAYED_WORK(&mvmvif->csa_work, - iwl_mvm_channel_switch_disconnect_wk); if (vif->type == NL80211_IFTYPE_MONITOR) { mvm->monitor_on = true; @@ -1671,6 +1684,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw, void iwl_mvm_prepare_mac_removal(struct iwl_mvm *mvm, struct ieee80211_vif *vif) { + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + if (vif->type == NL80211_IFTYPE_P2P_DEVICE) { /* * Flush the ROC worker which will flush the OFFCHANNEL queue. @@ -1679,6 +1694,8 @@ void iwl_mvm_prepare_mac_removal(struct iwl_mvm *mvm, */ flush_work(&mvm->roc_done_wk); } + + cancel_delayed_work_sync(&mvmvif->csa_work); } /* This function is doing the common part of removing the interface for @@ -3698,6 +3715,19 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) mvmvif->ap_sta = sta; + /* + * Initialize the rates here already - this really tells + * the firmware only what the supported legacy rates are + * (may be) since it's initialized already from what the + * AP advertised in the beacon/probe response. This will + * allow the firmware to send auth/assoc frames with one + * of the supported rates already, rather than having to + * use a mandatory rate. + * If we're the AP, we'll just assume mandatory rates at + * this point, but we know nothing about the STA anyway. + */ + iwl_mvm_rs_rate_init_all_links(mvm, vif, sta); + return 0; } @@ -3796,13 +3826,17 @@ iwl_mvm_sta_state_assoc_to_authorized(struct iwl_mvm *mvm, mvm_sta->authorized = true; - iwl_mvm_rs_rate_init_all_links(mvm, vif, sta); - /* MFP is set by default before the station is authorized. * Clear it here in case it's not used. */ - if (!sta->mfp) - return callbacks->update_sta(mvm, vif, sta); + if (!sta->mfp) { + int ret = callbacks->update_sta(mvm, vif, sta); + + if (ret) + return ret; + } + + iwl_mvm_rs_rate_init_all_links(mvm, vif, sta); return 0; } @@ -4651,7 +4685,7 @@ static int iwl_mvm_roc_station(struct iwl_mvm *mvm, if (fw_ver == IWL_FW_CMD_VER_UNKNOWN) { ret = iwl_mvm_send_aux_roc_cmd(mvm, channel, vif, duration); - } else if (fw_ver == 3) { + } else if (fw_ver >= 3) { ret = iwl_mvm_roc_add_cmd(mvm, channel, vif, duration, ROC_ACTIVITY_HOTSPOT); } else { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c index ea3e9e9c6e26c..fe4b39b19a612 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2022 - 2023 Intel Corporation + * Copyright (C) 2022 - 2024 Intel Corporation */ #include #include @@ -62,11 +62,13 @@ u32 iwl_mvm_get_sec_flags(struct iwl_mvm *mvm, struct ieee80211_key_conf *keyconf) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + bool pairwise = keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE; + bool igtk = keyconf->keyidx == 4 || keyconf->keyidx == 5; u32 flags = 0; lockdep_assert_held(&mvm->mutex); - if (!(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE)) + if (!pairwise) flags |= IWL_SEC_KEY_FLAG_MCAST_KEY; switch (keyconf->cipher) { @@ -96,12 +98,14 @@ u32 iwl_mvm_get_sec_flags(struct iwl_mvm *mvm, if (!sta && vif->type == NL80211_IFTYPE_STATION) sta = mvmvif->ap_sta; - /* Set the MFP flag also for an AP interface where the key is an IGTK - * key as in such a case the station would always be NULL + /* + * If we are installing an iGTK (in AP or STA mode), we need to tell + * the firmware this key will en/decrypt MGMT frames. + * Same goes if we are installing a pairwise key for an MFP station. + * In case we're installing a groupwise key (which is not an iGTK), + * then, we will not use this key for MGMT frames. */ - if ((!IS_ERR_OR_NULL(sta) && sta->mfp) || - (vif->type == NL80211_IFTYPE_AP && - (keyconf->keyidx == 4 || keyconf->keyidx == 5))) + if ((!IS_ERR_OR_NULL(sta) && sta->mfp && pairwise) || igtk) flags |= IWL_SEC_KEY_FLAG_MFP; return flags; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c index f313a8d771e42..ad78c69cc6cb7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c @@ -167,7 +167,7 @@ static int iwl_mvm_mld_mac_ctxt_cmd_listener(struct iwl_mvm *mvm, iwl_mvm_mld_mac_ctxt_cmd_common(mvm, vif, &cmd, action); cmd.filter_flags = cpu_to_le32(MAC_CFG_FILTER_PROMISC | - MAC_FILTER_IN_CONTROL_AND_MGMT | + MAC_CFG_FILTER_ACCEPT_CONTROL_AND_MGMT | MAC_CFG_FILTER_ACCEPT_BEACON | MAC_CFG_FILTER_ACCEPT_PROBE_REQ | MAC_CFG_FILTER_ACCEPT_GRP); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index 893b69fc841b8..7d3de5a6e3be3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -14,6 +14,8 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw, mutex_lock(&mvm->mutex); + iwl_mvm_mac_init_mvmvif(mvm, mvmvif); + mvmvif->mvm = mvm; /* Not much to do here. The stack will not allow interface @@ -73,8 +75,6 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw, goto out_free_bf; iwl_mvm_tcm_add_vif(mvm, vif); - INIT_DELAYED_WORK(&mvmvif->csa_work, - iwl_mvm_channel_switch_disconnect_wk); if (vif->type == NL80211_IFTYPE_MONITOR) { mvm->monitor_on = true; @@ -189,17 +189,13 @@ static void iwl_mvm_mld_mac_remove_interface(struct ieee80211_hw *hw, mutex_unlock(&mvm->mutex); } -static unsigned int iwl_mvm_mld_count_active_links(struct ieee80211_vif *vif) +static unsigned int iwl_mvm_mld_count_active_links(struct iwl_mvm_vif *mvmvif) { unsigned int n_active = 0; int i; for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { - struct ieee80211_bss_conf *link_conf; - - link_conf = link_conf_dereference_protected(vif, i); - if (link_conf && - rcu_access_pointer(link_conf->chanctx_conf)) + if (mvmvif->link[i] && mvmvif->link[i]->phy_ctxt) n_active++; } @@ -245,21 +241,18 @@ __iwl_mvm_mld_assign_vif_chanctx(struct iwl_mvm *mvm, { u16 *phy_ctxt_id = (u16 *)ctx->drv_priv; struct iwl_mvm_phy_ctxt *phy_ctxt = &mvm->phy_ctxts[*phy_ctxt_id]; - unsigned int n_active = iwl_mvm_mld_count_active_links(vif); struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + unsigned int n_active = iwl_mvm_mld_count_active_links(mvmvif); unsigned int link_id = link_conf->link_id; int ret; - /* if the assigned one was not counted yet, count it now */ - if (!rcu_access_pointer(link_conf->chanctx_conf)) - n_active++; - - if (n_active > iwl_mvm_max_active_links(mvm, vif)) - return -EOPNOTSUPP; - if (WARN_ON_ONCE(!mvmvif->link[link_id])) return -EINVAL; + /* if the assigned one was not counted yet, count it now */ + if (!mvmvif->link[link_id]->phy_ctxt) + n_active++; + /* mac parameters such as HE support can change at this stage * For sta, need first to configure correct state from drv_sta_state * and only after that update mac config. @@ -299,13 +292,8 @@ __iwl_mvm_mld_assign_vif_chanctx(struct iwl_mvm *mvm, * this needs the phy context assigned (and in FW?), and we cannot * do it later because it needs to be initialized as soon as we're * able to TX on the link, i.e. when active. - * - * Firmware restart isn't quite correct yet for MLO, but we don't - * need to do it in that case anyway since it will happen from the - * normal station state callback. */ - if (mvmvif->ap_sta && - !test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) { + if (mvmvif->ap_sta) { struct ieee80211_link_sta *link_sta; rcu_read_lock(); @@ -419,7 +407,7 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm, { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - unsigned int n_active = iwl_mvm_mld_count_active_links(vif); + unsigned int n_active = iwl_mvm_mld_count_active_links(mvmvif); unsigned int link_id = link_conf->link_id; /* shouldn't happen, but verify link_id is valid before accessing */ @@ -1122,17 +1110,12 @@ iwl_mvm_mld_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]) { struct iwl_mvm_vif_link_info *new_link[IEEE80211_MLD_MAX_NUM_LINKS] = {}; - unsigned int n_active = iwl_mvm_mld_count_active_links(vif); struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); u16 removed = old_links & ~new_links; u16 added = new_links & ~old_links; int err, i; - if (hweight16(new_links) > 1 && - n_active > iwl_mvm_max_active_links(mvm, vif)) - return -EOPNOTSUPP; - for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { int r; @@ -1224,6 +1207,15 @@ iwl_mvm_mld_change_sta_links(struct ieee80211_hw *hw, return ret; } +static bool iwl_mvm_mld_can_activate_links(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 desired_links) +{ + struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); + + return hweight16(desired_links) <= iwl_mvm_max_active_links(mvm, vif); +} + const struct ieee80211_ops iwl_mvm_mld_hw_ops = { .tx = iwl_mvm_mac_tx, .wake_tx_queue = iwl_mvm_mac_wake_tx_queue, @@ -1318,4 +1310,5 @@ const struct ieee80211_ops iwl_mvm_mld_hw_ops = { .change_vif_links = iwl_mvm_mld_change_vif_links, .change_sta_links = iwl_mvm_mld_change_sta_links, + .can_activate_links = iwl_mvm_mld_can_activate_links, }; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index 1628bf55458fc..36dc291d98dd6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -9,7 +9,9 @@ u32 iwl_mvm_sta_fw_id_mask(struct iwl_mvm *mvm, struct ieee80211_sta *sta, int filter_link_id) { + struct ieee80211_link_sta *link_sta; struct iwl_mvm_sta *mvmsta; + struct ieee80211_vif *vif; unsigned int link_id; u32 result = 0; @@ -17,26 +19,27 @@ u32 iwl_mvm_sta_fw_id_mask(struct iwl_mvm *mvm, struct ieee80211_sta *sta, return 0; mvmsta = iwl_mvm_sta_from_mac80211(sta); + vif = mvmsta->vif; /* it's easy when the STA is not an MLD */ if (!sta->valid_links) return BIT(mvmsta->deflink.sta_id); /* but if it is an MLD, get the mask of all the FW STAs it has ... */ - for (link_id = 0; link_id < ARRAY_SIZE(mvmsta->link); link_id++) { - struct iwl_mvm_link_sta *link_sta; + for_each_sta_active_link(vif, sta, link_sta, link_id) { + struct iwl_mvm_link_sta *mvm_link_sta; /* unless we have a specific link in mind */ if (filter_link_id >= 0 && link_id != filter_link_id) continue; - link_sta = + mvm_link_sta = rcu_dereference_check(mvmsta->link[link_id], lockdep_is_held(&mvm->mutex)); - if (!link_sta) + if (!mvm_link_sta) continue; - result |= BIT(link_sta->sta_id); + result |= BIT(mvm_link_sta->sta_id); } return result; @@ -582,14 +585,14 @@ static int iwl_mvm_mld_alloc_sta_links(struct iwl_mvm *mvm, struct ieee80211_sta *sta) { struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); + struct ieee80211_link_sta *link_sta; unsigned int link_id; int ret; lockdep_assert_held(&mvm->mutex); - for (link_id = 0; link_id < ARRAY_SIZE(sta->link); link_id++) { - if (!rcu_access_pointer(sta->link[link_id]) || - mvm_sta->link[link_id]) + for_each_sta_active_link(vif, sta, link_sta, link_id) { + if (WARN_ON(mvm_sta->link[link_id])) continue; ret = iwl_mvm_mld_alloc_sta_link(mvm, vif, sta, link_id); @@ -855,10 +858,15 @@ int iwl_mvm_mld_rm_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, int iwl_mvm_mld_rm_sta_id(struct iwl_mvm *mvm, u8 sta_id) { - int ret = iwl_mvm_mld_rm_sta_from_fw(mvm, sta_id); + int ret; lockdep_assert_held(&mvm->mutex); + if (WARN_ON(sta_id == IWL_MVM_INVALID_STA)) + return 0; + + ret = iwl_mvm_mld_rm_sta_from_fw(mvm, sta_id); + RCU_INIT_POINTER(mvm->fw_id_to_mac_id[sta_id], NULL); RCU_INIT_POINTER(mvm->fw_id_to_link_sta[sta_id], NULL); return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 81dbef6947f55..4653f608355cc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -121,7 +121,7 @@ struct iwl_mvm_time_event_data { * if the te is in the time event list or not (when id == TE_MAX) */ u32 id; - u8 link_id; + s8 link_id; }; /* Power management */ @@ -1769,6 +1769,8 @@ int iwl_mvm_load_d3_fw(struct iwl_mvm *mvm); int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm); +void iwl_mvm_mac_init_mvmvif(struct iwl_mvm *mvm, struct iwl_mvm_vif *mvmvif); + /* * FW notifications / CMD responses handlers * Convention: iwl_mvm_rx_ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c index 2ecd32bed752f..045c862a8fc4f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c @@ -132,14 +132,18 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm) if (ret) return ERR_PTR(ret); - if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != resp_size)) + if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != + resp_size)) { + iwl_free_resp(&cmd); return ERR_PTR(-EIO); + } resp = kmemdup(cmd.resp_pkt->data, resp_size, GFP_KERNEL); + iwl_free_resp(&cmd); + if (!resp) return ERR_PTR(-ENOMEM); - iwl_free_resp(&cmd); return resp; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h index 376b23b409dca..6cd4ec4d8f344 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h @@ -122,13 +122,8 @@ enum { #define LINK_QUAL_AGG_FRAME_LIMIT_DEF (63) #define LINK_QUAL_AGG_FRAME_LIMIT_MAX (63) -/* - * FIXME - various places in firmware API still use u8, - * e.g. LQ command and SCD config command. - * This should be 256 instead. - */ -#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF (255) -#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX (255) +#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF (64) +#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX (64) #define LINK_QUAL_AGG_FRAME_LIMIT_MIN (0) #define LQ_SIZE 2 /* 2 mode tables: "Active" and "Search" */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index af15d470c69bd..fe09622d36e87 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -236,21 +236,13 @@ static void iwl_mvm_add_rtap_sniffer_config(struct iwl_mvm *mvm, static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm, struct napi_struct *napi, struct sk_buff *skb, int queue, - struct ieee80211_sta *sta, - struct ieee80211_link_sta *link_sta) + struct ieee80211_sta *sta) { if (unlikely(iwl_mvm_check_pn(mvm, skb, queue, sta))) { kfree_skb(skb); return; } - if (sta && sta->valid_links && link_sta) { - struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); - - rx_status->link_valid = 1; - rx_status->link_id = link_sta->link_id; - } - ieee80211_rx_napi(mvm->hw, sta, skb, napi); } @@ -282,6 +274,7 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, u32 status, struct ieee80211_rx_status *stats) { + struct wireless_dev *wdev; struct iwl_mvm_sta *mvmsta; struct iwl_mvm_vif *mvmvif; u8 keyid; @@ -303,9 +296,15 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, if (!ieee80211_is_beacon(hdr->frame_control)) return 0; + if (!sta) + return -1; + + mvmsta = iwl_mvm_sta_from_mac80211(sta); + mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif); + /* key mismatch - will also report !MIC_OK but we shouldn't count it */ if (!(status & IWL_RX_MPDU_STATUS_KEY_VALID)) - return -1; + goto report; /* good cases */ if (likely(status & IWL_RX_MPDU_STATUS_MIC_OK && @@ -314,13 +313,6 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, return 0; } - if (!sta) - return -1; - - mvmsta = iwl_mvm_sta_from_mac80211(sta); - - mvmvif = iwl_mvm_vif_from_mac80211(mvmsta->vif); - /* * both keys will have the same cipher and MIC length, use * whichever one is available @@ -329,11 +321,11 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, if (!key) { key = rcu_dereference(mvmvif->bcn_prot.keys[1]); if (!key) - return -1; + goto report; } if (len < key->icv_len + IEEE80211_GMAC_PN_LEN + 2) - return -1; + goto report; /* get the real key ID */ keyid = frame[len - key->icv_len - IEEE80211_GMAC_PN_LEN - 2]; @@ -347,7 +339,7 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, return -1; key = rcu_dereference(mvmvif->bcn_prot.keys[keyid - 6]); if (!key) - return -1; + goto report; } /* Report status to mac80211 */ @@ -355,6 +347,10 @@ static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, ieee80211_key_mic_failure(key); else if (status & IWL_RX_MPDU_STATUS_REPLAY_ERROR) ieee80211_key_replay(key); +report: + wdev = ieee80211_vif_to_wdev(mvmsta->vif); + if (wdev->netdev) + cfg80211_rx_unprot_mlme_mgmt(wdev->netdev, (void *)hdr, len); return -1; } @@ -583,7 +579,7 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm, while ((skb = __skb_dequeue(skb_list))) { iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, reorder_buf->queue, - sta, NULL /* FIXME */); + sta); reorder_buf->num_stored--; } } @@ -2210,6 +2206,11 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, if (IS_ERR(sta)) sta = NULL; link_sta = rcu_dereference(mvm->fw_id_to_link_sta[id]); + + if (sta && sta->valid_links && link_sta) { + rx_status->link_valid = 1; + rx_status->link_id = link_sta->link_id; + } } } else if (!is_multicast_ether_addr(hdr->addr2)) { /* @@ -2353,8 +2354,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, !(desc->amsdu_info & IWL_RX_MPDU_AMSDU_LAST_SUBFRAME)) rx_status->flag |= RX_FLAG_AMSDU_MORE; - iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta, - link_sta); + iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta); } out: rcu_read_unlock(); @@ -2457,8 +2457,11 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, * * We mark it as mac header, for upper layers to know where * all radio tap header ends. + * + * Since data doesn't move data while putting data on skb and that is + * the only way we use, data + len is the next place that hdr would be put */ - skb_reset_mac_header(skb); + skb_set_mac_header(skb, skb->len); /* * Override the nss from the rx_vec since the rate_n_flags has diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 7b6f1cdca067e..786eba383c101 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1305,7 +1305,7 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm, if (IWL_MVM_ADWELL_MAX_BUDGET) cmd->v7.adwell_max_budget = cpu_to_le16(IWL_MVM_ADWELL_MAX_BUDGET); - else if (params->ssids && params->ssids[0].ssid_len) + else if (params->n_ssids && params->ssids[0].ssid_len) cmd->v7.adwell_max_budget = cpu_to_le16(IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN); else @@ -1407,7 +1407,7 @@ iwl_mvm_scan_umac_dwell_v11(struct iwl_mvm *mvm, if (IWL_MVM_ADWELL_MAX_BUDGET) general_params->adwell_max_budget = cpu_to_le16(IWL_MVM_ADWELL_MAX_BUDGET); - else if (params->ssids && params->ssids[0].ssid_len) + else if (params->n_ssids && params->ssids[0].ssid_len) general_params->adwell_max_budget = cpu_to_le16(IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN); else @@ -2815,7 +2815,8 @@ static int iwl_mvm_build_scan_cmd(struct iwl_mvm *mvm, if (ver_handler->version != scan_ver) continue; - return ver_handler->handler(mvm, vif, params, type, uid); + err = ver_handler->handler(mvm, vif, params, type, uid); + return err ? : uid; } err = iwl_mvm_scan_umac(mvm, vif, params, type, uid); @@ -3172,8 +3173,13 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm, struct iwl_mvm_vif_link_info *link_info = scan_vif->link[mvm->scan_link_id]; - if (!WARN_ON(!link_info)) + /* It is possible that by the time the scan is complete the link + * was already removed and is not valid. + */ + if (link_info) memcpy(info.tsf_bssid, link_info->bssid, ETH_ALEN); + else + IWL_DEBUG_SCAN(mvm, "Scan link is no longer valid\n"); ieee80211_scan_completed(mvm->hw, &info); mvm->scan_vif = NULL; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 2e653a417d626..3d96a824dbd65 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -692,7 +692,7 @@ void iwl_mvm_protect_session(struct iwl_mvm *mvm, /* Determine whether mac or link id should be used, and validate the link id */ static int iwl_mvm_get_session_prot_id(struct iwl_mvm *mvm, struct ieee80211_vif *vif, - u32 link_id) + s8 link_id) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); int ver = iwl_fw_lookup_cmd_ver(mvm->fw, @@ -706,8 +706,7 @@ static int iwl_mvm_get_session_prot_id(struct iwl_mvm *mvm, "Invalid link ID for session protection: %u\n", link_id)) return -EINVAL; - if (WARN(ieee80211_vif_is_mld(vif) && - !(vif->active_links & BIT(link_id)), + if (WARN(!mvmvif->link[link_id]->active, "Session Protection on an inactive link: %u\n", link_id)) return -EINVAL; @@ -716,7 +715,7 @@ static int iwl_mvm_get_session_prot_id(struct iwl_mvm *mvm, static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm, struct ieee80211_vif *vif, - u32 id, u32 link_id) + u32 id, s8 link_id) { int mac_link_id = iwl_mvm_get_session_prot_id(mvm, vif, link_id); struct iwl_mvm_session_prot_cmd cmd = { @@ -745,7 +744,7 @@ static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif = te_data->vif; struct iwl_mvm_vif *mvmvif; enum nl80211_iftype iftype; - unsigned int link_id; + s8 link_id; if (!vif) return false; @@ -899,9 +898,8 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_mvm_session_prot_notif *notif = (void *)pkt->data; unsigned int ver = - iwl_fw_lookup_cmd_ver(mvm->fw, - WIDE_ID(MAC_CONF_GROUP, - SESSION_PROTECTION_CMD), 2); + iwl_fw_lookup_notif_ver(mvm->fw, MAC_CONF_GROUP, + SESSION_PROTECTION_NOTIF, 2); int id = le32_to_cpu(notif->mac_link_id); struct ieee80211_vif *vif; struct iwl_mvm_vif *mvmvif; @@ -1297,7 +1295,7 @@ void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, struct iwl_mvm_time_event_data *te_data = &mvmvif->time_event_data; const u16 notif[] = { WIDE_ID(MAC_CONF_GROUP, SESSION_PROTECTION_NOTIF) }; struct iwl_notification_wait wait_notif; - int mac_link_id = iwl_mvm_get_session_prot_id(mvm, vif, link_id); + int mac_link_id = iwl_mvm_get_session_prot_id(mvm, vif, (s8)link_id); struct iwl_mvm_session_prot_cmd cmd = { .id_and_color = cpu_to_le32(mac_link_id), .action = cpu_to_le32(FW_CTXT_ACTION_ADD), diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 461f26d9214e4..930742e75c02a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2023 Intel Corporation + * Copyright (C) 2012-2014, 2018-2024 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -1636,12 +1636,18 @@ static void iwl_mvm_tx_status_check_trigger(struct iwl_mvm *mvm, * of the batch. This is why the SSN of the SCD is written at the end of the * whole struct at a variable offset. This function knows how to cope with the * variable offset and returns the SSN of the SCD. + * + * For 22000-series and lower, this is just 12 bits. For later, 16 bits. */ static inline u32 iwl_mvm_get_scd_ssn(struct iwl_mvm *mvm, struct iwl_mvm_tx_resp *tx_resp) { - return le32_to_cpup((__le32 *)iwl_mvm_get_agg_status(mvm, tx_resp) + - tx_resp->frame_count) & 0xfff; + u32 val = le32_to_cpup((__le32 *)iwl_mvm_get_agg_status(mvm, tx_resp) + + tx_resp->frame_count); + + if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) + return val & 0xFFFF; + return val & 0xFFF; } static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 2c9b98c8184b5..a135faaaae8ac 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2005-2014, 2018-2023 Intel Corporation + * Copyright (C) 2005-2014, 2018-2024 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -210,6 +210,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x088E, 0x446A, iwl6035_2agn_sff_cfg)}, {IWL_PCI_DEVICE(0x088E, 0x4860, iwl6035_2agn_cfg)}, {IWL_PCI_DEVICE(0x088F, 0x5260, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088F, 0x526A, iwl6035_2agn_cfg)}, /* 105 Series */ {IWL_PCI_DEVICE(0x0894, 0x0022, iwl105_bgn_cfg)}, @@ -502,12 +503,16 @@ static const struct pci_device_id iwl_hw_card_ids[] = { /* Bz devices */ {IWL_PCI_DEVICE(0x2727, PCI_ANY_ID, iwl_bz_trans_cfg)}, + {IWL_PCI_DEVICE(0x272D, PCI_ANY_ID, iwl_bz_trans_cfg)}, {IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_bz_trans_cfg)}, {IWL_PCI_DEVICE(0xA840, PCI_ANY_ID, iwl_bz_trans_cfg)}, {IWL_PCI_DEVICE(0x7740, PCI_ANY_ID, iwl_bz_trans_cfg)}, /* Sc devices */ {IWL_PCI_DEVICE(0xE440, PCI_ANY_ID, iwl_sc_trans_cfg)}, + {IWL_PCI_DEVICE(0xE340, PCI_ANY_ID, iwl_sc_trans_cfg)}, + {IWL_PCI_DEVICE(0xD340, PCI_ANY_ID, iwl_sc_trans_cfg)}, + {IWL_PCI_DEVICE(0x6E70, PCI_ANY_ID, iwl_sc_trans_cfg)}, #endif /* CONFIG_IWLMVM */ {0} @@ -1115,6 +1120,16 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_cfg_sc, iwl_sc_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_sc2, iwl_sc2_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_sc2f, iwl_sc2f_name), #endif /* CONFIG_IWLMVM */ }; diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c index ca74b1b63cac1..0efa304904bd3 100644 --- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c @@ -1588,9 +1588,9 @@ void iwl_txq_reclaim(struct iwl_trans *trans, int txq_id, int ssn, return; tfd_num = iwl_txq_get_cmd_index(txq, ssn); - read_ptr = iwl_txq_get_cmd_index(txq, txq->read_ptr); spin_lock_bh(&txq->lock); + read_ptr = iwl_txq_get_cmd_index(txq, txq->read_ptr); if (!test_bit(txq_id, trans->txqs.queue_used)) { IWL_DEBUG_TX_QUEUES(trans, "Q %d inactive - ignoring idx %d\n", diff --git a/drivers/net/wireless/marvell/libertas/cmd.c b/drivers/net/wireless/marvell/libertas/cmd.c index 104d2b6dc9af6..5a525da434c28 100644 --- a/drivers/net/wireless/marvell/libertas/cmd.c +++ b/drivers/net/wireless/marvell/libertas/cmd.c @@ -1132,7 +1132,7 @@ int lbs_allocate_cmd_buffer(struct lbs_private *priv) if (!cmdarray[i].cmdbuf) { lbs_deb_host("ALLOC_CMD_BUF: ptempvirtualaddr is NULL\n"); ret = -1; - goto done; + goto free_cmd_array; } } @@ -1140,8 +1140,17 @@ int lbs_allocate_cmd_buffer(struct lbs_private *priv) init_waitqueue_head(&cmdarray[i].cmdwait_q); lbs_cleanup_and_insert_cmd(priv, &cmdarray[i]); } - ret = 0; + return 0; +free_cmd_array: + for (i = 0; i < LBS_NUM_CMD_BUFFERS; i++) { + if (cmdarray[i].cmdbuf) { + kfree(cmdarray[i].cmdbuf); + cmdarray[i].cmdbuf = NULL; + } + } + kfree(priv->cmd_array); + priv->cmd_array = NULL; done: return ret; } diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c index f9c9fec7c792a..d14a0f4c1b6d7 100644 --- a/drivers/net/wireless/marvell/mwifiex/debugfs.c +++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c @@ -970,9 +970,6 @@ mwifiex_dev_debugfs_init(struct mwifiex_private *priv) priv->dfs_dev_dir = debugfs_create_dir(priv->netdev->name, mwifiex_dfs_dir); - if (!priv->dfs_dev_dir) - return; - MWIFIEX_DFS_ADD_FILE(info); MWIFIEX_DFS_ADD_FILE(debug); MWIFIEX_DFS_ADD_FILE(getlog); diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h index 62f3c9a52a1d5..1630287d639ea 100644 --- a/drivers/net/wireless/marvell/mwifiex/fw.h +++ b/drivers/net/wireless/marvell/mwifiex/fw.h @@ -206,6 +206,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER { #define TLV_TYPE_CHANNEL_STATS (PROPRIETARY_TLV_BASE_ID + 198) #define TLV_BTCOEX_WL_AGGR_WINSIZE (PROPRIETARY_TLV_BASE_ID + 202) #define TLV_BTCOEX_WL_SCANTIME (PROPRIETARY_TLV_BASE_ID + 203) +#define TLV_TYPE_LED_CONTROL (PROPRIETARY_TLV_BASE_ID + 205) #define TLV_TYPE_BSS_MODE (PROPRIETARY_TLV_BASE_ID + 206) #define TLV_TYPE_RANDOM_MAC (PROPRIETARY_TLV_BASE_ID + 236) #define TLV_TYPE_CHAN_ATTR_CFG (PROPRIETARY_TLV_BASE_ID + 237) @@ -353,6 +354,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER { #define HostCmd_CMD_802_11_AD_HOC_JOIN 0x002c #define HostCmd_CMD_802_11_AD_HOC_STOP 0x0040 #define HostCmd_CMD_802_11_MAC_ADDRESS 0x004D +#define HostCmd_CMD_802_11_LED_CONTROL 0X004E #define HostCmd_CMD_802_11D_DOMAIN_INFO 0x005b #define HostCmd_CMD_802_11_KEY_MATERIAL 0x005e #define HostCmd_CMD_802_11_BG_SCAN_CONFIG 0x006b @@ -1191,6 +1193,16 @@ struct ieee_types_oper_mode_ntf { u8 oper_mode; } __packed; +struct mwifiex_led_param { + __le16 mode; + __le16 on; +} __packed; + +struct mwifiex_ie_types_led_param { + struct mwifiex_ie_types_header header; + struct mwifiex_led_param led_cfg; +} __packed; + struct host_cmd_ds_802_11_ad_hoc_start { u8 ssid[IEEE80211_MAX_SSID_LEN]; u8 bss_mode; @@ -1314,6 +1326,11 @@ struct host_cmd_ds_802_11_hs_cfg_enh { } params; } __packed; +struct host_cmd_ds_802_11_led_control { + __le16 action; + __le16 num_led; +} __packed; + enum SNMP_MIB_INDEX { OP_RATE_SET_I = 1, DTIM_PERIOD_I = 3, @@ -2371,6 +2388,7 @@ struct host_cmd_ds_command { struct host_cmd_sdio_sp_rx_aggr_cfg sdio_rx_aggr_cfg; struct host_cmd_ds_multi_chan_policy mc_policy; struct host_cmd_ds_robust_coex coex; + struct host_cmd_ds_802_11_led_control led_cfg; struct host_cmd_ds_wakeup_reason hs_wakeup_reason; struct host_cmd_ds_gtk_rekey_params rekey; struct host_cmd_ds_chan_region_cfg reg_cfg; diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c index d99127dc466ec..b35fefbd56cba 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.c +++ b/drivers/net/wireless/marvell/mwifiex/main.c @@ -752,8 +752,10 @@ static int mwifiex_init_hw_fw(struct mwifiex_adapter *adapter, static int mwifiex_open(struct net_device *dev) { - netif_carrier_off(dev); + struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev); + netif_carrier_off(dev); + mwifiex_set_led(priv->adapter, MWIFIEX_LED_ON); return 0; } @@ -784,6 +786,7 @@ mwifiex_close(struct net_device *dev) cfg80211_sched_scan_stopped(priv->wdev.wiphy, 0); } + mwifiex_set_led(priv->adapter, MWIFIEX_LED_OFF); return 0; } diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h index 318b42b1896f8..0f4cc5ac73179 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.h +++ b/drivers/net/wireless/marvell/mwifiex/main.h @@ -122,6 +122,10 @@ enum { #define PKT_TYPE_MGMT 0xE5 +#define MWIFIEX_LED_ON 1 +#define MWIFIEX_LED_OFF 0 +#define MWIFIEX_LED_MAX 3 + /* * Do not check for data_received for USB, as data_received * is handled in mwifiex_usb_recv for USB @@ -681,6 +685,7 @@ struct mwifiex_private { struct mwifiex_user_scan_chan hidden_chan[MWIFIEX_USER_SCAN_CHAN_MAX]; u8 assoc_resp_ht_param; bool ht_param_present; + bool is_edge_gateway; }; @@ -1476,6 +1481,7 @@ int mwifiex_wait_queue_complete(struct mwifiex_adapter *adapter, struct cmd_ctrl_node *cmd_queued); int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss, struct cfg80211_ssid *req_ssid); +int mwifiex_set_led(struct mwifiex_adapter *adapter, int on); int mwifiex_cancel_hs(struct mwifiex_private *priv, int cmd_type); int mwifiex_enable_hs(struct mwifiex_adapter *adapter); int mwifiex_disable_auto_ds(struct mwifiex_private *priv); diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c index 5f997becdbaa2..acf5252954a88 100644 --- a/drivers/net/wireless/marvell/mwifiex/pcie.c +++ b/drivers/net/wireless/marvell/mwifiex/pcie.c @@ -377,6 +377,8 @@ static int mwifiex_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct pcie_service_card *card; + struct mwifiex_private *priv; + struct pci_dev *pdev_host; int ret; pr_debug("info: vendor=0x%4.04X device=0x%4.04X rev=%d\n", @@ -418,6 +420,14 @@ static int mwifiex_pcie_probe(struct pci_dev *pdev, return -1; } + priv = mwifiex_get_priv(card->adapter, MWIFIEX_BSS_ROLE_STA); + pdev_host = pci_get_subsys(PCI_ANY_ID, PCI_ANY_ID, 0x1028, 0x0720, NULL); + if (!pdev_host) + pdev_host = pci_get_subsys(PCI_ANY_ID, PCI_ANY_ID, 0x1028, 0x0733, NULL); + if (pdev_host) { + priv->is_edge_gateway = true; + pci_dev_put(pdev_host); + } return 0; } diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c index e2800a831c8ed..4edc9ac513347 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c @@ -416,6 +416,31 @@ mwifiex_cmd_802_11_hs_cfg(struct mwifiex_private *priv, return 0; } +static int mwifiex_cmd_802_11_led_cfg(struct mwifiex_private *priv, + struct host_cmd_ds_command *cmd, + u16 cmd_action, + struct mwifiex_led_param *ledcfg_param) +{ + struct host_cmd_ds_802_11_led_control *led_cfg = &cmd->params.led_cfg; + struct mwifiex_ie_types_led_param *led_tlv; + u8 *pos; + + cmd->command = cpu_to_le16(HostCmd_CMD_802_11_LED_CONTROL); + cmd->size = cpu_to_le16(S_DS_GEN); + le16_add_cpu(&cmd->size, sizeof(struct host_cmd_ds_802_11_led_control)); + + led_cfg->action = cpu_to_le16(cmd_action); + led_cfg->num_led = cpu_to_le16(MWIFIEX_LED_MAX); + + pos = (u8 *)led_cfg + sizeof(struct host_cmd_ds_802_11_led_control); + led_tlv = (void *)pos; + led_tlv->header.type = cpu_to_le16(TLV_TYPE_LED_CONTROL); + led_tlv->header.len = cpu_to_le16(sizeof(struct mwifiex_led_param)); + memcpy(&led_tlv->led_cfg, ledcfg_param, sizeof(struct mwifiex_led_param)); + le16_add_cpu(&cmd->size, sizeof(struct mwifiex_ie_types_led_param)); + return 0; +} + /* * This function prepares command to set/get MAC address. * @@ -1987,6 +2012,10 @@ int mwifiex_sta_prepare_cmd(struct mwifiex_private *priv, uint16_t cmd_no, ret = mwifiex_cmd_802_11_hs_cfg(priv, cmd_ptr, cmd_action, (struct mwifiex_hs_config_param *) data_buf); break; + case HostCmd_CMD_802_11_LED_CONTROL: + ret = mwifiex_cmd_802_11_led_cfg(priv, cmd_ptr, cmd_action, + data_buf); + break; case HostCmd_CMD_802_11_SCAN: ret = mwifiex_cmd_802_11_scan(cmd_ptr, data_buf); break; diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c index 7b69d27e0c0e5..cf0be4016c0ed 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c @@ -1422,6 +1422,8 @@ int mwifiex_process_sta_cmdresp(struct mwifiex_private *priv, u16 cmdresp_no, case HostCmd_CMD_ROBUST_COEX: ret = mwifiex_ret_robust_coex(priv, resp, data_buf); break; + case HostCmd_CMD_802_11_LED_CONTROL: + break; case HostCmd_CMD_GTK_REKEY_OFFLOAD_CFG: break; case HostCmd_CMD_CHAN_REGION_CFG: diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c index 32a27fad7b79a..74d44ab91e608 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c @@ -558,6 +558,24 @@ int mwifiex_enable_hs(struct mwifiex_adapter *adapter) } EXPORT_SYMBOL_GPL(mwifiex_enable_hs); +int mwifiex_set_led(struct mwifiex_adapter *adapter, int on) +{ + struct mwifiex_private *priv; + struct mwifiex_led_param ledcfg; + + priv = mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA); + if (!priv->is_edge_gateway) + return -ENODEV; + + memset(&ledcfg, 0, sizeof(struct mwifiex_led_param)); + ledcfg.on = cpu_to_le16(on); + + return mwifiex_send_cmd(priv, + HostCmd_CMD_802_11_LED_CONTROL, + HostCmd_ACT_GEN_SET, 0, + &ledcfg, true); +} + /* * IOCTL request handler to get BSS information. * diff --git a/drivers/net/wireless/marvell/mwl8k.c b/drivers/net/wireless/marvell/mwl8k.c index 13bcb123d1223..c0ecd769ada76 100644 --- a/drivers/net/wireless/marvell/mwl8k.c +++ b/drivers/net/wireless/marvell/mwl8k.c @@ -2718,7 +2718,7 @@ __mwl8k_cmd_mac_multicast_adr(struct ieee80211_hw *hw, int allmulti, cmd->action |= cpu_to_le16(MWL8K_ENABLE_RX_MULTICAST); cmd->numaddr = cpu_to_le16(mc_count); netdev_hw_addr_list_for_each(ha, mc_list) { - memcpy(cmd->addr[i], ha->addr, ETH_ALEN); + memcpy(cmd->addr[i++], ha->addr, ETH_ALEN); } } diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c index 7a2f5d38562b4..14304b0637158 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c @@ -4,6 +4,13 @@ #include "mac.h" #include "../dma.h" +static const u8 wmm_queue_map[] = { + [IEEE80211_AC_BK] = 0, + [IEEE80211_AC_BE] = 1, + [IEEE80211_AC_VI] = 2, + [IEEE80211_AC_VO] = 3, +}; + static void mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb) { @@ -22,10 +29,10 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb) struct ieee80211_sta *sta; struct mt7603_sta *msta; struct mt76_wcid *wcid; + u8 tid = 0, hwq = 0; void *priv; int idx; u32 val; - u8 tid = 0; if (skb->len < MT_TXD_SIZE + sizeof(struct ieee80211_hdr)) goto free; @@ -42,19 +49,36 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb) goto free; priv = msta = container_of(wcid, struct mt7603_sta, wcid); - val = le32_to_cpu(txd[0]); - val &= ~(MT_TXD0_P_IDX | MT_TXD0_Q_IDX); - val |= FIELD_PREP(MT_TXD0_Q_IDX, MT_TX_HW_QUEUE_MGMT); - txd[0] = cpu_to_le32(val); sta = container_of(priv, struct ieee80211_sta, drv_priv); hdr = (struct ieee80211_hdr *)&skb->data[MT_TXD_SIZE]; - if (ieee80211_is_data_qos(hdr->frame_control)) + + hwq = wmm_queue_map[IEEE80211_AC_BE]; + if (ieee80211_is_data_qos(hdr->frame_control)) { tid = *ieee80211_get_qos_ctl(hdr) & - IEEE80211_QOS_CTL_TAG1D_MASK; - skb_set_queue_mapping(skb, tid_to_ac[tid]); + IEEE80211_QOS_CTL_TAG1D_MASK; + u8 qid = tid_to_ac[tid]; + hwq = wmm_queue_map[qid]; + skb_set_queue_mapping(skb, qid); + } else if (ieee80211_is_data(hdr->frame_control)) { + skb_set_queue_mapping(skb, IEEE80211_AC_BE); + hwq = wmm_queue_map[IEEE80211_AC_BE]; + } else { + skb_pull(skb, MT_TXD_SIZE); + if (!ieee80211_is_bufferable_mmpdu(skb)) + goto free; + skb_push(skb, MT_TXD_SIZE); + skb_set_queue_mapping(skb, MT_TXQ_PSD); + hwq = MT_TX_HW_QUEUE_MGMT; + } + ieee80211_sta_set_buffered(sta, tid, true); + val = le32_to_cpu(txd[0]); + val &= ~(MT_TXD0_P_IDX | MT_TXD0_Q_IDX); + val |= FIELD_PREP(MT_TXD0_Q_IDX, hwq); + txd[0] = cpu_to_le32(val); + spin_lock_bh(&dev->ps_lock); __skb_queue_tail(&msta->psq, skb); if (skb_queue_len(&msta->psq) >= 64) { @@ -151,12 +175,6 @@ static int mt7603_poll_tx(struct napi_struct *napi, int budget) int mt7603_dma_init(struct mt7603_dev *dev) { - static const u8 wmm_queue_map[] = { - [IEEE80211_AC_BK] = 0, - [IEEE80211_AC_BE] = 1, - [IEEE80211_AC_VI] = 2, - [IEEE80211_AC_VO] = 3, - }; int ret; int i; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c index cf21d06257e53..dc8a77f0a1cc4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c @@ -1393,6 +1393,7 @@ void mt7603_pse_client_reset(struct mt7603_dev *dev) MT_CLIENT_RESET_TX_R_E_2_S); /* Start PSE client TX abort */ + mt76_set(dev, MT_WPDMA_GLO_CFG, MT_WPDMA_GLO_CFG_FORCE_TX_EOF); mt76_set(dev, addr, MT_CLIENT_RESET_TX_R_E_1); mt76_poll_msec(dev, addr, MT_CLIENT_RESET_TX_R_E_1_S, MT_CLIENT_RESET_TX_R_E_1_S, 500); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index 3a20ba0d24928..5809555a909d7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -66,7 +66,7 @@ int mt76_connac_mcu_init_download(struct mt76_dev *dev, u32 addr, u32 len, if ((!is_connac_v1(dev) && addr == MCU_PATCH_ADDRESS) || (is_mt7921(dev) && addr == 0x900000) || - (is_mt7925(dev) && addr == 0x900000) || + (is_mt7925(dev) && (addr == 0x900000 || addr == 0xe0002800)) || (is_mt7996(dev) && addr == 0x900000) || (is_mt7992(dev) && addr == 0x900000)) cmd = MCU_CMD(PATCH_START_REQ); @@ -2101,7 +2101,7 @@ mt76_connac_mcu_rate_txpower_band(struct mt76_phy *phy, int j, msg_len, num_ch; struct sk_buff *skb; - num_ch = i == batch_size - 1 ? n_chan % batch_len : batch_len; + num_ch = i == batch_size - 1 ? n_chan - i * batch_len : batch_len; msg_len = sizeof(tx_power_tlv) + num_ch * sizeof(sku_tlbv); skb = mt76_mcu_msg_alloc(dev, NULL, msg_len); if (!skb) { @@ -2524,6 +2524,7 @@ int mt76_connac_mcu_set_hif_suspend(struct mt76_dev *dev, bool suspend) __le16 tag; __le16 len; u8 suspend; + u8 pad[7]; } __packed hif_suspend; } req = { .hif_suspend = { diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h index ae6d0179727df..657a4d1f856b2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h @@ -808,6 +808,7 @@ enum { STA_REC_MLD = 0x20, STA_REC_EHT = 0x22, STA_REC_PN_INFO = 0x26, + STA_REC_KEY_V3 = 0x27, STA_REC_HDRT = 0x28, STA_REC_HDR_TRANS = 0x2B, STA_REC_MAX_NUM @@ -935,6 +936,9 @@ enum { PHY_TYPE_INDEX_NUM }; +#define HR_DSSS_ERP_BASIC_RATE GENMASK(3, 0) +#define OFDM_BASIC_RATE (BIT(6) | BIT(8) | BIT(10)) + #define PHY_TYPE_BIT_HR_DSSS BIT(PHY_TYPE_HR_DSSS_INDEX) #define PHY_TYPE_BIT_ERP BIT(PHY_TYPE_ERP_INDEX) #define PHY_TYPE_BIT_OFDM BIT(PHY_TYPE_OFDM_INDEX) diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c index 6c3696c8c7002..450f4d221184b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c @@ -1049,6 +1049,7 @@ static ssize_t mt7915_rate_txpower_set(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { + int i, ret, pwr, pwr160 = 0, pwr80 = 0, pwr40 = 0, pwr20 = 0; struct mt7915_phy *phy = file->private_data; struct mt7915_dev *dev = phy->dev; struct mt76_phy *mphy = phy->mt76; @@ -1057,7 +1058,6 @@ mt7915_rate_txpower_set(struct file *file, const char __user *user_buf, .band_idx = phy->mt76->band_idx, }; char buf[100]; - int i, ret, pwr160 = 0, pwr80 = 0, pwr40 = 0, pwr20 = 0; enum mac80211_rx_encoding mode; u32 offs = 0, len = 0; @@ -1130,8 +1130,8 @@ mt7915_rate_txpower_set(struct file *file, const char __user *user_buf, if (ret) goto out; - mphy->txpower_cur = max(mphy->txpower_cur, - max(pwr160, max(pwr80, max(pwr40, pwr20)))); + pwr = max3(pwr80, pwr40, pwr20); + mphy->txpower_cur = max3(mphy->txpower_cur, pwr160, pwr); out: mutex_unlock(&dev->mt76.mutex); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c index 3039f53e22454..dceb505987b19 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c @@ -490,6 +490,11 @@ static u32 __mt7915_reg_addr(struct mt7915_dev *dev, u32 addr) return dev->reg.map[i].maps + ofs; } + return 0; +} + +static u32 __mt7915_reg_remap_addr(struct mt7915_dev *dev, u32 addr) +{ if ((addr >= MT_INFRA_BASE && addr < MT_WFSYS0_PHY_START) || (addr >= MT_WFSYS0_PHY_START && addr < MT_WFSYS1_PHY_START) || (addr >= MT_WFSYS1_PHY_START && addr <= MT_WFSYS1_PHY_END)) @@ -514,15 +519,30 @@ void mt7915_memcpy_fromio(struct mt7915_dev *dev, void *buf, u32 offset, { u32 addr = __mt7915_reg_addr(dev, offset); - memcpy_fromio(buf, dev->mt76.mmio.regs + addr, len); + if (addr) { + memcpy_fromio(buf, dev->mt76.mmio.regs + addr, len); + return; + } + + spin_lock_bh(&dev->reg_lock); + memcpy_fromio(buf, dev->mt76.mmio.regs + + __mt7915_reg_remap_addr(dev, offset), len); + spin_unlock_bh(&dev->reg_lock); } static u32 mt7915_rr(struct mt76_dev *mdev, u32 offset) { struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); - u32 addr = __mt7915_reg_addr(dev, offset); + u32 addr = __mt7915_reg_addr(dev, offset), val; - return dev->bus_ops->rr(mdev, addr); + if (addr) + return dev->bus_ops->rr(mdev, addr); + + spin_lock_bh(&dev->reg_lock); + val = dev->bus_ops->rr(mdev, __mt7915_reg_remap_addr(dev, offset)); + spin_unlock_bh(&dev->reg_lock); + + return val; } static void mt7915_wr(struct mt76_dev *mdev, u32 offset, u32 val) @@ -530,7 +550,14 @@ static void mt7915_wr(struct mt76_dev *mdev, u32 offset, u32 val) struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); u32 addr = __mt7915_reg_addr(dev, offset); - dev->bus_ops->wr(mdev, addr, val); + if (addr) { + dev->bus_ops->wr(mdev, addr, val); + return; + } + + spin_lock_bh(&dev->reg_lock); + dev->bus_ops->wr(mdev, __mt7915_reg_remap_addr(dev, offset), val); + spin_unlock_bh(&dev->reg_lock); } static u32 mt7915_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) @@ -538,7 +565,14 @@ static u32 mt7915_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); u32 addr = __mt7915_reg_addr(dev, offset); - return dev->bus_ops->rmw(mdev, addr, mask, val); + if (addr) + return dev->bus_ops->rmw(mdev, addr, mask, val); + + spin_lock_bh(&dev->reg_lock); + val = dev->bus_ops->rmw(mdev, __mt7915_reg_remap_addr(dev, offset), mask, val); + spin_unlock_bh(&dev->reg_lock); + + return val; } #ifdef CONFIG_NET_MEDIATEK_SOC_WED @@ -707,6 +741,7 @@ static int mt7915_mmio_init(struct mt76_dev *mdev, dev = container_of(mdev, struct mt7915_dev, mt76); mt76_mmio_init(&dev->mt76, mem_base); + spin_lock_init(&dev->reg_lock); switch (device_id) { case 0x7915: diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h index 4727d9c7b11de..6e79bc65f5a51 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h @@ -287,6 +287,7 @@ struct mt7915_dev { struct list_head sta_rc_list; struct list_head twt_list; + spinlock_t reg_lock; u32 hw_pattern; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index 867e14f6b93a0..73e42ef429837 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -663,6 +663,7 @@ void mt7921_mac_reset_work(struct work_struct *work) int i, ret; dev_dbg(dev->mt76.dev, "chip reset\n"); + set_bit(MT76_RESET, &dev->mphy.state); dev->hw_full_reset = true; ieee80211_stop_queues(hw); @@ -691,6 +692,7 @@ void mt7921_mac_reset_work(struct work_struct *work) } dev->hw_full_reset = false; + clear_bit(MT76_RESET, &dev->mphy.state); pm->suspended = false; ieee80211_wake_queues(hw); ieee80211_iterate_active_interfaces(hw, diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index f5582477c7e4c..8b4ce32a2cd12 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -1272,7 +1272,7 @@ int __mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2, .mtcl_conf = mt792x_acpi_get_mtcl_conf(&dev->phy, alpha2), }; int ret, valid_cnt = 0; - u16 buf_len = 0; + u32 buf_len = 0; u8 *pos; if (!clc) @@ -1283,7 +1283,7 @@ int __mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2, if (mt76_find_power_limits_node(&dev->mt76)) req.cap |= CLC_CAP_DTS_EN; - buf_len = le16_to_cpu(clc->len) - sizeof(*clc); + buf_len = le32_to_cpu(clc->len) - sizeof(*clc); pos = clc->data; while (buf_len > 16) { struct mt7921_clc_rule *rule = (struct mt7921_clc_rule *)pos; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index dde26f3274783..82cf3ce90b52f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -387,6 +387,7 @@ static void mt7921_pci_remove(struct pci_dev *pdev) struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76); mt7921e_unregister_device(dev); + set_bit(MT76_REMOVED, &mdev->phy.state); devm_free_irq(&pdev->dev, pdev->irq, dev); mt76_free_device(&dev->mt76); pci_free_irq_vectors(pdev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c index c866144ff0613..031ba9aaa4e2f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c @@ -64,7 +64,6 @@ int mt7921e_mac_reset(struct mt792x_dev *dev) mt76_wr(dev, dev->irq_map->host_irq_enable, 0); mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0); - set_bit(MT76_RESET, &dev->mphy.state); set_bit(MT76_MCU_RESET, &dev->mphy.state); wake_up(&dev->mt76.mcu.wait); skb_queue_purge(&dev->mt76.mcu.res_q); @@ -115,7 +114,6 @@ int mt7921e_mac_reset(struct mt792x_dev *dev) err = __mt7921_start(&dev->phy); out: - clear_bit(MT76_RESET, &dev->mphy.state); local_bh_disable(); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c index 389eb0903807e..1f77cf71ca701 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c @@ -98,7 +98,6 @@ int mt7921s_mac_reset(struct mt792x_dev *dev) mt76_connac_free_pending_tx_skbs(&dev->pm, NULL); mt76_txq_schedule_all(&dev->mphy); mt76_worker_disable(&dev->mt76.tx_worker); - set_bit(MT76_RESET, &dev->mphy.state); set_bit(MT76_MCU_RESET, &dev->mphy.state); wake_up(&dev->mt76.mcu.wait); skb_queue_purge(&dev->mt76.mcu.res_q); @@ -135,7 +134,6 @@ int mt7921s_mac_reset(struct mt792x_dev *dev) err = __mt7921_start(&dev->phy); out: - clear_bit(MT76_RESET, &dev->mphy.state); mt76_worker_enable(&dev->mt76.tx_worker); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index 125a1be3cb64c..6179798a8845a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -359,6 +359,7 @@ mt7925_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) mvif->sta.wcid.phy_idx = mvif->mt76.band_idx; mvif->sta.wcid.hw_key_idx = -1; mvif->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET; + mvif->sta.vif = mvif; mt76_wcid_init(&mvif->sta.wcid); mt7925_mac_wtbl_update(dev, idx, @@ -526,7 +527,7 @@ static int mt7925_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, if (cmd == SET_KEY && !mvif->mt76.cipher) { struct mt792x_phy *phy = mt792x_hw_phy(hw); - mvif->mt76.cipher = mt76_connac_mcu_get_cipher(key->cipher); + mvif->mt76.cipher = mt7925_mcu_get_cipher(key->cipher); mt7925_mcu_add_bss_info(phy, mvif->mt76.ctx, vif, sta, true); } @@ -710,7 +711,7 @@ static void mt7925_bss_info_changed(struct ieee80211_hw *hw, if (slottime != phy->slottime) { phy->slottime = slottime; - mt792x_mac_set_timeing(phy); + mt7925_mcu_set_timing(phy, vif); } } @@ -1273,6 +1274,25 @@ mt7925_channel_switch_beacon(struct ieee80211_hw *hw, mt792x_mutex_release(dev); } +static int +mt7925_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id, u16 queue, + const struct ieee80211_tx_queue_params *params) +{ + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + static const u8 mq_to_aci[] = { + [IEEE80211_AC_VO] = 3, + [IEEE80211_AC_VI] = 2, + [IEEE80211_AC_BE] = 0, + [IEEE80211_AC_BK] = 1, + }; + + /* firmware uses access class index */ + mvif->queue_params[mq_to_aci[queue]] = *params; + + return 0; +} + static int mt7925_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf) @@ -1396,7 +1416,7 @@ const struct ieee80211_ops mt7925_ops = { .add_interface = mt7925_add_interface, .remove_interface = mt792x_remove_interface, .config = mt7925_config, - .conf_tx = mt792x_conf_tx, + .conf_tx = mt7925_conf_tx, .configure_filter = mt7925_configure_filter, .bss_info_changed = mt7925_bss_info_changed, .start_ap = mt7925_start_ap, diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index c5fd7116929b7..e1dd89a7a79ca 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -814,6 +814,7 @@ mt7925_mcu_sta_hdr_trans_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; struct sta_rec_hdr_trans *hdr_trans; struct mt76_wcid *wcid; struct tlv *tlv; @@ -827,7 +828,11 @@ mt7925_mcu_sta_hdr_trans_tlv(struct sk_buff *skb, else hdr_trans->from_ds = true; - wcid = (struct mt76_wcid *)sta->drv_priv; + if (sta) + wcid = (struct mt76_wcid *)sta->drv_priv; + else + wcid = &mvif->sta.wcid; + if (!wcid) return; @@ -895,7 +900,7 @@ int mt7925_mcu_set_tx(struct mt792x_dev *dev, struct ieee80211_vif *vif) e = (struct edca *)tlv; e->set = WMM_PARAM_SET; - e->queue = ac + mvif->mt76.wmm_idx * MT76_CONNAC_MAX_WMM_SETS; + e->queue = ac; e->aifs = q->aifs; e->txop = cpu_to_le16(q->txop); @@ -921,61 +926,67 @@ mt7925_mcu_sta_key_tlv(struct mt76_wcid *wcid, struct ieee80211_key_conf *key, enum set_key_cmd cmd) { + struct mt792x_sta *msta = container_of(wcid, struct mt792x_sta, wcid); struct sta_rec_sec_uni *sec; + struct mt792x_vif *mvif = msta->vif; + struct ieee80211_sta *sta; + struct ieee80211_vif *vif; struct tlv *tlv; - tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_KEY_V2, sizeof(*sec)); + sta = msta == &mvif->sta ? + NULL : + container_of((void *)msta, struct ieee80211_sta, drv_priv); + vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv); + + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_KEY_V3, sizeof(*sec)); sec = (struct sta_rec_sec_uni *)tlv; - sec->add = cmd; + sec->bss_idx = mvif->mt76.idx; + sec->is_authenticator = 0; + sec->mgmt_prot = 0; + sec->wlan_idx = (u8)wcid->idx; + + if (sta) { + sec->tx_key = 1; + sec->key_type = 1; + memcpy(sec->peer_addr, sta->addr, ETH_ALEN); + } else { + memcpy(sec->peer_addr, vif->bss_conf.bssid, ETH_ALEN); + } if (cmd == SET_KEY) { - struct sec_key_uni *sec_key; u8 cipher; - cipher = mt76_connac_mcu_get_cipher(key->cipher); - if (cipher == MCU_CIPHER_NONE) + sec->add = 1; + cipher = mt7925_mcu_get_cipher(key->cipher); + if (cipher == CONNAC3_CIPHER_NONE) return -EOPNOTSUPP; - sec_key = &sec->key[0]; - sec_key->cipher_len = sizeof(*sec_key); - - if (cipher == MCU_CIPHER_BIP_CMAC_128) { - sec_key->wlan_idx = cpu_to_le16(wcid->idx); - sec_key->cipher_id = MCU_CIPHER_AES_CCMP; - sec_key->key_id = sta_key_conf->keyidx; - sec_key->key_len = 16; - memcpy(sec_key->key, sta_key_conf->key, 16); - - sec_key = &sec->key[1]; - sec_key->wlan_idx = cpu_to_le16(wcid->idx); - sec_key->cipher_id = MCU_CIPHER_BIP_CMAC_128; - sec_key->cipher_len = sizeof(*sec_key); - sec_key->key_len = 16; - memcpy(sec_key->key, key->key, 16); - sec->n_cipher = 2; + if (cipher == CONNAC3_CIPHER_BIP_CMAC_128) { + sec->cipher_id = CONNAC3_CIPHER_BIP_CMAC_128; + sec->key_id = sta_key_conf->keyidx; + sec->key_len = 32; + memcpy(sec->key, sta_key_conf->key, 16); + memcpy(sec->key + 16, key->key, 16); } else { - sec_key->wlan_idx = cpu_to_le16(wcid->idx); - sec_key->cipher_id = cipher; - sec_key->key_id = key->keyidx; - sec_key->key_len = key->keylen; - memcpy(sec_key->key, key->key, key->keylen); + sec->cipher_id = cipher; + sec->key_id = key->keyidx; + sec->key_len = key->keylen; + memcpy(sec->key, key->key, key->keylen); - if (cipher == MCU_CIPHER_TKIP) { + if (cipher == CONNAC3_CIPHER_TKIP) { /* Rx/Tx MIC keys are swapped */ - memcpy(sec_key->key + 16, key->key + 24, 8); - memcpy(sec_key->key + 24, key->key + 16, 8); + memcpy(sec->key + 16, key->key + 24, 8); + memcpy(sec->key + 24, key->key + 16, 8); } /* store key_conf for BIP batch update */ - if (cipher == MCU_CIPHER_AES_CCMP) { + if (cipher == CONNAC3_CIPHER_AES_CCMP) { memcpy(sta_key_conf->key, key->key, key->keylen); sta_key_conf->keyidx = key->keyidx; } - - sec->n_cipher = 1; } } else { - sec->n_cipher = 0; + sec->add = 0; } return 0; @@ -1460,12 +1471,10 @@ mt7925_mcu_sta_phy_tlv(struct sk_buff *skb, struct tlv *tlv; u8 af = 0, mm = 0; - if (!sta->deflink.ht_cap.ht_supported && !sta->deflink.he_6ghz_capa.capa) - return; - tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_PHY, sizeof(*phy)); phy = (struct sta_rec_phy *)tlv; phy->phy_type = mt76_connac_get_phy_mode_v2(mvif->phy->mt76, vif, chandef->chan->band, sta); + phy->basic_rate = cpu_to_le16((u16)vif->bss_conf.basic_rates); if (sta->deflink.ht_cap.ht_supported) { af = sta->deflink.ht_cap.ampdu_factor; mm = sta->deflink.ht_cap.ampdu_density; @@ -1573,8 +1582,6 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, { struct mt76_vif *mvif = (struct mt76_vif *)info->vif->drv_priv; struct mt76_dev *dev = phy->dev; - struct wtbl_req_hdr *wtbl_hdr; - struct tlv *sta_wtbl; struct sk_buff *skb; skb = __mt76_connac_mcu_alloc_sta_req(dev, mvif, info->wcid, @@ -1598,30 +1605,11 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, mt7925_mcu_sta_state_v2_tlv(phy, skb, info->sta, info->vif, info->rcpi, info->state); - mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->sta); mt7925_mcu_sta_mld_tlv(skb, info->vif, info->sta); } - sta_wtbl = mt76_connac_mcu_add_tlv(skb, STA_REC_WTBL, - sizeof(struct tlv)); - - wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(dev, info->wcid, - WTBL_RESET_AND_SET, - sta_wtbl, &skb); - if (IS_ERR(wtbl_hdr)) - return PTR_ERR(wtbl_hdr); - - if (info->enable) { - mt76_connac_mcu_wtbl_generic_tlv(dev, skb, info->vif, - info->sta, sta_wtbl, - wtbl_hdr); - mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, info->vif, info->wcid, - sta_wtbl, wtbl_hdr); - if (info->sta) - mt76_connac_mcu_wtbl_ht_tlv(dev, skb, info->sta, - sta_wtbl, wtbl_hdr, - true, true); - } + if (info->enable) + mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->sta); return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true); } @@ -2049,9 +2037,9 @@ mt7925_mcu_bss_basic_tlv(struct sk_buff *skb, struct cfg80211_chan_def *chandef = ctx ? &ctx->def : &phy->chandef; enum nl80211_band band = chandef->chan->band; struct mt76_connac_bss_basic_tlv *basic_req; - u8 idx, basic_phy; struct tlv *tlv; int conn_type; + u8 idx; tlv = mt76_connac_mcu_add_tlv(skb, UNI_BSS_INFO_BASIC, sizeof(*basic_req)); basic_req = (struct mt76_connac_bss_basic_tlv *)tlv; @@ -2062,8 +2050,10 @@ mt7925_mcu_bss_basic_tlv(struct sk_buff *skb, basic_req->phymode_ext = mt7925_get_phy_mode_ext(phy, vif, band, sta); - basic_phy = mt76_connac_get_phy_mode_v2(phy, vif, band, sta); - basic_req->nonht_basic_phy = cpu_to_le16(basic_phy); + if (band == NL80211_BAND_2GHZ) + basic_req->nonht_basic_phy = cpu_to_le16(PHY_TYPE_ERP_INDEX); + else + basic_req->nonht_basic_phy = cpu_to_le16(PHY_TYPE_OFDM_INDEX); memcpy(basic_req->bssid, vif->bss_conf.bssid, ETH_ALEN); basic_req->phymode = mt76_connac_get_phy_mode(phy, vif, band, sta); @@ -2122,21 +2112,21 @@ mt7925_mcu_bss_sec_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) sec = (struct bss_sec_tlv *)tlv; switch (mvif->cipher) { - case MCU_CIPHER_GCMP_256: - case MCU_CIPHER_GCMP: + case CONNAC3_CIPHER_GCMP_256: + case CONNAC3_CIPHER_GCMP: sec->mode = MODE_WPA3_SAE; sec->status = 8; break; - case MCU_CIPHER_AES_CCMP: + case CONNAC3_CIPHER_AES_CCMP: sec->mode = MODE_WPA2_PSK; sec->status = 6; break; - case MCU_CIPHER_TKIP: + case CONNAC3_CIPHER_TKIP: sec->mode = MODE_WPA2_PSK; sec->status = 4; break; - case MCU_CIPHER_WEP104: - case MCU_CIPHER_WEP40: + case CONNAC3_CIPHER_WEP104: + case CONNAC3_CIPHER_WEP40: sec->mode = MODE_SHARED; sec->status = 0; break; @@ -2167,6 +2157,11 @@ mt7925_mcu_bss_bmc_tlv(struct sk_buff *skb, struct mt792x_phy *phy, bmc = (struct bss_rate_tlv *)tlv; + if (band == NL80211_BAND_2GHZ) + bmc->basic_rate = cpu_to_le16(HR_DSSS_ERP_BASIC_RATE); + else + bmc->basic_rate = cpu_to_le16(OFDM_BASIC_RATE); + bmc->short_preamble = (band == NL80211_BAND_2GHZ); bmc->bc_fixed_rate = idx; bmc->mc_fixed_rate = idx; @@ -2249,6 +2244,38 @@ mt7925_mcu_bss_color_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, vif->bss_conf.he_bss_color.color : 0; } +static void +mt7925_mcu_bss_ifs_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) +{ + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + struct mt792x_phy *phy = mvif->phy; + struct bss_ifs_time_tlv *ifs_time; + struct tlv *tlv; + + tlv = mt76_connac_mcu_add_tlv(skb, UNI_BSS_INFO_IFS_TIME, sizeof(*ifs_time)); + ifs_time = (struct bss_ifs_time_tlv *)tlv; + ifs_time->slot_valid = true; + ifs_time->slot_time = cpu_to_le16(phy->slottime); +} + +int mt7925_mcu_set_timing(struct mt792x_phy *phy, + struct ieee80211_vif *vif) +{ + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + struct mt792x_dev *dev = phy->dev; + struct sk_buff *skb; + + skb = __mt7925_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, + MT7925_BSS_UPDATE_MAX_SIZE); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + mt7925_mcu_bss_ifs_tlv(skb, vif); + + return mt76_mcu_skb_send_msg(&dev->mt76, skb, + MCU_UNI_CMD(BSS_INFO_UPDATE), true); +} + int mt7925_mcu_add_bss_info(struct mt792x_phy *phy, struct ieee80211_chanctx_conf *ctx, struct ieee80211_vif *vif, @@ -2273,6 +2300,7 @@ int mt7925_mcu_add_bss_info(struct mt792x_phy *phy, mt7925_mcu_bss_bmc_tlv(skb, phy, ctx, vif, sta); mt7925_mcu_bss_qos_tlv(skb, vif); mt7925_mcu_bss_mld_tlv(skb, vif, sta); + mt7925_mcu_bss_ifs_tlv(skb, vif); if (vif->bss_conf.he_support) { mt7925_mcu_bss_he_tlv(skb, vif, phy); @@ -2845,12 +2873,16 @@ int mt7925_mcu_fill_message(struct mt76_dev *mdev, struct sk_buff *skb, if (cmd & __MCU_CMD_FIELD_UNI) { uni_txd = (struct mt76_connac2_mcu_uni_txd *)txd; uni_txd->len = cpu_to_le16(skb->len - sizeof(uni_txd->txd)); - uni_txd->option = MCU_CMD_UNI_EXT_ACK; uni_txd->cid = cpu_to_le16(mcu_cmd); uni_txd->s2d_index = MCU_S2D_H2N; uni_txd->pkt_type = MCU_PKT_ID; uni_txd->seq = seq; + if (cmd & __MCU_CMD_FIELD_QUERY) + uni_txd->option = MCU_CMD_UNI_QUERY_ACK; + else + uni_txd->option = MCU_CMD_UNI_EXT_ACK; + goto exit; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h index 3c41e21303b1f..1599338e06310 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h @@ -159,6 +159,20 @@ enum { UNI_EVENT_SCAN_DONE_NLO = 3, }; +enum connac3_mcu_cipher_type { + CONNAC3_CIPHER_NONE = 0, + CONNAC3_CIPHER_WEP40 = 1, + CONNAC3_CIPHER_TKIP = 2, + CONNAC3_CIPHER_AES_CCMP = 4, + CONNAC3_CIPHER_WEP104 = 5, + CONNAC3_CIPHER_BIP_CMAC_128 = 6, + CONNAC3_CIPHER_WEP128 = 7, + CONNAC3_CIPHER_WAPI = 8, + CONNAC3_CIPHER_CCMP_256 = 10, + CONNAC3_CIPHER_GCMP = 11, + CONNAC3_CIPHER_GCMP_256 = 12, +}; + struct mt7925_mcu_scan_chinfo_event { u8 nr_chan; u8 alpha2[3]; @@ -334,7 +348,8 @@ struct bss_req_hdr { struct bss_rate_tlv { __le16 tag; __le16 len; - u8 __rsv1[4]; + u8 __rsv1[2]; + __le16 basic_rate; __le16 bc_trans; __le16 mc_trans; u8 short_preamble; @@ -382,25 +397,22 @@ struct sta_rec_eht { u8 _rsv2[3]; } __packed; -struct sec_key_uni { - __le16 wlan_idx; - u8 mgmt_prot; - u8 cipher_id; - u8 cipher_len; - u8 key_id; - u8 key_len; - u8 need_resp; - u8 key[32]; -} __packed; - struct sta_rec_sec_uni { __le16 tag; __le16 len; u8 add; - u8 n_cipher; - u8 rsv[2]; - - struct sec_key_uni key[2]; + u8 tx_key; + u8 key_type; + u8 is_authenticator; + u8 peer_addr[6]; + u8 bss_idx; + u8 cipher_id; + u8 key_id; + u8 key_len; + u8 wlan_idx; + u8 mgmt_prot; + u8 key[32]; + u8 key_rsc[16]; } __packed; struct sta_rec_hdr_trans { @@ -428,6 +440,22 @@ struct sta_rec_mld { } __packed link[2]; } __packed; +struct bss_ifs_time_tlv { + __le16 tag; + __le16 len; + u8 slot_valid; + u8 sifs_valid; + u8 rifs_valid; + u8 eifs_valid; + __le16 slot_time; + __le16 sifs_time; + __le16 rifs_time; + __le16 eifs_time; + u8 eifs_cck_valid; + u8 rsv; + __le16 eifs_cck_time; +} __packed; + #define MT7925_STA_UPDATE_MAX_SIZE (sizeof(struct sta_req_hdr) + \ sizeof(struct sta_rec_basic) + \ sizeof(struct sta_rec_bf) + \ @@ -440,7 +468,7 @@ struct sta_rec_mld { sizeof(struct sta_rec_bfee) + \ sizeof(struct sta_rec_phy) + \ sizeof(struct sta_rec_ra) + \ - sizeof(struct sta_rec_sec) + \ + sizeof(struct sta_rec_sec_uni) + \ sizeof(struct sta_rec_ra_fixed) + \ sizeof(struct sta_rec_he_6g_capa) + \ sizeof(struct sta_rec_eht) + \ @@ -455,6 +483,7 @@ struct sta_rec_mld { sizeof(struct bss_mld_tlv) + \ sizeof(struct bss_info_uni_he) + \ sizeof(struct bss_info_uni_bss_color) + \ + sizeof(struct bss_ifs_time_tlv) + \ sizeof(struct tlv)) #define MT_CONNAC3_SKU_POWER_LIMIT 449 @@ -506,9 +535,36 @@ struct mt7925_wow_pattern_tlv { u8 offset; u8 mask[MT76_CONNAC_WOW_MASK_MAX_LEN]; u8 pattern[MT76_CONNAC_WOW_PATTEN_MAX_LEN]; - u8 rsv[4]; + u8 rsv[7]; } __packed; +static inline enum connac3_mcu_cipher_type +mt7925_mcu_get_cipher(int cipher) +{ + switch (cipher) { + case WLAN_CIPHER_SUITE_WEP40: + return CONNAC3_CIPHER_WEP40; + case WLAN_CIPHER_SUITE_WEP104: + return CONNAC3_CIPHER_WEP104; + case WLAN_CIPHER_SUITE_TKIP: + return CONNAC3_CIPHER_TKIP; + case WLAN_CIPHER_SUITE_AES_CMAC: + return CONNAC3_CIPHER_BIP_CMAC_128; + case WLAN_CIPHER_SUITE_CCMP: + return CONNAC3_CIPHER_AES_CCMP; + case WLAN_CIPHER_SUITE_CCMP_256: + return CONNAC3_CIPHER_CCMP_256; + case WLAN_CIPHER_SUITE_GCMP: + return CONNAC3_CIPHER_GCMP; + case WLAN_CIPHER_SUITE_GCMP_256: + return CONNAC3_CIPHER_GCMP_256; + case WLAN_CIPHER_SUITE_SMS4: + return CONNAC3_CIPHER_WAPI; + default: + return CONNAC3_CIPHER_NONE; + } +} + int mt7925_mcu_set_dbdc(struct mt76_phy *phy); int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_scan_request *scan_req); @@ -525,6 +581,8 @@ int mt7925_mcu_add_bss_info(struct mt792x_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta, int enable); +int mt7925_mcu_set_timing(struct mt792x_phy *phy, + struct ieee80211_vif *vif); int mt7925_mcu_set_deep_sleep(struct mt792x_dev *dev, bool enable); int mt7925_mcu_set_channel_domain(struct mt76_phy *phy); int mt7925_mcu_set_radio_en(struct mt792x_phy *phy, bool enable); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c index 1fd99a8565415..07b74d492ce15 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c @@ -386,6 +386,8 @@ static int mt7925_pci_probe(struct pci_dev *pdev, dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev); + mt76_rmw_field(dev, MT_HW_EMI_CTL, MT_HW_EMI_CTL_SLPPROT_EN, 1); + ret = mt792x_wfsys_reset(dev); if (ret) goto err_free_dev; @@ -425,6 +427,7 @@ static void mt7925_pci_remove(struct pci_dev *pdev) struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76); mt7925e_unregister_device(dev); + set_bit(MT76_REMOVED, &mdev->phy.state); devm_free_irq(&pdev->dev, pdev->irq, dev); mt76_free_device(&dev->mt76); pci_free_irq_vectors(pdev); diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c index e7afea87e82e2..8fee3d481df0d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c @@ -66,13 +66,15 @@ mt792x_acpi_read(struct mt792x_dev *dev, u8 *method, u8 **tbl, u32 *len) } /* MTCL : Country List Table for 6G band */ -static void +static int mt792x_asar_acpi_read_mtcl(struct mt792x_dev *dev, u8 **table, u8 *version) { - if (mt792x_acpi_read(dev, MT792x_ACPI_MTCL, table, NULL) < 0) - *version = 1; - else - *version = 2; + int ret; + + *version = ((ret = mt792x_acpi_read(dev, MT792x_ACPI_MTCL, table, NULL)) < 0) + ? 1 : 2; + + return ret; } /* MTDS : Dynamic SAR Power Table */ @@ -166,16 +168,16 @@ int mt792x_init_acpi_sar(struct mt792x_dev *dev) if (!asar) return -ENOMEM; - mt792x_asar_acpi_read_mtcl(dev, (u8 **)&asar->countrylist, &asar->ver); + ret = mt792x_asar_acpi_read_mtcl(dev, (u8 **)&asar->countrylist, &asar->ver); + if (ret) { + devm_kfree(dev->mt76.dev, asar->countrylist); + asar->countrylist = NULL; + } - /* MTDS is mandatory. Return error if table is invalid */ ret = mt792x_asar_acpi_read_mtds(dev, (u8 **)&asar->dyn, asar->ver); if (ret) { devm_kfree(dev->mt76.dev, asar->dyn); - devm_kfree(dev->mt76.dev, asar->countrylist); - devm_kfree(dev->mt76.dev, asar); - - return ret; + asar->dyn = NULL; } /* MTGS is optional */ @@ -290,7 +292,7 @@ int mt792x_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default) const struct cfg80211_sar_capa *capa = phy->mt76->hw->wiphy->sar_capa; int i; - if (!phy->acpisar) + if (!phy->acpisar || !((struct mt792x_acpi_sar *)phy->acpisar)->dyn) return 0; /* When ACPI SAR enabled in HW, we should apply rules for .frp diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c index c42101aa9e45e..9ac5161dfff8c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c @@ -354,6 +354,7 @@ static const char mt792x_gstrings_stats[][ETH_GSTRING_LEN] = { "v_tx_bw_40", "v_tx_bw_80", "v_tx_bw_160", + "v_tx_bw_320", "v_tx_mcs_0", "v_tx_mcs_1", "v_tx_mcs_2", diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c index 488326ce5ed4d..5cc2d59b774af 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c @@ -12,6 +12,8 @@ irqreturn_t mt792x_irq_handler(int irq, void *dev_instance) { struct mt792x_dev *dev = dev_instance; + if (test_bit(MT76_REMOVED, &dev->mt76.phy.state)) + return IRQ_NONE; mt76_wr(dev, dev->irq_map->host_irq_enable, 0); if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state)) @@ -123,14 +125,13 @@ static void mt792x_dma_prefetch(struct mt792x_dev *dev) int mt792x_dma_enable(struct mt792x_dev *dev) { - if (is_mt7925(&dev->mt76)) - mt76_rmw(dev, MT_UWFDMA0_GLO_CFG_EXT1, BIT(28), BIT(28)); - /* configure perfetch settings */ mt792x_dma_prefetch(dev); /* reset dma idx */ mt76_wr(dev, MT_WFDMA0_RST_DTX_PTR, ~0); + if (is_mt7925(&dev->mt76)) + mt76_wr(dev, MT_WFDMA0_RST_DRX_PTR, ~0); /* configure delay interrupt */ mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG0, 0); @@ -140,12 +141,20 @@ int mt792x_dma_enable(struct mt792x_dev *dev) MT_WFDMA0_GLO_CFG_FIFO_LITTLE_ENDIAN | MT_WFDMA0_GLO_CFG_CLK_GAT_DIS | MT_WFDMA0_GLO_CFG_OMIT_TX_INFO | + FIELD_PREP(MT_WFDMA0_GLO_CFG_DMA_SIZE, 3) | + MT_WFDMA0_GLO_CFG_FIFO_DIS_CHECK | + MT_WFDMA0_GLO_CFG_RX_WB_DDONE | MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN | MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2); mt76_set(dev, MT_WFDMA0_GLO_CFG, MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN); + if (is_mt7925(&dev->mt76)) { + mt76_rmw(dev, MT_UWFDMA0_GLO_CFG_EXT1, BIT(28), BIT(28)); + mt76_set(dev, MT_WFDMA0_INT_RX_PRI, 0x0F00); + mt76_set(dev, MT_WFDMA0_INT_TX_PRI, 0x7F00); + } mt76_set(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT); /* enable interrupts for TX/RX rings */ diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h index a99af23e4b564..458cfd0260b13 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h @@ -292,9 +292,12 @@ #define MT_WFDMA0_GLO_CFG_TX_DMA_BUSY BIT(1) #define MT_WFDMA0_GLO_CFG_RX_DMA_EN BIT(2) #define MT_WFDMA0_GLO_CFG_RX_DMA_BUSY BIT(3) +#define MT_WFDMA0_GLO_CFG_DMA_SIZE GENMASK(5, 4) #define MT_WFDMA0_GLO_CFG_TX_WB_DDONE BIT(6) #define MT_WFDMA0_GLO_CFG_FW_DWLD_BYPASS_DMASHDL BIT(9) +#define MT_WFDMA0_GLO_CFG_FIFO_DIS_CHECK BIT(11) #define MT_WFDMA0_GLO_CFG_FIFO_LITTLE_ENDIAN BIT(12) +#define MT_WFDMA0_GLO_CFG_RX_WB_DDONE BIT(13) #define MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN BIT(15) #define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2 BIT(21) #define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO BIT(27) @@ -322,6 +325,8 @@ #define MT_WFDMA0_RST_DTX_PTR MT_WFDMA0(0x20c) #define MT_WFDMA0_RST_DRX_PTR MT_WFDMA0(0x280) +#define MT_WFDMA0_INT_RX_PRI MT_WFDMA0(0x298) +#define MT_WFDMA0_INT_TX_PRI MT_WFDMA0(0x29c) #define MT_WFDMA0_GLO_CFG_EXT0 MT_WFDMA0(0x2b0) #define MT_WFDMA0_CSR_TX_DMASHDL_ENABLE BIT(6) #define MT_WFDMA0_PRI_DLY_INT_CFG0 MT_WFDMA0(0x2f0) @@ -389,6 +394,9 @@ #define MT_HW_CHIPID 0x70010200 #define MT_HW_REV 0x70010204 +#define MT_HW_EMI_CTL 0x18011100 +#define MT_HW_EMI_CTL_SLPPROT_EN BIT(1) + #define MT_PCIE_MAC_BASE 0x10000 #define MT_PCIE_MAC(ofs) (MT_PCIE_MAC_BASE + (ofs)) #define MT_PCIE_MAC_INT_ENABLE MT_PCIE_MAC(0x188) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c index 483ad81b6eec6..fe37110e66875 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c @@ -237,7 +237,8 @@ void mt7996_dma_start(struct mt7996_dev *dev, bool reset, bool wed_reset) MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN | MT_WFDMA0_GLO_CFG_OMIT_TX_INFO | - MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2); + MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2 | + MT_WFDMA0_GLO_CFG_EXT_EN); if (dev->hif2) mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c index 0cf0d1fe420a2..a929c657be1c4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c @@ -493,7 +493,7 @@ static void mt7996_mac_init_basic_rates(struct mt7996_dev *dev) void mt7996_mac_init(struct mt7996_dev *dev) { -#define HIF_TXD_V2_1 4 +#define HIF_TXD_V2_1 0x21 int i; mt76_clear(dev, MT_MDP_DCR2, MT_MDP_DCR2_RX_TRANS_SHORT); @@ -1012,11 +1012,12 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy, /* the maximum cap is 4 x 3, (Nr, Nc) = (3, 2) */ elem->phy_cap_info[7] |= min_t(int, sts - 1, 2) << 3; - if (vif != NL80211_IFTYPE_AP) + if (!(vif == NL80211_IFTYPE_AP || vif == NL80211_IFTYPE_STATION)) return; elem->phy_cap_info[3] |= IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER; - elem->phy_cap_info[4] |= IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER; + if (vif == NL80211_IFTYPE_AP) + elem->phy_cap_info[4] |= IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER; c = FIELD_PREP(IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK, sts - 1) | diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 53258488d49f3..0384fb059ddfc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -732,6 +732,9 @@ mt7996_mac_write_txwi_8023(struct mt7996_dev *dev, __le32 *txwi, FIELD_PREP(MT_TXD2_SUB_TYPE, fc_stype); txwi[2] |= cpu_to_le32(val); + + if (wcid->amsdu) + txwi[3] |= cpu_to_le32(MT_TXD3_HW_AMSDU); } static void @@ -862,8 +865,6 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, val |= MT_TXD3_PROTECT_FRAME; if (info->flags & IEEE80211_TX_CTL_NO_ACK) val |= MT_TXD3_NO_ACK; - if (wcid->amsdu) - val |= MT_TXD3_HW_AMSDU; txwi[3] = cpu_to_le32(val); txwi[4] = 0; @@ -1188,25 +1189,28 @@ mt7996_mac_add_txs_skb(struct mt7996_dev *dev, struct mt76_wcid *wcid, struct ieee80211_tx_info *info; struct sk_buff_head list; struct rate_info rate = {}; - struct sk_buff *skb; + struct sk_buff *skb = NULL; bool cck = false; u32 txrate, txs, mode, stbc; txs = le32_to_cpu(txs_data[0]); mt76_tx_status_lock(mdev, &list); - skb = mt76_tx_status_skb_get(mdev, wcid, pid, &list); - if (skb) { - info = IEEE80211_SKB_CB(skb); - if (!(txs & MT_TXS0_ACK_ERROR_MASK)) - info->flags |= IEEE80211_TX_STAT_ACK; + /* only report MPDU TXS */ + if (le32_get_bits(txs_data[0], MT_TXS0_TXS_FORMAT) == 0) { + skb = mt76_tx_status_skb_get(mdev, wcid, pid, &list); + if (skb) { + info = IEEE80211_SKB_CB(skb); + if (!(txs & MT_TXS0_ACK_ERROR_MASK)) + info->flags |= IEEE80211_TX_STAT_ACK; - info->status.ampdu_len = 1; - info->status.ampdu_ack_len = - !!(info->flags & IEEE80211_TX_STAT_ACK); + info->status.ampdu_len = 1; + info->status.ampdu_ack_len = + !!(info->flags & IEEE80211_TX_STAT_ACK); - info->status.rates[0].idx = -1; + info->status.rates[0].idx = -1; + } } if (mtk_wed_device_active(&dev->mt76.mmio.wed) && wcid->sta) { @@ -2527,6 +2531,34 @@ static int mt7996_mac_check_twt_req(struct ieee80211_twt_setup *twt) return 0; } +static bool +mt7996_mac_twt_param_equal(struct mt7996_sta *msta, + struct ieee80211_twt_params *twt_agrt) +{ + u16 type = le16_to_cpu(twt_agrt->req_type); + u8 exp; + int i; + + exp = FIELD_GET(IEEE80211_TWT_REQTYPE_WAKE_INT_EXP, type); + for (i = 0; i < MT7996_MAX_STA_TWT_AGRT; i++) { + struct mt7996_twt_flow *f; + + if (!(msta->twt.flowid_mask & BIT(i))) + continue; + + f = &msta->twt.flow[i]; + if (f->duration == twt_agrt->min_twt_dur && + f->mantissa == twt_agrt->mantissa && + f->exp == exp && + f->protection == !!(type & IEEE80211_TWT_REQTYPE_PROTECTION) && + f->flowtype == !!(type & IEEE80211_TWT_REQTYPE_FLOWTYPE) && + f->trigger == !!(type & IEEE80211_TWT_REQTYPE_TRIGGER)) + return true; + } + + return false; +} + void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct ieee80211_twt_setup *twt) @@ -2538,8 +2570,7 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw, enum ieee80211_twt_setup_cmd sta_setup_cmd; struct mt7996_dev *dev = mt7996_hw_dev(hw); struct mt7996_twt_flow *flow; - int flowid, table_id; - u8 exp; + u8 flowid, table_id, exp; if (mt7996_mac_check_twt_req(twt)) goto out; @@ -2552,9 +2583,19 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw, if (hweight8(msta->twt.flowid_mask) == ARRAY_SIZE(msta->twt.flow)) goto unlock; + if (twt_agrt->min_twt_dur < MT7996_MIN_TWT_DUR) { + setup_cmd = TWT_SETUP_CMD_DICTATE; + twt_agrt->min_twt_dur = MT7996_MIN_TWT_DUR; + goto unlock; + } + + if (mt7996_mac_twt_param_equal(msta, twt_agrt)) + goto unlock; + flowid = ffs(~msta->twt.flowid_mask) - 1; - le16p_replace_bits(&twt_agrt->req_type, flowid, - IEEE80211_TWT_REQTYPE_FLOWID); + twt_agrt->req_type &= ~cpu_to_le16(IEEE80211_TWT_REQTYPE_FLOWID); + twt_agrt->req_type |= le16_encode_bits(flowid, + IEEE80211_TWT_REQTYPE_FLOWID); table_id = ffs(~dev->twt.table_mask) - 1; exp = FIELD_GET(IEEE80211_TWT_REQTYPE_WAKE_INT_EXP, req_type); @@ -2601,10 +2642,10 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw, unlock: mutex_unlock(&dev->mt76.mutex); out: - le16p_replace_bits(&twt_agrt->req_type, setup_cmd, - IEEE80211_TWT_REQTYPE_SETUP_CMD); - twt->control = (twt->control & IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT) | - (twt->control & IEEE80211_TWT_CONTROL_RX_DISABLED); + twt_agrt->req_type &= ~cpu_to_le16(IEEE80211_TWT_REQTYPE_SETUP_CMD); + twt_agrt->req_type |= + le16_encode_bits(setup_cmd, IEEE80211_TWT_REQTYPE_SETUP_CMD); + twt->control = twt->control & IEEE80211_TWT_CONTROL_RX_DISABLED; } void mt7996_mac_twt_teardown_flow(struct mt7996_dev *dev, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index 699be57309c2e..10d13fa45c5a1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -1240,6 +1240,9 @@ mt7996_mcu_sta_he_6g_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) static void mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) { + struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; + struct ieee80211_vif *vif = container_of((void *)msta->vif, + struct ieee80211_vif, drv_priv); struct ieee80211_eht_mcs_nss_supp *mcs_map; struct ieee80211_eht_cap_elem_fixed *elem; struct sta_rec_eht *eht; @@ -1259,8 +1262,17 @@ mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) eht->phy_cap = cpu_to_le64(*(u64 *)elem->phy_cap_info); eht->phy_cap_ext = cpu_to_le64(elem->phy_cap_info[8]); - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_20) - memcpy(eht->mcs_map_bw20, &mcs_map->only_20mhz, sizeof(eht->mcs_map_bw20)); + if (vif->type != NL80211_IFTYPE_STATION && + (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] & + (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)) == 0) { + memcpy(eht->mcs_map_bw20, &mcs_map->only_20mhz, + sizeof(eht->mcs_map_bw20)); + return; + } + memcpy(eht->mcs_map_bw80, &mcs_map->bw._80, sizeof(eht->mcs_map_bw80)); memcpy(eht->mcs_map_bw160, &mcs_map->bw._160, sizeof(eht->mcs_map_bw160)); memcpy(eht->mcs_map_bw320, &mcs_map->bw._320, sizeof(eht->mcs_map_bw320)); @@ -3539,7 +3551,7 @@ int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset) u32 addr = le32_to_cpu(*(__le32 *)(skb->data + 12)); u8 *buf = (u8 *)dev->mt76.eeprom.data + addr; - skb_pull(skb, 64); + skb_pull(skb, 48); memcpy(buf, skb->data, MT7996_EEPROM_BLOCK_SIZE); } @@ -3721,6 +3733,7 @@ int mt7996_mcu_get_temperature(struct mt7996_phy *phy) } __packed * res; struct sk_buff *skb; int ret; + u32 temp; ret = mt76_mcu_send_and_get_msg(&phy->dev->mt76, MCU_WM_UNI_CMD(THERMAL), &req, sizeof(req), true, &skb); @@ -3728,8 +3741,10 @@ int mt7996_mcu_get_temperature(struct mt7996_phy *phy) return ret; res = (void *)skb->data; + temp = le32_to_cpu(res->temperature); + dev_kfree_skb(skb); - return le32_to_cpu(res->temperature); + return temp; } int mt7996_mcu_set_thermal_throttling(struct mt7996_phy *phy, u8 state) @@ -4456,7 +4471,7 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy) u8 band_idx; } __packed req = { .tag = cpu_to_le16(UNI_TXPOWER_POWER_LIMIT_TABLE_CTRL), - .len = cpu_to_le16(sizeof(req) + MT7996_SKU_RATE_NUM - 4), + .len = cpu_to_le16(sizeof(req) + MT7996_SKU_PATH_NUM - 4), .power_ctrl_id = UNI_TXPOWER_POWER_LIMIT_TABLE_CTRL, .power_limit_type = TX_POWER_LIMIT_TABLE_RATE, .band_idx = phy->mt76->band_idx, @@ -4471,7 +4486,7 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy) mphy->txpower_cur = tx_power; skb = mt76_mcu_msg_alloc(&dev->mt76, NULL, - sizeof(req) + MT7996_SKU_RATE_NUM); + sizeof(req) + MT7996_SKU_PATH_NUM); if (!skb) return -ENOMEM; @@ -4495,6 +4510,9 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy) /* eht */ skb_put_data(skb, &la.eht[0], sizeof(la.eht)); + /* padding */ + skb_put_zero(skb, MT7996_SKU_PATH_NUM - MT7996_SKU_RATE_NUM); + return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_WM_UNI_CMD(TXPOWER), true); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c index 9f2abfa273c9b..c93f82548beeb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c @@ -140,7 +140,6 @@ static u32 mt7996_reg_map_l1(struct mt7996_dev *dev, u32 addr) u32 offset = FIELD_GET(MT_HIF_REMAP_L1_OFFSET, addr); u32 base = FIELD_GET(MT_HIF_REMAP_L1_BASE, addr); - dev->reg_l1_backup = dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L1); dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L1, MT_HIF_REMAP_L1_MASK, FIELD_PREP(MT_HIF_REMAP_L1_MASK, base)); @@ -155,7 +154,6 @@ static u32 mt7996_reg_map_l2(struct mt7996_dev *dev, u32 addr) u32 offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET, addr); u32 base = FIELD_GET(MT_HIF_REMAP_L2_BASE, addr); - dev->reg_l2_backup = dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L2); dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L2, MT_HIF_REMAP_L2_MASK, FIELD_PREP(MT_HIF_REMAP_L2_MASK, base)); @@ -165,26 +163,10 @@ static u32 mt7996_reg_map_l2(struct mt7996_dev *dev, u32 addr) return MT_HIF_REMAP_BASE_L2 + offset; } -static void mt7996_reg_remap_restore(struct mt7996_dev *dev) -{ - /* remap to ori status */ - if (unlikely(dev->reg_l1_backup)) { - dev->bus_ops->wr(&dev->mt76, MT_HIF_REMAP_L1, dev->reg_l1_backup); - dev->reg_l1_backup = 0; - } - - if (dev->reg_l2_backup) { - dev->bus_ops->wr(&dev->mt76, MT_HIF_REMAP_L2, dev->reg_l2_backup); - dev->reg_l2_backup = 0; - } -} - static u32 __mt7996_reg_addr(struct mt7996_dev *dev, u32 addr) { int i; - mt7996_reg_remap_restore(dev); - if (addr < 0x100000) return addr; @@ -201,6 +183,11 @@ static u32 __mt7996_reg_addr(struct mt7996_dev *dev, u32 addr) return dev->reg.map[i].mapped + ofs; } + return 0; +} + +static u32 __mt7996_reg_remap_addr(struct mt7996_dev *dev, u32 addr) +{ if ((addr >= MT_INFRA_BASE && addr < MT_WFSYS0_PHY_START) || (addr >= MT_WFSYS0_PHY_START && addr < MT_WFSYS1_PHY_START) || (addr >= MT_WFSYS1_PHY_START && addr <= MT_WFSYS1_PHY_END)) @@ -225,28 +212,60 @@ void mt7996_memcpy_fromio(struct mt7996_dev *dev, void *buf, u32 offset, { u32 addr = __mt7996_reg_addr(dev, offset); - memcpy_fromio(buf, dev->mt76.mmio.regs + addr, len); + if (addr) { + memcpy_fromio(buf, dev->mt76.mmio.regs + addr, len); + return; + } + + spin_lock_bh(&dev->reg_lock); + memcpy_fromio(buf, dev->mt76.mmio.regs + + __mt7996_reg_remap_addr(dev, offset), len); + spin_unlock_bh(&dev->reg_lock); } static u32 mt7996_rr(struct mt76_dev *mdev, u32 offset) { struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); + u32 addr = __mt7996_reg_addr(dev, offset), val; + + if (addr) + return dev->bus_ops->rr(mdev, addr); - return dev->bus_ops->rr(mdev, __mt7996_reg_addr(dev, offset)); + spin_lock_bh(&dev->reg_lock); + val = dev->bus_ops->rr(mdev, __mt7996_reg_remap_addr(dev, offset)); + spin_unlock_bh(&dev->reg_lock); + + return val; } static void mt7996_wr(struct mt76_dev *mdev, u32 offset, u32 val) { struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); + u32 addr = __mt7996_reg_addr(dev, offset); - dev->bus_ops->wr(mdev, __mt7996_reg_addr(dev, offset), val); + if (addr) { + dev->bus_ops->wr(mdev, addr, val); + return; + } + + spin_lock_bh(&dev->reg_lock); + dev->bus_ops->wr(mdev, __mt7996_reg_remap_addr(dev, offset), val); + spin_unlock_bh(&dev->reg_lock); } static u32 mt7996_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) { struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); + u32 addr = __mt7996_reg_addr(dev, offset); + + if (addr) + return dev->bus_ops->rmw(mdev, addr, mask, val); + + spin_lock_bh(&dev->reg_lock); + val = dev->bus_ops->rmw(mdev, __mt7996_reg_remap_addr(dev, offset), mask, val); + spin_unlock_bh(&dev->reg_lock); - return dev->bus_ops->rmw(mdev, __mt7996_reg_addr(dev, offset), mask, val); + return val; } #ifdef CONFIG_NET_MEDIATEK_SOC_WED @@ -421,6 +440,7 @@ static int mt7996_mmio_init(struct mt76_dev *mdev, dev = container_of(mdev, struct mt7996_dev, mt76); mt76_mmio_init(&dev->mt76, mem_base); + spin_lock_init(&dev->reg_lock); switch (device_id) { case 0x7990: @@ -499,7 +519,7 @@ static void mt7996_irq_tasklet(struct tasklet_struct *t) struct mt7996_dev *dev = from_tasklet(dev, t, mt76.irq_tasklet); struct mtk_wed_device *wed = &dev->mt76.mmio.wed; struct mtk_wed_device *wed_hif2 = &dev->mt76.mmio.wed_hif2; - u32 i, intr, mask, intr1; + u32 i, intr, mask, intr1 = 0; if (dev->hif2 && mtk_wed_device_active(wed_hif2)) { mtk_wed_device_irq_set_mask(wed_hif2, 0); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h index bc73bcb47bf02..ddeb40d522c5a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h @@ -50,9 +50,11 @@ #define MT7996_CFEND_RATE_11B 0x03 /* 11B LP, 11M */ #define MT7996_SKU_RATE_NUM 417 +#define MT7996_SKU_PATH_NUM 494 #define MT7996_MAX_TWT_AGRT 16 #define MT7996_MAX_STA_TWT_AGRT 8 +#define MT7996_MIN_TWT_DUR 64 #define MT7996_MAX_QUEUE (__MT_RXQ_MAX + __MT_MCUQ_MAX + 3) /* NOTE: used to map mt76_rates. idx may change if firmware expands table */ @@ -320,12 +322,11 @@ struct mt7996_dev { struct rchan *relay_fwlog; struct { - u8 table_mask; + u16 table_mask; u8 n_agrt; } twt; - u32 reg_l1_backup; - u32 reg_l2_backup; + spinlock_t reg_lock; u8 wtbl_size_group; }; diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c index 3e88798df0178..a4ed00eebc483 100644 --- a/drivers/net/wireless/mediatek/mt76/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/sdio.c @@ -499,7 +499,8 @@ static void mt76s_tx_status_data(struct mt76_worker *worker) dev = container_of(sdio, struct mt76_dev, sdio); while (true) { - if (test_bit(MT76_REMOVED, &dev->phy.state)) + if (test_bit(MT76_RESET, &dev->phy.state) || + test_bit(MT76_REMOVED, &dev->phy.state)) break; if (!dev->drv->tx_status_data(dev, &update)) diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index ad2509d8c99a4..f03fd15c0c97a 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -1609,7 +1609,6 @@ static int del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev) cfg80211_unregister_netdevice(vif->ndev); vif->monitor_flag = 0; - wilc_set_operation_mode(vif, 0, 0, 0); mutex_lock(&wl->vif_mutex); list_del_rcu(&vif->list); wl->vif_num--; @@ -1804,15 +1803,24 @@ int wilc_cfg80211_init(struct wilc **wilc, struct device *dev, int io_type, INIT_LIST_HEAD(&wl->rxq_head.list); INIT_LIST_HEAD(&wl->vif_list); + wl->hif_workqueue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, + wiphy_name(wl->wiphy)); + if (!wl->hif_workqueue) { + ret = -ENOMEM; + goto free_cfg; + } vif = wilc_netdev_ifc_init(wl, "wlan%d", WILC_STATION_MODE, NL80211_IFTYPE_STATION, false); if (IS_ERR(vif)) { ret = PTR_ERR(vif); - goto free_cfg; + goto free_hq; } return 0; +free_hq: + destroy_workqueue(wl->hif_workqueue); + free_cfg: wilc_wlan_cfg_deinit(wl); diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index 839f142663e86..d2b8c26308198 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -377,38 +377,49 @@ struct wilc_join_bss_param * wilc_parse_join_bss_param(struct cfg80211_bss *bss, struct cfg80211_crypto_settings *crypto) { - struct wilc_join_bss_param *param; - struct ieee80211_p2p_noa_attr noa_attr; - u8 rates_len = 0; - const u8 *tim_elm, *ssid_elm, *rates_ie, *supp_rates_ie; + const u8 *ies_data, *tim_elm, *ssid_elm, *rates_ie, *supp_rates_ie; const u8 *ht_ie, *wpa_ie, *wmm_ie, *rsn_ie; + struct ieee80211_p2p_noa_attr noa_attr; + const struct cfg80211_bss_ies *ies; + struct wilc_join_bss_param *param; + u8 rates_len = 0, ies_len; int ret; - const struct cfg80211_bss_ies *ies = rcu_dereference(bss->ies); param = kzalloc(sizeof(*param), GFP_KERNEL); if (!param) return NULL; + rcu_read_lock(); + ies = rcu_dereference(bss->ies); + ies_data = kmemdup(ies->data, ies->len, GFP_ATOMIC); + if (!ies_data) { + rcu_read_unlock(); + kfree(param); + return NULL; + } + ies_len = ies->len; + rcu_read_unlock(); + param->beacon_period = cpu_to_le16(bss->beacon_interval); param->cap_info = cpu_to_le16(bss->capability); param->bss_type = WILC_FW_BSS_TYPE_INFRA; param->ch = ieee80211_frequency_to_channel(bss->channel->center_freq); ether_addr_copy(param->bssid, bss->bssid); - ssid_elm = cfg80211_find_ie(WLAN_EID_SSID, ies->data, ies->len); + ssid_elm = cfg80211_find_ie(WLAN_EID_SSID, ies_data, ies_len); if (ssid_elm) { if (ssid_elm[1] <= IEEE80211_MAX_SSID_LEN) memcpy(param->ssid, ssid_elm + 2, ssid_elm[1]); } - tim_elm = cfg80211_find_ie(WLAN_EID_TIM, ies->data, ies->len); + tim_elm = cfg80211_find_ie(WLAN_EID_TIM, ies_data, ies_len); if (tim_elm && tim_elm[1] >= 2) param->dtim_period = tim_elm[3]; memset(param->p_suites, 0xFF, 3); memset(param->akm_suites, 0xFF, 3); - rates_ie = cfg80211_find_ie(WLAN_EID_SUPP_RATES, ies->data, ies->len); + rates_ie = cfg80211_find_ie(WLAN_EID_SUPP_RATES, ies_data, ies_len); if (rates_ie) { rates_len = rates_ie[1]; if (rates_len > WILC_MAX_RATES_SUPPORTED) @@ -419,7 +430,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss, if (rates_len < WILC_MAX_RATES_SUPPORTED) { supp_rates_ie = cfg80211_find_ie(WLAN_EID_EXT_SUPP_RATES, - ies->data, ies->len); + ies_data, ies_len); if (supp_rates_ie) { u8 ext_rates = supp_rates_ie[1]; @@ -434,11 +445,11 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss, } } - ht_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY, ies->data, ies->len); + ht_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY, ies_data, ies_len); if (ht_ie) param->ht_capable = true; - ret = cfg80211_get_p2p_attr(ies->data, ies->len, + ret = cfg80211_get_p2p_attr(ies_data, ies_len, IEEE80211_P2P_ATTR_ABSENCE_NOTICE, (u8 *)&noa_attr, sizeof(noa_attr)); if (ret > 0) { @@ -462,7 +473,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss, } wmm_ie = cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT, WLAN_OUI_TYPE_MICROSOFT_WMM, - ies->data, ies->len); + ies_data, ies_len); if (wmm_ie) { struct ieee80211_wmm_param_ie *ie; @@ -477,13 +488,13 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss, wpa_ie = cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT, WLAN_OUI_TYPE_MICROSOFT_WPA, - ies->data, ies->len); + ies_data, ies_len); if (wpa_ie) { param->mode_802_11i = 1; param->rsn_found = true; } - rsn_ie = cfg80211_find_ie(WLAN_EID_RSN, ies->data, ies->len); + rsn_ie = cfg80211_find_ie(WLAN_EID_RSN, ies_data, ies_len); if (rsn_ie) { int rsn_ie_len = sizeof(struct element) + rsn_ie[1]; int offset = 8; @@ -517,6 +528,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss, param->akm_suites[i] = crypto->akm_suites[i] & 0xFF; } + kfree(ies_data); return (void *)param; } diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c index 81e8f25863f5b..6068699e44109 100644 --- a/drivers/net/wireless/microchip/wilc1000/netdev.c +++ b/drivers/net/wireless/microchip/wilc1000/netdev.c @@ -890,8 +890,7 @@ static const struct net_device_ops wilc_netdev_ops = { void wilc_netdev_cleanup(struct wilc *wilc) { - struct wilc_vif *vif; - int srcu_idx, ifc_cnt = 0; + struct wilc_vif *vif, *vif_tmp; if (!wilc) return; @@ -901,32 +900,19 @@ void wilc_netdev_cleanup(struct wilc *wilc) wilc->firmware = NULL; } - srcu_idx = srcu_read_lock(&wilc->srcu); - list_for_each_entry_rcu(vif, &wilc->vif_list, list) { + list_for_each_entry_safe(vif, vif_tmp, &wilc->vif_list, list) { + mutex_lock(&wilc->vif_mutex); + list_del_rcu(&vif->list); + wilc->vif_num--; + mutex_unlock(&wilc->vif_mutex); + synchronize_srcu(&wilc->srcu); if (vif->ndev) unregister_netdev(vif->ndev); } - srcu_read_unlock(&wilc->srcu, srcu_idx); wilc_wfi_deinit_mon_interface(wilc, false); destroy_workqueue(wilc->hif_workqueue); - while (ifc_cnt < WILC_NUM_CONCURRENT_IFC) { - mutex_lock(&wilc->vif_mutex); - if (wilc->vif_num <= 0) { - mutex_unlock(&wilc->vif_mutex); - break; - } - vif = wilc_get_wl_to_vif(wilc); - if (!IS_ERR(vif)) - list_del_rcu(&vif->list); - - wilc->vif_num--; - mutex_unlock(&wilc->vif_mutex); - synchronize_srcu(&wilc->srcu); - ifc_cnt++; - } - wilc_wlan_cfg_deinit(wilc); wlan_deinit_locks(wilc); wiphy_unregister(wilc->wiphy); @@ -989,13 +975,6 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name, goto error; } - wl->hif_workqueue = alloc_ordered_workqueue("%s-wq", WQ_MEM_RECLAIM, - ndev->name); - if (!wl->hif_workqueue) { - ret = -ENOMEM; - goto unregister_netdev; - } - ndev->needs_free_netdev = true; vif->iftype = vif_type; vif->idx = wilc_get_available_idx(wl); @@ -1008,12 +987,11 @@ struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name, return vif; -unregister_netdev: +error: if (rtnl_locked) cfg80211_unregister_netdevice(ndev); else unregister_netdev(ndev); - error: free_netdev(ndev); return ERR_PTR(ret); } diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c index 1d8b241ce43ca..6a82b6ca2769e 100644 --- a/drivers/net/wireless/microchip/wilc1000/spi.c +++ b/drivers/net/wireless/microchip/wilc1000/spi.c @@ -192,11 +192,11 @@ static void wilc_wlan_power(struct wilc *wilc, bool on) /* assert ENABLE: */ gpiod_set_value(gpios->enable, 1); mdelay(5); - /* assert RESET: */ - gpiod_set_value(gpios->reset, 1); - } else { /* deassert RESET: */ gpiod_set_value(gpios->reset, 0); + } else { + /* assert RESET: */ + gpiod_set_value(gpios->reset, 1); /* deassert ENABLE: */ gpiod_set_value(gpios->enable, 0); } diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index 4695fb4e2d2db..af541e52e683b 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -121,6 +121,15 @@ enum rtl8xxxu_rx_type { RX_TYPE_ERROR = -1 }; +enum rtl8xxxu_rx_desc_enc { + RX_DESC_ENC_NONE = 0, + RX_DESC_ENC_WEP40 = 1, + RX_DESC_ENC_TKIP_WO_MIC = 2, + RX_DESC_ENC_TKIP_MIC = 3, + RX_DESC_ENC_AES = 4, + RX_DESC_ENC_WEP104 = 5, +}; + struct rtl8xxxu_rxdesc16 { #ifdef __LITTLE_ENDIAN u32 pktlen:14; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 180907319e8cd..5a16cf000f1db 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -1505,13 +1505,13 @@ rtl8xxxu_gen1_set_tx_power(struct rtl8xxxu_priv *priv, int channel, bool ht40) u8 cck[RTL8723A_MAX_RF_PATHS], ofdm[RTL8723A_MAX_RF_PATHS]; u8 ofdmbase[RTL8723A_MAX_RF_PATHS], mcsbase[RTL8723A_MAX_RF_PATHS]; u32 val32, ofdm_a, ofdm_b, mcs_a, mcs_b; - u8 val8; + u8 val8, base; int group, i; group = rtl8xxxu_gen1_channel_to_group(channel); - cck[0] = priv->cck_tx_power_index_A[group] - 1; - cck[1] = priv->cck_tx_power_index_B[group] - 1; + cck[0] = priv->cck_tx_power_index_A[group]; + cck[1] = priv->cck_tx_power_index_B[group]; if (priv->hi_pa) { if (cck[0] > 0x20) @@ -1522,10 +1522,6 @@ rtl8xxxu_gen1_set_tx_power(struct rtl8xxxu_priv *priv, int channel, bool ht40) ofdm[0] = priv->ht40_1s_tx_power_index_A[group]; ofdm[1] = priv->ht40_1s_tx_power_index_B[group]; - if (ofdm[0]) - ofdm[0] -= 1; - if (ofdm[1]) - ofdm[1] -= 1; ofdmbase[0] = ofdm[0] + priv->ofdm_tx_power_index_diff[group].a; ofdmbase[1] = ofdm[1] + priv->ofdm_tx_power_index_diff[group].b; @@ -1614,20 +1610,19 @@ rtl8xxxu_gen1_set_tx_power(struct rtl8xxxu_priv *priv, int channel, bool ht40) rtl8xxxu_write32(priv, REG_TX_AGC_A_MCS15_MCS12, mcs_a + power_base->reg_0e1c); + val8 = u32_get_bits(mcs_a + power_base->reg_0e1c, 0xff000000); for (i = 0; i < 3; i++) { - if (i != 2) - val8 = (mcsbase[0] > 8) ? (mcsbase[0] - 8) : 0; - else - val8 = (mcsbase[0] > 6) ? (mcsbase[0] - 6) : 0; + base = i != 2 ? 8 : 6; + val8 = max_t(int, val8 - base, 0); rtl8xxxu_write8(priv, REG_OFDM0_XC_TX_IQ_IMBALANCE + i, val8); } + rtl8xxxu_write32(priv, REG_TX_AGC_B_MCS15_MCS12, mcs_b + power_base->reg_0868); + val8 = u32_get_bits(mcs_b + power_base->reg_0868, 0xff000000); for (i = 0; i < 3; i++) { - if (i != 2) - val8 = (mcsbase[1] > 8) ? (mcsbase[1] - 8) : 0; - else - val8 = (mcsbase[1] > 6) ? (mcsbase[1] - 6) : 0; + base = i != 2 ? 8 : 6; + val8 = max_t(int, val8 - base, 0); rtl8xxxu_write8(priv, REG_OFDM0_XD_TX_IQ_IMBALANCE + i, val8); } } @@ -6324,7 +6319,8 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb) rx_status->mactime = rx_desc->tsfl; rx_status->flag |= RX_FLAG_MACTIME_START; - if (!rx_desc->swdec) + if (!rx_desc->swdec && + rx_desc->security != RX_DESC_ENC_NONE) rx_status->flag |= RX_FLAG_DECRYPTED; if (rx_desc->crc32) rx_status->flag |= RX_FLAG_FAILED_FCS_CRC; @@ -6424,7 +6420,8 @@ int rtl8xxxu_parse_rxdesc24(struct rtl8xxxu_priv *priv, struct sk_buff *skb) rx_status->mactime = rx_desc->tsfl; rx_status->flag |= RX_FLAG_MACTIME_START; - if (!rx_desc->swdec) + if (!rx_desc->swdec && + rx_desc->security != RX_DESC_ENC_NONE) rx_status->flag |= RX_FLAG_DECRYPTED; if (rx_desc->crc32) rx_status->flag |= RX_FLAG_FAILED_FCS_CRC; @@ -7304,6 +7301,7 @@ static void rtl8xxxu_stop(struct ieee80211_hw *hw) if (priv->usb_interrupts) rtl8xxxu_write32(priv, REG_USB_HIMR, 0); + cancel_work_sync(&priv->c2hcmd_work); cancel_delayed_work_sync(&priv->ra_watchdog); rtl8xxxu_free_rx_resources(priv); @@ -7659,6 +7657,7 @@ static int rtl8xxxu_probe(struct usb_interface *interface, ieee80211_hw_set(hw, HAS_RATE_CONTROL); ieee80211_hw_set(hw, SUPPORT_FAST_XMIT); ieee80211_hw_set(hw, AMPDU_AGGREGATION); + ieee80211_hw_set(hw, MFP_CAPABLE); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index 69e97647e3d6b..b08491869346c 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -633,21 +633,6 @@ static int rtl_op_config(struct ieee80211_hw *hw, u32 changed) } } - if (changed & IEEE80211_CONF_CHANGE_RETRY_LIMITS) { - rtl_dbg(rtlpriv, COMP_MAC80211, DBG_LOUD, - "IEEE80211_CONF_CHANGE_RETRY_LIMITS %x\n", - hw->conf.long_frame_max_tx_count); - /* brought up everything changes (changed == ~0) indicates first - * open, so use our default value instead of that of wiphy. - */ - if (changed != ~0) { - mac->retry_long = hw->conf.long_frame_max_tx_count; - mac->retry_short = hw->conf.long_frame_max_tx_count; - rtlpriv->cfg->ops->set_hw_reg(hw, HW_VAR_RETRY_LIMIT, - (u8 *)(&hw->conf.long_frame_max_tx_count)); - } - } - if (changed & IEEE80211_CONF_CHANGE_CHANNEL && !rtlpriv->proximity.proxim_on) { struct ieee80211_channel *channel = hw->conf.chandef.chan; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c index d835a27429f0f..56b5cd032a9ac 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c @@ -892,8 +892,8 @@ static u8 _rtl92c_phy_get_rightchnlplace(u8 chnl) u8 place = chnl; if (chnl > 14) { - for (place = 14; place < ARRAY_SIZE(channel5g); place++) { - if (channel5g[place] == chnl) { + for (place = 14; place < ARRAY_SIZE(channel_all); place++) { + if (channel_all[place] == chnl) { place++; break; } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c index 02ac69c08ed37..c3f008421d7d8 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.c @@ -35,7 +35,7 @@ static long _rtl92de_translate_todbm(struct ieee80211_hw *hw, static void _rtl92de_query_rxphystatus(struct ieee80211_hw *hw, struct rtl_stats *pstats, - struct rx_desc_92d *pdesc, + __le32 *pdesc, struct rx_fwinfo_92d *p_drvinfo, bool packet_match_bssid, bool packet_toself, @@ -49,8 +49,10 @@ static void _rtl92de_query_rxphystatus(struct ieee80211_hw *hw, u8 i, max_spatial_stream; u32 rssi, total_rssi = 0; bool is_cck_rate; + u8 rxmcs; - is_cck_rate = RX_HAL_IS_CCK_RATE(pdesc->rxmcs); + rxmcs = get_rx_desc_rxmcs(pdesc); + is_cck_rate = rxmcs <= DESC_RATE11M; pstats->packet_matchbssid = packet_match_bssid; pstats->packet_toself = packet_toself; pstats->packet_beacon = packet_beacon; @@ -158,8 +160,8 @@ static void _rtl92de_query_rxphystatus(struct ieee80211_hw *hw, pstats->rx_pwdb_all = pwdb_all; pstats->rxpower = rx_pwr_all; pstats->recvsignalpower = rx_pwr_all; - if (pdesc->rxht && pdesc->rxmcs >= DESC_RATEMCS8 && - pdesc->rxmcs <= DESC_RATEMCS15) + if (get_rx_desc_rxht(pdesc) && rxmcs >= DESC_RATEMCS8 && + rxmcs <= DESC_RATEMCS15) max_spatial_stream = 2; else max_spatial_stream = 1; @@ -365,7 +367,7 @@ static void _rtl92de_process_phyinfo(struct ieee80211_hw *hw, static void _rtl92de_translate_rx_signal_stuff(struct ieee80211_hw *hw, struct sk_buff *skb, struct rtl_stats *pstats, - struct rx_desc_92d *pdesc, + __le32 *pdesc, struct rx_fwinfo_92d *p_drvinfo) { struct rtl_mac *mac = rtl_mac(rtl_priv(hw)); @@ -414,7 +416,8 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats, stats->icv = (u16)get_rx_desc_icv(pdesc); stats->crc = (u16)get_rx_desc_crc32(pdesc); stats->hwerror = (stats->crc | stats->icv); - stats->decrypted = !get_rx_desc_swdec(pdesc); + stats->decrypted = !get_rx_desc_swdec(pdesc) && + get_rx_desc_enc_type(pdesc) != RX_DESC_ENC_NONE; stats->rate = (u8)get_rx_desc_rxmcs(pdesc); stats->shortpreamble = (u16)get_rx_desc_splcp(pdesc); stats->isampdu = (bool)(get_rx_desc_paggr(pdesc) == 1); @@ -427,8 +430,6 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats, rx_status->band = hw->conf.chandef.chan->band; if (get_rx_desc_crc32(pdesc)) rx_status->flag |= RX_FLAG_FAILED_FCS_CRC; - if (!get_rx_desc_swdec(pdesc)) - rx_status->flag |= RX_FLAG_DECRYPTED; if (get_rx_desc_bw(pdesc)) rx_status->bw = RATE_INFO_BW_40; if (get_rx_desc_rxht(pdesc)) @@ -442,9 +443,7 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats, if (phystatus) { p_drvinfo = (struct rx_fwinfo_92d *)(skb->data + stats->rx_bufshift); - _rtl92de_translate_rx_signal_stuff(hw, - skb, stats, - (struct rx_desc_92d *)pdesc, + _rtl92de_translate_rx_signal_stuff(hw, skb, stats, pdesc, p_drvinfo); } /*rx_status->qual = stats->signal; */ diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h index 2992668c156c6..2d4887490f00f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/trx.h @@ -14,6 +14,15 @@ #define USB_HWDESC_HEADER_LEN 32 #define CRCLENGTH 4 +enum rtl92d_rx_desc_enc { + RX_DESC_ENC_NONE = 0, + RX_DESC_ENC_WEP40 = 1, + RX_DESC_ENC_TKIP_WO_MIC = 2, + RX_DESC_ENC_TKIP_MIC = 3, + RX_DESC_ENC_AES = 4, + RX_DESC_ENC_WEP104 = 5, +}; + /* macros to read/write various fields in RX or TX descriptors */ static inline void set_tx_desc_pkt_size(__le32 *__pdesc, u32 __val) @@ -246,6 +255,11 @@ static inline u32 get_rx_desc_drv_info_size(__le32 *__pdesc) return le32_get_bits(*__pdesc, GENMASK(19, 16)); } +static inline u32 get_rx_desc_enc_type(__le32 *__pdesc) +{ + return le32_get_bits(*__pdesc, GENMASK(22, 20)); +} + static inline u32 get_rx_desc_shift(__le32 *__pdesc) { return le32_get_bits(*__pdesc, GENMASK(25, 24)); @@ -380,10 +394,17 @@ struct rx_fwinfo_92d { u8 csi_target[2]; u8 sigevm; u8 max_ex_pwr; +#ifdef __LITTLE_ENDIAN u8 ex_intf_flag:1; u8 sgi_en:1; u8 rxsc:2; u8 reserve:4; +#else + u8 reserve:4; + u8 rxsc:2; + u8 sgi_en:1; + u8 ex_intf_flag:1; +#endif } __packed; struct tx_desc_92d { @@ -488,64 +509,6 @@ struct tx_desc_92d { u32 reserve_pass_pcie_mm_limit[4]; } __packed; -struct rx_desc_92d { - u32 length:14; - u32 crc32:1; - u32 icverror:1; - u32 drv_infosize:4; - u32 security:3; - u32 qos:1; - u32 shift:2; - u32 phystatus:1; - u32 swdec:1; - u32 lastseg:1; - u32 firstseg:1; - u32 eor:1; - u32 own:1; - - u32 macid:5; - u32 tid:4; - u32 hwrsvd:5; - u32 paggr:1; - u32 faggr:1; - u32 a1_fit:4; - u32 a2_fit:4; - u32 pam:1; - u32 pwr:1; - u32 moredata:1; - u32 morefrag:1; - u32 type:2; - u32 mc:1; - u32 bc:1; - - u32 seq:12; - u32 frag:4; - u32 nextpktlen:14; - u32 nextind:1; - u32 rsvd:1; - - u32 rxmcs:6; - u32 rxht:1; - u32 amsdu:1; - u32 splcp:1; - u32 bandwidth:1; - u32 htc:1; - u32 tcpchk_rpt:1; - u32 ipcchk_rpt:1; - u32 tcpchk_valid:1; - u32 hwpcerr:1; - u32 hwpcind:1; - u32 iv0:16; - - u32 iv1; - - u32 tsfl; - - u32 bufferaddress; - u32 bufferaddress64; - -} __packed; - void rtl92de_tx_fill_desc(struct ieee80211_hw *hw, struct ieee80211_hdr *hdr, u8 *pdesc, u8 *pbd_desc_tx, struct ieee80211_tx_info *info, diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c index 298663b035808..0c1c1ff31085c 100644 --- a/drivers/net/wireless/realtek/rtw88/mac.c +++ b/drivers/net/wireless/realtek/rtw88/mac.c @@ -309,6 +309,13 @@ static int rtw_mac_power_switch(struct rtw_dev *rtwdev, bool pwr_on) pwr_seq = pwr_on ? chip->pwr_on_seq : chip->pwr_off_seq; ret = rtw_pwr_seq_parser(rtwdev, pwr_seq); + if (pwr_on && rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB) { + if (chip->id == RTW_CHIP_TYPE_8822C || + chip->id == RTW_CHIP_TYPE_8822B || + chip->id == RTW_CHIP_TYPE_8821C) + rtw_write8_clr(rtwdev, REG_SYS_STATUS1 + 1, BIT(0)); + } + if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_SDIO) rtw_write32(rtwdev, REG_SDIO_HIMR, imr); diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 6d22628129d0d..ffba6b88f392c 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -2032,8 +2032,6 @@ static int rtw_chip_board_info_setup(struct rtw_dev *rtwdev) rtw_phy_setup_phy_cond(rtwdev, hal->pkg_type); rtw_phy_init_tx_power(rtwdev); - if (rfe_def->agc_btg_tbl) - rtw_load_table(rtwdev, rfe_def->agc_btg_tbl); rtw_load_table(rtwdev, rfe_def->phy_pg_tbl); rtw_load_table(rtwdev, rfe_def->txpwr_lmt_tbl); rtw_phy_tx_power_by_rate_config(hal); diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c index 128e75a81bf3c..37ef80c9091db 100644 --- a/drivers/net/wireless/realtek/rtw88/phy.c +++ b/drivers/net/wireless/realtek/rtw88/phy.c @@ -1761,12 +1761,15 @@ static void rtw_load_rfk_table(struct rtw_dev *rtwdev) void rtw_phy_load_tables(struct rtw_dev *rtwdev) { + const struct rtw_rfe_def *rfe_def = rtw_get_rfe_def(rtwdev); const struct rtw_chip_info *chip = rtwdev->chip; u8 rf_path; rtw_load_table(rtwdev, chip->mac_tbl); rtw_load_table(rtwdev, chip->bb_tbl); rtw_load_table(rtwdev, chip->agc_tbl); + if (rfe_def->agc_btg_tbl) + rtw_load_table(rtwdev, rfe_def->agc_btg_tbl); rtw_load_rfk_table(rtwdev); for (rf_path = 0; rf_path < rtwdev->hal.rf_path_num; rf_path++) { diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c index 429bb420b0563..fe5d8e1883509 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -773,9 +773,9 @@ static void rtw8821c_false_alarm_statistics(struct rtw_dev *rtwdev) dm_info->cck_fa_cnt = cck_fa_cnt; dm_info->ofdm_fa_cnt = ofdm_fa_cnt; + dm_info->total_fa_cnt = ofdm_fa_cnt; if (cck_enable) dm_info->total_fa_cnt += cck_fa_cnt; - dm_info->total_fa_cnt = ofdm_fa_cnt; crc32_cnt = rtw_read32(rtwdev, REG_CRC_CCK); dm_info->cck_ok_cnt = FIELD_GET(GENMASK(15, 0), crc32_cnt); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c index 7a5cbdc31ef79..e2c7d9f876836 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c @@ -9,24 +9,36 @@ #include "usb.h" static const struct usb_device_id rtw_8821cu_id_table[] = { - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb82b, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x2006, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8731, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb820, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc821, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb82b, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc80c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc820, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc821, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82a, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82b, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc811, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8811CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8811, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8811CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x2006, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* TOTOLINK A650UA v3 */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x331d, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xc811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* Edimax */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xd811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* Edimax */ {}, }; MODULE_DEVICE_TABLE(usb, rtw_8821cu_id_table); diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c index e6ab1ac6d7093..a0188511099a1 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.c +++ b/drivers/net/wireless/realtek/rtw88/usb.c @@ -33,6 +33,36 @@ static void rtw_usb_fill_tx_checksum(struct rtw_usb *rtwusb, rtw_tx_fill_txdesc_checksum(rtwdev, &pkt_info, skb->data); } +static void rtw_usb_reg_sec(struct rtw_dev *rtwdev, u32 addr, __le32 *data) +{ + struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev); + struct usb_device *udev = rtwusb->udev; + bool reg_on_section = false; + u16 t_reg = 0x4e0; + u8 t_len = 1; + int status; + + /* There are three sections: + * 1. on (0x00~0xFF; 0x1000~0x10FF): this section is always powered on + * 2. off (< 0xFE00, excluding "on" section): this section could be + * powered off + * 3. local (>= 0xFE00): usb specific registers section + */ + if (addr <= 0xff || (addr >= 0x1000 && addr <= 0x10ff)) + reg_on_section = true; + + if (!reg_on_section) + return; + + status = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), + RTW_USB_CMD_REQ, RTW_USB_CMD_WRITE, + t_reg, 0, data, t_len, 500); + + if (status != t_len && status != -ENODEV) + rtw_err(rtwdev, "%s: reg 0x%x, usb write %u fail, status: %d\n", + __func__, t_reg, t_len, status); +} + static u32 rtw_usb_read(struct rtw_dev *rtwdev, u32 addr, u16 len) { struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev); @@ -58,6 +88,11 @@ static u32 rtw_usb_read(struct rtw_dev *rtwdev, u32 addr, u16 len) rtw_err(rtwdev, "read register 0x%x failed with %d\n", addr, ret); + if (rtwdev->chip->id == RTW_CHIP_TYPE_8822C || + rtwdev->chip->id == RTW_CHIP_TYPE_8822B || + rtwdev->chip->id == RTW_CHIP_TYPE_8821C) + rtw_usb_reg_sec(rtwdev, addr, data); + return le32_to_cpu(*data); } @@ -102,6 +137,11 @@ static void rtw_usb_write(struct rtw_dev *rtwdev, u32 addr, u32 val, int len) if (ret < 0 && ret != -ENODEV && count++ < 4) rtw_err(rtwdev, "write register 0x%x failed with %d\n", addr, ret); + + if (rtwdev->chip->id == RTW_CHIP_TYPE_8822C || + rtwdev->chip->id == RTW_CHIP_TYPE_8822B || + rtwdev->chip->id == RTW_CHIP_TYPE_8821C) + rtw_usb_reg_sec(rtwdev, addr, data); } static void rtw_usb_write8(struct rtw_dev *rtwdev, u32 addr, u8 val) diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index fd527a2499964..b967d80ec84b5 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -3940,6 +3940,24 @@ void rtw89_core_ntfy_btc_event(struct rtw89_dev *rtwdev, enum rtw89_btc_hmsg eve } } +void rtw89_check_quirks(struct rtw89_dev *rtwdev, const struct dmi_system_id *quirks) +{ + const struct dmi_system_id *match; + enum rtw89_quirks quirk; + + if (!quirks) + return; + + for (match = dmi_first_match(quirks); match; match = dmi_first_match(match + 1)) { + quirk = (uintptr_t)match->driver_data; + if (quirk >= NUM_OF_RTW89_QUIRKS) + continue; + + set_bit(quirk, rtwdev->quirks); + } +} +EXPORT_SYMBOL(rtw89_check_quirks); + int rtw89_core_start(struct rtw89_dev *rtwdev) { int ret; diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h index ea6df859ba152..e72a6a958a231 100644 --- a/drivers/net/wireless/realtek/rtw89/core.h +++ b/drivers/net/wireless/realtek/rtw89/core.h @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -3812,6 +3813,7 @@ union rtw89_bus_info { struct rtw89_driver_info { const struct rtw89_chip_info *chip; + const struct dmi_system_id *quirks; union rtw89_bus_info bus; }; @@ -4139,6 +4141,12 @@ enum rtw89_flags { NUM_OF_RTW89_FLAGS, }; +enum rtw89_quirks { + RTW89_QUIRK_PCI_BER, + + NUM_OF_RTW89_QUIRKS, +}; + enum rtw89_pkt_drop_sel { RTW89_PKT_DROP_SEL_MACID_BE_ONCE, RTW89_PKT_DROP_SEL_MACID_BK_ONCE, @@ -4804,6 +4812,7 @@ struct rtw89_dev { DECLARE_BITMAP(mac_id_map, RTW89_MAX_MAC_ID_NUM); DECLARE_BITMAP(flags, NUM_OF_RTW89_FLAGS); DECLARE_BITMAP(pkt_offload, RTW89_MAX_PKT_OFLD_NUM); + DECLARE_BITMAP(quirks, NUM_OF_RTW89_QUIRKS); struct rtw89_phy_stat phystat; struct rtw89_dack_info dack; @@ -5803,6 +5812,7 @@ int rtw89_core_sta_remove(struct rtw89_dev *rtwdev, void rtw89_core_set_tid_config(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta, struct cfg80211_tid_config *tid_config); +void rtw89_check_quirks(struct rtw89_dev *rtwdev, const struct dmi_system_id *quirks); int rtw89_core_init(struct rtw89_dev *rtwdev); void rtw89_core_deinit(struct rtw89_dev *rtwdev); int rtw89_core_register(struct rtw89_dev *rtwdev); diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 09684cea9731c..f1eaeb191af09 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -1086,13 +1086,12 @@ static void rtw89_fw_prog_cnt_dump(struct rtw89_dev *rtwdev) static void rtw89_fw_dl_fail_dump(struct rtw89_dev *rtwdev) { u32 val32; - u16 val16; val32 = rtw89_read32(rtwdev, R_AX_WCPU_FW_CTRL); rtw89_err(rtwdev, "[ERR]fwdl 0x1E0 = 0x%x\n", val32); - val16 = rtw89_read16(rtwdev, R_AX_BOOT_DBG + 2); - rtw89_err(rtwdev, "[ERR]fwdl 0x83F2 = 0x%x\n", val16); + val32 = rtw89_read32(rtwdev, R_AX_BOOT_DBG); + rtw89_err(rtwdev, "[ERR]fwdl 0x83F0 = 0x%x\n", val32); rtw89_fw_prog_cnt_dump(rtwdev); } @@ -1132,8 +1131,9 @@ static int rtw89_fw_download_suit(struct rtw89_dev *rtwdev, return 0; } -int rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type, - bool include_bb) +static +int __rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type, + bool include_bb) { const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; struct rtw89_fw_info *fw_info = &rtwdev->fw; @@ -1171,7 +1171,7 @@ int rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type, ret = rtw89_fw_check_rdy(rtwdev, RTW89_FWDL_CHECK_FREERTOS_DONE); if (ret) { rtw89_warn(rtwdev, "download firmware fail\n"); - return ret; + goto fwdl_err; } return ret; @@ -1181,6 +1181,21 @@ int rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type, return ret; } +int rtw89_fw_download(struct rtw89_dev *rtwdev, enum rtw89_fw_type type, + bool include_bb) +{ + int retry; + int ret; + + for (retry = 0; retry < 5; retry++) { + ret = __rtw89_fw_download(rtwdev, type, include_bb); + if (!ret) + return 0; + } + + return ret; +} + int rtw89_wait_firmware_completion(struct rtw89_dev *rtwdev) { struct rtw89_fw_info *fw = &rtwdev->fw; diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c index 93889d2fface1..db83be900c923 100644 --- a/drivers/net/wireless/realtek/rtw89/mac80211.c +++ b/drivers/net/wireless/realtek/rtw89/mac80211.c @@ -318,7 +318,7 @@ static u8 rtw89_aifsn_to_aifs(struct rtw89_dev *rtwdev, u8 sifs; slot_time = vif->bss_conf.use_short_slot ? 9 : 20; - sifs = chan->band_type == RTW89_BAND_5G ? 16 : 10; + sifs = chan->band_type == RTW89_BAND_2G ? 10 : 16; return aifsn * slot_time + sifs; } @@ -441,7 +441,7 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw, * when disconnected by peer */ if (rtwdev->scanning) - rtw89_hw_scan_abort(rtwdev, vif); + rtw89_hw_scan_abort(rtwdev, rtwdev->scan_info.scanning_vif); } } @@ -990,7 +990,7 @@ static int rtw89_ops_remain_on_channel(struct ieee80211_hw *hw, } if (rtwdev->scanning) - rtw89_hw_scan_abort(rtwdev, vif); + rtw89_hw_scan_abort(rtwdev, rtwdev->scan_info.scanning_vif); if (type == IEEE80211_ROC_TYPE_MGMT_TX) roc->state = RTW89_ROC_MGMT; diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c index 769f1ce62ebcc..0e989b7e49873 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.c +++ b/drivers/net/wireless/realtek/rtw89/pci.c @@ -155,8 +155,8 @@ static void rtw89_pci_sync_skb_for_device(struct rtw89_dev *rtwdev, DMA_FROM_DEVICE); } -static int rtw89_pci_rxbd_info_update(struct rtw89_dev *rtwdev, - struct sk_buff *skb) +static void rtw89_pci_rxbd_info_update(struct rtw89_dev *rtwdev, + struct sk_buff *skb) { struct rtw89_pci_rxbd_info *rxbd_info; struct rtw89_pci_rx_info *rx_info = RTW89_PCI_RX_SKB_CB(skb); @@ -166,10 +166,58 @@ static int rtw89_pci_rxbd_info_update(struct rtw89_dev *rtwdev, rx_info->ls = le32_get_bits(rxbd_info->dword, RTW89_PCI_RXBD_LS); rx_info->len = le32_get_bits(rxbd_info->dword, RTW89_PCI_RXBD_WRITE_SIZE); rx_info->tag = le32_get_bits(rxbd_info->dword, RTW89_PCI_RXBD_TAG); +} + +static int rtw89_pci_validate_rx_tag(struct rtw89_dev *rtwdev, + struct rtw89_pci_rx_ring *rx_ring, + struct sk_buff *skb) +{ + struct rtw89_pci_rx_info *rx_info = RTW89_PCI_RX_SKB_CB(skb); + const struct rtw89_pci_info *info = rtwdev->pci_info; + u32 target_rx_tag; + + if (!info->check_rx_tag) + return 0; + + /* valid range is 1 ~ 0x1FFF */ + if (rx_ring->target_rx_tag == 0) + target_rx_tag = 1; + else + target_rx_tag = rx_ring->target_rx_tag; + + if (rx_info->tag != target_rx_tag) { + rtw89_debug(rtwdev, RTW89_DBG_UNEXP, "mismatch RX tag 0x%x 0x%x\n", + rx_info->tag, target_rx_tag); + return -EAGAIN; + } return 0; } +static +int rtw89_pci_sync_skb_for_device_and_validate_rx_info(struct rtw89_dev *rtwdev, + struct rtw89_pci_rx_ring *rx_ring, + struct sk_buff *skb) +{ + struct rtw89_pci_rx_info *rx_info = RTW89_PCI_RX_SKB_CB(skb); + int rx_tag_retry = 100; + int ret; + + do { + rtw89_pci_sync_skb_for_cpu(rtwdev, skb); + rtw89_pci_rxbd_info_update(rtwdev, skb); + + ret = rtw89_pci_validate_rx_tag(rtwdev, rx_ring, skb); + if (ret != -EAGAIN) + break; + } while (rx_tag_retry--); + + /* update target rx_tag for next RX */ + rx_ring->target_rx_tag = rx_info->tag + 1; + + return ret; +} + static void rtw89_pci_ctrl_txdma_ch_pcie(struct rtw89_dev *rtwdev, bool enable) { const struct rtw89_pci_info *info = rtwdev->pci_info; @@ -259,9 +307,8 @@ static u32 rtw89_pci_rxbd_deliver_skbs(struct rtw89_dev *rtwdev, skb_idx = rtw89_pci_get_rx_skb_idx(rtwdev, bd_ring); skb = rx_ring->buf[skb_idx]; - rtw89_pci_sync_skb_for_cpu(rtwdev, skb); - ret = rtw89_pci_rxbd_info_update(rtwdev, skb); + ret = rtw89_pci_sync_skb_for_device_and_validate_rx_info(rtwdev, rx_ring, skb); if (ret) { rtw89_err(rtwdev, "failed to update %d RXBD info: %d\n", bd_ring->wp, ret); @@ -549,9 +596,8 @@ static u32 rtw89_pci_release_tx_skbs(struct rtw89_dev *rtwdev, skb_idx = rtw89_pci_get_rx_skb_idx(rtwdev, bd_ring); skb = rx_ring->buf[skb_idx]; - rtw89_pci_sync_skb_for_cpu(rtwdev, skb); - ret = rtw89_pci_rxbd_info_update(rtwdev, skb); + ret = rtw89_pci_sync_skb_for_device_and_validate_rx_info(rtwdev, rx_ring, skb); if (ret) { rtw89_err(rtwdev, "failed to update %d RXBD info: %d\n", bd_ring->wp, ret); @@ -1043,7 +1089,8 @@ u32 __rtw89_pci_check_and_reclaim_tx_resource_noio(struct rtw89_dev *rtwdev, spin_lock_bh(&rtwpci->trx_lock); cnt = rtw89_pci_get_avail_txbd_num(tx_ring); - cnt = min(cnt, wd_ring->curr_num); + if (txch != RTW89_TXCH_CH12) + cnt = min(cnt, wd_ring->curr_num); spin_unlock_bh(&rtwpci->trx_lock); return cnt; @@ -1550,6 +1597,7 @@ static void rtw89_pci_reset_trx_rings(struct rtw89_dev *rtwdev) bd_ring->rp = 0; rx_ring->diliver_skb = NULL; rx_ring->diliver_desc.ready = false; + rx_ring->target_rx_tag = 0; rtw89_write16(rtwdev, addr_num, bd_ring->len); rtw89_write32(rtwdev, addr_desa_l, bd_ring->dma); @@ -2186,6 +2234,22 @@ static int rtw89_pci_deglitch_setting(struct rtw89_dev *rtwdev) return 0; } +static void rtw89_pci_ber(struct rtw89_dev *rtwdev) +{ + u32 phy_offset; + + if (!test_bit(RTW89_QUIRK_PCI_BER, rtwdev->quirks)) + return; + + phy_offset = R_RAC_DIRECT_OFFSET_G1; + rtw89_write16(rtwdev, phy_offset + RAC_ANA1E * RAC_MULT, RAC_ANA1E_G1_VAL); + rtw89_write16(rtwdev, phy_offset + RAC_ANA2E * RAC_MULT, RAC_ANA2E_VAL); + + phy_offset = R_RAC_DIRECT_OFFSET_G2; + rtw89_write16(rtwdev, phy_offset + RAC_ANA1E * RAC_MULT, RAC_ANA1E_G2_VAL); + rtw89_write16(rtwdev, phy_offset + RAC_ANA2E * RAC_MULT, RAC_ANA2E_VAL); +} + static void rtw89_pci_rxdma_prefth(struct rtw89_dev *rtwdev) { if (rtwdev->chip->chip_id != RTL8852A) @@ -2583,6 +2647,7 @@ static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev) const struct rtw89_pci_info *info = rtwdev->pci_info; int ret; + rtw89_pci_ber(rtwdev); rtw89_pci_rxdma_prefth(rtwdev); rtw89_pci_l1off_pwroff(rtwdev); rtw89_pci_deglitch_setting(rtwdev); @@ -3148,6 +3213,7 @@ static int rtw89_pci_alloc_rx_ring(struct rtw89_dev *rtwdev, rx_ring->buf_sz = buf_sz; rx_ring->diliver_skb = NULL; rx_ring->diliver_desc.ready = false; + rx_ring->target_rx_tag = 0; for (i = 0; i < len; i++) { skb = dev_alloc_skb(buf_sz); @@ -4024,6 +4090,8 @@ int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) rtwdev->hci.rpwm_addr = pci_info->rpwm_addr; rtwdev->hci.cpwm_addr = pci_info->cpwm_addr; + rtw89_check_quirks(rtwdev, info->quirks); + SET_IEEE80211_DEV(rtwdev->hw, &pdev->dev); ret = rtw89_core_init(rtwdev); diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h index ca5de77fee90a..b50d7a18e30bc 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.h +++ b/drivers/net/wireless/realtek/rtw89/pci.h @@ -26,11 +26,16 @@ #define RAC_REG_FLD_0 0x1D #define BAC_AUTOK_N_MASK GENMASK(3, 2) #define PCIE_AUTOK_4 0x3 +#define RAC_ANA1E 0x1E +#define RAC_ANA1E_G1_VAL 0x66EA +#define RAC_ANA1E_G2_VAL 0x6EEA #define RAC_ANA1F 0x1F #define RAC_ANA24 0x24 #define B_AX_DEGLITCH GENMASK(11, 8) #define RAC_ANA26 0x26 #define B_AX_RXEN GENMASK(15, 14) +#define RAC_ANA2E 0x2E +#define RAC_ANA2E_VAL 0xFFFE #define RAC_CTRL_PPR_V1 0x30 #define B_AX_CLK_CALIB_EN BIT(12) #define B_AX_CALIB_EN BIT(13) @@ -996,7 +1001,7 @@ #define RTW89_PCI_TXWD_NUM_MAX 512 #define RTW89_PCI_TXWD_PAGE_SIZE 128 #define RTW89_PCI_ADDRINFO_MAX 4 -#define RTW89_PCI_RX_BUF_SIZE 11460 +#define RTW89_PCI_RX_BUF_SIZE (11454 + 40) /* +40 for rtw89_rxdesc_long_v2 */ #define RTW89_PCI_POLL_BDRAM_RST_CNT 100 #define RTW89_PCI_MULTITAG 8 @@ -1234,6 +1239,7 @@ struct rtw89_pci_info { enum mac_ax_pcie_func_ctrl io_rcy_en; enum mac_ax_io_rcy_tmr io_rcy_tmr; bool rx_ring_eq_is_full; + bool check_rx_tag; u32 init_cfg_reg; u32 txhci_en_bit; @@ -1276,7 +1282,7 @@ struct rtw89_pci_tx_data { struct rtw89_pci_rx_info { dma_addr_t dma; - u32 fs:1, ls:1, tag:11, len:14; + u32 fs:1, ls:1, tag:13, len:14; }; #define RTW89_PCI_TXBD_OPTION_LS BIT(14) @@ -1405,6 +1411,7 @@ struct rtw89_pci_rx_ring { u32 buf_sz; struct sk_buff *diliver_skb; struct rtw89_rx_desc_info diliver_desc; + u32 target_rx_tag:13; }; struct rtw89_pci_isrs { diff --git a/drivers/net/wireless/realtek/rtw89/ps.c b/drivers/net/wireless/realtek/rtw89/ps.c index 917c01e5e9eda..e86d5588ec609 100644 --- a/drivers/net/wireless/realtek/rtw89/ps.c +++ b/drivers/net/wireless/realtek/rtw89/ps.c @@ -54,7 +54,8 @@ static void rtw89_ps_power_mode_change_with_hci(struct rtw89_dev *rtwdev, static void rtw89_ps_power_mode_change(struct rtw89_dev *rtwdev, bool enter) { - if (rtwdev->chip->low_power_hci_modes & BIT(rtwdev->ps_mode)) + if (rtwdev->chip->low_power_hci_modes & BIT(rtwdev->ps_mode) && + !test_bit(RTW89_FLAG_WOWLAN, rtwdev->flags)) rtw89_ps_power_mode_change_with_hci(rtwdev, enter); else rtw89_mac_power_mode_change(rtwdev, enter); diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h index 8456e2b0c14f1..dad87b3ff7ce3 100644 --- a/drivers/net/wireless/realtek/rtw89/reg.h +++ b/drivers/net/wireless/realtek/rtw89/reg.h @@ -1891,7 +1891,6 @@ B_AX_B0_IMR_ERR_USRCTL_NOINIT | \ B_AX_B0_IMR_ERR_CMDPSR_1STCMDERR | \ B_AX_B0_IMR_ERR_CMDPSR_CMDTYPE | \ - B_AX_B0_IMR_ERR_CMDPSR_FRZTO | \ B_AX_B0_IMR_ERR_CMDPSR_TBLSZ | \ B_AX_B0_IMR_ERR_MPDUINFO_RECFG | \ B_AX_B0_IMR_ERR_MPDUIF_DATAERR | \ diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c index 5c167a9278ce4..6ebbe48ca50b2 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c @@ -2274,6 +2274,7 @@ static int rtw8851b_mac_disable_bb_rf(struct rtw89_dev *rtwdev) u8 wl_rfc_s1; int ret; + rtw89_write32_clr(rtwdev, R_AX_WLRF_CTRL, B_AX_AFC_AFEDIG); rtw89_write8_clr(rtwdev, R_AX_SYS_FUNC_EN, B_AX_FEN_BBRSTB | B_AX_FEN_BB_GLB_RSTN); diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851be.c b/drivers/net/wireless/realtek/rtw89/rtw8851be.c index ade69bd30fc86..ec3629d95fda1 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8851be.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8851be.c @@ -25,6 +25,8 @@ static const struct rtw89_pci_info rtw8851b_pci_info = { .autok_en = MAC_AX_PCIE_DISABLE, .io_rcy_en = MAC_AX_PCIE_DISABLE, .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, + .rx_ring_eq_is_full = false, + .check_rx_tag = false, .init_cfg_reg = R_AX_PCIE_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN, @@ -61,6 +63,7 @@ static const struct rtw89_pci_info rtw8851b_pci_info = { static const struct rtw89_driver_info rtw89_8851be_info = { .chip = &rtw8851b_chip_info, + .quirks = NULL, .bus = { .pci = &rtw8851b_pci_info, }, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852ae.c b/drivers/net/wireless/realtek/rtw89/rtw8852ae.c index f1e890bde0499..fdee5dd4ba148 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852ae.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852ae.c @@ -26,6 +26,7 @@ static const struct rtw89_pci_info rtw8852a_pci_info = { .io_rcy_en = MAC_AX_PCIE_DISABLE, .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, .rx_ring_eq_is_full = false, + .check_rx_tag = false, .init_cfg_reg = R_AX_PCIE_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN, @@ -60,6 +61,7 @@ static const struct rtw89_pci_info rtw8852a_pci_info = { static const struct rtw89_driver_info rtw89_8852ae_info = { .chip = &rtw8852a_chip_info, + .quirks = NULL, .bus = { .pci = &rtw8852a_pci_info, }, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c index de887a35f3fb4..491527e3c7a3c 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c @@ -550,6 +550,7 @@ static int rtw8852b_pwr_off_func(struct rtw89_dev *rtwdev) return ret; rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_EN_WLON); + rtw89_write32_clr(rtwdev, R_AX_WLRF_CTRL, B_AX_AFC_AFEDIG); rtw89_write8_clr(rtwdev, R_AX_SYS_FUNC_EN, B_AX_FEN_BB_GLB_RSTN | B_AX_FEN_BBRSTB); rtw89_write32_clr(rtwdev, R_AX_SYS_ADIE_PAD_PWR_CTRL, B_AX_SYM_PADPDN_WL_RFC_1P3); @@ -2443,6 +2444,7 @@ static int rtw8852b_mac_disable_bb_rf(struct rtw89_dev *rtwdev) u8 wl_rfc_s1; int ret; + rtw89_write32_clr(rtwdev, R_AX_WLRF_CTRL, B_AX_AFC_AFEDIG); rtw89_write8_clr(rtwdev, R_AX_SYS_FUNC_EN, B_AX_FEN_BBRSTB | B_AX_FEN_BB_GLB_RSTN); diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852be.c b/drivers/net/wireless/realtek/rtw89/rtw8852be.c index 920b20bbcfb73..5f941122655c4 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852be.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852be.c @@ -26,6 +26,7 @@ static const struct rtw89_pci_info rtw8852b_pci_info = { .io_rcy_en = MAC_AX_PCIE_DISABLE, .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, .rx_ring_eq_is_full = false, + .check_rx_tag = false, .init_cfg_reg = R_AX_PCIE_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN, @@ -62,6 +63,7 @@ static const struct rtw89_pci_info rtw8852b_pci_info = { static const struct rtw89_driver_info rtw89_8852be_info = { .chip = &rtw8852b_chip_info, + .quirks = NULL, .bus = { .pci = &rtw8852b_pci_info, }, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c index 8618d0204f665..619de4e420a3d 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c @@ -203,6 +203,9 @@ static int rtw8852c_pwr_on_func(struct rtw89_dev *rtwdev) rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APDM_HPDN); rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APFM_SWLPS); + rtw89_write32_mask(rtwdev, R_AX_SPS_DIG_ON_CTRL0, + B_AX_OCP_L1_MASK, 0x7); + ret = read_poll_timeout(rtw89_read32, val32, val32 & B_AX_RDY_SYSPWR, 1000, 20000, false, rtwdev, R_AX_SYS_PW_CTRL); if (ret) @@ -266,7 +269,7 @@ static int rtw8852c_pwr_on_func(struct rtw89_dev *rtwdev) ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_SRAM2RFC); if (ret) return ret; - ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_XTAL_XMD_2, 0, XTAL_SI_LDO_LPS); + ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_XTAL_XMD_2, 0x10, XTAL_SI_LDO_LPS); if (ret) return ret; ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_XTAL_XMD_4, 0, XTAL_SI_LPS_CAP); @@ -338,6 +341,7 @@ static int rtw8852c_pwr_off_func(struct rtw89_dev *rtwdev) return ret; rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_EN_WLON); + rtw89_write32_clr(rtwdev, R_AX_WLRF_CTRL, B_AX_AFC_AFEDIG); rtw89_write8_clr(rtwdev, R_AX_SYS_FUNC_EN, B_AX_FEN_BB_GLB_RSTN | B_AX_FEN_BBRSTB); rtw89_write32_clr(rtwdev, R_AX_SYS_ISO_CTRL_EXTEND, B_AX_R_SYM_FEN_WLBBGLB_1 | B_AX_R_SYM_FEN_WLBBFUN_1); @@ -360,8 +364,11 @@ static int rtw8852c_pwr_off_func(struct rtw89_dev *rtwdev) if (ret) return ret; - rtw89_write32(rtwdev, R_AX_WLLPS_CTRL, 0x0001A0B0); + rtw89_write32(rtwdev, R_AX_WLLPS_CTRL, SW_LPS_OPTION); rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_XTAL_OFF_A_DIE); + rtw89_write32_set(rtwdev, R_AX_SYS_SWR_CTRL1, B_AX_SYM_CTRL_SPS_PWMFREQ); + rtw89_write32_mask(rtwdev, R_AX_SPS_DIG_ON_CTRL0, + B_AX_REG_ZCDC_H_MASK, 0x3); rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APFM_SWLPS); return 0; @@ -2790,6 +2797,7 @@ static int rtw8852c_mac_enable_bb_rf(struct rtw89_dev *rtwdev) static int rtw8852c_mac_disable_bb_rf(struct rtw89_dev *rtwdev) { + rtw89_write32_clr(rtwdev, R_AX_WLRF_CTRL, B_AX_AFC_AFEDIG); rtw89_write8_clr(rtwdev, R_AX_SYS_FUNC_EN, B_AX_FEN_BBRSTB | B_AX_FEN_BB_GLB_RSTN); diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852ce.c b/drivers/net/wireless/realtek/rtw89/rtw8852ce.c index 4592de3dbd942..e07c7f3ade41e 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852ce.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852ce.c @@ -35,6 +35,7 @@ static const struct rtw89_pci_info rtw8852c_pci_info = { .io_rcy_en = MAC_AX_PCIE_ENABLE, .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_6MS, .rx_ring_eq_is_full = false, + .check_rx_tag = false, .init_cfg_reg = R_AX_HAXI_INIT_CFG1, .txhci_en_bit = B_AX_TXHCI_EN_V1, @@ -67,8 +68,31 @@ static const struct rtw89_pci_info rtw8852c_pci_info = { .recognize_intrs = rtw89_pci_recognize_intrs_v1, }; +static const struct dmi_system_id rtw8852c_pci_quirks[] = { + { + .ident = "Dell Inc. Vostro 16 5640", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 16 5640"), + DMI_MATCH(DMI_PRODUCT_SKU, "0CA0"), + }, + .driver_data = (void *)RTW89_QUIRK_PCI_BER, + }, + { + .ident = "Dell Inc. Inspiron 16 5640", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 16 5640"), + DMI_MATCH(DMI_PRODUCT_SKU, "0C9F"), + }, + .driver_data = (void *)RTW89_QUIRK_PCI_BER, + }, + {}, +}; + static const struct rtw89_driver_info rtw89_8852ce_info = { .chip = &rtw8852c_chip_info, + .quirks = rtw8852c_pci_quirks, .bus = { .pci = &rtw8852c_pci_info, }, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922ae.c b/drivers/net/wireless/realtek/rtw89/rtw8922ae.c index 7b3d98d2c402c..15ea8e20dde36 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8922ae.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8922ae.c @@ -26,6 +26,7 @@ static const struct rtw89_pci_info rtw8922a_pci_info = { .io_rcy_en = MAC_AX_PCIE_ENABLE, .io_rcy_tmr = MAC_AX_IO_RCY_ANA_TMR_DEF, .rx_ring_eq_is_full = true, + .check_rx_tag = true, .init_cfg_reg = R_BE_HAXI_INIT_CFG1, .txhci_en_bit = B_BE_TXDMA_EN, @@ -60,6 +61,7 @@ static const struct rtw89_pci_info rtw8922a_pci_info = { static const struct rtw89_driver_info rtw89_8922ae_info = { .chip = &rtw8922a_chip_info, + .quirks = NULL, .bus = { .pci = &rtw8922a_pci_info, }, diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c index 5c7ca36c09b6b..abb4d1cc55d0e 100644 --- a/drivers/net/wireless/realtek/rtw89/wow.c +++ b/drivers/net/wireless/realtek/rtw89/wow.c @@ -489,14 +489,17 @@ static int rtw89_wow_swap_fw(struct rtw89_dev *rtwdev, bool wow) struct rtw89_wow_param *rtw_wow = &rtwdev->wow; struct ieee80211_vif *wow_vif = rtw_wow->wow_vif; struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv; + enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id; const struct rtw89_chip_info *chip = rtwdev->chip; bool include_bb = !!chip->bbmcu_nr; + bool disable_intr_for_dlfw = false; struct ieee80211_sta *wow_sta; struct rtw89_sta *rtwsta = NULL; bool is_conn = true; int ret; - rtw89_hci_disable_intr(rtwdev); + if (chip_id == RTL8852C || chip_id == RTL8922A) + disable_intr_for_dlfw = true; wow_sta = ieee80211_find_sta(wow_vif, rtwvif->bssid); if (wow_sta) @@ -504,12 +507,18 @@ static int rtw89_wow_swap_fw(struct rtw89_dev *rtwdev, bool wow) else is_conn = false; + if (disable_intr_for_dlfw) + rtw89_hci_disable_intr(rtwdev); + ret = rtw89_fw_download(rtwdev, fw_type, include_bb); if (ret) { rtw89_warn(rtwdev, "download fw failed\n"); return ret; } + if (disable_intr_for_dlfw) + rtw89_hci_enable_intr(rtwdev); + rtw89_phy_init_rf_reg(rtwdev, true); ret = rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, rtwsta, @@ -552,7 +561,6 @@ static int rtw89_wow_swap_fw(struct rtw89_dev *rtwdev, bool wow) } rtw89_mac_hw_mgnt_sec(rtwdev, wow); - rtw89_hci_enable_intr(rtwdev); return 0; } diff --git a/drivers/net/wireless/silabs/wfx/sta.c b/drivers/net/wireless/silabs/wfx/sta.c index 537caf9d914a7..bb4446b88c12b 100644 --- a/drivers/net/wireless/silabs/wfx/sta.c +++ b/drivers/net/wireless/silabs/wfx/sta.c @@ -344,6 +344,7 @@ static int wfx_set_mfp_ap(struct wfx_vif *wvif) const int pairwise_cipher_suite_count_offset = 8 / sizeof(u16); const int pairwise_cipher_suite_size = 4 / sizeof(u16); const int akm_suite_size = 4 / sizeof(u16); + int ret = -EINVAL; const u16 *ptr; if (unlikely(!skb)) @@ -352,22 +353,26 @@ static int wfx_set_mfp_ap(struct wfx_vif *wvif) ptr = (u16 *)cfg80211_find_ie(WLAN_EID_RSN, skb->data + ieoffset, skb->len - ieoffset); if (unlikely(!ptr)) - return -EINVAL; + goto free_skb; ptr += pairwise_cipher_suite_count_offset; if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return -EINVAL; + goto free_skb; ptr += 1 + pairwise_cipher_suite_size * *ptr; if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return -EINVAL; + goto free_skb; ptr += 1 + akm_suite_size * *ptr; if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb))) - return -EINVAL; + goto free_skb; wfx_hif_set_mfp(wvif, *ptr & BIT(7), *ptr & BIT(6)); - return 0; + ret = 0; + +free_skb: + dev_kfree_skb(skb); + return ret; } int wfx_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif, diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index a84340c2075ff..a9c3fb2ccdcdb 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -3818,7 +3818,7 @@ static int hwsim_pmsr_report_nl(struct sk_buff *msg, struct genl_info *info) } nla_for_each_nested(peer, peers, rem) { - struct cfg80211_pmsr_result result; + struct cfg80211_pmsr_result result = {}; err = mac80211_hwsim_parse_pmsr_result(peer, &result, info); if (err) diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.c b/drivers/net/wwan/iosm/iosm_ipc_devlink.c index 2fe724d623c06..33c5a46f1b922 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_devlink.c +++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.c @@ -210,7 +210,7 @@ static int ipc_devlink_create_region(struct iosm_devlink *devlink) rc = PTR_ERR(devlink->cd_regions[i]); dev_err(devlink->dev, "Devlink region fail,err %d", rc); /* Delete previously created regions */ - for ( ; i >= 0; i--) + for (i--; i >= 0; i--) devlink_region_destroy(devlink->cd_regions[i]); goto region_create_fail; } diff --git a/drivers/net/wwan/t7xx/t7xx_cldma.c b/drivers/net/wwan/t7xx/t7xx_cldma.c index 9f43f256db1d0..f0a4783baf1f3 100644 --- a/drivers/net/wwan/t7xx/t7xx_cldma.c +++ b/drivers/net/wwan/t7xx/t7xx_cldma.c @@ -106,7 +106,7 @@ bool t7xx_cldma_tx_addr_is_set(struct t7xx_cldma_hw *hw_info, unsigned int qno) { u32 offset = REG_CLDMA_UL_START_ADDRL_0 + qno * ADDR_SIZE; - return ioread64(hw_info->ap_pdn_base + offset); + return ioread64_lo_hi(hw_info->ap_pdn_base + offset); } void t7xx_cldma_hw_set_start_addr(struct t7xx_cldma_hw *hw_info, unsigned int qno, u64 address, @@ -117,7 +117,7 @@ void t7xx_cldma_hw_set_start_addr(struct t7xx_cldma_hw *hw_info, unsigned int qn reg = tx_rx == MTK_RX ? hw_info->ap_ao_base + REG_CLDMA_DL_START_ADDRL_0 : hw_info->ap_pdn_base + REG_CLDMA_UL_START_ADDRL_0; - iowrite64(address, reg + offset); + iowrite64_lo_hi(address, reg + offset); } void t7xx_cldma_hw_resume_queue(struct t7xx_cldma_hw *hw_info, unsigned int qno, diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c index cc70360364b7d..97163e1e5783e 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c @@ -57,8 +57,6 @@ #define CHECK_Q_STOP_TIMEOUT_US 1000000 #define CHECK_Q_STOP_STEP_US 10000 -#define CLDMA_JUMBO_BUFF_SZ (63 * 1024 + sizeof(struct ccci_header)) - static void md_cd_queue_struct_reset(struct cldma_queue *queue, struct cldma_ctrl *md_ctrl, enum mtk_txrx tx_rx, unsigned int index) { @@ -139,8 +137,9 @@ static int t7xx_cldma_gpd_rx_from_q(struct cldma_queue *queue, int budget, bool return -ENODEV; } - gpd_addr = ioread64(hw_info->ap_pdn_base + REG_CLDMA_DL_CURRENT_ADDRL_0 + - queue->index * sizeof(u64)); + gpd_addr = ioread64_lo_hi(hw_info->ap_pdn_base + + REG_CLDMA_DL_CURRENT_ADDRL_0 + + queue->index * sizeof(u64)); if (req->gpd_addr == gpd_addr || hwo_polling_count++ >= 100) return 0; @@ -161,7 +160,7 @@ static int t7xx_cldma_gpd_rx_from_q(struct cldma_queue *queue, int budget, bool skb_reset_tail_pointer(skb); skb_put(skb, le16_to_cpu(gpd->data_buff_len)); - ret = md_ctrl->recv_skb(queue, skb); + ret = queue->recv_skb(queue, skb); /* Break processing, will try again later */ if (ret < 0) return ret; @@ -318,8 +317,8 @@ static void t7xx_cldma_txq_empty_hndl(struct cldma_queue *queue) struct t7xx_cldma_hw *hw_info = &md_ctrl->hw_info; /* Check current processing TGPD, 64-bit address is in a table by Q index */ - ul_curr_addr = ioread64(hw_info->ap_pdn_base + REG_CLDMA_UL_CURRENT_ADDRL_0 + - queue->index * sizeof(u64)); + ul_curr_addr = ioread64_lo_hi(hw_info->ap_pdn_base + REG_CLDMA_UL_CURRENT_ADDRL_0 + + queue->index * sizeof(u64)); if (req->gpd_addr != ul_curr_addr) { spin_unlock_irqrestore(&md_ctrl->cldma_lock, flags); dev_err(md_ctrl->dev, "CLDMA%d queue %d is not empty\n", @@ -897,13 +896,13 @@ static void t7xx_cldma_hw_start_send(struct cldma_ctrl *md_ctrl, int qno, /** * t7xx_cldma_set_recv_skb() - Set the callback to handle RX packets. - * @md_ctrl: CLDMA context structure. + * @queue: CLDMA queue. * @recv_skb: Receiving skb callback. */ -void t7xx_cldma_set_recv_skb(struct cldma_ctrl *md_ctrl, +void t7xx_cldma_set_recv_skb(struct cldma_queue *queue, int (*recv_skb)(struct cldma_queue *queue, struct sk_buff *skb)) { - md_ctrl->recv_skb = recv_skb; + queue->recv_skb = recv_skb; } /** @@ -993,6 +992,28 @@ int t7xx_cldma_send_skb(struct cldma_ctrl *md_ctrl, int qno, struct sk_buff *skb return ret; } +static void t7xx_cldma_adjust_config(struct cldma_ctrl *md_ctrl, enum cldma_cfg cfg_id) +{ + int qno; + + for (qno = 0; qno < CLDMA_RXQ_NUM; qno++) { + md_ctrl->rx_ring[qno].pkt_size = CLDMA_SHARED_Q_BUFF_SZ; + t7xx_cldma_set_recv_skb(&md_ctrl->rxq[qno], t7xx_port_proxy_recv_skb); + } + + md_ctrl->rx_ring[CLDMA_RXQ_NUM - 1].pkt_size = CLDMA_JUMBO_BUFF_SZ; + + for (qno = 0; qno < CLDMA_TXQ_NUM; qno++) + md_ctrl->tx_ring[qno].pkt_size = CLDMA_SHARED_Q_BUFF_SZ; + + if (cfg_id == CLDMA_DEDICATED_Q_CFG) { + md_ctrl->tx_ring[CLDMA_Q_IDX_DUMP].pkt_size = CLDMA_DEDICATED_Q_BUFF_SZ; + md_ctrl->rx_ring[CLDMA_Q_IDX_DUMP].pkt_size = CLDMA_DEDICATED_Q_BUFF_SZ; + t7xx_cldma_set_recv_skb(&md_ctrl->rxq[CLDMA_Q_IDX_DUMP], + t7xx_port_proxy_recv_skb_from_dedicated_queue); + } +} + static int t7xx_cldma_late_init(struct cldma_ctrl *md_ctrl) { char dma_pool_name[32]; @@ -1018,16 +1039,9 @@ static int t7xx_cldma_late_init(struct cldma_ctrl *md_ctrl) dev_err(md_ctrl->dev, "control TX ring init fail\n"); goto err_free_tx_ring; } - - md_ctrl->tx_ring[i].pkt_size = CLDMA_MTU; } for (j = 0; j < CLDMA_RXQ_NUM; j++) { - md_ctrl->rx_ring[j].pkt_size = CLDMA_MTU; - - if (j == CLDMA_RXQ_NUM - 1) - md_ctrl->rx_ring[j].pkt_size = CLDMA_JUMBO_BUFF_SZ; - ret = t7xx_cldma_rx_ring_init(md_ctrl, &md_ctrl->rx_ring[j]); if (ret) { dev_err(md_ctrl->dev, "Control RX ring init fail\n"); @@ -1094,6 +1108,7 @@ int t7xx_cldma_alloc(enum cldma_id hif_id, struct t7xx_pci_dev *t7xx_dev) { struct device *dev = &t7xx_dev->pdev->dev; struct cldma_ctrl *md_ctrl; + int qno; md_ctrl = devm_kzalloc(dev, sizeof(*md_ctrl), GFP_KERNEL); if (!md_ctrl) @@ -1102,7 +1117,9 @@ int t7xx_cldma_alloc(enum cldma_id hif_id, struct t7xx_pci_dev *t7xx_dev) md_ctrl->t7xx_dev = t7xx_dev; md_ctrl->dev = dev; md_ctrl->hif_id = hif_id; - md_ctrl->recv_skb = t7xx_cldma_default_recv_skb; + for (qno = 0; qno < CLDMA_RXQ_NUM; qno++) + md_ctrl->rxq[qno].recv_skb = t7xx_cldma_default_recv_skb; + t7xx_hw_info_init(md_ctrl); t7xx_dev->md->md_ctrl[hif_id] = md_ctrl; return 0; @@ -1332,9 +1349,10 @@ int t7xx_cldma_init(struct cldma_ctrl *md_ctrl) return -ENOMEM; } -void t7xx_cldma_switch_cfg(struct cldma_ctrl *md_ctrl) +void t7xx_cldma_switch_cfg(struct cldma_ctrl *md_ctrl, enum cldma_cfg cfg_id) { t7xx_cldma_late_release(md_ctrl); + t7xx_cldma_adjust_config(md_ctrl, cfg_id); t7xx_cldma_late_init(md_ctrl); } diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.h b/drivers/net/wwan/t7xx/t7xx_hif_cldma.h index 4410bac6993ae..f2d9941be9c83 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.h +++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.h @@ -31,6 +31,10 @@ #include "t7xx_cldma.h" #include "t7xx_pci.h" +#define CLDMA_JUMBO_BUFF_SZ (63 * 1024 + sizeof(struct ccci_header)) +#define CLDMA_SHARED_Q_BUFF_SZ 3584 +#define CLDMA_DEDICATED_Q_BUFF_SZ 2048 + /** * enum cldma_id - Identifiers for CLDMA HW units. * @CLDMA_ID_MD: Modem control channel. @@ -55,6 +59,11 @@ struct cldma_gpd { __le16 not_used2; }; +enum cldma_cfg { + CLDMA_SHARED_Q_CFG, + CLDMA_DEDICATED_Q_CFG, +}; + struct cldma_request { struct cldma_gpd *gpd; /* Virtual address for CPU */ dma_addr_t gpd_addr; /* Physical address for DMA */ @@ -82,6 +91,7 @@ struct cldma_queue { wait_queue_head_t req_wq; /* Only for TX */ struct workqueue_struct *worker; struct work_struct cldma_work; + int (*recv_skb)(struct cldma_queue *queue, struct sk_buff *skb); }; struct cldma_ctrl { @@ -101,24 +111,22 @@ struct cldma_ctrl { struct md_pm_entity *pm_entity; struct t7xx_cldma_hw hw_info; bool is_late_init; - int (*recv_skb)(struct cldma_queue *queue, struct sk_buff *skb); }; +#define CLDMA_Q_IDX_DUMP 1 #define GPD_FLAGS_HWO BIT(0) #define GPD_FLAGS_IOC BIT(7) #define GPD_DMAPOOL_ALIGN 16 -#define CLDMA_MTU 3584 /* 3.5kB */ - int t7xx_cldma_alloc(enum cldma_id hif_id, struct t7xx_pci_dev *t7xx_dev); void t7xx_cldma_hif_hw_init(struct cldma_ctrl *md_ctrl); int t7xx_cldma_init(struct cldma_ctrl *md_ctrl); void t7xx_cldma_exit(struct cldma_ctrl *md_ctrl); -void t7xx_cldma_switch_cfg(struct cldma_ctrl *md_ctrl); +void t7xx_cldma_switch_cfg(struct cldma_ctrl *md_ctrl, enum cldma_cfg cfg_id); void t7xx_cldma_start(struct cldma_ctrl *md_ctrl); int t7xx_cldma_stop(struct cldma_ctrl *md_ctrl); void t7xx_cldma_reset(struct cldma_ctrl *md_ctrl); -void t7xx_cldma_set_recv_skb(struct cldma_ctrl *md_ctrl, +void t7xx_cldma_set_recv_skb(struct cldma_queue *queue, int (*recv_skb)(struct cldma_queue *queue, struct sk_buff *skb)); int t7xx_cldma_send_skb(struct cldma_ctrl *md_ctrl, int qno, struct sk_buff *skb); void t7xx_cldma_stop_all_qs(struct cldma_ctrl *md_ctrl, enum mtk_txrx tx_rx); diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c index 24e7d491468e0..8d864d4ed77f5 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c @@ -177,6 +177,11 @@ int t7xx_acpi_fldr_func(struct t7xx_pci_dev *t7xx_dev) return t7xx_acpi_reset(t7xx_dev, "_RST"); } +int t7xx_acpi_pldr_func(struct t7xx_pci_dev *t7xx_dev) +{ + return t7xx_acpi_reset(t7xx_dev, "MRST._RST"); +} + static void t7xx_reset_device_via_pmic(struct t7xx_pci_dev *t7xx_dev) { u32 val; @@ -192,6 +197,7 @@ static irqreturn_t t7xx_rgu_isr_thread(int irq, void *data) { struct t7xx_pci_dev *t7xx_dev = data; + t7xx_mode_update(t7xx_dev, T7XX_RESET); msleep(RGU_RESET_DELAY_MS); t7xx_reset_device_via_pmic(t7xx_dev); return IRQ_HANDLED; @@ -529,7 +535,7 @@ static void t7xx_md_hk_wq(struct work_struct *work) /* Clear the HS2 EXIT event appended in core_reset() */ t7xx_fsm_clr_event(ctl, FSM_EVENT_MD_HS2_EXIT); - t7xx_cldma_switch_cfg(md->md_ctrl[CLDMA_ID_MD]); + t7xx_cldma_switch_cfg(md->md_ctrl[CLDMA_ID_MD], CLDMA_SHARED_Q_CFG); t7xx_cldma_start(md->md_ctrl[CLDMA_ID_MD]); t7xx_fsm_broadcast_state(ctl, MD_STATE_WAITING_FOR_HS2); md->core_md.handshake_ongoing = true; @@ -544,7 +550,7 @@ static void t7xx_ap_hk_wq(struct work_struct *work) /* Clear the HS2 EXIT event appended in t7xx_core_reset(). */ t7xx_fsm_clr_event(ctl, FSM_EVENT_AP_HS2_EXIT); t7xx_cldma_stop(md->md_ctrl[CLDMA_ID_AP]); - t7xx_cldma_switch_cfg(md->md_ctrl[CLDMA_ID_AP]); + t7xx_cldma_switch_cfg(md->md_ctrl[CLDMA_ID_AP], CLDMA_SHARED_Q_CFG); t7xx_cldma_start(md->md_ctrl[CLDMA_ID_AP]); md->core_ap.handshake_ongoing = true; t7xx_core_hk_handler(md, &md->core_ap, ctl, FSM_EVENT_AP_HS2, FSM_EVENT_AP_HS2_EXIT); @@ -758,6 +764,7 @@ int t7xx_md_init(struct t7xx_pci_dev *t7xx_dev) void t7xx_md_exit(struct t7xx_pci_dev *t7xx_dev) { + enum t7xx_mode mode = READ_ONCE(t7xx_dev->mode); struct t7xx_modem *md = t7xx_dev->md; t7xx_pcie_mac_clear_int(t7xx_dev, SAP_RGU_INT); @@ -765,7 +772,8 @@ void t7xx_md_exit(struct t7xx_pci_dev *t7xx_dev) if (!md->md_init_finish) return; - t7xx_fsm_append_cmd(md->fsm_ctl, FSM_CMD_PRE_STOP, FSM_CMD_FLAG_WAIT_FOR_COMPLETION); + if (mode != T7XX_RESET && mode != T7XX_UNKNOWN) + t7xx_fsm_append_cmd(md->fsm_ctl, FSM_CMD_PRE_STOP, FSM_CMD_FLAG_WAIT_FOR_COMPLETION); t7xx_port_proxy_uninit(md->port_prox); t7xx_cldma_exit(md->md_ctrl[CLDMA_ID_AP]); t7xx_cldma_exit(md->md_ctrl[CLDMA_ID_MD]); diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.h b/drivers/net/wwan/t7xx/t7xx_modem_ops.h index abe633cf7adc0..b39e945a92e01 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.h +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.h @@ -85,6 +85,7 @@ int t7xx_md_init(struct t7xx_pci_dev *t7xx_dev); void t7xx_md_exit(struct t7xx_pci_dev *t7xx_dev); void t7xx_clear_rgu_irq(struct t7xx_pci_dev *t7xx_dev); int t7xx_acpi_fldr_func(struct t7xx_pci_dev *t7xx_dev); +int t7xx_acpi_pldr_func(struct t7xx_pci_dev *t7xx_dev); int t7xx_pci_mhccif_isr(struct t7xx_pci_dev *t7xx_dev); #endif /* __T7XX_MODEM_OPS_H__ */ diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 91256e005b846..e0b1e7a616cae 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -52,6 +52,81 @@ #define PM_RESOURCE_POLL_TIMEOUT_US 10000 #define PM_RESOURCE_POLL_STEP_US 100 +static const char * const t7xx_mode_names[] = { + [T7XX_UNKNOWN] = "unknown", + [T7XX_READY] = "ready", + [T7XX_RESET] = "reset", + [T7XX_FASTBOOT_SWITCHING] = "fastboot_switching", + [T7XX_FASTBOOT_DOWNLOAD] = "fastboot_download", + [T7XX_FASTBOOT_DUMP] = "fastboot_dump", +}; + +static_assert(ARRAY_SIZE(t7xx_mode_names) == T7XX_MODE_LAST); + +static ssize_t t7xx_mode_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct t7xx_pci_dev *t7xx_dev; + struct pci_dev *pdev; + int index = 0; + + pdev = to_pci_dev(dev); + t7xx_dev = pci_get_drvdata(pdev); + if (!t7xx_dev) + return -ENODEV; + + index = sysfs_match_string(t7xx_mode_names, buf); + if (index == T7XX_FASTBOOT_SWITCHING) { + WRITE_ONCE(t7xx_dev->mode, T7XX_FASTBOOT_SWITCHING); + } else if (index == T7XX_RESET) { + WRITE_ONCE(t7xx_dev->mode, T7XX_RESET); + t7xx_acpi_pldr_func(t7xx_dev); + } + + return count; +}; + +static ssize_t t7xx_mode_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + enum t7xx_mode mode = T7XX_UNKNOWN; + struct t7xx_pci_dev *t7xx_dev; + struct pci_dev *pdev; + + pdev = to_pci_dev(dev); + t7xx_dev = pci_get_drvdata(pdev); + if (!t7xx_dev) + return -ENODEV; + + mode = READ_ONCE(t7xx_dev->mode); + if (mode < T7XX_MODE_LAST) + return sysfs_emit(buf, "%s\n", t7xx_mode_names[mode]); + + return sysfs_emit(buf, "%s\n", t7xx_mode_names[T7XX_UNKNOWN]); +} + +static DEVICE_ATTR_RW(t7xx_mode); + +static struct attribute *t7xx_mode_attr[] = { + &dev_attr_t7xx_mode.attr, + NULL +}; + +static const struct attribute_group t7xx_mode_attribute_group = { + .attrs = t7xx_mode_attr, +}; + +void t7xx_mode_update(struct t7xx_pci_dev *t7xx_dev, enum t7xx_mode mode) +{ + if (!t7xx_dev) + return; + + WRITE_ONCE(t7xx_dev->mode, mode); + sysfs_notify(&t7xx_dev->pdev->dev.kobj, NULL, "t7xx_mode"); +} + enum t7xx_pm_state { MTK_PM_EXCEPTION, MTK_PM_INIT, /* Device initialized, but handshake not completed */ @@ -108,7 +183,7 @@ static int t7xx_pci_pm_init(struct t7xx_pci_dev *t7xx_dev) pm_runtime_set_autosuspend_delay(&pdev->dev, PM_AUTOSUSPEND_MS); pm_runtime_use_autosuspend(&pdev->dev); - return t7xx_wait_pm_config(t7xx_dev); + return 0; } void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev) @@ -279,7 +354,8 @@ static int __t7xx_pci_pm_suspend(struct pci_dev *pdev) int ret; t7xx_dev = pci_get_drvdata(pdev); - if (atomic_read(&t7xx_dev->md_pm_state) <= MTK_PM_INIT) { + if (atomic_read(&t7xx_dev->md_pm_state) <= MTK_PM_INIT || + READ_ONCE(t7xx_dev->mode) != T7XX_READY) { dev_err(&pdev->dev, "[PM] Exiting suspend, modem in invalid state\n"); return -EFAULT; } @@ -729,16 +805,28 @@ static int t7xx_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) t7xx_pcie_mac_interrupts_dis(t7xx_dev); + ret = sysfs_create_group(&t7xx_dev->pdev->dev.kobj, + &t7xx_mode_attribute_group); + if (ret) + goto err_md_exit; + ret = t7xx_interrupt_init(t7xx_dev); - if (ret) { - t7xx_md_exit(t7xx_dev); - return ret; - } + if (ret) + goto err_remove_group; + t7xx_pcie_mac_set_int(t7xx_dev, MHCCIF_INT); t7xx_pcie_mac_interrupts_en(t7xx_dev); return 0; + +err_remove_group: + sysfs_remove_group(&t7xx_dev->pdev->dev.kobj, + &t7xx_mode_attribute_group); + +err_md_exit: + t7xx_md_exit(t7xx_dev); + return ret; } static void t7xx_pci_remove(struct pci_dev *pdev) @@ -747,6 +835,9 @@ static void t7xx_pci_remove(struct pci_dev *pdev) int i; t7xx_dev = pci_get_drvdata(pdev); + + sysfs_remove_group(&t7xx_dev->pdev->dev.kobj, + &t7xx_mode_attribute_group); t7xx_md_exit(t7xx_dev); for (i = 0; i < EXT_INT_NUM; i++) { diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h index f08f1ab744691..49a11586d8d84 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.h +++ b/drivers/net/wwan/t7xx/t7xx_pci.h @@ -43,6 +43,16 @@ struct t7xx_addr_base { typedef irqreturn_t (*t7xx_intr_callback)(int irq, void *param); +enum t7xx_mode { + T7XX_UNKNOWN, + T7XX_READY, + T7XX_RESET, + T7XX_FASTBOOT_SWITCHING, + T7XX_FASTBOOT_DOWNLOAD, + T7XX_FASTBOOT_DUMP, + T7XX_MODE_LAST, /* must always be last */ +}; + /* struct t7xx_pci_dev - MTK device context structure * @intr_handler: array of handler function for request_threaded_irq * @intr_thread: array of thread_fn for request_threaded_irq @@ -59,6 +69,7 @@ typedef irqreturn_t (*t7xx_intr_callback)(int irq, void *param); * @md_pm_lock: protects PCIe sleep lock * @sleep_disable_count: PCIe L1.2 lock counter * @sleep_lock_acquire: indicates that sleep has been disabled + * @mode: indicates the device mode */ struct t7xx_pci_dev { t7xx_intr_callback intr_handler[EXT_INT_NUM]; @@ -82,6 +93,7 @@ struct t7xx_pci_dev { #ifdef CONFIG_WWAN_DEBUGFS struct dentry *debugfs_dir; #endif + u32 mode; }; enum t7xx_pm_id { @@ -120,5 +132,5 @@ int t7xx_pci_pm_entity_register(struct t7xx_pci_dev *t7xx_dev, struct md_pm_enti int t7xx_pci_pm_entity_unregister(struct t7xx_pci_dev *t7xx_dev, struct md_pm_entity *pm_entity); void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev); void t7xx_pci_pm_exp_detected(struct t7xx_pci_dev *t7xx_dev); - +void t7xx_mode_update(struct t7xx_pci_dev *t7xx_dev, enum t7xx_mode mode); #endif /* __T7XX_PCI_H__ */ diff --git a/drivers/net/wwan/t7xx/t7xx_pcie_mac.c b/drivers/net/wwan/t7xx/t7xx_pcie_mac.c index 76da4c15e3de1..f071ec7ff23d5 100644 --- a/drivers/net/wwan/t7xx/t7xx_pcie_mac.c +++ b/drivers/net/wwan/t7xx/t7xx_pcie_mac.c @@ -75,7 +75,7 @@ static void t7xx_pcie_mac_atr_tables_dis(void __iomem *pbase, enum t7xx_atr_src_ for (i = 0; i < ATR_TABLE_NUM_PER_ATR; i++) { offset = ATR_PORT_OFFSET * port + ATR_TABLE_OFFSET * i; reg = pbase + ATR_PCIE_WIN0_T0_ATR_PARAM_SRC_ADDR + offset; - iowrite64(0, reg); + iowrite64_lo_hi(0, reg); } } @@ -112,17 +112,17 @@ static int t7xx_pcie_mac_atr_cfg(struct t7xx_pci_dev *t7xx_dev, struct t7xx_atr_ reg = pbase + ATR_PCIE_WIN0_T0_TRSL_ADDR + offset; value = cfg->trsl_addr & ATR_PCIE_WIN0_ADDR_ALGMT; - iowrite64(value, reg); + iowrite64_lo_hi(value, reg); reg = pbase + ATR_PCIE_WIN0_T0_TRSL_PARAM + offset; iowrite32(cfg->trsl_id, reg); reg = pbase + ATR_PCIE_WIN0_T0_ATR_PARAM_SRC_ADDR + offset; value = (cfg->src_addr & ATR_PCIE_WIN0_ADDR_ALGMT) | (atr_size << 1) | BIT(0); - iowrite64(value, reg); + iowrite64_lo_hi(value, reg); /* Ensure ATR is set */ - ioread64(reg); + ioread64_lo_hi(reg); return 0; } diff --git a/drivers/net/wwan/t7xx/t7xx_port.h b/drivers/net/wwan/t7xx/t7xx_port.h index 4ae8a00a85322..f74d3bab810d8 100644 --- a/drivers/net/wwan/t7xx/t7xx_port.h +++ b/drivers/net/wwan/t7xx/t7xx_port.h @@ -75,6 +75,8 @@ enum port_ch { PORT_CH_DSS6_TX = 0x20df, PORT_CH_DSS7_RX = 0x20e0, PORT_CH_DSS7_TX = 0x20e1, + + PORT_CH_UNIMPORTANT = 0xffff, }; struct t7xx_port; @@ -135,11 +137,13 @@ struct t7xx_port { }; }; +int t7xx_get_port_mtu(struct t7xx_port *port); struct sk_buff *t7xx_port_alloc_skb(int payload); struct sk_buff *t7xx_ctrl_alloc_skb(int payload); int t7xx_port_enqueue_skb(struct t7xx_port *port, struct sk_buff *skb); int t7xx_port_send_skb(struct t7xx_port *port, struct sk_buff *skb, unsigned int pkt_header, unsigned int ex_msg); +int t7xx_port_send_raw_skb(struct t7xx_port *port, struct sk_buff *skb); int t7xx_port_send_ctl_skb(struct t7xx_port *port, struct sk_buff *skb, unsigned int msg, unsigned int ex_msg); diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.c b/drivers/net/wwan/t7xx/t7xx_port_proxy.c index 274846d39fbf3..8f5e01705af29 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_proxy.c +++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.c @@ -48,6 +48,9 @@ i < (proxy)->port_count; \ i++, (p) = &(proxy)->ports[i]) +#define T7XX_MAX_POSSIBLE_PORTS_NUM \ + (max(ARRAY_SIZE(t7xx_port_conf), ARRAY_SIZE(t7xx_early_port_conf))) + static const struct t7xx_port_conf t7xx_port_conf[] = { { .tx_ch = PORT_CH_UART2_TX, @@ -100,6 +103,21 @@ static const struct t7xx_port_conf t7xx_port_conf[] = { }, }; +static const struct t7xx_port_conf t7xx_early_port_conf[] = { + { + .tx_ch = PORT_CH_UNIMPORTANT, + .rx_ch = PORT_CH_UNIMPORTANT, + .txq_index = CLDMA_Q_IDX_DUMP, + .rxq_index = CLDMA_Q_IDX_DUMP, + .txq_exp_index = CLDMA_Q_IDX_DUMP, + .rxq_exp_index = CLDMA_Q_IDX_DUMP, + .path_id = CLDMA_ID_AP, + .ops = &wwan_sub_port_ops, + .name = "fastboot", + .port_type = WWAN_PORT_FASTBOOT, + }, +}; + static struct t7xx_port *t7xx_proxy_get_port_by_ch(struct port_proxy *port_prox, enum port_ch ch) { const struct t7xx_port_conf *port_conf; @@ -214,7 +232,17 @@ int t7xx_port_enqueue_skb(struct t7xx_port *port, struct sk_buff *skb) return 0; } -static int t7xx_port_send_raw_skb(struct t7xx_port *port, struct sk_buff *skb) +int t7xx_get_port_mtu(struct t7xx_port *port) +{ + enum cldma_id path_id = port->port_conf->path_id; + int tx_qno = t7xx_port_get_queue_no(port); + struct cldma_ctrl *md_ctrl; + + md_ctrl = port->t7xx_dev->md->md_ctrl[path_id]; + return md_ctrl->tx_ring[tx_qno].pkt_size; +} + +int t7xx_port_send_raw_skb(struct t7xx_port *port, struct sk_buff *skb) { enum cldma_id path_id = port->port_conf->path_id; struct cldma_ctrl *md_ctrl; @@ -329,6 +357,39 @@ static void t7xx_proxy_setup_ch_mapping(struct port_proxy *port_prox) } } +/** + * t7xx_port_proxy_recv_skb_from_dedicated_queue() - Dispatch early port received skb. + * @queue: CLDMA queue. + * @skb: Socket buffer. + * + * Return: + ** 0 - Packet consumed. + ** -ERROR - Failed to process skb. + */ +int t7xx_port_proxy_recv_skb_from_dedicated_queue(struct cldma_queue *queue, struct sk_buff *skb) +{ + struct t7xx_pci_dev *t7xx_dev = queue->md_ctrl->t7xx_dev; + struct port_proxy *port_prox = t7xx_dev->md->port_prox; + const struct t7xx_port_conf *port_conf; + struct t7xx_port *port; + int ret; + + port = &port_prox->ports[0]; + if (WARN_ON_ONCE(port->port_conf->rxq_index != queue->index)) { + dev_kfree_skb_any(skb); + return -EINVAL; + } + + port_conf = port->port_conf; + ret = port_conf->ops->recv_skb(port, skb); + if (ret < 0 && ret != -ENOBUFS) { + dev_err(port->dev, "drop on RX ch %d, %d\n", port_conf->rx_ch, ret); + dev_kfree_skb_any(skb); + } + + return ret; +} + static struct t7xx_port *t7xx_port_proxy_find_port(struct t7xx_pci_dev *t7xx_dev, struct cldma_queue *queue, u16 channel) { @@ -359,7 +420,7 @@ static struct t7xx_port *t7xx_port_proxy_find_port(struct t7xx_pci_dev *t7xx_dev ** 0 - Packet consumed. ** -ERROR - Failed to process skb. */ -static int t7xx_port_proxy_recv_skb(struct cldma_queue *queue, struct sk_buff *skb) +int t7xx_port_proxy_recv_skb(struct cldma_queue *queue, struct sk_buff *skb) { struct ccci_header *ccci_h = (struct ccci_header *)skb->data; struct t7xx_pci_dev *t7xx_dev = queue->md_ctrl->t7xx_dev; @@ -444,33 +505,54 @@ static void t7xx_proxy_init_all_ports(struct t7xx_modem *md) spin_lock_init(&port->port_update_lock); port->chan_enable = false; - if (port_conf->ops->init) + if (port_conf->ops && port_conf->ops->init) port_conf->ops->init(port); } t7xx_proxy_setup_ch_mapping(port_prox); } +void t7xx_port_proxy_set_cfg(struct t7xx_modem *md, enum port_cfg_id cfg_id) +{ + struct port_proxy *port_prox = md->port_prox; + const struct t7xx_port_conf *port_conf; + u32 port_count; + int i; + + t7xx_port_proxy_uninit(port_prox); + + if (cfg_id == PORT_CFG_ID_EARLY) { + port_conf = t7xx_early_port_conf; + port_count = ARRAY_SIZE(t7xx_early_port_conf); + } else { + port_conf = t7xx_port_conf; + port_count = ARRAY_SIZE(t7xx_port_conf); + } + + for (i = 0; i < port_count; i++) + port_prox->ports[i].port_conf = &port_conf[i]; + + port_prox->cfg_id = cfg_id; + port_prox->port_count = port_count; + + t7xx_proxy_init_all_ports(md); +} + static int t7xx_proxy_alloc(struct t7xx_modem *md) { - unsigned int port_count = ARRAY_SIZE(t7xx_port_conf); struct device *dev = &md->t7xx_dev->pdev->dev; struct port_proxy *port_prox; - int i; - port_prox = devm_kzalloc(dev, sizeof(*port_prox) + sizeof(struct t7xx_port) * port_count, + port_prox = devm_kzalloc(dev, sizeof(*port_prox) + + sizeof(struct t7xx_port) * T7XX_MAX_POSSIBLE_PORTS_NUM, GFP_KERNEL); if (!port_prox) return -ENOMEM; md->port_prox = port_prox; port_prox->dev = dev; + t7xx_port_proxy_set_cfg(md, PORT_CFG_ID_EARLY); - for (i = 0; i < port_count; i++) - port_prox->ports[i].port_conf = &t7xx_port_conf[i]; - - port_prox->port_count = port_count; - t7xx_proxy_init_all_ports(md); return 0; } @@ -492,8 +574,6 @@ int t7xx_port_proxy_init(struct t7xx_modem *md) if (ret) return ret; - t7xx_cldma_set_recv_skb(md->md_ctrl[CLDMA_ID_AP], t7xx_port_proxy_recv_skb); - t7xx_cldma_set_recv_skb(md->md_ctrl[CLDMA_ID_MD], t7xx_port_proxy_recv_skb); return 0; } @@ -505,7 +585,7 @@ void t7xx_port_proxy_uninit(struct port_proxy *port_prox) for_each_proxy_port(i, port, port_prox) { const struct t7xx_port_conf *port_conf = port->port_conf; - if (port_conf->ops->uninit) + if (port_conf->ops && port_conf->ops->uninit) port_conf->ops->uninit(port); } } diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.h b/drivers/net/wwan/t7xx/t7xx_port_proxy.h index 81d059fbc0fb4..7f5706811445b 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_proxy.h +++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.h @@ -31,11 +31,18 @@ #define RX_QUEUE_MAXLEN 32 #define CTRL_QUEUE_MAXLEN 16 +enum port_cfg_id { + PORT_CFG_ID_INVALID, + PORT_CFG_ID_NORMAL, + PORT_CFG_ID_EARLY, +}; + struct port_proxy { int port_count; struct list_head rx_ch_ports[PORT_CH_ID_MASK + 1]; struct list_head queue_ports[CLDMA_NUM][MTK_QUEUES]; struct device *dev; + enum port_cfg_id cfg_id; struct t7xx_port ports[]; }; @@ -98,5 +105,8 @@ void t7xx_port_proxy_md_status_notify(struct port_proxy *port_prox, unsigned int int t7xx_port_enum_msg_handler(struct t7xx_modem *md, void *msg); int t7xx_port_proxy_chl_enable_disable(struct port_proxy *port_prox, unsigned int ch_id, bool en_flag); +void t7xx_port_proxy_set_cfg(struct t7xx_modem *md, enum port_cfg_id cfg_id); +int t7xx_port_proxy_recv_skb(struct cldma_queue *queue, struct sk_buff *skb); +int t7xx_port_proxy_recv_skb_from_dedicated_queue(struct cldma_queue *queue, struct sk_buff *skb); #endif /* __T7XX_PORT_PROXY_H__ */ diff --git a/drivers/net/wwan/t7xx/t7xx_port_wwan.c b/drivers/net/wwan/t7xx/t7xx_port_wwan.c index 17389c8f6600a..4b23ba693f3f1 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_wwan.c +++ b/drivers/net/wwan/t7xx/t7xx_port_wwan.c @@ -2,6 +2,7 @@ /* * Copyright (c) 2021, MediaTek Inc. * Copyright (c) 2021-2022, Intel Corporation. + * Copyright (c) 2024, Fibocom Wireless Inc. * * Authors: * Amir Hanania @@ -15,6 +16,7 @@ * Chiranjeevi Rapolu * Eliot Lee * Sreehari Kancharla + * Jinjian Song */ #include @@ -33,7 +35,7 @@ #include "t7xx_port_proxy.h" #include "t7xx_state_monitor.h" -static int t7xx_port_ctrl_start(struct wwan_port *port) +static int t7xx_port_wwan_start(struct wwan_port *port) { struct t7xx_port *port_mtk = wwan_port_get_drvdata(port); @@ -44,30 +46,60 @@ static int t7xx_port_ctrl_start(struct wwan_port *port) return 0; } -static void t7xx_port_ctrl_stop(struct wwan_port *port) +static void t7xx_port_wwan_stop(struct wwan_port *port) { struct t7xx_port *port_mtk = wwan_port_get_drvdata(port); atomic_dec(&port_mtk->usage_cnt); } -static int t7xx_port_ctrl_tx(struct wwan_port *port, struct sk_buff *skb) +static int t7xx_port_fastboot_tx(struct t7xx_port *port, struct sk_buff *skb) +{ + struct sk_buff *cur = skb, *tx_skb; + size_t actual, len, offset = 0; + int txq_mtu; + int ret; + + txq_mtu = t7xx_get_port_mtu(port); + if (txq_mtu < 0) + return -EINVAL; + + actual = cur->len; + while (actual) { + len = min_t(size_t, actual, txq_mtu); + tx_skb = __dev_alloc_skb(len, GFP_KERNEL); + if (!tx_skb) + return -ENOMEM; + + skb_put_data(tx_skb, cur->data + offset, len); + + ret = t7xx_port_send_raw_skb(port, tx_skb); + if (ret) { + dev_kfree_skb(tx_skb); + dev_err(port->dev, "Write error on fastboot port, %d\n", ret); + break; + } + offset += len; + actual -= len; + } + + dev_kfree_skb(skb); + return 0; +} + +static int t7xx_port_ctrl_tx(struct t7xx_port *port, struct sk_buff *skb) { - struct t7xx_port *port_private = wwan_port_get_drvdata(port); const struct t7xx_port_conf *port_conf; struct sk_buff *cur = skb, *cloned; struct t7xx_fsm_ctl *ctl; enum md_state md_state; int cnt = 0, ret; - if (!port_private->chan_enable) - return -EINVAL; - - port_conf = port_private->port_conf; - ctl = port_private->t7xx_dev->md->fsm_ctl; + port_conf = port->port_conf; + ctl = port->t7xx_dev->md->fsm_ctl; md_state = t7xx_fsm_get_md_state(ctl); if (md_state == MD_STATE_WAITING_FOR_HS1 || md_state == MD_STATE_WAITING_FOR_HS2) { - dev_warn(port_private->dev, "Cannot write to %s port when md_state=%d\n", + dev_warn(port->dev, "Cannot write to %s port when md_state=%d\n", port_conf->name, md_state); return -ENODEV; } @@ -75,10 +107,10 @@ static int t7xx_port_ctrl_tx(struct wwan_port *port, struct sk_buff *skb) while (cur) { cloned = skb_clone(cur, GFP_KERNEL); cloned->len = skb_headlen(cur); - ret = t7xx_port_send_skb(port_private, cloned, 0, 0); + ret = t7xx_port_send_skb(port, cloned, 0, 0); if (ret) { dev_kfree_skb(cloned); - dev_err(port_private->dev, "Write error on %s port, %d\n", + dev_err(port->dev, "Write error on %s port, %d\n", port_conf->name, ret); return cnt ? cnt + ret : ret; } @@ -93,14 +125,53 @@ static int t7xx_port_ctrl_tx(struct wwan_port *port, struct sk_buff *skb) return 0; } +static int t7xx_port_wwan_tx(struct wwan_port *port, struct sk_buff *skb) +{ + struct t7xx_port *port_private = wwan_port_get_drvdata(port); + const struct t7xx_port_conf *port_conf = port_private->port_conf; + int ret; + + if (!port_private->chan_enable) + return -EINVAL; + + if (port_conf->port_type != WWAN_PORT_FASTBOOT) + ret = t7xx_port_ctrl_tx(port_private, skb); + else + ret = t7xx_port_fastboot_tx(port_private, skb); + + return ret; +} + static const struct wwan_port_ops wwan_ops = { - .start = t7xx_port_ctrl_start, - .stop = t7xx_port_ctrl_stop, - .tx = t7xx_port_ctrl_tx, + .start = t7xx_port_wwan_start, + .stop = t7xx_port_wwan_stop, + .tx = t7xx_port_wwan_tx, }; +static void t7xx_port_wwan_create(struct t7xx_port *port) +{ + const struct t7xx_port_conf *port_conf = port->port_conf; + unsigned int header_len = sizeof(struct ccci_header), mtu; + struct wwan_port_caps caps; + + if (!port->wwan.wwan_port) { + mtu = t7xx_get_port_mtu(port); + caps.frag_len = mtu - header_len; + caps.headroom_len = header_len; + port->wwan.wwan_port = wwan_create_port(port->dev, port_conf->port_type, + &wwan_ops, &caps, port); + if (IS_ERR(port->wwan.wwan_port)) + dev_err(port->dev, "Unable to create WWAN port %s", port_conf->name); + } +} + static int t7xx_port_wwan_init(struct t7xx_port *port) { + const struct t7xx_port_conf *port_conf = port->port_conf; + + if (port_conf->port_type == WWAN_PORT_FASTBOOT) + t7xx_port_wwan_create(port); + port->rx_length_th = RX_QUEUE_MAXLEN; return 0; } @@ -152,20 +223,14 @@ static int t7xx_port_wwan_disable_chl(struct t7xx_port *port) static void t7xx_port_wwan_md_state_notify(struct t7xx_port *port, unsigned int state) { const struct t7xx_port_conf *port_conf = port->port_conf; - unsigned int header_len = sizeof(struct ccci_header); - struct wwan_port_caps caps; + + if (port_conf->port_type == WWAN_PORT_FASTBOOT) + return; if (state != MD_STATE_READY) return; - if (!port->wwan.wwan_port) { - caps.frag_len = CLDMA_MTU - header_len; - caps.headroom_len = header_len; - port->wwan.wwan_port = wwan_create_port(port->dev, port_conf->port_type, - &wwan_ops, &caps, port); - if (IS_ERR(port->wwan.wwan_port)) - dev_err(port->dev, "Unable to create WWWAN port %s", port_conf->name); - } + t7xx_port_wwan_create(port); } struct port_ops wwan_sub_port_ops = { diff --git a/drivers/net/wwan/t7xx/t7xx_reg.h b/drivers/net/wwan/t7xx/t7xx_reg.h index c41d7d094c085..9c7dc72ac6f62 100644 --- a/drivers/net/wwan/t7xx/t7xx_reg.h +++ b/drivers/net/wwan/t7xx/t7xx_reg.h @@ -101,11 +101,33 @@ enum t7xx_pm_resume_state { PM_RESUME_REG_STATE_L2_EXP, }; +enum host_event_e { + HOST_EVENT_INIT = 0, + FASTBOOT_DL_NOTIFY = 0x3, +}; + #define T7XX_PCIE_MISC_DEV_STATUS 0x0d1c #define MISC_STAGE_MASK GENMASK(2, 0) #define MISC_RESET_TYPE_PLDR BIT(26) #define MISC_RESET_TYPE_FLDR BIT(27) -#define LINUX_STAGE 4 +#define MISC_RESET_TYPE_PLDR BIT(26) +#define MISC_LK_EVENT_MASK GENMASK(11, 8) +#define HOST_EVENT_MASK GENMASK(31, 28) + +enum lk_event_id { + LK_EVENT_NORMAL = 0, + LK_EVENT_CREATE_PD_PORT = 1, + LK_EVENT_CREATE_POST_DL_PORT = 2, + LK_EVENT_RESET = 7, +}; + +enum t7xx_device_stage { + T7XX_DEV_STAGE_INIT = 0, + T7XX_DEV_STAGE_BROM_PRE = 1, + T7XX_DEV_STAGE_BROM_POST = 2, + T7XX_DEV_STAGE_LK = 3, + T7XX_DEV_STAGE_LINUX = 4, +}; #define T7XX_PCIE_RESOURCE_STATUS 0x0d28 #define T7XX_PCIE_RESOURCE_STS_MSK GENMASK(4, 0) diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.c b/drivers/net/wwan/t7xx/t7xx_state_monitor.c index 0bc97430211bf..9889ca4621cf5 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.c +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.c @@ -47,6 +47,13 @@ #define FSM_MD_EX_PASS_TIMEOUT_MS 45000 #define FSM_CMD_TIMEOUT_MS 2000 +#define wait_for_expected_dev_stage(status) \ + read_poll_timeout(ioread32, status, \ + ((status & MISC_STAGE_MASK) == T7XX_DEV_STAGE_LINUX) || \ + ((status & MISC_STAGE_MASK) == T7XX_DEV_STAGE_LK), 100000, \ + 20000000, false, IREG_BASE(md->t7xx_dev) + \ + T7XX_PCIE_MISC_DEV_STATUS) + void t7xx_fsm_notifier_register(struct t7xx_modem *md, struct t7xx_fsm_notifier *notifier) { struct t7xx_fsm_ctl *ctl = md->fsm_ctl; @@ -206,6 +213,55 @@ static void fsm_routine_exception(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comm fsm_finish_command(ctl, cmd, 0); } +static void t7xx_host_event_notify(struct t7xx_modem *md, unsigned int event_id) +{ + u32 value; + + value = ioread32(IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); + value &= ~HOST_EVENT_MASK; + value |= FIELD_PREP(HOST_EVENT_MASK, event_id); + iowrite32(value, IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); +} + +static void t7xx_lk_stage_event_handling(struct t7xx_fsm_ctl *ctl, unsigned int status) +{ + struct t7xx_modem *md = ctl->md; + struct cldma_ctrl *md_ctrl; + enum lk_event_id lk_event; + struct device *dev; + struct t7xx_port *port; + + dev = &md->t7xx_dev->pdev->dev; + lk_event = FIELD_GET(MISC_LK_EVENT_MASK, status); + switch (lk_event) { + case LK_EVENT_NORMAL: + case LK_EVENT_RESET: + break; + + case LK_EVENT_CREATE_PD_PORT: + case LK_EVENT_CREATE_POST_DL_PORT: + md_ctrl = md->md_ctrl[CLDMA_ID_AP]; + t7xx_cldma_hif_hw_init(md_ctrl); + t7xx_cldma_stop(md_ctrl); + t7xx_cldma_switch_cfg(md_ctrl, CLDMA_DEDICATED_Q_CFG); + + port = &ctl->md->port_prox->ports[0]; + port->port_conf->ops->enable_chl(port); + + t7xx_cldma_start(md_ctrl); + + if (lk_event == LK_EVENT_CREATE_POST_DL_PORT) + t7xx_mode_update(md->t7xx_dev, T7XX_FASTBOOT_DOWNLOAD); + else + t7xx_mode_update(md->t7xx_dev, T7XX_FASTBOOT_DUMP); + break; + + default: + dev_err(dev, "Invalid LK event %d\n", lk_event); + break; + } +} + static int fsm_stopped_handler(struct t7xx_fsm_ctl *ctl) { ctl->curr_state = FSM_STATE_STOPPED; @@ -226,8 +282,9 @@ static void fsm_routine_stopped(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comman static void fsm_routine_stopping(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command *cmd) { - struct t7xx_pci_dev *t7xx_dev; - struct cldma_ctrl *md_ctrl; + struct cldma_ctrl *md_ctrl = ctl->md->md_ctrl[CLDMA_ID_MD]; + struct t7xx_pci_dev *t7xx_dev = ctl->md->t7xx_dev; + enum t7xx_mode mode = READ_ONCE(t7xx_dev->mode); int err; if (ctl->curr_state == FSM_STATE_STOPPED || ctl->curr_state == FSM_STATE_STOPPING) { @@ -235,18 +292,20 @@ static void fsm_routine_stopping(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comma return; } - md_ctrl = ctl->md->md_ctrl[CLDMA_ID_MD]; - t7xx_dev = ctl->md->t7xx_dev; - ctl->curr_state = FSM_STATE_STOPPING; t7xx_fsm_broadcast_state(ctl, MD_STATE_WAITING_TO_STOP); t7xx_cldma_stop(md_ctrl); - if (!ctl->md->rgu_irq_asserted) { - t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DRM_DISABLE_AP); - /* Wait for the DRM disable to take effect */ - msleep(FSM_DRM_DISABLE_DELAY_MS); + if (mode == T7XX_FASTBOOT_SWITCHING) + t7xx_host_event_notify(ctl->md, FASTBOOT_DL_NOTIFY); + + t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DRM_DISABLE_AP); + /* Wait for the DRM disable to take effect */ + msleep(FSM_DRM_DISABLE_DELAY_MS); + if (mode == T7XX_FASTBOOT_SWITCHING) { + t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET); + } else { err = t7xx_acpi_fldr_func(t7xx_dev); if (err) t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET); @@ -272,6 +331,7 @@ static void fsm_routine_ready(struct t7xx_fsm_ctl *ctl) ctl->curr_state = FSM_STATE_READY; t7xx_fsm_broadcast_ready_state(ctl); + t7xx_mode_update(md->t7xx_dev, T7XX_READY); t7xx_md_event_notify(md, FSM_READY); } @@ -317,7 +377,8 @@ static int fsm_routine_starting(struct t7xx_fsm_ctl *ctl) static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command *cmd) { struct t7xx_modem *md = ctl->md; - u32 dev_status; + struct device *dev; + u32 status; int ret; if (!md) @@ -329,23 +390,53 @@ static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command return; } + dev = &md->t7xx_dev->pdev->dev; ctl->curr_state = FSM_STATE_PRE_START; t7xx_md_event_notify(md, FSM_PRE_START); - ret = read_poll_timeout(ioread32, dev_status, - (dev_status & MISC_STAGE_MASK) == LINUX_STAGE, 20000, 2000000, - false, IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); + ret = wait_for_expected_dev_stage(status); + if (ret) { - struct device *dev = &md->t7xx_dev->pdev->dev; + dev_err(dev, "read poll timeout %d\n", ret); + goto finish_command; + } - fsm_finish_command(ctl, cmd, -ETIMEDOUT); - dev_err(dev, "Invalid device status 0x%lx\n", dev_status & MISC_STAGE_MASK); - return; + if (status != ctl->status || cmd->flag != 0) { + u32 stage = FIELD_GET(MISC_STAGE_MASK, status); + + switch (stage) { + case T7XX_DEV_STAGE_INIT: + case T7XX_DEV_STAGE_BROM_PRE: + case T7XX_DEV_STAGE_BROM_POST: + dev_dbg(dev, "BROM_STAGE Entered\n"); + ret = t7xx_fsm_append_cmd(ctl, FSM_CMD_START, 0); + break; + + case T7XX_DEV_STAGE_LK: + dev_dbg(dev, "LK_STAGE Entered\n"); + t7xx_lk_stage_event_handling(ctl, status); + break; + + case T7XX_DEV_STAGE_LINUX: + dev_dbg(dev, "LINUX_STAGE Entered\n"); + t7xx_mhccif_mask_clr(md->t7xx_dev, D2H_INT_PORT_ENUM | + D2H_INT_ASYNC_MD_HK | D2H_INT_ASYNC_AP_HK); + if (cmd->flag == 0) + break; + t7xx_cldma_hif_hw_init(md->md_ctrl[CLDMA_ID_AP]); + t7xx_cldma_hif_hw_init(md->md_ctrl[CLDMA_ID_MD]); + t7xx_port_proxy_set_cfg(md, PORT_CFG_ID_NORMAL); + ret = fsm_routine_starting(ctl); + break; + + default: + break; + } + ctl->status = status; } - t7xx_cldma_hif_hw_init(md->md_ctrl[CLDMA_ID_AP]); - t7xx_cldma_hif_hw_init(md->md_ctrl[CLDMA_ID_MD]); - fsm_finish_command(ctl, cmd, fsm_routine_starting(ctl)); +finish_command: + fsm_finish_command(ctl, cmd, ret); } static int fsm_main_thread(void *data) @@ -517,6 +608,7 @@ void t7xx_fsm_reset(struct t7xx_modem *md) fsm_flush_event_cmd_qs(ctl); ctl->curr_state = FSM_STATE_STOPPED; ctl->exp_flg = false; + ctl->status = T7XX_DEV_STAGE_INIT; } int t7xx_fsm_init(struct t7xx_modem *md) diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.h b/drivers/net/wwan/t7xx/t7xx_state_monitor.h index b0b3662ae6d72..7b0a9baf488c1 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.h +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.h @@ -96,6 +96,7 @@ struct t7xx_fsm_ctl { bool exp_flg; spinlock_t notifier_lock; /* Protects notifier list */ struct list_head notifier_list; + u32 status; /* Device boot stage */ }; struct t7xx_fsm_event { diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 72e01e550a16c..2ed20b20e7fc9 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -328,6 +328,10 @@ static const struct { .name = "XMMRPC", .devsuf = "xmmrpc", }, + [WWAN_PORT_FASTBOOT] = { + .name = "FASTBOOT", + .devsuf = "fastboot", + }, }; static ssize_t type_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index ad29f370034e4..8d2aee88526c6 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -285,6 +285,7 @@ static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue) return NULL; } skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE); + skb_mark_for_recycle(skb); /* Align ip header to a 16 bytes boundary */ skb_reserve(skb, NET_IP_ALIGN); diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index 7eb17f46a8153..9e1a34e23af26 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -424,7 +424,8 @@ struct trf7970a { enum trf7970a_state state; struct device *dev; struct spi_device *spi; - struct regulator *regulator; + struct regulator *vin_regulator; + struct regulator *vddio_regulator; struct nfc_digital_dev *ddev; u32 quirks; bool is_initiator; @@ -1883,7 +1884,7 @@ static int trf7970a_power_up(struct trf7970a *trf) if (trf->state != TRF7970A_ST_PWR_OFF) return 0; - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vin_regulator); if (ret) { dev_err(trf->dev, "%s - Can't enable VIN: %d\n", __func__, ret); return ret; @@ -1926,7 +1927,7 @@ static int trf7970a_power_down(struct trf7970a *trf) if (trf->en2_gpiod && !(trf->quirks & TRF7970A_QUIRK_EN2_MUST_STAY_LOW)) gpiod_set_value_cansleep(trf->en2_gpiod, 0); - ret = regulator_disable(trf->regulator); + ret = regulator_disable(trf->vin_regulator); if (ret) dev_err(trf->dev, "%s - Can't disable VIN: %d\n", __func__, ret); @@ -2065,37 +2066,37 @@ static int trf7970a_probe(struct spi_device *spi) mutex_init(&trf->lock); INIT_DELAYED_WORK(&trf->timeout_work, trf7970a_timeout_work_handler); - trf->regulator = devm_regulator_get(&spi->dev, "vin"); - if (IS_ERR(trf->regulator)) { - ret = PTR_ERR(trf->regulator); + trf->vin_regulator = devm_regulator_get(&spi->dev, "vin"); + if (IS_ERR(trf->vin_regulator)) { + ret = PTR_ERR(trf->vin_regulator); dev_err(trf->dev, "Can't get VIN regulator: %d\n", ret); goto err_destroy_lock; } - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vin_regulator); if (ret) { dev_err(trf->dev, "Can't enable VIN: %d\n", ret); goto err_destroy_lock; } - uvolts = regulator_get_voltage(trf->regulator); + uvolts = regulator_get_voltage(trf->vin_regulator); if (uvolts > 4000000) trf->chip_status_ctrl = TRF7970A_CHIP_STATUS_VRS5_3; - trf->regulator = devm_regulator_get(&spi->dev, "vdd-io"); - if (IS_ERR(trf->regulator)) { - ret = PTR_ERR(trf->regulator); + trf->vddio_regulator = devm_regulator_get(&spi->dev, "vdd-io"); + if (IS_ERR(trf->vddio_regulator)) { + ret = PTR_ERR(trf->vddio_regulator); dev_err(trf->dev, "Can't get VDD_IO regulator: %d\n", ret); - goto err_destroy_lock; + goto err_disable_vin_regulator; } - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vddio_regulator); if (ret) { dev_err(trf->dev, "Can't enable VDD_IO: %d\n", ret); - goto err_destroy_lock; + goto err_disable_vin_regulator; } - if (regulator_get_voltage(trf->regulator) == 1800000) { + if (regulator_get_voltage(trf->vddio_regulator) == 1800000) { trf->io_ctrl = TRF7970A_REG_IO_CTRL_IO_LOW; dev_dbg(trf->dev, "trf7970a config vdd_io to 1.8V\n"); } @@ -2108,7 +2109,7 @@ static int trf7970a_probe(struct spi_device *spi) if (!trf->ddev) { dev_err(trf->dev, "Can't allocate NFC digital device\n"); ret = -ENOMEM; - goto err_disable_regulator; + goto err_disable_vddio_regulator; } nfc_digital_set_parent_dev(trf->ddev, trf->dev); @@ -2137,8 +2138,10 @@ static int trf7970a_probe(struct spi_device *spi) trf7970a_shutdown(trf); err_free_ddev: nfc_digital_free_device(trf->ddev); -err_disable_regulator: - regulator_disable(trf->regulator); +err_disable_vddio_regulator: + regulator_disable(trf->vddio_regulator); +err_disable_vin_regulator: + regulator_disable(trf->vin_regulator); err_destroy_lock: mutex_destroy(&trf->lock); return ret; @@ -2157,7 +2160,8 @@ static void trf7970a_remove(struct spi_device *spi) nfc_digital_unregister_device(trf->ddev); nfc_digital_free_device(trf->ddev); - regulator_disable(trf->regulator); + regulator_disable(trf->vddio_regulator); + regulator_disable(trf->vin_regulator); mutex_destroy(&trf->lock); } diff --git a/drivers/ntb/core.c b/drivers/ntb/core.c index 27dd93deff6e5..d702bee780826 100644 --- a/drivers/ntb/core.c +++ b/drivers/ntb/core.c @@ -100,6 +100,8 @@ EXPORT_SYMBOL(ntb_unregister_client); int ntb_register_device(struct ntb_dev *ntb) { + int ret; + if (!ntb) return -EINVAL; if (!ntb->pdev) @@ -120,7 +122,11 @@ int ntb_register_device(struct ntb_dev *ntb) ntb->ctx_ops = NULL; spin_lock_init(&ntb->ctx_lock); - return device_register(&ntb->dev); + ret = device_register(&ntb->dev); + if (ret) + put_device(&ntb->dev); + + return ret; } EXPORT_SYMBOL(ntb_register_device); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0a96362912ced..2f51c4a978589 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -405,7 +405,15 @@ static inline void nvme_end_req_zoned(struct request *req) } } -static inline void nvme_end_req(struct request *req) +static inline void __nvme_end_req(struct request *req) +{ + nvme_end_req_zoned(req); + nvme_trace_bio_complete(req); + if (req->cmd_flags & REQ_NVME_MPATH) + nvme_mpath_end_request(req); +} + +void nvme_end_req(struct request *req) { blk_status_t status = nvme_error_status(nvme_req(req)->status); @@ -415,10 +423,7 @@ static inline void nvme_end_req(struct request *req) else nvme_log_error(req); } - nvme_end_req_zoned(req); - nvme_trace_bio_complete(req); - if (req->cmd_flags & REQ_NVME_MPATH) - nvme_mpath_end_request(req); + __nvme_end_req(req); blk_mq_end_request(req, status); } @@ -467,7 +472,7 @@ void nvme_complete_batch_req(struct request *req) { trace_nvme_complete_rq(req); nvme_cleanup_cmd(req); - nvme_end_req_zoned(req); + __nvme_end_req(req); } EXPORT_SYMBOL_GPL(nvme_complete_batch_req); @@ -619,27 +624,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); -/* - * Returns true for sink states that can't ever transition back to live. - */ -static bool nvme_state_terminal(struct nvme_ctrl *ctrl) -{ - switch (nvme_ctrl_state(ctrl)) { - case NVME_CTRL_NEW: - case NVME_CTRL_LIVE: - case NVME_CTRL_RESETTING: - case NVME_CTRL_CONNECTING: - return false; - case NVME_CTRL_DELETING: - case NVME_CTRL_DELETING_NOIO: - case NVME_CTRL_DEAD: - return true; - default: - WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state); - return true; - } -} - /* * Waits for the controller state to be resetting, or returns false if it is * not possible to ever transition to that state. @@ -3630,7 +3614,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) "Found shared namespace %d, but multipathing not supported.\n", info->nsid); dev_warn_once(ctrl->device, - "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0\n."); + "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0.\n"); } } @@ -4359,7 +4343,8 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, set->ops = ops; set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; if (ctrl->ops->flags & NVME_F_FABRICS) - set->reserved_tags = NVMF_RESERVED_TAGS; + /* Reserved for fabric connect and keep alive */ + set->reserved_tags = 2; set->numa_node = ctrl->numa_node; set->flags = BLK_MQ_F_NO_SCHED; if (ctrl->ops->flags & NVME_F_BLOCKING) @@ -4428,7 +4413,8 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, if (ctrl->quirks & NVME_QUIRK_SHARED_TAGS) set->reserved_tags = NVME_AQ_DEPTH; else if (ctrl->ops->flags & NVME_F_FABRICS) - set->reserved_tags = NVMF_RESERVED_TAGS; + /* Reserved for fabric connect */ + set->reserved_tags = 1; set->numa_node = ctrl->numa_node; set->flags = BLK_MQ_F_SHOULD_MERGE; if (ctrl->ops->flags & NVME_F_BLOCKING) diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 06cc54851b1be..37c974c38dcb0 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -18,13 +18,6 @@ /* default is -1: the fail fast mechanism is disabled */ #define NVMF_DEF_FAIL_FAST_TMO -1 -/* - * Reserved one command for internal usage. This command is used for sending - * the connect command, as well as for the keep alive command on the admin - * queue once live. - */ -#define NVMF_RESERVED_TAGS 1 - /* * Define a host as seen by the target. We allocate one at boot, but also * allow the override it when creating controllers. This is both to provide diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 74de1e64aeead..e157c7983d466 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -118,7 +118,8 @@ void nvme_failover_req(struct request *req) blk_steal_bios(&ns->head->requeue_list, req); spin_unlock_irqrestore(&ns->head->requeue_lock, flags); - blk_mq_end_request(req, 0); + nvme_req(req)->status = 0; + nvme_end_req(req); kblockd_schedule_work(&ns->head->requeue_work); } @@ -247,7 +248,8 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) if (nvme_path_is_disabled(ns)) continue; - if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA) + if (ns->ctrl->numa_node != NUMA_NO_NODE && + READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA) distance = node_distance(node, ns->ctrl->numa_node); else distance = LOCAL_DISTANCE; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 7b87763e2f8a6..05d807fa0d3da 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -162,6 +162,11 @@ enum nvme_quirks { * Disables simple suspend/resume path. */ NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND = (1 << 20), + + /* + * MSI (but not MSI-X) interrupts are broken and never fire. + */ + NVME_QUIRK_BROKEN_MSI = (1 << 21), }; /* @@ -740,6 +745,28 @@ static inline bool nvme_is_aen_req(u16 qid, __u16 command_id) nvme_tag_from_cid(command_id) >= NVME_AQ_BLK_MQ_DEPTH; } +/* + * Returns true for sink states that can't ever transition back to live. + */ +static inline bool nvme_state_terminal(struct nvme_ctrl *ctrl) +{ + switch (nvme_ctrl_state(ctrl)) { + case NVME_CTRL_NEW: + case NVME_CTRL_LIVE: + case NVME_CTRL_RESETTING: + case NVME_CTRL_CONNECTING: + return false; + case NVME_CTRL_DELETING: + case NVME_CTRL_DELETING_NOIO: + case NVME_CTRL_DEAD: + return true; + default: + WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state); + return true; + } +} + +void nvme_end_req(struct request *req); void nvme_complete_rq(struct request *req); void nvme_complete_batch_req(struct request *req); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index e6267a6aa3801..710043086dffa 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1286,6 +1286,9 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) u32 csts = readl(dev->bar + NVME_REG_CSTS); u8 opcode; + if (nvme_state_terminal(&dev->ctrl)) + goto disable; + /* If PCI error recovery process is happening, we cannot reset or * the recovery mechanism will surely fail. */ @@ -1390,8 +1393,11 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) return BLK_EH_RESET_TIMER; disable: - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) { + if (nvme_state_terminal(&dev->ctrl)) + nvme_dev_disable(dev, true); return BLK_EH_DONE; + } nvme_dev_disable(dev, false); if (nvme_try_sched_reset(&dev->ctrl)) @@ -2218,6 +2224,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) .priv = dev, }; unsigned int irq_queues, poll_queues; + unsigned int flags = PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY; /* * Poll queues don't need interrupts, but we need at least one I/O queue @@ -2241,8 +2248,10 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) irq_queues = 1; if (!(dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR)) irq_queues += (nr_io_queues - poll_queues); - return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues, - PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd); + if (dev->ctrl.quirks & NVME_QUIRK_BROKEN_MSI) + flags &= ~PCI_IRQ_MSI; + return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues, flags, + &affd); } static unsigned int nvme_max_io_queues(struct nvme_dev *dev) @@ -2471,6 +2480,7 @@ static int nvme_pci_enable(struct nvme_dev *dev) { int result = -ENOMEM; struct pci_dev *pdev = to_pci_dev(dev->dev); + unsigned int flags = PCI_IRQ_ALL_TYPES; if (pci_enable_device_mem(pdev)) return result; @@ -2487,7 +2497,9 @@ static int nvme_pci_enable(struct nvme_dev *dev) * interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll * adjust this later. */ - result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (dev->ctrl.quirks & NVME_QUIRK_BROKEN_MSI) + flags &= ~PCI_IRQ_MSI; + result = pci_alloc_irq_vectors(pdev, 1, 1, flags); if (result < 0) goto disable; @@ -3363,6 +3375,9 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_BOGUS_NID, }, { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST | NVME_QUIRK_BOGUS_NID, }, @@ -3381,6 +3396,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY | NVME_QUIRK_DISABLE_WRITE_ZEROES| NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + { PCI_DEVICE(0x15b7, 0x5008), /* Sandisk SN530 */ + .driver_data = NVME_QUIRK_BROKEN_MSI }, { PCI_DEVICE(0x1987, 0x5012), /* Phison E12 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1987, 0x5016), /* Phison E16 */ diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c index fc3eed00f9ff1..9add6499f42ad 100644 --- a/drivers/nvme/host/pr.c +++ b/drivers/nvme/host/pr.c @@ -77,7 +77,7 @@ static int nvme_sc_to_pr_err(int nvme_sc) if (nvme_is_path_error(nvme_sc)) return PR_STS_PATH_FAILED; - switch (nvme_sc) { + switch (nvme_sc & 0x7ff) { case NVME_SC_SUCCESS: return PR_STS_SUCCESS; case NVME_SC_RESERVATION_CONFLICT: diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index f2832f70e7e0a..09fcaa519e5bc 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -221,14 +221,11 @@ static int ns_update_nuse(struct nvme_ns *ns) ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id); if (ret) - goto out_free_id; + return ret; ns->head->nuse = le64_to_cpu(id->nuse); - -out_free_id: kfree(id); - - return ret; + return 0; } static ssize_t nuse_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index a6d596e056021..6eeb96578d1b4 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -352,12 +352,18 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue) } while (ret > 0); } -static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue) +static inline bool nvme_tcp_queue_has_pending(struct nvme_tcp_queue *queue) { return !list_empty(&queue->send_list) || !llist_empty(&queue->req_list); } +static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue) +{ + return !nvme_tcp_tls(&queue->ctrl->ctrl) && + nvme_tcp_queue_has_pending(queue); +} + static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, bool sync, bool last) { @@ -378,7 +384,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, mutex_unlock(&queue->send_mutex); } - if (last && nvme_tcp_queue_more(queue)) + if (last && nvme_tcp_queue_has_pending(queue)) queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); } diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index 3ddbc3880cac8..fb518b00f71f6 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -285,9 +285,9 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, } if (shash_len != crypto_shash_digestsize(shash_tfm)) { - pr_debug("%s: hash len mismatch (len %d digest %d)\n", - __func__, shash_len, - crypto_shash_digestsize(shash_tfm)); + pr_err("%s: hash len mismatch (len %d digest %d)\n", + __func__, shash_len, + crypto_shash_digestsize(shash_tfm)); ret = -EINVAL; goto out_free_tfm; } @@ -370,7 +370,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, nvme_auth_free_key(transformed_key); out_free_tfm: crypto_free_shash(shash_tfm); - return 0; + return ret; } int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 2482a0db25043..303b49c604bd7 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -650,10 +650,18 @@ static ssize_t nvmet_ns_enable_store(struct config_item *item, if (kstrtobool(page, &enable)) return -EINVAL; + /* + * take a global nvmet_config_sem because the disable routine has a + * window where it releases the subsys-lock, giving a chance to + * a parallel enable to concurrently execute causing the disable to + * have a misaccounting of the ns percpu_ref. + */ + down_write(&nvmet_config_sem); if (enable) ret = nvmet_ns_enable(ns); else nvmet_ns_disable(ns); + up_write(&nvmet_config_sem); return ret ? ret : count; } @@ -728,6 +736,18 @@ static struct configfs_attribute *nvmet_ns_attrs[] = { NULL, }; +bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid) +{ + struct config_item *ns_item; + char name[12]; + + snprintf(name, sizeof(name), "%u", nsid); + mutex_lock(&subsys->namespaces_group.cg_subsys->su_mutex); + ns_item = config_group_find_item(&subsys->namespaces_group, name); + mutex_unlock(&subsys->namespaces_group.cg_subsys->su_mutex); + return ns_item != NULL; +} + static void nvmet_ns_release(struct config_item *item) { struct nvmet_ns *ns = to_nvmet_ns(item); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 8658e9c08534d..7a6b3d37cca70 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -425,10 +425,13 @@ void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl) u16 nvmet_req_find_ns(struct nvmet_req *req) { u32 nsid = le32_to_cpu(req->cmd->common.nsid); + struct nvmet_subsys *subsys = nvmet_req_subsys(req); - req->ns = xa_load(&nvmet_req_subsys(req)->namespaces, nsid); + req->ns = xa_load(&subsys->namespaces, nsid); if (unlikely(!req->ns)) { req->error_loc = offsetof(struct nvme_common_command, nsid); + if (nvmet_subsys_nsid_exists(subsys, nsid)) + return NVME_SC_INTERNAL_PATH_ERROR; return NVME_SC_INVALID_NS | NVME_SC_DNR; } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 6c8acebe1a1a6..477416abf85ab 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -542,6 +542,7 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys, struct nvmet_host *host); void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type, u8 event_info, u8 log_page); +bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid); #define NVMET_QUEUE_SIZE 1024 #define NVMET_NR_QUEUES 128 diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index f2d963e1fe94e..5569cef862bcc 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -226,13 +226,13 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) req->cmd->common.opcode == nvme_admin_identify) { switch (req->cmd->identify.cns) { case NVME_ID_CNS_CTRL: - nvmet_passthru_override_id_ctrl(req); + status = nvmet_passthru_override_id_ctrl(req); break; case NVME_ID_CNS_NS: - nvmet_passthru_override_id_ns(req); + status = nvmet_passthru_override_id_ns(req); break; case NVME_ID_CNS_NS_DESC_LIST: - nvmet_passthru_override_id_descs(req); + status = nvmet_passthru_override_id_descs(req); break; } } else if (status < 0) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index c8655fc5aa5b8..8d4531a1606d1 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -348,6 +348,7 @@ static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu) return 0; } +/* If cmd buffers are NULL, no operation is performed */ static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd) { kfree(cmd->iov); @@ -1580,13 +1581,9 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue) struct nvmet_tcp_cmd *cmd = queue->cmds; int i; - for (i = 0; i < queue->nr_cmds; i++, cmd++) { - if (nvmet_tcp_need_data_in(cmd)) - nvmet_tcp_free_cmd_buffers(cmd); - } - - if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect)) - nvmet_tcp_free_cmd_buffers(&queue->connect); + for (i = 0; i < queue->nr_cmds; i++, cmd++) + nvmet_tcp_free_cmd_buffers(cmd); + nvmet_tcp_free_cmd_buffers(&queue->connect); } static void nvmet_tcp_release_queue_work(struct work_struct *w) diff --git a/drivers/nvmem/meson-efuse.c b/drivers/nvmem/meson-efuse.c index b922df99f9bc3..33678d0af2c24 100644 --- a/drivers/nvmem/meson-efuse.c +++ b/drivers/nvmem/meson-efuse.c @@ -47,7 +47,6 @@ static int meson_efuse_probe(struct platform_device *pdev) struct nvmem_config *econfig; struct clk *clk; unsigned int size; - int ret; sm_np = of_parse_phandle(pdev->dev.of_node, "secure-monitor", 0); if (!sm_np) { @@ -60,27 +59,9 @@ static int meson_efuse_probe(struct platform_device *pdev) if (!fw) return -EPROBE_DEFER; - clk = devm_clk_get(dev, NULL); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get efuse gate"); - return ret; - } - - ret = clk_prepare_enable(clk); - if (ret) { - dev_err(dev, "failed to enable gate"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - clk); - if (ret) { - dev_err(dev, "failed to add disable callback"); - return ret; - } + clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "failed to get efuse gate"); if (meson_sm_call(fw, SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) { dev_err(dev, "failed to get max user"); diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 3bf27052832f3..4d57a4e341054 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "OF: " fmt +#include #include #include #include @@ -667,6 +668,17 @@ void of_changeset_destroy(struct of_changeset *ocs) { struct of_changeset_entry *ce, *cen; + /* + * When a device is deleted, the device links to/from it are also queued + * for deletion. Until these device links are freed, the devices + * themselves aren't freed. If the device being deleted is due to an + * overlay change, this device might be holding a reference to a device + * node that will be freed. So, wait until all already pending device + * links are deleted before freeing a device node. This ensures we don't + * free any device node that has a non-zero reference count. + */ + device_link_wait_removal(); + list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node) __of_changeset_entry_destroy(ce); } diff --git a/drivers/of/module.c b/drivers/of/module.c index 0e8aa974f0f2b..780fd82a7ecc5 100644 --- a/drivers/of/module.c +++ b/drivers/of/module.c @@ -16,19 +16,28 @@ ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len) ssize_t csize; ssize_t tsize; + /* + * Prevent a kernel oops in vsnprintf() -- it only allows passing a + * NULL ptr when the length is also 0. Also filter out the negative + * lengths... + */ + if ((len > 0 && !str) || len < 0) + return -EINVAL; + /* Name & Type */ /* %p eats all alphanum characters, so %c must be used here */ csize = snprintf(str, len, "of:N%pOFn%c%s", np, 'T', of_node_get_device_type(np)); tsize = csize; + if (csize >= len) + csize = len > 0 ? len - 1 : 0; len -= csize; - if (str) - str += csize; + str += csize; of_property_for_each_string(np, "compatible", p, compat) { csize = strlen(compat) + 1; tsize += csize; - if (csize > len) + if (csize >= len) continue; csize = snprintf(str, len, "C%s", compat); diff --git a/drivers/opp/core.c b/drivers/opp/core.c index c4e0432ae42a0..3f02deba4aef6 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2393,7 +2393,8 @@ static void _opp_detach_genpd(struct opp_table *opp_table) static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev, const char * const *names, struct device ***virt_devs) { - struct device *virt_dev; + struct device *virt_dev, *gdev; + struct opp_table *genpd_table; int index = 0, ret = -EINVAL; const char * const *name = names; @@ -2426,6 +2427,34 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev, goto err; } + /* + * The required_opp_tables parsing is not perfect, as the OPP + * core does the parsing solely based on the DT node pointers. + * The core sets the required_opp_tables entry to the first OPP + * table in the "opp_tables" list, that matches with the node + * pointer. + * + * If the target DT OPP table is used by multiple devices and + * they all create separate instances of 'struct opp_table' from + * it, then it is possible that the required_opp_tables entry + * may be set to the incorrect sibling device. + * + * Cross check it again and fix if required. + */ + gdev = dev_to_genpd_dev(virt_dev); + if (IS_ERR(gdev)) + return PTR_ERR(gdev); + + genpd_table = _find_opp_table(gdev); + if (!IS_ERR(genpd_table)) { + if (genpd_table != opp_table->required_opp_tables[index]) { + dev_pm_opp_put_opp_table(opp_table->required_opp_tables[index]); + opp_table->required_opp_tables[index] = genpd_table; + } else { + dev_pm_opp_put_opp_table(genpd_table); + } + } + /* * Add the virtual genpd device as a user of the OPP table, so * we can call dev_pm_opp_set_opp() on it directly. diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c index ec030b19164a3..f157fb50be50c 100644 --- a/drivers/opp/debugfs.c +++ b/drivers/opp/debugfs.c @@ -37,10 +37,12 @@ static ssize_t bw_name_read(struct file *fp, char __user *userbuf, size_t count, loff_t *ppos) { struct icc_path *path = fp->private_data; + const char *name = icc_get_name(path); char buf[64]; - int i; + int i = 0; - i = scnprintf(buf, sizeof(buf), "%.62s\n", icc_get_name(path)); + if (name) + i = scnprintf(buf, sizeof(buf), "%.62s\n", name); return simple_read_from_buffer(userbuf, count, ppos, buf, i); } diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 9a437cfce073c..c43a1479de2ce 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -604,11 +604,16 @@ static unsigned int dw_pcie_ep_find_ext_capability(struct dw_pcie *pci, int cap) int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func; + struct device *dev = pci->dev; + struct pci_epc *epc = ep->epc; unsigned int offset, ptm_cap_base; unsigned int nbars; u8 hdr_type; + u8 func_no; + int i, ret; + void *addr; u32 reg; - int i; hdr_type = dw_pcie_readb_dbi(pci, PCI_HEADER_TYPE) & PCI_HEADER_TYPE_MASK; @@ -619,6 +624,58 @@ int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) return -EIO; } + dw_pcie_version_detect(pci); + + dw_pcie_iatu_detect(pci); + + ret = dw_pcie_edma_detect(pci); + if (ret) + return ret; + + if (!ep->ib_window_map) { + ep->ib_window_map = devm_bitmap_zalloc(dev, pci->num_ib_windows, + GFP_KERNEL); + if (!ep->ib_window_map) + goto err_remove_edma; + } + + if (!ep->ob_window_map) { + ep->ob_window_map = devm_bitmap_zalloc(dev, pci->num_ob_windows, + GFP_KERNEL); + if (!ep->ob_window_map) + goto err_remove_edma; + } + + if (!ep->outbound_addr) { + addr = devm_kcalloc(dev, pci->num_ob_windows, sizeof(phys_addr_t), + GFP_KERNEL); + if (!addr) + goto err_remove_edma; + ep->outbound_addr = addr; + } + + for (func_no = 0; func_no < epc->max_functions; func_no++) { + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (ep_func) + continue; + + ep_func = devm_kzalloc(dev, sizeof(*ep_func), GFP_KERNEL); + if (!ep_func) + goto err_remove_edma; + + ep_func->func_no = func_no; + ep_func->msi_cap = dw_pcie_ep_find_capability(ep, func_no, + PCI_CAP_ID_MSI); + ep_func->msix_cap = dw_pcie_ep_find_capability(ep, func_no, + PCI_CAP_ID_MSIX); + + list_add_tail(&ep_func->list, &ep->func_list); + } + + if (ep->ops->init) + ep->ops->init(ep); + offset = dw_pcie_ep_find_ext_capability(pci, PCI_EXT_CAP_ID_REBAR); ptm_cap_base = dw_pcie_ep_find_ext_capability(pci, PCI_EXT_CAP_ID_PTM); @@ -629,8 +686,13 @@ int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >> PCI_REBAR_CTRL_NBAR_SHIFT; + /* + * PCIe r6.0, sec 7.8.6.2 require us to support at least one + * size in the range from 1 MB to 512 GB. Advertise support + * for 1 MB BAR size only. + */ for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) - dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, 0x0); + dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, BIT(4)); } /* @@ -653,14 +715,17 @@ int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) dw_pcie_dbi_ro_wr_dis(pci); return 0; + +err_remove_edma: + dw_pcie_edma_remove(pci); + + return ret; } EXPORT_SYMBOL_GPL(dw_pcie_ep_init_complete); int dw_pcie_ep_init(struct dw_pcie_ep *ep) { int ret; - void *addr; - u8 func_no; struct resource *res; struct pci_epc *epc; struct dw_pcie *pci = to_dw_pcie_from_ep(ep); @@ -668,7 +733,6 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) struct platform_device *pdev = to_platform_device(dev); struct device_node *np = dev->of_node; const struct pci_epc_features *epc_features; - struct dw_pcie_ep_func *ep_func; INIT_LIST_HEAD(&ep->func_list); @@ -686,26 +750,6 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) if (ep->ops->pre_init) ep->ops->pre_init(ep); - dw_pcie_version_detect(pci); - - dw_pcie_iatu_detect(pci); - - ep->ib_window_map = devm_bitmap_zalloc(dev, pci->num_ib_windows, - GFP_KERNEL); - if (!ep->ib_window_map) - return -ENOMEM; - - ep->ob_window_map = devm_bitmap_zalloc(dev, pci->num_ob_windows, - GFP_KERNEL); - if (!ep->ob_window_map) - return -ENOMEM; - - addr = devm_kcalloc(dev, pci->num_ob_windows, sizeof(phys_addr_t), - GFP_KERNEL); - if (!addr) - return -ENOMEM; - ep->outbound_addr = addr; - epc = devm_pci_epc_create(dev, &epc_ops); if (IS_ERR(epc)) { dev_err(dev, "Failed to create epc device\n"); @@ -719,23 +763,6 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) if (ret < 0) epc->max_functions = 1; - for (func_no = 0; func_no < epc->max_functions; func_no++) { - ep_func = devm_kzalloc(dev, sizeof(*ep_func), GFP_KERNEL); - if (!ep_func) - return -ENOMEM; - - ep_func->func_no = func_no; - ep_func->msi_cap = dw_pcie_ep_find_capability(ep, func_no, - PCI_CAP_ID_MSI); - ep_func->msix_cap = dw_pcie_ep_find_capability(ep, func_no, - PCI_CAP_ID_MSIX); - - list_add_tail(&ep_func->list, &ep->func_list); - } - - if (ep->ops->init) - ep->ops->init(ep); - ret = pci_epc_mem_init(epc, ep->phys_base, ep->addr_size, ep->page_size); if (ret < 0) { @@ -751,25 +778,25 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) goto err_exit_epc_mem; } - ret = dw_pcie_edma_detect(pci); - if (ret) - goto err_free_epc_mem; - if (ep->ops->get_features) { epc_features = ep->ops->get_features(ep); if (epc_features->core_init_notifier) return 0; } + /* + * NOTE:- Avoid accessing the hardware (Ex:- DBI space) before this + * step as platforms that implement 'core_init_notifier' feature may + * not have the hardware ready (i.e. core initialized) for access + * (Ex: tegra194). Any hardware access on such platforms result + * in system hang. + */ ret = dw_pcie_ep_init_complete(ep); if (ret) - goto err_remove_edma; + goto err_free_epc_mem; return 0; -err_remove_edma: - dw_pcie_edma_remove(pci); - err_free_epc_mem: pci_epc_mem_free_addr(epc, ep->msi_mem_phys, ep->msi_mem, epc->mem->window.page_size); diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 2ce2a3bd932bd..23bb0eee5c411 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -53,6 +53,7 @@ #define PARF_SLV_ADDR_SPACE_SIZE 0x358 #define PARF_DEVICE_TYPE 0x1000 #define PARF_BDF_TO_SID_TABLE_N 0x2000 +#define PARF_BDF_TO_SID_CFG 0x2c00 /* ELBI registers */ #define ELBI_SYS_CTRL 0x04 @@ -120,6 +121,9 @@ /* PARF_DEVICE_TYPE register fields */ #define DEVICE_TYPE_RC 0x4 +/* PARF_BDF_TO_SID_CFG fields */ +#define BDF_TO_SID_BYPASS BIT(0) + /* ELBI_SYS_CTRL register fields */ #define ELBI_SYS_CTRL_LT_ENABLE BIT(0) @@ -229,6 +233,7 @@ struct qcom_pcie_ops { struct qcom_pcie_cfg { const struct qcom_pcie_ops *ops; + bool no_l0s; }; struct qcom_pcie { @@ -272,6 +277,26 @@ static int qcom_pcie_start_link(struct dw_pcie *pci) return 0; } +static void qcom_pcie_clear_aspm_l0s(struct dw_pcie *pci) +{ + struct qcom_pcie *pcie = to_qcom_pcie(pci); + u16 offset; + u32 val; + + if (!pcie->cfg->no_l0s) + return; + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + dw_pcie_dbi_ro_wr_en(pci); + + val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_ASPM_L0S; + writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP); + + dw_pcie_dbi_ro_wr_dis(pci); +} + static void qcom_pcie_clear_hpc(struct dw_pcie *pci) { u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); @@ -961,6 +986,7 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie) static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) { + qcom_pcie_clear_aspm_l0s(pcie->pci); qcom_pcie_clear_hpc(pcie->pci); return 0; @@ -1008,11 +1034,17 @@ static int qcom_pcie_config_sid_1_9_0(struct qcom_pcie *pcie) u8 qcom_pcie_crc8_table[CRC8_TABLE_SIZE]; int i, nr_map, size = 0; u32 smmu_sid_base; + u32 val; of_get_property(dev->of_node, "iommu-map", &size); if (!size) return 0; + /* Enable BDF to SID translation by disabling bypass mode (default) */ + val = readl(pcie->parf + PARF_BDF_TO_SID_CFG); + val &= ~BDF_TO_SID_BYPASS; + writel(val, pcie->parf + PARF_BDF_TO_SID_CFG); + map = kzalloc(size, GFP_KERNEL); if (!map) return -ENOMEM; @@ -1358,6 +1390,11 @@ static const struct qcom_pcie_cfg cfg_2_9_0 = { .ops = &ops_2_9_0, }; +static const struct qcom_pcie_cfg cfg_sc8280xp = { + .ops = &ops_1_9_0, + .no_l0s = true, +}; + static const struct dw_pcie_ops dw_pcie_ops = { .link_up = qcom_pcie_link_up, .start_link = qcom_pcie_start_link, @@ -1629,11 +1666,11 @@ static const struct of_device_id qcom_pcie_match[] = { { .compatible = "qcom,pcie-ipq8074-gen3", .data = &cfg_2_9_0 }, { .compatible = "qcom,pcie-msm8996", .data = &cfg_2_3_2 }, { .compatible = "qcom,pcie-qcs404", .data = &cfg_2_4_0 }, - { .compatible = "qcom,pcie-sa8540p", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sa8540p", .data = &cfg_sc8280xp }, { .compatible = "qcom,pcie-sa8775p", .data = &cfg_1_9_0}, { .compatible = "qcom,pcie-sc7280", .data = &cfg_1_9_0 }, { .compatible = "qcom,pcie-sc8180x", .data = &cfg_1_9_0 }, - { .compatible = "qcom,pcie-sc8280xp", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sc8280xp", .data = &cfg_sc8280xp }, { .compatible = "qcom,pcie-sdm845", .data = &cfg_2_7_0 }, { .compatible = "qcom,pcie-sdx55", .data = &cfg_1_9_0 }, { .compatible = "qcom,pcie-sm8150", .data = &cfg_1_9_0 }, diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 7afa9e9aabe21..2349e284f6e8f 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -2269,11 +2269,14 @@ static int tegra_pcie_dw_probe(struct platform_device *pdev) ret = tegra_pcie_config_ep(pcie, pdev); if (ret < 0) goto fail; + else + return 0; break; default: dev_err(dev, "Invalid PCIe device type %d\n", pcie->of_data->mode); + ret = -EINVAL; } fail: diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 1eaffff40b8d4..5992280e8110b 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -49,6 +49,7 @@ #include #include #include +#include #include /* @@ -465,7 +466,7 @@ struct pci_eject_response { u32 status; } __packed; -static int pci_ring_size = (4 * PAGE_SIZE); +static int pci_ring_size = VMBUS_RING_SIZE(SZ_16K); /* * Driver specific state. diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index 5b0730c3891b8..c08683febdd40 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -336,7 +336,7 @@ static int brcm_pcie_mdio_write(void __iomem *base, u8 port, readl(base + PCIE_RC_DL_MDIO_ADDR); writel(MDIO_DATA_DONE_MASK | wrdata, base + PCIE_RC_DL_MDIO_WR_DATA); - err = readw_poll_timeout_atomic(base + PCIE_RC_DL_MDIO_WR_DATA, data, + err = readl_poll_timeout_atomic(base + PCIE_RC_DL_MDIO_WR_DATA, data, MDIO_WT_DONE(data), 10, 100); return err; } diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index c9046e97a1d27..79c3e7e9a2701 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -98,10 +98,8 @@ static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, /* All functions share the same vendor ID with function 0 */ if (fn == 0) { - u32 vid_regs = (hdr->vendorid & GENMASK(15, 0)) | - (hdr->subsys_vendor_id & GENMASK(31, 16)) << 16; - - rockchip_pcie_write(rockchip, vid_regs, + rockchip_pcie_write(rockchip, + hdr->vendorid | hdr->subsys_vendor_id << 16, PCIE_CORE_CONFIG_VENDOR); } diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 87b7856f375ab..c9c200adefd27 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -907,9 +907,13 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]); pci_add_resource_offset(&resources, &vmd->resources[2], offset[1]); + pci_lock_rescan_remove(); + vmd->bus = pci_create_root_bus(&vmd->dev->dev, vmd->busn_start, &vmd_ops, sd, &resources); if (!vmd->bus) { + pci_unlock_rescan_remove(); + pci_free_resource_list(&resources); vmd_remove_irq_domain(vmd); return -ENODEV; @@ -965,6 +969,8 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) vmd_acpi_end(); + pci_unlock_rescan_remove(); + WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj, "domain"), "Can't create symlink to domain\n"); return 0; diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c index e75a2af77328e..5b84821c0d602 100644 --- a/drivers/pci/endpoint/functions/pci-epf-vntb.c +++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c @@ -1275,15 +1275,11 @@ static int pci_vntb_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = ntb_register_device(&ndev->ntb); if (ret) { dev_err(dev, "Failed to register NTB device\n"); - goto err_register_dev; + return ret; } dev_dbg(dev, "PCI Virtual NTB driver loaded\n"); return 0; - -err_register_dev: - put_device(&ndev->ntb.dev); - return -EINVAL; } static struct pci_device_id pci_vntb_table[] = { diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 682fa877478fe..d719542d5c5c0 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -724,6 +724,9 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, goto out_disable; } + /* Ensure that all table entries are masked. */ + msix_mask_all(dev->msix_base, tsize); + ret = msix_setup_interrupts(dev, entries, nvec, affd); if (ret) goto out_disable; @@ -731,15 +734,6 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, /* Disable INTX */ pci_intx_for_msi(dev, 0); - /* - * Ensure that all table entries are masked to prevent - * stale entries from firing in a crash kernel. - * - * Done late to deal with a broken Marvell NVME device - * which takes the MSI-X mask bits into account even - * when MSI-X is disabled, which prevents MSI delivery. - */ - msix_mask_all(dev->msix_base, tsize); pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); pcibios_free_irq(dev); diff --git a/drivers/pci/of_property.c b/drivers/pci/of_property.c index c2c7334152bc0..03539e5053720 100644 --- a/drivers/pci/of_property.c +++ b/drivers/pci/of_property.c @@ -238,6 +238,8 @@ static int of_pci_prop_intr_map(struct pci_dev *pdev, struct of_changeset *ocs, return 0; int_map = kcalloc(map_sz, sizeof(u32), GFP_KERNEL); + if (!int_map) + return -ENOMEM; mapp = int_map; list_for_each_entry(child, &pdev->subordinate->devices, bus_list) { diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 0c361561b855c..4f47a13cb500f 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -661,7 +661,7 @@ calc_map_type_and_dist(struct pci_dev *provider, struct pci_dev *client, p2pdma = rcu_dereference(provider->p2pdma); if (p2pdma) xa_store(&p2pdma->map_types, map_types_idx(client), - xa_mk_value(map_type), GFP_KERNEL); + xa_mk_value(map_type), GFP_ATOMIC); rcu_read_unlock(); return map_type; } diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 51ec9e7e784f0..9c59bf03d6579 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -473,6 +473,13 @@ static void pci_device_remove(struct device *dev) if (drv->remove) { pm_runtime_get_sync(dev); + /* + * If the driver provides a .runtime_idle() callback and it has + * started to run already, it may continue to run in parallel + * with the code below, so wait until all of the runtime PM + * activity has completed. + */ + pm_runtime_barrier(dev); drv->remove(pci_dev); pm_runtime_put_noidle(dev); } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index c3585229c12a2..55eabb8dfd4a6 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1250,6 +1250,11 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout) for (;;) { u32 id; + if (pci_dev_is_disconnected(dev)) { + pci_dbg(dev, "disconnected; not waiting\n"); + return -ENOTTY; + } + pci_read_config_dword(dev, PCI_COMMAND, &id); if (!PCI_POSSIBLE_ERROR(id)) break; @@ -1649,25 +1654,10 @@ static int pci_save_pcie_state(struct pci_dev *dev) pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &cap[i++]); pcie_capability_read_word(dev, PCI_EXP_SLTCTL2, &cap[i++]); - return 0; -} - -void pci_bridge_reconfigure_ltr(struct pci_dev *dev) -{ -#ifdef CONFIG_PCIEASPM - struct pci_dev *bridge; - u32 ctl; + pci_save_aspm_l1ss_state(dev); + pci_save_ltr_state(dev); - bridge = pci_upstream_bridge(dev); - if (bridge && bridge->ltr_path) { - pcie_capability_read_dword(bridge, PCI_EXP_DEVCTL2, &ctl); - if (!(ctl & PCI_EXP_DEVCTL2_LTR_EN)) { - pci_dbg(bridge, "re-enabling LTR\n"); - pcie_capability_set_word(bridge, PCI_EXP_DEVCTL2, - PCI_EXP_DEVCTL2_LTR_EN); - } - } -#endif + return 0; } static void pci_restore_pcie_state(struct pci_dev *dev) @@ -1676,6 +1666,13 @@ static void pci_restore_pcie_state(struct pci_dev *dev) struct pci_cap_saved_state *save_state; u16 *cap; + /* + * Restore max latencies (in the LTR capability) before enabling + * LTR itself in PCI_EXP_DEVCTL2. + */ + pci_restore_ltr_state(dev); + pci_restore_aspm_l1ss_state(dev); + save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP); if (!save_state) return; @@ -1733,46 +1730,6 @@ static void pci_restore_pcix_state(struct pci_dev *dev) pci_write_config_word(dev, pos + PCI_X_CMD, cap[i++]); } -static void pci_save_ltr_state(struct pci_dev *dev) -{ - int ltr; - struct pci_cap_saved_state *save_state; - u32 *cap; - - if (!pci_is_pcie(dev)) - return; - - ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR); - if (!ltr) - return; - - save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR); - if (!save_state) { - pci_err(dev, "no suspend buffer for LTR; ASPM issues possible after resume\n"); - return; - } - - /* Some broken devices only support dword access to LTR */ - cap = &save_state->cap.data[0]; - pci_read_config_dword(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, cap); -} - -static void pci_restore_ltr_state(struct pci_dev *dev) -{ - struct pci_cap_saved_state *save_state; - int ltr; - u32 *cap; - - save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR); - ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR); - if (!save_state || !ltr) - return; - - /* Some broken devices only support dword access to LTR */ - cap = &save_state->cap.data[0]; - pci_write_config_dword(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, *cap); -} - /** * pci_save_state - save the PCI configuration space of a device before * suspending @@ -1797,7 +1754,6 @@ int pci_save_state(struct pci_dev *dev) if (i != 0) return i; - pci_save_ltr_state(dev); pci_save_dpc_state(dev); pci_save_aer_state(dev); pci_save_ptm_state(dev); @@ -1898,12 +1854,6 @@ void pci_restore_state(struct pci_dev *dev) if (!dev->state_saved) return; - /* - * Restore max latencies (in the LTR capability) before enabling - * LTR itself (in the PCIe capability). - */ - pci_restore_ltr_state(dev); - pci_restore_pcie_state(dev); pci_restore_pasid_state(dev); pci_restore_pri_state(dev); @@ -3102,6 +3052,18 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { DMI_MATCH(DMI_BOARD_VERSION, "Continental Z2"), }, }, + { + /* + * Changing power state of root port dGPU is connected fails + * https://gitlab.freedesktop.org/drm/amd/-/issues/3229 + */ + .ident = "Hewlett-Packard HP Pavilion 17 Notebook PC/1972", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_BOARD_NAME, "1972"), + DMI_MATCH(DMI_BOARD_VERSION, "95.33"), + }, + }, #endif { } }; @@ -5049,7 +5011,7 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt) * avoid LTSSM race as recommended in Implementation Note at the * end of PCIe r6.0.1 sec 7.5.3.7. */ - rc = pcie_wait_for_link_status(pdev, use_lt, !use_lt); + rc = pcie_wait_for_link_status(pdev, true, false); if (rc) return rc; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index e9750b1b19bad..1c918f7887e8a 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -97,7 +97,6 @@ void pci_msi_init(struct pci_dev *dev); void pci_msix_init(struct pci_dev *dev); bool pci_bridge_d3_possible(struct pci_dev *dev); void pci_bridge_d3_update(struct pci_dev *dev); -void pci_bridge_reconfigure_ltr(struct pci_dev *dev); int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type); static inline void pci_wakeup_event(struct pci_dev *dev) @@ -368,11 +367,6 @@ static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) return 0; } -static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) -{ - return dev->error_state == pci_channel_io_perm_failure; -} - /* pci_dev priv_flags */ #define PCI_DEV_ADDED 0 #define PCI_DPC_RECOVERED 1 @@ -568,16 +562,28 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, bool pcie_wait_for_link(struct pci_dev *pdev, bool active); int pcie_retrain_link(struct pci_dev *pdev, bool use_lt); + +/* ASPM-related functionality we need even without CONFIG_PCIEASPM */ +void pci_save_ltr_state(struct pci_dev *dev); +void pci_restore_ltr_state(struct pci_dev *dev); +void pci_configure_aspm_l1ss(struct pci_dev *dev); +void pci_save_aspm_l1ss_state(struct pci_dev *dev); +void pci_restore_aspm_l1ss_state(struct pci_dev *dev); + #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); +void pci_configure_ltr(struct pci_dev *pdev); +void pci_bridge_reconfigure_ltr(struct pci_dev *pdev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } +static inline void pci_configure_ltr(struct pci_dev *pdev) { } +static inline void pci_bridge_reconfigure_ltr(struct pci_dev *pdev) { } #endif #ifdef CONFIG_PCIE_ECRC diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile index 8de4ed5f98f14..6461aa93fe76e 100644 --- a/drivers/pci/pcie/Makefile +++ b/drivers/pci/pcie/Makefile @@ -6,7 +6,7 @@ pcieportdrv-y := portdrv.o rcec.o obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o -obj-$(CONFIG_PCIEASPM) += aspm.o +obj-y += aspm.o obj-$(CONFIG_PCIEAER) += aer.o err.o obj-$(CONFIG_PCIEAER_INJECT) += aer_inject.o obj-$(CONFIG_PCIE_PME) += pme.o diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 05fc30bb5134d..86bbdd34c5dee 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -1505,6 +1505,22 @@ static int aer_probe(struct pcie_device *dev) return 0; } +static int aer_suspend(struct pcie_device *dev) +{ + struct aer_rpc *rpc = get_service_data(dev); + + aer_disable_rootport(rpc); + return 0; +} + +static int aer_resume(struct pcie_device *dev) +{ + struct aer_rpc *rpc = get_service_data(dev); + + aer_enable_rootport(rpc); + return 0; +} + /** * aer_root_reset - reset Root Port hierarchy, RCEC, or RCiEP * @dev: pointer to Root Port, RCEC, or RCiEP @@ -1569,6 +1585,8 @@ static struct pcie_port_service_driver aerdriver = { .service = PCIE_PORT_SERVICE_AER, .probe = aer_probe, + .suspend = aer_suspend, + .resume = aer_resume, .remove = aer_remove, }; diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index bc0bd86695ec6..a8c20f2e3a468 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -24,6 +24,166 @@ #include "../pci.h" +void pci_save_ltr_state(struct pci_dev *dev) +{ + int ltr; + struct pci_cap_saved_state *save_state; + u32 *cap; + + if (!pci_is_pcie(dev)) + return; + + ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR); + if (!ltr) + return; + + save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR); + if (!save_state) { + pci_err(dev, "no suspend buffer for LTR; ASPM issues possible after resume\n"); + return; + } + + /* Some broken devices only support dword access to LTR */ + cap = &save_state->cap.data[0]; + pci_read_config_dword(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, cap); +} + +void pci_restore_ltr_state(struct pci_dev *dev) +{ + struct pci_cap_saved_state *save_state; + int ltr; + u32 *cap; + + save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR); + ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR); + if (!save_state || !ltr) + return; + + /* Some broken devices only support dword access to LTR */ + cap = &save_state->cap.data[0]; + pci_write_config_dword(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, *cap); +} + +void pci_configure_aspm_l1ss(struct pci_dev *pdev) +{ + int rc; + + pdev->l1ss = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS); + + rc = pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_L1SS, + 2 * sizeof(u32)); + if (rc) + pci_err(pdev, "unable to allocate ASPM L1SS save buffer (%pe)\n", + ERR_PTR(rc)); +} + +void pci_save_aspm_l1ss_state(struct pci_dev *pdev) +{ + struct pci_cap_saved_state *save_state; + u16 l1ss = pdev->l1ss; + u32 *cap; + + /* + * Save L1 substate configuration. The ASPM L0s/L1 configuration + * in PCI_EXP_LNKCTL_ASPMC is saved by pci_save_pcie_state(). + */ + if (!l1ss) + return; + + save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS); + if (!save_state) + return; + + cap = &save_state->cap.data[0]; + pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL2, cap++); + pci_read_config_dword(pdev, l1ss + PCI_L1SS_CTL1, cap++); +} + +void pci_restore_aspm_l1ss_state(struct pci_dev *pdev) +{ + struct pci_cap_saved_state *pl_save_state, *cl_save_state; + struct pci_dev *parent = pdev->bus->self; + u32 *cap, pl_ctl1, pl_ctl2, pl_l1_2_enable; + u32 cl_ctl1, cl_ctl2, cl_l1_2_enable; + u16 clnkctl, plnkctl; + + /* + * In case BIOS enabled L1.2 when resuming, we need to disable it first + * on the downstream component before the upstream. So, don't attempt to + * restore either until we are at the downstream component. + */ + if (pcie_downstream_port(pdev) || !parent) + return; + + if (!pdev->l1ss || !parent->l1ss) + return; + + cl_save_state = pci_find_saved_ext_cap(pdev, PCI_EXT_CAP_ID_L1SS); + pl_save_state = pci_find_saved_ext_cap(parent, PCI_EXT_CAP_ID_L1SS); + if (!cl_save_state || !pl_save_state) + return; + + cap = &cl_save_state->cap.data[0]; + cl_ctl2 = *cap++; + cl_ctl1 = *cap; + cap = &pl_save_state->cap.data[0]; + pl_ctl2 = *cap++; + pl_ctl1 = *cap; + + /* Make sure L0s/L1 are disabled before updating L1SS config */ + pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &clnkctl); + pcie_capability_read_word(parent, PCI_EXP_LNKCTL, &plnkctl); + if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, clnkctl) || + FIELD_GET(PCI_EXP_LNKCTL_ASPMC, plnkctl)) { + pcie_capability_write_word(pdev, PCI_EXP_LNKCTL, + clnkctl & ~PCI_EXP_LNKCTL_ASPMC); + pcie_capability_write_word(parent, PCI_EXP_LNKCTL, + plnkctl & ~PCI_EXP_LNKCTL_ASPMC); + } + + /* + * Disable L1.2 on this downstream endpoint device first, followed + * by the upstream + */ + pci_clear_and_set_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, + PCI_L1SS_CTL1_L1_2_MASK, 0); + pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, + PCI_L1SS_CTL1_L1_2_MASK, 0); + + /* + * In addition, Common_Mode_Restore_Time and LTR_L1.2_THRESHOLD + * in PCI_L1SS_CTL1 must be programmed *before* setting the L1.2 + * enable bits, even though they're all in PCI_L1SS_CTL1. + */ + pl_l1_2_enable = pl_ctl1 & PCI_L1SS_CTL1_L1_2_MASK; + pl_ctl1 &= ~PCI_L1SS_CTL1_L1_2_MASK; + cl_l1_2_enable = cl_ctl1 & PCI_L1SS_CTL1_L1_2_MASK; + cl_ctl1 &= ~PCI_L1SS_CTL1_L1_2_MASK; + + /* Write back without enables first (above we cleared them in ctl1) */ + pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, pl_ctl2); + pci_write_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2, cl_ctl2); + pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, pl_ctl1); + pci_write_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, cl_ctl1); + + /* Then write back the enables */ + if (pl_l1_2_enable || cl_l1_2_enable) { + pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, + pl_ctl1 | pl_l1_2_enable); + pci_write_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, + cl_ctl1 | cl_l1_2_enable); + } + + /* Restore L0s/L1 if they were enabled */ + if (FIELD_GET(PCI_EXP_LNKCTL_ASPMC, clnkctl) || + FIELD_GET(PCI_EXP_LNKCTL_ASPMC, plnkctl)) { + pcie_capability_write_word(parent, PCI_EXP_LNKCTL, plnkctl); + pcie_capability_write_word(pdev, PCI_EXP_LNKCTL, clnkctl); + } +} + +#ifdef CONFIG_PCIEASPM + #ifdef MODULE_PARAM_PREFIX #undef MODULE_PARAM_PREFIX #endif @@ -141,16 +301,42 @@ static int policy_to_clkpm_state(struct pcie_link_state *link) return 0; } +static void pci_update_aspm_saved_state(struct pci_dev *dev) +{ + struct pci_cap_saved_state *save_state; + u16 *cap, lnkctl, aspm_ctl; + + save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP); + if (!save_state) + return; + + pcie_capability_read_word(dev, PCI_EXP_LNKCTL, &lnkctl); + + /* + * Update ASPM and CLKREQ bits of LNKCTL in save_state. We only + * write PCI_EXP_LNKCTL_CCC during enumeration, so it shouldn't + * change after being captured in save_state. + */ + aspm_ctl = lnkctl & (PCI_EXP_LNKCTL_ASPMC | PCI_EXP_LNKCTL_CLKREQ_EN); + lnkctl &= ~(PCI_EXP_LNKCTL_ASPMC | PCI_EXP_LNKCTL_CLKREQ_EN); + + /* Depends on pci_save_pcie_state(): cap[1] is LNKCTL */ + cap = (u16 *)&save_state->cap.data[0]; + cap[1] = lnkctl | aspm_ctl; +} + static void pcie_set_clkpm_nocheck(struct pcie_link_state *link, int enable) { struct pci_dev *child; struct pci_bus *linkbus = link->pdev->subordinate; u32 val = enable ? PCI_EXP_LNKCTL_CLKREQ_EN : 0; - list_for_each_entry(child, &linkbus->devices, bus_list) + list_for_each_entry(child, &linkbus->devices, bus_list) { pcie_capability_clear_and_set_word(child, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_CLKREQ_EN, val); + pci_update_aspm_saved_state(child); + } link->clkpm_enabled = !!enable; } @@ -769,6 +955,12 @@ static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state) pcie_config_aspm_dev(parent, upstream); link->aspm_enabled = state; + + /* Update latest ASPM configuration in saved context */ + pci_save_aspm_l1ss_state(link->downstream); + pci_update_aspm_saved_state(link->downstream); + pci_save_aspm_l1ss_state(parent); + pci_update_aspm_saved_state(parent); } static void pcie_config_aspm_path(struct pcie_link_state *link) @@ -938,6 +1130,78 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev) up_read(&pci_bus_sem); } +void pci_bridge_reconfigure_ltr(struct pci_dev *pdev) +{ + struct pci_dev *bridge; + u32 ctl; + + bridge = pci_upstream_bridge(pdev); + if (bridge && bridge->ltr_path) { + pcie_capability_read_dword(bridge, PCI_EXP_DEVCTL2, &ctl); + if (!(ctl & PCI_EXP_DEVCTL2_LTR_EN)) { + pci_dbg(bridge, "re-enabling LTR\n"); + pcie_capability_set_word(bridge, PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_LTR_EN); + } + } +} + +void pci_configure_ltr(struct pci_dev *pdev) +{ + struct pci_host_bridge *host = pci_find_host_bridge(pdev->bus); + struct pci_dev *bridge; + u32 cap, ctl; + + if (!pci_is_pcie(pdev)) + return; + + pcie_capability_read_dword(pdev, PCI_EXP_DEVCAP2, &cap); + if (!(cap & PCI_EXP_DEVCAP2_LTR)) + return; + + pcie_capability_read_dword(pdev, PCI_EXP_DEVCTL2, &ctl); + if (ctl & PCI_EXP_DEVCTL2_LTR_EN) { + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) { + pdev->ltr_path = 1; + return; + } + + bridge = pci_upstream_bridge(pdev); + if (bridge && bridge->ltr_path) + pdev->ltr_path = 1; + + return; + } + + if (!host->native_ltr) + return; + + /* + * Software must not enable LTR in an Endpoint unless the Root + * Complex and all intermediate Switches indicate support for LTR. + * PCIe r4.0, sec 6.18. + */ + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) { + pcie_capability_set_word(pdev, PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_LTR_EN); + pdev->ltr_path = 1; + return; + } + + /* + * If we're configuring a hot-added device, LTR was likely + * disabled in the upstream bridge, so re-enable it before enabling + * it in the new device. + */ + bridge = pci_upstream_bridge(pdev); + if (bridge && bridge->ltr_path) { + pci_bridge_reconfigure_ltr(pdev); + pcie_capability_set_word(pdev, PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_LTR_EN); + pdev->ltr_path = 1; + } +} + /* Recheck latencies and update aspm_capable for links under the root */ static void pcie_update_aspm_capable(struct pcie_link_state *root) { @@ -1272,6 +1536,17 @@ bool pcie_aspm_enabled(struct pci_dev *pdev) } EXPORT_SYMBOL_GPL(pcie_aspm_enabled); +bool pcie_aspm_capable(struct pci_dev *pdev) +{ + struct pcie_link_state *link = pcie_aspm_get_link(pdev); + + if (!link) + return false; + + return link->aspm_capable; +} +EXPORT_SYMBOL_GPL(pcie_aspm_capable); + static ssize_t aspm_attr_show_common(struct device *dev, struct device_attribute *attr, char *buf, u8 state) @@ -1447,3 +1722,5 @@ bool pcie_aspm_support_enabled(void) { return aspm_support_enabled; } + +#endif /* CONFIG_PCIEASPM */ diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 94111e4382413..c590b08ac1b45 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -234,7 +234,7 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev) for (i = 0; i < pdev->dpc_rp_log_size - 5; i++) { pci_read_config_dword(pdev, - cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, &prefix); + cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG + i * 4, &prefix); pci_err(pdev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix); } clear_status: @@ -358,13 +358,34 @@ void pci_dpc_init(struct pci_dev *pdev) } } +static void dpc_enable(struct pcie_device *dev) +{ + struct pci_dev *pdev = dev->port; + u16 ctl; + + pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl); + ctl &= ~PCI_EXP_DPC_CTL_EN_MASK; + ctl |= PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN; + pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl); +} + +static void dpc_disable(struct pcie_device *dev) +{ + struct pci_dev *pdev = dev->port; + u16 ctl; + + pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl); + ctl &= ~(PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN); + pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl); +} + #define FLAG(x, y) (((x) & (y)) ? '+' : '-') static int dpc_probe(struct pcie_device *dev) { struct pci_dev *pdev = dev->port; struct device *device = &dev->device; int status; - u16 ctl, cap; + u16 cap; if (!pcie_aer_is_native(pdev) && !pcie_ports_dpc_native) return -ENOTSUPP; @@ -379,13 +400,9 @@ static int dpc_probe(struct pcie_device *dev) } pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CAP, &cap); - - pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl); - ctl &= ~PCI_EXP_DPC_CTL_EN_MASK; - ctl |= PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN; - pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl); - + dpc_enable(dev); pci_info(pdev, "enabled with IRQ %d\n", dev->irq); + pci_info(pdev, "error containment capabilities: Int Msg #%d, RPExt%c PoisonedTLP%c SwTrigger%c RP PIO Log %d, DL_ActiveErr%c\n", cap & PCI_EXP_DPC_IRQ, FLAG(cap, PCI_EXP_DPC_CAP_RP_EXT), FLAG(cap, PCI_EXP_DPC_CAP_POISONED_TLP), @@ -396,14 +413,21 @@ static int dpc_probe(struct pcie_device *dev) return status; } -static void dpc_remove(struct pcie_device *dev) +static int dpc_suspend(struct pcie_device *dev) { - struct pci_dev *pdev = dev->port; - u16 ctl; + dpc_disable(dev); + return 0; +} - pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl); - ctl &= ~(PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN); - pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl); +static int dpc_resume(struct pcie_device *dev) +{ + dpc_enable(dev); + return 0; +} + +static void dpc_remove(struct pcie_device *dev) +{ + dpc_disable(dev); } static struct pcie_port_service_driver dpcdriver = { @@ -411,6 +435,8 @@ static struct pcie_port_service_driver dpcdriver = { .port_type = PCIE_ANY_PORT, .service = PCIE_PORT_SERVICE_DPC, .probe = dpc_probe, + .suspend = dpc_suspend, + .resume = dpc_resume, .remove = dpc_remove, }; diff --git a/drivers/pci/pcie/edr.c b/drivers/pci/pcie/edr.c index 5f4914d313a17..e86298dbbcff6 100644 --- a/drivers/pci/pcie/edr.c +++ b/drivers/pci/pcie/edr.c @@ -32,10 +32,10 @@ static int acpi_enable_dpc(struct pci_dev *pdev) int status = 0; /* - * Behavior when calling unsupported _DSM functions is undefined, - * so check whether EDR_PORT_DPC_ENABLE_DSM is supported. + * Per PCI Firmware r3.3, sec 4.6.12, EDR_PORT_DPC_ENABLE_DSM is + * optional. Return success if it's not implemented. */ - if (!acpi_check_dsm(adev->handle, &pci_acpi_dsm_guid, 5, + if (!acpi_check_dsm(adev->handle, &pci_acpi_dsm_guid, 6, 1ULL << EDR_PORT_DPC_ENABLE_DSM)) return 0; @@ -46,12 +46,7 @@ static int acpi_enable_dpc(struct pci_dev *pdev) argv4.package.count = 1; argv4.package.elements = &req; - /* - * Per Downstream Port Containment Related Enhancements ECN to PCI - * Firmware Specification r3.2, sec 4.6.12, EDR_PORT_DPC_ENABLE_DSM is - * optional. Return success if it's not implemented. - */ - obj = acpi_evaluate_dsm(adev->handle, &pci_acpi_dsm_guid, 5, + obj = acpi_evaluate_dsm(adev->handle, &pci_acpi_dsm_guid, 6, EDR_PORT_DPC_ENABLE_DSM, &argv4); if (!obj) return 0; @@ -85,8 +80,9 @@ static struct pci_dev *acpi_dpc_port_get(struct pci_dev *pdev) u16 port; /* - * Behavior when calling unsupported _DSM functions is undefined, - * so check whether EDR_PORT_DPC_ENABLE_DSM is supported. + * If EDR_PORT_LOCATE_DSM is not implemented under the target of + * EDR, the target is the port that experienced the containment + * event (PCI Firmware r3.3, sec 4.6.13). */ if (!acpi_check_dsm(adev->handle, &pci_acpi_dsm_guid, 5, 1ULL << EDR_PORT_LOCATE_DSM)) @@ -103,6 +99,16 @@ static struct pci_dev *acpi_dpc_port_get(struct pci_dev *pdev) return NULL; } + /* + * Bit 31 represents the success/failure of the operation. If bit + * 31 is set, the operation failed. + */ + if (obj->integer.value & BIT(31)) { + ACPI_FREE(obj); + pci_err(pdev, "Locate Port _DSM failed\n"); + return NULL; + } + /* * Firmware returns DPC port BDF details in following format: * 15:8 = bus diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index 59c90d04a609a..705893b5f7b09 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -13,6 +13,7 @@ #define dev_fmt(fmt) "AER: " fmt #include +#include #include #include #include @@ -85,6 +86,18 @@ static int report_error_detected(struct pci_dev *dev, return 0; } +static int pci_pm_runtime_get_sync(struct pci_dev *pdev, void *data) +{ + pm_runtime_get_sync(&pdev->dev); + return 0; +} + +static int pci_pm_runtime_put(struct pci_dev *pdev, void *data) +{ + pm_runtime_put(&pdev->dev); + return 0; +} + static int report_frozen_detected(struct pci_dev *dev, void *data) { return report_error_detected(dev, pci_channel_io_frozen, data); @@ -207,6 +220,8 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, else bridge = pci_upstream_bridge(dev); + pci_walk_bridge(bridge, pci_pm_runtime_get_sync, NULL); + pci_dbg(bridge, "broadcast error_detected message\n"); if (state == pci_channel_io_frozen) { pci_walk_bridge(bridge, report_frozen_detected, &status); @@ -251,10 +266,15 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, pcie_clear_device_status(dev); pci_aer_clear_nonfatal_status(dev); } + + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); + pci_info(bridge, "device recovery successful\n"); return status; failed: + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); + pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT); /* TODO: Should kernel panic here? */ diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b7335be56008f..1434bf495db3c 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2209,67 +2209,6 @@ static void pci_configure_relaxed_ordering(struct pci_dev *dev) } } -static void pci_configure_ltr(struct pci_dev *dev) -{ -#ifdef CONFIG_PCIEASPM - struct pci_host_bridge *host = pci_find_host_bridge(dev->bus); - struct pci_dev *bridge; - u32 cap, ctl; - - if (!pci_is_pcie(dev)) - return; - - /* Read L1 PM substate capabilities */ - dev->l1ss = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_L1SS); - - pcie_capability_read_dword(dev, PCI_EXP_DEVCAP2, &cap); - if (!(cap & PCI_EXP_DEVCAP2_LTR)) - return; - - pcie_capability_read_dword(dev, PCI_EXP_DEVCTL2, &ctl); - if (ctl & PCI_EXP_DEVCTL2_LTR_EN) { - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) { - dev->ltr_path = 1; - return; - } - - bridge = pci_upstream_bridge(dev); - if (bridge && bridge->ltr_path) - dev->ltr_path = 1; - - return; - } - - if (!host->native_ltr) - return; - - /* - * Software must not enable LTR in an Endpoint unless the Root - * Complex and all intermediate Switches indicate support for LTR. - * PCIe r4.0, sec 6.18. - */ - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) { - pcie_capability_set_word(dev, PCI_EXP_DEVCTL2, - PCI_EXP_DEVCTL2_LTR_EN); - dev->ltr_path = 1; - return; - } - - /* - * If we're configuring a hot-added device, LTR was likely - * disabled in the upstream bridge, so re-enable it before enabling - * it in the new device. - */ - bridge = pci_upstream_bridge(dev); - if (bridge && bridge->ltr_path) { - pci_bridge_reconfigure_ltr(dev); - pcie_capability_set_word(dev, PCI_EXP_DEVCTL2, - PCI_EXP_DEVCTL2_LTR_EN); - dev->ltr_path = 1; - } -#endif -} - static void pci_configure_eetlp_prefix(struct pci_dev *dev) { #ifdef CONFIG_PCI_PASID @@ -2320,6 +2259,7 @@ static void pci_configure_device(struct pci_dev *dev) pci_configure_extended_tags(dev, NULL); pci_configure_relaxed_ordering(dev); pci_configure_ltr(dev); + pci_configure_aspm_l1ss(dev); pci_configure_eetlp_prefix(dev); pci_configure_serr(dev); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index d797df6e5f3e9..ce469d84ebaec 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -300,6 +300,21 @@ static void quirk_mmio_always_on(struct pci_dev *dev) DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_BRIDGE_HOST, 8, quirk_mmio_always_on); +/* The BAR0 ~ BAR4 of Marvell 9125 device can't be accessed +* by IO resource file, and need to skip the files +*/ +static void quirk_marvell_mask_bar(struct pci_dev *dev) +{ + int i; + + for (i = 0; i < 5; i++) + if (dev->resource[i].start) + dev->resource[i].start = + dev->resource[i].end = 0; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9125, + quirk_marvell_mask_bar); + /* * The Mellanox Tavor device gives false positive parity errors. Disable * parity error reporting. @@ -5527,6 +5542,7 @@ static void quirk_no_ext_tags(struct pci_dev *pdev) pci_walk_bus(bridge->bus, pci_configure_extended_tags, NULL); } +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_3WARE, 0x1004, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0132, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0140, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0141, quirk_no_ext_tags); @@ -6225,6 +6241,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2b, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2d, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa73f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa76e, dpc_log_size); #endif /* diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 1804794d0e686..5a4adf6c04cf8 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1672,7 +1672,7 @@ static int switchtec_pci_probe(struct pci_dev *pdev, rc = switchtec_init_isr(stdev); if (rc) { dev_err(&stdev->dev, "failed to init isr.\n"); - goto err_put; + goto err_exit_pci; } iowrite32(SWITCHTEC_EVENT_CLEAR | @@ -1693,6 +1693,8 @@ static int switchtec_pci_probe(struct pci_dev *pdev, err_devadd: stdev_kill(stdev); +err_exit_pci: + switchtec_exit_pci(stdev); err_put: ida_free(&switchtec_minor_ida, MINOR(stdev->dev.devt)); put_device(&stdev->dev); diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c index 30cea68595747..b6a677224d682 100644 --- a/drivers/perf/arm_dmc620_pmu.c +++ b/drivers/perf/arm_dmc620_pmu.c @@ -542,12 +542,16 @@ static int dmc620_pmu_event_init(struct perf_event *event) if (event->cpu < 0) return -EINVAL; + hwc->idx = -1; + + if (event->group_leader == event) + return 0; + /* * We can't atomically disable all HW counters so only one event allowed, * although software events are acceptable. */ - if (event->group_leader != event && - !is_software_event(event->group_leader)) + if (!is_software_event(event->group_leader)) return -EINVAL; for_each_sibling_event(sibling, event->group_leader) { @@ -556,7 +560,6 @@ static int dmc620_pmu_event_init(struct perf_event *event) return -EINVAL; } - hwc->idx = -1; return 0; } diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c index b90ba8aca3fa5..ec4d5fc30781c 100644 --- a/drivers/perf/hisilicon/hisi_pcie_pmu.c +++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c @@ -337,15 +337,27 @@ static bool hisi_pcie_pmu_validate_event_group(struct perf_event *event) return false; for (num = 0; num < counters; num++) { + /* + * If we find a related event, then it's a valid group + * since we don't need to allocate a new counter for it. + */ if (hisi_pcie_pmu_cmp_event(event_group[num], sibling)) break; } + /* + * Otherwise it's a new event but if there's no available counter, + * fail the check since we cannot schedule all the events in + * the group simultaneously. + */ + if (num == HISI_PCIE_MAX_COUNTERS) + return false; + if (num == counters) event_group[counters++] = sibling; } - return counters <= HISI_PCIE_MAX_COUNTERS; + return true; } static int hisi_pcie_pmu_event_init(struct perf_event *event) diff --git a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c index 636fb79647c8c..481dcc9e8fbf8 100644 --- a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c @@ -287,12 +287,52 @@ static u64 hisi_uc_pmu_read_counter(struct hisi_pmu *uc_pmu, return readq(uc_pmu->base + HISI_UC_CNTR_REGn(hwc->idx)); } -static void hisi_uc_pmu_write_counter(struct hisi_pmu *uc_pmu, +static bool hisi_uc_pmu_get_glb_en_state(struct hisi_pmu *uc_pmu) +{ + u32 val; + + val = readl(uc_pmu->base + HISI_UC_EVENT_CTRL_REG); + return !!FIELD_GET(HISI_UC_EVENT_GLB_EN, val); +} + +static void hisi_uc_pmu_write_counter_normal(struct hisi_pmu *uc_pmu, struct hw_perf_event *hwc, u64 val) { writeq(val, uc_pmu->base + HISI_UC_CNTR_REGn(hwc->idx)); } +static void hisi_uc_pmu_write_counter_quirk_v2(struct hisi_pmu *uc_pmu, + struct hw_perf_event *hwc, u64 val) +{ + hisi_uc_pmu_start_counters(uc_pmu); + hisi_uc_pmu_write_counter_normal(uc_pmu, hwc, val); + hisi_uc_pmu_stop_counters(uc_pmu); +} + +static void hisi_uc_pmu_write_counter(struct hisi_pmu *uc_pmu, + struct hw_perf_event *hwc, u64 val) +{ + bool enable = hisi_uc_pmu_get_glb_en_state(uc_pmu); + bool erratum = uc_pmu->identifier == HISI_PMU_V2; + + /* + * HiSilicon UC PMU v2 suffers the erratum 162700402 that the + * PMU counter cannot be set due to the lack of clock under power + * saving mode. This will lead to error or inaccurate counts. + * The clock can be enabled by the PMU global enabling control. + * The irq handler and pmu_start() will call the function to set + * period. If the function under irq context, the PMU has been + * enabled therefore we set counter directly. Other situations + * the PMU is disabled, we need to enable it to turn on the + * counter clock to set period, and then restore PMU enable + * status, the counter can hold its value without a clock. + */ + if (enable || !erratum) + hisi_uc_pmu_write_counter_normal(uc_pmu, hwc, val); + else + hisi_uc_pmu_write_counter_quirk_v2(uc_pmu, hwc, val); +} + static void hisi_uc_pmu_enable_counter_int(struct hisi_pmu *uc_pmu, struct hw_perf_event *hwc) { diff --git a/drivers/perf/hisilicon/hns3_pmu.c b/drivers/perf/hisilicon/hns3_pmu.c index 16869bf5bf4cc..60062eaa342aa 100644 --- a/drivers/perf/hisilicon/hns3_pmu.c +++ b/drivers/perf/hisilicon/hns3_pmu.c @@ -1085,15 +1085,27 @@ static bool hns3_pmu_validate_event_group(struct perf_event *event) return false; for (num = 0; num < counters; num++) { + /* + * If we find a related event, then it's a valid group + * since we don't need to allocate a new counter for it. + */ if (hns3_pmu_cmp_event(event_group[num], sibling)) break; } + /* + * Otherwise it's a new event but if there's no available counter, + * fail the check since we cannot schedule all the events in + * the group simultaneously. + */ + if (num == HNS3_PMU_MAX_HW_EVENTS) + return false; + if (num == counters) event_group[counters++] = sibling; } - return counters <= HNS3_PMU_MAX_HW_EVENTS; + return true; } static u32 hns3_pmu_get_filter_condition(struct perf_event *event) @@ -1515,7 +1527,7 @@ static int hns3_pmu_irq_register(struct pci_dev *pdev, return ret; } - ret = devm_add_action(&pdev->dev, hns3_pmu_free_irq, pdev); + ret = devm_add_action_or_reset(&pdev->dev, hns3_pmu_free_irq, pdev); if (ret) { pci_err(pdev, "failed to add free irq action, ret = %d.\n", ret); return ret; diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index c78a6fd6c57f6..b4efdddb2ad91 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -313,6 +313,10 @@ static int riscv_pmu_event_init(struct perf_event *event) u64 event_config = 0; uint64_t cmask; + /* driver does not support branch stack sampling */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + hwc->flags = 0; mapped_event = rvpmu->event_map(event, &event_config); if (mapped_event < 0) { diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index b700f52b7b679..11fcb1867118c 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -110,8 +110,10 @@ static int imx8_pcie_phy_power_on(struct phy *phy) /* Source clock from SoC internal PLL */ writel(ANA_PLL_CLK_OUT_TO_EXT_IO_SEL, imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG062); - writel(AUX_PLL_REFCLK_SEL_SYS_PLL, - imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG063); + if (imx8_phy->drvdata->variant != IMX8MM) { + writel(AUX_PLL_REFCLK_SEL_SYS_PLL, + imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG063); + } val = ANA_AUX_RX_TX_SEL_TX | ANA_AUX_TX_TERM; writel(val | ANA_AUX_RX_TERM_GND_EN, imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG064); diff --git a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c index 24c3371e2bb29..27f221a0f922d 100644 --- a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c @@ -603,7 +603,7 @@ static void comphy_gbe_phy_init(struct mvebu_a3700_comphy_lane *lane, u16 val; fix_idx = 0; - for (addr = 0; addr < 512; addr++) { + for (addr = 0; addr < ARRAY_SIZE(gbe_phy_init); addr++) { /* * All PHY register values are defined in full for 3.125Gbps * SERDES speed. The values required for 1.25 Gbps are almost @@ -611,11 +611,12 @@ static void comphy_gbe_phy_init(struct mvebu_a3700_comphy_lane *lane, * comparison to 3.125 Gbps values. These register values are * stored in "gbe_phy_init_fix" array. */ - if (!is_1gbps && gbe_phy_init_fix[fix_idx].addr == addr) { + if (!is_1gbps && + fix_idx < ARRAY_SIZE(gbe_phy_init_fix) && + gbe_phy_init_fix[fix_idx].addr == addr) { /* Use new value */ val = gbe_phy_init_fix[fix_idx].value; - if (fix_idx < ARRAY_SIZE(gbe_phy_init_fix)) - fix_idx++; + fix_idx++; } else { val = gbe_phy_init[addr]; } diff --git a/drivers/phy/qualcomm/Makefile b/drivers/phy/qualcomm/Makefile index ffd609ac62336..eb60e950ad533 100644 --- a/drivers/phy/qualcomm/Makefile +++ b/drivers/phy/qualcomm/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_PHY_QCOM_IPQ806X_SATA) += phy-qcom-ipq806x-sata.o obj-$(CONFIG_PHY_QCOM_M31_USB) += phy-qcom-m31.o obj-$(CONFIG_PHY_QCOM_PCIE2) += phy-qcom-pcie2.o -obj-$(CONFIG_PHY_QCOM_QMP_COMBO) += phy-qcom-qmp-combo.o +obj-$(CONFIG_PHY_QCOM_QMP_COMBO) += phy-qcom-qmp-combo.o phy-qcom-qmp-usbc.o obj-$(CONFIG_PHY_QCOM_QMP_PCIE) += phy-qcom-qmp-pcie.o obj-$(CONFIG_PHY_QCOM_QMP_PCIE_8996) += phy-qcom-qmp-pcie-msm8996.o obj-$(CONFIG_PHY_QCOM_QMP_UFS) += phy-qcom-qmp-ufs.o diff --git a/drivers/phy/qualcomm/phy-qcom-m31.c b/drivers/phy/qualcomm/phy-qcom-m31.c index 03fb0d4b75d74..20d4c020a83c1 100644 --- a/drivers/phy/qualcomm/phy-qcom-m31.c +++ b/drivers/phy/qualcomm/phy-qcom-m31.c @@ -297,7 +297,7 @@ static int m31usb_phy_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(qphy->phy), "failed to create phy\n"); - qphy->vreg = devm_regulator_get(dev, "vdda-phy"); + qphy->vreg = devm_regulator_get(dev, "vdd"); if (IS_ERR(qphy->vreg)) return dev_err_probe(dev, PTR_ERR(qphy->vreg), "failed to get vreg\n"); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 17c4ad7553a5e..0ecbc26a436f0 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -112,6 +112,7 @@ enum qphy_reg_layout { QPHY_COM_BIAS_EN_CLKBUFLR_EN, QPHY_DP_PHY_STATUS, + QPHY_DP_PHY_VCO_DIV, QPHY_TX_TX_POL_INV, QPHY_TX_TX_DRV_LVL, @@ -137,6 +138,7 @@ static const unsigned int qmp_v3_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, [QPHY_DP_PHY_STATUS] = QSERDES_V3_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V3_DP_PHY_VCO_DIV, [QPHY_TX_TX_POL_INV] = QSERDES_V3_TX_TX_POL_INV, [QPHY_TX_TX_DRV_LVL] = QSERDES_V3_TX_TX_DRV_LVL, @@ -161,6 +163,7 @@ static const unsigned int qmp_v45_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V4_COM_BIAS_EN_CLKBUFLR_EN, [QPHY_DP_PHY_STATUS] = QSERDES_V4_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V4_DP_PHY_VCO_DIV, [QPHY_TX_TX_POL_INV] = QSERDES_V4_TX_TX_POL_INV, [QPHY_TX_TX_DRV_LVL] = QSERDES_V4_TX_TX_DRV_LVL, @@ -185,6 +188,7 @@ static const unsigned int qmp_v5_5nm_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V5_COM_BIAS_EN_CLKBUFLR_EN, [QPHY_DP_PHY_STATUS] = QSERDES_V5_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V5_DP_PHY_VCO_DIV, [QPHY_TX_TX_POL_INV] = QSERDES_V5_5NM_TX_TX_POL_INV, [QPHY_TX_TX_DRV_LVL] = QSERDES_V5_5NM_TX_TX_DRV_LVL, @@ -209,6 +213,7 @@ static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V6_COM_PLL_BIAS_EN_CLK_BUFLR_EN, [QPHY_DP_PHY_STATUS] = QSERDES_V6_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V6_DP_PHY_VCO_DIV, [QPHY_TX_TX_POL_INV] = QSERDES_V6_TX_TX_POL_INV, [QPHY_TX_TX_DRV_LVL] = QSERDES_V6_TX_TX_DRV_LVL, @@ -217,6 +222,31 @@ static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_TX_TRANSCEIVER_BIAS_EN] = QSERDES_V6_TX_TRANSCEIVER_BIAS_EN, }; +static const unsigned int qmp_v6_n4_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { + [QPHY_SW_RESET] = QPHY_V6_N4_PCS_SW_RESET, + [QPHY_START_CTRL] = QPHY_V6_N4_PCS_START_CONTROL, + [QPHY_PCS_STATUS] = QPHY_V6_N4_PCS_PCS_STATUS1, + [QPHY_PCS_POWER_DOWN_CONTROL] = QPHY_V6_N4_PCS_POWER_DOWN_CONTROL, + + /* In PCS_USB */ + [QPHY_PCS_AUTONOMOUS_MODE_CTRL] = QPHY_V6_PCS_USB3_AUTONOMOUS_MODE_CTRL, + [QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V6_PCS_USB3_LFPS_RXTERM_IRQ_CLEAR, + + [QPHY_COM_RESETSM_CNTRL] = QSERDES_V6_COM_RESETSM_CNTRL, + [QPHY_COM_C_READY_STATUS] = QSERDES_V6_COM_C_READY_STATUS, + [QPHY_COM_CMN_STATUS] = QSERDES_V6_COM_CMN_STATUS, + [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V6_COM_PLL_BIAS_EN_CLK_BUFLR_EN, + + [QPHY_DP_PHY_STATUS] = QSERDES_V6_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V6_DP_PHY_VCO_DIV, + + [QPHY_TX_TX_POL_INV] = QSERDES_V6_N4_TX_TX_POL_INV, + [QPHY_TX_TX_DRV_LVL] = QSERDES_V6_N4_TX_TX_DRV_LVL, + [QPHY_TX_TX_EMP_POST1_LVL] = QSERDES_V6_N4_TX_TX_EMP_POST1_LVL, + [QPHY_TX_HIGHZ_DRVR_EN] = QSERDES_V6_N4_TX_HIGHZ_DRVR_EN, + [QPHY_TX_TRANSCEIVER_BIAS_EN] = QSERDES_V6_N4_TX_TRANSCEIVER_BIAS_EN, +}; + static const struct qmp_phy_init_tbl qmp_v3_usb3_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_IVCO, 0x07), QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYSCLK_EN_SEL, 0x14), @@ -1027,6 +1057,31 @@ static const struct qmp_phy_init_tbl qmp_v6_dp_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x0f), }; +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SVS_MODE_CLK_SEL, 0x15), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x3b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_ENABLE1, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_SELECT, 0x30), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xc0), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE0, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CORE_CLK_DIV_MODE0, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_CTRL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_BIAS_EN_CLK_BUFLR_EN, 0x17), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x0f), +}; + static const struct qmp_phy_init_tbl qmp_v6_dp_tx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V6_TX_VMODE_CTRL1, 0x40), QMP_PHY_INIT_CFG(QSERDES_V6_TX_PRE_STALL_LDO_BOOST_EN, 0x30), @@ -1041,6 +1096,19 @@ static const struct qmp_phy_init_tbl qmp_v6_dp_tx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V6_TX_TX_BAND, 0x4), }; +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_VMODE_CTRL1, 0x40), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_PRE_STALL_LDO_BOOST_EN, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_INTERFACE_SELECT, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_CLKBUF_ENABLE, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RESET_TSYNC_EN, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_TRAN_DRVR_EMP_EN, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_PARRATE_REC_DETECT_IDLE_EN, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX, 0x11), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX, 0x11), + QMP_PHY_INIT_CFG(QSERDES_V6_N4_TX_TX_BAND, 0x1), +}; + static const struct qmp_phy_init_tbl qmp_v6_dp_serdes_tbl_rbr[] = { QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x05), QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), @@ -1089,6 +1157,74 @@ static const struct qmp_phy_init_tbl qmp_v6_dp_serdes_tbl_hbr3[] = { QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0c), }; +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl_rbr[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x37), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x71), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x6b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x92), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x01), +}; + +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl_hbr[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x71), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x6b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x92), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x01), +}; + +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl_hbr2[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x46), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x97), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x10), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x6b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x18), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x02), +}; + +static const struct qmp_phy_init_tbl qmp_v6_n4_dp_serdes_tbl_hbr3[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x17), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x15), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x71), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x6b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x92), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x01), +}; + static const struct qmp_phy_init_tbl sc8280xp_usb43dp_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_COM_SSC_EN_CENTER, 0x01), QMP_PHY_INIT_CFG(QSERDES_V5_COM_SSC_PER1, 0x31), @@ -1303,20 +1439,20 @@ static const struct qmp_phy_init_tbl x1e80100_usb43dp_rx_tbl[] = { }; static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_tbl[] = { - QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG1, 0xc4), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG2, 0x89), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG3, 0x20), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_LOCK_DETECT_CONFIG6, 0x13), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x21), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0x55), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_CDR_RESET_TIME, 0x0a), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG1, 0xd4), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_ALIGN_DETECT_CONFIG2, 0x30), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0c), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG1, 0x4b), - QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG5, 0x10), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG1, 0xc4), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG2, 0x89), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG3, 0x20), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG6, 0x13), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_REFGEN_REQ_CONFIG1, 0x21), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_RX_SIGDET_LVL, 0x55), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_RX_CONFIG, 0x0a), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_ALIGN_DETECT_CONFIG1, 0xd4), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_ALIGN_DETECT_CONFIG2, 0x30), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_PCS_TX_RX_CONFIG, 0x0c), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_EQ_CONFIG1, 0x4b), + QMP_PHY_INIT_CFG(QPHY_V6_N4_PCS_EQ_CONFIG5, 0x10), }; static const struct qmp_phy_init_tbl x1e80100_usb43dp_pcs_usb_tbl[] = { @@ -1412,6 +1548,13 @@ static const u8 qmp_dp_v5_voltage_swing_hbr_rbr[4][4] = { { 0x3f, 0xff, 0xff, 0xff } }; +static const u8 qmp_dp_v6_voltage_swing_hbr_rbr[4][4] = { + { 0x27, 0x2f, 0x36, 0x3f }, + { 0x31, 0x3e, 0x3f, 0xff }, + { 0x36, 0x3f, 0xff, 0xff }, + { 0x3f, 0xff, 0xff, 0xff } +}; + static const u8 qmp_dp_v6_pre_emphasis_hbr_rbr[4][4] = { { 0x20, 0x2d, 0x34, 0x3a }, { 0x20, 0x2e, 0x35, 0xff }, @@ -1817,22 +1960,22 @@ static const struct qmp_phy_cfg x1e80100_usb3dpphy_cfg = { .pcs_usb_tbl = x1e80100_usb43dp_pcs_usb_tbl, .pcs_usb_tbl_num = ARRAY_SIZE(x1e80100_usb43dp_pcs_usb_tbl), - .dp_serdes_tbl = qmp_v6_dp_serdes_tbl, - .dp_serdes_tbl_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl), - .dp_tx_tbl = qmp_v6_dp_tx_tbl, - .dp_tx_tbl_num = ARRAY_SIZE(qmp_v6_dp_tx_tbl), - - .serdes_tbl_rbr = qmp_v6_dp_serdes_tbl_rbr, - .serdes_tbl_rbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr), - .serdes_tbl_hbr = qmp_v6_dp_serdes_tbl_hbr, - .serdes_tbl_hbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr), - .serdes_tbl_hbr2 = qmp_v6_dp_serdes_tbl_hbr2, - .serdes_tbl_hbr2_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2), - .serdes_tbl_hbr3 = qmp_v6_dp_serdes_tbl_hbr3, - .serdes_tbl_hbr3_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3), - - .swing_hbr_rbr = &qmp_dp_v5_voltage_swing_hbr_rbr, - .pre_emphasis_hbr_rbr = &qmp_dp_v5_pre_emphasis_hbr_rbr, + .dp_serdes_tbl = qmp_v6_n4_dp_serdes_tbl, + .dp_serdes_tbl_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl), + .dp_tx_tbl = qmp_v6_n4_dp_tx_tbl, + .dp_tx_tbl_num = ARRAY_SIZE(qmp_v6_n4_dp_tx_tbl), + + .serdes_tbl_rbr = qmp_v6_n4_dp_serdes_tbl_rbr, + .serdes_tbl_rbr_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl_rbr), + .serdes_tbl_hbr = qmp_v6_n4_dp_serdes_tbl_hbr, + .serdes_tbl_hbr_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl_hbr), + .serdes_tbl_hbr2 = qmp_v6_n4_dp_serdes_tbl_hbr2, + .serdes_tbl_hbr2_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl_hbr2), + .serdes_tbl_hbr3 = qmp_v6_n4_dp_serdes_tbl_hbr3, + .serdes_tbl_hbr3_num = ARRAY_SIZE(qmp_v6_n4_dp_serdes_tbl_hbr3), + + .swing_hbr_rbr = &qmp_dp_v6_voltage_swing_hbr_rbr, + .pre_emphasis_hbr_rbr = &qmp_dp_v6_pre_emphasis_hbr_rbr, .swing_hbr3_hbr2 = &qmp_dp_v5_voltage_swing_hbr3_hbr2, .pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2, @@ -1845,7 +1988,7 @@ static const struct qmp_phy_cfg x1e80100_usb3dpphy_cfg = { .num_resets = ARRAY_SIZE(msm8996_usb3phy_reset_l), .vreg_list = qmp_phy_vreg_l, .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), - .regs = qmp_v45_usb3phy_regs_layout, + .regs = qmp_v6_n4_usb3phy_regs_layout, }; static const struct qmp_phy_cfg sm6350_usb3dpphy_cfg = { @@ -2057,6 +2200,51 @@ static void qmp_combo_configure(void __iomem *base, qmp_combo_configure_lane(base, tbl, num, 0xff); } +static const struct qmp_phy_cfg sm8650_usb3dpphy_cfg = { + .offsets = &qmp_combo_offsets_v3, + + .serdes_tbl = sm8550_usb3_serdes_tbl, + .serdes_tbl_num = ARRAY_SIZE(sm8550_usb3_serdes_tbl), + .tx_tbl = sm8550_usb3_tx_tbl, + .tx_tbl_num = ARRAY_SIZE(sm8550_usb3_tx_tbl), + .rx_tbl = sm8550_usb3_rx_tbl, + .rx_tbl_num = ARRAY_SIZE(sm8550_usb3_rx_tbl), + .pcs_tbl = sm8550_usb3_pcs_tbl, + .pcs_tbl_num = ARRAY_SIZE(sm8550_usb3_pcs_tbl), + .pcs_usb_tbl = sm8550_usb3_pcs_usb_tbl, + .pcs_usb_tbl_num = ARRAY_SIZE(sm8550_usb3_pcs_usb_tbl), + + .dp_serdes_tbl = qmp_v6_dp_serdes_tbl, + .dp_serdes_tbl_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl), + .dp_tx_tbl = qmp_v6_dp_tx_tbl, + .dp_tx_tbl_num = ARRAY_SIZE(qmp_v6_dp_tx_tbl), + + .serdes_tbl_rbr = qmp_v6_dp_serdes_tbl_rbr, + .serdes_tbl_rbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr), + .serdes_tbl_hbr = qmp_v6_dp_serdes_tbl_hbr, + .serdes_tbl_hbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr), + .serdes_tbl_hbr2 = qmp_v6_dp_serdes_tbl_hbr2, + .serdes_tbl_hbr2_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2), + .serdes_tbl_hbr3 = qmp_v6_dp_serdes_tbl_hbr3, + .serdes_tbl_hbr3_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3), + + .swing_hbr_rbr = &qmp_dp_v6_voltage_swing_hbr_rbr, + .pre_emphasis_hbr_rbr = &qmp_dp_v6_pre_emphasis_hbr_rbr, + .swing_hbr3_hbr2 = &qmp_dp_v5_voltage_swing_hbr3_hbr2, + .pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2, + + .dp_aux_init = qmp_v4_dp_aux_init, + .configure_dp_tx = qmp_v4_configure_dp_tx, + .configure_dp_phy = qmp_v4_configure_dp_phy, + .calibrate_dp_phy = qmp_v4_calibrate_dp_phy, + + .regs = qmp_v6_usb3phy_regs_layout, + .reset_list = msm8996_usb3phy_reset_l, + .num_resets = ARRAY_SIZE(msm8996_usb3phy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), +}; + static int qmp_combo_dp_serdes_init(struct qmp_combo *qmp) { const struct qmp_phy_cfg *cfg = qmp->cfg; @@ -2211,9 +2399,9 @@ static bool qmp_combo_configure_dp_mode(struct qmp_combo *qmp) writel(val, qmp->dp_dp_phy + QSERDES_DP_PHY_PD_CTL); if (reverse) - writel(0x4c, qmp->pcs + QSERDES_DP_PHY_MODE); + writel(0x4c, qmp->dp_dp_phy + QSERDES_DP_PHY_MODE); else - writel(0x5c, qmp->pcs + QSERDES_DP_PHY_MODE); + writel(0x5c, qmp->dp_dp_phy + QSERDES_DP_PHY_MODE); return reverse; } @@ -2223,6 +2411,7 @@ static int qmp_combo_configure_dp_clocks(struct qmp_combo *qmp) const struct phy_configure_opts_dp *dp_opts = &qmp->dp_opts; u32 phy_vco_div; unsigned long pixel_freq; + const struct qmp_phy_cfg *cfg = qmp->cfg; switch (dp_opts->link_rate) { case 1620: @@ -2245,7 +2434,7 @@ static int qmp_combo_configure_dp_clocks(struct qmp_combo *qmp) /* Other link rates aren't supported */ return -EINVAL; } - writel(phy_vco_div, qmp->dp_dp_phy + QSERDES_V4_DP_PHY_VCO_DIV); + writel(phy_vco_div, qmp->dp_dp_phy + cfg->regs[QPHY_DP_PHY_VCO_DIV]); clk_set_rate(qmp->dp_link_hw.clk, dp_opts->link_rate * 100000); clk_set_rate(qmp->dp_pixel_hw.clk, pixel_freq); @@ -2492,8 +2681,6 @@ static int qmp_v4_configure_dp_phy(struct qmp_combo *qmp) writel(0x20, qmp->dp_tx2 + cfg->regs[QPHY_TX_TX_EMP_POST1_LVL]); return 0; - - return 0; } /* @@ -3686,7 +3873,7 @@ static const struct of_device_id qmp_combo_of_match_table[] = { }, { .compatible = "qcom,sm8650-qmp-usb3-dp-phy", - .data = &sm8550_usb3dpphy_cfg, + .data = &sm8650_usb3dpphy_cfg, }, { .compatible = "qcom,x1e80100-qmp-usb3-dp-phy", diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6-n4.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6-n4.h new file mode 100644 index 0000000000000..b3024714dab4e --- /dev/null +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6-n4.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023, Linaro Limited + */ + +#ifndef QCOM_PHY_QMP_PCS_V6_N4_H_ +#define QCOM_PHY_QMP_PCS_V6_N4_H_ + +/* Only for QMP V6 N4 PHY - USB/PCIe PCS registers */ +#define QPHY_V6_N4_PCS_SW_RESET 0x000 +#define QPHY_V6_N4_PCS_PCS_STATUS1 0x014 +#define QPHY_V6_N4_PCS_POWER_DOWN_CONTROL 0x040 +#define QPHY_V6_N4_PCS_START_CONTROL 0x044 +#define QPHY_V6_N4_PCS_POWER_STATE_CONFIG1 0x090 +#define QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG1 0x0c4 +#define QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG2 0x0c8 +#define QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG3 0x0cc +#define QPHY_V6_N4_PCS_LOCK_DETECT_CONFIG6 0x0d8 +#define QPHY_V6_N4_PCS_REFGEN_REQ_CONFIG1 0x0dc +#define QPHY_V6_N4_PCS_RX_SIGDET_LVL 0x188 +#define QPHY_V6_N4_PCS_RCVR_DTCT_DLY_P1U2_L 0x190 +#define QPHY_V6_N4_PCS_RCVR_DTCT_DLY_P1U2_H 0x194 +#define QPHY_V6_N4_PCS_RATE_SLEW_CNTRL1 0x198 +#define QPHY_V6_N4_PCS_RX_CONFIG 0x1b0 +#define QPHY_V6_N4_PCS_ALIGN_DETECT_CONFIG1 0x1c0 +#define QPHY_V6_N4_PCS_ALIGN_DETECT_CONFIG2 0x1c4 +#define QPHY_V6_N4_PCS_PCS_TX_RX_CONFIG 0x1d0 +#define QPHY_V6_N4_PCS_EQ_CONFIG1 0x1dc +#define QPHY_V6_N4_PCS_EQ_CONFIG2 0x1e0 +#define QPHY_V6_N4_PCS_EQ_CONFIG5 0x1ec + +#endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h index a814ad11af071..d37cc0d4fd365 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6_n4.h @@ -6,11 +6,24 @@ #ifndef QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_ #define QCOM_PHY_QMP_QSERDES_TXRX_V6_N4_H_ +#define QSERDES_V6_N4_TX_CLKBUF_ENABLE 0x08 +#define QSERDES_V6_N4_TX_TX_EMP_POST1_LVL 0x0c +#define QSERDES_V6_N4_TX_TX_DRV_LVL 0x14 +#define QSERDES_V6_N4_TX_RESET_TSYNC_EN 0x1c +#define QSERDES_V6_N4_TX_PRE_STALL_LDO_BOOST_EN 0x20 #define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_TX 0x30 #define QSERDES_V6_N4_TX_RES_CODE_LANE_OFFSET_RX 0x34 +#define QSERDES_V6_N4_TX_TRANSCEIVER_BIAS_EN 0x48 +#define QSERDES_V6_N4_TX_HIGHZ_DRVR_EN 0x4c +#define QSERDES_V6_N4_TX_TX_POL_INV 0x50 +#define QSERDES_V6_N4_TX_PARRATE_REC_DETECT_IDLE_EN 0x54 #define QSERDES_V6_N4_TX_LANE_MODE_1 0x78 #define QSERDES_V6_N4_TX_LANE_MODE_2 0x7c #define QSERDES_V6_N4_TX_LANE_MODE_3 0x80 +#define QSERDES_V6_N4_TX_TRAN_DRVR_EMP_EN 0xac +#define QSERDES_V6_N4_TX_TX_BAND 0xd8 +#define QSERDES_V6_N4_TX_INTERFACE_SELECT 0xe4 +#define QSERDES_V6_N4_TX_VMODE_CTRL1 0xb0 #define QSERDES_V6_N4_RX_UCDR_FO_GAIN_RATE2 0x8 #define QSERDES_V6_N4_RX_UCDR_SO_GAIN_RATE2 0x18 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index 5c003988c35d3..4c32304dae87f 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -121,15 +121,6 @@ static const unsigned int qmp_v3_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_PCS_MISC_CLAMP_ENABLE] = QPHY_V3_PCS_MISC_CLAMP_ENABLE, }; -static const unsigned int qmp_v3_usb3phy_regs_layout_qcm2290[QPHY_LAYOUT_SIZE] = { - [QPHY_SW_RESET] = QPHY_V3_PCS_SW_RESET, - [QPHY_START_CTRL] = QPHY_V3_PCS_START_CONTROL, - [QPHY_PCS_STATUS] = QPHY_V3_PCS_PCS_STATUS, - [QPHY_PCS_AUTONOMOUS_MODE_CTRL] = QPHY_V3_PCS_AUTONOMOUS_MODE_CTRL, - [QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V3_PCS_LFPS_RXTERM_IRQ_CLEAR, - [QPHY_PCS_POWER_DOWN_CONTROL] = QPHY_V3_PCS_POWER_DOWN_CONTROL, -}; - static const unsigned int qmp_v4_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_SW_RESET] = QPHY_V4_PCS_SW_RESET, [QPHY_START_CTRL] = QPHY_V4_PCS_START_CONTROL, @@ -514,115 +505,6 @@ static const struct qmp_phy_init_tbl qmp_v3_usb3_uniphy_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V3_PCS_REFGEN_REQ_CONFIG2, 0x60), }; -static const struct qmp_phy_init_tbl msm8998_usb3_serdes_tbl[] = { - QMP_PHY_INIT_CFG(QSERDES_V3_COM_CLK_SELECT, 0x30), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, 0x04), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYSCLK_EN_SEL, 0x14), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYS_CLK_CTRL, 0x06), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_RESETSM_CNTRL2, 0x08), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_CMN_CONFIG, 0x06), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SVS_MODE_CLK_SEL, 0x01), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_HSCLK_SEL, 0x80), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_DEC_START_MODE0, 0x82), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START1_MODE0, 0xab), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START2_MODE0, 0xea), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START3_MODE0, 0x02), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_CP_CTRL_MODE0, 0x06), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_RCTRL_MODE0, 0x16), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_CCTRL_MODE0, 0x36), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_INTEGLOOP_GAIN1_MODE0, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_INTEGLOOP_GAIN0_MODE0, 0x3f), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE2_MODE0, 0x01), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE1_MODE0, 0xc9), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_CORECLK_DIV_MODE0, 0x0a), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP3_MODE0, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP2_MODE0, 0x34), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP1_MODE0, 0x15), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP_EN, 0x04), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_CORE_CLK_EN, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP_CFG, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE_MAP, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_BG_TIMER, 0x0a), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_IVCO, 0x07), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_INTEGLOOP_INITVAL, 0x80), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_CMN_MODE, 0x01), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_EN_CENTER, 0x01), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_PER1, 0x31), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_PER2, 0x01), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_ADJ_PER1, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_ADJ_PER2, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_STEP_SIZE1, 0x85), - QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_STEP_SIZE2, 0x07), -}; - -static const struct qmp_phy_init_tbl msm8998_usb3_tx_tbl[] = { - QMP_PHY_INIT_CFG(QSERDES_V3_TX_HIGHZ_DRVR_EN, 0x10), - QMP_PHY_INIT_CFG(QSERDES_V3_TX_RCV_DETECT_LVL_2, 0x12), - QMP_PHY_INIT_CFG(QSERDES_V3_TX_LANE_MODE_1, 0x16), - QMP_PHY_INIT_CFG(QSERDES_V3_TX_RES_CODE_LANE_OFFSET_TX, 0x00), -}; - -static const struct qmp_phy_init_tbl msm8998_usb3_rx_tbl[] = { - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4e), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL4, 0x18), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x07), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_OFFSET_ADAPTOR_CNTRL2, 0x80), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_CNTRL, 0x43), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_DEGLITCH_CNTRL, 0x1c), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x75), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_LOW, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_PI_CONTROLS, 0x80), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FO_GAIN, 0x0a), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_GAIN, 0x06), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_ENABLES, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_VGA_CAL_CNTRL2, 0x03), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_MODE_00, 0x05), -}; - -static const struct qmp_phy_init_tbl msm8998_usb3_pcs_tbl[] = { - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL2, 0x83), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_L, 0x09), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_H_TOL, 0xa2), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_MAN_CODE, 0x40), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL1, 0x02), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG1, 0xd1), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG2, 0x1f), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG3, 0x47), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_POWER_STATE_CONFIG2, 0x1b), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V0, 0x9f), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V1, 0x9f), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V2, 0xb7), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V3, 0x4e), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V4, 0x65), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_LS, 0x6b), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V0, 0x15), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V0, 0x0d), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V1, 0x15), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V1, 0x0d), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V2, 0x15), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V2, 0x0d), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V3, 0x15), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V3, 0x0d), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V4, 0x15), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V4, 0x0d), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_LS, 0x15), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_LS, 0x0d), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RATE_SLEW_CNTRL, 0x02), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x04), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TSYNC_RSYNC_TIME, 0x44), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_L, 0x40), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_H, 0x00), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RX_SIGDET_LVL, 0x8a), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_WAIT_TIME, 0x75), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_LFPS_TX_ECSTART_EQTLOCK, 0x86), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13), -}; - static const struct qmp_phy_init_tbl sm8150_usb3_uniphy_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYSCLK_EN_SEL, 0x1a), QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_HSCLK_SEL, 0x11), @@ -1089,99 +971,6 @@ static const struct qmp_phy_init_tbl sm8350_usb3_uniphy_pcs_usb_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), }; -static const struct qmp_phy_init_tbl qcm2290_usb3_serdes_tbl[] = { - QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x14), - QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x08), - QMP_PHY_INIT_CFG(QSERDES_COM_CLK_SELECT, 0x30), - QMP_PHY_INIT_CFG(QSERDES_COM_SYS_CLK_CTRL, 0x06), - QMP_PHY_INIT_CFG(QSERDES_COM_RESETSM_CNTRL, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_RESETSM_CNTRL2, 0x08), - QMP_PHY_INIT_CFG(QSERDES_COM_BG_TRIM, 0x0f), - QMP_PHY_INIT_CFG(QSERDES_COM_SVS_MODE_CLK_SEL, 0x01), - QMP_PHY_INIT_CFG(QSERDES_COM_HSCLK_SEL, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_DEC_START_MODE0, 0x82), - QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START1_MODE0, 0x55), - QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START2_MODE0, 0x55), - QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START3_MODE0, 0x03), - QMP_PHY_INIT_CFG(QSERDES_COM_CP_CTRL_MODE0, 0x0b), - QMP_PHY_INIT_CFG(QSERDES_COM_PLL_RCTRL_MODE0, 0x16), - QMP_PHY_INIT_CFG(QSERDES_COM_PLL_CCTRL_MODE0, 0x28), - QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN0_MODE0, 0x80), - QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN1_MODE0, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_CORECLK_DIV, 0x0a), - QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP1_MODE0, 0x15), - QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP2_MODE0, 0x34), - QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP3_MODE0, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_EN, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_CORE_CLK_EN, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_CFG, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_MAP, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_BG_TIMER, 0x0a), - QMP_PHY_INIT_CFG(QSERDES_COM_SSC_EN_CENTER, 0x01), - QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER1, 0x31), - QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER2, 0x01), - QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER1, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER2, 0x00), - QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE1, 0xde), - QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE2, 0x07), - QMP_PHY_INIT_CFG(QSERDES_COM_PLL_IVCO, 0x0f), - QMP_PHY_INIT_CFG(QSERDES_COM_CMN_CONFIG, 0x06), - QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_INITVAL, 0x80), - QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CTRL_BY_PSM, 0x01), -}; - -static const struct qmp_phy_init_tbl qcm2290_usb3_tx_tbl[] = { - QMP_PHY_INIT_CFG(QSERDES_V3_TX_HIGHZ_DRVR_EN, 0x10), - QMP_PHY_INIT_CFG(QSERDES_V3_TX_RCV_DETECT_LVL_2, 0x12), - QMP_PHY_INIT_CFG(QSERDES_V3_TX_LANE_MODE_1, 0xc6), - QMP_PHY_INIT_CFG(QSERDES_V3_TX_RES_CODE_LANE_OFFSET_TX, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_TX_RES_CODE_LANE_OFFSET_RX, 0x00), -}; - -static const struct qmp_phy_init_tbl qcm2290_usb3_rx_tbl[] = { - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_PI_CONTROLS, 0x80), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_LOW, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FO_GAIN, 0x0a), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_GAIN, 0x06), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x75), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x02), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4e), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL4, 0x18), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x77), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_OFFSET_ADAPTOR_CNTRL2, 0x80), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_VGA_CAL_CNTRL2, 0x0a), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_CNTRL, 0x03), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_DEGLITCH_CNTRL, 0x16), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_ENABLES, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_MODE_00, 0x00), -}; - -static const struct qmp_phy_init_tbl qcm2290_usb3_pcs_tbl[] = { - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V0, 0x9f), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V0, 0x17), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V0, 0x0f), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL2, 0x83), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL1, 0x02), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_L, 0x09), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_H_TOL, 0xa2), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_MAN_CODE, 0x85), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG1, 0xd1), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG2, 0x1f), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG3, 0x47), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_WAIT_TIME, 0x75), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_LFPS_TX_ECSTART_EQTLOCK, 0x86), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x04), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_TSYNC_RSYNC_TIME, 0x44), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_L, 0x40), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_H, 0x00), - QMP_PHY_INIT_CFG(QPHY_V3_PCS_RX_SIGDET_LVL, 0x88), -}; - static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_COM_SYSCLK_EN_SEL, 0x1a), QMP_PHY_INIT_CFG(QSERDES_V5_COM_BIN_VCOCAL_HSCLK_SEL, 0x11), @@ -1579,16 +1368,6 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v3_msm8996 = { .rx = 0x400, }; -static const struct qmp_usb_offsets qmp_usb_offsets_v3_qcm2290 = { - .serdes = 0x0, - .pcs = 0xc00, - .pcs_misc = 0xa00, - .tx = 0x200, - .rx = 0x400, - .tx2 = 0x600, - .rx2 = 0x800, -}; - static const struct qmp_usb_offsets qmp_usb_offsets_v4 = { .serdes = 0, .pcs = 0x0800, @@ -1753,24 +1532,6 @@ static const struct qmp_phy_cfg qmp_v3_usb3_uniphy_cfg = { .has_pwrdn_delay = true, }; -static const struct qmp_phy_cfg msm8998_usb3phy_cfg = { - .lanes = 2, - - .offsets = &qmp_usb_offsets_v3_qcm2290, - - .serdes_tbl = msm8998_usb3_serdes_tbl, - .serdes_tbl_num = ARRAY_SIZE(msm8998_usb3_serdes_tbl), - .tx_tbl = msm8998_usb3_tx_tbl, - .tx_tbl_num = ARRAY_SIZE(msm8998_usb3_tx_tbl), - .rx_tbl = msm8998_usb3_rx_tbl, - .rx_tbl_num = ARRAY_SIZE(msm8998_usb3_rx_tbl), - .pcs_tbl = msm8998_usb3_pcs_tbl, - .pcs_tbl_num = ARRAY_SIZE(msm8998_usb3_pcs_tbl), - .vreg_list = qmp_phy_vreg_l, - .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), - .regs = qmp_v3_usb3phy_regs_layout, -}; - static const struct qmp_phy_cfg sm8150_usb3_uniphy_cfg = { .lanes = 1, @@ -1908,24 +1669,6 @@ static const struct qmp_phy_cfg sm8350_usb3_uniphy_cfg = { .has_pwrdn_delay = true, }; -static const struct qmp_phy_cfg qcm2290_usb3phy_cfg = { - .lanes = 2, - - .offsets = &qmp_usb_offsets_v3_qcm2290, - - .serdes_tbl = qcm2290_usb3_serdes_tbl, - .serdes_tbl_num = ARRAY_SIZE(qcm2290_usb3_serdes_tbl), - .tx_tbl = qcm2290_usb3_tx_tbl, - .tx_tbl_num = ARRAY_SIZE(qcm2290_usb3_tx_tbl), - .rx_tbl = qcm2290_usb3_rx_tbl, - .rx_tbl_num = ARRAY_SIZE(qcm2290_usb3_rx_tbl), - .pcs_tbl = qcm2290_usb3_pcs_tbl, - .pcs_tbl_num = ARRAY_SIZE(qcm2290_usb3_pcs_tbl), - .vreg_list = qmp_phy_vreg_l, - .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), - .regs = qmp_v3_usb3phy_regs_layout_qcm2290, -}; - static const struct qmp_phy_cfg x1e80100_usb3_uniphy_cfg = { .lanes = 1, @@ -2599,12 +2342,6 @@ static const struct of_device_id qmp_usb_of_match_table[] = { }, { .compatible = "qcom,msm8996-qmp-usb3-phy", .data = &msm8996_usb3phy_cfg, - }, { - .compatible = "qcom,msm8998-qmp-usb3-phy", - .data = &msm8998_usb3phy_cfg, - }, { - .compatible = "qcom,qcm2290-qmp-usb3-phy", - .data = &qcm2290_usb3phy_cfg, }, { .compatible = "qcom,sa8775p-qmp-usb3-uni-phy", .data = &sa8775p_usb3_uniphy_cfg, @@ -2623,9 +2360,6 @@ static const struct of_device_id qmp_usb_of_match_table[] = { }, { .compatible = "qcom,sdx75-qmp-usb3-uni-phy", .data = &sdx75_usb3_uniphy_cfg, - }, { - .compatible = "qcom,sm6115-qmp-usb3-phy", - .data = &qcm2290_usb3phy_cfg, }, { .compatible = "qcom,sm8150-qmp-usb3-uni-phy", .data = &sm8150_usb3_uniphy_cfg, diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usbc.c b/drivers/phy/qualcomm/phy-qcom-qmp-usbc.c new file mode 100644 index 0000000000000..3a4b4849db0f5 --- /dev/null +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usbc.c @@ -0,0 +1,1195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2017, The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "phy-qcom-qmp.h" +#include "phy-qcom-qmp-pcs-misc-v3.h" + +/* QPHY_SW_RESET bit */ +#define SW_RESET BIT(0) +/* QPHY_POWER_DOWN_CONTROL */ +#define SW_PWRDN BIT(0) +/* QPHY_START_CONTROL bits */ +#define SERDES_START BIT(0) +#define PCS_START BIT(1) +/* QPHY_PCS_STATUS bit */ +#define PHYSTATUS BIT(6) + +/* QPHY_V3_DP_COM_RESET_OVRD_CTRL register bits */ +/* DP PHY soft reset */ +#define SW_DPPHY_RESET BIT(0) +/* mux to select DP PHY reset control, 0:HW control, 1: software reset */ +#define SW_DPPHY_RESET_MUX BIT(1) +/* USB3 PHY soft reset */ +#define SW_USB3PHY_RESET BIT(2) +/* mux to select USB3 PHY reset control, 0:HW control, 1: software reset */ +#define SW_USB3PHY_RESET_MUX BIT(3) + +/* QPHY_V3_DP_COM_PHY_MODE_CTRL register bits */ +#define USB3_MODE BIT(0) /* enables USB3 mode */ +#define DP_MODE BIT(1) /* enables DP mode */ + +/* QPHY_PCS_AUTONOMOUS_MODE_CTRL register bits */ +#define ARCVR_DTCT_EN BIT(0) +#define ALFPS_DTCT_EN BIT(1) +#define ARCVR_DTCT_EVENT_SEL BIT(4) + +/* QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR register bits */ +#define IRQ_CLEAR BIT(0) + +#define PHY_INIT_COMPLETE_TIMEOUT 10000 + +struct qmp_phy_init_tbl { + unsigned int offset; + unsigned int val; + /* + * mask of lanes for which this register is written + * for cases when second lane needs different values + */ + u8 lane_mask; +}; + +#define QMP_PHY_INIT_CFG(o, v) \ + { \ + .offset = o, \ + .val = v, \ + .lane_mask = 0xff, \ + } + +#define QMP_PHY_INIT_CFG_LANE(o, v, l) \ + { \ + .offset = o, \ + .val = v, \ + .lane_mask = l, \ + } + +/* set of registers with offsets different per-PHY */ +enum qphy_reg_layout { + /* PCS registers */ + QPHY_SW_RESET, + QPHY_START_CTRL, + QPHY_PCS_STATUS, + QPHY_PCS_AUTONOMOUS_MODE_CTRL, + QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR, + QPHY_PCS_POWER_DOWN_CONTROL, + /* Keep last to ensure regs_layout arrays are properly initialized */ + QPHY_LAYOUT_SIZE +}; + +static const unsigned int qmp_v3_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { + [QPHY_SW_RESET] = QPHY_V3_PCS_SW_RESET, + [QPHY_START_CTRL] = QPHY_V3_PCS_START_CONTROL, + [QPHY_PCS_STATUS] = QPHY_V3_PCS_PCS_STATUS, + [QPHY_PCS_AUTONOMOUS_MODE_CTRL] = QPHY_V3_PCS_AUTONOMOUS_MODE_CTRL, + [QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V3_PCS_LFPS_RXTERM_IRQ_CLEAR, + [QPHY_PCS_POWER_DOWN_CONTROL] = QPHY_V3_PCS_POWER_DOWN_CONTROL, +}; + +static const unsigned int qmp_v3_usb3phy_regs_layout_qcm2290[QPHY_LAYOUT_SIZE] = { + [QPHY_SW_RESET] = QPHY_V3_PCS_SW_RESET, + [QPHY_START_CTRL] = QPHY_V3_PCS_START_CONTROL, + [QPHY_PCS_STATUS] = QPHY_V3_PCS_PCS_STATUS, + [QPHY_PCS_AUTONOMOUS_MODE_CTRL] = QPHY_V3_PCS_AUTONOMOUS_MODE_CTRL, + [QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR] = QPHY_V3_PCS_LFPS_RXTERM_IRQ_CLEAR, + [QPHY_PCS_POWER_DOWN_CONTROL] = QPHY_V3_PCS_POWER_DOWN_CONTROL, +}; + +static const struct qmp_phy_init_tbl msm8998_usb3_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V3_COM_CLK_SELECT, 0x30), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYSCLK_EN_SEL, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SYS_CLK_CTRL, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_RESETSM_CNTRL2, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_CMN_CONFIG, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SVS_MODE_CLK_SEL, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_HSCLK_SEL, 0x80), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_DEC_START_MODE0, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START1_MODE0, 0xab), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START2_MODE0, 0xea), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_DIV_FRAC_START3_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_CP_CTRL_MODE0, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_INTEGLOOP_GAIN1_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_INTEGLOOP_GAIN0_MODE0, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE2_MODE0, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE1_MODE0, 0xc9), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_CORECLK_DIV_MODE0, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP3_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP2_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP1_MODE0, 0x15), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP_EN, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_CORE_CLK_EN, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_LOCK_CMP_CFG, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_VCO_TUNE_MAP, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_BG_TIMER, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_PLL_IVCO, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_INTEGLOOP_INITVAL, 0x80), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_CMN_MODE, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_PER2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_ADJ_PER2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_STEP_SIZE1, 0x85), + QMP_PHY_INIT_CFG(QSERDES_V3_COM_SSC_STEP_SIZE2, 0x07), +}; + +static const struct qmp_phy_init_tbl msm8998_usb3_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V3_TX_HIGHZ_DRVR_EN, 0x10), + QMP_PHY_INIT_CFG(QSERDES_V3_TX_RCV_DETECT_LVL_2, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V3_TX_LANE_MODE_1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V3_TX_RES_CODE_LANE_OFFSET_TX, 0x00), +}; + +static const struct qmp_phy_init_tbl msm8998_usb3_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4e), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL4, 0x18), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_OFFSET_ADAPTOR_CNTRL2, 0x80), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_CNTRL, 0x43), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_DEGLITCH_CNTRL, 0x1c), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x75), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_LOW, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_PI_CONTROLS, 0x80), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FO_GAIN, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_GAIN, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_ENABLES, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_VGA_CAL_CNTRL2, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_MODE_00, 0x05), +}; + +static const struct qmp_phy_init_tbl msm8998_usb3_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL2, 0x83), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_L, 0x09), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_H_TOL, 0xa2), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_MAN_CODE, 0x40), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL1, 0x02), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG1, 0xd1), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG2, 0x1f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG3, 0x47), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_POWER_STATE_CONFIG2, 0x1b), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V0, 0x9f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V1, 0x9f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V2, 0xb7), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V3, 0x4e), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V4, 0x65), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_LS, 0x6b), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V0, 0x15), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V0, 0x0d), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V1, 0x15), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V1, 0x0d), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V2, 0x15), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V2, 0x0d), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V3, 0x15), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V3, 0x0d), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V4, 0x15), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V4, 0x0d), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_LS, 0x15), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_LS, 0x0d), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RATE_SLEW_CNTRL, 0x02), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x04), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TSYNC_RSYNC_TIME, 0x44), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_L, 0x40), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_H, 0x00), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RX_SIGDET_LVL, 0x8a), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_WAIT_TIME, 0x75), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_LFPS_TX_ECSTART_EQTLOCK, 0x86), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13), +}; + +static const struct qmp_phy_init_tbl qcm2290_usb3_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x14), + QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x08), + QMP_PHY_INIT_CFG(QSERDES_COM_CLK_SELECT, 0x30), + QMP_PHY_INIT_CFG(QSERDES_COM_SYS_CLK_CTRL, 0x06), + QMP_PHY_INIT_CFG(QSERDES_COM_RESETSM_CNTRL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_RESETSM_CNTRL2, 0x08), + QMP_PHY_INIT_CFG(QSERDES_COM_BG_TRIM, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_COM_SVS_MODE_CLK_SEL, 0x01), + QMP_PHY_INIT_CFG(QSERDES_COM_HSCLK_SEL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_DEC_START_MODE0, 0x82), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START2_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START3_MODE0, 0x03), + QMP_PHY_INIT_CFG(QSERDES_COM_CP_CTRL_MODE0, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_CCTRL_MODE0, 0x28), + QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN0_MODE0, 0x80), + QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN1_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_CORECLK_DIV, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP1_MODE0, 0x15), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP2_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP3_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_EN, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_CORE_CLK_EN, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_CFG, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_MAP, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_BG_TIMER, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE1, 0xde), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE2, 0x07), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_IVCO, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_COM_CMN_CONFIG, 0x06), + QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_INITVAL, 0x80), + QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CTRL_BY_PSM, 0x01), +}; + +static const struct qmp_phy_init_tbl qcm2290_usb3_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V3_TX_HIGHZ_DRVR_EN, 0x10), + QMP_PHY_INIT_CFG(QSERDES_V3_TX_RCV_DETECT_LVL_2, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V3_TX_LANE_MODE_1, 0xc6), + QMP_PHY_INIT_CFG(QSERDES_V3_TX_RES_CODE_LANE_OFFSET_TX, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_TX_RES_CODE_LANE_OFFSET_RX, 0x00), +}; + +static const struct qmp_phy_init_tbl qcm2290_usb3_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_PI_CONTROLS, 0x80), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_LOW, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FO_GAIN, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_GAIN, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x75), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4e), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL4, 0x18), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x77), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_OFFSET_ADAPTOR_CNTRL2, 0x80), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_VGA_CAL_CNTRL2, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_CNTRL, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_DEGLITCH_CNTRL, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_ENABLES, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_MODE_00, 0x00), +}; + +static const struct qmp_phy_init_tbl qcm2290_usb3_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXMGN_V0, 0x9f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M6DB_V0, 0x17), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TXDEEMPH_M3P5DB_V0, 0x0f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL2, 0x83), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNTRL1, 0x02), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_L, 0x09), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_CNT_VAL_H_TOL, 0xa2), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_FLL_MAN_CODE, 0x85), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG1, 0xd1), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG2, 0x1f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_LOCK_DETECT_CONFIG3, 0x47), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_WAIT_TIME, 0x75), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_LFPS_TX_ECSTART_EQTLOCK, 0x86), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x04), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_TSYNC_RSYNC_TIME, 0x44), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_L, 0xe7), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_L, 0x40), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RCVR_DTCT_DLY_U3_H, 0x00), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_RX_SIGDET_LVL, 0x88), +}; + +struct qmp_usbc_offsets { + u16 serdes; + u16 pcs; + u16 pcs_misc; + u16 tx; + u16 rx; + /* for PHYs with >= 2 lanes */ + u16 tx2; + u16 rx2; +}; + +/* struct qmp_phy_cfg - per-PHY initialization config */ +struct qmp_phy_cfg { + const struct qmp_usbc_offsets *offsets; + + /* Init sequence for PHY blocks - serdes, tx, rx, pcs */ + const struct qmp_phy_init_tbl *serdes_tbl; + int serdes_tbl_num; + const struct qmp_phy_init_tbl *tx_tbl; + int tx_tbl_num; + const struct qmp_phy_init_tbl *rx_tbl; + int rx_tbl_num; + const struct qmp_phy_init_tbl *pcs_tbl; + int pcs_tbl_num; + + /* regulators to be requested */ + const char * const *vreg_list; + int num_vregs; + + /* array of registers with different offsets */ + const unsigned int *regs; + + /* true, if PHY needs delay after POWER_DOWN */ + bool has_pwrdn_delay; +}; + +struct qmp_usbc { + struct device *dev; + + const struct qmp_phy_cfg *cfg; + + void __iomem *serdes; + void __iomem *pcs; + void __iomem *pcs_misc; + void __iomem *tx; + void __iomem *rx; + void __iomem *tx2; + void __iomem *rx2; + + struct regmap *tcsr_map; + u32 vls_clamp_reg; + + struct clk *pipe_clk; + struct clk_bulk_data *clks; + int num_clks; + int num_resets; + struct reset_control_bulk_data *resets; + struct regulator_bulk_data *vregs; + + struct mutex phy_mutex; + + enum phy_mode mode; + unsigned int usb_init_count; + + struct phy *phy; + + struct clk_fixed_rate pipe_clk_fixed; + + struct typec_switch_dev *sw; + enum typec_orientation orientation; +}; + +static inline void qphy_setbits(void __iomem *base, u32 offset, u32 val) +{ + u32 reg; + + reg = readl(base + offset); + reg |= val; + writel(reg, base + offset); + + /* ensure that above write is through */ + readl(base + offset); +} + +static inline void qphy_clrbits(void __iomem *base, u32 offset, u32 val) +{ + u32 reg; + + reg = readl(base + offset); + reg &= ~val; + writel(reg, base + offset); + + /* ensure that above write is through */ + readl(base + offset); +} + +/* list of clocks required by phy */ +static const char * const qmp_usbc_phy_clk_l[] = { + "aux", "cfg_ahb", "ref", "com_aux", +}; + +/* list of resets */ +static const char * const usb3phy_legacy_reset_l[] = { + "phy", "common", +}; + +static const char * const usb3phy_reset_l[] = { + "phy_phy", "phy", +}; + +/* list of regulators */ +static const char * const qmp_phy_vreg_l[] = { + "vdda-phy", "vdda-pll", +}; + +static const struct qmp_usbc_offsets qmp_usbc_offsets_v3_qcm2290 = { + .serdes = 0x0, + .pcs = 0xc00, + .pcs_misc = 0xa00, + .tx = 0x200, + .rx = 0x400, + .tx2 = 0x600, + .rx2 = 0x800, +}; + +static const struct qmp_phy_cfg msm8998_usb3phy_cfg = { + .offsets = &qmp_usbc_offsets_v3_qcm2290, + + .serdes_tbl = msm8998_usb3_serdes_tbl, + .serdes_tbl_num = ARRAY_SIZE(msm8998_usb3_serdes_tbl), + .tx_tbl = msm8998_usb3_tx_tbl, + .tx_tbl_num = ARRAY_SIZE(msm8998_usb3_tx_tbl), + .rx_tbl = msm8998_usb3_rx_tbl, + .rx_tbl_num = ARRAY_SIZE(msm8998_usb3_rx_tbl), + .pcs_tbl = msm8998_usb3_pcs_tbl, + .pcs_tbl_num = ARRAY_SIZE(msm8998_usb3_pcs_tbl), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = qmp_v3_usb3phy_regs_layout, +}; + +static const struct qmp_phy_cfg qcm2290_usb3phy_cfg = { + .offsets = &qmp_usbc_offsets_v3_qcm2290, + + .serdes_tbl = qcm2290_usb3_serdes_tbl, + .serdes_tbl_num = ARRAY_SIZE(qcm2290_usb3_serdes_tbl), + .tx_tbl = qcm2290_usb3_tx_tbl, + .tx_tbl_num = ARRAY_SIZE(qcm2290_usb3_tx_tbl), + .rx_tbl = qcm2290_usb3_rx_tbl, + .rx_tbl_num = ARRAY_SIZE(qcm2290_usb3_rx_tbl), + .pcs_tbl = qcm2290_usb3_pcs_tbl, + .pcs_tbl_num = ARRAY_SIZE(qcm2290_usb3_pcs_tbl), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = qmp_v3_usb3phy_regs_layout_qcm2290, +}; + +static void qmp_usbc_configure_lane(void __iomem *base, + const struct qmp_phy_init_tbl tbl[], + int num, + u8 lane_mask) +{ + int i; + const struct qmp_phy_init_tbl *t = tbl; + + if (!t) + return; + + for (i = 0; i < num; i++, t++) { + if (!(t->lane_mask & lane_mask)) + continue; + + writel(t->val, base + t->offset); + } +} + +static void qmp_usbc_configure(void __iomem *base, + const struct qmp_phy_init_tbl tbl[], + int num) +{ + qmp_usbc_configure_lane(base, tbl, num, 0xff); +} + +static int qmp_usbc_init(struct phy *phy) +{ + struct qmp_usbc *qmp = phy_get_drvdata(phy); + const struct qmp_phy_cfg *cfg = qmp->cfg; + void __iomem *pcs = qmp->pcs; + u32 val = 0; + int ret; + + ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); + if (ret) { + dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); + return ret; + } + + ret = reset_control_bulk_assert(qmp->num_resets, qmp->resets); + if (ret) { + dev_err(qmp->dev, "reset assert failed\n"); + goto err_disable_regulators; + } + + ret = reset_control_bulk_deassert(qmp->num_resets, qmp->resets); + if (ret) { + dev_err(qmp->dev, "reset deassert failed\n"); + goto err_disable_regulators; + } + + ret = clk_bulk_prepare_enable(qmp->num_clks, qmp->clks); + if (ret) + goto err_assert_reset; + + qphy_setbits(pcs, cfg->regs[QPHY_PCS_POWER_DOWN_CONTROL], SW_PWRDN); + +#define SW_PORTSELECT_VAL BIT(0) +#define SW_PORTSELECT_MUX BIT(1) + /* Use software based port select and switch on typec orientation */ + val = SW_PORTSELECT_MUX; + if (qmp->orientation == TYPEC_ORIENTATION_REVERSE) + val |= SW_PORTSELECT_VAL; + writel(val, qmp->pcs_misc); + + return 0; + +err_assert_reset: + reset_control_bulk_assert(qmp->num_resets, qmp->resets); +err_disable_regulators: + regulator_bulk_disable(cfg->num_vregs, qmp->vregs); + + return ret; +} + +static int qmp_usbc_exit(struct phy *phy) +{ + struct qmp_usbc *qmp = phy_get_drvdata(phy); + const struct qmp_phy_cfg *cfg = qmp->cfg; + + reset_control_bulk_assert(qmp->num_resets, qmp->resets); + + clk_bulk_disable_unprepare(qmp->num_clks, qmp->clks); + + regulator_bulk_disable(cfg->num_vregs, qmp->vregs); + + return 0; +} + +static int qmp_usbc_power_on(struct phy *phy) +{ + struct qmp_usbc *qmp = phy_get_drvdata(phy); + const struct qmp_phy_cfg *cfg = qmp->cfg; + void __iomem *status; + unsigned int val; + int ret; + + qmp_usbc_configure(qmp->serdes, cfg->serdes_tbl, cfg->serdes_tbl_num); + + ret = clk_prepare_enable(qmp->pipe_clk); + if (ret) { + dev_err(qmp->dev, "pipe_clk enable failed err=%d\n", ret); + return ret; + } + + /* Tx, Rx, and PCS configurations */ + qmp_usbc_configure_lane(qmp->tx, cfg->tx_tbl, cfg->tx_tbl_num, 1); + qmp_usbc_configure_lane(qmp->rx, cfg->rx_tbl, cfg->rx_tbl_num, 1); + + qmp_usbc_configure_lane(qmp->tx2, cfg->tx_tbl, cfg->tx_tbl_num, 2); + qmp_usbc_configure_lane(qmp->rx2, cfg->rx_tbl, cfg->rx_tbl_num, 2); + + qmp_usbc_configure(qmp->pcs, cfg->pcs_tbl, cfg->pcs_tbl_num); + + if (cfg->has_pwrdn_delay) + usleep_range(10, 20); + + /* Pull PHY out of reset state */ + qphy_clrbits(qmp->pcs, cfg->regs[QPHY_SW_RESET], SW_RESET); + + /* start SerDes and Phy-Coding-Sublayer */ + qphy_setbits(qmp->pcs, cfg->regs[QPHY_START_CTRL], SERDES_START | PCS_START); + + status = qmp->pcs + cfg->regs[QPHY_PCS_STATUS]; + ret = readl_poll_timeout(status, val, !(val & PHYSTATUS), 200, + PHY_INIT_COMPLETE_TIMEOUT); + if (ret) { + dev_err(qmp->dev, "phy initialization timed-out\n"); + goto err_disable_pipe_clk; + } + + return 0; + +err_disable_pipe_clk: + clk_disable_unprepare(qmp->pipe_clk); + + return ret; +} + +static int qmp_usbc_power_off(struct phy *phy) +{ + struct qmp_usbc *qmp = phy_get_drvdata(phy); + const struct qmp_phy_cfg *cfg = qmp->cfg; + + clk_disable_unprepare(qmp->pipe_clk); + + /* PHY reset */ + qphy_setbits(qmp->pcs, cfg->regs[QPHY_SW_RESET], SW_RESET); + + /* stop SerDes and Phy-Coding-Sublayer */ + qphy_clrbits(qmp->pcs, cfg->regs[QPHY_START_CTRL], + SERDES_START | PCS_START); + + /* Put PHY into POWER DOWN state: active low */ + qphy_clrbits(qmp->pcs, cfg->regs[QPHY_PCS_POWER_DOWN_CONTROL], + SW_PWRDN); + + return 0; +} + +static int qmp_usbc_enable(struct phy *phy) +{ + struct qmp_usbc *qmp = phy_get_drvdata(phy); + int ret; + + mutex_lock(&qmp->phy_mutex); + + ret = qmp_usbc_init(phy); + if (ret) + goto out_unlock; + + ret = qmp_usbc_power_on(phy); + if (ret) { + qmp_usbc_exit(phy); + goto out_unlock; + } + + qmp->usb_init_count++; +out_unlock: + mutex_unlock(&qmp->phy_mutex); + + return ret; +} + +static int qmp_usbc_disable(struct phy *phy) +{ + struct qmp_usbc *qmp = phy_get_drvdata(phy); + int ret; + + qmp->usb_init_count--; + ret = qmp_usbc_power_off(phy); + if (ret) + return ret; + return qmp_usbc_exit(phy); +} + +static int qmp_usbc_set_mode(struct phy *phy, enum phy_mode mode, int submode) +{ + struct qmp_usbc *qmp = phy_get_drvdata(phy); + + qmp->mode = mode; + + return 0; +} + +static const struct phy_ops qmp_usbc_phy_ops = { + .init = qmp_usbc_enable, + .exit = qmp_usbc_disable, + .set_mode = qmp_usbc_set_mode, + .owner = THIS_MODULE, +}; + +static void qmp_usbc_enable_autonomous_mode(struct qmp_usbc *qmp) +{ + const struct qmp_phy_cfg *cfg = qmp->cfg; + void __iomem *pcs = qmp->pcs; + u32 intr_mask; + + if (qmp->mode == PHY_MODE_USB_HOST_SS || + qmp->mode == PHY_MODE_USB_DEVICE_SS) + intr_mask = ARCVR_DTCT_EN | ALFPS_DTCT_EN; + else + intr_mask = ARCVR_DTCT_EN | ARCVR_DTCT_EVENT_SEL; + + /* Clear any pending interrupts status */ + qphy_setbits(pcs, cfg->regs[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR], IRQ_CLEAR); + /* Writing 1 followed by 0 clears the interrupt */ + qphy_clrbits(pcs, cfg->regs[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR], IRQ_CLEAR); + + qphy_clrbits(pcs, cfg->regs[QPHY_PCS_AUTONOMOUS_MODE_CTRL], + ARCVR_DTCT_EN | ALFPS_DTCT_EN | ARCVR_DTCT_EVENT_SEL); + + /* Enable required PHY autonomous mode interrupts */ + qphy_setbits(pcs, cfg->regs[QPHY_PCS_AUTONOMOUS_MODE_CTRL], intr_mask); + + /* Enable i/o clamp_n for autonomous mode */ + if (qmp->tcsr_map && qmp->vls_clamp_reg) + regmap_write(qmp->tcsr_map, qmp->vls_clamp_reg, 1); +} + +static void qmp_usbc_disable_autonomous_mode(struct qmp_usbc *qmp) +{ + const struct qmp_phy_cfg *cfg = qmp->cfg; + void __iomem *pcs = qmp->pcs; + + /* Disable i/o clamp_n on resume for normal mode */ + if (qmp->tcsr_map && qmp->vls_clamp_reg) + regmap_write(qmp->tcsr_map, qmp->vls_clamp_reg, 0); + + qphy_clrbits(pcs, cfg->regs[QPHY_PCS_AUTONOMOUS_MODE_CTRL], + ARCVR_DTCT_EN | ARCVR_DTCT_EVENT_SEL | ALFPS_DTCT_EN); + + qphy_setbits(pcs, cfg->regs[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR], IRQ_CLEAR); + /* Writing 1 followed by 0 clears the interrupt */ + qphy_clrbits(pcs, cfg->regs[QPHY_PCS_LFPS_RXTERM_IRQ_CLEAR], IRQ_CLEAR); +} + +static int __maybe_unused qmp_usbc_runtime_suspend(struct device *dev) +{ + struct qmp_usbc *qmp = dev_get_drvdata(dev); + + dev_vdbg(dev, "Suspending QMP phy, mode:%d\n", qmp->mode); + + if (!qmp->phy->init_count) { + dev_vdbg(dev, "PHY not initialized, bailing out\n"); + return 0; + } + + qmp_usbc_enable_autonomous_mode(qmp); + + clk_disable_unprepare(qmp->pipe_clk); + clk_bulk_disable_unprepare(qmp->num_clks, qmp->clks); + + return 0; +} + +static int __maybe_unused qmp_usbc_runtime_resume(struct device *dev) +{ + struct qmp_usbc *qmp = dev_get_drvdata(dev); + int ret = 0; + + dev_vdbg(dev, "Resuming QMP phy, mode:%d\n", qmp->mode); + + if (!qmp->phy->init_count) { + dev_vdbg(dev, "PHY not initialized, bailing out\n"); + return 0; + } + + ret = clk_bulk_prepare_enable(qmp->num_clks, qmp->clks); + if (ret) + return ret; + + ret = clk_prepare_enable(qmp->pipe_clk); + if (ret) { + dev_err(dev, "pipe_clk enable failed, err=%d\n", ret); + clk_bulk_disable_unprepare(qmp->num_clks, qmp->clks); + return ret; + } + + qmp_usbc_disable_autonomous_mode(qmp); + + return 0; +} + +static const struct dev_pm_ops qmp_usbc_pm_ops = { + SET_RUNTIME_PM_OPS(qmp_usbc_runtime_suspend, + qmp_usbc_runtime_resume, NULL) +}; + +static int qmp_usbc_vreg_init(struct qmp_usbc *qmp) +{ + const struct qmp_phy_cfg *cfg = qmp->cfg; + struct device *dev = qmp->dev; + int num = cfg->num_vregs; + int i; + + qmp->vregs = devm_kcalloc(dev, num, sizeof(*qmp->vregs), GFP_KERNEL); + if (!qmp->vregs) + return -ENOMEM; + + for (i = 0; i < num; i++) + qmp->vregs[i].supply = cfg->vreg_list[i]; + + return devm_regulator_bulk_get(dev, num, qmp->vregs); +} + +static int qmp_usbc_reset_init(struct qmp_usbc *qmp, + const char *const *reset_list, + int num_resets) +{ + struct device *dev = qmp->dev; + int i; + int ret; + + qmp->resets = devm_kcalloc(dev, num_resets, + sizeof(*qmp->resets), GFP_KERNEL); + if (!qmp->resets) + return -ENOMEM; + + for (i = 0; i < num_resets; i++) + qmp->resets[i].id = reset_list[i]; + + qmp->num_resets = num_resets; + + ret = devm_reset_control_bulk_get_exclusive(dev, num_resets, qmp->resets); + if (ret) + return dev_err_probe(dev, ret, "failed to get resets\n"); + + return 0; +} + +static int qmp_usbc_clk_init(struct qmp_usbc *qmp) +{ + struct device *dev = qmp->dev; + int num = ARRAY_SIZE(qmp_usbc_phy_clk_l); + int i; + + qmp->clks = devm_kcalloc(dev, num, sizeof(*qmp->clks), GFP_KERNEL); + if (!qmp->clks) + return -ENOMEM; + + for (i = 0; i < num; i++) + qmp->clks[i].id = qmp_usbc_phy_clk_l[i]; + + qmp->num_clks = num; + + return devm_clk_bulk_get_optional(dev, num, qmp->clks); +} + +static void phy_clk_release_provider(void *res) +{ + of_clk_del_provider(res); +} + +/* + * Register a fixed rate pipe clock. + * + * The _pipe_clksrc generated by PHY goes to the GCC that gate + * controls it. The _pipe_clk coming out of the GCC is requested + * by the PHY driver for its operations. + * We register the _pipe_clksrc here. The gcc driver takes care + * of assigning this _pipe_clksrc as parent to _pipe_clk. + * Below picture shows this relationship. + * + * +---------------+ + * | PHY block |<<---------------------------------------+ + * | | | + * | +-------+ | +-----+ | + * I/P---^-->| PLL |---^--->pipe_clksrc--->| GCC |--->pipe_clk---+ + * clk | +-------+ | +-----+ + * +---------------+ + */ +static int phy_pipe_clk_register(struct qmp_usbc *qmp, struct device_node *np) +{ + struct clk_fixed_rate *fixed = &qmp->pipe_clk_fixed; + struct clk_init_data init = { }; + int ret; + + ret = of_property_read_string(np, "clock-output-names", &init.name); + if (ret) { + dev_err(qmp->dev, "%pOFn: No clock-output-names\n", np); + return ret; + } + + init.ops = &clk_fixed_rate_ops; + + /* controllers using QMP phys use 125MHz pipe clock interface */ + fixed->fixed_rate = 125000000; + fixed->hw.init = &init; + + ret = devm_clk_hw_register(qmp->dev, &fixed->hw); + if (ret) + return ret; + + ret = of_clk_add_hw_provider(np, of_clk_hw_simple_get, &fixed->hw); + if (ret) + return ret; + + /* + * Roll a devm action because the clock provider is the child node, but + * the child node is not actually a device. + */ + return devm_add_action_or_reset(qmp->dev, phy_clk_release_provider, np); +} + +#if IS_ENABLED(CONFIG_TYPEC) +static int qmp_usbc_typec_switch_set(struct typec_switch_dev *sw, + enum typec_orientation orientation) +{ + struct qmp_usbc *qmp = typec_switch_get_drvdata(sw); + + if (orientation == qmp->orientation || orientation == TYPEC_ORIENTATION_NONE) + return 0; + + mutex_lock(&qmp->phy_mutex); + qmp->orientation = orientation; + + if (qmp->usb_init_count) { + qmp_usbc_power_off(qmp->phy); + qmp_usbc_exit(qmp->phy); + + qmp_usbc_init(qmp->phy); + qmp_usbc_power_on(qmp->phy); + } + + mutex_unlock(&qmp->phy_mutex); + + return 0; +} + +static void qmp_usbc_typec_unregister(void *data) +{ + struct qmp_usbc *qmp = data; + + typec_switch_unregister(qmp->sw); +} + +static int qmp_usbc_typec_switch_register(struct qmp_usbc *qmp) +{ + struct typec_switch_desc sw_desc = {}; + struct device *dev = qmp->dev; + + sw_desc.drvdata = qmp; + sw_desc.fwnode = dev->fwnode; + sw_desc.set = qmp_usbc_typec_switch_set; + qmp->sw = typec_switch_register(dev, &sw_desc); + if (IS_ERR(qmp->sw)) { + dev_err(dev, "Unable to register typec switch: %pe\n", qmp->sw); + return PTR_ERR(qmp->sw); + } + + return devm_add_action_or_reset(dev, qmp_usbc_typec_unregister, qmp); +} +#else +static int qmp_usbc_typec_switch_register(struct qmp_usbc *qmp) +{ + return 0; +} +#endif + +static int qmp_usbc_parse_dt_legacy(struct qmp_usbc *qmp, struct device_node *np) +{ + struct platform_device *pdev = to_platform_device(qmp->dev); + struct device *dev = qmp->dev; + int ret; + + qmp->serdes = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(qmp->serdes)) + return PTR_ERR(qmp->serdes); + + /* + * Get memory resources for the PHY: + * Resources are indexed as: tx -> 0; rx -> 1; pcs -> 2. + * For dual lane PHYs: tx2 -> 3, rx2 -> 4, pcs_misc (optional) -> 5 + * For single lane PHYs: pcs_misc (optional) -> 3. + */ + qmp->tx = devm_of_iomap(dev, np, 0, NULL); + if (IS_ERR(qmp->tx)) + return PTR_ERR(qmp->tx); + + qmp->rx = devm_of_iomap(dev, np, 1, NULL); + if (IS_ERR(qmp->rx)) + return PTR_ERR(qmp->rx); + + qmp->pcs = devm_of_iomap(dev, np, 2, NULL); + if (IS_ERR(qmp->pcs)) + return PTR_ERR(qmp->pcs); + + qmp->tx2 = devm_of_iomap(dev, np, 3, NULL); + if (IS_ERR(qmp->tx2)) + return PTR_ERR(qmp->tx2); + + qmp->rx2 = devm_of_iomap(dev, np, 4, NULL); + if (IS_ERR(qmp->rx2)) + return PTR_ERR(qmp->rx2); + + qmp->pcs_misc = devm_of_iomap(dev, np, 5, NULL); + if (IS_ERR(qmp->pcs_misc)) { + dev_vdbg(dev, "PHY pcs_misc-reg not used\n"); + qmp->pcs_misc = NULL; + } + + qmp->pipe_clk = devm_get_clk_from_child(dev, np, NULL); + if (IS_ERR(qmp->pipe_clk)) { + return dev_err_probe(dev, PTR_ERR(qmp->pipe_clk), + "failed to get pipe clock\n"); + } + + ret = devm_clk_bulk_get_all(qmp->dev, &qmp->clks); + if (ret < 0) + return ret; + + qmp->num_clks = ret; + + ret = qmp_usbc_reset_init(qmp, usb3phy_legacy_reset_l, + ARRAY_SIZE(usb3phy_legacy_reset_l)); + if (ret) + return ret; + + return 0; +} + +static int qmp_usbc_parse_dt(struct qmp_usbc *qmp) +{ + struct platform_device *pdev = to_platform_device(qmp->dev); + const struct qmp_phy_cfg *cfg = qmp->cfg; + const struct qmp_usbc_offsets *offs = cfg->offsets; + struct device *dev = qmp->dev; + void __iomem *base; + int ret; + + if (!offs) + return -EINVAL; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + qmp->serdes = base + offs->serdes; + qmp->pcs = base + offs->pcs; + if (offs->pcs_misc) + qmp->pcs_misc = base + offs->pcs_misc; + qmp->tx = base + offs->tx; + qmp->rx = base + offs->rx; + + qmp->tx2 = base + offs->tx2; + qmp->rx2 = base + offs->rx2; + + ret = qmp_usbc_clk_init(qmp); + if (ret) + return ret; + + qmp->pipe_clk = devm_clk_get(dev, "pipe"); + if (IS_ERR(qmp->pipe_clk)) { + return dev_err_probe(dev, PTR_ERR(qmp->pipe_clk), + "failed to get pipe clock\n"); + } + + ret = qmp_usbc_reset_init(qmp, usb3phy_reset_l, + ARRAY_SIZE(usb3phy_reset_l)); + if (ret) + return ret; + + return 0; +} + +static int qmp_usbc_parse_vls_clamp(struct qmp_usbc *qmp) +{ + struct of_phandle_args tcsr_args; + struct device *dev = qmp->dev; + int ret; + + /* for backwards compatibility ignore if there is no property */ + ret = of_parse_phandle_with_fixed_args(dev->of_node, "qcom,tcsr-reg", 1, 0, + &tcsr_args); + if (ret == -ENOENT) + return 0; + else if (ret < 0) + return dev_err_probe(dev, ret, "Failed to parse qcom,tcsr-reg\n"); + + qmp->tcsr_map = syscon_node_to_regmap(tcsr_args.np); + of_node_put(tcsr_args.np); + if (IS_ERR(qmp->tcsr_map)) + return PTR_ERR(qmp->tcsr_map); + + qmp->vls_clamp_reg = tcsr_args.args[0]; + + return 0; +} + +static int qmp_usbc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct phy_provider *phy_provider; + struct device_node *np; + struct qmp_usbc *qmp; + int ret; + + qmp = devm_kzalloc(dev, sizeof(*qmp), GFP_KERNEL); + if (!qmp) + return -ENOMEM; + + qmp->dev = dev; + + qmp->orientation = TYPEC_ORIENTATION_NORMAL; + + qmp->cfg = of_device_get_match_data(dev); + if (!qmp->cfg) + return -EINVAL; + + mutex_init(&qmp->phy_mutex); + + ret = qmp_usbc_vreg_init(qmp); + if (ret) + return ret; + + ret = qmp_usbc_typec_switch_register(qmp); + if (ret) + return ret; + + ret = qmp_usbc_parse_vls_clamp(qmp); + if (ret) + return ret; + + /* Check for legacy binding with child node. */ + np = of_get_child_by_name(dev->of_node, "phy"); + if (np) { + ret = qmp_usbc_parse_dt_legacy(qmp, np); + } else { + np = of_node_get(dev->of_node); + ret = qmp_usbc_parse_dt(qmp); + } + if (ret) + goto err_node_put; + + pm_runtime_set_active(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + goto err_node_put; + /* + * Prevent runtime pm from being ON by default. Users can enable + * it using power/control in sysfs. + */ + pm_runtime_forbid(dev); + + ret = phy_pipe_clk_register(qmp, np); + if (ret) + goto err_node_put; + + qmp->phy = devm_phy_create(dev, np, &qmp_usbc_phy_ops); + if (IS_ERR(qmp->phy)) { + ret = PTR_ERR(qmp->phy); + dev_err(dev, "failed to create PHY: %d\n", ret); + goto err_node_put; + } + + phy_set_drvdata(qmp->phy, qmp); + + of_node_put(np); + + phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); + + return PTR_ERR_OR_ZERO(phy_provider); + +err_node_put: + of_node_put(np); + return ret; +} + +static const struct of_device_id qmp_usbc_of_match_table[] = { + { + .compatible = "qcom,msm8998-qmp-usb3-phy", + .data = &msm8998_usb3phy_cfg, + }, { + .compatible = "qcom,qcm2290-qmp-usb3-phy", + .data = &qcm2290_usb3phy_cfg, + }, { + .compatible = "qcom,sm6115-qmp-usb3-phy", + .data = &qcm2290_usb3phy_cfg, + }, + { }, +}; +MODULE_DEVICE_TABLE(of, qmp_usbc_of_match_table); + +static struct platform_driver qmp_usbc_driver = { + .probe = qmp_usbc_probe, + .driver = { + .name = "qcom-qmp-usbc-phy", + .pm = &qmp_usbc_pm_ops, + .of_match_table = qmp_usbc_of_match_table, + }, +}; + +module_platform_driver(qmp_usbc_driver); + +MODULE_AUTHOR("Vivek Gautam "); +MODULE_DESCRIPTION("Qualcomm QMP USB-C PHY driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h index 6923496cbfee2..984d122e1ba70 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp.h @@ -46,6 +46,8 @@ #include "phy-qcom-qmp-pcs-v6.h" +#include "phy-qcom-qmp-pcs-v6-n4.h" + #include "phy-qcom-qmp-pcs-v6_20.h" #include "phy-qcom-qmp-pcs-v7.h" @@ -132,9 +134,11 @@ #define QSERDES_V4_DP_PHY_AUX_INTERRUPT_STATUS 0x0d8 #define QSERDES_V4_DP_PHY_STATUS 0x0dc +#define QSERDES_V5_DP_PHY_VCO_DIV 0x070 #define QSERDES_V5_DP_PHY_STATUS 0x0dc /* Only for QMP V6 PHY - DP PHY registers */ +#define QSERDES_V6_DP_PHY_VCO_DIV 0x070 #define QSERDES_V6_DP_PHY_AUX_INTERRUPT_STATUS 0x0e0 #define QSERDES_V6_DP_PHY_STATUS 0x0e4 diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c index 5de5e2e97ffa0..26b157f53f3da 100644 --- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c +++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c @@ -125,12 +125,15 @@ struct rockchip_combphy_grfcfg { }; struct rockchip_combphy_cfg { + unsigned int num_phys; + unsigned int phy_ids[3]; const struct rockchip_combphy_grfcfg *grfcfg; int (*combphy_cfg)(struct rockchip_combphy_priv *priv); }; struct rockchip_combphy_priv { u8 type; + int id; void __iomem *mmio; int num_clks; struct clk_bulk_data *clks; @@ -320,7 +323,7 @@ static int rockchip_combphy_probe(struct platform_device *pdev) struct rockchip_combphy_priv *priv; const struct rockchip_combphy_cfg *phy_cfg; struct resource *res; - int ret; + int ret, id; phy_cfg = of_device_get_match_data(dev); if (!phy_cfg) { @@ -338,6 +341,15 @@ static int rockchip_combphy_probe(struct platform_device *pdev) return ret; } + /* find the phy-id from the io address */ + priv->id = -ENODEV; + for (id = 0; id < phy_cfg->num_phys; id++) { + if (res->start == phy_cfg->phy_ids[id]) { + priv->id = id; + break; + } + } + priv->dev = dev; priv->type = PHY_NONE; priv->cfg = phy_cfg; @@ -562,6 +574,12 @@ static const struct rockchip_combphy_grfcfg rk3568_combphy_grfcfgs = { }; static const struct rockchip_combphy_cfg rk3568_combphy_cfgs = { + .num_phys = 3, + .phy_ids = { + 0xfe820000, + 0xfe830000, + 0xfe840000, + }, .grfcfg = &rk3568_combphy_grfcfgs, .combphy_cfg = rk3568_combphy_cfg, }; @@ -578,8 +596,14 @@ static int rk3588_combphy_cfg(struct rockchip_combphy_priv *priv) rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_pcie, true); rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_pcie, true); rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_pcie, true); - rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l0_sel, true); - rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l1_sel, true); + switch (priv->id) { + case 1: + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l0_sel, true); + break; + case 2: + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l1_sel, true); + break; + } break; case PHY_TYPE_USB3: /* Set SSC downward spread spectrum */ @@ -736,6 +760,12 @@ static const struct rockchip_combphy_grfcfg rk3588_combphy_grfcfgs = { }; static const struct rockchip_combphy_cfg rk3588_combphy_cfgs = { + .num_phys = 3, + .phy_ids = { + 0xfee00000, + 0xfee10000, + 0xfee20000, + }, .grfcfg = &rk3588_combphy_grfcfgs, .combphy_cfg = rk3588_combphy_cfg, }; diff --git a/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c b/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c index 121e5961ce114..9857ee45b89e0 100644 --- a/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c +++ b/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c @@ -40,6 +40,8 @@ #define RK3588_BIFURCATION_LANE_0_1 BIT(0) #define RK3588_BIFURCATION_LANE_2_3 BIT(1) #define RK3588_LANE_AGGREGATION BIT(2) +#define RK3588_PCIE1LN_SEL_EN (GENMASK(1, 0) << 16) +#define RK3588_PCIE30_PHY_MODE_EN (GENMASK(2, 0) << 16) struct rockchip_p3phy_ops; @@ -132,7 +134,7 @@ static const struct rockchip_p3phy_ops rk3568_ops = { static int rockchip_p3phy_rk3588_init(struct rockchip_p3phy_priv *priv) { u32 reg = 0; - u8 mode = 0; + u8 mode = RK3588_LANE_AGGREGATION; /* default */ int ret; /* Deassert PCIe PMA output clamp mode */ @@ -140,31 +142,24 @@ static int rockchip_p3phy_rk3588_init(struct rockchip_p3phy_priv *priv) /* Set bifurcation if needed */ for (int i = 0; i < priv->num_lanes; i++) { - if (!priv->lanes[i]) - mode |= (BIT(i) << 3); - if (priv->lanes[i] > 1) - mode |= (BIT(i) >> 1); - } - - if (!mode) - reg = RK3588_LANE_AGGREGATION; - else { - if (mode & (BIT(0) | BIT(1))) - reg |= RK3588_BIFURCATION_LANE_0_1; - - if (mode & (BIT(2) | BIT(3))) - reg |= RK3588_BIFURCATION_LANE_2_3; + mode &= ~RK3588_LANE_AGGREGATION; + if (priv->lanes[i] == 3) + mode |= RK3588_BIFURCATION_LANE_0_1; + if (priv->lanes[i] == 4) + mode |= RK3588_BIFURCATION_LANE_2_3; } - regmap_write(priv->phy_grf, RK3588_PCIE3PHY_GRF_CMN_CON0, (0x7<<16) | reg); + reg = mode; + regmap_write(priv->phy_grf, RK3588_PCIE3PHY_GRF_CMN_CON0, + RK3588_PCIE30_PHY_MODE_EN | reg); /* Set pcie1ln_sel in PHP_GRF_PCIESEL_CON */ if (!IS_ERR(priv->pipe_grf)) { - reg = (mode & (BIT(6) | BIT(7))) >> 6; + reg = mode & (RK3588_BIFURCATION_LANE_0_1 | RK3588_BIFURCATION_LANE_2_3); if (reg) regmap_write(priv->pipe_grf, PHP_GRF_PCIESEL_CON, - (reg << 16) | reg); + RK3588_PCIE1LN_SEL_EN | reg); } reset_control_deassert(priv->p30phy); diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 142ebe0247cc0..983a6e6173bd2 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1531,6 +1531,19 @@ int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, } EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_usb3_companion); +int tegra_xusb_padctl_get_port_number(struct phy *phy) +{ + struct tegra_xusb_lane *lane; + + if (!phy) + return -ENODEV; + + lane = phy_get_drvdata(phy); + + return lane->index; +} +EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_port_number); + MODULE_AUTHOR("Thierry Reding "); MODULE_DESCRIPTION("Tegra XUSB Pad Controller driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c index b4881cb344759..c23eecc7d1800 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -65,7 +65,6 @@ struct tusb1210 { struct delayed_work chg_det_work; struct notifier_block psy_nb; struct power_supply *psy; - struct power_supply *charger; #endif }; @@ -231,19 +230,24 @@ static const char * const tusb1210_chargers[] = { static bool tusb1210_get_online(struct tusb1210 *tusb) { + struct power_supply *charger = NULL; union power_supply_propval val; - int i; + bool online = false; + int i, ret; - for (i = 0; i < ARRAY_SIZE(tusb1210_chargers) && !tusb->charger; i++) - tusb->charger = power_supply_get_by_name(tusb1210_chargers[i]); + for (i = 0; i < ARRAY_SIZE(tusb1210_chargers) && !charger; i++) + charger = power_supply_get_by_name(tusb1210_chargers[i]); - if (!tusb->charger) + if (!charger) return false; - if (power_supply_get_property(tusb->charger, POWER_SUPPLY_PROP_ONLINE, &val)) - return false; + ret = power_supply_get_property(charger, POWER_SUPPLY_PROP_ONLINE, &val); + if (ret == 0) + online = val.intval; + + power_supply_put(charger); - return val.intval; + return online; } static void tusb1210_chg_det_work(struct work_struct *work) @@ -467,9 +471,6 @@ static void tusb1210_remove_charger_detect(struct tusb1210 *tusb) cancel_delayed_work_sync(&tusb->chg_det_work); power_supply_unregister(tusb->psy); } - - if (tusb->charger) - power_supply_put(tusb->charger); } #else static void tusb1210_probe_charger_detect(struct tusb1210 *tusb) { } diff --git a/drivers/pinctrl/aspeed/Makefile b/drivers/pinctrl/aspeed/Makefile index 489ea1778353f..db2a7600ae2bd 100644 --- a/drivers/pinctrl/aspeed/Makefile +++ b/drivers/pinctrl/aspeed/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only # Aspeed pinctrl support -ccflags-y += $(call cc-option,-Woverride-init) +ccflags-y += -Woverride-init obj-$(CONFIG_PINCTRL_ASPEED) += pinctrl-aspeed.o pinmux-aspeed.o obj-$(CONFIG_PINCTRL_ASPEED_G4) += pinctrl-aspeed-g4.o obj-$(CONFIG_PINCTRL_ASPEED_G5) += pinctrl-aspeed-g5.o diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c index d376fa7114d1a..029efe16f8cc2 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c @@ -43,7 +43,7 @@ #define SCU614 0x614 /* Disable GPIO Internal Pull-Down #1 */ #define SCU618 0x618 /* Disable GPIO Internal Pull-Down #2 */ #define SCU61C 0x61c /* Disable GPIO Internal Pull-Down #3 */ -#define SCU620 0x620 /* Disable GPIO Internal Pull-Down #4 */ +#define SCU630 0x630 /* Disable GPIO Internal Pull-Down #4 */ #define SCU634 0x634 /* Disable GPIO Internal Pull-Down #5 */ #define SCU638 0x638 /* Disable GPIO Internal Pull-Down #6 */ #define SCU690 0x690 /* Multi-function Pin Control #24 */ @@ -2495,38 +2495,38 @@ static struct aspeed_pin_config aspeed_g6_configs[] = { ASPEED_PULL_DOWN_PINCONF(D14, SCU61C, 0), /* GPIOS7 */ - ASPEED_PULL_DOWN_PINCONF(T24, SCU620, 23), + ASPEED_PULL_DOWN_PINCONF(T24, SCU630, 23), /* GPIOS6 */ - ASPEED_PULL_DOWN_PINCONF(P23, SCU620, 22), + ASPEED_PULL_DOWN_PINCONF(P23, SCU630, 22), /* GPIOS5 */ - ASPEED_PULL_DOWN_PINCONF(P24, SCU620, 21), + ASPEED_PULL_DOWN_PINCONF(P24, SCU630, 21), /* GPIOS4 */ - ASPEED_PULL_DOWN_PINCONF(R26, SCU620, 20), + ASPEED_PULL_DOWN_PINCONF(R26, SCU630, 20), /* GPIOS3*/ - ASPEED_PULL_DOWN_PINCONF(R24, SCU620, 19), + ASPEED_PULL_DOWN_PINCONF(R24, SCU630, 19), /* GPIOS2 */ - ASPEED_PULL_DOWN_PINCONF(T26, SCU620, 18), + ASPEED_PULL_DOWN_PINCONF(T26, SCU630, 18), /* GPIOS1 */ - ASPEED_PULL_DOWN_PINCONF(T25, SCU620, 17), + ASPEED_PULL_DOWN_PINCONF(T25, SCU630, 17), /* GPIOS0 */ - ASPEED_PULL_DOWN_PINCONF(R23, SCU620, 16), + ASPEED_PULL_DOWN_PINCONF(R23, SCU630, 16), /* GPIOR7 */ - ASPEED_PULL_DOWN_PINCONF(U26, SCU620, 15), + ASPEED_PULL_DOWN_PINCONF(U26, SCU630, 15), /* GPIOR6 */ - ASPEED_PULL_DOWN_PINCONF(W26, SCU620, 14), + ASPEED_PULL_DOWN_PINCONF(W26, SCU630, 14), /* GPIOR5 */ - ASPEED_PULL_DOWN_PINCONF(T23, SCU620, 13), + ASPEED_PULL_DOWN_PINCONF(T23, SCU630, 13), /* GPIOR4 */ - ASPEED_PULL_DOWN_PINCONF(U25, SCU620, 12), + ASPEED_PULL_DOWN_PINCONF(U25, SCU630, 12), /* GPIOR3*/ - ASPEED_PULL_DOWN_PINCONF(V26, SCU620, 11), + ASPEED_PULL_DOWN_PINCONF(V26, SCU630, 11), /* GPIOR2 */ - ASPEED_PULL_DOWN_PINCONF(V24, SCU620, 10), + ASPEED_PULL_DOWN_PINCONF(V24, SCU630, 10), /* GPIOR1 */ - ASPEED_PULL_DOWN_PINCONF(U24, SCU620, 9), + ASPEED_PULL_DOWN_PINCONF(U24, SCU630, 9), /* GPIOR0 */ - ASPEED_PULL_DOWN_PINCONF(V25, SCU620, 8), + ASPEED_PULL_DOWN_PINCONF(V25, SCU630, 8), /* GPIOX7 */ ASPEED_PULL_DOWN_PINCONF(AB10, SCU634, 31), diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index bbcdece83bf42..ae975e1365dfd 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2120,13 +2120,7 @@ int pinctrl_enable(struct pinctrl_dev *pctldev) error = pinctrl_claim_hogs(pctldev); if (error) { - dev_err(pctldev->dev, "could not claim hogs: %i\n", - error); - pinctrl_free_pindescs(pctldev, pctldev->desc->pins, - pctldev->desc->npins); - mutex_destroy(&pctldev->mutex); - kfree(pctldev); - + dev_err(pctldev->dev, "could not claim hogs: %i\n", error); return error; } diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index df1efc2e52025..6a94ecd6a8dea 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -220,14 +220,16 @@ int pinctrl_dt_to_map(struct pinctrl *p, struct pinctrl_dev *pctldev) for (state = 0; ; state++) { /* Retrieve the pinctrl-* property */ propname = kasprintf(GFP_KERNEL, "pinctrl-%d", state); - if (!propname) - return -ENOMEM; + if (!propname) { + ret = -ENOMEM; + goto err; + } prop = of_find_property(np, propname, &size); kfree(propname); if (!prop) { if (state == 0) { - of_node_put(np); - return -ENODEV; + ret = -ENODEV; + goto err; } break; } diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index ac97724c59bae..1edb6041fb424 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -278,33 +278,33 @@ static const unsigned int byt_score_plt_clk5_pins[] = { 101 }; static const unsigned int byt_score_smbus_pins[] = { 51, 52, 53 }; static const struct intel_pingroup byt_score_groups[] = { - PIN_GROUP("uart1_grp", byt_score_uart1_pins, 1), - PIN_GROUP("uart2_grp", byt_score_uart2_pins, 1), - PIN_GROUP("pwm0_grp", byt_score_pwm0_pins, 1), - PIN_GROUP("pwm1_grp", byt_score_pwm1_pins, 1), - PIN_GROUP("ssp2_grp", byt_score_ssp2_pins, 1), - PIN_GROUP("sio_spi_grp", byt_score_sio_spi_pins, 1), - PIN_GROUP("i2c5_grp", byt_score_i2c5_pins, 1), - PIN_GROUP("i2c6_grp", byt_score_i2c6_pins, 1), - PIN_GROUP("i2c4_grp", byt_score_i2c4_pins, 1), - PIN_GROUP("i2c3_grp", byt_score_i2c3_pins, 1), - PIN_GROUP("i2c2_grp", byt_score_i2c2_pins, 1), - PIN_GROUP("i2c1_grp", byt_score_i2c1_pins, 1), - PIN_GROUP("i2c0_grp", byt_score_i2c0_pins, 1), - PIN_GROUP("ssp0_grp", byt_score_ssp0_pins, 1), - PIN_GROUP("ssp1_grp", byt_score_ssp1_pins, 1), - PIN_GROUP("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values), - PIN_GROUP("sdio_grp", byt_score_sdio_pins, 1), - PIN_GROUP("emmc_grp", byt_score_emmc_pins, 1), - PIN_GROUP("lpc_grp", byt_score_ilb_lpc_pins, 1), - PIN_GROUP("sata_grp", byt_score_sata_pins, 1), - PIN_GROUP("plt_clk0_grp", byt_score_plt_clk0_pins, 1), - PIN_GROUP("plt_clk1_grp", byt_score_plt_clk1_pins, 1), - PIN_GROUP("plt_clk2_grp", byt_score_plt_clk2_pins, 1), - PIN_GROUP("plt_clk3_grp", byt_score_plt_clk3_pins, 1), - PIN_GROUP("plt_clk4_grp", byt_score_plt_clk4_pins, 1), - PIN_GROUP("plt_clk5_grp", byt_score_plt_clk5_pins, 1), - PIN_GROUP("smbus_grp", byt_score_smbus_pins, 1), + PIN_GROUP_GPIO("uart1_grp", byt_score_uart1_pins, 1), + PIN_GROUP_GPIO("uart2_grp", byt_score_uart2_pins, 1), + PIN_GROUP_GPIO("pwm0_grp", byt_score_pwm0_pins, 1), + PIN_GROUP_GPIO("pwm1_grp", byt_score_pwm1_pins, 1), + PIN_GROUP_GPIO("ssp2_grp", byt_score_ssp2_pins, 1), + PIN_GROUP_GPIO("sio_spi_grp", byt_score_sio_spi_pins, 1), + PIN_GROUP_GPIO("i2c5_grp", byt_score_i2c5_pins, 1), + PIN_GROUP_GPIO("i2c6_grp", byt_score_i2c6_pins, 1), + PIN_GROUP_GPIO("i2c4_grp", byt_score_i2c4_pins, 1), + PIN_GROUP_GPIO("i2c3_grp", byt_score_i2c3_pins, 1), + PIN_GROUP_GPIO("i2c2_grp", byt_score_i2c2_pins, 1), + PIN_GROUP_GPIO("i2c1_grp", byt_score_i2c1_pins, 1), + PIN_GROUP_GPIO("i2c0_grp", byt_score_i2c0_pins, 1), + PIN_GROUP_GPIO("ssp0_grp", byt_score_ssp0_pins, 1), + PIN_GROUP_GPIO("ssp1_grp", byt_score_ssp1_pins, 1), + PIN_GROUP_GPIO("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values), + PIN_GROUP_GPIO("sdio_grp", byt_score_sdio_pins, 1), + PIN_GROUP_GPIO("emmc_grp", byt_score_emmc_pins, 1), + PIN_GROUP_GPIO("lpc_grp", byt_score_ilb_lpc_pins, 1), + PIN_GROUP_GPIO("sata_grp", byt_score_sata_pins, 1), + PIN_GROUP_GPIO("plt_clk0_grp", byt_score_plt_clk0_pins, 1), + PIN_GROUP_GPIO("plt_clk1_grp", byt_score_plt_clk1_pins, 1), + PIN_GROUP_GPIO("plt_clk2_grp", byt_score_plt_clk2_pins, 1), + PIN_GROUP_GPIO("plt_clk3_grp", byt_score_plt_clk3_pins, 1), + PIN_GROUP_GPIO("plt_clk4_grp", byt_score_plt_clk4_pins, 1), + PIN_GROUP_GPIO("plt_clk5_grp", byt_score_plt_clk5_pins, 1), + PIN_GROUP_GPIO("smbus_grp", byt_score_smbus_pins, 1), }; static const char * const byt_score_uart_groups[] = { @@ -332,12 +332,14 @@ static const char * const byt_score_plt_clk_groups[] = { }; static const char * const byt_score_smbus_groups[] = { "smbus_grp" }; static const char * const byt_score_gpio_groups[] = { - "uart1_grp", "uart2_grp", "pwm0_grp", "pwm1_grp", "ssp0_grp", - "ssp1_grp", "ssp2_grp", "sio_spi_grp", "i2c0_grp", "i2c1_grp", - "i2c2_grp", "i2c3_grp", "i2c4_grp", "i2c5_grp", "i2c6_grp", - "sdcard_grp", "sdio_grp", "emmc_grp", "lpc_grp", "sata_grp", - "plt_clk0_grp", "plt_clk1_grp", "plt_clk2_grp", "plt_clk3_grp", - "plt_clk4_grp", "plt_clk5_grp", "smbus_grp", + "uart1_grp_gpio", "uart2_grp_gpio", "pwm0_grp_gpio", + "pwm1_grp_gpio", "ssp0_grp_gpio", "ssp1_grp_gpio", "ssp2_grp_gpio", + "sio_spi_grp_gpio", "i2c0_grp_gpio", "i2c1_grp_gpio", "i2c2_grp_gpio", + "i2c3_grp_gpio", "i2c4_grp_gpio", "i2c5_grp_gpio", "i2c6_grp_gpio", + "sdcard_grp_gpio", "sdio_grp_gpio", "emmc_grp_gpio", "lpc_grp_gpio", + "sata_grp_gpio", "plt_clk0_grp_gpio", "plt_clk1_grp_gpio", + "plt_clk2_grp_gpio", "plt_clk3_grp_gpio", "plt_clk4_grp_gpio", + "plt_clk5_grp_gpio", "smbus_grp_gpio", }; static const struct intel_function byt_score_functions[] = { @@ -456,8 +458,8 @@ static const struct intel_pingroup byt_sus_groups[] = { PIN_GROUP("usb_oc_grp_gpio", byt_sus_usb_over_current_pins, byt_sus_usb_over_current_gpio_mode_values), PIN_GROUP("usb_ulpi_grp_gpio", byt_sus_usb_ulpi_pins, byt_sus_usb_ulpi_gpio_mode_values), PIN_GROUP("pcu_spi_grp_gpio", byt_sus_pcu_spi_pins, byt_sus_pcu_spi_gpio_mode_values), - PIN_GROUP("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1), - PIN_GROUP("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1), + PIN_GROUP_GPIO("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1), + PIN_GROUP_GPIO("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1), }; static const char * const byt_sus_usb_groups[] = { @@ -469,7 +471,7 @@ static const char * const byt_sus_pmu_clk_groups[] = { }; static const char * const byt_sus_gpio_groups[] = { "usb_oc_grp_gpio", "usb_ulpi_grp_gpio", "pcu_spi_grp_gpio", - "pmu_clk1_grp", "pmu_clk2_grp", + "pmu_clk1_grp_gpio", "pmu_clk2_grp_gpio", }; static const struct intel_function byt_sus_functions[] = { diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h index fde65e18cd145..6981e2fab93f3 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.h +++ b/drivers/pinctrl/intel/pinctrl-intel.h @@ -179,6 +179,10 @@ struct intel_community { .modes = __builtin_choose_expr(__builtin_constant_p((m)), NULL, (m)), \ } +#define PIN_GROUP_GPIO(n, p, m) \ + PIN_GROUP(n, p, m), \ + PIN_GROUP(n "_gpio", p, 0) + #define FUNCTION(n, g) \ { \ .func = PINCTRL_PINFUNCTION((n), (g), ARRAY_SIZE(g)), \ diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8186.c b/drivers/pinctrl/mediatek/pinctrl-mt8186.c index 7be591591cce5..dd19e74856a92 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8186.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8186.c @@ -1198,7 +1198,6 @@ static const struct mtk_pin_reg_calc mt8186_reg_cals[PINCTRL_PIN_REG_MAX] = { [PINCTRL_PIN_REG_DIR] = MTK_RANGE(mt8186_pin_dir_range), [PINCTRL_PIN_REG_DI] = MTK_RANGE(mt8186_pin_di_range), [PINCTRL_PIN_REG_DO] = MTK_RANGE(mt8186_pin_do_range), - [PINCTRL_PIN_REG_SR] = MTK_RANGE(mt8186_pin_dir_range), [PINCTRL_PIN_REG_SMT] = MTK_RANGE(mt8186_pin_smt_range), [PINCTRL_PIN_REG_IES] = MTK_RANGE(mt8186_pin_ies_range), [PINCTRL_PIN_REG_PU] = MTK_RANGE(mt8186_pin_pu_range), diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8192.c b/drivers/pinctrl/mediatek/pinctrl-mt8192.c index e3a76381f7f4e..3f8a9dbcb7041 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8192.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8192.c @@ -1379,7 +1379,6 @@ static const struct mtk_pin_reg_calc mt8192_reg_cals[PINCTRL_PIN_REG_MAX] = { [PINCTRL_PIN_REG_DIR] = MTK_RANGE(mt8192_pin_dir_range), [PINCTRL_PIN_REG_DI] = MTK_RANGE(mt8192_pin_di_range), [PINCTRL_PIN_REG_DO] = MTK_RANGE(mt8192_pin_do_range), - [PINCTRL_PIN_REG_SR] = MTK_RANGE(mt8192_pin_dir_range), [PINCTRL_PIN_REG_SMT] = MTK_RANGE(mt8192_pin_smt_range), [PINCTRL_PIN_REG_IES] = MTK_RANGE(mt8192_pin_ies_range), [PINCTRL_PIN_REG_PU] = MTK_RANGE(mt8192_pin_pu_range), diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c index b6bc31abd2b06..b19bc391705ee 100644 --- a/drivers/pinctrl/mediatek/pinctrl-paris.c +++ b/drivers/pinctrl/mediatek/pinctrl-paris.c @@ -165,20 +165,21 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_SR, &ret); break; case PIN_CONFIG_INPUT_ENABLE: - case PIN_CONFIG_OUTPUT_ENABLE: + err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_IES, &ret); + if (!ret) + err = -EINVAL; + break; + case PIN_CONFIG_OUTPUT: err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DIR, &ret); if (err) break; - /* CONFIG Current direction return value - * ------------- ----------------- ---------------------- - * OUTPUT_ENABLE output 1 (= HW value) - * input 0 (= HW value) - * INPUT_ENABLE output 0 (= reverse HW value) - * input 1 (= reverse HW value) - */ - if (param == PIN_CONFIG_INPUT_ENABLE) - ret = !ret; + if (!ret) { + err = -EINVAL; + break; + } + + err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DO, &ret); break; case PIN_CONFIG_INPUT_SCHMITT_ENABLE: err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DIR, &ret); @@ -193,6 +194,8 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, } err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_SMT, &ret); + if (!ret) + err = -EINVAL; break; case PIN_CONFIG_DRIVE_STRENGTH: if (!hw->soc->drive_get) @@ -281,26 +284,9 @@ static int mtk_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, break; err = hw->soc->bias_set_combo(hw, desc, 0, arg); break; - case PIN_CONFIG_OUTPUT_ENABLE: - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_SMT, - MTK_DISABLE); - /* Keep set direction to consider the case that a GPIO pin - * does not have SMT control - */ - if (err != -ENOTSUPP) - break; - - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_DIR, - MTK_OUTPUT); - break; case PIN_CONFIG_INPUT_ENABLE: /* regard all non-zero value as enable */ err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_IES, !!arg); - if (err) - break; - - err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_DIR, - MTK_INPUT); break; case PIN_CONFIG_SLEW_RATE: /* regard all non-zero value as enable */ diff --git a/drivers/pinctrl/meson/pinctrl-meson-a1.c b/drivers/pinctrl/meson/pinctrl-meson-a1.c index 79f5d753d7e1a..50a87d9618a8e 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-a1.c +++ b/drivers/pinctrl/meson/pinctrl-meson-a1.c @@ -250,7 +250,7 @@ static const unsigned int pdm_dclk_x_pins[] = { GPIOX_10 }; static const unsigned int pdm_din2_a_pins[] = { GPIOA_6 }; static const unsigned int pdm_din1_a_pins[] = { GPIOA_7 }; static const unsigned int pdm_din0_a_pins[] = { GPIOA_8 }; -static const unsigned int pdm_dclk_pins[] = { GPIOA_9 }; +static const unsigned int pdm_dclk_a_pins[] = { GPIOA_9 }; /* gen_clk */ static const unsigned int gen_clk_x_pins[] = { GPIOX_7 }; @@ -591,7 +591,7 @@ static struct meson_pmx_group meson_a1_periphs_groups[] = { GROUP(pdm_din2_a, 3), GROUP(pdm_din1_a, 3), GROUP(pdm_din0_a, 3), - GROUP(pdm_dclk, 3), + GROUP(pdm_dclk_a, 3), GROUP(pwm_c_a, 3), GROUP(pwm_b_a, 3), @@ -755,7 +755,7 @@ static const char * const spi_a_groups[] = { static const char * const pdm_groups[] = { "pdm_din0_x", "pdm_din1_x", "pdm_din2_x", "pdm_dclk_x", "pdm_din2_a", - "pdm_din1_a", "pdm_din0_a", "pdm_dclk", + "pdm_din1_a", "pdm_din0_a", "pdm_dclk_a", }; static const char * const gen_clk_groups[] = { diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c index 7911353ac97d5..4f7c4af4f93cb 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c @@ -1579,8 +1579,10 @@ static int nmk_pmx_set(struct pinctrl_dev *pctldev, unsigned function, * Then mask the pins that need to be sleeping now when we're * switching to the ALT C function. */ - for (i = 0; i < g->grp.npins; i++) - slpm[g->grp.pins[i] / NMK_GPIO_PER_CHIP] &= ~BIT(g->grp.pins[i]); + for (i = 0; i < g->grp.npins; i++) { + unsigned int bit = g->grp.pins[i] % NMK_GPIO_PER_CHIP; + slpm[g->grp.pins[i] / NMK_GPIO_PER_CHIP] &= ~BIT(bit); + } nmk_gpio_glitch_slpm_init(slpm); } diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 49f89b70dcecb..7f66ec73199a9 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -1159,7 +1159,7 @@ static int amd_gpio_probe(struct platform_device *pdev) } ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler, - IRQF_SHARED | IRQF_ONESHOT, KBUILD_MODNAME, gpio_dev); + IRQF_SHARED | IRQF_COND_ONESHOT, KBUILD_MODNAME, gpio_dev); if (ret) goto out2; diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index e0f2829c15d6a..24619e80b2cce 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -125,7 +125,7 @@ config PINCTRL_SM8550_LPASS_LPI platform. config PINCTRL_SM8650_LPASS_LPI - tristate "Qualcomm Technologies Inc SM8550 LPASS LPI pin controller driver" + tristate "Qualcomm Technologies Inc SM8650 LPASS LPI pin controller driver" depends on ARM64 || COMPILE_TEST depends on PINCTRL_LPASS_LPI help diff --git a/drivers/pinctrl/qcom/pinctrl-sm7150.c b/drivers/pinctrl/qcom/pinctrl-sm7150.c index c25357ca1963e..b9f067de8ef0e 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm7150.c +++ b/drivers/pinctrl/qcom/pinctrl-sm7150.c @@ -65,7 +65,7 @@ enum { .intr_detection_width = 2, \ } -#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv) \ +#define SDC_QDSD_PINGROUP(pg_name, _tile, ctl, pull, drv) \ { \ .grp = PINCTRL_PINGROUP(#pg_name, \ pg_name##_pins, \ @@ -75,7 +75,7 @@ enum { .intr_cfg_reg = 0, \ .intr_status_reg = 0, \ .intr_target_reg = 0, \ - .tile = SOUTH, \ + .tile = _tile, \ .mux_bit = -1, \ .pull_bit = pull, \ .drv_bit = drv, \ @@ -101,7 +101,7 @@ enum { .intr_cfg_reg = 0, \ .intr_status_reg = 0, \ .intr_target_reg = 0, \ - .tile = SOUTH, \ + .tile = WEST, \ .mux_bit = -1, \ .pull_bit = 3, \ .drv_bit = 0, \ @@ -1199,13 +1199,13 @@ static const struct msm_pingroup sm7150_groups[] = { [117] = PINGROUP(117, NORTH, _, _, _, _, _, _, _, _, _), [118] = PINGROUP(118, NORTH, _, _, _, _, _, _, _, _, _), [119] = UFS_RESET(ufs_reset, 0x9f000), - [120] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x9a000, 15, 0), - [121] = SDC_QDSD_PINGROUP(sdc1_clk, 0x9a000, 13, 6), - [122] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x9a000, 11, 3), - [123] = SDC_QDSD_PINGROUP(sdc1_data, 0x9a000, 9, 0), - [124] = SDC_QDSD_PINGROUP(sdc2_clk, 0x98000, 14, 6), - [125] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x98000, 11, 3), - [126] = SDC_QDSD_PINGROUP(sdc2_data, 0x98000, 9, 0), + [120] = SDC_QDSD_PINGROUP(sdc1_rclk, WEST, 0x9a000, 15, 0), + [121] = SDC_QDSD_PINGROUP(sdc1_clk, WEST, 0x9a000, 13, 6), + [122] = SDC_QDSD_PINGROUP(sdc1_cmd, WEST, 0x9a000, 11, 3), + [123] = SDC_QDSD_PINGROUP(sdc1_data, WEST, 0x9a000, 9, 0), + [124] = SDC_QDSD_PINGROUP(sdc2_clk, SOUTH, 0x98000, 14, 6), + [125] = SDC_QDSD_PINGROUP(sdc2_cmd, SOUTH, 0x98000, 11, 3), + [126] = SDC_QDSD_PINGROUP(sdc2_data, SOUTH, 0x98000, 9, 0), }; static const struct msm_gpio_wakeirq_map sm7150_pdc_map[] = { diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c index 93e51abbf519a..757bbc549b0e2 100644 --- a/drivers/pinctrl/renesas/core.c +++ b/drivers/pinctrl/renesas/core.c @@ -731,10 +731,12 @@ static int sh_pfc_resume_noirq(struct device *dev) sh_pfc_walk_regs(pfc, sh_pfc_restore_reg); return 0; } +#define pm_psci_sleep_ptr(_ptr) pm_sleep_ptr(_ptr) #else static int sh_pfc_suspend_init(struct sh_pfc *pfc) { return 0; } static int sh_pfc_suspend_noirq(struct device *dev) { return 0; } static int sh_pfc_resume_noirq(struct device *dev) { return 0; } +#define pm_psci_sleep_ptr(_ptr) PTR_IF(false, (_ptr)) #endif /* CONFIG_ARM_PSCI_FW */ static DEFINE_NOIRQ_DEV_PM_OPS(sh_pfc_pm, sh_pfc_suspend_noirq, sh_pfc_resume_noirq); @@ -907,9 +909,11 @@ static void __init sh_pfc_check_cfg_reg(const char *drvname, sh_pfc_err("reg 0x%x: var_field_width declares %u instead of %u bits\n", cfg_reg->reg, rw, cfg_reg->reg_width); - if (n != cfg_reg->nr_enum_ids) + if (n != cfg_reg->nr_enum_ids) { sh_pfc_err("reg 0x%x: enum_ids[] has %u instead of %u values\n", cfg_reg->reg, cfg_reg->nr_enum_ids, n); + n = cfg_reg->nr_enum_ids; + } check_enum_ids: sh_pfc_check_reg_enums(drvname, cfg_reg->reg, cfg_reg->enum_ids, n); @@ -1415,7 +1419,7 @@ static struct platform_driver sh_pfc_driver = { .driver = { .name = DRV_NAME, .of_match_table = of_match_ptr(sh_pfc_of_table), - .pm = pm_sleep_ptr(&sh_pfc_pm), + .pm = pm_psci_sleep_ptr(&sh_pfc_pm), }, }; diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index acdea6ac15253..d2de526a3b588 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -2384,6 +2384,14 @@ static const unsigned int scif_clk_mux[] = { SCIF_CLK_MARK, }; +static const unsigned int scif_clk2_pins[] = { + /* SCIF_CLK2 */ + RCAR_GP_PIN(8, 11), +}; +static const unsigned int scif_clk2_mux[] = { + SCIF_CLK2_MARK, +}; + /* - SSI ------------------------------------------------- */ static const unsigned int ssi_data_pins[] = { /* SSI_SD */ @@ -2694,6 +2702,7 @@ static const struct sh_pfc_pin_group pinmux_groups[] = { SH_PFC_PIN_GROUP(scif4_clk), SH_PFC_PIN_GROUP(scif4_ctrl), SH_PFC_PIN_GROUP(scif_clk), + SH_PFC_PIN_GROUP(scif_clk2), SH_PFC_PIN_GROUP(ssi_data), SH_PFC_PIN_GROUP(ssi_ctrl), @@ -3015,6 +3024,10 @@ static const char * const scif_clk_groups[] = { "scif_clk", }; +static const char * const scif_clk2_groups[] = { + "scif_clk2", +}; + static const char * const ssi_groups[] = { "ssi_data", "ssi_ctrl", @@ -3102,6 +3115,7 @@ static const struct sh_pfc_function pinmux_functions[] = { SH_PFC_FUNCTION(scif3), SH_PFC_FUNCTION(scif4), SH_PFC_FUNCTION(scif_clk), + SH_PFC_FUNCTION(scif_clk2), SH_PFC_FUNCTION(ssi), diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index 80fb5011c7bbc..5bbcb38f843a0 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -447,6 +447,16 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, name = np->name; } + if (num_configs) { + ret = rzg2l_map_add_config(&maps[idx], name, + PIN_MAP_TYPE_CONFIGS_GROUP, + configs, num_configs); + if (ret < 0) + goto done; + + idx++; + } + mutex_lock(&pctrl->mutex); /* Register a single pin group listing all the pins we read from DT */ @@ -474,16 +484,6 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, maps[idx].data.mux.function = name; idx++; - if (num_configs) { - ret = rzg2l_map_add_config(&maps[idx], name, - PIN_MAP_TYPE_CONFIGS_GROUP, - configs, num_configs); - if (ret < 0) - goto remove_group; - - idx++; - } - dev_dbg(pctrl->dev, "Parsed %pOF with %d pins\n", np, num_pinmux); ret = 0; goto done; @@ -668,6 +668,8 @@ static int rzg2l_set_power_source(struct rzg2l_pinctrl *pctrl, u32 pin, u32 caps val = PVDD_1800; break; case 2500: + if (!(caps & (PIN_CFG_IO_VMC_ETH0 | PIN_CFG_IO_VMC_ETH1))) + return -EINVAL; val = PVDD_2500; break; case 3300: diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index badc68bbae8cc..47d19f7e295a7 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -432,6 +432,12 @@ static void cros_ec_send_resume_event(struct cros_ec_device *ec_dev) void cros_ec_resume_complete(struct cros_ec_device *ec_dev) { cros_ec_send_resume_event(ec_dev); + + /* + * Let the mfd devices know about events that occur during + * suspend. This way the clients know what to do with them. + */ + cros_ec_report_events_during_suspend(ec_dev); } EXPORT_SYMBOL(cros_ec_resume_complete); @@ -442,12 +448,6 @@ static void cros_ec_enable_irq(struct cros_ec_device *ec_dev) if (ec_dev->wake_enabled) disable_irq_wake(ec_dev->irq); - - /* - * Let the mfd devices know about events that occur during - * suspend. This way the clients know what to do with them. - */ - cros_ec_report_events_during_suspend(ec_dev); } /** @@ -475,8 +475,8 @@ EXPORT_SYMBOL(cros_ec_resume_early); */ int cros_ec_resume(struct cros_ec_device *ec_dev) { - cros_ec_enable_irq(ec_dev); - cros_ec_send_resume_event(ec_dev); + cros_ec_resume_early(ec_dev); + cros_ec_resume_complete(ec_dev); return 0; } EXPORT_SYMBOL(cros_ec_resume); diff --git a/drivers/platform/chrome/cros_ec_uart.c b/drivers/platform/chrome/cros_ec_uart.c index 68d80559fddc2..eb5eddeb73f72 100644 --- a/drivers/platform/chrome/cros_ec_uart.c +++ b/drivers/platform/chrome/cros_ec_uart.c @@ -263,12 +263,6 @@ static int cros_ec_uart_probe(struct serdev_device *serdev) if (!ec_dev) return -ENOMEM; - ret = devm_serdev_device_open(dev, serdev); - if (ret) { - dev_err(dev, "Unable to open UART device"); - return ret; - } - serdev_device_set_drvdata(serdev, ec_dev); init_waitqueue_head(&ec_uart->response.wait_queue); @@ -280,14 +274,6 @@ static int cros_ec_uart_probe(struct serdev_device *serdev) return ret; } - ret = serdev_device_set_baudrate(serdev, ec_uart->baudrate); - if (ret < 0) { - dev_err(dev, "Failed to set up host baud rate (%d)", ret); - return ret; - } - - serdev_device_set_flow_control(serdev, ec_uart->flowcontrol); - /* Initialize ec_dev for cros_ec */ ec_dev->phys_name = dev_name(dev); ec_dev->dev = dev; @@ -301,6 +287,20 @@ static int cros_ec_uart_probe(struct serdev_device *serdev) serdev_device_set_client_ops(serdev, &cros_ec_uart_client_ops); + ret = devm_serdev_device_open(dev, serdev); + if (ret) { + dev_err(dev, "Unable to open UART device"); + return ret; + } + + ret = serdev_device_set_baudrate(serdev, ec_uart->baudrate); + if (ret < 0) { + dev_err(dev, "Failed to set up host baud rate (%d)", ret); + return ret; + } + + serdev_device_set_flow_control(serdev, ec_uart->flowcontrol); + return cros_ec_register(ec_dev); } diff --git a/drivers/platform/chrome/cros_usbpd_logger.c b/drivers/platform/chrome/cros_usbpd_logger.c index f618757f8b321..930c2f47269f6 100644 --- a/drivers/platform/chrome/cros_usbpd_logger.c +++ b/drivers/platform/chrome/cros_usbpd_logger.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -249,6 +250,12 @@ static int __maybe_unused cros_usbpd_logger_suspend(struct device *dev) static SIMPLE_DEV_PM_OPS(cros_usbpd_logger_pm_ops, cros_usbpd_logger_suspend, cros_usbpd_logger_resume); +static const struct platform_device_id cros_usbpd_logger_id[] = { + { DRV_NAME, 0 }, + {} +}; +MODULE_DEVICE_TABLE(platform, cros_usbpd_logger_id); + static struct platform_driver cros_usbpd_logger_driver = { .driver = { .name = DRV_NAME, @@ -256,10 +263,10 @@ static struct platform_driver cros_usbpd_logger_driver = { }, .probe = cros_usbpd_logger_probe, .remove_new = cros_usbpd_logger_remove, + .id_table = cros_usbpd_logger_id, }; module_platform_driver(cros_usbpd_logger_driver); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Logging driver for ChromeOS EC USBPD Charger."); -MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/platform/chrome/cros_usbpd_notify.c b/drivers/platform/chrome/cros_usbpd_notify.c index aacad022f21df..c83f81d86483c 100644 --- a/drivers/platform/chrome/cros_usbpd_notify.c +++ b/drivers/platform/chrome/cros_usbpd_notify.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -218,12 +219,19 @@ static void cros_usbpd_notify_remove_plat(struct platform_device *pdev) &pdnotify->nb); } +static const struct platform_device_id cros_usbpd_notify_id[] = { + { DRV_NAME, 0 }, + {} +}; +MODULE_DEVICE_TABLE(platform, cros_usbpd_notify_id); + static struct platform_driver cros_usbpd_notify_plat_driver = { .driver = { .name = DRV_NAME, }, .probe = cros_usbpd_notify_probe_plat, .remove_new = cros_usbpd_notify_remove_plat, + .id_table = cros_usbpd_notify_id, }; static int __init cros_usbpd_notify_init(void) @@ -258,4 +266,3 @@ module_exit(cros_usbpd_notify_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ChromeOS power delivery notifier device"); MODULE_AUTHOR("Jon Flatley "); -MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index bdd302274b9ab..c38f675704f12 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -369,6 +369,20 @@ config AMILO_RFKILL This is a driver for enabling wifi on some Fujitsu-Siemens Amilo laptops. +config DELL_UART_BACKLIGHT + tristate "Dell AIO UART Backlight driver" + depends on SERIAL_8250 + depends on ACPI + help + Say Y here if you want to support Dell AIO UART backlight interface. + The Dell AIO machines released after 2017 come with a UART interface + to communicate with the backlight scalar board. This driver creates + a standard backlight interface and talks to the scalar board through + UART to adjust the AIO screen brightness. + + To compile this driver as a module, choose M here: the module will + be called dell_uart_backlight. + config FUJITSU_LAPTOP tristate "Fujitsu Laptop Extras" depends on ACPI diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 88b826e88ebd7..38c932df6446a 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -276,6 +276,7 @@ static bool has_type_aa; static u16 commun_func_bitmap; static u8 commun_fn_key_number; static bool cycle_gaming_thermal_profile = true; +static bool predator_v4; module_param(mailled, int, 0444); module_param(brightness, int, 0444); @@ -284,6 +285,7 @@ module_param(force_series, int, 0444); module_param(force_caps, int, 0444); module_param(ec_raw_mode, bool, 0444); module_param(cycle_gaming_thermal_profile, bool, 0644); +module_param(predator_v4, bool, 0444); MODULE_PARM_DESC(mailled, "Set initial state of Mail LED"); MODULE_PARM_DESC(brightness, "Set initial LCD backlight brightness"); MODULE_PARM_DESC(threeg, "Set initial state of 3G hardware"); @@ -292,6 +294,8 @@ MODULE_PARM_DESC(force_caps, "Force the capability bitmask to this value"); MODULE_PARM_DESC(ec_raw_mode, "Enable EC raw mode"); MODULE_PARM_DESC(cycle_gaming_thermal_profile, "Set thermal mode key in cycle mode. Disabling it sets the mode key in turbo toggle mode"); +MODULE_PARM_DESC(predator_v4, + "Enable features for predator laptops that use predator sense v4"); struct acer_data { int mailled; @@ -584,6 +588,24 @@ static const struct dmi_system_id acer_quirks[] __initconst = { }, .driver_data = &quirk_acer_predator_v4, }, + { + .callback = dmi_matched, + .ident = "Acer Predator PH16-71", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Predator PH16-71"), + }, + .driver_data = &quirk_acer_predator_v4, + }, + { + .callback = dmi_matched, + .ident = "Acer Predator PH18-71", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Predator PH18-71"), + }, + .driver_data = &quirk_acer_predator_v4, + }, { .callback = set_force_caps, .ident = "Acer Aspire Switch 10E SW3-016", @@ -725,7 +747,9 @@ enum acer_predator_v4_thermal_profile_wmi { /* Find which quirks are needed for a particular vendor/ model pair */ static void __init find_quirks(void) { - if (!force_series) { + if (predator_v4) { + quirks = &quirk_acer_predator_v4; + } else if (!force_series) { dmi_check_system(acer_quirks); dmi_check_system(non_acer_quirks); } else if (force_series == 2490) { diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index b456370166b6b..b4f49720c87f6 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -208,6 +208,15 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BIOS_VERSION, "03.03"), } }, + { + .ident = "Framework Laptop 13 (Phoenix)", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Framework"), + DMI_MATCH(DMI_PRODUCT_NAME, "Laptop 13 (AMD Ryzen 7040Series)"), + DMI_MATCH(DMI_BIOS_VERSION, "03.05"), + } + }, {} }; diff --git a/drivers/platform/x86/amd/pmf/acpi.c b/drivers/platform/x86/amd/pmf/acpi.c index f2eb07ef855af..60fc71c9fb0fa 100644 --- a/drivers/platform/x86/amd/pmf/acpi.c +++ b/drivers/platform/x86/amd/pmf/acpi.c @@ -90,12 +90,96 @@ static int apmf_if_call_store_buffer(struct amd_pmf_dev *pdev, int fn, void *des return err; } +static union acpi_object *apts_if_call(struct amd_pmf_dev *pdev, u32 state_index) +{ + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + acpi_handle ahandle = ACPI_HANDLE(pdev->dev); + struct acpi_object_list apts_if_arg_list; + union acpi_object apts_if_args[3]; + acpi_status status; + + apts_if_arg_list.count = 3; + apts_if_arg_list.pointer = &apts_if_args[0]; + + apts_if_args[0].type = ACPI_TYPE_INTEGER; + apts_if_args[0].integer.value = 1; + apts_if_args[1].type = ACPI_TYPE_INTEGER; + apts_if_args[1].integer.value = state_index; + apts_if_args[2].type = ACPI_TYPE_INTEGER; + apts_if_args[2].integer.value = 0; + + status = acpi_evaluate_object(ahandle, "APTS", &apts_if_arg_list, &buffer); + if (ACPI_FAILURE(status)) { + dev_err(pdev->dev, "APTS state_idx:%u call failed\n", state_index); + kfree(buffer.pointer); + return NULL; + } + + return buffer.pointer; +} + +static int apts_if_call_store_buffer(struct amd_pmf_dev *pdev, + u32 index, void *data, size_t out_sz) +{ + union acpi_object *info; + size_t size; + int err = 0; + + info = apts_if_call(pdev, index); + if (!info) + return -EIO; + + if (info->type != ACPI_TYPE_BUFFER) { + dev_err(pdev->dev, "object is not a buffer\n"); + err = -EINVAL; + goto out; + } + + size = *(u16 *)info->buffer.pointer; + if (info->buffer.length < size) { + dev_err(pdev->dev, "buffer smaller than header size %u < %zu\n", + info->buffer.length, size); + err = -EINVAL; + goto out; + } + + if (size < out_sz) { + dev_err(pdev->dev, "buffer too small %zu\n", size); + err = -EINVAL; + goto out; + } + + memcpy(data, info->buffer.pointer, out_sz); +out: + kfree(info); + return err; +} + int is_apmf_func_supported(struct amd_pmf_dev *pdev, unsigned long index) { /* If bit-n is set, that indicates function n+1 is supported */ return !!(pdev->supported_func & BIT(index - 1)); } +int apts_get_static_slider_granular_v2(struct amd_pmf_dev *pdev, + struct amd_pmf_apts_granular_output *data, u32 apts_idx) +{ + if (!is_apmf_func_supported(pdev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) + return -EINVAL; + + return apts_if_call_store_buffer(pdev, apts_idx, data, sizeof(*data)); +} + +int apmf_get_static_slider_granular_v2(struct amd_pmf_dev *pdev, + struct apmf_static_slider_granular_output_v2 *data) +{ + if (!is_apmf_func_supported(pdev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) + return -EINVAL; + + return apmf_if_call_store_buffer(pdev, APMF_FUNC_STATIC_SLIDER_GRANULAR, + data, sizeof(*data)); +} + int apmf_get_static_slider_granular(struct amd_pmf_dev *pdev, struct apmf_static_slider_granular_output *data) { @@ -140,6 +224,43 @@ static void apmf_sbios_heartbeat_notify(struct work_struct *work) kfree(info); } +int amd_pmf_notify_sbios_heartbeat_event_v2(struct amd_pmf_dev *dev, u8 flag) +{ + struct sbios_hb_event_v2 args = { }; + struct acpi_buffer params; + union acpi_object *info; + + args.size = sizeof(args); + + switch (flag) { + case ON_LOAD: + args.load = 1; + break; + case ON_UNLOAD: + args.unload = 1; + break; + case ON_SUSPEND: + args.suspend = 1; + break; + case ON_RESUME: + args.resume = 1; + break; + default: + dev_dbg(dev->dev, "Failed to send v2 heartbeat event, flag:0x%x\n", flag); + return -EINVAL; + } + + params.length = sizeof(args); + params.pointer = &args; + + info = apmf_if_call(dev, APMF_FUNC_SBIOS_HEARTBEAT_V2, ¶ms); + if (!info) + return -EIO; + + kfree(info); + return 0; +} + int apmf_update_fan_idx(struct amd_pmf_dev *pdev, bool manual, u32 idx) { union acpi_object *info; @@ -166,6 +287,11 @@ int apmf_get_auto_mode_def(struct amd_pmf_dev *pdev, struct apmf_auto_mode *data return apmf_if_call_store_buffer(pdev, APMF_FUNC_AUTO_MODE, data, sizeof(*data)); } +int apmf_get_sbios_requests_v2(struct amd_pmf_dev *pdev, struct apmf_sbios_req_v2 *req) +{ + return apmf_if_call_store_buffer(pdev, APMF_FUNC_SBIOS_REQUESTS, req, sizeof(*req)); +} + int apmf_get_sbios_requests(struct amd_pmf_dev *pdev, struct apmf_sbios_req *req) { return apmf_if_call_store_buffer(pdev, APMF_FUNC_SBIOS_REQUESTS, @@ -218,8 +344,10 @@ static int apmf_if_verify_interface(struct amd_pmf_dev *pdev) return err; pdev->supported_func = output.supported_functions; - dev_dbg(pdev->dev, "supported functions:0x%x notifications:0x%x\n", - output.supported_functions, output.notification_mask); + dev_dbg(pdev->dev, "supported functions:0x%x notifications:0x%x version:%u\n", + output.supported_functions, output.notification_mask, output.version); + + pdev->pmf_if_version = output.version; return 0; } @@ -309,7 +437,7 @@ int apmf_check_smart_pc(struct amd_pmf_dev *pmf_dev) status = acpi_walk_resources(ahandle, METHOD_NAME__CRS, apmf_walk_resources, pmf_dev); if (ACPI_FAILURE(status)) { - dev_err(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status); + dev_dbg(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status); return -EINVAL; } @@ -320,7 +448,7 @@ void apmf_acpi_deinit(struct amd_pmf_dev *pmf_dev) { acpi_handle ahandle = ACPI_HANDLE(pmf_dev->dev); - if (pmf_dev->hb_interval) + if (pmf_dev->hb_interval && pmf_dev->pmf_if_version == PMF_IF_V1) cancel_delayed_work_sync(&pmf_dev->heart_beat); if (is_apmf_func_supported(pmf_dev, APMF_FUNC_AUTO_MODE) && @@ -344,7 +472,7 @@ int apmf_acpi_init(struct amd_pmf_dev *pmf_dev) goto out; } - if (pmf_dev->hb_interval) { + if (pmf_dev->hb_interval && pmf_dev->pmf_if_version == PMF_IF_V1) { /* send heartbeats only if the interval is not zero */ INIT_DELAYED_WORK(&pmf_dev->heart_beat, apmf_sbios_heartbeat_notify); schedule_delayed_work(&pmf_dev->heart_beat, 0); diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index 4f734e049f4a4..5d4f80698a8b8 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -113,8 +113,9 @@ static void amd_pmf_dbgfs_unregister(struct amd_pmf_dev *dev) static void amd_pmf_dbgfs_register(struct amd_pmf_dev *dev) { dev->dbgfs_dir = debugfs_create_dir("amd_pmf", NULL); - debugfs_create_file("current_power_limits", 0644, dev->dbgfs_dir, dev, - ¤t_power_limits_fops); + if (dev->pmf_if_version == PMF_IF_V1) + debugfs_create_file("current_power_limits", 0644, dev->dbgfs_dir, dev, + ¤t_power_limits_fops); } int amd_pmf_get_power_source(void) @@ -299,6 +300,9 @@ static int amd_pmf_suspend_handler(struct device *dev) if (pdev->smart_pc_enabled) cancel_delayed_work_sync(&pdev->pb_work); + if (is_apmf_func_supported(pdev, APMF_FUNC_SBIOS_HEARTBEAT_V2)) + amd_pmf_notify_sbios_heartbeat_event_v2(pdev, ON_SUSPEND); + return 0; } @@ -313,6 +317,9 @@ static int amd_pmf_resume_handler(struct device *dev) return ret; } + if (is_apmf_func_supported(pdev, APMF_FUNC_SBIOS_HEARTBEAT_V2)) + amd_pmf_notify_sbios_heartbeat_event_v2(pdev, ON_RESUME); + if (pdev->smart_pc_enabled) schedule_delayed_work(&pdev->pb_work, msecs_to_jiffies(2000)); @@ -443,6 +450,8 @@ static int amd_pmf_probe(struct platform_device *pdev) amd_pmf_dbgfs_register(dev); amd_pmf_init_features(dev); apmf_install_handler(dev); + if (is_apmf_func_supported(dev, APMF_FUNC_SBIOS_HEARTBEAT_V2)) + amd_pmf_notify_sbios_heartbeat_event_v2(dev, ON_LOAD); dev_info(dev->dev, "registered PMF device successfully\n"); @@ -454,6 +463,8 @@ static void amd_pmf_remove(struct platform_device *pdev) struct amd_pmf_dev *dev = platform_get_drvdata(pdev); amd_pmf_deinit_features(dev); + if (is_apmf_func_supported(dev, APMF_FUNC_SBIOS_HEARTBEAT_V2)) + amd_pmf_notify_sbios_heartbeat_event_v2(dev, ON_UNLOAD); apmf_acpi_deinit(dev); amd_pmf_dbgfs_unregister(dev); mutex_destroy(&dev->lock); diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h index 66cae1cca73cc..282f80274d4ef 100644 --- a/drivers/platform/x86/amd/pmf/pmf.h +++ b/drivers/platform/x86/amd/pmf/pmf.h @@ -30,6 +30,7 @@ #define APMF_FUNC_STATIC_SLIDER_GRANULAR 9 #define APMF_FUNC_DYN_SLIDER_AC 11 #define APMF_FUNC_DYN_SLIDER_DC 12 +#define APMF_FUNC_SBIOS_HEARTBEAT_V2 16 /* Message Definitions */ #define SET_SPL 0x03 /* SPL: Sustained Power Limit */ @@ -50,6 +51,8 @@ #define GET_STT_LIMIT_APU 0x20 #define GET_STT_LIMIT_HS2 0x21 #define SET_P3T 0x23 /* P3T: Peak Package Power Limit */ +#define SET_PMF_PPT 0x25 +#define SET_PMF_PPT_APU_ONLY 0x26 /* OS slider update notification */ #define DC_BEST_PERF 0 @@ -83,6 +86,47 @@ #define TA_OUTPUT_RESERVED_MEM 906 #define MAX_OPERATION_PARAMS 4 +#define PMF_IF_V1 1 +#define PMF_IF_V2 2 + +#define APTS_MAX_STATES 16 + +/* APTS PMF BIOS Interface */ +struct amd_pmf_apts_output { + u16 table_version; + u32 fan_table_idx; + u32 pmf_ppt; + u32 ppt_pmf_apu_only; + u32 stt_min_limit; + u8 stt_skin_temp_limit_apu; + u8 stt_skin_temp_limit_hs2; +} __packed; + +struct amd_pmf_apts_granular_output { + u16 size; + struct amd_pmf_apts_output val; +} __packed; + +struct amd_pmf_apts_granular { + u16 size; + struct amd_pmf_apts_output val[APTS_MAX_STATES]; +}; + +struct sbios_hb_event_v2 { + u16 size; + u8 load; + u8 unload; + u8 suspend; + u8 resume; +} __packed; + +enum sbios_hb_v2 { + ON_LOAD, + ON_UNLOAD, + ON_SUSPEND, + ON_RESUME, +}; + /* AMD PMF BIOS interfaces */ struct apmf_verify_interface { u16 size; @@ -114,6 +158,18 @@ struct apmf_sbios_req { u8 skin_temp_hs2; } __packed; +struct apmf_sbios_req_v2 { + u16 size; + u32 pending_req; + u8 rsd; + u32 ppt_pmf; + u32 ppt_pmf_apu_only; + u32 stt_min_limit; + u8 skin_temp_apu; + u8 skin_temp_hs2; + u32 custom_policy[10]; +} __packed; + struct apmf_fan_idx { u16 size; u8 fan_ctl_mode; @@ -194,6 +250,14 @@ enum power_modes { POWER_MODE_MAX, }; +enum power_modes_v2 { + POWER_MODE_BEST_PERFORMANCE, + POWER_MODE_BALANCED, + POWER_MODE_BEST_POWER_EFFICIENCY, + POWER_MODE_ENERGY_SAVE, + POWER_MODE_V2_MAX, +}; + struct amd_pmf_dev { void __iomem *regbase; void __iomem *smu_virt_addr; @@ -231,8 +295,13 @@ struct amd_pmf_dev { u64 policy_addr; void *policy_base; bool smart_pc_enabled; + u16 pmf_if_version; }; +struct apmf_sps_prop_granular_v2 { + u8 power_states[POWER_SOURCE_MAX][POWER_MODE_V2_MAX]; +} __packed; + struct apmf_sps_prop_granular { u32 fppt; u32 sppt; @@ -254,6 +323,16 @@ struct amd_pmf_static_slider_granular { struct apmf_sps_prop_granular prop[POWER_SOURCE_MAX][POWER_MODE_MAX]; }; +struct apmf_static_slider_granular_output_v2 { + u16 size; + struct apmf_sps_prop_granular_v2 sps_idx; +} __packed; + +struct amd_pmf_static_slider_granular_v2 { + u16 size; + struct apmf_sps_prop_granular_v2 sps_idx; +}; + struct os_power_slider { u16 size; u8 slider_event; @@ -585,6 +664,7 @@ int amd_pmf_get_power_source(void); int apmf_install_handler(struct amd_pmf_dev *pmf_dev); int apmf_os_power_slider_update(struct amd_pmf_dev *dev, u8 flag); int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer); +int amd_pmf_notify_sbios_heartbeat_event_v2(struct amd_pmf_dev *dev, u8 flag); /* SPS Layer */ int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf); @@ -602,6 +682,10 @@ const char *amd_pmf_source_as_str(unsigned int state); int apmf_update_fan_idx(struct amd_pmf_dev *pdev, bool manual, u32 idx); int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf); +int apmf_get_static_slider_granular_v2(struct amd_pmf_dev *dev, + struct apmf_static_slider_granular_output_v2 *data); +int apts_get_static_slider_granular_v2(struct amd_pmf_dev *pdev, + struct amd_pmf_apts_granular_output *data, u32 apts_idx); /* Auto Mode Layer */ int apmf_get_auto_mode_def(struct amd_pmf_dev *pdev, struct apmf_auto_mode *data); @@ -609,6 +693,7 @@ void amd_pmf_init_auto_mode(struct amd_pmf_dev *dev); void amd_pmf_deinit_auto_mode(struct amd_pmf_dev *dev); void amd_pmf_trans_automode(struct amd_pmf_dev *dev, int socket_power, ktime_t time_elapsed_ms); int apmf_get_sbios_requests(struct amd_pmf_dev *pdev, struct apmf_sbios_req *req); +int apmf_get_sbios_requests_v2(struct amd_pmf_dev *pdev, struct apmf_sbios_req_v2 *req); void amd_pmf_update_2_cql(struct amd_pmf_dev *dev, bool is_cql_event); int amd_pmf_reset_amt(struct amd_pmf_dev *dev); diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c index 33e23e25c8b1e..92f7fb22277dc 100644 --- a/drivers/platform/x86/amd/pmf/sps.c +++ b/drivers/platform/x86/amd/pmf/sps.c @@ -10,9 +10,27 @@ #include "pmf.h" +static struct amd_pmf_static_slider_granular_v2 config_store_v2; static struct amd_pmf_static_slider_granular config_store; +static struct amd_pmf_apts_granular apts_config_store; #ifdef CONFIG_AMD_PMF_DEBUG +static const char *slider_v2_as_str(unsigned int state) +{ + switch (state) { + case POWER_MODE_BEST_PERFORMANCE: + return "Best Performance"; + case POWER_MODE_BALANCED: + return "Balanced"; + case POWER_MODE_BEST_POWER_EFFICIENCY: + return "Best Power Efficiency"; + case POWER_MODE_ENERGY_SAVE: + return "Energy Save"; + default: + return "Unknown Power Mode"; + } +} + static const char *slider_as_str(unsigned int state) { switch (state) { @@ -63,10 +81,88 @@ static void amd_pmf_dump_sps_defaults(struct amd_pmf_static_slider_granular *dat pr_debug("Static Slider Data - END\n"); } + +static void amd_pmf_dump_sps_defaults_v2(struct amd_pmf_static_slider_granular_v2 *data) +{ + unsigned int i, j; + + pr_debug("Static Slider APTS state index data - BEGIN"); + pr_debug("size: %u\n", data->size); + + for (i = 0; i < POWER_SOURCE_MAX; i++) + for (j = 0; j < POWER_MODE_V2_MAX; j++) + pr_debug("%s %s: %u\n", amd_pmf_source_as_str(i), slider_v2_as_str(j), + data->sps_idx.power_states[i][j]); + + pr_debug("Static Slider APTS state index data - END\n"); +} + +static void amd_pmf_dump_apts_sps_defaults(struct amd_pmf_apts_granular *info) +{ + int i; + + pr_debug("Static Slider APTS index default values data - BEGIN"); + + for (i = 0; i < APTS_MAX_STATES; i++) { + pr_debug("Table Version[%d] = %u\n", i, info->val[i].table_version); + pr_debug("Fan Index[%d] = %u\n", i, info->val[i].fan_table_idx); + pr_debug("PPT[%d] = %u\n", i, info->val[i].pmf_ppt); + pr_debug("PPT APU[%d] = %u\n", i, info->val[i].ppt_pmf_apu_only); + pr_debug("STT Min[%d] = %u\n", i, info->val[i].stt_min_limit); + pr_debug("STT APU[%d] = %u\n", i, info->val[i].stt_skin_temp_limit_apu); + pr_debug("STT HS2[%d] = %u\n", i, info->val[i].stt_skin_temp_limit_hs2); + } + + pr_debug("Static Slider APTS index default values data - END"); +} #else static void amd_pmf_dump_sps_defaults(struct amd_pmf_static_slider_granular *data) {} +static void amd_pmf_dump_sps_defaults_v2(struct amd_pmf_static_slider_granular_v2 *data) {} +static void amd_pmf_dump_apts_sps_defaults(struct amd_pmf_apts_granular *info) {} #endif +static void amd_pmf_load_apts_defaults_sps_v2(struct amd_pmf_dev *pdev) +{ + struct amd_pmf_apts_granular_output output; + struct amd_pmf_apts_output *ps; + int i; + + memset(&apts_config_store, 0, sizeof(apts_config_store)); + + ps = apts_config_store.val; + + for (i = 0; i < APTS_MAX_STATES; i++) { + apts_get_static_slider_granular_v2(pdev, &output, i); + ps[i].table_version = output.val.table_version; + ps[i].fan_table_idx = output.val.fan_table_idx; + ps[i].pmf_ppt = output.val.pmf_ppt; + ps[i].ppt_pmf_apu_only = output.val.ppt_pmf_apu_only; + ps[i].stt_min_limit = output.val.stt_min_limit; + ps[i].stt_skin_temp_limit_apu = output.val.stt_skin_temp_limit_apu; + ps[i].stt_skin_temp_limit_hs2 = output.val.stt_skin_temp_limit_hs2; + } + + amd_pmf_dump_apts_sps_defaults(&apts_config_store); +} + +static void amd_pmf_load_defaults_sps_v2(struct amd_pmf_dev *dev) +{ + struct apmf_static_slider_granular_output_v2 output; + unsigned int i, j; + + memset(&config_store_v2, 0, sizeof(config_store_v2)); + apmf_get_static_slider_granular_v2(dev, &output); + + config_store_v2.size = output.size; + + for (i = 0; i < POWER_SOURCE_MAX; i++) + for (j = 0; j < POWER_MODE_V2_MAX; j++) + config_store_v2.sps_idx.power_states[i][j] = + output.sps_idx.power_states[i][j]; + + amd_pmf_dump_sps_defaults_v2(&config_store_v2); +} + static void amd_pmf_load_defaults_sps(struct amd_pmf_dev *dev) { struct apmf_static_slider_granular_output output; @@ -94,6 +190,19 @@ static void amd_pmf_load_defaults_sps(struct amd_pmf_dev *dev) amd_pmf_dump_sps_defaults(&config_store); } +static void amd_pmf_update_slider_v2(struct amd_pmf_dev *dev, int idx) +{ + amd_pmf_send_cmd(dev, SET_PMF_PPT, false, apts_config_store.val[idx].pmf_ppt, NULL); + amd_pmf_send_cmd(dev, SET_PMF_PPT_APU_ONLY, false, + apts_config_store.val[idx].ppt_pmf_apu_only, NULL); + amd_pmf_send_cmd(dev, SET_STT_MIN_LIMIT, false, + apts_config_store.val[idx].stt_min_limit, NULL); + amd_pmf_send_cmd(dev, SET_STT_LIMIT_APU, false, + apts_config_store.val[idx].stt_skin_temp_limit_apu, NULL); + amd_pmf_send_cmd(dev, SET_STT_LIMIT_HS2, false, + apts_config_store.val[idx].stt_skin_temp_limit_hs2, NULL); +} + void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx, struct amd_pmf_static_slider_granular *table) { @@ -126,6 +235,32 @@ void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx, } } +static int amd_pmf_update_sps_power_limits_v2(struct amd_pmf_dev *pdev, int pwr_mode) +{ + int src, index; + + src = amd_pmf_get_power_source(); + + switch (pwr_mode) { + case POWER_MODE_PERFORMANCE: + index = config_store_v2.sps_idx.power_states[src][POWER_MODE_BEST_PERFORMANCE]; + amd_pmf_update_slider_v2(pdev, index); + break; + case POWER_MODE_BALANCED_POWER: + index = config_store_v2.sps_idx.power_states[src][POWER_MODE_BALANCED]; + amd_pmf_update_slider_v2(pdev, index); + break; + case POWER_MODE_POWER_SAVER: + index = config_store_v2.sps_idx.power_states[src][POWER_MODE_BEST_POWER_EFFICIENCY]; + amd_pmf_update_slider_v2(pdev, index); + break; + default: + return -EINVAL; + } + + return 0; +} + int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf) { int mode; @@ -134,6 +269,9 @@ int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf) if (mode < 0) return mode; + if (pmf->pmf_if_version == PMF_IF_V2) + return amd_pmf_update_sps_power_limits_v2(pmf, mode); + amd_pmf_update_slider(pmf, SLIDER_OP_SET, mode, NULL); return 0; @@ -256,7 +394,12 @@ int amd_pmf_init_sps(struct amd_pmf_dev *dev) dev->current_profile = PLATFORM_PROFILE_BALANCED; if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { - amd_pmf_load_defaults_sps(dev); + if (dev->pmf_if_version == PMF_IF_V2) { + amd_pmf_load_defaults_sps_v2(dev); + amd_pmf_load_apts_defaults_sps_v2(dev); + } else { + amd_pmf_load_defaults_sps(dev); + } /* update SPS balanced power mode thermals */ amd_pmf_set_sps_power_limits(dev); diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c index dcbe8f85e1229..4ebfe0f5a7fb2 100644 --- a/drivers/platform/x86/amd/pmf/tee-if.c +++ b/drivers/platform/x86/amd/pmf/tee-if.c @@ -249,8 +249,8 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev) u32 cookie, length; int res; - cookie = readl(dev->policy_buf + POLICY_COOKIE_OFFSET); - length = readl(dev->policy_buf + POLICY_COOKIE_LEN); + cookie = *(u32 *)(dev->policy_buf + POLICY_COOKIE_OFFSET); + length = *(u32 *)(dev->policy_buf + POLICY_COOKIE_LEN); if (cookie != POLICY_SIGN_COOKIE || !length) { dev_dbg(dev->dev, "cookie doesn't match\n"); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 18be35fdb3814..8cb2afafde161 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -489,7 +489,17 @@ static int asus_wmi_evaluate_method_agfn(const struct acpi_buffer args) static int asus_wmi_get_devstate(struct asus_wmi *asus, u32 dev_id, u32 *retval) { - return asus_wmi_evaluate_method(asus->dsts_id, dev_id, 0, retval); + int err; + + err = asus_wmi_evaluate_method(asus->dsts_id, dev_id, 0, retval); + + if (err) + return err; + + if (*retval == ~0) + return -ENODEV; + + return 0; } static int asus_wmi_set_devstate(u32 dev_id, u32 ctrl_param, diff --git a/drivers/platform/x86/dell/Makefile b/drivers/platform/x86/dell/Makefile index 1b89424266223..8176a257d9c35 100644 --- a/drivers/platform/x86/dell/Makefile +++ b/drivers/platform/x86/dell/Makefile @@ -14,6 +14,7 @@ dell-smbios-objs := dell-smbios-base.o dell-smbios-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o dell-smbios-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o obj-$(CONFIG_DELL_SMO8800) += dell-smo8800.o +obj-$(CONFIG_DELL_UART_BACKLIGHT) += dell-uart-backlight.o obj-$(CONFIG_DELL_WMI) += dell-wmi.o dell-wmi-objs := dell-wmi-base.o dell-wmi-$(CONFIG_DELL_WMI_PRIVACY) += dell-wmi-privacy.o diff --git a/drivers/platform/x86/dell/dell-smbios-base.c b/drivers/platform/x86/dell/dell-smbios-base.c index e61bfaf8b5c48..86b95206cb1bd 100644 --- a/drivers/platform/x86/dell/dell-smbios-base.c +++ b/drivers/platform/x86/dell/dell-smbios-base.c @@ -11,6 +11,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -25,11 +26,16 @@ static u32 da_supported_commands; static int da_num_tokens; static struct platform_device *platform_device; static struct calling_interface_token *da_tokens; -static struct device_attribute *token_location_attrs; -static struct device_attribute *token_value_attrs; +static struct token_sysfs_data *token_entries; static struct attribute **token_attrs; static DEFINE_MUTEX(smbios_mutex); +struct token_sysfs_data { + struct device_attribute location_attr; + struct device_attribute value_attr; + struct calling_interface_token *token; +}; + struct smbios_device { struct list_head list; struct device *device; @@ -416,47 +422,26 @@ static void __init find_tokens(const struct dmi_header *dm, void *dummy) } } -static int match_attribute(struct device *dev, - struct device_attribute *attr) -{ - int i; - - for (i = 0; i < da_num_tokens * 2; i++) { - if (!token_attrs[i]) - continue; - if (strcmp(token_attrs[i]->name, attr->attr.name) == 0) - return i/2; - } - dev_dbg(dev, "couldn't match: %s\n", attr->attr.name); - return -EINVAL; -} - static ssize_t location_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i; + struct token_sysfs_data *data = container_of(attr, struct token_sysfs_data, location_attr); if (!capable(CAP_SYS_ADMIN)) return -EPERM; - i = match_attribute(dev, attr); - if (i > 0) - return sysfs_emit(buf, "%08x", da_tokens[i].location); - return 0; + return sysfs_emit(buf, "%08x", data->token->location); } static ssize_t value_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i; + struct token_sysfs_data *data = container_of(attr, struct token_sysfs_data, value_attr); if (!capable(CAP_SYS_ADMIN)) return -EPERM; - i = match_attribute(dev, attr); - if (i > 0) - return sysfs_emit(buf, "%08x", da_tokens[i].value); - return 0; + return sysfs_emit(buf, "%08x", data->token->value); } static struct attribute_group smbios_attribute_group = { @@ -473,22 +458,15 @@ static int build_tokens_sysfs(struct platform_device *dev) { char *location_name; char *value_name; - size_t size; int ret; int i, j; - /* (number of tokens + 1 for null terminated */ - size = sizeof(struct device_attribute) * (da_num_tokens + 1); - token_location_attrs = kzalloc(size, GFP_KERNEL); - if (!token_location_attrs) + token_entries = kcalloc(da_num_tokens, sizeof(*token_entries), GFP_KERNEL); + if (!token_entries) return -ENOMEM; - token_value_attrs = kzalloc(size, GFP_KERNEL); - if (!token_value_attrs) - goto out_allocate_value; /* need to store both location and value + terminator*/ - size = sizeof(struct attribute *) * ((2 * da_num_tokens) + 1); - token_attrs = kzalloc(size, GFP_KERNEL); + token_attrs = kcalloc((2 * da_num_tokens) + 1, sizeof(*token_attrs), GFP_KERNEL); if (!token_attrs) goto out_allocate_attrs; @@ -496,27 +474,32 @@ static int build_tokens_sysfs(struct platform_device *dev) /* skip empty */ if (da_tokens[i].tokenID == 0) continue; + + token_entries[i].token = &da_tokens[i]; + /* add location */ location_name = kasprintf(GFP_KERNEL, "%04x_location", da_tokens[i].tokenID); if (location_name == NULL) goto out_unwind_strings; - sysfs_attr_init(&token_location_attrs[i].attr); - token_location_attrs[i].attr.name = location_name; - token_location_attrs[i].attr.mode = 0444; - token_location_attrs[i].show = location_show; - token_attrs[j++] = &token_location_attrs[i].attr; + + sysfs_attr_init(&token_entries[i].location_attr.attr); + token_entries[i].location_attr.attr.name = location_name; + token_entries[i].location_attr.attr.mode = 0444; + token_entries[i].location_attr.show = location_show; + token_attrs[j++] = &token_entries[i].location_attr.attr; /* add value */ value_name = kasprintf(GFP_KERNEL, "%04x_value", da_tokens[i].tokenID); if (value_name == NULL) goto loop_fail_create_value; - sysfs_attr_init(&token_value_attrs[i].attr); - token_value_attrs[i].attr.name = value_name; - token_value_attrs[i].attr.mode = 0444; - token_value_attrs[i].show = value_show; - token_attrs[j++] = &token_value_attrs[i].attr; + + sysfs_attr_init(&token_entries[i].value_attr.attr); + token_entries[i].value_attr.attr.name = value_name; + token_entries[i].value_attr.attr.mode = 0444; + token_entries[i].value_attr.show = value_show; + token_attrs[j++] = &token_entries[i].value_attr.attr; continue; loop_fail_create_value: @@ -532,14 +515,12 @@ static int build_tokens_sysfs(struct platform_device *dev) out_unwind_strings: while (i--) { - kfree(token_location_attrs[i].attr.name); - kfree(token_value_attrs[i].attr.name); + kfree(token_entries[i].location_attr.attr.name); + kfree(token_entries[i].value_attr.attr.name); } kfree(token_attrs); out_allocate_attrs: - kfree(token_value_attrs); -out_allocate_value: - kfree(token_location_attrs); + kfree(token_entries); return -ENOMEM; } @@ -551,12 +532,11 @@ static void free_group(struct platform_device *pdev) sysfs_remove_group(&pdev->dev.kobj, &smbios_attribute_group); for (i = 0; i < da_num_tokens; i++) { - kfree(token_location_attrs[i].attr.name); - kfree(token_value_attrs[i].attr.name); + kfree(token_entries[i].location_attr.attr.name); + kfree(token_entries[i].value_attr.attr.name); } kfree(token_attrs); - kfree(token_value_attrs); - kfree(token_location_attrs); + kfree(token_entries); } static int __init dell_smbios_init(void) diff --git a/drivers/platform/x86/dell/dell-uart-backlight.c b/drivers/platform/x86/dell/dell-uart-backlight.c new file mode 100644 index 0000000000000..120701e5b8b13 --- /dev/null +++ b/drivers/platform/x86/dell/dell-uart-backlight.c @@ -0,0 +1,526 @@ +/* + * Dell AIO Serial Backlight Driver + * + * Copyright (C) 2017 AceLan Kao + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "dell-uart-backlight.h" + +struct dell_uart_backlight { + struct device *dev; + struct backlight_device *dell_uart_bd; + struct mutex brightness_mutex; + int line; + int bl_power; +}; +struct uart_8250_port *serial8250_get_port(int line); +static struct tty_struct *tty; +static struct file *ftty; + +unsigned int (*io_serial_in)(struct uart_port *p, int offset); +int (*uart_write)(struct tty_struct *tty, const unsigned char *buf, int count); +void (*uart_flush_chars)(struct tty_struct *tty); + + +static bool force; +module_param(force, bool, 0444); +MODULE_PARM_DESC(force, "load the driver regardless of the scalar status"); + +static struct dell_uart_bl_cmd uart_cmd[] = { + /* + * Get Firmware Version: Tool uses this command to get firmware version. + * Command: 0x6A 0x06 0x8F (Length:3 Type: 0x0A, Cmd:6 Checksum:0x8F) + * Return data: 0x0D 0x06 Data checksum (Length:13,Cmd:0x06, + * Data :F/W version(APRILIA=APR27-VXXX,PHINE=PHI23-VXXX), + * checksum:SUM(Length and Cmd and Data)xor 0xFF . + */ + [DELL_UART_GET_FIRMWARE_VER] = { + .cmd = {0x6A, 0x06, 0x8F}, + .tx_len = 3, + }, + /* + * Get Brightness level: Application uses this command for scaler to + * get brightness. + * Command: 0x6A 0x0C 0x89 + * (Length:3 Type: 0x0A, Cmd:0x0C, Checksum:0x89) + * Return data: 0x04 0x0C Data checksum + * (Length:4 Cmd: 0x0C Data: brightness level + * checksum: SUM(Length and Cmd and Data)xor 0xFF) + * brightness level which ranges from 0~100. + */ + [DELL_UART_GET_BRIGHTNESS] = { + .cmd = {0x6A, 0x0C, 0x89}, + .ret = {0x04, 0x0C, 0x00, 0x00}, + .tx_len = 3, + .rx_len = 4, + }, + /* Set Brightness level: Application uses this command for scaler to + * set brightness. + * Command: 0x8A 0x0B Byte2 Checksum (Length:4 Type: 0x0A, Cmd:0x0B) + * where Byte2 is the brightness level which ranges from 0~100. + * Return data: 0x03 0x0B 0xF1(Length:3,Cmd:B,checksum:0xF1) + * Scaler must send the 3bytes ack within 1 second when success, + * other value if error + */ + [DELL_UART_SET_BRIGHTNESS] = { + .cmd = {0x8A, 0x0B, 0x0, 0x0}, + .ret = {0x03, 0x0B, 0xF1}, + .tx_len = 4, + .rx_len = 3, + }, + /* + * Screen ON/OFF Control: Application uses this command to control + * screen ON or OFF. + * Command: 0x8A 0x0E Byte2 Checksum (Length:4 Type: 0x0A, Cmd:0x0E) + * where + * Byte2=0 to turn OFF the screen. + * Byte2=1 to turn ON the screen + * Other value of Byte2 is reserved and invalid. + * Return data: 0x03 0x0E 0xEE(Length:3,Cmd:E,checksum:0xEE) + */ + [DELL_UART_SET_BACKLIGHT_POWER] = { + .cmd = {0x8A, 0x0E, 0x00, 0x0}, + .ret = {0x03, 0x0E, 0xEE}, + .tx_len = 4, + .rx_len = 3, + }, + /* + * Get display mode: Application uses this command to get scaler + * display mode. + * Command: 0x6A 0x10 0x85 (Length:3 Type: 0x0A, Cmd:0x10) + * Return data: 0x04 0x10 Data checksum + * (Length:4 Cmd:0x10 Data: mode checksum: SUM + * mode =0 if PC mode + * mode =1 if AV(HDMI) mode + */ + [DELL_UART_GET_DISPLAY_MODE] = { + .cmd = {0x6A, 0x10, 0x85}, + .ret = {0x04, 0x10, 0x00, 0x00}, + .tx_len = 3, + .rx_len = 4, + }, +}; + +static const struct dmi_system_id dell_uart_backlight_alpha_platform[] = { + { + .ident = "Dell Inspiron 7777 AIO", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7777 AIO"), + }, + }, + { + .ident = "Dell Inspiron 5477 AIO", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5477 AIO"), + }, + }, + { + .ident = "Dell OptiPlex 7769 AIO", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 7769 AIO"), + }, + }, + { + .ident = "Dell OptiPlex 5260 AIO", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 5260 AIO"), + }, + }, + { } +}; + +static int dell_uart_write(struct uart_8250_port *up, __u8 *buf, int len) +{ + int actual = 0; + struct uart_port *port = &up->port; + + tty_port_tty_wakeup(&port->state->port); + tty = tty_port_tty_get(&port->state->port); + actual = uart_write(tty, buf, len); + uart_flush_chars(tty); + + return actual; +} + +static int dell_uart_read(struct uart_8250_port *up, __u8 *buf, int len) +{ + int i, retry; + unsigned long flags; + + spin_lock_irqsave(&up->port.lock, flags); + for (i = 0; i < len; i++) { + retry = 10; + while (!(io_serial_in(&up->port, UART_LSR) & UART_LSR_DR)) { + if (--retry == 0) + break; + mdelay(20); + } + + if (retry == 0) + break; + buf[i] = io_serial_in(&up->port, UART_RX); + } + spin_unlock_irqrestore(&up->port.lock, flags); + + return i; +} + +static void dell_uart_dump_cmd(const char *func, const char *prefix, + const char *cmd, int len) +{ + char buf[80]; + + snprintf(buf, 80, "dell_uart_backlight:%s:%s", func, prefix); + if (len != 0) + print_hex_dump_debug(buf, DUMP_PREFIX_NONE, + 16, 1, cmd, len, false); + else + pr_debug("dell_uart_backlight:%s:%sNULL\n", func, prefix); + +} + +/* + * checksum: SUM(Length and Cmd and Data)xor 0xFF) + */ +static unsigned char dell_uart_checksum(unsigned char *buf, int len) +{ + unsigned char val = 0; + + while (len-- > 0) + val += buf[len]; + + return val ^ 0xff; +} + +/* + * There is no command to get backlight power status, + * so we set the backlight power to "on" while initializing, + * and then track and report its status by bl_power variable + */ +static inline int dell_uart_get_bl_power(struct dell_uart_backlight *dell_pdata) +{ + return dell_pdata->bl_power; +} + +static int dell_uart_set_bl_power(struct backlight_device *bd, int power) +{ + struct dell_uart_bl_cmd *bl_cmd = + &uart_cmd[DELL_UART_SET_BACKLIGHT_POWER]; + struct dell_uart_backlight *dell_pdata = bl_get_data(bd); + struct uart_8250_port *uart = serial8250_get_port(dell_pdata->line); + int rx_len; + + if (power != FB_BLANK_POWERDOWN) + power = FB_BLANK_UNBLANK; + + bl_cmd->cmd[2] = power ? 0 : 1; + bl_cmd->cmd[3] = dell_uart_checksum(bl_cmd->cmd, bl_cmd->tx_len - 1); + + dell_uart_dump_cmd(__func__, "tx: ", bl_cmd->cmd, bl_cmd->tx_len); + + if (mutex_lock_killable(&dell_pdata->brightness_mutex) < 0) { + pr_debug("Failed to get mutex_lock"); + return 0; + } + + dell_uart_write(uart, bl_cmd->cmd, bl_cmd->tx_len); + rx_len = dell_uart_read(uart, bl_cmd->ret, bl_cmd->rx_len); + + mutex_unlock(&dell_pdata->brightness_mutex); + + dell_uart_dump_cmd(__func__, "rx: ", bl_cmd->ret, rx_len); + + bd->props.power = power; + dell_pdata->bl_power = power; + + return 0; +} + +static int dell_uart_get_brightness(struct backlight_device *bd) +{ + struct dell_uart_bl_cmd *bl_cmd = &uart_cmd[DELL_UART_GET_BRIGHTNESS]; + struct dell_uart_backlight *dell_pdata = bl_get_data(bd); + struct uart_8250_port *uart = serial8250_get_port(dell_pdata->line); + int rx_len, brightness = 0; + + dell_uart_dump_cmd(__func__, "tx: ", bl_cmd->cmd, bl_cmd->tx_len); + + if (mutex_lock_killable(&dell_pdata->brightness_mutex) < 0) { + pr_debug("Failed to get mutex_lock"); + return 0; + } + + dell_uart_write(uart, bl_cmd->cmd, bl_cmd->tx_len); + rx_len = dell_uart_read(uart, bl_cmd->ret, bl_cmd->rx_len); + + mutex_unlock(&dell_pdata->brightness_mutex); + + dell_uart_dump_cmd(__func__, "rx: ", bl_cmd->ret, rx_len); + + brightness = (unsigned int)bl_cmd->ret[2]; + + return brightness; +} + +static int dell_uart_update_status(struct backlight_device *bd) +{ + struct dell_uart_bl_cmd *bl_cmd = &uart_cmd[DELL_UART_SET_BRIGHTNESS]; + struct dell_uart_backlight *dell_pdata = bl_get_data(bd); + struct uart_8250_port *uart = serial8250_get_port(dell_pdata->line); + int rx_len; + + bl_cmd->cmd[2] = bd->props.brightness; + bl_cmd->cmd[3] = dell_uart_checksum(bl_cmd->cmd, bl_cmd->tx_len - 1); + + dell_uart_dump_cmd(__func__, "tx: ", bl_cmd->cmd, bl_cmd->tx_len); + + if (mutex_lock_killable(&dell_pdata->brightness_mutex) < 0) { + pr_debug("Failed to get mutex_lock"); + return 0; + } + + dell_uart_write(uart, bl_cmd->cmd, bl_cmd->tx_len); + rx_len = dell_uart_read(uart, bl_cmd->ret, bl_cmd->rx_len); + + mutex_unlock(&dell_pdata->brightness_mutex); + + dell_uart_dump_cmd(__func__, "rx: ", bl_cmd->ret, rx_len); + + if (bd->props.power != dell_uart_get_bl_power(dell_pdata)) + dell_uart_set_bl_power(bd, bd->props.power); + + return 0; +} + +static int dell_uart_show_firmware_ver(struct dell_uart_backlight *dell_pdata) +{ + struct dell_uart_bl_cmd *bl_cmd = &uart_cmd[DELL_UART_GET_FIRMWARE_VER]; + struct uart_8250_port *uart = serial8250_get_port(dell_pdata->line); + int rx_len = 0, retry = 10; + + dell_uart_dump_cmd(__func__, "tx: ", bl_cmd->cmd, bl_cmd->tx_len); + + if (mutex_lock_killable(&dell_pdata->brightness_mutex) < 0) { + pr_debug("Failed to get mutex_lock"); + return -1; + } + + dell_uart_write(uart, bl_cmd->cmd, bl_cmd->tx_len); + while (retry-- > 0) { + /* first byte is data length */ + dell_uart_read(uart, bl_cmd->ret, 1); + rx_len = (int)bl_cmd->ret[0]; + if (bl_cmd->ret[0] > 80 || bl_cmd->ret[0] == 0) { + pr_debug("Failed to get firmware version\n"); + if (retry == 0) { + mutex_unlock(&dell_pdata->brightness_mutex); + return -1; + } + msleep(100); + continue; + } + + dell_uart_read(uart, bl_cmd->ret+1, rx_len-1); + break; + } + mutex_unlock(&dell_pdata->brightness_mutex); + + dell_uart_dump_cmd(__func__, "rx: ", bl_cmd->ret, rx_len); + + pr_debug("Firmare str(%d)= %s\n", (int)bl_cmd->ret[0], bl_cmd->ret+2); + return rx_len; +} + +static int dell_uart_get_display_mode(struct dell_uart_backlight *dell_pdata) +{ + struct dell_uart_bl_cmd *bl_cmd = &uart_cmd[DELL_UART_GET_DISPLAY_MODE]; + struct uart_8250_port *uart = serial8250_get_port(dell_pdata->line); + int rx_len; + int status = 0, retry = 10; + + do { + dell_uart_dump_cmd(__func__, "tx: ", bl_cmd->cmd, bl_cmd->tx_len); + + if (mutex_lock_killable(&dell_pdata->brightness_mutex) < 0) { + pr_debug("Failed to get mutex_lock"); + return 0; + } + + dell_uart_write(uart, bl_cmd->cmd, bl_cmd->tx_len); + rx_len = dell_uart_read(uart, bl_cmd->ret, bl_cmd->rx_len); + + mutex_unlock(&dell_pdata->brightness_mutex); + + dell_uart_dump_cmd(__func__, "rx: ", bl_cmd->ret, rx_len); + mdelay(1000); + } while (rx_len == 0 && --retry); + + if (rx_len == 4) + status = ((unsigned int)bl_cmd->ret[2] == PC_MODE); + + return status; +} + +static const struct backlight_ops dell_uart_backlight_ops = { + .get_brightness = dell_uart_get_brightness, + .update_status = dell_uart_update_status, +}; + +static int dell_uart_startup(struct dell_uart_backlight *dell_pdata) +{ + struct uart_8250_port *uartp; + struct uart_port *port; + + dell_pdata->line = 0; + uartp = serial8250_get_port(dell_pdata->line); + port = &uartp->port; + tty = port->state->port.tty; + io_serial_in = port->serial_in; + uart_write = tty->driver->ops->write; + uart_flush_chars = tty->driver->ops->flush_chars; + + return 0; +} + +static int dell_uart_bl_add(struct acpi_device *dev) +{ + struct dell_uart_backlight *dell_pdata; + struct backlight_properties props; + struct backlight_device *dell_uart_bd; + + dell_pdata = kzalloc(sizeof(struct dell_uart_backlight), GFP_KERNEL); + if (!dell_pdata) { + pr_debug("Failed to allocate memory for dell_uart_backlight\n"); + return -ENOMEM; + } + dell_pdata->dev = &dev->dev; + dell_uart_startup(dell_pdata); + dev->driver_data = dell_pdata; + + mutex_init(&dell_pdata->brightness_mutex); + + if (!force) { + if (dmi_check_system(dell_uart_backlight_alpha_platform)) { + /* try another command to make sure there is no scalar IC */ + if (dell_uart_show_firmware_ver(dell_pdata) <= 4) { + pr_debug("Scalar is not in charge of brightness adjustment.\n"); + kfree_sensitive(dell_pdata); + return -ENODEV; + } + } + else if (!dell_uart_get_display_mode(dell_pdata)) { + pr_debug("Scalar is not in charge of brightness adjustment.\n"); + kfree_sensitive(dell_pdata); + return -ENODEV; + } + } + + memset(&props, 0, sizeof(struct backlight_properties)); + props.type = BACKLIGHT_PLATFORM; + props.max_brightness = 100; + + dell_uart_bd = backlight_device_register("dell_uart_backlight", + &dev->dev, + dell_pdata, + &dell_uart_backlight_ops, + &props); + if (IS_ERR(dell_uart_bd)) { + kfree_sensitive(dell_pdata); + pr_debug("Backlight registration failed\n"); + return PTR_ERR(dell_uart_bd); + } + + dell_pdata->dell_uart_bd = dell_uart_bd; + + dell_uart_set_bl_power(dell_uart_bd, FB_BLANK_UNBLANK); + dell_uart_bd->props.brightness = 100; + backlight_update_status(dell_uart_bd); + + return 0; +} + +static void dell_uart_bl_remove(struct acpi_device *dev) +{ + struct dell_uart_backlight *dell_pdata = dev->driver_data; + + backlight_device_unregister(dell_pdata->dell_uart_bd); + kfree_sensitive(dell_pdata); +} + +static int dell_uart_bl_suspend(struct device *dev) +{ + filp_close(ftty, NULL); + return 0; +} + +static int dell_uart_bl_resume(struct device *dev) +{ + ftty = filp_open("/dev/ttyS0", O_RDWR | O_NOCTTY | O_NDELAY, 0); + return 0; +} + +static SIMPLE_DEV_PM_OPS(dell_uart_bl_pm, dell_uart_bl_suspend, dell_uart_bl_resume); + +static const struct acpi_device_id dell_uart_bl_ids[] = { + {"DELL0501", 0}, + {"", 0}, +}; + +static struct acpi_driver dell_uart_backlight_driver = { + .name = "Dell AIO serial backlight", + .ids = dell_uart_bl_ids, + .ops = { + .add = dell_uart_bl_add, + .remove = dell_uart_bl_remove, + }, + .drv.pm = &dell_uart_bl_pm, +}; + +static int __init dell_uart_bl_init(void) +{ + ftty = filp_open("/dev/ttyS0", O_RDWR | O_NOCTTY | O_NDELAY, 0); + if (IS_ERR(ftty)) { + pr_debug("cannot open /dev/ttyS0\n"); + return -EINVAL; + } + + return acpi_bus_register_driver(&dell_uart_backlight_driver); +} + +static void __exit dell_uart_bl_exit(void) +{ + filp_close(ftty, NULL); + + acpi_bus_unregister_driver(&dell_uart_backlight_driver); +} + +module_init(dell_uart_bl_init); +module_exit(dell_uart_bl_exit); +MODULE_DEVICE_TABLE(acpi, dell_uart_bl_ids); +MODULE_DESCRIPTION("Dell AIO Serial Backlight module"); +MODULE_AUTHOR("AceLan Kao "); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell/dell-uart-backlight.h b/drivers/platform/x86/dell/dell-uart-backlight.h new file mode 100644 index 0000000000000..5c732d362d4b9 --- /dev/null +++ b/drivers/platform/x86/dell/dell-uart-backlight.h @@ -0,0 +1,41 @@ +/* + * Dell AIO Serial Backlight Driver + * + * Copyright (C) 2017 AceLan Kao + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _DELL_UART_BACKLIGHT_H_ +#define _DELL_UART_BACKLIGHT_H_ + +enum { + DELL_UART_GET_FIRMWARE_VER, + DELL_UART_GET_BRIGHTNESS, + DELL_UART_SET_BRIGHTNESS, + DELL_UART_SET_BACKLIGHT_POWER, + DELL_UART_GET_DISPLAY_MODE, +}; + +enum { + PC_MODE, + AV_MODE, +}; + +struct dell_uart_bl_cmd { + unsigned char cmd[10]; + unsigned char ret[80]; + unsigned short tx_len; + unsigned short rx_len; +}; + +#endif /* _DELL_UART_BACKLIGHT_H_ */ diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 7457ca2b27a60..9ffbdc988fe50 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -504,6 +504,7 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) struct platform_device *device = context; struct intel_hid_priv *priv = dev_get_drvdata(&device->dev); unsigned long long ev_index; + struct key_entry *ke; int err; /* @@ -545,11 +546,15 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) if (event == 0xc0 || !priv->array) return; - if (!sparse_keymap_entry_from_scancode(priv->array, event)) { + ke = sparse_keymap_entry_from_scancode(priv->array, event); + if (!ke) { dev_info(&device->dev, "unknown event 0x%x\n", event); return; } + if (ke->type == KE_IGNORE) + return; + wakeup: pm_wakeup_hard_event(&device->dev); diff --git a/drivers/platform/x86/intel/int3472/common.h b/drivers/platform/x86/intel/int3472/common.h index 145dec66df64a..ad94a2a8d5848 100644 --- a/drivers/platform/x86/intel/int3472/common.h +++ b/drivers/platform/x86/intel/int3472/common.h @@ -22,6 +22,7 @@ #define INT3472_GPIO_TYPE_POWER_ENABLE 0x0b #define INT3472_GPIO_TYPE_CLK_ENABLE 0x0c #define INT3472_GPIO_TYPE_PRIVACY_LED 0x0d +#define INT3472_GPIO_TYPE_HANDSHAKE 0x12 #define INT3472_PDEV_MAX_NAME_LEN 23 #define INT3472_MAX_SENSOR_GPIOS 3 diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c index 07b302e093407..6612d3589dc39 100644 --- a/drivers/platform/x86/intel/int3472/discrete.c +++ b/drivers/platform/x86/intel/int3472/discrete.c @@ -148,6 +148,10 @@ static void int3472_get_func_and_polarity(u8 type, const char **func, u32 *polar *func = "power-enable"; *polarity = GPIO_ACTIVE_HIGH; break; + case INT3472_GPIO_TYPE_HANDSHAKE: + *func = "handshake"; + *polarity = GPIO_ACTIVE_HIGH; + break; default: *func = "unknown"; *polarity = GPIO_ACTIVE_HIGH; @@ -239,6 +243,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, switch (type) { case INT3472_GPIO_TYPE_RESET: case INT3472_GPIO_TYPE_POWERDOWN: + case INT3472_GPIO_TYPE_HANDSHAKE: ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, func, polarity); if (ret) err_msg = "Failed to map GPIO pin to sensor\n"; diff --git a/drivers/platform/x86/intel/pmc/arl.c b/drivers/platform/x86/intel/pmc/arl.c index 683ae828276b8..34b4cd23bfe59 100644 --- a/drivers/platform/x86/intel/pmc/arl.c +++ b/drivers/platform/x86/intel/pmc/arl.c @@ -673,6 +673,7 @@ static struct pmc_info arl_pmc_info_list[] = { }; #define ARL_NPU_PCI_DEV 0xad1d +#define ARL_GNA_PCI_DEV 0xae4c /* * Set power state of select devices that do not have drivers to D3 * so that they do not block Package C entry. @@ -680,6 +681,7 @@ static struct pmc_info arl_pmc_info_list[] = { static void arl_d3_fixup(void) { pmc_core_set_device_d3(ARL_NPU_PCI_DEV); + pmc_core_set_device_d3(ARL_GNA_PCI_DEV); } static int arl_resume(struct pmc_dev *pmcdev) diff --git a/drivers/platform/x86/intel/pmc/lnl.c b/drivers/platform/x86/intel/pmc/lnl.c index abad17cdd3d78..068d72504683f 100644 --- a/drivers/platform/x86/intel/pmc/lnl.c +++ b/drivers/platform/x86/intel/pmc/lnl.c @@ -13,21 +13,6 @@ #include "core.h" -#define SOCM_LPM_REQ_GUID 0x11594920 - -#define PMC_DEVID_SOCM 0xa87f - -static const u8 LNL_LPM_REG_INDEX[] = {0, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20}; - -static struct pmc_info lnl_pmc_info_list[] = { - { - .guid = SOCM_LPM_REQ_GUID, - .devid = PMC_DEVID_SOCM, - .map = &lnl_socm_reg_map, - }, - {} -}; - const struct pmc_bit_map lnl_ltr_show_map[] = { {"SOUTHPORT_A", CNP_PMC_LTR_SPA}, {"SOUTHPORT_B", CNP_PMC_LTR_SPB}, @@ -490,7 +475,6 @@ const struct pmc_reg_map lnl_socm_reg_map = { .lpm_sts = lnl_lpm_maps, .lpm_status_offset = MTL_LPM_STATUS_OFFSET, .lpm_live_status_offset = MTL_LPM_LIVE_STATUS_OFFSET, - .lpm_reg_index = LNL_LPM_REG_INDEX, }; #define LNL_NPU_PCI_DEV 0x643e @@ -517,33 +501,19 @@ static int lnl_resume(struct pmc_dev *pmcdev) int lnl_core_init(struct pmc_dev *pmcdev) { int ret; - int func = 2; - bool ssram_init = true; struct pmc *pmc = pmcdev->pmcs[PMC_IDX_SOC]; lnl_d3_fixup(); pmcdev->suspend = cnl_suspend; pmcdev->resume = lnl_resume; - pmcdev->regmap_list = lnl_pmc_info_list; - ret = pmc_core_ssram_init(pmcdev, func); - - /* If regbase not assigned, set map and discover using legacy method */ - if (ret) { - ssram_init = false; - pmc->map = &lnl_socm_reg_map; - ret = get_primary_reg_base(pmc); - if (ret) - return ret; - } - pmc_core_get_low_power_modes(pmcdev); + pmc->map = &lnl_socm_reg_map; + ret = get_primary_reg_base(pmc); + if (ret) + return ret; - if (ssram_init) { - ret = pmc_core_ssram_get_lpm_reqs(pmcdev); - if (ret) - return ret; - } + pmc_core_get_low_power_modes(pmcdev); return 0; } diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 08df9494603c5..1accdaaf282c5 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -719,7 +719,9 @@ static struct miscdevice isst_if_char_driver = { }; static const struct x86_cpu_id hpm_cpu_ids[] = { + X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, NULL), X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, NULL), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, NULL), X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, NULL), {} }; diff --git a/drivers/platform/x86/intel/tpmi.c b/drivers/platform/x86/intel/tpmi.c index e73cdea67fff8..003e765dedea1 100644 --- a/drivers/platform/x86/intel/tpmi.c +++ b/drivers/platform/x86/intel/tpmi.c @@ -96,7 +96,7 @@ struct intel_tpmi_pfs_entry { */ struct intel_tpmi_pm_feature { struct intel_tpmi_pfs_entry pfs_header; - unsigned int vsec_offset; + u64 vsec_offset; struct intel_vsec_device *vsec_dev; }; @@ -376,7 +376,7 @@ static int tpmi_pfs_dbg_show(struct seq_file *s, void *unused) read_blocked = feature_state.read_blocked ? 'Y' : 'N'; write_blocked = feature_state.write_blocked ? 'Y' : 'N'; } - seq_printf(s, "0x%02x\t\t0x%02x\t\t0x%04x\t\t0x%04x\t\t0x%02x\t\t0x%08x\t%c\t%c\t\t%c\t\t%c\n", + seq_printf(s, "0x%02x\t\t0x%02x\t\t0x%04x\t\t0x%04x\t\t0x%02x\t\t0x%016llx\t%c\t%c\t\t%c\t\t%c\n", pfs->pfs_header.tpmi_id, pfs->pfs_header.num_entries, pfs->pfs_header.entry_size, pfs->pfs_header.cap_offset, pfs->pfs_header.attribute, pfs->vsec_offset, locked, disabled, @@ -395,7 +395,8 @@ static int tpmi_mem_dump_show(struct seq_file *s, void *unused) struct intel_tpmi_pm_feature *pfs = s->private; int count, ret = 0; void __iomem *mem; - u32 off, size; + u32 size; + u64 off; u8 *buffer; size = TPMI_GET_SINGLE_ENTRY_SIZE(pfs); @@ -411,7 +412,7 @@ static int tpmi_mem_dump_show(struct seq_file *s, void *unused) mutex_lock(&tpmi_dev_lock); for (count = 0; count < pfs->pfs_header.num_entries; ++count) { - seq_printf(s, "TPMI Instance:%d offset:0x%x\n", count, off); + seq_printf(s, "TPMI Instance:%d offset:0x%llx\n", count, off); mem = ioremap(off, size); if (!mem) { @@ -762,8 +763,11 @@ static int intel_vsec_tpmi_init(struct auxiliary_device *auxdev) * when actual device nodes created outside this * loop via tpmi_create_devices(). */ - if (pfs->pfs_header.tpmi_id == TPMI_INFO_ID) - tpmi_process_info(tpmi_info, pfs); + if (pfs->pfs_header.tpmi_id == TPMI_INFO_ID) { + ret = tpmi_process_info(tpmi_info, pfs); + if (ret) + return ret; + } if (pfs->pfs_header.tpmi_id == TPMI_CONTROL_ID) tpmi_set_control_base(auxdev, tpmi_info, pfs); diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c index bd75d61ff8a66..587437211d722 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c @@ -240,6 +240,7 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_ bool read_blocked = 0, write_blocked = 0; struct intel_tpmi_plat_info *plat_info; struct tpmi_uncore_struct *tpmi_uncore; + bool uncore_sysfs_added = false; int ret, i, pkg = 0; int num_resources; @@ -384,9 +385,15 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_ } /* Point to next cluster offset */ cluster_offset >>= UNCORE_MAX_CLUSTER_PER_DOMAIN; + uncore_sysfs_added = true; } } + if (!uncore_sysfs_added) { + ret = -ENODEV; + goto remove_clusters; + } + auxiliary_set_drvdata(auxdev, tpmi_uncore); tpmi_uncore->root_cluster.root_domain = true; diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 084c355c86f5f..5d13452bb947a 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -136,8 +136,6 @@ static int intel_vbtn_input_setup(struct platform_device *device) priv->switches_dev->id.bustype = BUS_HOST; if (priv->has_switches) { - detect_tablet_mode(&device->dev); - ret = input_register_device(priv->switches_dev); if (ret) return ret; @@ -316,6 +314,9 @@ static int intel_vbtn_probe(struct platform_device *device) if (ACPI_FAILURE(status)) dev_err(&device->dev, "Error VBDL failed with ACPI status %d\n", status); } + // Check switches after buttons since VBDL may have side effects. + if (has_switches) + detect_tablet_mode(&device->dev); device_init_wakeup(&device->dev, true); /* diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c index ba38649cc1428..0458e36cb7a60 100644 --- a/drivers/platform/x86/intel_ips.c +++ b/drivers/platform/x86/intel_ips.c @@ -1415,6 +1415,14 @@ static const struct dmi_system_id ips_blacklist[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook"), }, }, + { + .callback = ips_blacklist_callback, + .ident = "G60JX", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "G60JX"), + }, + }, { } /* terminating entry */ }; diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index 3d66e1d4eb1f5..1ac30034f3e59 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -56,12 +56,9 @@ static int p2sb_get_devfn(unsigned int *devfn) return 0; } -static bool p2sb_valid_resource(struct resource *res) +static bool p2sb_valid_resource(const struct resource *res) { - if (res->flags) - return true; - - return false; + return res->flags & ~IORESOURCE_UNSET; } /* Copy resource from the first BAR of the device in question */ @@ -220,16 +217,20 @@ EXPORT_SYMBOL_GPL(p2sb_bar); static int __init p2sb_fs_init(void) { - p2sb_cache_resources(); - return 0; + return p2sb_cache_resources(); } /* - * pci_rescan_remove_lock to avoid access to unhidden P2SB devices can - * not be locked in sysfs pci bus rescan path because of deadlock. To - * avoid the deadlock, access to P2SB devices with the lock at an early - * step in kernel initialization and cache required resources. This - * should happen after subsys_initcall which initializes PCI subsystem - * and before device_initcall which requires P2SB resources. + * pci_rescan_remove_lock() can not be locked in sysfs PCI bus rescan path + * because of deadlock. To avoid the deadlock, access P2SB devices with the lock + * at an early step in kernel initialization and cache required resources. + * + * We want to run as early as possible. If the P2SB was assigned a bad BAR, + * we'll need to wait on pcibios_assign_resources() to fix it. So, our list of + * initcall dependencies looks something like this: + * + * ... + * subsys_initcall (pci_subsys_init) + * fs_initcall (pcibios_assign_resources) */ -fs_initcall(p2sb_fs_init); +fs_initcall_sync(p2sb_fs_init); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 5ecd9d33250d7..3dd49dd772662 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -3042,10 +3042,9 @@ static void tpacpi_send_radiosw_update(void) static void hotkey_exit(void) { -#ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL mutex_lock(&hotkey_mutex); +#ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL hotkey_poll_stop_sync(); - mutex_unlock(&hotkey_mutex); #endif dbg_printk(TPACPI_DBG_EXIT | TPACPI_DBG_HKEY, "restoring original HKEY status and mask\n"); @@ -3055,6 +3054,8 @@ static void hotkey_exit(void) hotkey_mask_set(hotkey_orig_mask)) | hotkey_status_set(false)) != 0) pr_err("failed to restore hot key mask to BIOS defaults\n"); + + mutex_unlock(&hotkey_mutex); } static void __init hotkey_unmap(const unsigned int scancode) diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index 291f14ef67024..2a5a651235fe6 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -57,6 +57,11 @@ module_param(turn_on_panel_on_resume, int, 0644); MODULE_PARM_DESC(turn_on_panel_on_resume, "Call HCI_PANEL_POWER_ON on resume (-1 = auto, 0 = no, 1 = yes"); +static int hci_hotkey_quickstart = -1; +module_param(hci_hotkey_quickstart, int, 0644); +MODULE_PARM_DESC(hci_hotkey_quickstart, + "Call HCI_HOTKEY_EVENT with value 0x5 for quickstart button support (-1 = auto, 0 = no, 1 = yes"); + #define TOSHIBA_WMI_EVENT_GUID "59142400-C6A3-40FA-BADB-8A2652834100" /* Scan code for Fn key on TOS1900 models */ @@ -136,6 +141,7 @@ MODULE_PARM_DESC(turn_on_panel_on_resume, #define HCI_ACCEL_MASK 0x7fff #define HCI_ACCEL_DIRECTION_MASK 0x8000 #define HCI_HOTKEY_DISABLE 0x0b +#define HCI_HOTKEY_ENABLE_QUICKSTART 0x05 #define HCI_HOTKEY_ENABLE 0x09 #define HCI_HOTKEY_SPECIAL_FUNCTIONS 0x10 #define HCI_LCD_BRIGHTNESS_BITS 3 @@ -2730,10 +2736,15 @@ static int toshiba_acpi_enable_hotkeys(struct toshiba_acpi_dev *dev) return -ENODEV; /* + * Enable quickstart buttons if supported. + * * Enable the "Special Functions" mode only if they are * supported and if they are activated. */ - if (dev->kbd_function_keys_supported && dev->special_functions) + if (hci_hotkey_quickstart) + result = hci_write(dev, HCI_HOTKEY_EVENT, + HCI_HOTKEY_ENABLE_QUICKSTART); + else if (dev->kbd_function_keys_supported && dev->special_functions) result = hci_write(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_SPECIAL_FUNCTIONS); else @@ -3257,7 +3268,14 @@ static const char *find_hci_method(acpi_handle handle) * works. toshiba_acpi_resume() uses HCI_PANEL_POWER_ON to avoid changing * the configured brightness level. */ -static const struct dmi_system_id turn_on_panel_on_resume_dmi_ids[] = { +#define QUIRK_TURN_ON_PANEL_ON_RESUME BIT(0) +/* + * Some Toshibas use "quickstart" keys. On these, HCI_HOTKEY_EVENT must use + * the value HCI_HOTKEY_ENABLE_QUICKSTART. + */ +#define QUIRK_HCI_HOTKEY_QUICKSTART BIT(1) + +static const struct dmi_system_id toshiba_dmi_quirks[] = { { /* Toshiba Portégé R700 */ /* https://bugzilla.kernel.org/show_bug.cgi?id=21012 */ @@ -3265,6 +3283,7 @@ static const struct dmi_system_id turn_on_panel_on_resume_dmi_ids[] = { DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE R700"), }, + .driver_data = (void *)QUIRK_TURN_ON_PANEL_ON_RESUME, }, { /* Toshiba Satellite/Portégé R830 */ @@ -3274,6 +3293,7 @@ static const struct dmi_system_id turn_on_panel_on_resume_dmi_ids[] = { DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), DMI_MATCH(DMI_PRODUCT_NAME, "R830"), }, + .driver_data = (void *)QUIRK_TURN_ON_PANEL_ON_RESUME, }, { /* Toshiba Satellite/Portégé Z830 */ @@ -3281,6 +3301,7 @@ static const struct dmi_system_id turn_on_panel_on_resume_dmi_ids[] = { DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), DMI_MATCH(DMI_PRODUCT_NAME, "Z830"), }, + .driver_data = (void *)(QUIRK_TURN_ON_PANEL_ON_RESUME | QUIRK_HCI_HOTKEY_QUICKSTART), }, }; @@ -3289,6 +3310,8 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev) struct toshiba_acpi_dev *dev; const char *hci_method; u32 dummy; + const struct dmi_system_id *dmi_id; + long quirks = 0; int ret = 0; if (toshiba_acpi) @@ -3441,8 +3464,15 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev) } #endif + dmi_id = dmi_first_match(toshiba_dmi_quirks); + if (dmi_id) + quirks = (long)dmi_id->driver_data; + if (turn_on_panel_on_resume == -1) - turn_on_panel_on_resume = dmi_check_system(turn_on_panel_on_resume_dmi_ids); + turn_on_panel_on_resume = !!(quirks & QUIRK_TURN_ON_PANEL_ON_RESUME); + + if (hci_hotkey_quickstart == -1) + hci_hotkey_quickstart = !!(quirks & QUIRK_HCI_HOTKEY_QUICKSTART); toshiba_wwan_available(dev); if (dev->wwan_supported) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 975cf24ae359a..c6a10ec2c83f6 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -1217,6 +1217,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.D86JLBNR"), }, }, + { + /* Chuwi Vi8 dual-boot (CWI506) */ + .driver_data = (void *)&chuwi_vi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "i86"), + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI2.D86JHBNR02"), + }, + }, { /* Chuwi Vi8 Plus (CWI519) */ .driver_data = (void *)&chuwi_vi8_plus_data, diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index a3415f1c0b5f8..6559bb4ea7305 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -278,25 +278,25 @@ static void x86_android_tablet_remove(struct platform_device *pdev) { int i; - for (i = 0; i < serdev_count; i++) { + for (i = serdev_count - 1; i >= 0; i--) { if (serdevs[i]) serdev_device_remove(serdevs[i]); } kfree(serdevs); - for (i = 0; i < pdev_count; i++) + for (i = pdev_count - 1; i >= 0; i--) platform_device_unregister(pdevs[i]); kfree(pdevs); kfree(buttons); - for (i = 0; i < spi_dev_count; i++) + for (i = spi_dev_count - 1; i >= 0; i--) spi_unregister_device(spi_devs[i]); kfree(spi_devs); - for (i = 0; i < i2c_client_count; i++) + for (i = i2c_client_count - 1; i >= 0; i--) i2c_unregister_device(i2c_clients[i]); kfree(i2c_clients); diff --git a/drivers/platform/x86/x86-android-tablets/dmi.c b/drivers/platform/x86/x86-android-tablets/dmi.c index 5d6c12494f082..141a2d25e83be 100644 --- a/drivers/platform/x86/x86-android-tablets/dmi.c +++ b/drivers/platform/x86/x86-android-tablets/dmi.c @@ -104,6 +104,24 @@ const struct dmi_system_id x86_android_tablet_ids[] __initconst = { }, .driver_data = (void *)&lenovo_yogabook_x91_info, }, + { + /* + * Lenovo Yoga Tablet 2 Pro 1380F/L (13") This has more or less + * the same BIOS as the 830F/L or 1050F/L (8" and 10") below, + * but unlike the 8" / 10" models which share the same mainboard + * this model has a different mainboard. + * This match for the 13" model MUST come before the 8" + 10" + * match since that one will also match the 13" model! + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corp."), + DMI_MATCH(DMI_PRODUCT_NAME, "VALLEYVIEW C0 PLATFORM"), + DMI_MATCH(DMI_BOARD_NAME, "BYT-T FFD8"), + /* Full match so as to NOT match the 830/1050 BIOS */ + DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21.X64.0005.R00.1504101516"), + }, + .driver_data = (void *)&lenovo_yoga_tab2_1380_info, + }, { /* * Lenovo Yoga Tablet 2 830F/L or 1050F/L (The 8" and 10" diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c index c297391955adb..16fa04d604a09 100644 --- a/drivers/platform/x86/x86-android-tablets/lenovo.c +++ b/drivers/platform/x86/x86-android-tablets/lenovo.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -565,6 +566,221 @@ static void lenovo_yoga_tab2_830_1050_exit(void) } } +/* + * Lenovo Yoga Tablet 2 Pro 1380F/L + * + * The Lenovo Yoga Tablet 2 Pro 1380F/L mostly has the same design as the 830F/L + * and the 1050F/L so this re-uses some of the handling for that from above. + */ +static const char * const lc824206xa_chg_det_psy[] = { "lc824206xa-charger-detect" }; + +static const struct property_entry lenovo_yoga_tab2_1380_bq24190_props[] = { + PROPERTY_ENTRY_STRING_ARRAY("supplied-from", lc824206xa_chg_det_psy), + PROPERTY_ENTRY_REF("monitored-battery", &generic_lipo_hv_4v35_battery_node), + PROPERTY_ENTRY_BOOL("omit-battery-class"), + PROPERTY_ENTRY_BOOL("disable-reset"), + { } +}; + +static const struct software_node lenovo_yoga_tab2_1380_bq24190_node = { + .properties = lenovo_yoga_tab2_1380_bq24190_props, +}; + +/* For enabling the bq24190 5V boost based on id-pin */ +static struct regulator_consumer_supply lc824206xa_consumer = { + .supply = "vbus", + .dev_name = "i2c-lc824206xa", +}; + +static const struct regulator_init_data lenovo_yoga_tab2_1380_bq24190_vbus_init_data = { + .constraints = { + .name = "bq24190_vbus", + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + }, + .consumer_supplies = &lc824206xa_consumer, + .num_consumer_supplies = 1, +}; + +struct bq24190_platform_data lenovo_yoga_tab2_1380_bq24190_pdata = { + .regulator_init_data = &lenovo_yoga_tab2_1380_bq24190_vbus_init_data, +}; + +static const struct property_entry lenovo_yoga_tab2_1380_lc824206xa_props[] = { + PROPERTY_ENTRY_BOOL("onnn,enable-miclr-for-dcp"), + { } +}; + +static const struct software_node lenovo_yoga_tab2_1380_lc824206xa_node = { + .properties = lenovo_yoga_tab2_1380_lc824206xa_props, +}; + +static const char * const lenovo_yoga_tab2_1380_lms303d_mount_matrix[] = { + "0", "-1", "0", + "-1", "0", "0", + "0", "0", "1" +}; + +static const struct property_entry lenovo_yoga_tab2_1380_lms303d_props[] = { + PROPERTY_ENTRY_STRING_ARRAY("mount-matrix", lenovo_yoga_tab2_1380_lms303d_mount_matrix), + { } +}; + +static const struct software_node lenovo_yoga_tab2_1380_lms303d_node = { + .properties = lenovo_yoga_tab2_1380_lms303d_props, +}; + +static const struct x86_i2c_client_info lenovo_yoga_tab2_1380_i2c_clients[] __initconst = { + { + /* BQ27541 fuel-gauge */ + .board_info = { + .type = "bq27541", + .addr = 0x55, + .dev_name = "bq27541", + .swnode = &fg_bq24190_supply_node, + }, + .adapter_path = "\\_SB_.I2C1", + }, { + /* bq24292i battery charger */ + .board_info = { + .type = "bq24190", + .addr = 0x6b, + .dev_name = "bq24292i", + .swnode = &lenovo_yoga_tab2_1380_bq24190_node, + .platform_data = &lenovo_yoga_tab2_1380_bq24190_pdata, + }, + .adapter_path = "\\_SB_.I2C1", + .irq_data = { + .type = X86_ACPI_IRQ_TYPE_GPIOINT, + .chip = "INT33FC:02", + .index = 2, + .trigger = ACPI_EDGE_SENSITIVE, + .polarity = ACPI_ACTIVE_HIGH, + .con_id = "bq24292i_irq", + }, + }, { + /* LP8557 Backlight controller */ + .board_info = { + .type = "lp8557", + .addr = 0x2c, + .dev_name = "lp8557", + .platform_data = &lenovo_lp8557_pwm_and_reg_pdata, + }, + .adapter_path = "\\_SB_.I2C3", + }, { + /* LC824206XA Micro USB Switch */ + .board_info = { + .type = "lc824206xa", + .addr = 0x48, + .dev_name = "lc824206xa", + .swnode = &lenovo_yoga_tab2_1380_lc824206xa_node, + }, + .adapter_path = "\\_SB_.I2C3", + .irq_data = { + .type = X86_ACPI_IRQ_TYPE_GPIOINT, + .chip = "INT33FC:02", + .index = 1, + .trigger = ACPI_LEVEL_SENSITIVE, + .polarity = ACPI_ACTIVE_LOW, + .con_id = "lc824206xa_irq", + }, + }, { + /* AL3320A ambient light sensor */ + .board_info = { + .type = "al3320a", + .addr = 0x1c, + .dev_name = "al3320a", + }, + .adapter_path = "\\_SB_.I2C5", + }, { + /* LSM303DA accelerometer + magnetometer */ + .board_info = { + .type = "lsm303d", + .addr = 0x1d, + .dev_name = "lsm303d", + .swnode = &lenovo_yoga_tab2_1380_lms303d_node, + }, + .adapter_path = "\\_SB_.I2C5", + }, { + /* Synaptics RMI touchscreen */ + .board_info = { + .type = "rmi4_i2c", + .addr = 0x38, + .dev_name = "rmi4_i2c", + .platform_data = &lenovo_yoga_tab2_830_1050_rmi_pdata, + }, + .adapter_path = "\\_SB_.I2C6", + .irq_data = { + .type = X86_ACPI_IRQ_TYPE_APIC, + .index = 0x45, + .trigger = ACPI_EDGE_SENSITIVE, + .polarity = ACPI_ACTIVE_HIGH, + }, + } +}; + +static const struct platform_device_info lenovo_yoga_tab2_1380_pdevs[] __initconst = { + { + /* For the Tablet 2 Pro 1380's custom fast charging driver */ + .name = "lenovo-yoga-tab2-pro-1380-fastcharger", + .id = PLATFORM_DEVID_NONE, + }, +}; + +const char * const lenovo_yoga_tab2_1380_modules[] __initconst = { + "bq24190_charger", /* For the Vbus regulator for lc824206xa */ + NULL +}; + +static int __init lenovo_yoga_tab2_1380_init(void) +{ + int ret; + + /* To verify that the DMI matching works vs the 830 / 1050 models */ + pr_info("detected Lenovo Yoga Tablet 2 Pro 1380F/L\n"); + + ret = lenovo_yoga_tab2_830_1050_init_codec(); + if (ret) + return ret; + + /* SYS_OFF_PRIO_FIRMWARE + 1 so that it runs before acpi_power_off */ + lenovo_yoga_tab2_830_1050_sys_off_handler = + register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, SYS_OFF_PRIO_FIRMWARE + 1, + lenovo_yoga_tab2_830_1050_power_off, NULL); + if (IS_ERR(lenovo_yoga_tab2_830_1050_sys_off_handler)) + return PTR_ERR(lenovo_yoga_tab2_830_1050_sys_off_handler); + + return 0; +} + +static struct gpiod_lookup_table lenovo_yoga_tab2_1380_fc_gpios = { + .dev_id = "serial0-0", + .table = { + GPIO_LOOKUP("INT33FC:00", 57, "uart3_txd", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("INT33FC:00", 61, "uart3_rxd", GPIO_ACTIVE_HIGH), + { } + }, +}; + +static struct gpiod_lookup_table * const lenovo_yoga_tab2_1380_gpios[] = { + &lenovo_yoga_tab2_830_1050_codec_gpios, + &lenovo_yoga_tab2_1380_fc_gpios, + NULL +}; + +const struct x86_dev_info lenovo_yoga_tab2_1380_info __initconst = { + .i2c_client_info = lenovo_yoga_tab2_1380_i2c_clients, + .i2c_client_count = ARRAY_SIZE(lenovo_yoga_tab2_1380_i2c_clients), + .pdev_info = lenovo_yoga_tab2_1380_pdevs, + .pdev_count = ARRAY_SIZE(lenovo_yoga_tab2_1380_pdevs), + .gpio_button = &lenovo_yoga_tab2_830_1050_lid, + .gpio_button_count = 1, + .gpiod_lookup_tables = lenovo_yoga_tab2_1380_gpios, + .bat_swnode = &generic_lipo_hv_4v35_battery_node, + .modules = lenovo_yoga_tab2_1380_modules, + .init = lenovo_yoga_tab2_1380_init, + .exit = lenovo_yoga_tab2_830_1050_exit, +}; + /* Lenovo Yoga Tab 3 Pro YT3-X90F */ /* diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h index 468993edfeee2..821dc094b0254 100644 --- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h +++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h @@ -112,6 +112,7 @@ extern const struct x86_dev_info czc_p10t; extern const struct x86_dev_info lenovo_yogabook_x90_info; extern const struct x86_dev_info lenovo_yogabook_x91_info; extern const struct x86_dev_info lenovo_yoga_tab2_830_1050_info; +extern const struct x86_dev_info lenovo_yoga_tab2_1380_info; extern const struct x86_dev_info lenovo_yt3_info; extern const struct x86_dev_info medion_lifetab_s10346_info; extern const struct x86_dev_info nextbook_ares8_info; diff --git a/drivers/platform/x86/xiaomi-wmi.c b/drivers/platform/x86/xiaomi-wmi.c index 54a2546bb93bf..be80f0bda9484 100644 --- a/drivers/platform/x86/xiaomi-wmi.c +++ b/drivers/platform/x86/xiaomi-wmi.c @@ -2,8 +2,10 @@ /* WMI driver for Xiaomi Laptops */ #include +#include #include #include +#include #include #include @@ -20,12 +22,21 @@ struct xiaomi_wmi { struct input_dev *input_dev; + struct mutex key_lock; /* Protects the key event sequence */ unsigned int key_code; }; +static void xiaomi_mutex_destroy(void *data) +{ + struct mutex *lock = data; + + mutex_destroy(lock); +} + static int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) { struct xiaomi_wmi *data; + int ret; if (wdev == NULL || context == NULL) return -EINVAL; @@ -35,6 +46,11 @@ static int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) return -ENOMEM; dev_set_drvdata(&wdev->dev, data); + mutex_init(&data->key_lock); + ret = devm_add_action_or_reset(&wdev->dev, xiaomi_mutex_destroy, &data->key_lock); + if (ret < 0) + return ret; + data->input_dev = devm_input_allocate_device(&wdev->dev); if (data->input_dev == NULL) return -ENOMEM; @@ -59,10 +75,12 @@ static void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy) if (data == NULL) return; + mutex_lock(&data->key_lock); input_report_key(data->input_dev, data->key_code, 1); input_sync(data->input_dev); input_report_key(data->input_dev, data->key_code, 0); input_sync(data->input_dev); + mutex_unlock(&data->key_lock); } static const struct wmi_device_id xiaomi_wmi_id_table[] = { diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 18e232b5ed53d..755e4d0c63224 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -184,6 +184,16 @@ static struct generic_pm_domain *dev_to_genpd(struct device *dev) return pd_to_genpd(dev->pm_domain); } +struct device *dev_to_genpd_dev(struct device *dev) +{ + struct generic_pm_domain *genpd = dev_to_genpd(dev); + + if (IS_ERR(genpd)) + return ERR_CAST(genpd); + + return &genpd->dev; +} + static int genpd_stop_dev(const struct generic_pm_domain *genpd, struct device *dev) { diff --git a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c index e3203eb6a0229..a56f7f92d0915 100644 --- a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c @@ -55,7 +55,7 @@ struct imx8mp_blk_ctrl_domain_data { const char *gpc_name; }; -#define DOMAIN_MAX_CLKS 2 +#define DOMAIN_MAX_CLKS 3 #define DOMAIN_MAX_PATHS 3 struct imx8mp_blk_ctrl_domain { @@ -457,8 +457,8 @@ static const struct imx8mp_blk_ctrl_domain_data imx8mp_hdmi_domain_data[] = { }, [IMX8MP_HDMIBLK_PD_LCDIF] = { .name = "hdmiblk-lcdif", - .clk_names = (const char *[]){ "axi", "apb" }, - .num_clks = 2, + .clk_names = (const char *[]){ "axi", "apb", "fdcc" }, + .num_clks = 3, .gpc_name = "lcdif", .path_names = (const char *[]){"lcdif-hdmi"}, .num_paths = 1, @@ -483,8 +483,8 @@ static const struct imx8mp_blk_ctrl_domain_data imx8mp_hdmi_domain_data[] = { }, [IMX8MP_HDMIBLK_PD_HDMI_TX] = { .name = "hdmiblk-hdmi-tx", - .clk_names = (const char *[]){ "apb", "ref_266m" }, - .num_clks = 2, + .clk_names = (const char *[]){ "apb", "ref_266m", "fdcc" }, + .num_clks = 3, .gpc_name = "hdmi-tx", }, [IMX8MP_HDMIBLK_PD_HDMI_TX_PHY] = { diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c index 47df910645f66..de9121ef4216b 100644 --- a/drivers/pmdomain/qcom/rpmhpd.c +++ b/drivers/pmdomain/qcom/rpmhpd.c @@ -217,7 +217,6 @@ static struct rpmhpd *sa8540p_rpmhpds[] = { [SC8280XP_CX] = &cx, [SC8280XP_CX_AO] = &cx_ao, [SC8280XP_EBI] = &ebi, - [SC8280XP_GFX] = &gfx, [SC8280XP_LCX] = &lcx, [SC8280XP_LMX] = &lmx, [SC8280XP_MMCX] = &mmcx, diff --git a/drivers/pmdomain/ti/omap_prm.c b/drivers/pmdomain/ti/omap_prm.c index c2feae3a634ca..b8ceb3c2b81c2 100644 --- a/drivers/pmdomain/ti/omap_prm.c +++ b/drivers/pmdomain/ti/omap_prm.c @@ -695,6 +695,8 @@ static int omap_prm_domain_init(struct device *dev, struct omap_prm *prm) data = prm->data; name = devm_kasprintf(dev, GFP_KERNEL, "prm_%s", data->name); + if (!name) + return -ENOMEM; prmd->dev = dev; prmd->prm = prm; diff --git a/drivers/pmdomain/ti/ti_sci_pm_domains.c b/drivers/pmdomain/ti/ti_sci_pm_domains.c index c091d569ecd5f..9e1efe903730e 100644 --- a/drivers/pmdomain/ti/ti_sci_pm_domains.c +++ b/drivers/pmdomain/ti/ti_sci_pm_domains.c @@ -114,6 +114,18 @@ static const struct of_device_id ti_sci_pm_domain_matches[] = { }; MODULE_DEVICE_TABLE(of, ti_sci_pm_domain_matches); +static bool ti_sci_pm_idx_exists(struct ti_sci_genpd_provider *pd_provider, u32 idx) +{ + struct ti_sci_pm_domain *pd; + + list_for_each_entry(pd, &pd_provider->pd_list, node) { + if (pd->idx == idx) + return true; + } + + return false; +} + static int ti_sci_pm_domain_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -149,8 +161,14 @@ static int ti_sci_pm_domain_probe(struct platform_device *pdev) break; if (args.args_count >= 1 && args.np == dev->of_node) { - if (args.args[0] > max_id) + if (args.args[0] > max_id) { max_id = args.args[0]; + } else { + if (ti_sci_pm_idx_exists(pd_provider, args.args[0])) { + index++; + continue; + } + } pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL); if (!pd) { diff --git a/drivers/pnp/isapnp/core.c b/drivers/pnp/isapnp/core.c index c43d8ad025294..ccab0abcfcd0f 100644 --- a/drivers/pnp/isapnp/core.c +++ b/drivers/pnp/isapnp/core.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include "../base.h" @@ -950,7 +951,7 @@ struct pnp_protocol isapnp_protocol = { .disable = isapnp_disable_resources, }; -static int __init isapnp_init(void) +static int __init real_isapnp_init(void) { int cards; struct pnp_card *card; @@ -1044,6 +1045,16 @@ static int __init isapnp_init(void) return 0; } +static void __init async_isapnp_init(void *unused, async_cookie_t cookie) +{ + (void)real_isapnp_init(); +} + +static int __init isapnp_init(void) +{ + async_schedule(async_isapnp_init, NULL); + return 0; +} device_initcall(isapnp_init); /* format is: noisapnp */ diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c index b6c96376776a9..8008e31c0c098 100644 --- a/drivers/power/supply/cros_usbpd-charger.c +++ b/drivers/power/supply/cros_usbpd-charger.c @@ -5,6 +5,7 @@ * Copyright (c) 2014 - 2018 Google, Inc */ +#include #include #include #include @@ -711,16 +712,22 @@ static int cros_usbpd_charger_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(cros_usbpd_charger_pm_ops, NULL, cros_usbpd_charger_resume); +static const struct platform_device_id cros_usbpd_charger_id[] = { + { DRV_NAME, 0 }, + {} +}; +MODULE_DEVICE_TABLE(platform, cros_usbpd_charger_id); + static struct platform_driver cros_usbpd_charger_driver = { .driver = { .name = DRV_NAME, .pm = &cros_usbpd_charger_pm_ops, }, - .probe = cros_usbpd_charger_probe + .probe = cros_usbpd_charger_probe, + .id_table = cros_usbpd_charger_id, }; module_platform_driver(cros_usbpd_charger_driver); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ChromeOS EC USBPD charger"); -MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/power/supply/mm8013.c b/drivers/power/supply/mm8013.c index caa272b035649..20c1651ca38e0 100644 --- a/drivers/power/supply/mm8013.c +++ b/drivers/power/supply/mm8013.c @@ -71,7 +71,6 @@ static int mm8013_checkdevice(struct mm8013_chip *chip) static enum power_supply_property mm8013_battery_props[] = { POWER_SUPPLY_PROP_CAPACITY, - POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR, POWER_SUPPLY_PROP_CHARGE_FULL, POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, POWER_SUPPLY_PROP_CHARGE_NOW, @@ -103,16 +102,6 @@ static int mm8013_get_property(struct power_supply *psy, val->intval = regval; break; - case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR: - ret = regmap_read(chip->regmap, REG_FLAGS, ®val); - if (ret < 0) - return ret; - - if (regval & MM8013_FLAG_CHG_INH) - val->intval = POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE; - else - val->intval = POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO; - break; case POWER_SUPPLY_PROP_CHARGE_FULL: ret = regmap_read(chip->regmap, REG_FULL_CHARGE_CAPACITY, ®val); if (ret < 0) @@ -187,6 +176,8 @@ static int mm8013_get_property(struct power_supply *psy, if (regval & MM8013_FLAG_DSG) val->intval = POWER_SUPPLY_STATUS_DISCHARGING; + else if (regval & MM8013_FLAG_CHG_INH) + val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING; else if (regval & MM8013_FLAG_CHG) val->intval = POWER_SUPPLY_STATUS_CHARGING; else if (regval & MM8013_FLAG_FC) diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index 1305cba61edd4..aca123783efcc 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -588,7 +588,7 @@ static const struct regulator_ops mt6360_chg_otg_ops = { }; static const struct regulator_desc mt6360_otg_rdesc = { - .of_match = "usb-otg-vbus", + .of_match = "usb-otg-vbus-regulator", .name = "usb-otg-vbus", .ops = &mt6360_chg_otg_ops, .owner = THIS_MODULE, diff --git a/drivers/power/supply/rt9455_charger.c b/drivers/power/supply/rt9455_charger.c index c345a77f9f78c..e4dbacd50a437 100644 --- a/drivers/power/supply/rt9455_charger.c +++ b/drivers/power/supply/rt9455_charger.c @@ -192,6 +192,7 @@ static const int rt9455_voreg_values[] = { 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000 }; +#if IS_ENABLED(CONFIG_USB_PHY) /* * When the charger is in boost mode, REG02[7:2] represent boost output * voltage. @@ -207,6 +208,7 @@ static const int rt9455_boost_voltage_values[] = { 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, }; +#endif /* REG07[3:0] (VMREG) in uV */ static const int rt9455_vmreg_values[] = { diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 9193c3b8edebe..ae7ee611978ba 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -219,7 +219,7 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent) ret = freq_qos_add_request(&policy->constraints, &dtpm_cpu->qos_req, FREQ_QOS_MAX, pd->table[pd->nr_perf_states - 1].frequency); - if (ret) + if (ret < 0) goto out_dtpm_unregister; cpufreq_cpu_put(policy); diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 2feed036c1cd4..aa627a6b12a4e 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -5,6 +5,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -759,6 +760,11 @@ static int rapl_config(struct rapl_package *rp) default: return -EINVAL; } + + /* defaults_msr can be NULL on unsupported platforms */ + if (!rp->priv->defaults || !rp->priv->rpi) + return -ENODEV; + return 0; } @@ -1256,6 +1262,8 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &rapl_defaults_spr_server), + X86_MATCH_INTEL_FAM6_MODEL(LUNARLAKE_M, &rapl_defaults_core), + X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(LAKEFIELD, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &rapl_defaults_byt), @@ -1499,7 +1507,7 @@ static int rapl_detect_domains(struct rapl_package *rp) } /* called from CPU hotplug notifier, hotplug lock held */ -void rapl_remove_package(struct rapl_package *rp) +void rapl_remove_package_cpuslocked(struct rapl_package *rp) { struct rapl_domain *rd, *rd_package = NULL; @@ -1528,10 +1536,18 @@ void rapl_remove_package(struct rapl_package *rp) list_del(&rp->plist); kfree(rp); } +EXPORT_SYMBOL_GPL(rapl_remove_package_cpuslocked); + +void rapl_remove_package(struct rapl_package *rp) +{ + guard(cpus_read_lock)(); + rapl_remove_package_cpuslocked(rp); +} EXPORT_SYMBOL_GPL(rapl_remove_package); /* caller to ensure CPU hotplug lock is held */ -struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu) +struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv, + bool id_is_cpu) { struct rapl_package *rp; int uid; @@ -1549,10 +1565,17 @@ struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, return NULL; } +EXPORT_SYMBOL_GPL(rapl_find_package_domain_cpuslocked); + +struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu) +{ + guard(cpus_read_lock)(); + return rapl_find_package_domain_cpuslocked(id, priv, id_is_cpu); +} EXPORT_SYMBOL_GPL(rapl_find_package_domain); /* called from CPU hotplug notifier, hotplug lock held */ -struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu) +struct rapl_package *rapl_add_package_cpuslocked(int id, struct rapl_if_priv *priv, bool id_is_cpu) { struct rapl_package *rp; int ret; @@ -1598,6 +1621,13 @@ struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id kfree(rp); return ERR_PTR(ret); } +EXPORT_SYMBOL_GPL(rapl_add_package_cpuslocked); + +struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu) +{ + guard(cpus_read_lock)(); + return rapl_add_package_cpuslocked(id, priv, id_is_cpu); +} EXPORT_SYMBOL_GPL(rapl_add_package); static void power_limit_state_save(void) diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c index 250bd41a588c7..b4b6930cacb0b 100644 --- a/drivers/powercap/intel_rapl_msr.c +++ b/drivers/powercap/intel_rapl_msr.c @@ -73,9 +73,9 @@ static int rapl_cpu_online(unsigned int cpu) { struct rapl_package *rp; - rp = rapl_find_package_domain(cpu, rapl_msr_priv, true); + rp = rapl_find_package_domain_cpuslocked(cpu, rapl_msr_priv, true); if (!rp) { - rp = rapl_add_package(cpu, rapl_msr_priv, true); + rp = rapl_add_package_cpuslocked(cpu, rapl_msr_priv, true); if (IS_ERR(rp)) return PTR_ERR(rp); } @@ -88,14 +88,14 @@ static int rapl_cpu_down_prep(unsigned int cpu) struct rapl_package *rp; int lead_cpu; - rp = rapl_find_package_domain(cpu, rapl_msr_priv, true); + rp = rapl_find_package_domain_cpuslocked(cpu, rapl_msr_priv, true); if (!rp) return 0; cpumask_clear_cpu(cpu, &rp->cpumask); lead_cpu = cpumask_first(&rp->cpumask); if (lead_cpu >= nr_cpu_ids) - rapl_remove_package(rp); + rapl_remove_package_cpuslocked(rp); else if (rp->lead_cpu == cpu) rp->lead_cpu = lead_cpu; return 0; diff --git a/drivers/powercap/intel_rapl_tpmi.c b/drivers/powercap/intel_rapl_tpmi.c index 891c90fefd8b7..f6b7f085977ce 100644 --- a/drivers/powercap/intel_rapl_tpmi.c +++ b/drivers/powercap/intel_rapl_tpmi.c @@ -40,6 +40,7 @@ enum tpmi_rapl_register { TPMI_RAPL_REG_ENERGY_STATUS, TPMI_RAPL_REG_PERF_STATUS, TPMI_RAPL_REG_POWER_INFO, + TPMI_RAPL_REG_DOMAIN_INFO, TPMI_RAPL_REG_INTERRUPT, TPMI_RAPL_REG_MAX = 15, }; @@ -130,6 +131,12 @@ static void trp_release(struct tpmi_rapl_package *trp) mutex_unlock(&tpmi_rapl_lock); } +/* + * Bit 0 of TPMI_RAPL_REG_DOMAIN_INFO indicates if the current package is a domain + * root or not. Only domain root packages can enumerate System (Psys) Domain. + */ +#define TPMI_RAPL_DOMAIN_ROOT BIT(0) + static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset) { u8 tpmi_domain_version; @@ -139,6 +146,7 @@ static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset) enum rapl_domain_reg_id reg_id; int tpmi_domain_size, tpmi_domain_flags; u64 tpmi_domain_header = readq(trp->base + offset); + u64 tpmi_domain_info; /* Domain Parent bits are ignored for now */ tpmi_domain_version = tpmi_domain_header & 0xff; @@ -169,6 +177,13 @@ static int parse_one_domain(struct tpmi_rapl_package *trp, u32 offset) domain_type = RAPL_DOMAIN_PACKAGE; break; case TPMI_RAPL_DOMAIN_SYSTEM: + if (!(tpmi_domain_flags & BIT(TPMI_RAPL_REG_DOMAIN_INFO))) { + pr_warn(FW_BUG "System domain must support Domain Info register\n"); + return -ENODEV; + } + tpmi_domain_info = readq(trp->base + offset + TPMI_RAPL_REG_DOMAIN_INFO); + if (!(tpmi_domain_info & TPMI_RAPL_DOMAIN_ROOT)) + return 0; domain_type = RAPL_DOMAIN_PLATFORM; break; case TPMI_RAPL_DOMAIN_MEMORY: diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 7513018c9f9ac..2067b0120d083 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -85,7 +85,8 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin, } if (info->verify(info, pin, func, chan)) { - pr_err("driver cannot use function %u on pin %u\n", func, chan); + pr_err("driver cannot use function %u and channel %u on pin %u\n", + func, chan, pin); return -EOPNOTSUPP; } diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 15b804ba48685..317cc28dad6d9 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -175,6 +175,9 @@ static void ptp_clock_release(struct device *dev) struct timestamp_event_queue *tsevq; unsigned long flags; + /* Release the clock's resources. */ + if (ptp->pps_source) + pps_unregister_source(ptp->pps_source); ptp_cleanup_pin_groups(ptp); kfree(ptp->vclock_index); mutex_destroy(&ptp->pincfg_mux); @@ -394,11 +397,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp) kthread_cancel_delayed_work_sync(&ptp->aux_work); kthread_destroy_worker(ptp->kworker); } - - /* Release the clock's resources. */ - if (ptp->pps_source) - pps_unregister_source(ptp->pps_source); - posix_clock_unregister(&ptp->clock); return 0; diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 5f858e426bbd5..05b8f325a887d 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -4277,7 +4277,7 @@ static int ptp_ocp_dpll_direction_set(const struct dpll_pin *pin, return -EOPNOTSUPP; mode = direction == DPLL_PIN_DIRECTION_INPUT ? SMA_MODE_IN : SMA_MODE_OUT; - return ptp_ocp_sma_store_val(bp, 0, mode, sma_nr); + return ptp_ocp_sma_store_val(bp, 0, mode, sma_nr + 1); } static int ptp_ocp_dpll_frequency_set(const struct dpll_pin *pin, @@ -4298,7 +4298,7 @@ static int ptp_ocp_dpll_frequency_set(const struct dpll_pin *pin, tbl = bp->sma_op->tbl[sma->mode]; for (i = 0; tbl[i].name; i++) if (tbl[i].frequency == frequency) - return ptp_ocp_sma_store_val(bp, i, sma->mode, sma_nr); + return ptp_ocp_sma_store_val(bp, i, sma->mode, sma_nr + 1); return -EINVAL; } @@ -4315,7 +4315,7 @@ static int ptp_ocp_dpll_frequency_get(const struct dpll_pin *pin, u32 val; int i; - val = bp->sma_op->get(bp, sma_nr); + val = bp->sma_op->get(bp, sma_nr + 1); tbl = bp->sma_op->tbl[sma->mode]; for (i = 0; tbl[i].name; i++) if (val == tbl[i].value) { diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index f7a499a1bd39e..2cdac19b5402d 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -297,8 +297,7 @@ static ssize_t max_vclocks_store(struct device *dev, if (max < ptp->n_vclocks) goto out; - size = sizeof(int) * max; - vclock_index = kzalloc(size, GFP_KERNEL); + vclock_index = kcalloc(max, sizeof(int), GFP_KERNEL); if (!vclock_index) { err = -ENOMEM; goto out; diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index f2728ee787d7a..9d2dc5e1c8aac 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -24,277 +24,358 @@ #define CREATE_TRACE_POINTS #include -static DEFINE_MUTEX(pwm_lookup_lock); -static LIST_HEAD(pwm_lookup_list); - /* protects access to pwm_chips */ static DEFINE_MUTEX(pwm_lock); static DEFINE_IDR(pwm_chips); -static struct pwm_chip *pwmchip_find_by_name(const char *name) +static void pwm_apply_debug(struct pwm_device *pwm, + const struct pwm_state *state) { - struct pwm_chip *chip; - unsigned long id, tmp; - - if (!name) - return NULL; - - mutex_lock(&pwm_lock); + struct pwm_state *last = &pwm->last; + struct pwm_chip *chip = pwm->chip; + struct pwm_state s1 = { 0 }, s2 = { 0 }; + int err; - idr_for_each_entry_ul(&pwm_chips, chip, tmp, id) { - const char *chip_name = dev_name(chip->dev); + if (!IS_ENABLED(CONFIG_PWM_DEBUG)) + return; - if (chip_name && strcmp(chip_name, name) == 0) { - mutex_unlock(&pwm_lock); - return chip; - } - } + /* No reasonable diagnosis possible without .get_state() */ + if (!chip->ops->get_state) + return; - mutex_unlock(&pwm_lock); + /* + * *state was just applied. Read out the hardware state and do some + * checks. + */ - return NULL; -} + err = chip->ops->get_state(chip, pwm, &s1); + trace_pwm_get(pwm, &s1, err); + if (err) + /* If that failed there isn't much to debug */ + return; -static int pwm_device_request(struct pwm_device *pwm, const char *label) -{ - int err; - struct pwm_chip *chip = pwm->chip; - const struct pwm_ops *ops = chip->ops; + /* + * The lowlevel driver either ignored .polarity (which is a bug) or as + * best effort inverted .polarity and fixed .duty_cycle respectively. + * Undo this inversion and fixup for further tests. + */ + if (s1.enabled && s1.polarity != state->polarity) { + s2.polarity = state->polarity; + s2.duty_cycle = s1.period - s1.duty_cycle; + s2.period = s1.period; + s2.enabled = s1.enabled; + } else { + s2 = s1; + } - if (test_bit(PWMF_REQUESTED, &pwm->flags)) - return -EBUSY; + if (s2.polarity != state->polarity && + state->duty_cycle < state->period) + dev_warn(pwmchip_parent(chip), ".apply ignored .polarity\n"); - if (!try_module_get(chip->owner)) - return -ENODEV; + if (state->enabled && + last->polarity == state->polarity && + last->period > s2.period && + last->period <= state->period) + dev_warn(pwmchip_parent(chip), + ".apply didn't pick the best available period (requested: %llu, applied: %llu, possible: %llu)\n", + state->period, s2.period, last->period); - if (ops->request) { - err = ops->request(chip, pwm); - if (err) { - module_put(chip->owner); - return err; - } - } + if (state->enabled && state->period < s2.period) + dev_warn(pwmchip_parent(chip), + ".apply is supposed to round down period (requested: %llu, applied: %llu)\n", + state->period, s2.period); - if (ops->get_state) { - /* - * Zero-initialize state because most drivers are unaware of - * .usage_power. The other members of state are supposed to be - * set by lowlevel drivers. We still initialize the whole - * structure for simplicity even though this might paper over - * faulty implementations of .get_state(). - */ - struct pwm_state state = { 0, }; + if (state->enabled && + last->polarity == state->polarity && + last->period == s2.period && + last->duty_cycle > s2.duty_cycle && + last->duty_cycle <= state->duty_cycle) + dev_warn(pwmchip_parent(chip), + ".apply didn't pick the best available duty cycle (requested: %llu/%llu, applied: %llu/%llu, possible: %llu/%llu)\n", + state->duty_cycle, state->period, + s2.duty_cycle, s2.period, + last->duty_cycle, last->period); - err = ops->get_state(chip, pwm, &state); - trace_pwm_get(pwm, &state, err); + if (state->enabled && state->duty_cycle < s2.duty_cycle) + dev_warn(pwmchip_parent(chip), + ".apply is supposed to round down duty_cycle (requested: %llu/%llu, applied: %llu/%llu)\n", + state->duty_cycle, state->period, + s2.duty_cycle, s2.period); - if (!err) - pwm->state = state; + if (!state->enabled && s2.enabled && s2.duty_cycle > 0) + dev_warn(pwmchip_parent(chip), + "requested disabled, but yielded enabled with duty > 0\n"); - if (IS_ENABLED(CONFIG_PWM_DEBUG)) - pwm->last = pwm->state; + /* reapply the state that the driver reported being configured. */ + err = chip->ops->apply(chip, pwm, &s1); + trace_pwm_apply(pwm, &s1, err); + if (err) { + *last = s1; + dev_err(pwmchip_parent(chip), "failed to reapply current setting\n"); + return; } - set_bit(PWMF_REQUESTED, &pwm->flags); - pwm->label = label; + *last = (struct pwm_state){ 0 }; + err = chip->ops->get_state(chip, pwm, last); + trace_pwm_get(pwm, last, err); + if (err) + return; - return 0; + /* reapplication of the current state should give an exact match */ + if (s1.enabled != last->enabled || + s1.polarity != last->polarity || + (s1.enabled && s1.period != last->period) || + (s1.enabled && s1.duty_cycle != last->duty_cycle)) { + dev_err(pwmchip_parent(chip), + ".apply is not idempotent (ena=%d pol=%d %llu/%llu) -> (ena=%d pol=%d %llu/%llu)\n", + s1.enabled, s1.polarity, s1.duty_cycle, s1.period, + last->enabled, last->polarity, last->duty_cycle, + last->period); + } } -struct pwm_device * -of_pwm_xlate_with_flags(struct pwm_chip *chip, const struct of_phandle_args *args) +/** + * __pwm_apply() - atomically apply a new state to a PWM device + * @pwm: PWM device + * @state: new state to apply + */ +static int __pwm_apply(struct pwm_device *pwm, const struct pwm_state *state) { - struct pwm_device *pwm; + struct pwm_chip *chip; + int err; - if (chip->of_pwm_n_cells < 2) - return ERR_PTR(-EINVAL); + if (!pwm || !state || !state->period || + state->duty_cycle > state->period) + return -EINVAL; - /* flags in the third cell are optional */ - if (args->args_count < 2) - return ERR_PTR(-EINVAL); + chip = pwm->chip; - if (args->args[0] >= chip->npwm) - return ERR_PTR(-EINVAL); + if (state->period == pwm->state.period && + state->duty_cycle == pwm->state.duty_cycle && + state->polarity == pwm->state.polarity && + state->enabled == pwm->state.enabled && + state->usage_power == pwm->state.usage_power) + return 0; - pwm = pwm_request_from_chip(chip, args->args[0], NULL); - if (IS_ERR(pwm)) - return pwm; + err = chip->ops->apply(chip, pwm, state); + trace_pwm_apply(pwm, state, err); + if (err) + return err; - pwm->args.period = args->args[1]; - pwm->args.polarity = PWM_POLARITY_NORMAL; + pwm->state = *state; - if (chip->of_pwm_n_cells >= 3) { - if (args->args_count > 2 && args->args[2] & PWM_POLARITY_INVERTED) - pwm->args.polarity = PWM_POLARITY_INVERSED; - } + /* + * only do this after pwm->state was applied as some + * implementations of .get_state depend on this + */ + pwm_apply_debug(pwm, state); - return pwm; + return 0; } -EXPORT_SYMBOL_GPL(of_pwm_xlate_with_flags); -struct pwm_device * -of_pwm_single_xlate(struct pwm_chip *chip, const struct of_phandle_args *args) +/** + * pwm_apply_might_sleep() - atomically apply a new state to a PWM device + * Cannot be used in atomic context. + * @pwm: PWM device + * @state: new state to apply + */ +int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state) { - struct pwm_device *pwm; - - if (chip->of_pwm_n_cells < 1) - return ERR_PTR(-EINVAL); + int err; - /* validate that one cell is specified, optionally with flags */ - if (args->args_count != 1 && args->args_count != 2) - return ERR_PTR(-EINVAL); + /* + * Some lowlevel driver's implementations of .apply() make use of + * mutexes, also with some drivers only returning when the new + * configuration is active calling pwm_apply_might_sleep() from atomic context + * is a bad idea. So make it explicit that calling this function might + * sleep. + */ + might_sleep(); - pwm = pwm_request_from_chip(chip, 0, NULL); - if (IS_ERR(pwm)) - return pwm; + if (IS_ENABLED(CONFIG_PWM_DEBUG) && pwm->chip->atomic) { + /* + * Catch any drivers that have been marked as atomic but + * that will sleep anyway. + */ + non_block_start(); + err = __pwm_apply(pwm, state); + non_block_end(); + } else { + err = __pwm_apply(pwm, state); + } - pwm->args.period = args->args[0]; - pwm->args.polarity = PWM_POLARITY_NORMAL; + return err; +} +EXPORT_SYMBOL_GPL(pwm_apply_might_sleep); - if (args->args_count == 2 && args->args[1] & PWM_POLARITY_INVERTED) - pwm->args.polarity = PWM_POLARITY_INVERSED; +/** + * pwm_apply_atomic() - apply a new state to a PWM device from atomic context + * Not all PWM devices support this function, check with pwm_might_sleep(). + * @pwm: PWM device + * @state: new state to apply + */ +int pwm_apply_atomic(struct pwm_device *pwm, const struct pwm_state *state) +{ + WARN_ONCE(!pwm->chip->atomic, + "sleeping PWM driver used in atomic context\n"); - return pwm; + return __pwm_apply(pwm, state); } -EXPORT_SYMBOL_GPL(of_pwm_single_xlate); +EXPORT_SYMBOL_GPL(pwm_apply_atomic); -static void of_pwmchip_add(struct pwm_chip *chip) +/** + * pwm_adjust_config() - adjust the current PWM config to the PWM arguments + * @pwm: PWM device + * + * This function will adjust the PWM config to the PWM arguments provided + * by the DT or PWM lookup table. This is particularly useful to adapt + * the bootloader config to the Linux one. + */ +int pwm_adjust_config(struct pwm_device *pwm) { - if (!chip->dev || !chip->dev->of_node) - return; + struct pwm_state state; + struct pwm_args pargs; - if (!chip->of_xlate) { - u32 pwm_cells; + pwm_get_args(pwm, &pargs); + pwm_get_state(pwm, &state); - if (of_property_read_u32(chip->dev->of_node, "#pwm-cells", - &pwm_cells)) - pwm_cells = 2; + /* + * If the current period is zero it means that either the PWM driver + * does not support initial state retrieval or the PWM has not yet + * been configured. + * + * In either case, we setup the new period and polarity, and assign a + * duty cycle of 0. + */ + if (!state.period) { + state.duty_cycle = 0; + state.period = pargs.period; + state.polarity = pargs.polarity; - chip->of_xlate = of_pwm_xlate_with_flags; - chip->of_pwm_n_cells = pwm_cells; + return pwm_apply_might_sleep(pwm, &state); } - of_node_get(chip->dev->of_node); -} - -static void of_pwmchip_remove(struct pwm_chip *chip) -{ - if (chip->dev) - of_node_put(chip->dev->of_node); -} - -static bool pwm_ops_check(const struct pwm_chip *chip) -{ - const struct pwm_ops *ops = chip->ops; - - if (!ops->apply) - return false; + /* + * Adjust the PWM duty cycle/period based on the period value provided + * in PWM args. + */ + if (pargs.period != state.period) { + u64 dutycycle = (u64)state.duty_cycle * pargs.period; - if (IS_ENABLED(CONFIG_PWM_DEBUG) && !ops->get_state) - dev_warn(chip->dev, - "Please implement the .get_state() callback\n"); + do_div(dutycycle, state.period); + state.duty_cycle = dutycycle; + state.period = pargs.period; + } - return true; + /* + * If the polarity changed, we should also change the duty cycle. + */ + if (pargs.polarity != state.polarity) { + state.polarity = pargs.polarity; + state.duty_cycle = state.period - state.duty_cycle; + } + + return pwm_apply_might_sleep(pwm, &state); } +EXPORT_SYMBOL_GPL(pwm_adjust_config); /** - * __pwmchip_add() - register a new PWM chip - * @chip: the PWM chip to add - * @owner: reference to the module providing the chip. - * - * Register a new PWM chip. @owner is supposed to be THIS_MODULE, use the - * pwmchip_add wrapper to do this right. + * pwm_capture() - capture and report a PWM signal + * @pwm: PWM device + * @result: structure to fill with capture result + * @timeout: time to wait, in milliseconds, before giving up on capture * * Returns: 0 on success or a negative error code on failure. */ -int __pwmchip_add(struct pwm_chip *chip, struct module *owner) +int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, + unsigned long timeout) { - unsigned int i; - int ret; + int err; - if (!chip || !chip->dev || !chip->ops || !chip->npwm) + if (!pwm || !pwm->chip->ops) return -EINVAL; - if (!pwm_ops_check(chip)) - return -EINVAL; + if (!pwm->chip->ops->capture) + return -ENOSYS; - chip->owner = owner; + mutex_lock(&pwm_lock); + err = pwm->chip->ops->capture(pwm->chip, pwm, result, timeout); + mutex_unlock(&pwm_lock); - chip->pwms = kcalloc(chip->npwm, sizeof(*chip->pwms), GFP_KERNEL); - if (!chip->pwms) - return -ENOMEM; + return err; +} +EXPORT_SYMBOL_GPL(pwm_capture); - mutex_lock(&pwm_lock); +static struct pwm_chip *pwmchip_find_by_name(const char *name) +{ + struct pwm_chip *chip; + unsigned long id, tmp; - ret = idr_alloc(&pwm_chips, chip, 0, 0, GFP_KERNEL); - if (ret < 0) { - mutex_unlock(&pwm_lock); - kfree(chip->pwms); - return ret; - } + if (!name) + return NULL; - chip->id = ret; + mutex_lock(&pwm_lock); - for (i = 0; i < chip->npwm; i++) { - struct pwm_device *pwm = &chip->pwms[i]; + idr_for_each_entry_ul(&pwm_chips, chip, tmp, id) { + const char *chip_name = dev_name(pwmchip_parent(chip)); - pwm->chip = chip; - pwm->hwpwm = i; + if (chip_name && strcmp(chip_name, name) == 0) { + mutex_unlock(&pwm_lock); + return chip; + } } mutex_unlock(&pwm_lock); - if (IS_ENABLED(CONFIG_OF)) - of_pwmchip_add(chip); - - pwmchip_sysfs_export(chip); - - return 0; + return NULL; } -EXPORT_SYMBOL_GPL(__pwmchip_add); -/** - * pwmchip_remove() - remove a PWM chip - * @chip: the PWM chip to remove - * - * Removes a PWM chip. - */ -void pwmchip_remove(struct pwm_chip *chip) +static int pwm_device_request(struct pwm_device *pwm, const char *label) { - pwmchip_sysfs_unexport(chip); - - if (IS_ENABLED(CONFIG_OF)) - of_pwmchip_remove(chip); + int err; + struct pwm_chip *chip = pwm->chip; + const struct pwm_ops *ops = chip->ops; - mutex_lock(&pwm_lock); + if (test_bit(PWMF_REQUESTED, &pwm->flags)) + return -EBUSY; - idr_remove(&pwm_chips, chip->id); + if (!try_module_get(chip->owner)) + return -ENODEV; - mutex_unlock(&pwm_lock); + if (ops->request) { + err = ops->request(chip, pwm); + if (err) { + module_put(chip->owner); + return err; + } + } - kfree(chip->pwms); -} -EXPORT_SYMBOL_GPL(pwmchip_remove); + if (ops->get_state) { + /* + * Zero-initialize state because most drivers are unaware of + * .usage_power. The other members of state are supposed to be + * set by lowlevel drivers. We still initialize the whole + * structure for simplicity even though this might paper over + * faulty implementations of .get_state(). + */ + struct pwm_state state = { 0, }; -static void devm_pwmchip_remove(void *data) -{ - struct pwm_chip *chip = data; + err = ops->get_state(chip, pwm, &state); + trace_pwm_get(pwm, &state, err); - pwmchip_remove(chip); -} + if (!err) + pwm->state = state; -int __devm_pwmchip_add(struct device *dev, struct pwm_chip *chip, struct module *owner) -{ - int ret; + if (IS_ENABLED(CONFIG_PWM_DEBUG)) + pwm->last = pwm->state; + } - ret = __pwmchip_add(chip, owner); - if (ret) - return ret; + set_bit(PWMF_REQUESTED, &pwm->flags); + pwm->label = label; - return devm_add_action_or_reset(dev, devm_pwmchip_remove, chip); + return 0; } -EXPORT_SYMBOL_GPL(__devm_pwmchip_add); /** * pwm_request_from_chip() - request a PWM device relative to a PWM chip @@ -328,301 +409,179 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, } EXPORT_SYMBOL_GPL(pwm_request_from_chip); -static void pwm_apply_debug(struct pwm_device *pwm, - const struct pwm_state *state) -{ - struct pwm_state *last = &pwm->last; - struct pwm_chip *chip = pwm->chip; - struct pwm_state s1 = { 0 }, s2 = { 0 }; - int err; - - if (!IS_ENABLED(CONFIG_PWM_DEBUG)) - return; - - /* No reasonable diagnosis possible without .get_state() */ - if (!chip->ops->get_state) - return; - - /* - * *state was just applied. Read out the hardware state and do some - * checks. - */ - - err = chip->ops->get_state(chip, pwm, &s1); - trace_pwm_get(pwm, &s1, err); - if (err) - /* If that failed there isn't much to debug */ - return; - - /* - * The lowlevel driver either ignored .polarity (which is a bug) or as - * best effort inverted .polarity and fixed .duty_cycle respectively. - * Undo this inversion and fixup for further tests. - */ - if (s1.enabled && s1.polarity != state->polarity) { - s2.polarity = state->polarity; - s2.duty_cycle = s1.period - s1.duty_cycle; - s2.period = s1.period; - s2.enabled = s1.enabled; - } else { - s2 = s1; - } - - if (s2.polarity != state->polarity && - state->duty_cycle < state->period) - dev_warn(chip->dev, ".apply ignored .polarity\n"); - - if (state->enabled && - last->polarity == state->polarity && - last->period > s2.period && - last->period <= state->period) - dev_warn(chip->dev, - ".apply didn't pick the best available period (requested: %llu, applied: %llu, possible: %llu)\n", - state->period, s2.period, last->period); - - if (state->enabled && state->period < s2.period) - dev_warn(chip->dev, - ".apply is supposed to round down period (requested: %llu, applied: %llu)\n", - state->period, s2.period); - - if (state->enabled && - last->polarity == state->polarity && - last->period == s2.period && - last->duty_cycle > s2.duty_cycle && - last->duty_cycle <= state->duty_cycle) - dev_warn(chip->dev, - ".apply didn't pick the best available duty cycle (requested: %llu/%llu, applied: %llu/%llu, possible: %llu/%llu)\n", - state->duty_cycle, state->period, - s2.duty_cycle, s2.period, - last->duty_cycle, last->period); - - if (state->enabled && state->duty_cycle < s2.duty_cycle) - dev_warn(chip->dev, - ".apply is supposed to round down duty_cycle (requested: %llu/%llu, applied: %llu/%llu)\n", - state->duty_cycle, state->period, - s2.duty_cycle, s2.period); - - if (!state->enabled && s2.enabled && s2.duty_cycle > 0) - dev_warn(chip->dev, - "requested disabled, but yielded enabled with duty > 0\n"); - - /* reapply the state that the driver reported being configured. */ - err = chip->ops->apply(chip, pwm, &s1); - trace_pwm_apply(pwm, &s1, err); - if (err) { - *last = s1; - dev_err(chip->dev, "failed to reapply current setting\n"); - return; - } - - *last = (struct pwm_state){ 0 }; - err = chip->ops->get_state(chip, pwm, last); - trace_pwm_get(pwm, last, err); - if (err) - return; - - /* reapplication of the current state should give an exact match */ - if (s1.enabled != last->enabled || - s1.polarity != last->polarity || - (s1.enabled && s1.period != last->period) || - (s1.enabled && s1.duty_cycle != last->duty_cycle)) { - dev_err(chip->dev, - ".apply is not idempotent (ena=%d pol=%d %llu/%llu) -> (ena=%d pol=%d %llu/%llu)\n", - s1.enabled, s1.polarity, s1.duty_cycle, s1.period, - last->enabled, last->polarity, last->duty_cycle, - last->period); - } -} -/** - * __pwm_apply() - atomically apply a new state to a PWM device - * @pwm: PWM device - * @state: new state to apply - */ -static int __pwm_apply(struct pwm_device *pwm, const struct pwm_state *state) +struct pwm_device * +of_pwm_xlate_with_flags(struct pwm_chip *chip, const struct of_phandle_args *args) { - struct pwm_chip *chip; - int err; + struct pwm_device *pwm; - if (!pwm || !state || !state->period || - state->duty_cycle > state->period) - return -EINVAL; + /* period in the second cell and flags in the third cell are optional */ + if (args->args_count < 1) + return ERR_PTR(-EINVAL); - chip = pwm->chip; + pwm = pwm_request_from_chip(chip, args->args[0], NULL); + if (IS_ERR(pwm)) + return pwm; - if (state->period == pwm->state.period && - state->duty_cycle == pwm->state.duty_cycle && - state->polarity == pwm->state.polarity && - state->enabled == pwm->state.enabled && - state->usage_power == pwm->state.usage_power) - return 0; + if (args->args_count > 1) + pwm->args.period = args->args[1]; - err = chip->ops->apply(chip, pwm, state); - trace_pwm_apply(pwm, state, err); - if (err) - return err; + pwm->args.polarity = PWM_POLARITY_NORMAL; + if (args->args_count > 2 && args->args[2] & PWM_POLARITY_INVERTED) + pwm->args.polarity = PWM_POLARITY_INVERSED; - pwm->state = *state; + return pwm; +} +EXPORT_SYMBOL_GPL(of_pwm_xlate_with_flags); - /* - * only do this after pwm->state was applied as some - * implementations of .get_state depend on this - */ - pwm_apply_debug(pwm, state); +struct pwm_device * +of_pwm_single_xlate(struct pwm_chip *chip, const struct of_phandle_args *args) +{ + struct pwm_device *pwm; - return 0; + pwm = pwm_request_from_chip(chip, 0, NULL); + if (IS_ERR(pwm)) + return pwm; + + if (args->args_count > 0) + pwm->args.period = args->args[0]; + + pwm->args.polarity = PWM_POLARITY_NORMAL; + if (args->args_count > 1 && args->args[1] & PWM_POLARITY_INVERTED) + pwm->args.polarity = PWM_POLARITY_INVERSED; + + return pwm; } +EXPORT_SYMBOL_GPL(of_pwm_single_xlate); -/** - * pwm_apply_might_sleep() - atomically apply a new state to a PWM device - * Cannot be used in atomic context. - * @pwm: PWM device - * @state: new state to apply - */ -int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state) +static void of_pwmchip_add(struct pwm_chip *chip) { - int err; + if (!pwmchip_parent(chip) || !pwmchip_parent(chip)->of_node) + return; - /* - * Some lowlevel driver's implementations of .apply() make use of - * mutexes, also with some drivers only returning when the new - * configuration is active calling pwm_apply_might_sleep() from atomic context - * is a bad idea. So make it explicit that calling this function might - * sleep. - */ - might_sleep(); + if (!chip->of_xlate) + chip->of_xlate = of_pwm_xlate_with_flags; - if (IS_ENABLED(CONFIG_PWM_DEBUG) && pwm->chip->atomic) { - /* - * Catch any drivers that have been marked as atomic but - * that will sleep anyway. - */ - non_block_start(); - err = __pwm_apply(pwm, state); - non_block_end(); - } else { - err = __pwm_apply(pwm, state); - } + of_node_get(pwmchip_parent(chip)->of_node); +} - return err; +static void of_pwmchip_remove(struct pwm_chip *chip) +{ + if (pwmchip_parent(chip)) + of_node_put(pwmchip_parent(chip)->of_node); } -EXPORT_SYMBOL_GPL(pwm_apply_might_sleep); -/** - * pwm_apply_atomic() - apply a new state to a PWM device from atomic context - * Not all PWM devices support this function, check with pwm_might_sleep(). - * @pwm: PWM device - * @state: new state to apply - */ -int pwm_apply_atomic(struct pwm_device *pwm, const struct pwm_state *state) +static bool pwm_ops_check(const struct pwm_chip *chip) { - WARN_ONCE(!pwm->chip->atomic, - "sleeping PWM driver used in atomic context\n"); + const struct pwm_ops *ops = chip->ops; - return __pwm_apply(pwm, state); + if (!ops->apply) + return false; + + if (IS_ENABLED(CONFIG_PWM_DEBUG) && !ops->get_state) + dev_warn(pwmchip_parent(chip), + "Please implement the .get_state() callback\n"); + + return true; } -EXPORT_SYMBOL_GPL(pwm_apply_atomic); /** - * pwm_capture() - capture and report a PWM signal - * @pwm: PWM device - * @result: structure to fill with capture result - * @timeout: time to wait, in milliseconds, before giving up on capture + * __pwmchip_add() - register a new PWM chip + * @chip: the PWM chip to add + * @owner: reference to the module providing the chip. + * + * Register a new PWM chip. @owner is supposed to be THIS_MODULE, use the + * pwmchip_add wrapper to do this right. * * Returns: 0 on success or a negative error code on failure. */ -int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, - unsigned long timeout) +int __pwmchip_add(struct pwm_chip *chip, struct module *owner) { - int err; + unsigned int i; + int ret; - if (!pwm || !pwm->chip->ops) + if (!chip || !pwmchip_parent(chip) || !chip->ops || !chip->npwm) return -EINVAL; - if (!pwm->chip->ops->capture) - return -ENOSYS; + if (!pwm_ops_check(chip)) + return -EINVAL; + + chip->owner = owner; + + chip->pwms = kcalloc(chip->npwm, sizeof(*chip->pwms), GFP_KERNEL); + if (!chip->pwms) + return -ENOMEM; mutex_lock(&pwm_lock); - err = pwm->chip->ops->capture(pwm->chip, pwm, result, timeout); + + ret = idr_alloc(&pwm_chips, chip, 0, 0, GFP_KERNEL); + if (ret < 0) { + mutex_unlock(&pwm_lock); + kfree(chip->pwms); + return ret; + } + + chip->id = ret; + + for (i = 0; i < chip->npwm; i++) { + struct pwm_device *pwm = &chip->pwms[i]; + + pwm->chip = chip; + pwm->hwpwm = i; + } + mutex_unlock(&pwm_lock); - return err; + if (IS_ENABLED(CONFIG_OF)) + of_pwmchip_add(chip); + + pwmchip_sysfs_export(chip); + + return 0; } -EXPORT_SYMBOL_GPL(pwm_capture); +EXPORT_SYMBOL_GPL(__pwmchip_add); /** - * pwm_adjust_config() - adjust the current PWM config to the PWM arguments - * @pwm: PWM device + * pwmchip_remove() - remove a PWM chip + * @chip: the PWM chip to remove * - * This function will adjust the PWM config to the PWM arguments provided - * by the DT or PWM lookup table. This is particularly useful to adapt - * the bootloader config to the Linux one. + * Removes a PWM chip. */ -int pwm_adjust_config(struct pwm_device *pwm) +void pwmchip_remove(struct pwm_chip *chip) { - struct pwm_state state; - struct pwm_args pargs; - - pwm_get_args(pwm, &pargs); - pwm_get_state(pwm, &state); - - /* - * If the current period is zero it means that either the PWM driver - * does not support initial state retrieval or the PWM has not yet - * been configured. - * - * In either case, we setup the new period and polarity, and assign a - * duty cycle of 0. - */ - if (!state.period) { - state.duty_cycle = 0; - state.period = pargs.period; - state.polarity = pargs.polarity; + pwmchip_sysfs_unexport(chip); - return pwm_apply_might_sleep(pwm, &state); - } + if (IS_ENABLED(CONFIG_OF)) + of_pwmchip_remove(chip); - /* - * Adjust the PWM duty cycle/period based on the period value provided - * in PWM args. - */ - if (pargs.period != state.period) { - u64 dutycycle = (u64)state.duty_cycle * pargs.period; + mutex_lock(&pwm_lock); - do_div(dutycycle, state.period); - state.duty_cycle = dutycycle; - state.period = pargs.period; - } + idr_remove(&pwm_chips, chip->id); - /* - * If the polarity changed, we should also change the duty cycle. - */ - if (pargs.polarity != state.polarity) { - state.polarity = pargs.polarity; - state.duty_cycle = state.period - state.duty_cycle; - } + mutex_unlock(&pwm_lock); - return pwm_apply_might_sleep(pwm, &state); + kfree(chip->pwms); } -EXPORT_SYMBOL_GPL(pwm_adjust_config); +EXPORT_SYMBOL_GPL(pwmchip_remove); -static struct pwm_chip *fwnode_to_pwmchip(struct fwnode_handle *fwnode) +static void devm_pwmchip_remove(void *data) { - struct pwm_chip *chip; - unsigned long id, tmp; + struct pwm_chip *chip = data; - mutex_lock(&pwm_lock); + pwmchip_remove(chip); +} - idr_for_each_entry_ul(&pwm_chips, chip, tmp, id) - if (chip->dev && device_match_fwnode(chip->dev, fwnode)) { - mutex_unlock(&pwm_lock); - return chip; - } +int __devm_pwmchip_add(struct device *dev, struct pwm_chip *chip, struct module *owner) +{ + int ret; - mutex_unlock(&pwm_lock); + ret = __pwmchip_add(chip, owner); + if (ret) + return ret; - return ERR_PTR(-EPROBE_DEFER); + return devm_add_action_or_reset(dev, devm_pwmchip_remove, chip); } +EXPORT_SYMBOL_GPL(__devm_pwmchip_add); static struct device_link *pwm_device_link_add(struct device *dev, struct pwm_device *pwm) @@ -635,21 +594,39 @@ static struct device_link *pwm_device_link_add(struct device *dev, * impact the PM sequence ordering: the PWM supplier may get * suspended before the consumer. */ - dev_warn(pwm->chip->dev, + dev_warn(pwmchip_parent(pwm->chip), "No consumer device specified to create a link to\n"); return NULL; } - dl = device_link_add(dev, pwm->chip->dev, DL_FLAG_AUTOREMOVE_CONSUMER); + dl = device_link_add(dev, pwmchip_parent(pwm->chip), DL_FLAG_AUTOREMOVE_CONSUMER); if (!dl) { dev_err(dev, "failed to create device link to %s\n", - dev_name(pwm->chip->dev)); + dev_name(pwmchip_parent(pwm->chip))); return ERR_PTR(-EINVAL); } return dl; } +static struct pwm_chip *fwnode_to_pwmchip(struct fwnode_handle *fwnode) +{ + struct pwm_chip *chip; + unsigned long id, tmp; + + mutex_lock(&pwm_lock); + + idr_for_each_entry_ul(&pwm_chips, chip, tmp, id) + if (pwmchip_parent(chip) && device_match_fwnode(pwmchip_parent(chip), fwnode)) { + mutex_unlock(&pwm_lock); + return chip; + } + + mutex_unlock(&pwm_lock); + + return ERR_PTR(-EPROBE_DEFER); +} + /** * of_pwm_get() - request a PWM via the PWM framework * @dev: device for PWM consumer @@ -784,6 +761,9 @@ static struct pwm_device *acpi_pwm_get(const struct fwnode_handle *fwnode) return pwm; } +static DEFINE_MUTEX(pwm_lookup_lock); +static LIST_HEAD(pwm_lookup_list); + /** * pwm_add_table() - register PWM device consumers * @table: array of consumers to register @@ -1105,8 +1085,8 @@ static int pwm_seq_show(struct seq_file *s, void *v) seq_printf(s, "%s%d: %s/%s, %d PWM device%s\n", (char *)s->private, chip->id, - chip->dev->bus ? chip->dev->bus->name : "no-bus", - dev_name(chip->dev), chip->npwm, + pwmchip_parent(chip)->bus ? pwmchip_parent(chip)->bus->name : "no-bus", + dev_name(pwmchip_parent(chip)), chip->npwm, (chip->npwm != 1) ? "s" : ""); pwm_dbg_show(chip, s); diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c index 3f2c5031a3ba8..1f6fc9a9fcf3e 100644 --- a/drivers/pwm/pwm-atmel-hlcdc.c +++ b/drivers/pwm/pwm-atmel-hlcdc.c @@ -185,7 +185,7 @@ static int atmel_hlcdc_pwm_suspend(struct device *dev) struct atmel_hlcdc_pwm *atmel = dev_get_drvdata(dev); /* Keep the periph clock enabled if the PWM is still running. */ - if (pwm_is_enabled(&atmel->chip.pwms[0])) + if (!pwm_is_enabled(&atmel->chip.pwms[0])) clk_disable_unprepare(atmel->hlcdc->periph_clk); return 0; diff --git a/drivers/pwm/pwm-clps711x.c b/drivers/pwm/pwm-clps711x.c index 42179b3f7ec39..06562d4bb9633 100644 --- a/drivers/pwm/pwm-clps711x.c +++ b/drivers/pwm/pwm-clps711x.c @@ -103,7 +103,6 @@ static int clps711x_pwm_probe(struct platform_device *pdev) priv->chip.dev = &pdev->dev; priv->chip.npwm = 2; priv->chip.of_xlate = clps711x_pwm_xlate; - priv->chip.of_pwm_n_cells = 1; spin_lock_init(&priv->lock); diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c index 5fe303b8656de..339cedf3a7b18 100644 --- a/drivers/pwm/pwm-cros-ec.c +++ b/drivers/pwm/pwm-cros-ec.c @@ -279,7 +279,6 @@ static int cros_ec_pwm_probe(struct platform_device *pdev) chip->dev = dev; chip->ops = &cros_ec_pwm_ops; chip->of_xlate = cros_ec_pwm_xlate; - chip->of_pwm_n_cells = 1; if (ec_pwm->use_pwm_type) { chip->npwm = CROS_EC_PWM_DT_COUNT; diff --git a/drivers/pwm/pwm-dwc.c b/drivers/pwm/pwm-dwc.c index 4929354f8cd95..a4a057ae03ea2 100644 --- a/drivers/pwm/pwm-dwc.c +++ b/drivers/pwm/pwm-dwc.c @@ -120,7 +120,7 @@ static struct pci_driver dwc_pwm_driver = { .remove = dwc_pwm_remove, .id_table = dwc_pwm_id_table, .driver = { - .pm = pm_ptr(&dwc_pwm_pm_ops), + .pm = pm_sleep_ptr(&dwc_pwm_pm_ops), }, }; diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c index 5965ac35b32ea..54dbafc51627e 100644 --- a/drivers/pwm/pwm-img.c +++ b/drivers/pwm/pwm-img.c @@ -284,9 +284,9 @@ static int img_pwm_probe(struct platform_device *pdev) return PTR_ERR(imgchip->sys_clk); } - imgchip->pwm_clk = devm_clk_get(&pdev->dev, "imgchip"); + imgchip->pwm_clk = devm_clk_get(&pdev->dev, "pwm"); if (IS_ERR(imgchip->pwm_clk)) { - dev_err(&pdev->dev, "failed to get imgchip clock\n"); + dev_err(&pdev->dev, "failed to get pwm clock\n"); return PTR_ERR(imgchip->pwm_clk); } diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 2971bbf3b5e7c..52ac3277f4204 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -122,7 +122,7 @@ static int meson_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm) { struct meson_pwm *meson = to_meson_pwm(chip); struct meson_pwm_channel *channel = &meson->channels[pwm->hwpwm]; - struct device *dev = chip->dev; + struct device *dev = pwmchip_parent(chip); int err; err = clk_prepare_enable(channel->clk); @@ -143,12 +143,13 @@ static void meson_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm) clk_disable_unprepare(channel->clk); } -static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, +static int meson_pwm_calc(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { + struct meson_pwm *meson = to_meson_pwm(chip); struct meson_pwm_channel *channel = &meson->channels[pwm->hwpwm]; unsigned int cnt, duty_cnt; - unsigned long fin_freq; + long fin_freq; u64 duty, period, freq; duty = state->duty_cycle; @@ -168,20 +169,21 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, freq = ULONG_MAX; fin_freq = clk_round_rate(channel->clk, freq); - if (fin_freq == 0) { - dev_err(meson->chip.dev, "invalid source clock frequency\n"); - return -EINVAL; + if (fin_freq <= 0) { + dev_err(pwmchip_parent(chip), + "invalid source clock frequency %llu\n", freq); + return fin_freq ? fin_freq : -EINVAL; } - dev_dbg(meson->chip.dev, "fin_freq: %lu Hz\n", fin_freq); + dev_dbg(pwmchip_parent(chip), "fin_freq: %ld Hz\n", fin_freq); - cnt = div_u64(fin_freq * period, NSEC_PER_SEC); + cnt = mul_u64_u64_div_u64(fin_freq, period, NSEC_PER_SEC); if (cnt > 0xffff) { - dev_err(meson->chip.dev, "unable to get period cnt\n"); + dev_err(pwmchip_parent(chip), "unable to get period cnt\n"); return -EINVAL; } - dev_dbg(meson->chip.dev, "period=%llu cnt=%u\n", period, cnt); + dev_dbg(pwmchip_parent(chip), "period=%llu cnt=%u\n", period, cnt); if (duty == period) { channel->hi = cnt; @@ -190,9 +192,9 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, channel->hi = 0; channel->lo = cnt; } else { - duty_cnt = div_u64(fin_freq * duty, NSEC_PER_SEC); + duty_cnt = mul_u64_u64_div_u64(fin_freq, duty, NSEC_PER_SEC); - dev_dbg(meson->chip.dev, "duty=%llu duty_cnt=%u\n", duty, duty_cnt); + dev_dbg(pwmchip_parent(chip), "duty=%llu duty_cnt=%u\n", duty, duty_cnt); channel->hi = duty_cnt; channel->lo = cnt - duty_cnt; @@ -203,8 +205,9 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, return 0; } -static void meson_pwm_enable(struct meson_pwm *meson, struct pwm_device *pwm) +static void meson_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm) { + struct meson_pwm *meson = to_meson_pwm(chip); struct meson_pwm_channel *channel = &meson->channels[pwm->hwpwm]; struct meson_pwm_channel_data *channel_data; unsigned long flags; @@ -215,7 +218,7 @@ static void meson_pwm_enable(struct meson_pwm *meson, struct pwm_device *pwm) err = clk_set_rate(channel->clk, channel->rate); if (err) - dev_err(meson->chip.dev, "setting clock rate failed\n"); + dev_err(pwmchip_parent(chip), "setting clock rate failed\n"); spin_lock_irqsave(&meson->lock, flags); @@ -230,8 +233,9 @@ static void meson_pwm_enable(struct meson_pwm *meson, struct pwm_device *pwm) spin_unlock_irqrestore(&meson->lock, flags); } -static void meson_pwm_disable(struct meson_pwm *meson, struct pwm_device *pwm) +static void meson_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm) { + struct meson_pwm *meson = to_meson_pwm(chip); unsigned long flags; u32 value; @@ -269,16 +273,16 @@ static int meson_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, channel->hi = ~0; channel->lo = 0; - meson_pwm_enable(meson, pwm); + meson_pwm_enable(chip, pwm); } else { - meson_pwm_disable(meson, pwm); + meson_pwm_disable(chip, pwm); } } else { - err = meson_pwm_calc(meson, pwm, state); + err = meson_pwm_calc(chip, pwm, state); if (err < 0) return err; - meson_pwm_enable(meson, pwm); + meson_pwm_enable(chip, pwm); } return 0; @@ -432,10 +436,11 @@ static const struct of_device_id meson_pwm_matches[] = { }; MODULE_DEVICE_TABLE(of, meson_pwm_matches); -static int meson_pwm_init_channels(struct meson_pwm *meson) +static int meson_pwm_init_channels(struct pwm_chip *chip) { + struct meson_pwm *meson = to_meson_pwm(chip); struct clk_parent_data mux_parent_data[MESON_MAX_MUX_PARENTS] = {}; - struct device *dev = meson->chip.dev; + struct device *dev = pwmchip_parent(chip); unsigned int i; char name[255]; int err; @@ -445,7 +450,7 @@ static int meson_pwm_init_channels(struct meson_pwm *meson) mux_parent_data[i].name = meson->data->parent_names[i]; } - for (i = 0; i < meson->chip.npwm; i++) { + for (i = 0; i < chip->npwm; i++) { struct meson_pwm_channel *channel = &meson->channels[i]; struct clk_parent_data div_parent = {}, gate_parent = {}; struct clk_init_data init = {}; @@ -543,7 +548,7 @@ static int meson_pwm_probe(struct platform_device *pdev) meson->data = of_device_get_match_data(&pdev->dev); - err = meson_pwm_init_channels(meson); + err = meson_pwm_init_channels(&meson->chip); if (err < 0) return err; diff --git a/drivers/pwm/pwm-pxa.c b/drivers/pwm/pwm-pxa.c index 76685f926c758..61b74fa1d3481 100644 --- a/drivers/pwm/pwm-pxa.c +++ b/drivers/pwm/pwm-pxa.c @@ -180,10 +180,8 @@ static int pwm_probe(struct platform_device *pdev) pc->chip.ops = &pxa_pwm_ops; pc->chip.npwm = (id->driver_data & HAS_SECONDARY_PWM) ? 2 : 1; - if (IS_ENABLED(CONFIG_OF)) { + if (IS_ENABLED(CONFIG_OF)) pc->chip.of_xlate = of_pwm_single_xlate; - pc->chip.of_pwm_n_cells = 1; - } pc->mmio_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pc->mmio_base)) diff --git a/drivers/pwm/pwm-sti.c b/drivers/pwm/pwm-sti.c index 6cf55cf34d39f..f3df7b1895d35 100644 --- a/drivers/pwm/pwm-sti.c +++ b/drivers/pwm/pwm-sti.c @@ -395,8 +395,17 @@ static int sti_pwm_capture(struct pwm_chip *chip, struct pwm_device *pwm, static int sti_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, const struct pwm_state *state) { + struct sti_pwm_chip *pc = to_sti_pwmchip(chip); + struct sti_pwm_compat_data *cdata = pc->cdata; + struct device *dev = pc->dev; int err; + if (pwm->hwpwm >= cdata->pwm_num_devs) { + dev_err(dev, "device %u is not valid for pwm mode\n", + pwm->hwpwm); + return -EINVAL; + } + if (state->polarity != PWM_POLARITY_NORMAL) return -EINVAL; @@ -561,6 +570,7 @@ static int sti_pwm_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct sti_pwm_compat_data *cdata; + struct pwm_chip *chip; struct sti_pwm_chip *pc; unsigned int i; int irq, ret; @@ -568,6 +578,7 @@ static int sti_pwm_probe(struct platform_device *pdev) pc = devm_kzalloc(dev, sizeof(*pc), GFP_KERNEL); if (!pc) return -ENOMEM; + chip = &pc->chip; cdata = devm_kzalloc(dev, sizeof(*cdata), GFP_KERNEL); if (!cdata) @@ -613,40 +624,28 @@ static int sti_pwm_probe(struct platform_device *pdev) return ret; if (cdata->pwm_num_devs) { - pc->pwm_clk = of_clk_get_by_name(dev->of_node, "pwm"); + pc->pwm_clk = devm_clk_get_prepared(dev, "pwm"); if (IS_ERR(pc->pwm_clk)) { dev_err(dev, "failed to get PWM clock\n"); return PTR_ERR(pc->pwm_clk); } - - ret = clk_prepare(pc->pwm_clk); - if (ret) { - dev_err(dev, "failed to prepare clock\n"); - return ret; - } } if (cdata->cpt_num_devs) { - pc->cpt_clk = of_clk_get_by_name(dev->of_node, "capture"); + pc->cpt_clk = devm_clk_get_prepared(dev, "capture"); if (IS_ERR(pc->cpt_clk)) { dev_err(dev, "failed to get PWM capture clock\n"); return PTR_ERR(pc->cpt_clk); } - ret = clk_prepare(pc->cpt_clk); - if (ret) { - dev_err(dev, "failed to prepare clock\n"); - return ret; - } - cdata->ddata = devm_kzalloc(dev, cdata->cpt_num_devs * sizeof(*cdata->ddata), GFP_KERNEL); if (!cdata->ddata) return -ENOMEM; } - pc->chip.dev = dev; - pc->chip.ops = &sti_pwm_ops; - pc->chip.npwm = pc->cdata->pwm_num_devs; + chip->dev = dev; + chip->ops = &sti_pwm_ops; + chip->npwm = max(cdata->pwm_num_devs, cdata->cpt_num_devs); for (i = 0; i < cdata->cpt_num_devs; i++) { struct sti_cpt_ddata *ddata = &cdata->ddata[i]; @@ -655,26 +654,7 @@ static int sti_pwm_probe(struct platform_device *pdev) mutex_init(&ddata->lock); } - ret = pwmchip_add(&pc->chip); - if (ret < 0) { - clk_unprepare(pc->pwm_clk); - clk_unprepare(pc->cpt_clk); - return ret; - } - - platform_set_drvdata(pdev, pc); - - return 0; -} - -static void sti_pwm_remove(struct platform_device *pdev) -{ - struct sti_pwm_chip *pc = platform_get_drvdata(pdev); - - pwmchip_remove(&pc->chip); - - clk_unprepare(pc->pwm_clk); - clk_unprepare(pc->cpt_clk); + return devm_pwmchip_add(dev, chip); } static const struct of_device_id sti_pwm_of_match[] = { @@ -689,7 +669,6 @@ static struct platform_driver sti_pwm_driver = { .of_match_table = sti_pwm_of_match, }, .probe = sti_pwm_probe, - .remove_new = sti_pwm_remove, }; module_platform_driver(sti_pwm_driver); diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c index 1698609d91c8a..3f434a771fb52 100644 --- a/drivers/pwm/sysfs.c +++ b/drivers/pwm/sysfs.c @@ -509,10 +509,10 @@ void pwmchip_sysfs_export(struct pwm_chip *chip) * If device_create() fails the pwm_chip is still usable by * the kernel it's just not exported. */ - parent = device_create(&pwm_class, chip->dev, MKDEV(0, 0), chip, + parent = device_create(&pwm_class, pwmchip_parent(chip), MKDEV(0, 0), chip, "pwmchip%d", chip->id); if (IS_ERR(parent)) { - dev_warn(chip->dev, + dev_warn(pwmchip_parent(chip), "device_create failed for pwm_chip sysfs export\n"); } } diff --git a/drivers/regulator/bd71815-regulator.c b/drivers/regulator/bd71815-regulator.c index 26192d55a6858..79fbb45297f6b 100644 --- a/drivers/regulator/bd71815-regulator.c +++ b/drivers/regulator/bd71815-regulator.c @@ -256,7 +256,7 @@ static int buck12_set_hw_dvs_levels(struct device_node *np, * 10: 2.50mV/usec 10mV 4uS * 11: 1.25mV/usec 10mV 8uS */ -static const unsigned int bd7181x_ramp_table[] = { 1250, 2500, 5000, 10000 }; +static const unsigned int bd7181x_ramp_table[] = { 10000, 5000, 2500, 1250 }; static int bd7181x_led_set_current_limit(struct regulator_dev *rdev, int min_uA, int max_uA) diff --git a/drivers/regulator/bd71828-regulator.c b/drivers/regulator/bd71828-regulator.c index 08d4ee369287e..dd871ffe979c3 100644 --- a/drivers/regulator/bd71828-regulator.c +++ b/drivers/regulator/bd71828-regulator.c @@ -206,14 +206,11 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { .suspend_reg = BD71828_REG_BUCK1_SUSP_VOLT, .suspend_mask = BD71828_MASK_BUCK1267_VOLT, .suspend_on_mask = BD71828_MASK_SUSP_EN, - .lpsr_on_mask = BD71828_MASK_LPSR_EN, /* * LPSR voltage is same as SUSPEND voltage. Allow - * setting it so that regulator can be set enabled at - * LPSR state + * only enabling/disabling regulator for LPSR state */ - .lpsr_reg = BD71828_REG_BUCK1_SUSP_VOLT, - .lpsr_mask = BD71828_MASK_BUCK1267_VOLT, + .lpsr_on_mask = BD71828_MASK_LPSR_EN, }, .reg_inits = buck1_inits, .reg_init_amnt = ARRAY_SIZE(buck1_inits), @@ -288,13 +285,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_BUCK3_VOLT, - .idle_reg = BD71828_REG_BUCK3_VOLT, - .suspend_reg = BD71828_REG_BUCK3_VOLT, - .lpsr_reg = BD71828_REG_BUCK3_VOLT, .run_mask = BD71828_MASK_BUCK3_VOLT, - .idle_mask = BD71828_MASK_BUCK3_VOLT, - .suspend_mask = BD71828_MASK_BUCK3_VOLT, - .lpsr_mask = BD71828_MASK_BUCK3_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -329,13 +320,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_BUCK4_VOLT, - .idle_reg = BD71828_REG_BUCK4_VOLT, - .suspend_reg = BD71828_REG_BUCK4_VOLT, - .lpsr_reg = BD71828_REG_BUCK4_VOLT, .run_mask = BD71828_MASK_BUCK4_VOLT, - .idle_mask = BD71828_MASK_BUCK4_VOLT, - .suspend_mask = BD71828_MASK_BUCK4_VOLT, - .lpsr_mask = BD71828_MASK_BUCK4_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -370,13 +355,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_BUCK5_VOLT, - .idle_reg = BD71828_REG_BUCK5_VOLT, - .suspend_reg = BD71828_REG_BUCK5_VOLT, - .lpsr_reg = BD71828_REG_BUCK5_VOLT, .run_mask = BD71828_MASK_BUCK5_VOLT, - .idle_mask = BD71828_MASK_BUCK5_VOLT, - .suspend_mask = BD71828_MASK_BUCK5_VOLT, - .lpsr_mask = BD71828_MASK_BUCK5_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -493,13 +472,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO1_VOLT, - .idle_reg = BD71828_REG_LDO1_VOLT, - .suspend_reg = BD71828_REG_LDO1_VOLT, - .lpsr_reg = BD71828_REG_LDO1_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -533,13 +506,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO2_VOLT, - .idle_reg = BD71828_REG_LDO2_VOLT, - .suspend_reg = BD71828_REG_LDO2_VOLT, - .lpsr_reg = BD71828_REG_LDO2_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -573,13 +540,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO3_VOLT, - .idle_reg = BD71828_REG_LDO3_VOLT, - .suspend_reg = BD71828_REG_LDO3_VOLT, - .lpsr_reg = BD71828_REG_LDO3_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -614,13 +575,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO4_VOLT, - .idle_reg = BD71828_REG_LDO4_VOLT, - .suspend_reg = BD71828_REG_LDO4_VOLT, - .lpsr_reg = BD71828_REG_LDO4_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -655,13 +610,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { ROHM_DVS_LEVEL_SUSPEND | ROHM_DVS_LEVEL_LPSR, .run_reg = BD71828_REG_LDO5_VOLT, - .idle_reg = BD71828_REG_LDO5_VOLT, - .suspend_reg = BD71828_REG_LDO5_VOLT, - .lpsr_reg = BD71828_REG_LDO5_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, @@ -720,9 +669,6 @@ static const struct bd71828_regulator_data bd71828_rdata[] = { .suspend_reg = BD71828_REG_LDO7_VOLT, .lpsr_reg = BD71828_REG_LDO7_VOLT, .run_mask = BD71828_MASK_LDO_VOLT, - .idle_mask = BD71828_MASK_LDO_VOLT, - .suspend_mask = BD71828_MASK_LDO_VOLT, - .lpsr_mask = BD71828_MASK_LDO_VOLT, .idle_on_mask = BD71828_MASK_IDLE_EN, .suspend_on_mask = BD71828_MASK_SUSP_EN, .lpsr_on_mask = BD71828_MASK_LPSR_EN, diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index a968dabb48f55..b92092022bf39 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -1911,19 +1911,24 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, } } - if (err != -EEXIST) + if (err != -EEXIST) { regulator->debugfs = debugfs_create_dir(supply_name, rdev->debugfs); - if (IS_ERR(regulator->debugfs)) - rdev_dbg(rdev, "Failed to create debugfs directory\n"); + if (IS_ERR(regulator->debugfs)) { + rdev_dbg(rdev, "Failed to create debugfs directory\n"); + regulator->debugfs = NULL; + } + } - debugfs_create_u32("uA_load", 0444, regulator->debugfs, - ®ulator->uA_load); - debugfs_create_u32("min_uV", 0444, regulator->debugfs, - ®ulator->voltage[PM_SUSPEND_ON].min_uV); - debugfs_create_u32("max_uV", 0444, regulator->debugfs, - ®ulator->voltage[PM_SUSPEND_ON].max_uV); - debugfs_create_file("constraint_flags", 0444, regulator->debugfs, - regulator, &constraint_flags_fops); + if (regulator->debugfs) { + debugfs_create_u32("uA_load", 0444, regulator->debugfs, + ®ulator->uA_load); + debugfs_create_u32("min_uV", 0444, regulator->debugfs, + ®ulator->voltage[PM_SUSPEND_ON].min_uV); + debugfs_create_u32("max_uV", 0444, regulator->debugfs, + ®ulator->voltage[PM_SUSPEND_ON].max_uV); + debugfs_create_file("constraint_flags", 0444, regulator->debugfs, + regulator, &constraint_flags_fops); + } /* * Check now if the regulator is an always on regulator - if @@ -3331,6 +3336,7 @@ struct regmap *regulator_get_regmap(struct regulator *regulator) return map ? map : ERR_PTR(-EOPNOTSUPP); } +EXPORT_SYMBOL_GPL(regulator_get_regmap); /** * regulator_get_hardware_vsel_register - get the HW voltage selector register diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c index d492683365532..6e1ace660b8cf 100644 --- a/drivers/regulator/helpers.c +++ b/drivers/regulator/helpers.c @@ -161,6 +161,32 @@ int regulator_get_voltage_sel_pickable_regmap(struct regulator_dev *rdev) } EXPORT_SYMBOL_GPL(regulator_get_voltage_sel_pickable_regmap); +static int write_separate_vsel_and_range(struct regulator_dev *rdev, + unsigned int sel, unsigned int range) +{ + bool range_updated; + int ret; + + ret = regmap_update_bits_base(rdev->regmap, rdev->desc->vsel_range_reg, + rdev->desc->vsel_range_mask, + range, &range_updated, false, false); + if (ret) + return ret; + + /* + * Some PMICs treat the vsel_reg same as apply-bit. Force it to be + * written if the range changed, even if the old selector was same as + * the new one + */ + if (rdev->desc->range_applied_by_vsel && range_updated) + return regmap_write_bits(rdev->regmap, + rdev->desc->vsel_reg, + rdev->desc->vsel_mask, sel); + + return regmap_update_bits(rdev->regmap, rdev->desc->vsel_reg, + rdev->desc->vsel_mask, sel); +} + /** * regulator_set_voltage_sel_pickable_regmap - pickable range set_voltage_sel * @@ -199,21 +225,12 @@ int regulator_set_voltage_sel_pickable_regmap(struct regulator_dev *rdev, range = rdev->desc->linear_range_selectors_bitfield[i]; range <<= ffs(rdev->desc->vsel_range_mask) - 1; - if (rdev->desc->vsel_reg == rdev->desc->vsel_range_reg) { - ret = regmap_update_bits(rdev->regmap, - rdev->desc->vsel_reg, + if (rdev->desc->vsel_reg == rdev->desc->vsel_range_reg) + ret = regmap_update_bits(rdev->regmap, rdev->desc->vsel_reg, rdev->desc->vsel_range_mask | rdev->desc->vsel_mask, sel | range); - } else { - ret = regmap_update_bits(rdev->regmap, - rdev->desc->vsel_range_reg, - rdev->desc->vsel_range_mask, range); - if (ret) - return ret; - - ret = regmap_update_bits(rdev->regmap, rdev->desc->vsel_reg, - rdev->desc->vsel_mask, sel); - } + else + ret = write_separate_vsel_and_range(rdev, sel, range); if (ret) return ret; diff --git a/drivers/regulator/irq_helpers.c b/drivers/regulator/irq_helpers.c index fe7ae0f3f46af..5ab1a0befe12f 100644 --- a/drivers/regulator/irq_helpers.c +++ b/drivers/regulator/irq_helpers.c @@ -352,6 +352,9 @@ void *regulator_irq_helper(struct device *dev, h->irq = irq; h->desc = *d; + h->desc.name = devm_kstrdup(dev, d->name, GFP_KERNEL); + if (!h->desc.name) + return ERR_PTR(-ENOMEM); ret = init_rdev_state(dev, h, rdev, common_errs, per_rdev_errs, rdev_amount); diff --git a/drivers/regulator/mt6360-regulator.c b/drivers/regulator/mt6360-regulator.c index ad6587a378d09..24cc9fc94e900 100644 --- a/drivers/regulator/mt6360-regulator.c +++ b/drivers/regulator/mt6360-regulator.c @@ -319,15 +319,15 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } } -#define MT6360_REGULATOR_DESC(_name, _sname, ereg, emask, vreg, vmask, \ - mreg, mmask, streg, stmask, vranges, \ - vcnts, offon_delay, irq_tbls) \ +#define MT6360_REGULATOR_DESC(match, _name, _sname, ereg, emask, vreg, \ + vmask, mreg, mmask, streg, stmask, \ + vranges, vcnts, offon_delay, irq_tbls) \ { \ .desc = { \ .name = #_name, \ .supply_name = #_sname, \ .id = MT6360_REGULATOR_##_name, \ - .of_match = of_match_ptr(#_name), \ + .of_match = of_match_ptr(match), \ .regulators_node = of_match_ptr("regulator"), \ .of_map_mode = mt6360_regulator_of_map_mode, \ .owner = THIS_MODULE, \ @@ -351,21 +351,29 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } static const struct mt6360_regulator_desc mt6360_regulator_descs[] = { - MT6360_REGULATOR_DESC(BUCK1, BUCK1_VIN, 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04, + MT6360_REGULATOR_DESC("buck1", BUCK1, BUCK1_VIN, + 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04, buck_vout_ranges, 256, 0, buck1_irq_tbls), - MT6360_REGULATOR_DESC(BUCK2, BUCK2_VIN, 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04, + MT6360_REGULATOR_DESC("buck2", BUCK2, BUCK2_VIN, + 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04, buck_vout_ranges, 256, 0, buck2_irq_tbls), - MT6360_REGULATOR_DESC(LDO6, LDO_VIN3, 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04, + MT6360_REGULATOR_DESC("ldo6", LDO6, LDO_VIN3, + 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04, ldo_vout_ranges1, 256, 0, ldo6_irq_tbls), - MT6360_REGULATOR_DESC(LDO7, LDO_VIN3, 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04, + MT6360_REGULATOR_DESC("ldo7", LDO7, LDO_VIN3, + 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04, ldo_vout_ranges1, 256, 0, ldo7_irq_tbls), - MT6360_REGULATOR_DESC(LDO1, LDO_VIN1, 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04, + MT6360_REGULATOR_DESC("ldo1", LDO1, LDO_VIN1, + 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04, ldo_vout_ranges2, 256, 0, ldo1_irq_tbls), - MT6360_REGULATOR_DESC(LDO2, LDO_VIN1, 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04, + MT6360_REGULATOR_DESC("ldo2", LDO2, LDO_VIN1, + 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04, ldo_vout_ranges2, 256, 0, ldo2_irq_tbls), - MT6360_REGULATOR_DESC(LDO3, LDO_VIN1, 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04, + MT6360_REGULATOR_DESC("ldo3", LDO3, LDO_VIN1, + 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04, ldo_vout_ranges2, 256, 100, ldo3_irq_tbls), - MT6360_REGULATOR_DESC(LDO5, LDO_VIN2, 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04, + MT6360_REGULATOR_DESC("ldo5", LDO5, LDO_VIN2, + 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04, ldo_vout_ranges3, 128, 100, ldo5_irq_tbls), }; diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c index 656fe330d38f0..063e12c08e75f 100644 --- a/drivers/regulator/qcom-refgen-regulator.c +++ b/drivers/regulator/qcom-refgen-regulator.c @@ -140,6 +140,7 @@ static const struct of_device_id qcom_refgen_match_table[] = { { .compatible = "qcom,sm8250-refgen-regulator", .data = &sm8250_refgen_desc }, { } }; +MODULE_DEVICE_TABLE(of, qcom_refgen_match_table); static struct platform_driver qcom_refgen_driver = { .probe = qcom_refgen_probe, diff --git a/drivers/regulator/tps6287x-regulator.c b/drivers/regulator/tps6287x-regulator.c index 9b7c3d77789e3..3c9d79e003e4b 100644 --- a/drivers/regulator/tps6287x-regulator.c +++ b/drivers/regulator/tps6287x-regulator.c @@ -115,6 +115,7 @@ static struct regulator_desc tps6287x_reg = { .vsel_mask = 0xFF, .vsel_range_reg = TPS6287X_CTRL2, .vsel_range_mask = TPS6287X_CTRL2_VRANGE, + .range_applied_by_vsel = true, .ramp_reg = TPS6287X_CTRL1, .ramp_mask = TPS6287X_CTRL1_VRAMP, .ramp_delay_table = tps6287x_ramp_table, diff --git a/drivers/regulator/tps65132-regulator.c b/drivers/regulator/tps65132-regulator.c index a06f5f2d79329..9c2f0dd42613d 100644 --- a/drivers/regulator/tps65132-regulator.c +++ b/drivers/regulator/tps65132-regulator.c @@ -267,10 +267,17 @@ static const struct i2c_device_id tps65132_id[] = { }; MODULE_DEVICE_TABLE(i2c, tps65132_id); +static const struct of_device_id __maybe_unused tps65132_of_match[] = { + { .compatible = "ti,tps65132" }, + {}, +}; +MODULE_DEVICE_TABLE(of, tps65132_of_match); + static struct i2c_driver tps65132_i2c_driver = { .driver = { .name = "tps65132", .probe_type = PROBE_PREFER_ASYNCHRONOUS, + .of_match_table = of_match_ptr(tps65132_of_match), }, .probe = tps65132_probe, .id_table = tps65132_id, diff --git a/drivers/regulator/tps6594-regulator.c b/drivers/regulator/tps6594-regulator.c index b7f0c87797577..5fad61785e72f 100644 --- a/drivers/regulator/tps6594-regulator.c +++ b/drivers/regulator/tps6594-regulator.c @@ -287,30 +287,30 @@ static struct tps6594_regulator_irq_type *tps6594_ldos_irq_types[] = { static const struct regulator_desc multi_regs[] = { TPS6594_REGULATOR("BUCK12", "buck12", TPS6594_BUCK_1, REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_VOUT_1(1), + TPS6594_REG_BUCKX_VOUT_1(0), TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_CTRL(1), + TPS6594_REG_BUCKX_CTRL(0), TPS6594_BIT_BUCK_EN, 0, 0, bucks_ranges, 4, 4000, 0, NULL, 0, 0), TPS6594_REGULATOR("BUCK34", "buck34", TPS6594_BUCK_3, REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_VOUT_1(3), + TPS6594_REG_BUCKX_VOUT_1(2), TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_CTRL(3), + TPS6594_REG_BUCKX_CTRL(2), TPS6594_BIT_BUCK_EN, 0, 0, bucks_ranges, 4, 0, 0, NULL, 0, 0), TPS6594_REGULATOR("BUCK123", "buck123", TPS6594_BUCK_1, REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_VOUT_1(1), + TPS6594_REG_BUCKX_VOUT_1(0), TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_CTRL(1), + TPS6594_REG_BUCKX_CTRL(0), TPS6594_BIT_BUCK_EN, 0, 0, bucks_ranges, 4, 4000, 0, NULL, 0, 0), TPS6594_REGULATOR("BUCK1234", "buck1234", TPS6594_BUCK_1, REGULATOR_VOLTAGE, tps6594_bucks_ops, TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_VOUT_1(1), + TPS6594_REG_BUCKX_VOUT_1(0), TPS6594_MASK_BUCKS_VSET, - TPS6594_REG_BUCKX_CTRL(1), + TPS6594_REG_BUCKX_CTRL(0), TPS6594_BIT_BUCK_EN, 0, 0, bucks_ranges, 4, 4000, 0, NULL, 0, 0), }; diff --git a/drivers/regulator/userspace-consumer.c b/drivers/regulator/userspace-consumer.c index 53d1b9d6f69c5..86a626a4f610a 100644 --- a/drivers/regulator/userspace-consumer.c +++ b/drivers/regulator/userspace-consumer.c @@ -208,6 +208,7 @@ static const struct of_device_id regulator_userspace_consumer_of_match[] = { { .compatible = "regulator-output", }, {}, }; +MODULE_DEVICE_TABLE(of, regulator_userspace_consumer_of_match); static struct platform_driver regulator_userspace_consumer_driver = { .probe = regulator_userspace_consumer_probe, diff --git a/drivers/regulator/vqmmc-ipq4019-regulator.c b/drivers/regulator/vqmmc-ipq4019-regulator.c index 086da36abc0b4..4955616517ce9 100644 --- a/drivers/regulator/vqmmc-ipq4019-regulator.c +++ b/drivers/regulator/vqmmc-ipq4019-regulator.c @@ -84,6 +84,7 @@ static const struct of_device_id regulator_ipq4019_of_match[] = { { .compatible = "qcom,vqmmc-ipq4019-regulator", }, {}, }; +MODULE_DEVICE_TABLE(of, regulator_ipq4019_of_match); static struct platform_driver ipq4019_regulator_driver = { .probe = ipq4019_regulator_probe, diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c index a35409eda0cf2..67518291a8ad6 100644 --- a/drivers/remoteproc/mtk_scp.c +++ b/drivers/remoteproc/mtk_scp.c @@ -132,7 +132,7 @@ static int scp_elf_read_ipi_buf_addr(struct mtk_scp *scp, static int scp_ipi_init(struct mtk_scp *scp, const struct firmware *fw) { int ret; - size_t offset; + size_t buf_sz, offset; /* read the ipi buf addr from FW itself first */ ret = scp_elf_read_ipi_buf_addr(scp, fw, &offset); @@ -144,6 +144,14 @@ static int scp_ipi_init(struct mtk_scp *scp, const struct firmware *fw) } dev_info(scp->dev, "IPI buf addr %#010zx\n", offset); + /* Make sure IPI buffer fits in the L2TCM range assigned to this core */ + buf_sz = sizeof(*scp->recv_buf) + sizeof(*scp->send_buf); + + if (scp->sram_size < buf_sz + offset) { + dev_err(scp->dev, "IPI buffer does not fit in SRAM.\n"); + return -EOVERFLOW; + } + scp->recv_buf = (struct mtk_share_obj __iomem *) (scp->sram_base + offset); scp->send_buf = (struct mtk_share_obj __iomem *) diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c index 83d76915a6ad6..25b66b113b695 100644 --- a/drivers/remoteproc/remoteproc_virtio.c +++ b/drivers/remoteproc/remoteproc_virtio.c @@ -351,6 +351,9 @@ static void rproc_virtio_dev_release(struct device *dev) kfree(vdev); + of_reserved_mem_device_release(&rvdev->pdev->dev); + dma_release_coherent_memory(&rvdev->pdev->dev); + put_device(&rvdev->pdev->dev); } @@ -584,9 +587,6 @@ static void rproc_virtio_remove(struct platform_device *pdev) rproc_remove_subdev(rproc, &rvdev->subdev); rproc_remove_rvdev(rvdev); - of_reserved_mem_device_release(&pdev->dev); - dma_release_coherent_memory(&pdev->dev); - put_device(&rproc->dev); } diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index 4f469f0bcf8b2..10b442c6f6323 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -120,7 +120,7 @@ static int stm32_rproc_mem_alloc(struct rproc *rproc, void *va; dev_dbg(dev, "map memory: %pad+%zx\n", &mem->dma, mem->len); - va = ioremap_wc(mem->dma, mem->len); + va = (__force void *)ioremap_wc(mem->dma, mem->len); if (IS_ERR_OR_NULL(va)) { dev_err(dev, "Unable to map memory region: %pad+0x%zx\n", &mem->dma, mem->len); @@ -137,7 +137,7 @@ static int stm32_rproc_mem_release(struct rproc *rproc, struct rproc_mem_entry *mem) { dev_dbg(rproc->dev.parent, "unmap memory: %pa\n", &mem->dma); - iounmap(mem->va); + iounmap((__force __iomem void *)mem->va); return 0; } @@ -657,7 +657,7 @@ stm32_rproc_get_loaded_rsc_table(struct rproc *rproc, size_t *table_sz) * entire area by overwriting it with the initial values stored in rproc->clean_table. */ *table_sz = RSC_TBL_SIZE; - return (struct resource_table *)ddata->rsc_va; + return (__force struct resource_table *)ddata->rsc_va; } static const struct rproc_ops st_rproc_ops = { diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c index ad3415a3851b2..50e486bcfa103 100644 --- a/drivers/remoteproc/ti_k3_r5_remoteproc.c +++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c @@ -103,12 +103,14 @@ struct k3_r5_soc_data { * @dev: cached device pointer * @mode: Mode to configure the Cluster - Split or LockStep * @cores: list of R5 cores within the cluster + * @core_transition: wait queue to sync core state changes * @soc_data: SoC-specific feature data for a R5FSS */ struct k3_r5_cluster { struct device *dev; enum cluster_mode mode; struct list_head cores; + wait_queue_head_t core_transition; const struct k3_r5_soc_data *soc_data; }; @@ -128,6 +130,7 @@ struct k3_r5_cluster { * @atcm_enable: flag to control ATCM enablement * @btcm_enable: flag to control BTCM enablement * @loczrama: flag to dictate which TCM is at device address 0x0 + * @released_from_reset: flag to signal when core is out of reset */ struct k3_r5_core { struct list_head elem; @@ -144,6 +147,7 @@ struct k3_r5_core { u32 atcm_enable; u32 btcm_enable; u32 loczrama; + bool released_from_reset; }; /** @@ -460,6 +464,8 @@ static int k3_r5_rproc_prepare(struct rproc *rproc) ret); return ret; } + core->released_from_reset = true; + wake_up_interruptible(&cluster->core_transition); /* * Newer IP revisions like on J7200 SoCs support h/w auto-initialization @@ -542,7 +548,7 @@ static int k3_r5_rproc_start(struct rproc *rproc) struct k3_r5_rproc *kproc = rproc->priv; struct k3_r5_cluster *cluster = kproc->cluster; struct device *dev = kproc->dev; - struct k3_r5_core *core; + struct k3_r5_core *core0, *core; u32 boot_addr; int ret; @@ -568,6 +574,16 @@ static int k3_r5_rproc_start(struct rproc *rproc) goto unroll_core_run; } } else { + /* do not allow core 1 to start before core 0 */ + core0 = list_first_entry(&cluster->cores, struct k3_r5_core, + elem); + if (core != core0 && core0->rproc->state == RPROC_OFFLINE) { + dev_err(dev, "%s: can not start core 1 before core 0\n", + __func__); + ret = -EPERM; + goto put_mbox; + } + ret = k3_r5_core_run(core); if (ret) goto put_mbox; @@ -613,7 +629,8 @@ static int k3_r5_rproc_stop(struct rproc *rproc) { struct k3_r5_rproc *kproc = rproc->priv; struct k3_r5_cluster *cluster = kproc->cluster; - struct k3_r5_core *core = kproc->core; + struct device *dev = kproc->dev; + struct k3_r5_core *core1, *core = kproc->core; int ret; /* halt all applicable cores */ @@ -626,6 +643,16 @@ static int k3_r5_rproc_stop(struct rproc *rproc) } } } else { + /* do not allow core 0 to stop before core 1 */ + core1 = list_last_entry(&cluster->cores, struct k3_r5_core, + elem); + if (core != core1 && core1->rproc->state != RPROC_OFFLINE) { + dev_err(dev, "%s: can not stop core 0 before core 1\n", + __func__); + ret = -EPERM; + goto out; + } + ret = k3_r5_core_halt(core); if (ret) goto out; @@ -1140,6 +1167,12 @@ static int k3_r5_rproc_configure_mode(struct k3_r5_rproc *kproc) return ret; } + /* + * Skip the waiting mechanism for sequential power-on of cores if the + * core has already been booted by another entity. + */ + core->released_from_reset = c_state; + ret = ti_sci_proc_get_status(core->tsp, &boot_vec, &cfg, &ctrl, &stat); if (ret < 0) { @@ -1280,6 +1313,26 @@ static int k3_r5_cluster_rproc_init(struct platform_device *pdev) cluster->mode == CLUSTER_MODE_SINGLECPU || cluster->mode == CLUSTER_MODE_SINGLECORE) break; + + /* + * R5 cores require to be powered on sequentially, core0 + * should be in higher power state than core1 in a cluster + * So, wait for current core to power up before proceeding + * to next core and put timeout of 2sec for each core. + * + * This waiting mechanism is necessary because + * rproc_auto_boot_callback() for core1 can be called before + * core0 due to thread execution order. + */ + ret = wait_event_interruptible_timeout(cluster->core_transition, + core->released_from_reset, + msecs_to_jiffies(2000)); + if (ret <= 0) { + dev_err(dev, + "Timed out waiting for %s core to power up!\n", + rproc->name); + return ret; + } } return 0; @@ -1709,6 +1762,7 @@ static int k3_r5_probe(struct platform_device *pdev) cluster->dev = dev; cluster->soc_data = data; INIT_LIST_HEAD(&cluster->cores); + init_waitqueue_head(&cluster->core_transition); ret = of_property_read_u32(np, "ti,cluster-mode", &cluster->mode); if (ret < 0 && ret != -EINVAL) { diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index e37a4341f442d..c63e32d012f23 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1858,7 +1858,8 @@ config RTC_DRV_MT2712 config RTC_DRV_MT6397 tristate "MediaTek PMIC based RTC" - depends on MFD_MT6397 || (COMPILE_TEST && IRQ_DOMAIN) + depends on MFD_MT6397 || COMPILE_TEST + select IRQ_DOMAIN help This selects the MediaTek(R) RTC driver. RTC is part of MediaTek MT6397 PMIC. You should enable MT6397 PMIC MFD before select diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/lib_test.c index d5caf36c56cdc..225c859d6da55 100644 --- a/drivers/rtc/lib_test.c +++ b/drivers/rtc/lib_test.c @@ -54,7 +54,7 @@ static void rtc_time64_to_tm_test_date_range(struct kunit *test) days = div_s64(secs, 86400); - #define FAIL_MSG "%d/%02d/%02d (%2d) : %ld", \ + #define FAIL_MSG "%d/%02d/%02d (%2d) : %lld", \ year, month, mday, yday, days KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG); diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c index 402fda8fd5488..a2441e5c2c74d 100644 --- a/drivers/rtc/rtc-max31335.c +++ b/drivers/rtc/rtc-max31335.c @@ -204,7 +204,7 @@ static bool max31335_volatile_reg(struct device *dev, unsigned int reg) return true; /* interrupt status register */ - if (reg == MAX31335_INT_EN1_A1IE) + if (reg == MAX31335_STATUS1) return true; /* temperature registers */ diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 7327e81352e9c..30851faade97b 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -8,9 +8,6 @@ * Copyright IBM Corp. 1999, 2009 */ -#define KMSG_COMPONENT "dasd" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt - #include #include #include @@ -3402,8 +3399,7 @@ static void dasd_generic_auto_online(void *data, async_cookie_t cookie) ret = ccw_device_set_online(cdev); if (ret) - pr_warn("%s: Setting the DASD online failed with rc=%d\n", - dev_name(&cdev->dev), ret); + dev_warn(&cdev->dev, "Setting the DASD online failed with rc=%d\n", ret); } /* @@ -3490,8 +3486,11 @@ int dasd_generic_set_online(struct ccw_device *cdev, { struct dasd_discipline *discipline; struct dasd_device *device; + struct device *dev; int rc; + dev = &cdev->dev; + /* first online clears initial online feature flag */ dasd_set_feature(cdev, DASD_FEATURE_INITIAL_ONLINE, 0); device = dasd_create_device(cdev); @@ -3504,11 +3503,10 @@ int dasd_generic_set_online(struct ccw_device *cdev, /* Try to load the required module. */ rc = request_module(DASD_DIAG_MOD); if (rc) { - pr_warn("%s Setting the DASD online failed " - "because the required module %s " - "could not be loaded (rc=%d)\n", - dev_name(&cdev->dev), DASD_DIAG_MOD, - rc); + dev_warn(dev, "Setting the DASD online failed " + "because the required module %s " + "could not be loaded (rc=%d)\n", + DASD_DIAG_MOD, rc); dasd_delete_device(device); return -ENODEV; } @@ -3516,8 +3514,7 @@ int dasd_generic_set_online(struct ccw_device *cdev, /* Module init could have failed, so check again here after * request_module(). */ if (!dasd_diag_discipline_pointer) { - pr_warn("%s Setting the DASD online failed because of missing DIAG discipline\n", - dev_name(&cdev->dev)); + dev_warn(dev, "Setting the DASD online failed because of missing DIAG discipline\n"); dasd_delete_device(device); return -ENODEV; } @@ -3527,37 +3524,33 @@ int dasd_generic_set_online(struct ccw_device *cdev, dasd_delete_device(device); return -EINVAL; } + device->base_discipline = base_discipline; if (!try_module_get(discipline->owner)) { - module_put(base_discipline->owner); dasd_delete_device(device); return -EINVAL; } - device->base_discipline = base_discipline; device->discipline = discipline; /* check_device will allocate block device if necessary */ rc = discipline->check_device(device); if (rc) { - pr_warn("%s Setting the DASD online with discipline %s failed with rc=%i\n", - dev_name(&cdev->dev), discipline->name, rc); - module_put(discipline->owner); - module_put(base_discipline->owner); + dev_warn(dev, "Setting the DASD online with discipline %s failed with rc=%i\n", + discipline->name, rc); dasd_delete_device(device); return rc; } dasd_set_target_state(device, DASD_STATE_ONLINE); if (device->state <= DASD_STATE_KNOWN) { - pr_warn("%s Setting the DASD online failed because of a missing discipline\n", - dev_name(&cdev->dev)); + dev_warn(dev, "Setting the DASD online failed because of a missing discipline\n"); rc = -ENODEV; dasd_set_target_state(device, DASD_STATE_NEW); if (device->block) dasd_free_block(device->block); dasd_delete_device(device); - } else - pr_debug("dasd_generic device %s found\n", - dev_name(&cdev->dev)); + } else { + dev_dbg(dev, "dasd_generic device found\n"); + } wait_event(dasd_init_waitq, _wait_for_device(device)); @@ -3568,10 +3561,13 @@ EXPORT_SYMBOL_GPL(dasd_generic_set_online); int dasd_generic_set_offline(struct ccw_device *cdev) { + int max_count, open_count, rc; struct dasd_device *device; struct dasd_block *block; - int max_count, open_count, rc; unsigned long flags; + struct device *dev; + + dev = &cdev->dev; rc = 0; spin_lock_irqsave(get_ccwdev_lock(cdev), flags); @@ -3592,11 +3588,10 @@ int dasd_generic_set_offline(struct ccw_device *cdev) open_count = atomic_read(&device->block->open_count); if (open_count > max_count) { if (open_count > 0) - pr_warn("%s: The DASD cannot be set offline with open count %i\n", - dev_name(&cdev->dev), open_count); + dev_warn(dev, "The DASD cannot be set offline with open count %i\n", + open_count); else - pr_warn("%s: The DASD cannot be set offline while it is in use\n", - dev_name(&cdev->dev)); + dev_warn(dev, "The DASD cannot be set offline while it is in use\n"); rc = -EBUSY; goto out_err; } @@ -3956,8 +3951,8 @@ static int dasd_handle_autoquiesce(struct dasd_device *device, if (dasd_eer_enabled(device)) dasd_eer_write(device, NULL, DASD_EER_AUTOQUIESCE); - pr_info("%s: The DASD has been put in the quiesce state\n", - dev_name(&device->cdev->dev)); + dev_info(&device->cdev->dev, + "The DASD has been put in the quiesce state\n"); dasd_device_set_stop_bits(device, DASD_STOPPED_QUIESCE); if (device->features & DASD_FEATURE_REQUEUEQUIESCE) diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c index 11c428f4c7cf9..7815e9bea69a1 100644 --- a/drivers/s390/char/sclp_cmd.c +++ b/drivers/s390/char/sclp_cmd.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -26,6 +27,7 @@ #include #include #include +#include #include "sclp.h" @@ -340,16 +342,38 @@ static int sclp_mem_notifier(struct notifier_block *nb, if (contains_standby_increment(start, start + size)) rc = -EPERM; break; - case MEM_ONLINE: - case MEM_CANCEL_OFFLINE: - break; - case MEM_GOING_ONLINE: + case MEM_PREPARE_ONLINE: + /* + * Access the altmap_start_pfn and altmap_nr_pages fields + * within the struct memory_notify specifically when dealing + * with only MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers. + * + * When altmap is in use, take the specified memory range + * online, which includes the altmap. + */ + if (arg->altmap_nr_pages) { + start = PFN_PHYS(arg->altmap_start_pfn); + size += PFN_PHYS(arg->altmap_nr_pages); + } rc = sclp_mem_change_state(start, size, 1); + if (rc || !arg->altmap_nr_pages) + break; + /* + * Set CMMA state to nodat here, since the struct page memory + * at the beginning of the memory block will not go through the + * buddy allocator later. + */ + __arch_set_page_nodat((void *)__va(start), arg->altmap_nr_pages); break; - case MEM_CANCEL_ONLINE: - sclp_mem_change_state(start, size, 0); - break; - case MEM_OFFLINE: + case MEM_FINISH_OFFLINE: + /* + * When altmap is in use, take the specified memory range + * offline, which includes the altmap. + */ + if (arg->altmap_nr_pages) { + start = PFN_PHYS(arg->altmap_start_pfn); + size += PFN_PHYS(arg->altmap_nr_pages); + } sclp_mem_change_state(start, size, 0); break; default: @@ -400,7 +424,9 @@ static void __init add_memory_merged(u16 rn) if (!size) goto skip_add; for (addr = start; addr < start + size; addr += block_size) - add_memory(0, addr, block_size, MHP_NONE); + add_memory(0, addr, block_size, + MACHINE_HAS_EDAT1 ? + MHP_MEMMAP_ON_MEMORY | MHP_OFFLINE_INACCESSIBLE : MHP_NONE); skip_add: first_rn = rn; num = 1; diff --git a/drivers/s390/cio/cio_inject.c b/drivers/s390/cio/cio_inject.c index 8613fa937237b..a2e771ebae8eb 100644 --- a/drivers/s390/cio/cio_inject.c +++ b/drivers/s390/cio/cio_inject.c @@ -95,7 +95,7 @@ static ssize_t crw_inject_write(struct file *file, const char __user *buf, return -EINVAL; } - buffer = vmemdup_user(buf, lbuf); + buffer = memdup_user_nul(buf, lbuf); if (IS_ERR(buffer)) return -ENOMEM; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 0cfb179e1bcb6..34b2567b8df49 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -363,10 +363,8 @@ int ccw_device_set_online(struct ccw_device *cdev) spin_lock_irq(cdev->ccwlock); ret = ccw_device_online(cdev); - spin_unlock_irq(cdev->ccwlock); - if (ret == 0) - wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev)); - else { + if (ret) { + spin_unlock_irq(cdev->ccwlock); CIO_MSG_EVENT(0, "ccw_device_online returned %d, " "device 0.%x.%04x\n", ret, cdev->private->dev_id.ssid, @@ -375,7 +373,12 @@ int ccw_device_set_online(struct ccw_device *cdev) put_device(&cdev->dev); return ret; } - spin_lock_irq(cdev->ccwlock); + /* Wait until a final state is reached */ + while (!dev_fsm_final_state(cdev)) { + spin_unlock_irq(cdev->ccwlock); + wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev)); + spin_lock_irq(cdev->ccwlock); + } /* Check if online processing was successful */ if ((cdev->private->state != DEV_STATE_ONLINE) && (cdev->private->state != DEV_STATE_W4SENSE)) { diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 9cde55730b65a..ebcb535809882 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -722,8 +722,8 @@ static void qdio_handle_activate_check(struct qdio_irq *irq_ptr, lgr_info_log(); } -static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, - int dstat) +static int qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, + int dstat, int dcc) { DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qest irq"); @@ -731,15 +731,18 @@ static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, goto error; if (dstat & ~(DEV_STAT_DEV_END | DEV_STAT_CHN_END)) goto error; + if (dcc == 1) + return -EAGAIN; if (!(dstat & DEV_STAT_DEV_END)) goto error; qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ESTABLISHED); - return; + return 0; error: DBF_ERROR("%4x EQ:error", irq_ptr->schid.sch_no); DBF_ERROR("ds: %2x cs:%2x", dstat, cstat); qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + return -EIO; } /* qdio interrupt handler */ @@ -748,7 +751,7 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, { struct qdio_irq *irq_ptr = cdev->private->qdio_data; struct subchannel_id schid; - int cstat, dstat; + int cstat, dstat, rc, dcc; if (!intparm || !irq_ptr) { ccw_device_get_schid(cdev, &schid); @@ -768,10 +771,12 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, qdio_irq_check_sense(irq_ptr, irb); cstat = irb->scsw.cmd.cstat; dstat = irb->scsw.cmd.dstat; + dcc = scsw_cmd_is_valid_cc(&irb->scsw) ? irb->scsw.cmd.cc : 0; + rc = 0; switch (irq_ptr->state) { case QDIO_IRQ_STATE_INACTIVE: - qdio_establish_handle_irq(irq_ptr, cstat, dstat); + rc = qdio_establish_handle_irq(irq_ptr, cstat, dstat, dcc); break; case QDIO_IRQ_STATE_CLEANUP: qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE); @@ -785,12 +790,25 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, if (cstat || dstat) qdio_handle_activate_check(irq_ptr, intparm, cstat, dstat); + else if (dcc == 1) + rc = -EAGAIN; break; case QDIO_IRQ_STATE_STOPPED: break; default: WARN_ON_ONCE(1); } + + if (rc == -EAGAIN) { + DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qint retry"); + rc = ccw_device_start(cdev, irq_ptr->ccw, intparm, 0, 0); + if (!rc) + return; + DBF_ERROR("%4x RETRY ERR", irq_ptr->schid.sch_no); + DBF_ERROR("rc:%4x", rc); + qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + } + wake_up(&cdev->private->wait_q); } diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h index 86993de253451..a4c5c6736b310 100644 --- a/drivers/s390/cio/trace.h +++ b/drivers/s390/cio/trace.h @@ -50,7 +50,7 @@ DECLARE_EVENT_CLASS(s390_class_schib, __entry->devno = schib->pmcw.dev; __entry->schib = *schib; __entry->pmcw_ena = schib->pmcw.ena; - __entry->pmcw_st = schib->pmcw.ena; + __entry->pmcw_st = schib->pmcw.st; __entry->pmcw_dnv = schib->pmcw.dnv; __entry->pmcw_dev = schib->pmcw.dev; __entry->pmcw_lpm = schib->pmcw.lpm; diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index f46dd6abacd70..ad6c1cf5bd251 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -83,14 +83,11 @@ EXPORT_SYMBOL(ap_perms); DEFINE_MUTEX(ap_perms_mutex); EXPORT_SYMBOL(ap_perms_mutex); -/* # of bus scans since init */ -static atomic64_t ap_scan_bus_count; - /* # of bindings complete since init */ static atomic64_t ap_bindings_complete_count = ATOMIC64_INIT(0); -/* completion for initial APQN bindings complete */ -static DECLARE_COMPLETION(ap_init_apqn_bindings_complete); +/* completion for APQN bindings complete */ +static DECLARE_COMPLETION(ap_apqn_bindings_complete); static struct ap_config_info *ap_qci_info; static struct ap_config_info *ap_qci_info_old; @@ -101,12 +98,16 @@ static struct ap_config_info *ap_qci_info_old; debug_info_t *ap_dbf_info; /* - * Workqueue timer for bus rescan. + * AP bus rescan related things. */ -static struct timer_list ap_config_timer; -static int ap_config_time = AP_CONFIG_TIME; -static void ap_scan_bus(struct work_struct *); -static DECLARE_WORK(ap_scan_work, ap_scan_bus); +static bool ap_scan_bus(void); +static bool ap_scan_bus_result; /* result of last ap_scan_bus() */ +static DEFINE_MUTEX(ap_scan_bus_mutex); /* mutex ap_scan_bus() invocations */ +static atomic64_t ap_scan_bus_count; /* counter ap_scan_bus() invocations */ +static int ap_scan_bus_time = AP_CONFIG_TIME; +static struct timer_list ap_scan_bus_timer; +static void ap_scan_bus_wq_callback(struct work_struct *); +static DECLARE_WORK(ap_scan_bus_work, ap_scan_bus_wq_callback); /* * Tasklet & timer for AP request polling and interrupts @@ -753,7 +754,7 @@ static void ap_calc_bound_apqns(unsigned int *apqns, unsigned int *bound) } /* - * After initial ap bus scan do check if all existing APQNs are + * After ap bus scan do check if all existing APQNs are * bound to device drivers. */ static void ap_check_bindings_complete(void) @@ -763,11 +764,11 @@ static void ap_check_bindings_complete(void) if (atomic64_read(&ap_scan_bus_count) >= 1) { ap_calc_bound_apqns(&apqns, &bound); if (bound == apqns) { - if (!completion_done(&ap_init_apqn_bindings_complete)) { - complete_all(&ap_init_apqn_bindings_complete); - AP_DBF_INFO("%s complete\n", __func__); + if (!completion_done(&ap_apqn_bindings_complete)) { + complete_all(&ap_apqn_bindings_complete); + ap_send_bindings_complete_uevent(); + pr_debug("%s all apqn bindings complete\n", __func__); } - ap_send_bindings_complete_uevent(); } } } @@ -782,27 +783,29 @@ static void ap_check_bindings_complete(void) * -ETIME is returned. On failures negative return values are * returned to the caller. */ -int ap_wait_init_apqn_bindings_complete(unsigned long timeout) +int ap_wait_apqn_bindings_complete(unsigned long timeout) { + int rc = 0; long l; - if (completion_done(&ap_init_apqn_bindings_complete)) + if (completion_done(&ap_apqn_bindings_complete)) return 0; if (timeout) l = wait_for_completion_interruptible_timeout( - &ap_init_apqn_bindings_complete, timeout); + &ap_apqn_bindings_complete, timeout); else l = wait_for_completion_interruptible( - &ap_init_apqn_bindings_complete); + &ap_apqn_bindings_complete); if (l < 0) - return l == -ERESTARTSYS ? -EINTR : l; + rc = l == -ERESTARTSYS ? -EINTR : l; else if (l == 0 && timeout) - return -ETIME; + rc = -ETIME; - return 0; + pr_debug("%s rc=%d\n", __func__, rc); + return rc; } -EXPORT_SYMBOL(ap_wait_init_apqn_bindings_complete); +EXPORT_SYMBOL(ap_wait_apqn_bindings_complete); static int __ap_queue_devices_with_id_unregister(struct device *dev, void *data) { @@ -826,8 +829,8 @@ static int __ap_revise_reserved(struct device *dev, void *dummy) drvres = to_ap_drv(dev->driver)->flags & AP_DRIVER_FLAG_DEFAULT; if (!!devres != !!drvres) { - AP_DBF_DBG("%s reprobing queue=%02x.%04x\n", - __func__, card, queue); + pr_debug("%s reprobing queue=%02x.%04x\n", + __func__, card, queue); rc = device_reprobe(dev); if (rc) AP_DBF_WARN("%s reprobing queue=%02x.%04x failed\n", @@ -925,6 +928,12 @@ static int ap_device_probe(struct device *dev) goto out; } + /* + * Rearm the bindings complete completion to trigger + * bindings complete when all devices are bound again + */ + reinit_completion(&ap_apqn_bindings_complete); + /* Add queue/card to list of active queues/cards */ spin_lock_bh(&ap_queues_lock); if (is_queue_dev(dev)) @@ -939,8 +948,6 @@ static int ap_device_probe(struct device *dev) if (is_queue_dev(dev)) hash_del(&to_ap_queue(dev)->hnode); spin_unlock_bh(&ap_queues_lock); - } else { - ap_check_bindings_complete(); } out: @@ -1012,16 +1019,47 @@ void ap_driver_unregister(struct ap_driver *ap_drv) } EXPORT_SYMBOL(ap_driver_unregister); -void ap_bus_force_rescan(void) +/* + * Enforce a synchronous AP bus rescan. + * Returns true if the bus scan finds a change in the AP configuration + * and AP devices have been added or deleted when this function returns. + */ +bool ap_bus_force_rescan(void) { + unsigned long scan_counter = atomic64_read(&ap_scan_bus_count); + bool rc = false; + + pr_debug(">%s scan counter=%lu\n", __func__, scan_counter); + /* Only trigger AP bus scans after the initial scan is done */ - if (atomic64_read(&ap_scan_bus_count) <= 0) - return; + if (scan_counter <= 0) + goto out; + + /* Try to acquire the AP scan bus mutex */ + if (mutex_trylock(&ap_scan_bus_mutex)) { + /* mutex acquired, run the AP bus scan */ + ap_scan_bus_result = ap_scan_bus(); + rc = ap_scan_bus_result; + mutex_unlock(&ap_scan_bus_mutex); + goto out; + } - /* processing a asynchronous bus rescan */ - del_timer(&ap_config_timer); - queue_work(system_long_wq, &ap_scan_work); - flush_work(&ap_scan_work); + /* + * Mutex acquire failed. So there is currently another task + * already running the AP bus scan. Then let's simple wait + * for the lock which means the other task has finished and + * stored the result in ap_scan_bus_result. + */ + if (mutex_lock_interruptible(&ap_scan_bus_mutex)) { + /* some error occurred, ignore and go out */ + goto out; + } + rc = ap_scan_bus_result; + mutex_unlock(&ap_scan_bus_mutex); + +out: + pr_debug("%s rc=%d\n", __func__, rc); + return rc; } EXPORT_SYMBOL(ap_bus_force_rescan); @@ -1030,7 +1068,7 @@ EXPORT_SYMBOL(ap_bus_force_rescan); */ void ap_bus_cfg_chg(void) { - AP_DBF_DBG("%s config change, forcing bus rescan\n", __func__); + pr_debug("%s config change, forcing bus rescan\n", __func__); ap_bus_force_rescan(); } @@ -1090,7 +1128,7 @@ static int hex2bitmap(const char *str, unsigned long *bitmap, int bits) */ static int modify_bitmap(const char *str, unsigned long *bitmap, int bits) { - int a, i, z; + unsigned long a, i, z; char *np, sign; /* bits needs to be a multiple of 8 */ @@ -1250,7 +1288,7 @@ static BUS_ATTR_RO(ap_interrupts); static ssize_t config_time_show(const struct bus_type *bus, char *buf) { - return sysfs_emit(buf, "%d\n", ap_config_time); + return sysfs_emit(buf, "%d\n", ap_scan_bus_time); } static ssize_t config_time_store(const struct bus_type *bus, @@ -1260,8 +1298,8 @@ static ssize_t config_time_store(const struct bus_type *bus, if (sscanf(buf, "%d\n", &time) != 1 || time < 5 || time > 120) return -EINVAL; - ap_config_time = time; - mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ); + ap_scan_bus_time = time; + mod_timer(&ap_scan_bus_timer, jiffies + ap_scan_bus_time * HZ); return count; } @@ -1888,8 +1926,8 @@ static inline void ap_scan_domains(struct ap_card *ac) aq->last_err_rc = AP_RESPONSE_CHECKSTOPPED; } spin_unlock_bh(&aq->lock); - AP_DBF_DBG("%s(%d,%d) queue dev checkstop on\n", - __func__, ac->id, dom); + pr_debug("%s(%d,%d) queue dev checkstop on\n", + __func__, ac->id, dom); /* 'receive' pending messages with -EAGAIN */ ap_flush_queue(aq); goto put_dev_and_continue; @@ -1899,8 +1937,8 @@ static inline void ap_scan_domains(struct ap_card *ac) if (aq->dev_state > AP_DEV_STATE_UNINITIATED) _ap_queue_init_state(aq); spin_unlock_bh(&aq->lock); - AP_DBF_DBG("%s(%d,%d) queue dev checkstop off\n", - __func__, ac->id, dom); + pr_debug("%s(%d,%d) queue dev checkstop off\n", + __func__, ac->id, dom); goto put_dev_and_continue; } /* config state change */ @@ -1912,8 +1950,8 @@ static inline void ap_scan_domains(struct ap_card *ac) aq->last_err_rc = AP_RESPONSE_DECONFIGURED; } spin_unlock_bh(&aq->lock); - AP_DBF_DBG("%s(%d,%d) queue dev config off\n", - __func__, ac->id, dom); + pr_debug("%s(%d,%d) queue dev config off\n", + __func__, ac->id, dom); ap_send_config_uevent(&aq->ap_dev, aq->config); /* 'receive' pending messages with -EAGAIN */ ap_flush_queue(aq); @@ -1924,8 +1962,8 @@ static inline void ap_scan_domains(struct ap_card *ac) if (aq->dev_state > AP_DEV_STATE_UNINITIATED) _ap_queue_init_state(aq); spin_unlock_bh(&aq->lock); - AP_DBF_DBG("%s(%d,%d) queue dev config on\n", - __func__, ac->id, dom); + pr_debug("%s(%d,%d) queue dev config on\n", + __func__, ac->id, dom); ap_send_config_uevent(&aq->ap_dev, aq->config); goto put_dev_and_continue; } @@ -1997,8 +2035,8 @@ static inline void ap_scan_adapter(int ap) ap_scan_rm_card_dev_and_queue_devs(ac); put_device(dev); } else { - AP_DBF_DBG("%s(%d) no type info (no APQN found), ignored\n", - __func__, ap); + pr_debug("%s(%d) no type info (no APQN found), ignored\n", + __func__, ap); } return; } @@ -2010,8 +2048,8 @@ static inline void ap_scan_adapter(int ap) ap_scan_rm_card_dev_and_queue_devs(ac); put_device(dev); } else { - AP_DBF_DBG("%s(%d) no valid type (0) info, ignored\n", - __func__, ap); + pr_debug("%s(%d) no valid type (0) info, ignored\n", + __func__, ap); } return; } @@ -2135,23 +2173,80 @@ static bool ap_get_configuration(void) sizeof(struct ap_config_info)) != 0; } +/* + * ap_config_has_new_aps - Check current against old qci info if + * new adapters have appeared. Returns true if at least one new + * adapter in the apm mask is showing up. Existing adapters or + * receding adapters are not counted. + */ +static bool ap_config_has_new_aps(void) +{ + + unsigned long m[BITS_TO_LONGS(AP_DEVICES)]; + + if (!ap_qci_info) + return false; + + bitmap_andnot(m, (unsigned long *)ap_qci_info->apm, + (unsigned long *)ap_qci_info_old->apm, AP_DEVICES); + if (!bitmap_empty(m, AP_DEVICES)) + return true; + + return false; +} + +/* + * ap_config_has_new_doms - Check current against old qci info if + * new (usage) domains have appeared. Returns true if at least one + * new domain in the aqm mask is showing up. Existing domains or + * receding domains are not counted. + */ +static bool ap_config_has_new_doms(void) +{ + unsigned long m[BITS_TO_LONGS(AP_DOMAINS)]; + + if (!ap_qci_info) + return false; + + bitmap_andnot(m, (unsigned long *)ap_qci_info->aqm, + (unsigned long *)ap_qci_info_old->aqm, AP_DOMAINS); + if (!bitmap_empty(m, AP_DOMAINS)) + return true; + + return false; +} + /** * ap_scan_bus(): Scan the AP bus for new devices - * Runs periodically, workqueue timer (ap_config_time) - * @unused: Unused pointer. + * Always run under mutex ap_scan_bus_mutex protection + * which needs to get locked/unlocked by the caller! + * Returns true if any config change has been detected + * during the scan, otherwise false. */ -static void ap_scan_bus(struct work_struct *unused) +static bool ap_scan_bus(void) { - int ap, config_changed = 0; + bool config_changed; + int ap; - /* config change notify */ + pr_debug(">%s\n", __func__); + + /* (re-)fetch configuration via QCI */ config_changed = ap_get_configuration(); - if (config_changed) + if (config_changed) { + if (ap_config_has_new_aps() || ap_config_has_new_doms()) { + /* + * Appearance of new adapters and/or domains need to + * build new ap devices which need to get bound to an + * device driver. Thus reset the APQN bindings complete + * completion. + */ + reinit_completion(&ap_apqn_bindings_complete); + } + /* post a config change notify */ notify_config_changed(); + } ap_select_domain(); - AP_DBF_DBG("%s running\n", __func__); - /* loop over all possible adapters */ for (ap = 0; ap <= ap_max_adapter_id; ap++) ap_scan_adapter(ap); @@ -2174,23 +2269,56 @@ static void ap_scan_bus(struct work_struct *unused) } if (atomic64_inc_return(&ap_scan_bus_count) == 1) { - AP_DBF_DBG("%s init scan complete\n", __func__); + pr_debug("%s init scan complete\n", __func__); ap_send_init_scan_done_uevent(); - ap_check_bindings_complete(); } - mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ); + ap_check_bindings_complete(); + + mod_timer(&ap_scan_bus_timer, jiffies + ap_scan_bus_time * HZ); + + pr_debug("<%s config_changed=%d\n", __func__, config_changed); + + return config_changed; +} + +/* + * Callback for the ap_scan_bus_timer + * Runs periodically, workqueue timer (ap_scan_bus_time) + */ +static void ap_scan_bus_timer_callback(struct timer_list *unused) +{ + /* + * schedule work into the system long wq which when + * the work is finally executed, calls the AP bus scan. + */ + queue_work(system_long_wq, &ap_scan_bus_work); } -static void ap_config_timeout(struct timer_list *unused) +/* + * Callback for the ap_scan_bus_work + */ +static void ap_scan_bus_wq_callback(struct work_struct *unused) { - queue_work(system_long_wq, &ap_scan_work); + /* + * Try to invoke an ap_scan_bus(). If the mutex acquisition + * fails there is currently another task already running the + * AP scan bus and there is no need to wait and re-trigger the + * scan again. Please note at the end of the scan bus function + * the AP scan bus timer is re-armed which triggers then the + * ap_scan_bus_timer_callback which enqueues a work into the + * system_long_wq which invokes this function here again. + */ + if (mutex_trylock(&ap_scan_bus_mutex)) { + ap_scan_bus_result = ap_scan_bus(); + mutex_unlock(&ap_scan_bus_mutex); + } } static int __init ap_debug_init(void) { ap_dbf_info = debug_register("ap", 2, 1, - DBF_MAX_SPRINTF_ARGS * sizeof(long)); + AP_DBF_MAX_SPRINTF_ARGS * sizeof(long)); debug_register_view(ap_dbf_info, &debug_sprintf_view); debug_set_level(ap_dbf_info, DBF_ERR); @@ -2274,7 +2402,7 @@ static int __init ap_module_init(void) ap_root_device->bus = &ap_bus_type; /* Setup the AP bus rescan timer. */ - timer_setup(&ap_config_timer, ap_config_timeout, 0); + timer_setup(&ap_scan_bus_timer, ap_scan_bus_timer_callback, 0); /* * Setup the high resolution poll timer. @@ -2292,7 +2420,7 @@ static int __init ap_module_init(void) goto out_work; } - queue_work(system_long_wq, &ap_scan_work); + queue_work(system_long_wq, &ap_scan_bus_work); return 0; diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 98814839ef301..59c7ed49aa024 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -266,7 +266,7 @@ int ap_sb_available(void); bool ap_is_se_guest(void); void ap_wait(enum ap_sm_wait wait); void ap_request_timeout(struct timer_list *t); -void ap_bus_force_rescan(void); +bool ap_bus_force_rescan(void); int ap_test_config_usage_domain(unsigned int domain); int ap_test_config_ctrl_domain(unsigned int domain); @@ -352,8 +352,12 @@ int ap_parse_mask_str(const char *str, * the return value is 0. If the timeout (in jiffies) hits instead * -ETIME is returned. On failures negative return values are * returned to the caller. + * It may be that the AP bus scan finds new devices. Then the + * condition that all APQNs are bound to their device drivers + * is reset to false and this call again blocks until either all + * APQNs are bound to a device driver or the timeout hits again. */ -int ap_wait_init_apqn_bindings_complete(unsigned long timeout); +int ap_wait_apqn_bindings_complete(unsigned long timeout); void ap_send_config_uevent(struct ap_device *ap_dev, bool cfg); void ap_send_online_uevent(struct ap_device *ap_dev, int online); diff --git a/drivers/s390/crypto/ap_debug.h b/drivers/s390/crypto/ap_debug.h index c083ce88a9a61..2f66271b85647 100644 --- a/drivers/s390/crypto/ap_debug.h +++ b/drivers/s390/crypto/ap_debug.h @@ -16,7 +16,7 @@ #define RC2ERR(rc) ((rc) ? DBF_ERR : DBF_INFO) #define RC2WARN(rc) ((rc) ? DBF_WARN : DBF_INFO) -#define DBF_MAX_SPRINTF_ARGS 6 +#define AP_DBF_MAX_SPRINTF_ARGS 6 #define AP_DBF(...) \ debug_sprintf_event(ap_dbf_info, ##__VA_ARGS__) @@ -26,8 +26,6 @@ debug_sprintf_event(ap_dbf_info, DBF_WARN, ##__VA_ARGS__) #define AP_DBF_INFO(...) \ debug_sprintf_event(ap_dbf_info, DBF_INFO, ##__VA_ARGS__) -#define AP_DBF_DBG(...) \ - debug_sprintf_event(ap_dbf_info, DBF_DEBUG, ##__VA_ARGS__) extern debug_info_t *ap_dbf_info; diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 682595443145a..6e4e8d324a6de 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -136,6 +136,8 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) switch (status.response_code) { case AP_RESPONSE_NORMAL: + print_hex_dump_debug("aprpl: ", DUMP_PREFIX_ADDRESS, 16, 1, + aq->reply->msg, aq->reply->len, false); aq->queue_count = max_t(int, 0, aq->queue_count - 1); if (!status.queue_empty && !aq->queue_count) aq->queue_count++; @@ -169,6 +171,9 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) aq->queue_count = 0; list_splice_init(&aq->pendingq, &aq->requestq); aq->requestq_count += aq->pendingq_count; + pr_debug("%s queue 0x%02x.%04x rescheduled %d reqs (new req %d)\n", + __func__, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid), + aq->pendingq_count, aq->requestq_count); aq->pendingq_count = 0; break; default: @@ -243,6 +248,8 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) /* Start the next request on the queue. */ ap_msg = list_entry(aq->requestq.next, struct ap_message, list); + print_hex_dump_debug("apreq: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg->msg, ap_msg->len, false); status = __ap_send(qid, ap_msg->psmid, ap_msg->msg, ap_msg->len, ap_msg->flags & AP_MSG_FLAG_SPECIAL); @@ -446,9 +453,9 @@ static enum ap_sm_wait ap_sm_assoc_wait(struct ap_queue *aq) case AP_BS_Q_USABLE: /* association is through */ aq->sm_state = AP_SM_STATE_IDLE; - AP_DBF_DBG("%s queue 0x%02x.%04x associated with %u\n", - __func__, AP_QID_CARD(aq->qid), - AP_QID_QUEUE(aq->qid), aq->assoc_idx); + pr_debug("%s queue 0x%02x.%04x associated with %u\n", + __func__, AP_QID_CARD(aq->qid), + AP_QID_QUEUE(aq->qid), aq->assoc_idx); return AP_SM_WAIT_NONE; case AP_BS_Q_USABLE_NO_SECURE_KEY: /* association still pending */ @@ -690,9 +697,9 @@ static ssize_t ap_functions_show(struct device *dev, status = ap_test_queue(aq->qid, 1, &hwinfo); if (status.response_code > AP_RESPONSE_BUSY) { - AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", - __func__, status.response_code, - AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return -EIO; } @@ -846,9 +853,9 @@ static ssize_t se_bind_show(struct device *dev, status = ap_test_queue(aq->qid, 1, &hwinfo); if (status.response_code > AP_RESPONSE_BUSY) { - AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", - __func__, status.response_code, - AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return -EIO; } @@ -974,9 +981,9 @@ static ssize_t se_associate_show(struct device *dev, status = ap_test_queue(aq->qid, 1, &hwinfo); if (status.response_code > AP_RESPONSE_BUSY) { - AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", - __func__, status.response_code, - AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return -EIO; } diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 6cfb6b2340c99..dccf664a3d957 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -42,24 +42,23 @@ MODULE_DESCRIPTION("s390 protected key interface"); * debug feature data and functions */ -static debug_info_t *debug_info; +static debug_info_t *pkey_dbf_info; -#define DEBUG_DBG(...) debug_sprintf_event(debug_info, 6, ##__VA_ARGS__) -#define DEBUG_INFO(...) debug_sprintf_event(debug_info, 5, ##__VA_ARGS__) -#define DEBUG_WARN(...) debug_sprintf_event(debug_info, 4, ##__VA_ARGS__) -#define DEBUG_ERR(...) debug_sprintf_event(debug_info, 3, ##__VA_ARGS__) +#define PKEY_DBF_INFO(...) debug_sprintf_event(pkey_dbf_info, 5, ##__VA_ARGS__) +#define PKEY_DBF_WARN(...) debug_sprintf_event(pkey_dbf_info, 4, ##__VA_ARGS__) +#define PKEY_DBF_ERR(...) debug_sprintf_event(pkey_dbf_info, 3, ##__VA_ARGS__) static void __init pkey_debug_init(void) { /* 5 arguments per dbf entry (including the format string ptr) */ - debug_info = debug_register("pkey", 1, 1, 5 * sizeof(long)); - debug_register_view(debug_info, &debug_sprintf_view); - debug_set_level(debug_info, 3); + pkey_dbf_info = debug_register("pkey", 1, 1, 5 * sizeof(long)); + debug_register_view(pkey_dbf_info, &debug_sprintf_view); + debug_set_level(pkey_dbf_info, 3); } static void __exit pkey_debug_exit(void) { - debug_unregister(debug_info); + debug_unregister(pkey_dbf_info); } /* inside view of a protected key token (only type 0x00 version 0x01) */ @@ -163,14 +162,14 @@ static int pkey_clr2protkey(u32 keytype, const u8 *clrkey, fc = CPACF_PCKMO_ENC_ECC_ED448_KEY; break; default: - DEBUG_ERR("%s unknown/unsupported keytype %u\n", - __func__, keytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", + __func__, keytype); return -EINVAL; } if (*protkeylen < keysize + AES_WK_VP_SIZE) { - DEBUG_ERR("%s prot key buffer size too small: %u < %d\n", - __func__, *protkeylen, keysize + AES_WK_VP_SIZE); + PKEY_DBF_ERR("%s prot key buffer size too small: %u < %d\n", + __func__, *protkeylen, keysize + AES_WK_VP_SIZE); return -EINVAL; } @@ -182,7 +181,7 @@ static int pkey_clr2protkey(u32 keytype, const u8 *clrkey, } /* check for the pckmo subfunction we need now */ if (!cpacf_test_func(&pckmo_functions, fc)) { - DEBUG_ERR("%s pckmo functions not available\n", __func__); + PKEY_DBF_ERR("%s pckmo functions not available\n", __func__); return -ENODEV; } @@ -244,7 +243,7 @@ static int pkey_skey2pkey(const u8 *key, u8 *protkey, } if (rc) - DEBUG_DBG("%s failed rc=%d\n", __func__, rc); + pr_debug("%s failed rc=%d\n", __func__, rc); return rc; } @@ -283,7 +282,7 @@ static int pkey_clr2ep11key(const u8 *clrkey, size_t clrkeylen, out: kfree(apqns); if (rc) - DEBUG_DBG("%s failed rc=%d\n", __func__, rc); + pr_debug("%s failed rc=%d\n", __func__, rc); return rc; } @@ -294,33 +293,36 @@ static int pkey_ep11key2pkey(const u8 *key, size_t keylen, u8 *protkey, u32 *protkeylen, u32 *protkeytype) { u32 nr_apqns, *apqns = NULL; + int i, j, rc = -ENODEV; u16 card, dom; - int i, rc; zcrypt_wait_api_operational(); - /* build a list of apqns suitable for this key */ - rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF, - ZCRYPT_CEX7, - ap_is_se_guest() ? EP11_API_V6 : EP11_API_V4, - ep11_kb_wkvp(key, keylen)); - if (rc) - goto out; + /* try two times in case of failure */ + for (i = 0; i < 2 && rc; i++) { - /* go through the list of apqns and try to derive an pkey */ - for (rc = -ENODEV, i = 0; i < nr_apqns; i++) { - card = apqns[i] >> 16; - dom = apqns[i] & 0xFFFF; - rc = ep11_kblob2protkey(card, dom, key, keylen, - protkey, protkeylen, protkeytype); - if (rc == 0) - break; + /* build a list of apqns suitable for this key */ + rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF, + ZCRYPT_CEX7, + ap_is_se_guest() ? EP11_API_V6 : EP11_API_V4, + ep11_kb_wkvp(key, keylen)); + if (rc) + continue; /* retry findcard on failure */ + + /* go through the list of apqns and try to derive an pkey */ + for (rc = -ENODEV, j = 0; j < nr_apqns && rc; j++) { + card = apqns[j] >> 16; + dom = apqns[j] & 0xFFFF; + rc = ep11_kblob2protkey(card, dom, key, keylen, + protkey, protkeylen, protkeytype); + } + + kfree(apqns); } -out: - kfree(apqns); if (rc) - DEBUG_DBG("%s failed rc=%d\n", __func__, rc); + pr_debug("%s failed rc=%d\n", __func__, rc); + return rc; } @@ -336,7 +338,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey, int rc; /* check the secure key for valid AES secure key */ - rc = cca_check_secaeskeytoken(debug_info, 3, (u8 *)seckey, 0); + rc = cca_check_secaeskeytoken(pkey_dbf_info, 3, (u8 *)seckey, 0); if (rc) goto out; if (pattributes) @@ -351,7 +353,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey, if (rc > 0) { /* key mkvp matches to old master key mkvp */ - DEBUG_DBG("%s secure key has old mkvp\n", __func__); + pr_debug("%s secure key has old mkvp\n", __func__); if (pattributes) *pattributes |= PKEY_VERIFY_ATTR_OLD_MKVP; rc = 0; @@ -363,7 +365,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey, *pdomain = domain; out: - DEBUG_DBG("%s rc=%d\n", __func__, rc); + pr_debug("%s rc=%d\n", __func__, rc); return rc; } @@ -379,8 +381,8 @@ static int pkey_genprotkey(u32 keytype, u8 *protkey, keysize = pkey_keytype_aes_to_size(keytype); if (!keysize) { - DEBUG_ERR("%s unknown/unsupported keytype %d\n", __func__, - keytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %d\n", __func__, + keytype); return -EINVAL; } @@ -428,13 +430,13 @@ static int pkey_verifyprotkey(const u8 *protkey, u32 protkeylen, fc = CPACF_KMC_PAES_256; break; default: - DEBUG_ERR("%s unknown/unsupported keytype %u\n", __func__, - protkeytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", __func__, + protkeytype); return -EINVAL; } if (protkeylen != pkeylen) { - DEBUG_ERR("%s invalid protected key size %u for keytype %u\n", - __func__, protkeylen, protkeytype); + PKEY_DBF_ERR("%s invalid protected key size %u for keytype %u\n", + __func__, protkeylen, protkeytype); return -EINVAL; } @@ -446,7 +448,7 @@ static int pkey_verifyprotkey(const u8 *protkey, u32 protkeylen, k = cpacf_kmc(fc | CPACF_ENCRYPT, ¶m, null_msg, dest_buf, sizeof(null_msg)); if (k != sizeof(null_msg)) { - DEBUG_ERR("%s protected key is not valid\n", __func__); + PKEY_DBF_ERR("%s protected key is not valid\n", __func__); return -EKEYREJECTED; } @@ -464,13 +466,13 @@ static int nonccatokaes2pkey(const struct clearkeytoken *t, keysize = pkey_keytype_aes_to_size(t->keytype); if (!keysize) { - DEBUG_ERR("%s unknown/unsupported keytype %u\n", - __func__, t->keytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", + __func__, t->keytype); return -EINVAL; } if (t->len != keysize) { - DEBUG_ERR("%s non clear key aes token: invalid key len %u\n", - __func__, t->len); + PKEY_DBF_ERR("%s non clear key aes token: invalid key len %u\n", + __func__, t->len); return -EINVAL; } @@ -505,7 +507,7 @@ static int nonccatokaes2pkey(const struct clearkeytoken *t, goto out; failure: - DEBUG_ERR("%s unable to build protected key from clear", __func__); + PKEY_DBF_ERR("%s unable to build protected key from clear", __func__); out: kfree(tmpbuf); @@ -536,14 +538,14 @@ static int nonccatokecc2pkey(const struct clearkeytoken *t, keylen = 64; break; default: - DEBUG_ERR("%s unknown/unsupported keytype %u\n", - __func__, t->keytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", + __func__, t->keytype); return -EINVAL; } if (t->len != keylen) { - DEBUG_ERR("%s non clear key ecc token: invalid key len %u\n", - __func__, t->len); + PKEY_DBF_ERR("%s non clear key ecc token: invalid key len %u\n", + __func__, t->len); return -EINVAL; } @@ -551,8 +553,8 @@ static int nonccatokecc2pkey(const struct clearkeytoken *t, rc = pkey_clr2protkey(t->keytype, t->clearkey, protkey, protkeylen, protkeytype); if (rc) { - DEBUG_ERR("%s unable to build protected key from clear", - __func__); + PKEY_DBF_ERR("%s unable to build protected key from clear", + __func__); } return rc; @@ -604,15 +606,15 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen, protkeylen, protkeytype); break; default: - DEBUG_ERR("%s unknown/unsupported non cca clear key type %u\n", - __func__, t->keytype); + PKEY_DBF_ERR("%s unknown/unsupported non cca clear key type %u\n", + __func__, t->keytype); return -EINVAL; } break; } case TOKVER_EP11_AES: { /* check ep11 key for exportable as protected key */ - rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1); + rc = ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1); if (rc) goto out; rc = pkey_ep11key2pkey(key, keylen, @@ -621,15 +623,16 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen, } case TOKVER_EP11_AES_WITH_HEADER: /* check ep11 key with header for exportable as protected key */ - rc = ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1); + rc = ep11_check_aes_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1); if (rc) goto out; rc = pkey_ep11key2pkey(key, keylen, protkey, protkeylen, protkeytype); break; default: - DEBUG_ERR("%s unknown/unsupported non-CCA token version %d\n", - __func__, hdr->version); + PKEY_DBF_ERR("%s unknown/unsupported non-CCA token version %d\n", + __func__, hdr->version); } out: @@ -654,8 +657,8 @@ static int pkey_ccainttok2pkey(const u8 *key, u32 keylen, return -EINVAL; break; default: - DEBUG_ERR("%s unknown/unsupported CCA internal token version %d\n", - __func__, hdr->version); + PKEY_DBF_ERR("%s unknown/unsupported CCA internal token version %d\n", + __func__, hdr->version); return -EINVAL; } @@ -672,7 +675,7 @@ int pkey_keyblob2pkey(const u8 *key, u32 keylen, int rc; if (keylen < sizeof(struct keytoken_header)) { - DEBUG_ERR("%s invalid keylen %d\n", __func__, keylen); + PKEY_DBF_ERR("%s invalid keylen %d\n", __func__, keylen); return -EINVAL; } @@ -686,12 +689,12 @@ int pkey_keyblob2pkey(const u8 *key, u32 keylen, protkey, protkeylen, protkeytype); break; default: - DEBUG_ERR("%s unknown/unsupported blob type %d\n", - __func__, hdr->type); + PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n", + __func__, hdr->type); return -EINVAL; } - DEBUG_DBG("%s rc=%d\n", __func__, rc); + pr_debug("%s rc=%d\n", __func__, rc); return rc; } EXPORT_SYMBOL(pkey_keyblob2pkey); @@ -839,7 +842,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, hdr->version == TOKVER_CCA_AES) { struct secaeskeytoken *t = (struct secaeskeytoken *)key; - rc = cca_check_secaeskeytoken(debug_info, 3, key, 0); + rc = cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0); if (rc) goto out; if (ktype) @@ -869,7 +872,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, hdr->version == TOKVER_CCA_VLSC) { struct cipherkeytoken *t = (struct cipherkeytoken *)key; - rc = cca_check_secaescipherkey(debug_info, 3, key, 0, 1); + rc = cca_check_secaescipherkey(pkey_dbf_info, 3, key, 0, 1); if (rc) goto out; if (ktype) @@ -907,7 +910,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, struct ep11keyblob *kb = (struct ep11keyblob *)key; int api; - rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1); + rc = ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1); if (rc) goto out; if (ktype) @@ -933,8 +936,8 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, struct ep11kblob_header *kh = (struct ep11kblob_header *)key; int api; - rc = ep11_check_aes_key_with_hdr(debug_info, 3, - key, keylen, 1); + rc = ep11_check_aes_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1); if (rc) goto out; if (ktype) @@ -981,25 +984,27 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns, if (hdr->version == TOKVER_CCA_AES) { if (keylen != sizeof(struct secaeskeytoken)) return -EINVAL; - if (cca_check_secaeskeytoken(debug_info, 3, key, 0)) + if (cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0)) return -EINVAL; } else if (hdr->version == TOKVER_CCA_VLSC) { if (keylen < hdr->len || keylen > MAXCCAVLSCTOKENSIZE) return -EINVAL; - if (cca_check_secaescipherkey(debug_info, 3, key, 0, 1)) + if (cca_check_secaescipherkey(pkey_dbf_info, + 3, key, 0, 1)) return -EINVAL; } else { - DEBUG_ERR("%s unknown CCA internal token version %d\n", - __func__, hdr->version); + PKEY_DBF_ERR("%s unknown CCA internal token version %d\n", + __func__, hdr->version); return -EINVAL; } } else if (hdr->type == TOKTYPE_NON_CCA) { if (hdr->version == TOKVER_EP11_AES) { - if (ep11_check_aes_key(debug_info, 3, key, keylen, 1)) + if (ep11_check_aes_key(pkey_dbf_info, + 3, key, keylen, 1)) return -EINVAL; } else if (hdr->version == TOKVER_EP11_AES_WITH_HEADER) { - if (ep11_check_aes_key_with_hdr(debug_info, 3, - key, keylen, 1)) + if (ep11_check_aes_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1)) return -EINVAL; } else { return pkey_nonccatok2pkey(key, keylen, @@ -1007,8 +1012,8 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns, protkeytype); } } else { - DEBUG_ERR("%s unknown/unsupported blob type %d\n", - __func__, hdr->type); + PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n", + __func__, hdr->type); return -EINVAL; } @@ -1234,50 +1239,53 @@ static int pkey_keyblob2pkey3(const struct pkey_apqn *apqns, size_t nr_apqns, hdr->version == TOKVER_EP11_AES_WITH_HEADER && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { /* EP11 AES key blob with header */ - if (ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1)) + if (ep11_check_aes_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_NON_CCA && hdr->version == TOKVER_EP11_ECC_WITH_HEADER && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { /* EP11 ECC key blob with header */ - if (ep11_check_ecc_key_with_hdr(debug_info, 3, key, keylen, 1)) + if (ep11_check_ecc_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_NON_CCA && hdr->version == TOKVER_EP11_AES && is_ep11_keyblob(key)) { /* EP11 AES key blob with header in session field */ - if (ep11_check_aes_key(debug_info, 3, key, keylen, 1)) + if (ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_CCA_INTERNAL) { if (hdr->version == TOKVER_CCA_AES) { /* CCA AES data key */ if (keylen != sizeof(struct secaeskeytoken)) return -EINVAL; - if (cca_check_secaeskeytoken(debug_info, 3, key, 0)) + if (cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0)) return -EINVAL; } else if (hdr->version == TOKVER_CCA_VLSC) { /* CCA AES cipher key */ if (keylen < hdr->len || keylen > MAXCCAVLSCTOKENSIZE) return -EINVAL; - if (cca_check_secaescipherkey(debug_info, 3, key, 0, 1)) + if (cca_check_secaescipherkey(pkey_dbf_info, + 3, key, 0, 1)) return -EINVAL; } else { - DEBUG_ERR("%s unknown CCA internal token version %d\n", - __func__, hdr->version); + PKEY_DBF_ERR("%s unknown CCA internal token version %d\n", + __func__, hdr->version); return -EINVAL; } } else if (hdr->type == TOKTYPE_CCA_INTERNAL_PKA) { /* CCA ECC (private) key */ if (keylen < sizeof(struct eccprivkeytoken)) return -EINVAL; - if (cca_check_sececckeytoken(debug_info, 3, key, keylen, 1)) + if (cca_check_sececckeytoken(pkey_dbf_info, 3, key, keylen, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_NON_CCA) { return pkey_nonccatok2pkey(key, keylen, protkey, protkeylen, protkeytype); } else { - DEBUG_ERR("%s unknown/unsupported blob type %d\n", - __func__, hdr->type); + PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n", + __func__, hdr->type); return -EINVAL; } @@ -1350,7 +1358,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = cca_genseckey(kgs.cardnr, kgs.domain, kgs.keytype, kgs.seckey.seckey); - DEBUG_DBG("%s cca_genseckey()=%d\n", __func__, rc); + pr_debug("%s cca_genseckey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(ugs, &kgs, sizeof(kgs))) @@ -1365,7 +1373,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = cca_clr2seckey(kcs.cardnr, kcs.domain, kcs.keytype, kcs.clrkey.clrkey, kcs.seckey.seckey); - DEBUG_DBG("%s cca_clr2seckey()=%d\n", __func__, rc); + pr_debug("%s cca_clr2seckey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(ucs, &kcs, sizeof(kcs))) @@ -1383,7 +1391,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = cca_sec2protkey(ksp.cardnr, ksp.domain, ksp.seckey.seckey, ksp.protkey.protkey, &ksp.protkey.len, &ksp.protkey.type); - DEBUG_DBG("%s cca_sec2protkey()=%d\n", __func__, rc); + pr_debug("%s cca_sec2protkey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(usp, &ksp, sizeof(ksp))) @@ -1400,7 +1408,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_clr2protkey(kcp.keytype, kcp.clrkey.clrkey, kcp.protkey.protkey, &kcp.protkey.len, &kcp.protkey.type); - DEBUG_DBG("%s pkey_clr2protkey()=%d\n", __func__, rc); + pr_debug("%s pkey_clr2protkey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(ucp, &kcp, sizeof(kcp))) @@ -1416,7 +1424,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = cca_findcard(kfc.seckey.seckey, &kfc.cardnr, &kfc.domain, 1); - DEBUG_DBG("%s cca_findcard()=%d\n", __func__, rc); + pr_debug("%s cca_findcard()=%d\n", __func__, rc); if (rc < 0) break; if (copy_to_user(ufc, &kfc, sizeof(kfc))) @@ -1432,7 +1440,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, ksp.protkey.len = sizeof(ksp.protkey.protkey); rc = pkey_skey2pkey(ksp.seckey.seckey, ksp.protkey.protkey, &ksp.protkey.len, &ksp.protkey.type); - DEBUG_DBG("%s pkey_skey2pkey()=%d\n", __func__, rc); + pr_debug("%s pkey_skey2pkey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(usp, &ksp, sizeof(ksp))) @@ -1447,7 +1455,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = pkey_verifykey(&kvk.seckey, &kvk.cardnr, &kvk.domain, &kvk.keysize, &kvk.attributes); - DEBUG_DBG("%s pkey_verifykey()=%d\n", __func__, rc); + pr_debug("%s pkey_verifykey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(uvk, &kvk, sizeof(kvk))) @@ -1463,7 +1471,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kgp.protkey.len = sizeof(kgp.protkey.protkey); rc = pkey_genprotkey(kgp.keytype, kgp.protkey.protkey, &kgp.protkey.len, &kgp.protkey.type); - DEBUG_DBG("%s pkey_genprotkey()=%d\n", __func__, rc); + pr_debug("%s pkey_genprotkey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(ugp, &kgp, sizeof(kgp))) @@ -1478,7 +1486,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = pkey_verifyprotkey(kvp.protkey.protkey, kvp.protkey.len, kvp.protkey.type); - DEBUG_DBG("%s pkey_verifyprotkey()=%d\n", __func__, rc); + pr_debug("%s pkey_verifyprotkey()=%d\n", __func__, rc); break; } case PKEY_KBLOB2PROTK: { @@ -1494,7 +1502,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, ktp.protkey.len = sizeof(ktp.protkey.protkey); rc = pkey_keyblob2pkey(kkey, ktp.keylen, ktp.protkey.protkey, &ktp.protkey.len, &ktp.protkey.type); - DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc); + pr_debug("%s pkey_keyblob2pkey()=%d\n", __func__, rc); memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) @@ -1523,7 +1531,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_genseckey2(apqns, kgs.apqn_entries, kgs.type, kgs.size, kgs.keygenflags, kkey, &klen); - DEBUG_DBG("%s pkey_genseckey2()=%d\n", __func__, rc); + pr_debug("%s pkey_genseckey2()=%d\n", __func__, rc); kfree(apqns); if (rc) { kfree(kkey); @@ -1565,7 +1573,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_clr2seckey2(apqns, kcs.apqn_entries, kcs.type, kcs.size, kcs.keygenflags, kcs.clrkey.clrkey, kkey, &klen); - DEBUG_DBG("%s pkey_clr2seckey2()=%d\n", __func__, rc); + pr_debug("%s pkey_clr2seckey2()=%d\n", __func__, rc); kfree(apqns); if (rc) { kfree(kkey); @@ -1601,7 +1609,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_verifykey2(kkey, kvk.keylen, &kvk.cardnr, &kvk.domain, &kvk.type, &kvk.size, &kvk.flags); - DEBUG_DBG("%s pkey_verifykey2()=%d\n", __func__, rc); + pr_debug("%s pkey_verifykey2()=%d\n", __func__, rc); kfree(kkey); if (rc) break; @@ -1630,7 +1638,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kkey, ktp.keylen, ktp.protkey.protkey, &ktp.protkey.len, &ktp.protkey.type); - DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); + pr_debug("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); kfree(apqns); memzero_explicit(kkey, ktp.keylen); kfree(kkey); @@ -1664,7 +1672,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, } rc = pkey_apqns4key(kkey, kak.keylen, kak.flags, apqns, &nr_apqns); - DEBUG_DBG("%s pkey_apqns4key()=%d\n", __func__, rc); + pr_debug("%s pkey_apqns4key()=%d\n", __func__, rc); kfree(kkey); if (rc && rc != -ENOSPC) { kfree(apqns); @@ -1707,7 +1715,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, } rc = pkey_apqns4keytype(kat.type, kat.cur_mkvp, kat.alt_mkvp, kat.flags, apqns, &nr_apqns); - DEBUG_DBG("%s pkey_apqns4keytype()=%d\n", __func__, rc); + pr_debug("%s pkey_apqns4keytype()=%d\n", __func__, rc); if (rc && rc != -ENOSPC) { kfree(apqns); break; @@ -1757,7 +1765,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_keyblob2pkey3(apqns, ktp.apqn_entries, kkey, ktp.keylen, protkey, &protkeylen, &ktp.pkeytype); - DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); + pr_debug("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); kfree(apqns); memzero_explicit(kkey, ktp.keylen); kfree(kkey); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 74200f54dfff7..73fe9cd59a636 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -12,6 +12,9 @@ * Multiple device nodes: Harald Freudenberger */ +#define KMSG_COMPONENT "zcrypt" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include #include #include @@ -57,10 +60,6 @@ DEFINE_SPINLOCK(zcrypt_list_lock); LIST_HEAD(zcrypt_card_list); static atomic_t zcrypt_open_count = ATOMIC_INIT(0); -static atomic_t zcrypt_rescan_count = ATOMIC_INIT(0); - -atomic_t zcrypt_rescan_req = ATOMIC_INIT(0); -EXPORT_SYMBOL(zcrypt_rescan_req); static LIST_HEAD(zcrypt_ops_list); @@ -69,20 +68,15 @@ debug_info_t *zcrypt_dbf_info; /* * Process a rescan of the transport layer. - * - * Returns 1, if the rescan has been processed, otherwise 0. + * Runs a synchronous AP bus rescan. + * Returns true if something has changed (for example the + * bus scan has found and build up new devices) and it is + * worth to do a retry. Otherwise false is returned meaning + * no changes on the AP bus level. */ -static inline int zcrypt_process_rescan(void) -{ - if (atomic_read(&zcrypt_rescan_req)) { - atomic_set(&zcrypt_rescan_req, 0); - atomic_inc(&zcrypt_rescan_count); - ap_bus_force_rescan(); - ZCRYPT_DBF_INFO("%s rescan count=%07d\n", __func__, - atomic_inc_return(&zcrypt_rescan_count)); - return 1; - } - return 0; +static inline bool zcrypt_process_rescan(void) +{ + return ap_bus_force_rescan(); } void zcrypt_msgtype_register(struct zcrypt_ops *zops) @@ -579,6 +573,7 @@ static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc, { if (!zq || !try_module_get(zq->queue->ap_dev.device.driver->owner)) return NULL; + zcrypt_card_get(zc); zcrypt_queue_get(zq); get_device(&zq->queue->ap_dev.device); atomic_add(weight, &zc->load); @@ -598,6 +593,7 @@ static inline void zcrypt_drop_queue(struct zcrypt_card *zc, atomic_sub(weight, &zq->load); put_device(&zq->queue->ap_dev.device); zcrypt_queue_put(zq); + zcrypt_card_put(zc); module_put(mod); } @@ -715,8 +711,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, spin_unlock(&zcrypt_list_lock); if (!pref_zq) { - ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n", - __func__); + pr_debug("%s no matching queue found => ENODEV\n", __func__); rc = -ENODEV; goto out; } @@ -820,8 +815,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, spin_unlock(&zcrypt_list_lock); if (!pref_zq) { - ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n", - __func__); + pr_debug("%s no matching queue found => ENODEV\n", __func__); rc = -ENODEV; goto out; } @@ -865,6 +859,8 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, rc = prep_cca_ap_msg(userspace, xcrb, &ap_msg, &func_code, &domain); if (rc) goto out; + print_hex_dump_debug("ccareq: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg.msg, ap_msg.len, false); tdom = *domain; if (perms != &ap_perms && tdom < AP_DOMAINS) { @@ -940,8 +936,8 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, spin_unlock(&zcrypt_list_lock); if (!pref_zq) { - ZCRYPT_DBF_DBG("%s no match for address %02x.%04x => ENODEV\n", - __func__, xcrb->user_defined, *domain); + pr_debug("%s no match for address %02x.%04x => ENODEV\n", + __func__, xcrb->user_defined, *domain); rc = -ENODEV; goto out; } @@ -952,6 +948,10 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, *domain = AP_QID_QUEUE(qid); rc = pref_zq->ops->send_cprb(userspace, pref_zq, xcrb, &ap_msg); + if (!rc) { + print_hex_dump_debug("ccarpl: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg.msg, ap_msg.len, false); + } spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); @@ -970,7 +970,26 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, long zcrypt_send_cprb(struct ica_xcRB *xcrb) { - return _zcrypt_send_cprb(false, &ap_perms, NULL, xcrb); + struct zcrypt_track tr; + int rc; + + memset(&tr, 0, sizeof(tr)); + + do { + rc = _zcrypt_send_cprb(false, &ap_perms, &tr, xcrb); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) + do { + rc = _zcrypt_send_cprb(false, &ap_perms, &tr, xcrb); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) + rc = -EIO; + if (rc) + pr_debug("%s rc=%d\n", __func__, rc); + + return rc; } EXPORT_SYMBOL(zcrypt_send_cprb); @@ -1045,6 +1064,8 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, rc = prep_ep11_ap_msg(userspace, xcrb, &ap_msg, &func_code, &domain); if (rc) goto out_free; + print_hex_dump_debug("ep11req: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg.msg, ap_msg.len, false); if (perms != &ap_perms && domain < AUTOSEL_DOM) { if (ap_msg.flags & AP_MSG_FLAG_ADMIN) { @@ -1113,15 +1134,15 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, if (!pref_zq) { if (targets && target_num == 1) { - ZCRYPT_DBF_DBG("%s no match for address %02x.%04x => ENODEV\n", - __func__, (int)targets->ap_id, - (int)targets->dom_id); + pr_debug("%s no match for address %02x.%04x => ENODEV\n", + __func__, (int)targets->ap_id, + (int)targets->dom_id); } else if (targets) { - ZCRYPT_DBF_DBG("%s no match for %d target addrs => ENODEV\n", - __func__, (int)target_num); + pr_debug("%s no match for %d target addrs => ENODEV\n", + __func__, (int)target_num); } else { - ZCRYPT_DBF_DBG("%s no match for address ff.ffff => ENODEV\n", - __func__); + pr_debug("%s no match for address ff.ffff => ENODEV\n", + __func__); } rc = -ENODEV; goto out_free; @@ -1129,6 +1150,10 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, qid = pref_zq->queue->qid; rc = pref_zq->ops->send_ep11_cprb(userspace, pref_zq, xcrb, &ap_msg); + if (!rc) { + print_hex_dump_debug("ep11rpl: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg.msg, ap_msg.len, false); + } spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); @@ -1149,7 +1174,26 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb) { - return _zcrypt_send_ep11_cprb(false, &ap_perms, NULL, xcrb); + struct zcrypt_track tr; + int rc; + + memset(&tr, 0, sizeof(tr)); + + do { + rc = _zcrypt_send_ep11_cprb(false, &ap_perms, &tr, xcrb); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) + do { + rc = _zcrypt_send_ep11_cprb(false, &ap_perms, &tr, xcrb); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) + rc = -EIO; + if (rc) + pr_debug("%s rc=%d\n", __func__, rc); + + return rc; } EXPORT_SYMBOL(zcrypt_send_ep11_cprb); @@ -1199,8 +1243,7 @@ static long zcrypt_rng(char *buffer) spin_unlock(&zcrypt_list_lock); if (!pref_zq) { - ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n", - __func__); + pr_debug("%s no matching queue found => ENODEV\n", __func__); rc = -ENODEV; goto out; } @@ -1431,20 +1474,17 @@ static int icarsamodexpo_ioctl(struct ap_perms *perms, unsigned long arg) do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) { - ZCRYPT_DBF_DBG("ioctl ICARSAMODEXPO rc=%d\n", rc); + pr_debug("ioctl ICARSAMODEXPO rc=%d\n", rc); return rc; } return put_user(mex.outputdatalength, &umex->outputdatalength); @@ -1463,20 +1503,17 @@ static int icarsacrt_ioctl(struct ap_perms *perms, unsigned long arg) do { rc = zcrypt_rsa_crt(perms, &tr, &crt); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = zcrypt_rsa_crt(perms, &tr, &crt); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) { - ZCRYPT_DBF_DBG("ioctl ICARSACRT rc=%d\n", rc); + pr_debug("ioctl ICARSACRT rc=%d\n", rc); return rc; } return put_user(crt.outputdatalength, &ucrt->outputdatalength); @@ -1495,21 +1532,18 @@ static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg) do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) - ZCRYPT_DBF_DBG("ioctl ZSENDCPRB rc=%d status=0x%x\n", - rc, xcrb.status); + pr_debug("ioctl ZSENDCPRB rc=%d status=0x%x\n", + rc, xcrb.status); if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb))) return -EFAULT; return rc; @@ -1528,20 +1562,17 @@ static int zsendep11cprb_ioctl(struct ap_perms *perms, unsigned long arg) do { rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) - ZCRYPT_DBF_DBG("ioctl ZSENDEP11CPRB rc=%d\n", rc); + pr_debug("ioctl ZSENDEP11CPRB rc=%d\n", rc); if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb))) return -EFAULT; return rc; @@ -1670,7 +1701,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, } /* unknown ioctl number */ default: - ZCRYPT_DBF_DBG("unknown ioctl 0x%08x\n", cmd); + pr_debug("unknown ioctl 0x%08x\n", cmd); return -ENOIOCTLCMD; } } @@ -1708,16 +1739,13 @@ static long trans_modexpo32(struct ap_perms *perms, struct file *filp, mex64.n_modulus = compat_ptr(mex32.n_modulus); do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) @@ -1761,16 +1789,13 @@ static long trans_modexpo_crt32(struct ap_perms *perms, struct file *filp, crt64.u_mult_inv = compat_ptr(crt32.u_mult_inv); do { rc = zcrypt_rsa_crt(perms, &tr, &crt64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = zcrypt_rsa_crt(perms, &tr, &crt64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) @@ -1833,16 +1858,13 @@ static long trans_xcrb32(struct ap_perms *perms, struct file *filp, xcrb64.status = xcrb32.status; do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; xcrb32.reply_control_blk_length = xcrb64.reply_control_blk_length; @@ -1914,8 +1936,8 @@ static int zcrypt_rng_data_read(struct hwrng *rng, u32 *data) */ if (zcrypt_rng_buffer_index == 0) { rc = zcrypt_rng((char *)zcrypt_rng_buffer); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + /* on ENODEV failure: retry once again after an AP bus rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) rc = zcrypt_rng((char *)zcrypt_rng_buffer); if (rc < 0) return -EIO; @@ -1977,7 +1999,7 @@ void zcrypt_rng_device_remove(void) * an asynchronous job. This function waits until these initial jobs * are done and so the zcrypt api should be ready to serve crypto * requests - if there are resources available. The function uses an - * internal timeout of 60s. The very first caller will either wait for + * internal timeout of 30s. The very first caller will either wait for * ap bus bindings complete or the timeout happens. This state will be * remembered for further callers which will only be blocked until a * decision is made (timeout or bindings complete). @@ -1996,8 +2018,8 @@ int zcrypt_wait_api_operational(void) switch (zcrypt_wait_api_state) { case 0: /* initial state, invoke wait for the ap bus complete */ - rc = ap_wait_init_apqn_bindings_complete( - msecs_to_jiffies(60 * 1000)); + rc = ap_wait_apqn_bindings_complete( + msecs_to_jiffies(ZCRYPT_WAIT_BINDINGS_COMPLETE_MS)); switch (rc) { case 0: /* ap bus bindings are complete */ @@ -2014,8 +2036,8 @@ int zcrypt_wait_api_operational(void) break; default: /* other failure */ - ZCRYPT_DBF_DBG("%s ap_wait_init_apqn_bindings_complete()=%d\n", - __func__, rc); + pr_debug("%s ap_wait_init_apqn_bindings_complete()=%d\n", + __func__, rc); break; } break; @@ -2038,7 +2060,7 @@ EXPORT_SYMBOL(zcrypt_wait_api_operational); int __init zcrypt_debug_init(void) { zcrypt_dbf_info = debug_register("zcrypt", 2, 1, - DBF_MAX_SPRINTF_ARGS * sizeof(long)); + ZCRYPT_DBF_MAX_SPRINTF_ARGS * sizeof(long)); debug_register_view(zcrypt_dbf_info, &debug_sprintf_view); debug_set_level(zcrypt_dbf_info, DBF_ERR); diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index de659954c8f7d..4ed481df57ca4 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -38,6 +38,15 @@ */ #define ZCRYPT_RNG_BUFFER_SIZE 4096 +/** + * The zcrypt_wait_api_operational() function waits this + * amount in milliseconds for ap_wait_aqpn_bindings_complete(). + * Also on a cprb send failure with ENODEV the send functions + * trigger an ap bus rescan and wait this time in milliseconds + * for ap_wait_aqpn_bindings_complete() before resending. + */ +#define ZCRYPT_WAIT_BINDINGS_COMPLETE_MS 30000 + /* * Identifier for Crypto Request Performance Index */ diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 263fe182648b8..0a3a678ffc7ee 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -23,11 +23,6 @@ #include "zcrypt_msgtype6.h" #include "zcrypt_ccamisc.h" -#define DEBUG_DBG(...) ZCRYPT_DBF(DBF_DEBUG, ##__VA_ARGS__) -#define DEBUG_INFO(...) ZCRYPT_DBF(DBF_INFO, ##__VA_ARGS__) -#define DEBUG_WARN(...) ZCRYPT_DBF(DBF_WARN, ##__VA_ARGS__) -#define DEBUG_ERR(...) ZCRYPT_DBF(DBF_ERR, ##__VA_ARGS__) - /* Size of parameter block used for all cca requests/replies */ #define PARMBSIZE 512 @@ -367,8 +362,8 @@ int cca_genseckey(u16 cardnr, u16 domain, memcpy(preqparm->lv1.key_length, "KEYLN32 ", 8); break; default: - DEBUG_ERR("%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); rc = -EINVAL; goto out; } @@ -386,15 +381,15 @@ int cca_genseckey(u16 cardnr, u16 domain, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, errno %d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, errno %d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR("%s secure key generate failure, card response %d/%d\n", - __func__, + ZCRYPT_DBF_ERR("%s secure key generate failure, card response %d/%d\n", + __func__, (int)prepcblk->ccp_rtcode, (int)prepcblk->ccp_rscode); rc = -EIO; @@ -411,8 +406,8 @@ int cca_genseckey(u16 cardnr, u16 domain, - sizeof(prepparm->lv3.keyblock.toklen) - sizeof(prepparm->lv3.keyblock.tokattr); if (seckeysize != SECKEYBLOBSIZE) { - DEBUG_ERR("%s secure token size mismatch %d != %d bytes\n", - __func__, seckeysize, SECKEYBLOBSIZE); + ZCRYPT_DBF_ERR("%s secure token size mismatch %d != %d bytes\n", + __func__, seckeysize, SECKEYBLOBSIZE); rc = -EIO; goto out; } @@ -505,8 +500,8 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, keysize = 32; break; default: - DEBUG_ERR("%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); rc = -EINVAL; goto out; } @@ -524,17 +519,17 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR("%s clear key import failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s clear key import failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } @@ -549,8 +544,8 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, - sizeof(prepparm->lv3.keyblock.toklen) - sizeof(prepparm->lv3.keyblock.tokattr); if (seckeysize != SECKEYBLOBSIZE) { - DEBUG_ERR("%s secure token size mismatch %d != %d bytes\n", - __func__, seckeysize, SECKEYBLOBSIZE); + ZCRYPT_DBF_ERR("%s secure token size mismatch %d != %d bytes\n", + __func__, seckeysize, SECKEYBLOBSIZE); rc = -EIO; goto out; } @@ -651,17 +646,17 @@ int cca_sec2protkey(u16 cardnr, u16 domain, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR("%s unwrap secure key failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -669,10 +664,10 @@ int cca_sec2protkey(u16 cardnr, u16 domain, goto out; } if (prepcblk->ccp_rscode != 0) { - DEBUG_WARN("%s unwrap secure key warning, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ @@ -683,8 +678,8 @@ int cca_sec2protkey(u16 cardnr, u16 domain, /* check the returned keyblock */ if (prepparm->lv3.ckb.version != 0x01 && prepparm->lv3.ckb.version != 0x02) { - DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x\n", - __func__, (int)prepparm->lv3.ckb.version); + ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x\n", + __func__, (int)prepparm->lv3.ckb.version); rc = -EIO; goto out; } @@ -707,8 +702,8 @@ int cca_sec2protkey(u16 cardnr, u16 domain, *protkeytype = PKEY_KEYTYPE_AES_256; break; default: - DEBUG_ERR("%s unknown/unsupported keylen %d\n", - __func__, prepparm->lv3.ckb.len); + ZCRYPT_DBF_ERR("%s unknown/unsupported keylen %d\n", + __func__, prepparm->lv3.ckb.len); rc = -EIO; goto out; } @@ -840,9 +835,8 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, case 256: break; default: - DEBUG_ERR( - "%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); rc = -EINVAL; goto out; } @@ -880,19 +874,17 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR( - "%s cipher key generate failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s cipher key generate failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } @@ -905,8 +897,8 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, /* do some plausibility checks on the key block */ if (prepparm->kb.len < 120 + 5 * sizeof(uint16_t) || prepparm->kb.len > 136 + 5 * sizeof(uint16_t)) { - DEBUG_ERR("%s reply with invalid or unknown key block\n", - __func__); + ZCRYPT_DBF_ERR("%s reply with invalid or unknown key block\n", + __func__); rc = -EIO; goto out; } @@ -1048,19 +1040,17 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR( - "%s CSNBKPI2 failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s CSNBKPI2 failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } @@ -1073,8 +1063,8 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, /* do some plausibility checks on the key block */ if (prepparm->kb.len < 120 + 3 * sizeof(uint16_t) || prepparm->kb.len > 136 + 3 * sizeof(uint16_t)) { - DEBUG_ERR("%s reply with invalid or unknown key block\n", - __func__); + ZCRYPT_DBF_ERR("%s reply with invalid or unknown key block\n", + __func__); rc = -EIO; goto out; } @@ -1132,33 +1122,29 @@ int cca_clr2cipherkey(u16 card, u16 dom, u32 keybitsize, u32 keygenflags, rc = _ip_cprb_helper(card, dom, "AES ", "FIRST ", "MIN3PART", exorbuf, keybitsize, token, &tokensize); if (rc) { - DEBUG_ERR( - "%s clear key import 1/4 with CSNBKPI2 failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s clear key import 1/4 with CSNBKPI2 failed, rc=%d\n", + __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "ADD-PART", NULL, clrkey, keybitsize, token, &tokensize); if (rc) { - DEBUG_ERR( - "%s clear key import 2/4 with CSNBKPI2 failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s clear key import 2/4 with CSNBKPI2 failed, rc=%d\n", + __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "ADD-PART", NULL, exorbuf, keybitsize, token, &tokensize); if (rc) { - DEBUG_ERR( - "%s clear key import 3/4 with CSNBKPI2 failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s clear key import 3/4 with CSNBKPI2 failed, rc=%d\n", + __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "COMPLETE", NULL, NULL, keybitsize, token, &tokensize); if (rc) { - DEBUG_ERR( - "%s clear key import 4/4 with CSNBKPI2 failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s clear key import 4/4 with CSNBKPI2 failed, rc=%d\n", + __func__, rc); goto out; } @@ -1265,19 +1251,17 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR( - "%s unwrap secure key failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -1285,11 +1269,10 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, goto out; } if (prepcblk->ccp_rscode != 0) { - DEBUG_WARN( - "%s unwrap secure key warning, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ @@ -1300,15 +1283,14 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, /* check the returned keyblock */ if (prepparm->vud.ckb.version != 0x01 && prepparm->vud.ckb.version != 0x02) { - DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x\n", - __func__, (int)prepparm->vud.ckb.version); + ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x\n", + __func__, (int)prepparm->vud.ckb.version); rc = -EIO; goto out; } if (prepparm->vud.ckb.algo != 0x02) { - DEBUG_ERR( - "%s reply param keyblock algo mismatch 0x%02x != 0x02\n", - __func__, (int)prepparm->vud.ckb.algo); + ZCRYPT_DBF_ERR("%s reply param keyblock algo mismatch 0x%02x != 0x02\n", + __func__, (int)prepparm->vud.ckb.algo); rc = -EIO; goto out; } @@ -1331,8 +1313,8 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, *protkeytype = PKEY_KEYTYPE_AES_256; break; default: - DEBUG_ERR("%s unknown/unsupported keylen %d\n", - __func__, prepparm->vud.ckb.keylen); + ZCRYPT_DBF_ERR("%s unknown/unsupported keylen %d\n", + __func__, prepparm->vud.ckb.keylen); rc = -EIO; goto out; } @@ -1432,19 +1414,17 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR( - "%s unwrap secure key failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -1452,11 +1432,10 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, goto out; } if (prepcblk->ccp_rscode != 0) { - DEBUG_WARN( - "%s unwrap secure key warning, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ @@ -1466,23 +1445,22 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, /* check the returned keyblock */ if (prepparm->vud.ckb.version != 0x02) { - DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x != 0x02\n", - __func__, (int)prepparm->vud.ckb.version); + ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x != 0x02\n", + __func__, (int)prepparm->vud.ckb.version); rc = -EIO; goto out; } if (prepparm->vud.ckb.algo != 0x81) { - DEBUG_ERR( - "%s reply param keyblock algo mismatch 0x%02x != 0x81\n", - __func__, (int)prepparm->vud.ckb.algo); + ZCRYPT_DBF_ERR("%s reply param keyblock algo mismatch 0x%02x != 0x81\n", + __func__, (int)prepparm->vud.ckb.algo); rc = -EIO; goto out; } /* copy the translated protected key */ if (prepparm->vud.ckb.keylen > *protkeylen) { - DEBUG_ERR("%s prot keylen mismatch %d > buffersize %u\n", - __func__, prepparm->vud.ckb.keylen, *protkeylen); + ZCRYPT_DBF_ERR("%s prot keylen mismatch %d > buffersize %u\n", + __func__, prepparm->vud.ckb.keylen, *protkeylen); rc = -EIO; goto out; } @@ -1550,17 +1528,17 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR("%s unwrap secure key failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } diff --git a/drivers/s390/crypto/zcrypt_debug.h b/drivers/s390/crypto/zcrypt_debug.h index 5cf88aabd64b9..9a208dc4c2005 100644 --- a/drivers/s390/crypto/zcrypt_debug.h +++ b/drivers/s390/crypto/zcrypt_debug.h @@ -17,7 +17,7 @@ #define RC2ERR(rc) ((rc) ? DBF_ERR : DBF_INFO) #define RC2WARN(rc) ((rc) ? DBF_WARN : DBF_INFO) -#define DBF_MAX_SPRINTF_ARGS 6 +#define ZCRYPT_DBF_MAX_SPRINTF_ARGS 6 #define ZCRYPT_DBF(...) \ debug_sprintf_event(zcrypt_dbf_info, ##__VA_ARGS__) @@ -27,8 +27,6 @@ debug_sprintf_event(zcrypt_dbf_info, DBF_WARN, ##__VA_ARGS__) #define ZCRYPT_DBF_INFO(...) \ debug_sprintf_event(zcrypt_dbf_info, DBF_INFO, ##__VA_ARGS__) -#define ZCRYPT_DBF_DBG(...) \ - debug_sprintf_event(zcrypt_dbf_info, DBF_DEBUG, ##__VA_ARGS__) extern debug_info_t *zcrypt_dbf_info; diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index 0a877f9792c2a..eb7f5489ccf95 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -24,11 +24,6 @@ #include "zcrypt_ep11misc.h" #include "zcrypt_ccamisc.h" -#define DEBUG_DBG(...) ZCRYPT_DBF(DBF_DEBUG, ##__VA_ARGS__) -#define DEBUG_INFO(...) ZCRYPT_DBF(DBF_INFO, ##__VA_ARGS__) -#define DEBUG_WARN(...) ZCRYPT_DBF(DBF_WARN, ##__VA_ARGS__) -#define DEBUG_ERR(...) ZCRYPT_DBF(DBF_ERR, ##__VA_ARGS__) - #define EP11_PINBLOB_V1_BYTES 56 /* default iv used here */ @@ -510,7 +505,7 @@ static int check_reply_pl(const u8 *pl, const char *func) /* start tag */ if (*pl++ != 0x30) { - DEBUG_ERR("%s reply start tag mismatch\n", func); + ZCRYPT_DBF_ERR("%s reply start tag mismatch\n", func); return -EIO; } @@ -527,40 +522,41 @@ static int check_reply_pl(const u8 *pl, const char *func) len = *((u16 *)pl); pl += 2; } else { - DEBUG_ERR("%s reply start tag lenfmt mismatch 0x%02hhx\n", - func, *pl); + ZCRYPT_DBF_ERR("%s reply start tag lenfmt mismatch 0x%02hhx\n", + func, *pl); return -EIO; } /* len should cover at least 3 fields with 32 bit value each */ if (len < 3 * 6) { - DEBUG_ERR("%s reply length %d too small\n", func, len); + ZCRYPT_DBF_ERR("%s reply length %d too small\n", func, len); return -EIO; } /* function tag, length and value */ if (pl[0] != 0x04 || pl[1] != 0x04) { - DEBUG_ERR("%s function tag or length mismatch\n", func); + ZCRYPT_DBF_ERR("%s function tag or length mismatch\n", func); return -EIO; } pl += 6; /* dom tag, length and value */ if (pl[0] != 0x04 || pl[1] != 0x04) { - DEBUG_ERR("%s dom tag or length mismatch\n", func); + ZCRYPT_DBF_ERR("%s dom tag or length mismatch\n", func); return -EIO; } pl += 6; /* return value tag, length and value */ if (pl[0] != 0x04 || pl[1] != 0x04) { - DEBUG_ERR("%s return value tag or length mismatch\n", func); + ZCRYPT_DBF_ERR("%s return value tag or length mismatch\n", + func); return -EIO; } pl += 2; ret = *((u32 *)pl); if (ret != 0) { - DEBUG_ERR("%s return value 0x%04x != 0\n", func, ret); + ZCRYPT_DBF_ERR("%s return value 0x%04x != 0\n", func, ret); return -EIO; } @@ -626,9 +622,8 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -636,13 +631,13 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, if (rc) goto out; if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } if (rep_pl->data_len > buflen) { - DEBUG_ERR("%s mismatch between reply data len and buffer len\n", - __func__); + ZCRYPT_DBF_ERR("%s mismatch between reply data len and buffer len\n", + __func__); rc = -ENOSPC; goto out; } @@ -816,9 +811,8 @@ static int _ep11_genaeskey(u16 card, u16 domain, case 256: break; default: - DEBUG_ERR( - "%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); rc = -EINVAL; goto out; } @@ -878,9 +872,8 @@ static int _ep11_genaeskey(u16 card, u16 domain, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)card, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)card, (int)domain, rc); goto out; } @@ -888,13 +881,13 @@ static int _ep11_genaeskey(u16 card, u16 domain, if (rc) goto out; if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } if (rep_pl->data_len > *keybufsize) { - DEBUG_ERR("%s mismatch reply data len / key buffer len\n", - __func__); + ZCRYPT_DBF_ERR("%s mismatch reply data len / key buffer len\n", + __func__); rc = -ENOSPC; goto out; } @@ -1030,9 +1023,8 @@ static int ep11_cryptsingle(u16 card, u16 domain, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)card, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)card, (int)domain, rc); goto out; } @@ -1040,7 +1032,7 @@ static int ep11_cryptsingle(u16 card, u16 domain, if (rc) goto out; if (rep_pl->data_tag != 0x04) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } @@ -1053,14 +1045,14 @@ static int ep11_cryptsingle(u16 card, u16 domain, n = *((u16 *)p); p += 2; } else { - DEBUG_ERR("%s unknown reply data length format 0x%02hhx\n", - __func__, rep_pl->data_lenfmt); + ZCRYPT_DBF_ERR("%s unknown reply data length format 0x%02hhx\n", + __func__, rep_pl->data_lenfmt); rc = -EIO; goto out; } if (n > *outbufsize) { - DEBUG_ERR("%s mismatch reply data len %d / output buffer %zu\n", - __func__, n, *outbufsize); + ZCRYPT_DBF_ERR("%s mismatch reply data len %d / output buffer %zu\n", + __func__, n, *outbufsize); rc = -ENOSPC; goto out; } @@ -1188,9 +1180,8 @@ static int _ep11_unwrapkey(u16 card, u16 domain, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)card, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)card, (int)domain, rc); goto out; } @@ -1198,13 +1189,13 @@ static int _ep11_unwrapkey(u16 card, u16 domain, if (rc) goto out; if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } if (rep_pl->data_len > *keybufsize) { - DEBUG_ERR("%s mismatch reply data len / key buffer len\n", - __func__); + ZCRYPT_DBF_ERR("%s mismatch reply data len / key buffer len\n", + __func__); rc = -ENOSPC; goto out; } @@ -1343,9 +1334,8 @@ static int _ep11_wrapkey(u16 card, u16 domain, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)card, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)card, (int)domain, rc); goto out; } @@ -1353,13 +1343,13 @@ static int _ep11_wrapkey(u16 card, u16 domain, if (rc) goto out; if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } if (rep_pl->data_len > *datasize) { - DEBUG_ERR("%s mismatch reply data len / data buffer len\n", - __func__); + ZCRYPT_DBF_ERR("%s mismatch reply data len / data buffer len\n", + __func__); rc = -ENOSPC; goto out; } @@ -1386,9 +1376,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, if (keybitsize == 128 || keybitsize == 192 || keybitsize == 256) { clrkeylen = keybitsize / 8; } else { - DEBUG_ERR( - "%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); return -EINVAL; } @@ -1405,9 +1394,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, 0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */ kek, &keklen); if (rc) { - DEBUG_ERR( - "%s generate kek key failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s generate kek key failed, rc=%d\n", + __func__, rc); goto out; } @@ -1415,9 +1403,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, rc = ep11_cryptsingle(card, domain, 0, 0, def_iv, kek, keklen, clrkey, clrkeylen, encbuf, &encbuflen); if (rc) { - DEBUG_ERR( - "%s encrypting key value with kek key failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s encrypting key value with kek key failed, rc=%d\n", + __func__, rc); goto out; } @@ -1426,9 +1413,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, encbuf, encbuflen, 0, def_iv, keybitsize, 0, keybuf, keybufsize, keytype); if (rc) { - DEBUG_ERR( - "%s importing key value as new key failed,, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s importing key value as new key failed,, rc=%d\n", + __func__, rc); goto out; } @@ -1476,17 +1462,16 @@ int ep11_kblob2protkey(u16 card, u16 dom, rc = _ep11_wrapkey(card, dom, (u8 *)key, keylen, 0, def_iv, wkbuf, &wkbuflen); if (rc) { - DEBUG_ERR( - "%s rewrapping ep11 key to pkey failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s rewrapping ep11 key to pkey failed, rc=%d\n", + __func__, rc); goto out; } wki = (struct wk_info *)wkbuf; /* check struct version and pkey type */ if (wki->version != 1 || wki->pkeytype < 1 || wki->pkeytype > 5) { - DEBUG_ERR("%s wk info version %d or pkeytype %d mismatch.\n", - __func__, (int)wki->version, (int)wki->pkeytype); + ZCRYPT_DBF_ERR("%s wk info version %d or pkeytype %d mismatch.\n", + __func__, (int)wki->version, (int)wki->pkeytype); rc = -EIO; goto out; } @@ -1511,8 +1496,8 @@ int ep11_kblob2protkey(u16 card, u16 dom, *protkeytype = PKEY_KEYTYPE_AES_256; break; default: - DEBUG_ERR("%s unknown/unsupported AES pkeysize %d\n", - __func__, (int)wki->pkeysize); + ZCRYPT_DBF_ERR("%s unknown/unsupported AES pkeysize %d\n", + __func__, (int)wki->pkeysize); rc = -EIO; goto out; } @@ -1525,16 +1510,16 @@ int ep11_kblob2protkey(u16 card, u16 dom, break; case 2: /* TDES */ default: - DEBUG_ERR("%s unknown/unsupported key type %d\n", - __func__, (int)wki->pkeytype); + ZCRYPT_DBF_ERR("%s unknown/unsupported key type %d\n", + __func__, (int)wki->pkeytype); rc = -EIO; goto out; } /* copy the translated protected key */ if (wki->pkeysize > *protkeylen) { - DEBUG_ERR("%s wk info pkeysize %llu > protkeysize %u\n", - __func__, wki->pkeysize, *protkeylen); + ZCRYPT_DBF_ERR("%s wk info pkeysize %llu > protkeysize %u\n", + __func__, wki->pkeysize, *protkeylen); rc = -EINVAL; goto out; } diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h index a44fcfcec9387..46e27b43a8afe 100644 --- a/drivers/s390/crypto/zcrypt_error.h +++ b/drivers/s390/crypto/zcrypt_error.h @@ -119,10 +119,9 @@ static inline int convert_error(struct zcrypt_queue *zq, case REP82_ERROR_MESSAGE_TYPE: /* 0x20 */ case REP82_ERROR_TRANSPORT_FAIL: /* 0x90 */ /* - * Msg to wrong type or card/infrastructure failure. - * Trigger rescan of the ap bus, trigger retry request. + * Msg to wrong type or card/infrastructure failure. Return + * EAGAIN, the upper layer may do a retry on the request. */ - atomic_set(&zcrypt_rescan_req, 1); /* For type 86 response show the apfs value (failure reason) */ if (ehdr->reply_code == REP82_ERROR_TRANSPORT_FAIL && ehdr->type == TYPE86_RSP_CODE) { diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 2e155de8abe5b..3b39cb8f926db 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -427,7 +427,7 @@ static void zcrypt_msgtype50_receive(struct ap_queue *aq, len = t80h->len; if (len > reply->bufsize || len > msg->bufsize || len != reply->len) { - ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); + pr_debug("%s len mismatch => EMSGSIZE\n", __func__); msg->rc = -EMSGSIZE; goto out; } @@ -487,9 +487,9 @@ static long zcrypt_msgtype50_modexpo(struct zcrypt_queue *zq, out: ap_msg->private = NULL; if (rc) - ZCRYPT_DBF_DBG("%s send me cprb at dev=%02x.%04x rc=%d\n", - __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), rc); + pr_debug("%s send me cprb at dev=%02x.%04x rc=%d\n", + __func__, AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), rc); return rc; } @@ -537,9 +537,9 @@ static long zcrypt_msgtype50_modexpo_crt(struct zcrypt_queue *zq, out: ap_msg->private = NULL; if (rc) - ZCRYPT_DBF_DBG("%s send crt cprb at dev=%02x.%04x rc=%d\n", - __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), rc); + pr_debug("%s send crt cprb at dev=%02x.%04x rc=%d\n", + __func__, AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), rc); return rc; } diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 3c53abbdc3420..215f257d2360d 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -437,9 +437,9 @@ static int xcrb_msg_to_type6cprb_msgx(bool userspace, struct ap_message *ap_msg, ap_msg->flags |= AP_MSG_FLAG_ADMIN; break; default: - ZCRYPT_DBF_DBG("%s unknown CPRB minor version '%c%c'\n", - __func__, msg->cprbx.func_id[0], - msg->cprbx.func_id[1]); + pr_debug("%s unknown CPRB minor version '%c%c'\n", + __func__, msg->cprbx.func_id[0], + msg->cprbx.func_id[1]); } /* copy data block */ @@ -629,9 +629,9 @@ static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq, /* Copy CPRB to user */ if (xcrb->reply_control_blk_length < msg->fmt2.count1) { - ZCRYPT_DBF_DBG("%s reply_control_blk_length %u < required %u => EMSGSIZE\n", - __func__, xcrb->reply_control_blk_length, - msg->fmt2.count1); + pr_debug("%s reply_control_blk_length %u < required %u => EMSGSIZE\n", + __func__, xcrb->reply_control_blk_length, + msg->fmt2.count1); return -EMSGSIZE; } if (z_copy_to_user(userspace, xcrb->reply_control_blk_addr, @@ -642,9 +642,9 @@ static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq, /* Copy data buffer to user */ if (msg->fmt2.count2) { if (xcrb->reply_data_length < msg->fmt2.count2) { - ZCRYPT_DBF_DBG("%s reply_data_length %u < required %u => EMSGSIZE\n", - __func__, xcrb->reply_data_length, - msg->fmt2.count2); + pr_debug("%s reply_data_length %u < required %u => EMSGSIZE\n", + __func__, xcrb->reply_data_length, + msg->fmt2.count2); return -EMSGSIZE; } if (z_copy_to_user(userspace, xcrb->reply_data_addr, @@ -673,9 +673,9 @@ static int convert_type86_ep11_xcrb(bool userspace, struct zcrypt_queue *zq, char *data = reply->msg; if (xcrb->resp_len < msg->fmt2.count1) { - ZCRYPT_DBF_DBG("%s resp_len %u < required %u => EMSGSIZE\n", - __func__, (unsigned int)xcrb->resp_len, - msg->fmt2.count1); + pr_debug("%s resp_len %u < required %u => EMSGSIZE\n", + __func__, (unsigned int)xcrb->resp_len, + msg->fmt2.count1); return -EMSGSIZE; } @@ -875,7 +875,8 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, len = sizeof(struct type86x_reply) + t86r->length; if (len > reply->bufsize || len > msg->bufsize || len != reply->len) { - ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); + pr_debug("%s len mismatch => EMSGSIZE\n", + __func__); msg->rc = -EMSGSIZE; goto out; } @@ -889,7 +890,8 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, len = t86r->fmt2.offset1 + t86r->fmt2.count1; if (len > reply->bufsize || len > msg->bufsize || len != reply->len) { - ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); + pr_debug("%s len mismatch => EMSGSIZE\n", + __func__); msg->rc = -EMSGSIZE; goto out; } @@ -939,7 +941,8 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq, len = t86r->fmt2.offset1 + t86r->fmt2.count1; if (len > reply->bufsize || len > msg->bufsize || len != reply->len) { - ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); + pr_debug("%s len mismatch => EMSGSIZE\n", + __func__); msg->rc = -EMSGSIZE; goto out; } @@ -1151,9 +1154,9 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, out: if (rc) - ZCRYPT_DBF_DBG("%s send cprb at dev=%02x.%04x rc=%d\n", - __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), rc); + pr_debug("%s send cprb at dev=%02x.%04x rc=%d\n", + __func__, AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), rc); return rc; } @@ -1274,9 +1277,9 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * out: if (rc) - ZCRYPT_DBF_DBG("%s send cprb at dev=%02x.%04x rc=%d\n", - __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), rc); + pr_debug("%s send cprb at dev=%02x.%04x rc=%d\n", + __func__, AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), rc); return rc; } diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 2c8e964425dc3..43778b088ffac 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -292,13 +292,16 @@ static int ism_read_local_gid(struct ism_dev *ism) static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { clear_bit(dmb->sba_idx, ism->sba_bitmap); - dma_free_coherent(&ism->pdev->dev, dmb->dmb_len, - dmb->cpu_addr, dmb->dma_addr); + dma_unmap_page(&ism->pdev->dev, dmb->dma_addr, dmb->dmb_len, + DMA_FROM_DEVICE); + folio_put(virt_to_folio(dmb->cpu_addr)); } static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { + struct folio *folio; unsigned long bit; + int rc; if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev)) return -EINVAL; @@ -315,14 +318,30 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb) test_and_set_bit(dmb->sba_idx, ism->sba_bitmap)) return -EINVAL; - dmb->cpu_addr = dma_alloc_coherent(&ism->pdev->dev, dmb->dmb_len, - &dmb->dma_addr, - GFP_KERNEL | __GFP_NOWARN | - __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!dmb->cpu_addr) - clear_bit(dmb->sba_idx, ism->sba_bitmap); + folio = folio_alloc(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | + __GFP_NORETRY, get_order(dmb->dmb_len)); - return dmb->cpu_addr ? 0 : -ENOMEM; + if (!folio) { + rc = -ENOMEM; + goto out_bit; + } + + dmb->cpu_addr = folio_address(folio); + dmb->dma_addr = dma_map_page(&ism->pdev->dev, + virt_to_page(dmb->cpu_addr), 0, + dmb->dmb_len, DMA_FROM_DEVICE); + if (dma_mapping_error(&ism->pdev->dev, dmb->dma_addr)) { + rc = -ENOMEM; + goto out_free; + } + + return 0; + +out_free: + kfree(dmb->cpu_addr); +out_bit: + clear_bit(dmb->sba_idx, ism->sba_bitmap); + return rc; } int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb, diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 613eab7297046..41fe8a043d61f 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -956,7 +956,7 @@ static inline struct dst_entry *qeth_dst_check_rcu(struct sk_buff *skb, struct dst_entry *dst = skb_dst(skb); struct rt6_info *rt; - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (dst) { if (proto == htons(ETH_P_IPV6)) dst = dst_check(dst, rt6_get_cookie(rt)); @@ -970,15 +970,14 @@ static inline struct dst_entry *qeth_dst_check_rcu(struct sk_buff *skb, static inline __be32 qeth_next_hop_v4_rcu(struct sk_buff *skb, struct dst_entry *dst) { - struct rtable *rt = (struct rtable *) dst; - - return (rt) ? rt_nexthop(rt, ip_hdr(skb)->daddr) : ip_hdr(skb)->daddr; + return (dst) ? rt_nexthop(dst_rtable(dst), ip_hdr(skb)->daddr) : + ip_hdr(skb)->daddr; } static inline struct in6_addr *qeth_next_hop_v6_rcu(struct sk_buff *skb, struct dst_entry *dst) { - struct rt6_info *rt = (struct rt6_info *) dst; + struct rt6_info *rt = dst_rt6_info(dst); if (rt && !ipv6_addr_any(&rt->rt6i_gateway)) return &rt->rt6i_gateway; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index cf8506d0f185c..dc5ae75d462b9 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -364,30 +364,33 @@ static int qeth_cq_init(struct qeth_card *card) return rc; } +static void qeth_free_cq(struct qeth_card *card) +{ + if (card->qdio.c_q) { + qeth_free_qdio_queue(card->qdio.c_q); + card->qdio.c_q = NULL; + } +} + static int qeth_alloc_cq(struct qeth_card *card) { if (card->options.cq == QETH_CQ_ENABLED) { QETH_CARD_TEXT(card, 2, "cqon"); - card->qdio.c_q = qeth_alloc_qdio_queue(); if (!card->qdio.c_q) { - dev_err(&card->gdev->dev, "Failed to create completion queue\n"); - return -ENOMEM; + card->qdio.c_q = qeth_alloc_qdio_queue(); + if (!card->qdio.c_q) { + dev_err(&card->gdev->dev, + "Failed to create completion queue\n"); + return -ENOMEM; + } } } else { QETH_CARD_TEXT(card, 2, "nocq"); - card->qdio.c_q = NULL; + qeth_free_cq(card); } return 0; } -static void qeth_free_cq(struct qeth_card *card) -{ - if (card->qdio.c_q) { - qeth_free_qdio_queue(card->qdio.c_q); - card->qdio.c_q = NULL; - } -} - static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15, int delayed) { @@ -1179,6 +1182,20 @@ static int qeth_check_irb_error(struct qeth_card *card, struct ccw_device *cdev, } } +/** + * qeth_irq() - qeth interrupt handler + * @cdev: ccw device + * @intparm: expect pointer to iob + * @irb: Interruption Response Block + * + * In the good path: + * corresponding qeth channel is locked with last used iob as active_cmd. + * But this function is also called for error interrupts. + * + * Caller ensures that: + * Interrupts are disabled; ccw device lock is held; + * + */ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) { @@ -1220,11 +1237,10 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, iob = (struct qeth_cmd_buffer *) (addr_t)intparm; } - qeth_unlock_channel(card, channel); - rc = qeth_check_irb_error(card, cdev, irb); if (rc) { /* IO was terminated, free its resources. */ + qeth_unlock_channel(card, channel); if (iob) qeth_cancel_cmd(iob, rc); return; @@ -1268,6 +1284,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, rc = qeth_get_problem(card, cdev, irb); if (rc) { card->read_or_write_problem = 1; + qeth_unlock_channel(card, channel); if (iob) qeth_cancel_cmd(iob, rc); qeth_clear_ipacmd_list(card); @@ -1276,6 +1293,26 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, } } + if (scsw_cmd_is_valid_cc(&irb->scsw) && irb->scsw.cmd.cc == 1 && iob) { + /* channel command hasn't started: retry. + * active_cmd is still set to last iob + */ + QETH_CARD_TEXT(card, 2, "irqcc1"); + rc = ccw_device_start_timeout(cdev, __ccw_from_cmd(iob), + (addr_t)iob, 0, 0, iob->timeout); + if (rc) { + QETH_DBF_MESSAGE(2, + "ccw retry on %x failed, rc = %i\n", + CARD_DEVID(card), rc); + QETH_CARD_TEXT_(card, 2, " err%d", rc); + qeth_unlock_channel(card, channel); + qeth_cancel_cmd(iob, rc); + } + return; + } + + qeth_unlock_channel(card, channel); + if (iob) { /* sanity check: */ if (irb->scsw.cmd.count > iob->length) { @@ -2594,6 +2631,10 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "allcqdbf"); + /* completion */ + if (qeth_alloc_cq(card)) + goto out_err; + if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED, QETH_QDIO_ALLOCATED) != QETH_QDIO_UNINITIALIZED) return 0; @@ -2629,10 +2670,6 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT; } - /* completion */ - if (qeth_alloc_cq(card)) - goto out_freeoutq; - return 0; out_freeoutq: @@ -2643,6 +2680,8 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) qeth_free_buffer_pool(card); out_buffer_pool: atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED); + qeth_free_cq(card); +out_err: return -ENOMEM; } @@ -2650,11 +2689,12 @@ static void qeth_free_qdio_queues(struct qeth_card *card) { int i, j; + qeth_free_cq(card); + if (atomic_xchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED) == QETH_QDIO_UNINITIALIZED) return; - qeth_free_cq(card); for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) { if (card->qdio.in_q->bufs[j].rx_skb) { consume_skb(card->qdio.in_q->bufs[j].rx_skb); @@ -3708,24 +3748,11 @@ static void qeth_qdio_poll(struct ccw_device *cdev, unsigned long card_ptr) int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) { - int rc; - - if (card->options.cq == QETH_CQ_NOTAVAILABLE) { - rc = -1; - goto out; - } else { - if (card->options.cq == cq) { - rc = 0; - goto out; - } - - qeth_free_qdio_queues(card); - card->options.cq = cq; - rc = 0; - } -out: - return rc; + if (card->options.cq == QETH_CQ_NOTAVAILABLE) + return -1; + card->options.cq = cq; + return 0; } EXPORT_SYMBOL_GPL(qeth_configure_cq); diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h index 7bd2ba1ad4d11..f30fe324e6ecc 100644 --- a/drivers/scsi/bfa/bfa.h +++ b/drivers/scsi/bfa/bfa.h @@ -20,7 +20,6 @@ struct bfa_s; typedef void (*bfa_isr_func_t) (struct bfa_s *bfa, struct bfi_msg_s *m); -typedef void (*bfa_cb_cbfn_status_t) (void *cbarg, bfa_status_t status); /* * Interrupt message handlers @@ -437,4 +436,12 @@ struct bfa_cb_pending_q_s { (__qe)->data = (__data); \ } while (0) +#define bfa_pending_q_init_status(__qe, __cbfn, __cbarg, __data) do { \ + bfa_q_qe_init(&((__qe)->hcb_qe.qe)); \ + (__qe)->hcb_qe.cbfn_status = (__cbfn); \ + (__qe)->hcb_qe.cbarg = (__cbarg); \ + (__qe)->hcb_qe.pre_rmv = BFA_TRUE; \ + (__qe)->data = (__data); \ +} while (0) + #endif /* __BFA_H__ */ diff --git a/drivers/scsi/bfa/bfa_core.c b/drivers/scsi/bfa/bfa_core.c index 6846ca8f7313c..3438d0b8ba062 100644 --- a/drivers/scsi/bfa/bfa_core.c +++ b/drivers/scsi/bfa/bfa_core.c @@ -1907,15 +1907,13 @@ bfa_comp_process(struct bfa_s *bfa, struct list_head *comp_q) struct list_head *qe; struct list_head *qen; struct bfa_cb_qe_s *hcb_qe; - bfa_cb_cbfn_status_t cbfn; list_for_each_safe(qe, qen, comp_q) { hcb_qe = (struct bfa_cb_qe_s *) qe; if (hcb_qe->pre_rmv) { /* qe is invalid after return, dequeue before cbfn() */ list_del(qe); - cbfn = (bfa_cb_cbfn_status_t)(hcb_qe->cbfn); - cbfn(hcb_qe->cbarg, hcb_qe->fw_status); + hcb_qe->cbfn_status(hcb_qe->cbarg, hcb_qe->fw_status); } else hcb_qe->cbfn(hcb_qe->cbarg, BFA_TRUE); } diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h index 933a1c3890ff5..5e568d6d7b261 100644 --- a/drivers/scsi/bfa/bfa_ioc.h +++ b/drivers/scsi/bfa/bfa_ioc.h @@ -361,14 +361,18 @@ struct bfa_reqq_wait_s { void *cbarg; }; -typedef void (*bfa_cb_cbfn_t) (void *cbarg, bfa_boolean_t complete); +typedef void (*bfa_cb_cbfn_t) (void *cbarg, bfa_boolean_t complete); +typedef void (*bfa_cb_cbfn_status_t) (void *cbarg, bfa_status_t status); /* * Generic BFA callback element. */ struct bfa_cb_qe_s { struct list_head qe; - bfa_cb_cbfn_t cbfn; + union { + bfa_cb_cbfn_status_t cbfn_status; + bfa_cb_cbfn_t cbfn; + }; bfa_boolean_t once; bfa_boolean_t pre_rmv; /* set for stack based qe(s) */ bfa_status_t fw_status; /* to access fw status in comp proc */ diff --git a/drivers/scsi/bfa/bfad_bsg.c b/drivers/scsi/bfa/bfad_bsg.c index d4ceca2d435ee..54bd11e6d5933 100644 --- a/drivers/scsi/bfa/bfad_bsg.c +++ b/drivers/scsi/bfa/bfad_bsg.c @@ -2135,8 +2135,7 @@ bfad_iocmd_fcport_get_stats(struct bfad_s *bfad, void *cmd) struct bfa_cb_pending_q_s cb_qe; init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, &iocmd->stats); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, &iocmd->stats); spin_lock_irqsave(&bfad->bfad_lock, flags); iocmd->status = bfa_fcport_get_stats(&bfad->bfa, &cb_qe); spin_unlock_irqrestore(&bfad->bfad_lock, flags); @@ -2159,7 +2158,7 @@ bfad_iocmd_fcport_reset_stats(struct bfad_s *bfad, void *cmd) struct bfa_cb_pending_q_s cb_qe; init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, &fcomp, NULL); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, NULL); spin_lock_irqsave(&bfad->bfad_lock, flags); iocmd->status = bfa_fcport_clear_stats(&bfad->bfa, &cb_qe); @@ -2443,8 +2442,7 @@ bfad_iocmd_qos_get_stats(struct bfad_s *bfad, void *cmd) struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(&bfad->bfa); init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, &iocmd->stats); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, &iocmd->stats); spin_lock_irqsave(&bfad->bfad_lock, flags); WARN_ON(!bfa_ioc_get_fcmode(&bfad->bfa.ioc)); @@ -2474,8 +2472,7 @@ bfad_iocmd_qos_reset_stats(struct bfad_s *bfad, void *cmd) struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(&bfad->bfa); init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, NULL); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, NULL); spin_lock_irqsave(&bfad->bfad_lock, flags); WARN_ON(!bfa_ioc_get_fcmode(&bfad->bfa.ioc)); diff --git a/drivers/scsi/bfa/bfad_debugfs.c b/drivers/scsi/bfa/bfad_debugfs.c index 52db147d9979d..f6dd077d47c9a 100644 --- a/drivers/scsi/bfa/bfad_debugfs.c +++ b/drivers/scsi/bfa/bfad_debugfs.c @@ -250,7 +250,7 @@ bfad_debugfs_write_regrd(struct file *file, const char __user *buf, unsigned long flags; void *kern_buf; - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); @@ -317,7 +317,7 @@ bfad_debugfs_write_regwr(struct file *file, const char __user *buf, unsigned long flags; void *kern_buf; - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); diff --git a/drivers/scsi/bnx2fc/bnx2fc_tgt.c b/drivers/scsi/bnx2fc/bnx2fc_tgt.c index 2c246e80c1c4d..d91659811eb3c 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_tgt.c +++ b/drivers/scsi/bnx2fc/bnx2fc_tgt.c @@ -833,7 +833,6 @@ static void bnx2fc_free_session_resc(struct bnx2fc_hba *hba, BNX2FC_TGT_DBG(tgt, "Freeing up session resources\n"); - spin_lock_bh(&tgt->cq_lock); ctx_base_ptr = tgt->ctx_base; tgt->ctx_base = NULL; @@ -889,7 +888,6 @@ static void bnx2fc_free_session_resc(struct bnx2fc_hba *hba, tgt->sq, tgt->sq_dma); tgt->sq = NULL; } - spin_unlock_bh(&tgt->cq_lock); if (ctx_base_ptr) iounmap(ctx_base_ptr); diff --git a/drivers/scsi/csiostor/csio_defs.h b/drivers/scsi/csiostor/csio_defs.h index c38017b4af982..e50e93e7fe5a1 100644 --- a/drivers/scsi/csiostor/csio_defs.h +++ b/drivers/scsi/csiostor/csio_defs.h @@ -73,7 +73,21 @@ csio_list_deleted(struct list_head *list) #define csio_list_prev(elem) (((struct list_head *)(elem))->prev) /* State machine */ -typedef void (*csio_sm_state_t)(void *, uint32_t); +struct csio_lnode; + +/* State machine evets */ +enum csio_ln_ev { + CSIO_LNE_NONE = (uint32_t)0, + CSIO_LNE_LINKUP, + CSIO_LNE_FAB_INIT_DONE, + CSIO_LNE_LINK_DOWN, + CSIO_LNE_DOWN_LINK, + CSIO_LNE_LOGO, + CSIO_LNE_CLOSE, + CSIO_LNE_MAX_EVENT, +}; + +typedef void (*csio_sm_state_t)(struct csio_lnode *ln, enum csio_ln_ev evt); struct csio_sm { struct list_head sm_list; @@ -83,7 +97,7 @@ struct csio_sm { static inline void csio_set_state(void *smp, void *state) { - ((struct csio_sm *)smp)->sm_state = (csio_sm_state_t)state; + ((struct csio_sm *)smp)->sm_state = state; } static inline void diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c index d5ac938970232..5b3ffefae476d 100644 --- a/drivers/scsi/csiostor/csio_lnode.c +++ b/drivers/scsi/csiostor/csio_lnode.c @@ -1095,7 +1095,7 @@ csio_handle_link_down(struct csio_hw *hw, uint8_t portid, uint32_t fcfi, int csio_is_lnode_ready(struct csio_lnode *ln) { - return (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_ready)); + return (csio_get_state(ln) == csio_lns_ready); } /*****************************************************************************/ @@ -1366,15 +1366,15 @@ csio_free_fcfinfo(struct kref *kref) void csio_lnode_state_to_str(struct csio_lnode *ln, int8_t *str) { - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_uninit)) { + if (csio_get_state(ln) == csio_lns_uninit) { strcpy(str, "UNINIT"); return; } - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_ready)) { + if (csio_get_state(ln) == csio_lns_ready) { strcpy(str, "READY"); return; } - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_offline)) { + if (csio_get_state(ln) == csio_lns_offline) { strcpy(str, "OFFLINE"); return; } diff --git a/drivers/scsi/csiostor/csio_lnode.h b/drivers/scsi/csiostor/csio_lnode.h index 372a67d122d38..607698a0f0631 100644 --- a/drivers/scsi/csiostor/csio_lnode.h +++ b/drivers/scsi/csiostor/csio_lnode.h @@ -53,19 +53,6 @@ extern int csio_fcoe_rnodes; extern int csio_fdmi_enable; -/* State machine evets */ -enum csio_ln_ev { - CSIO_LNE_NONE = (uint32_t)0, - CSIO_LNE_LINKUP, - CSIO_LNE_FAB_INIT_DONE, - CSIO_LNE_LINK_DOWN, - CSIO_LNE_DOWN_LINK, - CSIO_LNE_LOGO, - CSIO_LNE_CLOSE, - CSIO_LNE_MAX_EVENT, -}; - - struct csio_fcf_info { struct list_head list; uint8_t priority; diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index bbb7b2d9ffcfb..05c38e43f140a 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1792,7 +1792,7 @@ static int hisi_sas_debug_I_T_nexus_reset(struct domain_device *device) if (dev_is_sata(device)) { struct ata_link *link = &device->sata_dev.ap->link; - rc = ata_wait_after_reset(link, HISI_SAS_WAIT_PHYUP_TIMEOUT, + rc = ata_wait_after_reset(link, jiffies + HISI_SAS_WAIT_PHYUP_TIMEOUT, smp_ata_check_ready_type); } else { msleep(2000); @@ -1962,9 +1962,17 @@ static bool hisi_sas_internal_abort_timeout(struct sas_task *task, struct hisi_sas_internal_abort_data *timeout = data; if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct[0].itct) { - down(&hisi_hba->sem); + /* + * If timeout occurs in device gone scenario, to avoid + * circular dependency like: + * hisi_sas_dev_gone() -> down() -> ... -> + * hisi_sas_internal_abort_timeout() -> down(). + */ + if (!timeout->rst_ha_timeout) + down(&hisi_hba->sem); hisi_hba->hw->debugfs_snapshot_regs(hisi_hba); - up(&hisi_hba->sem); + if (!timeout->rst_ha_timeout) + up(&hisi_hba->sem); } if (task->task_state_flags & SAS_TASK_STATE_DONE) { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index b56fbc61a15ae..86112f234740d 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2244,7 +2244,15 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: if ((dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && (sipc_rx_err_type & RX_FIS_STATUS_ERR_MSK)) { - ts->stat = SAS_PROTO_RESPONSE; + if (task->ata_task.use_ncq) { + struct domain_device *device = task->dev; + struct hisi_sas_device *sas_dev = device->lldd_dev; + + sas_dev->dev_status = HISI_SAS_DEV_NCQ_ERR; + slot->abort = 1; + } else { + ts->stat = SAS_PROTO_RESPONSE; + } } else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { ts->residual = trans_tx_fail_type; ts->stat = SAS_DATA_UNDERRUN; diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index d7f51b84f3c78..445f4a220df3e 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -353,12 +353,13 @@ static void scsi_host_dev_release(struct device *dev) if (shost->shost_state == SHOST_CREATED) { /* - * Free the shost_dev device name here if scsi_host_alloc() - * and scsi_host_put() have been called but neither + * Free the shost_dev device name and remove the proc host dir + * here if scsi_host_{alloc,put}() have been called but neither * scsi_host_add() nor scsi_remove_host() has been called. * This avoids that the memory allocated for the shost_dev - * name is leaked. + * name as well as the proc dir structure are leaked. */ + scsi_proc_hostdir_rm(shost->hostt); kfree(dev_name(&shost->shost_dev)); } diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index af18d20f30794..49c57a9c110b5 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -5850,7 +5850,7 @@ static int hpsa_scsi_host_alloc(struct ctlr_info *h) { struct Scsi_Host *sh; - sh = scsi_host_alloc(&hpsa_driver_template, sizeof(struct ctlr_info)); + sh = scsi_host_alloc(&hpsa_driver_template, sizeof(struct ctlr_info *)); if (sh == NULL) { dev_err(&h->pdev->dev, "scsi_host_alloc failed\n"); return -ENOMEM; diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index a2204674b6808..e97f4e01a865a 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -135,7 +135,7 @@ static int smp_execute_task(struct domain_device *dev, void *req, int req_size, static inline void *alloc_smp_req(int size) { - u8 *p = kzalloc(size, GFP_KERNEL); + u8 *p = kzalloc(ALIGN(size, ARCH_DMA_MINALIGN), GFP_KERNEL); if (p) p[0] = SMP_REQUEST; return p; @@ -239,8 +239,7 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id, /* help some expanders that fail to zero sas_address in the 'no * device' case */ - if (phy->attached_dev_type == SAS_PHY_UNUSED || - phy->linkrate < SAS_LINK_RATE_1_5_GBPS) + if (phy->attached_dev_type == SAS_PHY_UNUSED) memset(phy->attached_sas_addr, 0, SAS_ADDR_SIZE); else memcpy(phy->attached_sas_addr, dr->attached_sas_addr, SAS_ADDR_SIZE); @@ -1621,6 +1620,16 @@ int sas_discover_root_expander(struct domain_device *dev) /* ---------- Domain revalidation ---------- */ +static void sas_get_sas_addr_and_dev_type(struct smp_disc_resp *disc_resp, + u8 *sas_addr, + enum sas_device_type *type) +{ + memcpy(sas_addr, disc_resp->disc.attached_sas_addr, SAS_ADDR_SIZE); + *type = to_dev_type(&disc_resp->disc); + if (*type == SAS_PHY_UNUSED) + memset(sas_addr, 0, SAS_ADDR_SIZE); +} + static int sas_get_phy_discover(struct domain_device *dev, int phy_id, struct smp_disc_resp *disc_resp) { @@ -1674,13 +1683,8 @@ int sas_get_phy_attached_dev(struct domain_device *dev, int phy_id, return -ENOMEM; res = sas_get_phy_discover(dev, phy_id, disc_resp); - if (res == 0) { - memcpy(sas_addr, disc_resp->disc.attached_sas_addr, - SAS_ADDR_SIZE); - *type = to_dev_type(&disc_resp->disc); - if (*type == 0) - memset(sas_addr, 0, SAS_ADDR_SIZE); - } + if (res == 0) + sas_get_sas_addr_and_dev_type(disc_resp, sas_addr, type); kfree(disc_resp); return res; } @@ -1940,6 +1944,7 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, struct expander_device *ex = &dev->ex_dev; struct ex_phy *phy = &ex->ex_phy[phy_id]; enum sas_device_type type = SAS_PHY_UNUSED; + struct smp_disc_resp *disc_resp; u8 sas_addr[SAS_ADDR_SIZE]; char msg[80] = ""; int res; @@ -1951,33 +1956,41 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, SAS_ADDR(dev->sas_addr), phy_id, msg); memset(sas_addr, 0, SAS_ADDR_SIZE); - res = sas_get_phy_attached_dev(dev, phy_id, sas_addr, &type); + disc_resp = alloc_smp_resp(DISCOVER_RESP_SIZE); + if (!disc_resp) + return -ENOMEM; + + res = sas_get_phy_discover(dev, phy_id, disc_resp); switch (res) { case SMP_RESP_NO_PHY: phy->phy_state = PHY_NOT_PRESENT; sas_unregister_devs_sas_addr(dev, phy_id, last); - return res; + goto out_free_resp; case SMP_RESP_PHY_VACANT: phy->phy_state = PHY_VACANT; sas_unregister_devs_sas_addr(dev, phy_id, last); - return res; + goto out_free_resp; case SMP_RESP_FUNC_ACC: break; case -ECOMM: break; default: - return res; + goto out_free_resp; } + if (res == 0) + sas_get_sas_addr_and_dev_type(disc_resp, sas_addr, &type); + if ((SAS_ADDR(sas_addr) == 0) || (res == -ECOMM)) { phy->phy_state = PHY_EMPTY; sas_unregister_devs_sas_addr(dev, phy_id, last); /* - * Even though the PHY is empty, for convenience we discover - * the PHY to update the PHY info, like negotiated linkrate. + * Even though the PHY is empty, for convenience we update + * the PHY info, like negotiated linkrate. */ - sas_ex_phy_discover(dev, phy_id); - return res; + if (res == 0) + sas_set_ex_phy(dev, phy_id, disc_resp); + goto out_free_resp; } else if (SAS_ADDR(sas_addr) == SAS_ADDR(phy->attached_sas_addr) && dev_type_flutter(type, phy->attached_dev_type)) { struct domain_device *ata_dev = sas_ex_to_ata(dev, phy_id); @@ -1989,7 +2002,7 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, action = ", needs recovery"; pr_debug("ex %016llx phy%02d broadcast flutter%s\n", SAS_ADDR(dev->sas_addr), phy_id, action); - return res; + goto out_free_resp; } /* we always have to delete the old device when we went here */ @@ -1998,7 +2011,10 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id, SAS_ADDR(phy->attached_sas_addr)); sas_unregister_devs_sas_addr(dev, phy_id, last); - return sas_discover_new(dev, phy_id); + res = sas_discover_new(dev, phy_id); +out_free_resp: + kfree(disc_resp); + return res; } /** diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index 9047cfcd1072e..cbbfb00ff4a06 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -431,6 +431,9 @@ int sas_eh_abort_handler(struct scsi_cmnd *cmd) struct sas_internal *i = to_sas_internal(host->transportt); unsigned long flags; + if (current != host->ehandler) + return FAILED; + if (!i->dft->lldd_abort_task) return FAILED; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 04d608ea91060..9670cb2bf198e 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -1325,7 +1325,6 @@ struct lpfc_hba { struct timer_list fabric_block_timer; unsigned long bit_flags; atomic_t num_rsrc_err; - atomic_t num_cmd_success; unsigned long last_rsrc_error_time; unsigned long last_ramp_down_time; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS @@ -1430,6 +1429,7 @@ struct lpfc_hba { struct timer_list inactive_vmid_poll; /* RAS Support */ + spinlock_t ras_fwlog_lock; /* do not take while holding another lock */ struct lpfc_ras_fwlog ras_fwlog; uint32_t iocb_cnt; diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index d3a5d6ecdf7d2..6f97a04171c44 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -5864,9 +5864,9 @@ lpfc_ras_fwlog_buffsize_set(struct lpfc_hba *phba, uint val) if (phba->cfg_ras_fwlog_func != PCI_FUNC(phba->pcidev->devfn)) return -EINVAL; - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); state = phba->ras_fwlog.state; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); if (state == REG_INPROGRESS) { lpfc_printf_log(phba, KERN_ERR, LOG_SLI, "6147 RAS Logging " diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index 595dca92e8db5..c305d16cfae9a 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -3169,10 +3169,10 @@ lpfc_bsg_diag_loopback_run(struct bsg_job *job) } cmdwqe = &cmdiocbq->wqe; - memset(cmdwqe, 0, sizeof(union lpfc_wqe)); + memset(cmdwqe, 0, sizeof(*cmdwqe)); if (phba->sli_rev < LPFC_SLI_REV4) { rspwqe = &rspiocbq->wqe; - memset(rspwqe, 0, sizeof(union lpfc_wqe)); + memset(rspwqe, 0, sizeof(*rspwqe)); } INIT_LIST_HEAD(&head); @@ -5070,12 +5070,12 @@ lpfc_bsg_get_ras_config(struct bsg_job *job) bsg_reply->reply_data.vendor_reply.vendor_rsp; /* Current logging state */ - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); if (ras_fwlog->state == ACTIVE) ras_reply->state = LPFC_RASLOG_STATE_RUNNING; else ras_reply->state = LPFC_RASLOG_STATE_STOPPED; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); ras_reply->log_level = phba->ras_fwlog.fw_loglevel; ras_reply->log_buff_sz = phba->cfg_ras_fwlog_buffsize; @@ -5132,13 +5132,13 @@ lpfc_bsg_set_ras_config(struct bsg_job *job) if (action == LPFC_RASACTION_STOP_LOGGING) { /* Check if already disabled */ - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); if (ras_fwlog->state != ACTIVE) { - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); rc = -ESRCH; goto ras_job_error; } - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); /* Disable logging */ lpfc_ras_stop_fwlog(phba); @@ -5149,10 +5149,10 @@ lpfc_bsg_set_ras_config(struct bsg_job *job) * FW-logging with new log-level. Return status * "Logging already Running" to caller. **/ - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); if (ras_fwlog->state != INACTIVE) action_status = -EINPROGRESS; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); /* Enable logging */ rc = lpfc_sli4_ras_fwlog_init(phba, log_level, @@ -5268,13 +5268,13 @@ lpfc_bsg_get_ras_fwlog(struct bsg_job *job) goto ras_job_error; /* Logging to be stopped before reading */ - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); if (ras_fwlog->state == ACTIVE) { - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); rc = -EINPROGRESS; goto ras_job_error; } - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); if (job->request_len < sizeof(struct fc_bsg_request) + diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index ea9b42225e629..20662b4f339eb 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -2196,12 +2196,12 @@ static int lpfc_debugfs_ras_log_data(struct lpfc_hba *phba, memset(buffer, 0, size); - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); if (phba->ras_fwlog.state != ACTIVE) { - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); return -EINVAL; } - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); list_for_each_entry_safe(dmabuf, next, &phba->ras_fwlog.fwlog_buff_list, list) { @@ -2252,13 +2252,13 @@ lpfc_debugfs_ras_log_open(struct inode *inode, struct file *file) int size; int rc = -ENOMEM; - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); if (phba->ras_fwlog.state != ACTIVE) { - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); rc = -EINVAL; goto out; } - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); if (check_mul_overflow(LPFC_RAS_MIN_BUFF_POST_SIZE, phba->cfg_ras_fwlog_buffsize, &size)) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 4d723200690a4..26736122bda17 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -4462,23 +4462,23 @@ lpfc_els_retry_delay(struct timer_list *t) unsigned long flags; struct lpfc_work_evt *evtp = &ndlp->els_retry_evt; + /* Hold a node reference for outstanding queued work */ + if (!lpfc_nlp_get(ndlp)) + return; + spin_lock_irqsave(&phba->hbalock, flags); if (!list_empty(&evtp->evt_listp)) { spin_unlock_irqrestore(&phba->hbalock, flags); + lpfc_nlp_put(ndlp); return; } - /* We need to hold the node by incrementing the reference - * count until the queued work is done - */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); - if (evtp->evt_arg1) { - evtp->evt = LPFC_EVT_ELS_RETRY; - list_add_tail(&evtp->evt_listp, &phba->work_list); - lpfc_worker_wake_up(phba); - } + evtp->evt_arg1 = ndlp; + evtp->evt = LPFC_EVT_ELS_RETRY; + list_add_tail(&evtp->evt_listp, &phba->work_list); spin_unlock_irqrestore(&phba->hbalock, flags); - return; + + lpfc_worker_wake_up(phba); } /** diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index f80bbc315f4ca..da3aee0f63237 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -257,7 +257,9 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) if (evtp->evt_arg1) { evtp->evt = LPFC_EVT_DEV_LOSS; list_add_tail(&evtp->evt_listp, &phba->work_list); + spin_unlock_irqrestore(&phba->hbalock, iflags); lpfc_worker_wake_up(phba); + return; } spin_unlock_irqrestore(&phba->hbalock, iflags); } else { @@ -275,10 +277,7 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) lpfc_disc_state_machine(vport, ndlp, NULL, NLP_EVT_DEVICE_RM); } - } - - return; } /** diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 70bcee64bc8c6..858ca395c0bf0 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -7698,6 +7698,9 @@ lpfc_setup_driver_resource_phase1(struct lpfc_hba *phba) "NVME" : " "), (phba->nvmet_support ? "NVMET" : " ")); + /* ras_fwlog state */ + spin_lock_init(&phba->ras_fwlog_lock); + /* Initialize the IO buffer list used by driver for SLI3 SCSI */ spin_lock_init(&phba->scsi_buf_list_get_lock); INIT_LIST_HEAD(&phba->lpfc_scsi_buf_list_get); @@ -13047,7 +13050,7 @@ lpfc_sli4_enable_msix(struct lpfc_hba *phba) rc = request_threaded_irq(eqhdl->irq, &lpfc_sli4_hba_intr_handler, &lpfc_sli4_hba_intr_handler_th, - IRQF_ONESHOT, name, eqhdl); + 0, name, eqhdl); if (rc) { lpfc_printf_log(phba, KERN_WARNING, LOG_INIT, "0486 MSI-X fast-path (%d) " diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index d9074929fbab8..b147304b01fa1 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -748,8 +748,10 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, /* Save the ELS cmd */ elsiocb->drvrTimeout = cmd; - lpfc_sli4_resume_rpi(ndlp, - lpfc_mbx_cmpl_resume_rpi, elsiocb); + if (lpfc_sli4_resume_rpi(ndlp, + lpfc_mbx_cmpl_resume_rpi, + elsiocb)) + kfree(elsiocb); goto out; } } diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 128fc1bab5865..47218cf4d110d 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -2616,9 +2616,9 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) /* No concern about the role change on the nvme remoteport. * The transport will update it. */ - spin_lock_irq(&vport->phba->hbalock); + spin_lock_irq(&ndlp->lock); ndlp->fc4_xpt_flags |= NVME_XPT_UNREG_WAIT; - spin_unlock_irq(&vport->phba->hbalock); + spin_unlock_irq(&ndlp->lock); /* Don't let the host nvme transport keep sending keep-alives * on this remoteport. Vport is unloading, no recovery. The diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index 425328d9c2d80..d41fea53e41e9 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1586,7 +1586,7 @@ lpfc_nvmet_setup_io_context(struct lpfc_hba *phba) wqe = &nvmewqe->wqe; /* Initialize WQE */ - memset(wqe, 0, sizeof(union lpfc_wqe)); + memset(wqe, 0, sizeof(*wqe)); ctx_buf->iocbq->cmd_dmabuf = NULL; spin_lock(&phba->sli4_hba.sgl_list_lock); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index bf879d81846b6..cf506556f3b0b 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -167,11 +167,10 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba) struct Scsi_Host *shost; struct scsi_device *sdev; unsigned long new_queue_depth; - unsigned long num_rsrc_err, num_cmd_success; + unsigned long num_rsrc_err; int i; num_rsrc_err = atomic_read(&phba->num_rsrc_err); - num_cmd_success = atomic_read(&phba->num_cmd_success); /* * The error and success command counters are global per @@ -186,20 +185,16 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba) for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) { shost = lpfc_shost_from_vport(vports[i]); shost_for_each_device(sdev, shost) { - new_queue_depth = - sdev->queue_depth * num_rsrc_err / - (num_rsrc_err + num_cmd_success); - if (!new_queue_depth) - new_queue_depth = sdev->queue_depth - 1; + if (num_rsrc_err >= sdev->queue_depth) + new_queue_depth = 1; else new_queue_depth = sdev->queue_depth - - new_queue_depth; + num_rsrc_err; scsi_change_queue_depth(sdev, new_queue_depth); } } lpfc_destroy_vport_work_array(phba, vports); atomic_set(&phba->num_rsrc_err, 0); - atomic_set(&phba->num_cmd_success, 0); } /** diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 706985358c6a0..e1821072552a5 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -1217,9 +1217,9 @@ lpfc_set_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp, empty = list_empty(&phba->active_rrq_list); list_add_tail(&rrq->list, &phba->active_rrq_list); phba->hba_flag |= HBA_RRQ_ACTIVE; + spin_unlock_irqrestore(&phba->hbalock, iflags); if (empty) lpfc_worker_wake_up(phba); - spin_unlock_irqrestore(&phba->hbalock, iflags); return 0; out: spin_unlock_irqrestore(&phba->hbalock, iflags); @@ -6849,9 +6849,9 @@ lpfc_ras_stop_fwlog(struct lpfc_hba *phba) { struct lpfc_ras_fwlog *ras_fwlog = &phba->ras_fwlog; - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); ras_fwlog->state = INACTIVE; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); /* Disable FW logging to host memory */ writel(LPFC_CTL_PDEV_CTL_DDL_RAS, @@ -6894,9 +6894,9 @@ lpfc_sli4_ras_dma_free(struct lpfc_hba *phba) ras_fwlog->lwpd.virt = NULL; } - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); ras_fwlog->state = INACTIVE; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); } /** @@ -6998,9 +6998,9 @@ lpfc_sli4_ras_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) goto disable_ras; } - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); ras_fwlog->state = ACTIVE; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); mempool_free(pmb, phba->mbox_mem_pool); return; @@ -7032,9 +7032,9 @@ lpfc_sli4_ras_fwlog_init(struct lpfc_hba *phba, uint32_t len = 0, fwlog_buffsize, fwlog_entry_count; int rc = 0; - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); ras_fwlog->state = INACTIVE; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); fwlog_buffsize = (LPFC_RAS_MIN_BUFF_POST_SIZE * phba->cfg_ras_fwlog_buffsize); @@ -7095,9 +7095,9 @@ lpfc_sli4_ras_fwlog_init(struct lpfc_hba *phba, mbx_fwlog->u.request.lwpd.addr_lo = putPaddrLow(ras_fwlog->lwpd.phys); mbx_fwlog->u.request.lwpd.addr_hi = putPaddrHigh(ras_fwlog->lwpd.phys); - spin_lock_irq(&phba->hbalock); + spin_lock_irq(&phba->ras_fwlog_lock); ras_fwlog->state = REG_INPROGRESS; - spin_unlock_irq(&phba->hbalock); + spin_unlock_irq(&phba->ras_fwlog_lock); mbox->vport = phba->pport; mbox->mbox_cmpl = lpfc_sli4_ras_mbox_cmpl; @@ -11373,18 +11373,18 @@ lpfc_sli_post_recovery_event(struct lpfc_hba *phba, unsigned long iflags; struct lpfc_work_evt *evtp = &ndlp->recovery_evt; + /* Hold a node reference for outstanding queued work */ + if (!lpfc_nlp_get(ndlp)) + return; + spin_lock_irqsave(&phba->hbalock, iflags); if (!list_empty(&evtp->evt_listp)) { spin_unlock_irqrestore(&phba->hbalock, iflags); + lpfc_nlp_put(ndlp); return; } - /* Incrementing the reference count until the queued work is done. */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); - if (!evtp->evt_arg1) { - spin_unlock_irqrestore(&phba->hbalock, iflags); - return; - } + evtp->evt_arg1 = ndlp; evtp->evt = LPFC_EVT_RECOVER_PORT; list_add_tail(&evtp->evt_listp, &phba->work_list); spin_unlock_irqrestore(&phba->hbalock, iflags); diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c index 6c7559cf1a4b6..9e0e9e02d2c47 100644 --- a/drivers/scsi/lpfc/lpfc_vport.c +++ b/drivers/scsi/lpfc/lpfc_vport.c @@ -683,10 +683,6 @@ lpfc_vport_delete(struct fc_vport *fc_vport) lpfc_free_sysfs_attr(vport); lpfc_debugfs_terminate(vport); - /* Remove FC host to break driver binding. */ - fc_remove_host(shost); - scsi_remove_host(shost); - /* Send the DA_ID and Fabric LOGO to cleanup Nameserver entries. */ ndlp = lpfc_findnode_did(vport, Fabric_DID); if (!ndlp) @@ -730,6 +726,10 @@ lpfc_vport_delete(struct fc_vport *fc_vport) skip_logo: + /* Remove FC host to break driver binding. */ + fc_remove_host(shost); + scsi_remove_host(shost); + lpfc_cleanup(vport); /* Remove scsi host now. The nodes are cleaned up. */ diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 0380996b5ad27..6a3db7032c695 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -1644,7 +1644,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) if ((mpirep_offset != 0xFF) && drv_bufs[mpirep_offset].bsg_buf_len) { drv_buf_iter = &drv_bufs[mpirep_offset]; - drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) - 1 + + drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) + mrioc->reply_sz); bsg_reply_buf = kzalloc(drv_buf_iter->kern_buf_len, GFP_KERNEL); @@ -2158,10 +2158,72 @@ persistent_id_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(persistent_id); +/** + * sas_ncq_prio_supported_show - Indicate if device supports NCQ priority + * @dev: pointer to embedded device + * @attr: sas_ncq_prio_supported attribute descriptor + * @buf: the buffer returned + * + * A sysfs 'read-only' sdev attribute, only works with SATA devices + */ +static ssize_t +sas_ncq_prio_supported_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev = to_scsi_device(dev); + + return sysfs_emit(buf, "%d\n", sas_ata_ncq_prio_supported(sdev)); +} +static DEVICE_ATTR_RO(sas_ncq_prio_supported); + +/** + * sas_ncq_prio_enable_show - send prioritized io commands to device + * @dev: pointer to embedded device + * @attr: sas_ncq_prio_enable attribute descriptor + * @buf: the buffer returned + * + * A sysfs 'read/write' sdev attribute, only works with SATA devices + */ +static ssize_t +sas_ncq_prio_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev = to_scsi_device(dev); + struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata; + + if (!sdev_priv_data) + return 0; + + return sysfs_emit(buf, "%d\n", sdev_priv_data->ncq_prio_enable); +} + +static ssize_t +sas_ncq_prio_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_device *sdev = to_scsi_device(dev); + struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata; + bool ncq_prio_enable = 0; + + if (kstrtobool(buf, &ncq_prio_enable)) + return -EINVAL; + + if (!sas_ata_ncq_prio_supported(sdev)) + return -EINVAL; + + sdev_priv_data->ncq_prio_enable = ncq_prio_enable; + + return strlen(buf); +} +static DEVICE_ATTR_RW(sas_ncq_prio_enable); + static struct attribute *mpi3mr_dev_attrs[] = { &dev_attr_sas_address.attr, &dev_attr_device_handle.attr, &dev_attr_persistent_id.attr, + &dev_attr_sas_ncq_prio_supported.attr, + &dev_attr_sas_ncq_prio_enable.attr, NULL, }; diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index d32ad46318cb0..7ca9a7c2709cf 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -1355,11 +1355,21 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, mpi3mr_sas_port_sanity_check(mrioc, mr_sas_node, mr_sas_port->remote_identify.sas_address, hba_port); + if (mr_sas_node->num_phys > sizeof(mr_sas_port->phy_mask) * 8) + ioc_info(mrioc, "max port count %u could be too high\n", + mr_sas_node->num_phys); + for (i = 0; i < mr_sas_node->num_phys; i++) { if ((mr_sas_node->phy[i].remote_identify.sas_address != mr_sas_port->remote_identify.sas_address) || (mr_sas_node->phy[i].hba_port != hba_port)) continue; + + if (i > sizeof(mr_sas_port->phy_mask) * 8) { + ioc_warn(mrioc, "skipping port %u, max allowed value is %lu\n", + i, sizeof(mr_sas_port->phy_mask) * 8); + goto out_fail; + } list_add_tail(&mr_sas_node->phy[i].port_siblings, &mr_sas_port->phy_list); mr_sas_port->num_phys++; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index b8120ca93c797..520ddaea2e233 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -8477,6 +8477,12 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pd_handles_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pd_handles_sz++; + /* + * pd_handles_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may occur. + */ + ioc->pd_handles_sz = ALIGN(ioc->pd_handles_sz, sizeof(unsigned long)); + ioc->pd_handles = kzalloc(ioc->pd_handles_sz, GFP_KERNEL); if (!ioc->pd_handles) { @@ -8494,6 +8500,13 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pend_os_device_add_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pend_os_device_add_sz++; + + /* + * pend_os_device_add_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory may occur. + */ + ioc->pend_os_device_add_sz = ALIGN(ioc->pend_os_device_add_sz, + sizeof(unsigned long)); ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz, GFP_KERNEL); if (!ioc->pend_os_device_add) { @@ -8785,6 +8798,12 @@ _base_check_ioc_facts_changes(struct MPT3SAS_ADAPTER *ioc) if (ioc->facts.MaxDevHandle % 8) pd_handles_sz++; + /* + * pd_handles should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may + * occur. + */ + pd_handles_sz = ALIGN(pd_handles_sz, sizeof(unsigned long)); pd_handles = krealloc(ioc->pd_handles, pd_handles_sz, GFP_KERNEL); if (!pd_handles) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 6d0bc8c667002..592c54e37493a 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -2044,9 +2044,6 @@ void mpt3sas_setup_direct_io(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd, struct _raid_device *raid_device, Mpi25SCSIIORequest_t *mpi_request); -/* NCQ Prio Handling Check */ -bool scsih_ncq_prio_supp(struct scsi_device *sdev); - void mpt3sas_setup_debugfs(struct MPT3SAS_ADAPTER *ioc); void mpt3sas_destroy_debugfs(struct MPT3SAS_ADAPTER *ioc); void mpt3sas_init_debugfs(void); diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 147cb7088d55f..63b06d3842a41 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -4034,7 +4034,7 @@ sas_ncq_prio_supported_show(struct device *dev, { struct scsi_device *sdev = to_scsi_device(dev); - return sysfs_emit(buf, "%d\n", scsih_ncq_prio_supp(sdev)); + return sysfs_emit(buf, "%d\n", sas_ata_ncq_prio_supported(sdev)); } static DEVICE_ATTR_RO(sas_ncq_prio_supported); @@ -4069,7 +4069,7 @@ sas_ncq_prio_enable_store(struct device *dev, if (kstrtobool(buf, &ncq_prio_enable)) return -EINVAL; - if (!scsih_ncq_prio_supp(sdev)) + if (!sas_ata_ncq_prio_supported(sdev)) return -EINVAL; sas_device_priv_data->ncq_prio_enable = ncq_prio_enable; diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 51b5788da040a..9e92f341dee6f 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -12572,29 +12572,6 @@ scsih_pci_mmio_enabled(struct pci_dev *pdev) return PCI_ERS_RESULT_RECOVERED; } -/** - * scsih_ncq_prio_supp - Check for NCQ command priority support - * @sdev: scsi device struct - * - * This is called when a user indicates they would like to enable - * ncq command priorities. This works only on SATA devices. - */ -bool scsih_ncq_prio_supp(struct scsi_device *sdev) -{ - struct scsi_vpd *vpd; - bool ncq_prio_supp = false; - - rcu_read_lock(); - vpd = rcu_dereference(sdev->vpd_pg89); - if (!vpd || vpd->len < 214) - goto out; - - ncq_prio_supp = (vpd->data[213] >> 4) & 1; -out: - rcu_read_unlock(); - - return ncq_prio_supp; -} /* * The pci device ids are defined in mpi/mpi2_cnfg.h. */ diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index ca2e932dd9b70..f684eb5e04898 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -1775,9 +1775,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrb_devstate_name(ldev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); } else { struct myrb_pdev_state *pdev_info = sdev->hostdata; @@ -1796,9 +1796,9 @@ static ssize_t raid_state_show(struct device *dev, else name = myrb_devstate_name(pdev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->state); } return ret; @@ -1886,11 +1886,11 @@ static ssize_t raid_level_show(struct device *dev, name = myrb_raidlevel_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } - return snprintf(buf, 32, "Physical Drive\n"); + return snprintf(buf, 64, "Physical Drive\n"); } static DEVICE_ATTR_RO(raid_level); @@ -1903,15 +1903,15 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < myrb_logical_channel(sdev->host)) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); status = myrb_get_rbld_progress(cb, &rbld_buf); if (rbld_buf.ldev_num != sdev->id || status != MYRB_STATUS_SUCCESS) - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); - return snprintf(buf, 32, "rebuilding block %u of %u\n", + return snprintf(buf, 64, "rebuilding block %u of %u\n", rbld_buf.ldev_size - rbld_buf.blocks_left, rbld_buf.ldev_size); } diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index a1eec65a9713f..e824be9d9bbb9 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -947,9 +947,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrs_devstate_name(ldev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else { struct myrs_pdev_info *pdev_info; @@ -958,9 +958,9 @@ static ssize_t raid_state_show(struct device *dev, pdev_info = sdev->hostdata; name = myrs_devstate_name(pdev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->dev_state); } return ret; @@ -1066,13 +1066,13 @@ static ssize_t raid_level_show(struct device *dev, ldev_info = sdev->hostdata; name = myrs_raid_level_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else name = myrs_raid_level_name(MYRS_RAID_PHYSICAL); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } static DEVICE_ATTR_RO(raid_level); @@ -1086,7 +1086,7 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); ldev_info = sdev->hostdata; ldev_num = ldev_info->ldev_num; @@ -1098,11 +1098,11 @@ static ssize_t rebuild_show(struct device *dev, return -EIO; } if (ldev_info->rbld_active) { - return snprintf(buf, 32, "rebuilding block %zu of %zu\n", + return snprintf(buf, 64, "rebuilding block %zu of %zu\n", (size_t)ldev_info->rbld_lba, (size_t)ldev_info->cfg_devsize); } else - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); } static ssize_t rebuild_store(struct device *dev, @@ -1190,7 +1190,7 @@ static ssize_t consistency_check_show(struct device *dev, unsigned short ldev_num; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not checking\n"); + return snprintf(buf, 64, "physical device - not checking\n"); ldev_info = sdev->hostdata; if (!ldev_info) @@ -1198,11 +1198,11 @@ static ssize_t consistency_check_show(struct device *dev, ldev_num = ldev_info->ldev_num; myrs_get_ldev_info(cs, ldev_num, ldev_info); if (ldev_info->cc_active) - return snprintf(buf, 32, "checking block %zu of %zu\n", + return snprintf(buf, 64, "checking block %zu of %zu\n", (size_t)ldev_info->cc_lba, (size_t)ldev_info->cfg_devsize); else - return snprintf(buf, 32, "not checking\n"); + return snprintf(buf, 64, "not checking\n"); } static ssize_t consistency_check_store(struct device *dev, diff --git a/drivers/scsi/qedf/qedf_debugfs.c b/drivers/scsi/qedf/qedf_debugfs.c index 451fd236bfd05..96174353e3898 100644 --- a/drivers/scsi/qedf/qedf_debugfs.c +++ b/drivers/scsi/qedf/qedf_debugfs.c @@ -170,7 +170,7 @@ qedf_dbg_debug_cmd_write(struct file *filp, const char __user *buffer, if (!count || *ppos) return 0; - kern_buf = memdup_user(buffer, count); + kern_buf = memdup_user_nul(buffer, count); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); diff --git a/drivers/scsi/qedi/qedi_debugfs.c b/drivers/scsi/qedi/qedi_debugfs.c index 8deb2001dc2ff..37eed6a278164 100644 --- a/drivers/scsi/qedi/qedi_debugfs.c +++ b/drivers/scsi/qedi/qedi_debugfs.c @@ -120,15 +120,11 @@ static ssize_t qedi_dbg_do_not_recover_cmd_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { - size_t cnt = 0; - - if (*ppos) - return 0; + char buf[64]; + int len; - cnt = sprintf(buffer, "do_not_recover=%d\n", qedi_do_not_recover); - cnt = min_t(int, count, cnt - *ppos); - *ppos += cnt; - return cnt; + len = sprintf(buf, "do_not_recover=%d\n", qedi_do_not_recover); + return simple_read_from_buffer(buffer, count, ppos, buf, len); } static int diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 44449c70a375f..76eeba435fd04 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2741,7 +2741,13 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rport *rport) return; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { - qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + /* Will wait for wind down of adapter */ + ql_dbg(ql_dbg_aer, fcport->vha, 0x900c, + "%s pci offline detected (id %06x)\n", __func__, + fcport->d_id.b24); + qla_pci_set_eeh_busy(fcport->vha); + qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, + 0, WAIT_TARGET); return; } } @@ -2763,7 +2769,11 @@ qla2x00_terminate_rport_io(struct fc_rport *rport) vha = fcport->vha; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { - qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + /* Will wait for wind down of adapter */ + ql_dbg(ql_dbg_aer, fcport->vha, 0x900b, + "%s pci offline detected (id %06x)\n", __func__, + fcport->d_id.b24); + qla_pci_set_eeh_busy(vha); qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, 0, WAIT_TARGET); return; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index deb642607deb6..2f49baf131e26 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -82,7 +82,7 @@ typedef union { #include "qla_nvme.h" #define QLA2XXX_DRIVER_NAME "qla2xxx" #define QLA2XXX_APIDEV "ql2xapidev" -#define QLA2XXX_MANUFACTURER "Marvell Semiconductor, Inc." +#define QLA2XXX_MANUFACTURER "Marvell" /* * We have MAILBOX_REGISTER_COUNT sized arrays in a few places, diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c index 55ff3d7482b3e..a1545dad0c0ce 100644 --- a/drivers/scsi/qla2xxx/qla_dfs.c +++ b/drivers/scsi/qla2xxx/qla_dfs.c @@ -274,7 +274,7 @@ qla_dfs_fw_resource_cnt_show(struct seq_file *s, void *unused) seq_printf(s, "Driver: estimate iocb used [%d] high water limit [%d]\n", iocbs_used, ha->base_qpair->fwres.iocbs_limit); - seq_printf(s, "estimate exchange used[%d] high water limit [%d] n", + seq_printf(s, "estimate exchange used[%d] high water limit [%d]\n", exch_used, ha->base_qpair->fwres.exch_limit); if (ql2xenforce_iocb_limit == 2) { diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index 26e6b3e3af431..dcde55c8ee5de 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -1100,7 +1100,7 @@ qla_edif_app_getstats(scsi_qla_host_t *vha, struct bsg_job *bsg_job) list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { if (fcport->edif.enable) { - if (pcnt > app_req.num_ports) + if (pcnt >= app_req.num_ports) break; app_reply->elem[pcnt].rekey_count = diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index 09cb9413670a5..7309310d2ab94 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -44,7 +44,7 @@ extern int qla2x00_fabric_login(scsi_qla_host_t *, fc_port_t *, uint16_t *); extern int qla2x00_local_device_login(scsi_qla_host_t *, fc_port_t *); extern int qla24xx_els_dcmd_iocb(scsi_qla_host_t *, int, port_id_t); -extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *, bool); +extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *); extern void qla2x00_els_dcmd2_free(scsi_qla_host_t *vha, struct els_plogi *els_plogi); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index a314cfc5b263f..8377624d76c98 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1193,8 +1193,12 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) return rval; done_free_sp: - /* ref: INIT */ - kref_put(&sp->cmd_kref, qla2x00_sp_release); + /* + * use qla24xx_async_gnl_sp_done to purge all pending gnl request. + * kref_put is call behind the scene. + */ + sp->u.iocb_cmd.u.mbx.in_mb[0] = MBS_COMMAND_ERROR; + qla24xx_async_gnl_sp_done(sp, QLA_COMMAND_ERROR); fcport->flags &= ~(FCF_ASYNC_SENT); done: fcport->flags &= ~(FCF_ASYNC_ACTIVE); @@ -2665,6 +2669,40 @@ qla83xx_nic_core_fw_load(scsi_qla_host_t *vha) return rval; } +static void qla_enable_fce_trace(scsi_qla_host_t *vha) +{ + int rval; + struct qla_hw_data *ha = vha->hw; + + if (ha->fce) { + ha->flags.fce_enabled = 1; + memset(ha->fce, 0, fce_calc_size(ha->fce_bufs)); + rval = qla2x00_enable_fce_trace(vha, + ha->fce_dma, ha->fce_bufs, ha->fce_mb, &ha->fce_bufs); + + if (rval) { + ql_log(ql_log_warn, vha, 0x8033, + "Unable to reinitialize FCE (%d).\n", rval); + ha->flags.fce_enabled = 0; + } + } +} + +static void qla_enable_eft_trace(scsi_qla_host_t *vha) +{ + int rval; + struct qla_hw_data *ha = vha->hw; + + if (ha->eft) { + memset(ha->eft, 0, EFT_SIZE); + rval = qla2x00_enable_eft_trace(vha, ha->eft_dma, EFT_NUM_BUFFERS); + + if (rval) { + ql_log(ql_log_warn, vha, 0x8034, + "Unable to reinitialize EFT (%d).\n", rval); + } + } +} /* * qla2x00_initialize_adapter * Initialize board. @@ -3668,9 +3706,8 @@ qla24xx_chip_diag(scsi_qla_host_t *vha) } static void -qla2x00_init_fce_trace(scsi_qla_host_t *vha) +qla2x00_alloc_fce_trace(scsi_qla_host_t *vha) { - int rval; dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; @@ -3699,27 +3736,17 @@ qla2x00_init_fce_trace(scsi_qla_host_t *vha) return; } - rval = qla2x00_enable_fce_trace(vha, tc_dma, FCE_NUM_BUFFERS, - ha->fce_mb, &ha->fce_bufs); - if (rval) { - ql_log(ql_log_warn, vha, 0x00bf, - "Unable to initialize FCE (%d).\n", rval); - dma_free_coherent(&ha->pdev->dev, FCE_SIZE, tc, tc_dma); - return; - } - ql_dbg(ql_dbg_init, vha, 0x00c0, "Allocated (%d KB) for FCE...\n", FCE_SIZE / 1024); - ha->flags.fce_enabled = 1; ha->fce_dma = tc_dma; ha->fce = tc; + ha->fce_bufs = FCE_NUM_BUFFERS; } static void -qla2x00_init_eft_trace(scsi_qla_host_t *vha) +qla2x00_alloc_eft_trace(scsi_qla_host_t *vha) { - int rval; dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; @@ -3744,14 +3771,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) return; } - rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS); - if (rval) { - ql_log(ql_log_warn, vha, 0x00c2, - "Unable to initialize EFT (%d).\n", rval); - dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc, tc_dma); - return; - } - ql_dbg(ql_dbg_init, vha, 0x00c3, "Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024); @@ -3759,13 +3778,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) ha->eft = tc; } -static void -qla2x00_alloc_offload_mem(scsi_qla_host_t *vha) -{ - qla2x00_init_fce_trace(vha); - qla2x00_init_eft_trace(vha); -} - void qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) { @@ -3820,10 +3832,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) if (ha->tgt.atio_ring) mq_size += ha->tgt.atio_q_length * sizeof(request_t); - qla2x00_init_fce_trace(vha); + qla2x00_alloc_fce_trace(vha); if (ha->fce) fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE; - qla2x00_init_eft_trace(vha); + qla2x00_alloc_eft_trace(vha); if (ha->eft) eft_size = EFT_SIZE; } @@ -4253,7 +4265,6 @@ qla2x00_setup_chip(scsi_qla_host_t *vha) struct qla_hw_data *ha = vha->hw; struct device_reg_2xxx __iomem *reg = &ha->iobase->isp; unsigned long flags; - uint16_t fw_major_version; int done_once = 0; if (IS_P3P_TYPE(ha)) { @@ -4320,7 +4331,6 @@ qla2x00_setup_chip(scsi_qla_host_t *vha) goto failed; enable_82xx_npiv: - fw_major_version = ha->fw_major_version; if (IS_P3P_TYPE(ha)) qla82xx_check_md_needed(vha); else @@ -4349,12 +4359,11 @@ qla2x00_setup_chip(scsi_qla_host_t *vha) if (rval != QLA_SUCCESS) goto failed; - if (!fw_major_version && !(IS_P3P_TYPE(ha))) - qla2x00_alloc_offload_mem(vha); - if (ql2xallocfwdump && !(IS_P3P_TYPE(ha))) qla2x00_alloc_fw_dump(vha); + qla_enable_fce_trace(vha); + qla_enable_eft_trace(vha); } else { goto failed; } @@ -7487,12 +7496,12 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha) int qla2x00_abort_isp(scsi_qla_host_t *vha) { - int rval; uint8_t status = 0; struct qla_hw_data *ha = vha->hw; struct scsi_qla_host *vp, *tvp; struct req_que *req = ha->req_q_map[0]; unsigned long flags; + fc_port_t *fcport; if (vha->flags.online) { qla2x00_abort_isp_cleanup(vha); @@ -7561,6 +7570,15 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) "ISP Abort - ISP reg disconnect post nvmram config, exiting.\n"); return status; } + + /* User may have updated [fcp|nvme] prefer in flash */ + list_for_each_entry(fcport, &vha->vp_fcports, list) { + if (NVME_PRIORITY(ha, fcport)) + fcport->do_prli_nvme = 1; + else + fcport->do_prli_nvme = 0; + } + if (!qla2x00_restart_isp(vha)) { clear_bit(RESET_MARKER_NEEDED, &vha->dpc_flags); @@ -7581,31 +7599,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) if (IS_QLA81XX(ha) || IS_QLA8031(ha)) qla2x00_get_fw_version(vha); - if (ha->fce) { - ha->flags.fce_enabled = 1; - memset(ha->fce, 0, - fce_calc_size(ha->fce_bufs)); - rval = qla2x00_enable_fce_trace(vha, - ha->fce_dma, ha->fce_bufs, ha->fce_mb, - &ha->fce_bufs); - if (rval) { - ql_log(ql_log_warn, vha, 0x8033, - "Unable to reinitialize FCE " - "(%d).\n", rval); - ha->flags.fce_enabled = 0; - } - } - if (ha->eft) { - memset(ha->eft, 0, EFT_SIZE); - rval = qla2x00_enable_eft_trace(vha, - ha->eft_dma, EFT_NUM_BUFFERS); - if (rval) { - ql_log(ql_log_warn, vha, 0x8034, - "Unable to reinitialize EFT " - "(%d).\n", rval); - } - } } else { /* failed the ISP abort */ vha->flags.online = 1; if (test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) { @@ -7655,6 +7649,14 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) atomic_inc(&vp->vref_count); spin_unlock_irqrestore(&ha->vport_slock, flags); + /* User may have updated [fcp|nvme] prefer in flash */ + list_for_each_entry(fcport, &vp->vp_fcports, list) { + if (NVME_PRIORITY(ha, fcport)) + fcport->do_prli_nvme = 1; + else + fcport->do_prli_nvme = 0; + } + qla2x00_vp_abort_isp(vp); spin_lock_irqsave(&ha->vport_slock, flags); diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index df90169f82440..0b41e8a066026 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2587,6 +2587,33 @@ void qla2x00_sp_release(struct kref *kref) { struct srb *sp = container_of(kref, struct srb, cmd_kref); + struct scsi_qla_host *vha = sp->vha; + + switch (sp->type) { + case SRB_CT_PTHRU_CMD: + /* GPSC & GFPNID use fcport->ct_desc.ct_sns for both req & rsp */ + if (sp->u.iocb_cmd.u.ctarg.req && + (!sp->fcport || + sp->u.iocb_cmd.u.ctarg.req != sp->fcport->ct_desc.ct_sns)) { + dma_free_coherent(&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.req_allocated_size, + sp->u.iocb_cmd.u.ctarg.req, + sp->u.iocb_cmd.u.ctarg.req_dma); + sp->u.iocb_cmd.u.ctarg.req = NULL; + } + if (sp->u.iocb_cmd.u.ctarg.rsp && + (!sp->fcport || + sp->u.iocb_cmd.u.ctarg.rsp != sp->fcport->ct_desc.ct_sns)) { + dma_free_coherent(&vha->hw->pdev->dev, + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size, + sp->u.iocb_cmd.u.ctarg.rsp, + sp->u.iocb_cmd.u.ctarg.rsp_dma); + sp->u.iocb_cmd.u.ctarg.rsp = NULL; + } + break; + default: + break; + } sp->free(sp); } @@ -2610,7 +2637,8 @@ static void qla2x00_els_dcmd_sp_free(srb_t *sp) { struct srb_iocb *elsio = &sp->u.iocb_cmd; - kfree(sp->fcport); + if (sp->fcport) + qla2x00_free_fcport(sp->fcport); if (elsio->u.els_logo.els_logo_pyld) dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE, @@ -2692,7 +2720,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, */ sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); if (!sp) { - kfree(fcport); + qla2x00_free_fcport(fcport); ql_log(ql_log_info, vha, 0x70e6, "SRB allocation failed\n"); return -ENOMEM; @@ -2723,6 +2751,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_logo.els_logo_pyld) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } @@ -2747,6 +2776,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode, if (rval != QLA_SUCCESS) { /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); + qla2x00_free_fcport(fcport); return QLA_FUNCTION_FAILED; } @@ -3012,7 +3042,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res) int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, - fc_port_t *fcport, bool wait) + fc_port_t *fcport) { srb_t *sp; struct srb_iocb *elsio = NULL; @@ -3027,8 +3057,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!sp) { ql_log(ql_log_info, vha, 0x70e6, "SRB allocation failed\n"); - fcport->flags &= ~FCF_ASYNC_ACTIVE; - return -ENOMEM; + goto done; } fcport->flags |= FCF_ASYNC_SENT; @@ -3037,9 +3066,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, ql_dbg(ql_dbg_io, vha, 0x3073, "%s Enter: PLOGI portid=%06x\n", __func__, fcport->d_id.b24); - if (wait) - sp->flags = SRB_WAKEUP_ON_COMP; - sp->type = SRB_ELS_DCMD; sp->name = "ELS_DCMD"; sp->fcport = fcport; @@ -3055,7 +3081,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_plogi.els_plogi_pyld) { rval = QLA_FUNCTION_FAILED; - goto out; + goto done_free_sp; } resp_ptr = elsio->u.els_plogi.els_resp_pyld = @@ -3064,7 +3090,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (!elsio->u.els_plogi.els_resp_pyld) { rval = QLA_FUNCTION_FAILED; - goto out; + goto done_free_sp; } ql_dbg(ql_dbg_io, vha, 0x3073, "PLOGI %p %p\n", ptr, resp_ptr); @@ -3080,7 +3106,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, if (els_opcode == ELS_DCMD_PLOGI && DBELL_ACTIVE(vha)) { struct fc_els_flogi *p = ptr; - p->fl_csp.sp_features |= cpu_to_be16(FC_SP_FT_SEC); } @@ -3089,10 +3114,11 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, sizeof(*elsio->u.els_plogi.els_plogi_pyld)); - init_completion(&elsio->u.els_plogi.comp); rval = qla2x00_start_sp(sp); if (rval != QLA_SUCCESS) { - rval = QLA_FUNCTION_FAILED; + fcport->flags |= FCF_LOGIN_NEEDED; + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + goto done_free_sp; } else { ql_dbg(ql_dbg_disc, vha, 0x3074, "%s PLOGI sent, hdl=%x, loopid=%x, to port_id %06x from port_id %06x\n", @@ -3100,21 +3126,15 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, fcport->d_id.b24, vha->d_id.b24); } - if (wait) { - wait_for_completion(&elsio->u.els_plogi.comp); - - if (elsio->u.els_plogi.comp_status != CS_COMPLETE) - rval = QLA_FUNCTION_FAILED; - } else { - goto done; - } + return rval; -out: - fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); +done_free_sp: qla2x00_els_dcmd2_free(vha, &elsio->u.els_plogi); /* ref: INIT */ kref_put(&sp->cmd_kref, qla2x00_sp_release); done: + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + qla2x00_set_fcport_disc_state(fcport, DSC_DELETED); return rval; } @@ -3918,7 +3938,7 @@ qla2x00_start_sp(srb_t *sp) return -EAGAIN; } - pkt = __qla2x00_alloc_iocbs(sp->qpair, sp); + pkt = qla2x00_alloc_iocbs_ready(sp->qpair, sp); if (!pkt) { rval = -EAGAIN; ql_log(ql_log_warn, vha, 0x700c, diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 21ec32b4fb280..0cd6f3e148824 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -194,7 +194,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) if (ha->flags.purge_mbox || chip_reset != ha->chip_reset || ha->flags.eeh_busy) { ql_log(ql_log_warn, vha, 0xd035, - "Error detected: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n", + "Purge mbox: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n", ha->flags.purge_mbox, ha->flags.eeh_busy, mcp->mb[0]); rval = QLA_ABORTED; goto premature_exit; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index dd674378f2f39..1e2f52210f605 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4602,6 +4602,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len, ha->init_cb_dma = 0; fail_free_vp_map: kfree(ha->vp_map); + ha->vp_map = NULL; fail: ql_log(ql_log_fatal, NULL, 0x0030, "Memory allocation failure.\n"); @@ -5583,7 +5584,7 @@ qla2x00_do_work(struct scsi_qla_host *vha) break; case QLA_EVT_ELS_PLOGI: qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI, - e->u.fcport.fcport, false); + e->u.fcport.fcport); break; case QLA_EVT_SA_REPLACE: rc = qla24xx_issue_sa_replace_iocb(vha, e); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 2ef2dbac0db27..d7551b1443e4a 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1062,6 +1062,16 @@ void qlt_free_session_done(struct work_struct *work) "%s: sess %p logout completed\n", __func__, sess); } + /* check for any straggling io left behind */ + if (!(sess->flags & FCF_FCP2_DEVICE) && + qla2x00_eh_wait_for_pending_commands(sess->vha, sess->d_id.b24, 0, WAIT_TARGET)) { + ql_log(ql_log_warn, vha, 0x3027, + "IO not return. Resetting.\n"); + set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + qla2x00_wait_for_chip_reset(vha); + } + if (sess->logo_ack_needed) { sess->logo_ack_needed = 0; qla24xx_async_notify_ack(vha, sess, diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 8cad9792a5627..191ea1e027973 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -350,6 +350,13 @@ static int scsi_get_vpd_size(struct scsi_device *sdev, u8 page) if (result < SCSI_VPD_HEADER_SIZE) return 0; + if (result > sizeof(vpd)) { + dev_warn_once(&sdev->sdev_gendev, + "%s: long VPD page 0 length: %d bytes\n", + __func__, result); + result = sizeof(vpd); + } + result -= SCSI_VPD_HEADER_SIZE; if (!memchr(&vpd[SCSI_VPD_HEADER_SIZE], page, result)) return 0; @@ -664,6 +671,13 @@ void scsi_cdl_check(struct scsi_device *sdev) sdev->use_10_for_rw = 0; sdev->cdl_supported = 1; + + /* + * If the device supports CDL, make sure that the current drive + * feature status is consistent with the user controlled + * cdl_enable state. + */ + scsi_cdl_enable(sdev, sdev->cdl_enable); } else { sdev->cdl_supported = 0; } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index df5ac03d5d6c2..189dfeb378202 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -543,10 +543,9 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (blk_queue_add_random(q)) add_disk_randomness(req->q->disk); - if (!blk_rq_is_passthrough(req)) { - WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED)); - cmd->flags &= ~SCMD_INITIALIZED; - } + WARN_ON_ONCE(!blk_rq_is_passthrough(req) && + !(cmd->flags & SCMD_INITIALIZED)); + cmd->flags = 0; /* * Calling rcu_barrier() is not necessary here because the diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 44680f65ea145..ca99be7341d9b 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1619,6 +1619,40 @@ int scsi_add_device(struct Scsi_Host *host, uint channel, } EXPORT_SYMBOL(scsi_add_device); +int scsi_resume_device(struct scsi_device *sdev) +{ + struct device *dev = &sdev->sdev_gendev; + int ret = 0; + + device_lock(dev); + + /* + * Bail out if the device or its queue are not running. Otherwise, + * the rescan may block waiting for commands to be executed, with us + * holding the device lock. This can result in a potential deadlock + * in the power management core code when system resume is on-going. + */ + if (sdev->sdev_state != SDEV_RUNNING || + blk_queue_pm_only(sdev->request_queue)) { + ret = -EWOULDBLOCK; + goto unlock; + } + + if (dev->driver && try_module_get(dev->driver->owner)) { + struct scsi_driver *drv = to_scsi_driver(dev->driver); + + if (drv->resume) + ret = drv->resume(dev); + module_put(dev->driver->owner); + } + +unlock: + device_unlock(dev); + + return ret; +} +EXPORT_SYMBOL(scsi_resume_device); + int scsi_rescan_device(struct scsi_device *sdev) { struct device *dev = &sdev->sdev_gendev; diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index d704c484a251c..7fdd2b61fe855 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -416,6 +416,29 @@ unsigned int sas_is_tlr_enabled(struct scsi_device *sdev) } EXPORT_SYMBOL_GPL(sas_is_tlr_enabled); +/** + * sas_ata_ncq_prio_supported - Check for ATA NCQ command priority support + * @sdev: SCSI device + * + * Check if an ATA device supports NCQ priority using VPD page 89h (ATA + * Information). Since this VPD page is implemented only for ATA devices, + * this function always returns false for SCSI devices. + */ +bool sas_ata_ncq_prio_supported(struct scsi_device *sdev) +{ + struct scsi_vpd *vpd; + bool ncq_prio_supported = false; + + rcu_read_lock(); + vpd = rcu_dereference(sdev->vpd_pg89); + if (vpd && vpd->len >= 214) + ncq_prio_supported = (vpd->data[213] >> 4) & 1; + rcu_read_unlock(); + + return ncq_prio_supported; +} +EXPORT_SYMBOL_GPL(sas_ata_ncq_prio_supported); + /* * SAS Phy attributes */ diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index bdd0acf7fa3cb..327d100a140ed 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3409,16 +3409,23 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, static void sd_read_block_zero(struct scsi_disk *sdkp) { - unsigned int buf_len = sdkp->device->sector_size; - char *buffer, cmd[10] = { }; + struct scsi_device *sdev = sdkp->device; + unsigned int buf_len = sdev->sector_size; + u8 *buffer, cmd[16] = { }; buffer = kmalloc(buf_len, GFP_KERNEL); if (!buffer) return; - cmd[0] = READ_10; - put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ - put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + if (sdev->use_16_for_rw) { + cmd[0] = READ_16; + put_unaligned_be64(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be32(1, &cmd[10]);/* Transfer 1 logical block */ + } else { + cmd[0] = READ_10; + put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + } scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len, SD_TIMEOUT, sdkp->max_retries, NULL); @@ -3542,8 +3549,10 @@ static int sd_revalidate_disk(struct gendisk *disk) */ if (sdkp->first_scan || q->limits.max_sectors > q->limits.max_dev_sectors || - q->limits.max_sectors > q->limits.max_hw_sectors) + q->limits.max_sectors > q->limits.max_hw_sectors) { q->limits.max_sectors = rw_max; + q->limits.max_user_sectors = rw_max; + } sdkp->first_scan = 0; @@ -3757,7 +3766,7 @@ static int sd_probe(struct device *dev) error = device_add_disk(dev, gd, NULL); if (error) { - put_device(&sdkp->disk_dev); + device_unregister(&sdkp->disk_dev); put_disk(gd); goto out; } @@ -3945,7 +3954,21 @@ static int sd_suspend_runtime(struct device *dev) return sd_suspend_common(dev, true); } -static int sd_resume(struct device *dev, bool runtime) +static int sd_resume(struct device *dev) +{ + struct scsi_disk *sdkp = dev_get_drvdata(dev); + + sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); + + if (opal_unlock_from_suspend(sdkp->opal_dev)) { + sd_printk(KERN_NOTICE, sdkp, "OPAL unlock failed\n"); + return -EIO; + } + + return 0; +} + +static int sd_resume_common(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret; @@ -3961,7 +3984,7 @@ static int sd_resume(struct device *dev, bool runtime) sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); ret = sd_start_stop_device(sdkp, 1); if (!ret) { - opal_unlock_from_suspend(sdkp->opal_dev); + sd_resume(dev); sdkp->suspended = false; } @@ -3980,7 +4003,7 @@ static int sd_resume_system(struct device *dev) return 0; } - return sd_resume(dev, false); + return sd_resume_common(dev, false); } static int sd_resume_runtime(struct device *dev) @@ -4007,7 +4030,7 @@ static int sd_resume_runtime(struct device *dev) "Failed to clear sense data\n"); } - return sd_resume(dev, true); + return sd_resume_common(dev, true); } static const struct dev_pm_ops sd_pm_ops = { @@ -4030,6 +4053,7 @@ static struct scsi_driver sd_template = { .pm = &sd_pm_ops, }, .rescan = sd_rescan, + .resume = sd_resume, .init_command = sd_init_command, .uninit_command = sd_uninit_command, .done = sd_done, diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 86210e4dd0d35..b2d02dacaebd9 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -285,6 +285,7 @@ sg_open(struct inode *inode, struct file *filp) int dev = iminor(inode); int flags = filp->f_flags; struct request_queue *q; + struct scsi_device *device; Sg_device *sdp; Sg_fd *sfp; int retval; @@ -301,11 +302,12 @@ sg_open(struct inode *inode, struct file *filp) /* This driver's module count bumped by fops_get in */ /* Prevent the device driver from vanishing while we sleep */ - retval = scsi_device_get(sdp->device); + device = sdp->device; + retval = scsi_device_get(device); if (retval) goto sg_put; - retval = scsi_autopm_get_device(sdp->device); + retval = scsi_autopm_get_device(device); if (retval) goto sdp_put; @@ -313,7 +315,7 @@ sg_open(struct inode *inode, struct file *filp) * check if O_NONBLOCK. Permits SCSI commands to be issued * during error recovery. Tread carefully. */ if (!((flags & O_NONBLOCK) || - scsi_block_when_processing_errors(sdp->device))) { + scsi_block_when_processing_errors(device))) { retval = -ENXIO; /* we are in error recovery for this device */ goto error_out; @@ -344,7 +346,7 @@ sg_open(struct inode *inode, struct file *filp) if (sdp->open_cnt < 1) { /* no existing opens */ sdp->sgdebug = 0; - q = sdp->device->request_queue; + q = device->request_queue; sdp->sg_tablesize = queue_max_segments(q); } sfp = sg_add_sfp(sdp); @@ -370,10 +372,11 @@ sg_open(struct inode *inode, struct file *filp) error_mutex_locked: mutex_unlock(&sdp->open_rel_lock); error_out: - scsi_autopm_put_device(sdp->device); + scsi_autopm_put_device(device); sdp_put: - scsi_device_put(sdp->device); - goto sg_put; + kref_put(&sdp->d_ref, sg_device_destroy); + scsi_device_put(device); + return retval; } /* Release resources associated with a successful sg_open() @@ -2207,6 +2210,7 @@ sg_remove_sfp_usercontext(struct work_struct *work) { struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work); struct sg_device *sdp = sfp->parentdp; + struct scsi_device *device = sdp->device; Sg_request *srp; unsigned long iflags; @@ -2232,8 +2236,8 @@ sg_remove_sfp_usercontext(struct work_struct *work) "sg_remove_sfp: sfp=0x%p\n", sfp)); kfree(sfp); - scsi_device_put(sdp->device); kref_put(&sdp->d_ref, sg_device_destroy); + scsi_device_put(device); module_put(THIS_MODULE); } diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index d43873bb5fe6d..01cbd46219810 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -436,8 +436,8 @@ static int slim_device_alloc_laddr(struct slim_device *sbdev, if (ret < 0) goto err; } else if (report_present) { - ret = ida_simple_get(&ctrl->laddr_ida, - 0, SLIM_LA_MANAGER - 1, GFP_KERNEL); + ret = ida_alloc_max(&ctrl->laddr_ida, + SLIM_LA_MANAGER - 1, GFP_KERNEL); if (ret < 0) goto err; diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c index 77aa6d26476cd..0da5d9d1af037 100644 --- a/drivers/slimbus/qcom-ngd-ctrl.c +++ b/drivers/slimbus/qcom-ngd-ctrl.c @@ -1451,7 +1451,11 @@ static void qcom_slim_ngd_up_worker(struct work_struct *work) ctrl = container_of(work, struct qcom_slim_ngd_ctrl, ngd_up_work); /* Make sure qmi service is up before continuing */ - wait_for_completion_interruptible(&ctrl->qmi_up); + if (!wait_for_completion_interruptible_timeout(&ctrl->qmi_up, + msecs_to_jiffies(MSEC_PER_SEC))) { + dev_err(ctrl->dev, "QMI wait timeout\n"); + return; + } mutex_lock(&ctrl->ssr_lock); qcom_slim_ngd_enable(ctrl, true); diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index 1d2b27e3ea63f..b811446e0fa55 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -523,7 +523,7 @@ int dpaa2_io_service_enqueue_multiple_desc_fq(struct dpaa2_io *d, struct qbman_eq_desc *ed; int i, ret; - ed = kcalloc(sizeof(struct qbman_eq_desc), 32, GFP_KERNEL); + ed = kcalloc(32, sizeof(struct qbman_eq_desc), GFP_KERNEL); if (!ed) return -ENOMEM; diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 739e4eee6b75c..7e9074519ad22 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -991,7 +991,7 @@ struct qman_portal { /* linked-list of CSCN handlers. */ struct list_head cgr_cbs; /* list lock */ - spinlock_t cgr_lock; + raw_spinlock_t cgr_lock; struct work_struct congestion_work; struct work_struct mr_work; char irqname[MAX_IRQNAME]; @@ -1281,7 +1281,7 @@ static int qman_create_portal(struct qman_portal *portal, /* if the given mask is NULL, assume all CGRs can be seen */ qman_cgrs_fill(&portal->cgrs[0]); INIT_LIST_HEAD(&portal->cgr_cbs); - spin_lock_init(&portal->cgr_lock); + raw_spin_lock_init(&portal->cgr_lock); INIT_WORK(&portal->congestion_work, qm_congestion_task); INIT_WORK(&portal->mr_work, qm_mr_process_task); portal->bits = 0; @@ -1456,11 +1456,14 @@ static void qm_congestion_task(struct work_struct *work) union qm_mc_result *mcr; struct qman_cgr *cgr; - spin_lock(&p->cgr_lock); + /* + * FIXME: QM_MCR_TIMEOUT is 10ms, which is too long for a raw spinlock! + */ + raw_spin_lock_irq(&p->cgr_lock); qm_mc_start(&p->p); qm_mc_commit(&p->p, QM_MCC_VERB_QUERYCONGESTION); if (!qm_mc_result_timeout(&p->p, &mcr)) { - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); dev_crit(p->config->dev, "QUERYCONGESTION timeout\n"); qman_p_irqsource_add(p, QM_PIRQ_CSCI); return; @@ -1476,7 +1479,7 @@ static void qm_congestion_task(struct work_struct *work) list_for_each_entry(cgr, &p->cgr_cbs, node) if (cgr->cb && qman_cgrs_get(&c, cgr->cgrid)) cgr->cb(p, cgr, qman_cgrs_get(&rr, cgr->cgrid)); - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); qman_p_irqsource_add(p, QM_PIRQ_CSCI); } @@ -2440,7 +2443,7 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, preempt_enable(); cgr->chan = p->config->channel; - spin_lock(&p->cgr_lock); + raw_spin_lock_irq(&p->cgr_lock); if (opts) { struct qm_mcc_initcgr local_opts = *opts; @@ -2477,7 +2480,7 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, qman_cgrs_get(&p->cgrs[1], cgr->cgrid)) cgr->cb(p, cgr, 1); out: - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); put_affine_portal(); return ret; } @@ -2512,7 +2515,7 @@ int qman_delete_cgr(struct qman_cgr *cgr) return -EINVAL; memset(&local_opts, 0, sizeof(struct qm_mcc_initcgr)); - spin_lock_irqsave(&p->cgr_lock, irqflags); + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); list_del(&cgr->node); /* * If there are no other CGR objects for this CGRID in the list, @@ -2537,7 +2540,7 @@ int qman_delete_cgr(struct qman_cgr *cgr) /* add back to the list */ list_add(&cgr->node, &p->cgr_cbs); release_lock: - spin_unlock_irqrestore(&p->cgr_lock, irqflags); + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); put_affine_portal(); return ret; } @@ -2577,9 +2580,9 @@ static int qman_update_cgr(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts) if (!p) return -EINVAL; - spin_lock_irqsave(&p->cgr_lock, irqflags); + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); ret = qm_modify_cgr(cgr, 0, opts); - spin_unlock_irqrestore(&p->cgr_lock, irqflags); + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); put_affine_portal(); return ret; } diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c index b0cd071c4719b..0b2e5690dacfa 100644 --- a/drivers/soc/mediatek/mtk-cmdq-helper.c +++ b/drivers/soc/mediatek/mtk-cmdq-helper.c @@ -14,7 +14,8 @@ #define CMDQ_POLL_ENABLE_MASK BIT(0) #define CMDQ_EOC_IRQ_EN BIT(0) #define CMDQ_REG_TYPE 1 -#define CMDQ_JUMP_RELATIVE 1 +#define CMDQ_JUMP_RELATIVE 0 +#define CMDQ_JUMP_ABSOLUTE 1 struct cmdq_instruction { union { @@ -397,7 +398,7 @@ int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr) struct cmdq_instruction inst = {}; inst.op = CMDQ_CODE_JUMP; - inst.offset = CMDQ_JUMP_RELATIVE; + inst.offset = CMDQ_JUMP_ABSOLUTE; inst.value = addr >> cmdq_get_shift_pa(((struct cmdq_client *)pkt->cl)->chan); return cmdq_pkt_append_command(pkt, inst); diff --git a/drivers/soc/mediatek/mtk-svs.c b/drivers/soc/mediatek/mtk-svs.c index c832f5c670bcf..9a91298c12539 100644 --- a/drivers/soc/mediatek/mtk-svs.c +++ b/drivers/soc/mediatek/mtk-svs.c @@ -1768,6 +1768,7 @@ static int svs_bank_resource_setup(struct svs_platform *svsp) const struct svs_bank_pdata *bdata; struct svs_bank *svsb; struct dev_pm_opp *opp; + char tz_name_buf[20]; unsigned long freq; int count, ret; u32 idx, i; @@ -1819,10 +1820,12 @@ static int svs_bank_resource_setup(struct svs_platform *svsp) } if (!IS_ERR_OR_NULL(bdata->tzone_name)) { - svsb->tzd = thermal_zone_get_zone_by_name(bdata->tzone_name); + snprintf(tz_name_buf, ARRAY_SIZE(tz_name_buf), + "%s-thermal", bdata->tzone_name); + svsb->tzd = thermal_zone_get_zone_by_name(tz_name_buf); if (IS_ERR(svsb->tzd)) { dev_err(svsb->dev, "cannot get \"%s\" thermal zone\n", - bdata->tzone_name); + tz_name_buf); return PTR_ERR(svsb->tzd); } } diff --git a/drivers/soc/qcom/cmd-db.c b/drivers/soc/qcom/cmd-db.c index a5fd68411bed5..86fb2cd4f484d 100644 --- a/drivers/soc/qcom/cmd-db.c +++ b/drivers/soc/qcom/cmd-db.c @@ -1,6 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2016-2018, 2020, The Linux Foundation. All rights reserved. */ +/* + * Copyright (c) 2016-2018, 2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ +#include #include #include #include @@ -17,6 +21,8 @@ #define MAX_SLV_ID 8 #define SLAVE_ID_MASK 0x7 #define SLAVE_ID_SHIFT 16 +#define SLAVE_ID(addr) FIELD_GET(GENMASK(19, 16), addr) +#define VRM_ADDR(addr) FIELD_GET(GENMASK(19, 4), addr) /** * struct entry_header: header for each entry in cmddb @@ -220,6 +226,30 @@ const void *cmd_db_read_aux_data(const char *id, size_t *len) } EXPORT_SYMBOL_GPL(cmd_db_read_aux_data); +/** + * cmd_db_match_resource_addr() - Compare if both Resource addresses are same + * + * @addr1: Resource address to compare + * @addr2: Resource address to compare + * + * Return: true if two addresses refer to the same resource, false otherwise + */ +bool cmd_db_match_resource_addr(u32 addr1, u32 addr2) +{ + /* + * Each RPMh VRM accelerator resource has 3 or 4 contiguous 4-byte + * aligned addresses associated with it. Ignore the offset to check + * for VRM requests. + */ + if (addr1 == addr2) + return true; + else if (SLAVE_ID(addr1) == CMD_DB_HW_VRM && VRM_ADDR(addr1) == VRM_ADDR(addr2)) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(cmd_db_match_resource_addr); + /** * cmd_db_read_slave_id - Get the slave ID for a given resource address * diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 4ca88eaebf06a..cbef0dea1d5d7 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -859,6 +859,8 @@ static int llcc_update_act_ctrl(u32 sid, ret = regmap_read_poll_timeout(drv_data->bcast_regmap, status_reg, slice_status, !(slice_status & status), 0, LLCC_STATUS_READ_DELAY); + if (ret) + return ret; if (drv_data->version >= LLCC_VERSION_4_1_0_0) ret = regmap_write(drv_data->bcast_regmap, act_clear_reg, diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c index f913e9bd57ed4..823fd108fa039 100644 --- a/drivers/soc/qcom/pmic_glink.c +++ b/drivers/soc/qcom/pmic_glink.c @@ -11,6 +11,7 @@ #include #include #include +#include enum { PMIC_GLINK_CLIENT_BATT = 0, @@ -36,7 +37,7 @@ struct pmic_glink { unsigned int pdr_state; /* serializing clients list updates */ - struct mutex client_lock; + spinlock_t client_lock; struct list_head clients; }; @@ -58,10 +59,11 @@ static void _devm_pmic_glink_release_client(struct device *dev, void *res) { struct pmic_glink_client *client = (struct pmic_glink_client *)res; struct pmic_glink *pg = client->pg; + unsigned long flags; - mutex_lock(&pg->client_lock); + spin_lock_irqsave(&pg->client_lock, flags); list_del(&client->node); - mutex_unlock(&pg->client_lock); + spin_unlock_irqrestore(&pg->client_lock, flags); } struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, @@ -72,6 +74,7 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, { struct pmic_glink_client *client; struct pmic_glink *pg = dev_get_drvdata(dev->parent); + unsigned long flags; client = devres_alloc(_devm_pmic_glink_release_client, sizeof(*client), GFP_KERNEL); if (!client) @@ -83,9 +86,14 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, client->pdr_notify = pdr; client->priv = priv; - mutex_lock(&pg->client_lock); + mutex_lock(&pg->state_lock); + spin_lock_irqsave(&pg->client_lock, flags); + list_add(&client->node, &pg->clients); - mutex_unlock(&pg->client_lock); + client->pdr_notify(client->priv, pg->client_state); + + spin_unlock_irqrestore(&pg->client_lock, flags); + mutex_unlock(&pg->state_lock); devres_add(dev, client); @@ -107,6 +115,7 @@ static int pmic_glink_rpmsg_callback(struct rpmsg_device *rpdev, void *data, struct pmic_glink_client *client; struct pmic_glink_hdr *hdr; struct pmic_glink *pg = dev_get_drvdata(&rpdev->dev); + unsigned long flags; if (len < sizeof(*hdr)) { dev_warn(pg->dev, "ignoring truncated message\n"); @@ -115,10 +124,12 @@ static int pmic_glink_rpmsg_callback(struct rpmsg_device *rpdev, void *data, hdr = data; + spin_lock_irqsave(&pg->client_lock, flags); list_for_each_entry(client, &pg->clients, node) { if (client->id == le32_to_cpu(hdr->owner)) client->cb(data, len, client->priv); } + spin_unlock_irqrestore(&pg->client_lock, flags); return 0; } @@ -158,6 +169,7 @@ static void pmic_glink_state_notify_clients(struct pmic_glink *pg) { struct pmic_glink_client *client; unsigned int new_state = pg->client_state; + unsigned long flags; if (pg->client_state != SERVREG_SERVICE_STATE_UP) { if (pg->pdr_state == SERVREG_SERVICE_STATE_UP && pg->ept) @@ -168,8 +180,10 @@ static void pmic_glink_state_notify_clients(struct pmic_glink *pg) } if (new_state != pg->client_state) { + spin_lock_irqsave(&pg->client_lock, flags); list_for_each_entry(client, &pg->clients, node) client->pdr_notify(client->priv, new_state); + spin_unlock_irqrestore(&pg->client_lock, flags); pg->client_state = new_state; } } @@ -256,7 +270,7 @@ static int pmic_glink_probe(struct platform_device *pdev) pg->dev = &pdev->dev; INIT_LIST_HEAD(&pg->clients); - mutex_init(&pg->client_lock); + spin_lock_init(&pg->client_lock); mutex_init(&pg->state_lock); match_data = (unsigned long *)of_device_get_match_data(&pdev->dev); diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c index a021dc71807be..daf64be966fe1 100644 --- a/drivers/soc/qcom/rpmh-rsc.c +++ b/drivers/soc/qcom/rpmh-rsc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * Copyright (c) 2023-2024, Qualcomm Innovation Center, Inc. All rights reserved. */ #define pr_fmt(fmt) "%s " fmt, KBUILD_MODNAME @@ -557,7 +558,7 @@ static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs, for_each_set_bit(j, &curr_enabled, MAX_CMDS_PER_TCS) { addr = read_tcs_cmd(drv, drv->regs[RSC_DRV_CMD_ADDR], i, j); for (k = 0; k < msg->num_cmds; k++) { - if (addr == msg->cmds[k].addr) + if (cmd_db_match_resource_addr(msg->cmds[k].addr, addr)) return -EBUSY; } } diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c index 6349a0debeb57..a980020ab854f 100644 --- a/drivers/soc/qcom/socinfo.c +++ b/drivers/soc/qcom/socinfo.c @@ -124,7 +124,7 @@ static const char *const pmic_models[] = { [50] = "PM8350B", [51] = "PMR735A", [52] = "PMR735B", - [55] = "PM2250", + [55] = "PM4125", [58] = "PM8450", [65] = "PM8010", [69] = "PM8550VS", diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index f54bb4dd2d101..42028ace063a4 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -148,6 +148,19 @@ static void amd_sdw_set_frameshape(struct amd_sdw_manager *amd_manager) writel(frame_size, amd_manager->mmio + ACP_SW_FRAMESIZE); } +static void amd_sdw_wake_enable(struct amd_sdw_manager *amd_manager, bool enable) +{ + u32 wake_ctrl; + + wake_ctrl = readl(amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11); + if (enable) + wake_ctrl |= AMD_SDW_WAKE_INTR_MASK; + else + wake_ctrl &= ~AMD_SDW_WAKE_INTR_MASK; + + writel(wake_ctrl, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11); +} + static void amd_sdw_ctl_word_prep(u32 *lower_word, u32 *upper_word, struct sdw_msg *msg, int cmd_offset) { @@ -1122,6 +1135,7 @@ static int __maybe_unused amd_suspend(struct device *dev) } if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + amd_sdw_wake_enable(amd_manager, false); return amd_sdw_clock_stop(amd_manager); } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { /* @@ -1148,6 +1162,7 @@ static int __maybe_unused amd_suspend_runtime(struct device *dev) return 0; } if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + amd_sdw_wake_enable(amd_manager, true); return amd_sdw_clock_stop(amd_manager); } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { ret = amd_sdw_clock_stop(amd_manager); diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h index 5f040151a259b..6dcc7a449346e 100644 --- a/drivers/soundwire/amd_manager.h +++ b/drivers/soundwire/amd_manager.h @@ -152,7 +152,7 @@ #define AMD_SDW0_EXT_INTR_MASK 0x200000 #define AMD_SDW1_EXT_INTR_MASK 4 #define AMD_SDW_IRQ_MASK_0TO7 0x77777777 -#define AMD_SDW_IRQ_MASK_8TO11 0x000d7777 +#define AMD_SDW_IRQ_MASK_8TO11 0x000c7777 #define AMD_SDW_IRQ_ERROR_MASK 0xff #define AMD_SDW_MAX_FREQ_NUM 1 #define AMD_SDW0_MAX_TX_PORTS 3 @@ -190,6 +190,7 @@ #define AMD_SDW_CLK_RESUME_REQ 2 #define AMD_SDW_CLK_RESUME_DONE 3 #define AMD_SDW_WAKE_STAT_MASK BIT(16) +#define AMD_SDW_WAKE_INTR_MASK BIT(16) static u32 amd_sdw_freq_tbl[AMD_SDW_MAX_FREQ_NUM] = { AMD_SDW_DEFAULT_CLK_FREQ, diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 0efc1c3bee5f5..3e7cf04aaf2a6 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -1880,7 +1880,7 @@ struct sdw_cdns_pdi *sdw_cdns_alloc_pdi(struct sdw_cdns *cdns, /* check if we found a PDI, else find in bi-directional */ if (!pdi) - pdi = cdns_find_pdi(cdns, 2, stream->num_bd, stream->bd, + pdi = cdns_find_pdi(cdns, 0, stream->num_bd, stream->bd, dai_id); if (pdi) { diff --git a/drivers/soundwire/dmi-quirks.c b/drivers/soundwire/dmi-quirks.c index 9ebdd0cd0b1cf..91ab97a456fa9 100644 --- a/drivers/soundwire/dmi-quirks.c +++ b/drivers/soundwire/dmi-quirks.c @@ -130,6 +130,14 @@ static const struct dmi_system_id adr_remap_quirk_table[] = { }, .driver_data = (void *)intel_rooks_county, }, + { + /* quirk used for NUC15 LAPRC710 skew */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "LAPRC710"), + }, + .driver_data = (void *)intel_rooks_county, + }, { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c index 9ace259d2d29d..2b07b6dbf8a34 100644 --- a/drivers/spi/spi-axi-spi-engine.c +++ b/drivers/spi/spi-axi-spi-engine.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -15,12 +16,6 @@ #include #include -#define SPI_ENGINE_VERSION_MAJOR(x) ((x >> 16) & 0xff) -#define SPI_ENGINE_VERSION_MINOR(x) ((x >> 8) & 0xff) -#define SPI_ENGINE_VERSION_PATCH(x) (x & 0xff) - -#define SPI_ENGINE_REG_VERSION 0x00 - #define SPI_ENGINE_REG_RESET 0x40 #define SPI_ENGINE_REG_INT_ENABLE 0x80 @@ -661,12 +656,12 @@ static int spi_engine_probe(struct platform_device *pdev) if (IS_ERR(spi_engine->base)) return PTR_ERR(spi_engine->base); - version = readl(spi_engine->base + SPI_ENGINE_REG_VERSION); - if (SPI_ENGINE_VERSION_MAJOR(version) != 1) { - dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n", - SPI_ENGINE_VERSION_MAJOR(version), - SPI_ENGINE_VERSION_MINOR(version), - SPI_ENGINE_VERSION_PATCH(version)); + version = readl(spi_engine->base + ADI_AXI_REG_VERSION); + if (ADI_AXI_PCORE_VER_MAJOR(version) != 1) { + dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%u\n", + ADI_AXI_PCORE_VER_MAJOR(version), + ADI_AXI_PCORE_VER_MINOR(version), + ADI_AXI_PCORE_VER_PATCH(version)); return -ENODEV; } diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c index adf19e8c4c8a0..d527627e3c535 100644 --- a/drivers/spi/spi-cs42l43.c +++ b/drivers/spi/spi-cs42l43.c @@ -19,7 +19,7 @@ #include #define CS42L43_FIFO_SIZE 16 -#define CS42L43_SPI_ROOT_HZ (40 * HZ_PER_MHZ) +#define CS42L43_SPI_ROOT_HZ 49152000 #define CS42L43_SPI_MAX_LENGTH 65532 enum cs42l43_spi_cmd { diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 11991eb126364..079035db7dd85 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -830,11 +830,11 @@ static int fsl_lpspi_probe(struct platform_device *pdev) is_target = of_property_read_bool((&pdev->dev)->of_node, "spi-slave"); if (is_target) - controller = spi_alloc_target(&pdev->dev, - sizeof(struct fsl_lpspi_data)); + controller = devm_spi_alloc_target(&pdev->dev, + sizeof(struct fsl_lpspi_data)); else - controller = spi_alloc_host(&pdev->dev, - sizeof(struct fsl_lpspi_data)); + controller = devm_spi_alloc_host(&pdev->dev, + sizeof(struct fsl_lpspi_data)); if (!controller) return -ENOMEM; diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c index 35ef5e8e2ffd2..77e9738e42f60 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -151,8 +151,6 @@ static const struct debugfs_reg32 hisi_spi_regs[] = { HISI_SPI_DBGFS_REG("ENR", HISI_SPI_ENR), HISI_SPI_DBGFS_REG("FIFOC", HISI_SPI_FIFOC), HISI_SPI_DBGFS_REG("IMR", HISI_SPI_IMR), - HISI_SPI_DBGFS_REG("DIN", HISI_SPI_DIN), - HISI_SPI_DBGFS_REG("DOUT", HISI_SPI_DOUT), HISI_SPI_DBGFS_REG("SR", HISI_SPI_SR), HISI_SPI_DBGFS_REG("RISR", HISI_SPI_RISR), HISI_SPI_DBGFS_REG("ISR", HISI_SPI_ISR), diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 833a1bb7a9143..09b6c1b45f1a1 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -660,18 +660,8 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, ctrl |= (spi_imx->target_burst * 8 - 1) << MX51_ECSPI_CTRL_BL_OFFSET; else { - if (spi_imx->usedma) { - ctrl |= (spi_imx->bits_per_word - 1) - << MX51_ECSPI_CTRL_BL_OFFSET; - } else { - if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST) - ctrl |= (MX51_ECSPI_CTRL_MAX_BURST * BITS_PER_BYTE - 1) - << MX51_ECSPI_CTRL_BL_OFFSET; - else - ctrl |= spi_imx->count / DIV_ROUND_UP(spi_imx->bits_per_word, - BITS_PER_BYTE) * spi_imx->bits_per_word - << MX51_ECSPI_CTRL_BL_OFFSET; - } + ctrl |= (spi_imx->bits_per_word - 1) + << MX51_ECSPI_CTRL_BL_OFFSET; } /* set clock speed */ diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index 2dc8ceb85374b..17b8baf749e6a 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -297,6 +297,49 @@ static void spi_mem_access_end(struct spi_mem *mem) pm_runtime_put(ctlr->dev.parent); } +static void spi_mem_add_op_stats(struct spi_statistics __percpu *pcpu_stats, + const struct spi_mem_op *op, int exec_op_ret) +{ + struct spi_statistics *stats; + u64 len, l2len; + + get_cpu(); + stats = this_cpu_ptr(pcpu_stats); + u64_stats_update_begin(&stats->syncp); + + /* + * We do not have the concept of messages or transfers. Let's consider + * that one operation is equivalent to one message and one transfer. + */ + u64_stats_inc(&stats->messages); + u64_stats_inc(&stats->transfers); + + /* Use the sum of all lengths as bytes count and histogram value. */ + len = op->cmd.nbytes + op->addr.nbytes; + len += op->dummy.nbytes + op->data.nbytes; + u64_stats_add(&stats->bytes, len); + l2len = min(fls(len), SPI_STATISTICS_HISTO_SIZE) - 1; + u64_stats_inc(&stats->transfer_bytes_histo[l2len]); + + /* Only account for data bytes as transferred bytes. */ + if (op->data.nbytes && op->data.dir == SPI_MEM_DATA_OUT) + u64_stats_add(&stats->bytes_tx, op->data.nbytes); + if (op->data.nbytes && op->data.dir == SPI_MEM_DATA_IN) + u64_stats_add(&stats->bytes_rx, op->data.nbytes); + + /* + * A timeout is not an error, following the same behavior as + * spi_transfer_one_message(). + */ + if (exec_op_ret == -ETIMEDOUT) + u64_stats_inc(&stats->timedout); + else if (exec_op_ret) + u64_stats_inc(&stats->errors); + + u64_stats_update_end(&stats->syncp); + put_cpu(); +} + /** * spi_mem_exec_op() - Execute a memory operation * @mem: the SPI memory @@ -339,8 +382,12 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op) * read path) and expect the core to use the regular SPI * interface in other cases. */ - if (!ret || ret != -ENOTSUPP || ret != -EOPNOTSUPP) + if (!ret || (ret != -ENOTSUPP && ret != -EOPNOTSUPP)) { + spi_mem_add_op_stats(ctlr->pcpu_statistics, op, ret); + spi_mem_add_op_stats(mem->spi->pcpu_statistics, op, ret); + return ret; + } } tmpbufsize = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes; diff --git a/drivers/spi/spi-microchip-core-qspi.c b/drivers/spi/spi-microchip-core-qspi.c index 03d125a71fd99..09f16471c5375 100644 --- a/drivers/spi/spi-microchip-core-qspi.c +++ b/drivers/spi/spi-microchip-core-qspi.c @@ -283,6 +283,7 @@ static int mchp_coreqspi_setup_clock(struct mchp_coreqspi *qspi, struct spi_devi } control = readl_relaxed(qspi->regs + REG_CONTROL); + control &= ~CONTROL_CLKRATE_MASK; control |= baud_rate_val << CONTROL_CLKRATE_SHIFT; writel_relaxed(control, qspi->regs + REG_CONTROL); control = readl_relaxed(qspi->regs + REG_CONTROL); diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 8d5d170d49cc4..109dac2e69df2 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -787,17 +787,19 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id) mdata->xfer_len = min(MTK_SPI_MAX_FIFO_SIZE, len); mtk_spi_setup_packet(host); - cnt = mdata->xfer_len / 4; - iowrite32_rep(mdata->base + SPI_TX_DATA_REG, - trans->tx_buf + mdata->num_xfered, cnt); + if (trans->tx_buf) { + cnt = mdata->xfer_len / 4; + iowrite32_rep(mdata->base + SPI_TX_DATA_REG, + trans->tx_buf + mdata->num_xfered, cnt); - remainder = mdata->xfer_len % 4; - if (remainder > 0) { - reg_val = 0; - memcpy(®_val, - trans->tx_buf + (cnt * 4) + mdata->num_xfered, - remainder); - writel(reg_val, mdata->base + SPI_TX_DATA_REG); + remainder = mdata->xfer_len % 4; + if (remainder > 0) { + reg_val = 0; + memcpy(®_val, + trans->tx_buf + (cnt * 4) + mdata->num_xfered, + remainder); + writel(reg_val, mdata->base + SPI_TX_DATA_REG); + } } mtk_spi_enable_transfer(host); diff --git a/drivers/spi/spi-pci1xxxx.c b/drivers/spi/spi-pci1xxxx.c index 5b2d3e4e21b7a..5a42266820522 100644 --- a/drivers/spi/spi-pci1xxxx.c +++ b/drivers/spi/spi-pci1xxxx.c @@ -275,6 +275,8 @@ static int pci1xxxx_spi_probe(struct pci_dev *pdev, const struct pci_device_id * spi_bus->spi_int[iter] = devm_kzalloc(&pdev->dev, sizeof(struct pci1xxxx_spi_internal), GFP_KERNEL); + if (!spi_bus->spi_int[iter]) + return -ENOMEM; spi_sub_ptr = spi_bus->spi_int[iter]; spi_sub_ptr->spi_host = devm_spi_alloc_host(dev, sizeof(struct spi_controller)); if (!spi_sub_ptr->spi_host) diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 0e48ffd499b9f..652eadbefe24c 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -3,19 +3,20 @@ // Copyright (c) 2009 Samsung Electronics Co., Ltd. // Jaswinder Singh -#include -#include -#include -#include +#include +#include #include +#include #include #include +#include +#include +#include +#include +#include #include #include #include -#include - -#include #define MAX_SPI_PORTS 12 #define S3C64XX_SPI_QUIRK_CS_AUTO (1 << 1) @@ -76,6 +77,7 @@ #define S3C64XX_SPI_INT_RX_FIFORDY_EN (1<<1) #define S3C64XX_SPI_INT_TX_FIFORDY_EN (1<<0) +#define S3C64XX_SPI_ST_TX_FIFO_LVL_SHIFT 6 #define S3C64XX_SPI_ST_RX_OVERRUN_ERR (1<<5) #define S3C64XX_SPI_ST_RX_UNDERRUN_ERR (1<<4) #define S3C64XX_SPI_ST_TX_OVERRUN_ERR (1<<3) @@ -106,9 +108,11 @@ #define FIFO_LVL_MASK(i) ((i)->port_conf->fifo_lvl_mask[i->port_id]) #define S3C64XX_SPI_ST_TX_DONE(v, i) (((v) & \ (1 << (i)->port_conf->tx_st_done)) ? 1 : 0) -#define TX_FIFO_LVL(v, i) (((v) >> 6) & FIFO_LVL_MASK(i)) -#define RX_FIFO_LVL(v, i) (((v) >> (i)->port_conf->rx_lvl_offset) & \ - FIFO_LVL_MASK(i)) +#define TX_FIFO_LVL(v, sdd) (((v) & (sdd)->tx_fifomask) >> \ + __ffs((sdd)->tx_fifomask)) +#define RX_FIFO_LVL(v, sdd) (((v) & (sdd)->rx_fifomask) >> \ + __ffs((sdd)->rx_fifomask)) +#define FIFO_DEPTH(i) ((FIFO_LVL_MASK(i) >> 1) + 1) #define S3C64XX_SPI_MAX_TRAILCNT 0x3ff #define S3C64XX_SPI_TRAILCNT_OFF 19 @@ -133,6 +137,10 @@ struct s3c64xx_spi_dma_data { * struct s3c64xx_spi_port_config - SPI Controller hardware info * @fifo_lvl_mask: Bit-mask for {TX|RX}_FIFO_LVL bits in SPI_STATUS register. * @rx_lvl_offset: Bit offset of RX_FIFO_LVL bits in SPI_STATUS regiter. + * @rx_fifomask: SPI_STATUS.RX_FIFO_LVL mask. Shifted mask defining the field's + * length and position. + * @tx_fifomask: SPI_STATUS.TX_FIFO_LVL mask. Shifted mask defining the field's + * length and position. * @tx_st_done: Bit offset of TX_DONE bit in SPI_STATUS regiter. * @clk_div: Internal clock divider * @quirks: Bitmask of known quirks @@ -150,6 +158,8 @@ struct s3c64xx_spi_dma_data { struct s3c64xx_spi_port_config { int fifo_lvl_mask[MAX_SPI_PORTS]; int rx_lvl_offset; + u32 rx_fifomask; + u32 tx_fifomask; int tx_st_done; int quirks; int clk_div; @@ -179,6 +189,11 @@ struct s3c64xx_spi_port_config { * @tx_dma: Local transmit DMA data (e.g. chan and direction) * @port_conf: Local SPI port configuartion data * @port_id: Port identification number + * @fifo_depth: depth of the FIFO. + * @rx_fifomask: SPI_STATUS.RX_FIFO_LVL mask. Shifted mask defining the field's + * length and position. + * @tx_fifomask: SPI_STATUS.TX_FIFO_LVL mask. Shifted mask defining the field's + * length and position. */ struct s3c64xx_spi_driver_data { void __iomem *regs; @@ -198,6 +213,9 @@ struct s3c64xx_spi_driver_data { struct s3c64xx_spi_dma_data tx_dma; const struct s3c64xx_spi_port_config *port_conf; unsigned int port_id; + unsigned int fifo_depth; + u32 rx_fifomask; + u32 tx_fifomask; }; static void s3c64xx_flush_fifo(struct s3c64xx_spi_driver_data *sdd) @@ -405,12 +423,10 @@ static bool s3c64xx_spi_can_dma(struct spi_controller *host, { struct s3c64xx_spi_driver_data *sdd = spi_controller_get_devdata(host); - if (sdd->rx_dma.ch && sdd->tx_dma.ch) { - return xfer->len > (FIFO_LVL_MASK(sdd) >> 1) + 1; - } else { - return false; - } + if (sdd->rx_dma.ch && sdd->tx_dma.ch) + return xfer->len >= sdd->fifo_depth; + return false; } static int s3c64xx_enable_datapath(struct s3c64xx_spi_driver_data *sdd, @@ -495,9 +511,7 @@ static u32 s3c64xx_spi_wait_for_timeout(struct s3c64xx_spi_driver_data *sdd, void __iomem *regs = sdd->regs; unsigned long val = 1; u32 status; - - /* max fifo depth available */ - u32 max_fifo = (FIFO_LVL_MASK(sdd) >> 1) + 1; + u32 max_fifo = sdd->fifo_depth; if (timeout_ms) val = msecs_to_loops(timeout_ms); @@ -604,7 +618,7 @@ static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd, * For any size less than the fifo size the below code is * executed atleast once. */ - loops = xfer->len / ((FIFO_LVL_MASK(sdd) >> 1) + 1); + loops = xfer->len / sdd->fifo_depth; buf = xfer->rx_buf; do { /* wait for data to be received in the fifo */ @@ -741,7 +755,7 @@ static int s3c64xx_spi_transfer_one(struct spi_controller *host, struct spi_transfer *xfer) { struct s3c64xx_spi_driver_data *sdd = spi_controller_get_devdata(host); - const unsigned int fifo_len = (FIFO_LVL_MASK(sdd) >> 1) + 1; + const unsigned int fifo_len = sdd->fifo_depth; const void *tx_buf = NULL; void *rx_buf = NULL; int target_len = 0, origin_len = 0; @@ -769,10 +783,9 @@ static int s3c64xx_spi_transfer_one(struct spi_controller *host, return status; } - if (!is_polling(sdd) && (xfer->len > fifo_len) && + if (!is_polling(sdd) && xfer->len >= fifo_len && sdd->rx_dma.ch && sdd->tx_dma.ch) { use_dma = 1; - } else if (xfer->len >= fifo_len) { tx_buf = xfer->tx_buf; rx_buf = xfer->rx_buf; @@ -1146,6 +1159,23 @@ static inline const struct s3c64xx_spi_port_config *s3c64xx_spi_get_port_config( return (const struct s3c64xx_spi_port_config *)platform_get_device_id(pdev)->driver_data; } +static void s3c64xx_spi_set_fifomask(struct s3c64xx_spi_driver_data *sdd) +{ + const struct s3c64xx_spi_port_config *port_conf = sdd->port_conf; + + if (port_conf->rx_fifomask) + sdd->rx_fifomask = port_conf->rx_fifomask; + else + sdd->rx_fifomask = FIFO_LVL_MASK(sdd) << + port_conf->rx_lvl_offset; + + if (port_conf->tx_fifomask) + sdd->tx_fifomask = port_conf->tx_fifomask; + else + sdd->tx_fifomask = FIFO_LVL_MASK(sdd) << + S3C64XX_SPI_ST_TX_FIFO_LVL_SHIFT; +} + static int s3c64xx_spi_probe(struct platform_device *pdev) { struct resource *mem_res; @@ -1191,6 +1221,10 @@ static int s3c64xx_spi_probe(struct platform_device *pdev) sdd->port_id = pdev->id; } + sdd->fifo_depth = FIFO_DEPTH(sdd); + + s3c64xx_spi_set_fifomask(sdd); + sdd->cur_bpw = 8; sdd->tx_dma.direction = DMA_MEM_TO_DEV; @@ -1280,7 +1314,7 @@ static int s3c64xx_spi_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "Samsung SoC SPI Driver loaded for Bus SPI-%d with %d Targets attached\n", sdd->port_id, host->num_chipselect); dev_dbg(&pdev->dev, "\tIOmem=[%pR]\tFIFO %dbytes\n", - mem_res, (FIFO_LVL_MASK(sdd) >> 1) + 1); + mem_res, sdd->fifo_depth); pm_runtime_mark_last_busy(&pdev->dev); pm_runtime_put_autosuspend(&pdev->dev); diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index 3858320304593..265c8bfa709a1 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -349,7 +349,7 @@ static int stm32_qspi_wait_poll_status(struct stm32_qspi *qspi) static int stm32_qspi_get_mode(u8 buswidth) { - if (buswidth == 4) + if (buswidth >= 4) return CCR_BUSWIDTH_4; return buswidth; @@ -653,9 +653,7 @@ static int stm32_qspi_setup(struct spi_device *spi) return -EINVAL; mode = spi->mode & (SPI_TX_OCTAL | SPI_RX_OCTAL); - if ((mode == SPI_TX_OCTAL || mode == SPI_RX_OCTAL) || - ((mode == (SPI_TX_OCTAL | SPI_RX_OCTAL)) && - gpiod_count(qspi->dev, "cs") == -ENOENT)) { + if (mode && gpiod_count(qspi->dev, "cs") == -ENOENT) { dev_err(qspi->dev, "spi-rx-bus-width\\/spi-tx-bus-width\\/cs-gpios\n"); dev_err(qspi->dev, "configuration not supported\n"); @@ -676,10 +674,10 @@ static int stm32_qspi_setup(struct spi_device *spi) qspi->cr_reg = CR_APMS | 3 << CR_FTHRES_SHIFT | CR_SSHIFT | CR_EN; /* - * Dual flash mode is only enable in case SPI_TX_OCTAL and SPI_TX_OCTAL - * are both set in spi->mode and "cs-gpios" properties is found in DT + * Dual flash mode is only enable in case SPI_TX_OCTAL or SPI_RX_OCTAL + * is set in spi->mode and "cs-gpios" properties is found in DT */ - if (mode == (SPI_TX_OCTAL | SPI_RX_OCTAL)) { + if (mode) { qspi->cr_reg |= CR_DFM; dev_dbg(qspi->dev, "Dual flash mode enable"); } diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index e61302ef3c21a..43712f793ff0e 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -1057,7 +1057,7 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id) mask |= STM32H7_SPI_SR_TXP | STM32H7_SPI_SR_RXP; if (!(sr & mask)) { - dev_warn(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n", + dev_vdbg(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n", sr, ier); spin_unlock_irqrestore(&spi->lock, flags); return IRQ_NONE; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index f2170f4b50775..688ae95f9df66 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -608,23 +608,35 @@ static void spi_dev_set_name(struct spi_device *spi) spi_get_chipselect(spi, 0)); } +static inline int spi_dev_check_cs(struct device *dev, + struct spi_device *spi, u8 idx, + struct spi_device *new_spi, u8 new_idx) +{ + u8 cs, cs_new; + u8 idx_new; + + cs = spi_get_chipselect(spi, idx); + for (idx_new = new_idx; idx_new < SPI_CS_CNT_MAX; idx_new++) { + cs_new = spi_get_chipselect(new_spi, idx_new); + if (cs != 0xFF && cs_new != 0xFF && cs == cs_new) { + dev_err(dev, "chipselect %u already in use\n", cs_new); + return -EBUSY; + } + } + return 0; +} + static int spi_dev_check(struct device *dev, void *data) { struct spi_device *spi = to_spi_device(dev); struct spi_device *new_spi = data; - int idx, nw_idx; - u8 cs, cs_nw; + int status, idx; if (spi->controller == new_spi->controller) { for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) { - cs = spi_get_chipselect(spi, idx); - for (nw_idx = 0; nw_idx < SPI_CS_CNT_MAX; nw_idx++) { - cs_nw = spi_get_chipselect(new_spi, nw_idx); - if (cs != 0xFF && cs_nw != 0xFF && cs == cs_nw) { - dev_err(dev, "chipselect %d already in use\n", cs_nw); - return -EBUSY; - } - } + status = spi_dev_check_cs(dev, spi, idx, new_spi, 0); + if (status) + return status; } } return 0; @@ -640,8 +652,8 @@ static int __spi_add_device(struct spi_device *spi) { struct spi_controller *ctlr = spi->controller; struct device *dev = ctlr->dev.parent; - int status, idx, nw_idx; - u8 cs, nw_cs; + int status, idx; + u8 cs; for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) { /* Chipselects are numbered 0..max; validate. */ @@ -657,14 +669,11 @@ static int __spi_add_device(struct spi_device *spi) * Make sure that multiple logical CS doesn't map to the same physical CS. * For example, spi->chip_select[0] != spi->chip_select[1] and so on. */ - for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) { - cs = spi_get_chipselect(spi, idx); - for (nw_idx = idx + 1; nw_idx < SPI_CS_CNT_MAX; nw_idx++) { - nw_cs = spi_get_chipselect(spi, nw_idx); - if (cs != 0xFF && nw_cs != 0xFF && cs == nw_cs) { - dev_err(dev, "chipselect %d already in use\n", nw_cs); - return -EBUSY; - } + if (!spi_controller_is_target(ctlr)) { + for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) { + status = spi_dev_check_cs(dev, spi, idx, spi, idx + 1); + if (status) + return status; } } @@ -1042,10 +1051,14 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) if (spi->mode & SPI_CS_HIGH) enable = !enable; - if (spi_is_csgpiod(spi)) { - if (!spi->controller->set_cs_timing && !activate) - spi_delay_exec(&spi->cs_hold, NULL); + /* + * Handle chip select delays for GPIO based CS or controllers without + * programmable chip select timing. + */ + if ((spi_is_csgpiod(spi) || !spi->controller->set_cs_timing) && !activate) + spi_delay_exec(&spi->cs_hold, NULL); + if (spi_is_csgpiod(spi)) { if (!(spi->mode & SPI_NO_CS)) { /* * Historically ACPI has no means of the GPIO polarity and @@ -1079,16 +1092,16 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) if ((spi->controller->flags & SPI_CONTROLLER_GPIO_SS) && spi->controller->set_cs) spi->controller->set_cs(spi, !enable); - - if (!spi->controller->set_cs_timing) { - if (activate) - spi_delay_exec(&spi->cs_setup, NULL); - else - spi_delay_exec(&spi->cs_inactive, NULL); - } } else if (spi->controller->set_cs) { spi->controller->set_cs(spi, !enable); } + + if (spi_is_csgpiod(spi) || !spi->controller->set_cs_timing) { + if (activate) + spi_delay_exec(&spi->cs_setup, NULL); + else + spi_delay_exec(&spi->cs_inactive, NULL); + } } #ifdef CONFIG_HAS_DMA @@ -1218,6 +1231,7 @@ static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg) else rx_dev = ctlr->dev.parent; + ret = -ENOMSG; list_for_each_entry(xfer, &msg->transfers, transfer_list) { /* The sync is done before each transfer. */ unsigned long attrs = DMA_ATTR_SKIP_CPU_SYNC; @@ -1247,6 +1261,9 @@ static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg) } } } + /* No transfer has been mapped, bail out with success */ + if (ret) + return 0; ctlr->cur_rx_dma_dev = rx_dev; ctlr->cur_tx_dma_dev = tx_dev; @@ -1747,13 +1764,37 @@ static int __spi_pump_transfer_message(struct spi_controller *ctlr, trace_spi_message_start(msg); - ret = spi_split_transfers_maxsize(ctlr, msg, - spi_max_transfer_size(msg->spi), - GFP_KERNEL | GFP_DMA); - if (ret) { - msg->status = ret; - spi_finalize_current_message(ctlr); - return ret; + /* + * If an SPI controller does not support toggling the CS line on each + * transfer (indicated by the SPI_CS_WORD flag) or we are using a GPIO + * for the CS line, we can emulate the CS-per-word hardware function by + * splitting transfers into one-word transfers and ensuring that + * cs_change is set for each transfer. + */ + if ((msg->spi->mode & SPI_CS_WORD) && (!(ctlr->mode_bits & SPI_CS_WORD) || + spi_is_csgpiod(msg->spi))) { + ret = spi_split_transfers_maxwords(ctlr, msg, 1, GFP_KERNEL); + if (ret) { + msg->status = ret; + spi_finalize_current_message(ctlr); + return ret; + } + + list_for_each_entry(xfer, &msg->transfers, transfer_list) { + /* Don't change cs_change on the last entry in the list */ + if (list_is_last(&xfer->transfer_list, &msg->transfers)) + break; + xfer->cs_change = 1; + } + } else { + ret = spi_split_transfers_maxsize(ctlr, msg, + spi_max_transfer_size(msg->spi), + GFP_KERNEL | GFP_DMA); + if (ret) { + msg->status = ret; + spi_finalize_current_message(ctlr); + return ret; + } } if (ctlr->prepare_message) { @@ -4063,33 +4104,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) if (list_empty(&message->transfers)) return -EINVAL; - /* - * If an SPI controller does not support toggling the CS line on each - * transfer (indicated by the SPI_CS_WORD flag) or we are using a GPIO - * for the CS line, we can emulate the CS-per-word hardware function by - * splitting transfers into one-word transfers and ensuring that - * cs_change is set for each transfer. - */ - if ((spi->mode & SPI_CS_WORD) && (!(ctlr->mode_bits & SPI_CS_WORD) || - spi_is_csgpiod(spi))) { - size_t maxsize = BITS_TO_BYTES(spi->bits_per_word); - int ret; - - /* spi_split_transfers_maxsize() requires message->spi */ - message->spi = spi; - - ret = spi_split_transfers_maxsize(ctlr, message, maxsize, - GFP_KERNEL); - if (ret) - return ret; - - list_for_each_entry(xfer, &message->transfers, transfer_list) { - /* Don't change cs_change on the last entry in the list */ - if (list_is_last(&xfer->transfer_list, &message->transfers)) - break; - xfer->cs_change = 1; - } - } + message->spi = spi; /* * Half-duplex links include original MicroWire, and ones with @@ -4214,8 +4229,6 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message) if (!ctlr->transfer) return -ENOTSUPP; - message->spi = spi; - SPI_STATISTICS_INCREMENT_FIELD(ctlr->pcpu_statistics, spi_async); SPI_STATISTICS_INCREMENT_FIELD(spi->pcpu_statistics, spi_async); @@ -4395,8 +4408,6 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message) if (status != 0) return status; - message->spi = spi; - SPI_STATISTICS_INCREMENT_FIELD(ctlr->pcpu_statistics, spi_sync); SPI_STATISTICS_INCREMENT_FIELD(spi->pcpu_statistics, spi_sync); @@ -4433,6 +4444,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message) wait_for_completion(&done); status = message->status; } + message->complete = NULL; message->context = NULL; return status; diff --git a/drivers/spmi/hisi-spmi-controller.c b/drivers/spmi/hisi-spmi-controller.c index 674a350cc6769..fa068b34b040c 100644 --- a/drivers/spmi/hisi-spmi-controller.c +++ b/drivers/spmi/hisi-spmi-controller.c @@ -300,7 +300,6 @@ static int spmi_controller_probe(struct platform_device *pdev) spin_lock_init(&spmi_controller->lock); - ctrl->nr = spmi_controller->channel; ctrl->dev.parent = pdev->dev.parent; ctrl->dev.of_node = of_node_get(pdev->dev.of_node); diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c index 9ed1180fe31f1..937c15324513f 100644 --- a/drivers/spmi/spmi-pmic-arb.c +++ b/drivers/spmi/spmi-pmic-arb.c @@ -1462,8 +1462,8 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev) */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "core"); core = devm_ioremap(&ctrl->dev, res->start, resource_size(res)); - if (IS_ERR(core)) - return PTR_ERR(core); + if (!core) + return -ENOMEM; pmic_arb->core_size = resource_size(res); @@ -1495,15 +1495,15 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev) "obsrvr"); pmic_arb->rd_base = devm_ioremap(&ctrl->dev, res->start, resource_size(res)); - if (IS_ERR(pmic_arb->rd_base)) - return PTR_ERR(pmic_arb->rd_base); + if (!pmic_arb->rd_base) + return -ENOMEM; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "chnls"); pmic_arb->wr_base = devm_ioremap(&ctrl->dev, res->start, resource_size(res)); - if (IS_ERR(pmic_arb->wr_base)) - return PTR_ERR(pmic_arb->wr_base); + if (!pmic_arb->wr_base) + return -ENOMEM; } pmic_arb->max_periphs = PMIC_ARB_MAX_PERIPHS; diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index b9934b9c2d708..070a99a4180cc 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -341,11 +341,13 @@ static int ssb_bus_match(struct device *dev, struct device_driver *drv) static int ssb_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { - const struct ssb_device *ssb_dev = dev_to_ssb_dev(dev); + const struct ssb_device *ssb_dev; if (!dev) return -ENODEV; + ssb_dev = dev_to_ssb_dev(dev); + return add_uevent_var(env, "MODALIAS=ssb:v%04Xid%04Xrev%02X", ssb_dev->id.vendor, ssb_dev->id.coreid, diff --git a/drivers/staging/greybus/arche-apb-ctrl.c b/drivers/staging/greybus/arche-apb-ctrl.c index 8541995008da8..aa6f266b62a14 100644 --- a/drivers/staging/greybus/arche-apb-ctrl.c +++ b/drivers/staging/greybus/arche-apb-ctrl.c @@ -466,6 +466,7 @@ static const struct of_device_id arche_apb_ctrl_of_match[] = { { .compatible = "usbffff,2", }, { }, }; +MODULE_DEVICE_TABLE(of, arche_apb_ctrl_of_match); static struct platform_driver arche_apb_ctrl_device_driver = { .probe = arche_apb_ctrl_probe, diff --git a/drivers/staging/greybus/arche-platform.c b/drivers/staging/greybus/arche-platform.c index 891b75327d7f7..b33977ccd5271 100644 --- a/drivers/staging/greybus/arche-platform.c +++ b/drivers/staging/greybus/arche-platform.c @@ -619,14 +619,7 @@ static const struct of_device_id arche_platform_of_match[] = { { .compatible = "google,arche-platform", }, { }, }; - -static const struct of_device_id arche_combined_id[] = { - /* Use PID/VID of SVC device */ - { .compatible = "google,arche-platform", }, - { .compatible = "usbffff,2", }, - { }, -}; -MODULE_DEVICE_TABLE(of, arche_combined_id); +MODULE_DEVICE_TABLE(of, arche_platform_of_match); static struct platform_driver arche_platform_device_driver = { .probe = arche_platform_probe, diff --git a/drivers/staging/greybus/light.c b/drivers/staging/greybus/light.c index 87d36948c6106..9999f84016992 100644 --- a/drivers/staging/greybus/light.c +++ b/drivers/staging/greybus/light.c @@ -100,15 +100,15 @@ static struct led_classdev *get_channel_cdev(struct gb_channel *channel) static struct gb_channel *get_channel_from_mode(struct gb_light *light, u32 mode) { - struct gb_channel *channel = NULL; + struct gb_channel *channel; int i; for (i = 0; i < light->channels_count; i++) { channel = &light->channels[i]; - if (channel && channel->mode == mode) - break; + if (channel->mode == mode) + return channel; } - return channel; + return NULL; } static int __gb_lights_flash_intensity_set(struct gb_channel *channel, @@ -147,6 +147,9 @@ static int __gb_lights_flash_brightness_set(struct gb_channel *channel) channel = get_channel_from_mode(channel->light, GB_CHANNEL_MODE_TORCH); + if (!channel) + return -EINVAL; + /* For not flash we need to convert brightness to intensity */ intensity = channel->intensity_uA.min + (channel->intensity_uA.step * channel->led->brightness); @@ -549,7 +552,10 @@ static int gb_lights_light_v4l2_register(struct gb_light *light) } channel_flash = get_channel_from_mode(light, GB_CHANNEL_MODE_FLASH); - WARN_ON(!channel_flash); + if (!channel_flash) { + dev_err(dev, "failed to get flash channel from mode\n"); + return -EINVAL; + } fled = &channel_flash->fled; diff --git a/drivers/staging/media/atomisp/pci/sh_css.c b/drivers/staging/media/atomisp/pci/sh_css.c index f35c90809414c..638f08b3f21be 100644 --- a/drivers/staging/media/atomisp/pci/sh_css.c +++ b/drivers/staging/media/atomisp/pci/sh_css.c @@ -4719,6 +4719,7 @@ static int load_video_binaries(struct ia_css_pipe *pipe) sizeof(struct ia_css_binary), GFP_KERNEL); if (!mycs->yuv_scaler_binary) { + mycs->num_yuv_scaler = 0; err = -ENOMEM; return err; } diff --git a/drivers/staging/media/imx/imx-media-csc-scaler.c b/drivers/staging/media/imx/imx-media-csc-scaler.c index 1fd39a2fca98a..95cca281e8a37 100644 --- a/drivers/staging/media/imx/imx-media-csc-scaler.c +++ b/drivers/staging/media/imx/imx-media-csc-scaler.c @@ -803,6 +803,7 @@ static int ipu_csc_scaler_release(struct file *file) dev_dbg(priv->dev, "Releasing instance %p\n", ctx); + v4l2_ctrl_handler_free(&ctx->ctrl_hdlr); v4l2_m2m_ctx_release(ctx->fh.m2m_ctx); v4l2_fh_del(&ctx->fh); v4l2_fh_exit(&ctx->fh); diff --git a/drivers/staging/media/ipu3/ipu3-v4l2.c b/drivers/staging/media/ipu3/ipu3-v4l2.c index a66f034380c05..3df58eb3e8822 100644 --- a/drivers/staging/media/ipu3/ipu3-v4l2.c +++ b/drivers/staging/media/ipu3/ipu3-v4l2.c @@ -1069,6 +1069,11 @@ static int imgu_v4l2_subdev_register(struct imgu_device *imgu, struct imgu_media_pipe *imgu_pipe = &imgu->imgu_pipe[pipe]; /* Initialize subdev media entity */ + imgu_sd->subdev.entity.ops = &imgu_media_ops; + for (i = 0; i < IMGU_NODE_NUM; i++) { + imgu_sd->subdev_pads[i].flags = imgu_pipe->nodes[i].output ? + MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE; + } r = media_entity_pads_init(&imgu_sd->subdev.entity, IMGU_NODE_NUM, imgu_sd->subdev_pads); if (r) { @@ -1076,11 +1081,6 @@ static int imgu_v4l2_subdev_register(struct imgu_device *imgu, "failed initialize subdev media entity (%d)\n", r); return r; } - imgu_sd->subdev.entity.ops = &imgu_media_ops; - for (i = 0; i < IMGU_NODE_NUM; i++) { - imgu_sd->subdev_pads[i].flags = imgu_pipe->nodes[i].output ? - MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE; - } /* Initialize subdev */ v4l2_subdev_init(&imgu_sd->subdev, &imgu_subdev_ops); @@ -1177,15 +1177,15 @@ static int imgu_v4l2_node_setup(struct imgu_device *imgu, unsigned int pipe, } /* Initialize media entities */ + node->vdev_pad.flags = node->output ? + MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK; + vdev->entity.ops = NULL; r = media_entity_pads_init(&vdev->entity, 1, &node->vdev_pad); if (r) { dev_err(dev, "failed initialize media entity (%d)\n", r); mutex_destroy(&node->lock); return r; } - node->vdev_pad.flags = node->output ? - MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK; - vdev->entity.ops = NULL; /* Initialize vbq */ vbq->type = node->vdev_fmt.type; diff --git a/drivers/staging/media/starfive/camss/stf-camss.c b/drivers/staging/media/starfive/camss/stf-camss.c index a587f860101ae..323aa70fdeaf1 100644 --- a/drivers/staging/media/starfive/camss/stf-camss.c +++ b/drivers/staging/media/starfive/camss/stf-camss.c @@ -162,6 +162,12 @@ static int stfcamss_register_devs(struct stfcamss *stfcamss) static void stfcamss_unregister_devs(struct stfcamss *stfcamss) { + struct stf_capture *cap_yuv = &stfcamss->captures[STF_CAPTURE_YUV]; + struct stf_isp_dev *isp_dev = &stfcamss->isp_dev; + + media_entity_remove_links(&isp_dev->subdev.entity); + media_entity_remove_links(&cap_yuv->video.vdev.entity); + stf_isp_unregister(&stfcamss->isp_dev); stf_capture_unregister(stfcamss); } diff --git a/drivers/staging/media/starfive/camss/stf-capture.c b/drivers/staging/media/starfive/camss/stf-capture.c index 70c24b050a1b5..ec5169e7b3918 100644 --- a/drivers/staging/media/starfive/camss/stf-capture.c +++ b/drivers/staging/media/starfive/camss/stf-capture.c @@ -20,28 +20,28 @@ static const struct stfcamss_format_info stf_wr_fmts[] = { .pixelformat = V4L2_PIX_FMT_SRGGB10, .planes = 1, .vsub = { 1 }, - .bpp = 10, + .bpp = 16, }, { .code = MEDIA_BUS_FMT_SGRBG10_1X10, .pixelformat = V4L2_PIX_FMT_SGRBG10, .planes = 1, .vsub = { 1 }, - .bpp = 10, + .bpp = 16, }, { .code = MEDIA_BUS_FMT_SGBRG10_1X10, .pixelformat = V4L2_PIX_FMT_SGBRG10, .planes = 1, .vsub = { 1 }, - .bpp = 10, + .bpp = 16, }, { .code = MEDIA_BUS_FMT_SBGGR10_1X10, .pixelformat = V4L2_PIX_FMT_SBGGR10, .planes = 1, .vsub = { 1 }, - .bpp = 10, + .bpp = 16, }, }; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c index 52e94c8f2f01a..780da4a8b5af1 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c @@ -427,11 +427,11 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) unsigned int ctb_addr_x, ctb_addr_y; struct cedrus_buffer *cedrus_buf; dma_addr_t src_buf_addr; - dma_addr_t src_buf_end_addr; u32 chroma_log2_weight_denom; u32 num_entry_point_offsets; u32 output_pic_list_index; u32 pic_order_cnt[2]; + size_t slice_bytes; u8 padding; int count; u32 reg; @@ -443,6 +443,7 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) pred_weight_table = &slice_params->pred_weight_table; num_entry_point_offsets = slice_params->num_entry_point_offsets; cedrus_buf = vb2_to_cedrus_buffer(&run->dst->vb2_buf); + slice_bytes = vb2_get_plane_payload(&run->src->vb2_buf, 0); /* * If entry points offsets are present, we should get them @@ -490,7 +491,7 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) cedrus_write(dev, VE_DEC_H265_BITS_OFFSET, 0); - reg = slice_params->bit_size; + reg = slice_bytes * 8; cedrus_write(dev, VE_DEC_H265_BITS_LEN, reg); /* Source beginning and end addresses. */ @@ -504,10 +505,7 @@ static int cedrus_h265_setup(struct cedrus_ctx *ctx, struct cedrus_run *run) cedrus_write(dev, VE_DEC_H265_BITS_ADDR, reg); - src_buf_end_addr = src_buf_addr + - DIV_ROUND_UP(slice_params->bit_size, 8); - - reg = VE_DEC_H265_BITS_END_ADDR_BASE(src_buf_end_addr); + reg = VE_DEC_H265_BITS_END_ADDR_BASE(src_buf_addr + slice_bytes); cedrus_write(dev, VE_DEC_H265_BITS_END_ADDR, reg); /* Coding tree block address */ diff --git a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c index 258aa0e37f554..4c3684dd902ed 100644 --- a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c +++ b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c @@ -937,8 +937,9 @@ static int create_component(struct vchiq_mmal_instance *instance, /* build component create message */ m.h.type = MMAL_MSG_TYPE_COMPONENT_CREATE; m.u.component_create.client_component = component->client_component; - strncpy(m.u.component_create.name, name, - sizeof(m.u.component_create.name)); + strscpy_pad(m.u.component_create.name, name, + sizeof(m.u.component_create.name)); + m.u.component_create.pid = 0; ret = send_synchronous_mmal_msg(instance, &m, sizeof(m.u.component_create), diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 1d25e64b068a0..f1eed1d49c8a0 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -3922,6 +3922,7 @@ int iscsi_target_tx_thread(void *arg) * connection recovery / failure event can be triggered externally. */ allow_signal(SIGINT); + complete(&conn->kthr_start_comp); while (!kthread_should_stop()) { /* @@ -4170,6 +4171,7 @@ int iscsi_target_rx_thread(void *arg) * connection recovery / failure event can be triggered externally. */ allow_signal(SIGINT); + complete(&conn->kthr_start_comp); /* * Wait for iscsi_post_login_handler() to complete before allowing * incoming iscsi/tcp socket I/O, and/or failing the connection. diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c index 6797200211836..26f3ecd25c28d 100644 --- a/drivers/target/iscsi/iscsi_target_erl1.c +++ b/drivers/target/iscsi/iscsi_target_erl1.c @@ -1102,6 +1102,18 @@ void iscsit_handle_dataout_timeout(struct timer_list *t) iscsit_inc_conn_usage_count(conn); + /* + * If the command was aborted, for instance following a LUN RESET, + * a dataout timeout might be normal. + */ + if (target_cmd_interrupted(&cmd->se_cmd)) { + pr_debug("DataOut timeout on interrupted cmd with" + " ITT[0x%08llx]\n", cmd->se_cmd.tag); + cmd->dataout_timer_flags &= ~ISCSI_TF_RUNNING; + iscsit_dec_conn_usage_count(conn); + return; + } + spin_lock_bh(&cmd->dataout_timeout_lock); if (cmd->dataout_timer_flags & ISCSI_TF_STOP) { spin_unlock_bh(&cmd->dataout_timeout_lock); @@ -1115,19 +1127,22 @@ void iscsit_handle_dataout_timeout(struct timer_list *t) if (!sess->sess_ops->ErrorRecoveryLevel) { pr_err("Unable to recover from DataOut timeout while" " in ERL=0, closing iSCSI connection for I_T Nexus" - " %s,i,0x%6phN,%s,t,0x%02x\n", + " %s,i,0x%6phN,%s,t,0x%02x, cmd ITT[0x%08llx]\n", sess->sess_ops->InitiatorName, sess->isid, - sess->tpg->tpg_tiqn->tiqn, (u32)sess->tpg->tpgt); + sess->tpg->tpg_tiqn->tiqn, (u32)sess->tpg->tpgt, + cmd->se_cmd.tag); goto failure; } if (++cmd->dataout_timeout_retries == na->dataout_timeout_retries) { pr_err("Command ITT: 0x%08x exceeded max retries" " for DataOUT timeout %u, closing iSCSI connection for" - " I_T Nexus %s,i,0x%6phN,%s,t,0x%02x\n", + " I_T Nexus %s,i,0x%6phN,%s,t,0x%02x," + " cmd ITT[0x%08llx]\n", cmd->init_task_tag, na->dataout_timeout_retries, sess->sess_ops->InitiatorName, sess->isid, - sess->tpg->tpg_tiqn->tiqn, (u32)sess->tpg->tpgt); + sess->tpg->tpg_tiqn->tiqn, (u32)sess->tpg->tpgt, + cmd->se_cmd.tag); goto failure; } diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 90b870f234f03..d564f9ae4db97 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -660,6 +660,7 @@ int iscsit_start_kthreads(struct iscsit_conn *conn) ret = PTR_ERR(conn->tx_thread); goto out_bitmap; } + wait_for_completion(&conn->kthr_start_comp); conn->tx_thread_active = true; conn->rx_thread = kthread_run(iscsi_target_rx_thread, conn, @@ -669,6 +670,7 @@ int iscsit_start_kthreads(struct iscsit_conn *conn) ret = PTR_ERR(conn->rx_thread); goto out_tx; } + wait_for_completion(&conn->kthr_start_comp); conn->rx_thread_active = true; return 0; @@ -1064,6 +1066,7 @@ static struct iscsit_conn *iscsit_alloc_conn(struct iscsi_np *np) init_completion(&conn->rx_half_close_comp); init_completion(&conn->tx_half_close_comp); init_completion(&conn->rx_login_comp); + init_completion(&conn->kthr_start_comp); spin_lock_init(&conn->cmd_lock); spin_lock_init(&conn->conn_usage_lock); spin_lock_init(&conn->immed_queue_lock); @@ -1132,7 +1135,7 @@ void iscsi_target_login_sess_out(struct iscsit_conn *conn, if (!new_sess) goto old_sess_out; - pr_err("iSCSI Login negotiation failed.\n"); + pr_debug("iSCSI Login negotiation failed.\n"); iscsit_collect_login_stats(conn, ISCSI_STATUS_CLS_INITIATOR_ERR, ISCSI_LOGIN_STATUS_INIT_ERR); if (!zero_tsih || !conn->sess) diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index fa3fb5f4e6bc4..5cddf8e60b3e6 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -1234,7 +1234,7 @@ int iscsi_target_locate_portal( */ tiqn = iscsit_get_tiqn_for_login(t_buf); if (!tiqn) { - pr_err("Unable to locate Target IQN: %s in" + pr_debug("Unable to locate Target IQN: %s in" " Storage Node\n", t_buf); iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_SVC_UNAVAILABLE); diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index c1fbcdd161826..c40217f44b1bc 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -3672,6 +3672,8 @@ static int __init target_core_init_configfs(void) { struct configfs_subsystem *subsys = &target_core_fabrics; struct t10_alua_lu_gp *lu_gp; + struct cred *kern_cred; + const struct cred *old_cred; int ret; pr_debug("TARGET_CORE[0]: Loading Generic Kernel Storage" @@ -3748,11 +3750,21 @@ static int __init target_core_init_configfs(void) if (ret < 0) goto out; + /* We use the kernel credentials to access the target directory */ + kern_cred = prepare_kernel_cred(&init_task); + if (!kern_cred) { + ret = -ENOMEM; + goto out; + } + old_cred = override_creds(kern_cred); target_init_dbroot(); + revert_creds(old_cred); + put_cred(kern_cred); return 0; out: + target_xcopy_release_pt(); configfs_unregister_subsystem(subsys); core_dev_release_virtual_lun0(); rd_module_exit(); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 73d0d6133ac8f..d37b2641bfe50 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -882,7 +882,7 @@ static void target_abort_work(struct work_struct *work) target_handle_abort(cmd); } -static bool target_cmd_interrupted(struct se_cmd *cmd) +bool target_cmd_interrupted(struct se_cmd *cmd) { int post_ret; @@ -901,6 +901,7 @@ static bool target_cmd_interrupted(struct se_cmd *cmd) return false; } +EXPORT_SYMBOL(target_cmd_interrupted); /* May be called from interrupt context so must not sleep. */ void target_complete_cmd_with_sense(struct se_cmd *cmd, u8 scsi_status, diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c index 262e62ab6cf2f..90b828bcca243 100644 --- a/drivers/thermal/devfreq_cooling.c +++ b/drivers/thermal/devfreq_cooling.c @@ -201,7 +201,7 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd res = dfc->power_ops->get_real_power(df, power, freq, voltage); if (!res) { - state = dfc->capped_state; + state = dfc->max_state - dfc->capped_state; /* Convert EM power into milli-Watts first */ dfc->res_util = dfc->em_pd->table[state].power; diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c index 81e061f183ad1..38581583ad289 100644 --- a/drivers/thermal/gov_power_allocator.c +++ b/drivers/thermal/gov_power_allocator.c @@ -606,7 +606,7 @@ static int allocate_actors_buffer(struct power_allocator_params *params, /* There might be no cooling devices yet. */ if (!num_actors) { - ret = -EINVAL; + ret = 0; goto clean_state; } @@ -679,11 +679,6 @@ static int power_allocator_bind(struct thermal_zone_device *tz) return -ENOMEM; get_governor_trips(tz, params); - if (!params->trip_max) { - dev_warn(&tz->device, "power_allocator: missing trip_max\n"); - kfree(params); - return -EINVAL; - } ret = check_power_actors(tz, params); if (ret < 0) { @@ -712,9 +707,10 @@ static int power_allocator_bind(struct thermal_zone_device *tz) if (!tz->tzp->sustainable_power) dev_warn(&tz->device, "power_allocator: sustainable_power will be estimated\n"); - estimate_pid_constants(tz, tz->tzp->sustainable_power, - params->trip_switch_on, - params->trip_max->temperature); + if (params->trip_max) + estimate_pid_constants(tz, tz->tzp->sustainable_power, + params->trip_switch_on, + params->trip_max->temperature); reset_pid_controller(params); diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c index 649f67fdf3454..d75fae7b7ed22 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c @@ -176,14 +176,14 @@ static int proc_thermal_get_zone_temp(struct thermal_zone_device *zone, int *temp) { int cpu; - int curr_temp; + int curr_temp, ret; *temp = 0; for_each_online_cpu(cpu) { - curr_temp = intel_tcc_get_temp(cpu, false); - if (curr_temp < 0) - return curr_temp; + ret = intel_tcc_get_temp(cpu, &curr_temp, false); + if (ret < 0) + return ret; if (!*temp || curr_temp > *temp) *temp = curr_temp; } diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h index 95c6013a33fb6..674f3c85dfbc9 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.h @@ -25,6 +25,7 @@ #define PCI_DEVICE_ID_INTEL_HSB_THERMAL 0x0A03 #define PCI_DEVICE_ID_INTEL_ICL_THERMAL 0x8a03 #define PCI_DEVICE_ID_INTEL_JSL_THERMAL 0x4E03 +#define PCI_DEVICE_ID_INTEL_LNLM_THERMAL 0x641D #define PCI_DEVICE_ID_INTEL_MTLP_THERMAL 0x7D03 #define PCI_DEVICE_ID_INTEL_RPL_THERMAL 0xA71D #define PCI_DEVICE_ID_INTEL_SKL_THERMAL 0x1903 diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c index d7495571dd5d4..c2fea2e93d1f3 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device_pci.c @@ -150,7 +150,7 @@ static irqreturn_t proc_thermal_irq_handler(int irq, void *devid) { struct proc_thermal_pci *pci_info = devid; struct proc_thermal_device *proc_priv; - int ret = IRQ_HANDLED; + int ret = IRQ_NONE; u32 status; proc_priv = pci_info->proc_priv; @@ -175,6 +175,7 @@ static irqreturn_t proc_thermal_irq_handler(int irq, void *devid) /* Disable enable interrupt flag */ proc_thermal_mmio_write(pci_info, PROC_THERMAL_MMIO_INT_ENABLE_0, 0); pkg_thermal_schedule_work(&pci_info->work); + ret = IRQ_HANDLED; } pci_write_config_byte(pci_info->pdev, 0xdc, 0x01); @@ -407,6 +408,7 @@ static SIMPLE_DEV_PM_OPS(proc_thermal_pci_pm, proc_thermal_pci_suspend, static const struct pci_device_id proc_thermal_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, ADL_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_WT_REQ) }, + { PCI_DEVICE_DATA(INTEL, LNLM_THERMAL, PROC_THERMAL_FEATURE_RAPL) }, { PCI_DEVICE_DATA(INTEL, MTLP_THERMAL, PROC_THERMAL_FEATURE_RAPL | PROC_THERMAL_FEATURE_FIVR | PROC_THERMAL_FEATURE_DVFS | PROC_THERMAL_FEATURE_DLVR | PROC_THERMAL_FEATURE_WT_HINT | PROC_THERMAL_FEATURE_POWER_FLOOR) }, diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c index 2f00fc3bf274a..e964a9375722a 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rapl.c @@ -27,9 +27,9 @@ static int rapl_mmio_cpu_online(unsigned int cpu) if (topology_physical_package_id(cpu)) return 0; - rp = rapl_find_package_domain(cpu, &rapl_mmio_priv, true); + rp = rapl_find_package_domain_cpuslocked(cpu, &rapl_mmio_priv, true); if (!rp) { - rp = rapl_add_package(cpu, &rapl_mmio_priv, true); + rp = rapl_add_package_cpuslocked(cpu, &rapl_mmio_priv, true); if (IS_ERR(rp)) return PTR_ERR(rp); } @@ -42,14 +42,14 @@ static int rapl_mmio_cpu_down_prep(unsigned int cpu) struct rapl_package *rp; int lead_cpu; - rp = rapl_find_package_domain(cpu, &rapl_mmio_priv, true); + rp = rapl_find_package_domain_cpuslocked(cpu, &rapl_mmio_priv, true); if (!rp) return 0; cpumask_clear_cpu(cpu, &rp->cpumask); lead_cpu = cpumask_first(&rp->cpumask); if (lead_cpu >= nr_cpu_ids) - rapl_remove_package(rp); + rapl_remove_package_cpuslocked(rp); else if (rp->lead_cpu == cpu) rp->lead_cpu = lead_cpu; return 0; diff --git a/drivers/thermal/intel/intel_tcc.c b/drivers/thermal/intel/intel_tcc.c index 2e5c741c41ca0..5e8b7f34b3951 100644 --- a/drivers/thermal/intel/intel_tcc.c +++ b/drivers/thermal/intel/intel_tcc.c @@ -103,18 +103,19 @@ EXPORT_SYMBOL_NS_GPL(intel_tcc_set_offset, INTEL_TCC); /** * intel_tcc_get_temp() - returns the current temperature * @cpu: cpu that the MSR should be run on, nagative value means any cpu. + * @temp: pointer to the memory for saving cpu temperature. * @pkg: true: Package Thermal Sensor. false: Core Thermal Sensor. * * Get the current temperature returned by the CPU core/package level * thermal sensor, in degrees C. * - * Return: Temperature in degrees C on success, negative error code otherwise. + * Return: 0 on success, negative error code otherwise. */ -int intel_tcc_get_temp(int cpu, bool pkg) +int intel_tcc_get_temp(int cpu, int *temp, bool pkg) { u32 low, high; u32 msr = pkg ? MSR_IA32_PACKAGE_THERM_STATUS : MSR_IA32_THERM_STATUS; - int tjmax, temp, err; + int tjmax, err; tjmax = intel_tcc_get_tjmax(cpu); if (tjmax < 0) @@ -131,9 +132,8 @@ int intel_tcc_get_temp(int cpu, bool pkg) if (!(low & BIT(31))) return -ENODATA; - temp = tjmax - ((low >> 16) & 0x7f); + *temp = tjmax - ((low >> 16) & 0x7f); - /* Do not allow negative CPU temperature */ - return temp >= 0 ? temp : -ENODATA; + return 0; } EXPORT_SYMBOL_NS_GPL(intel_tcc_get_temp, INTEL_TCC); diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c index 11a7f8108bbbf..61c3d450ee605 100644 --- a/drivers/thermal/intel/x86_pkg_temp_thermal.c +++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c @@ -108,11 +108,11 @@ static struct zone_device *pkg_temp_thermal_get_dev(unsigned int cpu) static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp) { struct zone_device *zonedev = thermal_zone_device_priv(tzd); - int val; + int val, ret; - val = intel_tcc_get_temp(zonedev->cpu, true); - if (val < 0) - return val; + ret = intel_tcc_get_temp(zonedev->cpu, &val, true); + if (ret < 0) + return ret; *temp = val * 1000; pr_debug("sys_get_curr_temp %d\n", *temp); diff --git a/drivers/thermal/mediatek/auxadc_thermal.c b/drivers/thermal/mediatek/auxadc_thermal.c index 8b0edb2048443..9ee2e7283435a 100644 --- a/drivers/thermal/mediatek/auxadc_thermal.c +++ b/drivers/thermal/mediatek/auxadc_thermal.c @@ -690,6 +690,9 @@ static const struct mtk_thermal_data mt7986_thermal_data = { .adcpnp = mt7986_adcpnp, .sensor_mux_values = mt7986_mux_values, .version = MTK_THERMAL_V3, + .apmixed_buffer_ctl_reg = APMIXED_SYS_TS_CON1, + .apmixed_buffer_ctl_mask = GENMASK(31, 6) | BIT(3), + .apmixed_buffer_ctl_set = BIT(0), }; static bool mtk_thermal_temp_is_valid(int temp) diff --git a/drivers/thermal/mediatek/lvts_thermal.c b/drivers/thermal/mediatek/lvts_thermal.c index 98d9c80bd4c62..6b9422bd8795d 100644 --- a/drivers/thermal/mediatek/lvts_thermal.c +++ b/drivers/thermal/mediatek/lvts_thermal.c @@ -719,8 +719,10 @@ static int lvts_calibration_read(struct device *dev, struct lvts_domain *lvts_td lvts_td->calib = devm_krealloc(dev, lvts_td->calib, lvts_td->calib_len + len, GFP_KERNEL); - if (!lvts_td->calib) + if (!lvts_td->calib) { + kfree(efuse); return -ENOMEM; + } memcpy(lvts_td->calib + lvts_td->calib_len, efuse, len); @@ -738,7 +740,11 @@ static int lvts_golden_temp_init(struct device *dev, u32 *value, int temp_offset gt = (*value) >> 24; - if (gt && gt < LVTS_GOLDEN_TEMP_MAX) + /* A zero value for gt means that device has invalid efuse data */ + if (!gt) + return -ENODATA; + + if (gt < LVTS_GOLDEN_TEMP_MAX) golden_temp = gt; golden_temp_offset = golden_temp * 500 + temp_offset; @@ -1528,11 +1534,15 @@ static const struct lvts_data mt7988_lvts_ap_data = { static const struct lvts_data mt8192_lvts_mcu_data = { .lvts_ctrl = mt8192_lvts_mcu_data_ctrl, .num_lvts_ctrl = ARRAY_SIZE(mt8192_lvts_mcu_data_ctrl), + .temp_factor = LVTS_COEFF_A_MT8195, + .temp_offset = LVTS_COEFF_B_MT8195, }; static const struct lvts_data mt8192_lvts_ap_data = { .lvts_ctrl = mt8192_lvts_ap_data_ctrl, .num_lvts_ctrl = ARRAY_SIZE(mt8192_lvts_ap_data_ctrl), + .temp_factor = LVTS_COEFF_A_MT8195, + .temp_offset = LVTS_COEFF_B_MT8195, }; static const struct lvts_data mt8195_lvts_mcu_data = { diff --git a/drivers/thermal/qcom/lmh.c b/drivers/thermal/qcom/lmh.c index f6edb12ec0041..5225b3621a56c 100644 --- a/drivers/thermal/qcom/lmh.c +++ b/drivers/thermal/qcom/lmh.c @@ -95,6 +95,9 @@ static int lmh_probe(struct platform_device *pdev) unsigned int enable_alg; u32 node_id; + if (!qcom_scm_is_available()) + return -EPROBE_DEFER; + lmh_data = devm_kzalloc(dev, sizeof(*lmh_data), GFP_KERNEL); if (!lmh_data) return -ENOMEM; diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c index 6d7c16ccb44dc..4edee8d929a75 100644 --- a/drivers/thermal/qcom/tsens.c +++ b/drivers/thermal/qcom/tsens.c @@ -264,7 +264,7 @@ void compute_intercept_slope(struct tsens_priv *priv, u32 *p1, for (i = 0; i < priv->num_sensors; i++) { dev_dbg(priv->dev, "%s: sensor%d - data_point1:%#x data_point2:%#x\n", - __func__, i, p1[i], p2[i]); + __func__, i, p1[i], p2 ? p2[i] : 0); if (!priv->sensor[i].slope) priv->sensor[i].slope = SLOPE_DEFAULT; diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c index ccc2eea7f9f54..404f01cca4dab 100644 --- a/drivers/thermal/qoriq_thermal.c +++ b/drivers/thermal/qoriq_thermal.c @@ -57,6 +57,9 @@ #define REGS_TTRnCR(n) (0xf10 + 4 * (n)) /* Temperature Range n * Control Register */ +#define NUM_TTRCR_V1 4 +#define NUM_TTRCR_MAX 16 + #define REGS_IPBRR(n) (0xbf8 + 4 * (n)) /* IP Block Revision * Register n */ @@ -71,6 +74,7 @@ struct qoriq_sensor { struct qoriq_tmu_data { int ver; + u32 ttrcr[NUM_TTRCR_MAX]; struct regmap *regmap; struct clk *clk; struct qoriq_sensor sensor[SITES_MAX]; @@ -182,17 +186,17 @@ static int qoriq_tmu_calibration(struct device *dev, struct qoriq_tmu_data *data) { int i, val, len; - u32 range[4]; const u32 *calibration; struct device_node *np = dev->of_node; len = of_property_count_u32_elems(np, "fsl,tmu-range"); - if (len < 0 || len > 4) { + if (len < 0 || (data->ver == TMU_VER1 && len > NUM_TTRCR_V1) || + (data->ver > TMU_VER1 && len > NUM_TTRCR_MAX)) { dev_err(dev, "invalid range data.\n"); return len; } - val = of_property_read_u32_array(np, "fsl,tmu-range", range, len); + val = of_property_read_u32_array(np, "fsl,tmu-range", data->ttrcr, len); if (val != 0) { dev_err(dev, "failed to read range data.\n"); return val; @@ -200,7 +204,7 @@ static int qoriq_tmu_calibration(struct device *dev, /* Init temperature range registers */ for (i = 0; i < len; i++) - regmap_write(data->regmap, REGS_TTRnCR(i), range[i]); + regmap_write(data->regmap, REGS_TTRnCR(i), data->ttrcr[i]); calibration = of_get_property(np, "fsl,tmu-calibration", &len); if (calibration == NULL || len % 8) { diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index dfaa6341694a0..e1f4153d8d1b4 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -432,7 +432,6 @@ static void update_temperature(struct thermal_zone_device *tz) trace_thermal_temperature(tz); thermal_genl_sampling_temp(tz->id, temp); - thermal_debug_update_temp(tz); } static void thermal_zone_device_check(struct work_struct *work) @@ -476,6 +475,8 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz, for_each_trip(tz, trip) handle_thermal_trip(tz, trip); + thermal_debug_update_temp(tz); + monitor_thermal_zone(tz); } @@ -898,6 +899,7 @@ __thermal_cooling_device_register(struct device_node *np, { struct thermal_cooling_device *cdev; struct thermal_zone_device *pos = NULL; + unsigned long current_state; int id, ret; if (!ops || !ops->get_max_state || !ops->get_cur_state || @@ -935,6 +937,18 @@ __thermal_cooling_device_register(struct device_node *np, if (ret) goto out_cdev_type; + /* + * The cooling device's current state is only needed for debug + * initialization below, so a failure to get it does not cause + * the entire cooling device initialization to fail. However, + * the debug will not work for the device if its initial state + * cannot be determined and drivers are responsible for ensuring + * that this will not happen. + */ + ret = cdev->ops->get_cur_state(cdev, ¤t_state); + if (ret) + current_state = ULONG_MAX; + thermal_cooling_device_setup_sysfs(cdev); ret = dev_set_name(&cdev->device, "cooling_device%d", cdev->id); @@ -948,6 +962,9 @@ __thermal_cooling_device_register(struct device_node *np, return ERR_PTR(ret); } + if (current_state <= cdev->max_state) + thermal_debug_cdev_add(cdev, current_state); + /* Add 'this' new cdev to the global cdev list */ mutex_lock(&thermal_list_lock); @@ -963,8 +980,6 @@ __thermal_cooling_device_register(struct device_node *np, mutex_unlock(&thermal_list_lock); - thermal_debug_cdev_add(cdev); - return cdev; out_cooling_dev: @@ -1634,6 +1649,12 @@ static int thermal_pm_notify(struct notifier_block *nb, static struct notifier_block thermal_pm_nb = { .notifier_call = thermal_pm_notify, + /* + * Run at the lowest priority to avoid interference between the thermal + * zone resume work items spawned by thermal_pm_notify() and the other + * PM notifiers. + */ + .priority = INT_MIN, }; static int __init thermal_init(void) diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c index c617e8b9f0ddf..403f74d663dce 100644 --- a/drivers/thermal/thermal_debugfs.c +++ b/drivers/thermal/thermal_debugfs.c @@ -139,11 +139,13 @@ struct tz_episode { * we keep track of the current position in the history array. * * @tz_episodes: a list of thermal mitigation episodes + * @tz: thermal zone this object belongs to * @trips_crossed: an array of trip points crossed by id * @nr_trips: the number of trip points currently being crossed */ struct tz_debugfs { struct list_head tz_episodes; + struct thermal_zone_device *tz; int *trips_crossed; int nr_trips; }; @@ -433,6 +435,14 @@ void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, } cdev_dbg->current_state = new_state; + + /* + * Create a record for the new state if it is not there, so its + * duration will be printed by cdev_dt_seq_show() as expected if it + * runs before the next state transition. + */ + thermal_debugfs_cdev_record_get(thermal_dbg, cdev_dbg->durations, new_state); + transition = (old_state << 16) | new_state; /* @@ -458,8 +468,9 @@ void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, * Allocates a cooling device object for debug, initializes the * statistics and create the entries in sysfs. * @cdev: a pointer to a cooling device + * @state: current state of the cooling device */ -void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) +void thermal_debug_cdev_add(struct thermal_cooling_device *cdev, int state) { struct thermal_debugfs *thermal_dbg; struct cdev_debugfs *cdev_dbg; @@ -476,9 +487,16 @@ void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) INIT_LIST_HEAD(&cdev_dbg->durations[i]); } - cdev_dbg->current_state = 0; + cdev_dbg->current_state = state; cdev_dbg->timestamp = ktime_get(); + /* + * Create a record for the initial cooling device state, so its + * duration will be printed by cdev_dt_seq_show() as expected if it + * runs before the first state transition. + */ + thermal_debugfs_cdev_record_get(thermal_dbg, cdev_dbg->durations, state); + debugfs_create_file("trans_table", 0400, thermal_dbg->d_top, thermal_dbg, &tt_fops); @@ -503,15 +521,23 @@ void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) */ void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev) { - struct thermal_debugfs *thermal_dbg = cdev->debugfs; + struct thermal_debugfs *thermal_dbg; - if (!thermal_dbg) + mutex_lock(&cdev->lock); + + thermal_dbg = cdev->debugfs; + if (!thermal_dbg) { + mutex_unlock(&cdev->lock); return; + } + + cdev->debugfs = NULL; + + mutex_unlock(&cdev->lock); mutex_lock(&thermal_dbg->lock); thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg); - cdev->debugfs = NULL; mutex_unlock(&thermal_dbg->lock); @@ -545,7 +571,6 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz, struct tz_episode *tze; struct tz_debugfs *tz_dbg; struct thermal_debugfs *thermal_dbg = tz->debugfs; - int temperature = tz->temperature; int trip_id = thermal_zone_trip_id(tz, trip); ktime_t now = ktime_get(); @@ -614,11 +639,6 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz, tze = list_first_entry(&tz_dbg->tz_episodes, struct tz_episode, node); tze->trip_stats[trip_id].timestamp = now; - tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, temperature); - tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, temperature); - tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg + - (temperature - tze->trip_stats[trip_id].avg) / - tze->trip_stats[trip_id].count; unlock: mutex_unlock(&thermal_dbg->lock); @@ -715,8 +735,7 @@ void thermal_debug_update_temp(struct thermal_zone_device *tz) static void *tze_seq_start(struct seq_file *s, loff_t *pos) { - struct thermal_zone_device *tz = s->private; - struct thermal_debugfs *thermal_dbg = tz->debugfs; + struct thermal_debugfs *thermal_dbg = s->private; struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg; mutex_lock(&thermal_dbg->lock); @@ -726,8 +745,7 @@ static void *tze_seq_start(struct seq_file *s, loff_t *pos) static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct thermal_zone_device *tz = s->private; - struct thermal_debugfs *thermal_dbg = tz->debugfs; + struct thermal_debugfs *thermal_dbg = s->private; struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg; return seq_list_next(v, &tz_dbg->tz_episodes, pos); @@ -735,15 +753,15 @@ static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos) static void tze_seq_stop(struct seq_file *s, void *v) { - struct thermal_zone_device *tz = s->private; - struct thermal_debugfs *thermal_dbg = tz->debugfs; + struct thermal_debugfs *thermal_dbg = s->private; mutex_unlock(&thermal_dbg->lock); } static int tze_seq_show(struct seq_file *s, void *v) { - struct thermal_zone_device *tz = s->private; + struct thermal_debugfs *thermal_dbg = s->private; + struct thermal_zone_device *tz = thermal_dbg->tz_dbg.tz; struct thermal_trip *trip; struct tz_episode *tze; const char *type; @@ -809,6 +827,8 @@ void thermal_debug_tz_add(struct thermal_zone_device *tz) tz_dbg = &thermal_dbg->tz_dbg; + tz_dbg->tz = tz; + tz_dbg->trips_crossed = kzalloc(sizeof(int) * tz->num_trips, GFP_KERNEL); if (!tz_dbg->trips_crossed) { thermal_debugfs_remove_id(thermal_dbg); @@ -817,23 +837,44 @@ void thermal_debug_tz_add(struct thermal_zone_device *tz) INIT_LIST_HEAD(&tz_dbg->tz_episodes); - debugfs_create_file("mitigations", 0400, thermal_dbg->d_top, tz, &tze_fops); + debugfs_create_file("mitigations", 0400, thermal_dbg->d_top, + thermal_dbg, &tze_fops); tz->debugfs = thermal_dbg; } void thermal_debug_tz_remove(struct thermal_zone_device *tz) { - struct thermal_debugfs *thermal_dbg = tz->debugfs; + struct thermal_debugfs *thermal_dbg; + struct tz_episode *tze, *tmp; + struct tz_debugfs *tz_dbg; + int *trips_crossed; - if (!thermal_dbg) + mutex_lock(&tz->lock); + + thermal_dbg = tz->debugfs; + if (!thermal_dbg) { + mutex_unlock(&tz->lock); return; + } + + tz->debugfs = NULL; + + mutex_unlock(&tz->lock); + + tz_dbg = &thermal_dbg->tz_dbg; mutex_lock(&thermal_dbg->lock); - tz->debugfs = NULL; + trips_crossed = tz_dbg->trips_crossed; + + list_for_each_entry_safe(tze, tmp, &tz_dbg->tz_episodes, node) { + list_del(&tze->node); + kfree(tze); + } mutex_unlock(&thermal_dbg->lock); thermal_debugfs_remove_id(thermal_dbg); + kfree(trips_crossed); } diff --git a/drivers/thermal/thermal_debugfs.h b/drivers/thermal/thermal_debugfs.h index 155b9af5fe870..c28bd4c114124 100644 --- a/drivers/thermal/thermal_debugfs.h +++ b/drivers/thermal/thermal_debugfs.h @@ -2,7 +2,7 @@ #ifdef CONFIG_THERMAL_DEBUGFS void thermal_debug_init(void); -void thermal_debug_cdev_add(struct thermal_cooling_device *cdev); +void thermal_debug_cdev_add(struct thermal_cooling_device *cdev, int state); void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev); void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, int state); void thermal_debug_tz_add(struct thermal_zone_device *tz); @@ -14,7 +14,7 @@ void thermal_debug_tz_trip_down(struct thermal_zone_device *tz, void thermal_debug_update_temp(struct thermal_zone_device *tz); #else static inline void thermal_debug_init(void) {} -static inline void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) {} +static inline void thermal_debug_cdev_add(struct thermal_cooling_device *cdev, int state) {} static inline void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev) {} static inline void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, int state) {} diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index 4d6c22e0ed85b..61bbd42aa2cb4 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -225,14 +225,18 @@ static int thermal_of_monitor_init(struct device_node *np, int *delay, int *pdel int ret; ret = of_property_read_u32(np, "polling-delay-passive", pdelay); - if (ret < 0) { - pr_err("%pOFn: missing polling-delay-passive property\n", np); + if (ret == -EINVAL) { + *pdelay = 0; + } else if (ret < 0) { + pr_err("%pOFn: Couldn't get polling-delay-passive: %d\n", np, ret); return ret; } ret = of_property_read_u32(np, "polling-delay", delay); - if (ret < 0) { - pr_err("%pOFn: missing polling-delay property\n", np); + if (ret == -EINVAL) { + *delay = 0; + } else if (ret < 0) { + pr_err("%pOFn: Couldn't get polling-delay: %d\n", np, ret); return ret; } diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c index c875a26d5adf4..e6dcb8117cb07 100644 --- a/drivers/thermal/thermal_trip.c +++ b/drivers/thermal/thermal_trip.c @@ -65,7 +65,6 @@ void __thermal_zone_set_trips(struct thermal_zone_device *tz) { const struct thermal_trip *trip; int low = -INT_MAX, high = INT_MAX; - bool same_trip = false; int ret; lockdep_assert_held(&tz->lock); @@ -74,36 +73,22 @@ void __thermal_zone_set_trips(struct thermal_zone_device *tz) return; for_each_trip(tz, trip) { - bool low_set = false; int trip_low; trip_low = trip->temperature - trip->hysteresis; - if (trip_low < tz->temperature && trip_low > low) { + if (trip_low < tz->temperature && trip_low > low) low = trip_low; - low_set = true; - same_trip = false; - } if (trip->temperature > tz->temperature && - trip->temperature < high) { + trip->temperature < high) high = trip->temperature; - same_trip = low_set; - } } /* No need to change trip points */ if (tz->prev_low_trip == low && tz->prev_high_trip == high) return; - /* - * If "high" and "low" are the same, skip the change unless this is the - * first time. - */ - if (same_trip && (tz->prev_low_trip != -INT_MAX || - tz->prev_high_trip != INT_MAX)) - return; - tz->prev_low_trip = low; tz->prev_high_trip = high; diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index e324cd8997193..0754fe76edde4 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -943,8 +943,9 @@ static void margining_port_init(struct tb_port *port) debugfs_create_file("run", 0600, dir, port, &margining_run_fops); debugfs_create_file("results", 0600, dir, port, &margining_results_fops); debugfs_create_file("test", 0600, dir, port, &margining_test_fops); - if (independent_voltage_margins(usb4) || - (supports_time(usb4) && independent_time_margins(usb4))) + if (independent_voltage_margins(usb4) == USB4_MARGIN_CAP_0_VOLTAGE_HL || + (supports_time(usb4) && + independent_time_margins(usb4) == USB4_MARGIN_CAP_1_TIME_LR)) debugfs_create_file("margin", 0600, dir, port, &margining_margin_fops); } diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c index 9fb1a64f3300b..df0d845e069ac 100644 --- a/drivers/thunderbolt/domain.c +++ b/drivers/thunderbolt/domain.c @@ -423,6 +423,7 @@ struct tb *tb_domain_alloc(struct tb_nhi *nhi, int timeout_msec, size_t privsize /** * tb_domain_add() - Add domain to the system * @tb: Domain to add + * @reset: Issue reset to the host router * * Starts the domain and adds it to the system. Hotplugging devices will * work after this has been returned successfully. In order to remove @@ -431,7 +432,7 @@ struct tb *tb_domain_alloc(struct tb_nhi *nhi, int timeout_msec, size_t privsize * * Return: %0 in case of success and negative errno in case of error */ -int tb_domain_add(struct tb *tb) +int tb_domain_add(struct tb *tb, bool reset) { int ret; @@ -460,7 +461,7 @@ int tb_domain_add(struct tb *tb) /* Start the domain */ if (tb->cm_ops->start) { - ret = tb->cm_ops->start(tb); + ret = tb->cm_ops->start(tb, reset); if (ret) goto err_domain_del; } diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 56790d50f9e32..baf10d099c778 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -2144,7 +2144,7 @@ static int icm_runtime_resume(struct tb *tb) return 0; } -static int icm_start(struct tb *tb) +static int icm_start(struct tb *tb, bool not_used) { struct icm *icm = tb_priv(tb); int ret; diff --git a/drivers/thunderbolt/lc.c b/drivers/thunderbolt/lc.c index 633970fbe9b05..63cb4b6afb718 100644 --- a/drivers/thunderbolt/lc.c +++ b/drivers/thunderbolt/lc.c @@ -6,6 +6,8 @@ * Author: Mika Westerberg */ +#include + #include "tb.h" /** @@ -45,6 +47,49 @@ static int find_port_lc_cap(struct tb_port *port) return sw->cap_lc + start + phys * size; } +/** + * tb_lc_reset_port() - Trigger downstream port reset through LC + * @port: Port that is reset + * + * Triggers downstream port reset through link controller registers. + * Returns %0 in case of success negative errno otherwise. Only supports + * non-USB4 routers with link controller (that's Thunderbolt 2 and + * Thunderbolt 3). + */ +int tb_lc_reset_port(struct tb_port *port) +{ + struct tb_switch *sw = port->sw; + int cap, ret; + u32 mode; + + if (sw->generation < 2) + return -EINVAL; + + cap = find_port_lc_cap(port); + if (cap < 0) + return cap; + + ret = tb_sw_read(sw, &mode, TB_CFG_SWITCH, cap + TB_LC_PORT_MODE, 1); + if (ret) + return ret; + + mode |= TB_LC_PORT_MODE_DPR; + + ret = tb_sw_write(sw, &mode, TB_CFG_SWITCH, cap + TB_LC_PORT_MODE, 1); + if (ret) + return ret; + + fsleep(10000); + + ret = tb_sw_read(sw, &mode, TB_CFG_SWITCH, cap + TB_LC_PORT_MODE, 1); + if (ret) + return ret; + + mode &= ~TB_LC_PORT_MODE_DPR; + + return tb_sw_write(sw, &mode, TB_CFG_SWITCH, cap + TB_LC_PORT_MODE, 1); +} + static int tb_lc_set_port_configured(struct tb_port *port, bool configured) { bool upstream = tb_is_upstream_port(port); diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index fb4f46e51753a..b22023fae60de 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -1221,7 +1221,7 @@ static void nhi_check_iommu(struct tb_nhi *nhi) str_enabled_disabled(port_ok)); } -static void nhi_reset(struct tb_nhi *nhi) +static bool nhi_reset(struct tb_nhi *nhi) { ktime_t timeout; u32 val; @@ -1229,11 +1229,11 @@ static void nhi_reset(struct tb_nhi *nhi) val = ioread32(nhi->iobase + REG_CAPS); /* Reset only v2 and later routers */ if (FIELD_GET(REG_CAPS_VERSION_MASK, val) < REG_CAPS_VERSION_2) - return; + return false; if (!host_reset) { dev_dbg(&nhi->pdev->dev, "skipping host router reset\n"); - return; + return false; } iowrite32(REG_RESET_HRR, nhi->iobase + REG_RESET); @@ -1244,12 +1244,14 @@ static void nhi_reset(struct tb_nhi *nhi) val = ioread32(nhi->iobase + REG_RESET); if (!(val & REG_RESET_HRR)) { dev_warn(&nhi->pdev->dev, "host router reset successful\n"); - return; + return true; } usleep_range(10, 20); } while (ktime_before(ktime_get(), timeout)); dev_warn(&nhi->pdev->dev, "timeout resetting host router\n"); + + return false; } static int nhi_init_msi(struct tb_nhi *nhi) @@ -1331,6 +1333,7 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct device *dev = &pdev->dev; struct tb_nhi *nhi; struct tb *tb; + bool reset; int res; if (!nhi_imr_valid(pdev)) @@ -1365,7 +1368,11 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id) nhi_check_quirks(nhi); nhi_check_iommu(nhi); - nhi_reset(nhi); + /* + * Only USB4 v2 hosts support host reset so if we already did + * that then don't do it again when the domain is initialized. + */ + reset = nhi_reset(nhi) ? false : host_reset; res = nhi_init_msi(nhi); if (res) @@ -1392,7 +1399,7 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_dbg(dev, "NHI initialized, starting thunderbolt\n"); - res = tb_domain_add(tb); + res = tb_domain_add(tb, reset); if (res) { /* * At this point the RX/TX rings might already have been diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index 091a81bbdbdc9..f760e54cd9bd1 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -446,6 +446,19 @@ static int __tb_path_deactivate_hop(struct tb_port *port, int hop_index, return -ETIMEDOUT; } +/** + * tb_path_deactivate_hop() - Deactivate one path in path config space + * @port: Lane or protocol adapter + * @hop_index: HopID of the path to be cleared + * + * This deactivates or clears a single path config space entry at + * @hop_index. Returns %0 in success and negative errno otherwise. + */ +int tb_path_deactivate_hop(struct tb_port *port, int hop_index) +{ + return __tb_path_deactivate_hop(port, hop_index, true); +} + static void __tb_path_deactivate_hops(struct tb_path *path, int first_hop) { int i, res; diff --git a/drivers/thunderbolt/quirks.c b/drivers/thunderbolt/quirks.c index e6bfa63b40aee..e81de9c30eac9 100644 --- a/drivers/thunderbolt/quirks.c +++ b/drivers/thunderbolt/quirks.c @@ -43,6 +43,12 @@ static void quirk_usb3_maximum_bandwidth(struct tb_switch *sw) } } +static void quirk_block_rpm_in_redrive(struct tb_switch *sw) +{ + sw->quirks |= QUIRK_KEEP_POWER_IN_DP_REDRIVE; + tb_sw_dbg(sw, "preventing runtime PM in DP redrive mode\n"); +} + struct tb_quirk { u16 hw_vendor_id; u16 hw_device_id; @@ -86,6 +92,14 @@ static const struct tb_quirk tb_quirks[] = { quirk_usb3_maximum_bandwidth }, { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HUB_40G_BRIDGE, 0x0000, 0x0000, quirk_usb3_maximum_bandwidth }, + /* + * Block Runtime PM in DP redrive mode for Intel Barlow Ridge host + * controllers. + */ + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI, 0x0000, 0x0000, + quirk_block_rpm_in_redrive }, + { 0x8087, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI, 0x0000, 0x0000, + quirk_block_rpm_in_redrive }, /* * CLx is not supported on AMD USB4 Yellow Carp and Pink Sardine platforms. */ diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index fad40c4bc7103..7b086923cec6b 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -676,6 +676,13 @@ int tb_port_disable(struct tb_port *port) return __tb_port_enable(port, false); } +static int tb_port_reset(struct tb_port *port) +{ + if (tb_switch_is_usb4(port->sw)) + return port->cap_usb4 ? usb4_port_reset(port) : 0; + return tb_lc_reset_port(port); +} + /* * tb_init_port() - initialize a port * @@ -1534,29 +1541,124 @@ static void tb_dump_switch(const struct tb *tb, const struct tb_switch *sw) regs->__unknown1, regs->__unknown4); } +static int tb_switch_reset_host(struct tb_switch *sw) +{ + if (sw->generation > 1) { + struct tb_port *port; + + tb_switch_for_each_port(sw, port) { + int i, ret; + + /* + * For lane adapters we issue downstream port + * reset and clear up path config spaces. + * + * For protocol adapters we disable the path and + * clear path config space one by one (from 8 to + * Max Input HopID of the adapter). + */ + if (tb_port_is_null(port) && !tb_is_upstream_port(port)) { + ret = tb_port_reset(port); + if (ret) + return ret; + } else if (tb_port_is_usb3_down(port) || + tb_port_is_usb3_up(port)) { + tb_usb3_port_enable(port, false); + } else if (tb_port_is_dpin(port) || + tb_port_is_dpout(port)) { + tb_dp_port_enable(port, false); + } else if (tb_port_is_pcie_down(port) || + tb_port_is_pcie_up(port)) { + tb_pci_port_enable(port, false); + } else { + continue; + } + + /* Cleanup path config space of protocol adapter */ + for (i = TB_PATH_MIN_HOPID; + i <= port->config.max_in_hop_id; i++) { + ret = tb_path_deactivate_hop(port, i); + if (ret) + return ret; + } + } + } else { + struct tb_cfg_result res; + + /* Thunderbolt 1 uses the "reset" config space packet */ + res.err = tb_sw_write(sw, ((u32 *) &sw->config) + 2, + TB_CFG_SWITCH, 2, 2); + if (res.err) + return res.err; + res = tb_cfg_reset(sw->tb->ctl, tb_route(sw)); + if (res.err > 0) + return -EIO; + else if (res.err < 0) + return res.err; + } + + return 0; +} + +static int tb_switch_reset_device(struct tb_switch *sw) +{ + return tb_port_reset(tb_switch_downstream_port(sw)); +} + +static bool tb_switch_enumerated(struct tb_switch *sw) +{ + u32 val; + int ret; + + /* + * Read directly from the hardware because we use this also + * during system sleep where sw->config.enabled is already set + * by us. + */ + ret = tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_3, 1); + if (ret) + return false; + + return !!(val & ROUTER_CS_3_V); +} + /** - * tb_switch_reset() - reconfigure route, enable and send TB_CFG_PKG_RESET - * @sw: Switch to reset + * tb_switch_reset() - Perform reset to the router + * @sw: Router to reset * - * Return: Returns 0 on success or an error code on failure. + * Issues reset to the router @sw. Can be used for any router. For host + * routers, resets all the downstream ports and cleans up path config + * spaces accordingly. For device routers issues downstream port reset + * through the parent router, so as side effect there will be unplug + * soon after this is finished. + * + * If the router is not enumerated does nothing. + * + * Returns %0 on success or negative errno in case of failure. */ int tb_switch_reset(struct tb_switch *sw) { - struct tb_cfg_result res; + int ret; - if (sw->generation > 1) + /* + * We cannot access the port config spaces unless the router is + * already enumerated. If the router is not enumerated it is + * equal to being reset so we can skip that here. + */ + if (!tb_switch_enumerated(sw)) return 0; - tb_sw_dbg(sw, "resetting switch\n"); + tb_sw_dbg(sw, "resetting\n"); + + if (tb_route(sw)) + ret = tb_switch_reset_device(sw); + else + ret = tb_switch_reset_host(sw); - res.err = tb_sw_write(sw, ((u32 *) &sw->config) + 2, - TB_CFG_SWITCH, 2, 2); - if (res.err) - return res.err; - res = tb_cfg_reset(sw->tb->ctl, tb_route(sw)); - if (res.err > 0) - return -EIO; - return res.err; + if (ret) + tb_sw_warn(sw, "failed to reset\n"); + + return ret; } /** @@ -3078,22 +3180,29 @@ void tb_switch_unconfigure_link(struct tb_switch *sw) { struct tb_port *up, *down; - if (sw->is_unplugged) - return; if (!tb_route(sw) || tb_switch_is_icm(sw)) return; + /* + * Unconfigure downstream port so that wake-on-connect can be + * configured after router unplug. No need to unconfigure upstream port + * since its router is unplugged. + */ up = tb_upstream_port(sw); - if (tb_switch_is_usb4(up->sw)) - usb4_port_unconfigure(up); - else - tb_lc_unconfigure_port(up); - down = up->remote; if (tb_switch_is_usb4(down->sw)) usb4_port_unconfigure(down); else tb_lc_unconfigure_port(down); + + if (sw->is_unplugged) + return; + + up = tb_upstream_port(sw); + if (tb_switch_is_usb4(up->sw)) + usb4_port_unconfigure(up); + else + tb_lc_unconfigure_port(up); } static void tb_switch_credits_init(struct tb_switch *sw) @@ -3339,7 +3448,26 @@ static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags) return tb_lc_set_wake(sw, flags); } -int tb_switch_resume(struct tb_switch *sw) +static void tb_switch_check_wakes(struct tb_switch *sw) +{ + if (device_may_wakeup(&sw->dev)) { + if (tb_switch_is_usb4(sw)) + usb4_switch_check_wakes(sw); + } +} + +/** + * tb_switch_resume() - Resume a switch after sleep + * @sw: Switch to resume + * @runtime: Is this resume from runtime suspend or system sleep + * + * Resumes and re-enumerates router (and all its children), if still plugged + * after suspend. Don't enumerate device router whose UID was changed during + * suspend. If this is resume from system sleep, notifies PM core about the + * wakes occurred during suspend. Disables all wakes, except USB4 wake of + * upstream port for USB4 routers that shall be always enabled. + */ +int tb_switch_resume(struct tb_switch *sw, bool runtime) { struct tb_port *port; int err; @@ -3388,6 +3516,9 @@ int tb_switch_resume(struct tb_switch *sw) if (err) return err; + if (!runtime) + tb_switch_check_wakes(sw); + /* Disable wakes */ tb_switch_set_wake(sw, 0); @@ -3417,7 +3548,8 @@ int tb_switch_resume(struct tb_switch *sw) */ if (tb_port_unlock(port)) tb_port_warn(port, "failed to unlock port\n"); - if (port->remote && tb_switch_resume(port->remote->sw)) { + if (port->remote && + tb_switch_resume(port->remote->sw, runtime)) { tb_port_warn(port, "lost during suspend, disconnecting\n"); tb_sw_set_unplugged(port->remote->sw); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 846d2813bb1a5..525f515e8b48b 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -1717,6 +1717,12 @@ static struct tb_port *tb_find_dp_out(struct tb *tb, struct tb_port *in) continue; } + /* Needs to be on different routers */ + if (in->sw == port->sw) { + tb_port_dbg(port, "skipping DP OUT on same router\n"); + continue; + } + tb_port_dbg(port, "DP OUT available\n"); /* @@ -1887,6 +1893,49 @@ static void tb_tunnel_dp(struct tb *tb) ; } +static void tb_enter_redrive(struct tb_port *port) +{ + struct tb_switch *sw = port->sw; + + if (!(sw->quirks & QUIRK_KEEP_POWER_IN_DP_REDRIVE)) + return; + + /* + * If we get hot-unplug for the DP IN port of the host router + * and the DP resource is not available anymore it means there + * is a monitor connected directly to the Type-C port and we are + * in "redrive" mode. For this to work we cannot enter RTD3 so + * we bump up the runtime PM reference count here. + */ + if (!tb_port_is_dpin(port)) + return; + if (tb_route(sw)) + return; + if (!tb_switch_query_dp_resource(sw, port)) { + port->redrive = true; + pm_runtime_get(&sw->dev); + tb_port_dbg(port, "enter redrive mode, keeping powered\n"); + } +} + +static void tb_exit_redrive(struct tb_port *port) +{ + struct tb_switch *sw = port->sw; + + if (!(sw->quirks & QUIRK_KEEP_POWER_IN_DP_REDRIVE)) + return; + + if (!tb_port_is_dpin(port)) + return; + if (tb_route(sw)) + return; + if (port->redrive && tb_switch_query_dp_resource(sw, port)) { + port->redrive = false; + pm_runtime_put(&sw->dev); + tb_port_dbg(port, "exit redrive mode\n"); + } +} + static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port) { struct tb_port *in, *out; @@ -1903,7 +1952,10 @@ static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port) } tunnel = tb_find_tunnel(tb, TB_TUNNEL_DP, in, out); - tb_deactivate_and_free_tunnel(tunnel); + if (tunnel) + tb_deactivate_and_free_tunnel(tunnel); + else + tb_enter_redrive(port); list_del_init(&port->list); /* @@ -1930,6 +1982,7 @@ static void tb_dp_resource_available(struct tb *tb, struct tb_port *port) tb_port_dbg(port, "DP %s resource available after hotplug\n", tb_port_is_dpin(port) ? "IN" : "OUT"); list_add_tail(&port->list, &tcm->dp_resources); + tb_exit_redrive(port); /* Look for suitable DP IN <-> DP OUT pairs now */ tb_tunnel_dp(tb); @@ -2581,7 +2634,7 @@ static int tb_scan_finalize_switch(struct device *dev, void *data) return 0; } -static int tb_start(struct tb *tb) +static int tb_start(struct tb *tb, bool reset) { struct tb_cm *tcm = tb_priv(tb); int ret; @@ -2622,12 +2675,24 @@ static int tb_start(struct tb *tb) tb_switch_tmu_configure(tb->root_switch, TB_SWITCH_TMU_MODE_LOWRES); /* Enable TMU if it is off */ tb_switch_tmu_enable(tb->root_switch); - /* Full scan to discover devices added before the driver was loaded. */ - tb_scan_switch(tb->root_switch); - /* Find out tunnels created by the boot firmware */ - tb_discover_tunnels(tb); - /* Add DP resources from the DP tunnels created by the boot firmware */ - tb_discover_dp_resources(tb); + + /* + * Boot firmware might have created tunnels of its own. Since we + * cannot be sure they are usable for us, tear them down and + * reset the ports to handle it as new hotplug for USB4 v1 + * routers (for USB4 v2 and beyond we already do host reset). + */ + if (reset && usb4_switch_version(tb->root_switch) == 1) { + tb_switch_reset(tb->root_switch); + } else { + /* Full scan to discover devices added before the driver was loaded. */ + tb_scan_switch(tb->root_switch); + /* Find out tunnels created by the boot firmware */ + tb_discover_tunnels(tb); + /* Add DP resources from the DP tunnels created by the boot firmware */ + tb_discover_dp_resources(tb); + } + /* * If the boot firmware did not create USB 3.x tunnels create them * now for the whole topology. @@ -2698,10 +2763,14 @@ static int tb_resume_noirq(struct tb *tb) tb_dbg(tb, "resuming...\n"); - /* remove any pci devices the firmware might have setup */ - tb_switch_reset(tb->root_switch); + /* + * For non-USB4 hosts (Apple systems) remove any PCIe devices + * the firmware might have setup. + */ + if (!tb_switch_is_usb4(tb->root_switch)) + tb_switch_reset(tb->root_switch); - tb_switch_resume(tb->root_switch); + tb_switch_resume(tb->root_switch, false); tb_free_invalid_tunnels(tb); tb_free_unplugged_children(tb->root_switch); tb_restore_children(tb->root_switch); @@ -2827,7 +2896,7 @@ static int tb_runtime_resume(struct tb *tb) struct tb_tunnel *tunnel, *n; mutex_lock(&tb->lock); - tb_switch_resume(tb->root_switch); + tb_switch_resume(tb->root_switch, true); tb_free_invalid_tunnels(tb); tb_restore_children(tb->root_switch); list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 997c5a5369052..7706f8e08c8d6 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -23,6 +23,8 @@ #define QUIRK_FORCE_POWER_LINK_CONTROLLER BIT(0) /* Disable CLx if not supported */ #define QUIRK_NO_CLX BIT(1) +/* Need to keep power on while USB4 port is in redrive mode */ +#define QUIRK_KEEP_POWER_IN_DP_REDRIVE BIT(2) /** * struct tb_nvm - Structure holding NVM information @@ -258,6 +260,7 @@ struct tb_bandwidth_group { * @group_list: The adapter is linked to the group's list of ports through this * @max_bw: Maximum possible bandwidth through this adapter if set to * non-zero. + * @redrive: For DP IN, if true the adapter is in redrive mode. * * In USB4 terminology this structure represents an adapter (protocol or * lane adapter). @@ -286,6 +289,7 @@ struct tb_port { struct tb_bandwidth_group *group; struct list_head group_list; unsigned int max_bw; + bool redrive; }; /** @@ -483,7 +487,7 @@ struct tb_path { */ struct tb_cm_ops { int (*driver_ready)(struct tb *tb); - int (*start)(struct tb *tb); + int (*start)(struct tb *tb, bool reset); void (*stop)(struct tb *tb); int (*suspend_noirq)(struct tb *tb); int (*resume_noirq)(struct tb *tb); @@ -746,7 +750,7 @@ int tb_xdomain_init(void); void tb_xdomain_exit(void); struct tb *tb_domain_alloc(struct tb_nhi *nhi, int timeout_msec, size_t privsize); -int tb_domain_add(struct tb *tb); +int tb_domain_add(struct tb *tb, bool reset); void tb_domain_remove(struct tb *tb); int tb_domain_suspend_noirq(struct tb *tb); int tb_domain_resume_noirq(struct tb *tb); @@ -813,7 +817,7 @@ int tb_switch_configuration_valid(struct tb_switch *sw); int tb_switch_add(struct tb_switch *sw); void tb_switch_remove(struct tb_switch *sw); void tb_switch_suspend(struct tb_switch *sw, bool runtime); -int tb_switch_resume(struct tb_switch *sw); +int tb_switch_resume(struct tb_switch *sw, bool runtime); int tb_switch_reset(struct tb_switch *sw); int tb_switch_wait_for_bit(struct tb_switch *sw, u32 offset, u32 bit, u32 value, int timeout_msec); @@ -1150,6 +1154,7 @@ struct tb_path *tb_path_alloc(struct tb *tb, struct tb_port *src, int src_hopid, void tb_path_free(struct tb_path *path); int tb_path_activate(struct tb_path *path); void tb_path_deactivate(struct tb_path *path); +int tb_path_deactivate_hop(struct tb_port *port, int hop_index); bool tb_path_is_invalid(struct tb_path *path); bool tb_path_port_on_path(const struct tb_path *path, const struct tb_port *port); @@ -1169,6 +1174,7 @@ int tb_drom_read(struct tb_switch *sw); int tb_drom_read_uid_only(struct tb_switch *sw, u64 *uid); int tb_lc_read_uuid(struct tb_switch *sw, u32 *uuid); +int tb_lc_reset_port(struct tb_port *port); int tb_lc_configure_port(struct tb_port *port); void tb_lc_unconfigure_port(struct tb_port *port); int tb_lc_configure_xdomain(struct tb_port *port); @@ -1272,6 +1278,7 @@ static inline bool tb_switch_is_usb4(const struct tb_switch *sw) return usb4_switch_version(sw) > 0; } +void usb4_switch_check_wakes(struct tb_switch *sw); int usb4_switch_setup(struct tb_switch *sw); int usb4_switch_configuration_valid(struct tb_switch *sw); int usb4_switch_read_uid(struct tb_switch *sw, u64 *uid); @@ -1301,6 +1308,7 @@ void usb4_switch_remove_ports(struct tb_switch *sw); int usb4_port_unlock(struct tb_port *port); int usb4_port_hotplug_enable(struct tb_port *port); +int usb4_port_reset(struct tb_port *port); int usb4_port_configure(struct tb_port *port); void usb4_port_unconfigure(struct tb_port *port); int usb4_port_configure_xdomain(struct tb_port *port, struct tb_xdomain *xd); diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index 6f798f6a2b848..4e43b47f9f119 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -194,6 +194,8 @@ struct tb_regs_switch_header { #define USB4_VERSION_MAJOR_MASK GENMASK(7, 5) #define ROUTER_CS_1 0x01 +#define ROUTER_CS_3 0x03 +#define ROUTER_CS_3_V BIT(31) #define ROUTER_CS_4 0x04 /* Used with the router cmuv field */ #define ROUTER_CS_4_CMUV_V1 0x10 @@ -389,6 +391,7 @@ struct tb_regs_port_header { #define PORT_CS_18_CSA BIT(22) #define PORT_CS_18_TIP BIT(24) #define PORT_CS_19 0x13 +#define PORT_CS_19_DPR BIT(0) #define PORT_CS_19_PC BIT(3) #define PORT_CS_19_PID BIT(4) #define PORT_CS_19_WOC BIT(16) @@ -584,6 +587,9 @@ struct tb_regs_hop { #define TB_LC_POWER 0x740 /* Link controller registers */ +#define TB_LC_PORT_MODE 0x26 +#define TB_LC_PORT_MODE_DPR BIT(0) + #define TB_LC_CS_42 0x2a #define TB_LC_CS_42_USB_PLUGGED BIT(31) diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 6fffb2c82d3d1..4f09216b70f90 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -1196,17 +1196,13 @@ static int tb_dp_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up, /* * Then see if the DPRX negotiation is ready and if yes * return that bandwidth (it may be smaller than the - * reduced one). Otherwise return the remote (possibly - * reduced) caps. + * reduced one). According to VESA spec, the DPRX + * negotiation shall compete in 5 seconds after tunnel + * established. We give it 100ms extra just in case. */ - ret = tb_dp_wait_dprx(tunnel, 150); - if (ret) { - if (ret == -ETIMEDOUT) - ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP, - &rate, &lanes); - if (ret) - return ret; - } + ret = tb_dp_wait_dprx(tunnel, 5100); + if (ret) + return ret; ret = tb_dp_read_cap(tunnel, DP_COMMON_CAP, &rate, &lanes); if (ret) return ret; diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 1515eff8cc3e2..a74c9ea67bf54 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -155,7 +155,13 @@ static inline int usb4_switch_op_data(struct tb_switch *sw, u16 opcode, tx_dwords, rx_data, rx_dwords); } -static void usb4_switch_check_wakes(struct tb_switch *sw) +/** + * usb4_switch_check_wakes() - Check for wakes and notify PM core about them + * @sw: Router whose wakes to check + * + * Checks wakes occurred during suspend and notify the PM core about them. + */ +void usb4_switch_check_wakes(struct tb_switch *sw) { bool wakeup_usb4 = false; struct usb4_port *usb4; @@ -163,9 +169,6 @@ static void usb4_switch_check_wakes(struct tb_switch *sw) bool wakeup = false; u32 val; - if (!device_may_wakeup(&sw->dev)) - return; - if (tb_route(sw)) { if (tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_6, 1)) return; @@ -244,8 +247,6 @@ int usb4_switch_setup(struct tb_switch *sw) u32 val = 0; int ret; - usb4_switch_check_wakes(sw); - if (!tb_route(sw)) return 0; @@ -1113,6 +1114,45 @@ int usb4_port_hotplug_enable(struct tb_port *port) return tb_port_write(port, &val, TB_CFG_PORT, ADP_CS_5, 1); } +/** + * usb4_port_reset() - Issue downstream port reset + * @port: USB4 port to reset + * + * Issues downstream port reset to @port. + */ +int usb4_port_reset(struct tb_port *port) +{ + int ret; + u32 val; + + if (!port->cap_usb4) + return -EINVAL; + + ret = tb_port_read(port, &val, TB_CFG_PORT, + port->cap_usb4 + PORT_CS_19, 1); + if (ret) + return ret; + + val |= PORT_CS_19_DPR; + + ret = tb_port_write(port, &val, TB_CFG_PORT, + port->cap_usb4 + PORT_CS_19, 1); + if (ret) + return ret; + + fsleep(10000); + + ret = tb_port_read(port, &val, TB_CFG_PORT, + port->cap_usb4 + PORT_CS_19, 1); + if (ret) + return ret; + + val &= ~PORT_CS_19_DPR; + + return tb_port_write(port, &val, TB_CFG_PORT, + port->cap_usb4 + PORT_CS_19, 1); +} + static int usb4_port_set_configured(struct tb_port *port, bool configured) { int ret; diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c index aac80b69a069c..afbf7738c7c47 100644 --- a/drivers/tty/mips_ejtag_fdc.c +++ b/drivers/tty/mips_ejtag_fdc.c @@ -309,7 +309,7 @@ static void mips_ejtag_fdc_console_write(struct console *c, const char *s, unsigned int i, buf_len, cpu; bool done_cr = false; char buf[4]; - const char *buf_ptr = buf; + const u8 *buf_ptr = buf; /* Number of bytes of input data encoded up to each byte in buf */ u8 inc[4]; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 4036566febcba..afbf7837b53ec 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -245,16 +245,18 @@ enum gsm_encoding { enum gsm_mux_state { GSM_SEARCH, - GSM_START, - GSM_ADDRESS, - GSM_CONTROL, - GSM_LEN, - GSM_DATA, - GSM_FCS, - GSM_OVERRUN, - GSM_LEN0, - GSM_LEN1, - GSM_SSOF, + GSM0_ADDRESS, + GSM0_CONTROL, + GSM0_LEN0, + GSM0_LEN1, + GSM0_DATA, + GSM0_FCS, + GSM0_SSOF, + GSM1_START, + GSM1_ADDRESS, + GSM1_CONTROL, + GSM1_DATA, + GSM1_OVERRUN, }; /* @@ -2847,6 +2849,30 @@ static void gsm_queue(struct gsm_mux *gsm) return; } +/** + * gsm0_receive_state_check_and_fix - check and correct receive state + * @gsm: gsm data for this ldisc instance + * + * Ensures that the current receive state is valid for basic option mode. + */ + +static void gsm0_receive_state_check_and_fix(struct gsm_mux *gsm) +{ + switch (gsm->state) { + case GSM_SEARCH: + case GSM0_ADDRESS: + case GSM0_CONTROL: + case GSM0_LEN0: + case GSM0_LEN1: + case GSM0_DATA: + case GSM0_FCS: + case GSM0_SSOF: + break; + default: + gsm->state = GSM_SEARCH; + break; + } +} /** * gsm0_receive - perform processing for non-transparency @@ -2860,26 +2886,27 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) { unsigned int len; + gsm0_receive_state_check_and_fix(gsm); switch (gsm->state) { case GSM_SEARCH: /* SOF marker */ if (c == GSM0_SOF) { - gsm->state = GSM_ADDRESS; + gsm->state = GSM0_ADDRESS; gsm->address = 0; gsm->len = 0; gsm->fcs = INIT_FCS; } break; - case GSM_ADDRESS: /* Address EA */ + case GSM0_ADDRESS: /* Address EA */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); if (gsm_read_ea(&gsm->address, c)) - gsm->state = GSM_CONTROL; + gsm->state = GSM0_CONTROL; break; - case GSM_CONTROL: /* Control Byte */ + case GSM0_CONTROL: /* Control Byte */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); gsm->control = c; - gsm->state = GSM_LEN0; + gsm->state = GSM0_LEN0; break; - case GSM_LEN0: /* Length EA */ + case GSM0_LEN0: /* Length EA */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); if (gsm_read_ea(&gsm->len, c)) { if (gsm->len > gsm->mru) { @@ -2889,14 +2916,14 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) } gsm->count = 0; if (!gsm->len) - gsm->state = GSM_FCS; + gsm->state = GSM0_FCS; else - gsm->state = GSM_DATA; + gsm->state = GSM0_DATA; break; } - gsm->state = GSM_LEN1; + gsm->state = GSM0_LEN1; break; - case GSM_LEN1: + case GSM0_LEN1: gsm->fcs = gsm_fcs_add(gsm->fcs, c); len = c; gsm->len |= len << 7; @@ -2907,26 +2934,29 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) } gsm->count = 0; if (!gsm->len) - gsm->state = GSM_FCS; + gsm->state = GSM0_FCS; else - gsm->state = GSM_DATA; + gsm->state = GSM0_DATA; break; - case GSM_DATA: /* Data */ + case GSM0_DATA: /* Data */ gsm->buf[gsm->count++] = c; - if (gsm->count == gsm->len) { + if (gsm->count >= MAX_MRU) { + gsm->bad_size++; + gsm->state = GSM_SEARCH; + } else if (gsm->count >= gsm->len) { /* Calculate final FCS for UI frames over all data */ if ((gsm->control & ~PF) != UIH) { gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, gsm->count); } - gsm->state = GSM_FCS; + gsm->state = GSM0_FCS; } break; - case GSM_FCS: /* FCS follows the packet */ + case GSM0_FCS: /* FCS follows the packet */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); - gsm->state = GSM_SSOF; + gsm->state = GSM0_SSOF; break; - case GSM_SSOF: + case GSM0_SSOF: gsm->state = GSM_SEARCH; if (c == GSM0_SOF) gsm_queue(gsm); @@ -2939,6 +2969,29 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) } } +/** + * gsm1_receive_state_check_and_fix - check and correct receive state + * @gsm: gsm data for this ldisc instance + * + * Ensures that the current receive state is valid for advanced option mode. + */ + +static void gsm1_receive_state_check_and_fix(struct gsm_mux *gsm) +{ + switch (gsm->state) { + case GSM_SEARCH: + case GSM1_START: + case GSM1_ADDRESS: + case GSM1_CONTROL: + case GSM1_DATA: + case GSM1_OVERRUN: + break; + default: + gsm->state = GSM_SEARCH; + break; + } +} + /** * gsm1_receive - perform processing for non-transparency * @gsm: gsm data for this ldisc instance @@ -2949,6 +3002,7 @@ static void gsm0_receive(struct gsm_mux *gsm, u8 c) static void gsm1_receive(struct gsm_mux *gsm, u8 c) { + gsm1_receive_state_check_and_fix(gsm); /* handle XON/XOFF */ if ((c & ISO_IEC_646_MASK) == XON) { gsm->constipated = true; @@ -2961,11 +3015,11 @@ static void gsm1_receive(struct gsm_mux *gsm, u8 c) } if (c == GSM1_SOF) { /* EOF is only valid in frame if we have got to the data state */ - if (gsm->state == GSM_DATA) { + if (gsm->state == GSM1_DATA) { if (gsm->count < 1) { /* Missing FSC */ gsm->malformed++; - gsm->state = GSM_START; + gsm->state = GSM1_START; return; } /* Remove the FCS from data */ @@ -2981,14 +3035,14 @@ static void gsm1_receive(struct gsm_mux *gsm, u8 c) gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->buf[gsm->count]); gsm->len = gsm->count; gsm_queue(gsm); - gsm->state = GSM_START; + gsm->state = GSM1_START; return; } /* Any partial frame was a runt so go back to start */ - if (gsm->state != GSM_START) { + if (gsm->state != GSM1_START) { if (gsm->state != GSM_SEARCH) gsm->malformed++; - gsm->state = GSM_START; + gsm->state = GSM1_START; } /* A SOF in GSM_START means we are still reading idling or framing bytes */ @@ -3009,30 +3063,30 @@ static void gsm1_receive(struct gsm_mux *gsm, u8 c) gsm->escape = false; } switch (gsm->state) { - case GSM_START: /* First byte after SOF */ + case GSM1_START: /* First byte after SOF */ gsm->address = 0; - gsm->state = GSM_ADDRESS; + gsm->state = GSM1_ADDRESS; gsm->fcs = INIT_FCS; fallthrough; - case GSM_ADDRESS: /* Address continuation */ + case GSM1_ADDRESS: /* Address continuation */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); if (gsm_read_ea(&gsm->address, c)) - gsm->state = GSM_CONTROL; + gsm->state = GSM1_CONTROL; break; - case GSM_CONTROL: /* Control Byte */ + case GSM1_CONTROL: /* Control Byte */ gsm->fcs = gsm_fcs_add(gsm->fcs, c); gsm->control = c; gsm->count = 0; - gsm->state = GSM_DATA; + gsm->state = GSM1_DATA; break; - case GSM_DATA: /* Data */ - if (gsm->count > gsm->mru) { /* Allow one for the FCS */ - gsm->state = GSM_OVERRUN; + case GSM1_DATA: /* Data */ + if (gsm->count > gsm->mru || gsm->count > MAX_MRU) { /* Allow one for the FCS */ + gsm->state = GSM1_OVERRUN; gsm->bad_size++; } else gsm->buf[gsm->count++] = c; break; - case GSM_OVERRUN: /* Over-long - eg a dropped SOF */ + case GSM1_OVERRUN: /* Over-long - eg a dropped SOF */ break; default: pr_debug("%s: unhandled state: %d\n", __func__, gsm->state); diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index f252d0b5a434e..5e9ca4376d686 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1619,15 +1619,25 @@ static void __receive_buf(struct tty_struct *tty, const u8 *cp, const u8 *fp, else if (ldata->raw || (L_EXTPROC(tty) && !preops)) n_tty_receive_buf_raw(tty, cp, fp, count); else if (tty->closing && !L_EXTPROC(tty)) { - if (la_count > 0) + if (la_count > 0) { n_tty_receive_buf_closing(tty, cp, fp, la_count, true); - if (count > la_count) - n_tty_receive_buf_closing(tty, cp, fp, count - la_count, false); + cp += la_count; + if (fp) + fp += la_count; + count -= la_count; + } + if (count > 0) + n_tty_receive_buf_closing(tty, cp, fp, count, false); } else { - if (la_count > 0) + if (la_count > 0) { n_tty_receive_buf_standard(tty, cp, fp, la_count, true); - if (count > la_count) - n_tty_receive_buf_standard(tty, cp, fp, count - la_count, false); + cp += la_count; + if (fp) + fp += la_count; + count -= la_count; + } + if (count > 0) + n_tty_receive_buf_standard(tty, cp, fp, count, false); flush_echoes(tty); if (tty->ops->flush_chars) diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index 504c4c0208577..4f8b70f8ce19f 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -676,18 +676,46 @@ static void init_real_clk_rates(struct device *dev, struct brcmuart_priv *priv) clk_set_rate(priv->baud_mux_clk, priv->default_mux_rate); } +static u32 find_quot(struct device *dev, u32 freq, u32 baud, u32 *percent) +{ + u32 quot; + u32 rate; + u64 hires_rate; + u64 hires_baud; + u64 hires_err; + + rate = freq / 16; + quot = DIV_ROUND_CLOSEST(rate, baud); + if (!quot) + return 0; + + /* increase resolution to get xx.xx percent */ + hires_rate = div_u64((u64)rate * 10000, (u64)quot); + hires_baud = (u64)baud * 10000; + + /* get the delta */ + if (hires_rate > hires_baud) + hires_err = (hires_rate - hires_baud); + else + hires_err = (hires_baud - hires_rate); + + *percent = (unsigned long)DIV_ROUND_CLOSEST_ULL(hires_err, baud); + + dev_dbg(dev, "Baud rate: %u, MUX Clk: %u, Error: %u.%u%%\n", + baud, freq, *percent / 100, *percent % 100); + + return quot; +} + static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, u32 baud) { u32 percent; u32 best_percent = UINT_MAX; u32 quot; + u32 freq; u32 best_quot = 1; - u32 rate; - int best_index = -1; - u64 hires_rate; - u64 hires_baud; - u64 hires_err; + u32 best_freq = 0; int rc; int i; int real_baud; @@ -696,44 +724,35 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, if (priv->baud_mux_clk == NULL) return; - /* Find the closest match for specified baud */ - for (i = 0; i < ARRAY_SIZE(priv->real_rates); i++) { - if (priv->real_rates[i] == 0) - continue; - rate = priv->real_rates[i] / 16; - quot = DIV_ROUND_CLOSEST(rate, baud); - if (!quot) - continue; - - /* increase resolution to get xx.xx percent */ - hires_rate = (u64)rate * 10000; - hires_baud = (u64)baud * 10000; - - hires_err = div_u64(hires_rate, (u64)quot); - - /* get the delta */ - if (hires_err > hires_baud) - hires_err = (hires_err - hires_baud); - else - hires_err = (hires_baud - hires_err); - - percent = (unsigned long)DIV_ROUND_CLOSEST_ULL(hires_err, baud); - dev_dbg(up->dev, - "Baud rate: %u, MUX Clk: %u, Error: %u.%u%%\n", - baud, priv->real_rates[i], percent / 100, - percent % 100); - if (percent < best_percent) { - best_percent = percent; - best_index = i; - best_quot = quot; + /* Try default_mux_rate first */ + quot = find_quot(up->dev, priv->default_mux_rate, baud, &percent); + if (quot) { + best_percent = percent; + best_freq = priv->default_mux_rate; + best_quot = quot; + } + /* If more than 1% error, find the closest match for specified baud */ + if (best_percent > 100) { + for (i = 0; i < ARRAY_SIZE(priv->real_rates); i++) { + freq = priv->real_rates[i]; + if (freq == 0 || freq == priv->default_mux_rate) + continue; + quot = find_quot(up->dev, freq, baud, &percent); + if (!quot) + continue; + + if (percent < best_percent) { + best_percent = percent; + best_freq = freq; + best_quot = quot; + } } } - if (best_index == -1) { + if (!best_freq) { dev_err(up->dev, "Error, %d BAUD rate is too fast.\n", baud); return; } - rate = priv->real_rates[best_index]; - rc = clk_set_rate(priv->baud_mux_clk, rate); + rc = clk_set_rate(priv->baud_mux_clk, best_freq); if (rc) dev_err(up->dev, "Error selecting BAUD MUX clock\n"); @@ -742,8 +761,8 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, dev_err(up->dev, "Error, baud: %d has %u.%u%% error\n", baud, percent / 100, percent % 100); - real_baud = rate / 16 / best_quot; - dev_dbg(up->dev, "Selecting BAUD MUX rate: %u\n", rate); + real_baud = best_freq / 16 / best_quot; + dev_dbg(up->dev, "Selecting BAUD MUX rate: %u\n", best_freq); dev_dbg(up->dev, "Requested baud: %u, Actual baud: %u\n", baud, real_baud); @@ -752,7 +771,7 @@ static void set_clock_mux(struct uart_port *up, struct brcmuart_priv *priv, i += (i / 2); priv->char_wait = ns_to_ktime(i); - up->uartclk = rate; + up->uartclk = best_freq; } static void brcmstb_set_termios(struct uart_port *up, diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index c1d43f040c43a..ee6fc7cce1b4c 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -9,7 +9,6 @@ * LCR is written whilst busy. If it is, then a busy detect interrupt is * raised, the LCR needs to be rewritten and the uart status register read. */ -#include #include #include #include @@ -17,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -56,6 +54,35 @@ #define DW_UART_QUIRK_ARMADA_38X BIT(1) #define DW_UART_QUIRK_SKIP_SET_RATE BIT(2) #define DW_UART_QUIRK_IS_DMA_FC BIT(3) +#define DW_UART_QUIRK_APMC0D08 BIT(4) +#define DW_UART_QUIRK_CPR_VALUE BIT(5) + +struct dw8250_platform_data { + u8 usr_reg; + u32 cpr_value; + unsigned int quirks; +}; + +struct dw8250_data { + struct dw8250_port_data data; + const struct dw8250_platform_data *pdata; + + int msr_mask_on; + int msr_mask_off; + struct clk *clk; + struct clk *pclk; + struct notifier_block clk_notifier; + struct work_struct clk_work; + struct reset_control *rst; + + unsigned int skip_autocfg:1; + unsigned int uart_16550_compatible:1; +}; + +static inline struct dw8250_data *to_dw8250_data(struct dw8250_port_data *data) +{ + return container_of(data, struct dw8250_data, data); +} static inline struct dw8250_data *clk_to_dw8250_data(struct notifier_block *nb) { @@ -357,9 +384,9 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios, long rate; int ret; + clk_disable_unprepare(d->clk); rate = clk_round_rate(d->clk, newrate); - if (rate > 0 && p->uartclk != rate) { - clk_disable_unprepare(d->clk); + if (rate > 0) { /* * Note that any clock-notifer worker will block in * serial8250_update_uartclk() until we are done. @@ -367,8 +394,8 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios, ret = clk_set_rate(d->clk, newrate); if (!ret) p->uartclk = rate; - clk_prepare_enable(d->clk); } + clk_prepare_enable(d->clk); dw8250_do_set_termios(p, termios, old); } @@ -445,44 +472,33 @@ static void dw8250_prepare_rx_dma(struct uart_8250_port *p) static void dw8250_quirks(struct uart_port *p, struct dw8250_data *data) { - struct device_node *np = p->dev->of_node; + unsigned int quirks = data->pdata ? data->pdata->quirks : 0; + u32 cpr_value = data->pdata ? data->pdata->cpr_value : 0; - if (np) { - unsigned int quirks = data->pdata->quirks; - int id; + if (quirks & DW_UART_QUIRK_CPR_VALUE) + data->data.cpr_value = cpr_value; - /* get index of serial line, if found in DT aliases */ - id = of_alias_get_id(np, "serial"); - if (id >= 0) - p->line = id; #ifdef CONFIG_64BIT - if (quirks & DW_UART_QUIRK_OCTEON) { - p->serial_in = dw8250_serial_inq; - p->serial_out = dw8250_serial_outq; - p->flags = UPF_SKIP_TEST | UPF_SHARE_IRQ | UPF_FIXED_TYPE; - p->type = PORT_OCTEON; - data->skip_autocfg = true; - } + if (quirks & DW_UART_QUIRK_OCTEON) { + p->serial_in = dw8250_serial_inq; + p->serial_out = dw8250_serial_outq; + p->flags = UPF_SKIP_TEST | UPF_SHARE_IRQ | UPF_FIXED_TYPE; + p->type = PORT_OCTEON; + data->skip_autocfg = true; + } #endif - if (of_device_is_big_endian(np)) { - p->iotype = UPIO_MEM32BE; - p->serial_in = dw8250_serial_in32be; - p->serial_out = dw8250_serial_out32be; - } - - if (quirks & DW_UART_QUIRK_ARMADA_38X) - p->serial_out = dw8250_serial_out38x; - if (quirks & DW_UART_QUIRK_SKIP_SET_RATE) - p->set_termios = dw8250_do_set_termios; - if (quirks & DW_UART_QUIRK_IS_DMA_FC) { - data->data.dma.txconf.device_fc = 1; - data->data.dma.rxconf.device_fc = 1; - data->data.dma.prepare_tx_dma = dw8250_prepare_tx_dma; - data->data.dma.prepare_rx_dma = dw8250_prepare_rx_dma; - } - - } else if (acpi_dev_present("APMC0D08", NULL, -1)) { + if (quirks & DW_UART_QUIRK_ARMADA_38X) + p->serial_out = dw8250_serial_out38x; + if (quirks & DW_UART_QUIRK_SKIP_SET_RATE) + p->set_termios = dw8250_do_set_termios; + if (quirks & DW_UART_QUIRK_IS_DMA_FC) { + data->data.dma.txconf.device_fc = 1; + data->data.dma.rxconf.device_fc = 1; + data->data.dma.prepare_tx_dma = dw8250_prepare_tx_dma; + data->data.dma.prepare_rx_dma = dw8250_prepare_rx_dma; + } + if (quirks & DW_UART_QUIRK_APMC0D08) { p->iotype = UPIO_MEM32; p->regshift = 2; p->serial_in = dw8250_serial_in32; @@ -510,39 +526,21 @@ static int dw8250_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct dw8250_data *data; struct resource *regs; - int irq; int err; - u32 val; regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!regs) return dev_err_probe(dev, -EINVAL, "no registers defined\n"); - irq = platform_get_irq_optional(pdev, 0); - /* no interrupt -> fall back to polling */ - if (irq == -ENXIO) - irq = 0; - if (irq < 0) - return irq; - spin_lock_init(&p->lock); - p->mapbase = regs->start; - p->irq = irq; p->handle_irq = dw8250_handle_irq; p->pm = dw8250_do_pm; p->type = PORT_8250; - p->flags = UPF_SHARE_IRQ | UPF_FIXED_PORT; + p->flags = UPF_FIXED_PORT; p->dev = dev; - p->iotype = UPIO_MEM; - p->serial_in = dw8250_serial_in; - p->serial_out = dw8250_serial_out; p->set_ldisc = dw8250_set_ldisc; p->set_termios = dw8250_set_termios; - p->membase = devm_ioremap(dev, regs->start, resource_size(regs)); - if (!p->membase) - return -ENOMEM; - data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -554,15 +552,35 @@ static int dw8250_probe(struct platform_device *pdev) data->uart_16550_compatible = device_property_read_bool(dev, "snps,uart-16550-compatible"); - err = device_property_read_u32(dev, "reg-shift", &val); - if (!err) - p->regshift = val; + p->mapbase = regs->start; + p->mapsize = resource_size(regs); - err = device_property_read_u32(dev, "reg-io-width", &val); - if (!err && val == 4) { - p->iotype = UPIO_MEM32; + p->membase = devm_ioremap(dev, p->mapbase, p->mapsize); + if (!p->membase) + return -ENOMEM; + + err = uart_read_port_properties(p); + /* no interrupt -> fall back to polling */ + if (err == -ENXIO) + err = 0; + if (err) + return err; + + switch (p->iotype) { + case UPIO_MEM: + p->serial_in = dw8250_serial_in; + p->serial_out = dw8250_serial_out; + break; + case UPIO_MEM32: p->serial_in = dw8250_serial_in32; p->serial_out = dw8250_serial_out32; + break; + case UPIO_MEM32BE: + p->serial_in = dw8250_serial_in32be; + p->serial_out = dw8250_serial_out32be; + break; + default: + return -ENODEV; } if (device_property_read_bool(dev, "dcd-override")) { @@ -589,9 +607,6 @@ static int dw8250_probe(struct platform_device *pdev) data->msr_mask_off |= UART_MSR_TERI; } - /* Always ask for fixed clock rate from a property. */ - device_property_read_u32(dev, "clock-frequency", &p->uartclk); - /* If there is separate baudclk, get the rate from it. */ data->clk = devm_clk_get_optional_enabled(dev, "baudclk"); if (data->clk == NULL) @@ -743,8 +758,8 @@ static const struct dw8250_platform_data dw8250_armada_38x_data = { static const struct dw8250_platform_data dw8250_renesas_rzn1_data = { .usr_reg = DW_UART_USR, - .cpr_val = 0x00012f32, - .quirks = DW_UART_QUIRK_IS_DMA_FC, + .cpr_value = 0x00012f32, + .quirks = DW_UART_QUIRK_CPR_VALUE | DW_UART_QUIRK_IS_DMA_FC, }; static const struct dw8250_platform_data dw8250_starfive_jh7100_data = { @@ -762,13 +777,18 @@ static const struct of_device_id dw8250_of_match[] = { }; MODULE_DEVICE_TABLE(of, dw8250_of_match); +static const struct dw8250_platform_data dw8250_apmc0d08 = { + .usr_reg = DW_UART_USR, + .quirks = DW_UART_QUIRK_APMC0D08, +}; + static const struct acpi_device_id dw8250_acpi_match[] = { { "80860F0A", (kernel_ulong_t)&dw8250_dw_apb }, { "8086228A", (kernel_ulong_t)&dw8250_dw_apb }, { "AMD0020", (kernel_ulong_t)&dw8250_dw_apb }, { "AMDI0020", (kernel_ulong_t)&dw8250_dw_apb }, { "AMDI0022", (kernel_ulong_t)&dw8250_dw_apb }, - { "APMC0D08", (kernel_ulong_t)&dw8250_dw_apb}, + { "APMC0D08", (kernel_ulong_t)&dw8250_apmc0d08 }, { "BRCM2032", (kernel_ulong_t)&dw8250_dw_apb }, { "HISI0031", (kernel_ulong_t)&dw8250_dw_apb }, { "INT33C4", (kernel_ulong_t)&dw8250_dw_apb }, diff --git a/drivers/tty/serial/8250/8250_dwlib.c b/drivers/tty/serial/8250/8250_dwlib.c index 3e33ddf7bc800..5a2520943dfd5 100644 --- a/drivers/tty/serial/8250/8250_dwlib.c +++ b/drivers/tty/serial/8250/8250_dwlib.c @@ -242,7 +242,6 @@ static const struct serial_rs485 dw8250_rs485_supported = { void dw8250_setup_port(struct uart_port *p) { struct dw8250_port_data *pd = p->private_data; - struct dw8250_data *data = to_dw8250_data(pd); struct uart_8250_port *up = up_to_u8250p(p); u32 reg, old_dlf; @@ -278,7 +277,7 @@ void dw8250_setup_port(struct uart_port *p) reg = dw8250_readl_ext(p, DW_UART_CPR); if (!reg) { - reg = data->pdata->cpr_val; + reg = pd->cpr_value; dev_dbg(p->dev, "CPR is not available, using 0x%08x instead\n", reg); } if (!reg) diff --git a/drivers/tty/serial/8250/8250_dwlib.h b/drivers/tty/serial/8250/8250_dwlib.h index f13e91f2cace9..7dd2a8e7b7808 100644 --- a/drivers/tty/serial/8250/8250_dwlib.h +++ b/drivers/tty/serial/8250/8250_dwlib.h @@ -2,15 +2,10 @@ /* Synopsys DesignWare 8250 library header file. */ #include -#include #include -#include #include "8250.h" -struct clk; -struct reset_control; - struct dw8250_port_data { /* Port properties */ int line; @@ -19,42 +14,16 @@ struct dw8250_port_data { struct uart_8250_dma dma; /* Hardware configuration */ + u32 cpr_value; u8 dlf_size; /* RS485 variables */ bool hw_rs485_support; }; -struct dw8250_platform_data { - u8 usr_reg; - u32 cpr_val; - unsigned int quirks; -}; - -struct dw8250_data { - struct dw8250_port_data data; - const struct dw8250_platform_data *pdata; - - int msr_mask_on; - int msr_mask_off; - struct clk *clk; - struct clk *pclk; - struct notifier_block clk_notifier; - struct work_struct clk_work; - struct reset_control *rst; - - unsigned int skip_autocfg:1; - unsigned int uart_16550_compatible:1; -}; - void dw8250_do_set_termios(struct uart_port *p, struct ktermios *termios, const struct ktermios *old); void dw8250_setup_port(struct uart_port *p); -static inline struct dw8250_data *to_dw8250_data(struct dw8250_port_data *data) -{ - return container_of(data, struct dw8250_data, data); -} - static inline u32 dw8250_readl_ext(struct uart_port *p, int offset) { if (p->iotype == UPIO_MEM32BE) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 23366f868ae3a..e21bbece5a59d 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -40,8 +40,50 @@ #define PCI_DEVICE_ID_COMMTECH_4228PCIE 0x0021 #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 +#define PCI_VENDOR_ID_CONNECT_TECH 0x12c4 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_2_SP_OPTO 0x0340 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_SP_OPTO_A 0x0341 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_SP_OPTO_B 0x0342 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_2_XPRS 0x0350 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_XPRS_A 0x0351 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_XPRS_B 0x0352 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_XPRS 0x0353 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_16_XPRS_A 0x0354 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_16_XPRS_B 0x0355 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_2_XPRS_OPTO 0x0360 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_XPRS_OPTO_A 0x0361 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_XPRS_OPTO_B 0x0362 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_SP 0x0370 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_SP_232 0x0371 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_SP_485 0x0372 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_4_SP 0x0373 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_6_2_SP 0x0374 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_2_6_SP 0x0375 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_SP_232_NS 0x0376 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_2_XP_OPTO_LEFT 0x0380 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_2_XP_OPTO_RIGHT 0x0381 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_XP_OPTO 0x0382 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_4_4_XPRS_OPTO 0x0392 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_XPRS_LP 0x03A0 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_XPRS_LP_232 0x03A1 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_XPRS_LP_485 0x03A2 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCI_UART_8_XPRS_LP_232_NS 0x03A3 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCIE_XEG001 0x0602 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCIE_XR35X_BASE 0x1000 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCIE_XR35X_2 0x1002 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCIE_XR35X_4 0x1004 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCIE_XR35X_8 0x1008 +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCIE_XR35X_12 0x100C +#define PCI_SUBDEVICE_ID_CONNECT_TECH_PCIE_XR35X_16 0x1010 +#define PCI_DEVICE_ID_CONNECT_TECH_PCI_XR79X_12_XIG00X 0x110c +#define PCI_DEVICE_ID_CONNECT_TECH_PCI_XR79X_12_XIG01X 0x110d +#define PCI_DEVICE_ID_CONNECT_TECH_PCI_XR79X_16 0x1110 + #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_DEVICE_ID_EXAR_XR17V252 0x0252 +#define PCI_DEVICE_ID_EXAR_XR17V254 0x0254 +#define PCI_DEVICE_ID_EXAR_XR17V258 0x0258 #define PCI_SUBDEVICE_ID_USR_2980 0x0128 #define PCI_SUBDEVICE_ID_USR_2981 0x0129 @@ -753,6 +795,7 @@ static void exar_pci_remove(struct pci_dev *pcidev) for (i = 0; i < priv->nr; i++) serial8250_unregister_port(priv->line[i]); + /* Ensure that every init quirk is properly torn down */ if (priv->board->exit) priv->board->exit(pcidev); } @@ -767,10 +810,6 @@ static int __maybe_unused exar_suspend(struct device *dev) if (priv->line[i] >= 0) serial8250_suspend_port(priv->line[i]); - /* Ensure that every init quirk is properly torn down */ - if (priv->board->exit) - priv->board->exit(pcidev); - return 0; } diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index 9ff6bbe9c0863..d14988d1492fe 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -209,15 +209,19 @@ static int mtk8250_startup(struct uart_port *port) static void mtk8250_shutdown(struct uart_port *port) { -#ifdef CONFIG_SERIAL_8250_DMA struct uart_8250_port *up = up_to_u8250p(port); struct mtk8250_data *data = port->private_data; + int irq = data->rx_wakeup_irq; +#ifdef CONFIG_SERIAL_8250_DMA if (up->dma) data->rx_status = DMA_RX_SHUTDOWN; #endif - return serial8250_do_shutdown(port); + serial8250_do_shutdown(port); + + if (irq >= 0) + serial8250_do_set_mctrl(&up->port, TIOCM_RTS); } static void mtk8250_disable_intrs(struct uart_8250_port *up, int mask) diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 34f17a9785e79..9dcc17e332690 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -4,7 +4,10 @@ * * Copyright (C) 2006 Arnd Bergmann , IBM Corp. */ + +#include #include +#include #include #include #include @@ -25,6 +28,36 @@ struct of_serial_info { int line; }; +/* Nuvoton NPCM timeout register */ +#define UART_NPCM_TOR 7 +#define UART_NPCM_TOIE BIT(7) /* Timeout Interrupt Enable */ + +static int npcm_startup(struct uart_port *port) +{ + /* + * Nuvoton calls the scratch register 'UART_TOR' (timeout + * register). Enable it, and set TIOC (timeout interrupt + * comparator) to be 0x20 for correct operation. + */ + serial_port_out(port, UART_NPCM_TOR, UART_NPCM_TOIE | 0x20); + + return serial8250_do_startup(port); +} + +/* Nuvoton NPCM UARTs have a custom divisor calculation */ +static unsigned int npcm_get_divisor(struct uart_port *port, unsigned int baud, + unsigned int *frac) +{ + return DIV_ROUND_CLOSEST(port->uartclk, 16 * baud + 2) - 2; +} + +static int npcm_setup(struct uart_port *port) +{ + port->get_divisor = npcm_get_divisor; + port->startup = npcm_startup; + return 0; +} + /* * Fill a struct uart_port for a given device node */ @@ -164,10 +197,17 @@ static int of_platform_serial_setup(struct platform_device *ofdev, switch (type) { case PORT_RT2880: ret = rt288x_setup(port); - if (ret) - goto err_pmruntime; + break; + case PORT_NPCM: + ret = npcm_setup(port); + break; + default: + /* Nothing to do */ + ret = 0; break; } + if (ret) + goto err_pmruntime; if (IS_REACHABLE(CONFIG_SERIAL_8250_FSL) && (of_device_is_compatible(np, "fsl,ns16550") || diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 8ca061d3bbb92..c0c34e410c581 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -38,10 +38,6 @@ #include "8250.h" -/* Nuvoton NPCM timeout register */ -#define UART_NPCM_TOR 7 -#define UART_NPCM_TOIE BIT(7) /* Timeout Interrupt Enable */ - /* * Debugging. */ @@ -1329,9 +1325,6 @@ static void autoconfig_irq(struct uart_8250_port *up) inb_p(ICP); } - if (uart_console(port)) - console_lock(); - /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); @@ -1371,9 +1364,6 @@ static void autoconfig_irq(struct uart_8250_port *up) if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); - if (uart_console(port)) - console_unlock(); - port->irq = (irq > 0) ? irq : 0; } @@ -2235,15 +2225,6 @@ int serial8250_do_startup(struct uart_port *port) UART_DA830_PWREMU_MGMT_FREE); } - if (port->type == PORT_NPCM) { - /* - * Nuvoton calls the scratch register 'UART_TOR' (timeout - * register). Enable it, and set TIOC (timeout interrupt - * comparator) to be 0x20 for correct operation. - */ - serial_port_out(port, UART_NPCM_TOR, UART_NPCM_TOIE | 0x20); - } - #ifdef CONFIG_SERIAL_8250_RSA /* * If this is an RSA port, see if we can kick it up to the @@ -2545,15 +2526,6 @@ static void serial8250_shutdown(struct uart_port *port) serial8250_do_shutdown(port); } -/* Nuvoton NPCM UARTs have a custom divisor calculation */ -static unsigned int npcm_get_divisor(struct uart_8250_port *up, - unsigned int baud) -{ - struct uart_port *port = &up->port; - - return DIV_ROUND_CLOSEST(port->uartclk, 16 * baud + 2) - 2; -} - static unsigned int serial8250_do_get_divisor(struct uart_port *port, unsigned int baud, unsigned int *frac) @@ -2598,8 +2570,6 @@ static unsigned int serial8250_do_get_divisor(struct uart_port *port, quot = 0x8001; else if (magic_multiplier && baud >= port->uartclk / 12) quot = 0x8002; - else if (up->port.type == PORT_NPCM) - quot = npcm_get_divisor(up, baud); else quot = uart_get_divisor(port, baud); diff --git a/drivers/tty/serial/8250/8250_pxa.c b/drivers/tty/serial/8250/8250_pxa.c index 77686da42ce8e..a34d6519488ae 100644 --- a/drivers/tty/serial/8250/8250_pxa.c +++ b/drivers/tty/serial/8250/8250_pxa.c @@ -124,6 +124,7 @@ static int serial_pxa_probe(struct platform_device *pdev) uart.port.regshift = 2; uart.port.irq = irq; uart.port.fifosize = 64; + uart.tx_loadsz = 32; uart.port.flags = UPF_IOREMAP | UPF_SKIP_TEST | UPF_FIXED_TYPE; uart.port.dev = &pdev->dev; uart.port.uartclk = clk_get_rate(data->clk); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index e148132506161..09c1678ddfd49 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -2010,7 +2011,7 @@ imx_uart_console_write(struct console *co, const char *s, unsigned int count) struct imx_port *sport = imx_uart_ports[co->index]; struct imx_port_ucrs old_ucr; unsigned long flags; - unsigned int ucr1; + unsigned int ucr1, usr2; int locked = 1; if (sport->port.sysrq) @@ -2041,8 +2042,8 @@ imx_uart_console_write(struct console *co, const char *s, unsigned int count) * Finally, wait for transmitter to become empty * and restore UCR1/2/3 */ - while (!(imx_uart_readl(sport, USR2) & USR2_TXDC)); - + read_poll_timeout_atomic(imx_uart_readl, usr2, usr2 & USR2_TXDC, + 0, USEC_PER_SEC, false, sport, USR2); imx_uart_ucrs_restore(sport, &old_ucr); if (locked) diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c index 7ce7bb1640054..58ea1e1391cee 100644 --- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -48,6 +49,25 @@ static struct kgdb_io kgdboc_earlycon_io_ops; static int (*earlycon_orig_exit)(struct console *con); #endif /* IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */ +/* + * When we leave the debug trap handler we need to reset the keyboard status + * (since the original keyboard state gets partially clobbered by kdb use of + * the keyboard). + * + * The path to deliver the reset is somewhat circuitous. + * + * To deliver the reset we register an input handler, reset the keyboard and + * then deregister the input handler. However, to get this done right, we do + * have to carefully manage the calling context because we can only register + * input handlers from task context. + * + * In particular we need to trigger the action from the debug trap handler with + * all its NMI and/or NMI-like oddities. To solve this the kgdboc trap exit code + * (the "post_exception" callback) uses irq_work_queue(), which is NMI-safe, to + * schedule a callback from a hardirq context. From there we have to defer the + * work again, this time using schedule_work(), to get a callback using the + * system workqueue, which runs in task context. + */ #ifdef CONFIG_KDB_KEYBOARD static int kgdboc_reset_connect(struct input_handler *handler, struct input_dev *dev, @@ -99,10 +119,17 @@ static void kgdboc_restore_input_helper(struct work_struct *dummy) static DECLARE_WORK(kgdboc_restore_input_work, kgdboc_restore_input_helper); +static void kgdboc_queue_restore_input_helper(struct irq_work *unused) +{ + schedule_work(&kgdboc_restore_input_work); +} + +static DEFINE_IRQ_WORK(kgdboc_restore_input_irq_work, kgdboc_queue_restore_input_helper); + static void kgdboc_restore_input(void) { if (likely(system_state == SYSTEM_RUNNING)) - schedule_work(&kgdboc_restore_input_work); + irq_work_queue(&kgdboc_restore_input_irq_work); } static int kgdboc_register_kbd(char **cptr) @@ -133,6 +160,7 @@ static void kgdboc_unregister_kbd(void) i--; } } + irq_work_sync(&kgdboc_restore_input_irq_work); flush_work(&kgdboc_restore_input_work); } #else /* ! CONFIG_KDB_KEYBOARD */ diff --git a/drivers/tty/serial/max3100.c b/drivers/tty/serial/max3100.c index 5efb2b593be33..3d2b83d6ab51a 100644 --- a/drivers/tty/serial/max3100.c +++ b/drivers/tty/serial/max3100.c @@ -45,6 +45,9 @@ #include #include #include +#include + +#include #include @@ -191,7 +194,7 @@ static void max3100_timeout(struct timer_list *t) static int max3100_sr(struct max3100_port *s, u16 tx, u16 *rx) { struct spi_message message; - u16 etx, erx; + __be16 etx, erx; int status; struct spi_transfer tran = { .tx_buf = &etx, @@ -213,7 +216,7 @@ static int max3100_sr(struct max3100_port *s, u16 tx, u16 *rx) return 0; } -static int max3100_handlerx(struct max3100_port *s, u16 rx) +static int max3100_handlerx_unlocked(struct max3100_port *s, u16 rx) { unsigned int status = 0; int ret = 0, cts; @@ -254,6 +257,17 @@ static int max3100_handlerx(struct max3100_port *s, u16 rx) return ret; } +static int max3100_handlerx(struct max3100_port *s, u16 rx) +{ + unsigned long flags; + int ret; + + uart_port_lock_irqsave(&s->port, &flags); + ret = max3100_handlerx_unlocked(s, rx); + uart_port_unlock_irqrestore(&s->port, flags); + return ret; +} + static void max3100_work(struct work_struct *w) { struct max3100_port *s = container_of(w, struct max3100_port, work); @@ -738,13 +752,14 @@ static int max3100_probe(struct spi_device *spi) mutex_lock(&max3100s_lock); if (!uart_driver_registered) { - uart_driver_registered = 1; retval = uart_register_driver(&max3100_uart_driver); if (retval) { printk(KERN_ERR "Couldn't register max3100 uart driver\n"); mutex_unlock(&max3100s_lock); return retval; } + + uart_driver_registered = 1; } for (i = 0; i < MAX_MAX3100; i++) @@ -830,6 +845,7 @@ static void max3100_remove(struct spi_device *spi) } pr_debug("removing max3100 driver\n"); uart_unregister_driver(&max3100_uart_driver); + uart_driver_registered = 0; mutex_unlock(&max3100s_lock); } diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 10bf6d75bf9ee..198413df091b4 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -1461,7 +1461,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty if (!ret) return 0; - dev_err(dev, "Unable to reguest IRQ %i\n", irq); + dev_err(dev, "Unable to request IRQ %i\n", irq); out_uart: for (i = 0; i < devtype->nr; i++) { @@ -1635,13 +1635,16 @@ static unsigned short max310x_i2c_slave_addr(unsigned short addr, static int max310x_i2c_probe(struct i2c_client *client) { - const struct max310x_devtype *devtype = - device_get_match_data(&client->dev); + const struct max310x_devtype *devtype; struct i2c_client *port_client; struct regmap *regmaps[4]; unsigned int i; u8 port_addr; + devtype = device_get_match_data(&client->dev); + if (!devtype) + return dev_err_probe(&client->dev, -ENODEV, "Failed to match device\n"); + if (client->addr < devtype->slave_addr.min || client->addr > devtype->slave_addr.max) return dev_err_probe(&client->dev, -EINVAL, diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index 4749331fe618c..1e8853eae5042 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -1086,11 +1086,13 @@ static void mxs_auart_set_ldisc(struct uart_port *port, static irqreturn_t mxs_auart_irq_handle(int irq, void *context) { - u32 istat; + u32 istat, stat; struct mxs_auart_port *s = context; u32 mctrl_temp = s->mctrl_prev; - u32 stat = mxs_read(s, REG_STAT); + uart_port_lock(&s->port); + + stat = mxs_read(s, REG_STAT); istat = mxs_read(s, REG_INTR); /* ack irq */ @@ -1126,6 +1128,8 @@ static irqreturn_t mxs_auart_irq_handle(int irq, void *context) istat &= ~AUART_INTR_TXIS; } + uart_port_unlock(&s->port); + return IRQ_HANDLED; } diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c index c8bf08c19c647..77691fbbf779a 100644 --- a/drivers/tty/serial/pmac_zilog.c +++ b/drivers/tty/serial/pmac_zilog.c @@ -210,7 +210,6 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) { struct tty_port *port; unsigned char ch, r1, drop, flag; - int loops = 0; /* Sanity check, make sure the old bug is no longer happening */ if (uap->port.state == NULL) { @@ -291,24 +290,11 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) if (r1 & Rx_OVR) tty_insert_flip_char(port, 0, TTY_OVERRUN); next_char: - /* We can get stuck in an infinite loop getting char 0 when the - * line is in a wrong HW state, we break that here. - * When that happens, I disable the receive side of the driver. - * Note that what I've been experiencing is a real irq loop where - * I'm getting flooded regardless of the actual port speed. - * Something strange is going on with the HW - */ - if ((++loops) > 1000) - goto flood; ch = read_zsreg(uap, R0); if (!(ch & Rx_CH_AV)) break; } - return true; - flood: - pmz_interrupt_control(uap, 0); - pmz_error("pmz: rx irq flood !\n"); return true; } diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index 71d17d804fdab..6fdb32b833466 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -987,11 +987,10 @@ static unsigned int s3c24xx_serial_tx_empty(struct uart_port *port) if ((ufstat & info->tx_fifomask) != 0 || (ufstat & info->tx_fifofull)) return 0; - - return 1; + return TIOCSER_TEMT; } - return s3c24xx_serial_txempty_nofifo(port); + return s3c24xx_serial_txempty_nofifo(port) ? TIOCSER_TEMT : 0; } /* no modem control lines */ diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 929206a9a6e11..ace2c4b333acc 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -25,7 +26,6 @@ #include #include #include -#include #define SC16IS7XX_NAME "sc16is7xx" #define SC16IS7XX_MAX_DEVS 8 @@ -554,16 +554,28 @@ static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg) return reg == SC16IS7XX_RHR_REG; } +/* + * Configure programmable baud rate generator (divisor) according to the + * desired baud rate. + * + * From the datasheet, the divisor is computed according to: + * + * XTAL1 input frequency + * ----------------------- + * prescaler + * divisor = --------------------------- + * baud-rate x sampling-rate + */ static int sc16is7xx_set_baud(struct uart_port *port, int baud) { struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); u8 lcr; - u8 prescaler = 0; + unsigned int prescaler = 1; unsigned long clk = port->uartclk, div = clk / 16 / baud; if (div >= BIT(16)) { - prescaler = SC16IS7XX_MCR_CLKSEL_BIT; - div /= 4; + prescaler = 4; + div /= prescaler; } /* Enable enhanced features */ @@ -573,9 +585,10 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud) SC16IS7XX_EFR_ENABLE_BIT); sc16is7xx_efr_unlock(port); + /* If bit MCR_CLKSEL is set, the divide by 4 prescaler is activated. */ sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_CLKSEL_BIT, - prescaler); + prescaler == 1 ? 0 : SC16IS7XX_MCR_CLKSEL_BIT); /* Backup LCR and access special register set (DLL/DLH) */ lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG); @@ -591,7 +604,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud) /* Restore LCR and access to general register set */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr); - return DIV_ROUND_CLOSEST(clk / 16, div); + return DIV_ROUND_CLOSEST((clk / prescaler) / 16, div); } static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen, diff --git a/drivers/tty/serial/serial_base.h b/drivers/tty/serial/serial_base.h index c74c548f0db62..b6c38d2edfd40 100644 --- a/drivers/tty/serial/serial_base.h +++ b/drivers/tty/serial/serial_base.h @@ -22,6 +22,7 @@ struct serial_ctrl_device { struct serial_port_device { struct device dev; struct uart_port *port; + unsigned int tx_enabled:1; }; int serial_base_ctrl_init(void); @@ -30,6 +31,9 @@ void serial_base_ctrl_exit(void); int serial_base_port_init(void); void serial_base_port_exit(void); +void serial_base_port_startup(struct uart_port *port); +void serial_base_port_shutdown(struct uart_port *port); + int serial_base_driver_register(struct device_driver *driver); void serial_base_driver_unregister(struct device_driver *driver); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index d6a58a9e072a1..c476d884356db 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -156,7 +156,7 @@ static void __uart_start(struct uart_state *state) * enabled, serial_port_runtime_resume() calls start_tx() again * after enabling the device. */ - if (pm_runtime_active(&port_dev->dev)) + if (!pm_runtime_enabled(port->dev) || pm_runtime_active(&port_dev->dev)) port->ops->start_tx(port); pm_runtime_mark_last_busy(&port_dev->dev); pm_runtime_put_autosuspend(&port_dev->dev); @@ -323,16 +323,26 @@ static int uart_startup(struct tty_struct *tty, struct uart_state *state, bool init_hw) { struct tty_port *port = &state->port; + struct uart_port *uport; int retval; if (tty_port_initialized(port)) - return 0; + goto out_base_port_startup; retval = uart_port_startup(tty, state, init_hw); - if (retval) + if (retval) { set_bit(TTY_IO_ERROR, &tty->flags); + return retval; + } - return retval; +out_base_port_startup: + uport = uart_port_check(state); + if (!uport) + return -EIO; + + serial_base_port_startup(uport); + + return 0; } /* @@ -355,6 +365,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) if (tty) set_bit(TTY_IO_ERROR, &tty->flags); + if (uport) + serial_base_port_shutdown(uport); + if (tty_port_initialized(port)) { tty_port_set_initialized(port, false); @@ -1775,6 +1788,7 @@ static void uart_tty_port_shutdown(struct tty_port *port) uport->ops->stop_rx(uport); uart_port_unlock_irq(uport); + serial_base_port_shutdown(uport); uart_port_shutdown(port); /* @@ -1788,6 +1802,7 @@ static void uart_tty_port_shutdown(struct tty_port *port) * Free the transmit buffer. */ uart_port_lock_irq(uport); + uart_circ_clear(&state->xmit); buf = state->xmit.buf; state->xmit.buf = NULL; uart_port_unlock_irq(uport); @@ -2608,7 +2623,12 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); port->ops->config_port(port, flags); + if (uart_console(port)) + console_unlock(); } if (port->type != PORT_UNKNOWN) { @@ -2616,6 +2636,10 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_report_port(drv, port); + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); + /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); @@ -2632,6 +2656,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_rs485_config(port); + if (uart_console(port)) + console_unlock(); + /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c index 72b6f4f326e2b..66fd117d8aea8 100644 --- a/drivers/tty/serial/serial_port.c +++ b/drivers/tty/serial/serial_port.c @@ -8,7 +8,10 @@ #include #include +#include +#include #include +#include #include #include @@ -36,8 +39,12 @@ static int serial_port_runtime_resume(struct device *dev) /* Flush any pending TX for the port */ uart_port_lock_irqsave(port, &flags); + if (!port_dev->tx_enabled) + goto unlock; if (__serial_port_busy(port)) port->ops->start_tx(port); + +unlock: uart_port_unlock_irqrestore(port, flags); out: @@ -56,7 +63,19 @@ static int serial_port_runtime_suspend(struct device *dev) if (port->flags & UPF_DEAD) return 0; + /* + * Nothing to do on pm_runtime_force_suspend(), see + * DEFINE_RUNTIME_DEV_PM_OPS. + */ + if (!pm_runtime_enabled(dev)) + return 0; + uart_port_lock_irqsave(port, &flags); + if (!port_dev->tx_enabled) { + uart_port_unlock_irqrestore(port, flags); + return 0; + } + busy = __serial_port_busy(port); if (busy) port->ops->start_tx(port); @@ -68,6 +87,31 @@ static int serial_port_runtime_suspend(struct device *dev) return busy ? -EBUSY : 0; } +static void serial_base_port_set_tx(struct uart_port *port, + struct serial_port_device *port_dev, + bool enabled) +{ + unsigned long flags; + + uart_port_lock_irqsave(port, &flags); + port_dev->tx_enabled = enabled; + uart_port_unlock_irqrestore(port, flags); +} + +void serial_base_port_startup(struct uart_port *port) +{ + struct serial_port_device *port_dev = port->port_dev; + + serial_base_port_set_tx(port, port_dev, true); +} + +void serial_base_port_shutdown(struct uart_port *port) +{ + struct serial_port_device *port_dev = port->port_dev; + + serial_base_port_set_tx(port, port_dev, false); +} + static DEFINE_RUNTIME_DEV_PM_OPS(serial_port_pm, serial_port_runtime_suspend, serial_port_runtime_resume, NULL); @@ -105,6 +149,148 @@ void uart_remove_one_port(struct uart_driver *drv, struct uart_port *port) } EXPORT_SYMBOL(uart_remove_one_port); +/** + * __uart_read_properties - read firmware properties of the given UART port + * @port: corresponding port + * @use_defaults: apply defaults (when %true) or validate the values (when %false) + * + * The following device properties are supported: + * - clock-frequency (optional) + * - fifo-size (optional) + * - no-loopback-test (optional) + * - reg-shift (defaults may apply) + * - reg-offset (value may be validated) + * - reg-io-width (defaults may apply or value may be validated) + * - interrupts (OF only) + * - serial [alias ID] (OF only) + * + * If the port->dev is of struct platform_device type the interrupt line + * will be retrieved via platform_get_irq() call against that device. + * Otherwise it will be assigned by fwnode_irq_get() call. In both cases + * the index 0 of the resource is used. + * + * The caller is responsible to initialize the following fields of the @port + * ->dev (must be valid) + * ->flags + * ->mapbase + * ->mapsize + * ->regshift (if @use_defaults is false) + * before calling this function. Alternatively the above mentioned fields + * may be zeroed, in such case the only ones, that have associated properties + * found, will be set to the respective values. + * + * If no error happened, the ->irq, ->mapbase, ->mapsize will be altered. + * The ->iotype is always altered. + * + * When @use_defaults is true and the respective property is not found + * the following values will be applied: + * ->regshift = 0 + * In this case IRQ must be provided, otherwise an error will be returned. + * + * When @use_defaults is false and the respective property is found + * the following values will be validated: + * - reg-io-width (->iotype) + * - reg-offset (->mapsize against ->mapbase) + * + * Returns: 0 on success or negative errno on failure + */ +static int __uart_read_properties(struct uart_port *port, bool use_defaults) +{ + struct device *dev = port->dev; + u32 value; + int ret; + + /* Read optional UART functional clock frequency */ + device_property_read_u32(dev, "clock-frequency", &port->uartclk); + + /* Read the registers alignment (default: 8-bit) */ + ret = device_property_read_u32(dev, "reg-shift", &value); + if (ret) + port->regshift = use_defaults ? 0 : port->regshift; + else + port->regshift = value; + + /* Read the registers I/O access type (default: MMIO 8-bit) */ + ret = device_property_read_u32(dev, "reg-io-width", &value); + if (ret) { + port->iotype = UPIO_MEM; + } else { + switch (value) { + case 1: + port->iotype = UPIO_MEM; + break; + case 2: + port->iotype = UPIO_MEM16; + break; + case 4: + port->iotype = device_is_big_endian(dev) ? UPIO_MEM32BE : UPIO_MEM32; + break; + default: + if (!use_defaults) { + dev_err(dev, "Unsupported reg-io-width (%u)\n", value); + return -EINVAL; + } + port->iotype = UPIO_UNKNOWN; + break; + } + } + + /* Read the address mapping base offset (default: no offset) */ + ret = device_property_read_u32(dev, "reg-offset", &value); + if (ret) + value = 0; + + /* Check for shifted address mapping overflow */ + if (!use_defaults && port->mapsize < value) { + dev_err(dev, "reg-offset %u exceeds region size %pa\n", value, &port->mapsize); + return -EINVAL; + } + + port->mapbase += value; + port->mapsize -= value; + + /* Read optional FIFO size */ + device_property_read_u32(dev, "fifo-size", &port->fifosize); + + if (device_property_read_bool(dev, "no-loopback-test")) + port->flags |= UPF_SKIP_TEST; + + /* Get index of serial line, if found in DT aliases */ + ret = of_alias_get_id(dev_of_node(dev), "serial"); + if (ret >= 0) + port->line = ret; + + if (dev_is_platform(dev)) + ret = platform_get_irq(to_platform_device(dev), 0); + else + ret = fwnode_irq_get(dev_fwnode(dev), 0); + if (ret == -EPROBE_DEFER) + return ret; + if (ret > 0) + port->irq = ret; + else if (use_defaults) + /* By default IRQ support is mandatory */ + return ret; + else + port->irq = 0; + + port->flags |= UPF_SHARE_IRQ; + + return 0; +} + +int uart_read_port_properties(struct uart_port *port) +{ + return __uart_read_properties(port, true); +} +EXPORT_SYMBOL_GPL(uart_read_port_properties); + +int uart_read_and_validate_port_properties(struct uart_port *port) +{ + return __uart_read_properties(port, false); +} +EXPORT_SYMBOL_GPL(uart_read_and_validate_port_properties); + static struct device_driver serial_port_driver = { .name = "port", .suppress_bind_attrs = true, diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index a85e7b9a2e492..0d9eab56747cc 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1272,9 +1272,14 @@ static void sci_dma_rx_chan_invalidate(struct sci_port *s) static void sci_dma_rx_release(struct sci_port *s) { struct dma_chan *chan = s->chan_rx_saved; + struct uart_port *port = &s->port; + unsigned long flags; + uart_port_lock_irqsave(port, &flags); s->chan_rx_saved = NULL; sci_dma_rx_chan_invalidate(s); + uart_port_unlock_irqrestore(port, flags); + dmaengine_terminate_sync(chan); dma_free_coherent(chan->device->dev, s->buf_len_rx * 2, s->rx_buf[0], sg_dma_address(&s->sg_rx[0])); diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 693e932d6feb5..d103b07d10ee5 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -857,6 +857,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; u32 sr; unsigned int size; + irqreturn_t ret = IRQ_NONE; sr = readl_relaxed(port->membase + ofs->isr); @@ -865,11 +866,14 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) (sr & USART_SR_TC)) { stm32_usart_tc_interrupt_disable(port); stm32_usart_rs485_rts_disable(port); + ret = IRQ_HANDLED; } - if ((sr & USART_SR_RTOF) && ofs->icr != UNDEF_REG) + if ((sr & USART_SR_RTOF) && ofs->icr != UNDEF_REG) { writel_relaxed(USART_ICR_RTOCF, port->membase + ofs->icr); + ret = IRQ_HANDLED; + } if ((sr & USART_SR_WUF) && ofs->icr != UNDEF_REG) { /* Clear wake up flag and disable wake up interrupt */ @@ -878,6 +882,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) stm32_usart_clr_bits(port, ofs->cr3, USART_CR3_WUFIE); if (irqd_is_wakeup_set(irq_get_irq_data(port->irq))) pm_wakeup_event(tport->tty->dev, 0); + ret = IRQ_HANDLED; } /* @@ -892,6 +897,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); + ret = IRQ_HANDLED; } } @@ -899,6 +905,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) uart_port_lock(port); stm32_usart_transmit_chars(port); uart_port_unlock(port); + ret = IRQ_HANDLED; } /* Receiver timeout irq for DMA RX */ @@ -908,9 +915,10 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); + ret = IRQ_HANDLED; } - return IRQ_HANDLED; + return ret; } static void stm32_usart_set_mctrl(struct uart_port *port, unsigned int mctrl) @@ -1080,6 +1088,7 @@ static int stm32_usart_startup(struct uart_port *port) val |= USART_CR2_SWAP; writel_relaxed(val, port->membase + ofs->cr2); } + stm32_port->throttled = false; /* RX FIFO Flush */ if (ofs->rqr != UNDEF_REG) diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 3f68e213df1f7..d80e9d4c974b4 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -545,6 +545,12 @@ int tty_set_ldisc(struct tty_struct *tty, int disc) goto out; } + if (tty->ops->ldisc_ok) { + retval = tty->ops->ldisc_ok(tty, disc); + if (retval) + goto out; + } + old_ldisc = tty->ldisc; /* Shutdown the old discipline. */ diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 38a765eadbe2b..09126aed97bc1 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -2469,7 +2469,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) } return; case EScsiignore: - if (c >= 20 && c <= 0x3f) + if (c >= 0x20 && c <= 0x3f) return; vc->vc_state = ESnormal; return; @@ -3396,6 +3396,15 @@ static void con_cleanup(struct tty_struct *tty) tty_port_put(&vc->port); } +/* + * We can't deal with anything but the N_TTY ldisc, + * because we can sleep in our write() routine. + */ +static int con_ldisc_ok(struct tty_struct *tty, int ldisc) +{ + return ldisc == N_TTY ? 0 : -EINVAL; +} + static int default_color = 7; /* white */ static int default_italic_color = 2; // green (ASCII) static int default_underline_color = 3; // cyan (ASCII) @@ -3515,6 +3524,7 @@ static const struct tty_operations con_ops = { .resize = vt_resize, .shutdown = con_shutdown, .cleanup = con_cleanup, + .ldisc_ok = con_ldisc_ok, }; static struct cdev vc0_cdev; diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 0787456c2b892..4e84ee6564d4b 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -94,7 +94,7 @@ void ufshcd_mcq_config_mac(struct ufs_hba *hba, u32 max_active_cmds) val = ufshcd_readl(hba, REG_UFS_MCQ_CFG); val &= ~MCQ_CFG_MAC_MASK; - val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds); + val |= FIELD_PREP(MCQ_CFG_MAC_MASK, max_active_cmds - 1); ufshcd_writel(hba, val, REG_UFS_MCQ_CFG); } EXPORT_SYMBOL_GPL(ufshcd_mcq_config_mac); @@ -597,8 +597,7 @@ static bool ufshcd_mcq_sqe_search(struct ufs_hba *hba, addr = le64_to_cpu(cmd_desc_base_addr) & CQE_UCD_BA; while (sq_head_slot != hwq->sq_tail_slot) { - utrd = hwq->sqe_base_addr + - sq_head_slot * sizeof(struct utp_transfer_req_desc); + utrd = hwq->sqe_base_addr + sq_head_slot; match = le64_to_cpu(utrd->command_desc_base_addr) & CQE_UCD_BA; if (addr == match) { ufshcd_mcq_nullify_sqe(utrd); @@ -631,20 +630,20 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) struct ufshcd_lrb *lrbp = &hba->lrb[tag]; struct ufs_hw_queue *hwq; unsigned long flags; - int err = FAILED; + int err; if (!ufshcd_cmd_inflight(lrbp->cmd)) { dev_err(hba->dev, "%s: skip abort. cmd at tag %d already completed.\n", __func__, tag); - goto out; + return FAILED; } /* Skip task abort in case previous aborts failed and report failure */ if (lrbp->req_abort_skip) { dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n", __func__, tag); - goto out; + return FAILED; } hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd)); @@ -656,7 +655,7 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) */ dev_err(hba->dev, "%s: cmd found in sq. hwq=%d, tag=%d\n", __func__, hwq->id, tag); - goto out; + return FAILED; } /* @@ -664,18 +663,17 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) * in the completion queue either. Query the device to see if * the command is being processed in the device. */ - if (ufshcd_try_to_abort_task(hba, tag)) { + err = ufshcd_try_to_abort_task(hba, tag); + if (err) { dev_err(hba->dev, "%s: device abort failed %d\n", __func__, err); lrbp->req_abort_skip = true; - goto out; + return FAILED; } - err = SUCCESS; spin_lock_irqsave(&hwq->cq_lock, flags); if (ufshcd_cmd_inflight(lrbp->cmd)) ufshcd_release_scsi_cmd(hba, lrbp); spin_unlock_irqrestore(&hwq->cq_lock, flags); -out: - return err; + return SUCCESS; } diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 3b89c9d4aa404..00776591e7499 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1347,7 +1347,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) * make sure that there are no outstanding requests when * clock scaling is in progress */ - ufshcd_scsi_block_requests(hba); + blk_mq_quiesce_tagset(&hba->host->tag_set); mutex_lock(&hba->wb_mutex); down_write(&hba->clk_scaling_lock); @@ -1356,7 +1356,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) ret = -EBUSY; up_write(&hba->clk_scaling_lock); mutex_unlock(&hba->wb_mutex); - ufshcd_scsi_unblock_requests(hba); + blk_mq_unquiesce_tagset(&hba->host->tag_set); goto out; } @@ -1377,7 +1377,7 @@ static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err, bool sc mutex_unlock(&hba->wb_mutex); - ufshcd_scsi_unblock_requests(hba); + blk_mq_unquiesce_tagset(&hba->host->tag_set); ufshcd_release(hba); } @@ -3172,7 +3172,9 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba, /* MCQ mode */ if (is_mcq_enabled(hba)) { - err = ufshcd_clear_cmd(hba, lrbp->task_tag); + /* successfully cleared the command, retry if needed */ + if (ufshcd_clear_cmd(hba, lrbp->task_tag) == 0) + err = -EAGAIN; hba->dev_cmd.complete = NULL; return err; } @@ -4242,7 +4244,7 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd) * Make sure UIC command completion interrupt is disabled before * issuing UIC command. */ - wmb(); + ufshcd_readl(hba, REG_INTERRUPT_ENABLE); reenable_intr = true; } spin_unlock_irqrestore(hba->host->host_lock, flags); @@ -8928,6 +8930,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params) (hba->quirks & UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH)) { /* Reset the device and controller before doing reinit */ ufshcd_device_reset(hba); + ufs_put_device_desc(hba); ufshcd_hba_stop(hba); ufshcd_vops_reinit_notify(hba); ret = ufshcd_hba_enable(hba); @@ -9745,7 +9748,10 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) /* UFS device & link must be active before we enter in this function */ if (!ufshcd_is_ufs_dev_active(hba) || !ufshcd_is_link_active(hba)) { - ret = -EINVAL; + /* Wait err handler finish or trigger err recovery */ + if (!ufshcd_eh_in_progress(hba)) + ufshcd_force_error_recovery(hba); + ret = -EBUSY; goto enable_scaling; } @@ -10348,7 +10354,7 @@ int ufshcd_system_restore(struct device *dev) * are updated with the latest queue addresses. Only after * updating these addresses, we can queue the new commands. */ - mb(); + ufshcd_readl(hba, REG_UTP_TASK_REQ_LIST_BASE_H); /* Resuming from hibernate, assume that link was OFF */ ufshcd_set_link_off(hba); @@ -10565,7 +10571,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) * Make sure that UFS interrupts are disabled and any pending interrupt * status is cleared before registering UFS interrupt handler. */ - mb(); + ufshcd_readl(hba, REG_INTERRUPT_ENABLE); /* IRQ registration */ err = devm_request_irq(dev, irq, ufshcd_intr, IRQF_SHARED, UFSHCD, hba); diff --git a/drivers/ufs/host/cdns-pltfrm.c b/drivers/ufs/host/cdns-pltfrm.c index bb30267da4711..66811d8d1929c 100644 --- a/drivers/ufs/host/cdns-pltfrm.c +++ b/drivers/ufs/host/cdns-pltfrm.c @@ -136,7 +136,7 @@ static int cdns_ufs_set_hclkdiv(struct ufs_hba *hba) * Make sure the register was updated, * UniPro layer will not work with an incorrect value. */ - mb(); + ufshcd_readl(hba, CDNS_UFS_REG_HCLKDIV); return 0; } diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 39eef470f8fa5..e5a4bf1c553bb 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -47,7 +47,7 @@ enum { TSTBUS_MAX, }; -#define QCOM_UFS_MAX_GEAR 4 +#define QCOM_UFS_MAX_GEAR 5 #define QCOM_UFS_MAX_LANE 2 enum { @@ -67,26 +67,32 @@ static const struct __ufs_qcom_bw_table { [MODE_PWM][UFS_PWM_G2][UFS_LANE_1] = { 1844, 1000 }, [MODE_PWM][UFS_PWM_G3][UFS_LANE_1] = { 3688, 1000 }, [MODE_PWM][UFS_PWM_G4][UFS_LANE_1] = { 7376, 1000 }, + [MODE_PWM][UFS_PWM_G5][UFS_LANE_1] = { 14752, 1000 }, [MODE_PWM][UFS_PWM_G1][UFS_LANE_2] = { 1844, 1000 }, [MODE_PWM][UFS_PWM_G2][UFS_LANE_2] = { 3688, 1000 }, [MODE_PWM][UFS_PWM_G3][UFS_LANE_2] = { 7376, 1000 }, [MODE_PWM][UFS_PWM_G4][UFS_LANE_2] = { 14752, 1000 }, + [MODE_PWM][UFS_PWM_G5][UFS_LANE_2] = { 29504, 1000 }, [MODE_HS_RA][UFS_HS_G1][UFS_LANE_1] = { 127796, 1000 }, [MODE_HS_RA][UFS_HS_G2][UFS_LANE_1] = { 255591, 1000 }, [MODE_HS_RA][UFS_HS_G3][UFS_LANE_1] = { 1492582, 102400 }, [MODE_HS_RA][UFS_HS_G4][UFS_LANE_1] = { 2915200, 204800 }, + [MODE_HS_RA][UFS_HS_G5][UFS_LANE_1] = { 5836800, 409600 }, [MODE_HS_RA][UFS_HS_G1][UFS_LANE_2] = { 255591, 1000 }, [MODE_HS_RA][UFS_HS_G2][UFS_LANE_2] = { 511181, 1000 }, [MODE_HS_RA][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 }, [MODE_HS_RA][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 }, + [MODE_HS_RA][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 }, [MODE_HS_RB][UFS_HS_G1][UFS_LANE_1] = { 149422, 1000 }, [MODE_HS_RB][UFS_HS_G2][UFS_LANE_1] = { 298189, 1000 }, [MODE_HS_RB][UFS_HS_G3][UFS_LANE_1] = { 1492582, 102400 }, [MODE_HS_RB][UFS_HS_G4][UFS_LANE_1] = { 2915200, 204800 }, + [MODE_HS_RB][UFS_HS_G5][UFS_LANE_1] = { 5836800, 409600 }, [MODE_HS_RB][UFS_HS_G1][UFS_LANE_2] = { 298189, 1000 }, [MODE_HS_RB][UFS_HS_G2][UFS_LANE_2] = { 596378, 1000 }, [MODE_HS_RB][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 }, [MODE_HS_RB][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 }, + [MODE_HS_RB][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 }, [MODE_MAX][0][0] = { 7643136, 307200 }, }; @@ -278,9 +284,6 @@ static void ufs_qcom_select_unipro_mode(struct ufs_qcom_host *host) if (host->hw_ver.major >= 0x05) ufshcd_rmwl(host->hba, QUNIPRO_G4_SEL, 0, REG_UFS_CFG0); - - /* make sure above configuration is applied before we return */ - mb(); } /* @@ -409,7 +412,7 @@ static void ufs_qcom_enable_hw_clk_gating(struct ufs_hba *hba) REG_UFS_CFG2); /* Ensure that HW clock gating is enabled before next operations */ - mb(); + ufshcd_readl(hba, REG_UFS_CFG2); } static int ufs_qcom_hce_enable_notify(struct ufs_hba *hba, @@ -501,7 +504,7 @@ static int ufs_qcom_cfg_timers(struct ufs_hba *hba, u32 gear, * make sure above write gets applied before we return from * this function. */ - mb(); + ufshcd_readl(hba, REG_UFS_SYS1CLK_1US); } return 0; @@ -738,8 +741,17 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba, * the second init can program the optimal PHY settings. This allows one to start * the first init with either the minimum or the maximum support gear. */ - if (hba->ufshcd_state == UFSHCD_STATE_RESET) - host->phy_gear = dev_req_params->gear_tx; + if (hba->ufshcd_state == UFSHCD_STATE_RESET) { + /* + * Skip REINIT if the negotiated gear matches with the + * initial phy_gear. Otherwise, update the phy_gear to + * program the optimal gear setting during REINIT. + */ + if (host->phy_gear == dev_req_params->gear_tx) + hba->quirks &= ~UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH; + else + host->phy_gear = dev_req_params->gear_tx; + } /* enable the device ref clock before changing to HS mode */ if (!ufshcd_is_hs_mode(&hba->pwr_info) && @@ -1196,8 +1208,10 @@ static int ufs_qcom_set_core_clk_ctrl(struct ufs_hba *hba, bool is_scale_up) list_for_each_entry(clki, head, list) { if (!IS_ERR_OR_NULL(clki->clk) && - !strcmp(clki->name, "core_clk_unipro")) { - if (is_scale_up) + !strcmp(clki->name, "core_clk_unipro")) { + if (!clki->max_freq) + cycles_in_1us = 150; /* default for backwards compatibility */ + else if (is_scale_up) cycles_in_1us = ceil(clki->max_freq, (1000 * 1000)); else cycles_in_1us = ceil(clk_get_rate(clki->clk), (1000 * 1000)); diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h index 9dd9a391ebb76..b9de170983c9e 100644 --- a/drivers/ufs/host/ufs-qcom.h +++ b/drivers/ufs/host/ufs-qcom.h @@ -151,10 +151,10 @@ static inline void ufs_qcom_assert_reset(struct ufs_hba *hba) ufshcd_rmwl(hba, UFS_PHY_SOFT_RESET, UFS_PHY_SOFT_RESET, REG_UFS_CFG1); /* - * Make sure assertion of ufs phy reset is written to - * register before returning + * Dummy read to ensure the write takes effect before doing any sort + * of delay */ - mb(); + ufshcd_readl(hba, REG_UFS_CFG1); } static inline void ufs_qcom_deassert_reset(struct ufs_hba *hba) @@ -162,10 +162,10 @@ static inline void ufs_qcom_deassert_reset(struct ufs_hba *hba) ufshcd_rmwl(hba, UFS_PHY_SOFT_RESET, 0, REG_UFS_CFG1); /* - * Make sure de-assertion of ufs phy reset is written to - * register before returning + * Dummy read to ensure the write takes effect before doing any sort + * of delay */ - mb(); + ufshcd_readl(hba, REG_UFS_CFG1); } /* Host controller hardware version: major.minor.step */ diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 20d9762331bd7..6be3462b109ff 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -181,12 +181,14 @@ hv_uio_cleanup(struct hv_device *dev, struct hv_uio_private_data *pdata) { if (pdata->send_gpadl.gpadl_handle) { vmbus_teardown_gpadl(dev->channel, &pdata->send_gpadl); - vfree(pdata->send_buf); + if (!pdata->send_gpadl.decrypted) + vfree(pdata->send_buf); } if (pdata->recv_gpadl.gpadl_handle) { vmbus_teardown_gpadl(dev->channel, &pdata->recv_gpadl); - vfree(pdata->recv_buf); + if (!pdata->recv_gpadl.decrypted) + vfree(pdata->recv_buf); } } @@ -295,7 +297,8 @@ hv_uio_probe(struct hv_device *dev, ret = vmbus_establish_gpadl(channel, pdata->recv_buf, RECV_BUFFER_SIZE, &pdata->recv_gpadl); if (ret) { - vfree(pdata->recv_buf); + if (!pdata->recv_gpadl.decrypted) + vfree(pdata->recv_buf); goto fail_close; } @@ -317,7 +320,8 @@ hv_uio_probe(struct hv_device *dev, ret = vmbus_establish_gpadl(channel, pdata->send_buf, SEND_BUFFER_SIZE, &pdata->send_gpadl); if (ret) { - vfree(pdata->send_buf); + if (!pdata->send_gpadl.decrypted) + vfree(pdata->send_buf); goto fail_close; } diff --git a/drivers/usb/Makefile b/drivers/usb/Makefile index 3a9a0dd4be706..949eca0adebea 100644 --- a/drivers/usb/Makefile +++ b/drivers/usb/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_USB_R8A66597_HCD) += host/ obj-$(CONFIG_USB_FSL_USB2) += host/ obj-$(CONFIG_USB_FOTG210_HCD) += host/ obj-$(CONFIG_USB_MAX3421_HCD) += host/ +obj-$(CONFIG_USB_XEN_HCD) += host/ obj-$(CONFIG_USB_C67X00_HCD) += c67x00/ diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 0e7439dba8fe8..ad7f1720c7639 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1987,6 +1987,20 @@ static const struct usb_device_id acm_ids[] = { .driver_info = IGNORE_DEVICE, }, + /* Exclude Exar USB serial ports */ + { USB_DEVICE(0x04e2, 0x1400), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1401), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1402), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1403), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1410), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1411), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1412), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1414), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1420), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1421), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1422), .driver_info = IGNORE_DEVICE, }, + { USB_DEVICE(0x04e2, 0x1424), .driver_info = IGNORE_DEVICE, }, + /* control interfaces without any protocol set */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM, USB_CDC_PROTO_NONE) }, diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index c553decb54610..6830be4419e20 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -266,14 +266,14 @@ static void wdm_int_callback(struct urb *urb) dev_err(&desc->intf->dev, "Stall on int endpoint\n"); goto sw; /* halt is cleared in work */ default: - dev_err(&desc->intf->dev, + dev_err_ratelimited(&desc->intf->dev, "nonzero urb status received: %d\n", status); break; } } if (urb->actual_length < sizeof(struct usb_cdc_notification)) { - dev_err(&desc->intf->dev, "wdm_int_callback - %d bytes\n", + dev_err_ratelimited(&desc->intf->dev, "wdm_int_callback - %d bytes\n", urb->actual_length); goto exit; } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 12b6dfeaf658c..f3afe58b6bbc9 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1625,6 +1625,7 @@ static void __usb_hcd_giveback_urb(struct urb *urb) struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); struct usb_anchor *anchor = urb->anchor; int status = urb->unlinked; + unsigned long flags; urb->hcpriv = NULL; if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && @@ -1642,13 +1643,14 @@ static void __usb_hcd_giveback_urb(struct urb *urb) /* pass ownership to the completion handler */ urb->status = status; /* - * This function can be called in task context inside another remote - * coverage collection section, but kcov doesn't support that kind of - * recursion yet. Only collect coverage in softirq context for now. + * Only collect coverage in the softirq context and disable interrupts + * to avoid scenarios with nested remote coverage collection sections + * that KCOV does not support. + * See the comment next to kcov_remote_start_usb_softirq() for details. */ - kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); + flags = kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); urb->complete(urb); - kcov_remote_stop_softirq(); + kcov_remote_stop_softirq(flags); usb_anchor_resume_wakeups(anchor); atomic_dec(&urb->use_count); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index e38a4124f6102..48e1e43780eb8 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -129,7 +129,6 @@ EXPORT_SYMBOL_GPL(ehci_cf_port_reset_rwsem); #define HUB_DEBOUNCE_STEP 25 #define HUB_DEBOUNCE_STABLE 100 -static void hub_release(struct kref *kref); static int usb_reset_and_verify_device(struct usb_device *udev); static int hub_port_disable(struct usb_hub *hub, int port1, int set_state); static bool hub_port_warm_reset_required(struct usb_hub *hub, int port1, @@ -691,14 +690,14 @@ static void kick_hub_wq(struct usb_hub *hub) */ intf = to_usb_interface(hub->intfdev); usb_autopm_get_interface_no_resume(intf); - kref_get(&hub->kref); + hub_get(hub); if (queue_work(hub_wq, &hub->events)) return; /* the work has already been scheduled */ usb_autopm_put_interface_async(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); } void usb_kick_hub_wq(struct usb_device *hdev) @@ -1066,7 +1065,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) goto init2; goto init3; } - kref_get(&hub->kref); + hub_get(hub); /* The superspeed hub except for root hub has to use Hub Depth * value as an offset into the route string to locate the bits @@ -1314,7 +1313,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) device_unlock(&hdev->dev); } - kref_put(&hub->kref, hub_release); + hub_put(hub); } /* Implement the continuations for the delays above */ @@ -1730,6 +1729,16 @@ static void hub_release(struct kref *kref) kfree(hub); } +void hub_get(struct usb_hub *hub) +{ + kref_get(&hub->kref); +} + +void hub_put(struct usb_hub *hub) +{ + kref_put(&hub->kref, hub_release); +} + static unsigned highspeed_hubs; static void hub_disconnect(struct usb_interface *intf) @@ -1778,7 +1787,7 @@ static void hub_disconnect(struct usb_interface *intf) onboard_hub_destroy_pdevs(&hub->onboard_hub_devs); - kref_put(&hub->kref, hub_release); + hub_put(hub); } static bool hub_descriptor_is_sane(struct usb_host_interface *desc) @@ -5072,9 +5081,10 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, } if (usb_endpoint_maxp(&udev->ep0.desc) == i) { ; /* Initial ep0 maxpacket guess is right */ - } else if ((udev->speed == USB_SPEED_FULL || + } else if (((udev->speed == USB_SPEED_FULL || udev->speed == USB_SPEED_HIGH) && - (i == 8 || i == 16 || i == 32 || i == 64)) { + (i == 8 || i == 16 || i == 32 || i == 64)) || + (udev->speed >= USB_SPEED_SUPER && i > 0)) { /* Initial guess is wrong; use the descriptor's value */ if (udev->speed == USB_SPEED_FULL) dev_dbg(&udev->dev, "ep0 maxpacket = %d\n", i); @@ -5905,7 +5915,7 @@ static void hub_event(struct work_struct *work) /* Balance the stuff in kick_hub_wq() and allow autosuspend */ usb_autopm_put_interface(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); kcov_remote_stop(); } diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h index 43ce21c96a511..183b69dc29554 100644 --- a/drivers/usb/core/hub.h +++ b/drivers/usb/core/hub.h @@ -129,6 +129,8 @@ extern void usb_hub_remove_port_device(struct usb_hub *hub, extern int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub, int port1, bool set); extern struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev); +extern void hub_get(struct usb_hub *hub); +extern void hub_put(struct usb_hub *hub); extern int hub_port_debounce(struct usb_hub *hub, int port1, bool must_be_connected); extern int usb_clear_port_feature(struct usb_device *hdev, diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 4d63496f98b6c..d34d67fcb47b2 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -50,16 +50,29 @@ static ssize_t disable_show(struct device *dev, struct usb_port *port_dev = to_usb_port(dev); struct usb_device *hdev = to_usb_device(dev->parent->parent); struct usb_hub *hub = usb_hub_to_struct_hub(hdev); - struct usb_interface *intf = to_usb_interface(hub->intfdev); + struct usb_interface *intf = to_usb_interface(dev->parent); int port1 = port_dev->portnum; u16 portstatus, unused; bool disabled; int rc; + struct kernfs_node *kn; + if (!hub) + return -ENODEV; + hub_get(hub); rc = usb_autopm_get_interface(intf); if (rc < 0) - return rc; + goto out_hub_get; + /* + * Prevent deadlock if another process is concurrently + * trying to unregister hdev. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (!kn) { + rc = -ENODEV; + goto out_autopm; + } usb_lock_device(hdev); if (hub->disconnected) { rc = -ENODEV; @@ -69,9 +82,13 @@ static ssize_t disable_show(struct device *dev, usb_hub_port_status(hub, port1, &portstatus, &unused); disabled = !usb_port_is_power_on(hub, portstatus); -out_hdev_lock: + out_hdev_lock: usb_unlock_device(hdev); + sysfs_unbreak_active_protection(kn); + out_autopm: usb_autopm_put_interface(intf); + out_hub_get: + hub_put(hub); if (rc) return rc; @@ -85,19 +102,32 @@ static ssize_t disable_store(struct device *dev, struct device_attribute *attr, struct usb_port *port_dev = to_usb_port(dev); struct usb_device *hdev = to_usb_device(dev->parent->parent); struct usb_hub *hub = usb_hub_to_struct_hub(hdev); - struct usb_interface *intf = to_usb_interface(hub->intfdev); + struct usb_interface *intf = to_usb_interface(dev->parent); int port1 = port_dev->portnum; bool disabled; int rc; + struct kernfs_node *kn; + if (!hub) + return -ENODEV; rc = kstrtobool(buf, &disabled); if (rc) return rc; + hub_get(hub); rc = usb_autopm_get_interface(intf); if (rc < 0) - return rc; + goto out_hub_get; + /* + * Prevent deadlock if another process is concurrently + * trying to unregister hdev. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (!kn) { + rc = -ENODEV; + goto out_autopm; + } usb_lock_device(hdev); if (hub->disconnected) { rc = -ENODEV; @@ -118,9 +148,13 @@ static ssize_t disable_store(struct device *dev, struct device_attribute *attr, if (!rc) rc = count; -out_hdev_lock: + out_hdev_lock: usb_unlock_device(hdev); + sysfs_unbreak_active_protection(kn); + out_autopm: usb_autopm_put_interface(intf); + out_hub_get: + hub_put(hub); return rc; } @@ -418,8 +452,10 @@ static void usb_port_shutdown(struct device *dev) { struct usb_port *port_dev = to_usb_port(dev); - if (port_dev->child) + if (port_dev->child) { usb_disable_usb2_hardware_lpm(port_dev->child); + usb_unlocked_disable_lpm(port_dev->child); + } } static const struct dev_pm_ops usb_port_pm_ops = { diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index 5d21718afb05c..f91f543ec636d 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -1168,14 +1168,24 @@ static ssize_t interface_authorized_store(struct device *dev, { struct usb_interface *intf = to_usb_interface(dev); bool val; + struct kernfs_node *kn; if (kstrtobool(buf, &val) != 0) return -EINVAL; - if (val) + if (val) { usb_authorize_interface(intf); - else - usb_deauthorize_interface(intf); + } else { + /* + * Prevent deadlock if another process is concurrently + * trying to unregister intf. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (kn) { + usb_deauthorize_interface(intf); + sysfs_unbreak_active_protection(kn); + } + } return count; } diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index c92a1da46a014..a141f83aba0cc 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -729,8 +729,14 @@ struct dwc2_dregs_backup { * struct dwc2_hregs_backup - Holds host registers state before * entering partial power down * @hcfg: Backup of HCFG register + * @hflbaddr: Backup of HFLBADDR register * @haintmsk: Backup of HAINTMSK register + * @hcchar: Backup of HCCHAR register + * @hcsplt: Backup of HCSPLT register * @hcintmsk: Backup of HCINTMSK register + * @hctsiz: Backup of HCTSIZ register + * @hdma: Backup of HCDMA register + * @hcdmab: Backup of HCDMAB register * @hprt0: Backup of HPTR0 register * @hfir: Backup of HFIR register * @hptxfsiz: Backup of HPTXFSIZ register @@ -738,8 +744,14 @@ struct dwc2_dregs_backup { */ struct dwc2_hregs_backup { u32 hcfg; + u32 hflbaddr; u32 haintmsk; + u32 hcchar[MAX_EPS_CHANNELS]; + u32 hcsplt[MAX_EPS_CHANNELS]; u32 hcintmsk[MAX_EPS_CHANNELS]; + u32 hctsiz[MAX_EPS_CHANNELS]; + u32 hcidma[MAX_EPS_CHANNELS]; + u32 hcidmab[MAX_EPS_CHANNELS]; u32 hprt0; u32 hfir; u32 hptxfsiz; @@ -1086,6 +1098,7 @@ struct dwc2_hsotg { bool needs_byte_swap; /* DWC OTG HW Release versions */ +#define DWC2_CORE_REV_4_30a 0x4f54430a #define DWC2_CORE_REV_2_71a 0x4f54271a #define DWC2_CORE_REV_2_72a 0x4f54272a #define DWC2_CORE_REV_2_80a 0x4f54280a @@ -1323,6 +1336,7 @@ int dwc2_backup_global_registers(struct dwc2_hsotg *hsotg); int dwc2_restore_global_registers(struct dwc2_hsotg *hsotg); void dwc2_enable_acg(struct dwc2_hsotg *hsotg); +void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup); /* This function should be called on every hardware interrupt. */ irqreturn_t dwc2_handle_common_intr(int irq, void *dev); diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c index 158ede7538548..26d752a4c3ca9 100644 --- a/drivers/usb/dwc2/core_intr.c +++ b/drivers/usb/dwc2/core_intr.c @@ -297,7 +297,8 @@ static void dwc2_handle_session_req_intr(struct dwc2_hsotg *hsotg) /* Exit gadget mode clock gating. */ if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_gadget_exit_clock_gating(hsotg, 0); } @@ -322,10 +323,11 @@ static void dwc2_handle_session_req_intr(struct dwc2_hsotg *hsotg) * @hsotg: Programming view of DWC_otg controller * */ -static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg) +void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup) { u32 glpmcfg; - u32 i = 0; + u32 pcgctl; + u32 dctl; if (hsotg->lx_state != DWC2_L1) { dev_err(hsotg->dev, "Core isn't in DWC2_L1 state\n"); @@ -334,37 +336,57 @@ static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg) glpmcfg = dwc2_readl(hsotg, GLPMCFG); if (dwc2_is_device_mode(hsotg)) { - dev_dbg(hsotg->dev, "Exit from L1 state\n"); + dev_dbg(hsotg->dev, "Exit from L1 state, remotewakeup=%d\n", remotewakeup); glpmcfg &= ~GLPMCFG_ENBLSLPM; - glpmcfg &= ~GLPMCFG_HIRD_THRES_EN; + glpmcfg &= ~GLPMCFG_HIRD_THRES_MASK; dwc2_writel(hsotg, glpmcfg, GLPMCFG); - do { - glpmcfg = dwc2_readl(hsotg, GLPMCFG); + pcgctl = dwc2_readl(hsotg, PCGCTL); + pcgctl &= ~PCGCTL_ENBL_SLEEP_GATING; + dwc2_writel(hsotg, pcgctl, PCGCTL); - if (!(glpmcfg & (GLPMCFG_COREL1RES_MASK | - GLPMCFG_L1RESUMEOK | GLPMCFG_SLPSTS))) - break; + glpmcfg = dwc2_readl(hsotg, GLPMCFG); + if (glpmcfg & GLPMCFG_ENBESL) { + glpmcfg |= GLPMCFG_RSTRSLPSTS; + dwc2_writel(hsotg, glpmcfg, GLPMCFG); + } + + if (remotewakeup) { + if (dwc2_hsotg_wait_bit_set(hsotg, GLPMCFG, GLPMCFG_L1RESUMEOK, 1000)) { + dev_warn(hsotg->dev, "%s: timeout GLPMCFG_L1RESUMEOK\n", __func__); + goto fail; + return; + } + + dctl = dwc2_readl(hsotg, DCTL); + dctl |= DCTL_RMTWKUPSIG; + dwc2_writel(hsotg, dctl, DCTL); - udelay(1); - } while (++i < 200); + if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS, GINTSTS_WKUPINT, 1000)) { + dev_warn(hsotg->dev, "%s: timeout GINTSTS_WKUPINT\n", __func__); + goto fail; + return; + } + } - if (i == 200) { - dev_err(hsotg->dev, "Failed to exit L1 sleep state in 200us.\n"); + glpmcfg = dwc2_readl(hsotg, GLPMCFG); + if (glpmcfg & GLPMCFG_COREL1RES_MASK || glpmcfg & GLPMCFG_SLPSTS || + glpmcfg & GLPMCFG_L1RESUMEOK) { + goto fail; return; } - dwc2_gadget_init_lpm(hsotg); + + /* Inform gadget to exit from L1 */ + call_gadget(hsotg, resume); + /* Change to L0 state */ + hsotg->lx_state = DWC2_L0; + hsotg->bus_suspended = false; +fail: dwc2_gadget_init_lpm(hsotg); } else { /* TODO */ dev_err(hsotg->dev, "Host side LPM is not supported.\n"); return; } - - /* Change to L0 state */ - hsotg->lx_state = DWC2_L0; - - /* Inform gadget to exit from L1 */ - call_gadget(hsotg, resume); } /* @@ -385,7 +407,7 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) dev_dbg(hsotg->dev, "%s lxstate = %d\n", __func__, hsotg->lx_state); if (hsotg->lx_state == DWC2_L1) { - dwc2_wakeup_from_lpm_l1(hsotg); + dwc2_wakeup_from_lpm_l1(hsotg, false); return; } @@ -408,7 +430,8 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) /* Exit gadget mode clock gating. */ if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_gadget_exit_clock_gating(hsotg, 0); } else { /* Change to L0 state */ @@ -425,7 +448,8 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) } if (hsotg->params.power_down == - DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended) + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) dwc2_host_exit_clock_gating(hsotg, 1); /* diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index b517a7216de22..b2f6da5b65ccd 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1415,6 +1415,10 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req, ep->name, req, req->length, req->buf, req->no_interrupt, req->zero, req->short_not_ok); + if (hs->lx_state == DWC2_L1) { + dwc2_wakeup_from_lpm_l1(hs, true); + } + /* Prevent new request submission when controller is suspended */ if (hs->lx_state != DWC2_L0) { dev_dbg(hs->dev, "%s: submit request only in active state\n", @@ -3727,6 +3731,12 @@ static irqreturn_t dwc2_hsotg_irq(int irq, void *pw) if (hsotg->in_ppd && hsotg->lx_state == DWC2_L2) dwc2_exit_partial_power_down(hsotg, 0, true); + /* Exit gadget mode clock gating. */ + if (hsotg->params.power_down == + DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended && + !hsotg->params.no_clock_gating) + dwc2_gadget_exit_clock_gating(hsotg, 0); + hsotg->lx_state = DWC2_L0; } diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index 35c7a4df8e717..dd5b1c5691e11 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2701,8 +2701,11 @@ enum dwc2_transaction_type dwc2_hcd_select_transactions( hsotg->available_host_channels--; } qh = list_entry(qh_ptr, struct dwc2_qh, qh_list_entry); - if (dwc2_assign_and_init_hc(hsotg, qh)) + if (dwc2_assign_and_init_hc(hsotg, qh)) { + if (hsotg->params.uframe_sched) + hsotg->available_host_channels++; break; + } /* * Move the QH from the periodic ready schedule to the @@ -2735,8 +2738,11 @@ enum dwc2_transaction_type dwc2_hcd_select_transactions( hsotg->available_host_channels--; } - if (dwc2_assign_and_init_hc(hsotg, qh)) + if (dwc2_assign_and_init_hc(hsotg, qh)) { + if (hsotg->params.uframe_sched) + hsotg->available_host_channels++; break; + } /* * Move the QH from the non-periodic inactive schedule to the @@ -4143,6 +4149,8 @@ void dwc2_host_complete(struct dwc2_hsotg *hsotg, struct dwc2_qtd *qtd, urb->actual_length); if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) { + if (!hsotg->params.dma_desc_enable) + urb->start_frame = qtd->qh->start_active_frame; urb->error_count = dwc2_hcd_urb_get_error_count(qtd->urb); for (i = 0; i < urb->number_of_packets; ++i) { urb->iso_frame_desc[i].actual_length = @@ -4649,7 +4657,7 @@ static int _dwc2_hcd_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, } if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE && - hsotg->bus_suspended) { + hsotg->bus_suspended && !hsotg->params.no_clock_gating) { if (dwc2_is_device_mode(hsotg)) dwc2_gadget_exit_clock_gating(hsotg, 0); else @@ -5406,9 +5414,16 @@ int dwc2_backup_host_registers(struct dwc2_hsotg *hsotg) /* Backup Host regs */ hr = &hsotg->hr_backup; hr->hcfg = dwc2_readl(hsotg, HCFG); + hr->hflbaddr = dwc2_readl(hsotg, HFLBADDR); hr->haintmsk = dwc2_readl(hsotg, HAINTMSK); - for (i = 0; i < hsotg->params.host_channels; ++i) + for (i = 0; i < hsotg->params.host_channels; ++i) { + hr->hcchar[i] = dwc2_readl(hsotg, HCCHAR(i)); + hr->hcsplt[i] = dwc2_readl(hsotg, HCSPLT(i)); hr->hcintmsk[i] = dwc2_readl(hsotg, HCINTMSK(i)); + hr->hctsiz[i] = dwc2_readl(hsotg, HCTSIZ(i)); + hr->hcidma[i] = dwc2_readl(hsotg, HCDMA(i)); + hr->hcidmab[i] = dwc2_readl(hsotg, HCDMAB(i)); + } hr->hprt0 = dwc2_read_hprt0(hsotg); hr->hfir = dwc2_readl(hsotg, HFIR); @@ -5442,10 +5457,17 @@ int dwc2_restore_host_registers(struct dwc2_hsotg *hsotg) hr->valid = false; dwc2_writel(hsotg, hr->hcfg, HCFG); + dwc2_writel(hsotg, hr->hflbaddr, HFLBADDR); dwc2_writel(hsotg, hr->haintmsk, HAINTMSK); - for (i = 0; i < hsotg->params.host_channels; ++i) + for (i = 0; i < hsotg->params.host_channels; ++i) { + dwc2_writel(hsotg, hr->hcchar[i], HCCHAR(i)); + dwc2_writel(hsotg, hr->hcsplt[i], HCSPLT(i)); dwc2_writel(hsotg, hr->hcintmsk[i], HCINTMSK(i)); + dwc2_writel(hsotg, hr->hctsiz[i], HCTSIZ(i)); + dwc2_writel(hsotg, hr->hcidma[i], HCDMA(i)); + dwc2_writel(hsotg, hr->hcidmab[i], HCDMAB(i)); + } dwc2_writel(hsotg, hr->hprt0, HPRT0); dwc2_writel(hsotg, hr->hfir, HFIR); @@ -5610,10 +5632,12 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup, dwc2_writel(hsotg, hr->hcfg, HCFG); /* De-assert Wakeup Logic */ - gpwrdn = dwc2_readl(hsotg, GPWRDN); - gpwrdn &= ~GPWRDN_PMUACTV; - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + if (!(rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) { + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn &= ~GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } hprt0 = hr->hprt0; hprt0 |= HPRT0_PWR; @@ -5638,6 +5662,13 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup, hprt0 |= HPRT0_RES; dwc2_writel(hsotg, hprt0, HPRT0); + /* De-assert Wakeup Logic */ + if ((rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) { + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn &= ~GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } /* Wait for Resume time and then program HPRT again */ mdelay(100); hprt0 &= ~HPRT0_RES; diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index 6b4d825e97a2d..994a78ad084b1 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -559,7 +559,7 @@ static void dwc2_init_isoc_dma_desc(struct dwc2_hsotg *hsotg, idx = qh->td_last; inc = qh->host_interval; hsotg->frame_number = dwc2_hcd_get_frame_number(hsotg); - cur_idx = dwc2_frame_list_idx(hsotg->frame_number); + cur_idx = idx; next_idx = dwc2_desclist_idx_inc(qh->td_last, inc, qh->dev_speed); /* @@ -866,20 +866,27 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, { struct dwc2_dma_desc *dma_desc; struct dwc2_hcd_iso_packet_desc *frame_desc; + u16 frame_desc_idx; + struct urb *usb_urb; u16 remain = 0; int rc = 0; if (!qtd->urb) return -EINVAL; + usb_urb = qtd->urb->priv; + dma_sync_single_for_cpu(hsotg->dev, qh->desc_list_dma + (idx * sizeof(struct dwc2_dma_desc)), sizeof(struct dwc2_dma_desc), DMA_FROM_DEVICE); dma_desc = &qh->desc_list[idx]; + frame_desc_idx = (idx - qtd->isoc_td_first) & (usb_urb->number_of_packets - 1); - frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index_last]; + frame_desc = &qtd->urb->iso_descs[frame_desc_idx]; + if (idx == qtd->isoc_td_first) + usb_urb->start_frame = dwc2_hcd_get_frame_number(hsotg); dma_desc->buf = (u32)(qtd->urb->dma + frame_desc->offset); if (chan->ep_is_in) remain = (dma_desc->status & HOST_DMA_ISOC_NBYTES_MASK) >> @@ -900,7 +907,7 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, frame_desc->status = 0; } - if (++qtd->isoc_frame_index == qtd->urb->packet_count) { + if (++qtd->isoc_frame_index == usb_urb->number_of_packets) { /* * urb->status is not used for isoc transfers here. The * individual frame_desc status are used instead. @@ -1005,11 +1012,11 @@ static void dwc2_complete_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, return; idx = dwc2_desclist_idx_inc(idx, qh->host_interval, chan->speed); - if (!rc) + if (rc == 0) continue; - if (rc == DWC2_CMPL_DONE) - break; + if (rc == DWC2_CMPL_DONE || rc == DWC2_CMPL_STOP) + goto stop_scan; /* rc == DWC2_CMPL_STOP */ diff --git a/drivers/usb/dwc2/hw.h b/drivers/usb/dwc2/hw.h index 13abdd5f67529..12f8c7f86dc98 100644 --- a/drivers/usb/dwc2/hw.h +++ b/drivers/usb/dwc2/hw.h @@ -698,7 +698,7 @@ #define TXSTS_QTOP_TOKEN_MASK (0x3 << 25) #define TXSTS_QTOP_TOKEN_SHIFT 25 #define TXSTS_QTOP_TERMINATE BIT(24) -#define TXSTS_QSPCAVAIL_MASK (0xff << 16) +#define TXSTS_QSPCAVAIL_MASK (0x7f << 16) #define TXSTS_QSPCAVAIL_SHIFT 16 #define TXSTS_FSPCAVAIL_MASK (0xffff << 0) #define TXSTS_FSPCAVAIL_SHIFT 0 diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index b1d48019e944f..7b84416dfc2b1 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -331,7 +331,7 @@ static void dwc2_driver_remove(struct platform_device *dev) /* Exit clock gating when driver is removed. */ if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE && - hsotg->bus_suspended) { + hsotg->bus_suspended && !hsotg->params.no_clock_gating) { if (dwc2_is_device_mode(hsotg)) dwc2_gadget_exit_clock_gating(hsotg, 0); else diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 3e55838c00014..100041320e8dd 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -104,6 +104,27 @@ static int dwc3_get_dr_mode(struct dwc3 *dwc) return 0; } +void dwc3_enable_susphy(struct dwc3 *dwc, bool enable) +{ + u32 reg; + + reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); + if (enable && !dwc->dis_u3_susphy_quirk) + reg |= DWC3_GUSB3PIPECTL_SUSPHY; + else + reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; + + dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), reg); + + reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + if (enable && !dwc->dis_u2_susphy_quirk) + reg |= DWC3_GUSB2PHYCFG_SUSPHY; + else + reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; + + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); +} + void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode) { u32 reg; @@ -585,11 +606,8 @@ static int dwc3_core_ulpi_init(struct dwc3 *dwc) */ static int dwc3_phy_setup(struct dwc3 *dwc) { - unsigned int hw_mode; u32 reg; - hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); - reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); /* @@ -599,21 +617,16 @@ static int dwc3_phy_setup(struct dwc3 *dwc) reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX; /* - * Above 1.94a, it is recommended to set DWC3_GUSB3PIPECTL_SUSPHY - * to '0' during coreConsultant configuration. So default value - * will be '0' when the core is reset. Application needs to set it - * to '1' after the core initialization is completed. - */ - if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) - reg |= DWC3_GUSB3PIPECTL_SUSPHY; - - /* - * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be cleared after - * power-on reset, and it can be set after core initialization, which is - * after device soft-reset during initialization. + * Above DWC_usb3.0 1.94a, it is recommended to set + * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration. + * So default value will be '0' when the core is reset. Application + * needs to set it to '1' after the core initialization is completed. + * + * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be + * cleared after power-on reset, and it can be set after core + * initialization. */ - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD) - reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; + reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; if (dwc->u2ss_inp3_quirk) reg |= DWC3_GUSB3PIPECTL_U2SSINP3OK; @@ -639,9 +652,6 @@ static int dwc3_phy_setup(struct dwc3 *dwc) if (dwc->tx_de_emphasis_quirk) reg |= DWC3_GUSB3PIPECTL_TX_DEEPH(dwc->tx_de_emphasis); - if (dwc->dis_u3_susphy_quirk) - reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; - if (dwc->dis_del_phy_power_chg_quirk) reg &= ~DWC3_GUSB3PIPECTL_DEPOCHANGE; @@ -689,24 +699,15 @@ static int dwc3_phy_setup(struct dwc3 *dwc) } /* - * Above 1.94a, it is recommended to set DWC3_GUSB2PHYCFG_SUSPHY to - * '0' during coreConsultant configuration. So default value will - * be '0' when the core is reset. Application needs to set it to - * '1' after the core initialization is completed. - */ - if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) - reg |= DWC3_GUSB2PHYCFG_SUSPHY; - - /* - * For DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared after - * power-on reset, and it can be set after core initialization, which is - * after device soft-reset during initialization. + * Above DWC_usb3.0 1.94a, it is recommended to set + * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration. + * So default value will be '0' when the core is reset. Application + * needs to set it to '1' after the core initialization is completed. + * + * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared + * after power-on reset, and it can be set after core initialization. */ - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD) - reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; - - if (dwc->dis_u2_susphy_quirk) - reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; + reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; if (dwc->dis_enblslpm_quirk) reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM; @@ -1227,21 +1228,6 @@ static int dwc3_core_init(struct dwc3 *dwc) if (ret) goto err_exit_phy; - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && - !DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) { - if (!dwc->dis_u3_susphy_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); - reg |= DWC3_GUSB3PIPECTL_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), reg); - } - - if (!dwc->dis_u2_susphy_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); - reg |= DWC3_GUSB2PHYCFG_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); - } - } - dwc3_core_setup_global_control(dwc); dwc3_core_num_eps(dwc); @@ -1519,6 +1505,8 @@ static void dwc3_get_properties(struct dwc3 *dwc) else dwc->sysdev = dwc->dev; + dwc->sys_wakeup = device_may_wakeup(dwc->sysdev); + ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name); if (ret >= 0) { dwc->usb_psy = power_supply_get_by_name(usb_psy_name); diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index e120611a5174f..d96a28eecbcc3 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1132,6 +1132,7 @@ struct dwc3_scratchpad_array { * 3 - Reserved * @dis_metastability_quirk: set to disable metastability quirk. * @dis_split_quirk: set to disable split boundary. + * @sys_wakeup: set if the device may do system wakeup. * @wakeup_configured: set if the device is configured for remote wakeup. * @suspended: set to track suspend event due to U3/L2. * @imod_interval: set the interrupt moderation interval in 250ns @@ -1355,6 +1356,7 @@ struct dwc3 { unsigned dis_split_quirk:1; unsigned async_callbacks:1; + unsigned sys_wakeup:1; unsigned wakeup_configured:1; unsigned suspended:1; @@ -1576,6 +1578,7 @@ int dwc3_event_buffers_setup(struct dwc3 *dwc); void dwc3_event_buffers_cleanup(struct dwc3 *dwc); int dwc3_core_soft_reset(struct dwc3 *dwc); +void dwc3_enable_susphy(struct dwc3 *dwc, bool enable); #if IS_ENABLED(CONFIG_USB_DWC3_HOST) || IS_ENABLED(CONFIG_USB_DWC3_DUAL_ROLE) int dwc3_host_init(struct dwc3 *dwc); diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index 90a587bc29b74..ea6e29091c0c9 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -267,21 +267,15 @@ static int dwc3_ti_probe(struct platform_device *pdev) return ret; } -static int dwc3_ti_remove_core(struct device *dev, void *c) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - return 0; -} - static void dwc3_ti_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct dwc3_am62 *am62 = platform_get_drvdata(pdev); u32 reg; - device_for_each_child(dev, NULL, dwc3_ti_remove_core); + pm_runtime_get_sync(dev); + device_init_wakeup(dev, false); + of_platform_depopulate(dev); /* Clear mode valid bit */ reg = dwc3_ti_readl(am62, USBSS_MODE_CONTROL); @@ -289,7 +283,6 @@ static void dwc3_ti_remove(struct platform_device *pdev) dwc3_ti_writel(am62, USBSS_MODE_CONTROL, reg); pm_runtime_put_sync(dev); - clk_disable_unprepare(am62->usb2_refclk); pm_runtime_disable(dev); pm_runtime_set_suspended(dev); } diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 39564e17f3b07..9ef821ca2fc71 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -8,6 +8,7 @@ * Sebastian Andrzej Siewior */ +#include #include #include #include @@ -51,7 +52,6 @@ #define PCI_DEVICE_ID_INTEL_MTLP 0x7ec1 #define PCI_DEVICE_ID_INTEL_MTLS 0x7f6f #define PCI_DEVICE_ID_INTEL_MTL 0x7e7e -#define PCI_DEVICE_ID_INTEL_ARLH 0x7ec1 #define PCI_DEVICE_ID_INTEL_ARLH_PCH 0x777e #define PCI_DEVICE_ID_INTEL_TGL 0x9a15 #define PCI_DEVICE_ID_AMD_MR 0x163a @@ -221,6 +221,7 @@ static int dwc3_pci_quirks(struct dwc3_pci *dwc, if (pdev->device == PCI_DEVICE_ID_INTEL_BYT) { struct gpio_desc *gpio; + const char *bios_ver; int ret; /* On BYT the FW does not always enable the refclock */ @@ -278,8 +279,12 @@ static int dwc3_pci_quirks(struct dwc3_pci *dwc, * detection. These can be identified by them _not_ * using the standard ACPI battery and ac drivers. */ + bios_ver = dmi_get_system_info(DMI_BIOS_VERSION); if (acpi_dev_present("INT33FD", "1", 2) && - acpi_quirk_skip_acpi_ac_and_battery()) { + acpi_quirk_skip_acpi_ac_and_battery() && + /* Lenovo Yoga Tablet 2 Pro 1380 uses LC824206XA instead */ + !(bios_ver && + strstarts(bios_ver, "BLADE_21.X64.0005.R00.1504101516"))) { dev_info(&pdev->dev, "Using TUSB1211 phy for charger detection\n"); swnode = &dwc3_pci_intel_phy_charger_detect_swnode; } @@ -423,7 +428,6 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_DEVICE_DATA(INTEL, MTLP, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, MTL, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, MTLS, &dwc3_pci_intel_swnode) }, - { PCI_DEVICE_DATA(INTEL, ARLH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, ARLH_PCH, &dwc3_pci_intel_swnode) }, { PCI_DEVICE_DATA(INTEL, TGL, &dwc3_pci_intel_swnode) }, diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 28f49400f3e8b..579d90efc281a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1718,7 +1718,6 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc) */ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) { - struct dwc3 *dwc = dep->dwc; struct dwc3_gadget_ep_cmd_params params; u32 cmd; int ret; @@ -1743,8 +1742,7 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int dep->resource_index = 0; if (!interrupt) { - if (!DWC3_IP_IS(DWC3) || DWC3_VER_IS_PRIOR(DWC3, 310A)) - mdelay(1); + mdelay(1); dep->flags &= ~DWC3_EP_TRANSFER_STARTED; } else if (!ret) { dep->flags |= DWC3_EP_END_TRANSFER_PENDING; @@ -2937,6 +2935,7 @@ static int __dwc3_gadget_start(struct dwc3 *dwc) dwc3_ep0_out_start(dwc); dwc3_gadget_enable_irq(dwc); + dwc3_enable_susphy(dwc, true); return 0; @@ -2968,6 +2967,9 @@ static int dwc3_gadget_start(struct usb_gadget *g, dwc->gadget_driver = driver; spin_unlock_irqrestore(&dwc->lock, flags); + if (dwc->sys_wakeup) + device_wakeup_enable(dwc->sysdev); + return 0; } @@ -2983,6 +2985,9 @@ static int dwc3_gadget_stop(struct usb_gadget *g) struct dwc3 *dwc = gadget_to_dwc(g); unsigned long flags; + if (dwc->sys_wakeup) + device_wakeup_disable(dwc->sysdev); + spin_lock_irqsave(&dwc->lock, flags); dwc->gadget_driver = NULL; dwc->max_cfg_eps = 0; @@ -4664,6 +4669,10 @@ int dwc3_gadget_init(struct dwc3 *dwc) else dwc3_gadget_set_speed(dwc->gadget, dwc->maximum_speed); + /* No system wakeup if no gadget driver bound */ + if (dwc->sys_wakeup) + device_wakeup_disable(dwc->sysdev); + return 0; err5: @@ -4693,6 +4702,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc) if (!dwc->gadget) return; + dwc3_enable_susphy(dwc, false); usb_del_gadget(dwc->gadget); dwc3_gadget_free_endpoints(dwc); usb_put_gadget(dwc->gadget); diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c index 43230915323c7..6c143f7d24103 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -10,9 +10,30 @@ #include #include #include +#include +#include +#include "../host/xhci-plat.h" #include "core.h" +static void dwc3_xhci_plat_start(struct usb_hcd *hcd) +{ + struct platform_device *pdev; + struct dwc3 *dwc; + + if (!usb_hcd_is_primary_hcd(hcd)) + return; + + pdev = to_platform_device(hcd->self.controller); + dwc = dev_get_drvdata(pdev->dev.parent); + + dwc3_enable_susphy(dwc, true); +} + +static const struct xhci_plat_priv dwc3_xhci_plat_quirk = { + .plat_start = dwc3_xhci_plat_start, +}; + static void dwc3_host_fill_xhci_irq_res(struct dwc3 *dwc, int irq, char *name) { @@ -117,12 +138,25 @@ int dwc3_host_init(struct dwc3 *dwc) } } + ret = platform_device_add_data(xhci, &dwc3_xhci_plat_quirk, + sizeof(struct xhci_plat_priv)); + if (ret) + goto err; + ret = platform_device_add(xhci); if (ret) { dev_err(dwc->dev, "failed to register xHCI device\n"); goto err; } + if (dwc->sys_wakeup) { + /* Restore wakeup setting if switched from device */ + device_wakeup_enable(dwc->sysdev); + + /* Pass on wakeup setting to the new xhci platform device */ + device_init_wakeup(&xhci->dev, true); + } + return 0; err: platform_device_put(xhci); @@ -131,6 +165,10 @@ int dwc3_host_init(struct dwc3 *dwc) void dwc3_host_exit(struct dwc3 *dwc) { + if (dwc->sys_wakeup) + device_init_wakeup(&dwc->xhci->dev, false); + + dwc3_enable_susphy(dwc, false); platform_device_unregister(dwc->xhci); dwc->xhci = NULL; } diff --git a/drivers/usb/fotg210/fotg210-core.c b/drivers/usb/fotg210/fotg210-core.c index 958fc40eae86b..0655afe7f9779 100644 --- a/drivers/usb/fotg210/fotg210-core.c +++ b/drivers/usb/fotg210/fotg210-core.c @@ -95,6 +95,7 @@ static int fotg210_gemini_init(struct fotg210 *fotg, struct resource *res, /** * fotg210_vbus() - Called by gadget driver to enable/disable VBUS + * @fotg: pointer to a private fotg210 object * @enable: true to enable VBUS, false to disable VBUS */ void fotg210_vbus(struct fotg210 *fotg, bool enable) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 0ace45b66a31c..0e151b54aae82 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2112,7 +2112,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) buf[5] = 0x01; switch (ctrl->bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: - if (w_index != 0x4 || (w_value >> 8)) + if (w_index != 0x4 || (w_value & 0xff)) break; buf[6] = w_index; /* Number of ext compat interfaces */ @@ -2128,9 +2128,9 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) } break; case USB_RECIP_INTERFACE: - if (w_index != 0x5 || (w_value >> 8)) + if (w_index != 0x5 || (w_value & 0xff)) break; - interface = w_value & 0xFF; + interface = w_value >> 8; if (interface >= MAX_CONFIG_INTERFACES || !os_desc_cfg->interface[interface]) break; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 6bff6cb937891..839426d92b995 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -821,6 +821,7 @@ static void ffs_user_copy_worker(struct work_struct *work) work); int ret = io_data->status; bool kiocb_has_eventfd = io_data->kiocb->ki_flags & IOCB_EVENTFD; + unsigned long flags; if (io_data->read && ret > 0) { kthread_use_mm(io_data->mm); @@ -833,6 +834,11 @@ static void ffs_user_copy_worker(struct work_struct *work) if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd) eventfd_signal(io_data->ffs->ffs_eventfd); + spin_lock_irqsave(&io_data->ffs->eps_lock, flags); + usb_ep_free_request(io_data->ep, io_data->req); + io_data->req = NULL; + spin_unlock_irqrestore(&io_data->ffs->eps_lock, flags); + if (io_data->read) kfree(io_data->to_free); ffs_free_buffer(io_data); @@ -846,7 +852,6 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep, struct ffs_data *ffs = io_data->ffs; io_data->status = req->status ? req->status : req->actual; - usb_ep_free_request(_ep, req); INIT_WORK(&io_data->work, ffs_user_copy_worker); queue_work(ffs->io_completion_wq, &io_data->work); @@ -3330,7 +3335,7 @@ static int ffs_func_setup(struct usb_function *f, __ffs_event_add(ffs, FUNCTIONFS_SETUP); spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags); - return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; + return ffs->ev.setup.wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; } static bool ffs_func_req_match(struct usb_function *f, diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 3c8a9dd585c09..2db01e03bfbf0 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -1029,9 +1029,9 @@ static inline int hidg_get_minor(void) { int ret; - ret = ida_simple_get(&hidg_ida, 0, 0, GFP_KERNEL); + ret = ida_alloc(&hidg_ida, GFP_KERNEL); if (ret >= HIDG_MINORS) { - ida_simple_remove(&hidg_ida, ret); + ida_free(&hidg_ida, ret); ret = -ENODEV; } @@ -1176,7 +1176,7 @@ static const struct config_item_type hid_func_type = { static inline void hidg_put_minor(int minor) { - ida_simple_remove(&hidg_ida, minor); + ida_free(&hidg_ida, minor); } static void hidg_free_inst(struct usb_function_instance *f) diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 28f4e6552e845..0acc32ed99609 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -878,7 +878,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (alt > 1) goto fail; - if (ncm->port.in_ep->enabled) { + if (ncm->netdev) { DBG(cdev, "reset ncm\n"); ncm->netdev = NULL; gether_disconnect(&ncm->port); @@ -1367,7 +1367,7 @@ static void ncm_disable(struct usb_function *f) DBG(cdev, "ncm deactivated\n"); - if (ncm->port.in_ep->enabled) { + if (ncm->netdev) { ncm->netdev = NULL; gether_disconnect(&ncm->port); } diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 076dd4c1be96c..ba7d180cc9e6d 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -1312,9 +1312,9 @@ static inline int gprinter_get_minor(void) { int ret; - ret = ida_simple_get(&printer_ida, 0, 0, GFP_KERNEL); + ret = ida_alloc(&printer_ida, GFP_KERNEL); if (ret >= PRINTER_MINORS) { - ida_simple_remove(&printer_ida, ret); + ida_free(&printer_ida, ret); ret = -ENODEV; } @@ -1323,7 +1323,7 @@ static inline int gprinter_get_minor(void) static inline void gprinter_put_minor(int minor) { - ida_simple_remove(&printer_ida, minor); + ida_free(&printer_ida, minor); } static int gprinter_setup(int); diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 29bf8664bf582..12c5d9cf450c1 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -869,12 +869,12 @@ EXPORT_SYMBOL_GPL(rndis_msg_parser); static inline int rndis_get_nr(void) { - return ida_simple_get(&rndis_ida, 0, 1000, GFP_KERNEL); + return ida_alloc_max(&rndis_ida, 999, GFP_KERNEL); } static inline void rndis_put_nr(int nr) { - ida_simple_remove(&rndis_ida, nr); + ida_free(&rndis_ida, nr); } struct rndis_params *rndis_register(void (*resp_avail)(void *v), void *v) diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index 4a42574b4a7fe..ec1dceb087293 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -57,13 +57,13 @@ struct uac_rtd_params { /* Volume/Mute controls and their state */ int fu_id; /* Feature Unit ID */ - struct snd_kcontrol *snd_kctl_volume; - struct snd_kcontrol *snd_kctl_mute; + struct snd_ctl_elem_id snd_kctl_volume_id; + struct snd_ctl_elem_id snd_kctl_mute_id; s16 volume_min, volume_max, volume_res; s16 volume; int mute; - struct snd_kcontrol *snd_kctl_rate; /* read-only current rate */ + struct snd_ctl_elem_id snd_kctl_rate_id; /* read-only current rate */ int srate; /* selected samplerate */ int active; /* playback/capture running */ @@ -494,14 +494,13 @@ static inline void free_ep_fback(struct uac_rtd_params *prm, struct usb_ep *ep) static void set_active(struct uac_rtd_params *prm, bool active) { // notifying through the Rate ctrl - struct snd_kcontrol *kctl = prm->snd_kctl_rate; unsigned long flags; spin_lock_irqsave(&prm->lock, flags); if (prm->active != active) { prm->active = active; snd_ctl_notify(prm->uac->card, SNDRV_CTL_EVENT_MASK_VALUE, - &kctl->id); + &prm->snd_kctl_rate_id); } spin_unlock_irqrestore(&prm->lock, flags); } @@ -807,7 +806,7 @@ int u_audio_set_volume(struct g_audio *audio_dev, int playback, s16 val) if (change) snd_ctl_notify(uac->card, SNDRV_CTL_EVENT_MASK_VALUE, - &prm->snd_kctl_volume->id); + &prm->snd_kctl_volume_id); return 0; } @@ -856,7 +855,7 @@ int u_audio_set_mute(struct g_audio *audio_dev, int playback, int val) if (change) snd_ctl_notify(uac->card, SNDRV_CTL_EVENT_MASK_VALUE, - &prm->snd_kctl_mute->id); + &prm->snd_kctl_mute_id); return 0; } @@ -1331,7 +1330,7 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, err = snd_ctl_add(card, kctl); if (err < 0) goto snd_fail; - prm->snd_kctl_mute = kctl; + prm->snd_kctl_mute_id = kctl->id; prm->mute = 0; } @@ -1359,7 +1358,7 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, err = snd_ctl_add(card, kctl); if (err < 0) goto snd_fail; - prm->snd_kctl_volume = kctl; + prm->snd_kctl_volume_id = kctl->id; prm->volume = fu->volume_max; prm->volume_max = fu->volume_max; prm->volume_min = fu->volume_min; @@ -1383,7 +1382,7 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, err = snd_ctl_add(card, kctl); if (err < 0) goto snd_fail; - prm->snd_kctl_rate = kctl; + prm->snd_kctl_rate_id = kctl->id; } strscpy(card->driver, card_name, sizeof(card->driver)); @@ -1420,6 +1419,8 @@ void g_audio_cleanup(struct g_audio *g_audio) return; uac = g_audio->uac; + g_audio->uac = NULL; + card = uac->card; if (card) snd_card_free_when_closed(card); diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 7e704b2bcfd1c..6fac696ea8463 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -13,6 +13,7 @@ #include "uvc_configfs.h" #include +#include #include /* ----------------------------------------------------------------------------- @@ -92,10 +93,10 @@ static int __uvcg_iter_item_entries(const char *page, size_t len, while (pg - page < len) { i = 0; - while (i < sizeof(buf) && (pg - page < len) && + while (i < bufsize && (pg - page < len) && *pg != '\0' && *pg != '\n') buf[i++] = *pg++; - if (i == sizeof(buf)) { + if (i == bufsize) { ret = -EINVAL; goto out_free_buf; } @@ -2260,6 +2261,8 @@ static ssize_t uvcg_uncompressed_guid_format_store(struct config_item *item, struct f_uvc_opts *opts; struct config_item *opts_item; struct mutex *su_mutex = &ch->fmt.group.cg_subsys->su_mutex; + const struct uvc_format_desc *format; + u8 tmpguidFormat[sizeof(ch->desc.guidFormat)]; int ret; mutex_lock(su_mutex); /* for navigating configfs hierarchy */ @@ -2273,7 +2276,16 @@ static ssize_t uvcg_uncompressed_guid_format_store(struct config_item *item, goto end; } - memcpy(ch->desc.guidFormat, page, + memcpy(tmpguidFormat, page, + min(sizeof(tmpguidFormat), len)); + + format = uvc_format_by_guid(tmpguidFormat); + if (!format) { + ret = -EINVAL; + goto end; + } + + memcpy(ch->desc.guidFormat, tmpguidFormat, min(sizeof(ch->desc.guidFormat), len)); ret = sizeof(ch->desc.guidFormat); diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index dd3241fc6939d..53e4cd81ea446 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -35,6 +35,9 @@ uvc_video_encode_header(struct uvc_video *video, struct uvc_buffer *buf, data[1] = UVC_STREAM_EOH | video->fid; + if (video->queue.flags & UVC_QUEUE_DROP_INCOMPLETE) + data[1] |= UVC_STREAM_ERR; + if (video->queue.buf_used == 0 && ts.tv_sec) { /* dwClockFrequency is 48 MHz */ u32 pts = ((u64)ts.tv_sec * USEC_PER_SEC + ts.tv_nsec / NSEC_PER_USEC) * 48; @@ -594,10 +597,7 @@ static void uvcg_video_pump(struct work_struct *work) */ spin_lock_irqsave(&queue->irqlock, flags); buf = uvcg_queue_head(queue); - - if (buf != NULL) { - video->encode(req, video, buf); - } else { + if (!buf) { /* * Either the queue has been disconnected or no video buffer * available for bulk transfer. Either way, stop processing @@ -607,6 +607,8 @@ static void uvcg_video_pump(struct work_struct *work) break; } + video->encode(req, video, buf); + spin_unlock_irqrestore(&queue->irqlock, flags); spin_lock_irqsave(&video->req_lock, flags); diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index d59f94464b870..8ac29f7230fcd 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -292,7 +292,9 @@ int usb_ep_queue(struct usb_ep *ep, { int ret = 0; - if (WARN_ON_ONCE(!ep->enabled && ep->address)) { + if (!ep->enabled && ep->address) { + pr_debug("USB gadget: queue request to disabled ep 0x%x (%s)\n", + ep->address, ep->name); ret = -ESHUTDOWN; goto out; } diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 12e76bb62c209..19bbc38f3d35d 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -2650,7 +2650,7 @@ net2272_plat_probe(struct platform_device *pdev) goto err_req; } - ret = net2272_probe_fin(dev, IRQF_TRIGGER_LOW); + ret = net2272_probe_fin(dev, irqflags); if (ret) goto err_io; diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index cb85168fd00c2..7aa46d426f31b 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -3491,8 +3491,8 @@ static void tegra_xudc_device_params_init(struct tegra_xudc *xudc) static int tegra_xudc_phy_get(struct tegra_xudc *xudc) { - int err = 0, usb3; - unsigned int i; + int err = 0, usb3_companion_port; + unsigned int i, j; xudc->utmi_phy = devm_kcalloc(xudc->dev, xudc->soc->num_phys, sizeof(*xudc->utmi_phy), GFP_KERNEL); @@ -3520,7 +3520,7 @@ static int tegra_xudc_phy_get(struct tegra_xudc *xudc) if (IS_ERR(xudc->utmi_phy[i])) { err = PTR_ERR(xudc->utmi_phy[i]); dev_err_probe(xudc->dev, err, - "failed to get usb2-%d PHY\n", i); + "failed to get PHY for phy-name usb2-%d\n", i); goto clean_up; } else if (xudc->utmi_phy[i]) { /* Get usb-phy, if utmi phy is available */ @@ -3539,19 +3539,30 @@ static int tegra_xudc_phy_get(struct tegra_xudc *xudc) } /* Get USB3 phy */ - usb3 = tegra_xusb_padctl_get_usb3_companion(xudc->padctl, i); - if (usb3 < 0) + usb3_companion_port = tegra_xusb_padctl_get_usb3_companion(xudc->padctl, i); + if (usb3_companion_port < 0) continue; - snprintf(phy_name, sizeof(phy_name), "usb3-%d", usb3); - xudc->usb3_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); - if (IS_ERR(xudc->usb3_phy[i])) { - err = PTR_ERR(xudc->usb3_phy[i]); - dev_err_probe(xudc->dev, err, - "failed to get usb3-%d PHY\n", usb3); - goto clean_up; - } else if (xudc->usb3_phy[i]) - dev_dbg(xudc->dev, "usb3-%d PHY registered", usb3); + for (j = 0; j < xudc->soc->num_phys; j++) { + snprintf(phy_name, sizeof(phy_name), "usb3-%d", j); + xudc->usb3_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); + if (IS_ERR(xudc->usb3_phy[i])) { + err = PTR_ERR(xudc->usb3_phy[i]); + dev_err_probe(xudc->dev, err, + "failed to get PHY for phy-name usb3-%d\n", j); + goto clean_up; + } else if (xudc->usb3_phy[i]) { + int usb2_port = + tegra_xusb_padctl_get_port_number(xudc->utmi_phy[i]); + int usb3_port = + tegra_xusb_padctl_get_port_number(xudc->usb3_phy[i]); + if (usb3_port == usb3_companion_port) { + dev_dbg(xudc->dev, "USB2 port %d is paired with USB3 port %d for device mode port %d\n", + usb2_port, usb3_port, i); + break; + } + } + } } return err; diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 4f9982ecfb583..5cec7640e913c 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -888,6 +888,7 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) /* Check for an all 1's result which is a typical consequence * of dead, unclocked, or unplugged (CardBus...) devices */ +again: if (ints == ~(u32)0) { ohci->rh_state = OHCI_RH_HALTED; ohci_dbg (ohci, "device removed!\n"); @@ -982,6 +983,13 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) } spin_unlock(&ohci->lock); + /* repeat until all enabled interrupts are handled */ + if (ohci->rh_state != OHCI_RH_HALTED) { + ints = ohci_readl(ohci, ®s->intrstatus); + if (ints && (ints & ohci_readl(ohci, ®s->intrenable))) + goto again; + } + return IRQ_HANDLED; } diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index 0956495bba575..2b871540bb500 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -585,6 +585,7 @@ done(struct sl811 *sl811, struct sl811h_ep *ep, u8 bank) finish_request(sl811, ep, urb, urbstat); } +#ifdef QUIRK2 static inline u8 checkdone(struct sl811 *sl811) { u8 ctl; @@ -616,6 +617,7 @@ static inline u8 checkdone(struct sl811 *sl811) #endif return irqstat; } +#endif static irqreturn_t sl811h_irq(struct usb_hcd *hcd) { diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index a7716202a8dd5..2246bb0dea191 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -2280,24 +2280,24 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags) } static struct xhci_interrupter * -xhci_alloc_interrupter(struct xhci_hcd *xhci, int segs, gfp_t flags) +xhci_alloc_interrupter(struct xhci_hcd *xhci, unsigned int segs, gfp_t flags) { struct device *dev = xhci_to_hcd(xhci)->self.sysdev; struct xhci_interrupter *ir; - unsigned int num_segs = segs; + unsigned int max_segs; int ret; + if (!segs) + segs = ERST_DEFAULT_SEGS; + + max_segs = BIT(HCS_ERST_MAX(xhci->hcs_params2)); + segs = min(segs, max_segs); + ir = kzalloc_node(sizeof(*ir), flags, dev_to_node(dev)); if (!ir) return NULL; - /* number of ring segments should be greater than 0 */ - if (segs <= 0) - num_segs = min_t(unsigned int, 1 << HCS_ERST_MAX(xhci->hcs_params2), - ERST_MAX_SEGS); - - ir->event_ring = xhci_ring_alloc(xhci, num_segs, 1, TYPE_EVENT, 0, - flags); + ir->event_ring = xhci_ring_alloc(xhci, segs, 1, TYPE_EVENT, 0, flags); if (!ir->event_ring) { xhci_warn(xhci, "Failed to allocate interrupter event ring\n"); kfree(ir); @@ -2355,7 +2355,7 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir, } struct xhci_interrupter * -xhci_create_secondary_interrupter(struct usb_hcd *hcd, int num_seg) +xhci_create_secondary_interrupter(struct usb_hcd *hcd, unsigned int segs) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct xhci_interrupter *ir; @@ -2365,7 +2365,7 @@ xhci_create_secondary_interrupter(struct usb_hcd *hcd, int num_seg) if (!xhci->interrupters || xhci->max_interrupters <= 1) return NULL; - ir = xhci_alloc_interrupter(xhci, num_seg, GFP_KERNEL); + ir = xhci_alloc_interrupter(xhci, segs, GFP_KERNEL); if (!ir) return NULL; @@ -2533,7 +2533,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) if (xhci_add_interrupter(xhci, ir, 0)) goto fail; - xhci->isoc_bei_interval = AVOID_BEI_INTERVAL_MAX; + ir->isoc_bei_interval = AVOID_BEI_INTERVAL_MAX; /* * XXX: Might need to set the Interrupter Moderation Register to diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index b534ca9752be4..904ccf706b64b 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -36,6 +36,7 @@ #define PCI_VENDOR_ID_ETRON 0x1b6f #define PCI_DEVICE_ID_EJ168 0x7023 +#define PCI_DEVICE_ID_EJ188 0x7052 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI 0x8c31 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31 @@ -270,17 +271,12 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) "QUIRK: Fresco Logic revision %u " "has broken MSI implementation", pdev->revision); - xhci->quirks |= XHCI_TRUST_TX_LENGTH; } if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC && pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009) xhci->quirks |= XHCI_BROKEN_STREAMS; - if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC && - pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1100) - xhci->quirks |= XHCI_TRUST_TX_LENGTH; - if (pdev->vendor == PCI_VENDOR_ID_NEC) xhci->quirks |= XHCI_NEC_HOST; @@ -307,9 +303,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_RESET_ON_RESUME; } - if (pdev->vendor == PCI_VENDOR_ID_AMD) - xhci->quirks |= XHCI_TRUST_TX_LENGTH; - if ((pdev->vendor == PCI_VENDOR_ID_AMD) && ((pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4) || (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_3) || @@ -396,12 +389,16 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_ETRON && pdev->device == PCI_DEVICE_ID_EJ168) { xhci->quirks |= XHCI_RESET_ON_RESUME; - xhci->quirks |= XHCI_TRUST_TX_LENGTH; xhci->quirks |= XHCI_BROKEN_STREAMS; } + if (pdev->vendor == PCI_VENDOR_ID_ETRON && + pdev->device == PCI_DEVICE_ID_EJ188) { + xhci->quirks |= XHCI_RESET_ON_RESUME; + xhci->quirks |= XHCI_BROKEN_STREAMS; + } + if (pdev->vendor == PCI_VENDOR_ID_RENESAS && pdev->device == 0x0014) { - xhci->quirks |= XHCI_TRUST_TX_LENGTH; xhci->quirks |= XHCI_ZERO_64B_REGS; } if (pdev->vendor == PCI_VENDOR_ID_RENESAS && @@ -431,7 +428,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) } if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) { - xhci->quirks |= XHCI_TRUST_TX_LENGTH; xhci->quirks |= XHCI_NO_64BIT_SUPPORT; } if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && diff --git a/drivers/usb/host/xhci-plat.h b/drivers/usb/host/xhci-plat.h index 2d15386f2c504..6475130eac4b3 100644 --- a/drivers/usb/host/xhci-plat.h +++ b/drivers/usb/host/xhci-plat.h @@ -8,7 +8,9 @@ #ifndef _XHCI_PLAT_H #define _XHCI_PLAT_H -#include "xhci.h" /* for hcd_to_xhci() */ +struct device; +struct platform_device; +struct usb_hcd; struct xhci_plat_priv { const char *firmware_name; diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c index ab9c5969e4624..8b357647728c2 100644 --- a/drivers/usb/host/xhci-rcar.c +++ b/drivers/usb/host/xhci-rcar.c @@ -214,8 +214,7 @@ static int xhci_rcar_resume_quirk(struct usb_hcd *hcd) */ #define SET_XHCI_PLAT_PRIV_FOR_RCAR(firmware) \ .firmware_name = firmware, \ - .quirks = XHCI_NO_64BIT_SUPPORT | XHCI_TRUST_TX_LENGTH | \ - XHCI_SLOW_SUSPEND, \ + .quirks = XHCI_NO_64BIT_SUPPORT | XHCI_SLOW_SUSPEND, \ .init_quirk = xhci_rcar_init_quirk, \ .plat_start = xhci_rcar_start, \ .resume_quirk = xhci_rcar_resume_quirk, @@ -229,8 +228,7 @@ static const struct xhci_plat_priv xhci_plat_renesas_rcar_gen3 = { }; static const struct xhci_plat_priv xhci_plat_renesas_rzv2m = { - .quirks = XHCI_NO_64BIT_SUPPORT | XHCI_TRUST_TX_LENGTH | - XHCI_SLOW_SUSPEND, + .quirks = XHCI_NO_64BIT_SUPPORT | XHCI_SLOW_SUSPEND, .init_quirk = xhci_rzv2m_init_quirk, .plat_start = xhci_rzv2m_start, }; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 4f64b814d4aa2..6da062235d521 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1028,13 +1028,27 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) break; case TD_DIRTY: /* TD is cached, clear it */ case TD_HALTED: + case TD_CLEARING_CACHE_DEFERRED: + if (cached_td) { + if (cached_td->urb->stream_id != td->urb->stream_id) { + /* Multiple streams case, defer move dq */ + xhci_dbg(xhci, + "Move dq deferred: stream %u URB %p\n", + td->urb->stream_id, td->urb); + td->cancel_status = TD_CLEARING_CACHE_DEFERRED; + break; + } + + /* Should never happen, but clear the TD if it does */ + xhci_warn(xhci, + "Found multiple active URBs %p and %p in stream %u?\n", + td->urb, cached_td->urb, + td->urb->stream_id); + td_to_noop(xhci, ring, cached_td, false); + cached_td->cancel_status = TD_CLEARED; + } + td->cancel_status = TD_CLEARING_CACHE; - if (cached_td) - /* FIXME stream case, several stopped rings */ - xhci_dbg(xhci, - "Move dq past stream %u URB %p instead of stream %u URB %p\n", - td->urb->stream_id, td->urb, - cached_td->urb->stream_id, cached_td->urb); cached_td = td; break; } @@ -1054,10 +1068,16 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) if (err) { /* Failed to move past cached td, just set cached TDs to no-op */ list_for_each_entry_safe(td, tmp_td, &ep->cancelled_td_list, cancelled_td_list) { - if (td->cancel_status != TD_CLEARING_CACHE) + /* + * Deferred TDs need to have the deq pointer set after the above command + * completes, so if that failed we just give up on all of them (and + * complain loudly since this could cause issues due to caching). + */ + if (td->cancel_status != TD_CLEARING_CACHE && + td->cancel_status != TD_CLEARING_CACHE_DEFERRED) continue; - xhci_dbg(xhci, "Failed to clear cancelled cached URB %p, mark clear anyway\n", - td->urb); + xhci_warn(xhci, "Failed to clear cancelled cached URB %p, mark clear anyway\n", + td->urb); td_to_noop(xhci, ring, td, false); td->cancel_status = TD_CLEARED; } @@ -1335,6 +1355,7 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id, struct xhci_ep_ctx *ep_ctx; struct xhci_slot_ctx *slot_ctx; struct xhci_td *td, *tmp_td; + bool deferred = false; ep_index = TRB_TO_EP_INDEX(le32_to_cpu(trb->generic.field[3])); stream_id = TRB_TO_STREAM_ID(le32_to_cpu(trb->generic.field[2])); @@ -1421,6 +1442,8 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id, xhci_dbg(ep->xhci, "%s: Giveback cancelled URB %p TD\n", __func__, td->urb); xhci_td_cleanup(ep->xhci, td, ep_ring, td->status); + } else if (td->cancel_status == TD_CLEARING_CACHE_DEFERRED) { + deferred = true; } else { xhci_dbg(ep->xhci, "%s: Keep cancelled URB %p TD as cancel_status is %d\n", __func__, td->urb, td->cancel_status); @@ -1430,8 +1453,17 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id, ep->ep_state &= ~SET_DEQ_PENDING; ep->queued_deq_seg = NULL; ep->queued_deq_ptr = NULL; - /* Restart any rings with pending URBs */ - ring_doorbell_for_active_rings(xhci, slot_id, ep_index); + + if (deferred) { + /* We have more streams to clear */ + xhci_dbg(ep->xhci, "%s: Pending TDs to clear, continuing with invalidation\n", + __func__); + xhci_invalidate_cancelled_tds(ep); + } else { + /* Restart any rings with pending URBs */ + xhci_dbg(ep->xhci, "%s: All TDs cleared, ring doorbell\n", __func__); + ring_doorbell_for_active_rings(xhci, slot_id, ep_index); + } } static void xhci_handle_cmd_reset_ep(struct xhci_hcd *xhci, int slot_id, @@ -2387,8 +2419,7 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, break; if (remaining) { frame->status = short_framestatus; - if (xhci->quirks & XHCI_TRUST_TX_LENGTH) - sum_trbs_for_length = true; + sum_trbs_for_length = true; break; } frame->status = 0; @@ -2523,9 +2554,8 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, goto finish_td; case COMP_STOPPED_LENGTH_INVALID: /* stopped on ep trb with invalid length, exclude it */ - ep_trb_len = 0; - remaining = 0; - break; + td->urb->actual_length = sum_trb_lengths(xhci, ep_ring, ep_trb); + goto finish_td; case COMP_USB_TRANSACTION_ERROR: if (xhci->quirks & XHCI_NO_SOFT_RETRY || (ep->err_count++ > MAX_SOFT_RETRY) || @@ -2638,15 +2668,11 @@ static int handle_tx_event(struct xhci_hcd *xhci, * transfer type */ case COMP_SUCCESS: - if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) == 0) - break; - if (xhci->quirks & XHCI_TRUST_TX_LENGTH || - ep_ring->last_td_was_short) + if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) != 0) { trb_comp_code = COMP_SHORT_PACKET; - else - xhci_warn_ratelimited(xhci, - "WARN Successful completion on short TX for slot %u ep %u: needs XHCI_TRUST_TX_LENGTH quirk?\n", - slot_id, ep_index); + xhci_dbg(xhci, "Successful completion on short TX for slot %u ep %u with last td short %d\n", + slot_id, ep_index, ep_ring->last_td_was_short); + } break; case COMP_SHORT_PACKET: break; @@ -3022,9 +3048,6 @@ static int xhci_handle_event(struct xhci_hcd *xhci, struct xhci_interrupter *ir) return 0; } - /* Update SW event ring dequeue pointer */ - inc_deq(xhci, ir->event_ring); - /* Are there more items on the event ring? Caller will call us again to * check. */ @@ -3038,30 +3061,26 @@ static int xhci_handle_event(struct xhci_hcd *xhci, struct xhci_interrupter *ir) */ static void xhci_update_erst_dequeue(struct xhci_hcd *xhci, struct xhci_interrupter *ir, - union xhci_trb *event_ring_deq, bool clear_ehb) { u64 temp_64; dma_addr_t deq; temp_64 = xhci_read_64(xhci, &ir->ir_set->erst_dequeue); - /* If necessary, update the HW's version of the event ring deq ptr. */ - if (event_ring_deq != ir->event_ring->dequeue) { - deq = xhci_trb_virt_to_dma(ir->event_ring->deq_seg, - ir->event_ring->dequeue); - if (deq == 0) - xhci_warn(xhci, "WARN something wrong with SW event ring dequeue ptr\n"); - /* - * Per 4.9.4, Software writes to the ERDP register shall - * always advance the Event Ring Dequeue Pointer value. - */ - if ((temp_64 & ERST_PTR_MASK) == (deq & ERST_PTR_MASK)) - return; + deq = xhci_trb_virt_to_dma(ir->event_ring->deq_seg, + ir->event_ring->dequeue); + if (deq == 0) + xhci_warn(xhci, "WARN something wrong with SW event ring dequeue ptr\n"); + /* + * Per 4.9.4, Software writes to the ERDP register shall always advance + * the Event Ring Dequeue Pointer value. + */ + if ((temp_64 & ERST_PTR_MASK) == (deq & ERST_PTR_MASK) && !clear_ehb) + return; - /* Update HC event ring dequeue pointer */ - temp_64 = ir->event_ring->deq_seg->num & ERST_DESI_MASK; - temp_64 |= deq & ERST_PTR_MASK; - } + /* Update HC event ring dequeue pointer */ + temp_64 = ir->event_ring->deq_seg->num & ERST_DESI_MASK; + temp_64 |= deq & ERST_PTR_MASK; /* Clear the event handler busy flag (RW1C) */ if (clear_ehb) @@ -3069,6 +3088,59 @@ static void xhci_update_erst_dequeue(struct xhci_hcd *xhci, xhci_write_64(xhci, temp_64, &ir->ir_set->erst_dequeue); } +/* Clear the interrupt pending bit for a specific interrupter. */ +static void xhci_clear_interrupt_pending(struct xhci_hcd *xhci, + struct xhci_interrupter *ir) +{ + if (!ir->ip_autoclear) { + u32 irq_pending; + + irq_pending = readl(&ir->ir_set->irq_pending); + irq_pending |= IMAN_IP; + writel(irq_pending, &ir->ir_set->irq_pending); + } +} + +static int xhci_handle_events(struct xhci_hcd *xhci, struct xhci_interrupter *ir) +{ + int event_loop = 0; + u64 temp; + + xhci_clear_interrupt_pending(xhci, ir); + + if (xhci->xhc_state & XHCI_STATE_DYING || + xhci->xhc_state & XHCI_STATE_HALTED) { + xhci_dbg(xhci, "xHCI dying, ignoring interrupt. Shouldn't IRQs be disabled?\n"); + + /* Clear the event handler busy flag (RW1C) */ + temp = xhci_read_64(xhci, &ir->ir_set->erst_dequeue); + xhci_write_64(xhci, temp | ERST_EHB, &ir->ir_set->erst_dequeue); + return -ENODEV; + } + + while (xhci_handle_event(xhci, ir) > 0) { + /* + * If half a segment of events have been handled in one go then + * update ERDP, and force isoc trbs to interrupt more often + */ + if (event_loop++ > TRBS_PER_SEGMENT / 2) { + xhci_update_erst_dequeue(xhci, ir, false); + + if (ir->isoc_bei_interval > AVOID_BEI_INTERVAL_MIN) + ir->isoc_bei_interval = ir->isoc_bei_interval / 2; + + event_loop = 0; + } + + /* Update SW event ring dequeue pointer */ + inc_deq(xhci, ir->event_ring); + } + + xhci_update_erst_dequeue(xhci, ir, true); + + return 0; +} + /* * xHCI spec says we can get an interrupt, and if the HC has an error condition, * we might get bad data out of the event ring. Section 4.10.2.7 has a list of @@ -3077,24 +3149,21 @@ static void xhci_update_erst_dequeue(struct xhci_hcd *xhci, irqreturn_t xhci_irq(struct usb_hcd *hcd) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); - union xhci_trb *event_ring_deq; - struct xhci_interrupter *ir; - irqreturn_t ret = IRQ_NONE; - u64 temp_64; + irqreturn_t ret = IRQ_HANDLED; u32 status; - int event_loop = 0; spin_lock(&xhci->lock); /* Check if the xHC generated the interrupt, or the irq is shared */ status = readl(&xhci->op_regs->status); if (status == ~(u32)0) { xhci_hc_died(xhci); - ret = IRQ_HANDLED; goto out; } - if (!(status & STS_EINT)) + if (!(status & STS_EINT)) { + ret = IRQ_NONE; goto out; + } if (status & STS_HCE) { xhci_warn(xhci, "WARNING: Host Controller Error\n"); @@ -3104,7 +3173,6 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) if (status & STS_FATAL) { xhci_warn(xhci, "WARNING: Host System Error\n"); xhci_halt(xhci); - ret = IRQ_HANDLED; goto out; } @@ -3117,48 +3185,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) writel(status, &xhci->op_regs->status); /* This is the handler of the primary interrupter */ - ir = xhci->interrupters[0]; - if (!hcd->msi_enabled) { - u32 irq_pending; - irq_pending = readl(&ir->ir_set->irq_pending); - irq_pending |= IMAN_IP; - writel(irq_pending, &ir->ir_set->irq_pending); - } - - if (xhci->xhc_state & XHCI_STATE_DYING || - xhci->xhc_state & XHCI_STATE_HALTED) { - xhci_dbg(xhci, "xHCI dying, ignoring interrupt. " - "Shouldn't IRQs be disabled?\n"); - /* Clear the event handler busy flag (RW1C); - * the event ring should be empty. - */ - temp_64 = xhci_read_64(xhci, &ir->ir_set->erst_dequeue); - xhci_write_64(xhci, temp_64 | ERST_EHB, - &ir->ir_set->erst_dequeue); - ret = IRQ_HANDLED; - goto out; - } - - event_ring_deq = ir->event_ring->dequeue; - /* FIXME this should be a delayed service routine - * that clears the EHB. - */ - while (xhci_handle_event(xhci, ir) > 0) { - if (event_loop++ < TRBS_PER_SEGMENT / 2) - continue; - xhci_update_erst_dequeue(xhci, ir, event_ring_deq, false); - event_ring_deq = ir->event_ring->dequeue; - - /* ring is half-full, force isoc trbs to interrupt more often */ - if (xhci->isoc_bei_interval > AVOID_BEI_INTERVAL_MIN) - xhci->isoc_bei_interval = xhci->isoc_bei_interval / 2; - - event_loop = 0; - } - - xhci_update_erst_dequeue(xhci, ir, event_ring_deq, true); - ret = IRQ_HANDLED; - + xhci_handle_events(xhci, xhci->interrupters[0]); out: spin_unlock(&xhci->lock); @@ -4019,7 +4046,8 @@ static int xhci_get_isoc_frame_id(struct xhci_hcd *xhci, } /* Check if we should generate event interrupt for a TD in an isoc URB */ -static bool trb_block_event_intr(struct xhci_hcd *xhci, int num_tds, int i) +static bool trb_block_event_intr(struct xhci_hcd *xhci, int num_tds, int i, + struct xhci_interrupter *ir) { if (xhci->hci_version < 0x100) return false; @@ -4030,8 +4058,8 @@ static bool trb_block_event_intr(struct xhci_hcd *xhci, int num_tds, int i) * If AVOID_BEI is set the host handles full event rings poorly, * generate an event at least every 8th TD to clear the event ring */ - if (i && xhci->quirks & XHCI_AVOID_BEI) - return !!(i % xhci->isoc_bei_interval); + if (i && ir->isoc_bei_interval && xhci->quirks & XHCI_AVOID_BEI) + return !!(i % ir->isoc_bei_interval); return true; } @@ -4040,6 +4068,7 @@ static bool trb_block_event_intr(struct xhci_hcd *xhci, int num_tds, int i) static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, struct urb *urb, int slot_id, unsigned int ep_index) { + struct xhci_interrupter *ir; struct xhci_ring *ep_ring; struct urb_priv *urb_priv; struct xhci_td *td; @@ -4057,6 +4086,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, xep = &xhci->devs[slot_id]->eps[ep_index]; ep_ring = xhci->devs[slot_id]->eps[ep_index].ring; + ir = xhci->interrupters[0]; num_tds = urb->number_of_packets; if (num_tds < 1) { @@ -4144,7 +4174,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, td->last_trb = ep_ring->enqueue; td->last_trb_seg = ep_ring->enq_seg; field |= TRB_IOC; - if (trb_block_event_intr(xhci, num_tds, i)) + if (trb_block_event_intr(xhci, num_tds, i, ir)) field |= TRB_BEI; } /* Calculate TRB length */ diff --git a/drivers/usb/host/xhci-rzv2m.c b/drivers/usb/host/xhci-rzv2m.c index ec65b24eafa86..4f59867d7117c 100644 --- a/drivers/usb/host/xhci-rzv2m.c +++ b/drivers/usb/host/xhci-rzv2m.c @@ -6,6 +6,7 @@ */ #include +#include "xhci.h" #include "xhci-plat.h" #include "xhci-rzv2m.h" diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index c057c42c36f4c..afccd58c9a75a 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -538,6 +538,9 @@ int xhci_run(struct usb_hcd *hcd) */ hcd->uses_new_polling = 1; + if (hcd->msi_enabled) + ir->ip_autoclear = true; + if (!usb_hcd_is_primary_hcd(hcd)) return xhci_run_finished(xhci); @@ -1217,6 +1220,8 @@ static int xhci_map_temp_buffer(struct usb_hcd *hcd, struct urb *urb) temp = kzalloc_node(buf_len, GFP_ATOMIC, dev_to_node(hcd->self.sysdev)); + if (!temp) + return -ENOMEM; if (usb_urb_dir_out(urb)) sg_pcopy_to_buffer(urb->sg, urb->num_sgs, diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 6f82d404883f9..ea25d7aeb20cb 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1533,6 +1533,7 @@ enum xhci_cancelled_td_status { TD_DIRTY = 0, TD_HALTED, TD_CLEARING_CACHE, + TD_CLEARING_CACHE_DEFERRED, TD_CLEARED, }; @@ -1649,8 +1650,8 @@ struct urb_priv { struct xhci_td td[] __counted_by(num_tds); }; -/* Reasonable limit for number of Event Ring segments (spec allows 32k) */ -#define ERST_MAX_SEGS 2 +/* Number of Event Ring segments to allocate, when amount is not specified. (spec allows 32k) */ +#define ERST_DEFAULT_SEGS 2 /* Poll every 60 seconds */ #define POLL_TIMEOUT 60 /* Stop endpoint command timeout (secs) for URB cancellation watchdog timer */ @@ -1688,6 +1689,8 @@ struct xhci_interrupter { struct xhci_erst erst; struct xhci_intr_reg __iomem *ir_set; unsigned int intr_num; + bool ip_autoclear; + u32 isoc_bei_interval; /* For interrupter registers save and restore over suspend/resume */ u32 s3_irq_pending; u32 s3_irq_control; @@ -1760,7 +1763,6 @@ struct xhci_hcd { u8 isoc_threshold; /* imod_interval in ns (I * 250ns) */ u32 imod_interval; - u32 isoc_bei_interval; int event_ring_max; /* 4KB min, 128MB max */ int page_size; @@ -1843,7 +1845,7 @@ struct xhci_hcd { #define XHCI_RESET_ON_RESUME BIT_ULL(7) #define XHCI_SW_BW_CHECKING BIT_ULL(8) #define XHCI_AMD_0x96_HOST BIT_ULL(9) -#define XHCI_TRUST_TX_LENGTH BIT_ULL(10) +#define XHCI_TRUST_TX_LENGTH BIT_ULL(10) /* Deprecated */ #define XHCI_LPM_SUPPORT BIT_ULL(11) #define XHCI_INTEL_HOST BIT_ULL(12) #define XHCI_SPURIOUS_REBOOT BIT_ULL(13) @@ -1983,8 +1985,6 @@ static inline bool xhci_has_one_roothub(struct xhci_hcd *xhci) dev_err(xhci_to_hcd(xhci)->self.controller , fmt , ## args) #define xhci_warn(xhci, fmt, args...) \ dev_warn(xhci_to_hcd(xhci)->self.controller , fmt , ## args) -#define xhci_warn_ratelimited(xhci, fmt, args...) \ - dev_warn_ratelimited(xhci_to_hcd(xhci)->self.controller , fmt , ## args) #define xhci_info(xhci, fmt, args...) \ dev_info(xhci_to_hcd(xhci)->self.controller , fmt , ## args) @@ -2087,7 +2087,7 @@ struct xhci_container_ctx *xhci_alloc_container_ctx(struct xhci_hcd *xhci, void xhci_free_container_ctx(struct xhci_hcd *xhci, struct xhci_container_ctx *ctx); struct xhci_interrupter * -xhci_create_secondary_interrupter(struct usb_hcd *hcd, int num_seg); +xhci_create_secondary_interrupter(struct usb_hcd *hcd, unsigned int segs); void xhci_remove_secondary_interrupter(struct usb_hcd *hcd, struct xhci_interrupter *ir); diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c index 0dd2b032c90b9..e162838bec3d9 100644 --- a/drivers/usb/misc/onboard_usb_hub.c +++ b/drivers/usb/misc/onboard_usb_hub.c @@ -78,7 +78,7 @@ static int onboard_hub_power_on(struct onboard_hub *hub) err = regulator_bulk_enable(hub->pdata->num_supplies, hub->supplies); if (err) { dev_err(hub->dev, "failed to enable supplies: %pe\n", ERR_PTR(err)); - return err; + goto disable_clk; } fsleep(hub->pdata->reset_us); @@ -87,6 +87,10 @@ static int onboard_hub_power_on(struct onboard_hub *hub) hub->is_powered_on = true; return 0; + +disable_clk: + clk_disable_unprepare(hub->clk); + return err; } static int onboard_hub_power_off(struct onboard_hub *hub) diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c index 35770e608c649..2d30fc1be3066 100644 --- a/drivers/usb/misc/usb-ljca.c +++ b/drivers/usb/misc/usb-ljca.c @@ -518,8 +518,10 @@ static int ljca_new_client_device(struct ljca_adapter *adap, u8 type, u8 id, int ret; client = kzalloc(sizeof *client, GFP_KERNEL); - if (!client) + if (!client) { + kfree(data); return -ENOMEM; + } client->type = type; client->id = id; @@ -535,8 +537,10 @@ static int ljca_new_client_device(struct ljca_adapter *adap, u8 type, u8 id, auxdev->dev.release = ljca_auxdev_release; ret = auxiliary_device_init(auxdev); - if (ret) + if (ret) { + kfree(data); goto err_free; + } ljca_auxdev_acpi_bind(adap, auxdev, adr, id); @@ -590,12 +594,8 @@ static int ljca_enumerate_gpio(struct ljca_adapter *adap) valid_pin[i] = get_unaligned_le32(&desc->bank_desc[i].valid_pins); bitmap_from_arr32(gpio_info->valid_pin_map, valid_pin, gpio_num); - ret = ljca_new_client_device(adap, LJCA_CLIENT_GPIO, 0, "ljca-gpio", + return ljca_new_client_device(adap, LJCA_CLIENT_GPIO, 0, "ljca-gpio", gpio_info, LJCA_GPIO_ACPI_ADR); - if (ret) - kfree(gpio_info); - - return ret; } static int ljca_enumerate_i2c(struct ljca_adapter *adap) @@ -629,10 +629,8 @@ static int ljca_enumerate_i2c(struct ljca_adapter *adap) ret = ljca_new_client_device(adap, LJCA_CLIENT_I2C, i, "ljca-i2c", i2c_info, LJCA_I2C1_ACPI_ADR + i); - if (ret) { - kfree(i2c_info); + if (ret) return ret; - } } return 0; @@ -669,10 +667,8 @@ static int ljca_enumerate_spi(struct ljca_adapter *adap) ret = ljca_new_client_device(adap, LJCA_CLIENT_SPI, i, "ljca-spi", spi_info, LJCA_SPI1_ACPI_ADR + i); - if (ret) { - kfree(spi_info); + if (ret) return ret; - } } return 0; diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index b00d92db5dfd1..eb5a8e0d9e2d6 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -677,7 +677,7 @@ static int uss720_probe(struct usb_interface *intf, struct parport_uss720_private *priv; struct parport *pp; unsigned char reg; - int i; + int ret; dev_dbg(&intf->dev, "probe: vendor id 0x%x, device id 0x%x\n", le16_to_cpu(usbdev->descriptor.idVendor), @@ -688,8 +688,8 @@ static int uss720_probe(struct usb_interface *intf, usb_put_dev(usbdev); return -ENODEV; } - i = usb_set_interface(usbdev, intf->altsetting->desc.bInterfaceNumber, 2); - dev_dbg(&intf->dev, "set interface result %d\n", i); + ret = usb_set_interface(usbdev, intf->altsetting->desc.bInterfaceNumber, 2); + dev_dbg(&intf->dev, "set interface result %d\n", ret); interface = intf->cur_altsetting; @@ -725,12 +725,18 @@ static int uss720_probe(struct usb_interface *intf, set_1284_register(pp, 7, 0x00, GFP_KERNEL); set_1284_register(pp, 6, 0x30, GFP_KERNEL); /* PS/2 mode */ set_1284_register(pp, 2, 0x0c, GFP_KERNEL); - /* debugging */ - get_1284_register(pp, 0, ®, GFP_KERNEL); + + /* The Belkin F5U002 Rev 2 P80453-B USB parallel port adapter shares the + * device ID 050d:0002 with some other device that works with this + * driver, but it itself does not. Detect and handle the bad cable + * here. */ + ret = get_1284_register(pp, 0, ®, GFP_KERNEL); dev_dbg(&intf->dev, "reg: %7ph\n", priv->reg); + if (ret < 0) + return ret; - i = usb_find_last_int_in_endpoint(interface, &epd); - if (!i) { + ret = usb_find_last_int_in_endpoint(interface, &epd); + if (!ret) { dev_dbg(&intf->dev, "epaddr %d interval %d\n", epd->bEndpointAddress, epd->bInterval); } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 923e0ed85444b..21fd26609252b 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -56,6 +56,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0471, 0x066A) }, /* AKTAKOM ACE-1001 cable */ { USB_DEVICE(0x0489, 0xE000) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */ { USB_DEVICE(0x0489, 0xE003) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */ + { USB_DEVICE(0x04BF, 0x1301) }, /* TDK Corporation NC0110013M - Network Controller */ + { USB_DEVICE(0x04BF, 0x1303) }, /* TDK Corporation MM0110113M - i3 Micro Module */ { USB_DEVICE(0x0745, 0x1000) }, /* CipherLab USB CCD Barcode Scanner 1000 */ { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */ { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ @@ -144,6 +146,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ + { USB_DEVICE(0x10C4, 0x863C) }, /* MGP Instruments PDS100 */ { USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */ { USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */ { USB_DEVICE(0x10C4, 0x87ED) }, /* IMST USB-Stick for Smart Meter */ @@ -177,6 +180,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */ { USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */ { USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */ + { USB_DEVICE(0x11CA, 0x0212) }, /* Verifone USB to Printer (UART, CP2102) */ { USB_DEVICE(0x12B8, 0xEC60) }, /* Link G4 ECU */ { USB_DEVICE(0x12B8, 0xEC62) }, /* Link G4+ ECU */ { USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 13a56783830df..22d01a0f10fbc 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1077,6 +1077,8 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_FALCONIA_JTAG_UNBUF_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + /* GMC devices */ + { USB_DEVICE(GMC_VID, GMC_Z216C_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 21a2b5a25fc09..5ee60ba2a73cd 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1606,3 +1606,9 @@ #define UBLOX_VID 0x1546 #define UBLOX_C099F9P_ZED_PID 0x0502 #define UBLOX_C099F9P_ODIN_PID 0x0503 + +/* + * GMC devices + */ +#define GMC_VID 0x1cd7 +#define GMC_Z216C_PID 0x0217 /* GMC Z216C Adapter IR-USB */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 2ae124c49d448..8a5846d4adf67 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -255,6 +255,10 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM061K_LMS 0x0124 #define QUECTEL_PRODUCT_EC25 0x0125 #define QUECTEL_PRODUCT_EM060K_128 0x0128 +#define QUECTEL_PRODUCT_EM060K_129 0x0129 +#define QUECTEL_PRODUCT_EM060K_12a 0x012a +#define QUECTEL_PRODUCT_EM060K_12b 0x012b +#define QUECTEL_PRODUCT_EM060K_12c 0x012c #define QUECTEL_PRODUCT_EG91 0x0191 #define QUECTEL_PRODUCT_EG95 0x0195 #define QUECTEL_PRODUCT_BG96 0x0296 @@ -613,6 +617,11 @@ static void option_instat_callback(struct urb *urb); /* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */ #define LUAT_PRODUCT_AIR720U 0x4e00 +/* MeiG Smart Technology products */ +#define MEIGSMART_VENDOR_ID 0x2dee +/* MeiG Smart SLM320 based on UNISOC UIS8910 */ +#define MEIGSMART_PRODUCT_SLM320 0x4d41 + /* Device flags */ /* Highest interface number which can be used with NCTRL() and RSVD() */ @@ -1213,6 +1222,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x40) }, @@ -1355,6 +1376,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff), /* Telit FE990 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a0, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a4, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a9, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2047,6 +2074,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9803, 0xff), .driver_info = RSVD(4) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b05), /* Longsung U8300 */ + .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b3c), /* Longsung U9300 */ + .driver_info = RSVD(0) | RSVD(4) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) }, { USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) }, @@ -2267,21 +2298,36 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) }, /* Fibocom FM160 (MBIM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0115, 0xff), /* Fibocom FM135 (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */ .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a04, 0xff) }, /* Fibocom FM650-CN (ECM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a05, 0xff) }, /* Fibocom FM650-CN (NCM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a06, 0xff) }, /* Fibocom FM650-CN (RNDIS mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a07, 0xff) }, /* Fibocom FM650-CN (MBIM mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ + { USB_DEVICE(0x33f8, 0x0104), /* Rolling RW101-GL (laptop RMNET) */ + .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a2, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a3, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a4, 0xff), /* Rolling RW101-GL (laptop MBIM) */ + .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0115, 0xff), /* Rolling RW135-GL (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/storage/alauda.c b/drivers/usb/storage/alauda.c index 115f05a6201a1..40d34cc28344a 100644 --- a/drivers/usb/storage/alauda.c +++ b/drivers/usb/storage/alauda.c @@ -105,6 +105,8 @@ struct alauda_info { unsigned char sense_key; unsigned long sense_asc; /* additional sense code */ unsigned long sense_ascq; /* additional sense code qualifier */ + + bool media_initialized; }; #define short_pack(lsb,msb) ( ((u16)(lsb)) | ( ((u16)(msb))<<8 ) ) @@ -476,11 +478,12 @@ static int alauda_check_media(struct us_data *us) } /* Check for media change */ - if (status[0] & 0x08) { + if (status[0] & 0x08 || !info->media_initialized) { usb_stor_dbg(us, "Media change detected\n"); alauda_free_maps(&MEDIA_INFO(us)); - alauda_init_media(us); - + rc = alauda_init_media(us); + if (rc == USB_STOR_TRANSPORT_GOOD) + info->media_initialized = true; info->sense_key = UNIT_ATTENTION; info->sense_asc = 0x28; info->sense_ascq = 0x00; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 71ace274761f1..08953f0d4532a 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -533,7 +533,7 @@ static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp, * daft to me. */ -static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) +static int uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) { struct uas_dev_info *devinfo = cmnd->device->hostdata; struct urb *urb; @@ -541,30 +541,28 @@ static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp) urb = uas_alloc_sense_urb(devinfo, gfp, cmnd); if (!urb) - return NULL; + return -ENOMEM; usb_anchor_urb(urb, &devinfo->sense_urbs); err = usb_submit_urb(urb, gfp); if (err) { usb_unanchor_urb(urb); uas_log_cmd_state(cmnd, "sense submit err", err); usb_free_urb(urb); - return NULL; } - return urb; + return err; } static int uas_submit_urbs(struct scsi_cmnd *cmnd, struct uas_dev_info *devinfo) { struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd); - struct urb *urb; int err; lockdep_assert_held(&devinfo->lock); if (cmdinfo->state & SUBMIT_STATUS_URB) { - urb = uas_submit_sense_urb(cmnd, GFP_ATOMIC); - if (!urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + err = uas_submit_sense_urb(cmnd, GFP_ATOMIC); + if (err) + return err; cmdinfo->state &= ~SUBMIT_STATUS_URB; } @@ -572,7 +570,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, cmdinfo->data_in_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC, cmnd, DMA_FROM_DEVICE); if (!cmdinfo->data_in_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_DATA_IN_URB; } @@ -582,7 +580,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->data_in_urb); uas_log_cmd_state(cmnd, "data in submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->state &= ~SUBMIT_DATA_IN_URB; cmdinfo->state |= DATA_IN_URB_INFLIGHT; @@ -592,7 +590,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, cmdinfo->data_out_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC, cmnd, DMA_TO_DEVICE); if (!cmdinfo->data_out_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_DATA_OUT_URB; } @@ -602,7 +600,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->data_out_urb); uas_log_cmd_state(cmnd, "data out submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->state &= ~SUBMIT_DATA_OUT_URB; cmdinfo->state |= DATA_OUT_URB_INFLIGHT; @@ -611,7 +609,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (cmdinfo->state & ALLOC_CMD_URB) { cmdinfo->cmd_urb = uas_alloc_cmd_urb(devinfo, GFP_ATOMIC, cmnd); if (!cmdinfo->cmd_urb) - return SCSI_MLQUEUE_DEVICE_BUSY; + return -ENOMEM; cmdinfo->state &= ~ALLOC_CMD_URB; } @@ -621,7 +619,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd, if (err) { usb_unanchor_urb(cmdinfo->cmd_urb); uas_log_cmd_state(cmnd, "cmd submit err", err); - return SCSI_MLQUEUE_DEVICE_BUSY; + return err; } cmdinfo->cmd_urb = NULL; cmdinfo->state &= ~SUBMIT_CMD_URB; @@ -698,7 +696,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd) * of queueing, no matter how fatal the error */ if (err == -ENODEV) { - set_host_byte(cmnd, DID_ERROR); + set_host_byte(cmnd, DID_NO_CONNECT); scsi_done(cmnd); goto zombie; } diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index fd68204374f2c..61d6c0f5d4856 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1359,6 +1359,13 @@ UNUSUAL_DEV( 0x0af0, 0x6971, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, option_ms_init, 0), +/* Reported by Timo Aaltonen */ +UNUSUAL_DEV( 0x0af0, 0x7011, 0x0000, 0x9999, + "Option", + "Mass Storage", + USB_SC_DEVICE, USB_PR_DEVICE, option_ms_init, + 0 ), + /* * Reported by F. Aben * This device (wrongly) has a vendor-specific device descriptor. diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 015aa92533536..e6a100376f09f 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1310,6 +1310,7 @@ static ssize_t select_usb_power_delivery_store(struct device *dev, { struct typec_port *port = to_typec_port(dev); struct usb_power_delivery *pd; + int ret; if (!port->ops || !port->ops->pd_set) return -EOPNOTSUPP; @@ -1318,7 +1319,11 @@ static ssize_t select_usb_power_delivery_store(struct device *dev, if (!pd) return -EINVAL; - return port->ops->pd_set(port, pd); + ret = port->ops->pd_set(port, pd); + if (ret) + return ret; + + return size; } static ssize_t select_usb_power_delivery_show(struct device *dev, diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 0ee3e6e29bb17..7118551827f6a 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -889,6 +889,7 @@ MODULE_DEVICE_TABLE(i2c, tcpci_id); #ifdef CONFIG_OF static const struct of_device_id tcpci_of_match[] = { { .compatible = "nxp,ptn5110", }, + { .compatible = "tcpci", }, {}, }; MODULE_DEVICE_TABLE(of, tcpci_of_match); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 0965972310275..9c872c9b9c450 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1501,7 +1501,8 @@ static void svdm_consume_identity(struct tcpm_port *port, const u32 *p, int cnt) port->partner_ident.cert_stat = p[VDO_INDEX_CSTAT]; port->partner_ident.product = product; - typec_partner_set_identity(port->partner); + if (port->partner) + typec_partner_set_identity(port->partner); tcpm_log(port, "Identity: %04x:%04x.%04x", PD_IDH_VID(vdo), @@ -1589,6 +1590,9 @@ static void tcpm_register_partner_altmodes(struct tcpm_port *port) struct typec_altmode *altmode; int i; + if (!port->partner) + return; + for (i = 0; i < modep->altmodes; i++) { altmode = typec_partner_register_altmode(port->partner, &modep->altmode_desc[i]); @@ -2435,7 +2439,7 @@ static int tcpm_register_sink_caps(struct tcpm_port *port) { struct usb_power_delivery_desc desc = { port->negotiated_rev }; struct usb_power_delivery_capabilities_desc caps = { }; - struct usb_power_delivery_capabilities *cap; + struct usb_power_delivery_capabilities *cap = port->partner_source_caps; if (!port->partner_pd) port->partner_pd = usb_power_delivery_register(NULL, &desc); @@ -2445,6 +2449,11 @@ static int tcpm_register_sink_caps(struct tcpm_port *port) memcpy(caps.pdo, port->sink_caps, sizeof(u32) * port->nr_sink_caps); caps.role = TYPEC_SINK; + if (cap) { + usb_power_delivery_unregister_capabilities(cap); + port->partner_source_caps = NULL; + } + cap = usb_power_delivery_register_capabilities(port->partner_pd, &caps); if (IS_ERR(cap)) return PTR_ERR(cap); @@ -3584,7 +3593,10 @@ static int tcpm_init_vconn(struct tcpm_port *port) static void tcpm_typec_connect(struct tcpm_port *port) { + struct typec_partner *partner; + if (!port->connected) { + port->connected = true; /* Make sure we don't report stale identity information */ memset(&port->partner_ident, 0, sizeof(port->partner_ident)); port->partner_desc.usb_pd = port->pd_capable; @@ -3594,9 +3606,13 @@ static void tcpm_typec_connect(struct tcpm_port *port) port->partner_desc.accessory = TYPEC_ACCESSORY_AUDIO; else port->partner_desc.accessory = TYPEC_ACCESSORY_NONE; - port->partner = typec_register_partner(port->typec_port, - &port->partner_desc); - port->connected = true; + partner = typec_register_partner(port->typec_port, &port->partner_desc); + if (IS_ERR(partner)) { + dev_err(port->dev, "Failed to register partner (%ld)\n", PTR_ERR(partner)); + return; + } + + port->partner = partner; typec_partner_set_usb_power_delivery(port->partner, port->partner_pd); } } @@ -3666,9 +3682,11 @@ static int tcpm_src_attach(struct tcpm_port *port) static void tcpm_typec_disconnect(struct tcpm_port *port) { if (port->connected) { - typec_partner_set_usb_power_delivery(port->partner, NULL); - typec_unregister_partner(port->partner); - port->partner = NULL; + if (port->partner) { + typec_partner_set_usb_power_delivery(port->partner, NULL); + typec_unregister_partner(port->partner); + port->partner = NULL; + } port->connected = false; } } @@ -3884,6 +3902,9 @@ static enum typec_cc_status tcpm_pwr_opmode_to_rp(enum typec_pwr_opmode opmode) static void tcpm_set_initial_svdm_version(struct tcpm_port *port) { + if (!port->partner) + return; + switch (port->negotiated_rev) { case PD_REV30: break; @@ -4873,6 +4894,7 @@ static void run_state_machine(struct tcpm_port *port) break; case PORT_RESET: tcpm_reset_port(port); + port->pd_events = 0; if (port->self_powered) tcpm_set_cc(port, TYPEC_CC_OPEN); else @@ -5407,6 +5429,7 @@ static void _tcpm_pd_hard_reset(struct tcpm_port *port) port->tcpc->set_bist_data(port->tcpc, false); switch (port->state) { + case TOGGLING: case ERROR_RECOVERY: case PORT_RESET: case PORT_RESET_WAIT_OFF: @@ -6111,14 +6134,14 @@ static int tcpm_pd_set(struct typec_port *p, struct usb_power_delivery *pd) if (data->sink_desc.pdo[0]) { for (i = 0; i < PDO_MAX_OBJECTS && data->sink_desc.pdo[i]; i++) port->snk_pdo[i] = data->sink_desc.pdo[i]; - port->nr_snk_pdo = i + 1; + port->nr_snk_pdo = i; port->operating_snk_mw = data->operating_snk_mw; } if (data->source_desc.pdo[0]) { for (i = 0; i < PDO_MAX_OBJECTS && data->source_desc.pdo[i]; i++) - port->snk_pdo[i] = data->source_desc.pdo[i]; - port->nr_src_pdo = i + 1; + port->src_pdo[i] = data->source_desc.pdo[i]; + port->nr_src_pdo = i; } switch (port->state) { @@ -6166,7 +6189,9 @@ static int tcpm_pd_set(struct typec_port *p, struct usb_power_delivery *pd) port->port_source_caps = data->source_cap; port->port_sink_caps = data->sink_cap; + typec_port_set_usb_power_delivery(p, NULL); port->selected_pd = pd; + typec_port_set_usb_power_delivery(p, port->selected_pd); unlock: mutex_unlock(&port->lock); return ret; @@ -6199,9 +6224,7 @@ static void tcpm_port_unregister_pd(struct tcpm_port *port) port->port_source_caps = NULL; for (i = 0; i < port->pd_count; i++) { usb_power_delivery_unregister_capabilities(port->pd_list[i]->sink_cap); - kfree(port->pd_list[i]->sink_cap); usb_power_delivery_unregister_capabilities(port->pd_list[i]->source_cap); - kfree(port->pd_list[i]->source_cap); devm_kfree(port->dev, port->pd_list[i]); port->pd_list[i] = NULL; usb_power_delivery_unregister(port->pds[i]); diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 0717cfcd9f8ca..191f86da283d0 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -28,6 +28,7 @@ #define TPS_REG_MODE 0x03 #define TPS_REG_CMD1 0x08 #define TPS_REG_DATA1 0x09 +#define TPS_REG_VERSION 0x0F #define TPS_REG_INT_EVENT1 0x14 #define TPS_REG_INT_EVENT2 0x15 #define TPS_REG_INT_MASK1 0x16 @@ -604,11 +605,11 @@ static irqreturn_t tps25750_interrupt(int irq, void *data) if (!tps6598x_read_status(tps, &status)) goto err_clear_ints; - if ((event[0] | event[1]) & TPS_REG_INT_POWER_STATUS_UPDATE) + if (event[0] & TPS_REG_INT_POWER_STATUS_UPDATE) if (!tps6598x_read_power_status(tps)) goto err_clear_ints; - if ((event[0] | event[1]) & TPS_REG_INT_DATA_STATUS_UPDATE) + if (event[0] & TPS_REG_INT_DATA_STATUS_UPDATE) if (!tps6598x_read_data_status(tps)) goto err_clear_ints; @@ -617,7 +618,7 @@ static irqreturn_t tps25750_interrupt(int irq, void *data) * a plug event. Therefore, we need to check * for pr/dr status change to set TypeC dr/pr accordingly. */ - if ((event[0] | event[1]) & TPS_REG_INT_PLUG_EVENT || + if (event[0] & TPS_REG_INT_PLUG_EVENT || tps6598x_has_role_changed(tps, status)) tps6598x_handle_plug_event(tps, status); @@ -636,49 +637,67 @@ static irqreturn_t tps25750_interrupt(int irq, void *data) static irqreturn_t tps6598x_interrupt(int irq, void *data) { + int intev_len = TPS_65981_2_6_INTEVENT_LEN; struct tps6598x *tps = data; - u64 event1 = 0; - u64 event2 = 0; + u64 event1[2] = { }; + u64 event2[2] = { }; + u32 version; u32 status; int ret; mutex_lock(&tps->lock); - ret = tps6598x_read64(tps, TPS_REG_INT_EVENT1, &event1); - ret |= tps6598x_read64(tps, TPS_REG_INT_EVENT2, &event2); + ret = tps6598x_read32(tps, TPS_REG_VERSION, &version); + if (ret) + dev_warn(tps->dev, "%s: failed to read version (%d)\n", + __func__, ret); + + if (TPS_VERSION_HW_VERSION(version) == TPS_VERSION_HW_65987_8_DH || + TPS_VERSION_HW_VERSION(version) == TPS_VERSION_HW_65987_8_DK) + intev_len = TPS_65987_8_INTEVENT_LEN; + + ret = tps6598x_block_read(tps, TPS_REG_INT_EVENT1, event1, intev_len); + + ret = tps6598x_block_read(tps, TPS_REG_INT_EVENT1, event1, intev_len); if (ret) { - dev_err(tps->dev, "%s: failed to read events\n", __func__); + dev_err(tps->dev, "%s: failed to read event1\n", __func__); goto err_unlock; } - trace_tps6598x_irq(event1, event2); + ret = tps6598x_block_read(tps, TPS_REG_INT_EVENT2, event2, intev_len); + if (ret) { + dev_err(tps->dev, "%s: failed to read event2\n", __func__); + goto err_unlock; + } + trace_tps6598x_irq(event1[0], event2[0]); - if (!(event1 | event2)) + if (!(event1[0] | event1[1] | event2[0] | event2[1])) goto err_unlock; if (!tps6598x_read_status(tps, &status)) goto err_clear_ints; - if ((event1 | event2) & TPS_REG_INT_POWER_STATUS_UPDATE) + if ((event1[0] | event2[0]) & TPS_REG_INT_POWER_STATUS_UPDATE) if (!tps6598x_read_power_status(tps)) goto err_clear_ints; - if ((event1 | event2) & TPS_REG_INT_DATA_STATUS_UPDATE) + if ((event1[0] | event2[0]) & TPS_REG_INT_DATA_STATUS_UPDATE) if (!tps6598x_read_data_status(tps)) goto err_clear_ints; /* Handle plug insert or removal */ - if ((event1 | event2) & TPS_REG_INT_PLUG_EVENT) + if ((event1[0] | event2[0]) & TPS_REG_INT_PLUG_EVENT) tps6598x_handle_plug_event(tps, status); err_clear_ints: - tps6598x_write64(tps, TPS_REG_INT_CLEAR1, event1); - tps6598x_write64(tps, TPS_REG_INT_CLEAR2, event2); + tps6598x_block_write(tps, TPS_REG_INT_CLEAR1, event1, intev_len); + tps6598x_block_write(tps, TPS_REG_INT_CLEAR2, event2, intev_len); err_unlock: mutex_unlock(&tps->lock); - if (event1 | event2) + if (event1[0] | event1[1] | event2[0] | event2[1]) return IRQ_HANDLED; + return IRQ_NONE; } diff --git a/drivers/usb/typec/tipd/tps6598x.h b/drivers/usb/typec/tipd/tps6598x.h index 89b24519463a1..9b23e90174521 100644 --- a/drivers/usb/typec/tipd/tps6598x.h +++ b/drivers/usb/typec/tipd/tps6598x.h @@ -253,4 +253,15 @@ #define TPS_PTCC_DEV 2 #define TPS_PTCC_APP 3 +/* Version Register */ +#define TPS_VERSION_HW_VERSION_MASK GENMASK(31, 24) +#define TPS_VERSION_HW_VERSION(x) TPS_FIELD_GET(TPS_VERSION_HW_VERSION_MASK, (x)) +#define TPS_VERSION_HW_65981_2_6 0x00 +#define TPS_VERSION_HW_65987_8_DH 0xF7 +#define TPS_VERSION_HW_65987_8_DK 0xF9 + +/* Int Event Register length */ +#define TPS_65981_2_6_INTEVENT_LEN 8 +#define TPS_65987_8_INTEVENT_LEN 11 + #endif /* __TPS6598X_H__ */ diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index d9d3c91125ca8..8be92fc1d12c9 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -275,8 +275,6 @@ static void ucsi_displayport_work(struct work_struct *work) struct ucsi_dp *dp = container_of(work, struct ucsi_dp, work); int ret; - mutex_lock(&dp->con->lock); - ret = typec_altmode_vdm(dp->alt, dp->header, dp->vdo_data, dp->vdo_size); if (ret) @@ -285,8 +283,6 @@ static void ucsi_displayport_work(struct work_struct *work) dp->vdo_data = NULL; dp->vdo_size = 0; dp->header = 0; - - mutex_unlock(&dp->con->lock); } void ucsi_displayport_remove_partner(struct typec_altmode *alt) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 14f5a7bfae2e9..b6a900cb657c6 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -36,6 +36,19 @@ */ #define UCSI_SWAP_TIMEOUT_MS 5000 +static int ucsi_read_message_in(struct ucsi *ucsi, void *buf, + size_t buf_size) +{ + /* + * Below UCSI 2.0, MESSAGE_IN was limited to 16 bytes. Truncate the + * reads here. + */ + if (ucsi->version <= UCSI_VERSION_1_2) + buf_size = clamp(buf_size, 0, 16); + + return ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, buf, buf_size); +} + static int ucsi_acknowledge_command(struct ucsi *ucsi) { u64 ctrl; @@ -72,7 +85,7 @@ static int ucsi_read_error(struct ucsi *ucsi) if (ret < 0) return ret; - ret = ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, &error, sizeof(error)); + ret = ucsi_read_message_in(ucsi, &error, sizeof(error)); if (ret) return ret; @@ -138,8 +151,12 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) if (!(cci & UCSI_CCI_COMMAND_COMPLETE)) return -EIO; - if (cci & UCSI_CCI_NOT_SUPPORTED) + if (cci & UCSI_CCI_NOT_SUPPORTED) { + if (ucsi_acknowledge_command(ucsi) < 0) + dev_err(ucsi->dev, + "ACK of unsupported command failed\n"); return -EOPNOTSUPP; + } if (cci & UCSI_CCI_ERROR) { if (cmd == UCSI_GET_ERROR_STATUS) @@ -170,7 +187,7 @@ int ucsi_send_command(struct ucsi *ucsi, u64 command, length = ret; if (data) { - ret = ucsi->ops->read(ucsi, UCSI_MESSAGE_IN, data, size); + ret = ucsi_read_message_in(ucsi, data, size); if (ret) goto out; } @@ -578,7 +595,8 @@ static int ucsi_read_pdos(struct ucsi_connector *con, u64 command; int ret; - if (ucsi->quirks & UCSI_NO_PARTNER_PDOS) + if (is_partner && + ucsi->quirks & UCSI_NO_PARTNER_PDOS) return 0; command = UCSI_COMMAND(UCSI_GET_PDOS) | UCSI_CONNECTOR_NUMBER(con->num); @@ -680,12 +698,6 @@ static int ucsi_register_partner_pdos(struct ucsi_connector *con) return PTR_ERR(cap); con->partner_source_caps = cap; - - ret = typec_partner_set_usb_power_delivery(con->partner, con->partner_pd); - if (ret) { - usb_power_delivery_unregister_capabilities(con->partner_source_caps); - return ret; - } } ret = ucsi_get_pdos(con, TYPEC_SINK, 1, caps.pdo); @@ -700,15 +712,9 @@ static int ucsi_register_partner_pdos(struct ucsi_connector *con) return PTR_ERR(cap); con->partner_sink_caps = cap; - - ret = typec_partner_set_usb_power_delivery(con->partner, con->partner_pd); - if (ret) { - usb_power_delivery_unregister_capabilities(con->partner_sink_caps); - return ret; - } } - return 0; + return typec_partner_set_usb_power_delivery(con->partner, con->partner_pd); } static void ucsi_unregister_partner_pdos(struct ucsi_connector *con) @@ -936,11 +942,11 @@ static void ucsi_handle_connector_change(struct work_struct *work) if (con->status.change & UCSI_CONSTAT_CAM_CHANGE) ucsi_partner_task(con, ucsi_check_altmodes, 1, 0); - clear_bit(EVENT_PENDING, &con->ucsi->flags); - mutex_lock(&ucsi->ppm_lock); + clear_bit(EVENT_PENDING, &con->ucsi->flags); ret = ucsi_acknowledge_connector_change(ucsi); mutex_unlock(&ucsi->ppm_lock); + if (ret) dev_err(ucsi->dev, "%s: ACK failed (%d)", __func__, ret); @@ -958,7 +964,7 @@ void ucsi_connector_change(struct ucsi *ucsi, u8 num) struct ucsi_connector *con = &ucsi->connector[num - 1]; if (!(ucsi->ntfy & UCSI_ENABLE_NTFY_CONNECTOR_CHANGE)) { - dev_dbg(ucsi->dev, "Bogus connector change event\n"); + dev_dbg(ucsi->dev, "Early connector change event\n"); return; } @@ -981,13 +987,47 @@ static int ucsi_reset_connector(struct ucsi_connector *con, bool hard) static int ucsi_reset_ppm(struct ucsi *ucsi) { - u64 command = UCSI_PPM_RESET; + u64 command; unsigned long tmo; u32 cci; int ret; mutex_lock(&ucsi->ppm_lock); + ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci)); + if (ret < 0) + goto out; + + /* + * If UCSI_CCI_RESET_COMPLETE is already set we must clear + * the flag before we start another reset. Send a + * UCSI_SET_NOTIFICATION_ENABLE command to achieve this. + * Ignore a timeout and try the reset anyway if this fails. + */ + if (cci & UCSI_CCI_RESET_COMPLETE) { + command = UCSI_SET_NOTIFICATION_ENABLE; + ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, + sizeof(command)); + if (ret < 0) + goto out; + + tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS); + do { + ret = ucsi->ops->read(ucsi, UCSI_CCI, + &cci, sizeof(cci)); + if (ret < 0) + goto out; + if (cci & UCSI_CCI_COMMAND_COMPLETE) + break; + if (time_is_before_jiffies(tmo)) + break; + msleep(20); + } while (1); + + WARN_ON(cci & UCSI_CCI_RESET_COMPLETE); + } + + command = UCSI_PPM_RESET; ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, sizeof(command)); if (ret < 0) @@ -1249,7 +1289,6 @@ static int ucsi_register_port(struct ucsi *ucsi, struct ucsi_connector *con) } con->port_source_caps = pd_cap; - typec_port_set_usb_power_delivery(con->port, con->pd); } memset(&pd_caps, 0, sizeof(pd_caps)); @@ -1266,9 +1305,10 @@ static int ucsi_register_port(struct ucsi *ucsi, struct ucsi_connector *con) } con->port_sink_caps = pd_cap; - typec_port_set_usb_power_delivery(con->port, con->pd); } + typec_port_set_usb_power_delivery(con->port, con->pd); + /* Alternate modes */ ret = ucsi_register_altmodes(con, UCSI_RECIPIENT_CON); if (ret) { @@ -1355,6 +1395,7 @@ static int ucsi_init(struct ucsi *ucsi) { struct ucsi_connector *con, *connector; u64 command, ntfy; + u32 cci; int ret; int i; @@ -1407,6 +1448,15 @@ static int ucsi_init(struct ucsi *ucsi) ucsi->connector = connector; ucsi->ntfy = ntfy; + + mutex_lock(&ucsi->ppm_lock); + ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci)); + mutex_unlock(&ucsi->ppm_lock); + if (ret) + return ret; + if (UCSI_CCI_CONNECTOR(cci)) + ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci)); + return 0; err_unregister: @@ -1558,6 +1608,15 @@ int ucsi_register(struct ucsi *ucsi) if (!ucsi->version) return -ENODEV; + /* + * Version format is JJ.M.N (JJ = Major version, M = Minor version, + * N = sub-minor version). + */ + dev_dbg(ucsi->dev, "Registered UCSI interface with version %x.%x.%x", + UCSI_BCD_GET_MAJOR(ucsi->version), + UCSI_BCD_GET_MINOR(ucsi->version), + UCSI_BCD_GET_SUBMINOR(ucsi->version)); + queue_delayed_work(system_long_wq, &ucsi->work, 0); ucsi_debugfs_register(ucsi); diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 6478016d5cb8b..ede9876488564 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -23,6 +23,17 @@ struct dentry; #define UCSI_CONTROL 8 #define UCSI_MESSAGE_IN 16 #define UCSI_MESSAGE_OUT 32 +#define UCSIv2_MESSAGE_OUT 272 + +/* UCSI versions */ +#define UCSI_VERSION_1_2 0x0120 +#define UCSI_VERSION_2_0 0x0200 +#define UCSI_VERSION_2_1 0x0210 +#define UCSI_VERSION_3_0 0x0300 + +#define UCSI_BCD_GET_MAJOR(_v_) (((_v_) >> 8) & 0xFF) +#define UCSI_BCD_GET_MINOR(_v_) (((_v_) >> 4) & 0x0F) +#define UCSI_BCD_GET_SUBMINOR(_v_) ((_v_) & 0x0F) /* Command Status and Connector Change Indication (CCI) bits */ #define UCSI_CCI_CONNECTOR(_c_) (((_c_) & GENMASK(7, 1)) >> 1) @@ -221,12 +232,12 @@ struct ucsi_cable_property { #define UCSI_CABLE_PROP_FLAG_VBUS_IN_CABLE BIT(0) #define UCSI_CABLE_PROP_FLAG_ACTIVE_CABLE BIT(1) #define UCSI_CABLE_PROP_FLAG_DIRECTIONALITY BIT(2) -#define UCSI_CABLE_PROP_FLAG_PLUG_TYPE(_f_) ((_f_) & GENMASK(3, 0)) +#define UCSI_CABLE_PROP_FLAG_PLUG_TYPE(_f_) (((_f_) & GENMASK(4, 3)) >> 3) #define UCSI_CABLE_PROPERTY_PLUG_TYPE_A 0 #define UCSI_CABLE_PROPERTY_PLUG_TYPE_B 1 #define UCSI_CABLE_PROPERTY_PLUG_TYPE_C 2 #define UCSI_CABLE_PROPERTY_PLUG_OTHER 3 -#define UCSI_CABLE_PROP_MODE_SUPPORT BIT(5) +#define UCSI_CABLE_PROP_FLAG_MODE_SUPPORT BIT(5) u8 latency; } __packed; diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c index 928eacbeb21ac..7b3ac133ef861 100644 --- a/drivers/usb/typec/ucsi/ucsi_acpi.c +++ b/drivers/usb/typec/ucsi/ucsi_acpi.c @@ -23,10 +23,11 @@ struct ucsi_acpi { void *base; struct completion complete; unsigned long flags; +#define UCSI_ACPI_SUPPRESS_EVENT 0 +#define UCSI_ACPI_COMMAND_PENDING 1 +#define UCSI_ACPI_ACK_PENDING 2 guid_t guid; u64 cmd; - bool dell_quirk_probed; - bool dell_quirk_active; }; static int ucsi_acpi_dsm(struct ucsi_acpi *ua, int func) @@ -79,9 +80,9 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, int ret; if (ack) - set_bit(ACK_PENDING, &ua->flags); + set_bit(UCSI_ACPI_ACK_PENDING, &ua->flags); else - set_bit(COMMAND_PENDING, &ua->flags); + set_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags); ret = ucsi_acpi_async_write(ucsi, offset, val, val_len); if (ret) @@ -92,9 +93,9 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, out_clear_bit: if (ack) - clear_bit(ACK_PENDING, &ua->flags); + clear_bit(UCSI_ACPI_ACK_PENDING, &ua->flags); else - clear_bit(COMMAND_PENDING, &ua->flags); + clear_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags); return ret; } @@ -129,51 +130,40 @@ static const struct ucsi_operations ucsi_zenbook_ops = { }; /* - * Some Dell laptops expect that an ACK command with the - * UCSI_ACK_CONNECTOR_CHANGE bit set is followed by a (separate) - * ACK command that only has the UCSI_ACK_COMMAND_COMPLETE bit set. - * If this is not done events are not delivered to OSPM and - * subsequent commands will timeout. + * Some Dell laptops don't like ACK commands with the + * UCSI_ACK_CONNECTOR_CHANGE but not the UCSI_ACK_COMMAND_COMPLETE + * bit set. To work around this send a dummy command and bundle the + * UCSI_ACK_CONNECTOR_CHANGE with the UCSI_ACK_COMMAND_COMPLETE + * for the dummy command. */ static int ucsi_dell_sync_write(struct ucsi *ucsi, unsigned int offset, const void *val, size_t val_len) { struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); - u64 cmd = *(u64 *)val, ack = 0; + u64 cmd = *(u64 *)val; + u64 dummycmd = UCSI_GET_CAPABILITY; int ret; - if (UCSI_COMMAND(cmd) == UCSI_ACK_CC_CI && - cmd & UCSI_ACK_CONNECTOR_CHANGE) - ack = UCSI_ACK_CC_CI | UCSI_ACK_COMMAND_COMPLETE; - - ret = ucsi_acpi_sync_write(ucsi, offset, val, val_len); - if (ret != 0) - return ret; - if (ack == 0) - return ret; - - if (!ua->dell_quirk_probed) { - ua->dell_quirk_probed = true; - - cmd = UCSI_GET_CAPABILITY; - ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd, - sizeof(cmd)); - if (ret == 0) - return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, - &ack, sizeof(ack)); - if (ret != -ETIMEDOUT) + if (cmd == (UCSI_ACK_CC_CI | UCSI_ACK_CONNECTOR_CHANGE)) { + cmd |= UCSI_ACK_COMMAND_COMPLETE; + + /* + * The UCSI core thinks it is sending a connector change ack + * and will accept new connector change events. We don't want + * this to happen for the dummy command as its response will + * still report the very event that the core is trying to clear. + */ + set_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags); + ret = ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &dummycmd, + sizeof(dummycmd)); + clear_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags); + + if (ret < 0) return ret; - - ua->dell_quirk_active = true; - dev_err(ua->dev, "Firmware bug: Additional ACK required after ACKing a connector change.\n"); - dev_err(ua->dev, "Firmware bug: Enabling workaround\n"); } - if (!ua->dell_quirk_active) - return ret; - - return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &ack, sizeof(ack)); + return ucsi_acpi_sync_write(ucsi, UCSI_CONTROL, &cmd, sizeof(cmd)); } static const struct ucsi_operations ucsi_dell_ops = { @@ -209,13 +199,14 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data) if (ret) return; - if (UCSI_CCI_CONNECTOR(cci)) + if (UCSI_CCI_CONNECTOR(cci) && + !test_bit(UCSI_ACPI_SUPPRESS_EVENT, &ua->flags)) ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci)); if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags)) complete(&ua->complete); if (cci & UCSI_CCI_COMMAND_COMPLETE && - test_bit(COMMAND_PENDING, &ua->flags)) + test_bit(UCSI_ACPI_COMMAND_PENDING, &ua->flags)) complete(&ua->complete); } diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index faccc942b381b..1d0e2d87e9b31 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -176,7 +176,8 @@ static int pmic_glink_ucsi_sync_write(struct ucsi *__ucsi, unsigned int offset, left = wait_for_completion_timeout(&ucsi->sync_ack, 5 * HZ); if (!left) { dev_err(ucsi->dev, "timeout waiting for UCSI sync write response\n"); - ret = -ETIMEDOUT; + /* return 0 here and let core UCSI code handle the CCI_BUSY */ + ret = 0; } else if (ucsi->sync_val) { dev_err(ucsi->dev, "sync write returned: %d\n", ucsi->sync_val); } @@ -243,10 +244,7 @@ static void pmic_glink_ucsi_notify(struct work_struct *work) ucsi_connector_change(ucsi->ucsi, con_num); } - if (ucsi->sync_pending && cci & UCSI_CCI_BUSY) { - ucsi->sync_val = -EBUSY; - complete(&ucsi->sync_ack); - } else if (ucsi->sync_pending && + if (ucsi->sync_pending && (cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE))) { complete(&ucsi->sync_ack); } @@ -255,6 +253,20 @@ static void pmic_glink_ucsi_notify(struct work_struct *work) static void pmic_glink_ucsi_register(struct work_struct *work) { struct pmic_glink_ucsi *ucsi = container_of(work, struct pmic_glink_ucsi, register_work); + int orientation; + int i; + + for (i = 0; i < PMIC_GLINK_MAX_PORTS; i++) { + if (!ucsi->port_orientation[i]) + continue; + orientation = gpiod_get_value(ucsi->port_orientation[i]); + + if (orientation >= 0) { + typec_switch_set(ucsi->port_switch[i], + orientation ? TYPEC_ORIENTATION_REVERSE + : TYPEC_ORIENTATION_NORMAL); + } + } ucsi_register(ucsi->ucsi); } @@ -297,11 +309,14 @@ static void pmic_glink_ucsi_destroy(void *data) mutex_unlock(&ucsi->lock); } +static unsigned long quirk_sc8180x = UCSI_NO_PARTNER_PDOS; + static const struct of_device_id pmic_glink_ucsi_of_quirks[] = { - { .compatible = "qcom,sc8180x-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, }, - { .compatible = "qcom,sc8280xp-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, }, - { .compatible = "qcom,sm8350-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, }, - { .compatible = "qcom,sm8550-pmic-glink", .data = (void *)UCSI_NO_PARTNER_PDOS, }, + { .compatible = "qcom,qcm6490-pmic-glink", .data = &quirk_sc8180x, }, + { .compatible = "qcom,sc8180x-pmic-glink", .data = &quirk_sc8180x, }, + { .compatible = "qcom,sc8280xp-pmic-glink", .data = &quirk_sc8180x, }, + { .compatible = "qcom,sm8350-pmic-glink", .data = &quirk_sc8180x, }, + { .compatible = "qcom,sm8550-pmic-glink", .data = &quirk_sc8180x, }, {} }; @@ -339,7 +354,7 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev, match = of_match_device(pmic_glink_ucsi_of_quirks, dev->parent); if (match) - ucsi->ucsi->quirks = (unsigned long)match->data; + ucsi->ucsi->quirks = *(unsigned long *)match->data; ucsi_set_drvdata(ucsi->ucsi, ucsi); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 778821bab7d93..ecfc16151d619 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -151,8 +151,6 @@ static void teardown_driver(struct mlx5_vdpa_net *ndev); static bool mlx5_vdpa_debug; -#define MLX5_CVQ_MAX_ENT 16 - #define MLX5_LOG_VIO_FLAG(_feature) \ do { \ if (features & BIT_ULL(_feature)) \ @@ -2276,9 +2274,16 @@ static void mlx5_vdpa_set_vq_num(struct vdpa_device *vdev, u16 idx, u32 num) struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; - if (!is_index_valid(mvdev, idx) || is_ctrl_vq_idx(mvdev, idx)) + if (!is_index_valid(mvdev, idx)) return; + if (is_ctrl_vq_idx(mvdev, idx)) { + struct mlx5_control_vq *cvq = &mvdev->cvq; + + cvq->vring.vring.num = num; + return; + } + mvq = &ndev->vqs[idx]; mvq->num_ent = num; } @@ -2963,7 +2968,7 @@ static int setup_cvq_vring(struct mlx5_vdpa_dev *mvdev) u16 idx = cvq->vring.last_avail_idx; err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features, - MLX5_CVQ_MAX_ENT, false, + cvq->vring.vring.num, false, (struct vring_desc *)(uintptr_t)cvq->desc_addr, (struct vring_avail *)(uintptr_t)cvq->driver_addr, (struct vring_used *)(uintptr_t)cvq->device_addr); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index be2925d0d2836..18584ce70bf07 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -160,7 +160,7 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim, u32 flags) } } - vdpasim->running = true; + vdpasim->running = false; spin_unlock(&vdpasim->iommu_lock); vdpasim->features = 0; @@ -483,6 +483,7 @@ static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status) mutex_lock(&vdpasim->mutex); vdpasim->status = status; + vdpasim->running = (status & VIRTIO_CONFIG_S_DRIVER_OK) != 0; mutex_unlock(&vdpasim->mutex); } diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index d62fbfff20b82..82b2afa9b7e31 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -141,13 +141,14 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, irq = &vdev->mc_irqs[index]; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_fsl_mc_irq_handler(hwirq, irq); + if (irq->trigger) + eventfd_signal(irq->trigger); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { u8 trigger = *(u8 *)data; - if (trigger) - vfio_fsl_mc_irq_handler(hwirq, irq); + if (trigger && irq->trigger) + eventfd_signal(irq->trigger); } return 0; diff --git a/drivers/vfio/pci/pds/lm.c b/drivers/vfio/pci/pds/lm.c index 79fe2e66bb498..6b94cc0bf45b4 100644 --- a/drivers/vfio/pci/pds/lm.c +++ b/drivers/vfio/pci/pds/lm.c @@ -92,8 +92,10 @@ static void pds_vfio_put_lm_file(struct pds_vfio_lm_file *lm_file) { mutex_lock(&lm_file->lock); + lm_file->disabled = true; lm_file->size = 0; lm_file->alloc_size = 0; + lm_file->filep->f_pos = 0; /* Free scatter list of file pages */ sg_free_table(&lm_file->sg_table); @@ -183,6 +185,12 @@ static ssize_t pds_vfio_save_read(struct file *filp, char __user *buf, pos = &filp->f_pos; mutex_lock(&lm_file->lock); + + if (lm_file->disabled) { + done = -ENODEV; + goto out_unlock; + } + if (*pos > lm_file->size) { done = -EINVAL; goto out_unlock; @@ -283,6 +291,11 @@ static ssize_t pds_vfio_restore_write(struct file *filp, const char __user *buf, mutex_lock(&lm_file->lock); + if (lm_file->disabled) { + done = -ENODEV; + goto out_unlock; + } + while (len) { size_t page_offset; struct page *page; diff --git a/drivers/vfio/pci/pds/lm.h b/drivers/vfio/pci/pds/lm.h index 13be893198b74..9511b1afc6a11 100644 --- a/drivers/vfio/pci/pds/lm.h +++ b/drivers/vfio/pci/pds/lm.h @@ -27,6 +27,7 @@ struct pds_vfio_lm_file { struct scatterlist *last_offset_sg; /* Iterator */ unsigned int sg_last_entry; unsigned long last_offset; + bool disabled; }; struct pds_vfio_pci_device; diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c index 4c351c59d05a9..a286ebcc71126 100644 --- a/drivers/vfio/pci/pds/vfio_dev.c +++ b/drivers/vfio/pci/pds/vfio_dev.c @@ -32,9 +32,9 @@ void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio) mutex_lock(&pds_vfio->reset_mutex); if (pds_vfio->deferred_reset) { pds_vfio->deferred_reset = false; + pds_vfio_put_restore_file(pds_vfio); + pds_vfio_put_save_file(pds_vfio); if (pds_vfio->state == VFIO_DEVICE_STATE_ERROR) { - pds_vfio_put_restore_file(pds_vfio); - pds_vfio_put_save_file(pds_vfio); pds_vfio_dirty_disable(pds_vfio, false); } pds_vfio->state = pds_vfio->deferred_reset_state; diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index cb5b7f865d585..e727941f589de 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -71,6 +71,8 @@ static bool vfio_pci_dev_in_denylist(struct pci_dev *pdev) case PCI_DEVICE_ID_INTEL_QAT_C62X_VF: case PCI_DEVICE_ID_INTEL_QAT_DH895XCC: case PCI_DEVICE_ID_INTEL_QAT_DH895XCC_VF: + case PCI_DEVICE_ID_INTEL_DSA_SPR0: + case PCI_DEVICE_ID_INTEL_IAX_SPR0: return true; default: return false; diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 1cbc990d42e07..142c9e494e506 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -778,25 +778,26 @@ static int vfio_pci_count_devs(struct pci_dev *pdev, void *data) } struct vfio_pci_fill_info { - struct vfio_pci_dependent_device __user *devices; - struct vfio_pci_dependent_device __user *devices_end; struct vfio_device *vdev; + struct vfio_pci_dependent_device *devices; + int nr_devices; u32 count; u32 flags; }; static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data) { - struct vfio_pci_dependent_device info = { - .segment = pci_domain_nr(pdev->bus), - .bus = pdev->bus->number, - .devfn = pdev->devfn, - }; + struct vfio_pci_dependent_device *info; struct vfio_pci_fill_info *fill = data; - fill->count++; - if (fill->devices >= fill->devices_end) - return 0; + /* The topology changed since we counted devices */ + if (fill->count >= fill->nr_devices) + return -EAGAIN; + + info = &fill->devices[fill->count++]; + info->segment = pci_domain_nr(pdev->bus); + info->bus = pdev->bus->number; + info->devfn = pdev->devfn; if (fill->flags & VFIO_PCI_HOT_RESET_FLAG_DEV_ID) { struct iommufd_ctx *iommufd = vfio_iommufd_device_ictx(fill->vdev); @@ -809,19 +810,19 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data) */ vdev = vfio_find_device_in_devset(dev_set, &pdev->dev); if (!vdev) { - info.devid = VFIO_PCI_DEVID_NOT_OWNED; + info->devid = VFIO_PCI_DEVID_NOT_OWNED; } else { int id = vfio_iommufd_get_dev_id(vdev, iommufd); if (id > 0) - info.devid = id; + info->devid = id; else if (id == -ENOENT) - info.devid = VFIO_PCI_DEVID_OWNED; + info->devid = VFIO_PCI_DEVID_OWNED; else - info.devid = VFIO_PCI_DEVID_NOT_OWNED; + info->devid = VFIO_PCI_DEVID_NOT_OWNED; } /* If devid is VFIO_PCI_DEVID_NOT_OWNED, clear owned flag. */ - if (info.devid == VFIO_PCI_DEVID_NOT_OWNED) + if (info->devid == VFIO_PCI_DEVID_NOT_OWNED) fill->flags &= ~VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED; } else { struct iommu_group *iommu_group; @@ -830,13 +831,10 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data) if (!iommu_group) return -EPERM; /* Cannot reset non-isolated devices */ - info.group_id = iommu_group_id(iommu_group); + info->group_id = iommu_group_id(iommu_group); iommu_group_put(iommu_group); } - if (copy_to_user(fill->devices, &info, sizeof(info))) - return -EFAULT; - fill->devices++; return 0; } @@ -1258,10 +1256,11 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info( { unsigned long minsz = offsetofend(struct vfio_pci_hot_reset_info, count); + struct vfio_pci_dependent_device *devices = NULL; struct vfio_pci_hot_reset_info hdr; struct vfio_pci_fill_info fill = {}; bool slot = false; - int ret = 0; + int ret, count; if (copy_from_user(&hdr, arg, minsz)) return -EFAULT; @@ -1277,9 +1276,23 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info( else if (pci_probe_reset_bus(vdev->pdev->bus)) return -ENODEV; - fill.devices = arg->devices; - fill.devices_end = arg->devices + - (hdr.argsz - sizeof(hdr)) / sizeof(arg->devices[0]); + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs, + &count, slot); + if (ret) + return ret; + + if (count > (hdr.argsz - sizeof(hdr)) / sizeof(*devices)) { + hdr.count = count; + ret = -ENOSPC; + goto header; + } + + devices = kcalloc(count, sizeof(*devices), GFP_KERNEL); + if (!devices) + return -ENOMEM; + + fill.devices = devices; + fill.nr_devices = count; fill.vdev = &vdev->vdev; if (vfio_device_cdev_opened(&vdev->vdev)) @@ -1291,16 +1304,23 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info( &fill, slot); mutex_unlock(&vdev->vdev.dev_set->lock); if (ret) - return ret; + goto out; + + if (copy_to_user(arg->devices, devices, + sizeof(*devices) * fill.count)) { + ret = -EFAULT; + goto out; + } hdr.count = fill.count; hdr.flags = fill.flags; - if (copy_to_user(arg, &hdr, minsz)) - return -EFAULT; - if (fill.count > fill.devices - arg->devices) - return -ENOSPC; - return 0; +header: + if (copy_to_user(arg, &hdr, minsz)) + ret = -EFAULT; +out: + kfree(devices); + return ret; } static int diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 237beac838097..e80c5d75b5419 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -90,22 +90,28 @@ static void vfio_send_intx_eventfd(void *opaque, void *unused) if (likely(is_intx(vdev) && !vdev->virq_disabled)) { struct vfio_pci_irq_ctx *ctx; + struct eventfd_ctx *trigger; ctx = vfio_irq_ctx_get(vdev, 0); if (WARN_ON_ONCE(!ctx)) return; - eventfd_signal(ctx->trigger); + + trigger = READ_ONCE(ctx->trigger); + if (likely(trigger)) + eventfd_signal(trigger); } } /* Returns true if the INTx vfio_pci_irq_ctx.masked value is changed. */ -bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) +static bool __vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; struct vfio_pci_irq_ctx *ctx; unsigned long flags; bool masked_changed = false; + lockdep_assert_held(&vdev->igate); + spin_lock_irqsave(&vdev->irqlock, flags); /* @@ -143,6 +149,17 @@ bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) return masked_changed; } +bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev) +{ + bool mask_changed; + + mutex_lock(&vdev->igate); + mask_changed = __vfio_pci_intx_mask(vdev); + mutex_unlock(&vdev->igate); + + return mask_changed; +} + /* * If this is triggered by an eventfd, we can't call eventfd_signal * or else we'll deadlock on the eventfd wait queue. Return >0 when @@ -194,12 +211,21 @@ static int vfio_pci_intx_unmask_handler(void *opaque, void *unused) return ret; } -void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) +static void __vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) { + lockdep_assert_held(&vdev->igate); + if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0) vfio_send_intx_eventfd(vdev, NULL); } +void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev) +{ + mutex_lock(&vdev->igate); + __vfio_pci_intx_unmask(vdev); + mutex_unlock(&vdev->igate); +} + static irqreturn_t vfio_intx_handler(int irq, void *dev_id) { struct vfio_pci_core_device *vdev = dev_id; @@ -231,97 +257,102 @@ static irqreturn_t vfio_intx_handler(int irq, void *dev_id) return ret; } -static int vfio_intx_enable(struct vfio_pci_core_device *vdev) +static int vfio_intx_enable(struct vfio_pci_core_device *vdev, + struct eventfd_ctx *trigger) { + struct pci_dev *pdev = vdev->pdev; struct vfio_pci_irq_ctx *ctx; + unsigned long irqflags; + char *name; + int ret; if (!is_irq_none(vdev)) return -EINVAL; - if (!vdev->pdev->irq) + if (!pdev->irq) return -ENODEV; + name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-intx(%s)", pci_name(pdev)); + if (!name) + return -ENOMEM; + ctx = vfio_irq_ctx_alloc(vdev, 0); - if (!ctx) + if (!ctx) { + kfree(name); return -ENOMEM; + } + + ctx->name = name; + ctx->trigger = trigger; /* - * If the virtual interrupt is masked, restore it. Devices - * supporting DisINTx can be masked at the hardware level - * here, non-PCI-2.3 devices will have to wait until the - * interrupt is enabled. + * Fill the initial masked state based on virq_disabled. After + * enable, changing the DisINTx bit in vconfig directly changes INTx + * masking. igate prevents races during setup, once running masked + * is protected via irqlock. + * + * Devices supporting DisINTx also reflect the current mask state in + * the physical DisINTx bit, which is not affected during IRQ setup. + * + * Devices without DisINTx support require an exclusive interrupt. + * IRQ masking is performed at the IRQ chip. Again, igate protects + * against races during setup and IRQ handlers and irqfds are not + * yet active, therefore masked is stable and can be used to + * conditionally auto-enable the IRQ. + * + * irq_type must be stable while the IRQ handler is registered, + * therefore it must be set before request_irq(). */ ctx->masked = vdev->virq_disabled; - if (vdev->pci_2_3) - pci_intx(vdev->pdev, !ctx->masked); + if (vdev->pci_2_3) { + pci_intx(pdev, !ctx->masked); + irqflags = IRQF_SHARED; + } else { + irqflags = ctx->masked ? IRQF_NO_AUTOEN : 0; + } vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX; + ret = request_irq(pdev->irq, vfio_intx_handler, + irqflags, ctx->name, vdev); + if (ret) { + vdev->irq_type = VFIO_PCI_NUM_IRQS; + kfree(name); + vfio_irq_ctx_free(vdev, ctx, 0); + return ret; + } + return 0; } -static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, int fd) +static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, + struct eventfd_ctx *trigger) { struct pci_dev *pdev = vdev->pdev; - unsigned long irqflags = IRQF_SHARED; struct vfio_pci_irq_ctx *ctx; - struct eventfd_ctx *trigger; - unsigned long flags; - int ret; + struct eventfd_ctx *old; ctx = vfio_irq_ctx_get(vdev, 0); if (WARN_ON_ONCE(!ctx)) return -EINVAL; - if (ctx->trigger) { - free_irq(pdev->irq, vdev); - kfree(ctx->name); - eventfd_ctx_put(ctx->trigger); - ctx->trigger = NULL; - } - - if (fd < 0) /* Disable only */ - return 0; + old = ctx->trigger; - ctx->name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-intx(%s)", - pci_name(pdev)); - if (!ctx->name) - return -ENOMEM; + WRITE_ONCE(ctx->trigger, trigger); - trigger = eventfd_ctx_fdget(fd); - if (IS_ERR(trigger)) { - kfree(ctx->name); - return PTR_ERR(trigger); - } - - ctx->trigger = trigger; - - if (!vdev->pci_2_3) - irqflags = 0; - - ret = request_irq(pdev->irq, vfio_intx_handler, - irqflags, ctx->name, vdev); - if (ret) { - ctx->trigger = NULL; - kfree(ctx->name); - eventfd_ctx_put(trigger); - return ret; + /* Releasing an old ctx requires synchronizing in-flight users */ + if (old) { + synchronize_irq(pdev->irq); + vfio_virqfd_flush_thread(&ctx->unmask); + eventfd_ctx_put(old); } - /* - * INTx disable will stick across the new irq setup, - * disable_irq won't. - */ - spin_lock_irqsave(&vdev->irqlock, flags); - if (!vdev->pci_2_3 && ctx->masked) - disable_irq_nosync(pdev->irq); - spin_unlock_irqrestore(&vdev->irqlock, flags); - return 0; } static void vfio_intx_disable(struct vfio_pci_core_device *vdev) { + struct pci_dev *pdev = vdev->pdev; struct vfio_pci_irq_ctx *ctx; ctx = vfio_irq_ctx_get(vdev, 0); @@ -329,10 +360,13 @@ static void vfio_intx_disable(struct vfio_pci_core_device *vdev) if (ctx) { vfio_virqfd_disable(&ctx->unmask); vfio_virqfd_disable(&ctx->mask); + free_irq(pdev->irq, vdev); + if (ctx->trigger) + eventfd_ctx_put(ctx->trigger); + kfree(ctx->name); + vfio_irq_ctx_free(vdev, ctx, 0); } - vfio_intx_set_signal(vdev, -1); vdev->irq_type = VFIO_PCI_NUM_IRQS; - vfio_irq_ctx_free(vdev, ctx, 0); } /* @@ -560,11 +594,11 @@ static int vfio_pci_set_intx_unmask(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_pci_intx_unmask(vdev); + __vfio_pci_intx_unmask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t unmask = *(uint8_t *)data; if (unmask) - vfio_pci_intx_unmask(vdev); + __vfio_pci_intx_unmask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { struct vfio_pci_irq_ctx *ctx = vfio_irq_ctx_get(vdev, 0); int32_t fd = *(int32_t *)data; @@ -591,11 +625,11 @@ static int vfio_pci_set_intx_mask(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_pci_intx_mask(vdev); + __vfio_pci_intx_mask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t mask = *(uint8_t *)data; if (mask) - vfio_pci_intx_mask(vdev); + __vfio_pci_intx_mask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { return -ENOTTY; /* XXX implement me */ } @@ -616,19 +650,23 @@ static int vfio_pci_set_intx_trigger(struct vfio_pci_core_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { + struct eventfd_ctx *trigger = NULL; int32_t fd = *(int32_t *)data; int ret; - if (is_intx(vdev)) - return vfio_intx_set_signal(vdev, fd); + if (fd >= 0) { + trigger = eventfd_ctx_fdget(fd); + if (IS_ERR(trigger)) + return PTR_ERR(trigger); + } - ret = vfio_intx_enable(vdev); - if (ret) - return ret; + if (is_intx(vdev)) + ret = vfio_intx_set_signal(vdev, trigger); + else + ret = vfio_intx_enable(vdev, trigger); - ret = vfio_intx_set_signal(vdev, fd); - if (ret) - vfio_intx_disable(vdev); + if (ret && trigger) + eventfd_ctx_put(trigger); return ret; } diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c index 61a1bfb68ac78..ef41ecef83af1 100644 --- a/drivers/vfio/platform/vfio_platform_irq.c +++ b/drivers/vfio/platform/vfio_platform_irq.c @@ -136,6 +136,16 @@ static int vfio_platform_set_irq_unmask(struct vfio_platform_device *vdev, return 0; } +/* + * The trigger eventfd is guaranteed valid in the interrupt path + * and protected by the igate mutex when triggered via ioctl. + */ +static void vfio_send_eventfd(struct vfio_platform_irq *irq_ctx) +{ + if (likely(irq_ctx->trigger)) + eventfd_signal(irq_ctx->trigger); +} + static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; @@ -155,7 +165,7 @@ static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) spin_unlock_irqrestore(&irq_ctx->lock, flags); if (ret == IRQ_HANDLED) - eventfd_signal(irq_ctx->trigger); + vfio_send_eventfd(irq_ctx); return ret; } @@ -164,52 +174,40 @@ static irqreturn_t vfio_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; - eventfd_signal(irq_ctx->trigger); + vfio_send_eventfd(irq_ctx); return IRQ_HANDLED; } static int vfio_set_trigger(struct vfio_platform_device *vdev, int index, - int fd, irq_handler_t handler) + int fd) { struct vfio_platform_irq *irq = &vdev->irqs[index]; struct eventfd_ctx *trigger; - int ret; if (irq->trigger) { - irq_clear_status_flags(irq->hwirq, IRQ_NOAUTOEN); - free_irq(irq->hwirq, irq); - kfree(irq->name); + disable_irq(irq->hwirq); eventfd_ctx_put(irq->trigger); irq->trigger = NULL; } if (fd < 0) /* Disable only */ return 0; - irq->name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-irq[%d](%s)", - irq->hwirq, vdev->name); - if (!irq->name) - return -ENOMEM; trigger = eventfd_ctx_fdget(fd); - if (IS_ERR(trigger)) { - kfree(irq->name); + if (IS_ERR(trigger)) return PTR_ERR(trigger); - } irq->trigger = trigger; - irq_set_status_flags(irq->hwirq, IRQ_NOAUTOEN); - ret = request_irq(irq->hwirq, handler, 0, irq->name, irq); - if (ret) { - kfree(irq->name); - eventfd_ctx_put(trigger); - irq->trigger = NULL; - return ret; - } - - if (!irq->masked) - enable_irq(irq->hwirq); + /* + * irq->masked effectively provides nested disables within the overall + * enable relative to trigger. Specifically request_irq() is called + * with NO_AUTOEN, therefore the IRQ is initially disabled. The user + * may only further disable the IRQ with a MASK operations because + * irq->masked is initially false. + */ + enable_irq(irq->hwirq); return 0; } @@ -228,7 +226,7 @@ static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev, handler = vfio_irq_handler; if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) - return vfio_set_trigger(vdev, index, -1, handler); + return vfio_set_trigger(vdev, index, -1); if (start != 0 || count != 1) return -EINVAL; @@ -236,7 +234,7 @@ static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev, if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { int32_t fd = *(int32_t *)data; - return vfio_set_trigger(vdev, index, fd, handler); + return vfio_set_trigger(vdev, index, fd); } if (flags & VFIO_IRQ_SET_DATA_NONE) { @@ -260,6 +258,14 @@ int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, unsigned start, unsigned count, uint32_t flags, void *data) = NULL; + /* + * For compatibility, errors from request_irq() are local to the + * SET_IRQS path and reflected in the name pointer. This allows, + * for example, polling mode fallback for an exclusive IRQ failure. + */ + if (IS_ERR(vdev->irqs[index].name)) + return PTR_ERR(vdev->irqs[index].name); + switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) { case VFIO_IRQ_SET_ACTION_MASK: func = vfio_platform_set_irq_mask; @@ -280,7 +286,7 @@ int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, int vfio_platform_irq_init(struct vfio_platform_device *vdev) { - int cnt = 0, i; + int cnt = 0, i, ret = 0; while (vdev->get_irq(vdev, cnt) >= 0) cnt++; @@ -292,37 +298,70 @@ int vfio_platform_irq_init(struct vfio_platform_device *vdev) for (i = 0; i < cnt; i++) { int hwirq = vdev->get_irq(vdev, i); + irq_handler_t handler = vfio_irq_handler; - if (hwirq < 0) + if (hwirq < 0) { + ret = -EINVAL; goto err; + } spin_lock_init(&vdev->irqs[i].lock); vdev->irqs[i].flags = VFIO_IRQ_INFO_EVENTFD; - if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) + if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) { vdev->irqs[i].flags |= VFIO_IRQ_INFO_MASKABLE | VFIO_IRQ_INFO_AUTOMASKED; + handler = vfio_automasked_irq_handler; + } vdev->irqs[i].count = 1; vdev->irqs[i].hwirq = hwirq; vdev->irqs[i].masked = false; + vdev->irqs[i].name = kasprintf(GFP_KERNEL_ACCOUNT, + "vfio-irq[%d](%s)", hwirq, + vdev->name); + if (!vdev->irqs[i].name) { + ret = -ENOMEM; + goto err; + } + + ret = request_irq(hwirq, handler, IRQF_NO_AUTOEN, + vdev->irqs[i].name, &vdev->irqs[i]); + if (ret) { + kfree(vdev->irqs[i].name); + vdev->irqs[i].name = ERR_PTR(ret); + } } vdev->num_irqs = cnt; return 0; err: + for (--i; i >= 0; i--) { + if (!IS_ERR(vdev->irqs[i].name)) { + free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]); + kfree(vdev->irqs[i].name); + } + } kfree(vdev->irqs); - return -EINVAL; + return ret; } void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev) { int i; - for (i = 0; i < vdev->num_irqs; i++) - vfio_set_trigger(vdev, i, -1, NULL); + for (i = 0; i < vdev->num_irqs; i++) { + vfio_virqfd_disable(&vdev->irqs[i].mask); + vfio_virqfd_disable(&vdev->irqs[i].unmask); + if (!IS_ERR(vdev->irqs[i].name)) { + free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]); + if (vdev->irqs[i].trigger) + eventfd_ctx_put(vdev->irqs[i].trigger); + kfree(vdev->irqs[i].name); + } + } vdev->num_irqs = 0; kfree(vdev->irqs); diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c index 29c564b7a6e13..5322691338019 100644 --- a/drivers/vfio/virqfd.c +++ b/drivers/vfio/virqfd.c @@ -101,6 +101,13 @@ static void virqfd_inject(struct work_struct *work) virqfd->thread(virqfd->opaque, virqfd->data); } +static void virqfd_flush_inject(struct work_struct *work) +{ + struct virqfd *virqfd = container_of(work, struct virqfd, flush_inject); + + flush_work(&virqfd->inject); +} + int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), @@ -124,6 +131,7 @@ int vfio_virqfd_enable(void *opaque, INIT_WORK(&virqfd->shutdown, virqfd_shutdown); INIT_WORK(&virqfd->inject, virqfd_inject); + INIT_WORK(&virqfd->flush_inject, virqfd_flush_inject); irqfd = fdget(fd); if (!irqfd.file) { @@ -213,3 +221,16 @@ void vfio_virqfd_disable(struct virqfd **pvirqfd) flush_workqueue(vfio_irqfd_cleanup_wq); } EXPORT_SYMBOL_GPL(vfio_virqfd_disable); + +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd) +{ + unsigned long flags; + + spin_lock_irqsave(&virqfd_lock, flags); + if (*pvirqfd && (*pvirqfd)->thread) + queue_work(vfio_irqfd_cleanup_wq, &(*pvirqfd)->flush_inject); + spin_unlock_irqrestore(&virqfd_lock, flags); + + flush_workqueue(vfio_irqfd_cleanup_wq); +} +EXPORT_SYMBOL_GPL(vfio_virqfd_flush_thread); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 045f666b4f12a..32686c79c41d6 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2799,9 +2799,19 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq) r = vhost_get_avail_idx(vq, &avail_idx); if (unlikely(r)) return false; + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); + if (vq->avail_idx != vq->last_avail_idx) { + /* Since we have updated avail_idx, the following + * call to vhost_get_vq_desc() will read available + * ring entries. Make sure that read happens after + * the avail_idx read. + */ + smp_rmb(); + return false; + } - return vq->avail_idx == vq->last_avail_idx; + return true; } EXPORT_SYMBOL_GPL(vhost_vq_avail_empty); @@ -2838,9 +2848,19 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) &vq->avail->idx, r); return false; } + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); + if (vq->avail_idx != vq->last_avail_idx) { + /* Since we have updated avail_idx, the following + * call to vhost_get_vq_desc() will read available + * ring entries. Make sure that read happens after + * the avail_idx read. + */ + smp_rmb(); + return true; + } - return vq->avail_idx != vq->last_avail_idx; + return false; } EXPORT_SYMBOL_GPL(vhost_enable_notify); diff --git a/drivers/video/backlight/da9052_bl.c b/drivers/video/backlight/da9052_bl.c index 1cdc8543310b4..b8ff7046510eb 100644 --- a/drivers/video/backlight/da9052_bl.c +++ b/drivers/video/backlight/da9052_bl.c @@ -117,6 +117,7 @@ static int da9052_backlight_probe(struct platform_device *pdev) wleds->led_reg = platform_get_device_id(pdev)->driver_data; wleds->state = DA9052_WLEDS_OFF; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; props.max_brightness = DA9052_MAX_BRIGHTNESS; diff --git a/drivers/video/backlight/hx8357.c b/drivers/video/backlight/hx8357.c index d7298376cf74d..bf18337ff0c2c 100644 --- a/drivers/video/backlight/hx8357.c +++ b/drivers/video/backlight/hx8357.c @@ -609,11 +609,13 @@ static int hx8357_probe(struct spi_device *spi) lcd->im_pins = devm_gpiod_get_array_optional(dev, "im", GPIOD_OUT_LOW); if (IS_ERR(lcd->im_pins)) return dev_err_probe(dev, PTR_ERR(lcd->im_pins), "failed to request im GPIOs\n"); - if (lcd->im_pins->ndescs < HX8357_NUM_IM_PINS) - return dev_err_probe(dev, -EINVAL, "not enough im GPIOs\n"); + if (lcd->im_pins) { + if (lcd->im_pins->ndescs < HX8357_NUM_IM_PINS) + return dev_err_probe(dev, -EINVAL, "not enough im GPIOs\n"); - for (i = 0; i < HX8357_NUM_IM_PINS; i++) - gpiod_set_consumer_name(lcd->im_pins->desc[i], "im_pins"); + for (i = 0; i < HX8357_NUM_IM_PINS; i++) + gpiod_set_consumer_name(lcd->im_pins->desc[i], "im_pins"); + } lcdev = devm_lcd_device_register(&spi->dev, "mxsfb", &spi->dev, lcd, &hx8357_ops); diff --git a/drivers/video/backlight/ktz8866.c b/drivers/video/backlight/ktz8866.c index 9c980f2571ee3..014877b5a9848 100644 --- a/drivers/video/backlight/ktz8866.c +++ b/drivers/video/backlight/ktz8866.c @@ -97,20 +97,20 @@ static void ktz8866_init(struct ktz8866 *ktz) { unsigned int val = 0; - if (of_property_read_u32(ktz->client->dev.of_node, "current-num-sinks", &val)) + if (!of_property_read_u32(ktz->client->dev.of_node, "current-num-sinks", &val)) ktz8866_write(ktz, BL_EN, BIT(val) - 1); else /* Enable all 6 current sinks if the number of current sinks isn't specified. */ ktz8866_write(ktz, BL_EN, BIT(6) - 1); - if (of_property_read_u32(ktz->client->dev.of_node, "kinetic,current-ramp-delay-ms", &val)) { + if (!of_property_read_u32(ktz->client->dev.of_node, "kinetic,current-ramp-delay-ms", &val)) { if (val <= 128) ktz8866_write(ktz, BL_CFG2, BIT(7) | (ilog2(val) << 3) | PWM_HYST); else ktz8866_write(ktz, BL_CFG2, BIT(7) | ((5 + val / 64) << 3) | PWM_HYST); } - if (of_property_read_u32(ktz->client->dev.of_node, "kinetic,led-enable-ramp-delay-ms", &val)) { + if (!of_property_read_u32(ktz->client->dev.of_node, "kinetic,led-enable-ramp-delay-ms", &val)) { if (val == 0) ktz8866_write(ktz, BL_DIMMING, 0); else { diff --git a/drivers/video/backlight/lm3630a_bl.c b/drivers/video/backlight/lm3630a_bl.c index a3412c936ca28..26ff4178cc161 100644 --- a/drivers/video/backlight/lm3630a_bl.c +++ b/drivers/video/backlight/lm3630a_bl.c @@ -233,7 +233,7 @@ static int lm3630a_bank_a_get_brightness(struct backlight_device *bl) if (rval < 0) goto out_i2c_err; brightness |= rval; - goto out; + return brightness; } /* disable sleep */ @@ -244,11 +244,8 @@ static int lm3630a_bank_a_get_brightness(struct backlight_device *bl) rval = lm3630a_read(pchip, REG_BRT_A); if (rval < 0) goto out_i2c_err; - brightness = rval; + return rval; -out: - bl->props.brightness = brightness; - return bl->props.brightness; out_i2c_err: dev_err(pchip->dev, "i2c failed to access register\n"); return 0; @@ -310,7 +307,7 @@ static int lm3630a_bank_b_get_brightness(struct backlight_device *bl) if (rval < 0) goto out_i2c_err; brightness |= rval; - goto out; + return brightness; } /* disable sleep */ @@ -321,11 +318,8 @@ static int lm3630a_bank_b_get_brightness(struct backlight_device *bl) rval = lm3630a_read(pchip, REG_BRT_B); if (rval < 0) goto out_i2c_err; - brightness = rval; + return rval; -out: - bl->props.brightness = brightness; - return bl->props.brightness; out_i2c_err: dev_err(pchip->dev, "i2c failed to access register\n"); return 0; @@ -343,6 +337,7 @@ static int lm3630a_backlight_register(struct lm3630a_chip *pchip) struct backlight_properties props; const char *label; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; if (pdata->leda_ctrl != LM3630A_LEDA_DISABLE) { props.brightness = pdata->leda_init_brt; diff --git a/drivers/video/backlight/lm3639_bl.c b/drivers/video/backlight/lm3639_bl.c index 5246c171497d6..564f62acd7211 100644 --- a/drivers/video/backlight/lm3639_bl.c +++ b/drivers/video/backlight/lm3639_bl.c @@ -338,6 +338,7 @@ static int lm3639_probe(struct i2c_client *client) } /* backlight */ + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; props.brightness = pdata->init_brt_led; props.max_brightness = pdata->max_brt_led; diff --git a/drivers/video/backlight/lp8788_bl.c b/drivers/video/backlight/lp8788_bl.c index d1a14b0db265b..31f97230ee506 100644 --- a/drivers/video/backlight/lp8788_bl.c +++ b/drivers/video/backlight/lp8788_bl.c @@ -191,6 +191,7 @@ static int lp8788_backlight_register(struct lp8788_bl *bl) int init_brt; char *name; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_PLATFORM; props.max_brightness = MAX_BRIGHTNESS; diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 2d0bcc1d786e5..411bf2b2c4d03 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -501,6 +501,7 @@ config FB_SBUS_HELPERS select FB_CFB_COPYAREA select FB_CFB_FILLRECT select FB_CFB_IMAGEBLIT + select FB_IOMEM_FOPS config FB_BW2 bool "BWtwo support" @@ -521,6 +522,7 @@ config FB_CG6 depends on (FB = y) && (SPARC && FB_SBUS) select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT + select FB_IOMEM_FOPS help This is the frame buffer device driver for the CGsix (GX, TurboGX) frame buffer. @@ -530,6 +532,7 @@ config FB_FFB depends on FB_SBUS && SPARC64 select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT + select FB_IOMEM_FOPS help This is the frame buffer device driver for the Creator, Creator3D, and Elite3D graphics boards. @@ -1677,8 +1680,8 @@ config FB_COBALT select FB_IOMEM_HELPERS config FB_SH7760 - bool "SH7760/SH7763/SH7720/SH7721 LCDC support" - depends on FB=y && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \ + tristate "SH7760/SH7763/SH7720/SH7721 LCDC support" + depends on FB && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \ || CPU_SUBTYPE_SH7720 || CPU_SUBTYPE_SH7721) select FB_IOMEM_HELPERS help diff --git a/drivers/video/fbdev/core/Kconfig b/drivers/video/fbdev/core/Kconfig index 21053bf00dc58..c0a5e4cbe0ac2 100644 --- a/drivers/video/fbdev/core/Kconfig +++ b/drivers/video/fbdev/core/Kconfig @@ -144,6 +144,12 @@ config FB_DMAMEM_HELPERS select FB_SYS_IMAGEBLIT select FB_SYSMEM_FOPS +config FB_DMAMEM_HELPERS_DEFERRED + bool + depends on FB_CORE + select FB_DEFERRED_IO + select FB_DMAMEM_HELPERS + config FB_IOMEM_FOPS tristate depends on FB_CORE diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index dae96c9f61cf8..806ecd32219b6 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -196,7 +196,7 @@ static vm_fault_t fb_deferred_io_track_page(struct fb_info *info, unsigned long */ static vm_fault_t fb_deferred_io_page_mkwrite(struct fb_info *info, struct vm_fault *vmf) { - unsigned long offset = vmf->address - vmf->vma->vm_start; + unsigned long offset = vmf->pgoff << PAGE_SHIFT; struct page *page = vmf->page; file_update_time(vmf->vma->vm_file); diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index 79e5bfbdd34c2..0a26399dbc899 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -1311,7 +1311,7 @@ int fb_get_mode(int flags, u32 val, struct fb_var_screeninfo *var, struct fb_inf int fb_videomode_from_videomode(const struct videomode *vm, struct fb_videomode *fbmode) { - unsigned int htotal, vtotal; + unsigned int htotal, vtotal, total; fbmode->xres = vm->hactive; fbmode->left_margin = vm->hback_porch; @@ -1344,8 +1344,9 @@ int fb_videomode_from_videomode(const struct videomode *vm, vtotal = vm->vactive + vm->vfront_porch + vm->vback_porch + vm->vsync_len; /* prevent division by zero */ - if (htotal && vtotal) { - fbmode->refresh = vm->pixelclock / (htotal * vtotal); + total = htotal * vtotal; + if (total) { + fbmode->refresh = vm->pixelclock / total; /* a mode must have htotal and vtotal != 0 or it is invalid */ } else { fbmode->refresh = 0; diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c index ebc9aeffdde7c..ac41f8f37589f 100644 --- a/drivers/video/fbdev/savage/savagefb_driver.c +++ b/drivers/video/fbdev/savage/savagefb_driver.c @@ -2276,7 +2276,10 @@ static int savagefb_probe(struct pci_dev *dev, const struct pci_device_id *id) if (info->var.xres_virtual > 0x1000) info->var.xres_virtual = 0x1000; #endif - savagefb_check_var(&info->var, info); + err = savagefb_check_var(&info->var, info); + if (err) + goto failed; + savagefb_set_fix(info); /* diff --git a/drivers/video/fbdev/sh_mobile_lcdcfb.c b/drivers/video/fbdev/sh_mobile_lcdcfb.c index eb2297b37504c..d35d2cf999988 100644 --- a/drivers/video/fbdev/sh_mobile_lcdcfb.c +++ b/drivers/video/fbdev/sh_mobile_lcdcfb.c @@ -1575,7 +1575,7 @@ sh_mobile_lcdc_overlay_fb_init(struct sh_mobile_lcdc_overlay *ovl) */ info->fix = sh_mobile_lcdc_overlay_fix; snprintf(info->fix.id, sizeof(info->fix.id), - "SH Mobile LCDC Overlay %u", ovl->index); + "SHMobile ovl %u", ovl->index); info->fix.smem_start = ovl->dma_handle; info->fix.smem_len = ovl->fb_size; info->fix.line_length = ovl->pitch; diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c index 6f58ee276ad1b..028a565250476 100644 --- a/drivers/video/fbdev/simplefb.c +++ b/drivers/video/fbdev/simplefb.c @@ -470,7 +470,7 @@ static int simplefb_attach_genpds(struct simplefb_par *par, if (err == -ENOENT) return 0; - dev_info(dev, "failed to parse power-domains: %d\n", err); + dev_err(dev, "failed to parse power-domains: %d\n", err); return err; } diff --git a/drivers/video/fbdev/sis/init301.c b/drivers/video/fbdev/sis/init301.c index a8fb41f1a2580..09329072004f4 100644 --- a/drivers/video/fbdev/sis/init301.c +++ b/drivers/video/fbdev/sis/init301.c @@ -172,7 +172,7 @@ static const unsigned char SiS_HiTVGroup3_2[] = { }; /* 301C / 302ELV extended Part2 TV registers (4 tap scaler) */ - +#ifdef CONFIG_FB_SIS_315 static const unsigned char SiS_Part2CLVX_1[] = { 0x00,0x00, 0x00,0x20,0x00,0x00,0x7F,0x20,0x02,0x7F,0x7D,0x20,0x04,0x7F,0x7D,0x1F,0x06,0x7E, @@ -245,7 +245,6 @@ static const unsigned char SiS_Part2CLVX_6[] = { /* 1080i */ 0xFF,0xFF, }; -#ifdef CONFIG_FB_SIS_315 /* 661 et al LCD data structure (2.03.00) */ static const unsigned char SiS_LCDStruct661[] = { /* 1024x768 */ diff --git a/drivers/video/fbdev/via/accel.c b/drivers/video/fbdev/via/accel.c index 0a1bc7a4d7853..1e04026f08091 100644 --- a/drivers/video/fbdev/via/accel.c +++ b/drivers/video/fbdev/via/accel.c @@ -115,7 +115,7 @@ static int hw_bitblt_1(void __iomem *engine, u8 op, u32 width, u32 height, if (op != VIA_BITBLT_FILL) { tmp = src_mem ? 0 : src_addr; - if (dst_addr & 0xE0000007) { + if (tmp & 0xE0000007) { printk(KERN_WARNING "hw_bitblt_1: Unsupported source " "address %X\n", tmp); return -EINVAL; @@ -260,7 +260,7 @@ static int hw_bitblt_2(void __iomem *engine, u8 op, u32 width, u32 height, writel(tmp, engine + 0x18); tmp = src_mem ? 0 : src_addr; - if (dst_addr & 0xE0000007) { + if (tmp & 0xE0000007) { printk(KERN_WARNING "hw_bitblt_2: Unsupported source " "address %X\n", tmp); return -EINVAL; diff --git a/drivers/virt/acrn/mm.c b/drivers/virt/acrn/mm.c index fa5d9ca6be570..9c75de0656d8d 100644 --- a/drivers/virt/acrn/mm.c +++ b/drivers/virt/acrn/mm.c @@ -155,43 +155,83 @@ int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) { struct vm_memory_region_batch *regions_info; - int nr_pages, i = 0, order, nr_regions = 0; + int nr_pages, i, order, nr_regions = 0; struct vm_memory_mapping *region_mapping; struct vm_memory_region_op *vm_region; struct page **pages = NULL, *page; void *remap_vaddr; int ret, pinned; u64 user_vm_pa; - unsigned long pfn; struct vm_area_struct *vma; if (!vm || !memmap) return -EINVAL; + /* Get the page number of the map region */ + nr_pages = memmap->len >> PAGE_SHIFT; + if (!nr_pages) + return -EINVAL; + mmap_read_lock(current->mm); vma = vma_lookup(current->mm, memmap->vma_base); if (vma && ((vma->vm_flags & VM_PFNMAP) != 0)) { + unsigned long start_pfn, cur_pfn; + spinlock_t *ptl; + bool writable; + pte_t *ptep; + if ((memmap->vma_base + memmap->len) > vma->vm_end) { mmap_read_unlock(current->mm); return -EINVAL; } - ret = follow_pfn(vma, memmap->vma_base, &pfn); + for (i = 0; i < nr_pages; i++) { + ret = follow_pte(vma->vm_mm, + memmap->vma_base + i * PAGE_SIZE, + &ptep, &ptl); + if (ret) + break; + + cur_pfn = pte_pfn(ptep_get(ptep)); + if (i == 0) + start_pfn = cur_pfn; + writable = !!pte_write(ptep_get(ptep)); + pte_unmap_unlock(ptep, ptl); + + /* Disallow write access if the PTE is not writable. */ + if (!writable && + (memmap->attr & ACRN_MEM_ACCESS_WRITE)) { + ret = -EFAULT; + break; + } + + /* Disallow refcounted pages. */ + if (pfn_valid(cur_pfn) && + !PageReserved(pfn_to_page(cur_pfn))) { + ret = -EFAULT; + break; + } + + /* Disallow non-contiguous ranges. */ + if (cur_pfn != start_pfn + i) { + ret = -EINVAL; + break; + } + } mmap_read_unlock(current->mm); - if (ret < 0) { + + if (ret) { dev_dbg(acrn_dev.this_device, "Failed to lookup PFN at VMA:%pK.\n", (void *)memmap->vma_base); return ret; } return acrn_mm_region_add(vm, memmap->user_vm_pa, - PFN_PHYS(pfn), memmap->len, + PFN_PHYS(start_pfn), memmap->len, ACRN_MEM_TYPE_WB, memmap->attr); } mmap_read_unlock(current->mm); - /* Get the page number of the map region */ - nr_pages = memmap->len >> PAGE_SHIFT; pages = vzalloc(array_size(nr_pages, sizeof(*pages))); if (!pages) return -ENOMEM; @@ -235,12 +275,11 @@ int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) mutex_unlock(&vm->regions_mapping_lock); /* Calculate count of vm_memory_region_op */ - while (i < nr_pages) { + for (i = 0; i < nr_pages; i += 1 << order) { page = pages[i]; VM_BUG_ON_PAGE(PageTail(page), page); order = compound_order(page); nr_regions++; - i += 1 << order; } /* Prepare the vm_memory_region_batch */ @@ -257,8 +296,7 @@ int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) regions_info->vmid = vm->vmid; regions_info->regions_gpa = virt_to_phys(vm_region); user_vm_pa = memmap->user_vm_pa; - i = 0; - while (i < nr_pages) { + for (i = 0; i < nr_pages; i += 1 << order) { u32 region_size; page = pages[i]; @@ -274,7 +312,6 @@ int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) vm_region++; user_vm_pa += region_size; - i += 1 << order; } /* Inform the ACRN Hypervisor to set up EPT mappings */ diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c index b67a28da47026..a1c467a0e9f71 100644 --- a/drivers/virt/vmgenid.c +++ b/drivers/virt/vmgenid.c @@ -68,7 +68,6 @@ static int vmgenid_add(struct acpi_device *device) static void vmgenid_notify(struct acpi_device *device, u32 event) { struct vmgenid_state *state = acpi_driver_data(device); - char *envp[] = { "NEW_VMGENID=1", NULL }; u8 old_id[VMGENID_SIZE]; memcpy(old_id, state->this_id, sizeof(old_id)); @@ -76,7 +75,6 @@ static void vmgenid_notify(struct acpi_device *device, u32 event) if (!memcmp(old_id, state->this_id, sizeof(old_id))) return; add_vmfork_randomness(state->this_id, sizeof(state->this_id)); - kobject_uevent_env(&device->dev.kobj, KOBJ_CHANGE, envp); } static const struct acpi_device_id vmgenid_ids[] = { diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index f4080692b3513..f513ee21b1c18 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -510,8 +510,10 @@ int virtio_device_freeze(struct virtio_device *dev) if (drv && drv->freeze) { ret = drv->freeze(dev); - if (ret) + if (ret) { + virtio_config_enable(dev); return ret; + } } if (dev->config->destroy_avq) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 1f5b3dd31fcfc..89bc8da80519f 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -450,7 +450,7 @@ static void start_update_balloon_size(struct virtio_balloon *vb) vb->adjustment_signal_pending = true; if (!vb->adjustment_in_progress) { vb->adjustment_in_progress = true; - pm_stay_awake(vb->vdev->dev.parent); + pm_stay_awake(&vb->vdev->dev); } spin_unlock_irqrestore(&vb->adjustment_lock, flags); @@ -462,7 +462,7 @@ static void end_update_balloon_size(struct virtio_balloon *vb) spin_lock_irq(&vb->adjustment_lock); if (!vb->adjustment_signal_pending && vb->adjustment_in_progress) { vb->adjustment_in_progress = false; - pm_relax(vb->vdev->dev.parent); + pm_relax(&vb->vdev->dev); } spin_unlock_irq(&vb->adjustment_lock); } @@ -1029,6 +1029,15 @@ static int virtballoon_probe(struct virtio_device *vdev) spin_lock_init(&vb->adjustment_lock); + /* + * The virtio balloon itself can't wake up the device, but it is + * responsible for processing wakeup events passed up from the transport + * layer. Wakeup sources don't support nesting/chaining calls, so we use + * our own wakeup source to ensure wakeup events are properly handled + * without trampling on the transport layer's wakeup source. + */ + device_set_wakeup_capable(&vb->vdev->dev, true); + virtio_device_ready(vdev); if (towards_target(vb)) diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index b655fccaf7733..f6b0b00e4599f 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -236,7 +236,7 @@ void vp_del_vqs(struct virtio_device *vdev) int i; list_for_each_entry_safe(vq, n, &vdev->vqs, list) { - if (vp_dev->is_avq(vdev, vq->index)) + if (vp_dev->is_avq && vp_dev->is_avq(vdev, vq->index)) continue; if (vp_dev->per_vq_vectors) { @@ -348,8 +348,10 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, vring_interrupt, 0, vp_dev->msix_names[msix_vec], vqs[i]); - if (err) + if (err) { + vp_del_vq(vqs[i]); goto error_find; + } } return 0; diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 49299b1f9ec74..6f7e5010a6735 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1340,7 +1340,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, sizeof(struct vring_packed_desc)); vq->packed.vring.desc[head].id = cpu_to_le16(id); - if (vq->do_unmap) { + if (vq->use_dma_api) { vq->packed.desc_extra[id].addr = addr; vq->packed.desc_extra[id].len = total_sg * sizeof(struct vring_packed_desc); @@ -1481,7 +1481,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, desc[i].len = cpu_to_le32(sg->length); desc[i].id = cpu_to_le16(id); - if (unlikely(vq->do_unmap)) { + if (unlikely(vq->use_dma_api)) { vq->packed.desc_extra[curr].addr = addr; vq->packed.desc_extra[curr].len = sg->length; vq->packed.desc_extra[curr].flags = @@ -1615,7 +1615,7 @@ static void detach_buf_packed(struct vring_virtqueue *vq, vq->free_head = id; vq->vq.num_free += state->num; - if (unlikely(vq->do_unmap)) { + if (unlikely(vq->use_dma_api)) { curr = id; for (i = 0; i < state->num; i++) { vring_unmap_extra_packed(vq, diff --git a/drivers/watchdog/bd9576_wdt.c b/drivers/watchdog/bd9576_wdt.c index 4a20e07fbb699..f00ea1b4e40b6 100644 --- a/drivers/watchdog/bd9576_wdt.c +++ b/drivers/watchdog/bd9576_wdt.c @@ -29,7 +29,6 @@ struct bd9576_wdt_priv { struct gpio_desc *gpiod_en; struct device *dev; struct regmap *regmap; - bool always_running; struct watchdog_device wdd; }; @@ -62,10 +61,7 @@ static int bd9576_wdt_stop(struct watchdog_device *wdd) { struct bd9576_wdt_priv *priv = watchdog_get_drvdata(wdd); - if (!priv->always_running) - bd9576_wdt_disable(priv); - else - set_bit(WDOG_HW_RUNNING, &wdd->status); + bd9576_wdt_disable(priv); return 0; } @@ -264,9 +260,6 @@ static int bd9576_wdt_probe(struct platform_device *pdev) if (ret) return ret; - priv->always_running = device_property_read_bool(dev->parent, - "always-running"); - watchdog_set_drvdata(&priv->wdd, priv); priv->wdd.info = &bd957x_wdt_ident; @@ -281,9 +274,6 @@ static int bd9576_wdt_probe(struct platform_device *pdev) watchdog_stop_on_reboot(&priv->wdd); - if (priv->always_running) - bd9576_wdt_start(&priv->wdd); - return devm_watchdog_register_device(dev, &priv->wdd); } diff --git a/drivers/watchdog/cpu5wdt.c b/drivers/watchdog/cpu5wdt.c index 688b112e712ba..9f279c0e13a66 100644 --- a/drivers/watchdog/cpu5wdt.c +++ b/drivers/watchdog/cpu5wdt.c @@ -252,7 +252,7 @@ static void cpu5wdt_exit(void) if (cpu5wdt_device.queue) { cpu5wdt_device.queue = 0; wait_for_completion(&cpu5wdt_device.stop); - del_timer(&cpu5wdt_device.timer); + timer_shutdown_sync(&cpu5wdt_device.timer); } misc_deregister(&cpu5wdt_misc); diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c old mode 100644 new mode 100755 diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c index 9215793a1c814..4895a69015a8e 100644 --- a/drivers/watchdog/rti_wdt.c +++ b/drivers/watchdog/rti_wdt.c @@ -59,6 +59,8 @@ #define PON_REASON_EOF_NUM 0xCCCCBBBB #define RESERVED_MEM_MIN_SIZE 12 +#define MAX_HW_ERROR 250 + static int heartbeat = DEFAULT_HEARTBEAT; /* @@ -97,7 +99,7 @@ static int rti_wdt_start(struct watchdog_device *wdd) * to be 50% or less than that; we obviouly want to configure the open * window as large as possible so we select the 50% option. */ - wdd->min_hw_heartbeat_ms = 500 * wdd->timeout; + wdd->min_hw_heartbeat_ms = 520 * wdd->timeout + MAX_HW_ERROR; /* Generate NMI when wdt expires */ writel_relaxed(RTIWWDRX_NMI, wdt->base + RTIWWDRXCTRL); @@ -131,31 +133,33 @@ static int rti_wdt_setup_hw_hb(struct watchdog_device *wdd, u32 wsize) * be petted during the open window; not too early or not too late. * The HW configuration options only allow for the open window size * to be 50% or less than that. + * To avoid any glitches, we accommodate 2% + max hardware error + * safety margin. */ switch (wsize) { case RTIWWDSIZE_50P: - /* 50% open window => 50% min heartbeat */ - wdd->min_hw_heartbeat_ms = 500 * heartbeat; + /* 50% open window => 52% min heartbeat */ + wdd->min_hw_heartbeat_ms = 520 * heartbeat + MAX_HW_ERROR; break; case RTIWWDSIZE_25P: - /* 25% open window => 75% min heartbeat */ - wdd->min_hw_heartbeat_ms = 750 * heartbeat; + /* 25% open window => 77% min heartbeat */ + wdd->min_hw_heartbeat_ms = 770 * heartbeat + MAX_HW_ERROR; break; case RTIWWDSIZE_12P5: - /* 12.5% open window => 87.5% min heartbeat */ - wdd->min_hw_heartbeat_ms = 875 * heartbeat; + /* 12.5% open window => 89.5% min heartbeat */ + wdd->min_hw_heartbeat_ms = 895 * heartbeat + MAX_HW_ERROR; break; case RTIWWDSIZE_6P25: - /* 6.5% open window => 93.5% min heartbeat */ - wdd->min_hw_heartbeat_ms = 935 * heartbeat; + /* 6.5% open window => 95.5% min heartbeat */ + wdd->min_hw_heartbeat_ms = 955 * heartbeat + MAX_HW_ERROR; break; case RTIWWDSIZE_3P125: - /* 3.125% open window => 96.9% min heartbeat */ - wdd->min_hw_heartbeat_ms = 969 * heartbeat; + /* 3.125% open window => 98.9% min heartbeat */ + wdd->min_hw_heartbeat_ms = 989 * heartbeat + MAX_HW_ERROR; break; default: @@ -233,14 +237,6 @@ static int rti_wdt_probe(struct platform_device *pdev) return -EINVAL; } - /* - * If watchdog is running at 32k clock, it is not accurate. - * Adjust frequency down in this case so that we don't pet - * the watchdog too often. - */ - if (wdt->freq < 32768) - wdt->freq = wdt->freq * 9 / 10; - pm_runtime_enable(dev); ret = pm_runtime_resume_and_get(dev); if (ret < 0) { diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c index 5d2df008b92a5..34a917221e316 100644 --- a/drivers/watchdog/sa1100_wdt.c +++ b/drivers/watchdog/sa1100_wdt.c @@ -191,9 +191,8 @@ static int sa1100dog_probe(struct platform_device *pdev) if (!res) return -ENXIO; reg_base = devm_ioremap(&pdev->dev, res->start, resource_size(res)); - ret = PTR_ERR_OR_ZERO(reg_base); - if (ret) - return ret; + if (!reg_base) + return -ENOMEM; clk = clk_get(NULL, "OSTIMER0"); if (IS_ERR(clk)) { diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c index e28ead24c520e..df68ae4acbd7e 100644 --- a/drivers/watchdog/starfive-wdt.c +++ b/drivers/watchdog/starfive-wdt.c @@ -494,8 +494,13 @@ static int starfive_wdt_probe(struct platform_device *pdev) if (ret) goto err_exit; - if (!early_enable) - pm_runtime_put_sync(&pdev->dev); + if (!early_enable) { + if (pm_runtime_enabled(&pdev->dev)) { + ret = pm_runtime_put_sync(&pdev->dev); + if (ret) + goto err_exit; + } + } return 0; diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c index d9fd50df9802c..5404e03876202 100644 --- a/drivers/watchdog/stm32_iwdg.c +++ b/drivers/watchdog/stm32_iwdg.c @@ -20,6 +20,8 @@ #include #include +#define DEFAULT_TIMEOUT 10 + /* IWDG registers */ #define IWDG_KR 0x00 /* Key register */ #define IWDG_PR 0x04 /* Prescaler Register */ @@ -248,6 +250,7 @@ static int stm32_iwdg_probe(struct platform_device *pdev) wdd->parent = dev; wdd->info = &stm32_iwdg_info; wdd->ops = &stm32_iwdg_ops; + wdd->timeout = DEFAULT_TIMEOUT; wdd->min_timeout = DIV_ROUND_UP((RLR_MIN + 1) * PR_MIN, wdt->rate); wdd->max_hw_heartbeat_ms = ((RLR_MAX + 1) * wdt->data->max_prescaler * 1000) / wdt->rate; diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 976c6cdf9ee67..aaf2514fcfa46 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -672,7 +672,6 @@ EXPORT_SYMBOL(xen_free_ballooned_pages); static void __init balloon_add_regions(void) { -#if defined(CONFIG_XEN_PV) unsigned long start_pfn, pages; unsigned long pfn, extra_pfn_end; unsigned int i; @@ -696,7 +695,6 @@ static void __init balloon_add_regions(void) balloon_stats.total_pages += extra_pfn_end - start_pfn; } -#endif } static int __init balloon_init(void) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 3b9f080109d7e..27553673e46bc 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -1190,7 +1190,7 @@ int xen_pirq_from_irq(unsigned irq) EXPORT_SYMBOL_GPL(xen_pirq_from_irq); static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip, - struct xenbus_device *dev) + struct xenbus_device *dev, bool shared) { int ret = -ENOMEM; struct irq_info *info; @@ -1224,7 +1224,8 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip, */ bind_evtchn_to_cpu(info, 0, false); } else if (!WARN_ON(info->type != IRQT_EVTCHN)) { - info->refcnt++; + if (shared && !WARN_ON(info->refcnt < 0)) + info->refcnt++; } ret = info->irq; @@ -1237,13 +1238,13 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip, int bind_evtchn_to_irq(evtchn_port_t evtchn) { - return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip, NULL); + return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip, NULL, false); } EXPORT_SYMBOL_GPL(bind_evtchn_to_irq); int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn) { - return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip, NULL); + return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip, NULL, false); } EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi); @@ -1295,7 +1296,8 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev, evtchn_port_t remote_port, - struct irq_chip *chip) + struct irq_chip *chip, + bool shared) { struct evtchn_bind_interdomain bind_interdomain; int err; @@ -1307,14 +1309,14 @@ static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev, &bind_interdomain); return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port, - chip, dev); + chip, dev, shared); } int bind_interdomain_evtchn_to_irq_lateeoi(struct xenbus_device *dev, evtchn_port_t remote_port) { return bind_interdomain_evtchn_to_irq_chip(dev, remote_port, - &xen_lateeoi_chip); + &xen_lateeoi_chip, false); } EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi); @@ -1430,7 +1432,8 @@ static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn, { int irq, retval; - irq = bind_evtchn_to_irq_chip(evtchn, chip, NULL); + irq = bind_evtchn_to_irq_chip(evtchn, chip, NULL, + irqflags & IRQF_SHARED); if (irq < 0) return irq; retval = request_irq(irq, handler, irqflags, devname, dev_id); @@ -1471,7 +1474,8 @@ static int bind_interdomain_evtchn_to_irqhandler_chip( { int irq, retval; - irq = bind_interdomain_evtchn_to_irq_chip(dev, remote_port, chip); + irq = bind_interdomain_evtchn_to_irq_chip(dev, remote_port, chip, + irqflags & IRQF_SHARED); if (irq < 0) return irq; diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 59717628ca42b..f6a2216c2c870 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -85,6 +85,7 @@ struct user_evtchn { struct per_user_data *user; evtchn_port_t port; bool enabled; + bool unbinding; }; static void evtchn_free_ring(evtchn_port_t *ring) @@ -164,6 +165,10 @@ static irqreturn_t evtchn_interrupt(int irq, void *data) struct per_user_data *u = evtchn->user; unsigned int prod, cons; + /* Handler might be called when tearing down the IRQ. */ + if (evtchn->unbinding) + return IRQ_HANDLED; + WARN(!evtchn->enabled, "Interrupt for port %u, but apparently not enabled; per-user %p\n", evtchn->port, u); @@ -421,6 +426,7 @@ static void evtchn_unbind_from_user(struct per_user_data *u, BUG_ON(irq < 0); + evtchn->unbinding = true; unbind_from_irqhandler(irq, evtchn); del_evtchn(u, evtchn); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 3205e5d724c8c..1a9ded0cddcb0 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -65,13 +65,17 @@ #include "xenbus.h" -static int xs_init_irq; +static int xs_init_irq = -1; int xen_store_evtchn; EXPORT_SYMBOL_GPL(xen_store_evtchn); struct xenstore_domain_interface *xen_store_interface; EXPORT_SYMBOL_GPL(xen_store_interface); +#define XS_INTERFACE_READY \ + ((xen_store_interface != NULL) && \ + (xen_store_interface->connection == XENSTORE_CONNECTED)) + enum xenstore_init xen_store_domain_type; EXPORT_SYMBOL_GPL(xen_store_domain_type); @@ -751,19 +755,19 @@ static void xenbus_probe(void) { xenstored_ready = 1; - if (!xen_store_interface) { + if (!xen_store_interface) xen_store_interface = memremap(xen_store_gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE, MEMREMAP_WB); - /* - * Now it is safe to free the IRQ used for xenstore late - * initialization. No need to unbind: it is about to be - * bound again from xb_init_comms. Note that calling - * unbind_from_irqhandler now would result in xen_evtchn_close() - * being called and the event channel not being enabled again - * afterwards, resulting in missed event notifications. - */ + /* + * Now it is safe to free the IRQ used for xenstore late + * initialization. No need to unbind: it is about to be + * bound again from xb_init_comms. Note that calling + * unbind_from_irqhandler now would result in xen_evtchn_close() + * being called and the event channel not being enabled again + * afterwards, resulting in missed event notifications. + */ + if (xs_init_irq >= 0) free_irq(xs_init_irq, &xb_waitq); - } /* * In the HVM case, xenbus_init() deferred its call to @@ -822,7 +826,7 @@ static int __init xenbus_probe_initcall(void) if (xen_store_domain_type == XS_PV || (xen_store_domain_type == XS_HVM && !xs_hvm_defer_init_for_callback() && - xen_store_interface != NULL)) + XS_INTERFACE_READY)) xenbus_probe(); /* @@ -831,7 +835,7 @@ static int __init xenbus_probe_initcall(void) * started, then probe. It will be triggered when communication * starts happening, by waiting on xb_waitq. */ - if (xen_store_domain_type == XS_LOCAL || xen_store_interface == NULL) { + if (xen_store_domain_type == XS_LOCAL || !XS_INTERFACE_READY) { struct task_struct *probe_task; probe_task = kthread_run(xenbus_probe_thread, NULL, @@ -1014,6 +1018,12 @@ static int __init xenbus_init(void) xen_store_interface = memremap(xen_store_gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE, MEMREMAP_WB); + if (!xen_store_interface) { + pr_err("%s: cannot map HVM_PARAM_STORE_PFN=%llx\n", + __func__, v); + err = -EINVAL; + goto out_error; + } if (xen_store_interface->connection != XENSTORE_CONNECTED) wait = true; } diff --git a/dropped.txt b/dropped.txt new file mode 100644 index 0000000000000..07d6866464002 --- /dev/null +++ b/dropped.txt @@ -0,0 +1,11 @@ +Driver-related patches (dropped at every major release if they are not yet upstream): + - UBUNTU: SAUCE: Revert "fbdev: Make registered_fb[] private to fbmem.c" (required by nvidia, plan was to drop in newer kernels) + +Ubuntu-specific features not supported anymore: + - UBUNTU: SAUCE: shiftfs: deprecated + - UBUNTU: SAUCE: ubuntu fan: deprecated + +Retpoline annotations reverted after enforcing objtool warnings as fatal (LP: #2046440): + - UBUNTU: SAUCE: apm -- annotate indirect calls within firmware_restrict_branch_speculation_{start,end} + - UBUNTU: SAUCE: early/late -- annotate indirect calls in early/late initialisation code + - UBUNTU: SAUCE: vga_set_mode -- avoid jump tables diff --git a/fs/9p/fid.h b/fs/9p/fid.h index 29281b7c38870..0d6138bee2a3d 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -49,9 +49,6 @@ static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry) static inline void v9fs_fid_add_modes(struct p9_fid *fid, unsigned int s_flags, unsigned int s_cache, unsigned int f_flags) { - if (fid->qid.type != P9_QTFILE) - return; - if ((!s_cache) || ((fid->qid.version == 0) && !(s_flags & V9FS_IGNORE_QV)) || (s_flags & V9FS_DIRECT_IO) || (f_flags & O_DIRECT)) { diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index f16f735816349..01338d4c2d9e6 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -48,12 +48,17 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry) static void v9fs_dentry_release(struct dentry *dentry) { struct hlist_node *p, *n; + struct hlist_head head; p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n", dentry, dentry); - hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata) + + spin_lock(&dentry->d_lock); + hlist_move_list((struct hlist_head *)&dentry->d_fsdata, &head); + spin_unlock(&dentry->d_lock); + + hlist_for_each_safe(p, n, &head) p9_fid_put(hlist_entry(p, struct p9_fid, dlist)); - dentry->d_fsdata = NULL; } static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index bae330c2f0cf0..a504240c818c8 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -520,6 +520,7 @@ const struct file_operations v9fs_file_operations = { .splice_read = v9fs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, + .setlease = simple_nosetlease, }; const struct file_operations v9fs_file_operations_dotl = { @@ -534,4 +535,5 @@ const struct file_operations v9fs_file_operations_dotl = { .splice_read = v9fs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, + .setlease = simple_nosetlease, }; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 32572982f72e6..0fde0ab77eff6 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -83,7 +83,7 @@ static int p9mode2perm(struct v9fs_session_info *v9ses, int res; int mode = stat->mode; - res = mode & S_IALLUGO; + res = mode & 0777; /* S_IRWXUGO */ if (v9fs_proto_dotu(v9ses)) { if ((mode & P9_DMSETUID) == P9_DMSETUID) res |= S_ISUID; @@ -178,6 +178,9 @@ int v9fs_uflags2omode(int uflags, int extended) break; } + if (uflags & O_TRUNC) + ret |= P9_OTRUNC; + if (extended) { if (uflags & O_EXCL) ret |= P9_OEXCL; @@ -371,17 +374,21 @@ void v9fs_evict_inode(struct inode *inode) struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode); __le32 __maybe_unused version; - truncate_inode_pages_final(&inode->i_data); + if (!is_bad_inode(inode)) { + truncate_inode_pages_final(&inode->i_data); - version = cpu_to_le32(v9inode->qid.version); - netfs_clear_inode_writeback(inode, &version); + version = cpu_to_le32(v9inode->qid.version); + netfs_clear_inode_writeback(inode, &version); - clear_inode(inode); - filemap_fdatawrite(&inode->i_data); + clear_inode(inode); + filemap_fdatawrite(&inode->i_data); #ifdef CONFIG_9P_FSCACHE - fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); + if (v9fs_inode_cookie(v9inode)) + fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); #endif + } else + clear_inode(inode); } static int v9fs_test_inode(struct inode *inode, void *data) @@ -1145,8 +1152,6 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, struct v9fs_session_info *v9ses = sb->s_fs_info; struct v9fs_inode *v9inode = V9FS_I(inode); - set_nlink(inode, 1); - inode_set_atime(inode, stat->atime, 0); inode_set_mtime(inode, stat->mtime, 0); inode_set_ctime(inode, stat->mtime, 0); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 941f7d0e0bfa2..23cc67f29af20 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -310,6 +310,7 @@ static const struct super_operations v9fs_super_ops = { .alloc_inode = v9fs_alloc_inode, .free_inode = v9fs_free_inode, .statfs = simple_statfs, + .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 8a67fc427e748..67afe68972d5c 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -474,16 +474,6 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, continue; } - /* Don't expose silly rename entries to userspace. */ - if (nlen > 6 && - dire->u.name[0] == '.' && - ctx->actor != afs_lookup_filldir && - ctx->actor != afs_lookup_one_filldir && - memcmp(dire->u.name, ".__afs", 6) == 0) { - ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); - continue; - } - /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, ntohl(dire->u.vnode), diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 97f50e9fd9eb0..297487ee83231 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -140,6 +140,11 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) put_page(page); if (ret < 0) return ret; + + /* Don't cross a backup volume mountpoint from a backup volume */ + if (src_as->volume && src_as->volume->type == AFSVL_BACKVOL && + ctx->type == AFSVL_BACKVOL) + return -ENODEV; } return 0; diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index 700a27bc8c257..ed04bd1eeae89 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -602,6 +602,8 @@ bool afs_select_fileserver(struct afs_operation *op) goto wait_for_more_probe_results; alist = op->estate->addresses; + best_prio = -1; + addr_index = 0; for (i = 0; i < alist->nr_addrs; i++) { if (alist->addrs[i].prio > best_prio) { addr_index = i; @@ -609,9 +611,7 @@ bool afs_select_fileserver(struct afs_operation *op) } } - addr_index = READ_ONCE(alist->preferred); - if (!test_bit(addr_index, &set)) - addr_index = __ffs(set); + alist->preferred = addr_index; op->addr_index = addr_index; set_bit(addr_index, &op->addr_tried); @@ -656,12 +656,6 @@ bool afs_select_fileserver(struct afs_operation *op) next_server: trace_afs_rotate(op, afs_rotate_trace_next_server, 0); _debug("next"); - ASSERT(op->estate); - alist = op->estate->addresses; - if (op->call_responded && - op->addr_index != READ_ONCE(alist->preferred) && - test_bit(alist->preferred, &op->addr_tried)) - WRITE_ONCE(alist->preferred, op->addr_index); op->estate = NULL; goto pick_server; @@ -690,14 +684,7 @@ bool afs_select_fileserver(struct afs_operation *op) failed: trace_afs_rotate(op, afs_rotate_trace_failed, 0); op->flags |= AFS_OPERATION_STOP; - if (op->estate) { - alist = op->estate->addresses; - if (op->call_responded && - op->addr_index != READ_ONCE(alist->preferred) && - test_bit(alist->preferred, &op->addr_tried)) - WRITE_ONCE(alist->preferred, op->addr_index); - op->estate = NULL; - } + op->estate = NULL; _leave(" = f [failed %d]", afs_op_error(op)); return false; } diff --git a/fs/afs/validation.c b/fs/afs/validation.c index 46b37f2cce7d9..32a53fc8dfb26 100644 --- a/fs/afs/validation.c +++ b/fs/afs/validation.c @@ -122,6 +122,9 @@ bool afs_check_validity(const struct afs_vnode *vnode) const struct afs_volume *volume = vnode->volume; time64_t deadline = ktime_get_real_seconds() + 10; + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) + return true; + if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) || atomic64_read(&vnode->cb_expires_at) <= deadline || volume->cb_expires_at <= deadline || @@ -389,12 +392,17 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) key_serial(key)); if (afs_check_validity(vnode)) - return 0; + return test_bit(AFS_VNODE_DELETED, &vnode->flags) ? -ESTALE : 0; ret = down_write_killable(&vnode->validate_lock); if (ret < 0) goto error; + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { + ret = -ESTALE; + goto error_unlock; + } + /* Validate a volume after the v_break has changed or the volume * callback expired. We only want to do this once per volume per * v_break change. The actual work will be done when parsing the @@ -448,12 +456,6 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) vnode->cb_ro_snapshot = cb_ro_snapshot; vnode->cb_scrub = cb_scrub; - if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { - _debug("file already deleted"); - ret = -ESTALE; - goto error_unlock; - } - /* if the vnode's data version number changed then its contents are * different */ zap |= test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); diff --git a/fs/aio.c b/fs/aio.c index 9cdaa2faa5363..0f4f531c97800 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1202,8 +1202,8 @@ static void aio_complete(struct aio_kiocb *iocb) spin_lock_irqsave(&ctx->wait.lock, flags); list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry) if (avail >= curr->min_nr) { - list_del_init_careful(&curr->w.entry); wake_up_process(curr->w.private); + list_del_init_careful(&curr->w.entry); } spin_unlock_irqrestore(&ctx->wait.lock, flags); } diff --git a/fs/bcachefs/mean_and_variance_test.c b/fs/bcachefs/mean_and_variance_test.c index 019583c3ca0ea..51093fa848202 100644 --- a/fs/bcachefs/mean_and_variance_test.c +++ b/fs/bcachefs/mean_and_variance_test.c @@ -130,20 +130,8 @@ static void mean_and_variance_test_1(struct kunit *test) d, mean, stddev, weighted_mean, weighted_stddev); } -static void mean_and_variance_test_2(struct kunit *test) -{ - s64 d[] = { 100, 10, 10, 10, 10, 10, 10 }; - s64 mean[] = { 10, 10, 10, 10, 10, 10, 10 }; - s64 stddev[] = { 9, 9, 9, 9, 9, 9, 9 }; - s64 weighted_mean[] = { 32, 27, 22, 19, 17, 15, 14 }; - s64 weighted_stddev[] = { 38, 35, 31, 27, 24, 21, 18 }; - - do_mean_and_variance_test(test, 10, 6, ARRAY_SIZE(d), 2, - d, mean, stddev, weighted_mean, weighted_stddev); -} - /* Test behaviour where we switch from one steady state to another: */ -static void mean_and_variance_test_3(struct kunit *test) +static void mean_and_variance_test_2(struct kunit *test) { s64 d[] = { 100, 100, 100, 100, 100 }; s64 mean[] = { 22, 32, 40, 46, 50 }; @@ -155,18 +143,6 @@ static void mean_and_variance_test_3(struct kunit *test) d, mean, stddev, weighted_mean, weighted_stddev); } -static void mean_and_variance_test_4(struct kunit *test) -{ - s64 d[] = { 100, 100, 100, 100, 100 }; - s64 mean[] = { 10, 11, 12, 13, 14 }; - s64 stddev[] = { 9, 13, 15, 17, 19 }; - s64 weighted_mean[] = { 32, 49, 61, 71, 78 }; - s64 weighted_stddev[] = { 38, 44, 44, 41, 38 }; - - do_mean_and_variance_test(test, 10, 6, ARRAY_SIZE(d), 2, - d, mean, stddev, weighted_mean, weighted_stddev); -} - static void mean_and_variance_fast_divpow2(struct kunit *test) { s64 i; @@ -224,8 +200,6 @@ static struct kunit_case mean_and_variance_test_cases[] = { KUNIT_CASE(mean_and_variance_weighted_advanced_test), KUNIT_CASE(mean_and_variance_test_1), KUNIT_CASE(mean_and_variance_test_2), - KUNIT_CASE(mean_and_variance_test_3), - KUNIT_CASE(mean_and_variance_test_4), {} }; diff --git a/fs/btrfs/accessors.c b/fs/btrfs/accessors.c index 1925a0919ca62..6eb850ad37d2a 100644 --- a/fs/btrfs/accessors.c +++ b/fs/btrfs/accessors.c @@ -63,8 +63,8 @@ u##bits btrfs_get_token_##bits(struct btrfs_map_token *token, \ const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \ const unsigned long oil = get_eb_offset_in_folio(token->eb, \ member_offset);\ - const int unit_size = folio_size(token->eb->folios[0]); \ - const int unit_shift = folio_shift(token->eb->folios[0]); \ + const int unit_size = token->eb->folio_size; \ + const int unit_shift = token->eb->folio_shift; \ const int size = sizeof(u##bits); \ u8 lebytes[sizeof(u##bits)]; \ const int part = unit_size - oil; \ @@ -94,7 +94,7 @@ u##bits btrfs_get_##bits(const struct extent_buffer *eb, \ const unsigned long idx = get_eb_folio_index(eb, member_offset);\ const unsigned long oil = get_eb_offset_in_folio(eb, \ member_offset);\ - const int unit_size = folio_size(eb->folios[0]); \ + const int unit_size = eb->folio_size; \ char *kaddr = folio_address(eb->folios[idx]); \ const int size = sizeof(u##bits); \ const int part = unit_size - oil; \ @@ -117,8 +117,8 @@ void btrfs_set_token_##bits(struct btrfs_map_token *token, \ const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \ const unsigned long oil = get_eb_offset_in_folio(token->eb, \ member_offset);\ - const int unit_size = folio_size(token->eb->folios[0]); \ - const int unit_shift = folio_shift(token->eb->folios[0]); \ + const int unit_size = token->eb->folio_size; \ + const int unit_shift = token->eb->folio_shift; \ const int size = sizeof(u##bits); \ u8 lebytes[sizeof(u##bits)]; \ const int part = unit_size - oil; \ @@ -151,7 +151,7 @@ void btrfs_set_##bits(const struct extent_buffer *eb, void *ptr, \ const unsigned long idx = get_eb_folio_index(eb, member_offset);\ const unsigned long oil = get_eb_offset_in_folio(eb, \ member_offset);\ - const int unit_size = folio_size(eb->folios[0]); \ + const int unit_size = eb->folio_size; \ char *kaddr = folio_address(eb->folios[idx]); \ const int size = sizeof(u##bits); \ const int part = unit_size - oil; \ diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index beed7e459dabd..fc0930dd922bc 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2773,20 +2773,14 @@ struct btrfs_data_container *init_data_container(u32 total_bytes) size_t alloc_bytes; alloc_bytes = max_t(size_t, total_bytes, sizeof(*data)); - data = kvmalloc(alloc_bytes, GFP_KERNEL); + data = kvzalloc(alloc_bytes, GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); - if (total_bytes >= sizeof(*data)) { + if (total_bytes >= sizeof(*data)) data->bytes_left = total_bytes - sizeof(*data); - data->bytes_missing = 0; - } else { + else data->bytes_missing = sizeof(*data) - total_bytes; - data->bytes_left = 0; - } - - data->elem_cnt = 0; - data->elem_missed = 0; return data; } diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 928f512cdb4a7..cc2926e61a77b 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -732,7 +732,9 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) ret = btrfs_bio_csum(bbio); if (ret) goto fail_put_bio; - } else if (use_append) { + } else if (use_append || + (btrfs_is_zoned(fs_info) && inode && + inode->flags & BTRFS_INODE_NODATASUM)) { ret = btrfs_alloc_dummy_sum(bbio); if (ret) goto fail_put_bio; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 378d9103a2072..86b99a3f03fe7 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1550,7 +1550,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * needing to allocate extents from the block group. */ used = btrfs_space_info_used(space_info, true); - if (space_info->total_bytes - block_group->length < used) { + if (space_info->total_bytes - block_group->length < used && + block_group->zone_unusable < block_group->length) { /* * Add a reference for the list, compensate for the ref * drop under the "next" label for the @@ -1775,6 +1776,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) container_of(work, struct btrfs_fs_info, reclaim_bgs_work); struct btrfs_block_group *bg; struct btrfs_space_info *space_info; + LIST_HEAD(retry_list); if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) return; @@ -1911,8 +1913,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) } next: - if (ret) - btrfs_mark_bg_to_reclaim(bg); + if (ret) { + /* Refcount held by the reclaim_bgs list after splice. */ + btrfs_get_block_group(bg); + list_add_tail(&bg->bg_list, &retry_list); + } btrfs_put_block_group(bg); mutex_unlock(&fs_info->reclaim_bgs_lock); @@ -1932,6 +1937,9 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); end: + spin_lock(&fs_info->unused_bgs_lock); + list_splice_tail(&retry_list, &fs_info->reclaim_bgs); + spin_unlock(&fs_info->unused_bgs_lock); btrfs_exclop_finish(fs_info); sb_end_write(fs_info->sb); } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 68345f73d429a..0041613a36ae5 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -284,7 +284,7 @@ static void end_bbio_comprssed_read(struct btrfs_bio *bbio) static noinline void end_compressed_writeback(const struct compressed_bio *cb) { struct inode *inode = &cb->bbio.inode->vfs_inode; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); unsigned long index = cb->start >> PAGE_SHIFT; unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_SHIFT; struct folio_batch fbatch; @@ -415,7 +415,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, struct compressed_bio *cb, int *memstall, unsigned long *pflags) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); unsigned long end_index; struct bio *orig_bio = &cb->orig_bbio->bio; u64 cur = cb->orig_bbio->file_offset + orig_bio->bi_iter.bi_size; @@ -441,7 +441,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, * This makes readahead less effective, so here disable readahead for * subpage for now, until full compressed write is supported. */ - if (btrfs_sb(inode->i_sb)->sectorsize < PAGE_SIZE) + if (fs_info->sectorsize < PAGE_SIZE) return 0; end_index = (i_size_read(inode) - 1) >> PAGE_SHIFT; @@ -1039,7 +1039,7 @@ static int btrfs_decompress_bio(struct compressed_bio *cb) int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page, unsigned long dest_pgoff, size_t srclen, size_t destlen) { - struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb); + struct btrfs_fs_info *fs_info = page_to_fs_info(dest_page); struct list_head *workspace; const u32 sectorsize = fs_info->sectorsize; int ret; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index e65e012bac553..33145da449cc8 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -820,7 +820,7 @@ int btrfs_bin_search(struct extent_buffer *eb, int first_slot, } while (low < high) { - const int unit_size = folio_size(eb->folios[0]); + const int unit_size = eb->folio_size; unsigned long oil; unsigned long offset; struct btrfs_disk_key *tmp; diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index 5b0b645714183..a77be9896dbd1 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -810,7 +810,7 @@ static u32 get_extent_max_capacity(const struct btrfs_fs_info *fs_info, static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, u32 extent_thresh, u64 newer_than, bool locked) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_map *next; bool ret = false; @@ -1366,7 +1366,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, struct btrfs_ioctl_defrag_range_args *range, u64 newer_than, unsigned long max_to_defrag) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); unsigned long sectors_defragged = 0; u64 isize = i_size_read(inode); u64 cur; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 08102883f560a..ab5a833e7d6ad 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1128,6 +1128,9 @@ __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, if (ret) return ret; + ret = btrfs_record_root_in_trans(trans, node->root); + if (ret) + return ret; ret = btrfs_update_delayed_inode(trans, node->root, path, node); return ret; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c843563914cad..781c1542958f1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -193,7 +193,7 @@ static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, struct folio *folio = eb->folios[i]; u64 start = max_t(u64, eb->start, folio_pos(folio)); u64 end = min_t(u64, eb->start + eb->len, - folio_pos(folio) + folio_size(folio)); + folio_pos(folio) + eb->folio_size); u32 len = end - start; ret = btrfs_repair_io_failure(fs_info, 0, start, len, @@ -498,15 +498,15 @@ static int btree_migrate_folio(struct address_space *mapping, static int btree_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct btrfs_fs_info *fs_info; int ret; if (wbc->sync_mode == WB_SYNC_NONE) { + struct btrfs_fs_info *fs_info; if (wbc->for_kupdate) return 0; - fs_info = BTRFS_I(mapping->host)->root->fs_info; + fs_info = inode_to_fs_info(mapping->host); /* this is a bit racy, but that's ok */ ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes, BTRFS_DIRTY_METADATA_THRESH, @@ -529,11 +529,12 @@ static void btree_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct extent_io_tree *tree; - tree = &BTRFS_I(folio->mapping->host)->io_tree; + + tree = &folio_to_inode(folio)->io_tree; extent_invalidate_folio(tree, folio, offset); btree_release_folio(folio, GFP_NOFS); if (folio_get_private(folio)) { - btrfs_warn(BTRFS_I(folio->mapping->host)->root->fs_info, + btrfs_warn(folio_to_fs_info(folio), "folio private not zero on folio %llu", (unsigned long long)folio_pos(folio)); folio_detach_private(folio); @@ -544,7 +545,7 @@ static void btree_invalidate_folio(struct folio *folio, size_t offset, static bool btree_dirty_folio(struct address_space *mapping, struct folio *folio) { - struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); struct btrfs_subpage_info *spi = fs_info->subpage_info; struct btrfs_subpage *subpage; struct extent_buffer *eb; @@ -2839,6 +2840,7 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block int ret; fs_info->sb = sb; + /* Temporary fixed values for block size until we read the superblock. */ sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); @@ -3356,6 +3358,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE); + /* Update the values for the current filesystem. */ sb->s_blocksize = sectorsize; sb->s_blocksize_bits = blksize_bits(sectorsize); memcpy(&sb->s_uuid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE); @@ -4541,18 +4544,10 @@ static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info) { struct rb_node *node; - struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs; struct btrfs_delayed_ref_node *ref; - delayed_refs = &trans->delayed_refs; - spin_lock(&delayed_refs->lock); - if (atomic_read(&delayed_refs->num_entries) == 0) { - spin_unlock(&delayed_refs->lock); - btrfs_debug(fs_info, "delayed_refs has NO entry"); - return; - } - while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) { struct btrfs_delayed_ref_head *head; struct rb_node *n; diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 744a02b7fd671..1ac00ee7959b7 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -174,8 +174,15 @@ struct dentry *btrfs_get_parent(struct dentry *child) ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto fail; + if (ret == 0) { + /* + * Key with offset of -1 found, there would have to exist an + * inode with such number or a root with such id. + */ + ret = -EUCLEAN; + goto fail; + } - BUG_ON(ret == 0); /* Key with offset of -1 found */ if (path->slots[0] == 0) { ret = -ENOENT; goto fail; @@ -215,7 +222,7 @@ static int btrfs_get_name(struct dentry *parent, char *name, { struct inode *inode = d_inode(child); struct inode *dir = d_inode(parent); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_path *path; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_inode_ref *iref; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 8b4bef05e2221..c4880b69298fd 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -78,7 +78,7 @@ void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info) eb = list_first_entry(&fs_info->allocated_ebs, struct extent_buffer, leak_list); pr_err( - "BTRFS: buffer leak start %llu len %lu refs %d bflags %lu owner %llu\n", + "BTRFS: buffer leak start %llu len %u refs %d bflags %lu owner %llu\n", eb->start, eb->len, atomic_read(&eb->refs), eb->bflags, btrfs_header_owner(eb)); list_del(&eb->leak_list); @@ -207,7 +207,7 @@ static void __process_pages_contig(struct address_space *mapping, struct page *locked_page, u64 start, u64 end, unsigned long page_ops) { - struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); pgoff_t start_index = start >> PAGE_SHIFT; pgoff_t end_index = end >> PAGE_SHIFT; pgoff_t index = start_index; @@ -251,7 +251,7 @@ static noinline int lock_delalloc_pages(struct inode *inode, u64 start, u64 end) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct address_space *mapping = inode->i_mapping; pgoff_t start_index = start >> PAGE_SHIFT; pgoff_t end_index = end >> PAGE_SHIFT; @@ -323,7 +323,7 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode, struct page *locked_page, u64 *start, u64 *end) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; const u64 orig_start = *start; const u64 orig_end = *end; @@ -433,7 +433,7 @@ static bool btrfs_verify_page(struct page *page, u64 start) static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) { - struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + struct btrfs_fs_info *fs_info = page_to_fs_info(page); struct folio *folio = page_folio(page); ASSERT(page_offset(page) <= start && @@ -692,31 +692,21 @@ static void end_bbio_data_read(struct btrfs_bio *bbio) int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, gfp_t extra_gfp) { + const gfp_t gfp = GFP_NOFS | extra_gfp; unsigned int allocated; for (allocated = 0; allocated < nr_pages;) { unsigned int last = allocated; - allocated = alloc_pages_bulk_array(GFP_NOFS | extra_gfp, - nr_pages, page_array); - - if (allocated == nr_pages) - return 0; - - /* - * During this iteration, no page could be allocated, even - * though alloc_pages_bulk_array() falls back to alloc_page() - * if it could not bulk-allocate. So we must be out of memory. - */ - if (allocated == last) { + allocated = alloc_pages_bulk_array(gfp, nr_pages, page_array); + if (unlikely(allocated == last)) { + /* No progress, fail and do cleanup. */ for (int i = 0; i < allocated; i++) { __free_page(page_array[i]); page_array[i] = NULL; } return -ENOMEM; } - - memalloc_retry_wait(GFP_NOFS); } return 0; } @@ -738,6 +728,8 @@ static int alloc_eb_folio_array(struct extent_buffer *eb, gfp_t extra_gfp) for (int i = 0; i < num_pages; i++) eb->folios[i] = page_folio(page_array[i]); + eb->folio_size = PAGE_SIZE; + eb->folio_shift = PAGE_SHIFT; return 0; } @@ -827,7 +819,7 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl, u64 disk_bytenr, struct page *page, size_t size, unsigned long pg_offset) { - struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + struct btrfs_inode *inode = page_to_inode(page); ASSERT(pg_offset + size <= PAGE_SIZE); ASSERT(bio_ctrl->end_io_func); @@ -936,17 +928,21 @@ static int attach_extent_buffer_folio(struct extent_buffer *eb, int set_page_extent_mapped(struct page *page) { - struct folio *folio = page_folio(page); + return set_folio_extent_mapped(page_folio(page)); +} + +int set_folio_extent_mapped(struct folio *folio) +{ struct btrfs_fs_info *fs_info; - ASSERT(page->mapping); + ASSERT(folio->mapping); if (folio_test_private(folio)) return 0; - fs_info = btrfs_sb(page->mapping->host->i_sb); + fs_info = folio_to_fs_info(folio); - if (btrfs_is_subpage(fs_info, page->mapping)) + if (btrfs_is_subpage(fs_info, folio->mapping)) return btrfs_attach_subpage(fs_info, folio, BTRFS_SUBPAGE_DATA); folio_attach_private(folio, (void *)EXTENT_FOLIO_PRIVATE); @@ -963,7 +959,7 @@ void clear_page_extent_mapped(struct page *page) if (!folio_test_private(folio)) return; - fs_info = btrfs_sb(page->mapping->host->i_sb); + fs_info = page_to_fs_info(page); if (btrfs_is_subpage(fs_info, page->mapping)) return btrfs_detach_subpage(fs_info, folio); @@ -1007,7 +1003,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start) { struct inode *inode = page->mapping->host; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); u64 start = page_offset(page); const u64 end = start + PAGE_SIZE - 1; u64 cur = start; @@ -1018,7 +1014,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, int ret = 0; size_t pg_offset = 0; size_t iosize; - size_t blocksize = inode->i_sb->s_blocksize; + size_t blocksize = fs_info->sectorsize; struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; ret = set_page_extent_mapped(page); @@ -1157,7 +1153,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, int btrfs_read_folio(struct file *file, struct folio *folio) { struct page *page = &folio->page; - struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + struct btrfs_inode *inode = page_to_inode(page); u64 start = page_offset(page); u64 end = start + PAGE_SIZE - 1; struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ }; @@ -1180,7 +1176,7 @@ static inline void contiguous_readpages(struct page *pages[], int nr_pages, struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start) { - struct btrfs_inode *inode = BTRFS_I(pages[0]->mapping->host); + struct btrfs_inode *inode = page_to_inode(pages[0]); int index; btrfs_lock_and_flush_ordered_range(inode, start, end, NULL); @@ -1739,10 +1735,10 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, folio_lock(folio); folio_clear_dirty_for_io(folio); folio_start_writeback(folio); - ret = bio_add_folio(&bbio->bio, folio, folio_size(folio), 0); + ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0); ASSERT(ret); wbc_account_cgroup_owner(wbc, folio_page(folio, 0), - folio_size(folio)); + eb->folio_size); wbc->nr_to_write -= folio_nr_pages(folio); folio_unlock(folio); } @@ -1766,7 +1762,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, */ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) { - struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + struct btrfs_fs_info *fs_info = page_to_fs_info(page); struct folio *folio = page_folio(page); int submitted = 0; u64 page_start = page_offset(page); @@ -1857,7 +1853,7 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx) if (!folio_test_private(folio)) return 0; - if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) + if (page_to_fs_info(page)->nodesize < PAGE_SIZE) return submit_eb_subpage(page, wbc); spin_lock(&mapping->i_private_lock); @@ -1915,7 +1911,7 @@ int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc) { struct btrfs_eb_write_context ctx = { .wbc = wbc }; - struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info; + struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); int ret = 0; int done = 0; int nr_to_write_done = 0; @@ -2203,7 +2199,7 @@ void extent_write_locked_range(struct inode *inode, struct page *locked_page, bool found_error = false; int ret = 0; struct address_space *mapping = inode->i_mapping; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); const u32 sectorsize = fs_info->sectorsize; loff_t i_size = i_size_read(inode); u64 cur = start; @@ -2309,7 +2305,7 @@ int extent_invalidate_folio(struct extent_io_tree *tree, struct extent_state *cached_state = NULL; u64 start = folio_pos(folio); u64 end = start + folio_size(folio) - 1; - size_t blocksize = folio->mapping->host->i_sb->s_blocksize; + size_t blocksize = folio_to_fs_info(folio)->sectorsize; /* This function is only called for the btree inode */ ASSERT(tree->owner == IO_TREE_BTREE_INODE_IO); @@ -2378,7 +2374,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) struct extent_map *em; u64 start = page_offset(page); u64 end = start + PAGE_SIZE - 1; - struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host); + struct btrfs_inode *btrfs_inode = page_to_inode(page); struct extent_io_tree *tree = &btrfs_inode->io_tree; struct extent_map_tree *map = &btrfs_inode->extent_tree; @@ -2453,12 +2449,65 @@ int try_release_extent_mapping(struct page *page, gfp_t mask) return try_release_extent_state(tree, page, mask); } +struct btrfs_fiemap_entry { + u64 offset; + u64 phys; + u64 len; + u32 flags; +}; + +/* + * Indicate the caller of emit_fiemap_extent() that it needs to unlock the file + * range from the inode's io tree, unlock the subvolume tree search path, flush + * the fiemap cache and relock the file range and research the subvolume tree. + * The value here is something negative that can't be confused with a valid + * errno value and different from 1 because that's also a return value from + * fiemap_fill_next_extent() and also it's often used to mean some btree search + * did not find a key, so make it some distinct negative value. + */ +#define BTRFS_FIEMAP_FLUSH_CACHE (-(MAX_ERRNO + 1)) + /* - * To cache previous fiemap extent + * Used to: * - * Will be used for merging fiemap extent + * - Cache the next entry to be emitted to the fiemap buffer, so that we can + * merge extents that are contiguous and can be grouped as a single one; + * + * - Store extents ready to be written to the fiemap buffer in an intermediary + * buffer. This intermediary buffer is to ensure that in case the fiemap + * buffer is memory mapped to the fiemap target file, we don't deadlock + * during btrfs_page_mkwrite(). This is because during fiemap we are locking + * an extent range in order to prevent races with delalloc flushing and + * ordered extent completion, which is needed in order to reliably detect + * delalloc in holes and prealloc extents. And this can lead to a deadlock + * if the fiemap buffer is memory mapped to the file we are running fiemap + * against (a silly, useless in practice scenario, but possible) because + * btrfs_page_mkwrite() will try to lock the same extent range. */ struct fiemap_cache { + /* An array of ready fiemap entries. */ + struct btrfs_fiemap_entry *entries; + /* Number of entries in the entries array. */ + int entries_size; + /* Index of the next entry in the entries array to write to. */ + int entries_pos; + /* + * Once the entries array is full, this indicates what's the offset for + * the next file extent item we must search for in the inode's subvolume + * tree after unlocking the extent range in the inode's io tree and + * releasing the search path. + */ + u64 next_search_offset; + /* + * This matches struct fiemap_extent_info::fi_mapped_extents, we use it + * to count ourselves emitted extents and stop instead of relying on + * fiemap_fill_next_extent() because we buffer ready fiemap entries at + * the @entries array, and we want to stop as soon as we hit the max + * amount of extents to map, not just to save time but also to make the + * logic at extent_fiemap() simpler. + */ + unsigned int extents_mapped; + /* Fields for the cached extent (unsubmitted, not ready, extent). */ u64 offset; u64 phys; u64 len; @@ -2466,6 +2515,28 @@ struct fiemap_cache { bool cached; }; +static int flush_fiemap_cache(struct fiemap_extent_info *fieinfo, + struct fiemap_cache *cache) +{ + for (int i = 0; i < cache->entries_pos; i++) { + struct btrfs_fiemap_entry *entry = &cache->entries[i]; + int ret; + + ret = fiemap_fill_next_extent(fieinfo, entry->offset, + entry->phys, entry->len, + entry->flags); + /* + * Ignore 1 (reached max entries) because we keep track of that + * ourselves in emit_fiemap_extent(). + */ + if (ret < 0) + return ret; + } + cache->entries_pos = 0; + + return 0; +} + /* * Helper to submit fiemap extent. * @@ -2480,8 +2551,8 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, struct fiemap_cache *cache, u64 offset, u64 phys, u64 len, u32 flags) { + struct btrfs_fiemap_entry *entry; u64 cache_end; - int ret = 0; /* Set at the end of extent_fiemap(). */ ASSERT((flags & FIEMAP_EXTENT_LAST) == 0); @@ -2494,7 +2565,9 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, * find an extent that starts at an offset behind the end offset of the * previous extent we processed. This happens if fiemap is called * without FIEMAP_FLAG_SYNC and there are ordered extents completing - * while we call btrfs_next_leaf() (through fiemap_next_leaf_item()). + * after we had to unlock the file range, release the search path, emit + * the fiemap extents stored in the buffer (cache->entries array) and + * the lock the remainder of the range and re-search the btree. * * For example we are in leaf X processing its last item, which is the * file extent item for file range [512K, 1M[, and after @@ -2607,11 +2680,35 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, emit: /* Not mergeable, need to submit cached one */ - ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, - cache->len, cache->flags); - cache->cached = false; - if (ret) - return ret; + + if (cache->entries_pos == cache->entries_size) { + /* + * We will need to research for the end offset of the last + * stored extent and not from the current offset, because after + * unlocking the range and releasing the path, if there's a hole + * between that end offset and this current offset, a new extent + * may have been inserted due to a new write, so we don't want + * to miss it. + */ + entry = &cache->entries[cache->entries_size - 1]; + cache->next_search_offset = entry->offset + entry->len; + cache->cached = false; + + return BTRFS_FIEMAP_FLUSH_CACHE; + } + + entry = &cache->entries[cache->entries_pos]; + entry->offset = cache->offset; + entry->phys = cache->phys; + entry->len = cache->len; + entry->flags = cache->flags; + cache->entries_pos++; + cache->extents_mapped++; + + if (cache->extents_mapped == fieinfo->fi_extents_max) { + cache->cached = false; + return 1; + } assign: cache->cached = true; cache->offset = offset; @@ -2737,8 +2834,8 @@ static int fiemap_search_slot(struct btrfs_inode *inode, struct btrfs_path *path * neighbour leaf). * We also need the private clone because holding a read lock on an * extent buffer of the subvolume's b+tree will make lockdep unhappy - * when we call fiemap_fill_next_extent(), because that may cause a page - * fault when filling the user space buffer with fiemap data. + * when we check if extents are shared, as backref walking may need to + * lock the same leaf we are processing. */ clone = btrfs_clone_extent_buffer(path->nodes[0]); if (!clone) @@ -2778,34 +2875,16 @@ static int fiemap_process_hole(struct btrfs_inode *inode, * it beyond i_size. */ while (cur_offset < end && cur_offset < i_size) { - struct extent_state *cached_state = NULL; u64 delalloc_start; u64 delalloc_end; u64 prealloc_start; - u64 lockstart; - u64 lockend; u64 prealloc_len = 0; bool delalloc; - lockstart = round_down(cur_offset, inode->root->fs_info->sectorsize); - lockend = round_up(end, inode->root->fs_info->sectorsize); - - /* - * We are only locking for the delalloc range because that's the - * only thing that can change here. With fiemap we have a lock - * on the inode, so no buffered or direct writes can happen. - * - * However mmaps and normal page writeback will cause this to - * change arbitrarily. We have to lock the extent lock here to - * make sure that nobody messes with the tree while we're doing - * btrfs_find_delalloc_in_range. - */ - lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end, delalloc_cached_state, &delalloc_start, &delalloc_end); - unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); if (!delalloc) break; @@ -2973,6 +3052,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { const u64 ino = btrfs_ino(inode); + struct extent_state *cached_state = NULL; struct extent_state *delalloc_cached_state = NULL; struct btrfs_path *path; struct fiemap_cache cache = { 0 }; @@ -2985,26 +3065,33 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, bool stopped = false; int ret; + cache.entries_size = PAGE_SIZE / sizeof(struct btrfs_fiemap_entry); + cache.entries = kmalloc_array(cache.entries_size, + sizeof(struct btrfs_fiemap_entry), + GFP_KERNEL); backref_ctx = btrfs_alloc_backref_share_check_ctx(); path = btrfs_alloc_path(); - if (!backref_ctx || !path) { + if (!cache.entries || !backref_ctx || !path) { ret = -ENOMEM; goto out; } +restart: range_start = round_down(start, sectorsize); range_end = round_up(start + len, sectorsize); prev_extent_end = range_start; + lock_extent(&inode->io_tree, range_start, range_end, &cached_state); + ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end); if (ret < 0) - goto out; + goto out_unlock; btrfs_release_path(path); path->reada = READA_FORWARD; ret = fiemap_search_slot(inode, path, range_start); if (ret < 0) { - goto out; + goto out_unlock; } else if (ret > 0) { /* * No file extent item found, but we may have delalloc between @@ -3051,7 +3138,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, backref_ctx, 0, 0, 0, prev_extent_end, hole_end); if (ret < 0) { - goto out; + goto out_unlock; } else if (ret > 0) { /* fiemap_fill_next_extent() told us to stop. */ stopped = true; @@ -3107,7 +3194,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, extent_gen, backref_ctx); if (ret < 0) - goto out; + goto out_unlock; else if (ret > 0) flags |= FIEMAP_EXTENT_SHARED; } @@ -3118,9 +3205,9 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, } if (ret < 0) { - goto out; + goto out_unlock; } else if (ret > 0) { - /* fiemap_fill_next_extent() told us to stop. */ + /* emit_fiemap_extent() told us to stop. */ stopped = true; break; } @@ -3129,12 +3216,12 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, next_item: if (fatal_signal_pending(current)) { ret = -EINTR; - goto out; + goto out_unlock; } ret = fiemap_next_leaf_item(inode, path); if (ret < 0) { - goto out; + goto out_unlock; } else if (ret > 0) { /* No more file extent items for this inode. */ break; @@ -3143,22 +3230,12 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, } check_eof_delalloc: - /* - * Release (and free) the path before emitting any final entries to - * fiemap_fill_next_extent() to keep lockdep happy. This is because - * once we find no more file extent items exist, we may have a - * non-cloned leaf, and fiemap_fill_next_extent() can trigger page - * faults when copying data to the user space buffer. - */ - btrfs_free_path(path); - path = NULL; - if (!stopped && prev_extent_end < range_end) { ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, 0, 0, 0, prev_extent_end, range_end - 1); if (ret < 0) - goto out; + goto out_unlock; prev_extent_end = range_end; } @@ -3166,28 +3243,16 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, const u64 i_size = i_size_read(&inode->vfs_inode); if (prev_extent_end < i_size) { - struct extent_state *cached_state = NULL; u64 delalloc_start; u64 delalloc_end; - u64 lockstart; - u64 lockend; bool delalloc; - lockstart = round_down(prev_extent_end, sectorsize); - lockend = round_up(i_size, sectorsize); - - /* - * See the comment in fiemap_process_hole as to why - * we're doing the locking here. - */ - lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); delalloc = btrfs_find_delalloc_in_range(inode, prev_extent_end, i_size - 1, &delalloc_cached_state, &delalloc_start, &delalloc_end); - unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); if (!delalloc) cache.flags |= FIEMAP_EXTENT_LAST; } else { @@ -3195,9 +3260,39 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, } } +out_unlock: + unlock_extent(&inode->io_tree, range_start, range_end, &cached_state); + + if (ret == BTRFS_FIEMAP_FLUSH_CACHE) { + btrfs_release_path(path); + ret = flush_fiemap_cache(fieinfo, &cache); + if (ret) + goto out; + len -= cache.next_search_offset - start; + start = cache.next_search_offset; + goto restart; + } else if (ret < 0) { + goto out; + } + + /* + * Must free the path before emitting to the fiemap buffer because we + * may have a non-cloned leaf and if the fiemap buffer is memory mapped + * to a file, a write into it (through btrfs_page_mkwrite()) may trigger + * waiting for an ordered extent that in order to complete needs to + * modify that leaf, therefore leading to a deadlock. + */ + btrfs_free_path(path); + path = NULL; + + ret = flush_fiemap_cache(fieinfo, &cache); + if (ret) + goto out; + ret = emit_last_fiemap_cache(fieinfo, &cache); out: free_extent_state(delalloc_cached_state); + kfree(cache.entries); btrfs_free_backref_share_ctx(backref_ctx); btrfs_free_path(path); return ret; @@ -3551,6 +3646,8 @@ static struct extent_buffer *grab_extent_buffer( struct folio *folio = page_folio(page); struct extent_buffer *exists; + lockdep_assert_held(&page->mapping->i_private_lock); + /* * For subpage case, we completely rely on radix tree to ensure we * don't try to insert two ebs for the same bytenr. So here we always @@ -3618,13 +3715,14 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) * The caller needs to free the existing folios and retry using the same order. */ static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i, + struct btrfs_subpage *prealloc, struct extent_buffer **found_eb_ret) { struct btrfs_fs_info *fs_info = eb->fs_info; struct address_space *mapping = fs_info->btree_inode->i_mapping; const unsigned long index = eb->start >> PAGE_SHIFT; - struct folio *existing_folio; + struct folio *existing_folio = NULL; int ret; ASSERT(found_eb_ret); @@ -3636,30 +3734,31 @@ static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i, ret = filemap_add_folio(mapping, eb->folios[i], index + i, GFP_NOFS | __GFP_NOFAIL); if (!ret) - return 0; + goto finish; existing_folio = filemap_lock_folio(mapping, index + i); /* The page cache only exists for a very short time, just retry. */ - if (IS_ERR(existing_folio)) + if (IS_ERR(existing_folio)) { + existing_folio = NULL; goto retry; + } /* For now, we should only have single-page folios for btree inode. */ ASSERT(folio_nr_pages(existing_folio) == 1); - if (folio_size(existing_folio) != folio_size(eb->folios[0])) { + if (folio_size(existing_folio) != eb->folio_size) { folio_unlock(existing_folio); folio_put(existing_folio); return -EAGAIN; } - if (fs_info->nodesize < PAGE_SIZE) { - /* - * We're going to reuse the existing page, can drop our page - * and subpage structure now. - */ +finish: + spin_lock(&mapping->i_private_lock); + if (existing_folio && fs_info->nodesize < PAGE_SIZE) { + /* We're going to reuse the existing page, can drop our folio now. */ __free_page(folio_page(eb->folios[i], 0)); eb->folios[i] = existing_folio; - } else { + } else if (existing_folio) { struct extent_buffer *existing_eb; existing_eb = grab_extent_buffer(fs_info, @@ -3667,6 +3766,7 @@ static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i, if (existing_eb) { /* The extent buffer still exists, we can use it directly. */ *found_eb_ret = existing_eb; + spin_unlock(&mapping->i_private_lock); folio_unlock(existing_folio); folio_put(existing_folio); return 1; @@ -3675,6 +3775,22 @@ static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i, __free_page(folio_page(eb->folios[i], 0)); eb->folios[i] = existing_folio; } + eb->folio_size = folio_size(eb->folios[i]); + eb->folio_shift = folio_shift(eb->folios[i]); + /* Should not fail, as we have preallocated the memory. */ + ret = attach_extent_buffer_folio(eb, eb->folios[i], prealloc); + ASSERT(!ret); + /* + * To inform we have an extra eb under allocation, so that + * detach_extent_buffer_page() won't release the folio private when the + * eb hasn't been inserted into radix tree yet. + * + * The ref will be decreased when the eb releases the page, in + * detach_extent_buffer_page(). Thus needs no special handling in the + * error path. + */ + btrfs_folio_inc_eb_refs(fs_info, eb->folios[i]); + spin_unlock(&mapping->i_private_lock); return 0; } @@ -3686,7 +3802,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, int attached = 0; struct extent_buffer *eb; struct extent_buffer *existing_eb = NULL; - struct address_space *mapping = fs_info->btree_inode->i_mapping; struct btrfs_subpage *prealloc = NULL; u64 lockdep_owner = owner_root; bool page_contig = true; @@ -3752,7 +3867,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, for (int i = 0; i < num_folios; i++) { struct folio *folio; - ret = attach_eb_folio_to_filemap(eb, i, &existing_eb); + ret = attach_eb_folio_to_filemap(eb, i, prealloc, &existing_eb); if (ret > 0) { ASSERT(existing_eb); goto out; @@ -3789,22 +3904,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, * and free the allocated page. */ folio = eb->folios[i]; - spin_lock(&mapping->i_private_lock); - /* Should not fail, as we have preallocated the memory */ - ret = attach_extent_buffer_folio(eb, folio, prealloc); - ASSERT(!ret); - /* - * To inform we have extra eb under allocation, so that - * detach_extent_buffer_page() won't release the folio private - * when the eb hasn't yet been inserted into radix tree. - * - * The ref will be decreased when the eb released the page, in - * detach_extent_buffer_page(). - * Thus needs no special handling in error path. - */ - btrfs_folio_inc_eb_refs(fs_info, folio); - spin_unlock(&mapping->i_private_lock); - WARN_ON(btrfs_folio_test_dirty(fs_info, folio, eb->start, eb->len)); /* @@ -4037,7 +4136,7 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans, * The actual zeroout of the buffer will happen later in * btree_csum_one_bio. */ - if (btrfs_is_zoned(fs_info)) { + if (btrfs_is_zoned(fs_info) && test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { set_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags); return; } @@ -4216,6 +4315,19 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags)) goto done; + /* + * Between the initial test_bit(EXTENT_BUFFER_UPTODATE) and the above + * test_and_set_bit(EXTENT_BUFFER_READING), someone else could have + * started and finished reading the same eb. In this case, UPTODATE + * will now be set, and we shouldn't read it in again. + */ + if (unlikely(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))) { + clear_bit(EXTENT_BUFFER_READING, &eb->bflags); + smp_mb__after_atomic(); + wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING); + return 0; + } + clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); eb->read_mirror = 0; check_buffer_tree_ref(eb); @@ -4238,7 +4350,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, for (int i = 0; i < num_folios; i++) { struct folio *folio = eb->folios[i]; - ret = bio_add_folio(&bbio->bio, folio, folio_size(folio), 0); + ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0); ASSERT(ret); } } @@ -4258,7 +4370,7 @@ static bool report_eb_range(const struct extent_buffer *eb, unsigned long start, unsigned long len) { btrfs_warn(eb->fs_info, - "access to eb bytenr %llu len %lu out of range start %lu len %lu", + "access to eb bytenr %llu len %u out of range start %lu len %lu", eb->start, eb->len, start, len); WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); @@ -4287,7 +4399,7 @@ static inline int check_eb_range(const struct extent_buffer *eb, void read_extent_buffer(const struct extent_buffer *eb, void *dstv, unsigned long start, unsigned long len) { - const int unit_size = folio_size(eb->folios[0]); + const int unit_size = eb->folio_size; size_t cur; size_t offset; char *dst = (char *)dstv; @@ -4327,7 +4439,7 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, void __user *dstv, unsigned long start, unsigned long len) { - const int unit_size = folio_size(eb->folios[0]); + const int unit_size = eb->folio_size; size_t cur; size_t offset; char __user *dst = (char __user *)dstv; @@ -4367,7 +4479,7 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, unsigned long start, unsigned long len) { - const int unit_size = folio_size(eb->folios[0]); + const int unit_size = eb->folio_size; size_t cur; size_t offset; char *kaddr; @@ -4438,7 +4550,7 @@ static void __write_extent_buffer(const struct extent_buffer *eb, const void *srcv, unsigned long start, unsigned long len, bool use_memmove) { - const int unit_size = folio_size(eb->folios[0]); + const int unit_size = eb->folio_size; size_t cur; size_t offset; char *kaddr; @@ -4487,7 +4599,7 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv, static void memset_extent_buffer(const struct extent_buffer *eb, int c, unsigned long start, unsigned long len) { - const int unit_size = folio_size(eb->folios[0]); + const int unit_size = eb->folio_size; unsigned long cur = start; if (eb->addr) { @@ -4518,7 +4630,7 @@ void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start, void copy_extent_buffer_full(const struct extent_buffer *dst, const struct extent_buffer *src) { - const int unit_size = folio_size(src->folios[0]); + const int unit_size = src->folio_size; unsigned long cur = 0; ASSERT(dst->len == src->len); @@ -4540,7 +4652,7 @@ void copy_extent_buffer(const struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { - const int unit_size = folio_size(dst->folios[0]); + const int unit_size = dst->folio_size; u64 dst_len = dst->len; size_t cur; size_t offset; @@ -4596,10 +4708,10 @@ static inline void eb_bitmap_offset(const struct extent_buffer *eb, * the bitmap item in the extent buffer + the offset of the byte in the * bitmap item. */ - offset = start + offset_in_folio(eb->folios[0], eb->start) + byte_offset; + offset = start + offset_in_eb_folio(eb, eb->start) + byte_offset; - *folio_index = offset >> folio_shift(eb->folios[0]); - *folio_offset = offset_in_folio(eb->folios[0], offset); + *folio_index = offset >> eb->folio_shift; + *folio_offset = offset_in_eb_folio(eb, offset); } /* @@ -4713,7 +4825,7 @@ void memcpy_extent_buffer(const struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { - const int unit_size = folio_size(dst->folios[0]); + const int unit_size = dst->folio_size; unsigned long cur_off = 0; if (check_eb_range(dst, dst_offset, len) || @@ -4837,7 +4949,7 @@ static struct extent_buffer *get_next_extent_buffer( static int try_release_subpage_extent_buffer(struct page *page) { - struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + struct btrfs_fs_info *fs_info = page_to_fs_info(page); u64 cur = page_offset(page); const u64 end = page_offset(page) + PAGE_SIZE; int ret; @@ -4910,7 +5022,7 @@ int try_release_extent_buffer(struct page *page) struct folio *folio = page_folio(page); struct extent_buffer *eb; - if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) + if (page_to_fs_info(page)->nodesize < PAGE_SIZE) return try_release_subpage_extent_buffer(page); /* diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 46050500529bf..6fa1373fd8cff 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -8,6 +8,7 @@ #include #include #include "compression.h" +#include "messages.h" #include "ulist.h" #include "misc.h" @@ -75,7 +76,8 @@ void __cold extent_buffer_free_cachep(void); #define INLINE_EXTENT_BUFFER_PAGES (BTRFS_MAX_METADATA_BLOCKSIZE / PAGE_SIZE) struct extent_buffer { u64 start; - unsigned long len; + u32 len; + u32 folio_size; unsigned long bflags; struct btrfs_fs_info *fs_info; @@ -90,6 +92,7 @@ struct extent_buffer { int read_mirror; /* >= 0 if eb belongs to a log tree, -1 otherwise */ s8 log_index; + u8 folio_shift; struct rcu_head rcu_head; struct rw_semaphore lock; @@ -113,6 +116,13 @@ struct btrfs_eb_write_context { struct btrfs_block_group *zoned_bg; }; +static inline unsigned long offset_in_eb_folio(const struct extent_buffer *eb, + u64 start) +{ + ASSERT(eb->folio_size); + return start & (eb->folio_size - 1); +} + /* * Get the correct offset inside the page of extent buffer. * @@ -151,13 +161,13 @@ static inline unsigned long get_eb_folio_index(const struct extent_buffer *eb, * the folio_shift would be large enough to always make us * return 0 as index. * 1.2) Several page sized folios - * The folio_shift() would be PAGE_SHIFT, giving us the correct + * The folio_shift would be PAGE_SHIFT, giving us the correct * index. * * 2) sectorsize < PAGE_SIZE and nodesize < PAGE_SIZE case * The folio would only be page sized, and always give us 0 as index. */ - return offset >> folio_shift(eb->folios[0]); + return offset >> eb->folio_shift; } /* @@ -221,6 +231,7 @@ int btree_write_cache_pages(struct address_space *mapping, void extent_readahead(struct readahead_control *rac); int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); +int set_folio_extent_mapped(struct folio *folio); int set_page_extent_mapped(struct page *page); void clear_page_extent_mapped(struct page *page); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index b61099bf97a82..54e111b5faa75 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -291,6 +291,10 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) * Called after an extent has been written to disk properly. Set the generation * to the generation that actually added the file item to the inode so we know * we need to sync this extent when we call fsync(). + * + * Returns: 0 on success + * -ENOENT when the extent is not found in the tree + * -EUCLEAN if the found extent does not match the expected start */ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen) { @@ -307,15 +311,19 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen) btrfs_warn(fs_info, "no extent map found for inode %llu (root %lld) when unpinning extent range [%llu, %llu), generation %llu", btrfs_ino(inode), btrfs_root_id(inode->root), - start, len, gen); + start, start + len, gen); + ret = -ENOENT; goto out; } - if (WARN_ON(em->start != start)) + if (WARN_ON(em->start != start)) { btrfs_warn(fs_info, "found extent map for inode %llu (root %lld) with unexpected start offset %llu when unpinning extent range [%llu, %llu), generation %llu", btrfs_ino(inode), btrfs_root_id(inode->root), - em->start, start, len, gen); + em->start, start, start + len, gen); + ret = -EUCLEAN; + goto out; + } em->generation = gen; em->flags &= ~EXTENT_FLAG_PINNED; @@ -334,9 +342,9 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen) em->mod_len = em->len; } - free_extent_map(em); out: write_unlock(&tree->lock); + free_extent_map(em); return ret; } @@ -810,7 +818,7 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, split->block_len = em->block_len; split->orig_start = em->orig_start; } else { - const u64 diff = start + len - em->start; + const u64 diff = end - em->start; split->block_len = split->len; split->block_start += diff; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 38dfcac476099..616790d6e5028 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1137,7 +1137,7 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); loff_t pos = iocb->ki_pos; int ret; loff_t oldsize; @@ -1185,7 +1185,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, struct file *file = iocb->ki_filp; loff_t pos; struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct page **pages = NULL; struct extent_changeset *data_reserved = NULL; u64 release_bytes = 0; @@ -1461,7 +1461,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); loff_t pos; ssize_t written = 0; ssize_t written_buffered; @@ -1787,7 +1787,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; struct btrfs_log_ctx ctx; @@ -2593,7 +2593,7 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode, static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; struct btrfs_path *path; @@ -3049,7 +3049,7 @@ static long btrfs_fallocate(struct file *file, int mode, int ret; /* Do not allow fallocate in ZONED mode */ - if (btrfs_is_zoned(btrfs_sb(inode->i_sb))) + if (btrfs_is_zoned(inode_to_fs_info(inode))) return -EOPNOTSUPP; alloc_start = round_down(offset, blocksize); @@ -3754,7 +3754,7 @@ static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) if (fsverity_active(inode)) return 0; - if (check_direct_read(btrfs_sb(inode->i_sb), to, iocb->ki_pos)) + if (check_direct_read(inode_to_fs_info(inode), to, iocb->ki_pos)) return 0; btrfs_inode_lock(BTRFS_I(inode), BTRFS_ILOCK_SHARED); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index d372c7ce0e6b4..815bb146b1a5e 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -399,7 +399,7 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, return -ENOMEM; io_ctl->num_pages = num_pages; - io_ctl->fs_info = btrfs_sb(inode->i_sb); + io_ctl->fs_info = inode_to_fs_info(inode); io_ctl->inode = inode; return 0; diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index f8bb73d6ab68c..bd59cf0aae267 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -829,6 +829,17 @@ struct btrfs_fs_info { #endif }; +#define page_to_inode(_page) (BTRFS_I(_Generic((_page), \ + struct page *: (_page))->mapping->host)) +#define folio_to_inode(_folio) (BTRFS_I(_Generic((_folio), \ + struct folio *: (_folio))->mapping->host)) + +#define page_to_fs_info(_page) (page_to_inode(_page)->root->fs_info) +#define folio_to_fs_info(_folio) (folio_to_inode(_folio)->root->fs_info) + +#define inode_to_fs_info(_inode) (BTRFS_I(_Generic((_inode), \ + struct inode *: (_inode)))->root->fs_info) + static inline u64 btrfs_get_fs_generation(const struct btrfs_fs_info *fs_info) { return READ_ONCE(fs_info->generation); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4795738d5785b..d3c534c1bfb59 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1144,13 +1144,13 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, 0, *alloc_hint, &ins, 1, 1); if (ret) { /* - * Here we used to try again by going back to non-compressed - * path for ENOSPC. But we can't reserve space even for - * compressed size, how could it work for uncompressed size - * which requires larger size? So here we directly go error - * path. + * We can't reserve contiguous space for the compressed size. + * Unlikely, but it's possible that we could have enough + * non-contiguous space for the uncompressed size instead. So + * fall back to uncompressed. */ - goto out_free; + submit_uncompressed_range(inode, async_extent, locked_page); + goto done; } /* Here we're doing allocation and writeback of the compressed pages */ @@ -1202,7 +1202,6 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, out_free_reserve: btrfs_dec_block_group_reservations(fs_info, ins.objectid); btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1); -out_free: mapping_set_error(inode->vfs_inode.i_mapping, -EIO); extent_clear_unlock_delalloc(inode, start, end, NULL, EXTENT_LOCKED | EXTENT_DELALLOC | @@ -2523,7 +2522,7 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode, */ if (bits & EXTENT_CLEAR_META_RESV && root != fs_info->tree_root) - btrfs_delalloc_release_metadata(inode, len, false); + btrfs_delalloc_release_metadata(inode, len, true); /* For sanity tests. */ if (btrfs_is_testing(fs_info)) @@ -2829,7 +2828,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) int btrfs_writepage_cow_fixup(struct page *page) { struct inode *inode = page->mapping->host; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_writepage_fixup *fixup; /* This page has ordered extent covering it already */ @@ -3127,8 +3126,13 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent) ordered_extent->disk_num_bytes); } } - unpin_extent_cache(inode, ordered_extent->file_offset, - ordered_extent->num_bytes, trans->transid); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + goto out; + } + + ret = unpin_extent_cache(inode, ordered_extent->file_offset, + ordered_extent->num_bytes, trans->transid); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto out; @@ -3254,7 +3258,7 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent) int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered) { - if (btrfs_is_zoned(btrfs_sb(ordered->inode->i_sb)) && + if (btrfs_is_zoned(inode_to_fs_info(ordered->inode)) && !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) && list_empty(&ordered->bioc_list)) btrfs_finish_ordered_zoned(ordered); @@ -3739,7 +3743,7 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, static int btrfs_read_locked_inode(struct inode *inode, struct btrfs_path *in_path) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_path *path = in_path; struct extent_buffer *leaf; struct btrfs_inode_item *inode_item; @@ -4464,13 +4468,14 @@ static void btrfs_prune_dentries(struct btrfs_root *root) int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) { - struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb); struct btrfs_root *root = dir->root; + struct btrfs_fs_info *fs_info = root->fs_info; struct inode *inode = d_inode(dentry); struct btrfs_root *dest = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; struct btrfs_block_rsv block_rsv; u64 root_flags; + u64 qgroup_reserved = 0; int ret; down_write(&fs_info->subvol_sem); @@ -4515,12 +4520,20 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); if (ret) goto out_undead; + qgroup_reserved = block_rsv.qgroup_rsv_reserved; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_release; } + ret = btrfs_record_root_in_trans(trans, root); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_end_trans; + } + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + qgroup_reserved = 0; trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; @@ -4579,7 +4592,9 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) ret = btrfs_end_transaction(trans); inode->i_flags |= S_DEAD; out_release: - btrfs_subvolume_release_metadata(root, &block_rsv); + btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL); + if (qgroup_reserved) + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); out_undead: if (ret) { spin_lock(&dest->root_item_lock); @@ -5019,7 +5034,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) btrfs_drew_write_unlock(&root->snapshot_lock); btrfs_end_transaction(trans); } else { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); if (btrfs_is_zoned(fs_info)) { ret = btrfs_wait_ordered_range(inode, @@ -5222,7 +5237,7 @@ static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root, void btrfs_evict_inode(struct inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info; struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_block_rsv *rsv = NULL; @@ -5236,6 +5251,7 @@ void btrfs_evict_inode(struct inode *inode) return; } + fs_info = inode_to_fs_info(inode); evict_inode_truncate_pages(inode); if (inode->i_nlink && @@ -5661,7 +5677,7 @@ static inline u8 btrfs_inode_type(struct inode *inode) struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct inode *inode; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_root *sub_root = root; @@ -6200,7 +6216,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, struct inode *dir = args->dir; struct inode *inode = args->inode; const struct fscrypt_str *name = args->orphan ? NULL : &args->fname.disk_name; - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct btrfs_root *root; struct btrfs_inode_item *inode_item; struct btrfs_key *location; @@ -6522,7 +6538,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, static int btrfs_create_common(struct inode *dir, struct dentry *dentry, struct inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_new_inode_args new_inode_args = { .dir = dir, @@ -6592,7 +6608,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, struct btrfs_trans_handle *trans = NULL; struct btrfs_root *root = BTRFS_I(dir)->root; struct inode *inode = d_inode(old_dentry); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct fscrypt_name fname; u64 index; int err; @@ -7078,7 +7094,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, u64 *ram_bytes, bool nowait, bool strict) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct can_nocow_file_extent_args nocow_args = { 0 }; struct btrfs_path *path; int ret; @@ -7317,7 +7333,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, unsigned int iomap_flags) { const bool nowait = (iomap_flags & IOMAP_NOWAIT); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_map *em = *map; int type; u64 block_start, orig_start, orig_block_len, ram_bytes; @@ -7457,7 +7473,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, struct iomap *srcmap) { struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_map *em; struct extent_state *cached_state = NULL; struct btrfs_dio_data *dio_data = iter->private; @@ -7903,7 +7919,7 @@ static void btrfs_readahead(struct readahead_control *rac) */ static void wait_subpage_spinlock(struct page *page) { - struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + struct btrfs_fs_info *fs_info = page_to_fs_info(page); struct folio *folio = page_folio(page); struct btrfs_subpage *subpage; @@ -7970,7 +7986,7 @@ static int btrfs_migrate_folio(struct address_space *mapping, static void btrfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) { - struct btrfs_inode *inode = BTRFS_I(folio->mapping->host); + struct btrfs_inode *inode = folio_to_inode(folio); struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_io_tree *tree = &inode->io_tree; struct extent_state *cached_state = NULL; @@ -8154,7 +8170,7 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf) struct page *page = vmf->page; struct folio *folio = page_folio(page); struct inode *inode = file_inode(vmf->vma->vm_file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; @@ -8723,7 +8739,7 @@ static int btrfs_getattr(struct mnt_idmap *idmap, u64 delalloc_bytes; u64 inode_bytes; struct inode *inode = d_inode(path->dentry); - u32 blocksize = inode->i_sb->s_blocksize; + u32 blocksize = btrfs_sb(inode->i_sb)->sectorsize; u32 bi_flags = BTRFS_I(inode)->flags; u32 bi_ro_flags = BTRFS_I(inode)->ro_flags; @@ -8763,7 +8779,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, struct inode *new_dir, struct dentry *new_dentry) { - struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(old_dir); struct btrfs_trans_handle *trans; unsigned int trans_num_items; struct btrfs_root *root = BTRFS_I(old_dir)->root; @@ -9015,7 +9031,7 @@ static int btrfs_rename(struct mnt_idmap *idmap, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(old_dir); struct btrfs_new_inode_args whiteout_args = { .dir = old_dir, .dentry = old_dentry, @@ -9457,7 +9473,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_path *path; @@ -9638,7 +9654,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, loff_t actual_len, u64 *alloc_hint, struct btrfs_trans_handle *trans) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_key ins; @@ -9790,7 +9806,7 @@ static int btrfs_permission(struct mnt_idmap *idmap, static int btrfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(dir)->root; struct inode *inode; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 9d1eac15e09e1..8851ba7a1e271 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -247,7 +247,7 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_inode *binode = BTRFS_I(inode); struct btrfs_root *root = binode->root; struct btrfs_trans_handle *trans; @@ -528,7 +528,7 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, * block group is in the logical address space, which can be any * sectorsize aligned bytenr in the range [0, U64_MAX]. */ - if (range.len < fs_info->sb->s_blocksize) + if (range.len < fs_info->sectorsize) return -EINVAL; range.minlen = max(range.minlen, minlen); @@ -584,7 +584,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct btrfs_qgroup_inherit *inherit) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct btrfs_trans_handle *trans; struct btrfs_key key; struct btrfs_root_item *root_item; @@ -603,6 +603,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap, int ret; dev_t anon_dev; u64 objectid; + u64 qgroup_reserved = 0; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) @@ -640,13 +641,18 @@ static noinline int create_subvol(struct mnt_idmap *idmap, trans_num_items, false); if (ret) goto out_new_inode_args; + qgroup_reserved = block_rsv.qgroup_rsv_reserved; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - btrfs_subvolume_release_metadata(root, &block_rsv); - goto out_new_inode_args; + goto out_release_rsv; } + ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root); + if (ret) + goto out; + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + qgroup_reserved = 0; trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; /* Tree log can't currently deal with an inode which is a new root. */ @@ -757,9 +763,11 @@ static noinline int create_subvol(struct mnt_idmap *idmap, out: trans->block_rsv = NULL; trans->bytes_reserved = 0; - btrfs_subvolume_release_metadata(root, &block_rsv); - btrfs_end_transaction(trans); +out_release_rsv: + btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL); + if (qgroup_reserved) + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); out_new_inode_args: btrfs_new_inode_args_destroy(&new_inode_args); out_inode: @@ -776,11 +784,13 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct dentry *dentry, bool readonly, struct btrfs_qgroup_inherit *inherit) { - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct inode *inode; struct btrfs_pending_snapshot *pending_snapshot; unsigned int trans_num_items; struct btrfs_trans_handle *trans; + struct btrfs_block_rsv *block_rsv; + u64 qgroup_reserved = 0; int ret; /* We do not support snapshotting right now. */ @@ -817,19 +827,19 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto free_pending; } - btrfs_init_block_rsv(&pending_snapshot->block_rsv, - BTRFS_BLOCK_RSV_TEMP); + block_rsv = &pending_snapshot->block_rsv; + btrfs_init_block_rsv(block_rsv, BTRFS_BLOCK_RSV_TEMP); /* * 1 to add dir item * 1 to add dir index * 1 to update parent inode item */ trans_num_items = create_subvol_num_items(inherit) + 3; - ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, - &pending_snapshot->block_rsv, + ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, block_rsv, trans_num_items, false); if (ret) goto free_pending; + qgroup_reserved = block_rsv->qgroup_rsv_reserved; pending_snapshot->dentry = dentry; pending_snapshot->root = root; @@ -842,6 +852,13 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, ret = PTR_ERR(trans); goto fail; } + ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root); + if (ret) { + btrfs_end_transaction(trans); + goto fail; + } + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + qgroup_reserved = 0; trans->pending_snapshot = pending_snapshot; @@ -871,7 +888,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret && pending_snapshot->snap) pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); - btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv); + btrfs_block_rsv_release(fs_info, block_rsv, (u64)-1, NULL); + if (qgroup_reserved) + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); free_pending: if (pending_snapshot->anon_dev) free_anon_bdev(pending_snapshot->anon_dev); @@ -962,7 +981,7 @@ static noinline int btrfs_mksubvol(const struct path *parent, struct btrfs_qgroup_inherit *inherit) { struct inode *dir = d_inode(parent->dentry); - struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct dentry *dentry; struct fscrypt_str name_str = FSTR_INIT((char *)name, namelen); int error; @@ -1097,7 +1116,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, { BTRFS_DEV_LOOKUP_ARGS(args); struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); u64 new_size; u64 old_size; u64 devid = 1; @@ -1362,7 +1381,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, if (vol_args->flags & BTRFS_SUBVOL_RDONLY) readonly = true; if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) { - u64 nums; + struct btrfs_fs_info *fs_info = inode_to_fs_info(file_inode(file)); if (vol_args->size < sizeof(*inherit) || vol_args->size > PAGE_SIZE) { @@ -1375,19 +1394,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, goto free_args; } - if (inherit->num_qgroups > PAGE_SIZE || - inherit->num_ref_copies > PAGE_SIZE || - inherit->num_excl_copies > PAGE_SIZE) { - ret = -EINVAL; - goto free_inherit; - } - - nums = inherit->num_qgroups + 2 * inherit->num_ref_copies + - 2 * inherit->num_excl_copies; - if (vol_args->size != struct_size(inherit, qgroups, nums)) { - ret = -EINVAL; + ret = btrfs_qgroup_check_inherit(fs_info, inherit, vol_args->size); + if (ret < 0) goto free_inherit; - } } ret = __btrfs_ioctl_snap_create(file, file_mnt_idmap(file), @@ -1405,7 +1414,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, static noinline int btrfs_ioctl_subvol_getflags(struct inode *inode, void __user *arg) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; int ret = 0; u64 flags = 0; @@ -1428,7 +1437,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; u64 root_flags; @@ -1675,7 +1684,7 @@ static noinline int search_ioctl(struct inode *inode, u64 *buf_size, char __user *ubuf) { - struct btrfs_fs_info *info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *info = inode_to_fs_info(inode); struct btrfs_root *root; struct btrfs_key key; struct btrfs_path *path; @@ -2346,9 +2355,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, bool destroy_v2) { struct dentry *parent = file->f_path.dentry; - struct btrfs_fs_info *fs_info = btrfs_sb(parent->d_sb); struct dentry *dentry; struct inode *dir = d_inode(parent); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dir); struct inode *inode; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_root *dest = NULL; @@ -2696,7 +2705,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) { BTRFS_DEV_LOOKUP_ARGS(args); struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_ioctl_vol_args_v2 *vol_args; struct bdev_handle *bdev_handle = NULL; int ret; @@ -2761,7 +2770,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) { BTRFS_DEV_LOOKUP_ARGS(args); struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_ioctl_vol_args *vol_args; struct bdev_handle *bdev_handle = NULL; int ret; @@ -2904,7 +2913,7 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_root *new_root; struct btrfs_dir_item *di; @@ -3178,7 +3187,7 @@ static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info, static long btrfs_ioctl_scrub(struct file *file, void __user *arg) { - struct btrfs_fs_info *fs_info = btrfs_sb(file_inode(file)->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(file_inode(file)); struct btrfs_ioctl_scrub_args *sa; int ret; @@ -3696,7 +3705,7 @@ static long btrfs_ioctl_balance_progress(struct btrfs_fs_info *fs_info, static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_ioctl_quota_ctl_args *sa; int ret; @@ -3713,15 +3722,43 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) goto drop_write; } - down_write(&fs_info->subvol_sem); - switch (sa->cmd) { case BTRFS_QUOTA_CTL_ENABLE: case BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA: + down_write(&fs_info->subvol_sem); ret = btrfs_quota_enable(fs_info, sa); + up_write(&fs_info->subvol_sem); break; case BTRFS_QUOTA_CTL_DISABLE: + /* + * Lock the cleaner mutex to prevent races with concurrent + * relocation, because relocation may be building backrefs for + * blocks of the quota root while we are deleting the root. This + * is like dropping fs roots of deleted snapshots/subvolumes, we + * need the same protection. + * + * This also prevents races between concurrent tasks trying to + * disable quotas, because we will unlock and relock + * qgroup_ioctl_lock across BTRFS_FS_QUOTA_ENABLED changes. + * + * We take this here because we have the dependency of + * + * inode_lock -> subvol_sem + * + * because of rename. With relocation we can prealloc extents, + * so that makes the dependency chain + * + * cleaner_mutex -> inode_lock -> subvol_sem + * + * so we must take the cleaner_mutex here before we take the + * subvol_sem. The deadlock can't actually happen, but this + * quiets lockdep. + */ + mutex_lock(&fs_info->cleaner_mutex); + down_write(&fs_info->subvol_sem); ret = btrfs_quota_disable(fs_info); + up_write(&fs_info->subvol_sem); + mutex_unlock(&fs_info->cleaner_mutex); break; default: ret = -EINVAL; @@ -3729,7 +3766,6 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) } kfree(sa); - up_write(&fs_info->subvol_sem); drop_write: mnt_drop_write_file(file); return ret; @@ -3738,7 +3774,7 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_ioctl_qgroup_assign_args *sa; struct btrfs_trans_handle *trans; @@ -3894,7 +3930,7 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg) static long btrfs_ioctl_quota_rescan(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_ioctl_quota_rescan_args *qsa; int ret; @@ -3958,7 +3994,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, struct btrfs_ioctl_received_subvol_args *sa) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_root_item *root_item = &root->root_item; struct btrfs_trans_handle *trans; @@ -4146,7 +4182,7 @@ static int btrfs_ioctl_get_fslabel(struct btrfs_fs_info *fs_info, static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_super_block *super_block = fs_info->super_copy; struct btrfs_trans_handle *trans; @@ -4289,7 +4325,7 @@ check_feature_bits(fs_info, FEAT_##mask_base, change_mask, flags, \ static int btrfs_ioctl_set_features(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_super_block *super_block = fs_info->super_copy; struct btrfs_ioctl_feature_flags flags[2]; @@ -4580,7 +4616,7 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_root *root = BTRFS_I(inode)->root; void __user *argp = (void __user *)arg; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index e43bc0fdc74ec..3e5d3b7028e8b 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -214,7 +214,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, unsigned long *total_in, unsigned long *total_out) { struct workspace *workspace = list_entry(ws, struct workspace, list); - const u32 sectorsize = btrfs_sb(mapping->host->i_sb)->sectorsize; + const u32 sectorsize = inode_to_fs_info(mapping->host)->sectorsize; struct page *page_in = NULL; char *sizes_ptr; const unsigned long max_nr_page = *out_pages; @@ -429,7 +429,7 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in, size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); - struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb); + struct btrfs_fs_info *fs_info = page_to_fs_info(dest_page); const u32 sectorsize = fs_info->sectorsize; size_t in_len; size_t out_len; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 59850dc17b22f..81f67ebf7426e 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -1189,6 +1189,7 @@ struct btrfs_ordered_extent *btrfs_split_ordered_extent( ordered->disk_bytenr += len; ordered->num_bytes -= len; ordered->disk_num_bytes -= len; + ordered->ram_bytes -= len; if (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags)) { ASSERT(ordered->bytes_left == 0); diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index f9bf591a07187..ac4a0af2b5543 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -302,7 +302,7 @@ static int prop_compression_validate(const struct btrfs_inode *inode, static int prop_compression_apply(struct inode *inode, const char *value, size_t len) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); int type; /* Reset to defaults */ diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5470e1cdf10c5..f3b275d153846 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -468,6 +468,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) } if (!qgroup) { struct btrfs_qgroup *prealloc; + struct btrfs_root *tree_root = fs_info->tree_root; prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL); if (!prealloc) { @@ -475,6 +476,25 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) goto out; } qgroup = add_qgroup_rb(fs_info, prealloc, found_key.offset); + /* + * If a qgroup exists for a subvolume ID, it is possible + * that subvolume has been deleted, in which case + * re-using that ID would lead to incorrect accounting. + * + * Ensure that we skip any such subvol ids. + * + * We don't need to lock because this is only called + * during mount before we start doing things like creating + * subvolumes. + */ + if (is_fstree(qgroup->qgroupid) && + qgroup->qgroupid > tree_root->free_objectid) + /* + * Don't need to check against BTRFS_LAST_FREE_OBJECTID, + * as it will get checked on the next call to + * btrfs_get_free_objectid. + */ + tree_root->free_objectid = qgroup->qgroupid + 1; } ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); if (ret < 0) @@ -1342,16 +1362,10 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) lockdep_assert_held_write(&fs_info->subvol_sem); /* - * Lock the cleaner mutex to prevent races with concurrent relocation, - * because relocation may be building backrefs for blocks of the quota - * root while we are deleting the root. This is like dropping fs roots - * of deleted snapshots/subvolumes, we need the same protection. - * - * This also prevents races between concurrent tasks trying to disable - * quotas, because we will unlock and relock qgroup_ioctl_lock across - * BTRFS_FS_QUOTA_ENABLED changes. + * Relocation will mess with backrefs, so make sure we have the + * cleaner_mutex held to protect us from relocate. */ - mutex_lock(&fs_info->cleaner_mutex); + lockdep_assert_held(&fs_info->cleaner_mutex); mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) @@ -1373,9 +1387,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); + /* + * We have nothing held here and no trans handle, just return the error + * if there is one. + */ ret = flush_reservations(fs_info); if (ret) - goto out_unlock_cleaner; + return ret; /* * 1 For the root item @@ -1439,9 +1457,6 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_end_transaction(trans); else if (trans) ret = btrfs_commit_transaction(trans); -out_unlock_cleaner: - mutex_unlock(&fs_info->cleaner_mutex); - return ret; } @@ -2959,11 +2974,6 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) ctx.roots = NULL; } - /* Free the reserved data space */ - btrfs_qgroup_free_refroot(fs_info, - record->data_rsv_refroot, - record->data_rsv, - BTRFS_QGROUP_RSV_DATA); /* * Use BTRFS_SEQ_LAST as time_seq to do special search, * which doesn't lock tree or delayed_refs and search @@ -2987,6 +2997,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) record->old_roots = NULL; new_roots = NULL; } + /* Free the reserved data space */ + btrfs_qgroup_free_refroot(fs_info, + record->data_rsv_refroot, + record->data_rsv, + BTRFS_QGROUP_RSV_DATA); cleanup: ulist_free(record->old_roots); ulist_free(new_roots); @@ -3048,6 +3063,59 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) return ret; } +int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_inherit *inherit, + size_t size) +{ + if (!btrfs_qgroup_enabled(fs_info)) + return 0; + if (inherit->flags & ~BTRFS_QGROUP_INHERIT_FLAGS_SUPP) + return -EOPNOTSUPP; + if (size < sizeof(*inherit) || size > PAGE_SIZE) + return -EINVAL; + + /* + * In the past we allowed btrfs_qgroup_inherit to specify to copy + * rfer/excl numbers directly from other qgroups. This behavior has + * been disabled in userspace for a very long time, but here we should + * also disable it in kernel, as this behavior is known to mark qgroup + * inconsistent, and a rescan would wipe out the changes anyway. + * + * Reject any btrfs_qgroup_inherit with num_ref_copies or num_excl_copies. + */ + if (inherit->num_ref_copies > 0 || inherit->num_excl_copies > 0) + return -EINVAL; + + if (inherit->num_qgroups > PAGE_SIZE) + return -EINVAL; + + if (size != struct_size(inherit, qgroups, inherit->num_qgroups)) + return -EINVAL; + + /* + * Now check all the remaining qgroups, they should all: + * + * - Exist + * - Be higher level qgroups. + */ + for (int i = 0; i < inherit->num_qgroups; i++) { + struct btrfs_qgroup *qgroup; + u64 qgroupid = inherit->qgroups[i]; + + if (btrfs_qgroup_level(qgroupid) == 0) + return -EINVAL; + + spin_lock(&fs_info->qgroup_lock); + qgroup = find_qgroup_rb(fs_info, qgroupid); + if (!qgroup) { + spin_unlock(&fs_info->qgroup_lock); + return -ENOENT; + } + spin_unlock(&fs_info->qgroup_lock); + } + return 0; +} + static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info, u64 inode_rootid, struct btrfs_qgroup_inherit **inherit) @@ -3083,7 +3151,7 @@ static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info, qgids = res->qgroups; list_for_each_entry(qg_list, &inode_qg->groups, next_group) - qgids[i] = qg_list->group->qgroupid; + qgids[i++] = qg_list->group->qgroupid; *inherit = res; return 0; @@ -3715,14 +3783,14 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, /* we're resuming qgroup rescan at mount time */ if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)) { - btrfs_warn(fs_info, + btrfs_debug(fs_info, "qgroup rescan init failed, qgroup rescan is not queued"); ret = -EINVAL; } else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { - btrfs_warn(fs_info, + btrfs_debug(fs_info, "qgroup rescan init failed, qgroup is not enabled"); - ret = -EINVAL; + ret = -ENOTCONN; } if (ret) @@ -3733,14 +3801,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, if (init_flags) { if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) { - btrfs_warn(fs_info, - "qgroup rescan is already in progress"); ret = -EINPROGRESS; } else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { - btrfs_warn(fs_info, + btrfs_debug(fs_info, "qgroup rescan init failed, qgroup is not enabled"); - ret = -EINVAL; + ret = -ENOTCONN; } else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) { /* Quota disable is in progress */ ret = -EBUSY; @@ -4381,6 +4447,8 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) BTRFS_QGROUP_RSV_META_PREALLOC); trace_qgroup_meta_convert(root, num_bytes); qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes); + if (!sb_rdonly(fs_info->sb)) + add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS); } /* diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index be18c862e64ed..45a7d8920d039 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -341,6 +341,9 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr, struct ulist *new_roots); int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans); int btrfs_run_qgroups(struct btrfs_trans_handle *trans); +int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_inherit *inherit, + size_t size); int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, u64 objectid, u64 inode_rootid, struct btrfs_qgroup_inherit *inherit); diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index ae90894dc7dc7..08d0fb46ceec4 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -174,7 +174,7 @@ static int clone_copy_inline_extent(struct inode *dst, char *inline_data, struct btrfs_trans_handle **trans_out) { - struct btrfs_fs_info *fs_info = btrfs_sb(dst->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(dst); struct btrfs_root *root = BTRFS_I(dst)->root; const u64 aligned_end = ALIGN(new_key->offset + datal, fs_info->sectorsize); @@ -337,7 +337,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode, const u64 off, const u64 olen, const u64 olen_aligned, const u64 destoff, int no_time_update) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_path *path = NULL; struct extent_buffer *leaf; struct btrfs_trans_handle *trans; @@ -663,7 +663,7 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len, struct inode *dst, u64 dst_loff) { struct btrfs_fs_info *fs_info = BTRFS_I(src)->root->fs_info; - const u64 bs = fs_info->sb->s_blocksize; + const u64 bs = fs_info->sectorsize; int ret; /* @@ -726,11 +726,11 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, { struct inode *inode = file_inode(file); struct inode *src = file_inode(file_src); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); int ret; int wb_ret; u64 len = olen; - u64 bs = fs_info->sb->s_blocksize; + u64 bs = fs_info->sectorsize; /* * VFS's generic_remap_file_range_prep() protects us from cloning the @@ -796,7 +796,7 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); - u64 bs = BTRFS_I(inode_out)->root->fs_info->sb->s_blocksize; + u64 bs = BTRFS_I(inode_out)->root->fs_info->sectorsize; u64 wb_len; int ret; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index abe594f77f99c..2fca67f2b39b9 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2987,7 +2987,7 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, const struct file_extent_cluster *cluster, int *cluster_nr, unsigned long page_index) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); u64 offset = BTRFS_I(inode)->index_cnt; const unsigned long last_index = (cluster->end - offset) >> PAGE_SHIFT; gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 603ad1459368c..5260677ad51e2 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -539,13 +539,3 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, } return ret; } - -void btrfs_subvolume_release_metadata(struct btrfs_root *root, - struct btrfs_block_rsv *rsv) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - u64 qgroup_to_release; - - btrfs_block_rsv_release(fs_info, rsv, (u64)-1, &qgroup_to_release); - btrfs_qgroup_convert_reserved_meta(root, qgroup_to_release); -} diff --git a/fs/btrfs/root-tree.h b/fs/btrfs/root-tree.h index 8b2c3859e4647..de0175cbdb1e5 100644 --- a/fs/btrfs/root-tree.h +++ b/fs/btrfs/root-tree.h @@ -8,8 +8,6 @@ struct fscrypt_str; int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, int nitems, bool use_global_rsv); -void btrfs_subvolume_release_metadata(struct btrfs_root *root, - struct btrfs_block_rsv *rsv); int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 sequence, const struct fscrypt_str *name); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0123d27289237..d89d5c0a8cd2d 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1012,6 +1012,7 @@ static void scrub_stripe_read_repair_worker(struct work_struct *work) struct btrfs_fs_info *fs_info = sctx->fs_info; int num_copies = btrfs_num_copies(fs_info, stripe->bg->start, stripe->bg->length); + unsigned long repaired; int mirror; int i; @@ -1078,16 +1079,15 @@ static void scrub_stripe_read_repair_worker(struct work_struct *work) * Submit the repaired sectors. For zoned case, we cannot do repair * in-place, but queue the bg to be relocated. */ - if (btrfs_is_zoned(fs_info)) { - if (!bitmap_empty(&stripe->error_bitmap, stripe->nr_sectors)) + bitmap_andnot(&repaired, &stripe->init_error_bitmap, &stripe->error_bitmap, + stripe->nr_sectors); + if (!sctx->readonly && !bitmap_empty(&repaired, stripe->nr_sectors)) { + if (btrfs_is_zoned(fs_info)) { btrfs_repair_one_zone(fs_info, sctx->stripes[0].bg->start); - } else if (!sctx->readonly) { - unsigned long repaired; - - bitmap_andnot(&repaired, &stripe->init_error_bitmap, - &stripe->error_bitmap, stripe->nr_sectors); - scrub_write_sectors(sctx, stripe, repaired, false); - wait_scrub_stripe_io(stripe); + } else { + scrub_write_sectors(sctx, stripe, repaired, false); + wait_scrub_stripe_io(stripe); + } } scrub_stripe_report_errors(sctx, stripe); @@ -2805,7 +2805,17 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, gen = btrfs_get_last_trans_committed(fs_info); for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { - bytenr = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr); + if (ret == -ENOENT) + break; + + if (ret) { + spin_lock(&sctx->stat_lock); + sctx->stat.super_errors++; + spin_unlock(&sctx->stat_lock); + continue; + } + if (bytenr + BTRFS_SUPER_INFO_SIZE > scrub_dev->commit_total_bytes) break; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index e48a063ef0851..e8187669153dd 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1070,7 +1070,15 @@ static int iterate_inode_ref(struct btrfs_root *root, struct btrfs_path *path, ret = PTR_ERR(start); goto out; } - BUG_ON(start < p->buf); + if (unlikely(start < p->buf)) { + btrfs_err(root->fs_info, + "send: path ref buffer underflow for key (%llu %u %llu)", + found_key->objectid, + found_key->type, + found_key->offset); + ret = -EINVAL; + goto out; + } } p->start = start; } else { @@ -6140,7 +6148,7 @@ static int send_write_or_clone(struct send_ctx *sctx, int ret = 0; u64 offset = key->offset; u64 end; - u64 bs = sctx->send_root->fs_info->sb->s_blocksize; + u64 bs = sctx->send_root->fs_info->sectorsize; end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size); if (offset >= end) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 101f786963d4d..8f171616159ee 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -121,6 +121,7 @@ enum { Opt_thread_pool, Opt_treelog, Opt_user_subvol_rm_allowed, + Opt_norecovery, /* Rescue options */ Opt_rescue, @@ -247,6 +248,8 @@ static const struct fs_parameter_spec btrfs_fs_parameters[] = { __fsparam(NULL, "nologreplay", Opt_nologreplay, fs_param_deprecated, NULL), /* Deprecated, with alias rescue=usebackuproot */ __fsparam(NULL, "usebackuproot", Opt_usebackuproot, fs_param_deprecated, NULL), + /* For compatibility only, alias for "rescue=nologreplay". */ + fsparam_flag("norecovery", Opt_norecovery), /* Debugging options. */ fsparam_flag_no("enospc_debug", Opt_enospc_debug), @@ -440,6 +443,11 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param) "'nologreplay' is deprecated, use 'rescue=nologreplay' instead"); btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY); break; + case Opt_norecovery: + btrfs_info(NULL, +"'norecovery' is for compatibility only, recommended to use 'rescue=nologreplay'"); + btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY); + break; case Opt_flushoncommit: if (result.negated) btrfs_clear_opt(ctx->mount_opt, FLUSHONCOMMIT); @@ -1767,7 +1775,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; - buf->f_bsize = dentry->d_sb->s_blocksize; + buf->f_bsize = fs_info->sectorsize; buf->f_namelen = BTRFS_NAME_LEN; /* We treat it as constant endianness (it doesn't matter _which_) diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 25b3349595e00..865d4af4b3035 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -11,6 +11,7 @@ #include "btrfs-tests.h" #include "../ctree.h" #include "../extent_io.h" +#include "../disk-io.h" #include "../btrfs_inode.h" #define PROCESS_UNLOCK (1 << 0) @@ -105,9 +106,11 @@ static void dump_extent_io_tree(const struct extent_io_tree *tree) } } -static int test_find_delalloc(u32 sectorsize) +static int test_find_delalloc(u32 sectorsize, u32 nodesize) { - struct inode *inode; + struct btrfs_fs_info *fs_info; + struct btrfs_root *root = NULL; + struct inode *inode = NULL; struct extent_io_tree *tmp; struct page *page; struct page *locked_page = NULL; @@ -121,12 +124,27 @@ static int test_find_delalloc(u32 sectorsize) test_msg("running find delalloc tests"); + fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); + if (!fs_info) { + test_std_err(TEST_ALLOC_FS_INFO); + return -ENOMEM; + } + + root = btrfs_alloc_dummy_root(fs_info); + if (IS_ERR(root)) { + test_std_err(TEST_ALLOC_ROOT); + ret = PTR_ERR(root); + goto out; + } + inode = btrfs_new_test_inode(); if (!inode) { test_std_err(TEST_ALLOC_INODE); - return -ENOMEM; + ret = -ENOMEM; + goto out; } tmp = &BTRFS_I(inode)->io_tree; + BTRFS_I(inode)->root = root; /* * Passing NULL as we don't have fs_info but tracepoints are not used @@ -316,6 +334,8 @@ static int test_find_delalloc(u32 sectorsize) process_page_range(inode, 0, total_dirty - 1, PROCESS_UNLOCK | PROCESS_RELEASE); iput(inode); + btrfs_free_dummy_root(root); + btrfs_free_dummy_fs_info(fs_info); return ret; } @@ -794,7 +814,7 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize) test_msg("running extent I/O tests"); - ret = test_find_delalloc(sectorsize); + ret = test_find_delalloc(sectorsize, nodesize); if (ret) goto out; diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 253cce7ffecfe..47b5d301038ee 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -847,6 +847,11 @@ static int test_case_7(struct btrfs_fs_info *fs_info) goto out; } + if (em->block_start != SZ_32K + SZ_4K) { + test_err("em->block_start is %llu, expected 36K", em->block_start); + goto out; + } + free_extent_map(em); read_lock(&em_tree->lock); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index bf8e64c766b63..b93cdf5f179cf 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -747,14 +747,6 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, h->reloc_reserved = reloc_reserved; } - /* - * Now that we have found a transaction to be a part of, convert the - * qgroup reservation from prealloc to pertrans. A different transaction - * can't race in and free our pertrans out from under us. - */ - if (qgroup_reserved) - btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); - got_it: if (!current->journal_info) current->journal_info = h; @@ -788,8 +780,15 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, * not just freed. */ btrfs_end_transaction(h); - return ERR_PTR(ret); + goto reserve_fail; } + /* + * Now that we have found a transaction to be a part of, convert the + * qgroup reservation from prealloc to pertrans. A different transaction + * can't race in and free our pertrans out from under us. + */ + if (qgroup_reserved) + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); return h; @@ -1497,6 +1496,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) radix_tree_tag_clear(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); + btrfs_qgroup_free_meta_all_pertrans(root); spin_unlock(&fs_info->fs_roots_radix_lock); btrfs_free_log(trans, root); @@ -1521,7 +1521,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) if (ret2) return ret2; spin_lock(&fs_info->fs_roots_radix_lock); - btrfs_qgroup_free_meta_all_pertrans(root); } } spin_unlock(&fs_info->fs_roots_radix_lock); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 6eccf8496486c..75c78a5556c5b 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1793,6 +1793,11 @@ enum btrfs_tree_block_status __btrfs_check_leaf(struct extent_buffer *leaf) return BTRFS_TREE_BLOCK_INVALID_LEVEL; } + if (unlikely(!btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_WRITTEN))) { + generic_err(leaf, 0, "invalid flag for leaf, WRITTEN not set"); + return BTRFS_TREE_BLOCK_WRITTEN_NOT_SET; + } + /* * Extent buffers from a relocation tree have a owner field that * corresponds to the subvolume tree they are based on. So just from an @@ -1854,6 +1859,7 @@ enum btrfs_tree_block_status __btrfs_check_leaf(struct extent_buffer *leaf) for (slot = 0; slot < nritems; slot++) { u32 item_end_expected; u64 item_data_end; + enum btrfs_tree_block_status ret; btrfs_item_key_to_cpu(leaf, &key, slot); @@ -1909,21 +1915,10 @@ enum btrfs_tree_block_status __btrfs_check_leaf(struct extent_buffer *leaf) return BTRFS_TREE_BLOCK_INVALID_OFFSETS; } - /* - * We only want to do this if WRITTEN is set, otherwise the leaf - * may be in some intermediate state and won't appear valid. - */ - if (btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_WRITTEN)) { - enum btrfs_tree_block_status ret; - - /* - * Check if the item size and content meet other - * criteria - */ - ret = check_leaf_item(leaf, &key, slot, &prev_key); - if (unlikely(ret != BTRFS_TREE_BLOCK_CLEAN)) - return ret; - } + /* Check if the item size and content meet other criteria. */ + ret = check_leaf_item(leaf, &key, slot, &prev_key); + if (unlikely(ret != BTRFS_TREE_BLOCK_CLEAN)) + return ret; prev_key.objectid = key.objectid; prev_key.type = key.type; @@ -1953,6 +1948,11 @@ enum btrfs_tree_block_status __btrfs_check_node(struct extent_buffer *node) int level = btrfs_header_level(node); u64 bytenr; + if (unlikely(!btrfs_header_flag(node, BTRFS_HEADER_FLAG_WRITTEN))) { + generic_err(node, 0, "invalid flag for node, WRITTEN not set"); + return BTRFS_TREE_BLOCK_WRITTEN_NOT_SET; + } + if (unlikely(level <= 0 || level >= BTRFS_MAX_LEVEL)) { generic_err(node, 0, "invalid level for node, have %d expect [1, %d]", diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h index 14b9fbe82da47..580ec4fde01a3 100644 --- a/fs/btrfs/tree-checker.h +++ b/fs/btrfs/tree-checker.h @@ -51,6 +51,7 @@ enum btrfs_tree_block_status { BTRFS_TREE_BLOCK_INVALID_BLOCKPTR, BTRFS_TREE_BLOCK_INVALID_ITEM, BTRFS_TREE_BLOCK_INVALID_OWNER, + BTRFS_TREE_BLOCK_WRITTEN_NOT_SET, }; /* diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 331fc7429952f..a5cc264dbc16f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4794,18 +4794,23 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, path->slots[0]++; continue; } - if (!dropped_extents) { - /* - * Avoid logging extent items logged in past fsync calls - * and leading to duplicate keys in the log tree. - */ + /* + * Avoid overlapping items in the log tree. The first time we + * get here, get rid of everything from a past fsync. After + * that, if the current extent starts before the end of the last + * extent we copied, truncate the last one. This can happen if + * an ordered extent completion modifies the subvolume tree + * while btrfs_next_leaf() has the tree unlocked. + */ + if (!dropped_extents || key.offset < truncate_offset) { ret = truncate_inode_items(trans, root->log_root, inode, - truncate_offset, + min(key.offset, truncate_offset), BTRFS_EXTENT_DATA_KEY); if (ret) goto out; dropped_extents = true; } + truncate_offset = btrfs_file_extent_end(path); if (ins_nr == 0) start_slot = slot; ins_nr++; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d67785be2c778..3ebadc5ec8aeb 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -694,6 +694,16 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, device->bdev = bdev_handle->bdev; clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); + if (device->devt != device->bdev->bd_dev) { + btrfs_warn(NULL, + "device %s maj:min changed from %d:%d to %d:%d", + device->name->str, MAJOR(device->devt), + MINOR(device->devt), MAJOR(device->bdev->bd_dev), + MINOR(device->bdev->bd_dev)); + + device->devt = device->bdev->bd_dev; + } + fs_devices->open_devices++; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && device->devid != BTRFS_DEV_REPLACE_DEVID) { @@ -1172,23 +1182,30 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device; struct btrfs_device *latest_dev = NULL; struct btrfs_device *tmp_device; + int ret = 0; list_for_each_entry_safe(device, tmp_device, &fs_devices->devices, dev_list) { - int ret; + int ret2; - ret = btrfs_open_one_device(fs_devices, device, flags, holder); - if (ret == 0 && + ret2 = btrfs_open_one_device(fs_devices, device, flags, holder); + if (ret2 == 0 && (!latest_dev || device->generation > latest_dev->generation)) { latest_dev = device; - } else if (ret == -ENODATA) { + } else if (ret2 == -ENODATA) { fs_devices->num_devices--; list_del(&device->dev_list); btrfs_free_device(device); } + if (ret == 0 && ret2 != 0) + ret = ret2; } - if (fs_devices->open_devices == 0) + + if (fs_devices->open_devices == 0) { + if (ret) + return ret; return -EINVAL; + } fs_devices->opened = 1; fs_devices->latest_dev = latest_dev; @@ -1301,6 +1318,47 @@ int btrfs_forget_devices(dev_t devt) return ret; } +static bool btrfs_skip_registration(struct btrfs_super_block *disk_super, + const char *path, dev_t devt, + bool mount_arg_dev) +{ + struct btrfs_fs_devices *fs_devices; + + /* + * Do not skip device registration for mounted devices with matching + * maj:min but different paths. Booting without initrd relies on + * /dev/root initially, later replaced with the actual root device. + * A successful scan ensures grub2-probe selects the correct device. + */ + list_for_each_entry(fs_devices, &fs_uuids, fs_list) { + struct btrfs_device *device; + + mutex_lock(&fs_devices->device_list_mutex); + + if (!fs_devices->opened) { + mutex_unlock(&fs_devices->device_list_mutex); + continue; + } + + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (device->bdev && (device->bdev->bd_dev == devt) && + strcmp(device->name->str, path) != 0) { + mutex_unlock(&fs_devices->device_list_mutex); + + /* Do not skip registration. */ + return false; + } + } + mutex_unlock(&fs_devices->device_list_mutex); + } + + if (!mount_arg_dev && btrfs_super_num_devices(disk_super) == 1 && + !(btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING)) + return true; + + return false; +} + /* * Look for a btrfs signature on a device. This may be called out of the mount path * and we are not allowed to call set_blocksize during the scan. The superblock @@ -1357,18 +1415,14 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags, goto error_bdev_put; } - if (!mount_arg_dev && btrfs_super_num_devices(disk_super) == 1 && - !(btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING)) { - dev_t devt; + if (btrfs_skip_registration(disk_super, path, bdev_handle->bdev->bd_dev, + mount_arg_dev)) { + pr_debug("BTRFS: skip registering single non-seed device %s (%d:%d)\n", + path, MAJOR(bdev_handle->bdev->bd_dev), + MINOR(bdev_handle->bdev->bd_dev)); - ret = lookup_bdev(path, &devt); - if (ret) - btrfs_warn(NULL, "lookup bdev failed for path %s: %d", - path, ret); - else - btrfs_free_stale_devices(devt, NULL); + btrfs_free_stale_devices(bdev_handle->bdev->bd_dev, NULL); - pr_debug("BTRFS: skip registering single non-seed device %s\n", path); device = NULL; goto free_disk_super; } @@ -1403,7 +1457,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start, if (in_range(physical_start, *start, len) || in_range(*start, physical_start, - physical_end - physical_start)) { + physical_end + 1 - physical_start)) { *start = physical_end + 1; return true; } @@ -3393,7 +3447,18 @@ static int btrfs_relocate_sys_chunks(struct btrfs_fs_info *fs_info) mutex_unlock(&fs_info->reclaim_bgs_lock); goto error; } - BUG_ON(ret == 0); /* Corruption */ + if (ret == 0) { + /* + * On the first search we would find chunk tree with + * offset -1, which is not possible. On subsequent + * loops this would find an existing item on an invalid + * offset (one less than the previous one, wrong + * alignment and size). + */ + ret = -EUCLEAN; + mutex_unlock(&fs_info->reclaim_bgs_lock); + goto error; + } ret = btrfs_previous_item(chunk_root, path, key.objectid, key.type); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 5f750fa53a2b2..495fa78027a13 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1279,7 +1279,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, struct btrfs_chunk_map *map) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; - struct btrfs_device *device = map->stripes[zone_idx].dev; + struct btrfs_device *device; int dev_replace_is_ongoing = 0; unsigned int nofs_flag; struct blk_zone zone; @@ -1287,7 +1287,11 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, info->physical = map->stripes[zone_idx].physical; + down_read(&dev_replace->rwsem); + device = map->stripes[zone_idx].dev; + if (!device->bdev) { + up_read(&dev_replace->rwsem); info->alloc_offset = WP_MISSING_DEV; return 0; } @@ -1297,6 +1301,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, __set_bit(zone_idx, active); if (!btrfs_dev_is_sequential(device, info->physical)) { + up_read(&dev_replace->rwsem); info->alloc_offset = WP_CONVENTIONAL; return 0; } @@ -1304,11 +1309,9 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, /* This zone will be used for allocation, so mark this zone non-empty. */ btrfs_dev_clear_zone_empty(device, info->physical); - down_read(&dev_replace->rwsem); dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace); if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL) btrfs_dev_clear_zone_empty(dev_replace->tgtdev, info->physical); - up_read(&dev_replace->rwsem); /* * The group is mapped to a sequential zone. Get the zone write pointer @@ -1319,6 +1322,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, ret = btrfs_get_dev_zone(device, info->physical, &zone); memalloc_nofs_restore(nofs_flag); if (ret) { + up_read(&dev_replace->rwsem); if (ret != -EIO && ret != -EOPNOTSUPP) return ret; info->alloc_offset = WP_MISSING_DEV; @@ -1330,6 +1334,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, "zoned: unexpected conventional zone %llu on device %s (devid %llu)", zone.start << SECTOR_SHIFT, rcu_str_deref(device->name), device->devid); + up_read(&dev_replace->rwsem); return -EIO; } @@ -1357,6 +1362,8 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx, break; } + up_read(&dev_replace->rwsem); + return 0; } @@ -1563,11 +1570,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) if (!map) return -EINVAL; - cache->physical_map = btrfs_clone_chunk_map(map, GFP_NOFS); - if (!cache->physical_map) { - ret = -ENOMEM; - goto out; - } + cache->physical_map = map; zone_info = kcalloc(map->num_stripes, sizeof(*zone_info), GFP_NOFS); if (!zone_info) { @@ -1679,7 +1682,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) } bitmap_free(active); kfree(zone_info); - btrfs_free_chunk_map(map); return ret; } @@ -2164,6 +2166,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ struct btrfs_chunk_map *map; const bool is_metadata = (block_group->flags & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)); + struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; int ret = 0; int i; @@ -2239,6 +2242,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ btrfs_clear_data_reloc_bg(block_group); spin_unlock(&block_group->lock); + down_read(&dev_replace->rwsem); map = block_group->physical_map; for (i = 0; i < map->num_stripes; i++) { struct btrfs_device *device = map->stripes[i].dev; @@ -2253,13 +2257,16 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ zinfo->zone_size >> SECTOR_SHIFT, GFP_NOFS); - if (ret) + if (ret) { + up_read(&dev_replace->rwsem); return ret; + } if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA)) zinfo->reserved_active_zones++; btrfs_dev_clear_active_zone(device, physical); } + up_read(&dev_replace->rwsem); if (!fully_written) btrfs_dec_block_group_ro(block_group); diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 6465e25742309..06cdf1a8a16f6 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -133,7 +133,7 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) return 0; } -static void cachefiles_flush_reqs(struct cachefiles_cache *cache) +void cachefiles_flush_reqs(struct cachefiles_cache *cache) { struct xarray *xa = &cache->reqs; struct cachefiles_req *req; @@ -159,6 +159,7 @@ static void cachefiles_flush_reqs(struct cachefiles_cache *cache) xa_for_each(xa, index, req) { req->error = -EIO; complete(&req->done); + __xa_erase(xa, index); } xa_unlock(xa); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index d33169f0018b1..6845a90cdfcce 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -55,6 +55,7 @@ struct cachefiles_ondemand_info { int ondemand_id; enum cachefiles_object_state state; struct cachefiles_object *object; + spinlock_t lock; }; /* @@ -138,6 +139,7 @@ static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) struct cachefiles_req { struct cachefiles_object *object; struct completion done; + refcount_t ref; int error; struct cachefiles_msg msg; }; @@ -186,6 +188,7 @@ extern int cachefiles_has_space(struct cachefiles_cache *cache, * daemon.c */ extern const struct file_operations cachefiles_daemon_fops; +extern void cachefiles_flush_reqs(struct cachefiles_cache *cache); extern void cachefiles_get_unbind_pincount(struct cachefiles_cache *cache); extern void cachefiles_put_unbind_pincount(struct cachefiles_cache *cache); @@ -424,6 +427,8 @@ do { \ pr_err("I/O Error: " FMT"\n", ##__VA_ARGS__); \ fscache_io_error((___cache)->cache); \ set_bit(CACHEFILES_DEAD, &(___cache)->flags); \ + if (cachefiles_in_ondemand_mode(___cache)) \ + cachefiles_flush_reqs(___cache); \ } while (0) #define cachefiles_io_error_obj(object, FMT, ...) \ diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 4ba42f1fa3b40..89f118d68d125 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -4,19 +4,40 @@ #include #include "internal.h" +struct ondemand_anon_file { + struct file *file; + int fd; +}; + +static inline void cachefiles_req_put(struct cachefiles_req *req) +{ + if (refcount_dec_and_test(&req->ref)) + kfree(req); +} + static int cachefiles_ondemand_fd_release(struct inode *inode, struct file *file) { struct cachefiles_object *object = file->private_data; - struct cachefiles_cache *cache = object->volume->cache; - struct cachefiles_ondemand_info *info = object->ondemand; - int object_id = info->ondemand_id; + struct cachefiles_cache *cache; + struct cachefiles_ondemand_info *info; + int object_id; struct cachefiles_req *req; - XA_STATE(xas, &cache->reqs, 0); + XA_STATE(xas, NULL, 0); + + if (!object) + return 0; + + info = object->ondemand; + cache = object->volume->cache; + xas.xa = &cache->reqs; xa_lock(&cache->reqs); + spin_lock(&info->lock); + object_id = info->ondemand_id; info->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; cachefiles_ondemand_set_object_close(object); + spin_unlock(&info->lock); /* Only flush CACHEFILES_REQ_NEW marked req to avoid race with daemon_read */ xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) { @@ -116,6 +137,7 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) { struct cachefiles_req *req; struct fscache_cookie *cookie; + struct cachefiles_ondemand_info *info; char *pid, *psize; unsigned long id; long size; @@ -166,6 +188,33 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) goto out; } + info = req->object->ondemand; + spin_lock(&info->lock); + /* + * The anonymous fd was closed before copen ? Fail the request. + * + * t1 | t2 + * --------------------------------------------------------- + * cachefiles_ondemand_copen + * req = xa_erase(&cache->reqs, id) + * // Anon fd is maliciously closed. + * cachefiles_ondemand_fd_release + * xa_lock(&cache->reqs) + * cachefiles_ondemand_set_object_close(object) + * xa_unlock(&cache->reqs) + * cachefiles_ondemand_set_object_open + * // No one will ever close it again. + * cachefiles_ondemand_daemon_read + * cachefiles_ondemand_select_req + * + * Get a read req but its fd is already closed. The daemon can't + * issue a cread ioctl with an closed fd, then hung. + */ + if (info->ondemand_id == CACHEFILES_ONDEMAND_ID_CLOSED) { + spin_unlock(&info->lock); + req->error = -EBADFD; + goto out; + } cookie = req->object->cookie; cookie->object_size = size; if (size) @@ -175,6 +224,7 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) trace_cachefiles_ondemand_copen(req->object, id, size); cachefiles_ondemand_set_object_open(req->object); + spin_unlock(&info->lock); wake_up_all(&cache->daemon_pollwq); out: @@ -205,14 +255,14 @@ int cachefiles_ondemand_restore(struct cachefiles_cache *cache, char *args) return 0; } -static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) +static int cachefiles_ondemand_get_fd(struct cachefiles_req *req, + struct ondemand_anon_file *anon_file) { struct cachefiles_object *object; struct cachefiles_cache *cache; struct cachefiles_open *load; - struct file *file; u32 object_id; - int ret, fd; + int ret; object = cachefiles_grab_object(req->object, cachefiles_obj_get_ondemand_fd); @@ -224,35 +274,53 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) if (ret < 0) goto err; - fd = get_unused_fd_flags(O_WRONLY); - if (fd < 0) { - ret = fd; + anon_file->fd = get_unused_fd_flags(O_WRONLY); + if (anon_file->fd < 0) { + ret = anon_file->fd; goto err_free_id; } - file = anon_inode_getfile("[cachefiles]", &cachefiles_ondemand_fd_fops, - object, O_WRONLY); - if (IS_ERR(file)) { - ret = PTR_ERR(file); + anon_file->file = anon_inode_getfile("[cachefiles]", + &cachefiles_ondemand_fd_fops, object, O_WRONLY); + if (IS_ERR(anon_file->file)) { + ret = PTR_ERR(anon_file->file); goto err_put_fd; } - file->f_mode |= FMODE_PWRITE | FMODE_LSEEK; - fd_install(fd, file); + spin_lock(&object->ondemand->lock); + if (object->ondemand->ondemand_id > 0) { + spin_unlock(&object->ondemand->lock); + /* Pair with check in cachefiles_ondemand_fd_release(). */ + anon_file->file->private_data = NULL; + ret = -EEXIST; + goto err_put_file; + } + + anon_file->file->f_mode |= FMODE_PWRITE | FMODE_LSEEK; load = (void *)req->msg.data; - load->fd = fd; + load->fd = anon_file->fd; object->ondemand->ondemand_id = object_id; + spin_unlock(&object->ondemand->lock); cachefiles_get_unbind_pincount(cache); trace_cachefiles_ondemand_open(object, &req->msg, load); return 0; +err_put_file: + fput(anon_file->file); + anon_file->file = NULL; err_put_fd: - put_unused_fd(fd); + put_unused_fd(anon_file->fd); + anon_file->fd = ret; err_free_id: xa_erase(&cache->ondemand_ids, object_id); err: + spin_lock(&object->ondemand->lock); + /* Avoid marking an opened object as closed. */ + if (object->ondemand->ondemand_id <= 0) + cachefiles_ondemand_set_object_close(object); + spin_unlock(&object->ondemand->lock); cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd); return ret; } @@ -299,9 +367,9 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, { struct cachefiles_req *req; struct cachefiles_msg *msg; - unsigned long id = 0; size_t n; int ret = 0; + struct ondemand_anon_file anon_file; XA_STATE(xas, &cache->reqs, cache->req_id_next); xa_lock(&cache->reqs); @@ -330,42 +398,45 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, xas_clear_mark(&xas, CACHEFILES_REQ_NEW); cache->req_id_next = xas.xa_index + 1; + refcount_inc(&req->ref); + cachefiles_grab_object(req->object, cachefiles_obj_get_read_req); xa_unlock(&cache->reqs); - id = xas.xa_index; - if (msg->opcode == CACHEFILES_OP_OPEN) { - ret = cachefiles_ondemand_get_fd(req); - if (ret) { - cachefiles_ondemand_set_object_close(req->object); - goto error; - } + ret = cachefiles_ondemand_get_fd(req, &anon_file); + if (ret) + goto out; } - msg->msg_id = id; + msg->msg_id = xas.xa_index; msg->object_id = req->object->ondemand->ondemand_id; - if (copy_to_user(_buffer, msg, n) != 0) { + if (copy_to_user(_buffer, msg, n) != 0) ret = -EFAULT; - goto err_put_fd; - } - /* CLOSE request has no reply */ - if (msg->opcode == CACHEFILES_OP_CLOSE) { - xa_erase(&cache->reqs, id); - complete(&req->done); + if (msg->opcode == CACHEFILES_OP_OPEN) { + if (ret < 0) { + fput(anon_file.file); + put_unused_fd(anon_file.fd); + goto out; + } + fd_install(anon_file.fd, anon_file.file); } - - return n; - -err_put_fd: - if (msg->opcode == CACHEFILES_OP_OPEN) - close_fd(((struct cachefiles_open *)msg->data)->fd); -error: - xa_erase(&cache->reqs, id); - req->error = ret; - complete(&req->done); - return ret; +out: + cachefiles_put_object(req->object, cachefiles_obj_put_read_req); + /* Remove error request and CLOSE request has no reply */ + if (ret || msg->opcode == CACHEFILES_OP_CLOSE) { + xas_reset(&xas); + xas_lock(&xas); + if (xas_load(&xas) == req) { + req->error = ret; + complete(&req->done); + xas_store(&xas, NULL); + } + xas_unlock(&xas); + } + cachefiles_req_put(req); + return ret ? ret : n; } typedef int (*init_req_fn)(struct cachefiles_req *req, void *private); @@ -395,6 +466,7 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, goto out; } + refcount_set(&req->ref, 1); req->object = object; init_completion(&req->done); req->msg.opcode = opcode; @@ -456,7 +528,7 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, wake_up_all(&cache->daemon_pollwq); wait_for_completion(&req->done); ret = req->error; - kfree(req); + cachefiles_req_put(req); return ret; out: /* Reset the object to close state in error handling path. @@ -578,6 +650,7 @@ int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object, return -ENOMEM; object->ondemand->object = object; + spin_lock_init(&object->ondemand->lock); INIT_WORK(&object->ondemand->ondemand_work, ondemand_object_worker); return 0; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 1340d77124ae4..ee9caf7916fb9 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -795,8 +795,10 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) ihold(inode); if (wbc->sync_mode == WB_SYNC_NONE && - ceph_inode_to_fs_client(inode)->write_congested) + ceph_inode_to_fs_client(inode)->write_congested) { + redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; + } wait_on_page_fscache(page); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 7fb4aae974124..e8d8e3e633cdb 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4775,13 +4775,13 @@ int ceph_drop_caps_for_unlink(struct inode *inode) doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode, ceph_vinop(inode)); - spin_lock(&mdsc->cap_unlink_delay_lock); + spin_lock(&mdsc->cap_delay_lock); ci->i_ceph_flags |= CEPH_I_FLUSH; if (!list_empty(&ci->i_cap_delay_list)) list_del_init(&ci->i_cap_delay_list); list_add_tail(&ci->i_cap_delay_list, &mdsc->cap_unlink_delay_list); - spin_unlock(&mdsc->cap_unlink_delay_lock); + spin_unlock(&mdsc->cap_delay_lock); /* * Fire the work immediately, because the MDS maybe diff --git a/fs/ceph/file.c b/fs/ceph/file.c index abe8028d95bf4..3d1cd079dbf16 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1138,7 +1138,12 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, } idx = 0; - left = ret > 0 ? ret : 0; + if (ret <= 0) + left = 0; + else if (off + ret > i_size) + left = i_size - off; + else + left = ret; while (left > 0) { size_t plen, copied; @@ -1167,15 +1172,13 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, } if (ret > 0) { - if (off > *ki_pos) { - if (off >= i_size) { - *retry_op = CHECK_EOF; - ret = i_size - *ki_pos; - *ki_pos = i_size; - } else { - ret = off - *ki_pos; - *ki_pos = off; - } + if (off >= i_size) { + *retry_op = CHECK_EOF; + ret = i_size - *ki_pos; + *ki_pos = i_size; + } else { + ret = off - *ki_pos; + *ki_pos = off; } if (last_objver) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 3ab9c268a8bb3..360b686c3c67c 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2504,7 +2504,7 @@ static void ceph_cap_unlink_work(struct work_struct *work) struct ceph_client *cl = mdsc->fsc->client; doutc(cl, "begin\n"); - spin_lock(&mdsc->cap_unlink_delay_lock); + spin_lock(&mdsc->cap_delay_lock); while (!list_empty(&mdsc->cap_unlink_delay_list)) { struct ceph_inode_info *ci; struct inode *inode; @@ -2516,15 +2516,15 @@ static void ceph_cap_unlink_work(struct work_struct *work) inode = igrab(&ci->netfs.inode); if (inode) { - spin_unlock(&mdsc->cap_unlink_delay_lock); + spin_unlock(&mdsc->cap_delay_lock); doutc(cl, "on %p %llx.%llx\n", inode, ceph_vinop(inode)); ceph_check_caps(ci, CHECK_CAPS_FLUSH); iput(inode); - spin_lock(&mdsc->cap_unlink_delay_lock); + spin_lock(&mdsc->cap_delay_lock); } } - spin_unlock(&mdsc->cap_unlink_delay_lock); + spin_unlock(&mdsc->cap_delay_lock); doutc(cl, "done\n"); } @@ -5404,7 +5404,6 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) INIT_LIST_HEAD(&mdsc->cap_wait_list); spin_lock_init(&mdsc->cap_delay_lock); INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list); - spin_lock_init(&mdsc->cap_unlink_delay_lock); INIT_LIST_HEAD(&mdsc->snap_flush_list); spin_lock_init(&mdsc->snap_flush_lock); mdsc->last_cap_flush_tid = 1; diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 03f8ff00874f7..b88e804152241 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -461,9 +461,8 @@ struct ceph_mds_client { struct delayed_work delayed_work; /* delayed work */ unsigned long last_renew_caps; /* last time we renewed our caps */ struct list_head cap_delay_list; /* caps with delayed release */ - spinlock_t cap_delay_lock; /* protects cap_delay_list */ struct list_head cap_unlink_delay_list; /* caps with delayed release for unlink */ - spinlock_t cap_unlink_delay_lock; /* protects cap_unlink_delay_list */ + spinlock_t cap_delay_lock; /* protects cap_delay_list and cap_unlink_delay_list */ struct list_head snap_flush_list; /* cap_snaps ready to flush */ spinlock_t snap_flush_lock; diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 8109aba66e023..4da1d05effefb 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -13,6 +13,7 @@ #include "mdsmap.h" #include "mds_client.h" #include "super.h" +#include "mdsmap.h" #define CEPH_MDS_IS_READY(i, ignore_laggy) \ (m->m_info[i].state > 0 && ignore_laggy ? true : !m->m_info[i].laggy) diff --git a/fs/ceph/super.h b/fs/ceph/super.h index b63b4cd9b5b68..26e1fc08e789d 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1134,8 +1134,7 @@ struct ceph_acl_sec_ctx { void *acl; #endif #ifdef CONFIG_CEPH_FS_SECURITY_LABEL - void *sec_ctx; - u32 sec_ctxlen; + struct lsmcontext lsmctx; #endif #ifdef CONFIG_FS_ENCRYPTION struct ceph_fscrypt_auth *fscrypt_auth; diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index e066a556eccbf..4c767a20ac4cb 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1383,8 +1383,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, int err; err = security_dentry_init_security(dentry, mode, &dentry->d_name, - &name, &as_ctx->sec_ctx, - &as_ctx->sec_ctxlen); + &name, &as_ctx->lsmctx); if (err < 0) { WARN_ON_ONCE(err != -EOPNOTSUPP); err = 0; /* do nothing */ @@ -1409,7 +1408,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, */ name_len = strlen(name); err = ceph_pagelist_reserve(pagelist, - 4 * 2 + name_len + as_ctx->sec_ctxlen); + 4 * 2 + name_len + as_ctx->lsmctx.len); if (err) goto out; @@ -1429,11 +1428,9 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, as_ctx->pagelist = pagelist; } - ceph_pagelist_encode_32(pagelist, name_len); - ceph_pagelist_append(pagelist, name, name_len); - - ceph_pagelist_encode_32(pagelist, as_ctx->sec_ctxlen); - ceph_pagelist_append(pagelist, as_ctx->sec_ctx, as_ctx->sec_ctxlen); + ceph_pagelist_encode_32(pagelist, as_ctx->lsmctx.len); + ceph_pagelist_append(pagelist, as_ctx->lsmctx.context, + as_ctx->lsmctx.len); err = 0; out: @@ -1451,7 +1448,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx) posix_acl_release(as_ctx->default_acl); #endif #ifdef CONFIG_CEPH_FS_SECURITY_LABEL - security_release_secctx(as_ctx->sec_ctx, as_ctx->sec_ctxlen); + security_release_secctx(&as_ctx->lsmctx); #endif #ifdef CONFIG_FS_ENCRYPTION kfree(as_ctx->fscrypt_auth); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 034a617cb1a5e..a40da00654336 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -751,13 +751,28 @@ static void __debugfs_file_removed(struct dentry *dentry) if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) return; - /* if we hit zero, just wait for all to finish */ - if (!refcount_dec_and_test(&fsd->active_users)) { - wait_for_completion(&fsd->active_users_drained); + /* if this was the last reference, we're done */ + if (refcount_dec_and_test(&fsd->active_users)) return; - } - /* if we didn't hit zero, try to cancel any we can */ + /* + * If there's still a reference, the code that obtained it can + * be in different states: + * - The common case of not using cancellations, or already + * after debugfs_leave_cancellation(), where we just need + * to wait for debugfs_file_put() which signals the completion; + * - inside a cancellation section, i.e. between + * debugfs_enter_cancellation() and debugfs_leave_cancellation(), + * in which case we need to trigger the ->cancel() function, + * and then wait for debugfs_file_put() just like in the + * previous case; + * - before debugfs_enter_cancellation() (but obviously after + * debugfs_file_get()), in which case we may not see the + * cancellation in the list on the first round of the loop, + * but debugfs_enter_cancellation() signals the completion + * after adding it, so this code gets woken up to call the + * ->cancel() function. + */ while (refcount_read(&fsd->active_users)) { struct debugfs_cancellation *c; diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index 1f2f70a1b824e..decedc4ee15f6 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -12,6 +12,7 @@ #include #include "dlm_internal.h" +#include "lvb_table.h" #include "memory.h" #include "lock.h" #include "user.h" @@ -42,6 +43,7 @@ int dlm_enqueue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode, struct dlm_ls *ls = lkb->lkb_resource->res_ls; int rv = DLM_ENQUEUE_CALLBACK_SUCCESS; struct dlm_callback *cb; + int copy_lvb = 0; int prev_mode; if (flags & DLM_CB_BAST) { @@ -73,6 +75,17 @@ int dlm_enqueue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode, goto out; } } + } else if (flags & DLM_CB_CAST) { + if (test_bit(DLM_DFL_USER_BIT, &lkb->lkb_dflags)) { + if (lkb->lkb_last_cast) + prev_mode = lkb->lkb_last_cb->mode; + else + prev_mode = -1; + + if (!status && lkb->lkb_lksb->sb_lvbptr && + dlm_lvb_operations[prev_mode + 1][mode + 1]) + copy_lvb = 1; + } } cb = dlm_allocate_cb(); @@ -85,6 +98,7 @@ int dlm_enqueue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode, cb->mode = mode; cb->sb_status = status; cb->sb_flags = (sbflags & 0x000000FF); + cb->copy_lvb = copy_lvb; kref_init(&cb->ref); if (!test_and_set_bit(DLM_IFL_CB_PENDING_BIT, &lkb->lkb_iflags)) rv = DLM_ENQUEUE_CALLBACK_NEED_SCHED; diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index dfc444dad3298..511d0b984f580 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -222,6 +222,7 @@ struct dlm_callback { int sb_status; /* copy to lksb status */ uint8_t sb_flags; /* copy to lksb flags */ int8_t mode; /* rq mode of bast, gr mode of cast */ + int copy_lvb; struct list_head list; struct kref ref; diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 695e691b38b31..12a483deeef5e 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -21,7 +21,6 @@ #include "dlm_internal.h" #include "lockspace.h" #include "lock.h" -#include "lvb_table.h" #include "user.h" #include "ast.h" #include "config.h" @@ -806,8 +805,7 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, struct dlm_lkb *lkb; DECLARE_WAITQUEUE(wait, current); struct dlm_callback *cb; - int rv, copy_lvb = 0; - int old_mode, new_mode; + int rv, ret; if (count == sizeof(struct dlm_device_version)) { rv = copy_version_to_user(buf, count); @@ -864,9 +862,6 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, lkb = list_first_entry(&proc->asts, struct dlm_lkb, lkb_cb_list); - /* rem_lkb_callback sets a new lkb_last_cast */ - old_mode = lkb->lkb_last_cast->mode; - rv = dlm_dequeue_lkb_callback(lkb, &cb); switch (rv) { case DLM_DEQUEUE_CALLBACK_EMPTY: @@ -895,20 +890,14 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, if (cb->flags & DLM_CB_BAST) { trace_dlm_bast(lkb->lkb_resource->res_ls, lkb, cb->mode); } else if (cb->flags & DLM_CB_CAST) { - new_mode = cb->mode; - - if (!cb->sb_status && lkb->lkb_lksb->sb_lvbptr && - dlm_lvb_operations[old_mode + 1][new_mode + 1]) - copy_lvb = 1; - lkb->lkb_lksb->sb_status = cb->sb_status; lkb->lkb_lksb->sb_flags = cb->sb_flags; trace_dlm_ast(lkb->lkb_resource->res_ls, lkb); } - rv = copy_result_to_user(lkb->lkb_ua, - test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags), - cb->flags, cb->mode, copy_lvb, buf, count); + ret = copy_result_to_user(lkb->lkb_ua, + test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags), + cb->flags, cb->mode, cb->copy_lvb, buf, count); kref_put(&cb->ref, dlm_release_callback); @@ -916,7 +905,7 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, if (rv == DLM_DEQUEUE_CALLBACK_LAST) dlm_put_lkb(lkb); - return rv; + return ret; } static __poll_t device_poll(struct file *file, poll_table *wait) diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 3fe41964c0d8d..7f9f68c00ef63 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -300,9 +300,11 @@ write_tag_66_packet(char *signature, u8 cipher_code, * | Key Identifier Size | 1 or 2 bytes | * | Key Identifier | arbitrary | * | File Encryption Key Size | 1 or 2 bytes | + * | Cipher Code | 1 byte | * | File Encryption Key | arbitrary | + * | Checksum | 2 bytes | */ - data_len = (5 + ECRYPTFS_SIG_SIZE_HEX + crypt_stat->key_size); + data_len = (8 + ECRYPTFS_SIG_SIZE_HEX + crypt_stat->key_size); *packet = kmalloc(data_len, GFP_KERNEL); message = *packet; if (!message) { diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c index b98872058abe8..26350c5b040e1 100644 --- a/fs/erofs/decompressor_deflate.c +++ b/fs/erofs/decompressor_deflate.c @@ -46,39 +46,15 @@ int __init z_erofs_deflate_init(void) /* by default, use # of possible CPUs instead */ if (!z_erofs_deflate_nstrms) z_erofs_deflate_nstrms = num_possible_cpus(); - - for (; z_erofs_deflate_avail_strms < z_erofs_deflate_nstrms; - ++z_erofs_deflate_avail_strms) { - struct z_erofs_deflate *strm; - - strm = kzalloc(sizeof(*strm), GFP_KERNEL); - if (!strm) - goto out_failed; - - /* XXX: in-kernel zlib cannot shrink windowbits currently */ - strm->z.workspace = vmalloc(zlib_inflate_workspacesize()); - if (!strm->z.workspace) { - kfree(strm); - goto out_failed; - } - - spin_lock(&z_erofs_deflate_lock); - strm->next = z_erofs_deflate_head; - z_erofs_deflate_head = strm; - spin_unlock(&z_erofs_deflate_lock); - } return 0; - -out_failed: - erofs_err(NULL, "failed to allocate zlib workspace"); - z_erofs_deflate_exit(); - return -ENOMEM; } int z_erofs_load_deflate_config(struct super_block *sb, struct erofs_super_block *dsb, void *data, int size) { struct z_erofs_deflate_cfgs *dfl = data; + static DEFINE_MUTEX(deflate_resize_mutex); + static bool inited; if (!dfl || size < sizeof(struct z_erofs_deflate_cfgs)) { erofs_err(sb, "invalid deflate cfgs, size=%u", size); @@ -89,9 +65,36 @@ int z_erofs_load_deflate_config(struct super_block *sb, erofs_err(sb, "unsupported windowbits %u", dfl->windowbits); return -EOPNOTSUPP; } + mutex_lock(&deflate_resize_mutex); + if (!inited) { + for (; z_erofs_deflate_avail_strms < z_erofs_deflate_nstrms; + ++z_erofs_deflate_avail_strms) { + struct z_erofs_deflate *strm; + + strm = kzalloc(sizeof(*strm), GFP_KERNEL); + if (!strm) + goto failed; + /* XXX: in-kernel zlib cannot customize windowbits */ + strm->z.workspace = vmalloc(zlib_inflate_workspacesize()); + if (!strm->z.workspace) { + kfree(strm); + goto failed; + } + spin_lock(&z_erofs_deflate_lock); + strm->next = z_erofs_deflate_head; + z_erofs_deflate_head = strm; + spin_unlock(&z_erofs_deflate_lock); + } + inited = true; + } + mutex_unlock(&deflate_resize_mutex); erofs_info(sb, "EXPERIMENTAL DEFLATE feature in use. Use at your own risk!"); return 0; +failed: + mutex_unlock(&deflate_resize_mutex); + z_erofs_deflate_exit(); + return -ENOMEM; } int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq, diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 89a7c2453aae6..122a4753ecea4 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -3,6 +3,7 @@ * Copyright (C) 2022, Alibaba Cloud * Copyright (C) 2022, Bytedance Inc. All rights reserved. */ +#include #include #include "internal.h" @@ -12,6 +13,18 @@ static LIST_HEAD(erofs_domain_list); static LIST_HEAD(erofs_domain_cookies_list); static struct vfsmount *erofs_pseudo_mnt; +static int erofs_anon_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, EROFS_SUPER_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type erofs_anon_fs_type = { + .owner = THIS_MODULE, + .name = "pseudo_erofs", + .init_fs_context = erofs_anon_init_fs_context, + .kill_sb = kill_anon_super, +}; + struct erofs_fscache_request { struct erofs_fscache_request *primary; struct netfs_cache_resources cache_resources; @@ -381,7 +394,7 @@ static int erofs_fscache_init_domain(struct super_block *sb) goto out; if (!erofs_pseudo_mnt) { - struct vfsmount *mnt = kern_mount(&erofs_fs_type); + struct vfsmount *mnt = kern_mount(&erofs_anon_fs_type); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index b0409badb0172..c69174675caf7 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -84,13 +84,6 @@ struct erofs_dev_context { bool flatdev; }; -struct erofs_fs_context { - struct erofs_mount_opts opt; - struct erofs_dev_context *devs; - char *fsid; - char *domain_id; -}; - /* all filesystem-wide lz4 configurations */ struct erofs_sb_lz4_info { /* # of pages needed for EROFS lz4 rolling decompression */ @@ -385,7 +378,6 @@ struct erofs_map_dev { unsigned int m_deviceid; }; -extern struct file_system_type erofs_fs_type; extern const struct super_operations erofs_sops; extern const struct address_space_operations erofs_raw_access_aops; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 5f60f163bd56e..a2fa745585704 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -370,18 +370,18 @@ static int erofs_read_superblock(struct super_block *sb) return ret; } -static void erofs_default_options(struct erofs_fs_context *ctx) +static void erofs_default_options(struct erofs_sb_info *sbi) { #ifdef CONFIG_EROFS_FS_ZIP - ctx->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND; - ctx->opt.max_sync_decompress_pages = 3; - ctx->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO; + sbi->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND; + sbi->opt.max_sync_decompress_pages = 3; + sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO; #endif #ifdef CONFIG_EROFS_FS_XATTR - set_opt(&ctx->opt, XATTR_USER); + set_opt(&sbi->opt, XATTR_USER); #endif #ifdef CONFIG_EROFS_FS_POSIX_ACL - set_opt(&ctx->opt, POSIX_ACL); + set_opt(&sbi->opt, POSIX_ACL); #endif } @@ -426,17 +426,17 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) { #ifdef CONFIG_FS_DAX - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; switch (mode) { case EROFS_MOUNT_DAX_ALWAYS: warnfc(fc, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); - set_opt(&ctx->opt, DAX_ALWAYS); - clear_opt(&ctx->opt, DAX_NEVER); + set_opt(&sbi->opt, DAX_ALWAYS); + clear_opt(&sbi->opt, DAX_NEVER); return true; case EROFS_MOUNT_DAX_NEVER: - set_opt(&ctx->opt, DAX_NEVER); - clear_opt(&ctx->opt, DAX_ALWAYS); + set_opt(&sbi->opt, DAX_NEVER); + clear_opt(&sbi->opt, DAX_ALWAYS); return true; default: DBG_BUGON(1); @@ -451,7 +451,7 @@ static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) static int erofs_fc_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; struct fs_parse_result result; struct erofs_device_info *dif; int opt, ret; @@ -464,9 +464,9 @@ static int erofs_fc_parse_param(struct fs_context *fc, case Opt_user_xattr: #ifdef CONFIG_EROFS_FS_XATTR if (result.boolean) - set_opt(&ctx->opt, XATTR_USER); + set_opt(&sbi->opt, XATTR_USER); else - clear_opt(&ctx->opt, XATTR_USER); + clear_opt(&sbi->opt, XATTR_USER); #else errorfc(fc, "{,no}user_xattr options not supported"); #endif @@ -474,16 +474,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, case Opt_acl: #ifdef CONFIG_EROFS_FS_POSIX_ACL if (result.boolean) - set_opt(&ctx->opt, POSIX_ACL); + set_opt(&sbi->opt, POSIX_ACL); else - clear_opt(&ctx->opt, POSIX_ACL); + clear_opt(&sbi->opt, POSIX_ACL); #else errorfc(fc, "{,no}acl options not supported"); #endif break; case Opt_cache_strategy: #ifdef CONFIG_EROFS_FS_ZIP - ctx->opt.cache_strategy = result.uint_32; + sbi->opt.cache_strategy = result.uint_32; #else errorfc(fc, "compression not supported, cache_strategy ignored"); #endif @@ -505,27 +505,27 @@ static int erofs_fc_parse_param(struct fs_context *fc, kfree(dif); return -ENOMEM; } - down_write(&ctx->devs->rwsem); - ret = idr_alloc(&ctx->devs->tree, dif, 0, 0, GFP_KERNEL); - up_write(&ctx->devs->rwsem); + down_write(&sbi->devs->rwsem); + ret = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL); + up_write(&sbi->devs->rwsem); if (ret < 0) { kfree(dif->path); kfree(dif); return ret; } - ++ctx->devs->extra_devices; + ++sbi->devs->extra_devices; break; #ifdef CONFIG_EROFS_FS_ONDEMAND case Opt_fsid: - kfree(ctx->fsid); - ctx->fsid = kstrdup(param->string, GFP_KERNEL); - if (!ctx->fsid) + kfree(sbi->fsid); + sbi->fsid = kstrdup(param->string, GFP_KERNEL); + if (!sbi->fsid) return -ENOMEM; break; case Opt_domain_id: - kfree(ctx->domain_id); - ctx->domain_id = kstrdup(param->string, GFP_KERNEL); - if (!ctx->domain_id) + kfree(sbi->domain_id); + sbi->domain_id = kstrdup(param->string, GFP_KERNEL); + if (!sbi->domain_id) return -ENOMEM; break; #else @@ -579,18 +579,10 @@ static const struct export_operations erofs_export_ops = { .get_parent = erofs_get_parent, }; -static int erofs_fc_fill_pseudo_super(struct super_block *sb, struct fs_context *fc) -{ - static const struct tree_descr empty_descr = {""}; - - return simple_fill_super(sb, EROFS_SUPER_MAGIC, &empty_descr); -} - static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; - struct erofs_sb_info *sbi; - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = EROFS_SB(sb); int err; sb->s_magic = EROFS_SUPER_MAGIC; @@ -598,19 +590,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_op = &erofs_sops; - sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); - if (!sbi) - return -ENOMEM; - - sb->s_fs_info = sbi; - sbi->opt = ctx->opt; - sbi->devs = ctx->devs; - ctx->devs = NULL; - sbi->fsid = ctx->fsid; - ctx->fsid = NULL; - sbi->domain_id = ctx->domain_id; - ctx->domain_id = NULL; - sbi->blkszbits = PAGE_SHIFT; if (erofs_is_fscache_mode(sb)) { sb->s_blocksize = PAGE_SIZE; @@ -712,16 +691,11 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return 0; } -static int erofs_fc_anon_get_tree(struct fs_context *fc) -{ - return get_tree_nodev(fc, erofs_fc_fill_pseudo_super); -} - static int erofs_fc_get_tree(struct fs_context *fc) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; - if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && ctx->fsid) + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) return get_tree_nodev(fc, erofs_fc_fill_super); return get_tree_bdev(fc, erofs_fc_fill_super); @@ -731,19 +705,19 @@ static int erofs_fc_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *new_sbi = fc->s_fs_info; DBG_BUGON(!sb_rdonly(sb)); - if (ctx->fsid || ctx->domain_id) + if (new_sbi->fsid || new_sbi->domain_id) erofs_info(sb, "ignoring reconfiguration for fsid|domain_id."); - if (test_opt(&ctx->opt, POSIX_ACL)) + if (test_opt(&new_sbi->opt, POSIX_ACL)) fc->sb_flags |= SB_POSIXACL; else fc->sb_flags &= ~SB_POSIXACL; - sbi->opt = ctx->opt; + sbi->opt = new_sbi->opt; fc->sb_flags |= SB_RDONLY; return 0; @@ -774,12 +748,15 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) static void erofs_fc_free(struct fs_context *fc) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; + + if (!sbi) + return; - erofs_free_dev_context(ctx->devs); - kfree(ctx->fsid); - kfree(ctx->domain_id); - kfree(ctx); + erofs_free_dev_context(sbi->devs); + kfree(sbi->fsid); + kfree(sbi->domain_id); + kfree(sbi); } static const struct fs_context_operations erofs_context_ops = { @@ -789,56 +766,37 @@ static const struct fs_context_operations erofs_context_ops = { .free = erofs_fc_free, }; -static const struct fs_context_operations erofs_anon_context_ops = { - .get_tree = erofs_fc_anon_get_tree, -}; - static int erofs_init_fs_context(struct fs_context *fc) { - struct erofs_fs_context *ctx; - - /* pseudo mount for anon inodes */ - if (fc->sb_flags & SB_KERNMOUNT) { - fc->ops = &erofs_anon_context_ops; - return 0; - } + struct erofs_sb_info *sbi; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) return -ENOMEM; - ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL); - if (!ctx->devs) { - kfree(ctx); + + sbi->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL); + if (!sbi->devs) { + kfree(sbi); return -ENOMEM; } - fc->fs_private = ctx; + fc->s_fs_info = sbi; - idr_init(&ctx->devs->tree); - init_rwsem(&ctx->devs->rwsem); - erofs_default_options(ctx); + idr_init(&sbi->devs->tree); + init_rwsem(&sbi->devs->rwsem); + erofs_default_options(sbi); fc->ops = &erofs_context_ops; return 0; } static void erofs_kill_sb(struct super_block *sb) { - struct erofs_sb_info *sbi; - - /* pseudo mount for anon inodes */ - if (sb->s_flags & SB_KERNMOUNT) { - kill_anon_super(sb); - return; - } + struct erofs_sb_info *sbi = EROFS_SB(sb); - if (erofs_is_fscache_mode(sb)) + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) kill_anon_super(sb); else kill_block_super(sb); - sbi = EROFS_SB(sb); - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); fs_put_dax(sbi->dax_dev, NULL); erofs_fscache_unregister_fs(sb); @@ -868,7 +826,7 @@ static void erofs_put_super(struct super_block *sb) erofs_fscache_unregister_fs(sb); } -struct file_system_type erofs_fs_type = { +static struct file_system_type erofs_fs_type = { .owner = THIS_MODULE, .name = "erofs", .init_fs_context = erofs_init_fs_context, diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 3534d36a14740..c5a9a483fb538 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -875,6 +875,34 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep return res; } +/* + * The ffd.file pointer may be in the process of being torn down due to + * being closed, but we may not have finished eventpoll_release() yet. + * + * Normally, even with the atomic_long_inc_not_zero, the file may have + * been free'd and then gotten re-allocated to something else (since + * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU). + * + * But for epoll, users hold the ep->mtx mutex, and as such any file in + * the process of being free'd will block in eventpoll_release_file() + * and thus the underlying file allocation will not be free'd, and the + * file re-use cannot happen. + * + * For the same reason we can avoid a rcu_read_lock() around the + * operation - 'ffd.file' cannot go away even if the refcount has + * reached zero (but we must still not call out to ->poll() functions + * etc). + */ +static struct file *epi_fget(const struct epitem *epi) +{ + struct file *file; + + file = epi->ffd.file; + if (!atomic_long_inc_not_zero(&file->f_count)) + file = NULL; + return file; +} + /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() @@ -883,14 +911,22 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { - struct file *file = epi->ffd.file; + struct file *file = epi_fget(epi); __poll_t res; + /* + * We could return EPOLLERR | EPOLLHUP or something, but let's + * treat this more as "file doesn't exist, poll didn't happen". + */ + if (!file) + return 0; + pt->_key = epi->event.events; if (!is_file_epoll(file)) res = vfs_poll(file, pt); else res = __ep_eventpoll_poll(file, pt, depth); + fput(file); return res & epi->event.events; } diff --git a/fs/exec.c b/fs/exec.c index af4fbb61cd53e..f11cfd7bce0b1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -67,6 +67,7 @@ #include #include #include +#include #include #include @@ -267,6 +268,14 @@ static int __bprm_mm_init(struct linux_binprm *bprm) goto err_free; } + /* + * Need to be called with mmap write lock + * held, to avoid race with ksmd. + */ + err = ksm_execve(mm); + if (err) + goto err_ksm; + /* * Place the stack at the largest stack address the architecture * supports. Later, we'll move this to an appropriate place. We don't @@ -288,6 +297,8 @@ static int __bprm_mm_init(struct linux_binprm *bprm) bprm->p = vma->vm_end - sizeof(void *); return 0; err: + ksm_exit(mm); +err_ksm: mmap_write_unlock(mm); err_free: bprm->vma = NULL; @@ -895,6 +906,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm, goto out; } + bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: diff --git a/fs/exfat/file.c b/fs/exfat/file.c index cc00f1a7a1e18..9adfc38ca7dac 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -51,7 +51,7 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) clu.flags = ei->flags; ret = exfat_alloc_cluster(inode, new_num_clusters - num_clusters, - &clu, IS_DIRSYNC(inode)); + &clu, inode_needs_sync(inode)); if (ret) return ret; @@ -77,12 +77,11 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) ei->i_size_aligned = round_up(size, sb->s_blocksize); ei->i_size_ondisk = ei->i_size_aligned; inode->i_blocks = round_up(size, sbi->cluster_size) >> 9; + mark_inode_dirty(inode); - if (IS_DIRSYNC(inode)) + if (IS_SYNC(inode)) return write_inode_now(inode, 1); - mark_inode_dirty(inode); - return 0; free_clu: diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 677a9ad45dcb7..f38bdd46e4f77 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -674,7 +674,7 @@ struct ext2_inode_info { struct inode vfs_inode; struct list_head i_orphan; /* unlinked but open inodes */ #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif }; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 01f9addc8b1f6..6d8587505cea3 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -320,7 +320,7 @@ static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, siz static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); static int ext2_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); -static struct dquot **ext2_get_dquots(struct inode *inode) +static struct dquot __rcu **ext2_get_dquots(struct inode *inode) { return EXT2_I(inode)->i_dquot; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 023571f8dd1b4..4fb938ba3f359 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1158,7 +1158,7 @@ struct ext4_inode_info { tid_t i_datasync_tid; #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2ccf3b5e3a7c4..4b665ae953b96 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2334,7 +2334,7 @@ static int mpage_journal_page_buffers(handle_t *handle, if (folio_pos(folio) + len > size && !ext4_verity_in_progress(inode)) - len = size - folio_pos(folio); + len = size & (len - 1); return ext4_journal_folio_buffers(handle, folio, len); } @@ -2887,9 +2887,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, if (IS_ERR(folio)) return PTR_ERR(folio); - /* In case writeback began while the folio was unlocked */ - folio_wait_stable(folio); - #ifdef CONFIG_FS_ENCRYPTION ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep); #else diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e4f7cf9d89c45..ade684db83e98 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -831,6 +831,8 @@ static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) return 0; if (order == MB_NUM_ORDERS(sb)) order--; + if (WARN_ON_ONCE(order > MB_NUM_ORDERS(sb))) + order = MB_NUM_ORDERS(sb) - 1; return order; } @@ -1008,6 +1010,8 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context * goal length. */ order = fls(ac->ac_g_ex.fe_len) - 1; + if (WARN_ON_ONCE(order - 1 > MB_NUM_ORDERS(ac->ac_sb))) + order = MB_NUM_ORDERS(ac->ac_sb); min_order = order - sbi->s_mb_best_avail_max_trim_order; if (min_order < 0) min_order = 0; @@ -3059,7 +3063,10 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); - seq_puts(seq, " ]\n"); + seq_puts(seq, " ]"); + if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info)) + seq_puts(seq, " Block bitmap corrupted!"); + seq_puts(seq, "\n"); return 0; } @@ -5169,10 +5176,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) .fe_len = ac->ac_orig_goal_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); + loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); - /* we can't allocate as much as normalizer wants. - * so, found space must get proper lstart - * to cover original request */ + /* + * We can't allocate as much as normalizer wants, so we try + * to get proper lstart to cover the original request, except + * when the goal doesn't cover the original request as below: + * + * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 + * best_ex:0/200(200) -> adjusted: 1848/2048(200) + */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); @@ -5184,7 +5197,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * 1. Check if best ex can be kept at end of goal (before * cr_best_avail trimmed it) and still cover original start * 2. Else, check if best ex can be kept at start of goal and - * still cover original start + * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; @@ -5194,7 +5207,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; - if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; @@ -5202,7 +5215,6 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); - BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } @@ -6111,6 +6123,7 @@ ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp) ext4_mb_mark_bb(sb, block, 1, true); ar->len = 1; + *errp = 0; return block; } diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 56938532b4ce2..7bfc5fb5a1285 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -193,8 +193,8 @@ struct ext4_allocation_context { ext4_grpblk_t ac_orig_goal_len; __u32 ac_flags; /* allocation hints */ + __u32 ac_groups_linear_remaining; __u16 ac_groups_scanned; - __u16 ac_groups_linear_remaining; __u16 ac_found; __u16 ac_cX_found[EXT4_MB_NUM_CRS]; __u16 ac_tail; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 05b647e6bc195..58fee3c6febcb 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2898,7 +2898,7 @@ static int ext4_tmpfile(struct mnt_idmap *idmap, struct inode *dir, inode = ext4_new_inode_start_handle(idmap, dir, mode, NULL, 0, NULL, EXT4_HT_DIR, - EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) + + EXT4_MAXQUOTAS_TRANS_BLOCKS(dir->i_sb) + 4 + EXT4_XATTR_TRANS_BLOCKS); handle = ext4_journal_current_handle(); err = PTR_ERR(inode); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 4d4a5a32e310d..3c0d12382e060 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1602,7 +1602,8 @@ static int ext4_flex_group_add(struct super_block *sb, int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); - int meta_bg = ext4_has_feature_meta_bg(sb); + int meta_bg = ext4_has_feature_meta_bg(sb) && + gdb_num >= le32_to_cpu(es->s_first_meta_bg); sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - ext4_group_first_block_no(sb, 0); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0f931d0c227da..b5fc5fa4e586c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1600,7 +1600,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); -static struct dquot **ext4_get_dquots(struct inode *inode) +static struct dquot __rcu **ext4_get_dquots(struct inode *inode) { return EXT4_I(inode)->i_dquot; } @@ -5555,19 +5555,15 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (err) goto failed_mount6; - err = ext4_register_sysfs(sb); - if (err) - goto failed_mount7; - err = ext4_init_orphan_info(sb); if (err) - goto failed_mount8; + goto failed_mount7; #ifdef CONFIG_QUOTA /* Enable quota usage during mount. */ if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) { err = ext4_enable_quotas(sb); if (err) - goto failed_mount9; + goto failed_mount8; } #endif /* CONFIG_QUOTA */ @@ -5593,7 +5589,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_msg(sb, KERN_INFO, "recovery complete"); err = ext4_mark_recovery_complete(sb, es); if (err) - goto failed_mount10; + goto failed_mount9; } if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) @@ -5610,15 +5606,17 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) atomic_set(&sbi->s_warning_count, 0); atomic_set(&sbi->s_msg_count, 0); + /* Register sysfs after all initializations are complete. */ + err = ext4_register_sysfs(sb); + if (err) + goto failed_mount9; + return 0; -failed_mount10: +failed_mount9: ext4_quotas_off(sb, EXT4_MAXQUOTAS); -failed_mount9: __maybe_unused +failed_mount8: __maybe_unused ext4_release_orphan_info(sb); -failed_mount8: - ext4_unregister_sysfs(sb); - kobject_put(&sbi->s_kobj); failed_mount7: ext4_unregister_li_request(sb); failed_mount6: @@ -6864,6 +6862,10 @@ static int ext4_write_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to commit dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6880,6 +6882,10 @@ static int ext4_acquire_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to acquire dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6899,6 +6905,10 @@ static int ext4_release_dquot(struct dquot *dquot) return PTR_ERR(handle); } ret = dquot_release(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to release dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 6d332dff79ddc..63cbda3700ea9 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -29,6 +29,7 @@ typedef enum { attr_trigger_test_error, attr_first_error_time, attr_last_error_time, + attr_clusters_in_group, attr_feature, attr_pointer_ui, attr_pointer_ul, @@ -104,7 +105,7 @@ static ssize_t reserved_clusters_store(struct ext4_sb_info *sbi, int ret; ret = kstrtoull(skip_spaces(buf), 0, &val); - if (ret || val >= clusters) + if (ret || val >= clusters || (s64)val < 0) return -EINVAL; atomic64_set(&sbi->s_resv_clusters, val); @@ -207,13 +208,14 @@ EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444); EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead, ext4_sb_info, s_inode_readahead_blks); +EXT4_ATTR_OFFSET(mb_group_prealloc, 0644, clusters_in_group, + ext4_sb_info, s_mb_group_prealloc); EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal); EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats); EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan); EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); -EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups); EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); @@ -392,6 +394,7 @@ static ssize_t ext4_attr_show(struct kobject *kobj, (unsigned long long) percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit)); case attr_inode_readahead: + case attr_clusters_in_group: case attr_pointer_ui: if (!ptr) return 0; @@ -451,7 +454,8 @@ static ssize_t ext4_attr_store(struct kobject *kobj, s_kobj); struct ext4_attr *a = container_of(attr, struct ext4_attr, attr); void *ptr = calc_ptr(a, sbi); - unsigned long t; + unsigned int t; + unsigned long lt; int ret; switch (a->attr_id) { @@ -460,7 +464,7 @@ static ssize_t ext4_attr_store(struct kobject *kobj, case attr_pointer_ui: if (!ptr) return 0; - ret = kstrtoul(skip_spaces(buf), 0, &t); + ret = kstrtouint(skip_spaces(buf), 0, &t); if (ret) return ret; if (a->attr_ptr == ptr_ext4_super_block_offset) @@ -468,13 +472,21 @@ static ssize_t ext4_attr_store(struct kobject *kobj, else *((unsigned int *) ptr) = t; return len; + case attr_clusters_in_group: + ret = kstrtouint(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if (t > sbi->s_clusters_per_group) + return -EINVAL; + *((unsigned int *) ptr) = t; + return len; case attr_pointer_ul: if (!ptr) return 0; - ret = kstrtoul(skip_spaces(buf), 0, &t); + ret = kstrtoul(skip_spaces(buf), 0, <); if (ret) return ret; - *((unsigned long *) ptr) = t; + *((unsigned long *) ptr) = lt; return len; case attr_inode_readahead: return inode_readahead_blks_store(sbi, buf, len); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 82dc5e673d5c4..3e9b088800b1b 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1565,46 +1565,49 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, /* * Add value of the EA in an inode. */ -static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode, - const void *value, size_t value_len, - struct inode **ret_inode) +static struct inode *ext4_xattr_inode_lookup_create(handle_t *handle, + struct inode *inode, const void *value, size_t value_len) { struct inode *ea_inode; u32 hash; int err; + /* Account inode & space to quota even if sharing... */ + err = ext4_xattr_inode_alloc_quota(inode, value_len); + if (err) + return ERR_PTR(err); + hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len); ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash); if (ea_inode) { err = ext4_xattr_inode_inc_ref(handle, ea_inode); - if (err) { - iput(ea_inode); - return err; - } - - *ret_inode = ea_inode; - return 0; + if (err) + goto out_err; + return ea_inode; } /* Create an inode for the EA value */ ea_inode = ext4_xattr_inode_create(handle, inode, hash); - if (IS_ERR(ea_inode)) - return PTR_ERR(ea_inode); + if (IS_ERR(ea_inode)) { + ext4_xattr_inode_free_quota(inode, NULL, value_len); + return ea_inode; + } err = ext4_xattr_inode_write(handle, ea_inode, value, value_len); if (err) { if (ext4_xattr_inode_dec_ref(handle, ea_inode)) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); - iput(ea_inode); - return err; + goto out_err; } if (EA_INODE_CACHE(inode)) mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash, ea_inode->i_ino, true /* reusable */); - - *ret_inode = ea_inode; - return 0; + return ea_inode; +out_err: + iput(ea_inode); + ext4_xattr_inode_free_quota(inode, NULL, value_len); + return ERR_PTR(err); } /* @@ -1616,6 +1619,7 @@ static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode, static int ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s, handle_t *handle, struct inode *inode, + struct inode *new_ea_inode, bool is_block) { struct ext4_xattr_entry *last, *next; @@ -1623,7 +1627,6 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, size_t min_offs = s->end - s->base, name_len = strlen(i->name); int in_inode = i->in_inode; struct inode *old_ea_inode = NULL; - struct inode *new_ea_inode = NULL; size_t old_size, new_size; int ret; @@ -1708,43 +1711,11 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, old_ea_inode = NULL; goto out; } - } - if (i->value && in_inode) { - WARN_ON_ONCE(!i->value_len); - - ret = ext4_xattr_inode_alloc_quota(inode, i->value_len); - if (ret) - goto out; - - ret = ext4_xattr_inode_lookup_create(handle, inode, i->value, - i->value_len, - &new_ea_inode); - if (ret) { - new_ea_inode = NULL; - ext4_xattr_inode_free_quota(inode, NULL, i->value_len); - goto out; - } - } - if (old_ea_inode) { /* We are ready to release ref count on the old_ea_inode. */ ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode); - if (ret) { - /* Release newly required ref count on new_ea_inode. */ - if (new_ea_inode) { - int err; - - err = ext4_xattr_inode_dec_ref(handle, - new_ea_inode); - if (err) - ext4_warning_inode(new_ea_inode, - "dec ref new_ea_inode err=%d", - err); - ext4_xattr_inode_free_quota(inode, new_ea_inode, - i->value_len); - } + if (ret) goto out; - } ext4_xattr_inode_free_quota(inode, old_ea_inode, le32_to_cpu(here->e_value_size)); @@ -1868,7 +1839,6 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, ret = 0; out: iput(old_ea_inode); - iput(new_ea_inode); return ret; } @@ -1931,9 +1901,21 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, size_t old_ea_inode_quota = 0; unsigned int ea_ino; - #define header(x) ((struct ext4_xattr_header *)(x)) + /* If we need EA inode, prepare it before locking the buffer */ + if (i->value && i->in_inode) { + WARN_ON_ONCE(!i->value_len); + + ea_inode = ext4_xattr_inode_lookup_create(handle, inode, + i->value, i->value_len); + if (IS_ERR(ea_inode)) { + error = PTR_ERR(ea_inode); + ea_inode = NULL; + goto cleanup; + } + } + if (s->base) { int offset = (char *)s->here - bs->bh->b_data; @@ -1942,6 +1924,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, EXT4_JTR_NONE); if (error) goto cleanup; + lock_buffer(bs->bh); if (header(s->base)->h_refcount == cpu_to_le32(1)) { @@ -1968,7 +1951,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, } ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, - true /* is_block */); + ea_inode, true /* is_block */); ext4_xattr_block_csum_set(inode, bs->bh); unlock_buffer(bs->bh); if (error == -EFSCORRUPTED) @@ -2036,29 +2019,13 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, s->end = s->base + sb->s_blocksize; } - error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); + error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode, + true /* is_block */); if (error == -EFSCORRUPTED) goto bad_block; if (error) goto cleanup; - if (i->value && s->here->e_value_inum) { - /* - * A ref count on ea_inode has been taken as part of the call to - * ext4_xattr_set_entry() above. We would like to drop this - * extra ref but we have to wait until the xattr block is - * initialized and has its own ref count on the ea_inode. - */ - ea_ino = le32_to_cpu(s->here->e_value_inum); - error = ext4_xattr_inode_iget(inode, ea_ino, - le32_to_cpu(s->here->e_hash), - &ea_inode); - if (error) { - ea_inode = NULL; - goto cleanup; - } - } - inserted: if (!IS_LAST_ENTRY(s->first)) { new_bh = ext4_xattr_block_cache_find(inode, header(s->base), @@ -2211,17 +2178,16 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, cleanup: if (ea_inode) { - int error2; - - error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); - if (error2) - ext4_warning_inode(ea_inode, "dec ref error=%d", - error2); + if (error) { + int error2; - /* If there was an error, revert the quota charge. */ - if (error) + error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); + if (error2) + ext4_warning_inode(ea_inode, "dec ref error=%d", + error2); ext4_xattr_inode_free_quota(inode, ea_inode, i_size_read(ea_inode)); + } iput(ea_inode); } if (ce) @@ -2279,14 +2245,38 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, { struct ext4_xattr_ibody_header *header; struct ext4_xattr_search *s = &is->s; + struct inode *ea_inode = NULL; int error; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return -ENOSPC; - error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); - if (error) + /* If we need EA inode, prepare it before locking the buffer */ + if (i->value && i->in_inode) { + WARN_ON_ONCE(!i->value_len); + + ea_inode = ext4_xattr_inode_lookup_create(handle, inode, + i->value, i->value_len); + if (IS_ERR(ea_inode)) + return PTR_ERR(ea_inode); + } + error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode, + false /* is_block */); + if (error) { + if (ea_inode) { + int error2; + + error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); + if (error2) + ext4_warning_inode(ea_inode, "dec ref error=%d", + error2); + + ext4_xattr_inode_free_quota(inode, ea_inode, + i_size_read(ea_inode)); + iput(ea_inode); + } return error; + } header = IHDR(inode, ext4_raw_inode(&is->iloc)); if (!IS_LAST_ENTRY(s->first)) { header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); @@ -2295,6 +2285,7 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, header->h_magic = cpu_to_le32(0); ext4_clear_inode_state(inode, EXT4_STATE_XATTR); } + iput(ea_inode); return 0; } @@ -3126,8 +3117,10 @@ ext4_xattr_block_cache_find(struct inode *inode, bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO); if (IS_ERR(bh)) { - if (PTR_ERR(bh) == -ENOMEM) + if (PTR_ERR(bh) == -ENOMEM) { + mb_cache_entry_put(ea_block_cache, ce); return NULL; + } bh = NULL; EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index b0597a539fc54..58ce751da92bf 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -889,7 +889,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, cp_blocks = le32_to_cpu(cp_block->cp_pack_total_block_count); - if (cp_blocks > sbi->blocks_per_seg || cp_blocks <= F2FS_CP_PACKS) { + if (cp_blocks > BLKS_PER_SEG(sbi) || cp_blocks <= F2FS_CP_PACKS) { f2fs_warn(sbi, "invalid cp_pack_total_block_count:%u", le32_to_cpu(cp_block->cp_pack_total_block_count)); goto invalid_cp; @@ -1324,7 +1324,7 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (cpc->reason & CP_UMOUNT) { if (le32_to_cpu(ckpt->cp_pack_total_block_count) + - NM_I(sbi)->nat_bits_blocks > sbi->blocks_per_seg) { + NM_I(sbi)->nat_bits_blocks > BLKS_PER_SEG(sbi)) { clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG); f2fs_notice(sbi, "Disable nat_bits due to no space"); } else if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG) && @@ -1527,7 +1527,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) cp_ver |= ((__u64)crc32 << 32); *(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver); - blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks; + blk = start_blk + BLKS_PER_SEG(sbi) - nm_i->nat_bits_blocks; for (i = 0; i < nm_i->nat_bits_blocks; i++) f2fs_update_meta_page(sbi, nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), blk + i); @@ -1587,8 +1587,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) */ if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi) || f2fs_sb_has_compression(sbi)) - invalidate_mapping_pages(META_MAPPING(sbi), - MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1); + f2fs_bug_on(sbi, + invalidate_inode_pages2_range(META_MAPPING(sbi), + MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1)); f2fs_release_ino_entry(sbi, false); @@ -1730,9 +1731,9 @@ void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi) im->ino_num = 0; } - sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS - + sbi->max_orphans = (BLKS_PER_SEG(sbi) - F2FS_CP_PACKS - NR_CURSEG_PERSIST_TYPE - __cp_payload(sbi)) * - F2FS_ORPHANS_PER_BLOCK; + F2FS_ORPHANS_PER_BLOCK; } int __init f2fs_create_checkpoint_caches(void) diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 531517dac0796..a9e41d91f2743 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -198,8 +198,8 @@ static int lzo_compress_pages(struct compress_ctx *cc) ret = lzo1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata, &cc->clen, cc->private); if (ret != LZO_E_OK) { - printk_ratelimited("%sF2FS-fs (%s): lzo compress failed, ret:%d\n", - KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, ret); + f2fs_err_ratelimited(F2FS_I_SB(cc->inode), + "lzo compress failed, ret:%d", ret); return -EIO; } return 0; @@ -212,17 +212,15 @@ static int lzo_decompress_pages(struct decompress_io_ctx *dic) ret = lzo1x_decompress_safe(dic->cbuf->cdata, dic->clen, dic->rbuf, &dic->rlen); if (ret != LZO_E_OK) { - printk_ratelimited("%sF2FS-fs (%s): lzo decompress failed, ret:%d\n", - KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret); + f2fs_err_ratelimited(F2FS_I_SB(dic->inode), + "lzo decompress failed, ret:%d", ret); return -EIO; } if (dic->rlen != PAGE_SIZE << dic->log_cluster_size) { - printk_ratelimited("%sF2FS-fs (%s): lzo invalid rlen:%zu, " - "expected:%lu\n", KERN_ERR, - F2FS_I_SB(dic->inode)->sb->s_id, - dic->rlen, - PAGE_SIZE << dic->log_cluster_size); + f2fs_err_ratelimited(F2FS_I_SB(dic->inode), + "lzo invalid rlen:%zu, expected:%lu", + dic->rlen, PAGE_SIZE << dic->log_cluster_size); return -EIO; } return 0; @@ -294,16 +292,15 @@ static int lz4_decompress_pages(struct decompress_io_ctx *dic) ret = LZ4_decompress_safe(dic->cbuf->cdata, dic->rbuf, dic->clen, dic->rlen); if (ret < 0) { - printk_ratelimited("%sF2FS-fs (%s): lz4 decompress failed, ret:%d\n", - KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret); + f2fs_err_ratelimited(F2FS_I_SB(dic->inode), + "lz4 decompress failed, ret:%d", ret); return -EIO; } if (ret != PAGE_SIZE << dic->log_cluster_size) { - printk_ratelimited("%sF2FS-fs (%s): lz4 invalid ret:%d, " - "expected:%lu\n", KERN_ERR, - F2FS_I_SB(dic->inode)->sb->s_id, ret, - PAGE_SIZE << dic->log_cluster_size); + f2fs_err_ratelimited(F2FS_I_SB(dic->inode), + "lz4 invalid ret:%d, expected:%lu", + ret, PAGE_SIZE << dic->log_cluster_size); return -EIO; } return 0; @@ -350,9 +347,8 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc) stream = zstd_init_cstream(¶ms, 0, workspace, workspace_size); if (!stream) { - printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_cstream failed\n", - KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, - __func__); + f2fs_err_ratelimited(F2FS_I_SB(cc->inode), + "%s zstd_init_cstream failed", __func__); kvfree(workspace); return -EIO; } @@ -390,16 +386,16 @@ static int zstd_compress_pages(struct compress_ctx *cc) ret = zstd_compress_stream(stream, &outbuf, &inbuf); if (zstd_is_error(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s zstd_compress_stream failed, ret: %d\n", - KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, + f2fs_err_ratelimited(F2FS_I_SB(cc->inode), + "%s zstd_compress_stream failed, ret: %d", __func__, zstd_get_error_code(ret)); return -EIO; } ret = zstd_end_stream(stream, &outbuf); if (zstd_is_error(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s zstd_end_stream returned %d\n", - KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, + f2fs_err_ratelimited(F2FS_I_SB(cc->inode), + "%s zstd_end_stream returned %d", __func__, zstd_get_error_code(ret)); return -EIO; } @@ -432,9 +428,8 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic) stream = zstd_init_dstream(max_window_size, workspace, workspace_size); if (!stream) { - printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_dstream failed\n", - KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, - __func__); + f2fs_err_ratelimited(F2FS_I_SB(dic->inode), + "%s zstd_init_dstream failed", __func__); kvfree(workspace); return -EIO; } @@ -469,16 +464,15 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic) ret = zstd_decompress_stream(stream, &outbuf, &inbuf); if (zstd_is_error(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s zstd_decompress_stream failed, ret: %d\n", - KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, + f2fs_err_ratelimited(F2FS_I_SB(dic->inode), + "%s zstd_decompress_stream failed, ret: %d", __func__, zstd_get_error_code(ret)); return -EIO; } if (dic->rlen != outbuf.pos) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD invalid rlen:%zu, " - "expected:%lu\n", KERN_ERR, - F2FS_I_SB(dic->inode)->sb->s_id, + f2fs_err_ratelimited(F2FS_I_SB(dic->inode), + "%s ZSTD invalid rlen:%zu, expected:%lu", __func__, dic->rlen, PAGE_SIZE << dic->log_cluster_size); return -EIO; @@ -512,8 +506,8 @@ static int lzorle_compress_pages(struct compress_ctx *cc) ret = lzorle1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata, &cc->clen, cc->private); if (ret != LZO_E_OK) { - printk_ratelimited("%sF2FS-fs (%s): lzo-rle compress failed, ret:%d\n", - KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, ret); + f2fs_err_ratelimited(F2FS_I_SB(cc->inode), + "lzo-rle compress failed, ret:%d", ret); return -EIO; } return 0; @@ -780,9 +774,9 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task) if (provided != calculated) { if (!is_inode_flag_set(dic->inode, FI_COMPRESS_CORRUPT)) { set_inode_flag(dic->inode, FI_COMPRESS_CORRUPT); - printk_ratelimited( - "%sF2FS-fs (%s): checksum invalid, nid = %lu, %x vs %x", - KERN_INFO, sbi->sb->s_id, dic->inode->i_ino, + f2fs_info_ratelimited(sbi, + "checksum invalid, nid = %lu, %x vs %x", + dic->inode->i_ino, provided, calculated); } set_sbi_flag(sbi, SBI_NEED_FSCK); @@ -1418,6 +1412,8 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) struct f2fs_sb_info *sbi = bio->bi_private; struct compress_io_ctx *cic = (struct compress_io_ctx *)page_private(page); + enum count_type type = WB_DATA_TYPE(page, + f2fs_is_compressed_page(page)); int i; if (unlikely(bio->bi_status)) @@ -1425,7 +1421,7 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) f2fs_compress_free_page(page); - dec_page_count(sbi, F2FS_WB_DATA); + dec_page_count(sbi, type); if (atomic_dec_return(&cic->pending_pages)) return; @@ -1441,12 +1437,14 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) } static int f2fs_write_raw_pages(struct compress_ctx *cc, - int *submitted, + int *submitted_p, struct writeback_control *wbc, enum iostat_type io_type) { struct address_space *mapping = cc->inode->i_mapping; - int _submitted, compr_blocks, ret, i; + struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + int submitted, compr_blocks, i; + int ret = 0; compr_blocks = f2fs_compressed_blocks(cc); @@ -1461,6 +1459,10 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc, if (compr_blocks < 0) return compr_blocks; + /* overwrite compressed cluster w/ normal cluster */ + if (compr_blocks > 0) + f2fs_lock_op(sbi); + for (i = 0; i < cc->cluster_size; i++) { if (!cc->rpages[i]) continue; @@ -1485,7 +1487,7 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc, if (!clear_page_dirty_for_io(cc->rpages[i])) goto continue_unlock; - ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted, + ret = f2fs_write_single_data_page(cc->rpages[i], &submitted, NULL, NULL, wbc, io_type, compr_blocks, false); if (ret) { @@ -1493,26 +1495,29 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc, unlock_page(cc->rpages[i]); ret = 0; } else if (ret == -EAGAIN) { + ret = 0; /* * for quota file, just redirty left pages to * avoid deadlock caused by cluster update race * from foreground operation. */ if (IS_NOQUOTA(cc->inode)) - return 0; - ret = 0; + goto out; f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); goto retry_write; } - return ret; + goto out; } - *submitted += _submitted; + *submitted_p += submitted; } - f2fs_balance_fs(F2FS_M_SB(mapping), true); +out: + if (compr_blocks > 0) + f2fs_unlock_op(sbi); - return 0; + f2fs_balance_fs(sbi, true); + return ret; } int f2fs_write_multi_pages(struct compress_ctx *cc, @@ -1806,16 +1811,18 @@ void f2fs_put_page_dic(struct page *page, bool in_task) * check whether cluster blocks are contiguous, and add extent cache entry * only if cluster blocks are logically and physically contiguous. */ -unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) +unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, + unsigned int ofs_in_node) { - bool compressed = f2fs_data_blkaddr(dn) == COMPRESS_ADDR; + bool compressed = data_blkaddr(dn->inode, dn->node_page, + ofs_in_node) == COMPRESS_ADDR; int i = compressed ? 1 : 0; block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + i); + ofs_in_node + i); for (i += 1; i < F2FS_I(dn->inode)->i_cluster_size; i++) { block_t blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + i); + ofs_in_node + i); if (!__is_valid_data_blkaddr(blkaddr)) break; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 26e317696b338..6456f539c4e97 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -48,7 +48,7 @@ void f2fs_destroy_bioset(void) bioset_exit(&f2fs_bioset); } -static bool __is_cp_guaranteed(struct page *page) +bool f2fs_is_cp_guaranteed(struct page *page) { struct address_space *mapping = page->mapping; struct inode *inode; @@ -65,8 +65,6 @@ static bool __is_cp_guaranteed(struct page *page) S_ISDIR(inode->i_mode)) return true; - if (f2fs_is_compressed_page(page)) - return false; if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) || page_private_gcing(page)) return true; @@ -338,18 +336,7 @@ static void f2fs_write_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; - enum count_type type = WB_DATA_TYPE(page); - - if (page_private_dummy(page)) { - clear_page_private_dummy(page); - unlock_page(page); - mempool_free(page, sbi->write_io_dummy); - - if (unlikely(bio->bi_status)) - f2fs_stop_checkpoint(sbi, true, - STOP_CP_REASON_WRITE_FAIL); - continue; - } + enum count_type type = WB_DATA_TYPE(page, false); fscrypt_finalize_bounce_page(&page); @@ -524,50 +511,13 @@ void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio, submit_bio(bio); } -static void f2fs_align_write_bio(struct f2fs_sb_info *sbi, struct bio *bio) -{ - unsigned int start = - (bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS) % F2FS_IO_SIZE(sbi); - - if (start == 0) - return; - - /* fill dummy pages */ - for (; start < F2FS_IO_SIZE(sbi); start++) { - struct page *page = - mempool_alloc(sbi->write_io_dummy, - GFP_NOIO | __GFP_NOFAIL); - f2fs_bug_on(sbi, !page); - - lock_page(page); - - zero_user_segment(page, 0, PAGE_SIZE); - set_page_private_dummy(page); - - if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) - f2fs_bug_on(sbi, 1); - } -} - static void f2fs_submit_write_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type) { WARN_ON_ONCE(is_read_io(bio_op(bio))); - if (type == DATA || type == NODE) { - if (f2fs_lfs_mode(sbi) && current->plug) - blk_finish_plug(current->plug); - - if (F2FS_IO_ALIGNED(sbi)) { - f2fs_align_write_bio(sbi, bio); - /* - * In the NODE case, we lose next block address chain. - * So, we need to do checkpoint in f2fs_sync_file. - */ - if (type == NODE) - set_sbi_flag(sbi, SBI_NEED_CP); - } - } + if (f2fs_lfs_mode(sbi) && current->plug && PAGE_TYPE_ON_MAIN(type)) + blk_finish_plug(current->plug); trace_f2fs_submit_write_bio(sbi->sb, type, bio); iostat_update_submit_ctx(bio, type); @@ -762,7 +712,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); inc_page_count(fio->sbi, is_read_io(fio->op) ? - __read_io_type(page) : WB_DATA_TYPE(fio->page)); + __read_io_type(page) : WB_DATA_TYPE(fio->page, false)); if (is_read_io(bio_op(bio))) f2fs_submit_read_bio(fio->sbi, bio, fio->type); @@ -796,16 +746,6 @@ static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio, block_t last_blkaddr, block_t cur_blkaddr) { - if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE)) { - unsigned int filled_blocks = - F2FS_BYTES_TO_BLK(bio->bi_iter.bi_size); - unsigned int io_size = F2FS_IO_SIZE(sbi); - unsigned int left_vecs = bio->bi_max_vecs - bio->bi_vcnt; - - /* IOs in bio is aligned and left space of vectors is not enough */ - if (!(filled_blocks % io_size) && left_vecs < io_size) - return false; - } if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr)) return false; return io_type_is_mergeable(io, fio); @@ -973,7 +913,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) if (fio->io_wbc) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); - inc_page_count(fio->sbi, WB_DATA_TYPE(page)); + inc_page_count(fio->sbi, WB_DATA_TYPE(page, false)); *fio->last_block = fio->new_blkaddr; *fio->bio = bio; @@ -1007,11 +947,12 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; struct page *bio_page; + enum count_type type; f2fs_bug_on(sbi, is_read_io(fio->op)); f2fs_down_write(&io->io_rwsem); - +next: #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && btype < META && io->zone_pending_bio) { wait_for_completion_io(&io->zone_wait); @@ -1021,7 +962,6 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) } #endif -next: if (fio->in_list) { spin_lock(&io->io_lock); if (list_empty(&io->io_list)) { @@ -1046,7 +986,8 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) /* set submitted = true as a return value */ fio->submitted = 1; - inc_page_count(sbi, WB_DATA_TYPE(bio_page)); + type = WB_DATA_TYPE(bio_page, fio->compressed_page); + inc_page_count(sbi, type); if (io->bio && (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio, @@ -1056,13 +997,6 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) __submit_merged_bio(io); alloc_new: if (io->bio == NULL) { - if (F2FS_IO_ALIGNED(sbi) && - (fio->type == DATA || fio->type == NODE) && - fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { - dec_page_count(sbi, WB_DATA_TYPE(bio_page)); - fio->retry = 1; - goto skip; - } io->bio = __bio_alloc(fio, BIO_MAX_VECS); f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host, bio_page->index, fio, GFP_NOIO); @@ -1080,10 +1014,6 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) io->last_block_in_bio = fio->new_blkaddr; trace_f2fs_submit_page_write(fio->page, fio); -skip: - if (fio->in_list) - goto next; -out: #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && btype < META && is_end_zone_blkaddr(sbi, fio->new_blkaddr)) { @@ -1096,6 +1026,9 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) __submit_merged_bio(io); } #endif + if (fio->in_list) + goto next; +out: if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || !f2fs_is_checkpoint_ready(sbi)) __submit_merged_bio(io); @@ -1218,7 +1151,8 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) + err = inc_valid_block_count(sbi, dn->inode, &count, true); + if (unlikely(err)) return err; trace_f2fs_reserve_new_blocks(dn->inode, dn->nid, @@ -1475,7 +1409,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) dn->data_blkaddr = f2fs_data_blkaddr(dn); if (dn->data_blkaddr == NULL_ADDR) { - err = inc_valid_block_count(sbi, dn->inode, &count); + err = inc_valid_block_count(sbi, dn->inode, &count, true); if (unlikely(err)) return err; } @@ -2668,8 +2602,6 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) if (fio) { if (page_private_gcing(fio->page)) return true; - if (page_private_dummy(fio->page)) - return true; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) return true; @@ -2838,7 +2770,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .encrypted_page = NULL, .submitted = 0, .compr_blocks = compr_blocks, - .need_lock = LOCK_RETRY, + .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY, .post_read = f2fs_post_read_required(inode) ? 1 : 0, .io_type = io_type, .io_wbc = wbc, @@ -2919,6 +2851,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, if (err == -EAGAIN) { err = f2fs_do_write_data_page(&fio); if (err == -EAGAIN) { + f2fs_bug_on(sbi, compr_blocks); fio.need_lock = LOCK_REQ; err = f2fs_do_write_data_page(&fio); } @@ -3906,25 +3839,34 @@ static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk, unsigned int blkofs; unsigned int blk_per_sec = BLKS_PER_SEC(sbi); unsigned int secidx = start_blk / blk_per_sec; - unsigned int end_sec = secidx + blkcnt / blk_per_sec; + unsigned int end_sec; int ret = 0; + if (!blkcnt) + return 0; + end_sec = secidx + (blkcnt - 1) / blk_per_sec; + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); set_inode_flag(inode, FI_ALIGNED_WRITE); set_inode_flag(inode, FI_OPU_WRITE); - for (; secidx < end_sec; secidx++) { + for (; secidx <= end_sec; secidx++) { + unsigned int blkofs_end = secidx == end_sec ? + (blkcnt - 1) % blk_per_sec : blk_per_sec - 1; + f2fs_down_write(&sbi->pin_sem); - f2fs_lock_op(sbi); - f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false); - f2fs_unlock_op(sbi); + ret = f2fs_allocate_pinning_section(sbi); + if (ret) { + f2fs_up_write(&sbi->pin_sem); + break; + } set_inode_flag(inode, FI_SKIP_WRITES); - for (blkofs = 0; blkofs < blk_per_sec; blkofs++) { + for (blkofs = 0; blkofs <= blkofs_end; blkofs++) { struct page *page; unsigned int blkidx = secidx * blk_per_sec + blkofs; @@ -3966,15 +3908,14 @@ static int check_swap_activate(struct swap_info_struct *sis, struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - sector_t cur_lblock; - sector_t last_lblock; - sector_t pblock; - sector_t lowest_pblock = -1; - sector_t highest_pblock = 0; + block_t cur_lblock; + block_t last_lblock; + block_t pblock; + block_t lowest_pblock = -1; + block_t highest_pblock = 0; int nr_extents = 0; - unsigned long nr_pblocks; + unsigned int nr_pblocks; unsigned int blks_per_sec = BLKS_PER_SEC(sbi); - unsigned int sec_blks_mask = BLKS_PER_SEC(sbi) - 1; unsigned int not_aligned = 0; int ret = 0; @@ -4012,28 +3953,35 @@ static int check_swap_activate(struct swap_info_struct *sis, pblock = map.m_pblk; nr_pblocks = map.m_len; - if ((pblock - SM_I(sbi)->main_blkaddr) & sec_blks_mask || - nr_pblocks & sec_blks_mask) { + if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec || + nr_pblocks % blks_per_sec || + !f2fs_valid_pinned_area(sbi, pblock)) { + bool last_extent = false; + not_aligned++; nr_pblocks = roundup(nr_pblocks, blks_per_sec); if (cur_lblock + nr_pblocks > sis->max) nr_pblocks -= blks_per_sec; + /* this extent is last one */ if (!nr_pblocks) { - /* this extent is last one */ - nr_pblocks = map.m_len; - f2fs_warn(sbi, "Swapfile: last extent is not aligned to section"); - goto next; + nr_pblocks = last_lblock - cur_lblock; + last_extent = true; } ret = f2fs_migrate_blocks(inode, cur_lblock, nr_pblocks); - if (ret) + if (ret) { + if (ret == -ENOENT) + ret = -EINVAL; goto out; - goto retry; + } + + if (!last_extent) + goto retry; } -next: + if (cur_lblock + nr_pblocks >= sis->max) nr_pblocks = sis->max - cur_lblock; @@ -4071,17 +4019,17 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, sector_t *span) { struct inode *inode = file_inode(file); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int ret; if (!S_ISREG(inode->i_mode)) return -EINVAL; - if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + if (f2fs_readonly(sbi->sb)) return -EROFS; - if (f2fs_lfs_mode(F2FS_I_SB(inode))) { - f2fs_err(F2FS_I_SB(inode), - "Swapfile not supported in LFS mode"); + if (f2fs_lfs_mode(sbi) && !f2fs_sb_has_blkzoned(sbi)) { + f2fs_err(sbi, "Swapfile not supported in LFS mode"); return -EINVAL; } @@ -4094,13 +4042,17 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, f2fs_precache_extents(inode); + ret = filemap_fdatawrite(inode->i_mapping); + if (ret < 0) + return ret; + ret = check_swap_activate(sis, file, span); if (ret < 0) return ret; stat_inc_swapfile_inode(inode); set_inode_flag(inode, FI_PIN_FILE); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + f2fs_update_time(sbi, REQ_TIME); return ret; } @@ -4244,7 +4196,7 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, if (WARN_ON_ONCE(map.m_pblk == COMPRESS_ADDR)) return -EINVAL; - if (map.m_pblk != NULL_ADDR) { + if (map.m_flags & F2FS_MAP_MAPPED) { iomap->length = blks_to_bytes(inode, map.m_len); iomap->type = IOMAP_MAPPED; iomap->flags |= IOMAP_F_MERGED; diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index fdbf994f12718..0d02224b99b72 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -41,7 +41,7 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi) total_vblocks = 0; blks_per_sec = CAP_BLKS_PER_SEC(sbi); hblks_per_sec = blks_per_sec / 2; - for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { + for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) { vblocks = get_valid_blocks(sbi, segno, true); dist = abs(vblocks - hblks_per_sec); bimodal += dist * dist; @@ -135,7 +135,7 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->cur_ckpt_time = sbi->cprc_info.cur_time; si->peak_ckpt_time = sbi->cprc_info.peak_time; spin_unlock(&sbi->cprc_info.stat_lock); - si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg; + si->total_count = (int)sbi->user_block_count / BLKS_PER_SEG(sbi); si->rsvd_segs = reserved_segments(sbi); si->overp_segs = overprovision_segments(sbi); si->valid_count = valid_user_blocks(sbi); @@ -208,7 +208,7 @@ static void update_general_status(struct f2fs_sb_info *sbi) if (!blks) continue; - if (blks == sbi->blocks_per_seg) + if (blks == BLKS_PER_SEG(sbi)) si->full_seg[type]++; else si->dirty_seg[type]++; diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 042593aed1ec0..02c9355176d3b 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -830,13 +830,14 @@ int f2fs_do_add_link(struct inode *dir, const struct qstr *name, return err; } -int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) +int f2fs_do_tmpfile(struct inode *inode, struct inode *dir, + struct f2fs_filename *fname) { struct page *page; int err = 0; f2fs_down_write(&F2FS_I(inode)->i_sem); - page = f2fs_init_inode_metadata(inode, dir, NULL, NULL); + page = f2fs_init_inode_metadata(inode, dir, fname, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; @@ -995,9 +996,8 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, de = &d->dentry[bit_pos]; if (de->name_len == 0) { if (found_valid_dirent || !bit_pos) { - printk_ratelimited( - "%sF2FS-fs (%s): invalid namelen(0), ino:%u, run fsck to fix.", - KERN_WARNING, sbi->sb->s_id, + f2fs_warn_ratelimited(sbi, + "invalid namelen(0), ino:%u, run fsck to fix.", le32_to_cpu(de->ino)); set_sbi_flag(sbi, SBI_NEED_FSCK); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 65294e3b0bef8..93303ad29271f 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -69,12 +69,17 @@ enum { struct f2fs_fault_info { atomic_t inject_ops; - unsigned int inject_rate; + int inject_rate; unsigned int inject_type; }; extern const char *f2fs_fault_name[FAULT_MAX]; #define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) + +/* maximum retry count for injected failure */ +#define DEFAULT_FAILURE_RETRY_COUNT 8 +#else +#define DEFAULT_FAILURE_RETRY_COUNT 1 #endif /* @@ -142,7 +147,6 @@ struct f2fs_rwsem { struct f2fs_mount_info { unsigned int opt; - int write_io_size_bits; /* Write IO size bits */ block_t root_reserved_blocks; /* root reserved blocks */ kuid_t s_resuid; /* reserved blocks for uid */ kgid_t s_resgid; /* reserved blocks for gid */ @@ -829,7 +833,7 @@ struct f2fs_inode_info { spinlock_t i_size_lock; /* protect last_disk_size */ #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; /* quota space reservation, managed internally by quota code */ qsize_t i_reserved_quota; @@ -1080,7 +1084,8 @@ struct f2fs_sm_info { * f2fs monitors the number of several block types such as on-writeback, * dirty dentry blocks, dirty node blocks, and dirty meta blocks. */ -#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) +#define WB_DATA_TYPE(p, f) \ + (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) enum count_type { F2FS_DIRTY_DENTS, F2FS_DIRTY_DATA, @@ -1110,6 +1115,7 @@ enum count_type { * ... Only can be used with META. */ #define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type)) +#define PAGE_TYPE_ON_MAIN(type) ((type) == DATA || (type) == NODE) enum page_type { DATA = 0, NODE = 1, /* should not change this */ @@ -1204,7 +1210,6 @@ struct f2fs_io_info { unsigned int submitted:1; /* indicate IO submission */ unsigned int in_list:1; /* indicate fio is in io_list */ unsigned int is_por:1; /* indicate IO is from recovery or not */ - unsigned int retry:1; /* need to reallocate block address */ unsigned int encrypted:1; /* indicate file is encrypted */ unsigned int post_read:1; /* require post read */ enum iostat_type io_type; /* io type */ @@ -1406,18 +1411,16 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr); * Layout A: lowest bit should be 1 * | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | * bit 0 PAGE_PRIVATE_NOT_POINTER - * bit 1 PAGE_PRIVATE_DUMMY_WRITE - * bit 2 PAGE_PRIVATE_ONGOING_MIGRATION - * bit 3 PAGE_PRIVATE_INLINE_INODE - * bit 4 PAGE_PRIVATE_REF_RESOURCE - * bit 5- f2fs private data + * bit 1 PAGE_PRIVATE_ONGOING_MIGRATION + * bit 2 PAGE_PRIVATE_INLINE_INODE + * bit 3 PAGE_PRIVATE_REF_RESOURCE + * bit 4- f2fs private data * * Layout B: lowest bit should be 0 * page.private is a wrapped pointer. */ enum { PAGE_PRIVATE_NOT_POINTER, /* private contains non-pointer data */ - PAGE_PRIVATE_DUMMY_WRITE, /* data page for padding aligned IO */ PAGE_PRIVATE_ONGOING_MIGRATION, /* data page which is on-going migrating */ PAGE_PRIVATE_INLINE_INODE, /* inode page contains inline data */ PAGE_PRIVATE_REF_RESOURCE, /* dirty page has referenced resources */ @@ -1564,7 +1567,6 @@ struct f2fs_sb_info { struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ /* keep migration IO order for LFS mode */ struct f2fs_rwsem io_order_lock; - mempool_t *write_io_dummy; /* Dummy pages */ pgoff_t page_eio_ofs[NR_PAGE_TYPE]; /* EIO page offset */ int page_eio_cnt[NR_PAGE_TYPE]; /* EIO count */ @@ -1810,6 +1812,35 @@ struct f2fs_sb_info { #endif }; +/* Definitions to access f2fs_sb_info */ +#define BLKS_PER_SEG(sbi) \ + ((sbi)->blocks_per_seg) +#define BLKS_PER_SEC(sbi) \ + ((sbi)->segs_per_sec << (sbi)->log_blocks_per_seg) +#define SEGS_PER_SEC(sbi) \ + ((sbi)->segs_per_sec) + +__printf(3, 4) +void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate, const char *fmt, ...); + +#define f2fs_err(sbi, fmt, ...) \ + f2fs_printk(sbi, false, KERN_ERR fmt, ##__VA_ARGS__) +#define f2fs_warn(sbi, fmt, ...) \ + f2fs_printk(sbi, false, KERN_WARNING fmt, ##__VA_ARGS__) +#define f2fs_notice(sbi, fmt, ...) \ + f2fs_printk(sbi, false, KERN_NOTICE fmt, ##__VA_ARGS__) +#define f2fs_info(sbi, fmt, ...) \ + f2fs_printk(sbi, false, KERN_INFO fmt, ##__VA_ARGS__) +#define f2fs_debug(sbi, fmt, ...) \ + f2fs_printk(sbi, false, KERN_DEBUG fmt, ##__VA_ARGS__) + +#define f2fs_err_ratelimited(sbi, fmt, ...) \ + f2fs_printk(sbi, true, KERN_ERR fmt, ##__VA_ARGS__) +#define f2fs_warn_ratelimited(sbi, fmt, ...) \ + f2fs_printk(sbi, true, KERN_WARNING fmt, ##__VA_ARGS__) +#define f2fs_info_ratelimited(sbi, fmt, ...) \ + f2fs_printk(sbi, true, KERN_INFO fmt, ##__VA_ARGS__) + #ifdef CONFIG_F2FS_FAULT_INJECTION #define time_to_inject(sbi, type) __time_to_inject(sbi, type, __func__, \ __builtin_return_address(0)) @@ -1827,9 +1858,8 @@ static inline bool __time_to_inject(struct f2fs_sb_info *sbi, int type, atomic_inc(&ffi->inject_ops); if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) { atomic_set(&ffi->inject_ops, 0); - printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n", - KERN_INFO, sbi->sb->s_id, f2fs_fault_name[type], - func, parent_func); + f2fs_info_ratelimited(sbi, "inject %s in %s of %pS", + f2fs_fault_name[type], func, parent_func); return true; } return false; @@ -2249,11 +2279,32 @@ static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, return false; } +static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi, + struct inode *inode, bool cap) +{ + block_t avail_user_block_count; + + avail_user_block_count = sbi->user_block_count - + sbi->current_reserved_blocks; + + if (!__allow_reserved_blocks(sbi, inode, cap)) + avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; + + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (avail_user_block_count > sbi->unusable_block_count) + avail_user_block_count -= sbi->unusable_block_count; + else + avail_user_block_count = 0; + } + + return avail_user_block_count; +} + static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, - struct inode *inode, blkcnt_t *count) + struct inode *inode, blkcnt_t *count, bool partial) { - blkcnt_t diff = 0, release = 0; + long long diff = 0, release = 0; block_t avail_user_block_count; int ret; @@ -2273,35 +2324,27 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, percpu_counter_add(&sbi->alloc_valid_block_count, (*count)); spin_lock(&sbi->stat_lock); - sbi->total_valid_block_count += (block_t)(*count); - avail_user_block_count = sbi->user_block_count - - sbi->current_reserved_blocks; - - if (!__allow_reserved_blocks(sbi, inode, true)) - avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; - if (F2FS_IO_ALIGNED(sbi)) - avail_user_block_count -= sbi->blocks_per_seg * - SM_I(sbi)->additional_reserved_segments; - - if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { - if (avail_user_block_count > sbi->unusable_block_count) - avail_user_block_count -= sbi->unusable_block_count; - else - avail_user_block_count = 0; - } - if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { - diff = sbi->total_valid_block_count - avail_user_block_count; + avail_user_block_count = get_available_block_count(sbi, inode, true); + diff = (long long)sbi->total_valid_block_count + *count - + avail_user_block_count; + if (unlikely(diff > 0)) { + if (!partial) { + spin_unlock(&sbi->stat_lock); + release = *count; + goto enospc; + } if (diff > *count) diff = *count; *count -= diff; release = diff; - sbi->total_valid_block_count -= diff; if (!*count) { spin_unlock(&sbi->stat_lock); goto enospc; } } + sbi->total_valid_block_count += (block_t)(*count); + spin_unlock(&sbi->stat_lock); if (unlikely(release)) { @@ -2318,20 +2361,6 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, return -ENOSPC; } -__printf(2, 3) -void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...); - -#define f2fs_err(sbi, fmt, ...) \ - f2fs_printk(sbi, KERN_ERR fmt, ##__VA_ARGS__) -#define f2fs_warn(sbi, fmt, ...) \ - f2fs_printk(sbi, KERN_WARNING fmt, ##__VA_ARGS__) -#define f2fs_notice(sbi, fmt, ...) \ - f2fs_printk(sbi, KERN_NOTICE fmt, ##__VA_ARGS__) -#define f2fs_info(sbi, fmt, ...) \ - f2fs_printk(sbi, KERN_INFO fmt, ##__VA_ARGS__) -#define f2fs_debug(sbi, fmt, ...) \ - f2fs_printk(sbi, KERN_DEBUG fmt, ##__VA_ARGS__) - #define PAGE_PRIVATE_GET_FUNC(name, flagname) \ static inline bool page_private_##name(struct page *page) \ { \ @@ -2360,17 +2389,14 @@ static inline void clear_page_private_##name(struct page *page) \ PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER); PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE); PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION); -PAGE_PRIVATE_GET_FUNC(dummy, DUMMY_WRITE); PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE); PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE); PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION); -PAGE_PRIVATE_SET_FUNC(dummy, DUMMY_WRITE); PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE); PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE); PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION); -PAGE_PRIVATE_CLEAR_FUNC(dummy, DUMMY_WRITE); static inline unsigned long get_page_private_data(struct page *page) { @@ -2504,11 +2530,8 @@ static inline int get_dirty_pages(struct inode *inode) static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type) { - unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg; - unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >> - sbi->log_blocks_per_seg; - - return segs / sbi->segs_per_sec; + return div_u64(get_pages(sbi, block_type) + BLKS_PER_SEC(sbi) - 1, + BLKS_PER_SEC(sbi)); } static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi) @@ -2572,7 +2595,7 @@ static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi) block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); if (sbi->cur_cp_pack == 2) - start_addr += sbi->blocks_per_seg; + start_addr += BLKS_PER_SEG(sbi); return start_addr; } @@ -2581,7 +2604,7 @@ static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi) block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); if (sbi->cur_cp_pack == 1) - start_addr += sbi->blocks_per_seg; + start_addr += BLKS_PER_SEG(sbi); return start_addr; } @@ -2600,7 +2623,8 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, struct inode *inode, bool is_inode) { block_t valid_block_count; - unsigned int valid_node_count, user_block_count; + unsigned int valid_node_count; + unsigned int avail_user_block_count; int err; if (is_inode) { @@ -2620,21 +2644,10 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); - valid_block_count = sbi->total_valid_block_count + - sbi->current_reserved_blocks + 1; - - if (!__allow_reserved_blocks(sbi, inode, false)) - valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; - - if (F2FS_IO_ALIGNED(sbi)) - valid_block_count += sbi->blocks_per_seg * - SM_I(sbi)->additional_reserved_segments; + valid_block_count = sbi->total_valid_block_count + 1; + avail_user_block_count = get_available_block_count(sbi, inode, false); - user_block_count = sbi->user_block_count; - if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) - user_block_count -= sbi->unusable_block_count; - - if (unlikely(valid_block_count > user_block_count)) { + if (unlikely(valid_block_count > avail_user_block_count)) { spin_unlock(&sbi->stat_lock); goto enospc; } @@ -3021,6 +3034,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, case FI_INLINE_DOTS: case FI_PIN_FILE: case FI_COMPRESS_RELEASED: + case FI_ATOMIC_COMMITTED: f2fs_mark_inode_dirty_sync(inode, true); } } @@ -3455,7 +3469,7 @@ static inline __le32 *get_dnode_addr(struct inode *inode, sizeof((f2fs_inode)->field)) \ <= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \ -#define __is_large_section(sbi) ((sbi)->segs_per_sec > 1) +#define __is_large_section(sbi) (SEGS_PER_SEC(sbi) > 1) #define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META) @@ -3464,11 +3478,9 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, static inline void verify_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { - if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) { + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.", blkaddr, type); - f2fs_bug_on(sbi, 1); - } } static inline bool __is_valid_data_blkaddr(block_t blkaddr) @@ -3570,7 +3582,8 @@ int f2fs_do_add_link(struct inode *dir, const struct qstr *name, struct inode *inode, nid_t ino, umode_t mode); void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, struct inode *dir, struct inode *inode); -int f2fs_do_tmpfile(struct inode *inode, struct inode *dir); +int f2fs_do_tmpfile(struct inode *inode, struct inode *dir, + struct f2fs_filename *fname); bool f2fs_empty_dir(struct inode *dir); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) @@ -3692,7 +3705,8 @@ void f2fs_get_new_segment(struct f2fs_sb_info *sbi, unsigned int *newseg, bool new_sec, int dir); void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, unsigned int start, unsigned int end); -void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force); +int f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force); +int f2fs_allocate_pinning_section(struct f2fs_sb_info *sbi); void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range); bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, @@ -3804,6 +3818,7 @@ void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi); */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); +bool f2fs_is_cp_guaranteed(struct page *page); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio, @@ -3867,6 +3882,9 @@ void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi); block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); +int f2fs_gc_range(struct f2fs_sb_info *sbi, + unsigned int start_seg, unsigned int end_seg, + bool dry_run, unsigned int dry_run_sections); int f2fs_resize_fs(struct file *filp, __u64 block_count); int __init f2fs_create_garbage_collection_cache(void); void f2fs_destroy_garbage_collection_cache(void); @@ -4287,7 +4305,8 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, bool in_task); void f2fs_put_page_dic(struct page *page, bool in_task); -unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn); +unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, + unsigned int ofs_in_node); int f2fs_init_compress_ctx(struct compress_ctx *cc); void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); void f2fs_init_compress_info(struct f2fs_sb_info *sbi); @@ -4344,7 +4363,8 @@ static inline void f2fs_put_page_dic(struct page *page, bool in_task) { WARN_ON_ONCE(1); } -static inline unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) { return 0; } +static inline unsigned int f2fs_cluster_blocks_are_contiguous( + struct dnode_of_data *dn, unsigned int ofs_in_node) { return 0; } static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; } static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { } @@ -4401,15 +4421,24 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); - if (!f2fs_compressed_file(inode)) + f2fs_down_write(&F2FS_I(inode)->i_sem); + + if (!f2fs_compressed_file(inode)) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return true; - if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) + } + if (f2fs_is_mmap_file(inode) || + (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return false; + } fi->i_flags &= ~F2FS_COMPR_FL; stat_dec_compr_inode(inode); clear_inode_flag(inode, FI_COMPRESSED_FILE); f2fs_mark_inode_dirty_sync(inode, true); + + f2fs_up_write(&F2FS_I(inode)->i_sem); return true; } @@ -4512,6 +4541,17 @@ static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi) return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS; } +static inline bool f2fs_valid_pinned_area(struct f2fs_sb_info *sbi, + block_t blkaddr) +{ + if (f2fs_sb_has_blkzoned(sbi)) { + int devi = f2fs_target_device_index(sbi, blkaddr); + + return !bdev_is_zoned(FDEV(devi).bdev); + } + return true; +} + static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi) { return F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW; @@ -4563,10 +4603,14 @@ static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) } #ifdef CONFIG_F2FS_FAULT_INJECTION -extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, - unsigned int type); +extern int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate, + unsigned long type); #else -#define f2fs_build_fault_attr(sbi, rate, type) do { } while (0) +static inline int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, + unsigned long rate, unsigned long type) +{ + return 0; +} #endif static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) @@ -4613,10 +4657,36 @@ static inline bool f2fs_is_readonly(struct f2fs_sb_info *sbi) return f2fs_sb_has_readonly(sbi) || f2fs_readonly(sbi->sb); } +static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi, + block_t blkaddr, unsigned int cnt) +{ + bool need_submit = false; + int i = 0; + + do { + struct page *page; + + page = find_get_page(META_MAPPING(sbi), blkaddr + i); + if (page) { + if (PageWriteback(page)) + need_submit = true; + f2fs_put_page(page, 0); + } + } while (++i < cnt && !need_submit); + + if (need_submit) + f2fs_submit_merged_write_cond(sbi, sbi->meta_inode, + NULL, 0, DATA); + + truncate_inode_pages_range(META_MAPPING(sbi), + F2FS_BLK_TO_BYTES((loff_t)blkaddr), + F2FS_BLK_END_BYTES((loff_t)(blkaddr + cnt - 1))); +} + static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi, block_t blkaddr) { - invalidate_mapping_pages(META_MAPPING(sbi), blkaddr, blkaddr); + f2fs_truncate_meta_inode_pages(sbi, blkaddr, 1); f2fs_invalidate_compress_page(sbi, blkaddr); } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index b58ab1157b7ef..24fe33fb9a1f3 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -39,6 +39,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); + vm_flags_t flags = vmf->vma->vm_flags; vm_fault_t ret; ret = filemap_fault(vmf); @@ -46,7 +47,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) f2fs_update_iostat(F2FS_I_SB(inode), inode, APP_MAPPED_READ_IO, F2FS_BLKSIZE); - trace_f2fs_filemap_fault(inode, vmf->pgoff, vmf->vma->vm_flags, ret); + trace_f2fs_filemap_fault(inode, vmf->pgoff, flags, ret); return ret; } @@ -818,8 +819,6 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw) */ if (f2fs_sb_has_blkzoned(sbi) && (rw == WRITE)) return true; - if (f2fs_lfs_mode(sbi) && rw == WRITE && F2FS_IO_ALIGNED(sbi)) - return true; if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) return true; @@ -936,9 +935,14 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, ATTR_GID | ATTR_TIMES_SET)))) return -EPERM; - if ((attr->ia_valid & ATTR_SIZE) && - !f2fs_is_compress_backend_ready(inode)) - return -EOPNOTSUPP; + if ((attr->ia_valid & ATTR_SIZE)) { + if (!f2fs_is_compress_backend_ready(inode)) + return -EOPNOTSUPP; + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) && + !IS_ALIGNED(attr->ia_size, + F2FS_BLK_TO_BYTES(F2FS_I(inode)->i_cluster_size))) + return -EINVAL; + } err = setattr_prepare(idmap, dentry, attr); if (err) @@ -1310,6 +1314,9 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, f2fs_put_page(psrc, 1); return PTR_ERR(pdst); } + + f2fs_wait_on_page_writeback(pdst, DATA, true, true); + memcpy_page(pdst, 0, psrc, 0, PAGE_SIZE); set_page_dirty(pdst); set_page_private_gcing(pdst); @@ -1731,9 +1738,11 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, f2fs_down_write(&sbi->pin_sem); - f2fs_lock_op(sbi); - f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false); - f2fs_unlock_op(sbi); + err = f2fs_allocate_pinning_section(sbi); + if (err) { + f2fs_up_write(&sbi->pin_sem); + goto out_err; + } map.m_seg_type = CURSEG_COLD_DATA_PINNED; err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_DIO); @@ -1799,15 +1808,6 @@ static long f2fs_fallocate(struct file *file, int mode, (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; - /* - * Pinned file should not support partial truncation since the block - * can be used by applications. - */ - if ((f2fs_compressed_file(inode) || f2fs_is_pinned_file(inode)) && - (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | - FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE))) - return -EOPNOTSUPP; - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)) @@ -1815,6 +1815,17 @@ static long f2fs_fallocate(struct file *file, int mode, inode_lock(inode); + /* + * Pinned file should not support partial truncation since the block + * can be used by applications. + */ + if ((f2fs_compressed_file(inode) || f2fs_is_pinned_file(inode)) && + (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | + FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE))) { + ret = -EOPNOTSUPP; + goto out; + } + ret = file_modified(file); if (ret) goto out; @@ -2578,7 +2589,6 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, .m_may_create = false }; struct extent_info ei = {}; pgoff_t pg_start, pg_end, next_pgofs; - unsigned int blk_per_seg = sbi->blocks_per_seg; unsigned int total = 0, sec_num; block_t blk_end = 0; bool fragmented = false; @@ -2687,7 +2697,8 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, set_inode_flag(inode, FI_SKIP_WRITES); idx = map.m_lblk; - while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) { + while (idx < map.m_lblk + map.m_len && + cnt < BLKS_PER_SEG(sbi)) { struct page *page; page = f2fs_get_lock_data_page(inode, idx, true); @@ -2707,7 +2718,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, map.m_lblk = idx; check: - if (map.m_lblk < pg_end && cnt < blk_per_seg) + if (map.m_lblk < pg_end && cnt < BLKS_PER_SEG(sbi)) goto do_map; clear_inode_flag(inode, FI_SKIP_WRITES); @@ -2813,7 +2824,8 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, goto out; } - if (f2fs_compressed_file(src) || f2fs_compressed_file(dst)) { + if (f2fs_compressed_file(src) || f2fs_compressed_file(dst) || + f2fs_is_pinned_file(src) || f2fs_is_pinned_file(dst)) { ret = -EOPNOTSUPP; goto out_unlock; } @@ -2976,8 +2988,8 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || __is_large_section(sbi)) { - f2fs_warn(sbi, "Can't flush %u in %d for segs_per_sec %u != 1", - range.dev_num, sbi->s_ndevs, sbi->segs_per_sec); + f2fs_warn(sbi, "Can't flush %u in %d for SEGS_PER_SEC %u != 1", + range.dev_num, sbi->s_ndevs, SEGS_PER_SEC(sbi)); return -EINVAL; } @@ -3183,6 +3195,7 @@ int f2fs_pin_file_control(struct inode *inode, bool inc) static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); __u32 pin; int ret = 0; @@ -3192,7 +3205,7 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) if (!S_ISREG(inode->i_mode)) return -EINVAL; - if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + if (f2fs_readonly(sbi->sb)) return -EROFS; ret = mnt_want_write_file(filp); @@ -3205,9 +3218,18 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) clear_inode_flag(inode, FI_PIN_FILE); f2fs_i_gc_failures_write(inode, 0); goto done; + } else if (f2fs_is_pinned_file(inode)) { + goto done; } - if (f2fs_should_update_outplace(inode, NULL)) { + if (f2fs_sb_has_blkzoned(sbi) && F2FS_HAS_BLOCKS(inode)) { + ret = -EFBIG; + goto out; + } + + /* Let's allow file pinning on zoned device. */ + if (!f2fs_sb_has_blkzoned(sbi) && + f2fs_should_update_outplace(inode, NULL)) { ret = -EINVAL; goto out; } @@ -3229,7 +3251,7 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) set_inode_flag(inode, FI_PIN_FILE); ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]; done: - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + f2fs_update_time(sbi, REQ_TIME); out: inode_unlock(inode); mnt_drop_write_file(filp); @@ -3490,9 +3512,6 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) if (!f2fs_sb_has_compression(sbi)) return -EOPNOTSUPP; - if (!f2fs_compressed_file(inode)) - return -EINVAL; - if (f2fs_readonly(sbi->sb)) return -EROFS; @@ -3511,7 +3530,8 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) goto out; } - if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + if (!f2fs_compressed_file(inode) || + is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { ret = -EINVAL; goto out; } @@ -3538,9 +3558,12 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) struct dnode_of_data dn; pgoff_t end_offset, count; + f2fs_lock_op(sbi); + set_new_dnode(&dn, inode, NULL, NULL, 0); ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE); if (ret) { + f2fs_unlock_op(sbi); if (ret == -ENOENT) { page_idx = f2fs_get_next_page_offset(&dn, page_idx); @@ -3558,6 +3581,8 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + if (ret < 0) break; @@ -3588,10 +3613,10 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) return ret; } -static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) +static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count, + unsigned int *reserved_blocks) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - unsigned int reserved_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; block_t blkaddr; int i; @@ -3611,43 +3636,63 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) while (count) { int compr_blocks = 0; - blkcnt_t reserved; + blkcnt_t reserved = 0; + blkcnt_t to_reserved; int ret; - for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { - blkaddr = f2fs_data_blkaddr(dn); + for (i = 0; i < cluster_size; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_page, + dn->ofs_in_node + i); if (i == 0) { - if (blkaddr == COMPRESS_ADDR) - continue; - dn->ofs_in_node += cluster_size; - goto next; + if (blkaddr != COMPRESS_ADDR) { + dn->ofs_in_node += cluster_size; + goto next; + } + continue; } + /* + * compressed cluster was not released due to it + * fails in release_compress_blocks(), so NEW_ADDR + * is a possible case. + */ + if (blkaddr == NEW_ADDR) { + reserved++; + continue; + } if (__is_valid_data_blkaddr(blkaddr)) { compr_blocks++; continue; } + } + + to_reserved = cluster_size - compr_blocks - reserved; - f2fs_set_data_blkaddr(dn, NEW_ADDR); + /* for the case all blocks in cluster were reserved */ + if (to_reserved == 1) { + dn->ofs_in_node += cluster_size; + goto next; } - reserved = cluster_size - compr_blocks; - ret = inc_valid_block_count(sbi, dn->inode, &reserved); - if (ret) + ret = inc_valid_block_count(sbi, dn->inode, + &to_reserved, false); + if (unlikely(ret)) return ret; - if (reserved != cluster_size - compr_blocks) - return -ENOSPC; + for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { + if (f2fs_data_blkaddr(dn) == NULL_ADDR) + f2fs_set_data_blkaddr(dn, NEW_ADDR); + } f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true); - reserved_blocks += reserved; + *reserved_blocks += to_reserved; next: count -= cluster_size; } - return reserved_blocks; + return 0; } static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) @@ -3661,9 +3706,6 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) if (!f2fs_sb_has_compression(sbi)) return -EOPNOTSUPP; - if (!f2fs_compressed_file(inode)) - return -EINVAL; - if (f2fs_readonly(sbi->sb)) return -EROFS; @@ -3671,18 +3713,19 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) if (ret) return ret; - if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) - goto out; - f2fs_balance_fs(sbi, true); inode_lock(inode); - if (!is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + if (!f2fs_compressed_file(inode) || + !is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { ret = -EINVAL; goto unlock_inode; } + if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) + goto unlock_inode; + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); @@ -3692,9 +3735,12 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) struct dnode_of_data dn; pgoff_t end_offset, count; + f2fs_lock_op(sbi); + set_new_dnode(&dn, inode, NULL, NULL, 0); ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE); if (ret) { + f2fs_unlock_op(sbi); if (ret == -ENOENT) { page_idx = f2fs_get_next_page_offset(&dn, page_idx); @@ -3708,31 +3754,31 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); count = round_up(count, F2FS_I(inode)->i_cluster_size); - ret = reserve_compress_blocks(&dn, count); + ret = reserve_compress_blocks(&dn, count, &reserved_blocks); f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + if (ret < 0) break; page_idx += count; - reserved_blocks += ret; } filemap_invalidate_unlock(inode->i_mapping); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - if (ret >= 0) { + if (!ret) { clear_inode_flag(inode, FI_COMPRESS_RELEASED); inode_set_ctime_current(inode); f2fs_mark_inode_dirty_sync(inode, true); } unlock_inode: inode_unlock(inode); -out: mnt_drop_write_file(filp); - if (ret >= 0) { + if (!ret) { ret = put_user(reserved_blocks, (u64 __user *)arg); } else if (reserved_blocks && atomic_read(&F2FS_I(inode)->i_compr_blocks)) { @@ -3981,16 +4027,20 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) sizeof(option))) return -EFAULT; - if (!f2fs_compressed_file(inode) || - option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || - option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || - option.algorithm >= COMPRESS_MAX) + if (option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || + option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || + option.algorithm >= COMPRESS_MAX) return -EINVAL; file_start_write(filp); inode_lock(inode); f2fs_down_write(&F2FS_I(inode)->i_sem); + if (!f2fs_compressed_file(inode)) { + ret = -EINVAL; + goto out; + } + if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) { ret = -EBUSY; goto out; @@ -4066,7 +4116,6 @@ static int f2fs_ioc_decompress_file(struct file *filp) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); pgoff_t page_idx = 0, last_idx; - unsigned int blk_per_seg = sbi->blocks_per_seg; int cluster_size = fi->i_cluster_size; int count, ret; @@ -4077,9 +4126,6 @@ static int f2fs_ioc_decompress_file(struct file *filp) if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; - if (!f2fs_compressed_file(inode)) - return -EINVAL; - f2fs_balance_fs(sbi, true); file_start_write(filp); @@ -4090,7 +4136,8 @@ static int f2fs_ioc_decompress_file(struct file *filp) goto out; } - if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + if (!f2fs_compressed_file(inode) || + is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { ret = -EINVAL; goto out; } @@ -4110,7 +4157,7 @@ static int f2fs_ioc_decompress_file(struct file *filp) if (ret < 0) break; - if (get_dirty_pages(inode) >= blk_per_seg) { + if (get_dirty_pages(inode) >= BLKS_PER_SEG(sbi)) { ret = filemap_fdatawrite(inode->i_mapping); if (ret < 0) break; @@ -4145,7 +4192,6 @@ static int f2fs_ioc_compress_file(struct file *filp) struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); pgoff_t page_idx = 0, last_idx; - unsigned int blk_per_seg = sbi->blocks_per_seg; int cluster_size = F2FS_I(inode)->i_cluster_size; int count, ret; @@ -4156,9 +4202,6 @@ static int f2fs_ioc_compress_file(struct file *filp) if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; - if (!f2fs_compressed_file(inode)) - return -EINVAL; - f2fs_balance_fs(sbi, true); file_start_write(filp); @@ -4169,7 +4212,8 @@ static int f2fs_ioc_compress_file(struct file *filp) goto out; } - if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + if (!f2fs_compressed_file(inode) || + is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { ret = -EINVAL; goto out; } @@ -4188,7 +4232,7 @@ static int f2fs_ioc_compress_file(struct file *filp) if (ret < 0) break; - if (get_dirty_pages(inode) >= blk_per_seg) { + if (get_dirty_pages(inode) >= BLKS_PER_SEG(sbi)) { ret = filemap_fdatawrite(inode->i_mapping); if (ret < 0) break; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index a079eebfb080b..8015d3fbc7dd3 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -259,7 +259,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, p->ofs_unit = 1; } else { p->gc_mode = select_gc_type(sbi, gc_type); - p->ofs_unit = sbi->segs_per_sec; + p->ofs_unit = SEGS_PER_SEC(sbi); if (__is_large_section(sbi)) { p->dirty_bitmap = dirty_i->dirty_secmap; p->max_search = count_bits(p->dirty_bitmap, @@ -280,11 +280,11 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, p->max_search > sbi->max_victim_search) p->max_search = sbi->max_victim_search; - /* let's select beginning hot/small space first in no_heap mode*/ + /* let's select beginning hot/small space first. */ if (f2fs_need_rand_seg(sbi)) - p->offset = get_random_u32_below(MAIN_SECS(sbi) * sbi->segs_per_sec); - else if (test_opt(sbi, NOHEAP) && - (type == CURSEG_HOT_DATA || IS_NODESEG(type))) + p->offset = get_random_u32_below(MAIN_SECS(sbi) * + SEGS_PER_SEC(sbi)); + else if (type == CURSEG_HOT_DATA || IS_NODESEG(type)) p->offset = 0; else p->offset = SIT_I(sbi)->last_victim[p->gc_mode]; @@ -295,13 +295,13 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi, { /* SSR allocates in a segment unit */ if (p->alloc_mode == SSR) - return sbi->blocks_per_seg; + return BLKS_PER_SEG(sbi); else if (p->alloc_mode == AT_SSR) return UINT_MAX; /* LFS */ if (p->gc_mode == GC_GREEDY) - return 2 * sbi->blocks_per_seg * p->ofs_unit; + return 2 * BLKS_PER_SEG(sbi) * p->ofs_unit; else if (p->gc_mode == GC_CB) return UINT_MAX; else if (p->gc_mode == GC_AT) @@ -496,9 +496,9 @@ static void add_victim_entry(struct f2fs_sb_info *sbi, return; } - for (i = 0; i < sbi->segs_per_sec; i++) + for (i = 0; i < SEGS_PER_SEC(sbi); i++) mtime += get_seg_entry(sbi, start + i)->mtime; - mtime = div_u64(mtime, sbi->segs_per_sec); + mtime = div_u64(mtime, SEGS_PER_SEC(sbi)); /* Handle if the system time has changed by the user */ if (mtime < sit_i->min_mtime) @@ -599,7 +599,6 @@ static void atssr_lookup_victim(struct f2fs_sb_info *sbi, unsigned long long age; unsigned long long max_mtime = sit_i->dirty_max_mtime; unsigned long long min_mtime = sit_i->dirty_min_mtime; - unsigned int seg_blocks = sbi->blocks_per_seg; unsigned int vblocks; unsigned int dirty_threshold = max(am->max_candidate_count, am->candidate_ratio * @@ -629,7 +628,7 @@ static void atssr_lookup_victim(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, !vblocks); /* rare case */ - if (vblocks == seg_blocks) + if (vblocks == BLKS_PER_SEG(sbi)) goto skip_node; iter++; @@ -755,7 +754,7 @@ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result, int ret = 0; mutex_lock(&dirty_i->seglist_lock); - last_segment = MAIN_SECS(sbi) * sbi->segs_per_sec; + last_segment = MAIN_SECS(sbi) * SEGS_PER_SEC(sbi); p.alloc_mode = alloc_mode; p.age = age; @@ -896,7 +895,7 @@ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result, else sm->last_victim[p.gc_mode] = segno + p.ofs_unit; sm->last_victim[p.gc_mode] %= - (MAIN_SECS(sbi) * sbi->segs_per_sec); + (MAIN_SECS(sbi) * SEGS_PER_SEC(sbi)); break; } } @@ -1184,7 +1183,6 @@ static int ra_data_block(struct inode *inode, pgoff_t index) .op_flags = 0, .encrypted_page = NULL, .in_list = 0, - .retry = 0, }; int err; @@ -1273,7 +1271,6 @@ static int move_data_block(struct inode *inode, block_t bidx, .op_flags = 0, .encrypted_page = NULL, .in_list = 0, - .retry = 0, }; struct dnode_of_data dn; struct f2fs_summary sum; @@ -1393,18 +1390,12 @@ static int move_data_block(struct inode *inode, block_t bidx, fio.op_flags = REQ_SYNC; fio.new_blkaddr = newaddr; f2fs_submit_page_write(&fio); - if (fio.retry) { - err = -EAGAIN; - if (PageWriteback(fio.encrypted_page)) - end_page_writeback(fio.encrypted_page); - goto put_page_out; - } f2fs_update_iostat(fio.sbi, NULL, FS_GC_DATA_IO, F2FS_BLKSIZE); f2fs_update_data_blkaddr(&dn, newaddr); set_inode_flag(inode, FI_APPEND_WRITE); -put_page_out: + f2fs_put_page(fio.encrypted_page, 1); recover_block: if (err) @@ -1560,10 +1551,15 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, int err; inode = f2fs_iget(sb, dni.ino); - if (IS_ERR(inode) || is_bad_inode(inode) || - special_file(inode->i_mode)) + if (IS_ERR(inode)) continue; + if (is_bad_inode(inode) || + special_file(inode->i_mode)) { + iput(inode); + continue; + } + err = f2fs_gc_pinned_control(inode, gc_type, segno); if (err == -EAGAIN) { iput(inode); @@ -1678,7 +1674,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, struct f2fs_summary_block *sum; struct blk_plug plug; unsigned int segno = start_segno; - unsigned int end_segno = start_segno + sbi->segs_per_sec; + unsigned int end_segno = start_segno + SEGS_PER_SEC(sbi); int seg_freed = 0, migrated = 0; unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? SUM_TYPE_DATA : SUM_TYPE_NODE; @@ -1686,7 +1682,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, int submitted = 0; if (__is_large_section(sbi)) - end_segno = rounddown(end_segno, sbi->segs_per_sec); + end_segno = rounddown(end_segno, SEGS_PER_SEC(sbi)); /* * zone-capacity can be less than zone-size in zoned devices, @@ -1694,7 +1690,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, * calculate the end segno in the zone which can be garbage collected */ if (f2fs_sb_has_blkzoned(sbi)) - end_segno -= sbi->segs_per_sec - + end_segno -= SEGS_PER_SEC(sbi) - f2fs_usable_segs_in_sec(sbi, segno); sanity_check_seg_type(sbi, get_seg_entry(sbi, segno)->type); @@ -1983,10 +1979,40 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) init_atgc_management(sbi); } +int f2fs_gc_range(struct f2fs_sb_info *sbi, + unsigned int start_seg, unsigned int end_seg, + bool dry_run, unsigned int dry_run_sections) +{ + unsigned int segno; + unsigned int gc_secs = dry_run_sections; + + for (segno = start_seg; segno <= end_seg; segno += SEGS_PER_SEC(sbi)) { + struct gc_inode_list gc_list = { + .ilist = LIST_HEAD_INIT(gc_list.ilist), + .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), + }; + + do_garbage_collect(sbi, segno, &gc_list, FG_GC, + dry_run_sections == 0); + put_gc_inode(&gc_list); + + if (!dry_run && get_valid_blocks(sbi, segno, true)) + return -EAGAIN; + if (dry_run && dry_run_sections && + !get_valid_blocks(sbi, segno, true) && --gc_secs == 0) + break; + + if (fatal_signal_pending(current)) + return -ERESTARTSYS; + } + + return 0; +} + static int free_segment_range(struct f2fs_sb_info *sbi, - unsigned int secs, bool gc_only) + unsigned int secs, bool dry_run) { - unsigned int segno, next_inuse, start, end; + unsigned int next_inuse, start, end; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; int gc_mode, gc_type; int err = 0; @@ -1994,7 +2020,7 @@ static int free_segment_range(struct f2fs_sb_info *sbi, /* Force block allocation for GC */ MAIN_SECS(sbi) -= secs; - start = MAIN_SECS(sbi) * sbi->segs_per_sec; + start = MAIN_SECS(sbi) * SEGS_PER_SEC(sbi); end = MAIN_SEGS(sbi) - 1; mutex_lock(&DIRTY_I(sbi)->seglist_lock); @@ -2012,25 +2038,8 @@ static int free_segment_range(struct f2fs_sb_info *sbi, f2fs_allocate_segment_for_resize(sbi, type, start, end); /* do GC to move out valid blocks in the range */ - for (segno = start; segno <= end; segno += sbi->segs_per_sec) { - struct gc_inode_list gc_list = { - .ilist = LIST_HEAD_INIT(gc_list.ilist), - .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), - }; - - do_garbage_collect(sbi, segno, &gc_list, FG_GC, true); - put_gc_inode(&gc_list); - - if (!gc_only && get_valid_blocks(sbi, segno, true)) { - err = -EAGAIN; - goto out; - } - if (fatal_signal_pending(current)) { - err = -ERESTARTSYS; - goto out; - } - } - if (gc_only) + err = f2fs_gc_range(sbi, start, end, dry_run, 0); + if (err || dry_run) goto out; stat_inc_cp_call_count(sbi, TOTAL_CALL); @@ -2056,7 +2065,7 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs) int segment_count; int segment_count_main; long long block_count; - int segs = secs * sbi->segs_per_sec; + int segs = secs * SEGS_PER_SEC(sbi); f2fs_down_write(&sbi->sb_lock); @@ -2069,7 +2078,7 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs) raw_sb->segment_count = cpu_to_le32(segment_count + segs); raw_sb->segment_count_main = cpu_to_le32(segment_count_main + segs); raw_sb->block_count = cpu_to_le64(block_count + - (long long)segs * sbi->blocks_per_seg); + (long long)(segs << sbi->log_blocks_per_seg)); if (f2fs_is_multi_device(sbi)) { int last_dev = sbi->s_ndevs - 1; int dev_segs = @@ -2084,8 +2093,8 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs) static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs) { - int segs = secs * sbi->segs_per_sec; - long long blks = (long long)segs * sbi->blocks_per_seg; + int segs = secs * SEGS_PER_SEC(sbi); + long long blks = (long long)segs << sbi->log_blocks_per_seg; long long user_block_count = le64_to_cpu(F2FS_CKPT(sbi)->user_block_count); @@ -2127,7 +2136,7 @@ int f2fs_resize_fs(struct file *filp, __u64 block_count) int last_dev = sbi->s_ndevs - 1; __u64 last_segs = FDEV(last_dev).total_segments; - if (block_count + last_segs * sbi->blocks_per_seg <= + if (block_count + (last_segs << sbi->log_blocks_per_seg) <= old_block_count) return -EINVAL; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index c26effdce9aa7..2af50bc34fcd7 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -361,6 +361,12 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } + if (fi->i_xattr_nid && f2fs_check_nid_range(sbi, fi->i_xattr_nid)) { + f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_xattr_nid: %u, run fsck to fix.", + __func__, inode->i_ino, fi->i_xattr_nid); + return false; + } + return true; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index b3bb815fc6aa4..550cc811e008a 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -852,7 +852,7 @@ static int f2fs_mknod(struct mnt_idmap *idmap, struct inode *dir, static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode, bool is_whiteout, - struct inode **new_inode) + struct inode **new_inode, struct f2fs_filename *fname) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; @@ -880,7 +880,7 @@ static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, if (err) goto out; - err = f2fs_do_tmpfile(inode, dir); + err = f2fs_do_tmpfile(inode, dir, fname); if (err) goto release_out; @@ -931,22 +931,24 @@ static int f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = __f2fs_tmpfile(idmap, dir, file, mode, false, NULL); + err = __f2fs_tmpfile(idmap, dir, file, mode, false, NULL, NULL); return finish_open_simple(file, err); } static int f2fs_create_whiteout(struct mnt_idmap *idmap, - struct inode *dir, struct inode **whiteout) + struct inode *dir, struct inode **whiteout, + struct f2fs_filename *fname) { - return __f2fs_tmpfile(idmap, dir, NULL, - S_IFCHR | WHITEOUT_MODE, true, whiteout); + return __f2fs_tmpfile(idmap, dir, NULL, S_IFCHR | WHITEOUT_MODE, + true, whiteout, fname); } int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct inode **new_inode) { - return __f2fs_tmpfile(idmap, dir, NULL, S_IFREG, false, new_inode); + return __f2fs_tmpfile(idmap, dir, NULL, S_IFREG, + false, new_inode, NULL); } static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, @@ -990,7 +992,14 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, } if (flags & RENAME_WHITEOUT) { - err = f2fs_create_whiteout(idmap, old_dir, &whiteout); + struct f2fs_filename fname; + + err = f2fs_setup_filename(old_dir, &old_dentry->d_name, + 0, &fname); + if (err) + return err; + + err = f2fs_create_whiteout(idmap, old_dir, &whiteout, &fname); if (err) return err; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9b546fd210100..d46cf74545040 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -852,21 +852,29 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) if (is_inode_flag_set(dn->inode, FI_COMPRESSED_FILE) && f2fs_sb_has_readonly(sbi)) { - unsigned int c_len = f2fs_cluster_blocks_are_contiguous(dn); + unsigned int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + unsigned int ofs_in_node = dn->ofs_in_node; + pgoff_t fofs = index; + unsigned int c_len; block_t blkaddr; + /* should align fofs and ofs_in_node to cluster_size */ + if (fofs % cluster_size) { + fofs = round_down(fofs, cluster_size); + ofs_in_node = round_down(ofs_in_node, cluster_size); + } + + c_len = f2fs_cluster_blocks_are_contiguous(dn, ofs_in_node); if (!c_len) goto out; - blkaddr = f2fs_data_blkaddr(dn); + blkaddr = data_blkaddr(dn->inode, dn->node_page, ofs_in_node); if (blkaddr == COMPRESS_ADDR) blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + 1); + ofs_in_node + 1); f2fs_update_read_extent_tree_range_compressed(dn->inode, - index, blkaddr, - F2FS_I(dn->inode)->i_cluster_size, - c_len); + fofs, blkaddr, cluster_size, c_len); } out: return 0; @@ -1179,7 +1187,17 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from) default: BUG(); } - if (err < 0 && err != -ENOENT) + if (err == -ENOENT) { + set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK); + f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); + f2fs_err_ratelimited(sbi, + "truncate node fail, ino:%lu, nid:%u, " + "offset[0]:%d, offset[1]:%d, nofs:%d", + inode->i_ino, dn.nid, offset[0], + offset[1], nofs); + err = 0; + } + if (err < 0) goto fail; if (offset[1] == 0 && ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) { @@ -1311,6 +1329,7 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs) } if (unlikely(new_ni.blk_addr != NULL_ADDR)) { err = -EFSCORRUPTED; + dec_valid_node_count(sbi, dn->inode, !ofs); set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); goto fail; @@ -1337,7 +1356,6 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs) if (ofs == 0) inc_valid_inode_count(sbi); return page; - fail: clear_node_page_dirty(page); f2fs_put_page(page, 1); @@ -2841,7 +2859,7 @@ int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, int i, idx, last_offset, nrpages; /* scan the node segment */ - last_offset = sbi->blocks_per_seg; + last_offset = BLKS_PER_SEG(sbi); addr = START_BLOCK(sbi, segno); sum_entry = &sum->entries[0]; @@ -3158,7 +3176,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG)) return 0; - nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg - + nat_bits_addr = __start_cp_addr(sbi) + BLKS_PER_SEG(sbi) - nm_i->nat_bits_blocks; for (i = 0; i < nm_i->nat_bits_blocks; i++) { struct page *page; diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 5bd16a95eef8f..6aea13024ac16 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -208,10 +208,10 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start) block_addr = (pgoff_t)(nm_i->nat_blkaddr + (block_off << 1) - - (block_off & (sbi->blocks_per_seg - 1))); + (block_off & (BLKS_PER_SEG(sbi) - 1))); if (f2fs_test_bit(block_off, nm_i->nat_bitmap)) - block_addr += sbi->blocks_per_seg; + block_addr += BLKS_PER_SEG(sbi); return block_addr; } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index d0f24ccbd1ac6..b3baec666afef 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -354,7 +354,7 @@ static unsigned int adjust_por_ra_blocks(struct f2fs_sb_info *sbi, if (blkaddr + 1 == next_blkaddr) ra_blocks = min_t(unsigned int, RECOVERY_MAX_RA_BLOCKS, ra_blocks * 2); - else if (next_blkaddr % sbi->blocks_per_seg) + else if (next_blkaddr % BLKS_PER_SEG(sbi)) ra_blocks = max_t(unsigned int, RECOVERY_MIN_RA_BLOCKS, ra_blocks / 2); return ra_blocks; @@ -611,6 +611,19 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, return 0; } +static int f2fs_reserve_new_block_retry(struct dnode_of_data *dn) +{ + int i, err = 0; + + for (i = DEFAULT_FAILURE_RETRY_COUNT; i > 0; i--) { + err = f2fs_reserve_new_block(dn); + if (!err) + break; + } + + return err; +} + static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, struct page *page) { @@ -712,14 +725,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, */ if (dest == NEW_ADDR) { f2fs_truncate_data_blocks_range(&dn, 1); - do { - err = f2fs_reserve_new_block(&dn); - if (err == -ENOSPC) { - f2fs_bug_on(sbi, 1); - break; - } - } while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + + err = f2fs_reserve_new_block_retry(&dn); if (err) goto err; continue; @@ -727,16 +734,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, /* dest is valid block, try to recover from src to dest */ if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { - if (src == NULL_ADDR) { - do { - err = f2fs_reserve_new_block(&dn); - if (err == -ENOSPC) { - f2fs_bug_on(sbi, 1); - break; - } - } while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + err = f2fs_reserve_new_block_retry(&dn); if (err) goto err; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 4c8836ded90fc..717eccb558fa2 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -192,6 +192,9 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) if (!f2fs_is_atomic_file(inode)) return; + if (clean) + truncate_inode_pages_final(inode->i_mapping); + release_atomic_write_cnt(inode); clear_inode_flag(inode, FI_ATOMIC_COMMITTED); clear_inode_flag(inode, FI_ATOMIC_REPLACE); @@ -201,7 +204,6 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) F2FS_I(inode)->atomic_write_task = NULL; if (clean) { - truncate_inode_pages_final(inode->i_mapping); f2fs_i_size_write(inode, fi->original_i_size); fi->original_i_size = 0; } @@ -248,7 +250,7 @@ static int __replace_atomic_write_block(struct inode *inode, pgoff_t index, } else { blkcnt_t count = 1; - err = inc_valid_block_count(sbi, inode, &count); + err = inc_valid_block_count(sbi, inode, &count, true); if (err) { f2fs_put_dnode(&dn); return err; @@ -448,8 +450,8 @@ static inline bool excess_dirty_threshold(struct f2fs_sb_info *sbi) unsigned int nodes = get_pages(sbi, F2FS_DIRTY_NODES); unsigned int meta = get_pages(sbi, F2FS_DIRTY_META); unsigned int imeta = get_pages(sbi, F2FS_DIRTY_IMETA); - unsigned int threshold = sbi->blocks_per_seg * factor * - DEFAULT_DIRTY_THRESHOLD; + unsigned int threshold = (factor * DEFAULT_DIRTY_THRESHOLD) << + sbi->log_blocks_per_seg; unsigned int global_threshold = threshold * 3 / 2; if (dents >= threshold || qdata >= threshold || @@ -1101,9 +1103,8 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, dc->error = 0; if (dc->error) - printk_ratelimited( - "%sF2FS-fs (%s): Issue discard(%u, %u, %u) failed, ret: %d", - KERN_INFO, sbi->sb->s_id, + f2fs_info_ratelimited(sbi, + "Issue discard(%u, %u, %u) failed, ret: %d", dc->di.lstart, dc->di.start, dc->di.len, dc->error); __detach_discard_cmd(dcc, dc); } @@ -1132,8 +1133,7 @@ static void __check_sit_bitmap(struct f2fs_sb_info *sbi, struct seg_entry *sentry; unsigned int segno; block_t blk = start; - unsigned long offset, size, max_blocks = sbi->blocks_per_seg; - unsigned long *map; + unsigned long offset, size, *map; while (blk < end) { segno = GET_SEGNO(sbi, blk); @@ -1143,7 +1143,7 @@ static void __check_sit_bitmap(struct f2fs_sb_info *sbi, if (end < START_BLOCK(sbi, segno + 1)) size = GET_BLKOFF_FROM_SEG0(sbi, end); else - size = max_blocks; + size = BLKS_PER_SEG(sbi); map = (unsigned long *)(sentry->cur_valid_map); offset = __find_rev_next_bit(map, size, offset); f2fs_bug_on(sbi, offset != size); @@ -2042,7 +2042,6 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, bool check_only) { int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long); - int max_blocks = sbi->blocks_per_seg; struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start); unsigned long *cur_map = (unsigned long *)se->cur_valid_map; unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map; @@ -2054,8 +2053,9 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, struct list_head *head = &SM_I(sbi)->dcc_info->entry_list; int i; - if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi) || - !f2fs_block_unit_discard(sbi)) + if (se->valid_blocks == BLKS_PER_SEG(sbi) || + !f2fs_hw_support_discard(sbi) || + !f2fs_block_unit_discard(sbi)) return false; if (!force) { @@ -2072,13 +2072,14 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, while (force || SM_I(sbi)->dcc_info->nr_discards <= SM_I(sbi)->dcc_info->max_discards) { - start = __find_rev_next_bit(dmap, max_blocks, end + 1); - if (start >= max_blocks) + start = __find_rev_next_bit(dmap, BLKS_PER_SEG(sbi), end + 1); + if (start >= BLKS_PER_SEG(sbi)) break; - end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1); - if (force && start && end != max_blocks - && (end - start) < cpc->trim_minlen) + end = __find_rev_next_zero_bit(dmap, + BLKS_PER_SEG(sbi), start + 1); + if (force && start && end != BLKS_PER_SEG(sbi) && + (end - start) < cpc->trim_minlen) continue; if (check_only) @@ -2160,8 +2161,8 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, start + 1); if (section_alignment) { - start = rounddown(start, sbi->segs_per_sec); - end = roundup(end, sbi->segs_per_sec); + start = rounddown(start, SEGS_PER_SEC(sbi)); + end = roundup(end, SEGS_PER_SEC(sbi)); } for (i = start; i < end; i++) { @@ -2189,9 +2190,9 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, if (!IS_CURSEC(sbi, secno) && !get_valid_blocks(sbi, start, true)) f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno), - sbi->segs_per_sec << sbi->log_blocks_per_seg); + BLKS_PER_SEC(sbi)); - start = start_segno + sbi->segs_per_sec; + start = start_segno + SEGS_PER_SEC(sbi); if (start < end) goto next; else @@ -2210,7 +2211,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, find_next: if (is_valid) { next_pos = find_next_zero_bit_le(entry->discard_map, - sbi->blocks_per_seg, cur_pos); + BLKS_PER_SEG(sbi), cur_pos); len = next_pos - cur_pos; if (f2fs_sb_has_blkzoned(sbi) || @@ -2222,13 +2223,13 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, total_len += len; } else { next_pos = find_next_bit_le(entry->discard_map, - sbi->blocks_per_seg, cur_pos); + BLKS_PER_SEG(sbi), cur_pos); } skip: cur_pos = next_pos; is_valid = !is_valid; - if (cur_pos < sbi->blocks_per_seg) + if (cur_pos < BLKS_PER_SEG(sbi)) goto find_next; release_discard_addr(entry); @@ -2277,7 +2278,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi) dcc->max_ordered_discard = DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY; dcc->discard_io_aware = DPOLICY_IO_AWARE_ENABLE; if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT) - dcc->discard_granularity = sbi->blocks_per_seg; + dcc->discard_granularity = BLKS_PER_SEG(sbi); else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION) dcc->discard_granularity = BLKS_PER_SEC(sbi); @@ -2540,7 +2541,7 @@ static unsigned short f2fs_curseg_valid_blocks(struct f2fs_sb_info *sbi, int typ struct curseg_info *curseg = CURSEG_I(sbi, type); if (sbi->ckpt->alloc_type[type] == SSR) - return sbi->blocks_per_seg; + return BLKS_PER_SEG(sbi); return curseg->next_blkoff; } @@ -2628,7 +2629,7 @@ static int is_next_segment_free(struct f2fs_sb_info *sbi, unsigned int segno = curseg->segno + 1; struct free_segmap_info *free_i = FREE_I(sbi); - if (segno < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec) + if (segno < MAIN_SEGS(sbi) && segno % SEGS_PER_SEC(sbi)) return !test_bit(segno, free_i->free_segmap); return 0; } @@ -2638,53 +2639,41 @@ static int is_next_segment_free(struct f2fs_sb_info *sbi, * This function should be returned with success, otherwise BUG */ static void get_new_segment(struct f2fs_sb_info *sbi, - unsigned int *newseg, bool new_sec, int dir) + unsigned int *newseg, bool new_sec, bool pinning) { struct free_segmap_info *free_i = FREE_I(sbi); unsigned int segno, secno, zoneno; unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone; unsigned int hint = GET_SEC_FROM_SEG(sbi, *newseg); unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg); - unsigned int left_start = hint; bool init = true; - int go_left = 0; int i; spin_lock(&free_i->segmap_lock); - if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) { + if (!new_sec && ((*newseg + 1) % SEGS_PER_SEC(sbi))) { segno = find_next_zero_bit(free_i->free_segmap, GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1); if (segno < GET_SEG_FROM_SEC(sbi, hint + 1)) goto got_it; } + + /* + * If we format f2fs on zoned storage, let's try to get pinned sections + * from beginning of the storage, which should be a conventional one. + */ + if (f2fs_sb_has_blkzoned(sbi)) { + segno = pinning ? 0 : max(first_zoned_segno(sbi), *newseg); + hint = GET_SEC_FROM_SEG(sbi, segno); + } + find_other_zone: secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint); if (secno >= MAIN_SECS(sbi)) { - if (dir == ALLOC_RIGHT) { - secno = find_first_zero_bit(free_i->free_secmap, + secno = find_first_zero_bit(free_i->free_secmap, MAIN_SECS(sbi)); - f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi)); - } else { - go_left = 1; - left_start = hint - 1; - } - } - if (go_left == 0) - goto skip_left; - - while (test_bit(left_start, free_i->free_secmap)) { - if (left_start > 0) { - left_start--; - continue; - } - left_start = find_first_zero_bit(free_i->free_secmap, - MAIN_SECS(sbi)); - f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi)); - break; + f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi)); } - secno = left_start; -skip_left: segno = GET_SEG_FROM_SEC(sbi, secno); zoneno = GET_ZONE_FROM_SEC(sbi, secno); @@ -2695,21 +2684,13 @@ static void get_new_segment(struct f2fs_sb_info *sbi, goto got_it; if (zoneno == old_zoneno) goto got_it; - if (dir == ALLOC_LEFT) { - if (!go_left && zoneno + 1 >= total_zones) - goto got_it; - if (go_left && zoneno == 0) - goto got_it; - } for (i = 0; i < NR_CURSEG_TYPE; i++) if (CURSEG_I(sbi, i)->zone == zoneno) break; if (i < NR_CURSEG_TYPE) { /* zone is in user, try another */ - if (go_left) - hint = zoneno * sbi->secs_per_zone - 1; - else if (zoneno + 1 >= total_zones) + if (zoneno + 1 >= total_zones) hint = 0; else hint = (zoneno + 1) * sbi->secs_per_zone; @@ -2755,9 +2736,8 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) sanity_check_seg_type(sbi, seg_type); if (f2fs_need_rand_seg(sbi)) - return get_random_u32_below(MAIN_SECS(sbi) * sbi->segs_per_sec); + return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi)); - /* if segs_per_sec is large than 1, we need to keep original policy. */ if (__is_large_section(sbi)) return curseg->segno; @@ -2768,8 +2748,7 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return 0; - if (test_opt(sbi, NOHEAP) && - (seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type))) + if (seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type)) return 0; if (SIT_I(sbi)->last_victim[ALLOC_NEXT]) @@ -2786,30 +2765,30 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) * Allocate a current working segment. * This function always allocates a free segment in LFS manner. */ -static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) +static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) { struct curseg_info *curseg = CURSEG_I(sbi, type); - unsigned short seg_type = curseg->seg_type; unsigned int segno = curseg->segno; - int dir = ALLOC_LEFT; + bool pinning = type == CURSEG_COLD_DATA_PINNED; if (curseg->inited) - write_sum_page(sbi, curseg->sum_blk, - GET_SUM_BLOCK(sbi, segno)); - if (seg_type == CURSEG_WARM_DATA || seg_type == CURSEG_COLD_DATA) - dir = ALLOC_RIGHT; - - if (test_opt(sbi, NOHEAP)) - dir = ALLOC_RIGHT; + write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, segno)); segno = __get_next_segno(sbi, type); - get_new_segment(sbi, &segno, new_sec, dir); + get_new_segment(sbi, &segno, new_sec, pinning); + if (new_sec && pinning && + !f2fs_valid_pinned_area(sbi, START_BLOCK(sbi, segno))) { + __set_free(sbi, segno); + return -EAGAIN; + } + curseg->next_segno = segno; reset_curseg(sbi, type, 1); curseg->alloc_type = LFS; if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) curseg->fragment_remained_chunk = get_random_u32_inclusive(1, sbi->max_fragment_chunk); + return 0; } static int __next_free_blkoff(struct f2fs_sb_info *sbi, @@ -2825,7 +2804,7 @@ static int __next_free_blkoff(struct f2fs_sb_info *sbi, for (i = 0; i < entries; i++) target_map[i] = ckpt_map[i] | cur_map[i]; - return __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start); + return __find_rev_next_zero_bit(target_map, BLKS_PER_SEG(sbi), start); } static int f2fs_find_next_ssr_block(struct f2fs_sb_info *sbi, @@ -2836,7 +2815,7 @@ static int f2fs_find_next_ssr_block(struct f2fs_sb_info *sbi, bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno) { - return __next_free_blkoff(sbi, segno, 0) < sbi->blocks_per_seg; + return __next_free_blkoff(sbi, segno, 0) < BLKS_PER_SEG(sbi); } /* @@ -3082,7 +3061,7 @@ void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, f2fs_up_read(&SM_I(sbi)->curseg_lock); } -static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type, +static int __allocate_new_segment(struct f2fs_sb_info *sbi, int type, bool new_sec, bool force) { struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -3092,21 +3071,49 @@ static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type, !curseg->next_blkoff && !get_valid_blocks(sbi, curseg->segno, new_sec) && !get_ckpt_valid_blocks(sbi, curseg->segno, new_sec)) - return; + return 0; old_segno = curseg->segno; - new_curseg(sbi, type, true); + if (new_curseg(sbi, type, true)) + return -EAGAIN; stat_inc_seg_type(sbi, curseg); locate_dirty_segment(sbi, old_segno); + return 0; } -void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force) +int f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force) { + int ret; + f2fs_down_read(&SM_I(sbi)->curseg_lock); down_write(&SIT_I(sbi)->sentry_lock); - __allocate_new_segment(sbi, type, true, force); + ret = __allocate_new_segment(sbi, type, true, force); up_write(&SIT_I(sbi)->sentry_lock); f2fs_up_read(&SM_I(sbi)->curseg_lock); + + return ret; +} + +int f2fs_allocate_pinning_section(struct f2fs_sb_info *sbi) +{ + int err; + bool gc_required = true; + +retry: + f2fs_lock_op(sbi); + err = f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false); + f2fs_unlock_op(sbi); + + if (f2fs_sb_has_blkzoned(sbi) && err && gc_required) { + f2fs_down_write(&sbi->gc_lock); + f2fs_gc_range(sbi, 0, GET_SEGNO(sbi, FDEV(0).end_blk), true, 1); + f2fs_up_write(&sbi->gc_lock); + + gc_required = false; + goto retry; + } + + return err; } void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi) @@ -3236,8 +3243,8 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 : GET_SEGNO(sbi, end); if (need_align) { - start_segno = rounddown(start_segno, sbi->segs_per_sec); - end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1; + start_segno = rounddown(start_segno, SEGS_PER_SEC(sbi)); + end_segno = roundup(end_segno + 1, SEGS_PER_SEC(sbi)) - 1; } cpc.reason = CP_DISCARD; @@ -3435,7 +3442,7 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, } *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); - f2fs_bug_on(sbi, curseg->next_blkoff >= sbi->blocks_per_seg); + f2fs_bug_on(sbi, curseg->next_blkoff >= BLKS_PER_SEG(sbi)); f2fs_wait_discard_bio(sbi, *new_blkaddr); @@ -3472,6 +3479,13 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, * new segment. */ if (segment_full) { + if (type == CURSEG_COLD_DATA_PINNED && + !((curseg->segno + 1) % sbi->segs_per_sec)) { + write_sum_page(sbi, curseg->sum_blk, + GET_SUM_BLOCK(sbi, curseg->segno)); + goto skip_new_segment; + } + if (from_gc) { get_atssr_segment(sbi, type, se->type, AT_SSR, se->mtime); @@ -3483,6 +3497,8 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, stat_inc_seg_type(sbi, curseg); } } + +skip_new_segment: /* * segment dirty status should be updated after segment allocation, * so we just need to update status only one time after previous @@ -3491,12 +3507,12 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr)); - if (IS_DATASEG(type)) + if (IS_DATASEG(curseg->seg_type)) atomic64_inc(&sbi->allocated_data_blocks); up_write(&sit_i->sentry_lock); - if (page && IS_NODESEG(type)) { + if (page && IS_NODESEG(curseg->seg_type)) { fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); f2fs_inode_chksum_set(sbi, page); @@ -3505,9 +3521,6 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, if (fio) { struct f2fs_bio_info *io; - if (F2FS_IO_ALIGNED(sbi)) - fio->retry = 0; - INIT_LIST_HEAD(&fio->list); fio->in_list = 1; io = sbi->write_io[fio->type] + fio->temp; @@ -3555,7 +3568,7 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) if (keep_order) f2fs_down_read(&fio->sbi->io_order_lock); -reallocate: + f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, &fio->new_blkaddr, sum, type, fio); if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) @@ -3563,10 +3576,6 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) /* writeout dirty page into bdev */ f2fs_submit_page_write(fio); - if (fio->retry) { - fio->old_blkaddr = fio->new_blkaddr; - goto reallocate; - } f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1); @@ -3653,8 +3662,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) } if (fio->post_read) - invalidate_mapping_pages(META_MAPPING(sbi), - fio->new_blkaddr, fio->new_blkaddr); + f2fs_truncate_meta_inode_pages(sbi, fio->new_blkaddr, 1); stat_inc_inplace_blocks(fio->sbi); @@ -3844,7 +3852,7 @@ void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, for (i = 0; i < len; i++) f2fs_wait_on_block_writeback(inode, blkaddr + i); - invalidate_mapping_pages(META_MAPPING(sbi), blkaddr, blkaddr + len - 1); + f2fs_truncate_meta_inode_pages(sbi, blkaddr, len); } static int read_compacted_summaries(struct f2fs_sb_info *sbi) @@ -3886,7 +3894,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) seg_i->next_blkoff = blk_off; if (seg_i->alloc_type == SSR) - blk_off = sbi->blocks_per_seg; + blk_off = BLKS_PER_SEG(sbi); for (j = 0; j < blk_off; j++) { struct f2fs_summary *s; @@ -3954,7 +3962,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) struct f2fs_summary *ns = &sum->entries[0]; int i; - for (i = 0; i < sbi->blocks_per_seg; i++, ns++) { + for (i = 0; i < BLKS_PER_SEG(sbi); i++, ns++) { ns->version = 0; ns->ofs_in_node = 0; } @@ -4587,21 +4595,20 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks; - if (f2fs_block_unit_discard(sbi)) { - /* build discard map only one time */ - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, + if (!f2fs_block_unit_discard(sbi)) + goto init_discard_map_done; + + /* build discard map only one time */ + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, - se->cur_valid_map, + goto init_discard_map_done; + } + memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += - sbi->blocks_per_seg - + sbi->discard_blks += BLKS_PER_SEG(sbi) - se->valid_blocks; - } - } - +init_discard_map_done: if (__is_large_section(sbi)) get_sec_entry(sbi, start)->valid_blocks += se->valid_blocks; @@ -4741,7 +4748,7 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi) return; mutex_lock(&dirty_i->seglist_lock); - for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { + for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) { valid_blocks = get_valid_blocks(sbi, segno, true); secno = GET_SEC_FROM_SEG(sbi, segno); @@ -4840,7 +4847,7 @@ static int sanity_check_curseg(struct f2fs_sb_info *sbi) if (curseg->alloc_type == SSR) continue; - for (blkofs += 1; blkofs < sbi->blocks_per_seg; blkofs++) { + for (blkofs += 1; blkofs < BLKS_PER_SEG(sbi); blkofs++) { if (!f2fs_test_bit(blkofs, se->cur_valid_map)) continue; out: @@ -5119,7 +5126,7 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg( unsigned int secno; if (!sbi->unusable_blocks_per_sec) - return sbi->blocks_per_seg; + return BLKS_PER_SEG(sbi); secno = GET_SEC_FROM_SEG(sbi, segno); seg_start = START_BLOCK(sbi, segno); @@ -5134,10 +5141,10 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg( */ if (seg_start >= sec_cap_blkaddr) return 0; - if (seg_start + sbi->blocks_per_seg > sec_cap_blkaddr) + if (seg_start + BLKS_PER_SEG(sbi) > sec_cap_blkaddr) return sec_cap_blkaddr - seg_start; - return sbi->blocks_per_seg; + return BLKS_PER_SEG(sbi); } #else int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi) @@ -5163,7 +5170,7 @@ unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, if (f2fs_sb_has_blkzoned(sbi)) return f2fs_usable_zone_blks_in_seg(sbi, segno); - return sbi->blocks_per_seg; + return BLKS_PER_SEG(sbi); } unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, @@ -5172,7 +5179,7 @@ unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, if (f2fs_sb_has_blkzoned(sbi)) return CAP_SEGS_PER_SEC(sbi); - return sbi->segs_per_sec; + return SEGS_PER_SEC(sbi); } /* @@ -5187,14 +5194,14 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi) sit_i->min_mtime = ULLONG_MAX; - for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { + for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) { unsigned int i; unsigned long long mtime = 0; - for (i = 0; i < sbi->segs_per_sec; i++) + for (i = 0; i < SEGS_PER_SEC(sbi); i++) mtime += get_seg_entry(sbi, segno + i)->mtime; - mtime = div_u64(mtime, sbi->segs_per_sec); + mtime = div_u64(mtime, SEGS_PER_SEC(sbi)); if (sit_i->min_mtime > mtime) sit_i->min_mtime = mtime; @@ -5233,7 +5240,7 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi) sm_info->ipu_policy = BIT(F2FS_IPU_FSYNC); sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; - sm_info->min_seq_blocks = sbi->blocks_per_seg; + sm_info->min_seq_blocks = BLKS_PER_SEG(sbi); sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS; sm_info->min_ssr_sections = reserved_sections(sbi); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 8129be788bd56..4595f1cc03828 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -48,21 +48,21 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, #define IS_CURSEC(sbi, secno) \ (((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \ - (sbi)->segs_per_sec) || \ + SEGS_PER_SEC(sbi)) || \ ((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \ - (sbi)->segs_per_sec) || \ + SEGS_PER_SEC(sbi)) || \ ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \ - (sbi)->segs_per_sec) || \ + SEGS_PER_SEC(sbi)) || \ ((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \ - (sbi)->segs_per_sec) || \ + SEGS_PER_SEC(sbi)) || \ ((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \ - (sbi)->segs_per_sec) || \ + SEGS_PER_SEC(sbi)) || \ ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \ - (sbi)->segs_per_sec) || \ + SEGS_PER_SEC(sbi)) || \ ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA_PINNED)->segno / \ - (sbi)->segs_per_sec) || \ + SEGS_PER_SEC(sbi)) || \ ((secno) == CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC)->segno / \ - (sbi)->segs_per_sec)) + SEGS_PER_SEC(sbi))) #define MAIN_BLKADDR(sbi) \ (SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \ @@ -93,24 +93,22 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, #define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> (sbi)->log_blocks_per_seg) #define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \ - (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1)) + (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (BLKS_PER_SEG(sbi) - 1)) #define GET_SEGNO(sbi, blk_addr) \ ((!__is_valid_data_blkaddr(blk_addr)) ? \ NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \ GET_SEGNO_FROM_SEG0(sbi, blk_addr))) -#define BLKS_PER_SEC(sbi) \ - ((sbi)->segs_per_sec * (sbi)->blocks_per_seg) #define CAP_BLKS_PER_SEC(sbi) \ - ((sbi)->segs_per_sec * (sbi)->blocks_per_seg - \ + (SEGS_PER_SEC(sbi) * BLKS_PER_SEG(sbi) - \ (sbi)->unusable_blocks_per_sec) #define CAP_SEGS_PER_SEC(sbi) \ - ((sbi)->segs_per_sec - ((sbi)->unusable_blocks_per_sec >>\ + (SEGS_PER_SEC(sbi) - ((sbi)->unusable_blocks_per_sec >> \ (sbi)->log_blocks_per_seg)) #define GET_SEC_FROM_SEG(sbi, segno) \ - (((segno) == -1) ? -1 : (segno) / (sbi)->segs_per_sec) + (((segno) == -1) ? -1 : (segno) / SEGS_PER_SEC(sbi)) #define GET_SEG_FROM_SEC(sbi, secno) \ - ((secno) * (sbi)->segs_per_sec) + ((secno) * SEGS_PER_SEC(sbi)) #define GET_ZONE_FROM_SEC(sbi, secno) \ (((secno) == -1) ? -1 : (secno) / (sbi)->secs_per_zone) #define GET_ZONE_FROM_SEG(sbi, segno) \ @@ -138,16 +136,6 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi, #define SECTOR_TO_BLOCK(sectors) \ ((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK) -/* - * indicate a block allocation direction: RIGHT and LEFT. - * RIGHT means allocating new sections towards the end of volume. - * LEFT means the opposite direction. - */ -enum { - ALLOC_RIGHT = 0, - ALLOC_LEFT -}; - /* * In the victim_sel_policy->alloc_mode, there are three block allocation modes. * LFS writes data sequentially with cleaning operations. @@ -364,7 +352,7 @@ static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi, unsigned int blocks = 0; int i; - for (i = 0; i < sbi->segs_per_sec; i++, start_segno++) { + for (i = 0; i < SEGS_PER_SEC(sbi); i++, start_segno++) { struct seg_entry *se = get_seg_entry(sbi, start_segno); blocks += se->ckpt_valid_blocks; @@ -449,7 +437,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno) free_i->free_segments++; next = find_next_bit(free_i->free_segmap, - start_segno + sbi->segs_per_sec, start_segno); + start_segno + SEGS_PER_SEC(sbi), start_segno); if (next >= start_segno + usable_segs) { clear_bit(secno, free_i->free_secmap); free_i->free_sections++; @@ -485,7 +473,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi, if (!inmem && IS_CURSEC(sbi, secno)) goto skip_free; next = find_next_bit(free_i->free_segmap, - start_segno + sbi->segs_per_sec, start_segno); + start_segno + SEGS_PER_SEC(sbi), start_segno); if (next >= start_segno + usable_segs) { if (test_and_clear_bit(secno, free_i->free_secmap)) free_i->free_sections++; @@ -573,23 +561,22 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi, unsigned int node_blocks, unsigned int dent_blocks) { - unsigned int segno, left_blocks; + unsigned segno, left_blocks; int i; - /* check current node segment */ + /* check current node sections in the worst case. */ for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) { segno = CURSEG_I(sbi, i)->segno; - left_blocks = f2fs_usable_blks_in_seg(sbi, segno) - - get_seg_entry(sbi, segno)->ckpt_valid_blocks; - + left_blocks = CAP_BLKS_PER_SEC(sbi) - + get_ckpt_valid_blocks(sbi, segno, true); if (node_blocks > left_blocks) return false; } - /* check current data segment */ + /* check current data section for dentry blocks. */ segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno; - left_blocks = f2fs_usable_blks_in_seg(sbi, segno) - - get_seg_entry(sbi, segno)->ckpt_valid_blocks; + left_blocks = CAP_BLKS_PER_SEC(sbi) - + get_ckpt_valid_blocks(sbi, segno, true); if (dent_blocks > left_blocks) return false; return true; @@ -638,7 +625,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, if (free_secs > upper_secs) return false; - else if (free_secs <= lower_secs) + if (free_secs <= lower_secs) return true; return !curseg_space; } @@ -793,10 +780,10 @@ static inline int check_block_count(struct f2fs_sb_info *sbi, return -EFSCORRUPTED; } - if (usable_blks_per_seg < sbi->blocks_per_seg) + if (usable_blks_per_seg < BLKS_PER_SEG(sbi)) f2fs_bug_on(sbi, find_next_bit_le(&raw_sit->valid_map, - sbi->blocks_per_seg, - usable_blks_per_seg) != sbi->blocks_per_seg); + BLKS_PER_SEG(sbi), + usable_blks_per_seg) != BLKS_PER_SEG(sbi)); /* check segment usage, and check boundary of a given segment number */ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > usable_blks_per_seg @@ -915,9 +902,9 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type) return 0; if (type == DATA) - return sbi->blocks_per_seg; + return BLKS_PER_SEG(sbi); else if (type == NODE) - return 8 * sbi->blocks_per_seg; + return 8 * BLKS_PER_SEG(sbi); else if (type == META) return 8 * BIO_MAX_VECS; else @@ -969,3 +956,13 @@ static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force) dcc->discard_wake = true; wake_up_interruptible_all(&dcc->discard_wait_queue); } + +static inline unsigned int first_zoned_segno(struct f2fs_sb_info *sbi) +{ + int devi; + + for (devi = 0; devi < sbi->s_ndevs; devi++) + if (bdev_is_zoned(FDEV(devi).bdev)) + return GET_SEGNO(sbi, FDEV(devi).start_blk); + return 0; +} diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d45ab0992ae59..c363e0a4c7e8c 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -64,21 +64,31 @@ const char *f2fs_fault_name[FAULT_MAX] = { [FAULT_BLKADDR] = "invalid blkaddr", }; -void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, - unsigned int type) +int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate, + unsigned long type) { struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; if (rate) { + if (rate > INT_MAX) + return -EINVAL; atomic_set(&ffi->inject_ops, 0); - ffi->inject_rate = rate; + ffi->inject_rate = (int)rate; } - if (type) - ffi->inject_type = type; + if (type) { + if (type >= BIT(FAULT_MAX)) + return -EINVAL; + ffi->inject_type = (unsigned int)type; + } if (!rate && !type) memset(ffi, 0, sizeof(struct f2fs_fault_info)); + else + f2fs_info(sbi, + "build fault injection attr: rate: %lu, type: 0x%lx", + rate, type); + return 0; } #endif @@ -137,7 +147,6 @@ enum { Opt_resgid, Opt_resuid, Opt_mode, - Opt_io_size_bits, Opt_fault_injection, Opt_fault_type, Opt_lazytime, @@ -216,7 +225,6 @@ static match_table_t f2fs_tokens = { {Opt_resgid, "resgid=%u"}, {Opt_resuid, "resuid=%u"}, {Opt_mode, "mode=%s"}, - {Opt_io_size_bits, "io_bits=%u"}, {Opt_fault_injection, "fault_injection=%u"}, {Opt_fault_type, "fault_type=%u"}, {Opt_lazytime, "lazytime"}, @@ -263,7 +271,8 @@ static match_table_t f2fs_tokens = { {Opt_err, NULL}, }; -void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...) +void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate, + const char *fmt, ...) { struct va_format vaf; va_list args; @@ -274,8 +283,12 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...) level = printk_get_level(fmt); vaf.fmt = printk_skip_level(fmt); vaf.va = &args; - printk("%c%cF2FS-fs (%s): %pV\n", - KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf); + if (limit_rate) + printk_ratelimited("%c%cF2FS-fs (%s): %pV\n", + KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf); + else + printk("%c%cF2FS-fs (%s): %pV\n", + KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf); va_end(args); } @@ -343,46 +356,6 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).s_resgid)); } -static inline int adjust_reserved_segment(struct f2fs_sb_info *sbi) -{ - unsigned int sec_blks = sbi->blocks_per_seg * sbi->segs_per_sec; - unsigned int avg_vblocks; - unsigned int wanted_reserved_segments; - block_t avail_user_block_count; - - if (!F2FS_IO_ALIGNED(sbi)) - return 0; - - /* average valid block count in section in worst case */ - avg_vblocks = sec_blks / F2FS_IO_SIZE(sbi); - - /* - * we need enough free space when migrating one section in worst case - */ - wanted_reserved_segments = (F2FS_IO_SIZE(sbi) / avg_vblocks) * - reserved_segments(sbi); - wanted_reserved_segments -= reserved_segments(sbi); - - avail_user_block_count = sbi->user_block_count - - sbi->current_reserved_blocks - - F2FS_OPTION(sbi).root_reserved_blocks; - - if (wanted_reserved_segments * sbi->blocks_per_seg > - avail_user_block_count) { - f2fs_err(sbi, "IO align feature can't grab additional reserved segment: %u, available segments: %u", - wanted_reserved_segments, - avail_user_block_count >> sbi->log_blocks_per_seg); - return -ENOSPC; - } - - SM_I(sbi)->additional_reserved_segments = wanted_reserved_segments; - - f2fs_info(sbi, "IO align feature needs additional reserved segment: %u", - wanted_reserved_segments); - - return 0; -} - static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi) { if (!F2FS_OPTION(sbi).unusable_cap_perc) @@ -663,7 +636,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) #ifdef CONFIG_F2FS_FS_ZSTD static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) { - unsigned int level; + int level; int len = 4; if (strlen(str) == len) { @@ -677,9 +650,15 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) f2fs_info(sbi, "wrong format, e.g. :"); return -EINVAL; } - if (kstrtouint(str + 1, 10, &level)) + if (kstrtoint(str + 1, 10, &level)) return -EINVAL; + /* f2fs does not support negative compress level now */ + if (level < 0) { + f2fs_info(sbi, "do not support negative compress level: %d", level); + return -ERANGE; + } + if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; @@ -763,10 +742,8 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) clear_opt(sbi, DISCARD); break; case Opt_noheap: - set_opt(sbi, NOHEAP); - break; case Opt_heap: - clear_opt(sbi, NOHEAP); + f2fs_warn(sbi, "heap/no_heap options were deprecated"); break; #ifdef CONFIG_F2FS_FS_XATTR case Opt_user_xattr: @@ -913,28 +890,21 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) } kfree(name); break; - case Opt_io_size_bits: - if (args->from && match_int(args, &arg)) - return -EINVAL; - if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) { - f2fs_warn(sbi, "Not support %ld, larger than %d", - BIT(arg), BIO_MAX_VECS); - return -EINVAL; - } - F2FS_OPTION(sbi).write_io_size_bits = arg; - break; #ifdef CONFIG_F2FS_FAULT_INJECTION case Opt_fault_injection: if (args->from && match_int(args, &arg)) return -EINVAL; - f2fs_build_fault_attr(sbi, arg, F2FS_ALL_FAULT_TYPE); + if (f2fs_build_fault_attr(sbi, arg, + F2FS_ALL_FAULT_TYPE)) + return -EINVAL; set_opt(sbi, FAULT_INJECTION); break; case Opt_fault_type: if (args->from && match_int(args, &arg)) return -EINVAL; - f2fs_build_fault_attr(sbi, 0, arg); + if (f2fs_build_fault_attr(sbi, 0, arg)) + return -EINVAL; set_opt(sbi, FAULT_INJECTION); break; #else @@ -1392,12 +1362,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) } #endif - if (F2FS_IO_SIZE_BITS(sbi) && !f2fs_lfs_mode(sbi)) { - f2fs_err(sbi, "Should set mode=lfs with %luKB-sized IO", - F2FS_IO_SIZE_KB(sbi)); - return -EINVAL; - } - if (test_opt(sbi, INLINE_XATTR_SIZE)) { int min_size, max_size; @@ -1718,7 +1682,6 @@ static void f2fs_put_super(struct super_block *sb) f2fs_destroy_page_array_cache(sbi); f2fs_destroy_xattr_caches(sbi); - mempool_destroy(sbi->write_io_dummy); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) kfree(F2FS_OPTION(sbi).s_qf_names[i]); @@ -2009,10 +1972,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) } else { seq_puts(seq, ",nodiscard"); } - if (test_opt(sbi, NOHEAP)) - seq_puts(seq, ",no_heap"); - else - seq_puts(seq, ",heap"); #ifdef CONFIG_F2FS_FS_XATTR if (test_opt(sbi, XATTR_USER)) seq_puts(seq, ",user_xattr"); @@ -2078,9 +2037,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) F2FS_OPTION(sbi).s_resuid), from_kgid_munged(&init_user_ns, F2FS_OPTION(sbi).s_resgid)); - if (F2FS_IO_SIZE_BITS(sbi)) - seq_printf(seq, ",io_bits=%u", - F2FS_OPTION(sbi).write_io_size_bits); #ifdef CONFIG_F2FS_FAULT_INJECTION if (test_opt(sbi, FAULT_INJECTION)) { seq_printf(seq, ",fault_injection=%u", @@ -2187,12 +2143,9 @@ static void default_options(struct f2fs_sb_info *sbi, bool remount) F2FS_OPTION(sbi).memory_mode = MEMORY_MODE_NORMAL; F2FS_OPTION(sbi).errors = MOUNT_ERRORS_CONTINUE; - sbi->sb->s_flags &= ~SB_INLINECRYPT; - set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); set_opt(sbi, INLINE_DENTRY); - set_opt(sbi, NOHEAP); set_opt(sbi, MERGE_CHECKPOINT); F2FS_OPTION(sbi).unusable_cap = 0; sbi->sb->s_flags |= SB_LAZYTIME; @@ -2332,7 +2285,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) bool no_read_extent_cache = !test_opt(sbi, READ_EXTENT_CACHE); bool no_age_extent_cache = !test_opt(sbi, AGE_EXTENT_CACHE); bool enable_checkpoint = !test_opt(sbi, DISABLE_CHECKPOINT); - bool no_io_align = !F2FS_IO_ALIGNED(sbi); bool no_atgc = !test_opt(sbi, ATGC); bool no_discard = !test_opt(sbi, DISCARD); bool no_compress_cache = !test_opt(sbi, COMPRESS_CACHE); @@ -2440,12 +2392,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if (no_io_align == !!F2FS_IO_ALIGNED(sbi)) { - err = -EINVAL; - f2fs_warn(sbi, "switch io_bits option is not allowed"); - goto restore_opts; - } - if (no_compress_cache == !!test_opt(sbi, COMPRESS_CACHE)) { err = -EINVAL; f2fs_warn(sbi, "switch compress_cache option is not allowed"); @@ -2768,7 +2714,7 @@ int f2fs_dquot_initialize(struct inode *inode) return dquot_initialize(inode); } -static struct dquot **f2fs_get_dquots(struct inode *inode) +static struct dquot __rcu **f2fs_get_dquots(struct inode *inode) { return F2FS_I(inode)->i_dquot; } @@ -3706,7 +3652,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) } main_segs = le32_to_cpu(raw_super->segment_count_main); - blocks_per_seg = sbi->blocks_per_seg; + blocks_per_seg = BLKS_PER_SEG(sbi); for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || @@ -3819,8 +3765,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone); sbi->total_sections = le32_to_cpu(raw_super->section_count); sbi->total_node_count = - (le32_to_cpu(raw_super->segment_count_nat) / 2) - * sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK; + ((le32_to_cpu(raw_super->segment_count_nat) / 2) * + NAT_ENTRY_PER_BLOCK) << sbi->log_blocks_per_seg; F2FS_ROOT_INO(sbi) = le32_to_cpu(raw_super->root_ino); F2FS_NODE_INO(sbi) = le32_to_cpu(raw_super->node_ino); F2FS_META_INO(sbi) = le32_to_cpu(raw_super->meta_ino); @@ -3829,7 +3775,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->next_victim_seg[BG_GC] = NULL_SEGNO; sbi->next_victim_seg[FG_GC] = NULL_SEGNO; sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH; - sbi->migration_granularity = sbi->segs_per_sec; + sbi->migration_granularity = SEGS_PER_SEC(sbi); sbi->seq_file_ra_mul = MIN_RA_MUL; sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE; sbi->max_fragment_hole = DEF_FRAGMENT_SIZE; @@ -3930,11 +3876,6 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) return 0; zone_sectors = bdev_zone_sectors(bdev); - if (!is_power_of_2(zone_sectors)) { - f2fs_err(sbi, "F2FS does not support non power of 2 zone sizes\n"); - return -EINVAL; - } - if (sbi->blocks_per_blkz && sbi->blocks_per_blkz != SECTOR_TO_BLOCK(zone_sectors)) return -EINVAL; @@ -4195,9 +4136,15 @@ void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason, if (shutdown) set_sbi_flag(sbi, SBI_IS_SHUTDOWN); - /* continue filesystem operators if errors=continue */ - if (continue_fs || f2fs_readonly(sb)) + /* + * Continue filesystem operators if errors=continue. Should not set + * RO by shutdown, since RO bypasses thaw_super which can hang the + * system. + */ + if (continue_fs || f2fs_readonly(sb) || shutdown) { + f2fs_warn(sbi, "Stopped filesystem due to reason: %d", reason); return; + } f2fs_warn(sbi, "Remounting filesystem read-only"); /* @@ -4305,8 +4252,6 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) FDEV(i).total_segments, FDEV(i).start_blk, FDEV(i).end_blk); } - f2fs_info(sbi, - "IO Block Size: %8ld KB", F2FS_IO_SIZE_KB(sbi)); return 0; } @@ -4519,19 +4464,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) if (err) goto free_iostat; - if (F2FS_IO_ALIGNED(sbi)) { - sbi->write_io_dummy = - mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0); - if (!sbi->write_io_dummy) { - err = -ENOMEM; - goto free_percpu; - } - } - /* init per sbi slab cache */ err = f2fs_init_xattr_caches(sbi); if (err) - goto free_io_dummy; + goto free_percpu; err = f2fs_init_page_array_cache(sbi); if (err) goto free_xattr_cache; @@ -4619,10 +4555,6 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) goto free_nm; } - err = adjust_reserved_segment(sbi); - if (err) - goto free_nm; - /* For write statistics */ sbi->sectors_written_start = f2fs_get_sectors_written(sbi); @@ -4853,8 +4785,6 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) f2fs_destroy_page_array_cache(sbi); free_xattr_cache: f2fs_destroy_xattr_caches(sbi); -free_io_dummy: - mempool_destroy(sbi->write_io_dummy); free_percpu: destroy_percpu_info(sbi); free_iostat: diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a7ec55c7bb20c..180a12cdca02e 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -484,17 +484,23 @@ static ssize_t __sbi_store(struct f2fs_attr *a, if (ret < 0) return ret; #ifdef CONFIG_F2FS_FAULT_INJECTION - if (a->struct_type == FAULT_INFO_TYPE && t >= BIT(FAULT_MAX)) - return -EINVAL; - if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX) - return -EINVAL; + if (a->struct_type == FAULT_INFO_TYPE) { + if (f2fs_build_fault_attr(sbi, 0, t)) + return -EINVAL; + return count; + } + if (a->struct_type == FAULT_INFO_RATE) { + if (f2fs_build_fault_attr(sbi, t, 0)) + return -EINVAL; + return count; + } #endif if (a->struct_type == RESERVED_BLOCKS) { spin_lock(&sbi->stat_lock); if (t > (unsigned long)(sbi->user_block_count - F2FS_OPTION(sbi).root_reserved_blocks - - sbi->blocks_per_seg * - SM_I(sbi)->additional_reserved_segments)) { + (SM_I(sbi)->additional_reserved_segments << + sbi->log_blocks_per_seg))) { spin_unlock(&sbi->stat_lock); return -EINVAL; } @@ -551,7 +557,7 @@ static ssize_t __sbi_store(struct f2fs_attr *a, } if (!strcmp(a->attr.name, "migration_granularity")) { - if (t == 0 || t > sbi->segs_per_sec) + if (t == 0 || t > SEGS_PER_SEC(sbi)) return -EINVAL; } diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index c52e63e10d35c..509eea96a457d 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; diff --git a/fs/fcntl.c b/fs/fcntl.c index c80a6acad742f..3ff707bf2743a 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -268,7 +268,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) } #endif -static bool rw_hint_valid(enum rw_hint hint) +static bool rw_hint_valid(u64 hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: @@ -288,19 +288,17 @@ static long fcntl_rw_hint(struct file *file, unsigned int cmd, { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; - enum rw_hint hint; - u64 h; + u64 hint; switch (cmd) { case F_GET_RW_HINT: - h = inode->i_write_hint; - if (copy_to_user(argp, &h, sizeof(*argp))) + hint = inode->i_write_hint; + if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: - if (copy_from_user(&h, argp, sizeof(h))) + if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; - hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; diff --git a/fs/fhandle.c b/fs/fhandle.c index 18b3ba8dc8ead..57a12614addfd 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -36,7 +36,7 @@ static long do_sys_name_to_handle(const struct path *path, if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; - handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes, GFP_KERNEL); if (!handle) return -ENOMEM; diff --git a/fs/file.c b/fs/file.c index 3b683b9101d84..e1f2381d6e6b6 100644 --- a/fs/file.c +++ b/fs/file.c @@ -818,6 +818,7 @@ struct file *file_close_fd(unsigned int fd) return file; } +EXPORT_SYMBOL(file_close_fd); void do_close_on_exec(struct files_struct *files) { diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 3d84fcc471c60..e89222ae285e9 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2044,6 +2044,7 @@ static long wb_writeback(struct bdi_writeback *wb, struct inode *inode; long progress; struct blk_plug plug; + bool queued = false; blk_start_plug(&plug); for (;;) { @@ -2086,8 +2087,10 @@ static long wb_writeback(struct bdi_writeback *wb, dirtied_before = jiffies; trace_writeback_start(wb, work); - if (list_empty(&wb->b_io)) + if (list_empty(&wb->b_io)) { queue_io(wb, work, dirtied_before); + queued = true; + } if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else @@ -2102,7 +2105,7 @@ static long wb_writeback(struct bdi_writeback *wb, * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ - if (progress) { + if (progress || !queued) { spin_unlock(&wb->list_lock); continue; } diff --git a/fs/fs_context.c b/fs/fs_context.c index 98589aae52085..54b122aa5074c 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -599,7 +599,7 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) param->key); } - if (size + len + 2 > PAGE_SIZE) + if (len > PAGE_SIZE || size + len + 2 > PAGE_SIZE) return invalf(fc, "VFS: Legacy: Cumulative options too large"); if (strchr(param->key, ',') || (param->type == fs_value_is_string && diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index d19cbf34c6341..fc7cdd2b1fac6 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -391,6 +391,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name err = -EIO; if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; + if (outarg->nodeid == FUSE_ROOT_ID && outarg->generation != 0) { + pr_warn_once("root generation should be zero\n"); + outarg->generation = 0; + } *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, &outarg->attr, ATTR_TIMEOUT(outarg), @@ -462,29 +466,29 @@ static int get_security_context(struct dentry *entry, umode_t mode, { struct fuse_secctx *fctx; struct fuse_secctx_header *header; - void *ctx = NULL, *ptr; - u32 ctxlen, total_len = sizeof(*header); + struct lsmcontext lsmctx = { }; + void *ptr; + u32 total_len = sizeof(*header); int err, nr_ctx = 0; - const char *name; + const char *name = NULL; size_t namelen; err = security_dentry_init_security(entry, mode, &entry->d_name, - &name, &ctx, &ctxlen); - if (err) { - if (err != -EOPNOTSUPP) - goto out_err; - /* No LSM is supporting this security hook. Ignore error */ - ctxlen = 0; - ctx = NULL; - } + &name, &lsmctx); - if (ctxlen) { + /* If no LSM is supporting this security hook ignore error */ + if (err && err != -EOPNOTSUPP) + goto out_err; + + if (lsmctx.len) { nr_ctx = 1; namelen = strlen(name) + 1; err = -EIO; - if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || ctxlen > S32_MAX)) + if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || + lsmctx.len > S32_MAX)) goto out_err; - total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + ctxlen); + total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + + lsmctx.len); } err = -ENOMEM; @@ -497,19 +501,20 @@ static int get_security_context(struct dentry *entry, umode_t mode, ptr += sizeof(*header); if (nr_ctx) { fctx = ptr; - fctx->size = ctxlen; + fctx->size = lsmctx.len; ptr += sizeof(*fctx); strcpy(ptr, name); ptr += namelen; - memcpy(ptr, ctx, ctxlen); + memcpy(ptr, lsmctx.context, lsmctx.len); } ext->size = total_len; ext->value = header; err = 0; out_err: - kfree(ctx); + if (nr_ctx) + security_release_secctx(&lsmctx); return err; } @@ -1210,7 +1215,7 @@ static int fuse_do_statx(struct inode *inode, struct file *file, if (((sx->mask & STATX_SIZE) && !fuse_valid_size(sx->size)) || ((sx->mask & STATX_TYPE) && (!fuse_valid_type(sx->mode) || inode_wrong_type(inode, sx->mode)))) { - make_bad_inode(inode); + fuse_make_bad(inode); return -EIO; } @@ -1313,6 +1318,7 @@ static int fuse_update_get_attr(struct inode *inode, struct file *file, err = fuse_do_statx(inode, file, stat); if (err == -ENOSYS) { fc->no_statx = 1; + err = 0; goto retry; } } else { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 148a71b8b4d0e..b9cff9b6ca1b8 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2468,7 +2468,8 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) return fuse_dax_mmap(file, vma); if (ff->open_flags & FOPEN_DIRECT_IO) { - /* Can't provide the coherency needed for MAP_SHARED + /* + * Can't provide the coherency needed for MAP_SHARED * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set. */ if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap) @@ -2476,7 +2477,10 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) invalidate_inode_pages2(file->f_mapping); - return generic_file_mmap(file, vma); + if (!(vma->vm_flags & VM_MAYSHARE)) { + /* MAP_PRIVATE */ + return generic_file_mmap(file, vma); + } } if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index bcbe344888627..20924e799c9f5 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -940,7 +940,6 @@ static inline bool fuse_stale_inode(const struct inode *inode, int generation, static inline void fuse_make_bad(struct inode *inode) { - remove_inode_hash(inode); set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 516ea2979a90f..f73865751c732 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -469,8 +469,11 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); - iput(inode); - goto retry; + if (inode != d_inode(sb->s_root)) { + remove_inode_hash(inode); + iput(inode); + goto retry; + } } fi = get_fuse_inode(inode); spin_lock(&fi->lock); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index d9ccfd27e4f11..643175498d1c3 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1718,7 +1718,8 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) struct buffer_head *dibh, *bh; struct gfs2_holder rd_gh; unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift; - u64 lblock = (offset + (1 << bsize_shift) - 1) >> bsize_shift; + unsigned int bsize = 1 << bsize_shift; + u64 lblock = (offset + bsize - 1) >> bsize_shift; __u16 start_list[GFS2_MAX_META_HEIGHT]; __u16 __end_list[GFS2_MAX_META_HEIGHT], *end_list = NULL; unsigned int start_aligned, end_aligned; @@ -1729,7 +1730,7 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) u64 prev_bnr = 0; __be64 *start, *end; - if (offset >= maxsize) { + if (offset + bsize - 1 >= maxsize) { /* * The starting point lies beyond the allocated metadata; * there are no blocks to deallocate. diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 34540f9d011ca..2507fe34cbdf0 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -166,19 +166,45 @@ static bool glock_blocked_by_withdraw(struct gfs2_glock *gl) return true; } -void gfs2_glock_free(struct gfs2_glock *gl) +static void __gfs2_glock_free(struct gfs2_glock *gl) { - struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - - gfs2_glock_assert_withdraw(gl, atomic_read(&gl->gl_revokes) == 0); rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms); smp_mb(); wake_up_glock(gl); call_rcu(&gl->gl_rcu, gfs2_glock_dealloc); +} + +void gfs2_glock_free(struct gfs2_glock *gl) { + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + __gfs2_glock_free(gl); + if (atomic_dec_and_test(&sdp->sd_glock_disposal)) + wake_up(&sdp->sd_kill_wait); +} + +void gfs2_glock_free_later(struct gfs2_glock *gl) { + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + spin_lock(&lru_lock); + list_add(&gl->gl_lru, &sdp->sd_dead_glocks); + spin_unlock(&lru_lock); if (atomic_dec_and_test(&sdp->sd_glock_disposal)) wake_up(&sdp->sd_kill_wait); } +static void gfs2_free_dead_glocks(struct gfs2_sbd *sdp) +{ + struct list_head *list = &sdp->sd_dead_glocks; + + while(!list_empty(list)) { + struct gfs2_glock *gl; + + gl = list_first_entry(list, struct gfs2_glock, gl_lru); + list_del_init(&gl->gl_lru); + __gfs2_glock_free(gl); + } +} + /** * gfs2_glock_hold() - increment reference count on glock * @gl: The glock to hold @@ -591,7 +617,6 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) struct gfs2_holder *gh; unsigned state = ret & LM_OUT_ST_MASK; - spin_lock(&gl->gl_lockref.lock); trace_gfs2_glock_state_change(gl, state); state_change(gl, state); gh = find_first_waiter(gl); @@ -639,7 +664,6 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) gl->gl_target, state); GLOCK_BUG_ON(gl, 1); } - spin_unlock(&gl->gl_lockref.lock); return; } @@ -662,7 +686,6 @@ static void finish_xmote(struct gfs2_glock *gl, unsigned int ret) } out: clear_bit(GLF_LOCK, &gl->gl_flags); - spin_unlock(&gl->gl_lockref.lock); } static bool is_system_glock(struct gfs2_glock *gl) @@ -690,6 +713,7 @@ __acquires(&gl->gl_lockref.lock) { const struct gfs2_glock_operations *glops = gl->gl_ops; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct lm_lockstruct *ls = &sdp->sd_lockstruct; unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0); int ret; @@ -718,6 +742,9 @@ __acquires(&gl->gl_lockref.lock) (gl->gl_state == LM_ST_EXCLUSIVE) || (lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB))) clear_bit(GLF_BLOCKING, &gl->gl_flags); + if (!glops->go_inval && !glops->go_sync) + goto skip_inval; + spin_unlock(&gl->gl_lockref.lock); if (glops->go_sync) { ret = glops->go_sync(gl); @@ -730,6 +757,7 @@ __acquires(&gl->gl_lockref.lock) fs_err(sdp, "Error %d syncing glock \n", ret); gfs2_dump_glock(NULL, gl, true); } + spin_lock(&gl->gl_lockref.lock); goto skip_inval; } } @@ -750,9 +778,10 @@ __acquires(&gl->gl_lockref.lock) glops->go_inval(gl, target == LM_ST_DEFERRED ? 0 : DIO_METADATA); clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags); } + spin_lock(&gl->gl_lockref.lock); skip_inval: - gfs2_glock_hold(gl); + gl->gl_lockref.count++; /* * Check for an error encountered since we called go_sync and go_inval. * If so, we can't withdraw from the glock code because the withdraw @@ -794,31 +823,37 @@ __acquires(&gl->gl_lockref.lock) */ clear_bit(GLF_LOCK, &gl->gl_flags); clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); - gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD); - goto out; + __gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD); + return; } else { clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags); } } - if (sdp->sd_lockstruct.ls_ops->lm_lock) { - /* lock_dlm */ - ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags); + if (ls->ls_ops->lm_lock) { + spin_unlock(&gl->gl_lockref.lock); + ret = ls->ls_ops->lm_lock(gl, target, lck_flags); + spin_lock(&gl->gl_lockref.lock); + if (ret == -EINVAL && gl->gl_target == LM_ST_UNLOCKED && target == LM_ST_UNLOCKED && - test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags)) { - finish_xmote(gl, target); - gfs2_glock_queue_work(gl, 0); + test_bit(DFL_UNMOUNT, &ls->ls_recover_flags)) { + /* + * The lockspace has been released and the lock has + * been unlocked implicitly. + */ } else if (ret) { fs_err(sdp, "lm_lock ret %d\n", ret); - GLOCK_BUG_ON(gl, !gfs2_withdrawing_or_withdrawn(sdp)); + target = gl->gl_state | LM_OUT_ERROR; + } else { + /* The operation will be completed asynchronously. */ + return; } - } else { /* lock_nolock */ - finish_xmote(gl, target); - gfs2_glock_queue_work(gl, 0); } -out: - spin_lock(&gl->gl_lockref.lock); + + /* Complete the operation now. */ + finish_xmote(gl, target); + __gfs2_glock_queue_work(gl, 0); } /** @@ -1071,11 +1106,12 @@ static void glock_work_func(struct work_struct *work) struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work); unsigned int drop_refs = 1; - if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) { + spin_lock(&gl->gl_lockref.lock); + if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags)) { + clear_bit(GLF_REPLY_PENDING, &gl->gl_flags); finish_xmote(gl, gl->gl_reply); drop_refs++; } - spin_lock(&gl->gl_lockref.lock); if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && gl->gl_state != LM_ST_UNLOCKED && gl->gl_demote_state != LM_ST_EXCLUSIVE) { @@ -2148,8 +2184,11 @@ static void thaw_glock(struct gfs2_glock *gl) return; if (!lockref_get_not_dead(&gl->gl_lockref)) return; + + spin_lock(&gl->gl_lockref.lock); set_bit(GLF_REPLY_PENDING, &gl->gl_flags); - gfs2_glock_queue_work(gl, 0); + __gfs2_glock_queue_work(gl, 0); + spin_unlock(&gl->gl_lockref.lock); } /** @@ -2225,6 +2264,8 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp) wait_event_timeout(sdp->sd_kill_wait, atomic_read(&sdp->sd_glock_disposal) == 0, HZ * 600); + gfs2_lm_unmount(sdp); + gfs2_free_dead_glocks(sdp); glock_hash_walk(dump_glock_func, sdp); } diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 0114f3e0ebe01..86987a59a0580 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -252,6 +252,7 @@ void gfs2_gl_dq_holders(struct gfs2_sbd *sdp); void gfs2_glock_thaw(struct gfs2_sbd *sdp); void gfs2_glock_add_to_lru(struct gfs2_glock *gl); void gfs2_glock_free(struct gfs2_glock *gl); +void gfs2_glock_free_later(struct gfs2_glock *gl); int __init gfs2_glock_init(void); void gfs2_glock_exit(void); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 45653cbc8a87d..e0e8dfeee777d 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -82,6 +82,9 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync, GLOCK_BUG_ON(gl, !fsync && atomic_read(&gl->gl_ail_count)); spin_unlock(&sdp->sd_ail_lock); gfs2_log_unlock(sdp); + + if (gfs2_withdrawing(sdp)) + gfs2_withdraw(sdp); } diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 95a334d64da2a..60abd7050c998 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -838,6 +838,7 @@ struct gfs2_sbd { /* For quiescing the filesystem */ struct gfs2_holder sd_freeze_gh; struct mutex sd_freeze_mutex; + struct list_head sd_dead_glocks; char sd_fsname[GFS2_FSNAME_LEN + 3 * sizeof(int) + 2]; char sd_table_name[GFS2_FSNAME_LEN]; diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index d1ac5d0679ea6..e028e55e67d95 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -121,6 +121,11 @@ static void gdlm_ast(void *arg) struct gfs2_glock *gl = arg; unsigned ret = gl->gl_state; + /* If the glock is dead, we only react to a dlm_unlock() reply. */ + if (__lockref_is_dead(&gl->gl_lockref) && + gl->gl_lksb.sb_status != -DLM_EUNLOCK) + return; + gfs2_update_reply_times(gl); BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED); @@ -171,6 +176,9 @@ static void gdlm_bast(void *arg, int mode) { struct gfs2_glock *gl = arg; + if (__lockref_is_dead(&gl->gl_lockref)) + return; + switch (mode) { case DLM_LOCK_EX: gfs2_glock_cb(gl, LM_ST_UNLOCKED); @@ -291,8 +299,12 @@ static void gdlm_put_lock(struct gfs2_glock *gl) struct lm_lockstruct *ls = &sdp->sd_lockstruct; int error; - if (gl->gl_lksb.sb_lkid == 0) - goto out_free; + BUG_ON(!__lockref_is_dead(&gl->gl_lockref)); + + if (gl->gl_lksb.sb_lkid == 0) { + gfs2_glock_free(gl); + return; + } clear_bit(GLF_BLOCKING, &gl->gl_flags); gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT); @@ -300,13 +312,17 @@ static void gdlm_put_lock(struct gfs2_glock *gl) gfs2_update_request_times(gl); /* don't want to call dlm if we've unmounted the lock protocol */ - if (test_bit(DFL_UNMOUNT, &ls->ls_recover_flags)) - goto out_free; + if (test_bit(DFL_UNMOUNT, &ls->ls_recover_flags)) { + gfs2_glock_free(gl); + return; + } /* don't want to skip dlm_unlock writing the lvb when lock has one */ if (test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags) && - !gl->gl_lksb.sb_lvbptr) - goto out_free; + !gl->gl_lksb.sb_lvbptr) { + gfs2_glock_free_later(gl); + return; + } again: error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK, @@ -321,10 +337,6 @@ static void gdlm_put_lock(struct gfs2_glock *gl) gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number, error); } - return; - -out_free: - gfs2_glock_free(gl); } static void gdlm_cancel(struct gfs2_glock *gl) diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1281e60be6390..db0df091a6a76 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -136,6 +136,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) atomic_set(&sdp->sd_log_in_flight, 0); init_waitqueue_head(&sdp->sd_log_flush_wait); mutex_init(&sdp->sd_freeze_mutex); + INIT_LIST_HEAD(&sdp->sd_dead_glocks); return sdp; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index e5f79466340d2..2d780b4701a23 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -646,10 +646,7 @@ static void gfs2_put_super(struct super_block *sb) gfs2_gl_hash_clear(sdp); truncate_inode_pages_final(&sdp->sd_aspace); gfs2_delete_debugfs_file(sdp); - /* Unmount the locking protocol */ - gfs2_lm_unmount(sdp); - /* At this point, we're through participating in the lockspace */ gfs2_sys_fs_del(sdp); free_sbd(sdp); } diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index f52141ce94853..fc3ecb180ac53 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -350,7 +350,6 @@ int gfs2_withdraw(struct gfs2_sbd *sdp) fs_err(sdp, "telling LM to unmount\n"); lm->lm_unmount(sdp); } - set_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags); fs_err(sdp, "File system withdrawn\n"); dump_stack(); clear_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags); diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index b0cb704009963..ce9346099c72d 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -30,7 +30,7 @@ struct hfsplus_wd { * @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes * @buf: buffer for I/O * @data: output pointer for location of requested data - * @opf: request op flags + * @opf: I/O operation type and flags * * The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than * HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 093c4515b22a5..9a16b6642282e 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -871,11 +871,11 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) { loff_t length = iomap_length(iter); - size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; loff_t pos = iter->pos; ssize_t written = 0; long status = 0; struct address_space *mapping = iter->inode->i_mapping; + size_t chunk = mapping_max_folio_size(mapping); unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0; do { @@ -1833,16 +1833,10 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, if (unlikely(error)) { /* * Let the filesystem know what portion of the current page - * failed to map. If the page hasn't been added to ioend, it - * won't be affected by I/O completion and we must unlock it - * now. + * failed to map. */ if (wpc->ops->discard_folio) wpc->ops->discard_folio(folio, pos); - if (!count) { - folio_unlock(folio); - goto done; - } } /* @@ -1851,6 +1845,16 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, * all the dirty bits in the folio here. */ iomap_clear_range_dirty(folio, 0, folio_size(folio)); + + /* + * If the page hasn't been added to the ioend, it won't be affected by + * I/O completion and we must unlock it now. + */ + if (error && !count) { + folio_unlock(folio); + goto done; + } + folio_start_writeback(folio); folio_unlock(folio); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 3e4d53e26f947..379c9edc907cf 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -908,8 +908,22 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) * we then decide whether to use the Joliet descriptor. */ inode = isofs_iget(s, sbi->s_firstdatazone, 0); - if (IS_ERR(inode)) - goto out_no_root; + + /* + * Fix for broken CDs with a corrupt root inode but a correct Joliet + * root directory. + */ + if (IS_ERR(inode)) { + if (joliet_level && sbi->s_firstdatazone != first_data_zone) { + printk(KERN_NOTICE + "ISOFS: root inode is unusable. " + "Disabling Rock Ridge and switching to Joliet."); + sbi->s_rock = 0; + inode = NULL; + } else { + goto out_no_root; + } + } /* * Fix for broken CDs with Rock Ridge and empty ISO root directory but diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index 00224f3a8d6e7..defb4162c3d5b 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -1110,6 +1110,9 @@ int do_jffs2_setxattr(struct inode *inode, int xprefix, const char *xname, return rc; request = PAD(sizeof(struct jffs2_raw_xattr) + strlen(xname) + 1 + size); + if (request > c->sector_size - c->cleanmarker_size) + return -ERANGE; + rc = jffs2_reserve_space(c, request, &length, ALLOC_NORMAL, JFFS2_SUMMARY_XATTR_SIZE); if (rc) { diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index dd4264aa9bedd..10934f9a11be3 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -92,7 +92,7 @@ struct jfs_inode_info { } link; } u; #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif u32 dev; /* will die when we get wide dev_t */ struct inode vfs_inode; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 8d8e556bd6104..ff135a43b5b7b 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -824,7 +824,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type, return len - towrite; } -static struct dquot **jfs_get_dquots(struct inode *inode) +static struct dquot __rcu **jfs_get_dquots(struct inode *inode) { return JFS_IP(inode)->i_dquot; } diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 0fb7afac298e1..9987055293b35 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -557,9 +557,11 @@ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size) size_check: if (EALIST_SIZE(ea_buf->xattr) != ea_size) { + int size = min_t(int, EALIST_SIZE(ea_buf->xattr), ea_size); + printk(KERN_ERR "ea_get: invalid extended attribute\n"); print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, - ea_buf->xattr, ea_size, 1); + ea_buf->xattr, size, 1); ea_release(inode, ea_buf); rc = -EIO; goto clean_up; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index bce1d7ac95caa..458519e416fe7 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -529,6 +529,20 @@ void kernfs_get(struct kernfs_node *kn) } EXPORT_SYMBOL_GPL(kernfs_get); +static void kernfs_free_rcu(struct rcu_head *rcu) +{ + struct kernfs_node *kn = container_of(rcu, struct kernfs_node, rcu); + + kfree_const(kn->name); + + if (kn->iattr) { + simple_xattrs_free(&kn->iattr->xattrs, NULL); + kmem_cache_free(kernfs_iattrs_cache, kn->iattr); + } + + kmem_cache_free(kernfs_node_cache, kn); +} + /** * kernfs_put - put a reference count on a kernfs_node * @kn: the target kernfs_node @@ -557,16 +571,11 @@ void kernfs_put(struct kernfs_node *kn) if (kernfs_type(kn) == KERNFS_LINK) kernfs_put(kn->symlink.target_kn); - kfree_const(kn->name); - - if (kn->iattr) { - simple_xattrs_free(&kn->iattr->xattrs, NULL); - kmem_cache_free(kernfs_iattrs_cache, kn->iattr); - } spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&kernfs_idr_lock); - kmem_cache_free(kernfs_node_cache, kn); + + call_rcu(&kn->rcu, kernfs_free_rcu); kn = parent; if (kn) { @@ -575,7 +584,7 @@ void kernfs_put(struct kernfs_node *kn) } else { /* just released the root kn, free @root too */ idr_destroy(&root->ino_idr); - kfree(root); + kfree_rcu(root, rcu); } } EXPORT_SYMBOL_GPL(kernfs_put); @@ -715,7 +724,7 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, ino_t ino = kernfs_id_ino(id); u32 gen = kernfs_id_gen(id); - spin_lock(&kernfs_idr_lock); + rcu_read_lock(); kn = idr_find(&root->ino_idr, (u32)ino); if (!kn) @@ -739,10 +748,10 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, if (unlikely(!__kernfs_active(kn) || !atomic_inc_not_zero(&kn->count))) goto err_unlock; - spin_unlock(&kernfs_idr_lock); + rcu_read_unlock(); return kn; err_unlock: - spin_unlock(&kernfs_idr_lock); + rcu_read_unlock(); return NULL; } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index ffa4565c275a7..b7f943f33366d 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -634,11 +634,18 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * - * Both paths of the branch look the same. They're supposed to + * For similar reasons, writable and readonly files are given different + * lockdep key, because the writable file /sys/power/resume may call vfs + * lookup helpers for arbitrary paths and readonly files can be read by + * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs. + * + * All three cases look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); + else if (file->f_mode & FMODE_WRITE) + mutex_init(&of->mutex); else mutex_init(&of->mutex); diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 237f2764b9412..b42ee6547cdc1 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -49,6 +49,8 @@ struct kernfs_root { struct rw_semaphore kernfs_rwsem; struct rw_semaphore kernfs_iattr_rwsem; struct rw_semaphore kernfs_supers_rwsem; + + struct rcu_head rcu; }; /* +1 to avoid triggering overflow warning when negating it */ diff --git a/fs/libfs.c b/fs/libfs.c index eec6031b01554..ef700d39f0f35 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -240,17 +240,22 @@ const struct inode_operations simple_dir_inode_operations = { }; EXPORT_SYMBOL(simple_dir_inode_operations); -static void offset_set(struct dentry *dentry, u32 offset) +/* 0 is '.', 1 is '..', so always start with offset 2 or more */ +enum { + DIR_OFFSET_MIN = 2, +}; + +static void offset_set(struct dentry *dentry, long offset) { - dentry->d_fsdata = (void *)((uintptr_t)(offset)); + dentry->d_fsdata = (void *)offset; } -static u32 dentry2offset(struct dentry *dentry) +static long dentry2offset(struct dentry *dentry) { - return (u32)((uintptr_t)(dentry->d_fsdata)); + return (long)dentry->d_fsdata; } -static struct lock_class_key simple_offset_xa_lock; +static struct lock_class_key simple_offset_lock_class; /** * simple_offset_init - initialize an offset_ctx @@ -259,11 +264,9 @@ static struct lock_class_key simple_offset_xa_lock; */ void simple_offset_init(struct offset_ctx *octx) { - xa_init_flags(&octx->xa, XA_FLAGS_ALLOC1); - lockdep_set_class(&octx->xa.xa_lock, &simple_offset_xa_lock); - - /* 0 is '.', 1 is '..', so always start with offset 2 */ - octx->next_offset = 2; + mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE); + lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class); + octx->next_offset = DIR_OFFSET_MIN; } /** @@ -271,20 +274,19 @@ void simple_offset_init(struct offset_ctx *octx) * @octx: directory offset ctx to be updated * @dentry: new dentry being added * - * Returns zero on success. @so_ctx and the dentry offset are updated. + * Returns zero on success. @octx and the dentry's offset are updated. * Otherwise, a negative errno value is returned. */ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) { - static const struct xa_limit limit = XA_LIMIT(2, U32_MAX); - u32 offset; + unsigned long offset; int ret; if (dentry2offset(dentry) != 0) return -EBUSY; - ret = xa_alloc_cyclic(&octx->xa, &offset, dentry, limit, - &octx->next_offset, GFP_KERNEL); + ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, + LONG_MAX, &octx->next_offset, GFP_KERNEL); if (ret < 0) return ret; @@ -292,6 +294,18 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) return 0; } +static int simple_offset_replace(struct offset_ctx *octx, struct dentry *dentry, + long offset) +{ + int ret; + + ret = mtree_store(&octx->mt, offset, dentry, GFP_KERNEL); + if (ret) + return ret; + offset_set(dentry, offset); + return 0; +} + /** * simple_offset_remove - Remove an entry to a directory's offset map * @octx: directory offset ctx to be updated @@ -300,16 +314,78 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) */ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) { - u32 offset; + long offset; offset = dentry2offset(dentry); if (offset == 0) return; - xa_erase(&octx->xa, offset); + mtree_erase(&octx->mt, offset); offset_set(dentry, 0); } +/** + * simple_offset_empty - Check if a dentry can be unlinked + * @dentry: dentry to be tested + * + * Returns 0 if @dentry is a non-empty directory; otherwise returns 1. + */ +int simple_offset_empty(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + struct offset_ctx *octx; + struct dentry *child; + unsigned long index; + int ret = 1; + + if (!inode || !S_ISDIR(inode->i_mode)) + return ret; + + index = DIR_OFFSET_MIN; + octx = inode->i_op->get_offset_ctx(inode); + mt_for_each(&octx->mt, child, index, LONG_MAX) { + spin_lock(&child->d_lock); + if (simple_positive(child)) { + spin_unlock(&child->d_lock); + ret = 0; + break; + } + spin_unlock(&child->d_lock); + } + + return ret; +} + +/** + * simple_offset_rename - handle directory offsets for rename + * @old_dir: parent directory of source entry + * @old_dentry: dentry of source entry + * @new_dir: parent_directory of destination entry + * @new_dentry: dentry of destination + * + * Caller provides appropriate serialization. + * + * User space expects the directory offset value of the replaced + * (new) directory entry to be unchanged after a rename. + * + * Returns zero on success, a negative errno value on failure. + */ +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); + struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); + long new_offset = dentry2offset(new_dentry); + + simple_offset_remove(old_ctx, old_dentry); + + if (new_offset) { + offset_set(new_dentry, 0); + return simple_offset_replace(new_ctx, old_dentry, new_offset); + } + return simple_offset_add(new_ctx, old_dentry); +} + /** * simple_offset_rename_exchange - exchange rename with directory offsets * @old_dir: parent of dentry being moved @@ -317,6 +393,9 @@ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) * @new_dir: destination parent * @new_dentry: destination dentry * + * This API preserves the directory offset values. Caller provides + * appropriate serialization. + * * Returns zero on success. Otherwise a negative errno is returned and the * rename is rolled back. */ @@ -327,18 +406,18 @@ int simple_offset_rename_exchange(struct inode *old_dir, { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); - u32 old_index = dentry2offset(old_dentry); - u32 new_index = dentry2offset(new_dentry); + long old_index = dentry2offset(old_dentry); + long new_index = dentry2offset(new_dentry); int ret; simple_offset_remove(old_ctx, old_dentry); simple_offset_remove(new_ctx, new_dentry); - ret = simple_offset_add(new_ctx, old_dentry); + ret = simple_offset_replace(new_ctx, old_dentry, new_index); if (ret) goto out_restore; - ret = simple_offset_add(old_ctx, new_dentry); + ret = simple_offset_replace(old_ctx, new_dentry, old_index); if (ret) { simple_offset_remove(new_ctx, old_dentry); goto out_restore; @@ -353,10 +432,8 @@ int simple_offset_rename_exchange(struct inode *old_dir, return 0; out_restore: - offset_set(old_dentry, old_index); - xa_store(&old_ctx->xa, old_index, old_dentry, GFP_KERNEL); - offset_set(new_dentry, new_index); - xa_store(&new_ctx->xa, new_index, new_dentry, GFP_KERNEL); + (void)simple_offset_replace(old_ctx, old_dentry, old_index); + (void)simple_offset_replace(new_ctx, new_dentry, new_index); return ret; } @@ -369,7 +446,7 @@ int simple_offset_rename_exchange(struct inode *old_dir, */ void simple_offset_destroy(struct offset_ctx *octx) { - xa_destroy(&octx->xa); + mtree_destroy(&octx->mt); } /** @@ -399,15 +476,16 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) /* In this case, ->private_data is protected by f_pos_lock */ file->private_data = NULL; - return vfs_setpos(file, offset, U32_MAX); + return vfs_setpos(file, offset, LONG_MAX); } -static struct dentry *offset_find_next(struct xa_state *xas) +static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset) { + MA_STATE(mas, &octx->mt, offset, offset); struct dentry *child, *found = NULL; rcu_read_lock(); - child = xas_next_entry(xas, U32_MAX); + child = mas_find(&mas, LONG_MAX); if (!child) goto out; spin_lock(&child->d_lock); @@ -421,8 +499,8 @@ static struct dentry *offset_find_next(struct xa_state *xas) static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { - u32 offset = dentry2offset(dentry); struct inode *inode = d_inode(dentry); + long offset = dentry2offset(dentry); return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset, inode->i_ino, fs_umode_to_dtype(inode->i_mode)); @@ -430,12 +508,11 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) { - struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode); - XA_STATE(xas, &so_ctx->xa, ctx->pos); + struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *dentry; while (true) { - dentry = offset_find_next(&xas); + dentry = offset_find_next(octx, ctx->pos); if (!dentry) return ERR_PTR(-ENOENT); @@ -444,8 +521,8 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) break; } + ctx->pos = dentry2offset(dentry) + 1; dput(dentry); - ctx->pos = xas.xa_index + 1; } return NULL; } @@ -481,7 +558,7 @@ static int offset_readdir(struct file *file, struct dir_context *ctx) return 0; /* In this case, ->private_data is protected by f_pos_lock */ - if (ctx->pos == 2) + if (ctx->pos == DIR_OFFSET_MIN) file->private_data = NULL; else if (file->private_data == ERR_PTR(-ENOENT)) return 0; diff --git a/fs/namei.c b/fs/namei.c index 9342fa6a38c2b..c67ce378c099f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1028,8 +1028,8 @@ static inline void put_link(struct nameidata *nd) path_put(&last->link); } -static int sysctl_protected_symlinks __read_mostly; -static int sysctl_protected_hardlinks __read_mostly; +static int sysctl_protected_symlinks __read_mostly = 1; +static int sysctl_protected_hardlinks __read_mostly = 1; static int sysctl_protected_fifos __read_mostly; static int sysctl_protected_regular __read_mostly; diff --git a/fs/namespace.c b/fs/namespace.c index 5a51315c66781..c8110a5ac85a5 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -169,7 +169,7 @@ void mnt_release_group_id(struct mount *mnt) /* * vfsmount lock must be held for read */ -static inline void mnt_add_count(struct mount *mnt, int n) +static noinline __noclone void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); @@ -1704,7 +1704,8 @@ static int do_umount_root(struct super_block *sb) return ret; } -static int do_umount(struct mount *mnt, int flags) +/* force a bpftrace dynamic function probe here */ +static noinline __noclone int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 9a0d32e4b422a..912ad0a1df021 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -163,8 +163,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, struct folio *folio; enum netfs_how_to_modify howto; enum netfs_folio_trace trace; - unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC; - ssize_t written = 0, ret; + unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; + ssize_t written = 0, ret, ret2; loff_t i_size, pos = iocb->ki_pos, from, to; size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; bool maybe_trouble = false; @@ -172,15 +172,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) || iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) ) { - if (pos < i_size_read(inode)) { - ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count); - if (ret < 0) { - goto out; - } - } - wbc_attach_fdatawrite_inode(&wbc, mapping->host); + ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count); + if (ret < 0) { + wbc_detach_inode(&wbc); + goto out; + } + wreq = netfs_begin_writethrough(iocb, iter->count); if (IS_ERR(wreq)) { wbc_detach_inode(&wbc); @@ -395,10 +394,12 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, out: if (unlikely(wreq)) { - ret = netfs_end_writethrough(wreq, iocb); + ret2 = netfs_end_writethrough(wreq, iocb); wbc_detach_inode(&wbc); - if (ret == -EIOCBQUEUED) - return ret; + if (ret2 == -EIOCBQUEUED) + return ret2; + if (ret == 0) + ret = ret2; } iocb->ki_pos += written; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index fbdc9ca80f714..a8fad331dff6b 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -73,7 +73,6 @@ const struct rpc_program nfs_program = { .number = NFS_PROGRAM, .nrvers = ARRAY_SIZE(nfs_version), .version = nfs_version, - .stats = &nfs_rpcstat, .pipe_dir_name = NFS_PIPE_DIRNAME, }; @@ -502,6 +501,7 @@ int nfs_create_rpc_client(struct nfs_client *clp, const struct nfs_client_initdata *cl_init, rpc_authflavor_t flavor) { + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { .net = clp->cl_net, @@ -513,6 +513,7 @@ int nfs_create_rpc_client(struct nfs_client *clp, .servername = clp->cl_hostname, .nodename = cl_init->nodename, .program = &nfs_program, + .stats = &nn->rpcstats, .version = clp->rpc_ops->version, .authflavor = flavor, .cred = cl_init->cred, @@ -1182,6 +1183,8 @@ void nfs_clients_init(struct net *net) #endif spin_lock_init(&nn->nfs_client_lock); nn->boot_time = ktime_get_real(); + memset(&nn->rpcstats, 0, sizeof(nn->rpcstats)); + nn->rpcstats.program = &nfs_program; nfs_netns_sysfs_setup(nn, net); } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ac505671efbdb..a82f67a4ef42b 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -807,7 +807,7 @@ static int nfs_readdir_entry_decode(struct nfs_readdir_descriptor *desc, int ret; if (entry->fattr->label) - entry->fattr->label->len = NFS4_MAXLABELLEN; + entry->fattr->label->lsmctx.len = NFS4_MAXLABELLEN; ret = xdr_decode(desc, entry, stream); if (ret || !desc->plus) return ret; @@ -1802,9 +1802,10 @@ __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; } else { - /* Wait for unlink to complete */ + /* Wait for unlink to complete - see unblock_revalidate() */ wait_var_event(&dentry->d_fsdata, - dentry->d_fsdata != NFS_FSDATA_BLOCKED); + smp_load_acquire(&dentry->d_fsdata) + != NFS_FSDATA_BLOCKED); parent = dget_parent(dentry); ret = reval(d_inode(parent), dentry, flags); dput(parent); @@ -1817,6 +1818,29 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate); } +static void block_revalidate(struct dentry *dentry) +{ + /* old devname - just in case */ + kfree(dentry->d_fsdata); + + /* Any new reference that could lead to an open + * will take ->d_lock in lookup_open() -> d_lookup(). + * Holding this lock ensures we cannot race with + * __nfs_lookup_revalidate() and removes and need + * for further barriers. + */ + lockdep_assert_held(&dentry->d_lock); + + dentry->d_fsdata = NFS_FSDATA_BLOCKED; +} + +static void unblock_revalidate(struct dentry *dentry) +{ + /* store_release ensures wait_var_event() sees the update */ + smp_store_release(&dentry->d_fsdata, NULL); + wake_up_var(&dentry->d_fsdata); +} + /* * A weaker form of d_revalidate for revalidating just the d_inode(dentry) * when we don't really care about the dentry name. This is called when a @@ -2501,15 +2525,12 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) spin_unlock(&dentry->d_lock); goto out; } - /* old devname */ - kfree(dentry->d_fsdata); - dentry->d_fsdata = NFS_FSDATA_BLOCKED; + block_revalidate(dentry); spin_unlock(&dentry->d_lock); error = nfs_safe_remove(dentry); nfs_dentry_remove_handle_error(dir, dentry, error); - dentry->d_fsdata = NULL; - wake_up_var(&dentry->d_fsdata); + unblock_revalidate(dentry); out: trace_nfs_unlink_exit(dir, dentry, error); return error; @@ -2616,8 +2637,7 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) { struct dentry *new_dentry = data->new_dentry; - new_dentry->d_fsdata = NULL; - wake_up_var(&new_dentry->d_fsdata); + unblock_revalidate(new_dentry); } /* @@ -2679,11 +2699,6 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (WARN_ON(new_dentry->d_flags & DCACHE_NFSFS_RENAMED) || WARN_ON(new_dentry->d_fsdata == NFS_FSDATA_BLOCKED)) goto out; - if (new_dentry->d_fsdata) { - /* old devname */ - kfree(new_dentry->d_fsdata); - new_dentry->d_fsdata = NULL; - } spin_lock(&new_dentry->d_lock); if (d_count(new_dentry) > 2) { @@ -2705,7 +2720,7 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, new_dentry = dentry; new_inode = NULL; } else { - new_dentry->d_fsdata = NFS_FSDATA_BLOCKED; + block_revalidate(new_dentry); must_unblock = true; spin_unlock(&new_dentry->d_lock); } @@ -2717,6 +2732,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, must_unblock ? nfs_unblock_rename : NULL); if (IS_ERR(task)) { + if (must_unblock) + unblock_revalidate(new_dentry); error = PTR_ERR(task); goto out; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index c03926a1cc73b..d8cd4f69e33a0 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -667,10 +667,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) LIST_HEAD(mds_list); nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_commit_begin(cinfo.mds); nfs_scan_commit(dreq->inode, &mds_list, &cinfo); res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); - if (res < 0) /* res == -ENOMEM */ - nfs_direct_write_reschedule(dreq); + if (res < 0) { /* res == -ENOMEM */ + spin_lock(&dreq->lock); + if (dreq->flags == 0) + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + } + if (nfs_commit_end(cinfo.mds)) + nfs_direct_write_complete(dreq); } static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index ce8f8934bca51..569ae4ec60845 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -883,7 +883,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, NFS4_MAX_UINT64, IOMODE_READ, false, - GFP_KERNEL); + nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -907,7 +907,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, NFS4_MAX_UINT64, IOMODE_RW, false, - GFP_NOFS); + nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index ef817a0475ffa..3e724cb7ef01d 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -2016,7 +2016,7 @@ static void ff_layout_cancel_io(struct pnfs_layout_segment *lseg) for (idx = 0; idx < flseg->mirror_array_cnt; idx++) { mirror = flseg->mirror_array[idx]; mirror_ds = mirror->mirror_ds; - if (!mirror_ds) + if (IS_ERR_OR_NULL(mirror_ds)) continue; ds = mirror->mirror_ds->ds; if (!ds) diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 853e8d609bb3b..41126d6dcd760 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -1111,9 +1111,12 @@ static int nfs23_parse_monolithic(struct fs_context *fc, ctx->acdirmax = data->acdirmax; ctx->need_mount = false; - memcpy(sap, &data->addr, sizeof(data->addr)); - ctx->nfs_server.addrlen = sizeof(data->addr); - ctx->nfs_server.port = ntohs(data->addr.sin_port); + if (!is_remount_fc(fc)) { + memcpy(sap, &data->addr, sizeof(data->addr)); + ctx->nfs_server.addrlen = sizeof(data->addr); + ctx->nfs_server.port = ntohs(data->addr.sin_port); + } + if (sap->ss_family != AF_INET || !nfs_verify_server_address(sap)) goto out_no_address; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 2d1bfee225c36..ddc1ee0319554 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -301,11 +301,11 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) struct inode *inode = sreq->rreq->inode; struct nfs_open_context *ctx = sreq->rreq->netfs_priv; struct page *page; + unsigned long idx; int err; pgoff_t start = (sreq->start + sreq->transferred) >> PAGE_SHIFT; pgoff_t last = ((sreq->start + sreq->len - sreq->transferred - 1) >> PAGE_SHIFT); - XA_STATE(xas, &sreq->rreq->mapping->i_pages, start); nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); @@ -316,19 +316,14 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) pgio.pg_netfs = netfs; /* used in completion */ - xas_lock(&xas); - xas_for_each(&xas, page, last) { + xa_for_each_range(&sreq->rreq->mapping->i_pages, idx, page, start, last) { /* nfs_read_add_folio() may schedule() due to pNFS layout and other RPCs */ - xas_pause(&xas); - xas_unlock(&xas); err = nfs_read_add_folio(&pgio, ctx, page_folio(page)); if (err < 0) { netfs->error = err; goto out; } - xas_lock(&xas); } - xas_unlock(&xas); out: nfs_pageio_complete_read(&pgio); nfs_netfs_put(netfs); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index ebb8d60e11526..35f4ea31f94ee 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -357,14 +357,15 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) return; if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) { - error = security_inode_notifysecctx(inode, fattr->label->label, - fattr->label->len); + error = security_inode_notifysecctx(inode, + fattr->label->lsmctx.context, + fattr->label->lsmctx.len); if (error) printk(KERN_ERR "%s() %s %d " "security_inode_notifysecctx() %d\n", __func__, - (char *)fattr->label->label, - fattr->label->len, error); + (char *)fattr->label->lsmctx.context, + fattr->label->lsmctx.len, error); nfs_clear_label_invalid(inode); } } @@ -380,12 +381,14 @@ struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) if (label == NULL) return ERR_PTR(-ENOMEM); - label->label = kzalloc(NFS4_MAXLABELLEN, flags); - if (label->label == NULL) { + label->lsmctx.context = kzalloc(NFS4_MAXLABELLEN, flags); + if (label->lsmctx.context == NULL) { kfree(label); return ERR_PTR(-ENOMEM); } - label->len = NFS4_MAXLABELLEN; + label->lsmctx.len = NFS4_MAXLABELLEN; + /* Use an invalid LSM ID as this should never be "released". */ + label->lsmctx.id = LSM_ID_UNDEF; return label; } @@ -2426,12 +2429,21 @@ EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { + struct nfs_net *nn = net_generic(net, nfs_net_id); + nfs_clients_init(net); + + if (!rpc_proc_register(net, &nn->rpcstats)) { + nfs_clients_exit(net); + return -ENOMEM; + } + return nfs_fs_proc_net_init(net); } static void nfs_net_exit(struct net *net) { + rpc_proc_unregister(net, "nfs"); nfs_fs_proc_net_exit(net); nfs_clients_exit(net); } @@ -2486,15 +2498,12 @@ static int __init init_nfs_fs(void) if (err) goto out1; - rpc_proc_register(&init_net, &nfs_rpcstat); - err = register_nfs_fs(); if (err) goto out0; return 0; out0: - rpc_proc_unregister(&init_net, "nfs"); nfs_destroy_directcache(); out1: nfs_destroy_writepagecache(); @@ -2524,7 +2533,6 @@ static void __exit exit_nfs_fs(void) nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); unregister_pernet_subsys(&nfs_net_ops); - rpc_proc_unregister(&init_net, "nfs"); unregister_nfs_fs(); nfs_fs_proc_exit(); nfsiod_stop(); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index e3722ce6722e2..bddbde1ec0934 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -346,13 +346,15 @@ nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) if (!dst || !src) return NULL; - if (src->len > NFS4_MAXLABELLEN) + if (src->lsmctx.len > NFS4_MAXLABELLEN) return NULL; dst->lfs = src->lfs; dst->pi = src->pi; - dst->len = src->len; - memcpy(dst->label, src->label, src->len); + /* Use an invalid LSM ID as lsmctx should never be "released" */ + dst->lsmctx.id = LSM_ID_UNDEF; + dst->lsmctx.len = src->lsmctx.len; + memcpy(dst->lsmctx.context, src->lsmctx.context, src->lsmctx.len); return dst; } @@ -449,8 +451,6 @@ int nfs_try_get_tree(struct fs_context *); int nfs_get_tree_common(struct fs_context *); void nfs_kill_super(struct super_block *); -extern struct rpc_stat nfs_rpcstat; - extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern bool nfs_sb_active(struct super_block *sb); @@ -712,9 +712,9 @@ unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) if ((bsize & (bsize - 1)) || nrbitsp) { unsigned char nrbits; - for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--) + for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--) ; - bsize = 1 << nrbits; + bsize = 1UL << nrbits; if (nrbitsp) *nrbitsp = nrbits; } diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index c8374f74dce11..a68b21603ea9a 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -9,6 +9,7 @@ #include #include #include +#include struct bl_dev_msg { int32_t status; @@ -34,6 +35,7 @@ struct nfs_net { struct nfs_netns_client *nfs_client; spinlock_t nfs_client_lock; ktime_t boot_time; + struct rpc_stat rpcstats; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_nfsfs; #endif diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index b59876b01a1e3..0282d93c8bccb 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -55,11 +55,14 @@ int nfs42_proc_removexattr(struct inode *inode, const char *name); * They would be 7 bytes long in the eventual buffer ("user.x\0"), and * 8 bytes long XDR-encoded. * - * Include the trailing eof word as well. + * Include the trailing eof word as well and make the result a multiple + * of 4 bytes. */ static inline u32 nfs42_listxattr_xdrsize(u32 buflen) { - return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4; + u32 size = 8 * buflen / (XATTR_USER_PREFIX_LEN + 2) + 4; + + return (size + 3) & ~3; } #endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 23819a7565085..f33cbd844df9e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -124,12 +124,11 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry, label->lfs = 0; label->pi = 0; - label->len = 0; - label->label = NULL; + label->lsmctx.len = 0; + label->lsmctx.context = NULL; err = security_dentry_init_security(dentry, sattr->ia_mode, - &dentry->d_name, NULL, - (void **)&label->label, &label->len); + &dentry->d_name, NULL, &label->lsmctx); if (err == 0) return label; @@ -139,7 +138,7 @@ static inline void nfs4_label_release_security(struct nfs4_label *label) { if (label) - security_release_secctx(label->label, label->len); + security_release_secctx(&label->lsmctx); } static inline u32 *nfs4_bitmask(struct nfs_server *server, struct nfs4_label *label) { @@ -4028,6 +4027,23 @@ static void test_fs_location_for_trunking(struct nfs4_fs_location *location, } } +static bool _is_same_nfs4_pathname(struct nfs4_pathname *path1, + struct nfs4_pathname *path2) +{ + int i; + + if (path1->ncomponents != path2->ncomponents) + return false; + for (i = 0; i < path1->ncomponents; i++) { + if (path1->components[i].len != path2->components[i].len) + return false; + if (memcmp(path1->components[i].data, path2->components[i].data, + path1->components[i].len)) + return false; + } + return true; +} + static int _nfs4_discover_trunking(struct nfs_server *server, struct nfs_fh *fhandle) { @@ -4061,9 +4077,13 @@ static int _nfs4_discover_trunking(struct nfs_server *server, if (status) goto out_free_3; - for (i = 0; i < locations->nlocations; i++) + for (i = 0; i < locations->nlocations; i++) { + if (!_is_same_nfs4_pathname(&locations->fs_path, + &locations->locations[i].rootpath)) + continue; test_fs_location_for_trunking(&locations->locations[i], clp, server); + } out_free_3: kfree(locations->fattr); out_free_2: @@ -5461,7 +5481,7 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, struct rpc_message *msg = &task->tk_msg; if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] && - server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) { + task->tk_status == -ENOTSUPP) { server->caps &= ~NFS_CAP_READ_PLUS; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; rpc_restart_call_prepare(task); @@ -6153,7 +6173,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, size_t buflen) { struct nfs_server *server = NFS_SERVER(inode); - struct nfs4_label label = {0, 0, buflen, buf}; + struct nfs4_label label = {0, 0, {buf, buflen, -1} }; u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL }; struct nfs_fattr fattr = { @@ -6181,7 +6201,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, return ret; if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL)) return -ENOENT; - return label.len; + return label.lsmctx.len; } static int nfs4_get_security_label(struct inode *inode, void *buf, @@ -6258,7 +6278,8 @@ static int nfs4_do_set_security_label(struct inode *inode, static int nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) { - struct nfs4_label ilabel = {0, 0, buflen, (char *)buf }; + struct nfs4_label ilabel = {0, 0, + {(char *)buf, buflen, -1}}; struct nfs_fattr *fattr; int status; @@ -10615,29 +10636,33 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) { ssize_t error, error2, error3; + size_t left = size; - error = generic_listxattr(dentry, list, size); + error = generic_listxattr(dentry, list, left); if (error < 0) return error; if (list) { list += error; - size -= error; + left -= error; } - error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, left); if (error2 < 0) return error2; if (list) { list += error2; - size -= error2; + left -= error2; } - error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size); + error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left); if (error3 < 0) return error3; - return error + error2 + error3; + error += error2 + error3; + if (size && error > size) + return -ERANGE; + return error; } static void nfs4_enable_swap(struct inode *inode) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 9a5d911a7edc7..c95c50328ced8 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2117,6 +2117,7 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred { struct nfs_client *clp = server->nfs_client; struct nfs4_fs_locations *locations = NULL; + struct nfs_fattr *fattr; struct inode *inode; struct page *page; int status, result; @@ -2126,19 +2127,16 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred (unsigned long long)server->fsid.minor, clp->cl_hostname); - result = 0; page = alloc_page(GFP_KERNEL); locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); - if (page == NULL || locations == NULL) { - dprintk("<-- %s: no memory\n", __func__); - goto out; - } - locations->fattr = nfs_alloc_fattr(); - if (locations->fattr == NULL) { + fattr = nfs_alloc_fattr(); + if (page == NULL || locations == NULL || fattr == NULL) { dprintk("<-- %s: no memory\n", __func__); + result = 0; goto out; } + locations->fattr = fattr; inode = d_inode(server->super->s_root); result = nfs4_proc_get_locations(server, NFS_FH(inode), locations, page, cred); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 69406e60f391e..d762cc693ed08 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1154,7 +1154,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, } if (label && (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL)) { - len += 4 + 4 + 4 + (XDR_QUADLEN(label->len) << 2); + len += 4 + 4 + 4 + (XDR_QUADLEN(label->lsmctx.len) << 2); bmval[2] |= FATTR4_WORD2_SECURITY_LABEL; } @@ -1186,8 +1186,9 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, if (label && (bmval[2] & FATTR4_WORD2_SECURITY_LABEL)) { *p++ = cpu_to_be32(label->lfs); *p++ = cpu_to_be32(label->pi); - *p++ = cpu_to_be32(label->len); - p = xdr_encode_opaque_fixed(p, label->label, label->len); + *p++ = cpu_to_be32(label->lsmctx.len); + p = xdr_encode_opaque_fixed(p, label->lsmctx.context, + label->lsmctx.len); } if (bmval[2] & FATTR4_WORD2_MODE_UMASK) { *p++ = cpu_to_be32(iap->ia_mode & S_IALLUGO); @@ -4245,11 +4246,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, return -EIO; bitmap[2] &= ~FATTR4_WORD2_SECURITY_LABEL; if (len < NFS4_MAXLABELLEN) { - if (label && label->len) { - if (label->len < len) + if (label && label->lsmctx.len) { + if (label->lsmctx.len < len) return -ERANGE; - memcpy(label->label, p, len); - label->len = len; + memcpy(label->lsmctx.context, p, len); + label->lsmctx.len = len; label->pi = pi; label->lfs = lfs; status = NFS_ATTR_FATTR_V4_SECURITY_LABEL; @@ -4257,10 +4258,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, } else printk(KERN_WARNING "%s: label too long (%u)!\n", __func__, len); - if (label && label->label) + if (label && label->lsmctx.context) dprintk("%s: label=%.*s, len=%d, PI=%d, LFS=%d\n", - __func__, label->len, (char *)label->label, - label->len, label->pi, label->lfs); + __func__, label->lsmctx.len, + (char *)label->lsmctx.context, + label->lsmctx.len, label->pi, label->lfs); } return status; } diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 7600100ba26f0..432612d224374 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -175,10 +175,10 @@ static int __init root_nfs_cat(char *dest, const char *src, size_t len = strlen(dest); if (len && dest[len - 1] != ',') - if (strlcat(dest, ",", destlen) > destlen) + if (strlcat(dest, ",", destlen) >= destlen) return -1; - if (strlcat(dest, src, destlen) > destlen) + if (strlcat(dest, src, destlen) >= destlen) return -1; return 0; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index afd23910f3bff..88e061bd711b7 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -919,6 +919,8 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); list_for_each_entry(da, &ds->ds_addrs, da_node) { + char servername[48]; + dprintk("%s: DS %s: trying address %s\n", __func__, ds->ds_remotestr, da->da_remotestr); @@ -929,6 +931,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, .dstaddr = (struct sockaddr *)&da->da_addr, .addrlen = da->da_addrlen, .servername = clp->cl_hostname, + .xprtsec = clp->cl_xprtsec, }; struct nfs4_add_xprt_data xprtdata = { .clp = clp, @@ -938,10 +941,45 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, .data = &xprtdata, }; - if (da->da_transport != clp->cl_proto) + if (da->da_transport != clp->cl_proto && + clp->cl_proto != XPRT_TRANSPORT_TCP_TLS) continue; + if (da->da_transport == XPRT_TRANSPORT_TCP && + mds_srv->nfs_client->cl_proto == + XPRT_TRANSPORT_TCP_TLS) { + struct sockaddr *addr = + (struct sockaddr *)&da->da_addr; + struct sockaddr_in *sin = + (struct sockaddr_in *)&da->da_addr; + struct sockaddr_in6 *sin6 = + (struct sockaddr_in6 *)&da->da_addr; + + /* for NFS with TLS we need to supply a correct + * servername of the trunked transport, not the + * servername of the main transport stored in + * clp->cl_hostname. And set the protocol to + * indicate to use TLS + */ + servername[0] = '\0'; + switch(addr->sa_family) { + case AF_INET: + snprintf(servername, sizeof(servername), + "%pI4", &sin->sin_addr.s_addr); + break; + case AF_INET6: + snprintf(servername, sizeof(servername), + "%pI6", &sin6->sin6_addr); + break; + default: + /* do not consider this address */ + continue; + } + xprt_args.ident = XPRT_TRANSPORT_TCP_TLS; + xprt_args.servername = servername; + } if (da->da_addr.ss_family != clp->cl_addr.ss_family) continue; + /** * Test this address for session trunking and * add as an alias @@ -953,6 +991,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, if (xprtdata.cred) put_cred(xprtdata.cred); } else { + if (da->da_transport == XPRT_TRANSPORT_TCP && + mds_srv->nfs_client->cl_proto == + XPRT_TRANSPORT_TCP_TLS) + da->da_transport = XPRT_TRANSPORT_TCP_TLS; clp = nfs4_set_ds_client(mds_srv, &da->da_addr, da->da_addrlen, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 7dc21a48e3e7b..a142287d86f68 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -305,6 +305,8 @@ int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, new = nfs_page_create_from_folio(ctx, folio, 0, aligned_len); if (IS_ERR(new)) { error = PTR_ERR(new); + if (nfs_netfs_folio_unlock(folio)) + folio_unlock(folio); goto out; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index bb79d3a886ae8..5d9dc6c053255 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1650,7 +1650,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo) !atomic_read(&cinfo->rpcs_out)); } -static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) { atomic_inc(&cinfo->rpcs_out); } diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 4cbe0434cbb8c..66a05fefae98e 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -80,8 +80,6 @@ enum { int nfsd_drc_slab_create(void); void nfsd_drc_slab_free(void); -int nfsd_net_reply_cache_init(struct nfsd_net *nn); -void nfsd_net_reply_cache_destroy(struct nfsd_net *nn); int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 74b4360779a11..0cef4bb407a9c 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -26,10 +27,22 @@ struct nfsd4_client_tracking_ops; enum { /* cache misses due only to checksum comparison failures */ - NFSD_NET_PAYLOAD_MISSES, + NFSD_STATS_PAYLOAD_MISSES, /* amount of memory (in bytes) currently consumed by the DRC */ - NFSD_NET_DRC_MEM_USAGE, - NFSD_NET_COUNTERS_NUM + NFSD_STATS_DRC_MEM_USAGE, + NFSD_STATS_RC_HITS, /* repcache hits */ + NFSD_STATS_RC_MISSES, /* repcache misses */ + NFSD_STATS_RC_NOCACHE, /* uncached reqs */ + NFSD_STATS_FH_STALE, /* FH stale error */ + NFSD_STATS_IO_READ, /* bytes returned to read requests */ + NFSD_STATS_IO_WRITE, /* bytes passed in write requests */ +#ifdef CONFIG_NFSD_V4 + NFSD_STATS_FIRST_NFS4_OP, /* count of individual nfsv4 operations */ + NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP, +#define NFSD_STATS_NFS4_OP(op) (NFSD_STATS_FIRST_NFS4_OP + (op)) + NFSD_STATS_WDELEG_GETATTR, /* count of getattr conflict with wdeleg */ +#endif + NFSD_STATS_COUNTERS_NUM }; /* @@ -164,7 +177,7 @@ struct nfsd_net { atomic_t num_drc_entries; /* Per-netns stats counters */ - struct percpu_counter counter[NFSD_NET_COUNTERS_NUM]; + struct percpu_counter counter[NFSD_STATS_COUNTERS_NUM]; /* longest hash chain seen */ unsigned int longest_chain; diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 926c29879c6ab..30aa241038eb4 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -85,7 +85,21 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n) static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, size_t len) { - WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0); + xdr_stream_encode_uint32_array(xdr, bitmap, len); +} + +static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs4_cb_fattr *fattr) +{ + fattr->ncf_cb_change = 0; + fattr->ncf_cb_fsize = 0; + if (bitmap[0] & FATTR4_WORD0_CHANGE) + if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0) + return -NFSERR_BAD_XDR; + if (bitmap[0] & FATTR4_WORD0_SIZE) + if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0) + return -NFSERR_BAD_XDR; + return 0; } static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op) @@ -333,6 +347,30 @@ encode_cb_recallany4args(struct xdr_stream *xdr, hdr->nops++; } +/* + * CB_GETATTR4args + * struct CB_GETATTR4args { + * nfs_fh4 fh; + * bitmap4 attr_request; + * }; + * + * The size and change attributes are the only one + * guaranteed to be serviced by the client. + */ +static void +encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr, + struct nfs4_cb_fattr *fattr) +{ + struct nfs4_delegation *dp = + container_of(fattr, struct nfs4_delegation, dl_cb_fattr); + struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle; + + encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR); + encode_nfs_fh4(xdr, fh); + encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap)); + hdr->nops++; +} + /* * CB_SEQUENCE4args * @@ -468,6 +506,26 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, xdr_reserve_space(xdr, 0); } +/* + * 20.1. Operation 3: CB_GETATTR - Get Attributes + */ +static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_getattr4args(xdr, &hdr, ncf); + encode_cb_nops(&hdr); +} + /* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ @@ -523,6 +581,42 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, return 0; } +/* + * 20.1. Operation 3: CB_GETATTR - Get Attributes + */ +static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + u32 bitmap[3] = {0}; + u32 attrlen; + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + + status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status); + if (status) + return status; + if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0) + return -NFSERR_BAD_XDR; + if (xdr_stream_decode_u32(xdr, &attrlen) < 0) + return -NFSERR_BAD_XDR; + if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize))) + return -NFSERR_BAD_XDR; + status = decode_cb_fattr4(xdr, bitmap, ncf); + return status; +} + /* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ @@ -831,6 +925,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), + PROC(CB_GETATTR, COMPOUND, cb_getattr, cb_getattr), }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 14712fa08f769..648ff427005e6 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2490,10 +2490,10 @@ nfsd4_proc_null(struct svc_rqst *rqstp) return rpc_success; } -static inline void nfsd4_increment_op_stats(u32 opnum) +static inline void nfsd4_increment_op_stats(struct nfsd_net *nn, u32 opnum) { if (opnum >= FIRST_NFS4_OP && opnum <= LAST_NFS4_OP) - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_NFS4_OP(opnum)]); + percpu_counter_inc(&nn->counter[NFSD_STATS_NFS4_OP(opnum)]); } static const struct nfsd4_operation nfsd4_ops[]; @@ -2768,7 +2768,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) status, nfsd4_op_name(op->opnum)); nfsd4_cstate_clear_replay(cstate); - nfsd4_increment_op_stats(op->opnum); + nfsd4_increment_op_stats(nn, op->opnum); } fh_put(current_fh); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 7d6c657e0409d..71f9442c5c9fc 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2888,12 +2888,9 @@ static void nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - spin_lock(&nn->client_lock); clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); - put_client_renew_locked(clp); - spin_unlock(&nn->client_lock); + drop_client(clp); } static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { @@ -6274,7 +6271,7 @@ deleg_reaper(struct nfsd_net *nn) list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ - atomic_inc(&clp->cl_rpc_users); + kref_get(&clp->cl_nfsdfs.cl_ref); set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); clp->cl_ra_time = ktime_get_boottime_seconds(); } @@ -8450,6 +8447,7 @@ __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode) { __be32 status; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct file_lock_context *ctx; struct file_lock *fl; struct nfs4_delegation *dp; @@ -8479,7 +8477,7 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode) } break_lease: spin_unlock(&ctx->flc_lock); - nfsd_stats_wdeleg_getattr_inc(); + nfsd_stats_wdeleg_getattr_inc(nn); status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (status != nfserr_jukebox || !nfsd_wait_for_delegreturn(rqstp, inode)) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index c719c475a068e..a01f31714d9dd 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2806,11 +2806,11 @@ static __be32 nfsd4_encode_nfsace4(struct xdr_stream *xdr, struct svc_rqst *rqst #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, - void *context, int len) + const struct lsmcontext *context) { __be32 *p; - p = xdr_reserve_space(xdr, len + 4 + 4 + 4); + p = xdr_reserve_space(xdr, context->len + 4 + 4 + 4); if (!p) return nfserr_resource; @@ -2820,13 +2820,13 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, */ *p++ = cpu_to_be32(0); /* lfs */ *p++ = cpu_to_be32(0); /* pi */ - p = xdr_encode_opaque(p, context, len); + p = xdr_encode_opaque(p, context->context, context->len); return 0; } #else static inline __be32 nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, - void *context, int len) + struct lsmcontext *context) { return 0; } #endif @@ -2909,8 +2909,7 @@ struct nfsd4_fattr_args { struct nfs4_acl *acl; u64 size; #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - void *context; - int contextlen; + struct lsmcontext context; #endif u32 rdattr_err; bool contextsupport; @@ -3365,8 +3364,7 @@ static __be32 nfsd4_encode_fattr4_suppattr_exclcreat(struct xdr_stream *xdr, static __be32 nfsd4_encode_fattr4_sec_label(struct xdr_stream *xdr, const struct nfsd4_fattr_args *args) { - return nfsd4_encode_security_label(xdr, args->rqstp, - args->context, args->contextlen); + return nfsd4_encode_security_label(xdr, args->rqstp, &args->context); } #endif @@ -3490,11 +3488,13 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct dentry *dentry, const u32 *bmval, int ignore_crossmnt) { + DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); struct nfsd4_fattr_args args; struct svc_fh *tempfh = NULL; int starting_len = xdr->buf->len; __be32 *attrlen_p, status; int attrlen_offset; + u32 attrmask[3]; int err; struct nfsd4_compoundres *resp = rqstp->rq_resp; u32 minorversion = resp->cstate.minorversion; @@ -3502,10 +3502,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, .mnt = exp->ex_path.mnt, .dentry = dentry, }; - union { - u32 attrmask[3]; - unsigned long mask[2]; - } u; unsigned long bit; WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1); @@ -3515,24 +3511,24 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.exp = exp; args.dentry = dentry; args.ignore_crossmnt = (ignore_crossmnt != 0); + args.acl = NULL; /* * Make a local copy of the attribute bitmap that can be modified. */ - memset(&u, 0, sizeof(u)); - u.attrmask[0] = bmval[0]; - u.attrmask[1] = bmval[1]; - u.attrmask[2] = bmval[2]; + attrmask[0] = bmval[0]; + attrmask[1] = bmval[1]; + attrmask[2] = bmval[2]; args.rdattr_err = 0; if (exp->ex_fslocs.migrated) { - status = fattr_handle_absent_fs(&u.attrmask[0], &u.attrmask[1], - &u.attrmask[2], &args.rdattr_err); + status = fattr_handle_absent_fs(&attrmask[0], &attrmask[1], + &attrmask[2], &args.rdattr_err); if (status) goto out; } args.size = 0; - if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { + if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry)); if (status) goto out; @@ -3547,16 +3543,16 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (!(args.stat.result_mask & STATX_BTIME)) /* underlying FS does not offer btime so we can't share it */ - u.attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; - if ((u.attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | + attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; + if ((attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || - (u.attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | + (attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL))) { err = vfs_statfs(&path, &args.statfs); if (err) goto out_nfserr; } - if ((u.attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && + if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) { tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL); status = nfserr_jukebox; @@ -3570,11 +3566,10 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, } else args.fhp = fhp; - args.acl = NULL; - if (u.attrmask[0] & FATTR4_WORD0_ACL) { + if (attrmask[0] & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) - u.attrmask[0] &= ~FATTR4_WORD0_ACL; + attrmask[0] &= ~FATTR4_WORD0_ACL; else if (err == -EINVAL) { status = nfserr_attrnotsupp; goto out; @@ -3585,18 +3580,17 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.contextsupport = false; #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - args.context = NULL; - if ((u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || - u.attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { + if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || + attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { if (exp->ex_flags & NFSEXP_SECURITY_LABEL) err = security_inode_getsecctx(d_inode(dentry), - &args.context, &args.contextlen); + &args.context); else err = -EOPNOTSUPP; args.contextsupport = (err == 0); - if (u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { + if (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { if (err == -EOPNOTSUPP) - u.attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; else if (err) goto out_nfserr; } @@ -3604,8 +3598,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ /* attrmask */ - status = nfsd4_encode_bitmap4(xdr, u.attrmask[0], - u.attrmask[1], u.attrmask[2]); + status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1], + attrmask[2]); if (status) goto out; @@ -3614,7 +3608,9 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); if (!attrlen_p) goto out_resource; - for_each_set_bit(bit, (const unsigned long *)&u.mask, + bitmap_from_arr32(attr_bitmap, attrmask, + ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); + for_each_set_bit(bit, attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) { status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args); if (status != nfs_ok) @@ -3625,8 +3621,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, out: #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if (args.context) - security_release_secctx(args.context, args.contextlen); + if (args.context.context) + security_release_secctx(&args.context); #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ kfree(args.acl); if (tempfh) { diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 5c1a4a0aa6056..cfcc6ac8f255a 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -176,27 +176,6 @@ void nfsd_drc_slab_free(void) kmem_cache_destroy(drc_slab); } -/** - * nfsd_net_reply_cache_init - per net namespace reply cache set-up - * @nn: nfsd_net being initialized - * - * Returns zero on succes; otherwise a negative errno is returned. - */ -int nfsd_net_reply_cache_init(struct nfsd_net *nn) -{ - return nfsd_percpu_counters_init(nn->counter, NFSD_NET_COUNTERS_NUM); -} - -/** - * nfsd_net_reply_cache_destroy - per net namespace reply cache tear-down - * @nn: nfsd_net being freed - * - */ -void nfsd_net_reply_cache_destroy(struct nfsd_net *nn) -{ - nfsd_percpu_counters_destroy(nn->counter, NFSD_NET_COUNTERS_NUM); -} - int nfsd_reply_cache_init(struct nfsd_net *nn) { unsigned int hashsize; @@ -501,7 +480,7 @@ nfsd_cache_insert(struct nfsd_drc_bucket *b, struct nfsd_cacherep *key, int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, unsigned int len, struct nfsd_cacherep **cacherep) { - struct nfsd_net *nn; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct nfsd_cacherep *rp, *found; __wsum csum; struct nfsd_drc_bucket *b; @@ -510,7 +489,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, int rtn = RC_DOIT; if (type == RC_NOCACHE) { - nfsd_stats_rc_nocache_inc(); + nfsd_stats_rc_nocache_inc(nn); goto out; } @@ -520,7 +499,6 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, * Since the common case is a cache miss followed by an insert, * preallocate an entry. */ - nn = net_generic(SVC_NET(rqstp), nfsd_net_id); rp = nfsd_cacherep_alloc(rqstp, csum, nn); if (!rp) goto out; @@ -537,7 +515,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, nfsd_cacherep_dispose(&dispose); - nfsd_stats_rc_misses_inc(); + nfsd_stats_rc_misses_inc(nn); atomic_inc(&nn->num_drc_entries); nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp)); goto out; @@ -545,7 +523,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, found_entry: /* We found a matching entry which is either in progress or done. */ nfsd_reply_cache_free_locked(NULL, rp, nn); - nfsd_stats_rc_hits_inc(); + nfsd_stats_rc_hits_inc(nn); rtn = RC_DROPIT; rp = found; @@ -687,15 +665,15 @@ int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) atomic_read(&nn->num_drc_entries)); seq_printf(m, "hash buckets: %u\n", 1 << nn->maskbits); seq_printf(m, "mem usage: %lld\n", - percpu_counter_sum_positive(&nn->counter[NFSD_NET_DRC_MEM_USAGE])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_DRC_MEM_USAGE])); seq_printf(m, "cache hits: %lld\n", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_HITS])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS])); seq_printf(m, "cache misses: %lld\n", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_MISSES])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES])); seq_printf(m, "not cached: %lld\n", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE])); seq_printf(m, "payload misses: %lld\n", - percpu_counter_sum_positive(&nn->counter[NFSD_NET_PAYLOAD_MISSES])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_PAYLOAD_MISSES])); seq_printf(m, "longest chain len: %u\n", nn->longest_chain); seq_printf(m, "cachesize at longest: %u\n", nn->longest_chain_cachesize); return 0; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index f206ca32e7f53..16b7de26d5b61 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -48,12 +48,10 @@ enum { NFSD_MaxBlkSize, NFSD_MaxConnections, NFSD_Filecache, -#ifdef CONFIG_NFSD_V4 NFSD_Leasetime, NFSD_Gracetime, NFSD_RecoveryDir, NFSD_V4EndGrace, -#endif NFSD_MaxReserved }; @@ -1359,7 +1357,9 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR}, +#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING [NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR}, +#endif [NFSD_V4EndGrace] = {"v4_end_grace", &transaction_ops, S_IWUSR|S_IRUGO}, #endif /* last one */ {""} @@ -1671,14 +1671,17 @@ static __net_init int nfsd_net_init(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; - retval = nfsd_net_reply_cache_init(nn); + retval = nfsd_stat_counters_init(nn); if (retval) goto out_repcache_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; + nn->nfsd_info.mutex = &nfsd_mutex; + nn->nfsd_serv = NULL; nfsd4_init_leases_net(nn); get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); + nfsd_proc_stat_init(net); return 0; @@ -1699,7 +1702,8 @@ static __net_exit void nfsd_net_exit(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nfsd_net_reply_cache_destroy(nn); + nfsd_proc_stat_shutdown(net); + nfsd_stat_counters_destroy(nn); nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); nfsd_netns_free_versions(nn); @@ -1722,12 +1726,9 @@ static int __init init_nfsd(void) retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; - retval = nfsd_stat_init(); /* Statistics */ - if (retval) - goto out_free_pnfs; retval = nfsd_drc_slab_create(); if (retval) - goto out_free_stat; + goto out_free_pnfs; nfsd_lockd_init(); /* lockd->nfsd callbacks */ retval = create_proc_exports_entry(); if (retval) @@ -1761,8 +1762,6 @@ static int __init init_nfsd(void) out_free_lockd: nfsd_lockd_shutdown(); nfsd_drc_slab_free(); -out_free_stat: - nfsd_stat_shutdown(); out_free_pnfs: nfsd4_exit_pnfs(); out_free_slabs: @@ -1780,7 +1779,6 @@ static void __exit exit_nfsd(void) nfsd_drc_slab_free(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); - nfsd_stat_shutdown(); nfsd_lockd_shutdown(); nfsd4_free_slabs(); nfsd4_exit_pnfs(); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index dbfa0ac13564a..0b75305fb5f53 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -327,6 +327,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) __be32 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct svc_export *exp = NULL; struct dentry *dentry; __be32 error; @@ -395,7 +396,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access) out: trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error); if (error == nfserr_stale) - nfsd_stats_fh_stale_inc(exp); + nfsd_stats_fh_stale_inc(nn, exp); return error; } @@ -572,7 +573,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, _fh_update(fhp, exp, dentry); if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { fh_put(fhp); - return nfserr_opnotsupp; + return nfserr_stale; } return 0; @@ -598,7 +599,7 @@ fh_update(struct svc_fh *fhp) _fh_update(fhp, fhp->fh_export, dentry); if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) - return nfserr_opnotsupp; + return nfserr_stale; return 0; out_bad: printk(KERN_ERR "fh_update: fh not verified!\n"); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index a667802e08e75..3cff673bfed8f 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -677,7 +677,6 @@ int nfsd_create_serv(struct net *net) return error; } spin_lock(&nfsd_notifier_lock); - nn->nfsd_info.mutex = &nfsd_mutex; nn->nfsd_serv = serv; spin_unlock(&nfsd_notifier_lock); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 41bdc913fa715..0bbbe57e027d3 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -117,6 +117,16 @@ struct nfs4_cpntf_state { time64_t cpntf_time; /* last time stateid used */ }; +struct nfs4_cb_fattr { + struct nfsd4_callback ncf_getattr; + u32 ncf_cb_status; + u32 ncf_cb_bmap[1]; + + /* from CB_GETATTR reply */ + u64 ncf_cb_change; + u64 ncf_cb_fsize; +}; + /* * Represents a delegation stateid. The nfs4_client holds references to these * and they are put when it is being destroyed or when the delegation is @@ -150,6 +160,9 @@ struct nfs4_delegation { int dl_retries; struct nfsd4_callback dl_recall; bool dl_recalled; + + /* for CB_GETATTR */ + struct nfs4_cb_fattr dl_cb_fattr; }; #define cb_to_delegation(cb) \ @@ -640,6 +653,7 @@ enum nfsd4_cb_op { NFSPROC4_CLNT_CB_SEQUENCE, NFSPROC4_CLNT_CB_NOTIFY_LOCK, NFSPROC4_CLNT_CB_RECALL_ANY, + NFSPROC4_CLNT_CB_GETATTR, }; /* Returns true iff a is later than b: */ diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 12d79f5d4eb1a..44e275324b06e 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -34,15 +34,17 @@ struct svc_stat nfsd_svcstats = { static int nfsd_show(struct seq_file *seq, void *v) { + struct net *net = pde_data(file_inode(seq->file)); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); int i; seq_printf(seq, "rc %lld %lld %lld\nfh %lld 0 0 0 0\nio %lld %lld\n", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_HITS]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_MISSES]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_FH_STALE]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_READ]), - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_IO_WRITE])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_FH_STALE]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_READ]), + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_WRITE])); /* thread usage: */ seq_printf(seq, "th %u 0", atomic_read(&nfsdstats.th_cnt)); @@ -63,10 +65,10 @@ static int nfsd_show(struct seq_file *seq, void *v) seq_printf(seq, "proc4ops %u", LAST_NFS4_OP + 1); for (i = 0; i <= LAST_NFS4_OP; i++) { seq_printf(seq, " %lld", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_NFS4_OP(i)])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_NFS4_OP(i)])); } seq_printf(seq, "\nwdeleg_getattr %lld", - percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_WDELEG_GETATTR])); + percpu_counter_sum_positive(&nn->counter[NFSD_STATS_WDELEG_GETATTR])); seq_putc(seq, '\n'); #endif @@ -108,31 +110,22 @@ void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num) percpu_counter_destroy(&counters[i]); } -static int nfsd_stat_counters_init(void) +int nfsd_stat_counters_init(struct nfsd_net *nn) { - return nfsd_percpu_counters_init(nfsdstats.counter, NFSD_STATS_COUNTERS_NUM); + return nfsd_percpu_counters_init(nn->counter, NFSD_STATS_COUNTERS_NUM); } -static void nfsd_stat_counters_destroy(void) +void nfsd_stat_counters_destroy(struct nfsd_net *nn) { - nfsd_percpu_counters_destroy(nfsdstats.counter, NFSD_STATS_COUNTERS_NUM); + nfsd_percpu_counters_destroy(nn->counter, NFSD_STATS_COUNTERS_NUM); } -int nfsd_stat_init(void) +void nfsd_proc_stat_init(struct net *net) { - int err; - - err = nfsd_stat_counters_init(); - if (err) - return err; - - svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_ops); - - return 0; + svc_proc_register(net, &nfsd_svcstats, &nfsd_proc_ops); } -void nfsd_stat_shutdown(void) +void nfsd_proc_stat_shutdown(struct net *net) { - nfsd_stat_counters_destroy(); - svc_proc_unregister(&init_net, "nfsd"); + svc_proc_unregister(net, "nfsd"); } diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index 14f50c660b619..c24be4ddbe7d7 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -10,26 +10,7 @@ #include #include - -enum { - NFSD_STATS_RC_HITS, /* repcache hits */ - NFSD_STATS_RC_MISSES, /* repcache misses */ - NFSD_STATS_RC_NOCACHE, /* uncached reqs */ - NFSD_STATS_FH_STALE, /* FH stale error */ - NFSD_STATS_IO_READ, /* bytes returned to read requests */ - NFSD_STATS_IO_WRITE, /* bytes passed in write requests */ -#ifdef CONFIG_NFSD_V4 - NFSD_STATS_FIRST_NFS4_OP, /* count of individual nfsv4 operations */ - NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP, -#define NFSD_STATS_NFS4_OP(op) (NFSD_STATS_FIRST_NFS4_OP + (op)) - NFSD_STATS_WDELEG_GETATTR, /* count of getattr conflict with wdeleg */ -#endif - NFSD_STATS_COUNTERS_NUM -}; - struct nfsd_stats { - struct percpu_counter counter[NFSD_STATS_COUNTERS_NUM]; - atomic_t th_cnt; /* number of available threads */ }; @@ -40,64 +21,69 @@ extern struct svc_stat nfsd_svcstats; int nfsd_percpu_counters_init(struct percpu_counter *counters, int num); void nfsd_percpu_counters_reset(struct percpu_counter *counters, int num); void nfsd_percpu_counters_destroy(struct percpu_counter *counters, int num); -int nfsd_stat_init(void); -void nfsd_stat_shutdown(void); +int nfsd_stat_counters_init(struct nfsd_net *nn); +void nfsd_stat_counters_destroy(struct nfsd_net *nn); +void nfsd_proc_stat_init(struct net *net); +void nfsd_proc_stat_shutdown(struct net *net); -static inline void nfsd_stats_rc_hits_inc(void) +static inline void nfsd_stats_rc_hits_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_HITS]); + percpu_counter_inc(&nn->counter[NFSD_STATS_RC_HITS]); } -static inline void nfsd_stats_rc_misses_inc(void) +static inline void nfsd_stats_rc_misses_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_MISSES]); + percpu_counter_inc(&nn->counter[NFSD_STATS_RC_MISSES]); } -static inline void nfsd_stats_rc_nocache_inc(void) +static inline void nfsd_stats_rc_nocache_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_RC_NOCACHE]); + percpu_counter_inc(&nn->counter[NFSD_STATS_RC_NOCACHE]); } -static inline void nfsd_stats_fh_stale_inc(struct svc_export *exp) +static inline void nfsd_stats_fh_stale_inc(struct nfsd_net *nn, + struct svc_export *exp) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_FH_STALE]); + percpu_counter_inc(&nn->counter[NFSD_STATS_FH_STALE]); if (exp && exp->ex_stats) percpu_counter_inc(&exp->ex_stats->counter[EXP_STATS_FH_STALE]); } -static inline void nfsd_stats_io_read_add(struct svc_export *exp, s64 amount) +static inline void nfsd_stats_io_read_add(struct nfsd_net *nn, + struct svc_export *exp, s64 amount) { - percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_READ], amount); + percpu_counter_add(&nn->counter[NFSD_STATS_IO_READ], amount); if (exp && exp->ex_stats) percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_READ], amount); } -static inline void nfsd_stats_io_write_add(struct svc_export *exp, s64 amount) +static inline void nfsd_stats_io_write_add(struct nfsd_net *nn, + struct svc_export *exp, s64 amount) { - percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_WRITE], amount); + percpu_counter_add(&nn->counter[NFSD_STATS_IO_WRITE], amount); if (exp && exp->ex_stats) percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_WRITE], amount); } static inline void nfsd_stats_payload_misses_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nn->counter[NFSD_NET_PAYLOAD_MISSES]); + percpu_counter_inc(&nn->counter[NFSD_STATS_PAYLOAD_MISSES]); } static inline void nfsd_stats_drc_mem_usage_add(struct nfsd_net *nn, s64 amount) { - percpu_counter_add(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount); + percpu_counter_add(&nn->counter[NFSD_STATS_DRC_MEM_USAGE], amount); } static inline void nfsd_stats_drc_mem_usage_sub(struct nfsd_net *nn, s64 amount) { - percpu_counter_sub(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount); + percpu_counter_sub(&nn->counter[NFSD_STATS_DRC_MEM_USAGE], amount); } #ifdef CONFIG_NFSD_V4 -static inline void nfsd_stats_wdeleg_getattr_inc(void) +static inline void nfsd_stats_wdeleg_getattr_inc(struct nfsd_net *nn) { - percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_WDELEG_GETATTR]); + percpu_counter_inc(&nn->counter[NFSD_STATS_WDELEG_GETATTR]); } #endif #endif /* _NFSD_STATS_H */ diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index d1e8cf079b0f4..2cd57033791ff 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -843,7 +843,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class, __array(unsigned char, addr, sizeof(struct sockaddr_in6)) __field(unsigned long, flavor) __array(unsigned char, verifier, NFS4_VERIFIER_SIZE) - __string_len(name, name, clp->cl_name.len) + __string_len(name, clp->cl_name.data, clp->cl_name.len) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b7c7a9273ea01..9b5e20b2d0387 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1002,7 +1002,9 @@ static __be32 nfsd_finish_read(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned long *count, u32 *eof, ssize_t host_err) { if (host_err >= 0) { - nfsd_stats_io_read_add(fhp->fh_export, host_err); + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + + nfsd_stats_io_read_add(nn, fhp->fh_export, host_err); *eof = nfsd_eof_on_read(file, offset, host_err, *count); *count = host_err; fsnotify_access(file); @@ -1185,7 +1187,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, goto out_nfserr; } *cnt = host_err; - nfsd_stats_io_write_add(exp, *cnt); + nfsd_stats_io_write_add(nn, exp, *cnt); fsnotify_modify(file); host_err = filemap_check_wb_err(file->f_mapping, since); if (host_err < 0) @@ -1833,7 +1835,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, trap = lock_rename(tdentry, fdentry); if (IS_ERR(trap)) { err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev; - goto out; + goto out_want_write; } err = fh_fill_pre_attrs(ffhp); if (err != nfs_ok) @@ -1903,6 +1905,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, } out_unlock: unlock_rename(tdentry, fdentry); +out_want_write: fh_drop_write(ffhp); /* diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index 0d39af1b00a0f..e8b00309c449f 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -54,3 +54,21 @@ #define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) + +/* + * 1: CB_GETATTR opcode (32-bit) + * N: file_handle + * 1: number of entry in attribute array (32-bit) + * 1: entry 0 in attribute array (32-bit) + */ +#define NFS4_enc_cb_getattr_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ + 1 + enc_nfs4_fh_sz + 1 + 1) +/* + * 4: fattr_bitmap_maxsz + * 1: attribute array len + * 2: change attr (64-bit) + * 2: size (64-bit) + */ +#define NFS4_dec_cb_getattr_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz) diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 13592e82eaf68..65659fa0372e6 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -724,7 +724,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr = blocknr; } cnt = 1; @@ -743,7 +743,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) @@ -781,6 +781,11 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, out: nilfs_btree_free_path(path); return ret; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index bc846b904b68d..35e6c55a0d231 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -240,7 +240,7 @@ nilfs_filetype_table[NILFS_FT_MAX] = { #define S_SHIFT 12 static unsigned char -nilfs_type_by_mode[S_IFMT >> S_SHIFT] = { +nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = NILFS_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = NILFS_FT_DIR, [S_IFCHR >> S_SHIFT] = NILFS_FT_CHRDEV, @@ -608,7 +608,7 @@ int nilfs_empty_dir(struct inode *inode) kaddr = nilfs_get_folio(inode, i, &folio); if (IS_ERR(kaddr)) - continue; + return 0; de = (struct nilfs_dir_entry *)kaddr; kaddr += nilfs_last_byte(inode, i) - NILFS_DIR_REC_LEN(1); diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 4c85914f2abc3..893ab36824cc2 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -66,7 +66,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, dat = nilfs_bmap_get_dat(direct); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr = blocknr; } @@ -79,7 +79,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt) @@ -87,6 +87,11 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, } *ptrp = ptr; return cnt; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + return ret; } static __u64 diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 9c334c722fc1c..5a888b2c1803d 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -112,7 +112,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", __func__, inode->i_ino, (unsigned long long)blkoff); - err = 0; + err = -EAGAIN; } nilfs_transaction_abort(inode->i_sb); goto out; diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index cfb6aca5ec383..d6e3f20e8872e 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -60,7 +60,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, if (argv->v_nmembs == 0) return 0; - if (argv->v_size > PAGE_SIZE) + if ((size_t)argv->v_size > PAGE_SIZE) return -EINVAL; /* diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 2bfb08052d399..6c1d580a31b5b 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1693,6 +1693,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) if (bh->b_folio != bd_folio) { if (bd_folio) { folio_lock(bd_folio); + folio_wait_writeback(bd_folio); folio_clear_dirty_for_io(bd_folio); folio_start_writeback(bd_folio); folio_unlock(bd_folio); @@ -1706,6 +1707,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) if (bh == segbuf->sb_super_root) { if (bh->b_folio != bd_folio) { folio_lock(bd_folio); + folio_wait_writeback(bd_folio); folio_clear_dirty_for_io(bd_folio); folio_start_writeback(bd_folio); folio_unlock(bd_folio); @@ -1722,6 +1724,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } if (bd_folio) { folio_lock(bd_folio); + folio_wait_writeback(bd_folio); folio_clear_dirty_for_io(bd_folio); folio_start_writeback(bd_folio); folio_unlock(bd_folio); @@ -2161,8 +2164,10 @@ static void nilfs_segctor_start_timer(struct nilfs_sc_info *sci) { spin_lock(&sci->sc_state_lock); if (!(sci->sc_state & NILFS_SEGCTOR_COMMIT)) { - sci->sc_timer.expires = jiffies + sci->sc_interval; - add_timer(&sci->sc_timer); + if (sci->sc_task) { + sci->sc_timer.expires = jiffies + sci->sc_interval; + add_timer(&sci->sc_timer); + } sci->sc_state |= NILFS_SEGCTOR_COMMIT; } spin_unlock(&sci->sc_state_lock); @@ -2209,19 +2214,36 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci) struct nilfs_segctor_wait_request wait_req; int err = 0; - spin_lock(&sci->sc_state_lock); init_wait(&wait_req.wq); wait_req.err = 0; atomic_set(&wait_req.done, 0); + init_waitqueue_entry(&wait_req.wq, current); + + /* + * To prevent a race issue where completion notifications from the + * log writer thread are missed, increment the request sequence count + * "sc_seq_request" and insert a wait queue entry using the current + * sequence number into the "sc_wait_request" queue at the same time + * within the lock section of "sc_state_lock". + */ + spin_lock(&sci->sc_state_lock); wait_req.seq = ++sci->sc_seq_request; + add_wait_queue(&sci->sc_wait_request, &wait_req.wq); spin_unlock(&sci->sc_state_lock); - init_waitqueue_entry(&wait_req.wq, current); - add_wait_queue(&sci->sc_wait_request, &wait_req.wq); - set_current_state(TASK_INTERRUPTIBLE); wake_up(&sci->sc_wait_daemon); for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + /* + * Synchronize only while the log writer thread is alive. + * Leave flushing out after the log writer thread exits to + * the cleanup work in nilfs_segctor_destroy(). + */ + if (!sci->sc_task) + break; + if (atomic_read(&wait_req.done)) { err = wait_req.err; break; @@ -2237,7 +2259,7 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci) return err; } -static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err) +static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err, bool force) { struct nilfs_segctor_wait_request *wrq, *n; unsigned long flags; @@ -2245,7 +2267,7 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err) spin_lock_irqsave(&sci->sc_wait_request.lock, flags); list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) { if (!atomic_read(&wrq->done) && - nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) { + (force || nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq))) { wrq->err = err; atomic_set(&wrq->done, 1); } @@ -2363,10 +2385,21 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode, */ static void nilfs_segctor_accept(struct nilfs_sc_info *sci) { + bool thread_is_alive; + spin_lock(&sci->sc_state_lock); sci->sc_seq_accepted = sci->sc_seq_request; + thread_is_alive = (bool)sci->sc_task; spin_unlock(&sci->sc_state_lock); - del_timer_sync(&sci->sc_timer); + + /* + * This function does not race with the log writer thread's + * termination. Therefore, deleting sc_timer, which should not be + * done after the log writer thread exits, can be done safely outside + * the area protected by sc_state_lock. + */ + if (thread_is_alive) + del_timer_sync(&sci->sc_timer); } /** @@ -2383,7 +2416,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err) if (mode == SC_LSEG_SR) { sci->sc_state &= ~NILFS_SEGCTOR_COMMIT; sci->sc_seq_done = sci->sc_seq_accepted; - nilfs_segctor_wakeup(sci, err); + nilfs_segctor_wakeup(sci, err, false); sci->sc_flush_request = 0; } else { if (mode == SC_FLUSH_FILE) @@ -2392,7 +2425,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err) sci->sc_flush_request &= ~FLUSH_DAT_BIT; /* re-enable timer if checkpoint creation was not done */ - if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && + if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && sci->sc_task && time_before(jiffies, sci->sc_timer.expires)) add_timer(&sci->sc_timer); } @@ -2582,6 +2615,7 @@ static int nilfs_segctor_thread(void *arg) int timeout = 0; sci->sc_timer_task = current; + timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0); /* start sync. */ sci->sc_task = current; @@ -2649,6 +2683,7 @@ static int nilfs_segctor_thread(void *arg) end_thread: /* end sync. */ sci->sc_task = NULL; + timer_shutdown_sync(&sci->sc_timer); wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ spin_unlock(&sci->sc_state_lock); return 0; @@ -2712,7 +2747,6 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_gc_inodes); INIT_LIST_HEAD(&sci->sc_iput_queue); INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); - timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; sci->sc_mjcp_freq = HZ * NILFS_SC_DEFAULT_SR_FREQ; @@ -2766,6 +2800,13 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + /* + * Forcibly wake up tasks waiting in nilfs_segctor_sync(), which can + * be called from delayed iput() via nilfs_evict_inode() and can race + * with the above log writer thread termination. + */ + nilfs_segctor_wakeup(sci, 0, true); + if (flush_work(&sci->sc_iput_work)) flag = true; @@ -2791,7 +2832,6 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) down_write(&nilfs->ns_segctor_sem); - timer_shutdown_sync(&sci->sc_timer); kfree(sci); } diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 5cf3d9decf646..45e556fd7c54f 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -475,6 +475,7 @@ static int ntfs_readdir(struct file *file, struct dir_context *ctx) vbo = (u64)bit << index_bits; if (vbo >= i_size) { ntfs_inode_err(dir, "Looks like your dir is corrupt"); + ctx->pos = eod; err = -EINVAL; goto out; } diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 855519713bf79..4085fe30bf481 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -1184,7 +1184,8 @@ static int read_log_page(struct ntfs_log *log, u32 vbo, static int log_read_rst(struct ntfs_log *log, bool first, struct restart_info *info) { - u32 skip, vbo; + u32 skip; + u64 vbo; struct RESTART_HDR *r_page = NULL; /* Determine which restart area we are looking for. */ diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index daabaad63aaf6..14284f0ed46aa 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1533,6 +1533,11 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, goto out1; } + if (data_size <= le64_to_cpu(alloc->nres.data_size)) { + /* Reuse index. */ + goto out; + } + /* Increase allocation. */ err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len, &indx->alloc_run, data_size, &data_size, true, @@ -1546,6 +1551,7 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni, if (in->name == I30_NAME) i_size_write(&ni->vfs_inode, data_size); +out: *vbn = bit << indx->idx2vbn_bits; return 0; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index eb7a8c9fba018..502a527e51cd1 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -37,7 +37,7 @@ static struct inode *ntfs_read_mft(struct inode *inode, bool is_dir; unsigned long ino = inode->i_ino; u32 rp_fa = 0, asize, t32; - u16 roff, rsize, names = 0; + u16 roff, rsize, names = 0, links = 0; const struct ATTR_FILE_NAME *fname = NULL; const struct INDEX_ROOT *root; struct REPARSE_DATA_BUFFER rp; // 0x18 bytes @@ -200,11 +200,12 @@ static struct inode *ntfs_read_mft(struct inode *inode, rsize < SIZEOF_ATTRIBUTE_FILENAME) goto out; + names += 1; fname = Add2Ptr(attr, roff); if (fname->type == FILE_NAME_DOS) goto next_attr; - names += 1; + links += 1; if (name && name->len == fname->name_len && !ntfs_cmp_names_cpu(name, (struct le_str *)&fname->name_len, NULL, false)) @@ -429,7 +430,7 @@ static struct inode *ntfs_read_mft(struct inode *inode, ni->mi.dirty = true; } - set_nlink(inode, names); + set_nlink(inode, links); if (S_ISDIR(mode)) { ni->std_fa |= FILE_ATTRIBUTE_DIRECTORY; @@ -570,13 +571,18 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, clear_buffer_uptodate(bh); if (is_resident(ni)) { - ni_lock(ni); - err = attr_data_read_resident(ni, &folio->page); - ni_unlock(ni); - - if (!err) - set_buffer_uptodate(bh); + bh->b_blocknr = RESIDENT_LCN; bh->b_size = block_size; + if (!folio) { + err = 0; + } else { + ni_lock(ni); + err = attr_data_read_resident(ni, &folio->page); + ni_unlock(ni); + + if (!err) + set_buffer_uptodate(bh); + } return err; } diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 9c7478150a035..3d6143c7abc03 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -59,7 +59,7 @@ struct GUID { struct cpu_str { u8 len; u8 unused; - u16 name[10]; + u16 name[]; }; struct le_str { diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 6aa3a9d44df1b..6c76503edc200 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -534,16 +534,9 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, if (aoff + asize > used) return false; - if (ni && is_attr_indexed(attr)) { + if (ni && is_attr_indexed(attr) && attr->type == ATTR_NAME) { u16 links = le16_to_cpu(ni->mi.mrec->hard_links); - struct ATTR_FILE_NAME *fname = - attr->type != ATTR_NAME ? - NULL : - resident_data_ex(attr, - SIZEOF_ATTRIBUTE_FILENAME); - if (fname && fname->type == FILE_NAME_DOS) { - /* Do not decrease links count deleting DOS name. */ - } else if (!links) { + if (!links) { /* minor error. Not critical. */ } else { ni->mi.mrec->hard_links = cpu_to_le16(links - 1); diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index cef5467fd9283..4643b06b1550f 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1804,8 +1804,6 @@ static int __init init_ntfs_fs(void) { int err; - pr_info("ntfs3: Max link count %u\n", NTFS_LINK_MAX); - if (IS_ENABLED(CONFIG_NTFS3_FS_POSIX_ACL)) pr_info("ntfs3: Enabled Linux POSIX ACLs support\n"); if (IS_ENABLED(CONFIG_NTFS3_64BIT_CLUSTER)) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8b6d15010703b..17c9ee95e53f7 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1936,6 +1936,8 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, inode_lock(inode); + /* Wait all existing dio workers, newcomers will block on i_rwsem */ + inode_dio_wait(inode); /* * This prevents concurrent writes on other nodes */ diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 82b28fdacc7e9..accf03d4765ed 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -65,7 +65,7 @@ struct ocfs2_inode_info tid_t i_sync_tid; tid_t i_datasync_tid; - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; }; /* diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 604fea3a26ff0..86807086b2dfd 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -479,12 +479,6 @@ int ocfs2_allocate_extend_trans(handle_t *handle, int thresh) return status; } - -struct ocfs2_triggers { - struct jbd2_buffer_trigger_type ot_triggers; - int ot_offset; -}; - static inline struct ocfs2_triggers *to_ocfs2_trigger(struct jbd2_buffer_trigger_type *triggers) { return container_of(triggers, struct ocfs2_triggers, ot_triggers); @@ -548,85 +542,76 @@ static void ocfs2_db_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh) { + struct ocfs2_triggers *ot = to_ocfs2_trigger(triggers); + mlog(ML_ERROR, "ocfs2_abort_trigger called by JBD2. bh = 0x%lx, " "bh->b_blocknr = %llu\n", (unsigned long)bh, (unsigned long long)bh->b_blocknr); - ocfs2_error(bh->b_assoc_map->host->i_sb, + ocfs2_error(ot->sb, "JBD2 has aborted our journal, ocfs2 cannot continue\n"); } -static struct ocfs2_triggers di_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dinode, i_check), -}; - -static struct ocfs2_triggers eb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_extent_block, h_check), -}; - -static struct ocfs2_triggers rb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_refcount_block, rf_check), -}; - -static struct ocfs2_triggers gd_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_group_desc, bg_check), -}; - -static struct ocfs2_triggers db_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_db_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, -}; +static void ocfs2_setup_csum_triggers(struct super_block *sb, + enum ocfs2_journal_trigger_type type, + struct ocfs2_triggers *ot) +{ + BUG_ON(type >= OCFS2_JOURNAL_TRIGGER_COUNT); -static struct ocfs2_triggers xb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_xattr_block, xb_check), -}; + switch (type) { + case OCFS2_JTR_DI: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dinode, i_check); + break; + case OCFS2_JTR_EB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_extent_block, h_check); + break; + case OCFS2_JTR_RB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_refcount_block, rf_check); + break; + case OCFS2_JTR_GD: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_group_desc, bg_check); + break; + case OCFS2_JTR_DB: + ot->ot_triggers.t_frozen = ocfs2_db_frozen_trigger; + break; + case OCFS2_JTR_XB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_xattr_block, xb_check); + break; + case OCFS2_JTR_DQ: + ot->ot_triggers.t_frozen = ocfs2_dq_frozen_trigger; + break; + case OCFS2_JTR_DR: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check); + break; + case OCFS2_JTR_DL: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check); + break; + case OCFS2_JTR_NONE: + /* To make compiler happy... */ + return; + } -static struct ocfs2_triggers dq_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_dq_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, -}; + ot->ot_triggers.t_abort = ocfs2_abort_trigger; + ot->sb = sb; +} -static struct ocfs2_triggers dr_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check), -}; +void ocfs2_initialize_journal_triggers(struct super_block *sb, + struct ocfs2_triggers triggers[]) +{ + enum ocfs2_journal_trigger_type type; -static struct ocfs2_triggers dl_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check), -}; + for (type = OCFS2_JTR_DI; type < OCFS2_JOURNAL_TRIGGER_COUNT; type++) + ocfs2_setup_csum_triggers(sb, type, &triggers[type]); +} static int __ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci, @@ -708,56 +693,91 @@ static int __ocfs2_journal_access(handle_t *handle, int ocfs2_journal_access_di(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &di_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DI], + type); } int ocfs2_journal_access_eb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &eb_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_EB], + type); } int ocfs2_journal_access_rb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &rb_triggers, + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_RB], type); } int ocfs2_journal_access_gd(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &gd_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_GD], + type); } int ocfs2_journal_access_db(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &db_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DB], + type); } int ocfs2_journal_access_xb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &xb_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_XB], + type); } int ocfs2_journal_access_dq(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dq_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DQ], + type); } int ocfs2_journal_access_dr(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dr_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DR], + type); } int ocfs2_journal_access_dl(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dl_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DL], + type); } int ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci, @@ -778,13 +798,15 @@ void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh) if (!is_handle_aborted(handle)) { journal_t *journal = handle->h_transaction->t_journal; - mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed. " - "Aborting transaction and journal.\n"); + mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed: " + "handle type %u started at line %u, credits %u/%u " + "errcode %d. Aborting transaction and journal.\n", + handle->h_type, handle->h_line_no, + handle->h_requested_credits, + jbd2_handle_buffer_credits(handle), status); handle->h_err = status; jbd2_journal_abort_handle(handle); jbd2_journal_abort(journal, status); - ocfs2_abort(bh->b_assoc_map->host->i_sb, - "Journal already aborted.\n"); } } } diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index c803c10dd97ef..33aeaaa056d70 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -863,14 +863,8 @@ static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb, numfound = bitoff = startoff = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) != -1) { - if (bitoff == left) { - /* mlog(0, "bitoff (%d) == left", bitoff); */ - break; - } - /* mlog(0, "Found a zero: bitoff = %d, startoff = %d, " - "numfound = %d\n", bitoff, startoff, numfound);*/ - + while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) < + left) { /* Ok, we found a zero bit... is it contig. or do we * start over?*/ if (bitoff == startoff) { @@ -976,9 +970,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) - != -1) { - if ((bit_off < left) && (bit_off == start)) { + while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) < + left) { + if (bit_off == start) { count++; start++; continue; @@ -1002,8 +996,7 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, goto bail; } } - if (bit_off >= left) - break; + count = 1; start = bit_off + 1; } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 9221a33f917b8..4d1ea8703fcdf 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -566,7 +566,7 @@ static int __ocfs2_mknod_locked(struct inode *dir, fe->i_last_eb_blk = 0; strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE); fe->i_flags |= cpu_to_le32(OCFS2_VALID_FL); - ktime_get_real_ts64(&ts); + ktime_get_coarse_real_ts64(&ts); fe->i_atime = fe->i_ctime = fe->i_mtime = cpu_to_le64(ts.tv_sec); fe->i_mtime_nsec = fe->i_ctime_nsec = fe->i_atime_nsec = @@ -797,6 +797,7 @@ static int ocfs2_link(struct dentry *old_dentry, ocfs2_set_links_count(fe, inode->i_nlink); fe->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); err = ocfs2_add_entry(handle, dentry, inode, @@ -993,6 +994,7 @@ static int ocfs2_unlink(struct inode *dir, drop_nlink(inode); drop_nlink(inode); ocfs2_set_links_count(fe, inode->i_nlink); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index a503c553bab21..8fe826143d7bf 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -284,6 +284,30 @@ enum ocfs2_mount_options #define OCFS2_OSB_ERROR_FS 0x0004 #define OCFS2_DEFAULT_ATIME_QUANTUM 60 +struct ocfs2_triggers { + struct jbd2_buffer_trigger_type ot_triggers; + int ot_offset; + struct super_block *sb; +}; + +enum ocfs2_journal_trigger_type { + OCFS2_JTR_DI, + OCFS2_JTR_EB, + OCFS2_JTR_RB, + OCFS2_JTR_GD, + OCFS2_JTR_DB, + OCFS2_JTR_XB, + OCFS2_JTR_DQ, + OCFS2_JTR_DR, + OCFS2_JTR_DL, + OCFS2_JTR_NONE /* This must be the last entry */ +}; + +#define OCFS2_JOURNAL_TRIGGER_COUNT OCFS2_JTR_NONE + +void ocfs2_initialize_journal_triggers(struct super_block *sb, + struct ocfs2_triggers triggers[]); + struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; @@ -351,6 +375,9 @@ struct ocfs2_super struct ocfs2_journal *journal; unsigned long osb_commit_interval; + /* Journal triggers for checksum */ + struct ocfs2_triggers s_journal_triggers[OCFS2_JOURNAL_TRIGGER_COUNT]; + struct delayed_work la_enable_wq; /* diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c index a9d1296d736dc..1fe61974d9f02 100644 --- a/fs/ocfs2/reservations.c +++ b/fs/ocfs2/reservations.c @@ -414,7 +414,7 @@ static int ocfs2_resmap_find_free_bits(struct ocfs2_reservation_map *resmap, start = search_start; while ((offset = ocfs2_find_next_zero_bit(bitmap, resmap->m_bitmap_len, - start)) != -1) { + start)) < resmap->m_bitmap_len) { /* Search reached end of the region */ if (offset >= (search_start + search_len)) break; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 166c8918c825a..961998415308d 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1290,10 +1290,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, found = start = best_offset = best_size = 0; bitmap = bg->bg_bitmap; - while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) { - if (offset == total_bits) - break; - + while ((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) < + total_bits) { if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) { /* We found a zero, but we can't use it as it * hasn't been put to disk yet! */ diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 6b906424902b4..cfc093937a178 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -122,7 +122,7 @@ static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend); static int ocfs2_enable_quotas(struct ocfs2_super *osb); static void ocfs2_disable_quotas(struct ocfs2_super *osb); -static struct dquot **ocfs2_get_dquots(struct inode *inode) +static struct dquot __rcu **ocfs2_get_dquots(struct inode *inode) { return OCFS2_I(inode)->i_dquot; } @@ -1075,9 +1075,11 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) debugfs_create_file("fs_state", S_IFREG|S_IRUSR, osb->osb_debug_root, osb, &ocfs2_osb_debug_fops); - if (ocfs2_meta_ecc(osb)) + if (ocfs2_meta_ecc(osb)) { + ocfs2_initialize_journal_triggers(sb, osb->s_journal_triggers); ocfs2_blockcheck_stats_debugfs_install( &osb->osb_ecc_stats, osb->osb_debug_root); + } status = ocfs2_mount_volume(sb); if (status < 0) diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index c4b65a6d41cc3..5cf1809d47bdb 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -355,10 +355,10 @@ static struct inode *openprom_iget(struct super_block *sb, ino_t ino) return inode; } -static int openprom_remount(struct super_block *sb, int *flags, char *data) +static int openpromfs_reconfigure(struct fs_context *fc) { - sync_filesystem(sb); - *flags |= SB_NOATIME; + sync_filesystem(fc->root->d_sb); + fc->sb_flags |= SB_NOATIME; return 0; } @@ -366,7 +366,6 @@ static const struct super_operations openprom_sops = { .alloc_inode = openprom_alloc_inode, .free_inode = openprom_free_inode, .statfs = simple_statfs, - .remount_fs = openprom_remount, }; static int openprom_fill_super(struct super_block *s, struct fs_context *fc) @@ -415,6 +414,7 @@ static int openpromfs_get_tree(struct fs_context *fc) static const struct fs_context_operations openpromfs_context_ops = { .get_tree = openpromfs_get_tree, + .reconfigure = openpromfs_reconfigure, }; static int openpromfs_init_fs_context(struct fs_context *fc) diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 5254256a224d7..4ca8ed410c3cf 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -527,7 +527,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst, sb->s_fs_info = kzalloc(sizeof(struct orangefs_sb_info_s), GFP_KERNEL); if (!ORANGEFS_SB(sb)) { d = ERR_PTR(-ENOMEM); - goto free_sb_and_op; + goto free_op; } ret = orangefs_fill_sb(sb, diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 8586e2f5d2439..0762575a1e708 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -234,11 +234,11 @@ static int ovl_verify_area(loff_t pos, loff_t pos2, loff_t len, loff_t totlen) { loff_t tmp; - if (WARN_ON_ONCE(pos != pos2)) + if (pos != pos2) return -EIO; - if (WARN_ON_ONCE(pos < 0 || len < 0 || totlen < 0)) + if (pos < 0 || len < 0 || totlen < 0) return -EIO; - if (WARN_ON_ONCE(check_add_overflow(pos, len, &tmp))) + if (check_add_overflow(pos, len, &tmp)) return -EIO; return 0; } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 0f8b4a719237c..02d89a285d0dc 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -327,9 +327,6 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode, struct dentry *newdentry; int err; - if (!attr->hardlink && !IS_POSIXACL(udir)) - attr->mode &= ~current_umask(); - inode_lock_nested(udir, I_MUTEX_PARENT); newdentry = ovl_create_real(ofs, udir, ovl_lookup_upper(ofs, dentry->d_name.name, diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 063409069f56d..5868cb2229552 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -181,6 +181,10 @@ static int ovl_check_encode_origin(struct dentry *dentry) struct ovl_fs *ofs = OVL_FS(dentry->d_sb); bool decodable = ofs->config.nfs_export; + /* No upper layer? */ + if (!ovl_upper_mnt(ofs)) + return 1; + /* Lower file handle for non-upper non-decodable */ if (!ovl_dentry_upper(dentry) && !decodable) return 1; @@ -209,7 +213,7 @@ static int ovl_check_encode_origin(struct dentry *dentry) * ovl_connect_layer() will try to make origin's layer "connected" by * copying up a "connectable" ancestor. */ - if (d_is_dir(dentry) && ovl_upper_mnt(ofs) && decodable) + if (d_is_dir(dentry) && decodable) return ovl_connect_layer(dentry); /* Lower file handle for indexed and non-upper dir/non-dir */ diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 112b4b12f8252..5aeea37cc895f 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -55,6 +55,7 @@ enum ovl_opt { Opt_uuid, Opt_nfs_export, Opt_userxattr, + Opt_nouserxattr, Opt_xino, Opt_metacopy, Opt_verity, @@ -155,6 +156,7 @@ const struct fs_parameter_spec ovl_parameter_spec[] = { fsparam_enum("uuid", Opt_uuid, ovl_parameter_uuid), fsparam_enum("nfs_export", Opt_nfs_export, ovl_parameter_bool), fsparam_flag("userxattr", Opt_userxattr), + fsparam_flag("nouserxattr", Opt_nouserxattr), fsparam_enum("xino", Opt_xino, ovl_parameter_xino), fsparam_enum("metacopy", Opt_metacopy, ovl_parameter_bool), fsparam_enum("verity", Opt_verity, ovl_parameter_verity), @@ -280,12 +282,20 @@ static int ovl_mount_dir_check(struct fs_context *fc, const struct path *path, { struct ovl_fs_context *ctx = fc->fs_private; - if (ovl_dentry_weird(path->dentry)) - return invalfc(fc, "filesystem on %s not supported", name); - if (!d_is_dir(path->dentry)) return invalfc(fc, "%s is not a directory", name); + /* + * Root dentries of case-insensitive capable filesystems might + * not have the dentry operations set, but still be incompatible + * with overlayfs. Check explicitly to prevent post-mount + * failures. + */ + if (sb_has_encoding(path->mnt->mnt_sb)) + return invalfc(fc, "case-insensitive capable filesystem on %s not supported", name); + + if (ovl_dentry_weird(path->dentry)) + return invalfc(fc, "filesystem on %s not supported", name); /* * Check whether upper path is read-only here to report failures @@ -619,6 +629,9 @@ static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_userxattr: config->userxattr = true; break; + case Opt_nouserxattr: + config->userxattr = false; + break; default: pr_err("unrecognized mount option \"%s\" or missing value\n", param->key); @@ -725,6 +738,8 @@ int ovl_init_fs_context(struct fs_context *fc) ofs->config.nfs_export = ovl_nfs_export_def; ofs->config.xino = ovl_xino_def(); ofs->config.metacopy = ovl_metacopy_def; + if (fc->user_ns != &init_user_ns) + ofs->config.userxattr = true; fc->s_fs_info = ofs; fc->fs_private = ctx; @@ -997,6 +1012,8 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry) seq_puts(m, ",volatile"); if (ofs->config.userxattr) seq_puts(m, ",userxattr"); + else + seq_puts(m, ",nouserxattr"); if (ofs->config.verity_mode != ovl_verity_mode_def()) seq_printf(m, ",verity=%s", ovl_verity_mode(&ofs->config)); diff --git a/fs/proc/Makefile b/fs/proc/Makefile index bd08616ed8bad..b92ed6889a357 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -5,7 +5,7 @@ obj-y += proc.o -CFLAGS_task_mmu.o += $(call cc-option,-Wno-override-init,) +CFLAGS_task_mmu.o += -Wno-override-init proc-y := nommu.o task_nommu.o proc-$(CONFIG_MMU) := task_mmu.o @@ -33,4 +33,4 @@ proc-$(CONFIG_PROC_KCORE) += kcore.o proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o -proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o +proc-$(CONFIG_BOOT_CONFIG) += bootconfig.o version_signature.o diff --git a/fs/proc/base.c b/fs/proc/base.c index 18550c071d71c..72a1acd03675c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3214,7 +3214,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); - seq_printf(m, "ksm_zero_pages %lu\n", mm->ksm_zero_pages); + seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm)); seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); mmput(mm); diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c index 902b326e1e560..87dcaae32ff87 100644 --- a/fs/proc/bootconfig.c +++ b/fs/proc/bootconfig.c @@ -62,12 +62,12 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size) break; dst += ret; } - if (ret >= 0 && boot_command_line[0]) { - ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n", - boot_command_line); - if (ret > 0) - dst += ret; - } + } + if (cmdline_has_extra_options() && ret >= 0 && boot_command_line[0]) { + ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n", + boot_command_line); + if (ret > 0) + dst += ret; } out: kfree(key); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 6e72e5ad42bc7..f4b1c8b42a511 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -74,7 +74,18 @@ static int seq_show(struct seq_file *m, void *v) return 0; } -static int proc_fdinfo_access_allowed(struct inode *inode) +static int seq_fdinfo_open(struct inode *inode, struct file *file) +{ + return single_open(file, seq_show, inode); +} + +/** + * Shared /proc/pid/fdinfo and /proc/pid/fdinfo/fd permission helper to ensure + * that the current task has PTRACE_MODE_READ in addition to the normal + * POSIX-like checks. + */ +static int proc_fdinfo_permission(struct mnt_idmap *idmap, struct inode *inode, + int mask) { bool allowed = false; struct task_struct *task = get_proc_task(inode); @@ -88,18 +99,13 @@ static int proc_fdinfo_access_allowed(struct inode *inode) if (!allowed) return -EACCES; - return 0; + return generic_permission(idmap, inode, mask); } -static int seq_fdinfo_open(struct inode *inode, struct file *file) -{ - int ret = proc_fdinfo_access_allowed(inode); - - if (ret) - return ret; - - return single_open(file, seq_show, inode); -} +static const struct inode_operations proc_fdinfo_file_inode_operations = { + .permission = proc_fdinfo_permission, + .setattr = proc_setattr, +}; static const struct file_operations proc_fdinfo_file_operations = { .open = seq_fdinfo_open, @@ -388,6 +394,8 @@ static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry, ei = PROC_I(inode); ei->fd = data->fd; + inode->i_op = &proc_fdinfo_file_inode_operations; + inode->i_fop = &proc_fdinfo_file_operations; tid_fd_update_inode(task, inode, 0); @@ -407,23 +415,13 @@ static int proc_readfdinfo(struct file *file, struct dir_context *ctx) proc_fdinfo_instantiate); } -static int proc_open_fdinfo(struct inode *inode, struct file *file) -{ - int ret = proc_fdinfo_access_allowed(inode); - - if (ret) - return ret; - - return 0; -} - const struct inode_operations proc_fdinfo_inode_operations = { .lookup = proc_lookupfdinfo, + .permission = proc_fdinfo_permission, .setattr = proc_setattr, }; const struct file_operations proc_fdinfo_operations = { - .open = proc_open_fdinfo, .read = generic_read_dir, .iterate_shared = proc_readfdinfo, .llseek = generic_file_llseek, diff --git a/fs/proc/page.c b/fs/proc/page.c index 195b077c0facb..9223856c934b4 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -67,7 +67,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, */ ppage = pfn_to_online_page(pfn); - if (!ppage || PageSlab(ppage) || page_has_type(ppage)) + if (!ppage) pcount = 0; else pcount = page_mapcount(ppage); @@ -124,11 +124,8 @@ u64 stable_page_flags(struct page *page) /* * pseudo flags for the well known (anonymous) memory mapped pages - * - * Note that page->_mapcount is overloaded in SLAB, so the - * simple test in page_mapped() is not enough. */ - if (!PageSlab(page) && page_mapped(page)) + if (page_mapped(page)) u |= 1 << KPF_MMAP; if (PageAnon(page)) u |= 1 << KPF_ANON; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3f78ebbb795fe..a44d0b578df77 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -965,12 +965,17 @@ static int show_smaps_rollup(struct seq_file *m, void *v) break; /* Case 1 and 2 above */ - if (vma->vm_start >= last_vma_end) + if (vma->vm_start >= last_vma_end) { + smap_gather_stats(vma, &mss, 0); + last_vma_end = vma->vm_end; continue; + } /* Case 4 above */ - if (vma->vm_end > last_vma_end) + if (vma->vm_end > last_vma_end) { smap_gather_stats(vma, &mss, last_vma_end); + last_vma_end = vma->vm_end; + } } } for_each_vma(vmi, vma); @@ -1818,15 +1823,13 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, } static void make_uffd_wp_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t *pte) + unsigned long addr, pte_t *pte, pte_t ptent) { - pte_t ptent = ptep_get(pte); - if (pte_present(ptent)) { pte_t old_pte; old_pte = ptep_modify_prot_start(vma, addr, pte); - ptent = pte_mkuffd_wp(ptent); + ptent = pte_mkuffd_wp(old_pte); ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); } else if (is_swap_pte(ptent)) { ptent = pte_swp_mkuffd_wp(ptent); @@ -2176,9 +2179,12 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) { /* Fast path for performing exclusive WP */ for (addr = start; addr != end; pte++, addr += PAGE_SIZE) { - if (pte_uffd_wp(ptep_get(pte))) + pte_t ptent = ptep_get(pte); + + if ((pte_present(ptent) && pte_uffd_wp(ptent)) || + pte_swp_uffd_wp_any(ptent)) continue; - make_uffd_wp_pte(vma, addr, pte); + make_uffd_wp_pte(vma, addr, pte, ptent); if (!flush_end) start = addr; flush_end = addr + PAGE_SIZE; @@ -2191,8 +2197,10 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, p->arg.return_mask == PAGE_IS_WRITTEN) { for (addr = start; addr < end; pte++, addr += PAGE_SIZE) { unsigned long next = addr + PAGE_SIZE; + pte_t ptent = ptep_get(pte); - if (pte_uffd_wp(ptep_get(pte))) + if ((pte_present(ptent) && pte_uffd_wp(ptent)) || + pte_swp_uffd_wp_any(ptent)) continue; ret = pagemap_scan_output(p->cur_vma_category | PAGE_IS_WRITTEN, p, addr, &next); @@ -2200,7 +2208,7 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, break; if (~p->arg.flags & PM_SCAN_WP_MATCHING) continue; - make_uffd_wp_pte(vma, addr, pte); + make_uffd_wp_pte(vma, addr, pte, ptent); if (!flush_end) start = addr; flush_end = next; @@ -2209,8 +2217,9 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, } for (addr = start; addr != end; pte++, addr += PAGE_SIZE) { + pte_t ptent = ptep_get(pte); unsigned long categories = p->cur_vma_category | - pagemap_page_category(p, vma, addr, ptep_get(pte)); + pagemap_page_category(p, vma, addr, ptent); unsigned long next = addr + PAGE_SIZE; if (!pagemap_scan_is_interesting_page(categories, p)) @@ -2225,7 +2234,7 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, if (~categories & PAGE_IS_WRITTEN) continue; - make_uffd_wp_pte(vma, addr, pte); + make_uffd_wp_pte(vma, addr, pte, ptent); if (!flush_end) start = addr; flush_end = next; diff --git a/fs/proc/version_signature.c b/fs/proc/version_signature.c new file mode 100644 index 0000000000000..1feb4dfa1ddd2 --- /dev/null +++ b/fs/proc/version_signature.c @@ -0,0 +1,32 @@ +#include +#include +#include +#include +#include +#include +#include + +static int version_signature_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s\n", CONFIG_VERSION_SIGNATURE); + return 0; +} + +static int version_signature_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, version_signature_proc_show, NULL); +} + +static const struct proc_ops version_signature_proc_fops = { + .proc_open = version_signature_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init proc_version_signature_init(void) +{ + proc_create("version_signature", 0, NULL, &version_signature_proc_fops); + return 0; +} +module_init(proc_version_signature_init); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 1fb213f379a5b..d06607a1f137a 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -383,6 +383,8 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) /* leave now if filled buffer already */ if (!iov_iter_count(iter)) return acc; + + cond_resched(); } list_for_each_entry(m, &vmcore_list, list) { diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index d0d9bfdad30cc..56815799ce798 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -307,7 +307,6 @@ int pstore_put_backend_records(struct pstore_info *psi) { struct pstore_private *pos, *tmp; struct dentry *root; - int rc = 0; root = psinfo_lock_root(); if (!root) @@ -317,11 +316,8 @@ int pstore_put_backend_records(struct pstore_info *psi) list_for_each_entry_safe(pos, tmp, &records_list, list) { if (pos->record->psi == psi) { list_del_init(&pos->list); - rc = simple_unlink(d_inode(root), pos->dentry); - if (WARN_ON(rc)) - break; - d_drop(pos->dentry); - dput(pos->dentry); + d_invalidate(pos->dentry); + simple_unlink(d_inode(root), pos->dentry); pos->dentry = NULL; } } @@ -329,7 +325,7 @@ int pstore_put_backend_records(struct pstore_info *psi) inode_unlock(d_inode(root)); - return rc; + return 0; } /* diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index 2770746bb7aa1..abca117725c81 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -973,6 +973,8 @@ static ssize_t psz_kmsg_read(struct pstore_zone *zone, char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n", kmsg_dump_reason_str(record->reason), record->count); + if (!buf) + return -ENOMEM; hlen = strlen(buf); record->buf = krealloc(buf, hlen + size, GFP_KERNEL); if (!record->buf) { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 1f0c754416b64..51ff554dc875a 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -399,15 +399,17 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) EXPORT_SYMBOL(dquot_mark_dquot_dirty); /* Dirtify all the dquots - this can block when journalling */ -static inline int mark_all_dquot_dirty(struct dquot * const *dquot) +static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots) { int ret, err, cnt; + struct dquot *dquot; ret = err = 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquot[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) /* Even in case of error we have to continue */ - ret = mark_dquot_dirty(dquot[cnt]); + ret = mark_dquot_dirty(dquot); if (!err) err = ret; } @@ -998,14 +1000,14 @@ struct dquot *dqget(struct super_block *sb, struct kqid qid) } EXPORT_SYMBOL(dqget); -static inline struct dquot **i_dquot(struct inode *inode) +static inline struct dquot __rcu **i_dquot(struct inode *inode) { return inode->i_sb->s_op->get_dquots(inode); } static int dqinit_needed(struct inode *inode, int type) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1095,14 +1097,16 @@ static void remove_dquot_ref(struct super_block *sb, int type) */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { - struct dquot **dquots = i_dquot(inode); - struct dquot *dquot = dquots[type]; + struct dquot __rcu **dquots = i_dquot(inode); + struct dquot *dquot = srcu_dereference_check( + dquots[type], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif - dquots[type] = NULL; + rcu_assign_pointer(dquots[type], NULL); if (dquot) dqput(dquot); } @@ -1455,7 +1459,8 @@ static int inode_quota_active(const struct inode *inode) static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot **dquots, *got[MAXQUOTAS] = {}; + struct dquot __rcu **dquots; + struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; @@ -1530,7 +1535,7 @@ static int __dquot_initialize(struct inode *inode, int type) if (!got[cnt]) continue; if (!dquots[cnt]) { - dquots[cnt] = got[cnt]; + rcu_assign_pointer(dquots[cnt], got[cnt]); got[cnt] = NULL; /* * Make quota reservation system happy if someone @@ -1538,12 +1543,16 @@ static int __dquot_initialize(struct inode *inode, int type) */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { + struct dquot *dquot = srcu_dereference_check( + dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + spin_lock(&inode->i_lock); /* Get reservation again under proper lock */ rsv = __inode_get_rsv_space(inode); - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquots[cnt]->dq_dqb.dqb_rsvspace += rsv; - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot->dq_dqb.dqb_rsvspace += rsv; + spin_unlock(&dquot->dq_dqb_lock); spin_unlock(&inode->i_lock); } } @@ -1565,7 +1574,7 @@ EXPORT_SYMBOL(dquot_initialize); bool dquot_initialize_needed(struct inode *inode) { - struct dquot **dquots; + struct dquot __rcu **dquots; int i; if (!inode_quota_active(inode)) @@ -1590,13 +1599,14 @@ EXPORT_SYMBOL(dquot_initialize_needed); static void __dquot_drop(struct inode *inode) { int cnt; - struct dquot **dquots = i_dquot(inode); + struct dquot __rcu **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - put[cnt] = dquots[cnt]; - dquots[cnt] = NULL; + put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + rcu_assign_pointer(dquots[cnt], NULL); } spin_unlock(&dq_data_lock); dqput_all(put); @@ -1604,7 +1614,7 @@ static void __dquot_drop(struct inode *inode) void dquot_drop(struct inode *inode) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1677,7 +1687,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; int reserve = flags & DQUOT_SPACE_RESERVE; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) { if (reserve) { @@ -1697,27 +1708,26 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; if (reserve) { - ret = dquot_add_space(dquots[cnt], 0, number, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]); } else { - ret = dquot_add_space(dquots[cnt], number, 0, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]); } if (ret) { /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); if (reserve) - dquot_free_reserved_space(dquots[cnt], - number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); goto out_flush_warn; @@ -1747,7 +1757,8 @@ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) return 0; @@ -1758,17 +1769,19 @@ int dquot_alloc_inode(struct inode *inode) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]); + ret = dquot_add_inodes(dquot, 1, &warn[cnt]); if (ret) { for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; /* Back out changes we already did */ - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } goto warn_put_all; } @@ -1789,7 +1802,8 @@ EXPORT_SYMBOL(dquot_alloc_inode); */ void dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1805,9 +1819,8 @@ void dquot_claim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) number = dquot->dq_dqb.dqb_rsvspace; @@ -1831,7 +1844,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty); */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1847,9 +1861,8 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) number = dquot->dq_dqb.dqb_curspace; @@ -1875,7 +1888,8 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!inode_quota_active(inode)) { @@ -1896,17 +1910,18 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_bdq_free(dquots[cnt], number); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_bdq_free(dquot, number); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); + prepare_warning(&warn[cnt], dquot, wtype); if (reserve) - dquot_free_reserved_space(dquots[cnt], number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } if (reserve) *inode_reserved_space(inode) -= number; @@ -1930,7 +1945,8 @@ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; int index; if (!inode_quota_active(inode)) @@ -1941,16 +1957,16 @@ void dquot_free_inode(struct inode *inode) spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; - warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_idq_free(dquots[cnt], 1); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_idq_free(dquot, 1); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + prepare_warning(&warn[cnt], dquot, wtype); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); @@ -1976,8 +1992,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) qsize_t cur_space; qsize_t rsv_space = 0; qsize_t inode_usage = 1; + struct dquot __rcu **dquots; struct dquot *transfer_from[MAXQUOTAS] = {}; - int cnt, ret = 0; + int cnt, index, ret = 0; char is_valid[MAXQUOTAS] = {}; struct dquot_warn warn_to[MAXQUOTAS]; struct dquot_warn warn_from_inodes[MAXQUOTAS]; @@ -2008,6 +2025,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) } cur_space = __inode_get_bytes(inode); rsv_space = __inode_get_rsv_space(inode); + dquots = i_dquot(inode); /* * Build the transfer_from list, check limits, and update usage in * the target structures. @@ -2022,7 +2040,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; - transfer_from[cnt] = i_dquot(inode)[cnt]; + transfer_from[cnt] = srcu_dereference_check(dquots[cnt], + &dquot_srcu, lockdep_is_held(&dq_data_lock)); ret = dquot_add_inodes(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) @@ -2061,13 +2080,21 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) rsv_space); spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } - i_dquot(inode)[cnt] = transfer_to[cnt]; + rcu_assign_pointer(dquots[cnt], transfer_to[cnt]); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(transfer_from); - mark_all_dquot_dirty(transfer_to); + /* + * These arrays are local and we hold dquot references so we don't need + * the srcu protection but still take dquot_srcu to avoid warning in + * mark_all_dquot_dirty(). + */ + index = srcu_read_lock(&dquot_srcu); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_from); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_to); + srcu_read_unlock(&dquot_srcu, index); + flush_warnings(warn_to); flush_warnings(warn_from_inodes); flush_warnings(warn_from_space); diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 725667880e626..b65549164590c 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -97,7 +97,7 @@ struct reiserfs_inode_info { struct rw_semaphore i_xattr_sem; #endif #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif struct inode vfs_inode; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 67b5510beded2..7b3d5aeb2a6fe 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -802,7 +802,7 @@ static ssize_t reiserfs_quota_write(struct super_block *, int, const char *, static ssize_t reiserfs_quota_read(struct super_block *, int, char *, size_t, loff_t); -static struct dquot **reiserfs_get_dquots(struct inode *inode) +static struct dquot __rcu **reiserfs_get_dquots(struct inode *inode) { return REISERFS_I(inode)->i_dquot; } diff --git a/fs/select.c b/fs/select.c index 0ee55af1a55c2..d4d881d439dcd 100644 --- a/fs/select.c +++ b/fs/select.c @@ -476,7 +476,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in, wait->_key |= POLLOUT_SET; } -static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) +static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 3de5047a7ff98..0ff2491c311d8 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -239,7 +239,8 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, .tcon = tcon, .path = path, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE), - .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES, + .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES | + FILE_READ_EA, .disposition = FILE_OPEN, .fid = pfid, .replay = !!(retries), @@ -416,6 +417,7 @@ smb2_close_cached_fid(struct kref *ref) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); + int rc; spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->on_list) { @@ -429,9 +431,10 @@ smb2_close_cached_fid(struct kref *ref) cfid->dentry = NULL; if (cfid->is_open) { - SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, cfid->fid.volatile_fid); - atomic_dec(&cfid->tcon->num_remote_opens); + if (rc) /* should we retry on -EBUSY or -EAGAIN? */ + cifs_dbg(VFS, "close cached dir rc %d\n", rc); } free_cached_dir(cfid); diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 3e4209f41c18f..aa95fa95ca112 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -250,6 +250,8 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); list_for_each_entry(cfile, &tcon->openFileList, tlist) { @@ -488,6 +490,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) ses->ses_count, ses->serverOS, ses->serverNOS, ses->capabilities, ses->ses_status); } + if (ses->expired_pwd) + seq_puts(m, "password no longer valid "); spin_unlock(&ses->ses_lock); seq_printf(m, "\n\tSecurity type: %s ", @@ -654,6 +658,8 @@ static ssize_t cifs_stats_proc_write(struct file *file, } #endif /* CONFIG_CIFS_STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { atomic_set(&tcon->num_smbs_sent, 0); spin_lock(&tcon->stat_lock); @@ -733,6 +739,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) } #endif /* STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { i++; seq_printf(m, "\n%d) %s", i, tcon->tree_name); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 0c269396ae151..c318cf8ed94c8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -134,7 +134,7 @@ module_param(enable_oplocks, bool, 0644); MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1"); module_param(enable_gcm_256, bool, 0644); -MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: n/N/0"); +MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/0"); module_param(require_gcm_256, bool, 0644); MODULE_PARM_DESC(require_gcm_256, "Require strongest (256 bit) GCM encryption. Default: n/N/0"); @@ -160,6 +160,7 @@ struct workqueue_struct *decrypt_wq; struct workqueue_struct *fileinfo_put_wq; struct workqueue_struct *cifsoplockd_wq; struct workqueue_struct *deferredclose_wq; +struct workqueue_struct *serverclose_wq; __u32 cifs_lock_secret; /* @@ -392,6 +393,7 @@ cifs_alloc_inode(struct super_block *sb) * server, can not assume caching of file data or metadata. */ cifs_set_oplock_level(cifs_inode, 0); + cifs_inode->lease_granted = false; cifs_inode->flags = 0; spin_lock_init(&cifs_inode->writers_lock); cifs_inode->writers = 0; @@ -1278,7 +1280,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, struct cifsFileInfo *smb_file_src = src_file->private_data; struct cifsFileInfo *smb_file_target = dst_file->private_data; struct cifs_tcon *target_tcon, *src_tcon; - unsigned long long destend, fstart, fend, new_size; + unsigned long long destend, fstart, fend, old_size, new_size; unsigned int xid; int rc; @@ -1343,6 +1345,9 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false); if (rc) goto unlock; + if (fend > target_cifsi->netfs.zero_point) + target_cifsi->netfs.zero_point = fend + 1; + old_size = target_cifsi->netfs.remote_i_size; /* Discard all the folios that overlap the destination region. */ cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend); @@ -1355,12 +1360,13 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, if (target_tcon->ses->server->ops->duplicate_extents) { rc = target_tcon->ses->server->ops->duplicate_extents(xid, smb_file_src, smb_file_target, off, len, destoff); - if (rc == 0 && new_size > i_size_read(target_inode)) { + if (rc == 0 && new_size > old_size) { truncate_setsize(target_inode, new_size); - netfs_resize_file(&target_cifsi->netfs, new_size, true); fscache_resize_cookie(cifs_inode_cookie(target_inode), new_size); } + if (rc == 0 && new_size > target_cifsi->netfs.zero_point) + target_cifsi->netfs.zero_point = new_size; } /* force revalidate of size and timestamps of target file now @@ -1452,6 +1458,8 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false); if (rc) goto unlock; + if (fend > target_cifsi->netfs.zero_point) + target_cifsi->netfs.zero_point = fend + 1; /* Discard all the folios that overlap the destination region. */ truncate_inode_pages_range(&target_inode->i_data, fstart, fend); @@ -1893,6 +1901,13 @@ init_cifs(void) goto out_destroy_cifsoplockd_wq; } + serverclose_wq = alloc_workqueue("serverclose", + WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); + if (!serverclose_wq) { + rc = -ENOMEM; + goto out_destroy_serverclose_wq; + } + rc = cifs_init_inodecache(); if (rc) goto out_destroy_deferredclose_wq; @@ -1967,6 +1982,8 @@ init_cifs(void) destroy_workqueue(decrypt_wq); out_destroy_cifsiod_wq: destroy_workqueue(cifsiod_wq); +out_destroy_serverclose_wq: + destroy_workqueue(serverclose_wq); out_clean_proc: cifs_proc_clean(); return rc; @@ -1996,6 +2013,7 @@ exit_cifs(void) destroy_workqueue(cifsoplockd_wq); destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); + destroy_workqueue(serverclose_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 53c75cfb33ab9..a393d505e847a 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -346,6 +346,9 @@ struct smb_version_operations { /* informational QFS call */ void (*qfs_tcon)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *); + /* query for server interfaces */ + int (*query_server_interfaces)(const unsigned int, struct cifs_tcon *, + bool); /* check if a path is accessible or not */ int (*is_path_accessible)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const char *); @@ -429,10 +432,10 @@ struct smb_version_operations { /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ - void (*close)(const unsigned int, struct cifs_tcon *, + int (*close)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); /* close a file, returning file attributes and timestamps */ - void (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, + int (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *pfile_info); /* send a flush request to the server */ int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *); @@ -1060,12 +1063,14 @@ struct cifs_ses { and after mount option parsing we fill it */ char *domainName; char *password; + char *password2; /* When key rotation used, new password may be set before it expires */ char workstation_name[CIFS_MAX_WORKSTATION_LEN]; struct session_key auth_key; struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */ enum securityEnum sectype; /* what security flavor was specified? */ bool sign; /* is signing required? */ bool domainAuto:1; + bool expired_pwd; /* track if access denied or expired pwd so can know if need to update */ unsigned int flags; __u16 session_flags; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; @@ -1257,13 +1262,14 @@ struct cifs_tcon { __u32 max_cached_dirs; #ifdef CONFIG_CIFS_FSCACHE u64 resource_id; /* server resource id */ + bool fscache_acquired; /* T if we've tried acquiring a cookie */ struct fscache_volume *fscache; /* cookie for share */ + struct mutex fscache_lock; /* Prevent regetting a cookie */ #endif struct list_head pending_opens; /* list of incomplete opens */ struct cached_fids *cfids; /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL - struct list_head dfs_ses_list; struct delayed_work dfs_cache_work; #endif struct delayed_work query_interfaces; /* query interfaces workqueue job */ @@ -1420,6 +1426,7 @@ struct cifsFileInfo { bool invalidHandle:1; /* file closed via session abend */ bool swapfile:1; bool oplock_break_cancelled:1; + bool offload:1; /* offload final part of _put to a wq */ unsigned int oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ int count; @@ -1428,6 +1435,7 @@ struct cifsFileInfo { struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ struct work_struct put; /* work for the final part of _put */ + struct work_struct serverclose; /* work for serverclose */ struct delayed_work deferred; bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ char *symlink_target; @@ -1784,7 +1792,6 @@ struct cifs_mount_ctx { struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct list_head dfs_ses_list; }; static inline void __free_dfs_info_param(struct dfs_info3_param *param) @@ -2085,6 +2092,7 @@ extern struct workqueue_struct *decrypt_wq; extern struct workqueue_struct *fileinfo_put_wq; extern struct workqueue_struct *cifsoplockd_wq; extern struct workqueue_struct *deferredclose_wq; +extern struct workqueue_struct *serverclose_wq; extern __u32 cifs_lock_secret; extern mempool_t *cifs_mid_poolp; @@ -2290,4 +2298,14 @@ struct smb2_compound_vars { struct smb2_file_link_info link_info; }; +static inline bool cifs_ses_exiting(struct cifs_ses *ses) +{ + bool ret; + + spin_lock(&ses->ses_lock); + ret = ses->ses_status == SES_EXITING; + spin_unlock(&ses->ses_lock); + return ret; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index c0513fbb8a59d..c46d418c1c0c3 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -882,7 +882,7 @@ typedef struct smb_com_open_rsp { __u8 OplockLevel; __u16 Fid; __le32 CreateAction; - struct_group(common_attributes, + struct_group_attr(common_attributes, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; @@ -2266,7 +2266,7 @@ typedef struct { /* QueryFileInfo/QueryPathinfo (also for SetPath/SetFile) data buffer formats */ /******************************************************************************/ typedef struct { /* data block encoding of response to level 263 QPathInfo */ - struct_group(common_attributes, + struct_group_attr(common_attributes, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index a841bf4967fa4..996ca413dd8bd 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -144,7 +144,8 @@ extern int cifs_reconnect(struct TCP_Server_Info *server, extern int checkSMB(char *buf, unsigned int len, struct TCP_Server_Info *srvr); extern bool is_valid_oplock_break(char *, struct TCP_Server_Info *); extern bool backup_cred(struct cifs_sb_info *); -extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof); +extern bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 eof, + bool from_readdir); extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset, unsigned int bytes_written); extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int); @@ -201,7 +202,8 @@ extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb); extern void cifs_dir_info_to_fattr(struct cifs_fattr *, FILE_DIRECTORY_INFO *, struct cifs_sb_info *); -extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr); +extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, + bool from_readdir); extern struct inode *cifs_iget(struct super_block *sb, struct cifs_fattr *fattr); @@ -721,31 +723,31 @@ struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon); void cifs_put_tcon_super(struct super_block *sb); int cifs_wait_for_server_reconnect(struct TCP_Server_Info *server, bool retry); -/* Put references of @ses and @ses->dfs_root_ses */ +/* Put references of @ses and its children */ static inline void cifs_put_smb_ses(struct cifs_ses *ses) { - struct cifs_ses *rses = ses->dfs_root_ses; + struct cifs_ses *next; - __cifs_put_smb_ses(ses); - if (rses) - __cifs_put_smb_ses(rses); + do { + next = ses->dfs_root_ses; + __cifs_put_smb_ses(ses); + } while ((ses = next)); } -/* Get an active reference of @ses and @ses->dfs_root_ses. +/* Get an active reference of @ses and its children. * * NOTE: make sure to call this function when incrementing reference count of * @ses to ensure that any DFS root session attached to it (@ses->dfs_root_ses) * will also get its reference count incremented. * - * cifs_put_smb_ses() will put both references, so call it when you're done. + * cifs_put_smb_ses() will put all references, so call it when you're done. */ static inline void cifs_smb_ses_inc_refcount(struct cifs_ses *ses) { lockdep_assert_held(&cifs_tcp_ses_lock); - ses->ses_count++; - if (ses->dfs_root_ses) - ses->dfs_root_ses->ses_count++; + for (; ses; ses = ses->dfs_root_ses) + ses->ses_count++; } static inline bool dfs_src_pathname_equal(const char *s1, const char *s2) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index ac9595504f4b1..e28f011f11d6c 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -123,12 +123,16 @@ static void smb2_query_server_interfaces(struct work_struct *work) struct cifs_tcon *tcon = container_of(work, struct cifs_tcon, query_interfaces.work); + struct TCP_Server_Info *server = tcon->ses->server; /* * query server network interfaces, in case they change */ + if (!server->ops->query_server_interfaces) + return; + xid = get_xid(); - rc = SMB3_request_interfaces(xid, tcon, false); + rc = server->ops->query_server_interfaces(xid, tcon, false); free_xid(xid); if (rc) { @@ -174,6 +178,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; spin_lock(&ses->chan_lock); for (i = 0; i < ses->chan_count; i++) { if (!ses->chans[i].server) @@ -231,7 +237,13 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { - /* check if iface is still active */ + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); + continue; + } + spin_unlock(&ses->ses_lock); + spin_lock(&ses->chan_lock); if (cifs_ses_get_chan_index(ses, server) == CIFS_INVAL_CHAN_INDEX) { @@ -1859,6 +1871,9 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) ctx->sectype != ses->sectype) return 0; + if (ctx->dfs_root_ses != ses->dfs_root_ses) + return 0; + /* * If an existing session is limited to less channels than * requested, it should not be reused @@ -1962,31 +1977,6 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) return rc; } -/** - * cifs_free_ipc - helper to release the session IPC tcon - * @ses: smb session to unmount the IPC from - * - * Needs to be called everytime a session is destroyed. - * - * On session close, the IPC is closed and the server must release all tcons of the session. - * No need to send a tree disconnect here. - * - * Besides, it will make the server to not close durable and resilient files on session close, as - * specified in MS-SMB2 3.3.5.6 Receiving an SMB2 LOGOFF Request. - */ -static int -cifs_free_ipc(struct cifs_ses *ses) -{ - struct cifs_tcon *tcon = ses->tcon_ipc; - - if (tcon == NULL) - return 0; - - tconInfoFree(tcon); - ses->tcon_ipc = NULL; - return 0; -} - static struct cifs_ses * cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { @@ -2018,48 +2008,52 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) void __cifs_put_smb_ses(struct cifs_ses *ses) { struct TCP_Server_Info *server = ses->server; + struct cifs_tcon *tcon; unsigned int xid; size_t i; + bool do_logoff; int rc; + spin_lock(&cifs_tcp_ses_lock); spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_EXITING) { + cifs_dbg(FYI, "%s: id=0x%llx ses_count=%d ses_status=%u ipc=%s\n", + __func__, ses->Suid, ses->ses_count, ses->ses_status, + ses->tcon_ipc ? ses->tcon_ipc->tree_name : "none"); + if (ses->ses_status == SES_EXITING || --ses->ses_count > 0) { spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); return; } - spin_unlock(&ses->ses_lock); + /* ses_count can never go negative */ + WARN_ON(ses->ses_count < 0); - cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); - cifs_dbg(FYI, - "%s: ses ipc: %s\n", __func__, ses->tcon_ipc ? ses->tcon_ipc->tree_name : "NONE"); + spin_lock(&ses->chan_lock); + cifs_chan_clear_need_reconnect(ses, server); + spin_unlock(&ses->chan_lock); - spin_lock(&cifs_tcp_ses_lock); - if (--ses->ses_count > 0) { - spin_unlock(&cifs_tcp_ses_lock); - return; - } - spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_GOOD) - ses->ses_status = SES_EXITING; + do_logoff = ses->ses_status == SES_GOOD && server->ops->logoff; + ses->ses_status = SES_EXITING; + tcon = ses->tcon_ipc; + ses->tcon_ipc = NULL; spin_unlock(&ses->ses_lock); spin_unlock(&cifs_tcp_ses_lock); - /* ses_count can never go negative */ - WARN_ON(ses->ses_count < 0); - - spin_lock(&ses->ses_lock); - if (ses->ses_status == SES_EXITING && server->ops->logoff) { - spin_unlock(&ses->ses_lock); - cifs_free_ipc(ses); + /* + * On session close, the IPC is closed and the server must release all + * tcons of the session. No need to send a tree disconnect here. + * + * Besides, it will make the server to not close durable and resilient + * files on session close, as specified in MS-SMB2 3.3.5.6 Receiving an + * SMB2 LOGOFF Request. + */ + tconInfoFree(tcon); + if (do_logoff) { xid = get_xid(); rc = server->ops->logoff(xid, ses); if (rc) cifs_server_dbg(VFS, "%s: Session Logoff failure rc=%d\n", __func__, rc); _free_xid(xid); - } else { - spin_unlock(&ses->ses_lock); - cifs_free_ipc(ses); } spin_lock(&cifs_tcp_ses_lock); @@ -2192,6 +2186,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) } ++delim; + /* BB consider adding support for password2 (Key Rotation) for multiuser in future */ ctx->password = kstrndup(delim, len, GFP_KERNEL); if (!ctx->password) { cifs_dbg(FYI, "Unable to allocate %zd bytes for password\n", @@ -2215,6 +2210,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) kfree(ctx->username); ctx->username = NULL; kfree_sensitive(ctx->password); + /* no need to free ctx->password2 since not allocated in this path */ ctx->password = NULL; goto out_key_put; } @@ -2326,6 +2322,12 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) if (!ses->password) goto get_ses_fail; } + /* ctx->password freed at unmount */ + if (ctx->password2) { + ses->password2 = kstrdup(ctx->password2, GFP_KERNEL); + if (!ses->password2) + goto get_ses_fail; + } if (ctx->domainname) { ses->domainName = kstrdup(ctx->domainname, GFP_KERNEL); if (!ses->domainName) @@ -2372,9 +2374,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) * need to lock before changing something in the session. */ spin_lock(&cifs_tcp_ses_lock); + if (ctx->dfs_root_ses) + cifs_smb_ses_inc_refcount(ctx->dfs_root_ses); ses->dfs_root_ses = ctx->dfs_root_ses; - if (ses->dfs_root_ses) - ses->dfs_root_ses->ses_count++; list_add(&ses->smb_ses_list, &server->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); @@ -3323,6 +3325,9 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx) cifs_put_smb_ses(mnt_ctx->ses); else if (mnt_ctx->server) cifs_put_tcp_session(mnt_ctx->server, 0); + mnt_ctx->ses = NULL; + mnt_ctx->tcon = NULL; + mnt_ctx->server = NULL; mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; free_xid(mnt_ctx->xid); } @@ -3601,8 +3606,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) bool isdfs; int rc; - INIT_LIST_HEAD(&mnt_ctx.dfs_ses_list); - rc = dfs_mount_share(&mnt_ctx, &isdfs); if (rc) goto error; @@ -3633,7 +3636,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) return rc; error: - dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list); cifs_mount_put_conns(&mnt_ctx); return rc; } @@ -3648,6 +3650,18 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; rc = cifs_mount_get_tcon(&mnt_ctx); + if (!rc) { + /* + * Prevent superblock from being created with any missing + * connections. + */ + if (WARN_ON(!mnt_ctx.server)) + rc = -EHOSTDOWN; + else if (WARN_ON(!mnt_ctx.ses)) + rc = -EACCES; + else if (WARN_ON(!mnt_ctx.tcon)) + rc = -ENOENT; + } if (rc) goto error; @@ -3985,13 +3999,14 @@ cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses) } static struct cifs_tcon * -cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) +__cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) { int rc; struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb); struct cifs_ses *ses; struct cifs_tcon *tcon = NULL; struct smb3_fs_context *ctx; + char *origin_fullpath = NULL; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (ctx == NULL) @@ -4015,6 +4030,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ctx->sign = master_tcon->ses->sign; ctx->seal = master_tcon->seal; ctx->witness = master_tcon->use_witness; + ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses; rc = cifs_set_vol_auth(ctx, master_tcon->ses); if (rc) { @@ -4034,12 +4050,39 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) goto out; } +#ifdef CONFIG_CIFS_DFS_UPCALL + spin_lock(&master_tcon->tc_lock); + if (master_tcon->origin_fullpath) { + spin_unlock(&master_tcon->tc_lock); + origin_fullpath = dfs_get_path(cifs_sb, cifs_sb->ctx->source); + if (IS_ERR(origin_fullpath)) { + tcon = ERR_CAST(origin_fullpath); + origin_fullpath = NULL; + cifs_put_smb_ses(ses); + goto out; + } + } else { + spin_unlock(&master_tcon->tc_lock); + } +#endif + tcon = cifs_get_tcon(ses, ctx); if (IS_ERR(tcon)) { cifs_put_smb_ses(ses); goto out; } +#ifdef CONFIG_CIFS_DFS_UPCALL + if (origin_fullpath) { + spin_lock(&tcon->tc_lock); + tcon->origin_fullpath = origin_fullpath; + spin_unlock(&tcon->tc_lock); + origin_fullpath = NULL; + queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, + dfs_cache_get_ttl() * HZ); + } +#endif + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(ses)) reset_cifs_unix_caps(0, tcon, NULL, ctx); @@ -4048,11 +4091,23 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) out: kfree(ctx->username); kfree_sensitive(ctx->password); + kfree(origin_fullpath); kfree(ctx); return tcon; } +static struct cifs_tcon * +cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) +{ + struct cifs_tcon *ret; + + cifs_mount_lock(); + ret = __cifs_construct_tcon(cifs_sb, fsuid); + cifs_mount_unlock(); + return ret; +} + struct cifs_tcon * cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb) { diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 449c59830039b..3ec965547e3d4 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -66,33 +66,20 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) } /* - * Track individual DFS referral servers used by new DFS mount. - * - * On success, their lifetime will be shared by final tcon (dfs_ses_list). - * Otherwise, they will be put by dfs_put_root_smb_sessions() in cifs_mount(). + * Get an active reference of @ses so that next call to cifs_put_tcon() won't + * release it as any new DFS referrals must go through its IPC tcon. */ -static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) +static void add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - struct dfs_root_ses *root_ses; struct cifs_ses *ses = mnt_ctx->ses; if (ses) { - root_ses = kmalloc(sizeof(*root_ses), GFP_KERNEL); - if (!root_ses) - return -ENOMEM; - - INIT_LIST_HEAD(&root_ses->list); - spin_lock(&cifs_tcp_ses_lock); cifs_smb_ses_inc_refcount(ses); spin_unlock(&cifs_tcp_ses_lock); - root_ses->ses = ses; - list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list); } - /* Select new DFS referral server so that new referrals go through it */ ctx->dfs_root_ses = ses; - return 0; } static inline int parse_dfs_target(struct smb3_fs_context *ctx, @@ -185,11 +172,8 @@ static int __dfs_referral_walk(struct cifs_mount_ctx *mnt_ctx, continue; } - if (is_refsrv) { - rc = add_root_smb_session(mnt_ctx); - if (rc) - goto out; - } + if (is_refsrv) + add_root_smb_session(mnt_ctx); rc = ref_walk_advance(rw); if (!rc) { @@ -232,6 +216,7 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_tcon *tcon; char *origin_fullpath; + bool new_tcon = true; int rc; origin_fullpath = dfs_get_path(cifs_sb, ctx->source); @@ -239,6 +224,18 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) return PTR_ERR(origin_fullpath); rc = dfs_referral_walk(mnt_ctx); + if (!rc) { + /* + * Prevent superblock from being created with any missing + * connections. + */ + if (WARN_ON(!mnt_ctx->server)) + rc = -EHOSTDOWN; + else if (WARN_ON(!mnt_ctx->ses)) + rc = -EACCES; + else if (WARN_ON(!mnt_ctx->tcon)) + rc = -ENOENT; + } if (rc) goto out; @@ -247,15 +244,14 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) if (!tcon->origin_fullpath) { tcon->origin_fullpath = origin_fullpath; origin_fullpath = NULL; + } else { + new_tcon = false; } spin_unlock(&tcon->tc_lock); - if (list_empty(&tcon->dfs_ses_list)) { - list_replace_init(&mnt_ctx->dfs_ses_list, &tcon->dfs_ses_list); + if (new_tcon) { queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, dfs_cache_get_ttl() * HZ); - } else { - dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list); } out: @@ -298,7 +294,6 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) if (rc) return rc; - ctx->dfs_root_ses = mnt_ctx->ses; /* * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally * try to get an DFS referral (even cached) to determine whether it is an DFS mount. @@ -324,7 +319,9 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) *isdfs = true; add_root_smb_session(mnt_ctx); - return __dfs_mount_share(mnt_ctx); + rc = __dfs_mount_share(mnt_ctx); + dfs_put_root_smb_sessions(mnt_ctx); + return rc; } /* Update dfs referral path of superblock */ diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h index 875ab7ae57fcd..e5c4dcf837503 100644 --- a/fs/smb/client/dfs.h +++ b/fs/smb/client/dfs.h @@ -7,7 +7,9 @@ #define _CIFS_DFS_H #include "cifsglob.h" +#include "cifsproto.h" #include "fs_context.h" +#include "dfs_cache.h" #include "cifs_unicode.h" #include @@ -114,11 +116,6 @@ static inline void ref_walk_set_tgt_hint(struct dfs_ref_walk *rw) ref_walk_tit(rw)); } -struct dfs_root_ses { - struct list_head list; - struct cifs_ses *ses; -}; - int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref, struct smb3_fs_context *ctx); int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs); @@ -133,20 +130,32 @@ static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *p { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; + struct cifs_ses *rses = ctx->dfs_root_ses ?: mnt_ctx->ses; - return dfs_cache_find(mnt_ctx->xid, ctx->dfs_root_ses, cifs_sb->local_nls, + return dfs_cache_find(mnt_ctx->xid, rses, cifs_sb->local_nls, cifs_remap(cifs_sb), path, ref, tl); } -static inline void dfs_put_root_smb_sessions(struct list_head *head) +/* + * cifs_get_smb_ses() already guarantees an active reference of + * @ses->dfs_root_ses when a new session is created, so we need to put extra + * references of all DFS root sessions that were used across the mount process + * in dfs_mount_share(). + */ +static inline void dfs_put_root_smb_sessions(struct cifs_mount_ctx *mnt_ctx) { - struct dfs_root_ses *root, *tmp; + const struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct cifs_ses *ses = ctx->dfs_root_ses; + struct cifs_ses *cur; + + if (!ses) + return; - list_for_each_entry_safe(root, tmp, head, list) { - list_del_init(&root->list); - cifs_put_smb_ses(root->ses); - kfree(root); + for (cur = ses; cur; cur = cur->dfs_root_ses) { + if (cur->dfs_root_ses) + cifs_put_smb_ses(cur->dfs_root_ses); } + cifs_put_smb_ses(ses); } #endif /* _CIFS_DFS_H */ diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 508d831fabe37..11c8efecf7aa1 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1172,8 +1172,8 @@ static bool is_ses_good(struct cifs_ses *ses) return ret; } -/* Refresh dfs referral of tcon and mark it for reconnect if needed */ -static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_refresh) +/* Refresh dfs referral of @ses and mark it for reconnect if needed */ +static void __refresh_ses_referral(struct cifs_ses *ses, bool force_refresh) { struct TCP_Server_Info *server = ses->server; DFS_CACHE_TGT_LIST(old_tl); @@ -1181,10 +1181,21 @@ static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_ref bool needs_refresh = false; struct cache_entry *ce; unsigned int xid; + char *path = NULL; int rc = 0; xid = get_xid(); + mutex_lock(&server->refpath_lock); + if (server->leaf_fullpath) { + path = kstrdup(server->leaf_fullpath + 1, GFP_ATOMIC); + if (!path) + rc = -ENOMEM; + } + mutex_unlock(&server->refpath_lock); + if (!path) + goto out; + down_read(&htable_rw_lock); ce = lookup_cache_entry(path); needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce); @@ -1218,19 +1229,17 @@ static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_ref free_xid(xid); dfs_cache_free_tgts(&old_tl); dfs_cache_free_tgts(&new_tl); - return rc; + kfree(path); } -static int refresh_tcon(struct cifs_tcon *tcon, bool force_refresh) +static inline void refresh_ses_referral(struct cifs_ses *ses) { - struct TCP_Server_Info *server = tcon->ses->server; - struct cifs_ses *ses = tcon->ses; + __refresh_ses_referral(ses, false); +} - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, force_refresh); - mutex_unlock(&server->refpath_lock); - return 0; +static inline void force_refresh_ses_referral(struct cifs_ses *ses) +{ + __refresh_ses_referral(ses, true); } /** @@ -1271,34 +1280,20 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) */ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; - return refresh_tcon(tcon, true); + force_refresh_ses_referral(tcon->ses); + return 0; } /* Refresh all DFS referrals related to DFS tcon */ void dfs_cache_refresh(struct work_struct *work) { - struct TCP_Server_Info *server; - struct dfs_root_ses *rses; struct cifs_tcon *tcon; struct cifs_ses *ses; tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work); - ses = tcon->ses; - server = ses->server; - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, false); - mutex_unlock(&server->refpath_lock); - - list_for_each_entry(rses, &tcon->dfs_ses_list, list) { - ses = rses->ses; - server = ses->server; - mutex_lock(&server->refpath_lock); - if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, ses, false); - mutex_unlock(&server->refpath_lock); - } + for (ses = tcon->ses; ses; ses = ses->dfs_root_ses) + refresh_ses_referral(ses); queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, atomic_read(&dfs_cache_ttl) * HZ); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 89333d9bce36e..37897b919dd5a 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -189,6 +189,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; *oplock = 0; if (tcon->ses->server->oplocks) @@ -200,6 +201,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned return PTR_ERR(full_path); } + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (oflags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -276,6 +281,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned desired_access |= GENERIC_READ; /* is this too little? */ if (OPEN_FMODE(oflags) & FMODE_WRITE) desired_access |= GENERIC_WRITE; + if (rdwr_for_fscache == 1) + desired_access |= GENERIC_READ; disposition = FILE_OVERWRITE_IF; if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) @@ -304,6 +311,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -317,8 +325,15 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned rc = server->ops->open(xid, &oparms, oplock, buf); if (rc) { cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc); + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access &= ~GENERIC_READ; + rdwr_for_fscache = 2; + goto retry_open; + } goto out; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY /* diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index f391c9b803d84..af5c476db6e66 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -206,12 +206,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) */ } -static inline int cifs_convert_flags(unsigned int flags) +static inline int cifs_convert_flags(unsigned int flags, int rdwr_for_fscache) { if ((flags & O_ACCMODE) == O_RDONLY) return GENERIC_READ; else if ((flags & O_ACCMODE) == O_WRONLY) - return GENERIC_WRITE; + return rdwr_for_fscache == 1 ? (GENERIC_READ | GENERIC_WRITE) : GENERIC_WRITE; else if ((flags & O_ACCMODE) == O_RDWR) { /* GENERIC_ALL is too much permission to request can cause unnecessary access denied on create */ @@ -329,7 +329,7 @@ int cifs_posix_open(const char *full_path, struct inode **pinode, } } else { cifs_revalidate_mapping(*pinode); - rc = cifs_fattr_to_inode(*pinode, &fattr); + rc = cifs_fattr_to_inode(*pinode, &fattr, false); } posix_open_ret: @@ -348,11 +348,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ int create_options = CREATE_NOT_DIR; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; if (!server->ops->open) return -ENOSYS; - desired_access = cifs_convert_flags(f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(f_flags, rdwr_for_fscache); /********************************************************************* * open flag mapping table: @@ -389,6 +394,7 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ if (f_flags & O_DIRECT) create_options |= CREATE_NO_BUFFER; +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -400,8 +406,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_ }; rc = server->ops->open(xid, &oparms, oplock, buf); - if (rc) + if (rc) { + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } return rc; + } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); /* TODO: Add support for calling posix query info but with passing in fid */ if (tcon->unix_ext) @@ -445,6 +459,7 @@ cifs_down_write(struct rw_semaphore *sem) } static void cifsFileInfo_put_work(struct work_struct *work); +void serverclose_work(struct work_struct *work); struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock, @@ -491,6 +506,7 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); INIT_WORK(&cfile->put, cifsFileInfo_put_work); + INIT_WORK(&cfile->serverclose, serverclose_work); INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close); mutex_init(&cfile->fh_mutex); spin_lock_init(&cfile->file_info_lock); @@ -582,6 +598,40 @@ static void cifsFileInfo_put_work(struct work_struct *work) cifsFileInfo_put_final(cifs_file); } +void serverclose_work(struct work_struct *work) +{ + struct cifsFileInfo *cifs_file = container_of(work, + struct cifsFileInfo, serverclose); + + struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); + + struct TCP_Server_Info *server = tcon->ses->server; + int rc = 0; + int retries = 0; + int MAX_RETRIES = 4; + + do { + if (server->ops->close_getattr) + rc = server->ops->close_getattr(0, tcon, cifs_file); + else if (server->ops->close) + rc = server->ops->close(0, tcon, &cifs_file->fid); + + if (rc == -EBUSY || rc == -EAGAIN) { + retries++; + msleep(250); + } + } while ((rc == -EBUSY || rc == -EAGAIN) && (retries < MAX_RETRIES) + ); + + if (retries == MAX_RETRIES) + pr_warn("Serverclose failed %d times, giving up\n", MAX_RETRIES); + + if (cifs_file->offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); +} + /** * cifsFileInfo_put - release a reference of file priv data * @@ -622,10 +672,13 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, struct cifs_fid fid = {}; struct cifs_pending_open open; bool oplock_break_cancelled; + bool serverclose_offloaded = false; spin_lock(&tcon->open_file_lock); spin_lock(&cifsi->open_file_lock); spin_lock(&cifs_file->file_info_lock); + + cifs_file->offload = offload; if (--cifs_file->count > 0) { spin_unlock(&cifs_file->file_info_lock); spin_unlock(&cifsi->open_file_lock); @@ -667,13 +720,20 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; unsigned int xid; + int rc = 0; xid = get_xid(); if (server->ops->close_getattr) - server->ops->close_getattr(xid, tcon, cifs_file); + rc = server->ops->close_getattr(xid, tcon, cifs_file); else if (server->ops->close) - server->ops->close(xid, tcon, &cifs_file->fid); + rc = server->ops->close(xid, tcon, &cifs_file->fid); _free_xid(xid); + + if (rc == -EBUSY || rc == -EAGAIN) { + // Server close failed, hence offloading it as an async op + queue_work(serverclose_wq, &cifs_file->serverclose); + serverclose_offloaded = true; + } } if (oplock_break_cancelled) @@ -681,10 +741,15 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, cifs_del_pending_open(&open); - if (offload) - queue_work(fileinfo_put_wq, &cifs_file->put); - else - cifsFileInfo_put_final(cifs_file); + // if serverclose has been offloaded to wq (on failure), it will + // handle offloading put as well. If serverclose not offloaded, + // we need to handle offloading put here. + if (!serverclose_offloaded) { + if (offload) + queue_work(fileinfo_put_wq, &cifs_file->put); + else + cifsFileInfo_put_final(cifs_file); + } } int cifs_open(struct inode *inode, struct file *file) @@ -834,11 +899,11 @@ int cifs_open(struct inode *inode, struct file *file) use_cache: fscache_use_cookie(cifs_inode_cookie(file_inode(file)), file->f_mode & FMODE_WRITE); - if (file->f_flags & O_DIRECT && - (!((file->f_flags & O_ACCMODE) != O_RDONLY) || - file->f_flags & O_APPEND)) - cifs_invalidate_cache(file_inode(file), - FSCACHE_INVAL_DIO_WRITE); + if (!(file->f_flags & O_DIRECT)) + goto out; + if ((file->f_flags & (O_ACCMODE | O_APPEND)) == O_RDONLY) + goto out; + cifs_invalidate_cache(file_inode(file), FSCACHE_INVAL_DIO_WRITE); out: free_dentry_path(page); @@ -903,6 +968,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) int disposition = FILE_OPEN; int create_options = CREATE_NOT_DIR; struct cifs_open_parms oparms; + int rdwr_for_fscache = 0; xid = get_xid(); mutex_lock(&cfile->fh_mutex); @@ -966,7 +1032,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - desired_access = cifs_convert_flags(cfile->f_flags); + /* If we're caching, we need to be able to fill in around partial writes. */ + if (cifs_fscache_enabled(inode) && (cfile->f_flags & O_ACCMODE) == O_WRONLY) + rdwr_for_fscache = 1; + + desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache); /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (cfile->f_flags & O_SYNC) @@ -978,6 +1048,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); +retry_open: oparms = (struct cifs_open_parms) { .tcon = tcon, .cifs_sb = cifs_sb, @@ -1003,6 +1074,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) /* indicate that we need to relock the file */ oparms.reconnect = true; } + if (rc == -EACCES && rdwr_for_fscache == 1) { + desired_access = cifs_convert_flags(cfile->f_flags, 0); + rdwr_for_fscache = 2; + goto retry_open; + } if (rc) { mutex_unlock(&cfile->fh_mutex); @@ -1011,6 +1087,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) goto reopen_error_exit; } + if (rdwr_for_fscache == 2) + cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE); + #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY reopen_success: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ @@ -2624,20 +2703,20 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) * dirty pages if possible, but don't sleep while doing so. */ static void cifs_extend_writeback(struct address_space *mapping, + struct xa_state *xas, long *_count, loff_t start, int max_pages, - size_t max_len, - unsigned int *_len) + loff_t max_len, + size_t *_len) { struct folio_batch batch; struct folio *folio; - unsigned int psize, nr_pages; - size_t len = *_len; - pgoff_t index = (start + len) / PAGE_SIZE; + unsigned int nr_pages; + pgoff_t index = (start + *_len) / PAGE_SIZE; + size_t len; bool stop = true; unsigned int i; - XA_STATE(xas, &mapping->i_pages, index); folio_batch_init(&batch); @@ -2648,54 +2727,64 @@ static void cifs_extend_writeback(struct address_space *mapping, */ rcu_read_lock(); - xas_for_each(&xas, folio, ULONG_MAX) { + xas_for_each(xas, folio, ULONG_MAX) { stop = true; - if (xas_retry(&xas, folio)) + if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) break; - if (folio->index != index) + if (folio->index != index) { + xas_reset(xas); break; + } + if (!folio_try_get_rcu(folio)) { - xas_reset(&xas); + xas_reset(xas); continue; } nr_pages = folio_nr_pages(folio); - if (nr_pages > max_pages) + if (nr_pages > max_pages) { + xas_reset(xas); break; + } /* Has the page moved or been split? */ - if (unlikely(folio != xas_reload(&xas))) { + if (unlikely(folio != xas_reload(xas))) { folio_put(folio); + xas_reset(xas); break; } if (!folio_trylock(folio)) { folio_put(folio); + xas_reset(xas); break; } - if (!folio_test_dirty(folio) || folio_test_writeback(folio)) { + if (!folio_test_dirty(folio) || + folio_test_writeback(folio)) { folio_unlock(folio); folio_put(folio); + xas_reset(xas); break; } max_pages -= nr_pages; - psize = folio_size(folio); - len += psize; + len = folio_size(folio); stop = false; - if (max_pages <= 0 || len >= max_len || *_count <= 0) - stop = true; index += nr_pages; + *_count -= nr_pages; + *_len += len; + if (max_pages <= 0 || *_len >= max_len || *_count <= 0) + stop = true; + if (!folio_batch_add(&batch, folio)) break; if (stop) break; } - if (!stop) - xas_pause(&xas); + xas_pause(xas); rcu_read_unlock(); /* Now, if we obtained any pages, we can shift them to being @@ -2712,16 +2801,12 @@ static void cifs_extend_writeback(struct address_space *mapping, if (!folio_clear_dirty_for_io(folio)) WARN_ON(1); folio_start_writeback(folio); - - *_count -= folio_nr_pages(folio); folio_unlock(folio); } folio_batch_release(&batch); cond_resched(); } while (!stop); - - *_len = len; } /* @@ -2729,8 +2814,10 @@ static void cifs_extend_writeback(struct address_space *mapping, */ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, struct writeback_control *wbc, + struct xa_state *xas, struct folio *folio, - loff_t start, loff_t end) + unsigned long long start, + unsigned long long end) { struct inode *inode = mapping->host; struct TCP_Server_Info *server; @@ -2739,17 +2826,18 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, struct cifs_credits credits_on_stack; struct cifs_credits *credits = &credits_on_stack; struct cifsFileInfo *cfile = NULL; - unsigned int xid, wsize, len; - loff_t i_size = i_size_read(inode); - size_t max_len; + unsigned long long i_size = i_size_read(inode), max_len; + unsigned int xid, wsize; + size_t len = folio_size(folio); long count = wbc->nr_to_write; int rc; /* The folio should be locked, dirty and not undergoing writeback. */ + if (!folio_clear_dirty_for_io(folio)) + WARN_ON_ONCE(1); folio_start_writeback(folio); count -= folio_nr_pages(folio); - len = folio_size(folio); xid = get_xid(); server = cifs_pick_channel(cifs_sb_master_tcon(cifs_sb)->ses); @@ -2779,9 +2867,10 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, wdata->server = server; cfile = NULL; - /* Find all consecutive lockable dirty pages, stopping when we find a - * page that is not immediately lockable, is not dirty or is missing, - * or we reach the end of the range. + /* Find all consecutive lockable dirty pages that have contiguous + * written regions, stopping when we find a page that is not + * immediately lockable, is not dirty or is missing, or we reach the + * end of the range. */ if (start < i_size) { /* Trim the write to the EOF; the extra data is ignored. Also @@ -2801,19 +2890,18 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, max_pages -= folio_nr_pages(folio); if (max_pages > 0) - cifs_extend_writeback(mapping, &count, start, + cifs_extend_writeback(mapping, xas, &count, start, max_pages, max_len, &len); } - len = min_t(loff_t, len, max_len); } - - wdata->bytes = len; + len = min_t(unsigned long long, len, i_size - start); /* We now have a contiguous set of dirty pages, each with writeback * set; the first page is still locked at this point, but all the rest * have been unlocked. */ folio_unlock(folio); + wdata->bytes = len; if (start < i_size) { iov_iter_xarray(&wdata->iter, ITER_SOURCE, &mapping->i_pages, @@ -2864,102 +2952,118 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, /* * write a region of pages back to the server */ -static int cifs_writepages_region(struct address_space *mapping, - struct writeback_control *wbc, - loff_t start, loff_t end, loff_t *_next) +static ssize_t cifs_writepages_begin(struct address_space *mapping, + struct writeback_control *wbc, + struct xa_state *xas, + unsigned long long *_start, + unsigned long long end) { - struct folio_batch fbatch; + struct folio *folio; + unsigned long long start = *_start; + ssize_t ret; int skips = 0; - folio_batch_init(&fbatch); - do { - int nr; - pgoff_t index = start / PAGE_SIZE; +search_again: + /* Find the first dirty page. */ + rcu_read_lock(); - nr = filemap_get_folios_tag(mapping, &index, end / PAGE_SIZE, - PAGECACHE_TAG_DIRTY, &fbatch); - if (!nr) + for (;;) { + folio = xas_find_marked(xas, end / PAGE_SIZE, PAGECACHE_TAG_DIRTY); + if (xas_retry(xas, folio) || xa_is_value(folio)) + continue; + if (!folio) break; - for (int i = 0; i < nr; i++) { - ssize_t ret; - struct folio *folio = fbatch.folios[i]; + if (!folio_try_get_rcu(folio)) { + xas_reset(xas); + continue; + } -redo_folio: - start = folio_pos(folio); /* May regress with THPs */ + if (unlikely(folio != xas_reload(xas))) { + folio_put(folio); + xas_reset(xas); + continue; + } - /* At this point we hold neither the i_pages lock nor the - * page lock: the page may be truncated or invalidated - * (changing page->mapping to NULL), or even swizzled - * back from swapper_space to tmpfs file mapping - */ - if (wbc->sync_mode != WB_SYNC_NONE) { - ret = folio_lock_killable(folio); - if (ret < 0) - goto write_error; - } else { - if (!folio_trylock(folio)) - goto skip_write; - } + xas_pause(xas); + break; + } + rcu_read_unlock(); + if (!folio) + return 0; - if (folio->mapping != mapping || - !folio_test_dirty(folio)) { - start += folio_size(folio); - folio_unlock(folio); - continue; - } + start = folio_pos(folio); /* May regress with THPs */ - if (folio_test_writeback(folio) || - folio_test_fscache(folio)) { - folio_unlock(folio); - if (wbc->sync_mode == WB_SYNC_NONE) - goto skip_write; + /* At this point we hold neither the i_pages lock nor the page lock: + * the page may be truncated or invalidated (changing page->mapping to + * NULL), or even swizzled back from swapper_space to tmpfs file + * mapping + */ +lock_again: + if (wbc->sync_mode != WB_SYNC_NONE) { + ret = folio_lock_killable(folio); + if (ret < 0) + return ret; + } else { + if (!folio_trylock(folio)) + goto search_again; + } - folio_wait_writeback(folio); + if (folio->mapping != mapping || + !folio_test_dirty(folio)) { + start += folio_size(folio); + folio_unlock(folio); + goto search_again; + } + + if (folio_test_writeback(folio) || + folio_test_fscache(folio)) { + folio_unlock(folio); + if (wbc->sync_mode != WB_SYNC_NONE) { + folio_wait_writeback(folio); #ifdef CONFIG_CIFS_FSCACHE - folio_wait_fscache(folio); + folio_wait_fscache(folio); #endif - goto redo_folio; - } - - if (!folio_clear_dirty_for_io(folio)) - /* We hold the page lock - it should've been dirty. */ - WARN_ON(1); - - ret = cifs_write_back_from_locked_folio(mapping, wbc, folio, start, end); - if (ret < 0) - goto write_error; - - start += ret; - continue; - -write_error: - folio_batch_release(&fbatch); - *_next = start; - return ret; + goto lock_again; + } -skip_write: - /* - * Too many skipped writes, or need to reschedule? - * Treat it as a write error without an error code. - */ + start += folio_size(folio); + if (wbc->sync_mode == WB_SYNC_NONE) { if (skips >= 5 || need_resched()) { ret = 0; - goto write_error; + goto out; } - - /* Otherwise, just skip that folio and go on to the next */ skips++; - start += folio_size(folio); - continue; } + goto search_again; + } - folio_batch_release(&fbatch); - cond_resched(); - } while (wbc->nr_to_write > 0); + ret = cifs_write_back_from_locked_folio(mapping, wbc, xas, folio, start, end); +out: + if (ret > 0) + *_start = start + ret; + return ret; +} - *_next = start; - return 0; +/* + * Write a region of pages back to the server + */ +static int cifs_writepages_region(struct address_space *mapping, + struct writeback_control *wbc, + unsigned long long *_start, + unsigned long long end) +{ + ssize_t ret; + + XA_STATE(xas, &mapping->i_pages, *_start / PAGE_SIZE); + + do { + ret = cifs_writepages_begin(mapping, wbc, &xas, _start, end); + if (ret > 0 && wbc->nr_to_write > 0) + cond_resched(); + } while (ret > 0 && wbc->nr_to_write > 0); + + return ret > 0 ? 0 : ret; } /* @@ -2968,7 +3072,7 @@ static int cifs_writepages_region(struct address_space *mapping, static int cifs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - loff_t start, next; + loff_t start, end; int ret; /* We have to be careful as we can end up racing with setattr() @@ -2976,28 +3080,34 @@ static int cifs_writepages(struct address_space *mapping, * to prevent it. */ - if (wbc->range_cyclic) { + if (wbc->range_cyclic && mapping->writeback_index) { start = mapping->writeback_index * PAGE_SIZE; - ret = cifs_writepages_region(mapping, wbc, start, LLONG_MAX, &next); - if (ret == 0) { - mapping->writeback_index = next / PAGE_SIZE; - if (start > 0 && wbc->nr_to_write > 0) { - ret = cifs_writepages_region(mapping, wbc, 0, - start, &next); - if (ret == 0) - mapping->writeback_index = - next / PAGE_SIZE; - } + ret = cifs_writepages_region(mapping, wbc, &start, LLONG_MAX); + if (ret < 0) + goto out; + + if (wbc->nr_to_write <= 0) { + mapping->writeback_index = start / PAGE_SIZE; + goto out; } + + start = 0; + end = mapping->writeback_index * PAGE_SIZE; + mapping->writeback_index = 0; + ret = cifs_writepages_region(mapping, wbc, &start, end); + if (ret == 0) + mapping->writeback_index = start / PAGE_SIZE; } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { - ret = cifs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next); + start = 0; + ret = cifs_writepages_region(mapping, wbc, &start, LLONG_MAX); if (wbc->nr_to_write > 0 && ret == 0) - mapping->writeback_index = next / PAGE_SIZE; + mapping->writeback_index = start / PAGE_SIZE; } else { - ret = cifs_writepages_region(mapping, wbc, - wbc->range_start, wbc->range_end, &next); + start = wbc->range_start; + ret = cifs_writepages_region(mapping, wbc, &start, wbc->range_end); } +out: return ret; } @@ -4738,12 +4848,14 @@ static int is_inode_writable(struct cifsInodeInfo *cifs_inode) refreshing the inode only on increases in the file size but this is tricky to do without racing with writebehind page caching in the current Linux kernel design */ -bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file) +bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file, + bool from_readdir) { if (!cifsInode) return true; - if (is_inode_writable(cifsInode)) { + if (is_inode_writable(cifsInode) || + ((cifsInode->oplock & CIFS_CACHE_RW_FLG) != 0 && from_readdir)) { /* This inode is open for write at least once */ struct cifs_sb_info *cifs_sb; diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 4b2f5aa2ea0e1..f119035a82725 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -37,7 +37,7 @@ #include "rfc1002pdu.h" #include "fs_context.h" -static DEFINE_MUTEX(cifs_mount_mutex); +DEFINE_MUTEX(cifs_mount_mutex); static const match_table_t cifs_smb_version_tokens = { { Smb_1, SMB1_VERSION_STRING }, @@ -162,6 +162,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_string("username", Opt_user), fsparam_string("pass", Opt_pass), fsparam_string("password", Opt_pass), + fsparam_string("password2", Opt_pass2), fsparam_string("ip", Opt_ip), fsparam_string("addr", Opt_ip), fsparam_string("domain", Opt_domain), @@ -315,6 +316,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->nodename = NULL; new_ctx->username = NULL; new_ctx->password = NULL; + new_ctx->password2 = NULL; new_ctx->server_hostname = NULL; new_ctx->domainname = NULL; new_ctx->UNC = NULL; @@ -327,6 +329,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(prepath); DUP_CTX_STR(username); DUP_CTX_STR(password); + DUP_CTX_STR(password2); DUP_CTX_STR(server_hostname); DUP_CTX_STR(UNC); DUP_CTX_STR(source); @@ -715,6 +718,16 @@ static int smb3_fs_context_validate(struct fs_context *fc) /* set the port that we got earlier */ cifs_set_port((struct sockaddr *)&ctx->dstaddr, ctx->port); + if (ctx->uid_specified && !ctx->forceuid_specified) { + ctx->override_uid = 1; + pr_notice("enabling forceuid mount option implicitly because uid= option is specified\n"); + } + + if (ctx->gid_specified && !ctx->forcegid_specified) { + ctx->override_gid = 1; + pr_notice("enabling forcegid mount option implicitly because gid= option is specified\n"); + } + if (ctx->override_uid && !ctx->uid_specified) { ctx->override_uid = 0; pr_notice("ignoring forceuid mount option specified with no uid= option\n"); @@ -753,9 +766,9 @@ static int smb3_get_tree(struct fs_context *fc) if (err) return err; - mutex_lock(&cifs_mount_mutex); + cifs_mount_lock(); ret = smb3_get_tree_common(fc); - mutex_unlock(&cifs_mount_mutex); + cifs_mount_unlock(); return ret; } @@ -772,7 +785,7 @@ static void smb3_fs_context_free(struct fs_context *fc) */ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, struct smb3_fs_context *new_ctx, - struct smb3_fs_context *old_ctx) + struct smb3_fs_context *old_ctx, bool need_recon) { if (new_ctx->posix_paths != old_ctx->posix_paths) { cifs_errorf(fc, "can not change posixpaths during remount\n"); @@ -798,8 +811,15 @@ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, } if (new_ctx->password && (!old_ctx->password || strcmp(new_ctx->password, old_ctx->password))) { - cifs_errorf(fc, "can not change password during remount\n"); - return -EINVAL; + if (need_recon == false) { + cifs_errorf(fc, + "can not change password of active session during remount\n"); + return -EINVAL; + } else if (old_ctx->sectype == Kerberos) { + cifs_errorf(fc, + "can not change password for Kerberos via remount\n"); + return -EINVAL; + } } if (new_ctx->domainname && (!old_ctx->domainname || strcmp(new_ctx->domainname, old_ctx->domainname))) { @@ -843,9 +863,14 @@ static int smb3_reconfigure(struct fs_context *fc) struct smb3_fs_context *ctx = smb3_fc2context(fc); struct dentry *root = fc->root; struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb); + struct cifs_ses *ses = cifs_sb_master_tcon(cifs_sb)->ses; + bool need_recon = false; int rc; - rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx); + if (ses->expired_pwd) + need_recon = true; + + rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx, need_recon); if (rc) return rc; @@ -858,7 +883,14 @@ static int smb3_reconfigure(struct fs_context *fc) STEAL_STRING(cifs_sb, ctx, UNC); STEAL_STRING(cifs_sb, ctx, source); STEAL_STRING(cifs_sb, ctx, username); - STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); + if (need_recon == false) + STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); + else { + kfree_sensitive(ses->password); + ses->password = kstrdup(ctx->password, GFP_KERNEL); + kfree_sensitive(ses->password2); + ses->password2 = kstrdup(ctx->password2, GFP_KERNEL); + } STEAL_STRING(cifs_sb, ctx, domainname); STEAL_STRING(cifs_sb, ctx, nodename); STEAL_STRING(cifs_sb, ctx, iocharset); @@ -967,12 +999,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->override_uid = 0; else ctx->override_uid = 1; + ctx->forceuid_specified = true; break; case Opt_forcegid: if (result.negated) ctx->override_gid = 0; else ctx->override_gid = 1; + ctx->forcegid_specified = true; break; case Opt_perm: if (result.negated) @@ -1258,6 +1292,18 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, goto cifs_parse_mount_err; } break; + case Opt_pass2: + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; + if (strlen(param->string) == 0) + break; + + ctx->password2 = kstrdup(param->string, GFP_KERNEL); + if (ctx->password2 == NULL) { + cifs_errorf(fc, "OOM when copying password2 string\n"); + goto cifs_parse_mount_err; + } + break; case Opt_ip: if (strlen(param->string) == 0) { ctx->got_ip = false; @@ -1557,6 +1603,8 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_parse_mount_err: kfree_sensitive(ctx->password); ctx->password = NULL; + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; return -EINVAL; } @@ -1661,6 +1709,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->username = NULL; kfree_sensitive(ctx->password); ctx->password = NULL; + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; kfree(ctx->server_hostname); ctx->server_hostname = NULL; kfree(ctx->UNC); diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 182ce11cbe936..369a3fea1dfe0 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -138,6 +138,7 @@ enum cifs_param { Opt_source, Opt_user, Opt_pass, + Opt_pass2, Opt_ip, Opt_domain, Opt_srcaddr, @@ -156,6 +157,8 @@ enum cifs_param { }; struct smb3_fs_context { + bool forceuid_specified; + bool forcegid_specified; bool uid_specified; bool cruid_specified; bool gid_specified; @@ -169,6 +172,7 @@ struct smb3_fs_context { char *username; char *password; + char *password2; char *domainname; char *source; char *server_hostname; @@ -295,4 +299,16 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); #define MAX_CACHED_FIDS 16 extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp); +extern struct mutex cifs_mount_mutex; + +static inline void cifs_mount_lock(void) +{ + mutex_lock(&cifs_mount_mutex); +} + +static inline void cifs_mount_unlock(void) +{ + mutex_unlock(&cifs_mount_mutex); +} + #endif diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index c4a3cb736881a..113bde8f1e613 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -12,6 +12,16 @@ #include "cifs_fs_sb.h" #include "cifsproto.h" +/* + * Key for fscache inode. [!] Contents must match comparisons in cifs_find_inode(). + */ +struct cifs_fscache_inode_key { + + __le64 uniqueid; /* server inode number */ + __le64 createtime; /* creation time on server */ + u8 type; /* S_IFMT file type */ +} __packed; + static void cifs_fscache_fill_volume_coherency( struct cifs_tcon *tcon, struct cifs_fscache_volume_coherency_data *cd) @@ -33,12 +43,23 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) char *key; int ret = -ENOMEM; + if (tcon->fscache_acquired) + return 0; + + mutex_lock(&tcon->fscache_lock); + if (tcon->fscache_acquired) { + mutex_unlock(&tcon->fscache_lock); + return 0; + } + tcon->fscache_acquired = true; + tcon->fscache = NULL; switch (sa->sa_family) { case AF_INET: case AF_INET6: break; default: + mutex_unlock(&tcon->fscache_lock); cifs_dbg(VFS, "Unknown network family '%d'\n", sa->sa_family); return -EINVAL; } @@ -47,6 +68,7 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) sharename = extract_sharename(tcon->tree_name); if (IS_ERR(sharename)) { + mutex_unlock(&tcon->fscache_lock); cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__); return PTR_ERR(sharename); } @@ -80,6 +102,7 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) kfree(key); out: kfree(sharename); + mutex_unlock(&tcon->fscache_lock); return ret; } @@ -97,15 +120,19 @@ void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon) void cifs_fscache_get_inode_cookie(struct inode *inode) { struct cifs_fscache_inode_coherency_data cd; + struct cifs_fscache_inode_key key; struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + key.uniqueid = cpu_to_le64(cifsi->uniqueid); + key.createtime = cpu_to_le64(cifsi->createtime); + key.type = (inode->i_mode & S_IFMT) >> 12; cifs_fscache_fill_coherency(&cifsi->netfs.inode, &cd); cifsi->netfs.cache = fscache_acquire_cookie(tcon->fscache, 0, - &cifsi->uniqueid, sizeof(cifsi->uniqueid), + &key, sizeof(key), &cd, sizeof(cd), i_size_read(&cifsi->netfs.inode)); if (cifsi->netfs.cache) diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h index a3d73720914f8..1f2ea9f5cc9a8 100644 --- a/fs/smb/client/fscache.h +++ b/fs/smb/client/fscache.h @@ -109,6 +109,11 @@ static inline void cifs_readahead_to_fscache(struct inode *inode, __cifs_readahead_to_fscache(inode, pos, len); } +static inline bool cifs_fscache_enabled(struct inode *inode) +{ + return fscache_cookie_enabled(cifs_inode_cookie(inode)); +} + #else /* CONFIG_CIFS_FSCACHE */ static inline void cifs_fscache_fill_coherency(struct inode *inode, @@ -124,6 +129,7 @@ static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {} static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) {} static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {} +static inline bool cifs_fscache_enabled(struct inode *inode) { return false; } static inline int cifs_fscache_query_occupancy(struct inode *inode, pgoff_t first, unsigned int nr_pages, diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index d02f8ba29cb5b..4c3dec384f922 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -147,7 +147,8 @@ cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) /* populate an inode with info from a cifs_fattr struct */ int -cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) +cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, + bool from_readdir) { struct cifsInodeInfo *cifs_i = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); @@ -199,7 +200,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) * Can't safely change the file size here if the client is writing to * it due to potential races. */ - if (is_size_safe_to_change(cifs_i, fattr->cf_eof)) { + if (is_size_safe_to_change(cifs_i, fattr->cf_eof, from_readdir)) { i_size_write(inode, fattr->cf_eof); /* @@ -368,7 +369,7 @@ static int update_inode_info(struct super_block *sb, CIFS_I(*inode)->time = 0; /* force reval */ return -ESTALE; } - return cifs_fattr_to_inode(*inode, fattr); + return cifs_fattr_to_inode(*inode, fattr, false); } #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY @@ -403,7 +404,7 @@ cifs_get_file_info_unix(struct file *filp) } else goto cifs_gfiunix_out; - rc = cifs_fattr_to_inode(inode, &fattr); + rc = cifs_fattr_to_inode(inode, &fattr, false); cifs_gfiunix_out: free_xid(xid); @@ -934,7 +935,7 @@ cifs_get_file_info(struct file *filp) fattr.cf_uniqueid = CIFS_I(inode)->uniqueid; fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; /* if filetype is different, return error */ - rc = cifs_fattr_to_inode(inode, &fattr); + rc = cifs_fattr_to_inode(inode, &fattr, false); cgfi_exit: cifs_free_open_info(&data); free_xid(xid); @@ -1413,6 +1414,8 @@ cifs_find_inode(struct inode *inode, void *opaque) { struct cifs_fattr *fattr = opaque; + /* [!] The compared values must be the same in struct cifs_fscache_inode_key. */ + /* don't match inode with different uniqueid */ if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid) return 0; @@ -1491,7 +1494,7 @@ cifs_iget(struct super_block *sb, struct cifs_fattr *fattr) } /* can't fail - see cifs_find_inode() */ - cifs_fattr_to_inode(inode, fattr); + cifs_fattr_to_inode(inode, fattr, false); if (sb->s_flags & SB_NOATIME) inode->i_flags |= S_NOATIME | S_NOCMTIME; if (inode->i_state & I_NEW) { diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index e2f92c21fff50..682eabdd1d6cc 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -247,7 +247,9 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) { - if (ses_it->Suid == out.session_id) { + spin_lock(&ses_it->ses_lock); + if (ses_it->ses_status != SES_EXITING && + ses_it->Suid == out.session_id) { ses = ses_it; /* * since we are using the session outside the crit @@ -255,9 +257,11 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug * so increment its refcount */ cifs_smb_ses_inc_refcount(ses); + spin_unlock(&ses_it->ses_lock); found = true; goto search_end; } + spin_unlock(&ses_it->ses_lock); } } search_end: diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 0748d7b757b95..d56959d02e36d 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -101,6 +101,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) kfree(buf_to_free->serverDomain); kfree(buf_to_free->serverNOS); kfree_sensitive(buf_to_free->password); + kfree_sensitive(buf_to_free->password2); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); kfree_sensitive(buf_to_free->auth_key.response); @@ -141,8 +142,8 @@ tcon_info_alloc(bool dir_leases_enabled) atomic_set(&ret_buf->num_local_opens, 0); atomic_set(&ret_buf->num_remote_opens, 0); ret_buf->stats_from_time = ktime_get_real_seconds(); -#ifdef CONFIG_CIFS_DFS_UPCALL - INIT_LIST_HEAD(&ret_buf->dfs_ses_list); +#ifdef CONFIG_CIFS_FSCACHE + mutex_init(&ret_buf->fscache_lock); #endif return ret_buf; @@ -159,9 +160,6 @@ tconInfoFree(struct cifs_tcon *tcon) atomic_dec(&tconInfoAllocCount); kfree(tcon->nativeFileSystem); kfree_sensitive(tcon->password); -#ifdef CONFIG_CIFS_DFS_UPCALL - dfs_put_root_smb_sessions(&tcon->dfs_ses_list); -#endif kfree(tcon->origin_fullpath); kfree(tcon); } @@ -490,6 +488,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index b520eea7bfce8..132ae7d884a97 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -148,7 +148,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, rc = -ESTALE; } } - if (!rc && !cifs_fattr_to_inode(inode, fattr)) { + if (!rc && !cifs_fattr_to_inode(inode, fattr, true)) { dput(dentry); return; } diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 8f37373fd3334..3216f786908fb 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -230,7 +230,7 @@ int cifs_try_adding_channels(struct cifs_ses *ses) spin_lock(&ses->iface_lock); if (!ses->iface_count) { spin_unlock(&ses->iface_lock); - cifs_dbg(VFS, "server %s does not advertise interfaces\n", + cifs_dbg(ONCE, "server %s does not advertise interfaces\n", ses->server->hostname); break; } @@ -396,7 +396,7 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) spin_lock(&ses->iface_lock); if (!ses->iface_count) { spin_unlock(&ses->iface_lock); - cifs_dbg(VFS, "server %s does not advertise interfaces\n", ses->server->hostname); + cifs_dbg(ONCE, "server %s does not advertise interfaces\n", ses->server->hostname); return; } diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index a9eaba8083b0d..212ec6f66ec65 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -753,11 +753,11 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); } -static void +static int cifs_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - CIFSSMBClose(xid, tcon, fid->netfid); + return CIFSSMBClose(xid, tcon, fid->netfid); } static int diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 82b84a4941dd2..cc72be5a93a93 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -622,6 +622,8 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); cifs_stats_inc( @@ -697,6 +699,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 4695433fcf397..0875b1a582896 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1411,14 +1411,14 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) memcpy(cfile->fid.create_guid, fid->create_guid, 16); } -static void +static int smb2_close_file(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *fid) { - SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); + return SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid); } -static void +static int smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *cfile) { @@ -1429,7 +1429,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, &file_inf); if (rc) - return; + return rc; inode = d_inode(cfile->dentry); @@ -1458,6 +1458,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, /* End of file and Attributes should not have to be updated on close */ spin_unlock(&inode->i_lock); + return rc; } static int @@ -2026,6 +2027,7 @@ smb2_duplicate_extents(const unsigned int xid, * size will be queried on next revalidate, but it is important * to make sure that file's cached size is updated immediately */ + netfs_resize_file(netfs_inode(inode), dest_off + len, true); cifs_setsize(inode, dest_off + len); } rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, @@ -2479,6 +2481,8 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (cifs_ses_exiting(ses)) + continue; list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { spin_lock(&tcon->tc_lock); @@ -5538,6 +5542,7 @@ struct smb_version_operations smb30_operations = { .tree_connect = SMB2_tcon, .tree_disconnect = SMB2_tdis, .qfs_tcon = smb3_qfs_tcon, + .query_server_interfaces = SMB3_request_interfaces, .is_path_accessible = smb2_is_path_accessible, .can_echo = smb2_can_echo, .echo = SMB2_echo, @@ -5653,6 +5658,7 @@ struct smb_version_operations smb311_operations = { .tree_connect = SMB2_tcon, .tree_disconnect = SMB2_tdis, .qfs_tcon = smb3_qfs_tcon, + .query_server_interfaces = SMB3_request_interfaces, .is_path_accessible = smb2_is_path_accessible, .can_echo = smb2_can_echo, .echo = SMB2_echo, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 608ee05491e26..60793143e24c6 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -367,6 +367,17 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, } rc = cifs_setup_session(0, ses, server, nls_codepage); + if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) { + /* + * Try alternate password for next reconnect (key rotation + * could be enabled on the server e.g.) if an alternate + * password is available and the current password is expired, + * but do not swap on non pwd related errors like host down + */ + if (ses->password2) + swap(ses->password2, ses->password); + } + if ((rc == -EACCES) && !tcon->retry) { mutex_unlock(&ses->session_mutex); rc = -EHOSTDOWN; @@ -409,14 +420,15 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, spin_unlock(&ses->ses_lock); if (!rc && - (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { + (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL) && + server->ops->query_server_interfaces) { mutex_unlock(&ses->session_mutex); /* * query server network interfaces, in case they change */ xid = get_xid(); - rc = SMB3_request_interfaces(xid, tcon, false); + rc = server->ops->query_server_interfaces(xid, tcon, false); free_xid(xid); if (rc == -EOPNOTSUPP && ses->chan_count > 1) { @@ -1536,6 +1548,11 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) &sess_data->buf0_type, CIFS_LOG_ERROR | CIFS_SESS_OP, &rsp_iov); cifs_small_buf_release(sess_data->iov[0].iov_base); + if (rc == 0) + sess_data->ses->expired_pwd = false; + else if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) + sess_data->ses->expired_pwd = true; + memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec)); return rc; @@ -3600,9 +3617,9 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, memcpy(&pbuf->network_open_info, &rsp->network_open_info, sizeof(pbuf->network_open_info)); + atomic_dec(&tcon->num_remote_opens); } - atomic_dec(&tcon->num_remote_opens); close_exit: SMB2_close_free(&rqst); free_rsp_buf(resp_buftype, rsp); diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index db08194484e06..b00f707bddfcc 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -319,7 +319,7 @@ struct smb2_file_reparse_point_info { } __packed; struct smb2_file_network_open_info { - struct_group(network_open_info, + struct_group_attr(network_open_info, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 5a3ca62d2f07f..6208ba27c75cc 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -214,8 +214,8 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) } tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid); if (!tcon) { - cifs_put_smb_ses(ses); spin_unlock(&cifs_tcp_ses_lock); + cifs_put_smb_ses(ses); return NULL; } spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 994d701934329..ddf1a3aafee5c 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -909,12 +909,15 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; } + spin_unlock(&server->mid_lock); cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n", __func__, mid->mid, mid->mid_state); rc = -EIO; + goto sync_mid_done; } spin_unlock(&server->mid_lock); +sync_mid_done: release_mid(mid); return rc; } @@ -1057,9 +1060,11 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) index = (uint)atomic_inc_return(&ses->chan_seq); index %= ses->chan_count; } + + server = ses->chans[index].server; spin_unlock(&ses->chan_lock); - return ses->chans[index].server; + return server; } int diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 57f2343164a34..a233a24352b1f 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -702,7 +702,7 @@ struct smb2_close_rsp { __le16 StructureSize; /* 60 */ __le16 Flags; __le32 Reserved; - struct_group(network_open_info, + struct_group_attr(network_open_info, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index 0ebf91ffa2361..4464a62228cf3 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -166,7 +166,8 @@ struct ksmbd_share_config_response { __u16 force_uid; __u16 force_gid; __s8 share_name[KSMBD_REQ_MAX_SHARE_NAME]; - __u32 reserved[112]; /* Reserved room */ + __u32 reserved[111]; /* Reserved room */ + __u32 payload_sz; __u32 veto_list_sz; __s8 ____payload[]; }; diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index 328a412259dc1..e0a6b758094fc 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -158,10 +158,19 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, share->name = kstrdup(name, GFP_KERNEL); if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) { - share->path = kstrdup(ksmbd_share_config_path(resp), + int path_len = PATH_MAX; + + if (resp->payload_sz) + path_len = resp->payload_sz - resp->veto_list_sz; + + share->path = kstrndup(ksmbd_share_config_path(resp), path_len, GFP_KERNEL); - if (share->path) + if (share->path) { share->path_sz = strlen(share->path); + while (share->path_sz > 1 && + share->path[share->path_sz - 1] == '/') + share->path[--share->path_sz] = '\0'; + } share->create_mask = resp->create_mask; share->directory_mask = resp->directory_mask; share->force_create_mode = resp->force_create_mode; diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 53dfaac425c68..2292ca6ff00b6 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -612,13 +612,28 @@ static int oplock_break_pending(struct oplock_info *opinfo, int req_op_level) if (opinfo->op_state == OPLOCK_CLOSING) return -ENOENT; - else if (!opinfo->is_lease && opinfo->level <= req_op_level) - return 1; + else if (opinfo->level <= req_op_level) { + if (opinfo->is_lease == false) + return 1; + + if (opinfo->o_lease->state != + (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_READ_CACHING_LE)) + return 1; + } } - if (!opinfo->is_lease && opinfo->level <= req_op_level) { - wake_up_oplock_break(opinfo); - return 1; + if (opinfo->level <= req_op_level) { + if (opinfo->is_lease == false) { + wake_up_oplock_break(opinfo); + return 1; + } + if (opinfo->o_lease->state != + (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_READ_CACHING_LE)) { + wake_up_oplock_break(opinfo); + return 1; + } } return 0; } @@ -886,7 +901,6 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) struct lease *lease = brk_opinfo->o_lease; atomic_inc(&brk_opinfo->breaking_cnt); - err = oplock_break_pending(brk_opinfo, req_op_level); if (err) return err < 0 ? err : 0; @@ -1199,7 +1213,9 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, /* Only v2 leases handle the directory */ if (S_ISDIR(file_inode(fp->filp)->i_mode)) { - if (!lctx || lctx->version != 2) + if (!lctx || lctx->version != 2 || + (lctx->flags != SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE && + !lctx->epoch)) return 0; } @@ -1461,8 +1477,9 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) buf->lcontext.LeaseFlags = lease->flags; buf->lcontext.Epoch = cpu_to_le16(lease->epoch); buf->lcontext.LeaseState = lease->state; - memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, - SMB2_LEASE_KEY_SIZE); + if (lease->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) + memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, + SMB2_LEASE_KEY_SIZE); buf->ccontext.DataOffset = cpu_to_le16(offsetof (struct create_lease_v2, lcontext)); buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context_v2)); @@ -1527,8 +1544,9 @@ struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) lreq->flags = lc->lcontext.LeaseFlags; lreq->epoch = lc->lcontext.Epoch; lreq->duration = lc->lcontext.LeaseDuration; - memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, - SMB2_LEASE_KEY_SIZE); + if (lreq->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) + memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, + SMB2_LEASE_KEY_SIZE); lreq->version = 2; } else { struct create_lease *lc = (struct create_lease *)cc; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 3079e607c5fe6..2bbc3c3316f0f 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -167,20 +167,17 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, int rc; bool is_chained = false; - if (conn->ops->allocate_rsp_buf(work)) - return; - if (conn->ops->is_transform_hdr && conn->ops->is_transform_hdr(work->request_buf)) { rc = conn->ops->decrypt_req(work); - if (rc < 0) { - conn->ops->set_rsp_status(work, STATUS_DATA_ERROR); - goto send; - } - + if (rc < 0) + return; work->encrypted = true; } + if (conn->ops->allocate_rsp_buf(work)) + return; + rc = conn->ops->init_rsp_hdr(work); if (rc) { /* either uid or tid is not correct */ diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 03dded29a9804..727cb49926ee5 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -101,13 +101,17 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, *len = le16_to_cpu(((struct smb2_sess_setup_req *)hdr)->SecurityBufferLength); break; case SMB2_TREE_CONNECT: - *off = le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathOffset); + *off = max_t(unsigned short int, + le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathOffset), + offsetof(struct smb2_tree_connect_req, Buffer)); *len = le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathLength); break; case SMB2_CREATE: { unsigned short int name_off = - le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); + max_t(unsigned short int, + le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset), + offsetof(struct smb2_create_req, Buffer)); unsigned short int name_len = le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); @@ -128,11 +132,15 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; } case SMB2_QUERY_INFO: - *off = le16_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferOffset); + *off = max_t(unsigned int, + le16_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferOffset), + offsetof(struct smb2_query_info_req, Buffer)); *len = le32_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferLength); break; case SMB2_SET_INFO: - *off = le16_to_cpu(((struct smb2_set_info_req *)hdr)->BufferOffset); + *off = max_t(unsigned int, + le16_to_cpu(((struct smb2_set_info_req *)hdr)->BufferOffset), + offsetof(struct smb2_set_info_req, Buffer)); *len = le32_to_cpu(((struct smb2_set_info_req *)hdr)->BufferLength); break; case SMB2_READ: @@ -142,7 +150,7 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, case SMB2_WRITE: if (((struct smb2_write_req *)hdr)->DataOffset || ((struct smb2_write_req *)hdr)->Length) { - *off = max_t(unsigned int, + *off = max_t(unsigned short int, le16_to_cpu(((struct smb2_write_req *)hdr)->DataOffset), offsetof(struct smb2_write_req, Buffer)); *len = le32_to_cpu(((struct smb2_write_req *)hdr)->Length); @@ -153,7 +161,9 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, *len = le16_to_cpu(((struct smb2_write_req *)hdr)->WriteChannelInfoLength); break; case SMB2_QUERY_DIRECTORY: - *off = le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameOffset); + *off = max_t(unsigned short int, + le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameOffset), + offsetof(struct smb2_query_directory_req, Buffer)); *len = le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameLength); break; case SMB2_LOCK: @@ -168,7 +178,9 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; } case SMB2_IOCTL: - *off = le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputOffset); + *off = max_t(unsigned int, + le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputOffset), + offsetof(struct smb2_ioctl_req, Buffer)); *len = le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputCount); break; default: diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index 27a9dce3e03ab..8600f32c981a1 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -228,6 +228,11 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || + (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && + conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) + conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; + if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; } @@ -275,11 +280,6 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_DIRECTORY_LEASING; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || - (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && - conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 0c97d3c860726..3462290f8163b 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -535,6 +535,10 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) if (cmd == SMB2_QUERY_INFO_HE) { struct smb2_query_info_req *req; + if (get_rfc1002_len(work->request_buf) < + offsetof(struct smb2_query_info_req, OutputBufferLength)) + return -EINVAL; + req = smb2_get_msg(work->request_buf); if ((req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || @@ -650,6 +654,12 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls) return name; } + if (*name == '\\') { + pr_err("not allow directory name included leading slash\n"); + kfree(name); + return ERR_PTR(-EINVAL); + } + ksmbd_conv_path_to_unix(name); ksmbd_strip_last_slash(name); return name; @@ -1951,7 +1961,7 @@ int smb2_tree_connect(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); - treename = smb_strndup_from_utf16(req->Buffer, + treename = smb_strndup_from_utf16((char *)req + le16_to_cpu(req->PathOffset), le16_to_cpu(req->PathLength), true, conn->local_nls); if (IS_ERR(treename)) { @@ -2376,7 +2386,8 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, if (rc > 0) { rc = ksmbd_vfs_remove_xattr(idmap, path, - attr_name); + attr_name, + get_write); if (rc < 0) { ksmbd_debug(SMB, @@ -2391,7 +2402,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, } else { rc = ksmbd_vfs_setxattr(idmap, path, attr_name, value, le16_to_cpu(eabuf->EaValueLength), - 0, true); + 0, get_write); if (rc < 0) { ksmbd_debug(SMB, "ksmbd_vfs_setxattr is failed(%d)\n", @@ -2483,7 +2494,7 @@ static int smb2_remove_smb_xattrs(const struct path *path) !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) { err = ksmbd_vfs_remove_xattr(idmap, path, - name); + name, true); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); @@ -2697,20 +2708,11 @@ int smb2_open(struct ksmbd_work *work) } if (req->NameLength) { - if ((req->CreateOptions & FILE_DIRECTORY_FILE_LE) && - *(char *)req->Buffer == '\\') { - pr_err("not allow directory name included leading slash\n"); - rc = -EINVAL; - goto err_out2; - } - - name = smb2_get_name(req->Buffer, + name = smb2_get_name((char *)req + le16_to_cpu(req->NameOffset), le16_to_cpu(req->NameLength), work->conn->local_nls); if (IS_ERR(name)) { rc = PTR_ERR(name); - if (rc != -ENOMEM) - rc = -ENOENT; name = NULL; goto err_out2; } @@ -3828,11 +3830,16 @@ static int process_query_dir_entries(struct smb2_query_dir_private *priv) } ksmbd_kstat.kstat = &kstat; - if (priv->info_level != FILE_NAMES_INFORMATION) - ksmbd_vfs_fill_dentry_attrs(priv->work, - idmap, - dent, - &ksmbd_kstat); + if (priv->info_level != FILE_NAMES_INFORMATION) { + rc = ksmbd_vfs_fill_dentry_attrs(priv->work, + idmap, + dent, + &ksmbd_kstat); + if (rc) { + dput(dent); + continue; + } + } rc = smb2_populate_readdir_entry(priv->work->conn, priv->info_level, @@ -4075,7 +4082,7 @@ int smb2_query_dir(struct ksmbd_work *work) } srch_flag = req->Flags; - srch_ptr = smb_strndup_from_utf16(req->Buffer, + srch_ptr = smb_strndup_from_utf16((char *)req + le16_to_cpu(req->FileNameOffset), le16_to_cpu(req->FileNameLength), 1, conn->local_nls); if (IS_ERR(srch_ptr)) { @@ -4335,7 +4342,8 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, sizeof(struct smb2_ea_info_req)) return -EINVAL; - ea_req = (struct smb2_ea_info_req *)req->Buffer; + ea_req = (struct smb2_ea_info_req *)((char *)req + + le16_to_cpu(req->InputBufferOffset)); } else { /* need to send all EAs, if no specific EA is requested*/ if (le32_to_cpu(req->Flags) & SL_RETURN_SINGLE_ENTRY) @@ -4480,6 +4488,7 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, struct smb2_file_basic_info *basic_info; struct kstat stat; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { pr_err("no right to read the attributes : 0x%x\n", @@ -4487,9 +4496,12 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return -EACCES; } + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; + basic_info = (struct smb2_file_basic_info *)rsp->Buffer; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); basic_info->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); basic_info->LastAccessTime = cpu_to_le64(time); @@ -4504,27 +4516,31 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return 0; } -static void get_file_standard_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_standard_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_standard_info *sinfo; unsigned int delete_pending; - struct inode *inode; struct kstat stat; + int ret; - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; sinfo = (struct smb2_file_standard_info *)rsp->Buffer; delete_pending = ksmbd_inode_pending_delete(fp); - sinfo->AllocationSize = cpu_to_le64(inode->i_blocks << 9); + sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9); sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); sinfo->DeletePending = delete_pending; sinfo->Directory = S_ISDIR(stat.mode) ? 1 : 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_standard_info)); + + return 0; } static void get_file_alignment_info(struct smb2_query_info_rsp *rsp, @@ -4546,11 +4562,11 @@ static int get_file_all_info(struct ksmbd_work *work, struct ksmbd_conn *conn = work->conn; struct smb2_file_all_info *file_info; unsigned int delete_pending; - struct inode *inode; struct kstat stat; int conv_len; char *filename; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { ksmbd_debug(SMB, "no right to read the attributes : 0x%x\n", @@ -4562,8 +4578,10 @@ static int get_file_all_info(struct ksmbd_work *work, if (IS_ERR(filename)) return PTR_ERR(filename); - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; ksmbd_debug(SMB, "filename = %s\n", filename); delete_pending = ksmbd_inode_pending_delete(fp); @@ -4579,7 +4597,7 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Attributes = fp->f_ci->m_fattr; file_info->Pad1 = 0; file_info->AllocationSize = - cpu_to_le64(inode->i_blocks << 9); + cpu_to_le64(stat.blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); @@ -4623,10 +4641,10 @@ static void get_file_alternate_info(struct ksmbd_work *work, cpu_to_le32(sizeof(struct smb2_file_alt_name_info) + conv_len); } -static void get_file_stream_info(struct ksmbd_work *work, - struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, - void *rsp_org) +static int get_file_stream_info(struct ksmbd_work *work, + struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, + void *rsp_org) { struct ksmbd_conn *conn = work->conn; struct smb2_file_stream_info *file_info; @@ -4637,9 +4655,13 @@ static void get_file_stream_info(struct ksmbd_work *work, int nbytes = 0, streamlen, stream_name_len, next, idx = 0; int buf_free_len; struct smb2_query_info_req *req = ksmbd_req_buf_next(work); + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); file_info = (struct smb2_file_stream_info *)rsp->Buffer; buf_free_len = @@ -4720,29 +4742,37 @@ static void get_file_stream_info(struct ksmbd_work *work, kvfree(xattr_list); rsp->OutputBufferLength = cpu_to_le32(nbytes); + + return 0; } -static void get_file_internal_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_internal_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_internal_info *file_info; struct kstat stat; + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); file_info = (struct smb2_file_internal_info *)rsp->Buffer; file_info->IndexNumber = cpu_to_le64(stat.ino); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_internal_info)); + + return 0; } static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_ntwrk_info *file_info; - struct inode *inode; struct kstat stat; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { pr_err("no right to read the attributes : 0x%x\n", @@ -4750,10 +4780,12 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, return -EACCES; } - file_info = (struct smb2_file_ntwrk_info *)rsp->Buffer; + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + file_info = (struct smb2_file_ntwrk_info *)rsp->Buffer; file_info->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); @@ -4763,8 +4795,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, time = ksmbd_UnixTimeToNT(stat.ctime); file_info->ChangeTime = cpu_to_le64(time); file_info->Attributes = fp->f_ci->m_fattr; - file_info->AllocationSize = - cpu_to_le64(inode->i_blocks << 9); + file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->Reserved = cpu_to_le32(0); rsp->OutputBufferLength = @@ -4804,14 +4835,17 @@ static void get_file_mode_info(struct smb2_query_info_rsp *rsp, cpu_to_le32(sizeof(struct smb2_file_mode_info)); } -static void get_file_compression_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_compression_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_comp_info *file_info; struct kstat stat; + int ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; file_info = (struct smb2_file_comp_info *)rsp->Buffer; file_info->CompressedFileSize = cpu_to_le64(stat.blocks << 9); @@ -4823,6 +4857,8 @@ static void get_file_compression_info(struct smb2_query_info_rsp *rsp, rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_comp_info)); + + return 0; } static int get_file_attribute_tag_info(struct smb2_query_info_rsp *rsp, @@ -4844,7 +4880,7 @@ static int get_file_attribute_tag_info(struct smb2_query_info_rsp *rsp, return 0; } -static void find_file_posix_info(struct smb2_query_info_rsp *rsp, +static int find_file_posix_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { struct smb311_posix_qinfo *file_info; @@ -4852,24 +4888,31 @@ static void find_file_posix_info(struct smb2_query_info_rsp *rsp, struct mnt_idmap *idmap = file_mnt_idmap(fp->filp); vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); + struct kstat stat; u64 time; int out_buf_len = sizeof(struct smb311_posix_qinfo) + 32; + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; file_info = (struct smb311_posix_qinfo *)rsp->Buffer; file_info->CreationTime = cpu_to_le64(fp->create_time); - time = ksmbd_UnixTimeToNT(inode_get_atime(inode)); + time = ksmbd_UnixTimeToNT(stat.atime); file_info->LastAccessTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_mtime(inode)); + time = ksmbd_UnixTimeToNT(stat.mtime); file_info->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_ctime(inode)); + time = ksmbd_UnixTimeToNT(stat.ctime); file_info->ChangeTime = cpu_to_le64(time); file_info->DosAttributes = fp->f_ci->m_fattr; - file_info->Inode = cpu_to_le64(inode->i_ino); - file_info->EndOfFile = cpu_to_le64(inode->i_size); - file_info->AllocationSize = cpu_to_le64(inode->i_blocks << 9); - file_info->HardLinks = cpu_to_le32(inode->i_nlink); - file_info->Mode = cpu_to_le32(inode->i_mode & 0777); - file_info->DeviceId = cpu_to_le32(inode->i_rdev); + file_info->Inode = cpu_to_le64(stat.ino); + file_info->EndOfFile = cpu_to_le64(stat.size); + file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); + file_info->HardLinks = cpu_to_le32(stat.nlink); + file_info->Mode = cpu_to_le32(stat.mode & 0777); + file_info->DeviceId = cpu_to_le32(stat.rdev); /* * Sids(32) contain two sids(Domain sid(16), UNIX group sid(16)). @@ -4882,6 +4925,8 @@ static void find_file_posix_info(struct smb2_query_info_rsp *rsp, SIDUNIX_GROUP, (struct smb_sid *)&file_info->Sids[16]); rsp->OutputBufferLength = cpu_to_le32(out_buf_len); + + return 0; } static int smb2_get_info_file(struct ksmbd_work *work, @@ -4930,7 +4975,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_STANDARD_INFORMATION: - get_file_standard_info(rsp, fp, work->response_buf); + rc = get_file_standard_info(rsp, fp, work->response_buf); break; case FILE_ALIGNMENT_INFORMATION: @@ -4946,11 +4991,11 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_STREAM_INFORMATION: - get_file_stream_info(work, rsp, fp, work->response_buf); + rc = get_file_stream_info(work, rsp, fp, work->response_buf); break; case FILE_INTERNAL_INFORMATION: - get_file_internal_info(rsp, fp, work->response_buf); + rc = get_file_internal_info(rsp, fp, work->response_buf); break; case FILE_NETWORK_OPEN_INFORMATION: @@ -4974,7 +5019,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_COMPRESSION_INFORMATION: - get_file_compression_info(rsp, fp, work->response_buf); + rc = get_file_compression_info(rsp, fp, work->response_buf); break; case FILE_ATTRIBUTE_TAG_INFORMATION: @@ -4985,7 +5030,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, pr_err("client doesn't negotiate with SMB3.1.1 POSIX Extensions\n"); rc = -EOPNOTSUPP; } else { - find_file_posix_info(rsp, fp, work->response_buf); + rc = find_file_posix_info(rsp, fp, work->response_buf); } break; default: @@ -5398,7 +5443,6 @@ int smb2_close(struct ksmbd_work *work) struct smb2_close_rsp *rsp; struct ksmbd_conn *conn = work->conn; struct ksmbd_file *fp; - struct inode *inode; u64 time; int err = 0; @@ -5453,24 +5497,33 @@ int smb2_close(struct ksmbd_work *work) rsp->Reserved = 0; if (req->Flags == SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB) { + struct kstat stat; + int ret; + fp = ksmbd_lookup_fd_fast(work, volatile_id); if (!fp) { err = -ENOENT; goto out; } - inode = file_inode(fp->filp); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) { + ksmbd_fd_put(work, fp); + goto out; + } + rsp->Flags = SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB; - rsp->AllocationSize = S_ISDIR(inode->i_mode) ? 0 : - cpu_to_le64(inode->i_blocks << 9); - rsp->EndOfFile = cpu_to_le64(inode->i_size); + rsp->AllocationSize = S_ISDIR(stat.mode) ? 0 : + cpu_to_le64(stat.blocks << 9); + rsp->EndOfFile = cpu_to_le64(stat.size); rsp->Attributes = fp->f_ci->m_fattr; rsp->CreationTime = cpu_to_le64(fp->create_time); - time = ksmbd_UnixTimeToNT(inode_get_atime(inode)); + time = ksmbd_UnixTimeToNT(stat.atime); rsp->LastAccessTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_mtime(inode)); + time = ksmbd_UnixTimeToNT(stat.mtime); rsp->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_ctime(inode)); + time = ksmbd_UnixTimeToNT(stat.ctime); rsp->ChangeTime = cpu_to_le64(time); ksmbd_fd_put(work, fp); } else { @@ -5581,8 +5634,9 @@ static int smb2_rename(struct ksmbd_work *work, if (!file_info->ReplaceIfExists) flags = RENAME_NOREPLACE; - smb_break_all_levII_oplock(work, fp, 0); rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags); + if (!rc) + smb_break_all_levII_oplock(work, fp, 0); out: kfree(new_name); return rc; @@ -5759,15 +5813,21 @@ static int set_file_allocation_info(struct ksmbd_work *work, loff_t alloc_blks; struct inode *inode; + struct kstat stat; int rc; if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; + rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; + alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); - if (alloc_blks > inode->i_blocks) { + if (alloc_blks > stat.blocks) { smb_break_all_levII_oplock(work, fp, 1); rc = vfs_fallocate(fp->filp, FALLOC_FL_KEEP_SIZE, 0, alloc_blks * 512); @@ -5775,7 +5835,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, pr_err("vfs_fallocate is failed : %d\n", rc); return rc; } - } else if (alloc_blks < inode->i_blocks) { + } else if (alloc_blks < stat.blocks) { loff_t size; /* @@ -5930,6 +5990,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, struct ksmbd_share_config *share) { unsigned int buf_len = le32_to_cpu(req->BufferLength); + char *buffer = (char *)req + le16_to_cpu(req->BufferOffset); switch (req->FileInfoClass) { case FILE_BASIC_INFORMATION: @@ -5937,7 +5998,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_file_basic_info)) return -EINVAL; - return set_file_basic_info(fp, (struct smb2_file_basic_info *)req->Buffer, share); + return set_file_basic_info(fp, (struct smb2_file_basic_info *)buffer, share); } case FILE_ALLOCATION_INFORMATION: { @@ -5945,7 +6006,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_file_allocation_info(work, fp, - (struct smb2_file_alloc_info *)req->Buffer); + (struct smb2_file_alloc_info *)buffer); } case FILE_END_OF_FILE_INFORMATION: { @@ -5953,7 +6014,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_end_of_file_info(work, fp, - (struct smb2_file_eof_info *)req->Buffer); + (struct smb2_file_eof_info *)buffer); } case FILE_RENAME_INFORMATION: { @@ -5961,7 +6022,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_rename_info(work, fp, - (struct smb2_file_rename_info *)req->Buffer, + (struct smb2_file_rename_info *)buffer, buf_len); } case FILE_LINK_INFORMATION: @@ -5970,7 +6031,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return smb2_create_link(work, work->tcon->share_conf, - (struct smb2_file_link_info *)req->Buffer, + (struct smb2_file_link_info *)buffer, buf_len, fp->filp, work->conn->local_nls); } @@ -5980,7 +6041,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_file_disposition_info(fp, - (struct smb2_file_disposition_info *)req->Buffer); + (struct smb2_file_disposition_info *)buffer); } case FILE_FULL_EA_INFORMATION: { @@ -5993,7 +6054,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_ea_info)) return -EINVAL; - return smb2_set_ea((struct smb2_ea_info *)req->Buffer, + return smb2_set_ea((struct smb2_ea_info *)buffer, buf_len, &fp->filp->f_path, true); } case FILE_POSITION_INFORMATION: @@ -6001,14 +6062,14 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_file_pos_info)) return -EINVAL; - return set_file_position_info(fp, (struct smb2_file_pos_info *)req->Buffer); + return set_file_position_info(fp, (struct smb2_file_pos_info *)buffer); } case FILE_MODE_INFORMATION: { if (buf_len < sizeof(struct smb2_file_mode_info)) return -EINVAL; - return set_file_mode_info(fp, (struct smb2_file_mode_info *)req->Buffer); + return set_file_mode_info(fp, (struct smb2_file_mode_info *)buffer); } } @@ -6089,7 +6150,7 @@ int smb2_set_info(struct ksmbd_work *work) } rc = smb2_set_info_sec(fp, le32_to_cpu(req->AdditionalInformation), - req->Buffer, + (char *)req + le16_to_cpu(req->BufferOffset), le32_to_cpu(req->BufferLength)); ksmbd_revert_fsids(work); break; @@ -7535,7 +7596,7 @@ static int fsctl_pipe_transceive(struct ksmbd_work *work, u64 id, struct smb2_ioctl_rsp *rsp) { struct ksmbd_rpc_command *rpc_resp; - char *data_buf = (char *)&req->Buffer[0]; + char *data_buf = (char *)req + le32_to_cpu(req->InputOffset); int nbytes = 0; rpc_resp = ksmbd_rpc_ioctl(work->sess, id, data_buf, @@ -7648,6 +7709,7 @@ int smb2_ioctl(struct ksmbd_work *work) u64 id = KSMBD_NO_FID; struct ksmbd_conn *conn = work->conn; int ret = 0; + char *buffer; if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); @@ -7670,6 +7732,8 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } + buffer = (char *)req + le32_to_cpu(req->InputOffset); + cnt_code = le32_to_cpu(req->CtlCode); ret = smb2_calc_max_out_buf_len(work, 48, le32_to_cpu(req->MaxOutputResponse)); @@ -7727,7 +7791,7 @@ int smb2_ioctl(struct ksmbd_work *work) } ret = fsctl_validate_negotiate_info(conn, - (struct validate_negotiate_info_req *)&req->Buffer[0], + (struct validate_negotiate_info_req *)buffer, (struct validate_negotiate_info_rsp *)&rsp->Buffer[0], in_buf_len); if (ret < 0) @@ -7780,7 +7844,7 @@ int smb2_ioctl(struct ksmbd_work *work) rsp->VolatileFileId = req->VolatileFileId; rsp->PersistentFileId = req->PersistentFileId; fsctl_copychunk(work, - (struct copychunk_ioctl_req *)&req->Buffer[0], + (struct copychunk_ioctl_req *)buffer, le32_to_cpu(req->CtlCode), le32_to_cpu(req->InputCount), req->VolatileFileId, @@ -7793,8 +7857,7 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } - ret = fsctl_set_sparse(work, id, - (struct file_sparse *)&req->Buffer[0]); + ret = fsctl_set_sparse(work, id, (struct file_sparse *)buffer); if (ret < 0) goto out; break; @@ -7817,7 +7880,7 @@ int smb2_ioctl(struct ksmbd_work *work) } zero_data = - (struct file_zero_data_information *)&req->Buffer[0]; + (struct file_zero_data_information *)buffer; off = le64_to_cpu(zero_data->FileOffset); bfz = le64_to_cpu(zero_data->BeyondFinalZero); @@ -7848,7 +7911,7 @@ int smb2_ioctl(struct ksmbd_work *work) } ret = fsctl_query_allocated_ranges(work, id, - (struct file_allocated_range_buffer *)&req->Buffer[0], + (struct file_allocated_range_buffer *)buffer, (struct file_allocated_range_buffer *)&rsp->Buffer[0], out_buf_len / sizeof(struct file_allocated_range_buffer), &nbytes); @@ -7892,7 +7955,7 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } - dup_ext = (struct duplicate_extents_to_file *)&req->Buffer[0]; + dup_ext = (struct duplicate_extents_to_file *)buffer; fp_in = ksmbd_lookup_fd_slow(work, dup_ext->VolatileFileHandle, dup_ext->PersistentFileHandle); diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 7c98bf699772f..fcaf373cc0080 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -457,10 +457,13 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, } ksmbd_kstat.kstat = &kstat; - ksmbd_vfs_fill_dentry_attrs(work, - idmap, - dentry, - &ksmbd_kstat); + rc = ksmbd_vfs_fill_dentry_attrs(work, + idmap, + dentry, + &ksmbd_kstat); + if (rc) + break; + rc = fn(conn, info_level, d_info, &ksmbd_kstat); if (rc) break; diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index f29bb03f0dc47..8752ac82c557b 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -65,6 +65,7 @@ struct ipc_msg_table_entry { struct hlist_node ipc_table_hlist; void *response; + unsigned int msg_sz; }; static struct delayed_work ipc_timer_work; @@ -275,6 +276,7 @@ static int handle_response(int type, void *payload, size_t sz) } memcpy(entry->response, payload, sz); + entry->msg_sz = sz; wake_up_interruptible(&entry->wait); ret = 0; break; @@ -453,6 +455,34 @@ static int ipc_msg_send(struct ksmbd_ipc_msg *msg) return ret; } +static int ipc_validate_msg(struct ipc_msg_table_entry *entry) +{ + unsigned int msg_sz = entry->msg_sz; + + if (entry->type == KSMBD_EVENT_RPC_REQUEST) { + struct ksmbd_rpc_command *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_rpc_command) + resp->payload_sz; + } else if (entry->type == KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST) { + struct ksmbd_spnego_authen_response *resp = entry->response; + + msg_sz = sizeof(struct ksmbd_spnego_authen_response) + + resp->session_key_len + resp->spnego_blob_len; + } else if (entry->type == KSMBD_EVENT_SHARE_CONFIG_REQUEST) { + struct ksmbd_share_config_response *resp = entry->response; + + if (resp->payload_sz) { + if (resp->payload_sz < resp->veto_list_sz) + return -EINVAL; + + msg_sz = sizeof(struct ksmbd_share_config_response) + + resp->payload_sz; + } + } + + return entry->msg_sz != msg_sz ? -EINVAL : 0; +} + static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle) { struct ipc_msg_table_entry entry; @@ -477,6 +507,13 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle ret = wait_event_interruptible_timeout(entry.wait, entry.response != NULL, IPC_WAIT_TIMEOUT); + if (entry.response) { + ret = ipc_validate_msg(&entry); + if (ret) { + kvfree(entry.response); + entry.response = NULL; + } + } out: down_write(&ipc_msg_table_lock); hash_del(&entry.ipc_table_hlist); diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 002a3f0dc7c58..6633fa78e9b96 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -448,6 +448,10 @@ static int create_socket(struct interface *iface) sin6.sin6_family = PF_INET6; sin6.sin6_addr = in6addr_any; sin6.sin6_port = htons(server_conf.tcp_port); + + lock_sock(ksmbd_socket->sk); + ksmbd_socket->sk->sk_ipv6only = false; + release_sock(ksmbd_socket->sk); } ksmbd_tcp_nodelay(ksmbd_socket); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index a6961bfe3e139..613d32d460944 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -754,10 +754,15 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, goto out4; } + /* + * explicitly handle file overwrite case, for compatibility with + * filesystems that may not support rename flags (e.g: fuse) + */ if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) { err = -EEXIST; goto out4; } + flags &= ~(RENAME_NOREPLACE); if (old_child == trap) { err = -EINVAL; @@ -1053,16 +1058,21 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, } int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - const struct path *path, char *attr_name) + const struct path *path, char *attr_name, + bool get_write) { int err; - err = mnt_want_write(path->mnt); - if (err) - return err; + if (get_write == true) { + err = mnt_want_write(path->mnt); + if (err) + return err; + } err = vfs_removexattr(idmap, path->dentry, attr_name); - mnt_drop_write(path->mnt); + + if (get_write == true) + mnt_drop_write(path->mnt); return err; } @@ -1375,7 +1385,7 @@ int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path) ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); if (!strncmp(name, XATTR_NAME_SD, XATTR_NAME_SD_LEN)) { - err = ksmbd_vfs_remove_xattr(idmap, path, name); + err = ksmbd_vfs_remove_xattr(idmap, path, name, true); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); } @@ -1682,11 +1692,19 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, struct dentry *dentry, struct ksmbd_kstat *ksmbd_kstat) { + struct ksmbd_share_config *share_conf = work->tcon->share_conf; u64 time; int rc; + struct path path = { + .mnt = share_conf->vfs_path.mnt, + .dentry = dentry, + }; - generic_fillattr(idmap, STATX_BASIC_STATS, d_inode(dentry), - ksmbd_kstat->kstat); + rc = vfs_getattr(&path, ksmbd_kstat->kstat, + STATX_BASIC_STATS | STATX_BTIME, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; time = ksmbd_UnixTimeToNT(ksmbd_kstat->kstat->ctime); ksmbd_kstat->create_time = time; diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index cfe1c8092f230..cb76f4b5bafe8 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -114,7 +114,8 @@ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - const struct path *path, char *attr_name); + const struct path *path, char *attr_name, + bool get_write); int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, unsigned int flags, struct path *parent_path, struct path *path, bool caseless); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 4e82ff627d122..1596cd2bef4ec 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -254,7 +254,8 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) ci->m_flags &= ~S_DEL_ON_CLS_STREAM; err = ksmbd_vfs_remove_xattr(file_mnt_idmap(filp), &filp->f_path, - fp->stream.name); + fp->stream.name, + true); if (err) pr_err("remove xattr failed : %s\n", fp->stream.name); diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index aa3411354e66d..16bd693d0b3aa 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -48,6 +48,10 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, gid_t i_gid; int err; + inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); + if (inode->i_ino == 0) + return -EINVAL; + err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &i_uid); if (err) return err; @@ -58,7 +62,6 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); - inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); inode_set_mtime(inode, le32_to_cpu(sqsh_ino->mtime), 0); inode_set_atime(inode, inode_get_mtime_sec(inode), 0); inode_set_ctime(inode, inode_get_mtime_sec(inode), 0); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 6b7652fb80505..7cd64021d453d 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -463,6 +463,8 @@ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, kn = kernfs_find_and_get(kobj->sd, attr->name); if (kn) kernfs_break_active_protection(kn); + else + kobject_put(kobj); return kn; } EXPORT_SYMBOL_GPL(sysfs_break_active_protection); diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 410ab2a44d2f6..19bcb51a22036 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -83,9 +83,6 @@ static inline sysv_zone_t *block_end(struct buffer_head *bh) return (sysv_zone_t*)((char*)bh->b_data + bh->b_size); } -/* - * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock) - */ static Indirect *get_branch(struct inode *inode, int depth, int offsets[], @@ -105,15 +102,18 @@ static Indirect *get_branch(struct inode *inode, bh = sb_bread(sb, block); if (!bh) goto failure; + read_lock(&pointers_lock); if (!verify_chain(chain, p)) goto changed; add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets); + read_unlock(&pointers_lock); if (!p->key) goto no_block; } return NULL; changed: + read_unlock(&pointers_lock); brelse(bh); *err = -EAGAIN; goto no_block; @@ -219,9 +219,7 @@ static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *b goto out; reread: - read_lock(&pointers_lock); partial = get_branch(inode, depth, offsets, chain, &err); - read_unlock(&pointers_lock); /* Simplest case - block found, no allocation needed */ if (!partial) { @@ -291,9 +289,9 @@ static Indirect *find_shared(struct inode *inode, *top = 0; for (k = depth; k > 1 && !offsets[k-1]; k--) ; + partial = get_branch(inode, k, offsets, chain, &err); write_lock(&pointers_lock); - partial = get_branch(inode, k, offsets, chain, &err); if (!partial) partial = chain + k-1; /* diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 110e8a2721890..b406bb3430f3d 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -35,11 +35,27 @@ static DEFINE_MUTEX(eventfs_mutex); /* Choose something "unique" ;-) */ #define EVENTFS_FILE_INODE_INO 0x12c4e37 +struct eventfs_root_inode { + struct eventfs_inode ei; + struct inode *parent_inode; + struct dentry *events_dir; +}; + +static struct eventfs_root_inode *get_root_inode(struct eventfs_inode *ei) +{ + WARN_ON_ONCE(!ei->is_events); + return container_of(ei, struct eventfs_root_inode, ei); +} + /* Just try to make something consistent and unique */ static int eventfs_dir_ino(struct eventfs_inode *ei) { - if (!ei->ino) + if (!ei->ino) { ei->ino = get_next_ino(); + /* Must not have the file inode number */ + if (ei->ino == EVENTFS_FILE_INODE_INO) + ei->ino = get_next_ino(); + } return ei->ino; } @@ -57,11 +73,25 @@ enum { EVENTFS_SAVE_MODE = BIT(16), EVENTFS_SAVE_UID = BIT(17), EVENTFS_SAVE_GID = BIT(18), - EVENTFS_TOPLEVEL = BIT(19), }; #define EVENTFS_MODE_MASK (EVENTFS_SAVE_MODE - 1) +static void free_ei_rcu(struct rcu_head *rcu) +{ + struct eventfs_inode *ei = container_of(rcu, struct eventfs_inode, rcu); + struct eventfs_root_inode *rei; + + kfree(ei->entry_attrs); + kfree_const(ei->name); + if (ei->is_events) { + rei = get_root_inode(ei); + kfree(rei); + } else { + kfree(ei); + } +} + /* * eventfs_inode reference count management. * @@ -73,12 +103,17 @@ enum { static void release_ei(struct kref *ref) { struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref); + const struct eventfs_entry *entry; WARN_ON_ONCE(!ei->is_freed); - kfree(ei->entry_attrs); - kfree_const(ei->name); - kfree_rcu(ei, rcu); + for (int i = 0; i < ei->nr_entries; i++) { + entry = &ei->entries[i]; + if (entry->release) + entry->release(entry->name, ei->data); + } + + call_rcu(&ei->rcu, free_ei_rcu); } static inline void put_ei(struct eventfs_inode *ei) @@ -95,6 +130,18 @@ static inline void free_ei(struct eventfs_inode *ei) } } +/* + * Called when creation of an ei fails, do not call release() functions. + */ +static inline void cleanup_ei(struct eventfs_inode *ei) +{ + if (ei) { + /* Set nr_entries to 0 to prevent release() function being called */ + ei->nr_entries = 0; + free_ei(ei); + } +} + static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei) { if (ei) @@ -164,21 +211,7 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, * determined by the parent directory. */ if (dentry->d_inode->i_mode & S_IFDIR) { - /* - * The events directory dentry is never freed, unless its - * part of an instance that is deleted. It's attr is the - * default for its child files and directories. - * Do not update it. It's not used for its own mode or ownership. - */ - if (ei->is_events) { - /* But it still needs to know if it was modified */ - if (iattr->ia_valid & ATTR_UID) - ei->attr.mode |= EVENTFS_SAVE_UID; - if (iattr->ia_valid & ATTR_GID) - ei->attr.mode |= EVENTFS_SAVE_GID; - } else { - update_attr(&ei->attr, iattr); - } + update_attr(&ei->attr, iattr); } else { name = dentry->d_name.name; @@ -196,18 +229,25 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, return ret; } -static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb) +static void update_events_attr(struct eventfs_inode *ei, struct super_block *sb) { - struct inode *root; + struct eventfs_root_inode *rei; + struct inode *parent; - /* Only update if the "events" was on the top level */ - if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL)) - return; + rei = get_root_inode(ei); + + /* Use the parent inode permissions unless root set its permissions */ + parent = rei->parent_inode; + + if (rei->ei.attr.mode & EVENTFS_SAVE_UID) + ei->attr.uid = rei->ei.attr.uid; + else + ei->attr.uid = parent->i_uid; - /* Get the tracefs root inode. */ - root = d_inode(sb->s_root); - ei->attr.uid = root->i_uid; - ei->attr.gid = root->i_gid; + if (rei->ei.attr.mode & EVENTFS_SAVE_GID) + ei->attr.gid = rei->ei.attr.gid; + else + ei->attr.gid = parent->i_gid; } static void set_top_events_ownership(struct inode *inode) @@ -216,10 +256,10 @@ static void set_top_events_ownership(struct inode *inode) struct eventfs_inode *ei = ti->private; /* The top events directory doesn't get automatically updated */ - if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL)) + if (!ei || !ei->is_events) return; - update_top_events_attr(ei, inode->i_sb); + update_events_attr(ei, inode->i_sb); if (!(ei->attr.mode & EVENTFS_SAVE_UID)) inode->i_uid = ei->attr.uid; @@ -248,7 +288,7 @@ static int eventfs_permission(struct mnt_idmap *idmap, return generic_permission(idmap, inode, mask); } -static const struct inode_operations eventfs_root_dir_inode_operations = { +static const struct inode_operations eventfs_dir_inode_operations = { .lookup = eventfs_root_lookup, .setattr = eventfs_set_attr, .getattr = eventfs_get_attr, @@ -265,6 +305,62 @@ static const struct file_operations eventfs_file_operations = { .llseek = generic_file_llseek, }; +static void eventfs_set_attrs(struct eventfs_inode *ei, bool update_uid, kuid_t uid, + bool update_gid, kgid_t gid, int level) +{ + struct eventfs_inode *ei_child; + + /* Update events// */ + if (WARN_ON_ONCE(level > 3)) + return; + + if (update_uid) { + ei->attr.mode &= ~EVENTFS_SAVE_UID; + ei->attr.uid = uid; + } + + if (update_gid) { + ei->attr.mode &= ~EVENTFS_SAVE_GID; + ei->attr.gid = gid; + } + + list_for_each_entry(ei_child, &ei->children, list) { + eventfs_set_attrs(ei_child, update_uid, uid, update_gid, gid, level + 1); + } + + if (!ei->entry_attrs) + return; + + for (int i = 0; i < ei->nr_entries; i++) { + if (update_uid) { + ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID; + ei->entry_attrs[i].uid = uid; + } + if (update_gid) { + ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID; + ei->entry_attrs[i].gid = gid; + } + } + +} + +/* + * On a remount of tracefs, if UID or GID options are set, then + * the mount point inode permissions should be used. + * Reset the saved permission flags appropriately. + */ +void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid) +{ + struct eventfs_inode *ei = ti->private; + + /* Only the events directory does the updates */ + if (!ei || !ei->is_events || ei->is_freed) + return; + + eventfs_set_attrs(ei, update_uid, ti->vfs_inode.i_uid, + update_gid, ti->vfs_inode.i_gid, 0); +} + /* Return the evenfs_inode of the "events" directory */ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) { @@ -280,14 +376,13 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) * If the ei is being freed, the ownership of the children * doesn't matter. */ - if (ei->is_freed) { - ei = NULL; - break; - } + if (ei->is_freed) + return NULL; + // Walk upwards until you find the events inode } while (!ei->is_events); - update_top_events_attr(ei, dentry->d_sb); + update_events_attr(ei, dentry->d_sb); return ei; } @@ -391,7 +486,7 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry, update_inode_attr(dentry, inode, &ei->attr, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO); - inode->i_op = &eventfs_root_dir_inode_operations; + inode->i_op = &eventfs_dir_inode_operations; inode->i_fop = &eventfs_file_operations; /* All directories will have the same inode number */ @@ -408,19 +503,43 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry, return NULL; } +static inline struct eventfs_inode *init_ei(struct eventfs_inode *ei, const char *name) +{ + ei->name = kstrdup_const(name, GFP_KERNEL); + if (!ei->name) + return NULL; + kref_init(&ei->kref); + return ei; +} + static inline struct eventfs_inode *alloc_ei(const char *name) { struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL); + struct eventfs_inode *result; if (!ei) return NULL; - ei->name = kstrdup_const(name, GFP_KERNEL); - if (!ei->name) { + result = init_ei(ei, name); + if (!result) kfree(ei); + + return result; +} + +static inline struct eventfs_inode *alloc_root_ei(const char *name) +{ + struct eventfs_root_inode *rei = kzalloc(sizeof(*rei), GFP_KERNEL); + struct eventfs_inode *ei; + + if (!rei) return NULL; - } - kref_init(&ei->kref); + + rei->ei.is_events = 1; + ei = init_ei(&rei->ei, name); + if (!ei) + kfree(rei); + return ei; } @@ -686,7 +805,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode /* Was the parent freed? */ if (list_empty(&ei->list)) { - free_ei(ei); + cleanup_ei(ei); ei = NULL; } return ei; @@ -709,6 +828,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry int size, void *data) { struct dentry *dentry = tracefs_start_creating(name, parent); + struct eventfs_root_inode *rei; struct eventfs_inode *ei; struct tracefs_inode *ti; struct inode *inode; @@ -721,7 +841,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry if (IS_ERR(dentry)) return ERR_CAST(dentry); - ei = alloc_ei(name); + ei = alloc_root_ei(name); if (!ei) goto fail; @@ -730,39 +850,38 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry goto fail; // Note: we have a ref to the dentry from tracefs_start_creating() - ei->events_dir = dentry; + rei = get_root_inode(ei); + rei->events_dir = dentry; + rei->parent_inode = d_inode(dentry->d_sb->s_root); + ei->entries = entries; ei->nr_entries = size; - ei->is_events = 1; ei->data = data; /* Save the ownership of this directory */ uid = d_inode(dentry->d_parent)->i_uid; gid = d_inode(dentry->d_parent)->i_gid; - /* - * If the events directory is of the top instance, then parent - * is NULL. Set the attr.mode to reflect this and its permissions will - * default to the tracefs root dentry. - */ - if (!parent) - ei->attr.mode = EVENTFS_TOPLEVEL; - - /* This is used as the default ownership of the files and directories */ ei->attr.uid = uid; ei->attr.gid = gid; + /* + * When the "events" directory is created, it takes on the + * permissions of its parent. But can be reset on remount. + */ + ei->attr.mode |= EVENTFS_SAVE_UID | EVENTFS_SAVE_GID; + INIT_LIST_HEAD(&ei->children); INIT_LIST_HEAD(&ei->list); ti = get_tracefs(inode); - ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE; + ti->flags |= TRACEFS_EVENT_INODE; ti->private = ei; inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; inode->i_uid = uid; inode->i_gid = gid; - inode->i_op = &eventfs_root_dir_inode_operations; + inode->i_op = &eventfs_dir_inode_operations; inode->i_fop = &eventfs_file_operations; dentry->d_fsdata = get_ei(ei); @@ -785,7 +904,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry return ei; fail: - free_ei(ei); + cleanup_ei(ei); tracefs_failed_creating(dentry); return ERR_PTR(-ENOMEM); } @@ -844,13 +963,15 @@ void eventfs_remove_dir(struct eventfs_inode *ei) */ void eventfs_remove_events_dir(struct eventfs_inode *ei) { + struct eventfs_root_inode *rei; struct dentry *dentry; - dentry = ei->events_dir; + rei = get_root_inode(ei); + dentry = rei->events_dir; if (!dentry) return; - ei->events_dir = NULL; + rei->events_dir = NULL; eventfs_remove_dir(ei); /* diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index d65ffad4c327c..7ad53745ecd77 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -30,20 +30,47 @@ static struct vfsmount *tracefs_mount; static int tracefs_mount_count; static bool tracefs_registered; +/* + * Keep track of all tracefs_inodes in order to update their + * flags if necessary on a remount. + */ +static DEFINE_SPINLOCK(tracefs_inode_lock); +static LIST_HEAD(tracefs_inodes); + static struct inode *tracefs_alloc_inode(struct super_block *sb) { struct tracefs_inode *ti; + unsigned long flags; ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL); if (!ti) return NULL; + spin_lock_irqsave(&tracefs_inode_lock, flags); + list_add_rcu(&ti->list, &tracefs_inodes); + spin_unlock_irqrestore(&tracefs_inode_lock, flags); + return &ti->vfs_inode; } +static void tracefs_free_inode_rcu(struct rcu_head *rcu) +{ + struct tracefs_inode *ti; + + ti = container_of(rcu, struct tracefs_inode, rcu); + kmem_cache_free(tracefs_inode_cachep, ti); +} + static void tracefs_free_inode(struct inode *inode) { - kmem_cache_free(tracefs_inode_cachep, get_tracefs(inode)); + struct tracefs_inode *ti = get_tracefs(inode); + unsigned long flags; + + spin_lock_irqsave(&tracefs_inode_lock, flags); + list_del_rcu(&ti->list); + spin_unlock_irqrestore(&tracefs_inode_lock, flags); + + call_rcu(&ti->rcu, tracefs_free_inode_rcu); } static ssize_t default_read_file(struct file *file, char __user *buf, @@ -153,16 +180,39 @@ static void set_tracefs_inode_owner(struct inode *inode) { struct tracefs_inode *ti = get_tracefs(inode); struct inode *root_inode = ti->private; + kuid_t uid; + kgid_t gid; + + uid = root_inode->i_uid; + gid = root_inode->i_gid; + + /* + * If the root is not the mount point, then check the root's + * permissions. If it was never set, then default to the + * mount point. + */ + if (root_inode != d_inode(root_inode->i_sb->s_root)) { + struct tracefs_inode *rti; + + rti = get_tracefs(root_inode); + root_inode = d_inode(root_inode->i_sb->s_root); + + if (!(rti->flags & TRACEFS_UID_PERM_SET)) + uid = root_inode->i_uid; + + if (!(rti->flags & TRACEFS_GID_PERM_SET)) + gid = root_inode->i_gid; + } /* * If this inode has never been referenced, then update * the permissions to the superblock. */ if (!(ti->flags & TRACEFS_UID_PERM_SET)) - inode->i_uid = root_inode->i_uid; + inode->i_uid = uid; if (!(ti->flags & TRACEFS_GID_PERM_SET)) - inode->i_gid = root_inode->i_gid; + inode->i_gid = gid; } static int tracefs_permission(struct mnt_idmap *idmap, @@ -313,6 +363,8 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) struct tracefs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); struct tracefs_mount_opts *opts = &fsi->mount_opts; + struct tracefs_inode *ti; + bool update_uid, update_gid; umode_t tmp_mode; /* @@ -332,6 +384,25 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) if (!remount || opts->opts & BIT(Opt_gid)) inode->i_gid = opts->gid; + if (remount && (opts->opts & BIT(Opt_uid) || opts->opts & BIT(Opt_gid))) { + + update_uid = opts->opts & BIT(Opt_uid); + update_gid = opts->opts & BIT(Opt_gid); + + rcu_read_lock(); + list_for_each_entry_rcu(ti, &tracefs_inodes, list) { + if (update_uid) + ti->flags &= ~TRACEFS_UID_PERM_SET; + + if (update_gid) + ti->flags &= ~TRACEFS_GID_PERM_SET; + + if (ti->flags & TRACEFS_EVENT_INODE) + eventfs_remount(ti, update_uid, update_gid); + } + rcu_read_unlock(); + } + return 0; } @@ -368,10 +439,26 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root) return 0; } +static int tracefs_drop_inode(struct inode *inode) +{ + struct tracefs_inode *ti = get_tracefs(inode); + + /* + * This inode is being freed and cannot be used for + * eventfs. Clear the flag so that it doesn't call into + * eventfs during the remount flag updates. The eventfs_inode + * gets freed after an RCU cycle, so the content will still + * be safe if the iteration is going on now. + */ + ti->flags &= ~TRACEFS_EVENT_INODE; + + return 1; +} + static const struct super_operations tracefs_super_operations = { .alloc_inode = tracefs_alloc_inode, .free_inode = tracefs_free_inode, - .drop_inode = generic_delete_inode, + .drop_inode = tracefs_drop_inode, .statfs = simple_statfs, .remount_fs = tracefs_remount, .show_options = tracefs_show_options, diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index beb3dcd0e4342..f704d8348357e 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -4,15 +4,18 @@ enum { TRACEFS_EVENT_INODE = BIT(1), - TRACEFS_EVENT_TOP_INODE = BIT(2), - TRACEFS_GID_PERM_SET = BIT(3), - TRACEFS_UID_PERM_SET = BIT(4), - TRACEFS_INSTANCE_INODE = BIT(5), + TRACEFS_GID_PERM_SET = BIT(2), + TRACEFS_UID_PERM_SET = BIT(3), + TRACEFS_INSTANCE_INODE = BIT(4), }; struct tracefs_inode { - struct inode vfs_inode; + union { + struct inode vfs_inode; + struct rcu_head rcu; + }; /* The below gets initialized with memset_after(ti, 0, vfs_inode) */ + struct list_head list; unsigned long flags; void *private; }; @@ -36,7 +39,6 @@ struct eventfs_attr { * @children: link list into the child eventfs_inode * @entries: the array of entries representing the files in the directory * @name: the name of the directory to create - * @events_dir: the dentry of the events directory * @entry_attrs: Saved mode and ownership of the @d_children * @data: The private data to pass to the callbacks * @attr: Saved mode and ownership of eventfs_inode itself @@ -54,7 +56,6 @@ struct eventfs_inode { struct list_head children; const struct eventfs_entry *entries; const char *name; - struct dentry *events_dir; struct eventfs_attr *entry_attrs; void *data; struct eventfs_attr attr; @@ -75,6 +76,7 @@ struct dentry *tracefs_end_creating(struct dentry *dentry); struct dentry *tracefs_failed_creating(struct dentry *dentry); struct inode *tracefs_get_inode(struct super_block *sb); +void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid); void eventfs_d_release(struct dentry *dentry); #endif /* _TRACEFS_INTERNAL_H */ diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index e413a9cf8ee38..6b3db00d9b121 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1134,6 +1134,8 @@ static int ubifs_mknod(struct mnt_idmap *idmap, struct inode *dir, dir_ui->ui_size = dir->i_size; mutex_unlock(&dir_ui->ui_mutex); out_inode: + /* Free inode->i_link before inode is marked as bad. */ + fscrypt_free_inode(inode); make_bad_inode(inode); iput(inode); out_fname: diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 5029eb3390a56..d0694b83dd02c 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -261,9 +261,6 @@ static int write_begin_slow(struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } if (PagePrivate(page)) @@ -463,9 +460,6 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } err = allocate_budget(c, page, ui, appending); @@ -475,10 +469,8 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * If we skipped reading the page because we were going to * write all of it, then it is not up to date. */ - if (skipped_read) { + if (skipped_read) ClearPageChecked(page); - ClearPageUptodate(page); - } /* * Budgeting failed which means it would have to force * write-back but didn't, because we set the @fast flag in the @@ -569,6 +561,9 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, goto out; } + if (len == PAGE_SIZE) + SetPageUptodate(page); + if (!PagePrivate(page)) { attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index d8493449d4c57..bbf8918417fd8 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -341,7 +341,7 @@ const struct address_space_operations udf_aops = { */ int udf_expand_file_adinicb(struct inode *inode) { - struct page *page; + struct folio *folio; struct udf_inode_info *iinfo = UDF_I(inode); int err; @@ -357,12 +357,13 @@ int udf_expand_file_adinicb(struct inode *inode) return 0; } - page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS); - if (!page) - return -ENOMEM; + folio = __filemap_get_folio(inode->i_mapping, 0, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_KERNEL); + if (IS_ERR(folio)) + return PTR_ERR(folio); - if (!PageUptodate(page)) - udf_adinicb_readpage(page); + if (!folio_test_uptodate(folio)) + udf_adinicb_readpage(&folio->page); down_write(&iinfo->i_data_sem); memset(iinfo->i_data + iinfo->i_lenEAttr, 0x00, iinfo->i_lenAlloc); @@ -371,22 +372,22 @@ int udf_expand_file_adinicb(struct inode *inode) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; else iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; - set_page_dirty(page); - unlock_page(page); + folio_mark_dirty(folio); + folio_unlock(folio); up_write(&iinfo->i_data_sem); err = filemap_fdatawrite(inode->i_mapping); if (err) { /* Restore everything back so that we don't lose data... */ - lock_page(page); + folio_lock(folio); down_write(&iinfo->i_data_sem); - memcpy_to_page(page, 0, iinfo->i_data + iinfo->i_lenEAttr, - inode->i_size); - unlock_page(page); + memcpy_from_folio(iinfo->i_data + iinfo->i_lenEAttr, + folio, 0, inode->i_size); + folio_unlock(folio); iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; iinfo->i_lenAlloc = inode->i_size; up_write(&iinfo->i_data_sem); } - put_page(page); + folio_put(folio); mark_inode_dirty(inode); return err; diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c index 758163af39c26..78ecc633606fb 100644 --- a/fs/udf/udftime.c +++ b/fs/udf/udftime.c @@ -46,13 +46,18 @@ udf_disk_stamp_to_time(struct timespec64 *dest, struct timestamp src) dest->tv_sec = mktime64(year, src.month, src.day, src.hour, src.minute, src.second); dest->tv_sec -= offset * 60; - dest->tv_nsec = 1000 * (src.centiseconds * 10000 + - src.hundredsOfMicroseconds * 100 + src.microseconds); + /* * Sanitize nanosecond field since reportedly some filesystems are * recorded with bogus sub-second values. */ - dest->tv_nsec %= NSEC_PER_SEC; + if (src.centiseconds < 100 && src.hundredsOfMicroseconds < 100 && + src.microseconds < 100) { + dest->tv_nsec = 1000 * (src.centiseconds * 10000 + + src.hundredsOfMicroseconds * 100 + src.microseconds); + } else { + dest->tv_nsec = 0; + } } void diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 959551ff9a951..13ef4e1fc1237 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -925,6 +925,10 @@ static int userfaultfd_release(struct inode *inode, struct file *file) prev = vma; continue; } + /* Reset ptes for the whole vma range if wr-protected */ + if (userfaultfd_wp(vma)) + uffd_wp_range(vma, vma->vm_start, + vma->vm_end - vma->vm_start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; vma = vma_modify_flags_uffd(&vmi, prev, vma, vma->vm_start, vma->vm_end, new_flags, diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index 2307f8037efc3..118dedef8ebe8 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -218,6 +218,7 @@ const struct file_operations vboxsf_reg_fops = { .release = vboxsf_file_release, .fsync = noop_fsync, .splice_read = filemap_splice_read, + .setlease = simple_nosetlease, }; const struct inode_operations vboxsf_reg_iops = { diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 1fb8f4df60cbb..9848af78215bf 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -151,7 +151,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) if (!sbi->nls) { vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); err = -EINVAL; - goto fail_free; + goto fail_destroy_idr; } } @@ -224,6 +224,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); if (sbi->nls) unload_nls(sbi->nls); +fail_destroy_idr: idr_destroy(&sbi->ino_idr); kfree(sbi); return err; diff --git a/fs/verity/init.c b/fs/verity/init.c index cb2c9aac61ed0..f440f0e61e3e6 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -10,8 +10,6 @@ #include #ifdef CONFIG_SYSCTL -static struct ctl_table_header *fsverity_sysctl_header; - static struct ctl_table fsverity_sysctl_table[] = { #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES { @@ -28,10 +26,7 @@ static struct ctl_table fsverity_sysctl_table[] = { static void __init fsverity_init_sysctl(void) { - fsverity_sysctl_header = register_sysctl("fs/verity", - fsverity_sysctl_table); - if (!fsverity_sysctl_header) - panic("fsverity sysctl registration failed"); + register_sysctl_init("fs/verity", fsverity_sysctl_table); } #else /* CONFIG_SYSCTL */ static inline void fsverity_init_sysctl(void) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 39d9525270b74..b3b27047b9f12 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -979,14 +979,23 @@ xfs_ag_shrink_space( if (error) { /* - * if extent allocation fails, need to roll the transaction to + * If extent allocation fails, need to roll the transaction to * ensure that the AGFL fixup has been committed anyway. + * + * We need to hold the AGF across the roll to ensure nothing can + * access the AG for allocation until the shrink is fully + * cleaned up. And due to the resetting of the AG block + * reservation space needing to lock the AGI, we also have to + * hold that so we don't get AGI/AGF lock order inversions in + * the error handling path. */ xfs_trans_bhold(*tpp, agfbp); + xfs_trans_bhold(*tpp, agibp); err2 = xfs_trans_roll(tpp); if (err2) return err2; xfs_trans_bjoin(*tpp, agfbp); + xfs_trans_bjoin(*tpp, agibp); goto resv_init_out; } diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 5bb6e2bd6deee..aa3032b449073 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -530,7 +530,8 @@ xfs_validate_sb_common( } if (!xfs_validate_stripe_geometry(mp, XFS_FSB_TO_B(mp, sbp->sb_unit), - XFS_FSB_TO_B(mp, sbp->sb_width), 0, false)) + XFS_FSB_TO_B(mp, sbp->sb_width), 0, + xfs_buf_daddr(bp) == XFS_SB_DADDR, false)) return -EFSCORRUPTED; /* @@ -1321,8 +1322,10 @@ xfs_sb_get_secondary( } /* - * sunit, swidth, sectorsize(optional with 0) should be all in bytes, - * so users won't be confused by values in error messages. + * sunit, swidth, sectorsize(optional with 0) should be all in bytes, so users + * won't be confused by values in error messages. This function returns false + * if the stripe geometry is invalid and the caller is unable to repair the + * stripe configuration later in the mount process. */ bool xfs_validate_stripe_geometry( @@ -1330,20 +1333,21 @@ xfs_validate_stripe_geometry( __s64 sunit, __s64 swidth, int sectorsize, + bool may_repair, bool silent) { if (swidth > INT_MAX) { if (!silent) xfs_notice(mp, "stripe width (%lld) is too large", swidth); - return false; + goto check_override; } if (sunit > swidth) { if (!silent) xfs_notice(mp, "stripe unit (%lld) is larger than the stripe width (%lld)", sunit, swidth); - return false; + goto check_override; } if (sectorsize && (int)sunit % sectorsize) { @@ -1351,21 +1355,21 @@ xfs_validate_stripe_geometry( xfs_notice(mp, "stripe unit (%lld) must be a multiple of the sector size (%d)", sunit, sectorsize); - return false; + goto check_override; } if (sunit && !swidth) { if (!silent) xfs_notice(mp, "invalid stripe unit (%lld) and stripe width of 0", sunit); - return false; + goto check_override; } if (!sunit && swidth) { if (!silent) xfs_notice(mp, "invalid stripe width (%lld) and stripe unit of 0", swidth); - return false; + goto check_override; } if (sunit && (int)swidth % (int)sunit) { @@ -1373,9 +1377,27 @@ xfs_validate_stripe_geometry( xfs_notice(mp, "stripe width (%lld) must be a multiple of the stripe unit (%lld)", swidth, sunit); - return false; + goto check_override; } return true; + +check_override: + if (!may_repair) + return false; + /* + * During mount, mp->m_dalign will not be set unless the sunit mount + * option was set. If it was set, ignore the bad stripe alignment values + * and allow the validation and overwrite later in the mount process to + * attempt to overwrite the bad stripe alignment values with the values + * supplied by mount options. + */ + if (!mp->m_dalign) + return false; + if (!silent) + xfs_notice(mp, +"Will try to correct with specified mount options sunit (%d) and swidth (%d)", + BBTOB(mp->m_dalign), BBTOB(mp->m_swidth)); + return true; } /* diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index 2e8e8d63d4eb2..37b1ed1bc2095 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -35,8 +35,9 @@ extern int xfs_sb_get_secondary(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **bpp); -extern bool xfs_validate_stripe_geometry(struct xfs_mount *mp, - __s64 sunit, __s64 swidth, int sectorsize, bool silent); +bool xfs_validate_stripe_geometry(struct xfs_mount *mp, + __s64 sunit, __s64 swidth, int sectorsize, bool may_repair, + bool silent); uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents); diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 1935b9ce1885c..c3a9f33e5a8d1 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -385,7 +385,12 @@ xchk_btree_check_block_owner( agno = xfs_daddr_to_agno(bs->cur->bc_mp, daddr); agbno = xfs_daddr_to_agbno(bs->cur->bc_mp, daddr); - init_sa = bs->cur->bc_flags & XFS_BTREE_LONG_PTRS; + /* + * If the btree being examined is not itself a per-AG btree, initialize + * sc->sa so that we can check for the presence of an ownership record + * in the rmap btree for the AG containing the block. + */ + init_sa = bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE; if (init_sa) { error = xchk_ag_init_existing(bs->sc, agno, &bs->sc->sa); if (!xchk_btree_xref_process_error(bs->sc, bs->cur, diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 81f2b96bb5a74..d853348a48c87 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -1000,9 +1000,7 @@ xchk_irele( struct xfs_scrub *sc, struct xfs_inode *ip) { - if (current->journal_info != NULL) { - ASSERT(current->journal_info == sc->tp); - + if (sc->tp) { /* * If we are in a transaction, we /cannot/ drop the inode * ourselves, because the VFS will trigger writeback, which diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index cd91db4a55489..82499270e20b9 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -329,9 +329,9 @@ xchk_stats_register( if (!cs->cs_debugfs) return; - debugfs_create_file("stats", 0644, cs->cs_debugfs, cs, + debugfs_create_file("stats", 0444, cs->cs_debugfs, cs, &scrub_stats_fops); - debugfs_create_file("clear_stats", 0400, cs->cs_debugfs, cs, + debugfs_create_file("clear_stats", 0200, cs->cs_debugfs, cs, &clear_scrub_stats_fops); } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 813f85156b0c3..bc3b649d29c44 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -502,13 +502,6 @@ xfs_vm_writepages( { struct xfs_writepage_ctx wpc = { }; - /* - * Writing back data in a transaction context can result in recursive - * transactions. This is bad, so issue a warning and get out of here. - */ - if (WARN_ON_ONCE(current->journal_info)) - return 0; - xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops); } diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index dba514a2c84d9..b881ed410d7f3 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -2031,8 +2031,10 @@ xfs_inodegc_want_queue_work( * - Memory shrinkers queued the inactivation worker and it hasn't finished. * - The queue depth exceeds the maximum allowable percpu backlog. * - * Note: If the current thread is running a transaction, we don't ever want to - * wait for other transactions because that could introduce a deadlock. + * Note: If we are in a NOFS context here (e.g. current thread is running a + * transaction) the we don't want to block here as inodegc progress may require + * filesystem resources we hold to make progress and that could result in a + * deadlock. Hence we skip out of here if we are in a scoped NOFS context. */ static inline bool xfs_inodegc_want_flush_work( @@ -2040,7 +2042,7 @@ xfs_inodegc_want_flush_work( unsigned int items, unsigned int shrinker_hits) { - if (current->journal_info) + if (current->flags & PF_MEMALLOC_NOFS) return false; if (shrinker_hits > 0) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 1fd94958aa97a..b7be19be0132e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1240,8 +1240,19 @@ xfs_link( */ if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) && tdp->i_projid != sip->i_projid)) { - error = -EXDEV; - goto error_return; + /* + * Project quota setup skips special files which can + * leave inodes in a PROJINHERIT directory without a + * project ID set. We need to allow links to be made + * to these "project-less" inodes because userspace + * expects them to succeed after project ID setup, + * but everything else should be rejected. + */ + if (!special_file(VFS_I(sip)->i_mode) || + sip->i_projid != 0) { + error = -EXDEV; + goto error_return; + } } if (!resblks) { diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 18c8f168b1532..055cdec2e9ad6 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1323,7 +1323,7 @@ xfs_seek_iomap_begin( if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) { if (data_fsb < cow_fsb + cmap.br_blockcount) end_fsb = min(end_fsb, data_fsb); - xfs_trim_extent(&cmap, offset_fsb, end_fsb); + xfs_trim_extent(&cmap, offset_fsb, end_fsb - offset_fsb); seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED); error = xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq); @@ -1348,7 +1348,7 @@ xfs_seek_iomap_begin( imap.br_state = XFS_EXT_NORM; done: seq = xfs_iomap_inode_sequence(ip, 0); - xfs_trim_extent(&imap, offset_fsb, end_fsb); + xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb); error = xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq); out_unlock: xfs_iunlock(ip, lockmode); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 1251c81e55f98..9625cf62b0387 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3204,11 +3204,28 @@ xlog_do_recovery_pass( kmem_free(hbp); /* - * Submit buffers that have been added from the last record processed, - * regardless of error status. + * Submit buffers that have been dirtied by the last record recovered. */ - if (!list_empty(&buffer_list)) + if (!list_empty(&buffer_list)) { + if (error) { + /* + * If there has been an item recovery error then we + * cannot allow partial checkpoint writeback to + * occur. We might have multiple checkpoints with the + * same start LSN in this buffer list, and partial + * writeback of a checkpoint in this situation can + * prevent future recovery of all the changes in the + * checkpoints at this start LSN. + * + * Note: Shutting down the filesystem will result in the + * delwri submission marking all the buffers stale, + * completing them and cleaning up _XBF_LOGRECOVERY + * state without doing any IO. + */ + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); + } error2 = xfs_buf_delwri_submit(&buffer_list); + } if (error && first_bad) *first_bad = rhead_blk; diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 08ce757c74545..23a96df5f1670 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -267,19 +267,14 @@ static inline void xfs_trans_set_context( struct xfs_trans *tp) { - ASSERT(current->journal_info == NULL); tp->t_pflags = memalloc_nofs_save(); - current->journal_info = tp; } static inline void xfs_trans_clear_context( struct xfs_trans *tp) { - if (current->journal_info == tp) { - memalloc_nofs_restore(tp->t_pflags); - current->journal_info = NULL; - } + memalloc_nofs_restore(tp->t_pflags); } static inline void @@ -287,10 +282,8 @@ xfs_trans_switch_context( struct xfs_trans *old_tp, struct xfs_trans *new_tp) { - ASSERT(current->journal_info == old_tp); new_tp->t_pflags = old_tp->t_pflags; old_tp->t_pflags = 0; - current->journal_info = new_tp; } #endif /* __XFS_TRANS_H__ */ diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index e4d24d3f9abb5..bb37a4cd20bfd 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -749,6 +749,7 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s bool acpi_quirk_skip_acpi_ac_and_battery(void); int acpi_install_cmos_rtc_space_handler(acpi_handle handle); void acpi_remove_cmos_rtc_space_handler(acpi_handle handle); +int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip); #else static inline bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *status) @@ -766,23 +767,22 @@ static inline int acpi_install_cmos_rtc_space_handler(acpi_handle handle) static inline void acpi_remove_cmos_rtc_space_handler(acpi_handle handle) { } +static inline int +acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) +{ + *skip = false; + return 0; +} #endif #if IS_ENABLED(CONFIG_X86_ANDROID_TABLETS) bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev); -int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip); bool acpi_quirk_skip_gpio_event_handlers(void); #else static inline bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev) { return false; } -static inline int -acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) -{ - *skip = false; - return 0; -} static inline bool acpi_quirk_skip_gpio_event_handlers(void) { return false; @@ -911,17 +911,19 @@ static inline bool acpi_int_uid_match(struct acpi_device *adev, u64 uid2) * acpi_dev_hid_uid_match - Match device by supplied HID and UID * @adev: ACPI device to match. * @hid2: Hardware ID of the device. - * @uid2: Unique ID of the device, pass 0 or NULL to not check _UID. + * @uid2: Unique ID of the device, pass NULL to not check _UID. * * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2 * will be treated as a match. If user wants to validate @uid2, it should be * done before calling this function. * - * Returns: %true if matches or @uid2 is 0 or NULL, %false otherwise. + * Returns: %true if matches or @uid2 is NULL, %false otherwise. */ #define acpi_dev_hid_uid_match(adev, hid2, uid2) \ (acpi_dev_hid_match(adev, hid2) && \ - (!(uid2) || acpi_dev_uid_match(adev, uid2))) + /* Distinguish integer 0 from NULL @uid2 */ \ + (_Generic(uid2, ACPI_STR_TYPES(!(uid2)), default: 0) || \ + acpi_dev_uid_match(adev, uid2))) void acpi_dev_clear_dependencies(struct acpi_device *supplier); bool acpi_dev_ready_for_enumeration(const struct acpi_device *device); @@ -976,11 +978,16 @@ static inline void acpi_put_acpi_dev(struct acpi_device *adev) { acpi_dev_put(adev); } + +int acpi_wait_for_acpi_ipmi(void); + #else /* CONFIG_ACPI */ static inline int register_acpi_bus_type(void *bus) { return 0; } static inline int unregister_acpi_bus_type(void *bus) { return 0; } +static inline int acpi_wait_for_acpi_ipmi(void) { return 0; } + #endif /* CONFIG_ACPI */ #endif /*__ACPI_BUS_H__*/ diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 3d90716f95229..f5fbc15e56980 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -662,6 +662,10 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)) +ACPI_EXTERNAL_RETURN_STATUS(acpi_status + acpi_execute_orphan_reg_method(acpi_handle device, + acpi_adr_space_type + space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_remove_address_space_handler(acpi_handle device, diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 961f4d88f9ef7..1985c22d90ca4 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -296,5 +296,13 @@ do { \ #define io_stop_wc() do { } while (0) #endif +/* + * Architectures that guarantee an implicit smp_mb() in switch_mm() + * can override smp_mb__after_switch_mm. + */ +#ifndef smp_mb__after_switch_mm +# define smp_mb__after_switch_mm() smp_mb() +#endif + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_GENERIC_BARRIER_H */ diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index fdac4a1714ec0..caa7a6f590934 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -135,7 +135,7 @@ union hv_reference_tsc_msr { * */ -#define HV_LINUX_VENDOR_ID 0x8100 +#define HV_LINUX_VENDOR_ID 0x80 /* Canonical */ /* * Crash notification flags. diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 430f0ae0dde2d..ee759c8245f64 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -18,6 +18,7 @@ #ifndef _ASM_GENERIC_MSHYPERV_H #define _ASM_GENERIC_MSHYPERV_H +#include #include #include #include @@ -115,6 +116,14 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, return status; } +#ifndef PKG_ABI +/* + * Preserve the ability to 'make deb-pkg' since PKG_ABI is provided + * by the Ubuntu build rules. + */ +#define PKG_ABI "0" +#endif + /* Generate the guest OS identifier as described in the Hyper-V TLFS */ static inline u64 hv_generate_guest_id(u64 kernel_version) { @@ -122,6 +131,15 @@ static inline u64 hv_generate_guest_id(u64 kernel_version) guest_id = (((u64)HV_LINUX_VENDOR_ID) << 48); guest_id |= (kernel_version << 16); + /* + * Delphix mutates the ABI number by appending a date and the commit hash. Strip it. + */ + char *token; + char *pkg_abi_str = PKG_ABI; + token = strsep(&pkg_abi_str, "-"); + unsigned long abi_number = simple_strtoul(token, NULL, 10); + guest_id |= (abi_number << 8); + return guest_id; } diff --git a/include/drm/bridge/aux-bridge.h b/include/drm/bridge/aux-bridge.h index 4453906105ca1..c2f5a855512f3 100644 --- a/include/drm/bridge/aux-bridge.h +++ b/include/drm/bridge/aux-bridge.h @@ -33,7 +33,7 @@ static inline struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct devic return NULL; } -static inline int devm_drm_dp_hpd_bridge_add(struct auxiliary_device *adev) +static inline int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev) { return 0; } diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 863b2e7add29e..472359a9d6756 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -463,9 +463,15 @@ struct drm_dp_aux { * @is_remote: Is this AUX CH actually using sideband messaging. */ bool is_remote; + + /** + * @powered_down: If true then the remote endpoint is powered down. + */ + bool powered_down; }; int drm_dp_dpcd_probe(struct drm_dp_aux *aux, unsigned int offset); +void drm_dp_dpcd_set_powered(struct drm_dp_aux *aux, bool powered); ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, void *buffer, size_t size); ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, diff --git a/include/drm/display/drm_dp_mst_helper.h b/include/drm/display/drm_dp_mst_helper.h index 9b19d8bd520af..6c9145abc7e2b 100644 --- a/include/drm/display/drm_dp_mst_helper.h +++ b/include/drm/display/drm_dp_mst_helper.h @@ -851,7 +851,6 @@ int drm_dp_add_payload_part1(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_topology_state *mst_state, struct drm_dp_mst_atomic_payload *payload); int drm_dp_add_payload_part2(struct drm_dp_mst_topology_mgr *mgr, - struct drm_atomic_state *state, struct drm_dp_mst_atomic_payload *payload); void drm_dp_remove_payload_part1(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_topology_state *mst_state, diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index e39da5807ba71..b7aed3ead705b 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -557,6 +557,37 @@ struct drm_bridge_funcs { int (*get_modes)(struct drm_bridge *bridge, struct drm_connector *connector); + /** + * @edid_read: + * + * Read the EDID data of the connected display. + * + * The @edid_read callback is the preferred way of reporting mode + * information for a display connected to the bridge output. Bridges + * that support reading EDID shall implement this callback and leave + * the @get_modes callback unimplemented. + * + * The caller of this operation shall first verify the output + * connection status and refrain from reading EDID from a disconnected + * output. + * + * This callback is optional. Bridges that implement it shall set the + * DRM_BRIDGE_OP_EDID flag in their &drm_bridge->ops. + * + * The connector parameter shall be used for the sole purpose of EDID + * retrieval, and shall not be stored internally by bridge drivers for + * future usage. + * + * RETURNS: + * + * An edid structure newly allocated with drm_edid_alloc() or returned + * from drm_edid_read() family of functions on success, or NULL + * otherwise. The caller is responsible for freeing the returned edid + * structure with drm_edid_free(). + */ + const struct drm_edid *(*edid_read)(struct drm_bridge *bridge, + struct drm_connector *connector); + /** * @get_edid: * @@ -888,6 +919,8 @@ drm_atomic_helper_bridge_propagate_bus_fmt(struct drm_bridge *bridge, enum drm_connector_status drm_bridge_detect(struct drm_bridge *bridge); int drm_bridge_get_modes(struct drm_bridge *bridge, struct drm_connector *connector); +const struct drm_edid *drm_bridge_edid_read(struct drm_bridge *bridge, + struct drm_connector *connector); struct edid *drm_bridge_get_edid(struct drm_bridge *bridge, struct drm_connector *connector); void drm_bridge_hpd_enable(struct drm_bridge *bridge, diff --git a/include/drm/drm_displayid.h b/include/drm/drm_displayid.h index 566497eeb3b81..bc1f6b378195f 100644 --- a/include/drm/drm_displayid.h +++ b/include/drm/drm_displayid.h @@ -30,7 +30,6 @@ struct drm_edid; #define VESA_IEEE_OUI 0x3a0292 /* DisplayID Structure versions */ -#define DISPLAY_ID_STRUCTURE_VER_12 0x12 #define DISPLAY_ID_STRUCTURE_VER_20 0x20 /* DisplayID Structure v1r2 Data Blocks */ diff --git a/include/drm/drm_fixed.h b/include/drm/drm_fixed.h index 6ea339d5de088..81572d32db0c2 100644 --- a/include/drm/drm_fixed.h +++ b/include/drm/drm_fixed.h @@ -71,7 +71,6 @@ static inline u32 dfixed_div(fixed20_12 A, fixed20_12 B) } #define DRM_FIXED_POINT 32 -#define DRM_FIXED_POINT_HALF 16 #define DRM_FIXED_ONE (1ULL << DRM_FIXED_POINT) #define DRM_FIXED_DECIMAL_MASK (DRM_FIXED_ONE - 1) #define DRM_FIXED_DIGITS_MASK (~DRM_FIXED_DECIMAL_MASK) @@ -90,12 +89,12 @@ static inline int drm_fixp2int(s64 a) static inline int drm_fixp2int_round(s64 a) { - return drm_fixp2int(a + (1 << (DRM_FIXED_POINT_HALF - 1))); + return drm_fixp2int(a + DRM_FIXED_ONE / 2); } static inline int drm_fixp2int_ceil(s64 a) { - if (a > 0) + if (a >= 0) return drm_fixp2int(a + DRM_FIXED_ALMOST_ONE); else return drm_fixp2int(a - DRM_FIXED_ALMOST_ONE); diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index 369505447acd8..2ebec3984cd44 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -553,6 +553,19 @@ unsigned long drm_gem_lru_scan(struct drm_gem_lru *lru, int drm_gem_evict(struct drm_gem_object *obj); +/** + * drm_gem_object_is_shared_for_memory_stats - helper for shared memory stats + * + * This helper should only be used for fdinfo shared memory stats to determine + * if a GEM object is shared. + * + * @obj: obj in question + */ +static inline bool drm_gem_object_is_shared_for_memory_stats(struct drm_gem_object *obj) +{ + return (obj->handle_count > 1) || obj->dma_buf; +} + #ifdef CONFIG_LOCKDEP /** * drm_gem_gpuva_set_lock() - Set the lock protecting accesses to the gpuva list. diff --git a/include/drm/drm_kunit_helpers.h b/include/drm/drm_kunit_helpers.h index ba483c87f0e7b..3ae19892229db 100644 --- a/include/drm/drm_kunit_helpers.h +++ b/include/drm/drm_kunit_helpers.h @@ -3,6 +3,8 @@ #ifndef DRM_KUNIT_HELPERS_H_ #define DRM_KUNIT_HELPERS_H_ +#include + #include #include diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index c0aec0d4d664e..3011d33eccbd2 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -241,9 +241,9 @@ int mipi_dsi_shutdown_peripheral(struct mipi_dsi_device *dsi); int mipi_dsi_turn_on_peripheral(struct mipi_dsi_device *dsi); int mipi_dsi_set_maximum_return_packet_size(struct mipi_dsi_device *dsi, u16 value); -ssize_t mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable); -ssize_t mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi, - const struct drm_dsc_picture_parameter_set *pps); +int mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable); +int mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi, + const struct drm_dsc_picture_parameter_set *pps); ssize_t mipi_dsi_generic_write(struct mipi_dsi_device *dsi, const void *payload, size_t size); diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index 881b03e4dc288..9ed42469540eb 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -898,7 +898,8 @@ struct drm_connector_helper_funcs { * * RETURNS: * - * The number of modes added by calling drm_mode_probed_add(). + * The number of modes added by calling drm_mode_probed_add(). Return 0 + * on failures (no modes) instead of negative error codes. */ int (*get_modes)(struct drm_connector *connector); diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index a4eff85b1f449..2b9d856ff388d 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -79,6 +79,12 @@ struct ttm_tt { * page_flags = TTM_TT_FLAG_EXTERNAL | * TTM_TT_FLAG_EXTERNAL_MAPPABLE; * + * TTM_TT_FLAG_DECRYPTED: The mapped ttm pages should be marked as + * not encrypted. The framework will try to match what the dma layer + * is doing, but note that it is a little fragile because ttm page + * fault handling abuses the DMA api a bit and dma_map_attrs can't be + * used to assure pgprot always matches. + * * TTM_TT_FLAG_PRIV_POPULATED: TTM internal only. DO NOT USE. This is * set by TTM after ttm_tt_populate() has successfully returned, and is * then unset when TTM calls ttm_tt_unpopulate(). @@ -87,8 +93,9 @@ struct ttm_tt { #define TTM_TT_FLAG_ZERO_ALLOC BIT(1) #define TTM_TT_FLAG_EXTERNAL BIT(2) #define TTM_TT_FLAG_EXTERNAL_MAPPABLE BIT(3) +#define TTM_TT_FLAG_DECRYPTED BIT(4) -#define TTM_TT_FLAG_PRIV_POPULATED BIT(4) +#define TTM_TT_FLAG_PRIV_POPULATED BIT(5) uint32_t page_flags; /** @num_pages: Number of pages in the page array. */ uint32_t num_pages; diff --git a/include/dt-bindings/clock/r8a779g0-cpg-mssr.h b/include/dt-bindings/clock/r8a779g0-cpg-mssr.h index 754c54a6eb06a..7850cdc62e285 100644 --- a/include/dt-bindings/clock/r8a779g0-cpg-mssr.h +++ b/include/dt-bindings/clock/r8a779g0-cpg-mssr.h @@ -86,5 +86,6 @@ #define R8A779G0_CLK_CPEX 74 #define R8A779G0_CLK_CBFUSA 75 #define R8A779G0_CLK_R 76 +#define R8A779G0_CLK_CP 77 #endif /* __DT_BINDINGS_CLOCK_R8A779G0_CPG_MSSR_H__ */ diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 4b9d8fb393a84..df32355e3e38f 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -86,7 +86,7 @@ void kvm_vcpu_pmu_resync_el0(void); */ #define kvm_pmu_update_vcpu_events(vcpu) \ do { \ - if (!has_vhe() && kvm_vcpu_has_pmu(vcpu)) \ + if (!has_vhe() && kvm_arm_support_pmu_v3()) \ vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ } while (0) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index b7165e52b3c68..d62be29cf7a6e 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -573,9 +573,13 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 +#define OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT 0x00000200 +#define OSC_SB_OVER_16_PSTATES_SUPPORT 0x00000400 +#define OSC_SB_GED_SUPPORT 0x00000800 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 -#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT 0x00002000 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 +#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_PRM_SUPPORT 0x00200000 #define OSC_SB_FFH_OPR_SUPPORT 0x00400000 @@ -1170,6 +1174,7 @@ static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif #ifdef CONFIG_ACPI +char *acpi_handle_path(acpi_handle handle); __printf(3, 4) void acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...); diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 5e95faa959c42..9915df9e6eed8 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -2234,7 +2234,7 @@ raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4346,7 +4346,7 @@ raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4662,4 +4662,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// eec048affea735b8464f58e6d96992101f8f85f1 +// 192d6476c0a1486196d1a01386828be566343816 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 54d7bbe0aeaa6..aa08799713eb2 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1341,7 +1341,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -2905,7 +2905,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4469,7 +4469,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -5008,4 +5008,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 2cc4bc990fef44d3836ec108f11b610f3f438184 +// 1b2571b4e17a6671a7631db8158e0fa5afb6e51d diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index c82947170ddc8..aa4a5c09660fd 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -1527,7 +1527,7 @@ raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -1795,4 +1795,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v) } #endif /* _LINUX_ATOMIC_LONG_H */ -// 4ef23f98c73cff96d239896175fd26b10b88899e +// f8204cfa718c04a01e3c7a15257ac85bbef54c23 diff --git a/include/linux/audit.h b/include/linux/audit.h index 0050ef288ab3c..c5c14c97f8fc6 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -37,6 +37,7 @@ struct audit_watch; struct audit_tree; struct sk_buff; struct kern_ipc_perm; +struct lsmblob; struct audit_krule { u32 pflags; @@ -185,6 +186,10 @@ extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); +extern void audit_log_object_context(struct audit_buffer *ab, + struct lsmblob *blob); +extern int audit_log_subject_context(struct audit_buffer *ab, + struct lsmblob *blob); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); @@ -245,6 +250,14 @@ static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } +static inline void audit_log_object_context(struct audit_buffer *ab, + struct lsmblob *blob) +{ } +static inline int audit_log_subject_context(struct audit_buffer *ab, + struct lsmblob *blob) +{ + return 0; +} static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2ba557e067fe6..f7f5a783da2aa 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -80,6 +80,7 @@ __check_bitop_pr(__test_and_set_bit); __check_bitop_pr(__test_and_clear_bit); __check_bitop_pr(__test_and_change_bit); __check_bitop_pr(test_bit); +__check_bitop_pr(test_bit_acquire); #undef __check_bitop_pr diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 99e4f5e722132..6ee8e7d7383ca 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -126,6 +126,8 @@ typedef unsigned int __bitwise blk_mode_t; #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) /* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ #define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) +/* return partition scanning errors */ +#define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6)) struct gendisk { /* @@ -231,6 +233,19 @@ static inline unsigned int disk_openers(struct gendisk *disk) return atomic_read(&disk->part0->bd_openers); } +/** + * disk_has_partscan - return %true if partition scanning is enabled on a disk + * @disk: disk to check + * + * Returns %true if partitions scanning is enabled for @disk, or %false if + * partition scanning is disabled either permanently or temporarily. + */ +static inline bool disk_has_partscan(struct gendisk *disk) +{ + return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) && + !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index ca73940e26df8..3f4b4ac527ca2 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -10,6 +10,7 @@ #ifdef __KERNEL__ #include #include +bool __init cmdline_has_extra_options(void); #else /* !__KERNEL__ */ /* * NOTE: This is only for tools/bootconfig, because tools/bootconfig will @@ -287,7 +288,12 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ -void __init xbc_exit(void); +void __init _xbc_exit(bool early); + +static inline void xbc_exit(void) +{ + _xbc_exit(false); +} /* XBC embedded bootconfig data in kernel */ #ifdef CONFIG_BOOT_CONFIG_EMBED diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e30100597d0a9..7d719976b5641 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1568,12 +1568,26 @@ struct bpf_link { enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; - struct work_struct work; + /* rcu is used before freeing, work can be used to schedule that + * RCU-based freeing before that, so they never overlap + */ + union { + struct rcu_head rcu; + struct work_struct work; + }; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); + /* deallocate link resources callback, called without RCU grace period + * waiting + */ void (*dealloc)(struct bpf_link *link); + /* deallocate link resources callback, called after RCU grace period; + * if underlying BPF program is sleepable we go through tasks trace + * RCU GP and then "classic" RCU GP + */ + void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d07d857ca67fe..a685535dfbab0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -732,6 +732,8 @@ struct bpf_verifier_env { /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; + /* buffer used to temporary hold constants as scalar registers */ + struct bpf_reg_state fake_reg[2]; /* buffer used to generate temporary string representations, * e.g., in reg_type_str() to generate reg_type string */ diff --git a/include/linux/clk.h b/include/linux/clk.h index 06f1b292f8a00..d01a5de97b01e 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -201,6 +201,18 @@ bool clk_is_match(const struct clk *p, const struct clk *q); */ int clk_rate_exclusive_get(struct clk *clk); +/** + * devm_clk_rate_exclusive_get - devm variant of clk_rate_exclusive_get + * @dev: device the exclusivity is bound to + * @clk: clock source + * + * Calls clk_rate_exclusive_get() on @clk and registers a devm cleanup handler + * on @dev to call clk_rate_exclusive_put(). + * + * Must not be called from within atomic context. + */ +int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk); + /** * clk_rate_exclusive_put - release exclusivity over the rate control of a * producer @@ -274,6 +286,11 @@ static inline int clk_rate_exclusive_get(struct clk *clk) return 0; } +static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk) +{ + return 0; +} + static inline void clk_rate_exclusive_put(struct clk *clk) {} #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 0caf354cb94b5..a6a28952836cb 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -278,6 +278,17 @@ struct ftrace_likely_data { # define __no_kcsan #endif +#ifdef __SANITIZE_MEMORY__ +/* + * Similarly to KASAN and KCSAN, KMSAN loses function attributes of inlined + * functions, therefore disabling KMSAN checks also requires disabling inlining. + * + * __no_sanitize_or_inline effectively prevents KMSAN from reporting errors + * within the function and marks all its outputs as initialized. + */ +# define __no_sanitize_or_inline __no_kmsan_checks notrace __maybe_unused +#endif + #ifndef __no_sanitize_or_inline #define __no_sanitize_or_inline __always_inline #endif diff --git a/include/linux/counter.h b/include/linux/counter.h index 702e9108bbb44..b767b5c821f58 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -359,7 +359,6 @@ struct counter_ops { * @num_counts: number of Counts specified in @counts * @ext: optional array of Counter device extensions * @num_ext: number of Counter device extensions specified in @ext - * @priv: optional private data supplied by driver * @dev: internal device structure * @chrdev: internal character device structure * @events_list: list of current watching Counter events diff --git a/include/linux/cpu.h b/include/linux/cpu.h index dcb89c9871640..75f0344bd3b94 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -75,6 +75,8 @@ extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, @@ -217,7 +219,18 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +#ifdef CONFIG_CPU_MITIGATIONS extern bool cpu_mitigations_off(void); extern bool cpu_mitigations_auto_nosmt(void); +#else +static inline bool cpu_mitigations_off(void) +{ + return true; +} +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return false; +} +#endif #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index afda5f24d3ddc..320fab7d2e940 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1021,6 +1021,18 @@ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy, efficiencies); } +static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx) +{ + unsigned int freq; + + if (idx < 0) + return false; + + freq = policy->freq_table[idx].frequency; + + return freq == clamp_val(freq, policy->min, policy->max); +} + static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) @@ -1054,7 +1066,8 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, return 0; } - if (idx < 0 && efficiencies) { + /* Limit frequency index to honor policy->min/max */ + if (!cpufreq_is_in_limits(policy, idx) && efficiencies) { efficiencies = false; goto retry; } diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 875d12598bd2d..c9c90ada8cf91 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -70,7 +70,6 @@ extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); -extern void cpuset_wait_for_hotplug(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); @@ -190,8 +189,6 @@ static inline void cpuset_update_active_cpus(void) partition_sched_domains(1, NULL, NULL); } -static inline void cpuset_wait_for_hotplug(void) { } - static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 6bfe70decc9fb..ae80a303c216b 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -129,6 +129,16 @@ void _dev_info(const struct device *dev, const char *fmt, ...) _dev_printk(level, dev, fmt, ##__VA_ARGS__); \ }) +/* + * Dummy dev_printk for disabled debugging statements to use whilst maintaining + * gcc's format checking. + */ +#define dev_no_printk(level, dev, fmt, ...) \ + ({ \ + if (0) \ + _dev_printk(level, dev, fmt, ##__VA_ARGS__); \ + }) + /* * #defines for all the dev_ macros to prefix with whatever * possible use of #define dev_fmt(fmt) ... @@ -158,10 +168,7 @@ void _dev_info(const struct device *dev, const char *fmt, ...) dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #else #define dev_dbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif #ifdef CONFIG_PRINTK @@ -247,20 +254,14 @@ do { \ } while (0) #else #define dev_dbg_ratelimited(dev, fmt, ...) \ -do { \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -} while (0) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif #ifdef VERBOSE_DEBUG #define dev_vdbg dev_dbg #else #define dev_vdbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif /* diff --git a/include/linux/device.h b/include/linux/device.h index 97c4b046c09d9..b9f5464f44ed8 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1247,6 +1247,7 @@ void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); +void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index 7595142f3fc57..7b2968612b7e6 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -80,7 +80,8 @@ void dm_io_client_destroy(struct dm_io_client *client); * error occurred doing io to the corresponding region. */ int dm_io(struct dm_io_request *io_req, unsigned int num_regions, - struct dm_io_region *region, unsigned int long *sync_error_bits); + struct dm_io_region *region, unsigned int long *sync_error_bits, + unsigned short ioprio); #endif /* __KERNEL__ */ #endif /* _LINUX_DM_IO_H */ diff --git a/include/linux/efi.h b/include/linux/efi.h index c74f47711f0bd..02224080917f3 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -45,6 +45,8 @@ struct screen_info; #define EFI_ABORTED (21 | (1UL << (BITS_PER_LONG-1))) #define EFI_SECURITY_VIOLATION (26 | (1UL << (BITS_PER_LONG-1))) +#define EFI_IS_ERROR(x) ((x) & (1UL << (BITS_PER_LONG-1))) + typedef unsigned long efi_status_t; typedef u8 efi_bool_t; typedef u16 efi_char16_t; /* UNICODE character */ @@ -386,6 +388,7 @@ void efi_native_runtime_setup(void); #define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0) #define EFI_TCG2_PROTOCOL_GUID EFI_GUID(0x607f766c, 0x7455, 0x42be, 0x93, 0x0b, 0xe4, 0xd7, 0x6d, 0xb2, 0x72, 0x0f) +#define EFI_TCG2_FINAL_EVENTS_TABLE_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) @@ -400,6 +403,8 @@ void efi_native_runtime_setup(void); #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) #define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) +#define EFI_CC_MEASUREMENT_PROTOCOL_GUID EFI_GUID(0x96751a3d, 0x72f4, 0x41a6, 0xa7, 0x94, 0xed, 0x5d, 0x0e, 0x67, 0xae, 0x6b) +#define EFI_CC_FINAL_EVENTS_TABLE_GUID EFI_GUID(0xdd4a4648, 0x2de7, 0x4665, 0x96, 0x4d, 0x21, 0xd9, 0xef, 0x5f, 0xb4, 0x46) /* * This GUID is used to pass to the kernel proper the struct screen_info @@ -411,7 +416,6 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_LOADER_ENTRY_GUID EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) #define LINUX_EFI_RANDOM_SEED_TABLE_GUID EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2, 0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b) #define LINUX_EFI_TPM_EVENT_LOG_GUID EFI_GUID(0xb7799cb0, 0xeca2, 0x4943, 0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa) -#define LINUX_EFI_TPM_FINAL_LOG_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) @@ -865,6 +869,23 @@ static inline int efi_range_is_wc(unsigned long start, unsigned long len) #define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */ #define EFI_MEM_NO_SOFT_RESERVE 11 /* Is the kernel configured to ignore soft reservations? */ #define EFI_PRESERVE_BS_REGIONS 12 /* Are EFI boot-services memory segments available? */ +#define EFI_SECURE_BOOT 13 /* Are we in Secure Boot mode? */ + +enum efi_secureboot_mode { + efi_secureboot_mode_unset, + efi_secureboot_mode_unknown, + efi_secureboot_mode_disabled, + efi_secureboot_mode_enabled, +}; + +#ifdef CONFIG_EFI_PARAMS_FROM_FDT +u32 __init efi_get__secure_boot(void); +#else +static inline u32 efi_get__secure_boot(void) +{ + return efi_secureboot_mode_unset; +}; +#endif #ifdef CONFIG_EFI /* @@ -876,6 +897,8 @@ static inline bool efi_enabled(int feature) } extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); +extern void __init efi_set_secure_boot(enum efi_secureboot_mode mode); + bool __pure __efi_soft_reserve_enabled(void); static inline bool __pure efi_soft_reserve_enabled(void) @@ -897,6 +920,8 @@ static inline bool efi_enabled(int feature) static inline void efi_reboot(enum reboot_mode reboot_mode, const char *__unused) {} +static inline void efi_set_secure_boot(enum efi_secureboot_mode mode) {} + static inline bool efi_soft_reserve_enabled(void) { return false; @@ -911,6 +936,7 @@ static inline void efi_find_mirror(void) {} #endif extern int efi_status_to_err(efi_status_t status); +extern const char *efi_status_to_str(efi_status_t status); /* * Variable Attributes @@ -1127,13 +1153,6 @@ static inline bool efi_runtime_disabled(void) { return true; } extern void efi_call_virt_check_flags(unsigned long flags, const void *caller); extern unsigned long efi_call_virt_save_flags(void); -enum efi_secureboot_mode { - efi_secureboot_mode_unset, - efi_secureboot_mode_unknown, - efi_secureboot_mode_disabled, - efi_secureboot_mode_enabled, -}; - static inline enum efi_secureboot_mode efi_get_secureboot_mode(efi_get_variable_t *get_var) { diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 224645f17c333..e44913a8200fd 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -607,6 +607,39 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, eth_hw_addr_set(dev, addr); } +/** + * eth_skb_pkt_type - Assign packet type if destination address does not match + * @skb: Assigned a packet type if address does not match @dev address + * @dev: Network device used to compare packet address against + * + * If the destination MAC address of the packet does not match the network + * device address, assign an appropriate packet type. + */ +static inline void eth_skb_pkt_type(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct ethhdr *eth = eth_hdr(skb); + + if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { + if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { + if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else { + skb->pkt_type = PACKET_OTHERHOST; + } + } +} + +static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + + skb_pull_inline(skb, ETH_HLEN); + return eth; +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 053137a0fe456..a8c0c081ec4df 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -27,6 +27,7 @@ #define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS) #define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS) +#define F2FS_BLK_END_BYTES(blk) (F2FS_BLK_TO_BYTES(blk + 1) - 1) /* 0, 1(node nid), 2(meta nid) are reserved node id */ #define F2FS_RESERVED_NODE_NUM 3 @@ -40,12 +41,6 @@ #define F2FS_ENC_UTF8_12_1 1 -#define F2FS_IO_SIZE(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ -#define F2FS_IO_SIZE_KB(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits + 2) /* KB */ -#define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */ -#define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) -#define F2FS_IO_ALIGNED(sbi) (F2FS_IO_SIZE(sbi) > 1) - /* This flag is used by node and meta inodes, and by recovery */ #define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO) diff --git a/include/linux/fb.h b/include/linux/fb.h index 05dc9624897df..25ca209e4d21d 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -686,6 +686,10 @@ extern int fb_deferred_io_fsync(struct file *file, loff_t start, __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) +#define FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(__prefix, __damage_range, __damage_area) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) + /* * Initializes struct fb_ops for deferred I/O. */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 68fb6c8142fec..f537a394c42d0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -547,24 +547,27 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) -#define BPF_CALL_x(x, name, ...) \ +#define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ - u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ - u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ + attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ + attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) -#define BPF_CALL_0(name, ...) BPF_CALL_x(0, name, __VA_ARGS__) -#define BPF_CALL_1(name, ...) BPF_CALL_x(1, name, __VA_ARGS__) -#define BPF_CALL_2(name, ...) BPF_CALL_x(2, name, __VA_ARGS__) -#define BPF_CALL_3(name, ...) BPF_CALL_x(3, name, __VA_ARGS__) -#define BPF_CALL_4(name, ...) BPF_CALL_x(4, name, __VA_ARGS__) -#define BPF_CALL_5(name, ...) BPF_CALL_x(5, name, __VA_ARGS__) +#define __NOATTR +#define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) + +#define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 5c28298a98bec..366243ee96096 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -10,6 +10,7 @@ #define __QCOM_QSEECOM_H #include +#include #include #include @@ -24,12 +25,57 @@ struct qseecom_client { u32 app_id; }; +/** + * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. + * @client: The QSEECOM client device. + * + * Returns the SCM device under which the provided QSEECOM client device + * operates. This function is intended to be used for DMA allocations. + */ +static inline struct device *qseecom_scm_dev(struct qseecom_client *client) +{ + return client->aux_dev.dev.parent->parent; +} + +/** + * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. + * @client: The QSEECOM client to allocate the memory for. + * @size: The number of bytes to allocate. + * @dma_handle: Pointer to where the DMA address should be stored. + * @gfp: Allocation flags. + * + * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for + * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. + */ +static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); +} + +/** + * dma_free_coherent() - Free QSEECOM DMA memory. + * @client: The QSEECOM client for which the memory has been allocated. + * @size: The number of bytes allocated. + * @cpu_addr: Virtual memory address to free. + * @dma_handle: DMA memory address to free. + * + * Wrapper function for dma_free_coherent(), freeing memory previously + * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for + * details. + */ +static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, + void *cpu_addr, dma_addr_t dma_handle) +{ + return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); +} + /** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. - * @req: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given client and read @@ -43,8 +89,9 @@ struct qseecom_client { * * Return: Zero on success, nonzero on failure. */ -static inline int qcom_qseecom_app_send(struct qseecom_client *client, void *req, size_t req_size, - void *rsp, size_t rsp_size) +static inline int qcom_qseecom_app_send(struct qseecom_client *client, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size); } diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index ccaf288460546..aaa19f93ac430 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -118,8 +118,8 @@ bool qcom_scm_lmh_dcvsh_available(void); #ifdef CONFIG_QCOM_QSEECOM int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id); -int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, - size_t rsp_size); +int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size); #else /* CONFIG_QCOM_QSEECOM */ @@ -128,9 +128,9 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) return -EINVAL; } -static inline int qcom_scm_qseecom_app_send(u32 app_id, void *req, - size_t req_size, void *rsp, - size_t rsp_size) +static inline int qcom_scm_qseecom_app_send(u32 app_id, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return -EINVAL; } diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 89a6888f2f9e5..e99dbc0525751 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -31,17 +31,30 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning(" __ret; \ }) -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +#if defined(__SANITIZE_ADDRESS__) + +#if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +#elif defined(CONFIG_KASAN_GENERIC) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy); +#else /* CONFIG_KASAN_SW_TAGS */ +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy); +#endif + extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); -extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); -extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); -extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); + #else #if defined(__SANITIZE_MEMORY__) @@ -66,6 +79,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy + #endif /** diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index 223da48a6d18b..94c4edd047e54 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -45,6 +45,7 @@ struct fpga_bridge_info { * @dev: FPGA bridge device * @mutex: enforces exclusive reference to bridge * @br_ops: pointer to struct of FPGA bridge ops + * @br_ops_owner: module containing the br_ops * @info: fpga image specific information * @node: FPGA bridge list node * @priv: low level driver private date @@ -54,6 +55,7 @@ struct fpga_bridge { struct device dev; struct mutex mutex; /* for exclusive reference to bridge */ const struct fpga_bridge_ops *br_ops; + struct module *br_ops_owner; struct fpga_image_info *info; struct list_head node; void *priv; @@ -79,10 +81,12 @@ int of_fpga_bridge_get_to_list(struct device_node *np, struct fpga_image_info *info, struct list_head *bridge_list); +#define fpga_bridge_register(parent, name, br_ops, priv) \ + __fpga_bridge_register(parent, name, br_ops, priv, THIS_MODULE) struct fpga_bridge * -fpga_bridge_register(struct device *parent, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv); +__fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, void *priv, + struct module *owner); void fpga_bridge_unregister(struct fpga_bridge *br); #endif /* _LINUX_FPGA_BRIDGE_H */ diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 54f63459efd6e..0d4fe068f3d8a 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -201,6 +201,7 @@ struct fpga_manager_ops { * @state: state of fpga manager * @compat_id: FPGA manager id for compatibility check. * @mops: pointer to struct of fpga manager ops + * @mops_owner: module containing the mops * @priv: low level driver private date */ struct fpga_manager { @@ -210,6 +211,7 @@ struct fpga_manager { enum fpga_mgr_states state; struct fpga_compat_id *compat_id; const struct fpga_manager_ops *mops; + struct module *mops_owner; void *priv; }; @@ -230,18 +232,30 @@ struct fpga_manager *fpga_mgr_get(struct device *dev); void fpga_mgr_put(struct fpga_manager *mgr); +#define fpga_mgr_register_full(parent, info) \ + __fpga_mgr_register_full(parent, info, THIS_MODULE) struct fpga_manager * -fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +__fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner); +#define fpga_mgr_register(parent, name, mops, priv) \ + __fpga_mgr_register(parent, name, mops, priv, THIS_MODULE) struct fpga_manager * -fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv); +__fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, struct module *owner); + void fpga_mgr_unregister(struct fpga_manager *mgr); +#define devm_fpga_mgr_register_full(parent, info) \ + __devm_fpga_mgr_register_full(parent, info, THIS_MODULE) struct fpga_manager * -devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +__devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner); +#define devm_fpga_mgr_register(parent, name, mops, priv) \ + __devm_fpga_mgr_register(parent, name, mops, priv, THIS_MODULE) struct fpga_manager * -devm_fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv); +__devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, + struct module *owner); #endif /*_LINUX_FPGA_MGR_H */ diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 9d4d32909340a..5fbc05fe70a6b 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -36,6 +36,7 @@ struct fpga_region_info { * @mgr: FPGA manager * @info: FPGA image info * @compat_id: FPGA region id for compatibility check. + * @ops_owner: module containing the get_bridges function * @priv: private data * @get_bridges: optional function to get bridges to a list */ @@ -46,6 +47,7 @@ struct fpga_region { struct fpga_manager *mgr; struct fpga_image_info *info; struct fpga_compat_id *compat_id; + struct module *ops_owner; void *priv; int (*get_bridges)(struct fpga_region *region); }; @@ -58,12 +60,17 @@ fpga_region_class_find(struct device *start, const void *data, int fpga_region_program_fpga(struct fpga_region *region); +#define fpga_region_register_full(parent, info) \ + __fpga_region_register_full(parent, info, THIS_MODULE) struct fpga_region * -fpga_region_register_full(struct device *parent, const struct fpga_region_info *info); +__fpga_region_register_full(struct device *parent, const struct fpga_region_info *info, + struct module *owner); +#define fpga_region_register(parent, mgr, get_bridges) \ + __fpga_region_register(parent, mgr, get_bridges, THIS_MODULE) struct fpga_region * -fpga_region_register(struct device *parent, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); +__fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *), struct module *owner); void fpga_region_unregister(struct fpga_region *region); #endif /* _FPGA_REGION_H */ diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h index 9a9b88962c296..2b85fe9e7f9a7 100644 --- a/include/linux/framer/framer.h +++ b/include/linux/framer/framer.h @@ -181,12 +181,12 @@ static inline int framer_notifier_unregister(struct framer *framer, return -ENOSYS; } -struct framer *framer_get(struct device *dev, const char *con_id) +static inline struct framer *framer_get(struct device *dev, const char *con_id) { return ERR_PTR(-ENOSYS); } -void framer_put(struct device *dev, struct framer *framer) +static inline void framer_put(struct device *dev, struct framer *framer) { } diff --git a/include/linux/fs.h b/include/linux/fs.h index 1fbc72c5f112c..10e32c8ef1e9c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -2158,7 +2159,7 @@ struct super_operations { #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); - struct dquot **(*get_dquots)(struct inode *); + struct dquot __rcu **(*get_dquots)(struct inode *); #endif long (*nr_cached_objects)(struct super_block *, struct shrink_control *); @@ -3259,13 +3260,16 @@ extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { - struct xarray xa; - u32 next_offset; + struct maple_tree mt; + unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); +int simple_offset_empty(struct dentry *dentry); +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, @@ -3281,6 +3285,15 @@ extern int generic_check_addressable(unsigned, u64); extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); +static inline bool sb_has_encoding(const struct super_block *sb) +{ +#if IS_ENABLED(CONFIG_UNICODE) + return !!sb->s_encoding; +#else + return false; +#endif +} + int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 1b6053da8754e..495ebf5f2cb6d 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -2,6 +2,8 @@ #ifndef __LINUX_GFP_TYPES_H #define __LINUX_GFP_TYPES_H +#include + /* The typedef is in types.h but we want the documentation here */ #if 0 /** diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h index 6c75c8bd44a0b..1a14e239221f7 100644 --- a/include/linux/gpio/property.h +++ b/include/linux/gpio/property.h @@ -2,7 +2,6 @@ #ifndef __LINUX_GPIO_PROPERTY_H #define __LINUX_GPIO_PROPERTY_H -#include /* for GPIO_* flags */ #include #define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6ef0557b4bff8..96ceb4095425e 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -832,6 +832,7 @@ struct vmbus_gpadl { u32 gpadl_handle; u32 size; void *buffer; + bool decrypted; }; struct vmbus_channel { diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 83c4d060a5596..b69771a2e4e74 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -5145,7 +5145,7 @@ static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, info_len += 1; return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len <= len; + fixed + prof->sta_info_len - 1 <= len; } /** diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h deleted file mode 100644 index b7904992d5619..0000000000000 --- a/include/linux/iio/adc/adi-axi-adc.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Analog Devices Generic AXI ADC IP core driver/library - * Link: https://wiki.analog.com/resources/fpga/docs/axi_adc_ip - * - * Copyright 2012-2020 Analog Devices Inc. - */ -#ifndef __ADI_AXI_ADC_H__ -#define __ADI_AXI_ADC_H__ - -struct device; -struct iio_chan_spec; - -/** - * struct adi_axi_adc_chip_info - Chip specific information - * @name Chip name - * @id Chip ID (usually product ID) - * @channels Channel specifications of type @struct iio_chan_spec - * @num_channels Number of @channels - * @scale_table Supported scales by the chip; tuples of 2 ints - * @num_scales Number of scales in the table - * @max_rate Maximum sampling rate supported by the device - */ -struct adi_axi_adc_chip_info { - const char *name; - unsigned int id; - - const struct iio_chan_spec *channels; - unsigned int num_channels; - - const unsigned int (*scale_table)[2]; - int num_scales; - - unsigned long max_rate; -}; - -/** - * struct adi_axi_adc_conv - data of the ADC attached to the AXI ADC - * @chip_info chip info details for the client ADC - * @preenable_setup op to run in the client before enabling the AXI ADC - * @reg_access IIO debugfs_reg_access hook for the client ADC - * @read_raw IIO read_raw hook for the client ADC - * @write_raw IIO write_raw hook for the client ADC - * @read_avail IIO read_avail hook for the client ADC - */ -struct adi_axi_adc_conv { - const struct adi_axi_adc_chip_info *chip_info; - - int (*preenable_setup)(struct adi_axi_adc_conv *conv); - int (*reg_access)(struct adi_axi_adc_conv *conv, unsigned int reg, - unsigned int writeval, unsigned int *readval); - int (*read_raw)(struct adi_axi_adc_conv *conv, - struct iio_chan_spec const *chan, - int *val, int *val2, long mask); - int (*write_raw)(struct adi_axi_adc_conv *conv, - struct iio_chan_spec const *chan, - int val, int val2, long mask); - int (*read_avail)(struct adi_axi_adc_conv *conv, - struct iio_chan_spec const *chan, - const int **val, int *type, int *length, long mask); -}; - -struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev, - size_t sizeof_priv); - -void *adi_axi_adc_conv_priv(struct adi_axi_adc_conv *conv); - -#endif diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h new file mode 100644 index 0000000000000..a6d79381866ec --- /dev/null +++ b/include/linux/iio/backend.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _IIO_BACKEND_H_ +#define _IIO_BACKEND_H_ + +#include + +struct fwnode_handle; +struct iio_backend; +struct device; +struct iio_dev; + +enum iio_backend_data_type { + IIO_BACKEND_TWOS_COMPLEMENT, + IIO_BACKEND_OFFSET_BINARY, + IIO_BACKEND_DATA_TYPE_MAX +}; + +/** + * struct iio_backend_data_fmt - Backend data format + * @type: Data type. + * @sign_extend: Bool to tell if the data is sign extended. + * @enable: Enable/Disable the data format module. If disabled, + * not formatting will happen. + */ +struct iio_backend_data_fmt { + enum iio_backend_data_type type; + bool sign_extend; + bool enable; +}; + +/** + * struct iio_backend_ops - operations structure for an iio_backend + * @enable: Enable backend. + * @disable: Disable backend. + * @chan_enable: Enable one channel. + * @chan_disable: Disable one channel. + * @data_format_set: Configure the data format for a specific channel. + * @request_buffer: Request an IIO buffer. + * @free_buffer: Free an IIO buffer. + **/ +struct iio_backend_ops { + int (*enable)(struct iio_backend *back); + void (*disable)(struct iio_backend *back); + int (*chan_enable)(struct iio_backend *back, unsigned int chan); + int (*chan_disable)(struct iio_backend *back, unsigned int chan); + int (*data_format_set)(struct iio_backend *back, unsigned int chan, + const struct iio_backend_data_fmt *data); + struct iio_buffer *(*request_buffer)(struct iio_backend *back, + struct iio_dev *indio_dev); + void (*free_buffer)(struct iio_backend *back, + struct iio_buffer *buffer); +}; + +int iio_backend_chan_enable(struct iio_backend *back, unsigned int chan); +int iio_backend_chan_disable(struct iio_backend *back, unsigned int chan); +int devm_iio_backend_enable(struct device *dev, struct iio_backend *back); +int iio_backend_data_format_set(struct iio_backend *back, unsigned int chan, + const struct iio_backend_data_fmt *data); +int devm_iio_backend_request_buffer(struct device *dev, + struct iio_backend *back, + struct iio_dev *indio_dev); + +void *iio_backend_get_priv(const struct iio_backend *conv); +struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name); +struct iio_backend * +__devm_iio_backend_get_from_fwnode_lookup(struct device *dev, + struct fwnode_handle *fwnode); + +int devm_iio_backend_register(struct device *dev, + const struct iio_backend_ops *ops, void *priv); + +#endif diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h index 5c355be898149..cbb8ba957fade 100644 --- a/include/linux/iio/buffer-dmaengine.h +++ b/include/linux/iio/buffer-dmaengine.h @@ -10,6 +10,9 @@ struct iio_dev; struct device; +struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, + const char *channel); +void iio_dmaengine_buffer_free(struct iio_buffer *buffer); int devm_iio_dmaengine_buffer_setup(struct device *dev, struct iio_dev *indio_dev, const char *channel); diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 33f21bd85dbf2..f3196f82fd8a1 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -178,6 +178,12 @@ struct rapl_package { struct rapl_if_priv *priv; }; +struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv, + bool id_is_cpu); +struct rapl_package *rapl_add_package_cpuslocked(int id, struct rapl_if_priv *priv, + bool id_is_cpu); +void rapl_remove_package_cpuslocked(struct rapl_package *rp); + struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu); struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu); void rapl_remove_package(struct rapl_package *rp); diff --git a/include/linux/intel_tcc.h b/include/linux/intel_tcc.h index f422612c28d6b..8ff8eabb4a987 100644 --- a/include/linux/intel_tcc.h +++ b/include/linux/intel_tcc.h @@ -13,6 +13,6 @@ int intel_tcc_get_tjmax(int cpu); int intel_tcc_get_offset(int cpu); int intel_tcc_set_offset(int cpu, int offset); -int intel_tcc_get_temp(int cpu, bool pkg); +int intel_tcc_get_temp(int cpu, int *temp, bool pkg); #endif /* __INTEL_TCC_H__ */ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 76121c2bb4f82..5c9bdd3ffccc8 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -67,6 +67,8 @@ * later. * IRQF_NO_DEBUG - Exclude from runnaway detection for IPI and similar handlers, * depends on IRQF_PERCPU. + * IRQF_COND_ONESHOT - Agree to do IRQF_ONESHOT if already set for a shared + * interrupt. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 @@ -82,6 +84,7 @@ #define IRQF_COND_SUSPEND 0x00040000 #define IRQF_NO_AUTOEN 0x00080000 #define IRQF_NO_DEBUG 0x00100000 +#define IRQF_COND_ONESHOT 0x00200000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 854ad67a5f70e..73de1f6f0ab11 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -281,7 +281,6 @@ struct io_ring_ctx { struct io_submit_state submit_state; - struct io_buffer_list *io_bl; struct xarray io_bl_xa; struct io_hash_table cancel_table_locked; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5e27cb3a3be99..b58f15b914abc 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -487,6 +487,7 @@ struct iommu_ops { struct module *owner; struct iommu_domain *identity_domain; struct iommu_domain *blocked_domain; + struct iommu_domain *release_domain; struct iommu_domain *default_domain; }; @@ -1460,7 +1461,7 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle); static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { - return NULL; + return ERR_PTR(-ENODEV); } static inline void iommu_sva_unbind_device(struct iommu_sva *handle) diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e8240cf2611ad..e02b71e3fd6aa 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -128,6 +128,9 @@ extern int mq_init_ns(struct ipc_namespace *ns); static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; } #endif +extern struct ipc_namespace *get_ipc_ns_exported(struct ipc_namespace *ns); +extern struct ipc_namespace *show_init_ipc_ns(void); + #if defined(CONFIG_IPC_NS) extern struct ipc_namespace *copy_ipcs(unsigned long flags, struct user_namespace *user_ns, struct ipc_namespace *ns); diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 147feebd508ca..3f003d5fde534 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -114,7 +114,7 @@ do { \ # define lockdep_softirq_enter() do { } while (0) # define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false -# define lockdep_hrtimer_exit(__context) do { } while (0) +# define lockdep_hrtimer_exit(__context) do { (void)(__context); } while (0) # define lockdep_posixtimer_enter() do { } while (0) # define lockdep_posixtimer_exit() do { } while (0) # define lockdep_irq_work_enter(__work) do { } while (0) diff --git a/include/linux/kcov.h b/include/linux/kcov.h index b851ba415e03f..75a2fb8b16c32 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -21,6 +21,8 @@ enum kcov_mode { KCOV_MODE_TRACE_PC = 2, /* Collecting comparison operands mode. */ KCOV_MODE_TRACE_CMP = 3, + /* The process owns a KCOV remote reference. */ + KCOV_MODE_REMOTE = 4, }; #define KCOV_IN_CTXSW (1 << 30) @@ -55,21 +57,47 @@ static inline void kcov_remote_start_usb(u64 id) /* * The softirq flavor of kcov_remote_*() functions is introduced as a temporary - * work around for kcov's lack of nested remote coverage sections support in - * task context. Adding support for nested sections is tracked in: - * https://bugzilla.kernel.org/show_bug.cgi?id=210337 + * workaround for KCOV's lack of nested remote coverage sections support. + * + * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337. + * + * kcov_remote_start_usb_softirq(): + * + * 1. Only collects coverage when called in the softirq context. This allows + * avoiding nested remote coverage collection sections in the task context. + * For example, USB/IP calls usb_hcd_giveback_urb() in the task context + * within an existing remote coverage collection section. Thus, KCOV should + * not attempt to start collecting coverage within the coverage collection + * section in __usb_hcd_giveback_urb() in this case. + * + * 2. Disables interrupts for the duration of the coverage collection section. + * This allows avoiding nested remote coverage collection sections in the + * softirq context (a softirq might occur during the execution of a work in + * the BH workqueue, which runs with in_serving_softirq() > 0). + * For example, usb_giveback_urb_bh() runs in the BH workqueue with + * interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in + * the middle of its remote coverage collection section, and the interrupt + * handler might invoke __usb_hcd_giveback_urb() again. */ -static inline void kcov_remote_start_usb_softirq(u64 id) +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) { - if (in_serving_softirq()) + unsigned long flags = 0; + + if (in_serving_softirq()) { + local_irq_save(flags); kcov_remote_start_usb(id); + } + + return flags; } -static inline void kcov_remote_stop_softirq(void) +static inline void kcov_remote_stop_softirq(unsigned long flags) { - if (in_serving_softirq()) + if (in_serving_softirq()) { kcov_remote_stop(); + local_irq_restore(flags); + } } #ifdef CONFIG_64BIT @@ -103,8 +131,11 @@ static inline u64 kcov_common_handle(void) } static inline void kcov_remote_start_common(u64 id) {} static inline void kcov_remote_start_usb(u64 id) {} -static inline void kcov_remote_start_usb_softirq(u64 id) {} -static inline void kcov_remote_stop_softirq(void) {} +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) +{ + return 0; +} +static inline void kcov_remote_stop_softirq(unsigned long flags) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 99aaa050ccb76..e857a150babc6 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -223,6 +223,8 @@ struct kernfs_node { unsigned short flags; umode_t mode; struct kernfs_iattrs *iattr; + + struct rcu_head rcu; }; /* diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 400cb6c02176e..9d2ec5237dc06 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -502,10 +502,8 @@ static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; } extern bool kexec_file_dbg_print; -#define kexec_dprintk(fmt, ...) \ - printk("%s" fmt, \ - kexec_file_dbg_print ? KERN_INFO : KERN_DEBUG, \ - ##__VA_ARGS__) +#define kexec_dprintk(fmt, arg...) \ + do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0) #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 0ff44d6633e33..5fcbc254d1864 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -378,11 +378,15 @@ static inline void wait_for_kprobe_optimizer(void) { } extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs); extern int arch_prepare_kprobe_ftrace(struct kprobe *p); +/* Set when ftrace has been killed: kprobes on ftrace must be disabled for safety */ +extern bool kprobe_ftrace_disabled __read_mostly; +extern void kprobe_ftrace_kill(void); #else static inline int arch_prepare_kprobe_ftrace(struct kprobe *p) { return -EINVAL; } +static inline void kprobe_ftrace_kill(void) {} #endif /* CONFIG_KPROBES_ON_FTRACE */ /* Get the kprobe at this addr (if any) - called with preemption disabled */ @@ -495,6 +499,9 @@ static inline void kprobe_flush_task(struct task_struct *tk) static inline void kprobe_free_init_mem(void) { } +static inline void kprobe_ftrace_kill(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -EOPNOTSUPP; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 401348e9f92b4..f4692ec361e1b 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -33,16 +33,27 @@ void __ksm_exit(struct mm_struct *mm); */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) -extern unsigned long ksm_zero_pages; +extern atomic_long_t ksm_zero_pages; + +static inline void ksm_map_zero_page(struct mm_struct *mm) +{ + atomic_long_inc(&ksm_zero_pages); + atomic_long_inc(&mm->ksm_zero_pages); +} static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { - ksm_zero_pages--; - mm->ksm_zero_pages--; + atomic_long_dec(&ksm_zero_pages); + atomic_long_dec(&mm->ksm_zero_pages); } } +static inline long mm_ksm_zero_pages(struct mm_struct *mm) +{ + return atomic_long_read(&mm->ksm_zero_pages); +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { int ret; @@ -59,6 +70,14 @@ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) return 0; } +static inline int ksm_execve(struct mm_struct *mm) +{ + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + return __ksm_enter(mm); + + return 0; +} + static inline void ksm_exit(struct mm_struct *mm) { if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) @@ -107,6 +126,11 @@ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) return 0; } +static inline int ksm_execve(struct mm_struct *mm) +{ + return 0; +} + static inline void ksm_exit(struct mm_struct *mm) { } diff --git a/include/linux/libata.h b/include/linux/libata.h index 26d68115afb82..324d792e7c786 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -107,6 +107,7 @@ enum { ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 20), /* Priority cmds sent to dev */ ATA_DFLAG_CDL_ENABLED = (1 << 21), /* cmd duration limits is enabled */ + ATA_DFLAG_RESUMING = (1 << 22), /* Device is resuming */ ATA_DFLAG_DETACH = (1 << 24), ATA_DFLAG_DETACHED = (1 << 25), ATA_DFLAG_DA = (1 << 26), /* device supports Device Attention */ diff --git a/include/linux/lsm/apparmor.h b/include/linux/lsm/apparmor.h new file mode 100644 index 0000000000000..8ff1cd899a201 --- /dev/null +++ b/include/linux/lsm/apparmor.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * AppArmor presents a single u32 value which is known as a secid. + */ +#ifndef __LINUX_LSM_APPARMOR_H +#define __LINUX_LSM_APPARMOR_H + +struct aa_label; + +struct lsmblob_apparmor { +#ifdef CONFIG_SECURITY_APPARMOR + struct aa_label *label; +#endif +}; + +#endif /* ! __LINUX_LSM_APPARMOR_H */ diff --git a/include/linux/lsm/bpf.h b/include/linux/lsm/bpf.h new file mode 100644 index 0000000000000..48abdcd82ded2 --- /dev/null +++ b/include/linux/lsm/bpf.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * BPF may present a single u32 value. + */ +#ifndef __LINUX_LSM_BPF_H +#define __LINUX_LSM_BPF_H +#include + +struct lsmblob_bpf { +#ifdef CONFIG_BPF_LSM + u32 secid; +#endif +}; + +#endif /* ! __LINUX_LSM_BPF_H */ diff --git a/include/linux/lsm/selinux.h b/include/linux/lsm/selinux.h new file mode 100644 index 0000000000000..fd16456b36ac2 --- /dev/null +++ b/include/linux/lsm/selinux.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * SELinux presents a single u32 value which is known as a secid. + */ +#ifndef __LINUX_LSM_SELINUX_H +#define __LINUX_LSM_SELINUX_H +#include + +struct lsmblob_selinux { +#ifdef CONFIG_SECURITY_SELINUX + u32 secid; +#endif +}; + +#endif /* ! __LINUX_LSM_SELINUX_H */ diff --git a/include/linux/lsm/smack.h b/include/linux/lsm/smack.h new file mode 100644 index 0000000000000..2018f288302f4 --- /dev/null +++ b/include/linux/lsm/smack.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Linux Security Module interface to other subsystems. + * Smack presents a pointer into the global Smack label list. + */ +#ifndef __LINUX_LSM_SMACK_H +#define __LINUX_LSM_SMACK_H + +struct smack_known; + +struct lsmblob_smack { +#ifdef CONFIG_SECURITY_SMACK + struct smack_known *skp; +#endif +}; + +#endif /* ! __LINUX_LSM_SMACK_H */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 76458b6d53da7..57b35199edea4 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -83,7 +83,7 @@ LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, - void **ctx, u32 *ctxlen) + struct lsmcontext *cp) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) @@ -161,7 +161,8 @@ LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) -LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, inode_getlsmblob, struct inode *inode, + struct lsmblob *blob) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, const char *name) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, @@ -197,6 +198,8 @@ LSM_HOOK(int, 0, cred_prepare, struct cred *new, const struct cred *old, LSM_HOOK(void, LSM_RET_VOID, cred_transfer, struct cred *new, const struct cred *old) LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, cred_getlsmblob, const struct cred *c, + struct lsmblob *blob) LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid) LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode) LSM_HOOK(int, 0, kernel_module_request, char *kmod_name) @@ -215,9 +218,9 @@ LSM_HOOK(int, 0, task_fix_setgroups, struct cred *new, const struct cred * old) LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) -LSM_HOOK(void, LSM_RET_VOID, current_getsecid_subj, u32 *secid) -LSM_HOOK(void, LSM_RET_VOID, task_getsecid_obj, - struct task_struct *p, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, current_getlsmblob_subj, struct lsmblob *blob) +LSM_HOOK(void, LSM_RET_VOID, task_getlsmblob_obj, + struct task_struct *p, struct lsmblob *blob) LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) LSM_HOOK(int, 0, task_setioprio, struct task_struct *p, int ioprio) LSM_HOOK(int, 0, task_getioprio, struct task_struct *p) @@ -236,8 +239,8 @@ LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p, struct inode *inode) LSM_HOOK(int, 0, userns_create, const struct cred *cred) LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag) -LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp, - u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, ipc_getlsmblob, struct kern_ipc_perm *ipcp, + struct lsmblob *blob) LSM_HOOK(int, 0, msg_msg_alloc_security, struct msg_msg *msg) LSM_HOOK(void, LSM_RET_VOID, msg_msg_free_security, struct msg_msg *msg) LSM_HOOK(int, 0, msg_queue_alloc_security, struct kern_ipc_perm *perm) @@ -265,22 +268,23 @@ LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb) LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry, struct inode *inode) LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr, - struct lsm_ctx __user *ctx, size_t *size, u32 flags) + struct lsm_ctx __user *ctx, u32 *size, u32 flags) LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr, - struct lsm_ctx *ctx, size_t size, u32 flags) + struct lsm_ctx *ctx, u32 size, u32 flags) LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) -LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, - u32 *seclen) +LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, struct lsmcontext *cp) +LSM_HOOK(int, -EOPNOTSUPP, lsmblob_to_secctx, struct lsmblob *blob, + struct lsmcontext *cp) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) -LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) +LSM_HOOK(void, LSM_RET_VOID, release_secctx, struct lsmcontext *cp) LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen) LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) -LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, void **ctx, - u32 *ctxlen) +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, + struct lsmcontext *cp) #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) LSM_HOOK(int, 0, post_notification, const struct cred *w_cred, @@ -394,10 +398,11 @@ LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) #ifdef CONFIG_AUDIT LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, int lsmid, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) -LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule) -LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) +LSM_HOOK(int, 0, audit_rule_match, struct lsmblob *blob, u32 field, u32 op, + void *lsmrule, int lsmid) +LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule, int lsmid) #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL @@ -411,6 +416,8 @@ LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) +LSM_HOOK(int, 0, lock_kernel_down, const char *where, enum lockdown_reason level) + #ifdef CONFIG_PERF_EVENTS LSM_HOOK(int, 0, perf_event_open, struct perf_event_attr *attr, int type) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a2ade0ffe9e7d..da60bf1634474 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -47,12 +47,14 @@ struct security_hook_heads { * struct lsm_id - Identify a Linux Security Module. * @lsm: name of the LSM, must be approved by the LSM maintainers * @id: LSM ID number from uapi/linux/lsm.h + * @lsmblob: indicates the LSM has an entry in struct lsmblob * * Contains the information that identifies the LSM. */ struct lsm_id { const char *name; u64 id; + bool lsmblob; }; /* @@ -73,11 +75,16 @@ struct lsm_blob_sizes { int lbs_cred; int lbs_file; int lbs_inode; + int lbs_sock; int lbs_superblock; int lbs_ipc; + int lbs_key; int lbs_msg_msg; int lbs_task; int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ + int lbs_mnt_opts; + bool lbs_secmark; /* expressed desire for secmark use */ + bool lbs_netlabel; /* expressed desire for netlabel use */ }; /** @@ -151,5 +158,6 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; __aligned(sizeof(unsigned long)) extern int lsm_inode_alloc(struct inode *inode); +extern void *lsm_mnt_opts_alloc(gfp_t priority); #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index b3d63123b945b..a53ad4dabd7e8 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -171,6 +171,7 @@ enum maple_type { #define MT_FLAGS_LOCK_IRQ 0x100 #define MT_FLAGS_LOCK_BH 0x200 #define MT_FLAGS_LOCK_EXTERN 0x300 +#define MT_FLAGS_ALLOC_WRAPPED 0x0800 #define MAPLE_HEIGHT_MAX 31 @@ -319,6 +320,9 @@ int mtree_insert_range(struct maple_tree *mt, unsigned long first, int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); +int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); @@ -499,6 +503,9 @@ void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); +int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp); bool mas_nomem(struct ma_state *mas, gfp_t gfp); void mas_pause(struct ma_state *mas); diff --git a/include/linux/memory.h b/include/linux/memory.h index f53cfdaaaa416..939a16bd5cea1 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,8 +96,17 @@ int set_memory_block_size_order(unsigned int order); #define MEM_GOING_ONLINE (1<<3) #define MEM_CANCEL_ONLINE (1<<4) #define MEM_CANCEL_OFFLINE (1<<5) +#define MEM_PREPARE_ONLINE (1<<6) +#define MEM_FINISH_OFFLINE (1<<7) struct memory_notify { + /* + * The altmap_start_pfn and altmap_nr_pages fields are designated for + * specifying the altmap range and are exclusively intended for use in + * MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers. + */ + unsigned long altmap_start_pfn; + unsigned long altmap_nr_pages; unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7d20765834941..ee00015575aab 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -106,6 +106,22 @@ typedef int __bitwise mhp_t; * implies the node id (nid). */ #define MHP_NID_IS_MGID ((__force mhp_t)BIT(2)) +/* + * The hotplugged memory is completely inaccessible while the memory is + * offline. The memory provider will handle MEM_PREPARE_ONLINE / + * MEM_FINISH_OFFLINE notifications and make the memory accessible. + * + * This flag is only relevant when used along with MHP_MEMMAP_ON_MEMORY, + * because the altmap cannot be written (e.g., poisoned) when adding + * memory -- before it is set online. + * + * This allows for adding memory with an altmap that is not currently + * made available by a hypervisor. When onlining that memory, the + * hypervisor can be instructed to make that memory available, and + * the onlining phase will not require any memory allocations, which is + * helpful in low-memory situations. + */ +#define MHP_OFFLINE_INACCESSIBLE ((__force mhp_t)BIT(3)) /* * Extended parameters for memory hotplug: @@ -154,7 +170,7 @@ extern void adjust_present_page_count(struct page *page, long nr_pages); /* VM interface that may be used by firmware interface */ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, - struct zone *zone); + struct zone *zone, bool mhp_off_inaccessible); extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 744c830f4b132..9837f3e6fb958 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -25,6 +25,7 @@ struct vmem_altmap { unsigned long free; unsigned long align; unsigned long alloc; + bool inaccessible; }; /* diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 41f03b352401e..38d425a187fa3 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -861,6 +861,7 @@ struct mlx5_cmd_work_ent { void *context; int idx; struct completion handling; + struct completion slotted; struct completion done; struct mlx5_cmd *cmd; struct work_struct work; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 486b7492050c3..d2c27a7227bb4 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10265,9 +10265,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mfrl[0x1]; u8 regs_39_to_32[0x8]; - u8 regs_31_to_10[0x16]; + u8 regs_31_to_11[0x15]; u8 mtmp[0x1]; - u8 regs_8_to_0[0x9]; + u8 regs_9_to_0[0xa]; }; struct mlx5_ifc_mcam_access_reg_bits1 { diff --git a/include/linux/mm.h b/include/linux/mm.h index f5a97dec51694..adbab01e2e90a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1204,14 +1204,16 @@ static inline void page_mapcount_reset(struct page *page) * a large folio, it includes the number of times this page is mapped * as part of that folio. * - * The result is undefined for pages which cannot be mapped into userspace. - * For example SLAB or special types of pages. See function page_has_type(). - * They use this field in struct page differently. + * Will report 0 for pages which cannot be mapped into userspace, eg + * slab, page tables and similar. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; + /* Handle page_has_type() pages */ + if (mapcount < 0) + mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8b611e13153e6..1dfeed04bc3ce 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -960,7 +960,7 @@ struct mm_struct { * Represent how many empty pages are merged with kernel zero * pages when enabling KSM use_zero_pages. */ - unsigned long ksm_zero_pages; + atomic_long_t ksm_zero_pages; #endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN_WALKS_MMU struct { diff --git a/include/linux/mman.h b/include/linux/mman.h index dc7048824be81..bcb201ab7a412 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -162,6 +162,14 @@ calc_vm_flag_bits(unsigned long flags) unsigned long vm_commit_limit(void); +#ifndef arch_memory_deny_write_exec_supported +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return true; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported +#endif + /* * Denies creating a writable executable mapping or gaining executable permissions. * diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 5d3d15e97868a..66272fdce43d8 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -21,6 +21,7 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int debounce); int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, unsigned int debounce); +int mmc_gpiod_set_cd_config(struct mmc_host *host, unsigned long config); void mmc_gpio_set_cd_isr(struct mmc_host *host, irqreturn_t (*isr)(int irq, void *dev_id)); int mmc_gpio_set_cd_wake(struct mmc_host *host, bool on); diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index f458469c5ce5c..c49f5d981f864 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -690,6 +690,8 @@ struct x86_cpu_id { __u16 model; __u16 steppings; __u16 feature; /* bit index */ + /* Solely for kernel-internal use: DO NOT EXPORT to userspace! */ + __u16 flags; kernel_ulong_t driver_data; }; diff --git a/include/linux/module.h b/include/linux/module.h index 96bc462872c0c..382f2d73afa97 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -35,9 +35,11 @@ #define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN struct modversion_info { - unsigned long crc; - char name[MODULE_NAME_LEN]; -}; + /* Offset of the next modversion entry in relation to this one. */ + u32 next; + u32 crc; + char name[]; /* Flexible array member */ +} __packed; struct module; struct exception_table_entry; diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 001b2ce83832e..89b1e0ed98114 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -115,6 +115,14 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod); +#ifdef CONFIG_MODULES +void flush_module_init_free_work(void); +#else +static inline void flush_module_init_free_work(void) +{ +} +#endif + /* Any cleanup needed when module leaves. */ void module_arch_cleanup(struct module *mod); diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index badb4c1ac079e..5c19ead604996 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -169,7 +169,7 @@ struct spinand_op; struct spinand_device; -#define SPINAND_MAX_ID_LEN 4 +#define SPINAND_MAX_ID_LEN 5 /* * For erase, write and read operation, we got the following timings : * tBERS (erase) 1ms to 4ms diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 78a09af89e39b..dba428b3a87a5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2144,6 +2144,7 @@ struct net_device { struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; }; + unsigned long state; unsigned int flags; unsigned short hard_header_len; netdev_features_t features; @@ -2189,7 +2190,6 @@ struct net_device { * part of the usual set specified in Space.c. */ - unsigned long state; struct list_head dev_list; struct list_head napi_list; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index ef8d2d618d5b3..b20dcd4390915 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -15,6 +15,7 @@ #include #include +#include #include #include @@ -44,10 +45,9 @@ struct nfs4_acl { #define NFS4_MAXLABELLEN 2048 struct nfs4_label { - uint32_t lfs; - uint32_t pi; - u32 len; - char *label; + uint32_t lfs; + uint32_t pi; + struct lsmcontext lsmctx; }; typedef struct { char data[NFS4_VERIFIER_SIZE]; } nfs4_verifier; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f5ce7b1011461..1cf21bc472913 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -457,7 +457,7 @@ static inline void nfs4_label_free(struct nfs4_label *label) { #ifdef CONFIG_NFS_V4_SECURITY_LABEL if (label) { - kfree(label->label); + kfree(label->lsmctx.context); kfree(label); } #endif @@ -611,6 +611,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline bool nfs_have_writebacks(const struct inode *inode) diff --git a/include/linux/node.h b/include/linux/node.h index 25b66d705ee2e..dfc004e4bee74 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -34,6 +34,18 @@ struct access_coordinate { unsigned int write_latency; }; +/* + * ACCESS_COORDINATE_LOCAL correlates to ACCESS CLASS 0 + * - access_coordinate between target node and nearest initiator node + * ACCESS_COORDINATE_CPU correlates to ACCESS CLASS 1 + * - access_coordinate between target node and nearest CPU node + */ +enum access_coordinate_class { + ACCESS_COORDINATE_LOCAL, + ACCESS_COORDINATE_CPU, + ACCESS_COORDINATE_MAX +}; + enum cache_indexing { NODE_CACHE_DIRECT_MAP, NODE_CACHE_INDEXED, @@ -66,7 +78,7 @@ struct node_cache_attrs { #ifdef CONFIG_HMEM_REPORTING void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs); void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord, - unsigned access); + enum access_coordinate_class access); #else static inline void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs) @@ -75,7 +87,7 @@ static inline void node_add_cache(unsigned int nid, static inline void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord, - unsigned access) + enum access_coordinate_class access) { } #endif @@ -137,7 +149,7 @@ extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, - unsigned access); + enum access_coordinate_class access); #else static inline void node_dev_init(void) { diff --git a/include/linux/numa.h b/include/linux/numa.h index 915033a757315..1d43371fafd2f 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -36,12 +36,7 @@ int memory_add_physaddr_to_nid(u64 start); int phys_to_target_node(u64 start); #endif -#ifndef numa_fill_memblks -static inline int __init numa_fill_memblks(u64 start, u64 end) -{ - return NUMA_NO_MEMBLK; -} -#endif +int numa_fill_memblks(u64 start, u64 end); #else /* !CONFIG_NUMA */ static inline int numa_nearest_node(int node, unsigned int state) diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 3921fbed0b286..51421fdbb0bad 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -17,10 +17,12 @@ * build_OID_registry.pl to generate the data for look_up_OID(). */ enum OID { + OID_id_dsa_with_sha1, /* 1.2.840.10030.4.3 */ OID_id_dsa, /* 1.2.840.10040.4.1 */ OID_id_ecPublicKey, /* 1.2.840.10045.2.1 */ OID_id_prime192v1, /* 1.2.840.10045.3.1.1 */ OID_id_prime256v1, /* 1.2.840.10045.3.1.7 */ + OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */ OID_id_ecdsa_with_sha224, /* 1.2.840.10045.4.3.1 */ OID_id_ecdsa_with_sha256, /* 1.2.840.10045.4.3.2 */ OID_id_ecdsa_with_sha384, /* 1.2.840.10045.4.3.3 */ @@ -28,6 +30,7 @@ enum OID { /* PKCS#1 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-1(1)} */ OID_rsaEncryption, /* 1.2.840.113549.1.1.1 */ + OID_sha1WithRSAEncryption, /* 1.2.840.113549.1.1.5 */ OID_sha256WithRSAEncryption, /* 1.2.840.113549.1.1.11 */ OID_sha384WithRSAEncryption, /* 1.2.840.113549.1.1.12 */ OID_sha512WithRSAEncryption, /* 1.2.840.113549.1.1.13 */ @@ -64,6 +67,7 @@ enum OID { OID_PKU2U, /* 1.3.5.1.5.2.7 */ OID_Scram, /* 1.3.6.1.5.5.14 */ OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ + OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 7b5cf4a5cd191..ab4fa77516236 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -31,8 +31,10 @@ * credit to Christian Biere. */ #define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) -#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) -#define type_min(T) ((T)((T)-type_max(T)-(T)1)) +#define __type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) +#define type_max(t) __type_max(typeof(t)) +#define __type_min(T) ((T)((T)-type_max(T)-(T)1)) +#define type_min(t) __type_min(typeof(t)) /* * Avoids triggering -Wtype-limits compilation warning, @@ -130,10 +132,10 @@ static inline bool __must_check __must_check_overflow(bool overflow) #define __overflows_type_constexpr(x, T) ( \ is_unsigned_type(typeof(x)) ? \ - (x) > type_max(typeof(T)) : \ + (x) > type_max(T) : \ is_unsigned_type(typeof(T)) ? \ - (x) < 0 || (x) > type_max(typeof(T)) : \ - (x) < type_min(typeof(T)) || (x) > type_max(typeof(T))) + (x) < 0 || (x) > type_max(T) : \ + (x) < type_min(T) || (x) > type_max(T)) #define __overflows_type(x, T) ({ \ typeof(T) v = 0; \ @@ -319,7 +321,7 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * @count: Number of elements in the array; must be compile-time const. * @initializer: initializer expression (could be empty for no init). */ -#define _DEFINE_FLEX(type, name, member, count, initializer) \ +#define _DEFINE_FLEX(type, name, member, count, initializer...) \ _Static_assert(__builtin_constant_p(count), \ "onstack flex array members require compile-time const count"); \ union { \ @@ -329,8 +331,8 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) type *name = (type *)&name##_u /** - * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing - * flexible array member. + * DEFINE_RAW_FLEX() - Define an on-stack instance of structure with a trailing + * flexible array member, when it does not have a __counted_by annotation. * * @type: structure type name, including "struct" keyword. * @name: Name for a variable to define. @@ -341,7 +343,24 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * flexible array member. * Use __struct_size(@name) to get compile-time size of it afterwards. */ -#define DEFINE_FLEX(type, name, member, count) \ +#define DEFINE_RAW_FLEX(type, name, member, count) \ _DEFINE_FLEX(type, name, member, count, = {}) +/** + * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing + * flexible array member. + * + * @TYPE: structure type name, including "struct" keyword. + * @NAME: Name for a variable to define. + * @MEMBER: Name of the array member. + * @COUNTER: Name of the __counted_by member. + * @COUNT: Number of elements in the array; must be compile-time const. + * + * Define a zeroed, on-stack, instance of @TYPE structure with a trailing + * flexible array member. + * Use __struct_size(@NAME) to get compile-time size of it afterwards. + */ +#define DEFINE_FLEX(TYPE, NAME, MEMBER, COUNTER, COUNT) \ + _DEFINE_FLEX(TYPE, NAME, MEMBER, COUNT, = { .obj.COUNTER = COUNT, }) + #endif /* __LINUX_OVERFLOW_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 735cddc13d20e..68e9973cd62d9 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,7 +190,6 @@ enum pageflags { /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_error, - PG_hugetlb = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; @@ -432,30 +431,51 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) +#define FOLIO_TEST_FLAG_FALSE(name) \ +static inline bool folio_test_##name(const struct folio *folio) \ +{ return false; } +#define FOLIO_SET_FLAG_NOOP(name) \ +static inline void folio_set_##name(struct folio *folio) { } +#define FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void folio_clear_##name(struct folio *folio) { } +#define __FOLIO_SET_FLAG_NOOP(name) \ +static inline void __folio_set_##name(struct folio *folio) { } +#define __FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void __folio_clear_##name(struct folio *folio) { } +#define FOLIO_TEST_SET_FLAG_FALSE(name) \ +static inline bool folio_test_set_##name(struct folio *folio) \ +{ return false; } +#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ +static inline bool folio_test_clear_##name(struct folio *folio) \ +{ return false; } + +#define FOLIO_FLAG_FALSE(name) \ +FOLIO_TEST_FLAG_FALSE(name) \ +FOLIO_SET_FLAG_NOOP(name) \ +FOLIO_CLEAR_FLAG_NOOP(name) + #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ +FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_set_##lname(struct folio *folio) { } \ +FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_clear_##lname(struct folio *folio) { } \ +FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void __folio_clear_##lname(struct folio *folio) { } \ +__FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ -static inline bool folio_test_set_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ -static inline bool folio_test_clear_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ @@ -829,29 +849,6 @@ TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) #define PG_head_mask ((1UL << PG_head)) -#ifdef CONFIG_HUGETLB_PAGE -int PageHuge(struct page *page); -SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) -CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) - -/** - * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs - * @folio: The folio to test. - * - * Context: Any context. Caller should have a reference on the folio to - * prevent it from being turned into a tail page. - * Return: True for hugetlbfs folios, false for anon folios or folios - * belonging to other filesystems. - */ -static inline bool folio_test_hugetlb(struct folio *folio) -{ - return folio_test_large(folio) && - test_bit(PG_hugetlb, folio_flags(folio, 1)); -} -#else -TESTPAGEFLAG_FALSE(Huge, hugetlb) -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -907,34 +904,23 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif -/* - * Check if a page is currently marked HWPoisoned. Note that this check is - * best effort only and inherently racy: there is no way to synchronize with - * failing hardware. - */ -static inline bool is_page_hwpoison(struct page *page) -{ - if (PageHWPoison(page)) - return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); -} - /* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and - * low bits so that an underflow or overflow of page_mapcount() won't be + * low bits so that an underflow or overflow of _mapcount won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of page_mapcount */ +/* Reserve 0x0000007f to catch underflows of _mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 #define PG_table 0x00000200 #define PG_guard 0x00000400 +#define PG_hugetlb 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -951,35 +937,38 @@ static inline int page_has_type(struct page *page) return page_type_has_type(page->page_type); } +#define FOLIO_TYPE_OPS(lname, fname) \ +static __always_inline bool folio_test_##fname(const struct folio *folio)\ +{ \ + return folio_test_type(folio, PG_##lname); \ +} \ +static __always_inline void __folio_set_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ + folio->page.page_type &= ~PG_##lname; \ +} \ +static __always_inline void __folio_clear_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ + folio->page.page_type |= PG_##lname; \ +} + #define PAGE_TYPE_OPS(uname, lname, fname) \ +FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ -static __always_inline int folio_test_##fname(const struct folio *folio)\ -{ \ - return folio_test_type(folio, PG_##lname); \ -} \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ -static __always_inline void __folio_set_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ - folio->page.page_type &= ~PG_##lname; \ -} \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ -} \ -static __always_inline void __folio_clear_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ - folio->page.page_type |= PG_##lname; \ -} \ +} /* * PageBuddy() indicates that the page is free and in the buddy system @@ -1026,6 +1015,37 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) +#ifdef CONFIG_HUGETLB_PAGE +FOLIO_TYPE_OPS(hugetlb, hugetlb) +#else +FOLIO_TEST_FLAG_FALSE(hugetlb) +#endif + +/** + * PageHuge - Determine if the page belongs to hugetlbfs + * @page: The page to test. + * + * Context: Any context. + * Return: True for hugetlbfs pages, false for anon pages or pages + * belonging to other filesystems. + */ +static inline bool PageHuge(const struct page *page) +{ + return folio_test_hugetlb(page_folio(page)); +} + +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(struct page *page) +{ + if (PageHWPoison(page)) + return true; + return PageHuge(page) && PageHWPoison(compound_head(page)); +} + extern bool is_free_buddy_page(struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); @@ -1092,7 +1112,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_hugetlb | 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2df35e65557d2..5283b6193e7dc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -344,6 +344,19 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/* + * There are some parts of the kernel which assume that PMD entries + * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, + * limit the maximum allocation order to PMD size. I'm not aware of any + * assumptions about maximum order if THP are disabled, but 8 seems like + * a good order (that's 1MB if you're using 4kB pages) + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#else +#define MAX_PAGECACHE_ORDER 8 +#endif + /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The file. @@ -370,6 +383,14 @@ static inline bool mapping_large_folio_support(struct address_space *mapping) test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* Return the maximum folio size for this pagecache mapping, in bytes. */ +static inline size_t mapping_max_folio_size(struct address_space *mapping) +{ + if (mapping_large_folio_support(mapping)) + return PAGE_SIZE << MAX_PAGECACHE_ORDER; + return PAGE_SIZE; +} + static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -528,19 +549,6 @@ static inline void *detach_page_private(struct page *page) return folio_detach_private(page_folio(page)); } -/* - * There are some parts of the kernel which assume that PMD entries - * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, - * limit the maximum allocation order to PMD size. I'm not aware of any - * assumptions about maximum order if THP are disabled, but 8 seems like - * a good order (that's 1MB if you're using 4kB pages) - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER -#else -#define MAX_PAGECACHE_ORDER 8 -#endif - #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order); #else diff --git a/include/linux/pci.h b/include/linux/pci.h index 7ab0d13672daf..1f90649a6603a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -390,9 +390,9 @@ struct pci_dev { unsigned int d3hot_delay; /* D3hot->D0 transition time in ms */ unsigned int d3cold_delay; /* D3cold->D0 transition time in ms */ + u16 l1ss; /* L1SS Capability pointer */ #ifdef CONFIG_PCIEASPM struct pcie_link_state *link_state; /* ASPM link state */ - u16 l1ss; /* L1SS Capability pointer */ unsigned int ltr_path:1; /* Latency Tolerance Reporting supported from root to here */ #endif @@ -1841,6 +1841,7 @@ int pci_enable_link_state_locked(struct pci_dev *pdev, int state); void pcie_no_aspm(void); bool pcie_aspm_support_enabled(void); bool pcie_aspm_enabled(struct pci_dev *pdev); +bool pcie_aspm_capable(struct pci_dev *pdev); #else static inline int pci_disable_link_state(struct pci_dev *pdev, int state) { return 0; } @@ -1853,6 +1854,7 @@ static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state) static inline void pcie_no_aspm(void) { } static inline bool pcie_aspm_support_enabled(void) { return false; } static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; } +static inline bool pcie_aspm_capable(struct pci_dev *pdev) { return false; } #endif #ifdef CONFIG_PCIEAER @@ -2517,6 +2519,16 @@ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) return NULL; } +static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) +{ + /* + * error_state is set in pci_dev_set_io_state() using xchg/cmpxchg() + * and read w/o common lock. READ_ONCE() ensures compiler cannot cache + * the value (e.g. inside the loop in pci_dev_wait()). + */ + return READ_ONCE(dev->error_state) == pci_channel_io_perm_failure; +} + void pci_request_acs(void); bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags); bool pci_acs_path_enabled(struct pci_dev *start, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a0c75e467df36..5bfa57a5f7340 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2686,8 +2686,10 @@ #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_HDA_HSW_0 0x0a0c +#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 #define PCI_DEVICE_ID_INTEL_HDA_HSW_2 0x0c0c #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 +#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe #define PCI_DEVICE_ID_INTEL_HDA_HSW_3 0x0d0c #define PCI_DEVICE_ID_INTEL_HDA_BYT 0x0f04 #define PCI_DEVICE_ID_INTEL_SST_BYT 0x0f28 diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d2a15c0c6f8a9..513fea882192e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1612,6 +1612,12 @@ int perf_event_max_stack_handler(struct ctl_table *table, int write, #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 +#define PERF_SECURITY_MAX 4 + +static inline bool perf_paranoid_any(void) +{ + return sysctl_perf_event_paranoid >= PERF_SECURITY_MAX; +} static inline int perf_is_paranoid(void) { diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h index 70998e6dd6fdc..6ca51e0080ec0 100644 --- a/include/linux/phy/tegra/xusb.h +++ b/include/linux/phy/tegra/xusb.h @@ -26,6 +26,7 @@ void tegra_phy_xusb_utmi_pad_power_down(struct phy *phy); int tegra_phy_xusb_utmi_port_reset(struct phy *phy); int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, unsigned int port); +int tegra_xusb_padctl_get_port_number(struct phy *phy); int tegra_xusb_padctl_enable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy, enum usb_device_speed speed); int tegra_xusb_padctl_disable_phy_sleepwalk(struct tegra_xusb_padctl *padctl, struct phy *phy); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index b97c5e9820f97..0e18088af392d 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -233,6 +233,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, int pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); int pm_genpd_remove(struct generic_pm_domain *genpd); +struct device *dev_to_genpd_dev(struct device *dev); int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb); int dev_pm_genpd_remove_notifier(struct device *dev); @@ -280,6 +281,11 @@ static inline int pm_genpd_remove(struct generic_pm_domain *genpd) return -EOPNOTSUPP; } +static inline struct device *dev_to_genpd_dev(struct device *dev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state) { diff --git a/include/linux/poll.h b/include/linux/poll.h index a9e0e1c2d1f2f..d1ea4f3714a84 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -14,11 +14,7 @@ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ -#ifdef __clang__ -#define MAX_STACK_ALLOC 768 -#else #define MAX_STACK_ALLOC 832 -#endif #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC diff --git a/include/linux/printk.h b/include/linux/printk.h index 8ef499ab3c1ed..2fde40cc96778 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -126,7 +126,7 @@ struct va_format { #define no_printk(fmt, ...) \ ({ \ if (0) \ - printk(fmt, ##__VA_ARGS__); \ + _printk(fmt, ##__VA_ARGS__); \ 0; \ }) @@ -273,6 +273,8 @@ static inline void printk_trigger_flush(void) } #endif +bool this_cpu_in_panic(void); + #ifdef CONFIG_SMP extern int __printk_cpu_sync_try_get(void); extern void __printk_cpu_sync_wait(void); diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index fb724c65c77bc..5ce0cd76956e0 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -114,14 +114,14 @@ static inline int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, struct pse_control_status *status) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config) { - return -ENOTSUPP; + return -EOPNOTSUPP; } #endif diff --git a/include/linux/pwm.h b/include/linux/pwm.h index fcc2c4496f731..07af6910bdced 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -271,7 +271,6 @@ struct pwm_ops { * @id: unique number of this PWM chip * @npwm: number of PWMs controlled by this chip * @of_xlate: request a PWM device given a device tree PWM specifier - * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier * @atomic: can the driver's ->apply() be called in atomic context * @pwms: array of PWM devices allocated by the framework */ @@ -284,13 +283,17 @@ struct pwm_chip { struct pwm_device * (*of_xlate)(struct pwm_chip *chip, const struct of_phandle_args *args); - unsigned int of_pwm_n_cells; bool atomic; /* only used internally by the PWM framework */ struct pwm_device *pwms; }; +static inline struct device *pwmchip_parent(const struct pwm_chip *chip) +{ + return chip->dev; +} + #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state); diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 5d868505a94e4..6d92b68efbf6c 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -80,7 +80,7 @@ DECLARE_PER_CPU(u32, kstack_offset); if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - offset ^= (rand); \ + offset = ror32(offset, 5) ^ (rand); \ raw_cpu_write(kstack_offset, offset); \ } \ } while (0) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0746b1b0b6639..17d7ed5f3ae6e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -184,9 +184,9 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t); do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ - if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) && \ + if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ - rcu_trc_cmpxchg_need_qs((t), 0, TRC_NEED_QS_CHECKED); \ + rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ @@ -247,6 +247,37 @@ do { \ cond_resched(); \ } while (0) +/** + * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states + * @old_ts: jiffies at start of processing. + * + * This helper is for long-running softirq handlers, such as NAPI threads in + * networking. The caller should initialize the variable passed in as @old_ts + * at the beginning of the softirq handler. When invoked frequently, this macro + * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will + * provide both RCU and RCU-Tasks quiescent states. Note that this macro + * modifies its old_ts argument. + * + * Because regions of code that have disabled softirq act as RCU read-side + * critical sections, this macro should be invoked with softirq (and + * preemption) enabled. + * + * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would + * have more chance to invoke schedule() calls and provide necessary quiescent + * states. As a contrast, calling cond_resched() only won't achieve the same + * effect because cond_resched() does not provide RCU-Tasks quiescent states. + */ +#define rcu_softirq_qs_periodic(old_ts) \ +do { \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ + time_after(jiffies, (old_ts) + HZ / 10)) { \ + preempt_disable(); \ + rcu_softirq_qs(); \ + preempt_enable(); \ + (old_ts) = jiffies; \ + } \ +} while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. diff --git a/include/linux/regmap.h b/include/linux/regmap.h index c9182a47736ef..113261287af28 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1225,6 +1225,7 @@ int regmap_multi_reg_write_bypassed(struct regmap *map, int regmap_raw_write_async(struct regmap *map, unsigned int reg, const void *val, size_t val_len); int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_noinc_read(struct regmap *map, unsigned int reg, @@ -1734,6 +1735,13 @@ static inline int regmap_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_read_bypassed(struct regmap *map, unsigned int reg, + unsigned int *val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4660582a33022..ed180ca419dad 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -320,13 +320,13 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) static inline int devm_regulator_get_enable(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline int devm_regulator_get_enable_optional(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline struct regulator *__must_check diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 22a07c0900a41..f230a472ccd35 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -299,6 +299,8 @@ enum regulator_type { * @vsel_range_reg: Register for range selector when using pickable ranges * and ``regulator_map_*_voltage_*_pickable`` functions. * @vsel_range_mask: Mask for register bitfield used for range selector + * @range_applied_by_vsel: A flag to indicate that changes to vsel_range_reg + * are only effective after vsel_reg is written * @vsel_reg: Register for selector when using ``regulator_map_*_voltage_*`` * @vsel_mask: Mask for register bitfield used for selector * @vsel_step: Specify the resolution of selector stepping when setting @@ -389,6 +391,7 @@ struct regulator_desc { unsigned int vsel_range_reg; unsigned int vsel_range_mask; + bool range_applied_by_vsel; unsigned int vsel_reg; unsigned int vsel_mask; unsigned int vsel_step; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index fa802db216f94..dc5ae4e96aee0 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -98,7 +98,9 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); +typedef bool (*ring_buffer_cond_fn)(void *data); +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full); void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 35f3a4a8ceb1e..acf7e1a3f3def 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(struct folio *folio) /* * Using folio_mapping() is quite slow because of the actual call * instruction. - * We know that secretmem pages are not compound and LRU so we can + * We know that secretmem pages are not compound, so we can * save a couple of cycles here. */ - if (folio_test_large(folio) || !folio_test_lru(folio)) + if (folio_test_large(folio)) return false; mapping = (struct address_space *) diff --git a/include/linux/security.h b/include/linux/security.h index d0eb20f90b264..f1cf484c42fae 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -33,6 +33,10 @@ #include #include #include +#include +#include +#include +#include struct linux_binprm; struct cred; @@ -139,8 +143,31 @@ enum lockdown_reason { LOCKDOWN_CONFIDENTIALITY_MAX, }; +/* + * A "security context" is the text representation of + * the information used by LSMs. + * This structure contains the string, its length, and which LSM + * it is useful for. + */ +struct lsmcontext { + char *context; /* Provided by the module */ + u32 len; + int id; /* Identifies the module */ +}; + +/* + * Data exported by the security modules + */ +struct lsmblob { + struct lsmblob_selinux selinux; + struct lsmblob_smack smack; + struct lsmblob_apparmor apparmor; + struct lsmblob_bpf bpf; +}; + extern const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1]; extern u32 lsm_active_cnt; +extern u32 lsm_blob_cnt; extern const struct lsm_id *lsm_idlist[]; /* These functions are in security/commoncap.c */ @@ -256,6 +283,30 @@ static inline const char *kernel_load_data_id_str(enum kernel_load_data_id id) return kernel_load_data_str[id]; } +/** + * lsmblob_is_set - report if there is a value in the lsmblob + * @blob: Pointer to the exported LSM data + * + * Returns true if there is a value set, false otherwise + */ +static inline bool lsmblob_is_set(struct lsmblob *blob) +{ + const struct lsmblob empty = {}; + + return !!memcmp(blob, &empty, sizeof(*blob)); +} + +/** + * lsmblob_init - initialize a lsmblob structure + * @blob: Pointer to the data to initialize + * + * Set all secid for all modules to the specified value. + */ +static inline void lsmblob_init(struct lsmblob *blob) +{ + memset(blob, 0, sizeof(*blob)); +} + #ifdef CONFIG_SECURITY int call_blocking_lsm_notifier(enum lsm_event event, void *data); @@ -266,6 +317,8 @@ int unregister_blocking_lsm_notifier(struct notifier_block *nb); extern int security_init(void); extern int early_security_init(void); extern u64 lsm_name_to_attr(const char *name); +extern u64 lsm_name_to_id(const char *name); +extern const char *lsm_id_to_name(u64 id); /* Security operations */ int security_binder_set_context_mgr(const struct cred *mgr); @@ -327,8 +380,8 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb, int security_move_mount(const struct path *from_path, const struct path *to_path); int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, - const char **xattr_name, void **ctx, - u32 *ctxlen); + const char **xattr_name, + struct lsmcontext *lsmcxt); int security_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, @@ -385,7 +438,7 @@ int security_inode_getsecurity(struct mnt_idmap *idmap, void **buffer, bool alloc); int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags); int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); -void security_inode_getsecid(struct inode *inode, u32 *secid); +void security_inode_getlsmblob(struct inode *inode, struct lsmblob *blob); int security_inode_copy_up(struct dentry *src, struct cred **new); int security_inode_copy_up_xattr(const char *name); int security_kernfs_init_security(struct kernfs_node *kn_dir, @@ -416,6 +469,7 @@ void security_cred_free(struct cred *cred); int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp); void security_transfer_creds(struct cred *new, const struct cred *old); void security_cred_getsecid(const struct cred *c, u32 *secid); +void security_cred_getlsmblob(const struct cred *c, struct lsmblob *blob); int security_kernel_act_as(struct cred *new, u32 secid); int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_kernel_module_request(char *kmod_name); @@ -435,8 +489,8 @@ int security_task_fix_setgroups(struct cred *new, const struct cred *old); int security_task_setpgid(struct task_struct *p, pid_t pgid); int security_task_getpgid(struct task_struct *p); int security_task_getsid(struct task_struct *p); -void security_current_getsecid_subj(u32 *secid); -void security_task_getsecid_obj(struct task_struct *p, u32 *secid); +void security_current_getlsmblob_subj(struct lsmblob *blob); +void security_task_getlsmblob_obj(struct task_struct *p, struct lsmblob *blob); int security_task_setnice(struct task_struct *p, int nice); int security_task_setioprio(struct task_struct *p, int ioprio); int security_task_getioprio(struct task_struct *p); @@ -454,7 +508,7 @@ int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, void security_task_to_inode(struct task_struct *p, struct inode *inode); int security_create_user_ns(const struct cred *cred); int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag); -void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid); +void security_ipc_getlsmblob(struct kern_ipc_perm *ipcp, struct lsmblob *blob); int security_msg_msg_alloc(struct msg_msg *msg); void security_msg_msg_free(struct msg_msg *msg); int security_msg_queue_alloc(struct kern_ipc_perm *msq); @@ -478,23 +532,26 @@ int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter); void security_d_instantiate(struct dentry *dentry, struct inode *inode); int security_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, - size_t __user *size, u32 flags); + u32 __user *size, u32 flags); int security_setselfattr(unsigned int attr, struct lsm_ctx __user *ctx, - size_t size, u32 flags); + u32 size, u32 flags); int security_getprocattr(struct task_struct *p, int lsmid, const char *name, char **value); int security_setprocattr(int lsmid, const char *name, void *value, size_t size); int security_netlink_send(struct sock *sk, struct sk_buff *skb); int security_ismaclabel(const char *name); -int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); +int security_secid_to_secctx(u32 secid, struct lsmcontext *cp); +int security_lsmblob_to_secctx(struct lsmblob *blob, struct lsmcontext *cp, + int lsmid); int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid); -void security_release_secctx(char *secdata, u32 seclen); +void security_release_secctx(struct lsmcontext *cp); void security_inode_invalidate_secctx(struct inode *inode); int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen); int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen); -int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); +int security_inode_getsecctx(struct inode *inode, struct lsmcontext *cp); int security_locked_down(enum lockdown_reason what); -int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, size_t *uctx_len, +int security_lock_kernel_down(const char *where, enum lockdown_reason level); +int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags); #else /* CONFIG_SECURITY */ @@ -518,6 +575,16 @@ static inline u64 lsm_name_to_attr(const char *name) return LSM_ATTR_UNDEF; } +static inline u64 lsm_name_to_id(const char *name) +{ + return LSM_ID_UNDEF; +} + +static inline const char *lsm_id_to_name(u64 id) +{ + return NULL; +} + static inline void security_free_mnt_opts(void **mnt_opts) { } @@ -768,8 +835,7 @@ static inline int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, - void **ctx, - u32 *ctxlen) + struct lsmcontext *lsmcxt) { return -EOPNOTSUPP; } @@ -964,9 +1030,10 @@ static inline int security_inode_listsecurity(struct inode *inode, char *buffer, return 0; } -static inline void security_inode_getsecid(struct inode *inode, u32 *secid) +static inline void security_inode_getlsmblob(struct inode *inode, + struct lsmblob *blob) { - *secid = 0; + lsmblob_init(blob); } static inline int security_inode_copy_up(struct dentry *src, struct cred **new) @@ -1101,6 +1168,12 @@ static inline void security_cred_getsecid(const struct cred *c, u32 *secid) *secid = 0; } +static inline void security_cred_getlsmblob(const struct cred *c, + struct lsmblob *blob) +{ + lsmblob_init(blob); +} + static inline int security_kernel_act_as(struct cred *cred, u32 secid) { return 0; @@ -1178,14 +1251,15 @@ static inline int security_task_getsid(struct task_struct *p) return 0; } -static inline void security_current_getsecid_subj(u32 *secid) +static inline void security_current_getlsmblob_subj(struct lsmblob *blob) { - *secid = 0; + lsmblob_init(blob); } -static inline void security_task_getsecid_obj(struct task_struct *p, u32 *secid) +static inline void security_task_getlsmblob_obj(struct task_struct *p, + struct lsmblob *blob) { - *secid = 0; + lsmblob_init(blob); } static inline int security_task_setnice(struct task_struct *p, int nice) @@ -1261,9 +1335,10 @@ static inline int security_ipc_permission(struct kern_ipc_perm *ipcp, return 0; } -static inline void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) +static inline void security_ipc_getlsmblob(struct kern_ipc_perm *ipcp, + struct lsmblob *blob) { - *secid = 0; + lsmblob_init(blob); } static inline int security_msg_msg_alloc(struct msg_msg *msg) @@ -1397,7 +1472,13 @@ static inline int security_ismaclabel(const char *name) return 0; } -static inline int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +static inline int security_secid_to_secctx(u32 secid, struct lsmcontext *cp) +{ + return -EOPNOTSUPP; +} + +static inline int security_lsmblob_to_secctx(struct lsmblob *blob, + struct lsmcontext *cp, int lsmid) { return -EOPNOTSUPP; } @@ -1409,7 +1490,7 @@ static inline int security_secctx_to_secid(const char *secdata, return -EOPNOTSUPP; } -static inline void security_release_secctx(char *secdata, u32 seclen) +static inline void security_release_secctx(struct lsmcontext *cp) { } @@ -1425,7 +1506,8 @@ static inline int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 { return -EOPNOTSUPP; } -static inline int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +static inline int security_inode_getsecctx(struct inode *inode, + struct lsmcontext *cp) { return -EOPNOTSUPP; } @@ -1433,8 +1515,12 @@ static inline int security_locked_down(enum lockdown_reason what) { return 0; } +static inline int security_lock_kernel_down(const char *where, enum lockdown_reason level) +{ + return 0; +} static inline int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, - size_t *uctx_len, void *val, size_t val_len, + u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags) { return -EOPNOTSUPP; @@ -1988,15 +2074,17 @@ static inline int security_key_getsecurity(struct key *key, char **_buffer) #ifdef CONFIG_AUDIT #ifdef CONFIG_SECURITY -int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule); +int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + gfp_t gfp); int security_audit_rule_known(struct audit_krule *krule); -int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule); +int security_audit_rule_match(struct lsmblob *blob, u32 field, u32 op, + void *lsmrule); void security_audit_rule_free(void *lsmrule); #else static inline int security_audit_rule_init(u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) { return 0; } @@ -2006,8 +2094,8 @@ static inline int security_audit_rule_known(struct audit_krule *krule) return 0; } -static inline int security_audit_rule_match(u32 secid, u32 field, u32 op, - void *lsmrule) +static inline int security_audit_rule_match(struct lsmblob *blob, u32 field, + u32 op, void *lsmrule) { return 0; } @@ -2018,6 +2106,32 @@ static inline void security_audit_rule_free(void *lsmrule) #endif /* CONFIG_SECURITY */ #endif /* CONFIG_AUDIT */ +#if defined(CONFIG_IMA_LSM_RULES) && defined(CONFIG_SECURITY) +int ima_filter_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + int lsmid, gfp_t gfp); +int ima_filter_rule_match(struct lsmblob *blob, u32 field, u32 op, + void *lsmrule, int lsmid); +void ima_filter_rule_free(void *lsmrule, int lsmid); + +#else + +static inline int ima_filter_rule_init(u32 field, u32 op, char *rulestr, + void **lsmrule, int lsmid, gfp_t gfp) +{ + return 0; +} + +static inline int ima_filter_rule_match(struct lsmblob *blob, u32 field, u32 op, + void *lsmrule, int lsmid) +{ + return 0; +} + +static inline void ima_filter_rule_free(void *lsmrule, int lsmid) +{ } + +#endif /* defined(CONFIG_IMA_LSM_RULES) && defined(CONFIG_SECURITY) */ + #ifdef CONFIG_SECURITYFS extern struct dentry *securityfs_create_file(const char *name, umode_t mode, diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 55b1f3ba48ac1..f43143901ef71 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -470,6 +470,7 @@ struct uart_port { unsigned char iotype; /* io access style */ unsigned char quirks; /* internal quirks */ +#define UPIO_UNKNOWN ((unsigned char)~0U) /* UCHAR_MAX */ #define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ #define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ #define UPIO_MEM (SERIAL_IO_MEM) /* driver-specific */ @@ -786,7 +787,8 @@ enum UART_TX_FLAGS { if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ - if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ + if (!((flags) & UART_TX_NOSTOP) && pending == 0 && \ + __port->ops->tx_empty(__port)) \ __port->ops->stop_tx(__port); \ } \ \ @@ -959,6 +961,8 @@ int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); void uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); +int uart_read_port_properties(struct uart_port *port); +int uart_read_and_validate_port_properties(struct uart_port *port); bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 2caa6b86106aa..f0c6bf9828327 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -37,7 +37,7 @@ struct shmem_inode_info { unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */ atomic_t stop_eviction; /* hold when working on inode */ #ifdef CONFIG_TMPFS_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif struct inode vfs_inode; }; @@ -114,8 +114,17 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +#else +static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, + struct mm_struct *mm, unsigned long vm_flags) +{ + return false; +} +#endif + #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); #else diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2dde34c29203b..d4e53a5a262c7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -748,8 +748,6 @@ typedef unsigned char *sk_buff_data_t; * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by - * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in - * fragmentation management * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -870,10 +868,7 @@ struct sk_buff { struct llist_node ll_node; }; - union { - struct sock *sk; - int ip_defrag_offset; - }; + struct sock *sk; union { ktime_t tstamp; @@ -1174,15 +1169,6 @@ static inline bool skb_dst_is_noref(const struct sk_buff *skb) return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } -/** - * skb_rtable - Returns the skb &rtable - * @skb: buffer - */ -static inline struct rtable *skb_rtable(const struct sk_buff *skb) -{ - return (struct rtable *)skb_dst(skb); -} - /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. @@ -2642,6 +2628,8 @@ static inline void skb_put_u8(struct sk_buff *skb, u8 val) void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb->data -= len; skb->len += len; return skb->data; @@ -2650,6 +2638,8 @@ static inline void *__skb_push(struct sk_buff *skb, unsigned int len) void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) @@ -2674,6 +2664,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; @@ -2846,6 +2838,11 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header += offset; } +static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) +{ + return skb->inner_network_header > 0; +} + static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; @@ -2966,6 +2963,21 @@ static inline void skb_mac_header_rebuild(struct sk_buff *skb) } } +/* Move the full mac header up to current network_header. + * Leaves skb->data pointing at offset skb->mac_len into the mac_header. + * Must be provided the complete mac header length. + */ +static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -full_mac_len); + memmove(skb_mac_header(skb), old_mac, full_mac_len); + __skb_push(skb, full_mac_len - skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); @@ -3448,6 +3460,16 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) bool napi_pp_put_page(struct page *page, bool napi_safe); +static inline void +skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) +{ +#ifdef CONFIG_PAGE_POOL + if (skb->pp_recycle && napi_pp_put_page(page, napi_safe)) + return; +#endif + put_page(page); +} + static inline void napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) { diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd27998..a509caf823d61 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -461,10 +461,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/include/linux/slab.h b/include/linux/slab.h index b5f5ee8308d0f..34b32c59ce790 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -228,7 +228,7 @@ void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); -DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) +DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) /** * ksize - Report actual allocation size of associated object @@ -754,7 +754,7 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) __realloc_size(3); extern void kvfree(const void *addr); -DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T)) +DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); diff --git a/include/linux/smp.h b/include/linux/smp.h index e87520dc2959d..7a83fd2fccbe4 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -218,6 +218,8 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } static inline void wake_up_all_idle_cpus(void) { } +#define setup_max_cpus 0 + #ifdef CONFIG_UP_LATE_INIT extern void __init up_late_init(void); static inline void smp_init(void) { up_late_init(); } diff --git a/include/linux/soc/andes/irq.h b/include/linux/soc/andes/irq.h new file mode 100644 index 0000000000000..edc3182d6e661 --- /dev/null +++ b/include/linux/soc/andes/irq.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 Andes Technology Corporation + */ +#ifndef __ANDES_IRQ_H +#define __ANDES_IRQ_H + +/* Andes PMU irq number */ +#define ANDES_RV_IRQ_PMOVI 18 +#define ANDES_RV_IRQ_LAST ANDES_RV_IRQ_PMOVI +#define ANDES_SLI_CAUSE_BASE 256 + +/* Andes PMU related registers */ +#define ANDES_CSR_SLIE 0x9c4 +#define ANDES_CSR_SLIP 0x9c5 +#define ANDES_CSR_SCOUNTEROF 0x9d4 + +#endif /* __ANDES_IRQ_H */ diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 307961b41541a..317200cd3a603 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -50,11 +50,36 @@ static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, return 0; } +/* Deprecated. + * This is unsafe, unless caller checked user provided optlen. + * Prefer copy_safe_from_sockptr() instead. + */ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } +/** + * copy_safe_from_sockptr: copy a struct from sockptr + * @dst: Destination address, in kernel space. This buffer must be @ksize + * bytes long. + * @ksize: Size of @dst struct. + * @optval: Source address. (in user or kernel space) + * @optlen: Size of @optval data. + * + * Returns: + * * -EINVAL: @optlen < @ksize + * * -EFAULT: access to userspace failed. + * * 0 : @ksize bytes were copied + */ +static inline int copy_safe_from_sockptr(void *dst, size_t ksize, + sockptr_t optval, unsigned int optlen) +{ + if (optlen < ksize) + return -EINVAL; + return copy_from_sockptr(dst, optval, ksize); +} + static inline int copy_struct_from_sockptr(void *dst, size_t ksize, sockptr_t src, size_t usize) { diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index adcbb8f236000..bf0136891a0f2 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -30,6 +30,52 @@ typedef u32 depot_stack_handle_t; */ #define STACK_DEPOT_EXTRA_BITS 5 +#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8) + +#define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */ +#define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER)) +#define DEPOT_STACK_ALIGN 4 +#define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN) +#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \ + STACK_DEPOT_EXTRA_BITS) + +#ifdef CONFIG_STACKDEPOT +/* Compact structure that stores a reference to a stack. */ +union handle_parts { + depot_stack_handle_t handle; + struct { + u32 pool_index_plus_1 : DEPOT_POOL_INDEX_BITS; + u32 offset : DEPOT_OFFSET_BITS; + u32 extra : STACK_DEPOT_EXTRA_BITS; + }; +}; + +struct stack_record { + struct list_head hash_list; /* Links in the hash table */ + u32 hash; /* Hash in hash table */ + u32 size; /* Number of stored frames */ + union handle_parts handle; /* Constant after initialization */ + refcount_t count; + union { + unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */ + struct { + /* + * An important invariant of the implementation is to + * only place a stack record onto the freelist iff its + * refcount is zero. Because stack records with a zero + * refcount are never considered as valid, it is safe to + * union @entries and freelist management state below. + * Conversely, as soon as an entry is off the freelist + * and its refcount becomes non-zero, the below must not + * be accessed until being placed back on the freelist. + */ + struct list_head free_list; /* Links in the freelist */ + unsigned long rcu_state; /* RCU cookie */ + }; + }; +}; +#endif + typedef u32 depot_flags_t; /* diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dee5ad6e48c5a..c0d74f97fd187 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -117,7 +117,6 @@ struct stmmac_axi { #define EST_GCL 1024 struct stmmac_est { - struct mutex lock; int enable; u32 btr_reserve[2]; u32 btr_offset[2]; @@ -127,6 +126,7 @@ struct stmmac_est { u32 gcl_unaligned[EST_GCL]; u32 gcl[EST_GCL]; u32 gcl_size; + u32 max_sdu[MTL_MAX_TX_QUEUES]; }; struct stmmac_rxq_cfg { diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 5e9d1469c6fae..5321585c778fc 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -139,6 +139,7 @@ struct rpc_create_args { const char *servername; const char *nodename; const struct rpc_program *program; + struct rpc_stat *stats; u32 prognumber; /* overrides program->number */ u32 version; rpc_authflavor_t authflavor; diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 2d61987b35456..0c77ba488bbae 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -197,7 +197,7 @@ struct rpc_wait_queue { unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char nr; /* # tasks remaining for cookie */ - unsigned short qlen; /* total # tasks waiting in queue */ + unsigned int qlen; /* total # tasks waiting in queue */ struct rpc_timer timer_list; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) const char * name; diff --git a/include/linux/swapops.h b/include/linux/swapops.h index bff1e8d97de0e..925c84653af5e 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -390,6 +390,35 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) } #endif /* CONFIG_MIGRATION */ +#ifdef CONFIG_MEMORY_FAILURE + +/* + * Support for hardware poisoned pages + */ +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + BUG_ON(!PageLocked(page)); + return swp_entry(SWP_HWPOISON, page_to_pfn(page)); +} + +static inline int is_hwpoison_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_HWPOISON; +} + +#else + +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + return swp_entry(0, 0); +} + +static inline int is_hwpoison_entry(swp_entry_t swp) +{ + return 0; +} +#endif + typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) @@ -470,8 +499,9 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) /* * A pfn swap entry is a special type of swap entry that always has a pfn stored - * in the swap offset. They are used to represent unaddressable device memory - * and to restrict access to a page undergoing migration. + * in the swap offset. They can either be used to represent unaddressable device + * memory, to restrict access to a page undergoing migration or to represent a + * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { @@ -479,7 +509,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || - is_device_exclusive_entry(entry); + is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; @@ -548,35 +578,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd) } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ -#ifdef CONFIG_MEMORY_FAILURE - -/* - * Support for hardware poisoned pages - */ -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - BUG_ON(!PageLocked(page)); - return swp_entry(SWP_HWPOISON, page_to_pfn(page)); -} - -static inline int is_hwpoison_entry(swp_entry_t entry) -{ - return swp_type(entry) == SWP_HWPOISON; -} - -#else - -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - return swp_entry(0, 0); -} - -static inline int is_hwpoison_entry(swp_entry_t swp) -{ - return 0; -} -#endif - static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 77eb9b0e76850..e619ac10cd234 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -960,10 +960,10 @@ asmlinkage long sys_cachestat(unsigned int fd, struct cachestat __user *cstat, unsigned int flags); asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags); asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx, - size_t *size, __u32 flags); + u32 *size, u32 flags); asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx, - size_t size, __u32 flags); -asmlinkage long sys_lsm_list_modules(u64 *ids, size_t *size, u32 flags); + u32 size, u32 flags); +asmlinkage long sys_lsm_list_modules(u64 *ids, u32 *size, u32 flags); /* * Architecture-specific system calls diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index d68ff9b1247f9..fc6d0af56bb17 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -103,13 +103,16 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; - long wait_index; + atomic_t wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; cpumask_var_t started; + /* Set when the file is closed to prevent new waiters */ + bool closed; + /* it's true when current open file is snapshot */ bool snapshot; diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 7a5fe17b6bf9c..d03f746587167 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -62,6 +62,8 @@ struct eventfs_file; typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); +typedef void (*eventfs_release)(const char *name, void *data); + /** * struct eventfs_entry - dynamically created eventfs file call back handler * @name: Then name of the dynamic file in an eventfs directory @@ -72,6 +74,7 @@ typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, struct eventfs_entry { const char *name; eventfs_callback callback; + eventfs_release release; }; struct eventfs_inode; diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 7372124fbf90b..dd4b31ce6d5d4 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -154,6 +154,13 @@ struct serial_struct; * * Optional. Called under the @tty->termios_rwsem. May sleep. * + * @ldisc_ok: ``int ()(struct tty_struct *tty, int ldisc)`` + * + * This routine allows the @tty driver to decide if it can deal + * with a particular @ldisc. + * + * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. + * * @set_ldisc: ``void ()(struct tty_struct *tty)`` * * This routine allows the @tty driver to be notified when the device's @@ -372,6 +379,7 @@ struct tty_operations { void (*hangup)(struct tty_struct *tty); int (*break_ctl)(struct tty_struct *tty, int state); void (*flush_buffer)(struct tty_struct *tty); + int (*ldisc_ok)(struct tty_struct *tty, int ldisc); void (*set_ldisc)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, int timeout); void (*send_xchar)(struct tty_struct *tty, u8 ch); diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index ffe48e69b3f3a..457879938fc19 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -135,10 +135,11 @@ static inline void u64_stats_inc(u64_stats_t *p) p->v++; } -static inline void u64_stats_init(struct u64_stats_sync *syncp) -{ - seqcount_init(&syncp->seq); -} +#define u64_stats_init(syncp) \ + do { \ + struct u64_stats_sync *__s = (syncp); \ + seqcount_init(&__s->seq); \ + } while (0) static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { diff --git a/include/linux/udp.h b/include/linux/udp.h index d04188714dca1..00790bb5cbde6 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -105,7 +105,7 @@ struct udp_sock { #define udp_assign_bit(nr, sk, val) \ assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) @@ -140,6 +140,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -153,6 +171,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 6030a82356173..eeb7cd94bca0e 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -187,6 +187,8 @@ extern bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); struct ns_common *ns_get_owner(struct ns_common *ns); + +extern int unprivileged_userns_clone; #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 89b265bc6ec31..8b1a298204091 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -356,6 +356,7 @@ struct virqfd { wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; + struct work_struct flush_inject; struct virqfd **pvirqfd; }; @@ -363,5 +364,6 @@ int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), void *data, struct virqfd **pvirqfd, int fd); void vfio_virqfd_disable(struct virqfd **pvirqfd); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd); #endif /* VFIO_H */ diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 01fa15506286d..170fdee6339c7 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -16,6 +16,7 @@ * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol * @WWAN_PORT_XMMRPC: Control protocol for Intel XMM modems + * @WWAN_PORT_FASTBOOT: Fastboot protocol control * * @WWAN_PORT_MAX: Highest supported port types * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type @@ -28,6 +29,7 @@ enum wwan_port_type { WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, WWAN_PORT_XMMRPC, + WWAN_PORT_FASTBOOT, /* Add new port types above this line */ diff --git a/include/media/cec.h b/include/media/cec.h index d77982685116e..dc425cdc3da9e 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -260,6 +260,7 @@ struct cec_adapter { u16 phys_addr; bool needs_hpd; bool is_enabled; + bool is_claiming_log_addrs; bool is_configuring; bool must_reconfigure; bool is_configured; diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 2b6cd343ee9e0..4d95893c89846 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -225,6 +225,7 @@ enum media_pad_signal_type { * @graph_obj: Embedded structure containing the media object common data * @entity: Entity this pad belongs to * @index: Pad index in the entity pads array, numbered from 0 to n + * @num_links: Number of links connected to this pad * @sig_type: Type of the signal inside a media pad * @flags: Pad flags, as defined in * :ref:`include/uapi/linux/media.h ` @@ -236,6 +237,7 @@ struct media_pad { struct media_gobj graph_obj; /* must be first field in struct */ struct media_entity *entity; u16 index; + u16 num_links; enum media_pad_signal_type sig_type; unsigned long flags; diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 56719a26a46c3..bec8c3a1ed824 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -72,6 +72,10 @@ struct vb2_buffer; * argument to other ops in this structure. * @put_userptr: inform the allocator that a USERPTR buffer will no longer * be used. + * @prepare: called every time the buffer is passed from userspace to the + * driver, useful for cache synchronisation, optional. + * @finish: called every time the buffer is passed back from the driver + * to the userspace, also optional. * @attach_dmabuf: attach a shared &struct dma_buf for a hardware operation; * used for DMABUF memory types; dev is the alloc device * dbuf is the shared dma_buf; returns ERR_PTR() on failure; @@ -86,10 +90,6 @@ struct vb2_buffer; * dmabuf. * @unmap_dmabuf: releases access control to the dmabuf - allocator is notified * that this driver is done using the dmabuf for now. - * @prepare: called every time the buffer is passed from userspace to the - * driver, useful for cache synchronisation, optional. - * @finish: called every time the buffer is passed back from the driver - * to the userspace, also optional. * @vaddr: return a kernel virtual address to a given memory buffer * associated with the passed private structure or NULL if no * such mapping exists. @@ -484,7 +484,6 @@ struct vb2_buf_ops { * caller. For example, for V4L2, it should match * the types defined on &enum v4l2_buf_type. * @io_modes: supported io methods (see &enum vb2_io_modes). - * @alloc_devs: &struct device memory type/allocator-specific per-plane device * @dev: device to use for the default allocation context if the driver * doesn't fill in the @alloc_devs array. * @dma_attrs: DMA attributes to use for the DMA. @@ -553,6 +552,7 @@ struct vb2_buf_ops { * VIDIOC_REQBUFS will ensure at least @min_queued_buffers * buffers will be allocated. Note that VIDIOC_CREATE_BUFS will not * modify the requested buffer count. + * @alloc_devs: &struct device memory type/allocator-specific per-plane device */ /* * Private elements (won't appear at the uAPI book): @@ -577,6 +577,9 @@ struct vb2_buf_ops { * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for * buffers. Only set for capture queues if qbuf has not yet been * called since poll() needs to return %EPOLLERR in that situation. + * @waiting_in_dqbuf: set by the core for the duration of a blocking DQBUF, when + * it has to wait for a buffer to become available with vb2_queue->lock + * released. Used to prevent destroying the queue by other threads. * @is_multiplanar: set if buffer type is multiplanar * @is_output: set if buffer type is output * @copy_timestamp: set if vb2-core should set timestamps diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 61ebe723ee4d5..facb7a469efad 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -437,6 +437,10 @@ static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) refcount_inc(&ifp->refcnt); } +static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp) +{ + return refcount_inc_not_zero(&ifp->refcnt); +} /* * compute link-local solicited-node multicast address diff --git a/include/net/af_unix.h b/include/net/af_unix.h index afd40dce40f3d..77bf30203d3cf 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -55,7 +55,7 @@ struct unix_sock { struct mutex iolock, bindlock; struct sock *peer; struct list_head link; - atomic_long_t inflight; + unsigned long inflight; spinlock_t lock; unsigned long gc_flags; #define UNIX_GC_CANDIDATE 0 @@ -77,6 +77,9 @@ enum unix_socket_lock_class { U_LOCK_NORMAL, U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ + U_LOCK_GC_LISTENER, /* used for listening socket while determining gc + * candidates to close a small race window. + */ }; static inline void unix_state_lock_nested(struct sock *sk, diff --git a/include/net/ax25.h b/include/net/ax25.h index 0d939e5aee4ec..c2a85fd3f5ea4 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -216,7 +216,7 @@ typedef struct { struct ctl_table; typedef struct ax25_dev { - struct ax25_dev *next; + struct list_head list; struct net_device *dev; netdevice_tracker dev_tracker; @@ -330,7 +330,6 @@ int ax25_addr_size(const ax25_digi *); void ax25_digi_invert(const ax25_digi *, ax25_digi *); /* ax25_dev.c */ -extern ax25_dev *ax25_dev_list; extern spinlock_t ax25_dev_lock; #if IS_ENABLED(CONFIG_AX25) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 7ffa8c192c3f2..b3228bd6cd6be 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -164,6 +164,8 @@ struct bt_voice { #define BT_ISO_QOS_BIG_UNSET 0xff #define BT_ISO_QOS_BIS_UNSET 0xff +#define BT_ISO_SYNC_TIMEOUT 0x07d0 /* 20 secs */ + struct bt_iso_io_qos { __u32 interval; __u16 latency; @@ -283,7 +285,7 @@ void bt_err_ratelimited(const char *fmt, ...); bt_err_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) /* Connection and socket states */ -enum { +enum bt_sock_state { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ BT_OPEN, BT_BOUND, @@ -583,6 +585,15 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } +static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, + sockptr_t src, size_t src_size) +{ + if (dst_size > src_size) + return -EINVAL; + + return copy_from_sockptr(dst, src, dst_size); +} + int bt_to_errno(u16 code); __u8 bt_status(int err); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index bdee5d649cc61..9eb3d2360b1ae 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -33,9 +33,6 @@ #define HCI_MAX_FRAME_SIZE (HCI_MAX_ACL_SIZE + 4) #define HCI_LINK_KEY_SIZE 16 -#define HCI_AMP_LINK_KEY_SIZE (2 * HCI_LINK_KEY_SIZE) - -#define HCI_MAX_AMP_ASSOC_SIZE 672 #define HCI_MAX_CPB_DATA_SIZE 252 @@ -71,26 +68,6 @@ #define HCI_SMD 9 #define HCI_VIRTIO 10 -/* HCI controller types */ -#define HCI_PRIMARY 0x00 -#define HCI_AMP 0x01 - -/* First BR/EDR Controller shall have ID = 0 */ -#define AMP_ID_BREDR 0x00 - -/* AMP controller types */ -#define AMP_TYPE_BREDR 0x00 -#define AMP_TYPE_80211 0x01 - -/* AMP controller status */ -#define AMP_STATUS_POWERED_DOWN 0x00 -#define AMP_STATUS_BLUETOOTH_ONLY 0x01 -#define AMP_STATUS_NO_CAPACITY 0x02 -#define AMP_STATUS_LOW_CAPACITY 0x03 -#define AMP_STATUS_MEDIUM_CAPACITY 0x04 -#define AMP_STATUS_HIGH_CAPACITY 0x05 -#define AMP_STATUS_FULL_CAPACITY 0x06 - /* HCI device quirks */ enum { /* When this quirk is set, the HCI Reset command is send when @@ -176,6 +153,15 @@ enum { */ HCI_QUIRK_USE_BDADDR_PROPERTY, + /* When this quirk is set, the Bluetooth Device Address provided by + * the 'local-bd-address' fwnode property is incorrectly specified in + * big-endian order. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BDADDR_PROPERTY_BROKEN, + /* When this quirk is set, the duplicate filtering during * scanning is based on Bluetooth devices addresses. To allow * RSSI based updates, restart scanning if needed. @@ -330,6 +316,14 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_BROKEN_LE_CODED, + + /* + * When this quirk is set, the HCI_OP_READ_ENC_KEY_SIZE command is + * skipped during an HCI_EV_ENCRYPT_CHANGE event. This is required + * for Actions Semiconductor ATS2851 based controllers, which erroneously + * claim to support it. + */ + HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, }; /* HCI device flags */ @@ -393,7 +387,6 @@ enum { HCI_LIMITED_PRIVACY, HCI_RPA_EXPIRED, HCI_RPA_RESOLVING, - HCI_HS_ENABLED, HCI_LE_ENABLED, HCI_ADVERTISING, HCI_ADVERTISING_CONNECTABLE, @@ -437,7 +430,7 @@ enum { #define HCI_NCMD_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ #define HCI_ACL_TX_TIMEOUT msecs_to_jiffies(45000) /* 45 seconds */ #define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ -#define HCI_POWER_OFF_TIMEOUT msecs_to_jiffies(5000) /* 5 seconds */ +#define HCI_ACL_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_AUTOCONN_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ @@ -511,7 +504,6 @@ enum { #define ESCO_LINK 0x02 /* Low Energy links do not have defined link type. Use invented one */ #define LE_LINK 0x80 -#define AMP_LINK 0x81 #define ISO_LINK 0x82 #define INVALID_LINK 0xff @@ -653,6 +645,7 @@ enum { #define HCI_ERROR_PIN_OR_KEY_MISSING 0x06 #define HCI_ERROR_MEMORY_EXCEEDED 0x07 #define HCI_ERROR_CONNECTION_TIMEOUT 0x08 +#define HCI_ERROR_COMMAND_DISALLOWED 0x0c #define HCI_ERROR_REJ_LIMITED_RESOURCES 0x0d #define HCI_ERROR_REJ_BAD_ADDR 0x0f #define HCI_ERROR_INVALID_PARAMETERS 0x12 @@ -661,6 +654,7 @@ enum { #define HCI_ERROR_REMOTE_POWER_OFF 0x15 #define HCI_ERROR_LOCAL_HOST_TERM 0x16 #define HCI_ERROR_PAIRING_NOT_ALLOWED 0x18 +#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE 0x1e #define HCI_ERROR_INVALID_LL_PARAMS 0x1e #define HCI_ERROR_UNSPECIFIED 0x1f #define HCI_ERROR_ADVERTISING_TIMEOUT 0x3c @@ -925,56 +919,6 @@ struct hci_cp_io_capability_neg_reply { __u8 reason; } __packed; -#define HCI_OP_CREATE_PHY_LINK 0x0435 -struct hci_cp_create_phy_link { - __u8 phy_handle; - __u8 key_len; - __u8 key_type; - __u8 key[HCI_AMP_LINK_KEY_SIZE]; -} __packed; - -#define HCI_OP_ACCEPT_PHY_LINK 0x0436 -struct hci_cp_accept_phy_link { - __u8 phy_handle; - __u8 key_len; - __u8 key_type; - __u8 key[HCI_AMP_LINK_KEY_SIZE]; -} __packed; - -#define HCI_OP_DISCONN_PHY_LINK 0x0437 -struct hci_cp_disconn_phy_link { - __u8 phy_handle; - __u8 reason; -} __packed; - -struct ext_flow_spec { - __u8 id; - __u8 stype; - __le16 msdu; - __le32 sdu_itime; - __le32 acc_lat; - __le32 flush_to; -} __packed; - -#define HCI_OP_CREATE_LOGICAL_LINK 0x0438 -#define HCI_OP_ACCEPT_LOGICAL_LINK 0x0439 -struct hci_cp_create_accept_logical_link { - __u8 phy_handle; - struct ext_flow_spec tx_flow_spec; - struct ext_flow_spec rx_flow_spec; -} __packed; - -#define HCI_OP_DISCONN_LOGICAL_LINK 0x043a -struct hci_cp_disconn_logical_link { - __le16 log_handle; -} __packed; - -#define HCI_OP_LOGICAL_LINK_CANCEL 0x043b -struct hci_cp_logical_link_cancel { - __u8 phy_handle; - __u8 flow_spec_id; -} __packed; - #define HCI_OP_ENHANCED_SETUP_SYNC_CONN 0x043d struct hci_coding_format { __u8 id; @@ -1596,46 +1540,6 @@ struct hci_rp_read_enc_key_size { __u8 key_size; } __packed; -#define HCI_OP_READ_LOCAL_AMP_INFO 0x1409 -struct hci_rp_read_local_amp_info { - __u8 status; - __u8 amp_status; - __le32 total_bw; - __le32 max_bw; - __le32 min_latency; - __le32 max_pdu; - __u8 amp_type; - __le16 pal_cap; - __le16 max_assoc_size; - __le32 max_flush_to; - __le32 be_flush_to; -} __packed; - -#define HCI_OP_READ_LOCAL_AMP_ASSOC 0x140a -struct hci_cp_read_local_amp_assoc { - __u8 phy_handle; - __le16 len_so_far; - __le16 max_len; -} __packed; -struct hci_rp_read_local_amp_assoc { - __u8 status; - __u8 phy_handle; - __le16 rem_len; - __u8 frag[]; -} __packed; - -#define HCI_OP_WRITE_REMOTE_AMP_ASSOC 0x140b -struct hci_cp_write_remote_amp_assoc { - __u8 phy_handle; - __le16 len_so_far; - __le16 rem_len; - __u8 frag[]; -} __packed; -struct hci_rp_write_remote_amp_assoc { - __u8 status; - __u8 phy_handle; -} __packed; - #define HCI_OP_GET_MWS_TRANSPORT_CONFIG 0x140c #define HCI_OP_ENABLE_DUT_MODE 0x1803 @@ -1647,6 +1551,15 @@ struct hci_cp_le_set_event_mask { __u8 mask[8]; } __packed; +/* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 4, Part E + * 7.8.2 LE Read Buffer Size command + * MAX_LE_MTU is 0xffff. + * 0 is also valid. It means that no dedicated LE Buffer exists. + * It should use the HCI_Read_Buffer_Size command and mtu is shared + * between BR/EDR and LE. + */ +#define HCI_MIN_LE_MTU 0x001b + #define HCI_OP_LE_READ_BUFFER_SIZE 0x2002 struct hci_rp_le_read_buffer_size { __u8 status; @@ -2007,7 +1920,7 @@ struct hci_cp_le_set_ext_adv_data { __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA 0x2038 @@ -2016,7 +1929,7 @@ struct hci_cp_le_set_ext_scan_rsp_data { __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_EXT_ADV_ENABLE 0x2039 @@ -2035,13 +1948,14 @@ struct hci_cp_le_set_per_adv_params { } __packed; #define HCI_MAX_PER_AD_LENGTH 252 +#define HCI_MAX_PER_AD_TOT_LEN 1650 #define HCI_OP_LE_SET_PER_ADV_DATA 0x203f struct hci_cp_le_set_per_adv_data { __u8 handle; __u8 operation; __u8 length; - __u8 data[]; + __u8 data[] __counted_by(length); } __packed; #define HCI_OP_LE_SET_PER_ADV_ENABLE 0x2040 @@ -2142,7 +2056,7 @@ struct hci_cis { struct hci_cp_le_create_cis { __u8 num_cis; - struct hci_cis cis[]; + struct hci_cis cis[] __counted_by(num_cis); } __packed; #define HCI_OP_LE_REMOVE_CIG 0x2065 @@ -2795,6 +2709,10 @@ struct hci_ev_le_per_adv_report { __u8 data[]; } __packed; +#define LE_PA_DATA_COMPLETE 0x00 +#define LE_PA_DATA_MORE_TO_COME 0x01 +#define LE_PA_DATA_TRUNCATED 0x02 + #define HCI_EV_LE_EXT_ADV_SET_TERM 0x12 struct hci_evt_le_ext_adv_set_term { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8f8dd91737142..17b2a7baa4d8f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1,7 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. - Copyright 2023 NXP + Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky @@ -126,7 +126,6 @@ enum suspended_state { struct hci_conn_hash { struct list_head list; unsigned int acl_num; - unsigned int amp_num; unsigned int sco_num; unsigned int iso_num; unsigned int le_num; @@ -247,6 +246,7 @@ struct adv_info { bool periodic; __u8 mesh; __u8 instance; + __u8 handle; __u32 flags; __u16 timeout; __u16 remaining_time; @@ -341,14 +341,6 @@ struct adv_monitor { /* Default authenticated payload timeout 30s */ #define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 -struct amp_assoc { - __u16 len; - __u16 offset; - __u16 rem_len; - __u16 len_so_far; - __u8 data[HCI_MAX_AMP_ASSOC_SIZE]; -}; - #define HCI_MAX_PAGES 3 struct hci_dev { @@ -361,7 +353,6 @@ struct hci_dev { unsigned long flags; __u16 id; __u8 bus; - __u8 dev_type; bdaddr_t bdaddr; bdaddr_t setup_addr; bdaddr_t public_addr; @@ -467,21 +458,6 @@ struct hci_dev { __u16 sniff_min_interval; __u16 sniff_max_interval; - __u8 amp_status; - __u32 amp_total_bw; - __u32 amp_max_bw; - __u32 amp_min_latency; - __u32 amp_max_pdu; - __u8 amp_type; - __u16 amp_pal_cap; - __u16 amp_assoc_size; - __u32 amp_max_flush_to; - __u32 amp_be_flush_to; - - struct amp_assoc loc_assoc; - - __u8 flow_ctl_mode; - unsigned int auto_accept_delay; unsigned long quirks; @@ -501,11 +477,6 @@ struct hci_dev { unsigned int le_pkts; unsigned int iso_pkts; - __u16 block_len; - __u16 block_mtu; - __u16 num_blocks; - __u16 block_cnt; - unsigned long acl_last_tx; unsigned long sco_last_tx; unsigned long le_last_tx; @@ -552,6 +523,7 @@ struct hci_dev { __u32 req_status; __u32 req_result; struct sk_buff *req_skb; + struct sk_buff *req_rsp; void *smp_data; void *smp_bredr_data; @@ -705,6 +677,7 @@ struct hci_conn { __u16 handle; __u16 sync_handle; __u16 state; + __u16 mtu; __u8 mode; __u8 type; __u8 role; @@ -734,8 +707,11 @@ struct hci_conn { __u16 le_supv_timeout; __u8 le_adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 le_adv_data_len; - __u8 le_per_adv_data[HCI_MAX_PER_AD_LENGTH]; - __u8 le_per_adv_data_len; + __u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN]; + __u16 le_per_adv_data_len; + __u16 le_per_adv_data_offset; + __u8 le_adv_phy; + __u8 le_adv_sec_phy; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; @@ -773,7 +749,6 @@ struct hci_conn { void *l2cap_data; void *sco_data; void *iso_data; - struct amp_mgr *amp_mgr; struct list_head link_list; struct hci_conn *parent; @@ -800,7 +775,6 @@ struct hci_chan { struct sk_buff_head data_q; unsigned int sent; __u8 state; - bool amp; }; struct hci_conn_params { @@ -1009,9 +983,6 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) case ACL_LINK: h->acl_num++; break; - case AMP_LINK: - h->amp_num++; - break; case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) @@ -1038,9 +1009,6 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) case ACL_LINK: h->acl_num--; break; - case AMP_LINK: - h->amp_num--; - break; case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) @@ -1062,8 +1030,6 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) switch (type) { case ACL_LINK: return h->acl_num; - case AMP_LINK: - return h->amp_num; case LE_LINK: return h->le_num; case SCO_LINK: @@ -1080,7 +1046,25 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; - return c->acl_num + c->amp_num + c->sco_num + c->le_num + c->iso_num; + return c->acl_num + c->sco_num + c->le_num + c->iso_num; +} + +static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c == conn) { + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); + + return false; } static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle) @@ -1351,8 +1335,7 @@ hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle) rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK || - !test_bit(HCI_CONN_PA_SYNC, &c->flags)) + if (c->type != ISO_LINK) continue; if (c->sync_handle == sync_handle) { @@ -1480,7 +1463,6 @@ struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); -void hci_conn_check_pending(struct hci_dev *hdev); struct hci_chan *hci_chan_create(struct hci_conn *conn); void hci_chan_del(struct hci_chan *chan); @@ -1493,12 +1475,14 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, - u16 conn_timeout, u8 role); + u16 conn_timeout, u8 role, u8 phy, u8 sec_phy); +void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, - enum conn_reasons conn_reason); + enum conn_reasons conn_reason, u16 timeout); struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u16 setting, struct bt_codec *codec); + __u16 setting, struct bt_codec *codec, + u16 timeout); struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, @@ -1509,8 +1493,8 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, __u8 data_len, __u8 *data); -int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, - __u8 sid, struct bt_iso_qos *qos); +struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, + __u8 dst_type, __u8 sid, struct bt_iso_qos *qos); int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]); @@ -1587,10 +1571,6 @@ static inline void hci_conn_drop(struct hci_conn *conn) } break; - case AMP_LINK: - timeo = conn->disc_timeout; - break; - default: timeo = 0; break; @@ -1884,6 +1864,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ (hdev->commands[39] & 0x04)) +#define read_key_size_capable(dev) \ + ((dev)->commands[20] & 0x10 && \ + !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) + /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ @@ -2129,18 +2113,46 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, { u16 max_latency; - if (min > max || min < 6 || max > 3200) + if (min > max) { + BT_WARN("min %d > max %d", min, max); + return -EINVAL; + } + + if (min < 6) { + BT_WARN("min %d < 6", min); + return -EINVAL; + } + + if (max > 3200) { + BT_WARN("max %d > 3200", max); return -EINVAL; + } - if (to_multiplier < 10 || to_multiplier > 3200) + if (to_multiplier < 10) { + BT_WARN("to_multiplier %d < 10", to_multiplier); return -EINVAL; + } - if (max >= to_multiplier * 8) + if (to_multiplier > 3200) { + BT_WARN("to_multiplier %d > 3200", to_multiplier); return -EINVAL; + } + + if (max >= to_multiplier * 8) { + BT_WARN("max %d >= to_multiplier %d * 8", max, to_multiplier); + return -EINVAL; + } max_latency = (to_multiplier * 4 / max) - 1; - if (latency > 499 || latency > max_latency) + if (latency > 499) { + BT_WARN("latency %d > 499", latency); return -EINVAL; + } + + if (latency > max_latency) { + BT_WARN("latency %d > max_latency %d", latency, max_latency); + return -EINVAL; + } return 0; } diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 6efbc2152146b..6a9d063e9f472 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -42,12 +42,24 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, void hci_cmd_sync_init(struct hci_dev *hdev); void hci_cmd_sync_clear(struct hci_dev *hdev); void hci_cmd_sync_cancel(struct hci_dev *hdev, int err); -void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err); +void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err); int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +struct hci_cmd_sync_work_entry * +hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +void hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry); +bool hci_cmd_sync_dequeue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +bool hci_cmd_sync_dequeue_once(struct hci_dev *hdev, + hci_cmd_sync_work_func_t func, void *data, + hci_cmd_sync_work_destroy_t destroy); int hci_update_eir_sync(struct hci_dev *hdev); int hci_update_class_sync(struct hci_dev *hdev); @@ -127,8 +139,6 @@ struct hci_conn; int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason); -int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn); - int hci_le_create_cis_sync(struct hci_dev *hdev); int hci_le_remove_cig_sync(struct hci_dev *hdev, u8 handle); @@ -138,3 +148,9 @@ int hci_le_terminate_big_sync(struct hci_dev *hdev, u8 handle, u8 reason); int hci_le_big_terminate_sync(struct hci_dev *hdev, u8 handle); int hci_le_pa_terminate_sync(struct hci_dev *hdev, u16 handle); + +int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn); + +int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn); + +int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index cf393e72d6ed6..3434cfc26b6af 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -59,8 +59,6 @@ #define L2CAP_WAIT_ACK_POLL_PERIOD msecs_to_jiffies(200) #define L2CAP_WAIT_ACK_TIMEOUT msecs_to_jiffies(10000) -#define L2CAP_A2MP_DEFAULT_MTU 670 - /* L2CAP socket address */ struct sockaddr_l2 { sa_family_t l2_family; @@ -109,12 +107,6 @@ struct l2cap_conninfo { #define L2CAP_ECHO_RSP 0x09 #define L2CAP_INFO_REQ 0x0a #define L2CAP_INFO_RSP 0x0b -#define L2CAP_CREATE_CHAN_REQ 0x0c -#define L2CAP_CREATE_CHAN_RSP 0x0d -#define L2CAP_MOVE_CHAN_REQ 0x0e -#define L2CAP_MOVE_CHAN_RSP 0x0f -#define L2CAP_MOVE_CHAN_CFM 0x10 -#define L2CAP_MOVE_CHAN_CFM_RSP 0x11 #define L2CAP_CONN_PARAM_UPDATE_REQ 0x12 #define L2CAP_CONN_PARAM_UPDATE_RSP 0x13 #define L2CAP_LE_CONN_REQ 0x14 @@ -144,7 +136,6 @@ struct l2cap_conninfo { /* L2CAP fixed channels */ #define L2CAP_FC_SIG_BREDR 0x02 #define L2CAP_FC_CONNLESS 0x04 -#define L2CAP_FC_A2MP 0x08 #define L2CAP_FC_ATT 0x10 #define L2CAP_FC_SIG_LE 0x20 #define L2CAP_FC_SMP_LE 0x40 @@ -267,7 +258,6 @@ struct l2cap_conn_rsp { /* channel identifier */ #define L2CAP_CID_SIGNALING 0x0001 #define L2CAP_CID_CONN_LESS 0x0002 -#define L2CAP_CID_A2MP 0x0003 #define L2CAP_CID_ATT 0x0004 #define L2CAP_CID_LE_SIGNALING 0x0005 #define L2CAP_CID_SMP 0x0006 @@ -282,7 +272,6 @@ struct l2cap_conn_rsp { #define L2CAP_CR_BAD_PSM 0x0002 #define L2CAP_CR_SEC_BLOCK 0x0003 #define L2CAP_CR_NO_MEM 0x0004 -#define L2CAP_CR_BAD_AMP 0x0005 #define L2CAP_CR_INVALID_SCID 0x0006 #define L2CAP_CR_SCID_IN_USE 0x0007 @@ -404,29 +393,6 @@ struct l2cap_info_rsp { __u8 data[]; } __packed; -struct l2cap_create_chan_req { - __le16 psm; - __le16 scid; - __u8 amp_id; -} __packed; - -struct l2cap_create_chan_rsp { - __le16 dcid; - __le16 scid; - __le16 result; - __le16 status; -} __packed; - -struct l2cap_move_chan_req { - __le16 icid; - __u8 dest_amp_id; -} __packed; - -struct l2cap_move_chan_rsp { - __le16 icid; - __le16 result; -} __packed; - #define L2CAP_MR_SUCCESS 0x0000 #define L2CAP_MR_PEND 0x0001 #define L2CAP_MR_BAD_ID 0x0002 @@ -539,8 +505,6 @@ struct l2cap_seq_list { struct l2cap_chan { struct l2cap_conn *conn; - struct hci_conn *hs_hcon; - struct hci_chan *hs_hchan; struct kref kref; atomic_t nesting; @@ -584,6 +548,9 @@ struct l2cap_chan { __u16 tx_credits; __u16 rx_credits; + /* estimated available receive buffer space or -1 if unknown */ + ssize_t rx_avail; + __u8 tx_state; __u8 rx_state; @@ -591,12 +558,6 @@ struct l2cap_chan { unsigned long conn_state; unsigned long flags; - __u8 remote_amp_id; - __u8 local_amp_id; - __u8 move_id; - __u8 move_state; - __u8 move_role; - __u16 next_tx_seq; __u16 expected_ack_seq; __u16 expected_tx_seq; @@ -724,10 +685,15 @@ struct l2cap_user { /* ----- L2CAP socket info ----- */ #define l2cap_pi(sk) ((struct l2cap_pinfo *) sk) +struct l2cap_rx_busy { + struct list_head list; + struct sk_buff *skb; +}; + struct l2cap_pinfo { struct bt_sock bt; struct l2cap_chan *chan; - struct sk_buff *rx_busy_skb; + struct list_head rx_busy; }; enum { @@ -981,10 +947,11 @@ int l2cap_add_scid(struct l2cap_chan *chan, __u16 scid); struct l2cap_chan *l2cap_chan_create(void); void l2cap_chan_close(struct l2cap_chan *chan, int reason); int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, - bdaddr_t *dst, u8 dst_type); + bdaddr_t *dst, u8 dst_type, u16 timeout); int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu); int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len); void l2cap_chan_busy(struct l2cap_chan *chan, int busy); +void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail); int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator); void l2cap_chan_set_defaults(struct l2cap_chan *chan); int l2cap_ertm_init(struct l2cap_chan *chan); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2b54fdd8ca15a..0180eaec457bf 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4972,6 +4972,7 @@ struct cfg80211_ops { * set this flag to update channels on beacon hints. * @WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY: support connection to non-primary link * of an NSTR mobile AP MLD. + * @WIPHY_FLAG_DISABLE_WEXT: disable wireless extensions for this device */ enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), @@ -4983,6 +4984,7 @@ enum wiphy_flags { WIPHY_FLAG_4ADDR_STATION = BIT(6), WIPHY_FLAG_CONTROL_PORT_PROTOCOL = BIT(7), WIPHY_FLAG_IBSS_RSN = BIT(8), + WIPHY_FLAG_DISABLE_WEXT = BIT(9), WIPHY_FLAG_MESH_AUTH = BIT(10), WIPHY_FLAG_SUPPORTS_EXT_KCK_32 = BIT(11), WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY = BIT(12), diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index cd95711b12b8e..76d2cd2e2b309 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -401,6 +401,7 @@ struct ieee802154_llsec_key { struct ieee802154_llsec_key_entry { struct list_head list; + struct rcu_head rcu; struct ieee802154_llsec_key_id id; struct ieee802154_llsec_key *key; diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 6d1c8541183db..3a9001a042a5c 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -24,7 +24,7 @@ struct dst_ops { void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev); - struct dst_entry * (*negative_advice)(struct dst_entry *); + void (*negative_advice)(struct sock *sk, struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, diff --git a/include/net/gro.h b/include/net/gro.h index b435f0ddbf64f..62b006f3ed184 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -86,6 +86,15 @@ struct napi_gro_cb { /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; + + /* L3 offsets */ + union { + struct { + u16 network_offset; + u16 inner_network_offset; + }; + u16 network_offsets[2]; + }; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 9ab4bf704e864..ccf171f7eb60d 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -175,6 +175,7 @@ void inet_csk_init_xmit_timers(struct sock *sk, void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); +void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { diff --git a/include/net/ip.h b/include/net/ip.h index 25cb688bdc623..6d735e00d3f3e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -423,7 +423,7 @@ int ip_decrease_ttl(struct iphdr *iph) static inline int ip_mtu_locked(const struct dst_entry *dst) { - const struct rtable *rt = (const struct rtable *)dst; + const struct rtable *rt = dst_rtable(dst); return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); } @@ -461,7 +461,7 @@ static inline bool ip_sk_ignore_df(const struct sock *sk) static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { - const struct rtable *rt = container_of(dst, struct rtable, dst); + const struct rtable *rt = dst_rtable(dst); struct net *net = dev_net(dst->dev); unsigned int mtu; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 9ba6413fd2e3e..1121d614942c8 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -237,9 +237,11 @@ struct fib6_result { for (rt = (w)->leaf; rt; \ rt = rcu_dereference_protected(rt->fib6_next, 1)) -static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) +#define dst_rt6_info(_ptr) container_of_const(_ptr, struct rt6_info, dst) + +static inline struct inet6_dev *ip6_dst_idev(const struct dst_entry *dst) { - return ((struct rt6_info *)dst)->rt6i_idev; + return dst_rt6_info(dst)->rt6i_idev; } static inline bool fib6_requires_src(const struct fib6_info *rt) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 28b0657902615..e94d2867770c5 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -209,12 +209,11 @@ void rt6_uncached_list_del(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); - const struct rt6_info *rt6 = NULL; if (dst) - rt6 = container_of(dst, struct rt6_info, dst); + return dst_rt6_info(dst); - return rt6; + return NULL; } /* @@ -226,7 +225,7 @@ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, { struct ipv6_pinfo *np = inet6_sk(sk); - np->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); + np->dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); sk_setup_caps(sk, dst); np->daddr_cache = daddr; #ifdef CONFIG_IPV6_SUBTREES @@ -239,7 +238,7 @@ void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, static inline bool ipv6_unicast_destination(const struct sk_buff *skb) { - struct rt6_info *rt = (struct rt6_info *) skb_dst(skb); + const struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); return rt->rt6i_flags & RTF_LOCAL; } @@ -247,7 +246,7 @@ static inline bool ipv6_unicast_destination(const struct sk_buff *skb) static inline bool ipv6_anycast_destination(const struct dst_entry *dst, const struct in6_addr *daddr) { - struct rt6_info *rt = (struct rt6_info *)dst; + const struct rt6_info *rt = dst_rt6_info(dst); return rt->rt6i_flags & RTF_ANYCAST || (rt->rt6i_dst.plen < 127 && diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 2d746f4c9a0a4..de2f2ace947b7 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -109,6 +109,28 @@ struct ip_tunnel_prl_entry { }; struct metadata_dst; +/* A fan overlay /8 (250.0.0.0/8, for example) maps to exactly one /16 + * underlay (10.88.0.0/16, for example). Multiple local addresses within + * the /16 may be used, but a particular overlay may not span + * multiple underlay subnets. + * + * We store one underlay, indexed by the overlay's high order octet. + */ +#define FAN_OVERLAY_CNT 256 + +struct ip_fan_map { + __be32 underlay; + __be32 overlay; + u16 underlay_prefix; + u16 overlay_prefix; + u32 overlay_mask; + struct list_head list; + struct rcu_head rcu; +}; + +struct ip_tunnel_fan { + struct list_head fan_maps; +}; struct ip_tunnel { struct ip_tunnel __rcu *next; @@ -149,6 +171,7 @@ struct ip_tunnel { #endif struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ unsigned int prl_count; /* # of entries in PRL */ + struct ip_tunnel_fan fan; unsigned int ip_tnl_net_id; struct gro_cells gro_cells; __u32 fwmark; @@ -156,6 +179,11 @@ struct ip_tunnel { bool ignore_df; }; +static inline int fan_has_map(const struct ip_tunnel_fan *fan) +{ + return !list_empty(&fan->fan_maps); +} + struct tnl_ptk_info { __be16 flags; __be16 proto; @@ -360,6 +388,40 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb) return pskb_network_may_pull(skb, nhlen); } +/* Variant of pskb_inet_may_pull(). + */ +static inline bool skb_vlan_inet_prepare(struct sk_buff *skb, + bool inner_proto_inherit) +{ + int nhlen = 0, maclen = inner_proto_inherit ? 0 : ETH_HLEN; + __be16 type = skb->protocol; + + /* Essentially this is skb_protocol(skb, true) + * And we get MAC len. + */ + if (eth_type_vlan(type)) + type = __vlan_get_protocol(skb, type, &maclen); + + switch (type) { +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + nhlen = sizeof(struct ipv6hdr); + break; +#endif + case htons(ETH_P_IP): + nhlen = sizeof(struct iphdr); + break; + } + /* For ETH_P_IPV6/ETH_P_IP we make sure to pull + * a base network header in skb->head. + */ + if (!pskb_may_pull(skb, maclen + nhlen)) + return false; + + skb_set_network_header(skb, maclen); + return true; +} + static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d400fe2e8668d..df9b578e58bb2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -932,6 +932,8 @@ enum mac80211_tx_info_flags { * of their QoS TID or other priority field values. * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally * for sequence number assignment + * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted + * due to scanning, not in normal operation on the interface. * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this * frame should be transmitted on the specific link. This really is * only relevant for frames that do not have data present, and is @@ -952,6 +954,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9), + IEEE80211_TX_CTRL_SCAN_TX = BIT(10), IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; diff --git a/include/net/macsec.h b/include/net/macsec.h index dbd22180cc5c3..de216cbc6b059 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -321,6 +321,7 @@ struct macsec_context { * for the TX tag * @needed_tailroom: number of bytes reserved at the end of the sk_buff for the * TX tag + * @rx_uses_md_dst: whether MACsec device offload supports sk_buff md_dst */ struct macsec_ops { /* Device wide */ @@ -352,6 +353,7 @@ struct macsec_ops { struct sk_buff *skb); unsigned int needed_headroom; unsigned int needed_tailroom; + bool rx_uses_md_dst; }; void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 76147feb0d10a..4eeedf14711b3 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -39,7 +39,6 @@ enum TRI_STATE { #define COMP_ENTRY_SIZE 64 #define RX_BUFFERS_PER_QUEUE 512 -#define MANA_RX_DATA_ALIGN 64 #define MAX_SEND_BUFFERS_PER_QUEUE 256 diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index a763dd327c6ea..9abb7ee40d72f 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -336,7 +336,7 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, int nf_flow_table_offload_init(void); void nf_flow_table_offload_exit(void); -static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) { __be16 proto; @@ -352,6 +352,16 @@ static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) return 0; } +static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) +{ + if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) + return false; + + *inner_proto = __nf_flow_pppoe_proto(skb); + + return true; +} + #define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count) \ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 510244cc0f8f0..1cf9cb0f0a975 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -307,9 +307,23 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) return (void *)priv; } + +/** + * enum nft_iter_type - nftables set iterator type + * + * @NFT_ITER_READ: read-only iteration over set elements + * @NFT_ITER_UPDATE: iteration under mutex to update set element state + */ +enum nft_iter_type { + NFT_ITER_UNSPEC, + NFT_ITER_READ, + NFT_ITER_UPDATE, +}; + struct nft_set; struct nft_set_iter { u8 genmask; + enum nft_iter_type type:8; unsigned int count; unsigned int skip; int err; diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 43ae503376851..03656b8d0b4f0 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -97,7 +97,7 @@ struct calipso_doi; /* NetLabel audit information */ struct netlbl_audit { - u32 secid; + struct lsmblob blob; kuid_t loginuid; unsigned int sessionid; }; diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 02bbdc577f8e2..a6a0bf4a247e5 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -15,6 +15,9 @@ struct netns_nf { const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; +#ifdef CONFIG_LWTUNNEL + struct ctl_table_header *nf_lwtnl_dir_header; +#endif #endif struct nf_hook_entries __rcu *hooks_ipv4[NF_INET_NUMHOOKS]; struct nf_hook_entries __rcu *hooks_ipv6[NF_INET_NUMHOOKS]; diff --git a/include/net/route.h b/include/net/route.h index 980ab474eabdc..9cc68c2d23271 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -80,6 +80,17 @@ struct rtable { rt_pmtu:31; }; +#define dst_rtable(_ptr) container_of_const(_ptr, struct rtable, dst) + +/** + * skb_rtable - Returns the skb &rtable + * @skb: buffer + */ +static inline struct rtable *skb_rtable(const struct sk_buff *skb) +{ + return dst_rtable(skb_dst(skb)); +} + static inline bool rt_is_input_route(const struct rtable *rt) { return rt->rt_is_input != 0; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index cefe0c4bdae34..0014b9ee5e381 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -117,6 +117,7 @@ struct Qdisc { struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; + int owner; unsigned long state; unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; @@ -127,6 +128,7 @@ struct Qdisc { struct rcu_head rcu; netdevice_tracker dev_tracker; + struct lock_class_key root_lock_key; /* private data */ long privdata[] ____cacheline_aligned; }; diff --git a/include/net/scm.h b/include/net/scm.h index cf68acec4d70a..8351b2fedfdd9 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -94,16 +94,16 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg, #ifdef CONFIG_SECURITY_NETWORK static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm) { - char *secdata; - u32 seclen; + struct lsmcontext ctx; int err; if (test_bit(SOCK_PASSSEC, &sock->flags)) { - err = security_secid_to_secctx(scm->secid, &secdata, &seclen); + err = security_secid_to_secctx(scm->secid, &ctx); - if (!err) { - put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, seclen, secdata); - security_release_secctx(secdata, seclen); + if (err >= 0) { + put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, ctx.len, + ctx.context); + security_release_secctx(&ctx); } } } diff --git a/include/net/sock.h b/include/net/sock.h index 54ca8dcbfb433..afb5bcf217ab8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1429,33 +1429,36 @@ sk_memory_allocated(const struct sock *sk) /* 1 MB per cpu, in page units */ #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) +extern int sysctl_mem_pcpu_rsv; + +static inline void proto_memory_pcpu_drain(struct proto *proto) +{ + int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); + + if (val) + atomic_long_add(val, proto->memory_allocated); +} static inline void -sk_memory_allocated_add(struct sock *sk, int amt) +sk_memory_allocated_add(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } static inline void -sk_memory_allocated_sub(struct sock *sk, int amt) +sk_memory_allocated_sub(const struct sock *sk, int val) { - int local_reserve; + struct proto *proto = sk->sk_prot; - preempt_disable(); - local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); - if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { - __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); - atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); - } - preempt_enable(); + val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); + + if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv))) + proto_memory_pcpu_drain(proto); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 @@ -1779,6 +1782,13 @@ static inline void sock_owned_by_me(const struct sock *sk) #endif } +static inline void sock_not_owned_by_me(const struct sock *sk) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); +#endif +} + static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); @@ -2145,17 +2155,10 @@ sk_dst_get(const struct sock *sk) static inline void __dst_negative_advice(struct sock *sk) { - struct dst_entry *ndst, *dst = __sk_dst_get(sk); + struct dst_entry *dst = __sk_dst_get(sk); - if (dst && dst->ops->negative_advice) { - ndst = dst->ops->negative_advice(dst); - - if (ndst != dst) { - rcu_assign_pointer(sk->sk_dst_cache, ndst); - sk_tx_queue_clear(sk); - WRITE_ONCE(sk->sk_dst_pending_confirm, 0); - } - } + if (dst && dst->ops->negative_advice) + dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) diff --git a/include/net/tcp.h b/include/net/tcp.h index f6eba9652d010..ab62e53f187c5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1494,11 +1494,10 @@ static inline int tcp_space_from_win(const struct sock *sk, int win) return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); } -/* Assume a conservative default of 1200 bytes of payload per 4K page. +/* Assume a 50% default for skb->len/skb->truesize ratio. * This may be adjusted later in tcp_measure_rcv_mss(). */ -#define TCP_DEFAULT_SCALING_RATIO ((1200 << TCP_RMEM_TO_WIN_SCALE) / \ - SKB_TRUESIZE(4096)) +#define TCP_DEFAULT_SCALING_RATIO (1 << (TCP_RMEM_TO_WIN_SCALE - 1)) static inline void tcp_scaling_ratio_init(struct sock *sk) { diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 471e177362b4c..5d8e9ed2c0056 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -86,7 +86,8 @@ static inline int tcp_ao_sizeof_key(const struct tcp_ao_key *key) struct tcp_ao_info { /* List of tcp_ao_key's */ struct hlist_head head; - /* current_key and rnext_key aren't maintained on listen sockets. + /* current_key and rnext_key are maintained on sockets + * in TCP_AO_ESTABLISHED states. * Their purpose is to cache keys on established connections, * saving needless lookups. Never dereference any of them from * listen sockets. @@ -201,9 +202,9 @@ struct tcp6_ao_context { }; struct tcp_sigpool; +/* Established states are fast-path and there always is current_key/rnext_key */ #define TCP_AO_ESTABLISHED (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | \ - TCPF_CLOSE | TCPF_CLOSE_WAIT | \ - TCPF_LAST_ACK | TCPF_CLOSING) + TCPF_CLOSE_WAIT | TCPF_LAST_ACK | TCPF_CLOSING) int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb, struct tcp_ao_key *key, struct tcphdr *th, diff --git a/include/net/tls.h b/include/net/tls.h index 340ad43971e47..33f657d3c0510 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -111,7 +111,8 @@ struct tls_strparser { u32 stopped : 1; u32 copy_mode : 1; u32 mixed_decrypted : 1; - u32 msg_ready : 1; + + bool msg_ready; struct strp_msg stm; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 33ba6fc151cf8..e55d5b1483db8 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -294,6 +294,8 @@ struct vxlan_dev { struct net *net; /* netns for packet i/o */ struct vxlan_rdst default_dst; /* default destination */ + struct ip_tunnel_fan fan; + struct timer_list age_timer; spinlock_t hash_lock[FDB_HASH_SIZE]; unsigned int addrcnt; diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 3cb4dc9bd70e4..3d54de168a6d9 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -188,6 +188,8 @@ static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl, { if (!compl) return; + if (!compl->tx_timestamp) + return; *compl->tx_timestamp = ops->tmo_fill_timestamp(priv); } diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 1d107241b9018..5d0f8f40b8d16 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1047,6 +1047,9 @@ struct xfrm_offload { #define CRYPTO_INVALID_PACKET_SYNTAX 64 #define CRYPTO_INVALID_PROTOCOL 128 + /* Used to keep whole l2 header for transport mode GRO */ + __u32 orig_mac_len; + __u8 proto; __u8 inner_ipproto; }; diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h index 4ce1988b2ba01..f40915d2eceef 100644 --- a/include/scsi/scsi_driver.h +++ b/include/scsi/scsi_driver.h @@ -12,6 +12,7 @@ struct request; struct scsi_driver { struct device_driver gendrv; + int (*resume)(struct device *); void (*rescan)(struct device *); blk_status_t (*init_command)(struct scsi_cmnd *); void (*uninit_command)(struct scsi_cmnd *); diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 3b907fc2ef08f..510f594b06368 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -767,6 +767,7 @@ scsi_template_proc_dir(const struct scsi_host_template *sht); #define scsi_template_proc_dir(sht) NULL #endif extern void scsi_scan_host(struct Scsi_Host *); +extern int scsi_resume_device(struct scsi_device *sdev); extern int scsi_rescan_device(struct scsi_device *sdev); extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); diff --git a/include/scsi/scsi_transport_sas.h b/include/scsi/scsi_transport_sas.h index 0e75b9277c8c6..e3b6ce3cbf883 100644 --- a/include/scsi/scsi_transport_sas.h +++ b/include/scsi/scsi_transport_sas.h @@ -200,6 +200,8 @@ unsigned int sas_is_tlr_enabled(struct scsi_device *); void sas_disable_tlr(struct scsi_device *); void sas_enable_tlr(struct scsi_device *); +bool sas_ata_ncq_prio_supported(struct scsi_device *sdev); + extern struct sas_rphy *sas_end_device_alloc(struct sas_port *); extern struct sas_rphy *sas_expander_alloc(struct sas_port *, enum sas_device_type); void sas_rphy_free(struct sas_rphy *); diff --git a/include/soc/qcom/cmd-db.h b/include/soc/qcom/cmd-db.h index c8bb56e6852a8..47a6cab75e630 100644 --- a/include/soc/qcom/cmd-db.h +++ b/include/soc/qcom/cmd-db.h @@ -1,5 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. */ +/* + * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ #ifndef __QCOM_COMMAND_DB_H__ #define __QCOM_COMMAND_DB_H__ @@ -21,6 +24,8 @@ u32 cmd_db_read_addr(const char *resource_id); const void *cmd_db_read_aux_data(const char *resource_id, size_t *len); +bool cmd_db_match_resource_addr(u32 addr1, u32 addr2); + enum cmd_db_hw_type cmd_db_read_slave_id(const char *resource_id); int cmd_db_ready(void); @@ -31,6 +36,9 @@ static inline u32 cmd_db_read_addr(const char *resource_id) static inline const void *cmd_db_read_aux_data(const char *resource_id, size_t *len) { return ERR_PTR(-ENODEV); } +static inline bool cmd_db_match_resource_addr(u32 addr1, u32 addr2) +{ return false; } + static inline enum cmd_db_hw_type cmd_db_read_slave_id(const char *resource_id) { return -ENODEV; } diff --git a/include/soc/qcom/qcom-spmi-pmic.h b/include/soc/qcom/qcom-spmi-pmic.h index 17a0a8c3d6560..a62d500a6fdaf 100644 --- a/include/soc/qcom/qcom-spmi-pmic.h +++ b/include/soc/qcom/qcom-spmi-pmic.h @@ -49,7 +49,7 @@ #define PMK8350_SUBTYPE 0x2f #define PMR735B_SUBTYPE 0x34 #define PM6350_SUBTYPE 0x36 -#define PM2250_SUBTYPE 0x37 +#define PM4125_SUBTYPE 0x37 #define PMI8998_FAB_ID_SMIC 0x11 #define PMI8998_FAB_ID_GF 0x30 diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h index 1af9e68193920..9cc10fab01a8c 100644 --- a/include/sound/emu10k1.h +++ b/include/sound/emu10k1.h @@ -1684,8 +1684,7 @@ struct snd_emu1010 { unsigned int clock_fallback; unsigned int optical_in; /* 0:SPDIF, 1:ADAT */ unsigned int optical_out; /* 0:SPDIF, 1:ADAT */ - struct work_struct firmware_work; - struct work_struct clock_work; + struct work_struct work; }; struct snd_emu10k1 { diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index a8bebac1e4b28..957295364a5e3 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -56,6 +56,9 @@ struct hdac_ext_stream { u32 pphcldpl; u32 pphcldpu; + u32 pplcllpl; + u32 pplcllpu; + bool decoupled:1; bool link_locked:1; bool link_prepared; diff --git a/include/sound/tas2781-dsp.h b/include/sound/tas2781-dsp.h index ea9af2726a53f..7fba7ea26a4b0 100644 --- a/include/sound/tas2781-dsp.h +++ b/include/sound/tas2781-dsp.h @@ -2,7 +2,7 @@ // // ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier // -// Copyright (C) 2022 - 2023 Texas Instruments Incorporated +// Copyright (C) 2022 - 2024 Texas Instruments Incorporated // https://www.ti.com // // The TAS2781 driver implements a flexible and configurable @@ -13,8 +13,8 @@ // Author: Kevin Lu // -#ifndef __TASDEVICE_DSP_H__ -#define __TASDEVICE_DSP_H__ +#ifndef __TAS2781_DSP_H__ +#define __TAS2781_DSP_H__ #define MAIN_ALL_DEVICES 0x0d #define MAIN_DEVICE_A 0x01 @@ -180,7 +180,6 @@ void tasdevice_calbin_remove(void *context); int tasdevice_select_tuningprm_cfg(void *context, int prm, int cfg_no, int rca_conf_no); int tasdevice_prmg_load(void *context, int prm_no); -int tasdevice_prmg_calibdata_load(void *context, int prm_no); void tasdevice_tuning_switch(void *context, int state); int tas2781_load_calibration(void *context, char *file_name, unsigned short i); diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 60af7c63b34e6..002f37b6366f5 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -550,6 +550,7 @@ struct iscsit_conn { struct completion conn_logout_comp; struct completion tx_half_close_comp; struct completion rx_half_close_comp; + struct completion kthr_start_comp; /* socket used by this connection */ struct socket *sock; void (*orig_data_ready)(struct sock *); diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 3378ff9ee271c..4f136a98df63e 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -191,6 +191,7 @@ sense_reason_t transport_generic_new_cmd(struct se_cmd *); void target_put_cmd_and_wait(struct se_cmd *cmd); void target_execute_cmd(struct se_cmd *cmd); +bool target_cmd_interrupted(struct se_cmd *cmd); int transport_generic_free_cmd(struct se_cmd *, int); diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h index 4d8ef71090af1..97a434d021356 100644 --- a/include/trace/events/asoc.h +++ b/include/trace/events/asoc.h @@ -12,6 +12,8 @@ #define DAPM_DIRECT "(direct)" #define DAPM_ARROW(dir) (((dir) == SND_SOC_DAPM_DIR_OUT) ? "->" : "<-") +TRACE_DEFINE_ENUM(SND_SOC_DAPM_DIR_OUT); + struct snd_soc_jack; struct snd_soc_card; struct snd_soc_dapm_widget; diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index cf4b98b9a9edc..7d931db02b934 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -33,6 +33,8 @@ enum cachefiles_obj_ref_trace { cachefiles_obj_see_withdrawal, cachefiles_obj_get_ondemand_fd, cachefiles_obj_put_ondemand_fd, + cachefiles_obj_get_read_req, + cachefiles_obj_put_read_req, }; enum fscache_why_object_killed { @@ -127,7 +129,11 @@ enum cachefiles_error_trace { EM(cachefiles_obj_see_lookup_cookie, "SEE lookup_cookie") \ EM(cachefiles_obj_see_lookup_failed, "SEE lookup_failed") \ EM(cachefiles_obj_see_withdraw_cookie, "SEE withdraw_cookie") \ - E_(cachefiles_obj_see_withdrawal, "SEE withdrawal") + EM(cachefiles_obj_see_withdrawal, "SEE withdrawal") \ + EM(cachefiles_obj_get_ondemand_fd, "GET ondemand_fd") \ + EM(cachefiles_obj_put_ondemand_fd, "PUT ondemand_fd") \ + EM(cachefiles_obj_get_read_req, "GET read_req") \ + E_(cachefiles_obj_put_read_req, "PUT read_req") #define cachefiles_coherency_traces \ EM(cachefiles_coherency_check_aux, "BAD aux ") \ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index d801409b33cfe..d55e53ac91bd2 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -135,6 +135,7 @@ IF_HAVE_PG_ARCH_X(arch_3) #define DEF_PAGETYPE_NAME(_name) { PG_##_name, __stringify(_name) } #define __def_pagetype_names \ + DEF_PAGETYPE_NAME(hugetlb), \ DEF_PAGETYPE_NAME(offline), \ DEF_PAGETYPE_NAME(guard), \ DEF_PAGETYPE_NAME(table), \ diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index ba2d96a1bc2f9..f50fcafc69de2 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -609,7 +609,7 @@ TRACE_EVENT(rpcgss_context, __field(unsigned int, timeout) __field(u32, window_size) __field(int, len) - __string(acceptor, data) + __string_len(acceptor, data, len) ), TP_fast_assign( @@ -618,7 +618,7 @@ TRACE_EVENT(rpcgss_context, __entry->timeout = timeout; __entry->window_size = window_size; __entry->len = len; - strncpy(__get_str(acceptor), data, len); + __assign_str(acceptor, data); ), TP_printk("win_size=%u expiry=%lu now=%lu timeout=%u acceptor=%.*s", diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 87b8de9b6c1c4..ecf9da5462359 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -83,7 +83,7 @@ EM(rxrpc_badmsg_bad_abort, "bad-abort") \ EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \ EM(rxrpc_badmsg_short_ack, "short-ack") \ - EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \ + EM(rxrpc_badmsg_short_ack_trailer, "short-ack-trailer") \ EM(rxrpc_badmsg_short_hdr, "short-hdr") \ EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \ EM(rxrpc_badmsg_zero_call, "zero-call") \ diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 80f37a0d40d7d..6f49952f1e3c4 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -115,13 +115,11 @@ #define F_GETSIG 11 /* for sockets. */ #endif -#if __BITS_PER_LONG == 32 || defined(__KERNEL__) #ifndef F_GETLK64 #define F_GETLK64 12 /* using 'struct flock64' */ #define F_SETLK64 13 #define F_SETLKW64 14 #endif -#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */ #ifndef F_SETOWN_EX #define F_SETOWN_EX 15 diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index 77d7ff0d5b110..c3d8dc7512971 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -68,6 +68,13 @@ extern "C" { */ #define NOUVEAU_GETPARAM_VRAM_USED 19 +/* + * NOUVEAU_GETPARAM_HAS_VMA_TILEMODE + * + * Query whether tile mode and PTE kind are accepted with VM allocs or not. + */ +#define NOUVEAU_GETPARAM_HAS_VMA_TILEMODE 20 + struct drm_nouveau_getparam { __u64 param; __u64 value; diff --git a/include/uapi/linux/apparmor.h b/include/uapi/linux/apparmor.h new file mode 100644 index 0000000000000..c0c9b13a548fe --- /dev/null +++ b/include/uapi/linux/apparmor.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_APPARMOR_H +#define _UAPI_LINUX_APPARMOR_H + +#include + +#define APPARMOR_MODESET_AUDIT 1 +#define APPARMOR_MODESET_ALLOWED 2 +#define APPARMOR_MODESET_ENFORCE 4 +#define APPARMOR_MODESET_HINT 8 +#define APPARMOR_MODESET_STATUS 16 +#define APPARMOR_MODESET_ERROR 32 +#define APPARMOR_MODESET_KILL 64 +#define APPARMOR_MODESET_USER 128 + +#define APPARMOR_FLAG_NOCACHE 1 + +enum apparmor_notif_type { + APPARMOR_NOTIF_RESP_PERM, + APPARMOR_NOTIF_CANCEL, + APPARMOR_NOTIF_INTERUPT, + APPARMOR_NOTIF_ALIVE, + APPARMOR_NOTIF_OP, + APPARMOR_NOTIF_RESP_NAME, +}; + +#define APPARMOR_NOTIFY_VERSION 3 + +/* base notification struct embedded as head of notifications to userspace */ +struct apparmor_notif_common { + __u16 len; /* actual len data */ + __u16 version; /* interface version */ +} __attribute__((packed)); + +struct apparmor_notif_filter { + struct apparmor_notif_common base; + __u32 modeset; /* which notification mode */ + __u32 ns; /* offset into data */ + __u32 filter; /* offset into data */ + + __u8 data[]; +} __attribute__((packed)); + +// flags +#define URESPONSE_NO_CACHE 1 +#define URESPONSE_LOOKUP 2 +#define URESPONSE_PROFILE 4 +#define URESPONSE_TAILGLOB 8 + +struct apparmor_notif { + struct apparmor_notif_common base; + __u16 ntype; /* notify type */ + __u8 signalled; + __u8 flags; + __u64 id; /* unique id, not gloablly unique*/ + __s32 error; /* error if unchanged */ +} __attribute__((packed)); + + +struct apparmor_notif_update { + struct apparmor_notif base; + __u16 ttl; /* max keep alives left */ +} __attribute__((packed)); + +/* userspace response to notification that expects a response */ +struct apparmor_notif_resp_perm { + struct apparmor_notif base; + __s32 error; /* error if unchanged */ + __u32 allow; + __u32 deny; +} __attribute__((packed)); + +struct apparmor_notif_resp_name { + union { + struct apparmor_notif base; + struct apparmor_notif_resp_perm perm; + }; + __u32 name; + __u8 data[]; +} __attribute__((packed)); + +union apparmor_notif_resp { + struct apparmor_notif base; + struct apparmor_notif_resp_perm perm; + struct apparmor_notif_resp_name name; +} __attribute__((packed)); + +struct apparmor_notif_op { + struct apparmor_notif base; + __u32 allow; + __u32 deny; + pid_t pid; /* pid of task causing notification */ + __u32 label; /* offset into data */ + __u16 class; + __u16 op; +} __attribute__((packed)); + +struct apparmor_notif_file { + struct apparmor_notif_op base; + uid_t subj_uid, obj_uid; + __u32 name; /* offset into data */ + + __u8 data[]; +} __attribute__((packed)); + +union apparmor_notif_all { + struct apparmor_notif_common common; + struct apparmor_notif_filter filter; + struct apparmor_notif base; + struct apparmor_notif_op op; + struct apparmor_notif_file file; + union apparmor_notif_resp respnse; +}; + +#define APPARMOR_IOC_MAGIC 0xF8 + +/* Flags for apparmor notification fd ioctl. */ + +#define APPARMOR_NOTIF_SET_FILTER _IOW(APPARMOR_IOC_MAGIC, 0, \ + struct apparmor_notif_filter *) +#define APPARMOR_NOTIF_GET_FILTER _IOR(APPARMOR_IOC_MAGIC, 1, \ + struct apparmor_notif_filter *) +#define APPARMOR_NOTIF_IS_ID_VALID _IOR(APPARMOR_IOC_MAGIC, 3, \ + __u64) +/* RECV/SEND from userspace pov */ +#define APPARMOR_NOTIF_RECV _IOWR(APPARMOR_IOC_MAGIC, 4, \ + struct apparmor_notif *) +#define APPARMOR_NOTIF_SEND _IOWR(APPARMOR_IOC_MAGIC, 5, \ + union apparmor_notif_resp *) + +#endif /* _UAPI_LINUX_APPARMOR_H */ diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index d676ed2b246ec..bed324162a7c1 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -143,6 +143,8 @@ #define AUDIT_MAC_UNLBL_STCDEL 1417 /* NetLabel: del a static label */ #define AUDIT_MAC_CALIPSO_ADD 1418 /* NetLabel: add CALIPSO DOI entry */ #define AUDIT_MAC_CALIPSO_DEL 1419 /* NetLabel: del CALIPSO DOI entry */ +#define AUDIT_MAC_TASK_CONTEXTS 1420 /* Multiple LSM task contexts */ +#define AUDIT_MAC_OBJ_CONTEXTS 1421 /* Multiple LSM objext contexts */ #define AUDIT_FIRST_KERN_ANOM_MSG 1700 #define AUDIT_LAST_KERN_ANOM_MSG 1799 diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 754e68ca8744c..83f31916e2635 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7040,7 +7040,7 @@ struct bpf_fib_lookup { /* output: MTU value */ __u16 mtu_result; - }; + } __attribute__((packed, aligned(2))); /* input: L3 device index for lookup * output: device index from FIB lookup */ diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index f8bc34a6bcfa2..cdf6ad872149c 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -92,6 +92,7 @@ struct btrfs_qgroup_limit { * struct btrfs_qgroup_inherit.flags */ #define BTRFS_QGROUP_INHERIT_SET_LIMITS (1ULL << 0) +#define BTRFS_QGROUP_INHERIT_FLAGS_SUPP (BTRFS_QGROUP_INHERIT_SET_LIMITS) struct btrfs_qgroup_inherit { __u64 flags; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ab9bcff96e4da..4345ceae5d99d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1378,6 +1378,7 @@ enum { IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ IFLA_VXLAN_LOCALBYPASS, IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */ + IFLA_VXLAN_FAN_MAP = 33, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 102119628ff54..f1401060d5b59 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -77,6 +77,10 @@ enum { IFLA_IPTUN_ENCAP_DPORT, IFLA_IPTUN_COLLECT_METADATA, IFLA_IPTUN_FWMARK, + + __IFLA_IPTUN_VENDOR_BREAK, /* Ensure new entries do not hit the below. */ + IFLA_IPTUN_FAN_MAP = 33, + __IFLA_IPTUN_MAX, }; #define IFLA_IPTUN_MAX (__IFLA_IPTUN_MAX - 1) @@ -182,4 +186,19 @@ enum { (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT | \ TUNNEL_GTP_OPT) +enum { + IFLA_FAN_UNSPEC, + IFLA_FAN_MAPPING, + __IFLA_FAN_MAX, +}; + +#define IFLA_FAN_MAX (__IFLA_FAN_MAX - 1) + +struct ifla_fan_map { + __be32 underlay; + __be32 overlay; + __u16 underlay_prefix; + __u16 overlay_prefix; +}; + #endif /* _UAPI_IF_TUNNEL_H_ */ diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 022a520e31fc2..03edf2ccdf6c8 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -602,6 +602,7 @@ #define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ #define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */ +#define KEY_REFRESH_RATE_TOGGLE 0x232 /* Display refresh rate toggle */ #define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ #define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index f0ed68974c543..5fdaf0ab460da 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -912,14 +912,25 @@ enum kfd_dbg_trap_exception_code { KFD_EC_MASK(EC_DEVICE_NEW)) #define KFD_EC_MASK_PROCESS (KFD_EC_MASK(EC_PROCESS_RUNTIME) | \ KFD_EC_MASK(EC_PROCESS_DEVICE_REMOVE)) +#define KFD_EC_MASK_PACKET (KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_DIM_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_CODE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_RESERVED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_UNSUPPORTED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_VENDOR_UNSUPPORTED)) /* Checks for exception code types for KFD search */ +#define KFD_DBG_EC_IS_VALID(ecode) (ecode > EC_NONE && ecode < EC_MAX) #define KFD_DBG_EC_TYPE_IS_QUEUE(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE)) #define KFD_DBG_EC_TYPE_IS_DEVICE(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE)) #define KFD_DBG_EC_TYPE_IS_PROCESS(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS)) +#define KFD_DBG_EC_TYPE_IS_PACKET(ecode) \ + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PACKET)) /* Runtime enable states */ diff --git a/include/uapi/linux/netfilter/xt_connmark.h b/include/uapi/linux/netfilter/xt_connmark.h index 41b578ccd03b8..36cc956ead1ae 100644 --- a/include/uapi/linux/netfilter/xt_connmark.h +++ b/include/uapi/linux/netfilter/xt_connmark.h @@ -1,37 +1,7 @@ -/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ -/* Copyright (C) 2002,2004 MARA Systems AB - * by Henrik Nordstrom - */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _XT_CONNMARK_H_target +#define _XT_CONNMARK_H_target -#ifndef _XT_CONNMARK_H -#define _XT_CONNMARK_H +#include -#include - -enum { - XT_CONNMARK_SET = 0, - XT_CONNMARK_SAVE, - XT_CONNMARK_RESTORE -}; - -enum { - D_SHIFT_LEFT = 0, - D_SHIFT_RIGHT, -}; - -struct xt_connmark_tginfo1 { - __u32 ctmark, ctmask, nfmask; - __u8 mode; -}; - -struct xt_connmark_tginfo2 { - __u32 ctmark, ctmask, nfmask; - __u8 shift_dir, shift_bits, mode; -}; - -struct xt_connmark_mtinfo1 { - __u32 mark, mask; - __u8 invert; -}; - -#endif /*_XT_CONNMARK_H*/ +#endif /*_XT_CONNMARK_H_target*/ diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index db6c8588c1d0c..9b77cfc42efa3 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -159,16 +159,8 @@ struct rfkill_event_ext { * old behaviour for all userspace, unless it explicitly opts in to the * rules outlined here by using the new &struct rfkill_event_ext. * - * Additionally, some other userspace (bluez, g-s-d) was reading with a - * large size but as streaming reads rather than message-based, or with - * too strict checks for the returned size. So eventually, we completely - * reverted this, and extended messages need to be opted in to by using - * an ioctl: - * - * ioctl(fd, RFKILL_IOCTL_MAX_SIZE, sizeof(struct rfkill_event_ext)); - * - * Userspace using &struct rfkill_event_ext and the ioctl must adhere to - * the following rules: + * Userspace using &struct rfkill_event_ext must adhere to the following + * rules * * 1. accept short writes, optionally using them to detect that it's * running on an older kernel; @@ -183,8 +175,6 @@ struct rfkill_event_ext { #define RFKILL_IOC_MAGIC 'R' #define RFKILL_IOC_NOINPUT 1 #define RFKILL_IOCTL_NOINPUT _IO(RFKILL_IOC_MAGIC, RFKILL_IOC_NOINPUT) -#define RFKILL_IOC_MAX_SIZE 2 -#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_MAX_SIZE, __u32) /* and that's all userspace gets */ diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 8981f00204db5..31bd38d17cafd 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -153,7 +153,7 @@ enum KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */ KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */ KERN_PANIC_ON_WARN=77, /* int: call panic() in WARN() functions */ - KERN_PANIC_PRINT=78, /* ulong: bitmask to print system info on panic */ + KERN_PANIC_PRINT=78, /* unsigned long: bitmask to print system info on panic */ }; diff --git a/include/uapi/linux/tty_flags.h b/include/uapi/linux/tty_flags.h index cf25056d4b27e..03f0a7cfca2e5 100644 --- a/include/uapi/linux/tty_flags.h +++ b/include/uapi/linux/tty_flags.h @@ -32,6 +32,7 @@ #define ASYNCB_AUTOPROBE 15 /* [x] Port was autoprobed by PCI/PNP code */ #define ASYNCB_MAGIC_MULTIPLIER 16 /* Use special CLK or divisor */ #define ASYNCB_LAST_USER 16 +#define ASYNCB_INITIALIZED 31 /* Serial port was initialized */ /* * Internal flags used only by kernel (read-only) @@ -40,7 +41,6 @@ * TTY_PORT_ flags in the iflags field (and not userspace-visible) */ #ifndef __KERNEL__ -#define ASYNCB_INITIALIZED 31 /* Serial port was initialized */ #define ASYNCB_SUSPENDED 30 /* Serial port is suspended */ #define ASYNCB_NORMAL_ACTIVE 29 /* Normal device is active */ #define ASYNCB_BOOT_AUTOCONF 28 /* Autoconfigure port on bootup */ diff --git a/include/uapi/linux/virtio_bt.h b/include/uapi/linux/virtio_bt.h index af798f4c96804..3cc7d633456b6 100644 --- a/include/uapi/linux/virtio_bt.h +++ b/include/uapi/linux/virtio_bt.h @@ -13,7 +13,6 @@ enum virtio_bt_config_type { VIRTIO_BT_CONFIG_TYPE_PRIMARY = 0, - VIRTIO_BT_CONFIG_TYPE_AMP = 1, }; enum virtio_bt_config_vendor { diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index ef3810dee7efa..a8208492e8227 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -240,7 +240,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ 0x5 #define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO 0x6 -struct __packed virtio_admin_cmd_hdr { +struct virtio_admin_cmd_hdr { __le16 opcode; /* * 1 - SR-IOV @@ -252,20 +252,20 @@ struct __packed virtio_admin_cmd_hdr { __le64 group_member_id; }; -struct __packed virtio_admin_cmd_status { +struct virtio_admin_cmd_status { __le16 status; __le16 status_qualifier; /* Unused, reserved for future extensions. */ __u8 reserved2[4]; }; -struct __packed virtio_admin_cmd_legacy_wr_data { +struct virtio_admin_cmd_legacy_wr_data { __u8 offset; /* Starting offset of the register(s) to write. */ __u8 reserved[7]; __u8 registers[]; }; -struct __packed virtio_admin_cmd_legacy_rd_data { +struct virtio_admin_cmd_legacy_rd_data { __u8 offset; /* Starting offset of the register(s) to read. */ }; @@ -275,7 +275,7 @@ struct __packed virtio_admin_cmd_legacy_rd_data { #define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4 -struct __packed virtio_admin_cmd_notify_info_data { +struct virtio_admin_cmd_notify_info_data { __u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */ __u8 bar; /* BAR of the member or the owner device */ __u8 padding[6]; diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h index c72ce387286ad..30a5c1a593764 100644 --- a/include/uapi/scsi/scsi_bsg_mpi3mr.h +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -382,7 +382,7 @@ struct mpi3mr_bsg_in_reply_buf { __u8 mpi_reply_type; __u8 rsvd1; __u16 rsvd2; - __u8 reply_buf[1]; + __u8 reply_buf[]; }; /** diff --git a/init/Kconfig b/init/Kconfig index bee58f7468c36..e094e57ec456a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -376,6 +376,15 @@ config DEFAULT_HOSTNAME but you may wish to use a different default here to make a minimal system more usable with less configuration. +config VERSION_SIGNATURE + string "Arbitrary version signature" + help + This string will be created in a file, /proc/version_signature. It + is useful in determining arbitrary data about your kernel. For instance, + if you have several kernels of the same version, but need to keep track + of a revision of the same kernel, but not affect it's ability to load + compatible modules, this is the easiest way to do that. + config SYSVIPC bool "System V IPC" help @@ -743,8 +752,8 @@ config LOG_CPU_MAX_BUF_SHIFT int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)" depends on SMP range 0 21 - default 12 if !BASE_SMALL - default 0 if BASE_SMALL + default 0 if BASE_SMALL != 0 + default 12 depends on PRINTK help This option allows to increase the default ring buffer size @@ -1904,11 +1913,10 @@ config RUST bool "Rust support" depends on HAVE_RUST depends on RUST_IS_AVAILABLE - depends on !MODVERSIONS + depends on !CFI_CLANG depends on !GCC_PLUGINS depends on !RANDSTRUCT depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE - select CONSTRUCTORS help Enables Rust support in the kernel. diff --git a/init/do_mounts.c b/init/do_mounts.c index 279ad28bf4fb1..eb29443dc67cb 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -461,6 +461,8 @@ static dev_t __init parse_root_device(char *root_device_name) */ void __init prepare_namespace(void) { + int err; + if (root_delay) { printk(KERN_INFO "Waiting %d sec before mounting root device...\n", root_delay); @@ -491,6 +493,13 @@ void __init prepare_namespace(void) devtmpfs_mount(); init_mount(".", "/", NULL, MS_MOVE, NULL); init_chroot("."); +#ifdef CONFIG_BLOCK + /* recreate the /dev/root */ + err = create_dev("/dev/root", ROOT_DEV); + + if (err < 0) + pr_emerg("Failed to create /dev/root: %d\n", err); +#endif } static bool is_tmpfs; diff --git a/init/initramfs.c b/init/initramfs.c index 76deb48c38cb1..b607d3463b477 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -683,7 +683,7 @@ static void __init populate_initrd_image(char *err) printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", err); - file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700); + file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700); if (IS_ERR(file)) return; diff --git a/init/main.c b/init/main.c index e24b0780fdff7..69828618cb6e4 100644 --- a/init/main.c +++ b/init/main.c @@ -88,6 +88,7 @@ #include #include #include +#include #include #include #include @@ -484,6 +485,11 @@ static int __init warn_bootconfig(char *str) early_param("bootconfig", warn_bootconfig); +bool __init cmdline_has_extra_options(void) +{ + return extra_command_line || extra_init_args; +} + /* Change NUL term back to "=", to make "param" the whole string. */ static void __init repair_env_string(char *param, char *val) { @@ -603,7 +609,6 @@ static int __init rdinit_setup(char *str) __setup("rdinit=", rdinit_setup); #ifndef CONFIG_SMP -static const unsigned int setup_max_cpus = NR_CPUS; static inline void setup_nr_cpu_ids(void) { } static inline void smp_prepare_cpus(unsigned int maxcpus) { } #endif @@ -629,6 +634,8 @@ static void __init setup_command_line(char *command_line) if (!saved_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen); + len = xlen + strlen(command_line) + 1; + static_command_line = memblock_alloc(len, SMP_CACHE_BYTES); if (!static_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len); @@ -1402,11 +1409,11 @@ static void mark_readonly(void) if (rodata_enabled) { /* * load_module() results in W+X mappings, which are cleaned - * up with call_rcu(). Let's make sure that queued work is + * up with init_free_wq. Let's make sure that queued work is * flushed so that we don't hit false positives looking for * insecure pages which are W+X. */ - rcu_barrier(); + flush_module_init_free_work(); mark_rodata_ro(); rodata_test(); } else diff --git a/init/version-timestamp.c b/init/version-timestamp.c index 043cbf80a766d..649275e25ff4b 100644 --- a/init/version-timestamp.c +++ b/init/version-timestamp.c @@ -27,4 +27,8 @@ struct uts_namespace init_uts_ns = { /* FIXED STRINGS! Don't touch! */ const char linux_banner[] = "Linux version " UTS_RELEASE " (" LINUX_COMPILE_BY "@" - LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION "\n"; + LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION +#ifdef CONFIG_VERSION_SIGNATURE + " (" CONFIG_VERSION_SIGNATURE ")" +#endif + "\n"; diff --git a/io_uring/futex.c b/io_uring/futex.c index 3c3575303c3d0..792a03df58dea 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -159,6 +159,7 @@ bool io_futex_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, hlist_for_each_entry_safe(req, tmp, &ctx->futex_list, hash_node) { if (!io_match_task_safe(req, task, cancel_all)) continue; + hlist_del_init(&req->hash_node); __io_futex_cancel(ctx, req); found = true; } diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 522196dfb0ff5..8a99aabcac2c3 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -25,10 +25,10 @@ #define WORKER_IDLE_TIMEOUT (5 * HZ) enum { - IO_WORKER_F_UP = 1, /* up and active */ - IO_WORKER_F_RUNNING = 2, /* account as running */ - IO_WORKER_F_FREE = 4, /* worker on free list */ - IO_WORKER_F_BOUND = 8, /* is doing bounded work */ + IO_WORKER_F_UP = 0, /* up and active */ + IO_WORKER_F_RUNNING = 1, /* account as running */ + IO_WORKER_F_FREE = 2, /* worker on free list */ + IO_WORKER_F_BOUND = 3, /* is doing bounded work */ }; enum { @@ -44,7 +44,8 @@ enum { */ struct io_worker { refcount_t ref; - unsigned flags; + int create_index; + unsigned long flags; struct hlist_nulls_node nulls_node; struct list_head all_list; struct task_struct *task; @@ -58,7 +59,6 @@ struct io_worker { unsigned long create_state; struct callback_head create_work; - int create_index; union { struct rcu_head rcu; @@ -165,7 +165,7 @@ static inline struct io_wq_acct *io_work_get_acct(struct io_wq *wq, static inline struct io_wq_acct *io_wq_get_acct(struct io_worker *worker) { - return io_get_acct(worker->wq, worker->flags & IO_WORKER_F_BOUND); + return io_get_acct(worker->wq, test_bit(IO_WORKER_F_BOUND, &worker->flags)); } static void io_worker_ref_put(struct io_wq *wq) @@ -225,7 +225,7 @@ static void io_worker_exit(struct io_worker *worker) wait_for_completion(&worker->ref_done); raw_spin_lock(&wq->lock); - if (worker->flags & IO_WORKER_F_FREE) + if (test_bit(IO_WORKER_F_FREE, &worker->flags)) hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); raw_spin_unlock(&wq->lock); @@ -410,7 +410,7 @@ static void io_wq_dec_running(struct io_worker *worker) struct io_wq_acct *acct = io_wq_get_acct(worker); struct io_wq *wq = worker->wq; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; if (!atomic_dec_and_test(&acct->nr_running)) @@ -430,8 +430,8 @@ static void io_wq_dec_running(struct io_worker *worker) */ static void __io_worker_busy(struct io_wq *wq, struct io_worker *worker) { - if (worker->flags & IO_WORKER_F_FREE) { - worker->flags &= ~IO_WORKER_F_FREE; + if (test_bit(IO_WORKER_F_FREE, &worker->flags)) { + clear_bit(IO_WORKER_F_FREE, &worker->flags); raw_spin_lock(&wq->lock); hlist_nulls_del_init_rcu(&worker->nulls_node); raw_spin_unlock(&wq->lock); @@ -444,8 +444,8 @@ static void __io_worker_busy(struct io_wq *wq, struct io_worker *worker) static void __io_worker_idle(struct io_wq *wq, struct io_worker *worker) __must_hold(wq->lock) { - if (!(worker->flags & IO_WORKER_F_FREE)) { - worker->flags |= IO_WORKER_F_FREE; + if (!test_bit(IO_WORKER_F_FREE, &worker->flags)) { + set_bit(IO_WORKER_F_FREE, &worker->flags); hlist_nulls_add_head_rcu(&worker->nulls_node, &wq->free_list); } } @@ -564,10 +564,7 @@ static void io_worker_handle_work(struct io_wq_acct *acct, * clear the stalled flag. */ work = io_get_next_work(acct, worker); - raw_spin_unlock(&acct->lock); if (work) { - __io_worker_busy(wq, worker); - /* * Make sure cancelation can find this, even before * it becomes the active work. That avoids a window @@ -578,9 +575,15 @@ static void io_worker_handle_work(struct io_wq_acct *acct, raw_spin_lock(&worker->lock); worker->next_work = work; raw_spin_unlock(&worker->lock); - } else { - break; } + + raw_spin_unlock(&acct->lock); + + if (!work) + break; + + __io_worker_busy(wq, worker); + io_assign_current_work(worker, work); __set_current_state(TASK_RUNNING); @@ -631,7 +634,8 @@ static int io_wq_worker(void *data) bool exit_mask = false, last_timeout = false; char buf[TASK_COMM_LEN]; - worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + set_mask_bits(&worker->flags, 0, + BIT(IO_WORKER_F_UP) | BIT(IO_WORKER_F_RUNNING)); snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); set_task_comm(current, buf); @@ -695,11 +699,11 @@ void io_wq_worker_running(struct task_struct *tsk) if (!worker) return; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; - if (worker->flags & IO_WORKER_F_RUNNING) + if (test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; - worker->flags |= IO_WORKER_F_RUNNING; + set_bit(IO_WORKER_F_RUNNING, &worker->flags); io_wq_inc_running(worker); } @@ -713,12 +717,12 @@ void io_wq_worker_sleeping(struct task_struct *tsk) if (!worker) return; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; - if (!(worker->flags & IO_WORKER_F_RUNNING)) + if (!test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; - worker->flags &= ~IO_WORKER_F_RUNNING; + clear_bit(IO_WORKER_F_RUNNING, &worker->flags); io_wq_dec_running(worker); } @@ -732,7 +736,7 @@ static void io_init_new_worker(struct io_wq *wq, struct io_worker *worker, raw_spin_lock(&wq->lock); hlist_nulls_add_head_rcu(&worker->nulls_node, &wq->free_list); list_add_tail_rcu(&worker->all_list, &wq->all_list); - worker->flags |= IO_WORKER_F_FREE; + set_bit(IO_WORKER_F_FREE, &worker->flags); raw_spin_unlock(&wq->lock); wake_up_new_task(tsk); } @@ -838,7 +842,7 @@ static bool create_io_worker(struct io_wq *wq, int index) init_completion(&worker->ref_done); if (index == IO_WQ_ACCT_BOUND) - worker->flags |= IO_WORKER_F_BOUND; + set_bit(IO_WORKER_F_BOUND, &worker->flags); tsk = create_io_thread(io_wq_worker, worker, NUMA_NO_NODE); if (!IS_ERR(tsk)) { @@ -924,8 +928,12 @@ static bool io_wq_work_match_item(struct io_wq_work *work, void *data) void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) { struct io_wq_acct *acct = io_work_get_acct(wq, work); - struct io_cb_cancel_data match; - unsigned work_flags = work->flags; + unsigned long work_flags = work->flags; + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_item, + .data = work, + .cancel_all = false, + }; bool do_create; /* @@ -963,10 +971,6 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) raw_spin_unlock(&wq->lock); /* fatal condition, failed to create the first worker */ - match.fn = io_wq_work_match_item, - match.data = work, - match.cancel_all = false, - io_acct_cancel_pending_work(wq, acct, &match); } } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index cd9a137ad6cef..dc0235ff472d3 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -152,6 +152,7 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, static void io_queue_sqe(struct io_kiocb *req); struct kmem_cache *req_cachep; +static struct workqueue_struct *iou_wq __ro_after_init; static int __read_mostly sysctl_io_uring_disabled; static int __read_mostly sysctl_io_uring_group = -1; @@ -353,7 +354,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) err: kfree(ctx->cancel_table.hbs); kfree(ctx->cancel_table_locked.hbs); - kfree(ctx->io_bl); xa_destroy(&ctx->io_bl_xa); kfree(ctx); return NULL; @@ -949,6 +949,8 @@ bool io_fill_cqe_req_aux(struct io_kiocb *req, bool defer, s32 res, u32 cflags) u64 user_data = req->cqe.user_data; struct io_uring_cqe *cqe; + lockdep_assert(!io_wq_current_is_worker()); + if (!defer) return __io_post_aux_cqe(ctx, user_data, res, cflags, false); @@ -1176,12 +1178,11 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx, struct io_tw_state *ts) static unsigned int handle_tw_list(struct llist_node *node, struct io_ring_ctx **ctx, - struct io_tw_state *ts, - struct llist_node *last) + struct io_tw_state *ts) { unsigned int count = 0; - while (node && node != last) { + do { struct llist_node *next = node->next; struct io_kiocb *req = container_of(node, struct io_kiocb, io_task_work.node); @@ -1205,7 +1206,7 @@ static unsigned int handle_tw_list(struct llist_node *node, *ctx = NULL; cond_resched(); } - } + } while (node); return count; } @@ -1224,22 +1225,6 @@ static inline struct llist_node *io_llist_xchg(struct llist_head *head, return xchg(&head->first, new); } -/** - * io_llist_cmpxchg - possibly swap all entries in a lock-less list - * @head: the head of lock-less list to delete all entries - * @old: expected old value of the first entry of the list - * @new: new entry as the head of the list - * - * perform a cmpxchg on the first entry of the list. - */ - -static inline struct llist_node *io_llist_cmpxchg(struct llist_head *head, - struct llist_node *old, - struct llist_node *new) -{ - return cmpxchg(&head->first, old, new); -} - static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync) { struct llist_node *node = llist_del_all(&tctx->task_list); @@ -1274,9 +1259,7 @@ void tctx_task_work(struct callback_head *cb) struct io_ring_ctx *ctx = NULL; struct io_uring_task *tctx = container_of(cb, struct io_uring_task, task_work); - struct llist_node fake = {}; struct llist_node *node; - unsigned int loops = 0; unsigned int count = 0; if (unlikely(current->flags & PF_EXITING)) { @@ -1284,21 +1267,9 @@ void tctx_task_work(struct callback_head *cb) return; } - do { - loops++; - node = io_llist_xchg(&tctx->task_list, &fake); - count += handle_tw_list(node, &ctx, &ts, &fake); - - /* skip expensive cmpxchg if there are items in the list */ - if (READ_ONCE(tctx->task_list.first) != &fake) - continue; - if (ts.locked && !wq_list_empty(&ctx->submit_state.compl_reqs)) { - io_submit_flush_completions(ctx); - if (READ_ONCE(tctx->task_list.first) != &fake) - continue; - } - node = io_llist_cmpxchg(&tctx->task_list, &fake, NULL); - } while (node != &fake); + node = llist_del_all(&tctx->task_list); + if (node) + count = handle_tw_list(node, &ctx, &ts); ctx_flush_and_put(ctx, &ts); @@ -1306,7 +1277,7 @@ void tctx_task_work(struct callback_head *cb) if (unlikely(atomic_read(&tctx->in_cancel))) io_uring_drop_tctx_refs(current); - trace_io_uring_task_work_run(tctx, count, loops); + trace_io_uring_task_work_run(tctx, count, 1); } static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags) @@ -1420,7 +1391,20 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx) } } -static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts) +static bool io_run_local_work_continue(struct io_ring_ctx *ctx, int events, + int min_events) +{ + if (llist_empty(&ctx->work_llist)) + return false; + if (events < min_events) + return true; + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) + atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); + return false; +} + +static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts, + int min_events) { struct llist_node *node; unsigned int loops = 0; @@ -1449,18 +1433,20 @@ static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts) } loops++; - if (!llist_empty(&ctx->work_llist)) + if (io_run_local_work_continue(ctx, ret, min_events)) goto again; if (ts->locked) { io_submit_flush_completions(ctx); - if (!llist_empty(&ctx->work_llist)) + if (io_run_local_work_continue(ctx, ret, min_events)) goto again; } + trace_io_uring_local_work_run(ctx, ret, loops); return ret; } -static inline int io_run_local_work_locked(struct io_ring_ctx *ctx) +static inline int io_run_local_work_locked(struct io_ring_ctx *ctx, + int min_events) { struct io_tw_state ts = { .locked = true, }; int ret; @@ -1468,20 +1454,20 @@ static inline int io_run_local_work_locked(struct io_ring_ctx *ctx) if (llist_empty(&ctx->work_llist)) return 0; - ret = __io_run_local_work(ctx, &ts); + ret = __io_run_local_work(ctx, &ts, min_events); /* shouldn't happen! */ if (WARN_ON_ONCE(!ts.locked)) mutex_lock(&ctx->uring_lock); return ret; } -static int io_run_local_work(struct io_ring_ctx *ctx) +static int io_run_local_work(struct io_ring_ctx *ctx, int min_events) { struct io_tw_state ts = {}; int ret; ts.locked = mutex_trylock(&ctx->uring_lock); - ret = __io_run_local_work(ctx, &ts); + ret = __io_run_local_work(ctx, &ts, min_events); if (ts.locked) mutex_unlock(&ctx->uring_lock); @@ -1677,7 +1663,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) io_task_work_pending(ctx)) { u32 tail = ctx->cached_cq_tail; - (void) io_run_local_work_locked(ctx); + (void) io_run_local_work_locked(ctx, min); if (task_work_pending(current) || wq_list_empty(&ctx->iopoll_list)) { @@ -1966,6 +1952,29 @@ void io_wq_submit_work(struct io_wq_work *work) goto fail; } + /* + * If DEFER_TASKRUN is set, it's only allowed to post CQEs from the + * submitter task context. Final request completions are handed to the + * right context, however this is not the case of auxiliary CQEs, + * which is the main mean of operation for multishot requests. + * Don't allow any multishot execution from io-wq. It's more restrictive + * than necessary and also cleaner. + */ + if (req->flags & REQ_F_APOLL_MULTISHOT) { + err = -EBADFD; + if (!file_can_poll(req->file)) + goto fail; + if (req->file->f_flags & O_NONBLOCK || + req->file->f_mode & FMODE_NOWAIT) { + err = -ECANCELED; + if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK) + goto fail; + return; + } else { + req->flags &= ~REQ_F_APOLL_MULTISHOT; + } + } + if (req->flags & REQ_F_FORCE_ASYNC) { bool opcode_poll = def->pollin || def->pollout; @@ -2159,6 +2168,13 @@ static void io_init_req_drain(struct io_kiocb *req) } } +static __cold int io_init_fail_req(struct io_kiocb *req, int err) +{ + /* ensure per-opcode data is cleared if we fail before prep */ + memset(&req->cmd.data, 0, sizeof(req->cmd.data)); + return err; +} + static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) @@ -2179,29 +2195,29 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (unlikely(opcode >= IORING_OP_LAST)) { req->opcode = 0; - return -EINVAL; + return io_init_fail_req(req, -EINVAL); } def = &io_issue_defs[opcode]; if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) { /* enforce forwards compatibility on users */ if (sqe_flags & ~SQE_VALID_FLAGS) - return -EINVAL; + return io_init_fail_req(req, -EINVAL); if (sqe_flags & IOSQE_BUFFER_SELECT) { if (!def->buffer_select) - return -EOPNOTSUPP; + return io_init_fail_req(req, -EOPNOTSUPP); req->buf_index = READ_ONCE(sqe->buf_group); } if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS) ctx->drain_disabled = true; if (sqe_flags & IOSQE_IO_DRAIN) { if (ctx->drain_disabled) - return -EOPNOTSUPP; + return io_init_fail_req(req, -EOPNOTSUPP); io_init_req_drain(req); } } if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) { if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags)) - return -EACCES; + return io_init_fail_req(req, -EACCES); /* knock it to the slow queue path, will be drained there */ if (ctx->drain_active) req->flags |= REQ_F_FORCE_ASYNC; @@ -2214,9 +2230,9 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, } if (!def->ioprio && sqe->ioprio) - return -EINVAL; + return io_init_fail_req(req, -EINVAL); if (!def->iopoll && (ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; + return io_init_fail_req(req, -EINVAL); if (def->needs_file) { struct io_submit_state *state = &ctx->submit_state; @@ -2240,12 +2256,12 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->creds = xa_load(&ctx->personalities, personality); if (!req->creds) - return -EINVAL; + return io_init_fail_req(req, -EINVAL); get_cred(req->creds); ret = security_uring_override_creds(req->creds); if (ret) { put_cred(req->creds); - return ret; + return io_init_fail_req(req, ret); } req->flags |= REQ_F_CREDS; } @@ -2520,7 +2536,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx) { if (!llist_empty(&ctx->work_llist)) { __set_current_state(TASK_RUNNING); - if (io_run_local_work(ctx) > 0) + if (io_run_local_work(ctx, INT_MAX) > 0) return 0; } if (io_run_task_work() > 0) @@ -2543,7 +2559,7 @@ static bool current_pending_io(void) static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { - int io_wait, ret; + int ret; if (unlikely(READ_ONCE(ctx->check_cq))) return 1; @@ -2561,7 +2577,6 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, * can take into account that the task is waiting for IO - turns out * to be important for low QD IO. */ - io_wait = current->in_iowait; if (current_pending_io()) current->in_iowait = 1; ret = 0; @@ -2569,7 +2584,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, schedule(); else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS)) ret = -ETIME; - current->in_iowait = io_wait; + current->in_iowait = 0; return ret; } @@ -2588,26 +2603,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, if (!io_allowed_run_tw(ctx)) return -EEXIST; if (!llist_empty(&ctx->work_llist)) - io_run_local_work(ctx); + io_run_local_work(ctx, min_events); io_run_task_work(); io_cqring_overflow_flush(ctx); /* if user messes with these they will just get an early return */ if (__io_cqring_events_user(ctx) >= min_events) return 0; - if (sig) { -#ifdef CONFIG_COMPAT - if (in_compat_syscall()) - ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, - sigsz); - else -#endif - ret = set_user_sigmask(sig, sigsz); - - if (ret) - return ret; - } - init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; INIT_LIST_HEAD(&iowq.wq.entry); @@ -2624,13 +2626,25 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, iowq.timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } + if (sig) { +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, + sigsz); + else +#endif + ret = set_user_sigmask(sig, sigsz); + + if (ret) + return ret; + } + trace_io_uring_cqring_wait(ctx, min_events); do { + int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail); unsigned long check_cq; if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { - int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail); - atomic_set(&ctx->cq_wait_nr, nr_wait); set_current_state(TASK_INTERRUPTIBLE); } else { @@ -2649,7 +2663,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, */ io_run_task_work(); if (!llist_empty(&ctx->work_llist)) - io_run_local_work(ctx); + io_run_local_work(ctx, nr_wait); /* * Non-local task_work will be run on exit to userspace, but @@ -2720,7 +2734,7 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, struct page **page_array; unsigned int nr_pages; void *page_addr; - int ret, i; + int ret, i, pinned; *npages = 0; @@ -2734,12 +2748,12 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, if (!page_array) return ERR_PTR(-ENOMEM); - ret = pin_user_pages_fast(uaddr, nr_pages, FOLL_WRITE | FOLL_LONGTERM, - page_array); - if (ret != nr_pages) { -err: - io_pages_free(&page_array, ret > 0 ? ret : 0); - return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT); + + pinned = pin_user_pages_fast(uaddr, nr_pages, FOLL_WRITE | FOLL_LONGTERM, + page_array); + if (pinned != nr_pages) { + ret = (pinned < 0) ? pinned : -EFAULT; + goto free_pages; } page_addr = page_address(page_array[0]); @@ -2753,7 +2767,7 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, * didn't support this feature. */ if (PageHighMem(page_array[i])) - goto err; + goto free_pages; /* * No support for discontig pages for now, should either be a @@ -2762,13 +2776,17 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, * just fail them with EINVAL. */ if (page_address(page_array[i]) != page_addr) - goto err; + goto free_pages; page_addr += PAGE_SIZE; } *pages = page_array; *npages = nr_pages; return page_to_virt(page_array[0]); + +free_pages: + io_pages_free(&page_array, pinned > 0 ? pinned : 0); + return ERR_PTR(ret); } static void *io_rings_map(struct io_ring_ctx *ctx, unsigned long uaddr, @@ -2790,14 +2808,15 @@ static void io_rings_free(struct io_ring_ctx *ctx) if (!(ctx->flags & IORING_SETUP_NO_MMAP)) { io_mem_free(ctx->rings); io_mem_free(ctx->sq_sqes); - ctx->rings = NULL; - ctx->sq_sqes = NULL; } else { io_pages_free(&ctx->ring_pages, ctx->n_ring_pages); ctx->n_ring_pages = 0; io_pages_free(&ctx->sqe_pages, ctx->n_sqe_pages); ctx->n_sqe_pages = 0; } + + ctx->rings = NULL; + ctx->sq_sqes = NULL; } void *io_mem_alloc(size_t size) @@ -2919,7 +2938,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_wq_put_hash(ctx->hash_map); kfree(ctx->cancel_table.hbs); kfree(ctx->cancel_table_locked.hbs); - kfree(ctx->io_bl); xa_destroy(&ctx->io_bl_xa); kfree(ctx); } @@ -3154,7 +3172,7 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) * noise and overhead, there's no discernable change in runtime * over using system_wq. */ - queue_work(system_unbound_wq, &ctx->exit_work); + queue_work(iou_wq, &ctx->exit_work); } static int io_uring_release(struct inode *inode, struct file *file) @@ -3304,7 +3322,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) && io_allowed_defer_tw_run(ctx)) - ret |= io_run_local_work(ctx) > 0; + ret |= io_run_local_work(ctx, INT_MAX) > 0; ret |= io_cancel_defer_files(ctx, task, cancel_all); mutex_lock(&ctx->uring_lock); ret |= io_poll_remove_all(ctx, task, cancel_all); @@ -3436,14 +3454,15 @@ static void *io_uring_validate_mmap_request(struct file *file, ptr = ctx->sq_sqes; break; case IORING_OFF_PBUF_RING: { + struct io_buffer_list *bl; unsigned int bgid; bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT; - rcu_read_lock(); - ptr = io_pbuf_get_address(ctx, bgid); - rcu_read_unlock(); - if (!ptr) - return ERR_PTR(-EINVAL); + bl = io_pbuf_get_bl(ctx, bgid); + if (IS_ERR(bl)) + return bl; + ptr = bl->buf_ring; + io_put_bl(ctx, bl); break; } default: @@ -3666,7 +3685,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, * it should handle ownership problems if any. */ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) - (void)io_run_local_work_locked(ctx); + (void)io_run_local_work_locked(ctx, min_complete); } mutex_unlock(&ctx->uring_lock); } @@ -4179,6 +4198,8 @@ static int __init io_uring_init(void) SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); + iou_wq = alloc_workqueue("iou_exit", WQ_UNBOUND, 64); + #ifdef CONFIG_SYSCTL register_sysctl_init("kernel", kernel_io_uring_disabled_table); #endif diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index d5495710c1787..c0cff024db7b4 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -301,7 +301,7 @@ static inline int io_run_task_work(void) static inline bool io_task_work_pending(struct io_ring_ctx *ctx) { - return task_work_pending(current) || !wq_list_empty(&ctx->work_llist); + return task_work_pending(current) || !llist_empty(&ctx->work_llist); } static inline void io_tw_lock(struct io_ring_ctx *ctx, struct io_tw_state *ts) diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 18df5a9d2f5e7..2c9f47a25cd7e 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -17,8 +17,6 @@ #define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf)) -#define BGID_ARRAY 64 - /* BIDs are addressed by a 16-bit field in a CQE */ #define MAX_BIDS_PER_BGID (1 << 16) @@ -40,13 +38,9 @@ struct io_buf_free { int inuse; }; -static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, - struct io_buffer_list *bl, - unsigned int bgid) +static inline struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, + unsigned int bgid) { - if (bl && bgid < BGID_ARRAY) - return &bl[bgid]; - return xa_load(&ctx->io_bl_xa, bgid); } @@ -55,7 +49,7 @@ static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, { lockdep_assert_held(&ctx->uring_lock); - return __io_buffer_get_list(ctx, ctx->io_bl, bgid); + return __io_buffer_get_list(ctx, bgid); } static int io_buffer_add_list(struct io_ring_ctx *ctx, @@ -67,11 +61,7 @@ static int io_buffer_add_list(struct io_ring_ctx *ctx, * always under the ->uring_lock, but the RCU lookup from mmap does. */ bl->bgid = bgid; - smp_store_release(&bl->is_ready, 1); - - if (bgid < BGID_ARRAY) - return 0; - + atomic_set(&bl->refs, 1); return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } @@ -180,7 +170,8 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, req->buf_list = bl; req->buf_index = buf->bid; - if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) { + if (issue_flags & IO_URING_F_UNLOCKED || + (req->file && !file_can_poll(req->file))) { /* * If we came in unlocked, we have no choice but to consume the * buffer here, otherwise nothing ensures that the buffer won't @@ -217,24 +208,6 @@ void __user *io_buffer_select(struct io_kiocb *req, size_t *len, return ret; } -static __cold int io_init_bl_list(struct io_ring_ctx *ctx) -{ - struct io_buffer_list *bl; - int i; - - bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL); - if (!bl) - return -ENOMEM; - - for (i = 0; i < BGID_ARRAY; i++) { - INIT_LIST_HEAD(&bl[i].buf_list); - bl[i].bgid = i; - } - - smp_store_release(&ctx->io_bl, bl); - return 0; -} - /* * Mark the given mapped range as free for reuse */ @@ -303,24 +276,24 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, return i; } +void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) +{ + if (atomic_dec_and_test(&bl->refs)) { + __io_remove_buffers(ctx, bl, -1U); + kfree_rcu(bl, rcu); + } +} + void io_destroy_buffers(struct io_ring_ctx *ctx) { struct io_buffer_list *bl; struct list_head *item, *tmp; struct io_buffer *buf; unsigned long index; - int i; - - for (i = 0; i < BGID_ARRAY; i++) { - if (!ctx->io_bl) - break; - __io_remove_buffers(ctx, &ctx->io_bl[i], -1U); - } xa_for_each(&ctx->io_bl_xa, index, bl) { xa_erase(&ctx->io_bl_xa, bl->bgid); - __io_remove_buffers(ctx, bl, -1U); - kfree_rcu(bl, rcu); + io_put_bl(ctx, bl); } /* @@ -498,12 +471,6 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) io_ring_submit_lock(ctx, issue_flags); - if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) { - ret = io_init_bl_list(ctx); - if (ret) - goto err; - } - bl = io_buffer_get_list(ctx, p->bgid); if (unlikely(!bl)) { bl = kzalloc(sizeof(*bl), GFP_KERNEL_ACCOUNT); @@ -516,14 +483,9 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) if (ret) { /* * Doesn't need rcu free as it was never visible, but - * let's keep it consistent throughout. Also can't - * be a lower indexed array group, as adding one - * where lookup failed cannot happen. + * let's keep it consistent throughout. */ - if (p->bgid >= BGID_ARRAY) - kfree_rcu(bl, rcu); - else - WARN_ON_ONCE(1); + kfree_rcu(bl, rcu); goto err; } } @@ -688,12 +650,6 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) if (reg.ring_entries >= 65536) return -EINVAL; - if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) { - int ret = io_init_bl_list(ctx); - if (ret) - return ret; - } - bl = io_buffer_get_list(ctx, reg.bgid); if (bl) { /* if mapped buffer ring OR classic exists, don't allow */ @@ -742,11 +698,8 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) if (!bl->is_mapped) return -EINVAL; - __io_remove_buffers(ctx, bl, -1U); - if (bl->bgid >= BGID_ARRAY) { - xa_erase(&ctx->io_bl_xa, bl->bgid); - kfree_rcu(bl, rcu); - } + xa_erase(&ctx->io_bl_xa, bl->bgid); + io_put_bl(ctx, bl); return 0; } @@ -776,23 +729,35 @@ int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg) return 0; } -void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid) +struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx, + unsigned long bgid) { struct io_buffer_list *bl; + bool ret; - bl = __io_buffer_get_list(ctx, smp_load_acquire(&ctx->io_bl), bgid); - - if (!bl || !bl->is_mmap) - return NULL; /* - * Ensure the list is fully setup. Only strictly needed for RCU lookup - * via mmap, and in that case only for the array indexed groups. For - * the xarray lookups, it's either visible and ready, or not at all. + * We have to be a bit careful here - we're inside mmap and cannot grab + * the uring_lock. This means the buffer_list could be simultaneously + * going away, if someone is trying to be sneaky. Look it up under rcu + * so we know it's not going away, and attempt to grab a reference to + * it. If the ref is already zero, then fail the mapping. If successful, + * the caller will call io_put_bl() to drop the the reference at at the + * end. This may then safely free the buffer_list (and drop the pages) + * at that point, vm_insert_pages() would've already grabbed the + * necessary vma references. */ - if (!smp_load_acquire(&bl->is_ready)) - return NULL; - - return bl->buf_ring; + rcu_read_lock(); + bl = xa_load(&ctx->io_bl_xa, bgid); + /* must be a mmap'able buffer ring and have pages */ + ret = false; + if (bl && bl->is_mmap) + ret = atomic_inc_not_zero(&bl->refs); + rcu_read_unlock(); + + if (ret) + return bl; + + return ERR_PTR(-EINVAL); } /* diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index 53dfaa71a397c..038091a0047d4 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -25,12 +25,12 @@ struct io_buffer_list { __u16 head; __u16 mask; + atomic_t refs; + /* ring mapped provided buffers */ __u8 is_mapped; /* ring mapped provided buffers, but mmap'ed by application */ __u8 is_mmap; - /* bl is visible from an RCU point of view for lookup */ - __u8 is_ready; }; struct io_buffer { @@ -61,7 +61,9 @@ unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags); bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags); -void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid); +void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl); +struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx, + unsigned long bgid); static inline bool io_kbuf_recycle_ring(struct io_kiocb *req) { diff --git a/io_uring/net.c b/io_uring/net.c index 161622029147c..dbabe0058f1cb 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -78,19 +78,6 @@ struct io_sr_msg { */ #define MULTISHOT_MAX_RETRY 32 -static inline bool io_check_multishot(struct io_kiocb *req, - unsigned int issue_flags) -{ - /* - * When ->locked_cq is set we only allow to post CQEs from the original - * task context. Usual request completions will be handled in other - * generic paths but multipoll may decide to post extra cqes. - */ - return !(issue_flags & IO_URING_F_IOWQ) || - !(issue_flags & IO_URING_F_MULTISHOT) || - !req->ctx->task_complete; -} - int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown); @@ -204,16 +191,115 @@ static int io_setup_async_msg(struct io_kiocb *req, return -EAGAIN; } +#ifdef CONFIG_COMPAT +static int io_compat_msg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg, + struct compat_msghdr *msg, int ddir) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + struct compat_iovec __user *uiov; + int ret; + + if (copy_from_user(msg, sr->umsg_compat, sizeof(*msg))) + return -EFAULT; + + uiov = compat_ptr(msg->msg_iov); + if (req->flags & REQ_F_BUFFER_SELECT) { + compat_ssize_t clen; + + iomsg->free_iov = NULL; + if (msg->msg_iovlen == 0) { + sr->len = 0; + } else if (msg->msg_iovlen > 1) { + return -EINVAL; + } else { + if (!access_ok(uiov, sizeof(*uiov))) + return -EFAULT; + if (__get_user(clen, &uiov->iov_len)) + return -EFAULT; + if (clen < 0) + return -EINVAL; + sr->len = clen; + } + + return 0; + } + + iomsg->free_iov = iomsg->fast_iov; + ret = __import_iovec(ddir, (struct iovec __user *)uiov, msg->msg_iovlen, + UIO_FASTIOV, &iomsg->free_iov, + &iomsg->msg.msg_iter, true); + if (unlikely(ret < 0)) + return ret; + + return 0; +} +#endif + +static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg, + struct user_msghdr *msg, int ddir) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + int ret; + + if (copy_from_user(msg, sr->umsg, sizeof(*sr->umsg))) + return -EFAULT; + + if (req->flags & REQ_F_BUFFER_SELECT) { + if (msg->msg_iovlen == 0) { + sr->len = iomsg->fast_iov[0].iov_len = 0; + iomsg->fast_iov[0].iov_base = NULL; + iomsg->free_iov = NULL; + } else if (msg->msg_iovlen > 1) { + return -EINVAL; + } else { + if (copy_from_user(iomsg->fast_iov, msg->msg_iov, + sizeof(*msg->msg_iov))) + return -EFAULT; + sr->len = iomsg->fast_iov[0].iov_len; + iomsg->free_iov = NULL; + } + + return 0; + } + + iomsg->free_iov = iomsg->fast_iov; + ret = __import_iovec(ddir, msg->msg_iov, msg->msg_iovlen, UIO_FASTIOV, + &iomsg->free_iov, &iomsg->msg.msg_iter, false); + if (unlikely(ret < 0)) + return ret; + + return 0; +} + static int io_sendmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + struct user_msghdr msg; int ret; iomsg->msg.msg_name = &iomsg->addr; - iomsg->free_iov = iomsg->fast_iov; - ret = sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags, - &iomsg->free_iov); + iomsg->msg.msg_iter.nr_segs = 0; + +#ifdef CONFIG_COMPAT + if (unlikely(req->ctx->compat)) { + struct compat_msghdr cmsg; + + ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_SOURCE); + if (unlikely(ret)) + return ret; + + return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL); + } +#endif + + ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_SOURCE); + if (unlikely(ret)) + return ret; + + ret = __copy_msghdr(&iomsg->msg, &msg, NULL); + /* save msg_control as sys_sendmsg() overwrites it */ sr->msg_control = iomsg->msg.msg_control_user; return ret; @@ -225,7 +311,10 @@ int io_send_prep_async(struct io_kiocb *req) struct io_async_msghdr *io; int ret; - if (!zc->addr || req_has_async_data(req)) + if (req_has_async_data(req)) + return 0; + zc->done_io = 0; + if (!zc->addr) return 0; io = io_msg_alloc_async_prep(req); if (!io) @@ -252,8 +341,10 @@ static int io_setup_async_addr(struct io_kiocb *req, int io_sendmsg_prep_async(struct io_kiocb *req) { + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); int ret; + sr->done_io = 0; if (!io_msg_alloc_async_prep(req)) return -ENOMEM; ret = io_sendmsg_copy_hdr(req, req->async_data); @@ -273,6 +364,8 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + sr->done_io = 0; + if (req->opcode == IORING_OP_SEND) { if (READ_ONCE(sqe->__pad3[0])) return -EINVAL; @@ -295,7 +388,6 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif - sr->done_io = 0; return 0; } @@ -435,142 +527,79 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } -static bool io_recvmsg_multishot_overflow(struct io_async_msghdr *iomsg) +static int io_recvmsg_mshot_prep(struct io_kiocb *req, + struct io_async_msghdr *iomsg, + int namelen, size_t controllen) { - int hdr; - - if (iomsg->namelen < 0) - return true; - if (check_add_overflow((int)sizeof(struct io_uring_recvmsg_out), - iomsg->namelen, &hdr)) - return true; - if (check_add_overflow(hdr, (int)iomsg->controllen, &hdr)) - return true; + if ((req->flags & (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) == + (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) { + int hdr; + + if (unlikely(namelen < 0)) + return -EOVERFLOW; + if (check_add_overflow(sizeof(struct io_uring_recvmsg_out), + namelen, &hdr)) + return -EOVERFLOW; + if (check_add_overflow(hdr, controllen, &hdr)) + return -EOVERFLOW; + + iomsg->namelen = namelen; + iomsg->controllen = controllen; + return 0; + } - return false; + return 0; } -static int __io_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) +static int io_recvmsg_copy_hdr(struct io_kiocb *req, + struct io_async_msghdr *iomsg) { - struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); struct user_msghdr msg; int ret; - if (copy_from_user(&msg, sr->umsg, sizeof(*sr->umsg))) - return -EFAULT; - - ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr); - if (ret) - return ret; - - if (req->flags & REQ_F_BUFFER_SELECT) { - if (msg.msg_iovlen == 0) { - sr->len = iomsg->fast_iov[0].iov_len = 0; - iomsg->fast_iov[0].iov_base = NULL; - iomsg->free_iov = NULL; - } else if (msg.msg_iovlen > 1) { - return -EINVAL; - } else { - if (copy_from_user(iomsg->fast_iov, msg.msg_iov, sizeof(*msg.msg_iov))) - return -EFAULT; - sr->len = iomsg->fast_iov[0].iov_len; - iomsg->free_iov = NULL; - } - - if (req->flags & REQ_F_APOLL_MULTISHOT) { - iomsg->namelen = msg.msg_namelen; - iomsg->controllen = msg.msg_controllen; - if (io_recvmsg_multishot_overflow(iomsg)) - return -EOVERFLOW; - } - } else { - iomsg->free_iov = iomsg->fast_iov; - ret = __import_iovec(ITER_DEST, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, - &iomsg->free_iov, &iomsg->msg.msg_iter, - false); - if (ret > 0) - ret = 0; - } - - return ret; -} + iomsg->msg.msg_name = &iomsg->addr; + iomsg->msg.msg_iter.nr_segs = 0; #ifdef CONFIG_COMPAT -static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) -{ - struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); - struct compat_msghdr msg; - struct compat_iovec __user *uiov; - int ret; - - if (copy_from_user(&msg, sr->umsg_compat, sizeof(msg))) - return -EFAULT; + if (unlikely(req->ctx->compat)) { + struct compat_msghdr cmsg; - ret = __get_compat_msghdr(&iomsg->msg, &msg, &iomsg->uaddr); - if (ret) - return ret; - - uiov = compat_ptr(msg.msg_iov); - if (req->flags & REQ_F_BUFFER_SELECT) { - compat_ssize_t clen; - - iomsg->free_iov = NULL; - if (msg.msg_iovlen == 0) { - sr->len = 0; - } else if (msg.msg_iovlen > 1) { - return -EINVAL; - } else { - if (!access_ok(uiov, sizeof(*uiov))) - return -EFAULT; - if (__get_user(clen, &uiov->iov_len)) - return -EFAULT; - if (clen < 0) - return -EINVAL; - sr->len = clen; - } + ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_DEST); + if (unlikely(ret)) + return ret; - if (req->flags & REQ_F_APOLL_MULTISHOT) { - iomsg->namelen = msg.msg_namelen; - iomsg->controllen = msg.msg_controllen; - if (io_recvmsg_multishot_overflow(iomsg)) - return -EOVERFLOW; - } - } else { - iomsg->free_iov = iomsg->fast_iov; - ret = __import_iovec(ITER_DEST, (struct iovec __user *)uiov, msg.msg_iovlen, - UIO_FASTIOV, &iomsg->free_iov, - &iomsg->msg.msg_iter, true); - if (ret < 0) + ret = __get_compat_msghdr(&iomsg->msg, &cmsg, &iomsg->uaddr); + if (unlikely(ret)) return ret; - } - return 0; -} + return io_recvmsg_mshot_prep(req, iomsg, cmsg.msg_namelen, + cmsg.msg_controllen); + } #endif -static int io_recvmsg_copy_hdr(struct io_kiocb *req, - struct io_async_msghdr *iomsg) -{ - iomsg->msg.msg_name = &iomsg->addr; - iomsg->msg.msg_iter.nr_segs = 0; + ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_DEST); + if (unlikely(ret)) + return ret; -#ifdef CONFIG_COMPAT - if (req->ctx->compat) - return __io_compat_recvmsg_copy_hdr(req, iomsg); -#endif + ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr); + if (unlikely(ret)) + return ret; - return __io_recvmsg_copy_hdr(req, iomsg); + return io_recvmsg_mshot_prep(req, iomsg, msg.msg_namelen, + msg.msg_controllen); } int io_recvmsg_prep_async(struct io_kiocb *req) { + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + struct io_async_msghdr *iomsg; int ret; + sr->done_io = 0; if (!io_msg_alloc_async_prep(req)) return -ENOMEM; - ret = io_recvmsg_copy_hdr(req, req->async_data); + iomsg = req->async_data; + ret = io_recvmsg_copy_hdr(req, iomsg); if (!ret) req->flags |= REQ_F_NEED_CLEANUP; return ret; @@ -582,6 +611,8 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + sr->done_io = 0; + if (unlikely(sqe->file_index || sqe->addr2)) return -EINVAL; @@ -618,7 +649,6 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif - sr->done_io = 0; sr->nr_multishot_loops = 0; return 0; } @@ -803,9 +833,6 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) (sr->flags & IORING_RECVSEND_POLL_FIRST)) return io_setup_async_msg(req, kmsg, issue_flags); - if (!io_check_multishot(req, issue_flags)) - return io_setup_async_msg(req, kmsg, issue_flags); - retry_multishot: if (io_do_buffer_select(req)) { void __user *buf; @@ -881,7 +908,8 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) kfree(kmsg->free_iov); io_netmsg_recycle(req, issue_flags); req->flags &= ~REQ_F_NEED_CLEANUP; - } + } else if (ret == -EAGAIN) + return io_setup_async_msg(req, kmsg, issue_flags); return ret; } @@ -900,9 +928,6 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) (sr->flags & IORING_RECVSEND_POLL_FIRST)) return -EAGAIN; - if (!io_check_multishot(req, issue_flags)) - return -EAGAIN; - sock = sock_from_file(req->file); if (unlikely(!sock)) return -ENOTSOCK; @@ -1003,6 +1028,9 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *notif; + zc->done_io = 0; + req->flags |= REQ_F_POLL_NO_LAZY; + if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3))) return -EINVAL; /* we don't support IOSQE_CQE_SKIP_SUCCESS just yet */ @@ -1055,8 +1083,6 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (zc->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; - zc->done_io = 0; - #ifdef CONFIG_COMPAT if (req->ctx->compat) zc->msg_flags |= MSG_CMSG_COMPAT; @@ -1239,6 +1265,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags) if (req_has_async_data(req)) { kmsg = req->async_data; + kmsg->msg.msg_control_user = sr->msg_control; } else { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) @@ -1301,7 +1328,7 @@ void io_sendrecv_fail(struct io_kiocb *req) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); - if (req->flags & REQ_F_PARTIAL_IO) + if (sr->done_io) req->cqe.res = sr->done_io; if ((req->flags & REQ_F_NEED_CLEANUP) && @@ -1351,8 +1378,6 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags) struct file *file; int ret, fd; - if (!io_check_multishot(req, issue_flags)) - return -EAGAIN; retry: if (!fixed) { fd = __get_unused_fd_flags(accept->flags, accept->nofile); diff --git a/io_uring/nop.c b/io_uring/nop.c index d956599a3c1b8..1a4e312dfe510 100644 --- a/io_uring/nop.c +++ b/io_uring/nop.c @@ -12,6 +12,8 @@ int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + if (READ_ONCE(sqe->rw_flags)) + return -EINVAL; return 0; } diff --git a/io_uring/poll.c b/io_uring/poll.c index 7513afc7b702e..c6f4789623cb2 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -539,14 +539,6 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt, poll->wait.private = (void *) wqe_private; if (poll->events & EPOLLEXCLUSIVE) { - /* - * Exclusive waits may only wake a limited amount of entries - * rather than all of them, this may interfere with lazy - * wake if someone does wait(events > 1). Ensure we don't do - * lazy wake for those, as we need to process each one as they - * come in. - */ - req->flags |= REQ_F_POLL_NO_LAZY; add_wait_queue_exclusive(head, &poll->wait); } else { add_wait_queue(head, &poll->wait); @@ -618,6 +610,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req, if (issue_flags & IO_URING_F_UNLOCKED) req->flags &= ~REQ_F_HASH_LOCKED; + + /* + * Exclusive waits may only wake a limited amount of entries + * rather than all of them, this may interfere with lazy + * wake if someone does wait(events > 1). Ensure we don't do + * lazy wake for those, as we need to process each one as they + * come in. + */ + if (poll->events & EPOLLEXCLUSIVE) + req->flags |= REQ_F_POLL_NO_LAZY; + mask = vfs_poll(req->file, &ipt->pt) & poll->events; if (unlikely(ipt->error || !ipt->nr_entries)) { @@ -995,7 +998,6 @@ int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags) struct io_hash_bucket *bucket; struct io_kiocb *preq; int ret2, ret = 0; - struct io_tw_state ts = { .locked = true }; io_ring_submit_lock(ctx, issue_flags); preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table, &bucket); @@ -1044,7 +1046,8 @@ int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags) req_set_fail(preq); io_req_set_res(preq, -ECANCELED, 0); - io_req_task_complete(preq, &ts); + preq->io_task_work.func = io_req_task_complete; + io_req_task_work_add(preq); out: io_ring_submit_unlock(ctx, issue_flags); if (ret < 0) { diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 4818b79231ddb..956e2c715eb48 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -250,6 +250,7 @@ __cold static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, ret = io_run_task_work_sig(ctx); if (ret < 0) { + __set_current_state(TASK_RUNNING); mutex_lock(&ctx->uring_lock); if (list_empty(&ctx->rsrc_ref_list)) ret = 0; @@ -1104,7 +1105,6 @@ int io_import_fixed(int ddir, struct iov_iter *iter, * branch doesn't expect non PAGE_SIZE'd chunks. */ iter->bvec = bvec; - iter->nr_segs = bvec->bv_len; iter->count -= offset; iter->iov_offset = offset; } else { diff --git a/io_uring/rw.c b/io_uring/rw.c index d5e79d9bdc717..c3c154790e452 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -935,6 +935,13 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) ret = __io_read(req, issue_flags); + /* + * If the file doesn't support proper NOWAIT, then disable multishot + * and stay in single shot mode. + */ + if (!io_file_supports_nowait(req)) + req->flags &= ~REQ_F_APOLL_MULTISHOT; + /* * If we get -EAGAIN, recycle our buffer and just let normal poll * handling arm it. @@ -946,13 +953,15 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) */ if (io_kbuf_recycle(req, issue_flags)) rw->len = 0; + if (issue_flags & IO_URING_F_MULTISHOT) + return IOU_ISSUE_SKIP_COMPLETE; return -EAGAIN; } /* * Any successful return value will keep the multishot read armed. */ - if (ret > 0) { + if (ret > 0 && req->flags & REQ_F_APOLL_MULTISHOT) { /* * Put our buffer and post a CQE. If we fail to post a CQE, then * jump to the termination path. This request is then done. diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 65b5dbe3c850e..350436e55aafe 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -240,6 +240,14 @@ static int io_sq_thread(void *data) sqd->sq_cpu = raw_smp_processor_id(); } + /* + * Force audit context to get setup, in case we do prep side async + * operations that would trigger an audit call before any issue side + * audit has been done. + */ + audit_uring_entry(IORING_OP_NOP); + audit_uring_exit(true, 0); + mutex_lock(&sqd->lock); while (1) { bool cap_entries, sqt_spin = false; diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 6f851978606d9..77d340666cb95 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -125,12 +125,6 @@ static void io_waitid_complete(struct io_kiocb *req, int ret) lockdep_assert_held(&req->ctx->uring_lock); - /* - * Did cancel find it meanwhile? - */ - if (hlist_unhashed(&req->hash_node)) - return; - hlist_del_init(&req->hash_node); ret = io_waitid_finish(req, ret); @@ -202,6 +196,7 @@ bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { if (!io_match_task_safe(req, task, cancel_all)) continue; + hlist_del_init(&req->hash_node); __io_waitid_cancel(ctx, req); found = true; } diff --git a/ipc/namespace.c b/ipc/namespace.c index 6ecc30effd3ec..aa3c2fe5d9fb8 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -205,6 +205,23 @@ void put_ipc_ns(struct ipc_namespace *ns) schedule_work(&free_ipc_work); } } +EXPORT_SYMBOL(put_ipc_ns); + +struct ipc_namespace *get_ipc_ns_exported(struct ipc_namespace *ns) +{ + return get_ipc_ns(ns); +} +EXPORT_SYMBOL(get_ipc_ns_exported); + +struct ipc_namespace *show_init_ipc_ns(void) +{ +#if defined(CONFIG_IPC_NS) + return &init_ipc_ns; +#else + return NULL; +#endif +} +EXPORT_SYMBOL(show_init_ipc_ns); static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns) { diff --git a/kernel/audit.c b/kernel/audit.c index 9c8e5f732c4c7..3dd2e9930550f 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include #include @@ -123,7 +124,7 @@ static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME; /* The identity of the user shutting down the audit system. */ static kuid_t audit_sig_uid = INVALID_UID; static pid_t audit_sig_pid = -1; -static u32 audit_sig_sid; +static struct lsmblob audit_sig_lsm; /* Records can be lost in several ways: 0) [suppressed in audit_alloc] @@ -195,8 +196,10 @@ static struct audit_ctl_mutex { * to place it on a transmit queue. Multiple audit_buffers can be in * use simultaneously. */ struct audit_buffer { - struct sk_buff *skb; /* formatted skb ready to send */ + struct sk_buff *skb; /* the skb for audit_log functions */ + struct sk_buff_head skb_list; /* formatted skbs, ready to send */ struct audit_context *ctx; /* NULL or associated context */ + struct audit_stamp stamp; /* audit stamp for these records */ gfp_t gfp_mask; }; @@ -1113,7 +1116,6 @@ static int is_audit_feature_set(int i) return af.features & AUDIT_FEATURE_TO_MASK(i); } - static int audit_get_feature(struct sk_buff *skb) { u32 seq; @@ -1221,8 +1223,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; struct audit_sig_info *sig_data; - char *ctx = NULL; - u32 len; + struct lsmcontext lsmctx; err = audit_netlink_ok(skb, msg_type); if (err) @@ -1471,29 +1472,33 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, kfree(new); break; } - case AUDIT_SIGNAL_INFO: - len = 0; - if (audit_sig_sid) { - err = security_secid_to_secctx(audit_sig_sid, &ctx, &len); - if (err) + case AUDIT_SIGNAL_INFO: { + size_t sig_data_size; + + if (lsmblob_is_set(&audit_sig_lsm)) { + err = security_lsmblob_to_secctx(&audit_sig_lsm, + &lsmctx, LSM_ID_UNDEF); + if (err < 0) return err; } - sig_data = kmalloc(struct_size(sig_data, ctx, len), GFP_KERNEL); + sig_data_size = struct_size(sig_data, ctx, lsmctx.len); + sig_data = kmalloc(sig_data_size, GFP_KERNEL); if (!sig_data) { - if (audit_sig_sid) - security_release_secctx(ctx, len); + if (lsmblob_is_set(&audit_sig_lsm)) + security_release_secctx(&lsmctx); return -ENOMEM; } sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid); sig_data->pid = audit_sig_pid; - if (audit_sig_sid) { - memcpy(sig_data->ctx, ctx, len); - security_release_secctx(ctx, len); + if (lsmblob_is_set(&audit_sig_lsm)) { + memcpy(sig_data->ctx, lsmctx.context, lsmctx.len); + security_release_secctx(&lsmctx); } audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, - sig_data, struct_size(sig_data, ctx, len)); + sig_data, sig_data_size); kfree(sig_data); break; + } case AUDIT_TTY_GET: { struct audit_tty_status s; unsigned int t; @@ -1777,10 +1782,13 @@ __setup("audit_backlog_limit=", audit_backlog_limit_set); static void audit_buffer_free(struct audit_buffer *ab) { + struct sk_buff *skb; + if (!ab) return; - kfree_skb(ab->skb); + while ((skb = skb_dequeue(&ab->skb_list))) + kfree_skb(skb); kmem_cache_free(audit_buffer_cache, ab); } @@ -1796,6 +1804,10 @@ static struct audit_buffer *audit_buffer_alloc(struct audit_context *ctx, ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask); if (!ab->skb) goto err; + + skb_queue_head_init(&ab->skb_list); + skb_queue_tail(&ab->skb_list, ab->skb); + if (!nlmsg_put(ab->skb, 0, 0, type, 0, 0)) goto err; @@ -1834,11 +1846,11 @@ unsigned int audit_serial(void) } static inline void audit_get_stamp(struct audit_context *ctx, - struct timespec64 *t, unsigned int *serial) + struct audit_stamp *stamp) { - if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { - ktime_get_coarse_real_ts64(t); - *serial = audit_serial(); + if (!ctx || !auditsc_get_stamp(ctx, stamp)) { + ktime_get_coarse_real_ts64(&stamp->ctime); + stamp->serial = audit_serial(); } } @@ -1861,8 +1873,6 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; - struct timespec64 t; - unsigned int serial; if (audit_initialized != AUDIT_INITIALIZED) return NULL; @@ -1917,12 +1927,14 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, return NULL; } - audit_get_stamp(ab->ctx, &t, &serial); + audit_get_stamp(ab->ctx, &ab->stamp); /* cancel dummy context to enable supporting records */ if (ctx) ctx->dummy = 0; audit_log_format(ab, "audit(%llu.%03lu:%u): ", - (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); + (unsigned long long)ab->stamp.ctime.tv_sec, + ab->stamp.ctime.tv_nsec/1000000, + ab->stamp.serial); return ab; } @@ -2178,34 +2190,171 @@ void audit_log_key(struct audit_buffer *ab, char *key) audit_log_format(ab, "(null)"); } -int audit_log_task_context(struct audit_buffer *ab) +/** + * audit_buffer_aux_new - Add an aux record buffer to the skb list + * @ab: audit_buffer + * @type: message type + * + * Aux records are allocated and added to the skb list of + * the "main" record. The ab->skb is reset to point to the + * aux record on its creation. When the aux record in complete + * ab->skb has to be reset to point to the "main" record. + * This allows the audit_log_ functions to be ignorant of + * which kind of record it is logging to. It also avoids adding + * special data for aux records. + * + * On success ab->skb will point to the new aux record. + * Returns 0 on success, -ENOMEM should allocation fail. + */ +static int audit_buffer_aux_new(struct audit_buffer *ab, int type) { - char *ctx = NULL; - unsigned len; + WARN_ON(ab->skb != skb_peek(&ab->skb_list)); + + ab->skb = nlmsg_new(AUDIT_BUFSIZ, ab->gfp_mask); + if (!ab->skb) + goto err; + if (!nlmsg_put(ab->skb, 0, 0, type, 0, 0)) + goto err; + skb_queue_tail(&ab->skb_list, ab->skb); + + audit_log_format(ab, "audit(%llu.%03lu:%u): ", + (unsigned long long)ab->stamp.ctime.tv_sec, + ab->stamp.ctime.tv_nsec/1000000, + ab->stamp.serial); + + return 0; + +err: + kfree_skb(ab->skb); + ab->skb = skb_peek(&ab->skb_list); + return -ENOMEM; +} + +/** + * audit_buffer_aux_end - Switch back to the "main" record from an aux record + * @ab: audit_buffer + * + * Restores the "main" audit record to ab->skb. + */ +static void audit_buffer_aux_end(struct audit_buffer *ab) +{ + ab->skb = skb_peek(&ab->skb_list); +} + +int audit_log_subject_context(struct audit_buffer *ab, struct lsmblob *blob) +{ + struct lsmcontext ctx; + bool space = false; int error; - u32 sid; + int i; - security_current_getsecid_subj(&sid); - if (!sid) + if (!lsmblob_is_set(blob)) return 0; - error = security_secid_to_secctx(sid, &ctx, &len); - if (error) { - if (error != -EINVAL) - goto error_path; + if (lsm_blob_cnt < 2) { + error = security_lsmblob_to_secctx(blob, &ctx, LSM_ID_UNDEF); + if (error < 0) { + if (error != -EINVAL) + goto error_path; + return 0; + } + audit_log_format(ab, " subj=%s", ctx.context); + security_release_secctx(&ctx); return 0; } - - audit_log_format(ab, " subj=%s", ctx); - security_release_secctx(ctx, len); + /* Multiple LSMs provide contexts. Include an aux record. */ + audit_log_format(ab, " subj=?"); + error = audit_buffer_aux_new(ab, AUDIT_MAC_TASK_CONTEXTS); + if (error) + goto error_path; + + for (i = 0; i < lsm_active_cnt; i++) { + if (!lsm_idlist[i]->lsmblob) + continue; + error = security_lsmblob_to_secctx(blob, &ctx, + lsm_idlist[i]->id); + if (error < 0) { + if (error == -EOPNOTSUPP) + continue; + audit_log_format(ab, "%ssubj_%s=?", space ? " " : "", + lsm_idlist[i]->name); + if (error != -EINVAL) + audit_panic("error in audit_log_task_context"); + } else { + audit_log_format(ab, "%ssubj_%s=%s", space ? " " : "", + lsm_idlist[i]->name, ctx.context); + security_release_secctx(&ctx); + } + space = true; + } + audit_buffer_aux_end(ab); return 0; error_path: - audit_panic("error in audit_log_task_context"); + audit_panic("error in audit_log_subject_context"); return error; } +EXPORT_SYMBOL(audit_log_subject_context); + +int audit_log_task_context(struct audit_buffer *ab) +{ + struct lsmblob blob; + + security_current_getlsmblob_subj(&blob); + return audit_log_subject_context(ab, &blob); +} EXPORT_SYMBOL(audit_log_task_context); +void audit_log_object_context(struct audit_buffer *ab, struct lsmblob *blob) +{ + int i; + int error; + bool space = false; + struct lsmcontext context; + + if (lsm_blob_cnt < 2) { + error = security_lsmblob_to_secctx(blob, &context, + LSM_ID_UNDEF); + if (error) { + if (error != -EINVAL) + goto error_path; + return; + } + audit_log_format(ab, " obj=%s", context.context); + security_release_secctx(&context); + return; + } + audit_log_format(ab, " obj=?"); + error = audit_buffer_aux_new(ab, AUDIT_MAC_OBJ_CONTEXTS); + if (error) + goto error_path; + + for (i = 0; i < lsm_blob_cnt; i++) { + if (!lsm_idlist[i]->lsmblob) + continue; + error = security_lsmblob_to_secctx(blob, &context, + lsm_idlist[i]->id); + if (error) { + audit_log_format(ab, "%sobj_%s=?", + space ? " " : "", lsm_idlist[i]->name); + if (error != -EINVAL) + audit_panic("error in audit_log_object_context"); + } else { + audit_log_format(ab, "%sobj_%s=%s", + space ? " " : "", lsm_idlist[i]->name, + context.context); + security_release_secctx(&context); + } + space = true; + } + + audit_buffer_aux_end(ab); + return; + +error_path: + audit_panic("error in audit_log_object_context"); +} + void audit_log_d_path_exe(struct audit_buffer *ab, struct mm_struct *mm) { @@ -2406,33 +2555,21 @@ int audit_signal_info(int sig, struct task_struct *t) audit_sig_uid = auid; else audit_sig_uid = uid; - security_current_getsecid_subj(&audit_sig_sid); + security_current_getlsmblob_subj(&audit_sig_lsm); } return audit_signal_info_syscall(t); } /** - * audit_log_end - end one audit record - * @ab: the audit_buffer - * - * We can not do a netlink send inside an irq context because it blocks (last - * arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed on a - * queue and a kthread is scheduled to remove them from the queue outside the - * irq context. May be called in any context. + * __audit_log_end - enqueue one audit record + * @skb: the buffer to send */ -void audit_log_end(struct audit_buffer *ab) +static void __audit_log_end(struct sk_buff *skb) { - struct sk_buff *skb; struct nlmsghdr *nlh; - if (!ab) - return; - if (audit_rate_check()) { - skb = ab->skb; - ab->skb = NULL; - /* setup the netlink header, see the comments in * kauditd_send_multicast_skb() for length quirks */ nlh = nlmsg_hdr(skb); @@ -2443,6 +2580,26 @@ void audit_log_end(struct audit_buffer *ab) wake_up_interruptible(&kauditd_wait); } else audit_log_lost("rate limit exceeded"); +} + +/** + * audit_log_end - end one audit record + * @ab: the audit_buffer + * + * We can not do a netlink send inside an irq context because it blocks (last + * arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed on a + * queue and a kthread is scheduled to remove them from the queue outside the + * irq context. May be called in any context. + */ +void audit_log_end(struct audit_buffer *ab) +{ + struct sk_buff *skb; + + if (!ab) + return; + + while ((skb = skb_dequeue(&ab->skb_list))) + __audit_log_end(skb); audit_buffer_free(ab); } diff --git a/kernel/audit.h b/kernel/audit.h index a60d2840559e2..f147540862c77 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -81,7 +82,7 @@ struct audit_names { kuid_t uid; kgid_t gid; dev_t rdev; - u32 osid; + struct lsmblob oblob; struct audit_cap_data fcap; unsigned int fcap_ver; unsigned char type; /* record type */ @@ -98,6 +99,12 @@ struct audit_proctitle { char *value; /* the cmdline field */ }; +/* A timestamp/serial pair to identify an event */ +struct audit_stamp { + struct timespec64 ctime; /* time of syscall entry */ + unsigned int serial; /* serial number for record */ +}; + /* The per-task audit context. */ struct audit_context { int dummy; /* must be the first element */ @@ -107,10 +114,9 @@ struct audit_context { AUDIT_CTX_URING, /* in use by io_uring */ } context; enum audit_state state, current_state; - unsigned int serial; /* serial number for record */ + struct audit_stamp stamp; /* event identifier */ int major; /* syscall number */ int uring_op; /* uring operation */ - struct timespec64 ctime; /* time of syscall entry */ unsigned long argv[4]; /* syscall arguments */ long return_code;/* syscall return code */ u64 prio; @@ -143,7 +149,7 @@ struct audit_context { kuid_t target_auid; kuid_t target_uid; unsigned int target_sessionid; - u32 target_sid; + struct lsmblob target_blob; char target_comm[TASK_COMM_LEN]; struct audit_tree_refs *trees, *first_trees; @@ -160,7 +166,7 @@ struct audit_context { kuid_t uid; kgid_t gid; umode_t mode; - u32 osid; + struct lsmblob oblob; int has_perm; uid_t perm_uid; gid_t perm_gid; @@ -262,7 +268,7 @@ extern void audit_put_tty(struct tty_struct *tty); extern unsigned int audit_serial(void); #ifdef CONFIG_AUDITSYSCALL extern int auditsc_get_stamp(struct audit_context *ctx, - struct timespec64 *t, unsigned int *serial); + struct audit_stamp *stamp); extern void audit_put_watch(struct audit_watch *watch); extern void audit_get_watch(struct audit_watch *watch); @@ -303,7 +309,7 @@ extern void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx); extern struct list_head *audit_killed_trees(void); #else /* CONFIG_AUDITSYSCALL */ -#define auditsc_get_stamp(c, t, s) 0 +#define auditsc_get_stamp(c, s) 0 #define audit_put_watch(w) do { } while (0) #define audit_get_watch(w) do { } while (0) #define audit_to_watch(k, p, l, o) (-EINVAL) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 8317a37dea0bb..12d364e47468d 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -529,7 +529,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, entry->rule.buflen += f_val; f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, - (void **)&f->lsm_rule); + (void **)&f->lsm_rule, + GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { @@ -799,7 +800,7 @@ static inline int audit_dupe_lsm_field(struct audit_field *df, /* our own (refreshed) copy of lsm_rule */ ret = security_audit_rule_init(df->type, df->op, df->lsm_str, - (void **)&df->lsm_rule); + (void **)&df->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { @@ -1338,8 +1339,8 @@ int audit_filter(int msgtype, unsigned int listtype) for (i = 0; i < e->rule.field_count; i++) { struct audit_field *f = &e->rule.fields[i]; + struct lsmblob blob = { }; pid_t pid; - u32 sid; switch (f->type) { case AUDIT_PID: @@ -1369,9 +1370,10 @@ int audit_filter(int msgtype, unsigned int listtype) case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: if (f->lsm_rule) { - security_current_getsecid_subj(&sid); - result = security_audit_rule_match(sid, - f->type, f->op, f->lsm_rule); + security_current_getlsmblob_subj(&blob); + result = security_audit_rule_match( + &blob, f->type, f->op, + f->lsm_rule); } break; case AUDIT_EXE: diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 6f0d6fb6523fa..bc13666dd6ed2 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -100,7 +100,7 @@ struct audit_aux_data_pids { kuid_t target_auid[AUDIT_AUX_PIDS]; kuid_t target_uid[AUDIT_AUX_PIDS]; unsigned int target_sessionid[AUDIT_AUX_PIDS]; - u32 target_sid[AUDIT_AUX_PIDS]; + struct lsmblob target_blob[AUDIT_AUX_PIDS]; char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN]; int pid_count; }; @@ -470,7 +470,7 @@ static int audit_filter_rules(struct task_struct *tsk, { const struct cred *cred; int i, need_sid = 1; - u32 sid; + struct lsmblob blob = { }; unsigned int sessionid; if (ctx && rule->prio <= ctx->prio) @@ -674,14 +674,16 @@ static int audit_filter_rules(struct task_struct *tsk, * fork()/copy_process() in which case * the new @tsk creds are still a dup * of @current's creds so we can still - * use security_current_getsecid_subj() + * use + * security_current_getlsmblob_subj() * here even though it always refs * @current's creds */ - security_current_getsecid_subj(&sid); + security_current_getlsmblob_subj(&blob); need_sid = 0; } - result = security_audit_rule_match(sid, f->type, + result = security_audit_rule_match(&blob, + f->type, f->op, f->lsm_rule); } @@ -697,14 +699,14 @@ static int audit_filter_rules(struct task_struct *tsk, /* Find files that match */ if (name) { result = security_audit_rule_match( - name->osid, + &name->oblob, f->type, f->op, f->lsm_rule); } else if (ctx) { list_for_each_entry(n, &ctx->names_list, list) { if (security_audit_rule_match( - n->osid, + &n->oblob, f->type, f->op, f->lsm_rule)) { @@ -716,7 +718,7 @@ static int audit_filter_rules(struct task_struct *tsk, /* Find ipc objects that match */ if (!ctx || ctx->type != AUDIT_IPC) break; - if (security_audit_rule_match(ctx->ipc.osid, + if (security_audit_rule_match(&ctx->ipc.oblob, f->type, f->op, f->lsm_rule)) ++result; @@ -992,10 +994,10 @@ static void audit_reset_context(struct audit_context *ctx) */ ctx->current_state = ctx->state; - ctx->serial = 0; + ctx->stamp.serial = 0; ctx->major = 0; ctx->uring_op = 0; - ctx->ctime = (struct timespec64){ .tv_sec = 0, .tv_nsec = 0 }; + ctx->stamp.ctime = (struct timespec64){ .tv_sec = 0, .tv_nsec = 0 }; memset(ctx->argv, 0, sizeof(ctx->argv)); ctx->return_code = 0; ctx->prio = (ctx->state == AUDIT_STATE_RECORD ? ~0ULL : 0); @@ -1017,7 +1019,7 @@ static void audit_reset_context(struct audit_context *ctx) ctx->target_pid = 0; ctx->target_auid = ctx->target_uid = KUIDT_INIT(0); ctx->target_sessionid = 0; - ctx->target_sid = 0; + lsmblob_init(&ctx->target_blob); ctx->target_comm[0] = '\0'; unroll_tree_refs(ctx, NULL, 0); WARN_ON(!list_empty(&ctx->killed_trees)); @@ -1090,36 +1092,27 @@ static inline void audit_free_context(struct audit_context *context) kfree(context); } -static int audit_log_pid_context(struct audit_context *context, pid_t pid, - kuid_t auid, kuid_t uid, unsigned int sessionid, - u32 sid, char *comm) +static void audit_log_pid_context(struct audit_context *context, pid_t pid, + kuid_t auid, kuid_t uid, + unsigned int sessionid, struct lsmblob *blob, + char *comm) { struct audit_buffer *ab; - char *ctx = NULL; - u32 len; - int rc = 0; ab = audit_log_start(context, GFP_KERNEL, AUDIT_OBJ_PID); if (!ab) - return rc; + return; audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid, from_kuid(&init_user_ns, auid), from_kuid(&init_user_ns, uid), sessionid); - if (sid) { - if (security_secid_to_secctx(sid, &ctx, &len)) { - audit_log_format(ab, " obj=(none)"); - rc = 1; - } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); - } - } + if (lsmblob_is_set(blob)) + audit_log_object_context(ab, blob); audit_log_format(ab, " ocomm="); audit_log_untrustedstring(ab, comm); audit_log_end(ab); - return rc; + return; } static void audit_log_execve_info(struct audit_context *context, @@ -1384,25 +1377,13 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_format(ab, " a%d=%lx", i, context->socketcall.args[i]); break; } - case AUDIT_IPC: { - u32 osid = context->ipc.osid; - + case AUDIT_IPC: audit_log_format(ab, "ouid=%u ogid=%u mode=%#ho", from_kuid(&init_user_ns, context->ipc.uid), from_kgid(&init_user_ns, context->ipc.gid), context->ipc.mode); - if (osid) { - char *ctx = NULL; - u32 len; - - if (security_secid_to_secctx(osid, &ctx, &len)) { - audit_log_format(ab, " osid=%u", osid); - *call_panic = 1; - } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); - } - } + if (lsmblob_is_set(&context->ipc.oblob)) + audit_log_object_context(ab, &context->ipc.oblob); if (context->ipc.has_perm) { audit_log_end(ab); ab = audit_log_start(context, GFP_KERNEL, @@ -1416,7 +1397,7 @@ static void show_special(struct audit_context *context, int *call_panic) context->ipc.perm_gid, context->ipc.perm_mode); } - break; } + break; case AUDIT_MQ_OPEN: audit_log_format(ab, "oflag=0x%x mode=%#ho mq_flags=0x%lx mq_maxmsg=%ld " @@ -1558,20 +1539,8 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, from_kgid(&init_user_ns, n->gid), MAJOR(n->rdev), MINOR(n->rdev)); - if (n->osid != 0) { - char *ctx = NULL; - u32 len; - - if (security_secid_to_secctx( - n->osid, &ctx, &len)) { - audit_log_format(ab, " osid=%u", n->osid); - if (call_panic) - *call_panic = 2; - } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); - } - } + if (lsmblob_is_set(&n->oblob)) + audit_log_object_context(ab, &n->oblob); /* log the audit_names record type */ switch (n->type) { @@ -1776,21 +1745,20 @@ static void audit_log_exit(void) struct audit_aux_data_pids *axs = (void *)aux; for (i = 0; i < axs->pid_count; i++) - if (audit_log_pid_context(context, axs->target_pid[i], - axs->target_auid[i], - axs->target_uid[i], - axs->target_sessionid[i], - axs->target_sid[i], - axs->target_comm[i])) - call_panic = 1; - } - - if (context->target_pid && - audit_log_pid_context(context, context->target_pid, - context->target_auid, context->target_uid, - context->target_sessionid, - context->target_sid, context->target_comm)) - call_panic = 1; + audit_log_pid_context(context, axs->target_pid[i], + axs->target_auid[i], + axs->target_uid[i], + axs->target_sessionid[i], + &axs->target_blob[i], + axs->target_comm[i]); + } + + if (context->target_pid) + audit_log_pid_context(context, context->target_pid, + context->target_auid, context->target_uid, + context->target_sessionid, + &context->target_blob, + context->target_comm); if (context->pwd.dentry && context->pwd.mnt) { ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD); @@ -1921,7 +1889,7 @@ void __audit_uring_entry(u8 op) ctx->context = AUDIT_CTX_URING; ctx->current_state = ctx->state; - ktime_get_coarse_real_ts64(&ctx->ctime); + ktime_get_coarse_real_ts64(&ctx->stamp.ctime); } /** @@ -2043,7 +2011,7 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, context->argv[3] = a4; context->context = AUDIT_CTX_SYSCALL; context->current_state = state; - ktime_get_coarse_real_ts64(&context->ctime); + ktime_get_coarse_real_ts64(&context->stamp.ctime); } /** @@ -2278,7 +2246,7 @@ static void audit_copy_inode(struct audit_names *name, name->uid = inode->i_uid; name->gid = inode->i_gid; name->rdev = inode->i_rdev; - security_inode_getsecid(inode, &name->osid); + security_inode_getlsmblob(inode, &name->oblob); if (flags & AUDIT_INODE_NOEVAL) { name->fcap_ver = -1; return; @@ -2514,21 +2482,17 @@ EXPORT_SYMBOL_GPL(__audit_inode_child); /** * auditsc_get_stamp - get local copies of audit_context values * @ctx: audit_context for the task - * @t: timespec64 to store time recorded in the audit_context - * @serial: serial value that is recorded in the audit_context + * @stamp: timestamp to record * * Also sets the context as auditable. */ -int auditsc_get_stamp(struct audit_context *ctx, - struct timespec64 *t, unsigned int *serial) +int auditsc_get_stamp(struct audit_context *ctx, struct audit_stamp *stamp) { if (ctx->context == AUDIT_CTX_UNUSED) return 0; - if (!ctx->serial) - ctx->serial = audit_serial(); - t->tv_sec = ctx->ctime.tv_sec; - t->tv_nsec = ctx->ctime.tv_nsec; - *serial = ctx->serial; + if (!ctx->stamp.serial) + ctx->stamp.serial = audit_serial(); + *stamp = ctx->stamp; if (!ctx->prio) { ctx->prio = 1; ctx->current_state = AUDIT_STATE_RECORD; @@ -2632,7 +2596,7 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp) context->ipc.gid = ipcp->gid; context->ipc.mode = ipcp->mode; context->ipc.has_perm = 0; - security_ipc_getsecid(ipcp, &context->ipc.osid); + security_ipc_getlsmblob(ipcp, &context->ipc.oblob); context->type = AUDIT_IPC; } @@ -2729,7 +2693,7 @@ void __audit_ptrace(struct task_struct *t) context->target_auid = audit_get_loginuid(t); context->target_uid = task_uid(t); context->target_sessionid = audit_get_sessionid(t); - security_task_getsecid_obj(t, &context->target_sid); + security_task_getlsmblob_obj(t, &context->target_blob); memcpy(context->target_comm, t->comm, TASK_COMM_LEN); } @@ -2756,7 +2720,7 @@ int audit_signal_info_syscall(struct task_struct *t) ctx->target_auid = audit_get_loginuid(t); ctx->target_uid = t_uid; ctx->target_sessionid = audit_get_sessionid(t); - security_task_getsecid_obj(t, &ctx->target_sid); + security_task_getlsmblob_obj(t, &ctx->target_blob); memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN); return 0; } @@ -2777,7 +2741,7 @@ int audit_signal_info_syscall(struct task_struct *t) axp->target_auid[axp->pid_count] = audit_get_loginuid(t); axp->target_uid[axp->pid_count] = t_uid; axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); - security_task_getsecid_obj(t, &axp->target_sid[axp->pid_count]); + security_task_getlsmblob_obj(t, &axp->target_blob[axp->pid_count]); memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN); axp->pid_count++; diff --git a/kernel/bounds.c b/kernel/bounds.c index b529182e8b04f..29b2cd00df2cc 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -19,7 +19,7 @@ int main(void) DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES); #ifdef CONFIG_SMP - DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); + DEFINE(NR_CPUS_BITS, order_base_2(CONFIG_NR_CPUS)); #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); #ifdef CONFIG_LRU_GEN diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573e97c..418a8188a8e84 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,7 +4,7 @@ ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y) # ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif -CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) +CFLAGS_core.o += -Wno-override-init $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index addf3dd57b59b..35e1ddca74d21 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -80,6 +80,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key return -EOPNOTSUPP; } +/* Called from syscall */ +static int bloom_map_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; @@ -191,6 +203,7 @@ static u64 bloom_map_mem_usage(const struct bpf_map *map) BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bloom_map_alloc_check, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 5964711891767..92aa3cf0396b8 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7009,6 +7009,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); if (nargs > MAX_BPF_FUNC_REG_ARGS) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() with %d > %d args. Buggy compiler.\n", tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; @@ -7018,6 +7020,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_int(t) && !btf_is_any_enum(t)) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() doesn't return scalar. Only those are supported.\n", tname); @@ -7058,10 +7062,6 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_int(t) || btf_is_any_enum(t)) { - sub->args[i].arg_type = ARG_ANYTHING; - continue; - } if (btf_type_is_ptr(t) && btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { sub->args[i].arg_type = ARG_PTR_TO_CTX; continue; @@ -7091,6 +7091,12 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) bpf_log(log, "arg#%d marked as non-null, but is not a pointer type\n", i); return -EINVAL; } + if (btf_type_is_int(t) || btf_is_any_enum(t)) { + sub->args[i].arg_type = ARG_ANYTHING; + continue; + } + if (!is_global) + return -EINVAL; bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", i, btf_type_str(t), tname); return -EINVAL; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ea6843be2616c..026627226ec48 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -888,7 +888,12 @@ static LIST_HEAD(pack_list); * CONFIG_MMU=n. Use PAGE_SIZE in these cases. */ #ifdef PMD_SIZE -#define BPF_PROG_PACK_SIZE (PMD_SIZE * num_possible_nodes()) +/* PMD_SIZE is really big for some archs. It doesn't make sense to + * reserve too much memory in one allocation. Hardcode BPF_PROG_PACK_SIZE to + * 2MiB * num_possible_nodes(). On most architectures PMD_SIZE will be + * greater than or equal to 2MB. + */ +#define BPF_PROG_PACK_SIZE (SZ_2M * num_possible_nodes()) #else #define BPF_PROG_PACK_SIZE PAGE_SIZE #endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index ef82ffc90cbe9..8f1d390bcbdeb 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -262,6 +262,7 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + unsigned long last_qs = jiffies; complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); @@ -287,10 +288,12 @@ static int cpu_map_kthread_run(void *data) if (__ptr_ring_empty(rcpu->queue)) { schedule(); sched = 1; + last_qs = jiffies; } else { __set_current_state(TASK_RUNNING); } } else { + rcu_softirq_qs_periodic(last_qs); sched = cond_resched(); } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index a936c704d4e77..4e2cdbb5629f2 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -130,13 +130,14 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); - - if (!dtab->n_buckets) /* Overflow check */ + /* hash table size must be power of 2; roundup_pow_of_two() can + * overflow into UB on 32-bit arches, so check that first + */ + if (dtab->map.max_entries > 1UL << 31) return -EINVAL; - } - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 03a6a2500b6ab..3a088a5349bc0 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -499,7 +499,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) num_possible_cpus()); } - /* hash table size must be power of 2 */ + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + err = -E2BIG; + if (htab->map.max_entries > 1UL << 31) + goto free_htab; + htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct htab_elem) + @@ -509,10 +515,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else htab->elem_size += round_up(htab->map.value_size, 8); - err = -E2BIG; - /* prevent zero size kmalloc and check for u32 overflow */ - if (htab->n_buckets == 0 || - htab->n_buckets > U32_MAX / sizeof(struct bucket)) + /* check for u32 overflow */ + if (htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; err = bpf_map_init_elem_count(&htab->map); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index d19cd863d294e..b10092754dde3 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -334,7 +334,7 @@ static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) __this_cpu_write(irqsave_flags, flags); } -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) { __bpf_spin_lock_irqsave(lock); return 0; @@ -357,7 +357,7 @@ static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) local_irq_restore(flags); } -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) { __bpf_spin_unlock_irqrestore(lock); return 0; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b32be680da6cd..10ff0386355ef 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -308,6 +308,7 @@ static long trie_update_elem(struct bpf_map *map, { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; + struct lpm_trie_node *free_node = NULL; struct lpm_trie_node __rcu **slot; struct bpf_lpm_trie_key *key = _key; unsigned long irq_flags; @@ -382,7 +383,7 @@ static long trie_update_elem(struct bpf_map *map, trie->n_entries--; rcu_assign_pointer(*slot, new_node); - kfree_rcu(node, rcu); + free_node = node; goto out; } @@ -429,6 +430,7 @@ static long trie_update_elem(struct bpf_map *map, } spin_unlock_irqrestore(&trie->lock, irq_flags); + kfree_rcu(free_node, rcu); return ret; } @@ -437,6 +439,7 @@ static long trie_update_elem(struct bpf_map *map, static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct lpm_trie_node *free_node = NULL, *free_parent = NULL; struct bpf_lpm_trie_key *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; @@ -506,8 +509,8 @@ static long trie_delete_elem(struct bpf_map *map, void *_key) else rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[0])); - kfree_rcu(parent, rcu); - kfree_rcu(node, rcu); + free_parent = parent; + free_node = node; goto out; } @@ -521,10 +524,12 @@ static long trie_delete_elem(struct bpf_map *map, void *_key) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); else RCU_INIT_POINTER(*trim, NULL); - kfree_rcu(node, rcu); + free_node = node; out: spin_unlock_irqrestore(&trie->lock, irq_flags); + kfree_rcu(free_parent, rcu); + kfree_rcu(free_node, rcu); return ret; } diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 0ee653a936ea0..e20b90c361316 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -51,7 +51,8 @@ struct bpf_ringbuf { * This prevents a user-space application from modifying the * position and ruining in-kernel tracking. The permissions of the * pages depend on who is producing samples: user-space or the - * kernel. + * kernel. Note that the pending counter is placed in the same + * page as the producer, so that it shares the same cache line. * * Kernel-producer * --------------- @@ -70,6 +71,7 @@ struct bpf_ringbuf { */ unsigned long consumer_pos __aligned(PAGE_SIZE); unsigned long producer_pos __aligned(PAGE_SIZE); + unsigned long pending_pos; char data[] __aligned(PAGE_SIZE); }; @@ -179,6 +181,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) rb->mask = data_sz - 1; rb->consumer_pos = 0; rb->producer_pos = 0; + rb->pending_pos = 0; return rb; } @@ -404,9 +407,9 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) { - unsigned long cons_pos, prod_pos, new_prod_pos, flags; - u32 len, pg_off; + unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags; struct bpf_ringbuf_hdr *hdr; + u32 len, pg_off, tmp_size, hdr_len; if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) return NULL; @@ -424,13 +427,29 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) spin_lock_irqsave(&rb->spinlock, flags); } + pend_pos = rb->pending_pos; prod_pos = rb->producer_pos; new_prod_pos = prod_pos + len; - /* check for out of ringbuf space by ensuring producer position - * doesn't advance more than (ringbuf_size - 1) ahead + while (pend_pos < prod_pos) { + hdr = (void *)rb->data + (pend_pos & rb->mask); + hdr_len = READ_ONCE(hdr->len); + if (hdr_len & BPF_RINGBUF_BUSY_BIT) + break; + tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT; + tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8); + pend_pos += tmp_size; + } + rb->pending_pos = pend_pos; + + /* check for out of ringbuf space: + * - by ensuring producer position doesn't advance more than + * (ringbuf_size - 1) ahead + * - by ensuring oldest not yet committed record until newest + * record does not span more than (ringbuf_size - 1) */ - if (new_prod_pos - cons_pos > rb->mask) { + if (new_prod_pos - cons_pos > rb->mask || + new_prod_pos - pend_pos > rb->mask) { spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index dff7ba5397015..c99f8e5234ac4 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -91,11 +91,14 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) } else if (value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); - /* hash table size must be power of 2 */ - n_buckets = roundup_pow_of_two(attr->max_entries); - if (!n_buckets) + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + if (attr->max_entries > 1UL << 31) return ERR_PTR(-E2BIG); + n_buckets = roundup_pow_of_two(attr->max_entries); + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a1f18681721c7..dc5c56dfe4935 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2856,6 +2856,7 @@ static int bpf_obj_get(const union bpf_attr *attr) void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { + WARN_ON(ops->dealloc && ops->dealloc_deferred); atomic64_set(&link->refcnt, 1); link->type = type; link->id = 0; @@ -2895,17 +2896,46 @@ void bpf_link_inc(struct bpf_link *link) atomic64_inc(&link->refcnt); } +static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) +{ + struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); + + /* free bpf_link and its containing memory */ + link->ops->dealloc_deferred(link); +} + +static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_link_defer_dealloc_rcu_gp(rcu); + else + call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp); +} + /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { + const struct bpf_link_ops *ops = link->ops; + bool sleepable = false; + bpf_link_free_id(link->id); if (link->prog) { + sleepable = link->prog->aux->sleepable; /* detach BPF program, clean up used resources */ - link->ops->release(link); + ops->release(link); bpf_prog_put(link->prog); } - /* free bpf_link and its containing memory */ - link->ops->dealloc(link); + if (ops->dealloc_deferred) { + /* schedule BPF link deallocation; if underlying BPF program + * is sleepable, we need to first wait for RCU tasks trace + * sync, then go through "classic" RCU grace period + */ + if (sleepable) + call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); + else + call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); + } else if (ops->dealloc) + ops->dealloc(link); } static void bpf_link_put_deferred(struct work_struct *work) @@ -3415,7 +3445,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, - .dealloc = bpf_raw_tp_link_dealloc, + .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; @@ -3823,6 +3853,11 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, * check permissions at attach time. */ return -EPERM; + + ptype = attach_type_to_prog_type(attach_type); + if (prog->type != ptype) + return -EINVAL; + return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ddea9567f7559..4e618b8d71020 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2328,6 +2328,8 @@ static void mark_btf_ld_reg(struct bpf_verifier_env *env, regs[regno].type = PTR_TO_BTF_ID | flag; regs[regno].btf = btf; regs[regno].btf_id = btf_id; + if (type_may_be_null(flag)) + regs[regno].id = ++env->id_gen; } #define DEF_NOT_SUBREG (0) @@ -3584,7 +3586,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * sreg needs precision before this insn */ bt_clear_reg(bt, dreg); - bt_set_reg(bt, sreg); + if (sreg != BPF_REG_FP) + bt_set_reg(bt, sreg); } else { /* dreg = K * dreg needs precision after this insn. @@ -3600,7 +3603,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * both dreg and sreg need precision * before this insn */ - bt_set_reg(bt, sreg); + if (sreg != BPF_REG_FP) + bt_set_reg(bt, sreg); } /* else dreg += K * dreg still needs precision before this insn */ @@ -5320,8 +5324,6 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, */ mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field)); - /* For mark_ptr_or_null_reg */ - val_reg->id = ++env->id_gen; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!register_is_null(val_reg) && @@ -5632,7 +5634,8 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg) return true; /* Types listed in the reg2btf_ids are always trusted */ - if (reg2btf_ids[base_type(reg->type)]) + if (reg2btf_ids[base_type(reg->type)] && + !bpf_type_has_unsafe_modifiers(reg->type)) return true; /* If a register is not referenced, it is trusted if it has the @@ -6242,6 +6245,7 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val, #define BTF_TYPE_SAFE_RCU(__type) __PASTE(__type, __safe_rcu) #define BTF_TYPE_SAFE_RCU_OR_NULL(__type) __PASTE(__type, __safe_rcu_or_null) #define BTF_TYPE_SAFE_TRUSTED(__type) __PASTE(__type, __safe_trusted) +#define BTF_TYPE_SAFE_TRUSTED_OR_NULL(__type) __PASTE(__type, __safe_trusted_or_null) /* * Allow list few fields as RCU trusted or full trusted. @@ -6305,7 +6309,7 @@ BTF_TYPE_SAFE_TRUSTED(struct dentry) { struct inode *d_inode; }; -BTF_TYPE_SAFE_TRUSTED(struct socket) { +BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) { struct sock *sk; }; @@ -6340,11 +6344,20 @@ static bool type_is_trusted(struct bpf_verifier_env *env, BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file)); BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry)); - BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct socket)); return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted"); } +static bool type_is_trusted_or_null(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const char *field_name, u32 btf_id) +{ + BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket)); + + return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, + "__safe_trusted_or_null"); +} + static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, @@ -6453,6 +6466,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, */ if (type_is_trusted(env, reg, field_name, btf_id)) { flag |= PTR_TRUSTED; + } else if (type_is_trusted_or_null(env, reg, field_name, btf_id)) { + flag |= PTR_TRUSTED | PTR_MAYBE_NULL; } else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) { if (type_is_rcu(env, reg, field_name, btf_id)) { /* ignore __rcu tag and mark it MEM_RCU */ @@ -6618,6 +6633,11 @@ static int check_stack_access_within_bounds( err = check_stack_slot_within_bounds(env, min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ + if (!err && access_size < 0) + /* access_size should not be negative (or overflow an int); others checks + * along the way should have prevented such an access. + */ + err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { @@ -8736,7 +8756,8 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); - if (func_id != BPF_FUNC_map_update_elem) + if (func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these @@ -8747,6 +8768,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) if (eatype == BPF_TRACE_ITER) return true; break; + case BPF_PROG_TYPE_SOCK_OPS: + /* map_update allowed only via dedicated helpers with event type checks */ + if (func_id == BPF_FUNC_map_delete_elem) + return true; + break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: @@ -8842,7 +8868,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && @@ -8852,7 +8877,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && @@ -14802,7 +14826,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; struct bpf_reg_state *eq_branch_regs; - struct bpf_reg_state fake_reg = {}; u8 opcode = BPF_OP(insn->code); bool is_jmp32; int pred = -1; @@ -14843,7 +14866,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } - src_reg = &fake_reg; + src_reg = &env->fake_reg[0]; + memset(src_reg, 0, sizeof(*src_reg)); src_reg->type = SCALAR_VALUE; __mark_reg_known(src_reg, insn->imm); } @@ -14903,10 +14927,16 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, &other_branch_regs[insn->src_reg], dst_reg, src_reg, opcode, is_jmp32); } else /* BPF_SRC(insn->code) == BPF_K */ { + /* reg_set_min_max() can mangle the fake_reg. Make a copy + * so that these are two different memory locations. The + * src_reg is not used beyond here in context of K. + */ + memcpy(&env->fake_reg[1], &env->fake_reg[0], + sizeof(env->fake_reg[0])); err = reg_set_min_max(env, &other_branch_regs[insn->dst_reg], - src_reg /* fake one */, - dst_reg, src_reg /* same fake one */, + &env->fake_reg[0], + dst_reg, &env->fake_reg[1], opcode, is_jmp32); } if (err) @@ -18035,8 +18065,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose(env, "fd %d is not pointing to valid bpf_map\n", - insn[0].imm); + verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 927bef3a598ad..0645d92b084cc 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -201,6 +201,14 @@ struct cpuset { struct list_head remote_sibling; }; +/* + * Legacy hierarchy call to cgroup_transfer_tasks() is handled asynchrously + */ +struct cpuset_remove_tasks_struct { + struct work_struct work; + struct cpuset *cs; +}; + /* * Exclusive CPUs distributed out to sub-partitions of top_cpuset */ @@ -449,12 +457,6 @@ static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; -/* - * CPU / memory hotplug is handled asynchronously. - */ -static void cpuset_hotplug_workfn(struct work_struct *work); -static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); - static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); static inline void check_insane_mems_config(nodemask_t *nodes) @@ -540,22 +542,10 @@ static void guarantee_online_cpus(struct task_struct *tsk, rcu_read_lock(); cs = task_cs(tsk); - while (!cpumask_intersects(cs->effective_cpus, pmask)) { + while (!cpumask_intersects(cs->effective_cpus, pmask)) cs = parent_cs(cs); - if (unlikely(!cs)) { - /* - * The top cpuset doesn't have any online cpu as a - * consequence of a race between cpuset_hotplug_work - * and cpu hotplug notifier. But we know the top - * cpuset's effective_cpus is on its way to be - * identical to cpu_online_mask. - */ - goto out_unlock; - } - } - cpumask_and(pmask, pmask, cs->effective_cpus); -out_unlock: + cpumask_and(pmask, pmask, cs->effective_cpus); rcu_read_unlock(); } @@ -1217,7 +1207,7 @@ static void rebuild_sched_domains_locked(void) /* * If we have raced with CPU hotplug, return early to avoid * passing doms with offlined cpu to partition_sched_domains(). - * Anyways, cpuset_hotplug_workfn() will rebuild sched domains. + * Anyways, cpuset_handle_hotplug() will rebuild sched domains. * * With no CPUs in any subpartitions, top_cpuset's effective CPUs * should be the same as the active CPUs, so checking only top_cpuset @@ -1260,12 +1250,17 @@ static void rebuild_sched_domains_locked(void) } #endif /* CONFIG_SMP */ -void rebuild_sched_domains(void) +static void rebuild_sched_domains_cpuslocked(void) { - cpus_read_lock(); mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); +} + +void rebuild_sched_domains(void) +{ + cpus_read_lock(); + rebuild_sched_domains_cpuslocked(); cpus_read_unlock(); } @@ -2079,14 +2074,11 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, /* * For partcmd_update without newmask, it is being called from - * cpuset_hotplug_workfn() where cpus_read_lock() wasn't taken. - * Update the load balance flag and scheduling domain if - * cpus_read_trylock() is successful. + * cpuset_handle_hotplug(). Update the load balance flag and + * scheduling domain accordingly. */ - if ((cmd == partcmd_update) && !newmask && cpus_read_trylock()) { + if ((cmd == partcmd_update) && !newmask) update_partition_sd_lb(cs, old_prs); - cpus_read_unlock(); - } notify_partition_change(cs, old_prs); return 0; @@ -2948,7 +2940,7 @@ bool current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP - if (val < -1 || val >= sched_domain_level_max) + if (val < -1 || val > sched_domain_level_max + 1) return -EINVAL; #endif @@ -3599,8 +3591,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. * - * cpuset_hotplug_work calls back into cgroup core via - * cgroup_transfer_tasks() and waiting for it from a cgroupfs + * cpuset_handle_hotplug may call back into cgroup core asynchronously + * via cgroup_transfer_tasks() and waiting for it from a cgroupfs * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after @@ -3609,7 +3601,6 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, */ css_get(&cs->css); kernfs_break_active_protection(of->kn); - flush_work(&cpuset_hotplug_work); cpus_read_lock(); mutex_lock(&cpuset_mutex); @@ -4353,6 +4344,16 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) } } +static void cpuset_migrate_tasks_workfn(struct work_struct *work) +{ + struct cpuset_remove_tasks_struct *s; + + s = container_of(work, struct cpuset_remove_tasks_struct, work); + remove_tasks_in_empty_cpuset(s->cs); + css_put(&s->cs->css); + kfree(s); +} + static void hotplug_update_tasks_legacy(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, @@ -4382,12 +4383,21 @@ hotplug_update_tasks_legacy(struct cpuset *cs, /* * Move tasks to the nearest ancestor with execution resources, * This is full cgroup operation which will also call back into - * cpuset. Should be done outside any lock. + * cpuset. Execute it asynchronously using workqueue. */ - if (is_empty) { - mutex_unlock(&cpuset_mutex); - remove_tasks_in_empty_cpuset(cs); - mutex_lock(&cpuset_mutex); + if (is_empty && cs->css.cgroup->nr_populated_csets && + css_tryget_online(&cs->css)) { + struct cpuset_remove_tasks_struct *s; + + s = kzalloc(sizeof(*s), GFP_KERNEL); + if (WARN_ON_ONCE(!s)) { + css_put(&cs->css); + return; + } + + s->cs = cs; + INIT_WORK(&s->work, cpuset_migrate_tasks_workfn); + schedule_work(&s->work); } } @@ -4420,30 +4430,6 @@ void cpuset_force_rebuild(void) force_rebuild = true; } -/* - * Attempt to acquire a cpus_read_lock while a hotplug operation may be in - * progress. - * Return: true if successful, false otherwise - * - * To avoid circular lock dependency between cpuset_mutex and cpus_read_lock, - * cpus_read_trylock() is used here to acquire the lock. - */ -static bool cpuset_hotplug_cpus_read_trylock(void) -{ - int retries = 0; - - while (!cpus_read_trylock()) { - /* - * CPU hotplug still in progress. Retry 5 times - * with a 10ms wait before bailing out. - */ - if (++retries > 5) - return false; - msleep(10); - } - return true; -} - /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest @@ -4492,13 +4478,11 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) compute_partition_effective_cpumask(cs, &new_cpus); if (remote && cpumask_empty(&new_cpus) && - partition_is_populated(cs, NULL) && - cpuset_hotplug_cpus_read_trylock()) { + partition_is_populated(cs, NULL)) { remote_partition_disable(cs, tmp); compute_effective_cpumask(&new_cpus, cs, parent); remote = false; cpuset_force_rebuild(); - cpus_read_unlock(); } /* @@ -4518,18 +4502,8 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) else if (is_partition_valid(parent) && is_partition_invalid(cs)) partcmd = partcmd_update; - /* - * cpus_read_lock needs to be held before calling - * update_parent_effective_cpumask(). To avoid circular lock - * dependency between cpuset_mutex and cpus_read_lock, - * cpus_read_trylock() is used here to acquire the lock. - */ if (partcmd >= 0) { - if (!cpuset_hotplug_cpus_read_trylock()) - goto update_tasks; - update_parent_effective_cpumask(cs, partcmd, NULL, tmp); - cpus_read_unlock(); if ((partcmd == partcmd_invalidate) || is_partition_valid(cs)) { compute_partition_effective_cpumask(cs, &new_cpus); cpuset_force_rebuild(); @@ -4557,8 +4531,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) } /** - * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset - * @work: unused + * cpuset_handle_hotplug - handle CPU/memory hot{,un}plug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always @@ -4572,8 +4545,10 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. + * + * CPU / memory hotplug is handled synchronously. */ -static void cpuset_hotplug_workfn(struct work_struct *work) +static void cpuset_handle_hotplug(void) { static cpumask_t new_cpus; static nodemask_t new_mems; @@ -4584,6 +4559,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; + lockdep_assert_cpus_held(); mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ @@ -4665,7 +4641,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) /* rebuild sched domains if cpus_allowed has changed */ if (cpus_updated || force_rebuild) { force_rebuild = false; - rebuild_sched_domains(); + rebuild_sched_domains_cpuslocked(); } free_cpumasks(NULL, ptmp); @@ -4678,12 +4654,7 @@ void cpuset_update_active_cpus(void) * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ - schedule_work(&cpuset_hotplug_work); -} - -void cpuset_wait_for_hotplug(void) -{ - flush_work(&cpuset_hotplug_work); + cpuset_handle_hotplug(); } /* @@ -4694,7 +4665,7 @@ void cpuset_wait_for_hotplug(void) static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { - schedule_work(&cpuset_hotplug_work); + cpuset_handle_hotplug(); return NOTIFY_OK; } diff --git a/kernel/cpu.c b/kernel/cpu.c index e6ec3ba4950b4..4d4de93d44136 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1209,52 +1209,6 @@ void __init cpuhp_threads_init(void) kthread_unpark(this_cpu_read(cpuhp_state.thread)); } -/* - * - * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock - * protected region. - * - * The operation is still serialized against concurrent CPU hotplug via - * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ - * serialized against other hotplug related activity like adding or - * removing of state callbacks and state instances, which invoke either the - * startup or the teardown callback of the affected state. - * - * This is required for subsystems which are unfixable vs. CPU hotplug and - * evade lock inversion problems by scheduling work which has to be - * completed _before_ cpu_up()/_cpu_down() returns. - * - * Don't even think about adding anything to this for any new code or even - * drivers. It's only purpose is to keep existing lock order trainwrecks - * working. - * - * For cpu_down() there might be valid reasons to finish cleanups which are - * not required to be done under cpu_hotplug_lock, but that's a different - * story and would be not invoked via this. - */ -static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) -{ - /* - * cpusets delegate hotplug operations to a worker to "solve" the - * lock order problems. Wait for the worker, but only if tasks are - * _not_ frozen (suspend, hibernate) as that would wait forever. - * - * The wait is required because otherwise the hotplug operation - * returns with inconsistent state, which could even be observed in - * user space when a new CPU is brought up. The CPU plug uevent - * would be delivered and user space reacting on it would fail to - * move tasks to the newly plugged CPU up to the point where the - * work has finished because up to that point the newly plugged CPU - * is not assignable in cpusets/cgroups. On unplug that's not - * necessarily a visible issue, but it is still inconsistent state, - * which is the real problem which needs to be "fixed". This can't - * prevent the transient state between scheduling the work and - * returning from waiting for it. - */ - if (!tasks_frozen) - cpuset_wait_for_hotplug(); -} - #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) @@ -1498,7 +1452,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ lockup_detector_cleanup(); arch_smt_update(); - cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } @@ -1732,7 +1685,6 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) out: cpus_write_unlock(); arch_smt_update(); - cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } @@ -3196,6 +3148,7 @@ void __init boot_cpu_hotplug_init(void) this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } +#ifdef CONFIG_CPU_MITIGATIONS /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. @@ -3206,8 +3159,7 @@ enum cpu_mitigations { CPU_MITIGATIONS_AUTO_NOSMT, }; -static enum cpu_mitigations cpu_mitigations __ro_after_init = - CPU_MITIGATIONS_AUTO; +static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { @@ -3223,7 +3175,6 @@ static int __init mitigations_parse_cmdline(char *arg) return 0; } -early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) @@ -3238,3 +3189,11 @@ bool cpu_mitigations_auto_nosmt(void) return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); +#else +static int __init mitigations_parse_cmdline(char *arg) +{ + pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); + return 0; +} +#endif +early_param("mitigations", mitigations_parse_cmdline); diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 75cd6a736d030..ebde3063b5312 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -376,6 +376,9 @@ static int __init reserve_crashkernel_low(unsigned long long low_size) crashk_low_res.start = low_base; crashk_low_res.end = low_base + low_size - 1; +#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY + insert_resource(&iomem_resource, &crashk_low_res); +#endif #endif return 0; } @@ -457,8 +460,12 @@ void __init reserve_crashkernel_generic(char *cmdline, crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; +#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY + insert_resource(&iomem_resource, &crashk_res); +#endif } +#ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY static __init int insert_crashkernel_resources(void) { if (crashk_res.start < crashk_res.end) @@ -471,6 +478,7 @@ static __init int insert_crashkernel_resources(void) } early_initcall(insert_crashkernel_resources); #endif +#endif int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz) @@ -806,11 +814,10 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_head_mask); #define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(PG_hugetlb); +#define PAGE_HUGETLB_MAPCOUNT_VALUE (~PG_hugetlb) + VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE); #define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); -#endif #ifdef CONFIG_KALLSYMS VMCOREINFO_SYMBOL(kallsyms_names); diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 9443bc63c5a24..2aeaf9765b248 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -184,6 +184,33 @@ char kdb_getchar(void) unreachable(); } +/** + * kdb_position_cursor() - Place cursor in the correct horizontal position + * @prompt: Nil-terminated string containing the prompt string + * @buffer: Nil-terminated string containing the entire command line + * @cp: Cursor position, pointer the character in buffer where the cursor + * should be positioned. + * + * The cursor is positioned by sending a carriage-return and then printing + * the content of the line until we reach the correct cursor position. + * + * There is some additional fine detail here. + * + * Firstly, even though kdb_printf() will correctly format zero-width fields + * we want the second call to kdb_printf() to be conditional. That keeps things + * a little cleaner when LOGGING=1. + * + * Secondly, we can't combine everything into one call to kdb_printf() since + * that renders into a fixed length buffer and the combined print could result + * in unwanted truncation. + */ +static void kdb_position_cursor(char *prompt, char *buffer, char *cp) +{ + kdb_printf("\r%s", kdb_prompt_str); + if (cp > buffer) + kdb_printf("%.*s", (int)(cp - buffer), buffer); +} + /* * kdb_read * @@ -212,7 +239,6 @@ static char *kdb_read(char *buffer, size_t bufsize) * and null byte */ char *lastchar; char *p_tmp; - char tmp; static char tmpbuffer[CMD_BUFLEN]; int len = strlen(buffer); int len_tmp; @@ -249,12 +275,8 @@ static char *kdb_read(char *buffer, size_t bufsize) } *(--lastchar) = '\0'; --cp; - kdb_printf("\b%s \r", cp); - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + kdb_printf("\b%s ", cp); + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 10: /* linefeed */ @@ -272,19 +294,14 @@ static char *kdb_read(char *buffer, size_t bufsize) memcpy(tmpbuffer, cp+1, lastchar - cp - 1); memcpy(cp, tmpbuffer, lastchar - cp - 1); *(--lastchar) = '\0'; - kdb_printf("%s \r", cp); - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + kdb_printf("%s ", cp); + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 1: /* Home */ if (cp > buffer) { - kdb_printf("\r"); - kdb_printf(kdb_prompt_str); cp = buffer; + kdb_position_cursor(kdb_prompt_str, buffer, cp); } break; case 5: /* End */ @@ -300,11 +317,10 @@ static char *kdb_read(char *buffer, size_t bufsize) } break; case 14: /* Down */ - memset(tmpbuffer, ' ', - strlen(kdb_prompt_str) + (lastchar-buffer)); - *(tmpbuffer+strlen(kdb_prompt_str) + - (lastchar-buffer)) = '\0'; - kdb_printf("\r%s\r", tmpbuffer); + case 16: /* Up */ + kdb_printf("\r%*c\r", + (int)(strlen(kdb_prompt_str) + (lastchar - buffer)), + ' '); *lastchar = (char)key; *(lastchar+1) = '\0'; return lastchar; @@ -314,15 +330,6 @@ static char *kdb_read(char *buffer, size_t bufsize) ++cp; } break; - case 16: /* Up */ - memset(tmpbuffer, ' ', - strlen(kdb_prompt_str) + (lastchar-buffer)); - *(tmpbuffer+strlen(kdb_prompt_str) + - (lastchar-buffer)) = '\0'; - kdb_printf("\r%s\r", tmpbuffer); - *lastchar = (char)key; - *(lastchar+1) = '\0'; - return lastchar; case 9: /* Tab */ if (tab < 2) ++tab; @@ -366,15 +373,25 @@ static char *kdb_read(char *buffer, size_t bufsize) kdb_printf("\n"); kdb_printf(kdb_prompt_str); kdb_printf("%s", buffer); + if (cp != lastchar) + kdb_position_cursor(kdb_prompt_str, buffer, cp); } else if (tab != 2 && count > 0) { - len_tmp = strlen(p_tmp); - strncpy(p_tmp+len_tmp, cp, lastchar-cp+1); - len_tmp = strlen(p_tmp); - strncpy(cp, p_tmp+len, len_tmp-len + 1); - len = len_tmp - len; - kdb_printf("%s", cp); - cp += len; - lastchar += len; + /* How many new characters do we want from tmpbuffer? */ + len_tmp = strlen(p_tmp) - len; + if (lastchar + len_tmp >= bufend) + len_tmp = bufend - lastchar; + + if (len_tmp) { + /* + 1 ensures the '\0' is memmove'd */ + memmove(cp+len_tmp, cp, (lastchar-cp) + 1); + memcpy(cp, p_tmp+len, len_tmp); + kdb_printf("%s", cp); + cp += len_tmp; + lastchar += len_tmp; + if (cp != lastchar) + kdb_position_cursor(kdb_prompt_str, + buffer, cp); + } } kdb_nextline = 1; /* reset output line number */ break; @@ -385,13 +402,9 @@ static char *kdb_read(char *buffer, size_t bufsize) memcpy(cp+1, tmpbuffer, lastchar - cp); *++lastchar = '\0'; *cp = key; - kdb_printf("%s\r", cp); + kdb_printf("%s", cp); ++cp; - tmp = *cp; - *cp = '\0'; - kdb_printf(kdb_prompt_str); - kdb_printf("%s", buffer); - *cp = tmp; + kdb_position_cursor(kdb_prompt_str, buffer, cp); } else { *++lastchar = '\0'; *cp++ = key; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 98b2e192fd696..4d543b1e9d577 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -286,7 +286,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, } else { ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) - goto out_free_pages; + goto out_leak_pages; } memset(ret, 0, size); @@ -307,6 +307,8 @@ void *dma_direct_alloc(struct device *dev, size_t size, out_free_pages: __dma_direct_free_pages(dev, page, size); return NULL; +out_leak_pages: + return NULL; } void dma_direct_free(struct device *dev, size_t size, @@ -367,12 +369,11 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) - goto out_free_pages; + goto out_leak_pages; memset(ret, 0, size); *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); return page; -out_free_pages: - __dma_direct_free_pages(dev, page, size); +out_leak_pages: return NULL; } diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index 02205ab53b7e9..f7f3d14fa69a7 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -101,7 +101,6 @@ static int do_map_benchmark(struct map_benchmark_data *map) struct task_struct **tsk; int threads = map->bparam.threads; int node = map->bparam.node; - const cpumask_t *cpu_mask = cpumask_of_node(node); u64 loops; int ret = 0; int i; @@ -118,11 +117,13 @@ static int do_map_benchmark(struct map_benchmark_data *map) if (IS_ERR(tsk[i])) { pr_err("create dma_map thread failed\n"); ret = PTR_ERR(tsk[i]); + while (--i >= 0) + kthread_stop(tsk[i]); goto out; } if (node != NUMA_NO_NODE) - kthread_bind_mask(tsk[i], cpu_mask); + kthread_bind_mask(tsk[i], cpumask_of_node(node)); } /* clear the old value in the previous benchmark */ @@ -139,13 +140,17 @@ static int do_map_benchmark(struct map_benchmark_data *map) msleep_interruptible(map->bparam.seconds * 1000); - /* wait for the completion of benchmark threads */ + /* wait for the completion of all started benchmark threads */ for (i = 0; i < threads; i++) { - ret = kthread_stop(tsk[i]); - if (ret) - goto out; + int kthread_ret = kthread_stop_put(tsk[i]); + + if (kthread_ret) + ret = kthread_ret; } + if (ret) + goto out; + loops = atomic64_read(&map->loops); if (likely(loops > 0)) { u64 map_variance, unmap_variance; @@ -170,8 +175,6 @@ static int do_map_benchmark(struct map_benchmark_data *map) } out: - for (i = 0; i < threads; i++) - put_task_struct(tsk[i]); put_device(map->dev); kfree(tsk); return ret; @@ -208,7 +211,8 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, } if (map->bparam.node != NUMA_NO_NODE && - !node_possible(map->bparam.node)) { + (map->bparam.node < 0 || map->bparam.node >= MAX_NUMNODES || + !node_possible(map->bparam.node))) { pr_err("invalid numa node\n"); return -EINVAL; } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b079a9a8e0879..b77a661989990 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -69,11 +69,14 @@ * @alloc_size: Size of the allocated buffer. * @list: The free list describing the number of free entries available * from each index. + * @pad_slots: Number of preceding padding slots. Valid only in the first + * allocated non-padding slot. */ struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; - unsigned int list; + unsigned short list; + unsigned short pad_slots; }; static bool swiotlb_force_bounce; @@ -287,6 +290,7 @@ static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start, mem->nslabs - i); mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; + mem->slots[i].pad_slots = 0; } memset(vaddr, 0, bytes); @@ -821,12 +825,30 @@ void swiotlb_dev_init(struct device *dev) #endif } -/* - * Return the offset into a iotlb slot required to keep the device happy. +/** + * swiotlb_align_offset() - Get required offset into an IO TLB allocation. + * @dev: Owning device. + * @align_mask: Allocation alignment mask. + * @addr: DMA address. + * + * Return the minimum offset from the start of an IO TLB allocation which is + * required for a given buffer address and allocation alignment to keep the + * device happy. + * + * First, the address bits covered by min_align_mask must be identical in the + * original address and the bounce buffer address. High bits are preserved by + * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra + * padding bytes before the bounce buffer. + * + * Second, @align_mask specifies which bits of the first allocated slot must + * be zero. This may require allocating additional padding slots, and then the + * offset (in bytes) from the first such padding slot is returned. */ -static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) +static unsigned int swiotlb_align_offset(struct device *dev, + unsigned int align_mask, u64 addr) { - return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); + return addr & dma_get_min_align_mask(dev) & + (align_mask | (IO_TLB_SIZE - 1)); } /* @@ -847,7 +869,7 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size return; tlb_offset = tlb_addr & (IO_TLB_SIZE - 1); - orig_addr_offset = swiotlb_align_offset(dev, orig_addr); + orig_addr_offset = swiotlb_align_offset(dev, 0, orig_addr); if (tlb_offset < orig_addr_offset) { dev_WARN_ONCE(dev, 1, "Access before mapping start detected. orig offset %u, requested offset %u.\n", @@ -981,10 +1003,9 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, pool->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); - unsigned int iotlb_align_mask = - dma_get_min_align_mask(dev) | alloc_align_mask; + unsigned int iotlb_align_mask = dma_get_min_align_mask(dev); unsigned int nslots = nr_slots(alloc_size), stride; - unsigned int offset = swiotlb_align_offset(dev, orig_addr); + unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr); unsigned int index, slots_checked, count = 0, i; unsigned long flags; unsigned int slot_base; @@ -994,18 +1015,29 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool BUG_ON(area_index >= pool->nareas); /* - * For allocations of PAGE_SIZE or larger only look for page aligned - * allocations. + * Historically, swiotlb allocations >= PAGE_SIZE were guaranteed to be + * page-aligned in the absence of any other alignment requirements. + * 'alloc_align_mask' was later introduced to specify the alignment + * explicitly, however this is passed as zero for streaming mappings + * and so we preserve the old behaviour there in case any drivers are + * relying on it. + */ + if (!alloc_align_mask && !iotlb_align_mask && alloc_size >= PAGE_SIZE) + alloc_align_mask = PAGE_SIZE - 1; + + /* + * Ensure that the allocation is at least slot-aligned and update + * 'iotlb_align_mask' to ignore bits that will be preserved when + * offsetting into the allocation. */ - if (alloc_size >= PAGE_SIZE) - iotlb_align_mask |= ~PAGE_MASK; - iotlb_align_mask &= ~(IO_TLB_SIZE - 1); + alloc_align_mask |= (IO_TLB_SIZE - 1); + iotlb_align_mask &= ~alloc_align_mask; /* * For mappings with an alignment requirement don't bother looping to * unaligned slots once we found an aligned one. */ - stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1; + stride = get_max_slots(max(alloc_align_mask, iotlb_align_mask)); spin_lock_irqsave(&area->lock, flags); if (unlikely(nslots > pool->area_nslabs - area->used)) @@ -1015,11 +1047,14 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool index = area->index; for (slots_checked = 0; slots_checked < pool->area_nslabs; ) { + phys_addr_t tlb_addr; + slot_index = slot_base + index; + tlb_addr = slot_addr(tbl_dma_addr, slot_index); - if (orig_addr && - (slot_addr(tbl_dma_addr, slot_index) & - iotlb_align_mask) != (orig_addr & iotlb_align_mask)) { + if ((tlb_addr & alloc_align_mask) || + (orig_addr && (tlb_addr & iotlb_align_mask) != + (orig_addr & iotlb_align_mask))) { index = wrap_area_index(pool, index + 1); slots_checked++; continue; @@ -1292,11 +1327,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, unsigned long attrs) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; - unsigned int offset = swiotlb_align_offset(dev, orig_addr); + unsigned int offset; struct io_tlb_pool *pool; unsigned int i; int index; phys_addr_t tlb_addr; + unsigned short pad_slots; if (!mem || !mem->nslabs) { dev_warn_ratelimited(dev, @@ -1313,6 +1349,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, return (phys_addr_t)DMA_MAPPING_ERROR; } + offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr); index = swiotlb_find_slots(dev, orig_addr, alloc_size + offset, alloc_align_mask, &pool); if (index == -1) { @@ -1328,6 +1365,10 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, * This is needed when we sync the memory. Then we sync the buffer if * needed. */ + pad_slots = offset >> IO_TLB_SHIFT; + offset &= (IO_TLB_SIZE - 1); + index += pad_slots; + pool->slots[index].pad_slots = pad_slots; for (i = 0; i < nr_slots(alloc_size + offset); i++) pool->slots[index + i].orig_addr = slot_addr(orig_addr, i); tlb_addr = slot_addr(pool->start, index) + offset; @@ -1348,13 +1389,17 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) { struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr); unsigned long flags; - unsigned int offset = swiotlb_align_offset(dev, tlb_addr); - int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; - int nslots = nr_slots(mem->slots[index].alloc_size + offset); - int aindex = index / mem->area_nslabs; - struct io_tlb_area *area = &mem->areas[aindex]; + unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr); + int index, nslots, aindex; + struct io_tlb_area *area; int count, i; + index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; + index -= mem->slots[index].pad_slots; + nslots = nr_slots(mem->slots[index].alloc_size + offset); + aindex = index / mem->area_nslabs; + area = &mem->areas[aindex]; + /* * Return the buffer to the free list by setting the corresponding * entries to indicate the number of contiguous entries available. @@ -1377,6 +1422,7 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) mem->slots[i].list = ++count; mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; + mem->slots[i].pad_slots = 0; } /* @@ -1631,16 +1677,24 @@ struct page *swiotlb_alloc(struct device *dev, size_t size) struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; phys_addr_t tlb_addr; + unsigned int align; int index; if (!mem) return NULL; - index = swiotlb_find_slots(dev, 0, size, 0, &pool); + align = (1 << (get_order(size) + PAGE_SHIFT)) - 1; + index = swiotlb_find_slots(dev, 0, size, align, &pool); if (index == -1) return NULL; tlb_addr = slot_addr(pool->start, index); + if (unlikely(!PAGE_ALIGNED(tlb_addr))) { + dev_WARN_ONCE(dev, 1, "Cannot allocate pages from non page-aligned swiotlb addr 0x%pa.\n", + &tlb_addr); + swiotlb_release_slots(dev, tlb_addr); + return NULL; + } return pfn_to_page(PFN_DOWN(tlb_addr)); } @@ -1706,6 +1760,7 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, mem->for_alloc = true; #ifdef CONFIG_SWIOTLB_DYNAMIC spin_lock_init(&mem->lock); + INIT_LIST_HEAD_RCU(&mem->pools); #endif add_mem_pool(mem, pool); diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 88cb3c88aaa5c..90843cc385880 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -57,8 +57,14 @@ long syscall_trace_enter(struct pt_regs *regs, long syscall, /* Either of the above might have changed the syscall number */ syscall = syscall_get_nr(current, regs); - if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) + if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) { trace_sys_enter(regs, syscall); + /* + * Probes or BPF hooks in the tracepoint may have changed the + * system call number as well. + */ + syscall = syscall_get_nr(current, regs); + } syscall_enter_audit(regs, syscall); diff --git a/kernel/events/core.c b/kernel/events/core.c index f0f0f71213a1d..e8e0b21d0a860 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -415,8 +415,13 @@ static struct kmem_cache *perf_event_cache; * 0 - disallow raw tracepoint access for unpriv * 1 - disallow cpu events for unpriv * 2 - disallow kernel profiling for unpriv + * 4 - disallow all unpriv perf event use */ +#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT +int sysctl_perf_event_paranoid __read_mostly = PERF_SECURITY_MAX; +#else int sysctl_perf_event_paranoid __read_mostly = 2; +#endif /* Minimum for 512 kiB + 1 user control page */ int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */ @@ -5365,6 +5370,7 @@ int perf_event_release_kernel(struct perf_event *event) again: mutex_lock(&event->child_mutex); list_for_each_entry(child, &event->child_list, child_list) { + void *var = NULL; /* * Cannot change, child events are not migrated, see the @@ -5405,11 +5411,23 @@ int perf_event_release_kernel(struct perf_event *event) * this can't be the last reference. */ put_event(event); + } else { + var = &ctx->refcount; } mutex_unlock(&event->child_mutex); mutex_unlock(&ctx->mutex); put_ctx(ctx); + + if (var) { + /* + * If perf_event_free_task() has deleted all events from the + * ctx while the child_mutex got released above, make sure to + * notify about the preceding put_ctx(). + */ + smp_mb(); /* pairs with wait_var_event() */ + wake_up_var(var); + } goto again; } mutex_unlock(&event->child_mutex); @@ -12440,6 +12458,9 @@ SYSCALL_DEFINE5(perf_event_open, if (flags & ~PERF_FLAG_ALL) return -EINVAL; + if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN)) + return -EACCES; + err = perf_copy_attr(attr_uptr, &attr); if (err) return err; diff --git a/kernel/fork.c b/kernel/fork.c index 0d944e92a43ff..172fc8c09973c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -112,6 +112,11 @@ #define CREATE_TRACE_POINTS #include +#ifdef CONFIG_USER_NS +extern int unprivileged_userns_clone; +#else +#define unprivileged_userns_clone 0 +#endif /* * Minimum number of threads to boot the kernel @@ -2260,6 +2265,10 @@ __latent_entropy struct task_struct *copy_process( if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); + if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. @@ -3406,6 +3415,12 @@ int ksys_unshare(unsigned long unshare_flags) if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; + if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) { + err = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto bad_unshare_out; + } + err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 74a4ef1da9ad7..fd75b4a484d76 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,9 @@ #include #include "gcov.h" -#if (__GNUC__ >= 10) +#if (__GNUC__ >= 14) +#define GCOV_COUNTERS 9 +#elif (__GNUC__ >= 10) #define GCOV_COUNTERS 8 #elif (__GNUC__ >= 7) #define GCOV_COUNTERS 9 diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 6d443ea22bb73..383fd43ac6122 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -14,7 +14,12 @@ include/ arch/$SRCARCH/include/ " -type cpio > /dev/null +if ! command -v cpio >/dev/null; then + echo >&2 "***" + echo >&2 "*** 'cpio' could not be found." + echo >&2 "***" + exit 1 +fi # Support incremental builds by skipping archive generation # if timestamps of files being archived are not changed. @@ -84,7 +89,7 @@ find $cpio_dir -type f -print0 | # Create archive and try to normalize metadata for reproducibility. tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ - --owner=0 --group=0 --sort=name --numeric-owner \ + --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \ -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null echo $headers_md5 > kernel/kheaders.md5 diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 1ed2b1739363b..5ecd072a34fe7 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -69,6 +69,14 @@ static bool migrate_one_irq(struct irq_desc *desc) return false; } + /* + * Complete an eventually pending irq move cleanup. If this + * interrupt was moved in hard irq context, then the vectors need + * to be cleaned up. It can't wait until this interrupt actually + * happens and this CPU was involved. + */ + irq_force_complete_move(desc); + /* * No move required, if: * - Interrupt is per cpu @@ -87,14 +95,6 @@ static bool migrate_one_irq(struct irq_desc *desc) return false; } - /* - * Complete an eventually pending irq move cleanup. If this - * interrupt was moved in hard irq context, then the vectors need - * to be cleaned up. It can't wait until this interrupt actually - * happens and this CPU was involved. - */ - irq_force_complete_move(desc); - /* * If there is a setaffinity pending, then try to reuse the pending * mask, so the last change of the affinity does not get lost. If diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 371eb1711d346..5c9888901ef44 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -148,7 +148,10 @@ static int irq_find_free_area(unsigned int from, unsigned int cnt) static unsigned int irq_find_at_or_after(unsigned int offset) { unsigned long index = offset; - struct irq_desc *desc = mt_find(&sparse_irqs, &index, nr_irqs); + struct irq_desc *desc; + + guard(rcu)(); + desc = mt_find(&sparse_irqs, &index, nr_irqs); return desc ? irq_desc_get_irq(desc) : nr_irqs; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1782f90cd8c6c..7389add52791f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1642,8 +1642,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!((old->flags & new->flags) & IRQF_SHARED) || - (oldtype != (new->flags & IRQF_TRIGGER_MASK)) || - ((old->flags ^ new->flags) & IRQF_ONESHOT)) + (oldtype != (new->flags & IRQF_TRIGGER_MASK))) + goto mismatch; + + if ((old->flags & IRQF_ONESHOT) && + (new->flags & IRQF_COND_ONESHOT)) + new->flags |= IRQF_ONESHOT; + else if ((old->flags ^ new->flags) & IRQF_ONESHOT) goto mismatch; /* All handlers must agree on per-cpuness */ diff --git a/kernel/kcov.c b/kernel/kcov.c index f9ac2e9e460fc..9f4affae4fad4 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -631,6 +631,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, return -EINVAL; kcov->mode = mode; t->kcov = kcov; + t->kcov_mode = KCOV_MODE_REMOTE; kcov->t = t; kcov->remote = true; kcov->remote_size = remote_arg->area_size; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9d9095e817928..4f917bdad1e11 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1068,6 +1068,7 @@ static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = { static int kprobe_ipmodify_enabled; static int kprobe_ftrace_enabled; +bool kprobe_ftrace_disabled; static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) @@ -1136,6 +1137,11 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops, ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } + +void kprobe_ftrace_kill(void) +{ + kprobe_ftrace_disabled = true; +} #else /* !CONFIG_KPROBES_ON_FTRACE */ static inline int arm_kprobe_ftrace(struct kprobe *p) { @@ -1567,10 +1573,17 @@ static int check_kprobe_address_safe(struct kprobe *p, jump_label_lock(); preempt_disable(); - /* Ensure it is not in reserved area nor out of text */ - if (!(core_kernel_text((unsigned long) p->addr) || - is_module_text_address((unsigned long) p->addr)) || - in_gate_area_no_mm((unsigned long) p->addr) || + /* Ensure the address is in a text area, and find a module if exists. */ + *probed_mod = NULL; + if (!core_kernel_text((unsigned long) p->addr)) { + *probed_mod = __module_text_address((unsigned long) p->addr); + if (!(*probed_mod)) { + ret = -EINVAL; + goto out; + } + } + /* Ensure it is not in reserved area. */ + if (in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || @@ -1580,8 +1593,7 @@ static int check_kprobe_address_safe(struct kprobe *p, goto out; } - /* Check if 'p' is probing a module. */ - *probed_mod = __module_text_address((unsigned long) p->addr); + /* Get module refcount and reject __init functions for loaded modules. */ if (*probed_mod) { /* * We must hold a refcount of the probed module while updating diff --git a/kernel/kthread.c b/kernel/kthread.c index c5e40830c1f2d..ce07480731afb 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -458,6 +458,17 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), * new kernel thread. */ if (unlikely(wait_for_completion_killable(&done))) { + int i = 0; + + /* + * I got SIGKILL, but wait for 10 more seconds for completion + * unless chosen by the OOM killer. This delay is there as a + * workaround for boot failure caused by SIGKILL upon device + * driver initialization timeout. + */ + while (i++ < 10 && !test_tsk_thread_flag(current, TIF_MEMDIE)) + if (wait_for_completion_timeout(&done, HZ)) + goto ready; /* * If I was killed by a fatal signal before kthreadd (or new * kernel thread) calls complete(), leave the cleanup of this @@ -471,6 +482,7 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), */ wait_for_completion(&done); } +ready: task = create->result; free_create: kfree(create); diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 0ea1b2970a23b..28db5b7589eb2 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -236,6 +236,10 @@ choice possible to load a signed module containing the algorithm to check the signature on that module. +config MODULE_SIG_SHA1 + bool "Sign modules with SHA-1" + select CRYPTO_SHA1 + config MODULE_SIG_SHA256 bool "Sign modules with SHA-256" select CRYPTO_SHA256 @@ -265,6 +269,7 @@ endchoice config MODULE_SIG_HASH string depends on MODULE_SIG || IMA_APPRAISE_MODSIG + default "sha1" if MODULE_SIG_SHA1 default "sha256" if MODULE_SIG_SHA256 default "sha384" if MODULE_SIG_SHA384 default "sha512" if MODULE_SIG_SHA512 diff --git a/kernel/module/main.c b/kernel/module/main.c index 36681911c05ac..b0b99348e1a8b 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2489,6 +2489,11 @@ static void do_free_init(struct work_struct *w) } } +void flush_module_init_free_work(void) +{ + flush_work(&init_free_wq); +} + #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "module." /* Default value for module->async_probe_requested */ @@ -2593,8 +2598,8 @@ static noinline int do_init_module(struct module *mod) * Note that module_alloc() on most architectures creates W+X page * mappings which won't be cleaned up until do_free_init() runs. Any * code such as mark_rodata_ro() which depends on those mappings to - * be cleaned up needs to sync with the queued work - ie - * rcu_barrier() + * be cleaned up needs to sync with the queued work by invoking + * flush_module_init_free_work(). */ if (llist_add(&freeinit->node, &init_free_list)) schedule_work(&init_free_wq); diff --git a/kernel/module/signing.c b/kernel/module/signing.c index a2ff4242e623d..f0d2be1ee4f1c 100644 --- a/kernel/module/signing.c +++ b/kernel/module/signing.c @@ -61,10 +61,17 @@ int mod_verify_sig(const void *mod, struct load_info *info) modlen -= sig_len + sizeof(ms); info->len = modlen; - return verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len, + ret = verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len, VERIFY_USE_SECONDARY_KEYRING, VERIFYING_MODULE_SIGNATURE, NULL, NULL); + if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) { + ret = verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len, + VERIFY_USE_PLATFORM_KEYRING, + VERIFYING_MODULE_SIGNATURE, + NULL, NULL); + } + return ret; } int module_sig_check(struct load_info *info, int flags) diff --git a/kernel/module/version.c b/kernel/module/version.c index 53f43ac5a73e9..5528f98c42dc2 100644 --- a/kernel/module/version.c +++ b/kernel/module/version.c @@ -17,32 +17,30 @@ int check_version(const struct load_info *info, { Elf_Shdr *sechdrs = info->sechdrs; unsigned int versindex = info->index.vers; - unsigned int i, num_versions; - struct modversion_info *versions; + struct modversion_info *versions, *end; + u32 crcval; /* Exporting module didn't supply crcs? OK, we're already tainted. */ if (!crc) return 1; + crcval = *crc; /* No versions at all? modprobe --force does this. */ if (versindex == 0) return try_to_force_load(mod, symname) == 0; versions = (void *)sechdrs[versindex].sh_addr; - num_versions = sechdrs[versindex].sh_size - / sizeof(struct modversion_info); + end = (void *)versions + sechdrs[versindex].sh_size; - for (i = 0; i < num_versions; i++) { - u32 crcval; - - if (strcmp(versions[i].name, symname) != 0) + for (; versions < end && versions->next; + versions = (void *)versions + versions->next) { + if (strcmp(versions->name, symname) != 0) continue; - crcval = *crc; - if (versions[i].crc == crcval) + if (versions->crc == crcval) return 1; - pr_debug("Found checksum %X vs module %lX\n", - crcval, versions[i].crc); + pr_debug("Found checksum %X vs module %X\n", + crcval, versions->crc); goto bad_version; } diff --git a/kernel/padata.c b/kernel/padata.c index 179fb1518070c..c974568f65f5d 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -106,7 +106,7 @@ static int __init padata_work_alloc_mt(int nworks, void *data, { int i; - spin_lock(&padata_works_lock); + spin_lock_bh(&padata_works_lock); /* Start at 1 because the current task participates in the job. */ for (i = 1; i < nworks; ++i) { struct padata_work *pw = padata_work_alloc(); @@ -116,7 +116,7 @@ static int __init padata_work_alloc_mt(int nworks, void *data, padata_work_init(pw, padata_mt_helper, data, 0); list_add(&pw->pw_list, head); } - spin_unlock(&padata_works_lock); + spin_unlock_bh(&padata_works_lock); return i; } @@ -134,12 +134,12 @@ static void __init padata_works_free(struct list_head *works) if (list_empty(works)) return; - spin_lock(&padata_works_lock); + spin_lock_bh(&padata_works_lock); list_for_each_entry_safe(cur, next, works, pw_list) { list_del(&cur->pw_list); padata_work_free(cur); } - spin_unlock(&padata_works_lock); + spin_unlock_bh(&padata_works_lock); } static void padata_parallel_worker(struct work_struct *parallel_work) diff --git a/kernel/panic.c b/kernel/panic.c index 2807639aab51d..f22d8f33ea147 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -446,6 +446,14 @@ void panic(const char *fmt, ...) /* Do not scroll important messages printed above */ suppress_printk = 1; + + /* + * The final messages may not have been printed if in a context that + * defers printing (such as NMI) and irq_work is not available. + * Explicitly flush the kernel log buffer one last time. + */ + console_flush_on_panic(CONSOLE_FLUSH_PENDING); + local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 7ade20e952321..415201ca0c7e4 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -218,6 +218,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) */ do { clear_thread_flag(TIF_SIGPENDING); + clear_thread_flag(TIF_NOTIFY_SIGNAL); rc = kernel_wait4(-1, NULL, __WALL, NULL); } while (rc != -ECHILD); diff --git a/kernel/power/process.c b/kernel/power/process.c index cae81a87cc91e..66ac067d9ae64 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -194,8 +194,6 @@ void thaw_processes(void) __usermodehelper_set_disable_depth(UMH_FREEZING); thaw_workqueues(); - cpuset_wait_for_hotplug(); - read_lock(&tasklist_lock); for_each_process_thread(g, p) { /* No other threads should have PF_SUSPEND_TASK set */ diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index fa3bf161d13f7..3aae526cc4aac 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -106,6 +106,12 @@ static void s2idle_enter(void) swait_event_exclusive(s2idle_wait_head, s2idle_state == S2IDLE_STATE_WAKE); + /* + * Kick all CPUs to ensure that they resume their timers and restore + * consistent system state. + */ + wake_up_all_idle_cpus(); + cpus_read_unlock(); raw_spin_lock_irq(&s2idle_lock); @@ -192,6 +198,7 @@ static int __init mem_sleep_default_setup(char *str) if (mem_sleep_labels[state] && !strcmp(str, mem_sleep_labels[state])) { mem_sleep_default = state; + mem_sleep_current = state; break; } diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index b96077152f49d..c8093bcc01fe6 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -140,39 +140,6 @@ static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_sta return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom); } -#ifdef CONFIG_64BIT - -#define __seq_to_nbcon_seq(seq) (seq) -#define __nbcon_seq_to_seq(seq) (seq) - -#else /* CONFIG_64BIT */ - -#define __seq_to_nbcon_seq(seq) ((u32)seq) - -static inline u64 __nbcon_seq_to_seq(u32 nbcon_seq) -{ - u64 seq; - u64 rb_next_seq; - - /* - * The provided sequence is only the lower 32 bits of the ringbuffer - * sequence. It needs to be expanded to 64bit. Get the next sequence - * number from the ringbuffer and fold it. - * - * Having a 32bit representation in the console is sufficient. - * If a console ever gets more than 2^31 records behind - * the ringbuffer then this is the least of the problems. - * - * Also the access to the ring buffer is always safe. - */ - rb_next_seq = prb_next_seq(prb); - seq = rb_next_seq - ((u32)rb_next_seq - nbcon_seq); - - return seq; -} - -#endif /* CONFIG_64BIT */ - /** * nbcon_seq_read - Read the current console sequence * @con: Console to read the sequence of @@ -183,7 +150,7 @@ u64 nbcon_seq_read(struct console *con) { unsigned long nbcon_seq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_seq)); - return __nbcon_seq_to_seq(nbcon_seq); + return __ulseq_to_u64seq(prb, nbcon_seq); } /** @@ -204,7 +171,7 @@ void nbcon_seq_force(struct console *con, u64 seq) */ u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb)); - atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __seq_to_nbcon_seq(valid_seq)); + atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __u64seq_to_ulseq(valid_seq)); /* Clear con->seq since nbcon consoles use con->nbcon_seq instead. */ con->seq = 0; @@ -223,11 +190,11 @@ void nbcon_seq_force(struct console *con, u64 seq) */ static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq) { - unsigned long nbcon_seq = __seq_to_nbcon_seq(ctxt->seq); + unsigned long nbcon_seq = __u64seq_to_ulseq(ctxt->seq); struct console *con = ctxt->console; if (atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_seq), &nbcon_seq, - __seq_to_nbcon_seq(new_seq))) { + __u64seq_to_ulseq(new_seq))) { ctxt->seq = new_seq; } else { ctxt->seq = nbcon_seq_read(con); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index f2444b581e16c..e1b992652ab25 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -347,6 +347,29 @@ static bool panic_in_progress(void) return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); } +/* Return true if a panic is in progress on the current CPU. */ +bool this_cpu_in_panic(void) +{ + /* + * We can use raw_smp_processor_id() here because it is impossible for + * the task to be migrated to the panic_cpu, or away from it. If + * panic_cpu has already been set, and we're not currently executing on + * that CPU, then we never will be. + */ + return unlikely(atomic_read(&panic_cpu) == raw_smp_processor_id()); +} + +/* + * Return true if a panic is in progress on a remote CPU. + * + * On true, the local CPU should immediately release any printing resources + * that may be needed by the panic CPU. + */ +bool other_cpu_in_panic(void) +{ + return (panic_in_progress() && !this_cpu_in_panic()); +} + /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's @@ -1846,10 +1869,23 @@ static bool console_waiter; */ static void console_lock_spinning_enable(void) { + /* + * Do not use spinning in panic(). The panic CPU wants to keep the lock. + * Non-panic CPUs abandon the flush anyway. + * + * Just keep the lockdep annotation. The panic-CPU should avoid + * taking console_owner_lock because it might cause a deadlock. + * This looks like the easiest way how to prevent false lockdep + * reports without handling races a lockless way. + */ + if (panic_in_progress()) + goto lockdep; + raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); +lockdep: /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } @@ -1874,6 +1910,22 @@ static int console_lock_spinning_disable_and_check(int cookie) { int waiter; + /* + * Ignore spinning waiters during panic() because they might get stopped + * or blocked at any time, + * + * It is safe because nobody is allowed to start spinning during panic + * in the first place. If there has been a waiter then non panic CPUs + * might stay spinning. They would get stopped anyway. The panic context + * will never start spinning and an interrupted spin on panic CPU will + * never continue. + */ + if (panic_in_progress()) { + /* Keep lockdep happy. */ + spin_release(&console_owner_dep_map, _THIS_IP_); + return 0; + } + raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; @@ -1974,6 +2026,12 @@ static int console_trylock_spinning(void) */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); + /* + * Update @console_may_schedule for trylock because the previous + * owner may have been schedulable. + */ + console_may_schedule = 0; + return 1; } @@ -2270,8 +2328,7 @@ asmlinkage int vprintk_emit(int facility, int level, if (unlikely(suppress_printk)) return 0; - if (unlikely(suppress_panic_printk) && - atomic_read(&panic_cpu) != raw_smp_processor_id()) + if (unlikely(suppress_panic_printk) && other_cpu_in_panic()) return 0; if (level == LOGLEVEL_SCHED) { @@ -2601,26 +2658,6 @@ static int console_cpu_notify(unsigned int cpu) return 0; } -/* - * Return true if a panic is in progress on a remote CPU. - * - * On true, the local CPU should immediately release any printing resources - * that may be needed by the panic CPU. - */ -bool other_cpu_in_panic(void) -{ - if (!panic_in_progress()) - return false; - - /* - * We can use raw_smp_processor_id() here because it is impossible for - * the task to be migrated to the panic_cpu, or away from it. If - * panic_cpu has already been set, and we're not currently executing on - * that CPU, then we never will be. - */ - return atomic_read(&panic_cpu) != raw_smp_processor_id(); -} - /** * console_lock - block the console subsystem from printing * @@ -3263,6 +3300,21 @@ static int __init keep_bootcon_setup(char *str) early_param("keep_bootcon", keep_bootcon_setup); +static int console_call_setup(struct console *newcon, char *options) +{ + int err; + + if (!newcon->setup) + return 0; + + /* Synchronize with possible boot console. */ + console_lock(); + err = newcon->setup(newcon, options); + console_unlock(); + + return err; +} + /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected @@ -3298,8 +3350,8 @@ static int try_enable_preferred_console(struct console *newcon, if (_braille_register_console(newcon, c)) return 0; - if (newcon->setup && - (err = newcon->setup(newcon, c->options)) != 0) + err = console_call_setup(newcon, c->options); + if (err) return err; } newcon->flags |= CON_ENABLED; @@ -3325,7 +3377,7 @@ static void try_enable_default_console(struct console *newcon) if (newcon->index < 0) newcon->index = 0; - if (newcon->setup && newcon->setup(newcon, NULL) != 0) + if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; @@ -3761,7 +3813,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre might_sleep(); - seq = prb_next_seq(prb); + seq = prb_next_reserve_seq(prb); /* Flush the consoles so that records up to @seq are printed. */ console_lock(); diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c index fde338606ce83..f5a8bb606fe50 100644 --- a/kernel/printk/printk_ringbuffer.c +++ b/kernel/printk/printk_ringbuffer.c @@ -6,6 +6,7 @@ #include #include #include "printk_ringbuffer.h" +#include "internal.h" /** * DOC: printk_ringbuffer overview @@ -303,6 +304,9 @@ * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) + * + * desc_update_last_finalized:A / desc_last_finalized_seq:A + * store finalized record, then set new highest finalized sequence number */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) @@ -1441,20 +1445,118 @@ bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer return false; } +/* + * @last_finalized_seq value guarantees that all records up to and including + * this sequence number are finalized and can be read. The only exception are + * too old records which have already been overwritten. + * + * It is also guaranteed that @last_finalized_seq only increases. + * + * Be aware that finalized records following non-finalized records are not + * reported because they are not yet available to the reader. For example, + * a new record stored via printk() will not be available to a printer if + * it follows a record that has not been finalized yet. However, once that + * non-finalized record becomes finalized, @last_finalized_seq will be + * appropriately updated and the full set of finalized records will be + * available to the printer. And since each printk() caller will either + * directly print or trigger deferred printing of all available unprinted + * records, all printk() messages will get printed. + */ +static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + unsigned long ulseq; + + /* + * Guarantee the sequence number is loaded before loading the + * associated record in order to guarantee that the record can be + * seen by this CPU. This pairs with desc_update_last_finalized:A. + */ + ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq + ); /* LMM(desc_last_finalized_seq:A) */ + + return __ulseq_to_u64seq(rb, ulseq); +} + +static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, + struct printk_record *r, unsigned int *line_count); + +/* + * Check if there are records directly following @last_finalized_seq that are + * finalized. If so, update @last_finalized_seq to the latest of these + * records. It is not allowed to skip over records that are not yet finalized. + */ +static void desc_update_last_finalized(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + u64 old_seq = desc_last_finalized_seq(rb); + unsigned long oldval; + unsigned long newval; + u64 finalized_seq; + u64 try_seq; + +try_again: + finalized_seq = old_seq; + try_seq = finalized_seq + 1; + + /* Try to find later finalized records. */ + while (_prb_read_valid(rb, &try_seq, NULL, NULL)) { + finalized_seq = try_seq; + try_seq++; + } + + /* No update needed if no later finalized record was found. */ + if (finalized_seq == old_seq) + return; + + oldval = __u64seq_to_ulseq(old_seq); + newval = __u64seq_to_ulseq(finalized_seq); + + /* + * Set the sequence number of a later finalized record that has been + * seen. + * + * Guarantee the record data is visible to other CPUs before storing + * its sequence number. This pairs with desc_last_finalized_seq:A. + * + * Memory barrier involvement: + * + * If desc_last_finalized_seq:A reads from + * desc_update_last_finalized:A, then desc_read:A reads from + * _prb_commit:B. + * + * Relies on: + * + * RELEASE from _prb_commit:B to desc_update_last_finalized:A + * matching + * ACQUIRE from desc_last_finalized_seq:A to desc_read:A + * + * Note: _prb_commit:B and desc_update_last_finalized:A can be + * different CPUs. However, the desc_update_last_finalized:A + * CPU (which performs the release) must have previously seen + * _prb_commit:B. + */ + if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq, + &oldval, newval)) { /* LMM(desc_update_last_finalized:A) */ + old_seq = __ulseq_to_u64seq(rb, oldval); + goto try_again; + } +} + /* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ -static void desc_make_final(struct prb_desc_ring *desc_ring, unsigned long id) +static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id) { + struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); - atomic_long_cmpxchg_relaxed(&d->state_var, prev_state_val, - DESC_SV(id, desc_finalized)); /* LMM(desc_make_final:A) */ - - /* Best effort to remember the last finalized @id. */ - atomic_long_set(&desc_ring->last_finalized_id, id); + if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val, + DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */ + desc_update_last_finalized(rb); + } } /** @@ -1550,7 +1652,7 @@ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) - desc_make_final(desc_ring, DESC_ID(id - 1)); + desc_make_final(rb, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ @@ -1643,7 +1745,7 @@ void prb_commit(struct prb_reserved_entry *e) */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) - desc_make_final(desc_ring, e->id); + desc_make_final(e->rb, e->id); } /** @@ -1663,12 +1765,9 @@ void prb_commit(struct prb_reserved_entry *e) */ void prb_final_commit(struct prb_reserved_entry *e) { - struct prb_desc_ring *desc_ring = &e->rb->desc_ring; - _prb_commit(e, desc_finalized); - /* Best effort to remember the last finalized @id. */ - atomic_long_set(&desc_ring->last_finalized_id, e->id); + desc_update_last_finalized(e->rb); } /* @@ -1832,7 +1931,7 @@ static int prb_read(struct printk_ringbuffer *rb, u64 seq, } /* Get the sequence number of the tail descriptor. */ -static u64 prb_first_seq(struct printk_ringbuffer *rb) +u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; @@ -1875,12 +1974,123 @@ static u64 prb_first_seq(struct printk_ringbuffer *rb) return seq; } +/** + * prb_next_reserve_seq() - Get the sequence number after the most recently + * reserved record. + * + * @rb: The ringbuffer to get the sequence number from. + * + * This is the public function available to readers to see what sequence + * number will be assigned to the next reserved record. + * + * Note that depending on the situation, this value can be equal to or + * higher than the sequence number returned by prb_next_seq(). + * + * Context: Any context. + * Return: The sequence number that will be assigned to the next record + * reserved. + */ +u64 prb_next_reserve_seq(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + unsigned long last_finalized_id; + atomic_long_t *state_var; + u64 last_finalized_seq; + unsigned long head_id; + struct prb_desc desc; + unsigned long diff; + struct prb_desc *d; + int err; + + /* + * It may not be possible to read a sequence number for @head_id. + * So the ID of @last_finailzed_seq is used to calculate what the + * sequence number of @head_id will be. + */ + +try_again: + last_finalized_seq = desc_last_finalized_seq(rb); + + /* + * @head_id is loaded after @last_finalized_seq to ensure that + * it points to the record with @last_finalized_seq or newer. + * + * Memory barrier involvement: + * + * If desc_last_finalized_seq:A reads from + * desc_update_last_finalized:A, then + * prb_next_reserve_seq:A reads from desc_reserve:D. + * + * Relies on: + * + * RELEASE from desc_reserve:D to desc_update_last_finalized:A + * matching + * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A + * + * Note: desc_reserve:D and desc_update_last_finalized:A can be + * different CPUs. However, the desc_update_last_finalized:A CPU + * (which performs the release) must have previously seen + * desc_read:C, which implies desc_reserve:D can be seen. + */ + head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */ + + d = to_desc(desc_ring, last_finalized_seq); + state_var = &d->state_var; + + /* Extract the ID, used to specify the descriptor to read. */ + last_finalized_id = DESC_ID(atomic_long_read(state_var)); + + /* Ensure @last_finalized_id is correct. */ + err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc); + + if (err == -EINVAL) { + if (last_finalized_seq == 0) { + /* + * No record has been finalized or even reserved yet. + * + * The @head_id is initialized such that the first + * increment will yield the first record (seq=0). + * Handle it separately to avoid a negative @diff + * below. + */ + if (head_id == DESC0_ID(desc_ring->count_bits)) + return 0; + + /* + * One or more descriptors are already reserved. Use + * the descriptor ID of the first one (@seq=0) for + * the @diff below. + */ + last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1; + } else { + /* Record must have been overwritten. Try again. */ + goto try_again; + } + } + + /* Diff of known descriptor IDs to compute related sequence numbers. */ + diff = head_id - last_finalized_id; + + /* + * @head_id points to the most recently reserved record, but this + * function returns the sequence number that will be assigned to the + * next (not yet reserved) record. Thus +1 is needed. + */ + return (last_finalized_seq + diff + 1); +} + /* - * Non-blocking read of a record. Updates @seq to the last finalized record - * (which may have no data available). + * Non-blocking read of a record. + * + * On success @seq is updated to the record that was read and (if provided) + * @r and @line_count will contain the read/calculated data. + * + * On failure @seq is updated to a record that is not yet available to the + * reader, but it will be the next record available to the reader. * - * See the description of prb_read_valid() and prb_read_valid_info() - * for details. + * Note: When the current CPU is in panic, this function will skip over any + * non-existent/non-finalized records in order to allow the panic CPU + * to print any and all records that have been finalized. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) @@ -1899,12 +2109,32 @@ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, *seq = tail_seq; } else if (err == -ENOENT) { - /* Record exists, but no data available. Skip. */ + /* Record exists, but the data was lost. Skip. */ (*seq)++; } else { - /* Non-existent/non-finalized record. Must stop. */ - return false; + /* + * Non-existent/non-finalized record. Must stop. + * + * For panic situations it cannot be expected that + * non-finalized records will become finalized. But + * there may be other finalized records beyond that + * need to be printed for a panic situation. If this + * is the panic CPU, skip this + * non-existent/non-finalized record unless it is + * at or beyond the head, in which case it is not + * possible to continue. + * + * Note that new messages printed on panic CPU are + * finalized when we are here. The only exception + * might be the last message without trailing newline. + * But it would have the sequence number returned + * by "prb_next_reserve_seq() - 1". + */ + if (this_cpu_in_panic() && ((*seq + 1) < prb_next_reserve_seq(rb))) + (*seq)++; + else + return false; } } @@ -1932,7 +2162,7 @@ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * - * Failure means @seq refers to a not yet written record. + * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) @@ -1962,7 +2192,7 @@ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * - * Failure means @seq refers to a not yet written record. + * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) @@ -2008,7 +2238,9 @@ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently - * available records should be skipped. + * available records should be skipped. It is guaranteed that all records + * previous to the returned value have been finalized and are (or were) + * available to the reader. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record @@ -2016,34 +2248,19 @@ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) */ u64 prb_next_seq(struct printk_ringbuffer *rb) { - struct prb_desc_ring *desc_ring = &rb->desc_ring; - enum desc_state d_state; - unsigned long id; u64 seq; - /* Check if the cached @id still points to a valid @seq. */ - id = atomic_long_read(&desc_ring->last_finalized_id); - d_state = desc_read(desc_ring, id, NULL, &seq, NULL); + seq = desc_last_finalized_seq(rb); - if (d_state == desc_finalized || d_state == desc_reusable) { - /* - * Begin searching after the last finalized record. - * - * On 0, the search must begin at 0 because of hack#2 - * of the bootstrapping phase it is not known if a - * record at index 0 exists. - */ - if (seq != 0) - seq++; - } else { - /* - * The information about the last finalized sequence number - * has gone. It should happen only when there is a flood of - * new messages and the ringbuffer is rapidly recycled. - * Give up and start from the beginning. - */ - seq = 0; - } + /* + * Begin searching after the last finalized record. + * + * On 0, the search must begin at 0 because of hack#2 + * of the bootstrapping phase it is not known if a + * record at index 0 exists. + */ + if (seq != 0) + seq++; /* * The information about the last finalized @seq might be inaccurate. @@ -2085,7 +2302,7 @@ void prb_init(struct printk_ringbuffer *rb, rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); - atomic_long_set(&rb->desc_ring.last_finalized_id, DESC0_ID(descbits)); + atomic_long_set(&rb->desc_ring.last_finalized_seq, 0); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; diff --git a/kernel/printk/printk_ringbuffer.h b/kernel/printk/printk_ringbuffer.h index 18cd25e489b89..cb887489d00f0 100644 --- a/kernel/printk/printk_ringbuffer.h +++ b/kernel/printk/printk_ringbuffer.h @@ -75,7 +75,7 @@ struct prb_desc_ring { struct printk_info *infos; atomic_long_t head_id; atomic_long_t tail_id; - atomic_long_t last_finalized_id; + atomic_long_t last_finalized_seq; }; /* @@ -259,7 +259,7 @@ static struct printk_ringbuffer name = { \ .infos = &_##name##_infos[0], \ .head_id = ATOMIC_INIT(DESC0_ID(descbits)), \ .tail_id = ATOMIC_INIT(DESC0_ID(descbits)), \ - .last_finalized_id = ATOMIC_INIT(DESC0_ID(descbits)), \ + .last_finalized_seq = ATOMIC_INIT(0), \ }, \ .text_data_ring = { \ .size_bits = (avgtextbits) + (descbits), \ @@ -378,7 +378,41 @@ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count); +u64 prb_first_seq(struct printk_ringbuffer *rb); u64 prb_first_valid_seq(struct printk_ringbuffer *rb); u64 prb_next_seq(struct printk_ringbuffer *rb); +u64 prb_next_reserve_seq(struct printk_ringbuffer *rb); + +#ifdef CONFIG_64BIT + +#define __u64seq_to_ulseq(u64seq) (u64seq) +#define __ulseq_to_u64seq(rb, ulseq) (ulseq) + +#else /* CONFIG_64BIT */ + +#define __u64seq_to_ulseq(u64seq) ((u32)u64seq) + +static inline u64 __ulseq_to_u64seq(struct printk_ringbuffer *rb, u32 ulseq) +{ + u64 rb_first_seq = prb_first_seq(rb); + u64 seq; + + /* + * The provided sequence is only the lower 32 bits of the ringbuffer + * sequence. It needs to be expanded to 64bit. Get the first sequence + * number from the ringbuffer and fold it. + * + * Having a 32bit representation in the console is sufficient. + * If a console ever gets more than 2^31 records behind + * the ringbuffer then this is the least of the problems. + * + * Also the access to the ring buffer is always safe. + */ + seq = rb_first_seq - (s32)((u32)rb_first_seq - ulseq); + + return seq; +} + +#endif /* CONFIG_64BIT */ #endif /* _KERNEL_PRINTK_RINGBUFFER_H */ diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index bdd7eadb33d8f..e7d2dd2675931 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -314,6 +314,19 @@ config RCU_LAZY To save power, batch RCU callbacks and flush after delay, memory pressure, or callback list growing too big. + Requires rcu_nocbs=all to be set. + + Use rcutree.enable_rcu_lazy=0 to turn it off at boot time. + +config RCU_LAZY_DEFAULT_OFF + bool "Turn RCU lazy invocation off by default" + depends on RCU_LAZY + default n + help + Allows building the kernel with CONFIG_RCU_LAZY=y yet keep it default + off. Boot time param rcutree.enable_rcu_lazy=1 can be used to switch + it back on. + config RCU_DOUBLE_CHECK_CB_TIME bool "RCU callback-batch backup time check" depends on RCU_EXPERT diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 7567ca8e743ca..0b665609fc3ba 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1993,7 +1993,8 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid) preempt_disable(); pipe_count = READ_ONCE(p->rtort_pipe_count); if (pipe_count > RCU_TORTURE_PIPE_LEN) { - /* Should not happen, but... */ + // Should not happen in a correct RCU implementation, + // happens quite often for torture_type=busted. pipe_count = RCU_TORTURE_PIPE_LEN; } completed = cur_ops->get_gp_seq(); @@ -2481,8 +2482,8 @@ static int rcu_torture_stall(void *args) preempt_disable(); pr_alert("%s start on CPU %d.\n", __func__, raw_smp_processor_id()); - while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(), - stop_at)) + while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(), stop_at) && + !kthread_should_stop()) if (stall_cpu_block) { #ifdef CONFIG_PREEMPTION preempt_schedule(); @@ -3035,11 +3036,12 @@ static void rcu_torture_barrier_cbf(struct rcu_head *rcu) } /* IPI handler to get callback posted on desired CPU, if online. */ -static void rcu_torture_barrier1cb(void *rcu_void) +static int rcu_torture_barrier1cb(void *rcu_void) { struct rcu_head *rhp = rcu_void; cur_ops->call(rhp, rcu_torture_barrier_cbf); + return 0; } /* kthread function to register callbacks used to test RCU barriers. */ @@ -3065,11 +3067,9 @@ static int rcu_torture_barrier_cbs(void *arg) * The above smp_load_acquire() ensures barrier_phase load * is ordered before the following ->call(). */ - if (smp_call_function_single(myid, rcu_torture_barrier1cb, - &rcu, 1)) { - // IPI failed, so use direct call from current CPU. + if (smp_call_on_cpu(myid, rcu_torture_barrier1cb, &rcu, 1)) cur_ops->call(&rcu, rcu_torture_barrier_cbf); - } + if (atomic_dec_and_test(&barrier_cbs_count)) wake_up(&barrier_wq); } while (!torture_must_stop()); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 732ad5b39946a..3f64268fe9ead 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1941,7 +1941,7 @@ void show_rcu_tasks_trace_gp_kthread(void) { char buf[64]; - sprintf(buf, "N%lu h:%lu/%lu/%lu", + snprintf(buf, sizeof(buf), "N%lu h:%lu/%lu/%lu", data_race(n_trc_holdouts), data_race(n_heavy_reader_ofl_updates), data_race(n_heavy_reader_updates), diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b2bccfd37c383..0ae3c74a134c0 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2753,6 +2753,9 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in) } #ifdef CONFIG_RCU_LAZY +static bool enable_rcu_lazy __read_mostly = !IS_ENABLED(CONFIG_RCU_LAZY_DEFAULT_OFF); +module_param(enable_rcu_lazy, bool, 0444); + /** * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and * flush all lazy callbacks (including the new one) to the main ->cblist while @@ -2778,6 +2781,8 @@ void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) __call_rcu_common(head, func, false); } EXPORT_SYMBOL_GPL(call_rcu_hurry); +#else +#define enable_rcu_lazy false #endif /** @@ -2826,7 +2831,7 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry); */ void call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY)); + __call_rcu_common(head, func, enable_rcu_lazy); } EXPORT_SYMBOL_GPL(call_rcu); @@ -4743,13 +4748,16 @@ static void __init rcu_start_exp_gp_kworkers(void) rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name); if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { pr_err("Failed to create %s!\n", gp_kworker_name); + rcu_exp_gp_kworker = NULL; return; } rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name); if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) { pr_err("Failed to create %s!\n", par_gp_kworker_name); + rcu_exp_par_gp_kworker = NULL; kthread_destroy_worker(rcu_exp_gp_kworker); + rcu_exp_gp_kworker = NULL; return; } diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 2ac440bc7e10b..8107f818455da 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -428,7 +428,12 @@ static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp) __sync_rcu_exp_select_node_cpus(rewp); } -static inline bool rcu_gp_par_worker_started(void) +static inline bool rcu_exp_worker_started(void) +{ + return !!READ_ONCE(rcu_exp_gp_kworker); +} + +static inline bool rcu_exp_par_worker_started(void) { return !!READ_ONCE(rcu_exp_par_gp_kworker); } @@ -478,7 +483,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) __sync_rcu_exp_select_node_cpus(rewp); } -static inline bool rcu_gp_par_worker_started(void) +static inline bool rcu_exp_worker_started(void) +{ + return !!READ_ONCE(rcu_gp_wq); +} + +static inline bool rcu_exp_par_worker_started(void) { return !!READ_ONCE(rcu_par_gp_wq); } @@ -541,7 +551,7 @@ static void sync_rcu_exp_select_cpus(void) rnp->exp_need_flush = false; if (!READ_ONCE(rnp->expmask)) continue; /* Avoid early boot non-existent wq. */ - if (!rcu_gp_par_worker_started() || + if (!rcu_exp_par_worker_started() || rcu_scheduler_active != RCU_SCHEDULER_RUNNING || rcu_is_last_leaf_node(rnp)) { /* No worker started yet or last leaf, do direct call. */ @@ -956,7 +966,7 @@ static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp) */ void synchronize_rcu_expedited(void) { - bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT); + bool use_worker; unsigned long flags; struct rcu_exp_work rew; struct rcu_node *rnp; @@ -967,6 +977,9 @@ void synchronize_rcu_expedited(void) lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_rcu_expedited() in RCU read-side critical section"); + use_worker = (rcu_scheduler_active != RCU_SCHEDULER_INIT) && + rcu_exp_worker_started(); + /* Is the state is such that the call is a grace period? */ if (rcu_blocking_is_gp()) { // Note well that this code runs with !PREEMPT && !SMP. @@ -996,7 +1009,7 @@ void synchronize_rcu_expedited(void) return; /* Someone else did our work for us. */ /* Ensure that load happens before action based on it. */ - if (unlikely(boottime)) { + if (unlikely(!use_worker)) { /* Direct call during scheduler init and early_initcalls(). */ rcu_exp_sel_wait_wake(s); } else { @@ -1014,7 +1027,7 @@ void synchronize_rcu_expedited(void) /* Let the next expedited grace period start. */ mutex_unlock(&rcu_state.exp_mutex); - if (likely(!boottime)) + if (likely(use_worker)) synchronize_rcu_expedited_destroy_work(&rew); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 4efbf7333d4e1..d430b4656f59e 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -1383,7 +1383,7 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) rcu_nocb_unlock_irqrestore(rdp, flags); continue; } - WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false)); + rcu_nocb_try_flush_bypass(rdp, jiffies); rcu_nocb_unlock_irqrestore(rdp, flags); wake_nocb_gp(rdp, false); sc->nr_to_scan -= _count; diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 5d666428546b0..b5ec62b2d850a 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -504,7 +504,8 @@ static void print_cpu_stall_info(int cpu) rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu)); rcuc_starved = rcu_is_rcuc_kthread_starving(rdp, &j); if (rcuc_starved) - sprintf(buf, " rcuc=%ld jiffies(starved)", j); + // Print signed value, as negative values indicate a probable bug. + snprintf(buf, sizeof(buf), " rcuc=%ld jiffies(starved)", j); pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%04x/%ld/%#lx softirq=%u/%u fqs=%ld%s%s\n", cpu, "O."[!!cpu_online(cpu)], diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9116bcc903467..e11f7890d9419 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7328,6 +7328,7 @@ int can_nice(const struct task_struct *p, const int nice) { return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE); } +EXPORT_SYMBOL(can_nice); #ifdef __ARCH_WANT_SYS_NICE @@ -11381,7 +11382,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of, { struct task_group *tg = css_tg(of_css(of)); u64 period = tg_get_cfs_period(tg); - u64 burst = tg_get_cfs_burst(tg); + u64 burst = tg->cfs_bandwidth.burst; u64 quota; int ret; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 533547e3c90a7..a01269ed968a7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -696,15 +696,21 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * * XXX could add max_slice to the augmented data to track this. */ -static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) +static s64 entity_lag(u64 avruntime, struct sched_entity *se) { - s64 lag, limit; + s64 vlag, limit; + + vlag = avruntime - se->vruntime; + limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); + + return clamp(vlag, -limit, limit); +} +static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ SCHED_WARN_ON(!se->on_rq); - lag = avg_vruntime(cfs_rq) - se->vruntime; - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); - se->vlag = clamp(lag, -limit, limit); + se->vlag = entity_lag(avg_vruntime(cfs_rq), se); } /* @@ -3670,11 +3676,10 @@ static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif -static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, +static void reweight_eevdf(struct sched_entity *se, u64 avruntime, unsigned long weight) { unsigned long old_weight = se->load.weight; - u64 avruntime = avg_vruntime(cfs_rq); s64 vlag, vslice; /* @@ -3755,7 +3760,7 @@ static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, * = V - vl' */ if (avruntime != se->vruntime) { - vlag = (s64)(avruntime - se->vruntime); + vlag = entity_lag(avruntime, se); vlag = div_s64(vlag * old_weight, weight); se->vruntime = avruntime - vlag; } @@ -3781,25 +3786,26 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { bool curr = cfs_rq->curr == se; + u64 avruntime; if (se->on_rq) { /* commit outstanding execution time */ - if (curr) - update_curr(cfs_rq); - else + update_curr(cfs_rq); + avruntime = avg_vruntime(cfs_rq); + if (!curr) __dequeue_entity(cfs_rq, se); update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); - if (!se->on_rq) { + if (se->on_rq) { + reweight_eevdf(se, avruntime, weight); + } else { /* * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), * we need to scale se->vlag when w_i changes. */ se->vlag = div_s64(se->vlag * se->load.weight, weight); - } else { - reweight_eevdf(cfs_rq, se, weight); } update_load_set(&se->load, weight); @@ -6663,22 +6669,42 @@ static inline void hrtick_update(struct rq *rq) #ifdef CONFIG_SMP static inline bool cpu_overutilized(int cpu) { - unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); - unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + unsigned long rq_util_min, rq_util_max; + + if (!sched_energy_enabled()) + return false; + + rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); + rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); /* Return true only if the utilization doesn't fit CPU's capacity */ return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu); } -static inline void update_overutilized_status(struct rq *rq) +static inline void set_rd_overutilized_status(struct root_domain *rd, + unsigned int status) { - if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) { - WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED); - trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED); - } + if (!sched_energy_enabled()) + return; + + WRITE_ONCE(rd->overutilized, status); + trace_sched_overutilized_tp(rd, !!status); +} + +static inline void check_update_overutilized_status(struct rq *rq) +{ + /* + * overutilized field is used for load balancing decisions only + * if energy aware scheduler is being used + */ + if (!sched_energy_enabled()) + return; + + if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) + set_rd_overutilized_status(rq->rd, SG_OVERUTILIZED); } #else -static inline void update_overutilized_status(struct rq *rq) { } +static inline void check_update_overutilized_status(struct rq *rq) { } #endif /* Runqueue only has SCHED_IDLE tasks enqueued */ @@ -6779,7 +6805,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) * and the following generally works well enough in practice. */ if (!task_new) - update_overutilized_status(rq); + check_update_overutilized_status(rq); enqueue_throttle: assert_list_leaf_cfs_rq(rq); @@ -7289,7 +7315,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu if (!available_idle_cpu(cpu)) { idle = false; if (*idle_cpu == -1) { - if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) { + if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, cpus)) { *idle_cpu = cpu; break; } @@ -7297,7 +7323,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu } break; } - if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr)) + if (*idle_cpu == -1 && cpumask_test_cpu(cpu, cpus)) *idle_cpu = cpu; } @@ -7311,13 +7337,19 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu /* * Scan the local SMT mask for idle CPUs. */ -static int select_idle_smt(struct task_struct *p, int target) +static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { int cpu; for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) { if (cpu == target) continue; + /* + * Check if the CPU is in the LLC scheduling domain of @target. + * Due to isolcpus, there is no guarantee that all the siblings are in the domain. + */ + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) + continue; if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) return cpu; } @@ -7341,7 +7373,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma return __select_idle_cpu(core, p); } -static inline int select_idle_smt(struct task_struct *p, int target) +static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { return -1; } @@ -7591,7 +7623,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) has_idle_core = test_idle_cores(target); if (!has_idle_core && cpus_share_cache(prev, target)) { - i = select_idle_smt(p, prev); + i = select_idle_smt(p, sd, prev); if ((unsigned int)i < nr_cpumask_bits) return i; } @@ -10609,19 +10641,14 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd env->fbq_type = fbq_classify_group(&sds->busiest_stat); if (!env->sd->parent) { - struct root_domain *rd = env->dst_rq->rd; - /* update overload indicator if we are at root domain */ - WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD); + WRITE_ONCE(env->dst_rq->rd->overload, sg_status & SG_OVERLOAD); /* Update over-utilization (tipping point, U >= 0) indicator */ - WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED); - trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED); + set_rd_overutilized_status(env->dst_rq->rd, + sg_status & SG_OVERUTILIZED); } else if (sg_status & SG_OVERUTILIZED) { - struct root_domain *rd = env->dst_rq->rd; - - WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED); - trace_sched_overutilized_tp(rd, SG_OVERUTILIZED); + set_rd_overutilized_status(env->dst_rq->rd, SG_OVERUTILIZED); } update_idle_cpu_scan(env, sum_util); @@ -12627,7 +12654,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) task_tick_numa(rq, curr); update_misfit_status(curr, rq); - update_overutilized_status(task_rq(curr)); + check_update_overutilized_status(task_rq(curr)); task_tick_core(rq, curr); } diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 373d42c707bc5..82e2f7fc7c267 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -109,6 +109,7 @@ static void __init housekeeping_setup_type(enum hk_type type, static int __init housekeeping_setup(char *str, unsigned long flags) { cpumask_var_t non_housekeeping_mask, housekeeping_staging; + unsigned int first_cpu; int err = 0; if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) { @@ -129,7 +130,8 @@ static int __init housekeeping_setup(char *str, unsigned long flags) cpumask_andnot(housekeeping_staging, cpu_possible_mask, non_housekeeping_mask); - if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) { + first_cpu = cpumask_first_and(cpu_present_mask, housekeeping_staging); + if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) { __cpumask_set_cpu(smp_processor_id(), housekeeping_staging); __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); if (!housekeeping.flags) { @@ -138,6 +140,9 @@ static int __init housekeeping_setup(char *str, unsigned long flags) } } + if (cpumask_empty(non_housekeeping_mask)) + goto free_housekeeping_staging; + if (!housekeeping.flags) { /* First setup call ("nohz_full=" or "isolcpus=") */ enum hk_type type; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 001fe047bd5d8..8c817d0a92f3e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -79,6 +79,8 @@ # include #endif +#include + #include "cpupri.h" #include "cpudeadline.h" @@ -3445,13 +3447,19 @@ static inline void switch_mm_cid(struct rq *rq, * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu]. * Provide it here. */ - if (!prev->mm) // from kernel + if (!prev->mm) { // from kernel smp_mb(); - /* - * user -> user transition guarantees a memory barrier through - * switch_mm() when current->mm changes. If current->mm is - * unchanged, no barrier is needed. - */ + } else { // from user + /* + * user->user transition relies on an implicit + * memory barrier in switch_mm() when + * current->mm changes. If the architecture + * switch_mm() does not have an implicit memory + * barrier, it is emitted here. If current->mm + * is unchanged, no barrier is needed. + */ + smp_mb__after_switch_mm(); + } } if (prev->mm_cid_active) { mm_cid_snapshot_time(rq, prev->mm); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 10d1391e74161..4fdab14953fc9 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1468,7 +1468,7 @@ static void set_domain_attribute(struct sched_domain *sd, } else request = attr->relax_domain_level; - if (sd->level > request) { + if (sd->level >= request) { /* Turn off idle balance on this domain: */ sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); } diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 51e38f5f47018..8b3547706b00a 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -212,6 +212,7 @@ void __wake_up_pollfree(struct wait_queue_head *wq_head) /* POLLFREE must have cleared the queue. */ WARN_ON_ONCE(waitqueue_active(wq_head)); } +EXPORT_SYMBOL_GPL(__wake_up_pollfree); /* * Note: we use "set_current_state()" _after_ the wait-queue add, diff --git a/kernel/softirq.c b/kernel/softirq.c index 210cf5f8d92c2..bd9716d7bb638 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -507,7 +507,7 @@ static inline bool lockdep_softirq_start(void) { return false; } static inline void lockdep_softirq_end(bool in_hardirq) { } #endif -asmlinkage __visible void __softirq_entry __do_softirq(void) +static void handle_softirqs(bool ksirqd) { unsigned long end = jiffies + MAX_SOFTIRQ_TIME; unsigned long old_flags = current->flags; @@ -562,8 +562,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) pending >>= softirq_bit; } - if (!IS_ENABLED(CONFIG_PREEMPT_RT) && - __this_cpu_read(ksoftirqd) == current) + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd) rcu_softirq_qs(); local_irq_disable(); @@ -583,6 +582,11 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) current_restore_flags(old_flags, PF_MEMALLOC); } +asmlinkage __visible void __softirq_entry __do_softirq(void) +{ + handle_softirqs(false); +} + /** * irq_enter_rcu - Enter an interrupt context with RCU watching */ @@ -918,7 +922,7 @@ static void run_ksoftirqd(unsigned int cpu) * We can safely run softirq on inline stack, as we are not deep * in the task stack here. */ - __do_softirq(); + handle_softirqs(true); ksoftirqd_run_end(); cond_resched(); return; diff --git a/kernel/sys.c b/kernel/sys.c index f8e543f1e38a0..4889a902609b7 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1262,6 +1262,21 @@ SYSCALL_DEFINE0(setsid) DECLARE_RWSEM(uts_sem); +#ifdef COMPAT_UTS_MACHINE +static char compat_uts_machine[__OLD_UTS_LEN+1] = COMPAT_UTS_MACHINE; + +static int __init parse_compat_uts_machine(char *arg) +{ + strncpy(compat_uts_machine, arg, __OLD_UTS_LEN); + compat_uts_machine[__OLD_UTS_LEN] = 0; + return 0; +} +early_param("compat_uts_machine", parse_compat_uts_machine); + +#undef COMPAT_UTS_MACHINE +#define COMPAT_UTS_MACHINE compat_uts_machine +#endif + #ifdef COMPAT_UTS_MACHINE #define override_architecture(name) \ (personality(current->personality) == PER_LINUX32 && \ @@ -2408,8 +2423,11 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; - /* PARISC cannot allow mdwe as it needs writable stacks */ - if (IS_ENABLED(CONFIG_PARISC)) + /* + * EOPNOTSUPP might be more appropriate here in principle, but + * existing userspace depends on EINVAL specifically. + */ + if (!arch_memory_deny_write_exec_supported()) return -EINVAL; current_bits = get_current_mdwe(); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 157f7ce2942d2..9d198d7f482b8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -63,6 +63,7 @@ #include #include #include +#include #include "../lib/kstrtox.h" @@ -1766,6 +1767,15 @@ static struct ctl_table kern_table[] = { .proc_handler = sysrq_sysctl_handler, }, #endif +#ifdef CONFIG_USER_NS + { + .procname = "unprivileged_userns_clone", + .data = &unprivileged_userns_clone, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif #ifdef CONFIG_PROC_SYSCTL { .procname = "cad_pid", diff --git a/kernel/task_work.c b/kernel/task_work.c index 95a7e1b7f1dab..c15a750ee4cd2 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -73,6 +73,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work, return 0; } +EXPORT_SYMBOL(task_work_add); /** * task_work_cancel_match - cancel a pending work added by task_work_add() diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 3052b1f1168e2..53fa647a65fe9 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -20,6 +20,16 @@ #include "tick-internal.h" #include "timekeeping_internal.h" +static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) +{ + u64 delta = clocksource_delta(end, start, cs->mask); + + if (likely(delta < cs->max_cycles)) + return clocksource_cyc2ns(delta, cs->mult, cs->shift); + + return mul_u64_u32_shr(delta, cs->mult, cs->shift); +} + /** * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks * @mult: pointer to mult variable @@ -225,8 +235,8 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { unsigned int nretries; - u64 wd_end, wd_end2, wd_delta; int64_t wd_delay, wd_seq_delay; + u64 wd_end, wd_end2; for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) { local_irq_disable(); @@ -236,9 +246,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, wd_end2 = watchdog->read(watchdog); local_irq_enable(); - wd_delta = clocksource_delta(wd_end, *wdnow, watchdog->mask); - wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, - watchdog->shift); + wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end); if (wd_delay <= WATCHDOG_MAX_SKEW) { if (nretries > 1 || nretries >= max_cswd_read_retries) { pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", @@ -256,8 +264,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, * report system busy, reinit the watchdog and skip the current * watchdog test. */ - wd_delta = clocksource_delta(wd_end2, wd_end, watchdog->mask); - wd_seq_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift); + wd_seq_delay = cycles_to_nsec_safe(watchdog, wd_end, wd_end2); if (wd_seq_delay > WATCHDOG_MAX_SKEW/2) goto skip_test; } @@ -368,8 +375,7 @@ void clocksource_verify_percpu(struct clocksource *cs) delta = (csnow_end - csnow_mid) & cs->mask; if (delta < 0) cpumask_set_cpu(cpu, &cpus_ahead); - delta = clocksource_delta(csnow_end, csnow_begin, cs->mask); - cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + cs_nsec = cycles_to_nsec_safe(cs, csnow_begin, csnow_end); if (cs_nsec > cs_nsec_max) cs_nsec_max = cs_nsec; if (cs_nsec < cs_nsec_min) @@ -400,8 +406,8 @@ static inline void clocksource_reset_watchdog(void) static void clocksource_watchdog(struct timer_list *unused) { - u64 csnow, wdnow, cslast, wdlast, delta; int64_t wd_nsec, cs_nsec, interval; + u64 csnow, wdnow, cslast, wdlast; int next_cpu, reset_pending; struct clocksource *cs; enum wd_read_status read_ret; @@ -458,12 +464,8 @@ static void clocksource_watchdog(struct timer_list *unused) continue; } - delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask); - wd_nsec = clocksource_cyc2ns(delta, watchdog->mult, - watchdog->shift); - - delta = clocksource_delta(csnow, cs->cs_last, cs->mask); - cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + wd_nsec = cycles_to_nsec_safe(watchdog, cs->wd_last, wdnow); + cs_nsec = cycles_to_nsec_safe(cs, cs->cs_last, csnow); wdlast = cs->wd_last; /* save these in case we print them */ cslast = cs->cs_last; cs->cs_last = csnow; @@ -834,7 +836,7 @@ void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles) */ u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) { - u64 now, delta, nsec = 0; + u64 now, nsec = 0; if (!suspend_clocksource) return 0; @@ -849,12 +851,8 @@ u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) else now = suspend_clocksource->read(suspend_clocksource); - if (now > suspend_start) { - delta = clocksource_delta(now, suspend_start, - suspend_clocksource->mask); - nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult, - suspend_clocksource->shift); - } + if (now > suspend_start) + nsec = cycles_to_nsec_safe(suspend_clocksource, suspend_start, now); /* * Disable the suspend timer to save power if current clocksource is diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 9de66bbbb3d15..4782edcbe7b9b 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -129,15 +129,17 @@ static int posix_clock_open(struct inode *inode, struct file *fp) goto out; } pccontext->clk = clk; - fp->private_data = pccontext; - if (clk->ops.open) + if (clk->ops.open) { err = clk->ops.open(pccontext, fp->f_mode); - else - err = 0; - - if (!err) { - get_device(clk->dev); + if (err) { + kfree(pccontext); + goto out; + } } + + fp->private_data = pccontext; + get_device(clk->dev); + err = 0; out: up_read(&clk->rwsem); return err; diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index e9138cd7a0f52..7f2b17fc8ce40 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -179,26 +179,6 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) } } -#ifdef CONFIG_NO_HZ_FULL -static void giveup_do_timer(void *info) -{ - int cpu = *(unsigned int *)info; - - WARN_ON(tick_do_timer_cpu != smp_processor_id()); - - tick_do_timer_cpu = cpu; -} - -static void tick_take_do_timer_from_boot(void) -{ - int cpu = smp_processor_id(); - int from = tick_do_timer_boot_cpu; - - if (from >= 0 && from != cpu) - smp_call_function_single(from, giveup_do_timer, &cpu, 1); -} -#endif - /* * Setup the tick device */ @@ -222,19 +202,25 @@ static void tick_setup_device(struct tick_device *td, tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* - * The boot CPU may be nohz_full, in which case set - * tick_do_timer_boot_cpu so the first housekeeping - * secondary that comes up will take do_timer from - * us. + * The boot CPU may be nohz_full, in which case the + * first housekeeping secondary will take do_timer() + * from it. */ if (tick_nohz_full_cpu(cpu)) tick_do_timer_boot_cpu = cpu; - } else if (tick_do_timer_boot_cpu != -1 && - !tick_nohz_full_cpu(cpu)) { - tick_take_do_timer_from_boot(); + } else if (tick_do_timer_boot_cpu != -1 && !tick_nohz_full_cpu(cpu)) { tick_do_timer_boot_cpu = -1; - WARN_ON(tick_do_timer_cpu != cpu); + /* + * The boot CPU will stay in periodic (NOHZ disabled) + * mode until clocksource_done_booting() called after + * smp_init() selects a high resolution clocksource and + * timekeeping_notify() kicks the NOHZ stuff alive. + * + * So this WRITE_ONCE can only race with the READ_ONCE + * check in tick_periodic() but this race is harmless. + */ + WRITE_ONCE(tick_do_timer_cpu, cpu); #endif } diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c index ca058c8af6baf..3e5d422dd15cb 100644 --- a/kernel/time/time_test.c +++ b/kernel/time/time_test.c @@ -73,7 +73,7 @@ static void time64_to_tm_test_date_range(struct kunit *test) days = div_s64(secs, 86400); - #define FAIL_MSG "%05ld/%02d/%02d (%2d) : %ld", \ + #define FAIL_MSG "%05ld/%02d/%02d (%2d) : %lld", \ year, month, mdday, yday, days KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 266d02809dbb1..8aab7ed414907 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1180,13 +1180,15 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history, } /* - * cycle_between - true if test occurs chronologically between before and after + * timestamp_in_interval - true if ts is chronologically in [start, end] + * + * True if ts occurs chronologically at or after start, and before or at end. */ -static bool cycle_between(u64 before, u64 test, u64 after) +static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { - if (test > before && test < after) + if (ts >= start && ts <= end) return true; - if (test < before && before > after) + if (start > end && (ts >= start || ts <= end)) return true; return false; } @@ -1246,7 +1248,7 @@ int get_device_system_crosststamp(int (*get_time_fn) */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; - if (!cycle_between(interval_start, cycles, now)) { + if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; @@ -1259,10 +1261,8 @@ int get_device_system_crosststamp(int (*get_time_fn) tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; - nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, - system_counterval.cycles); - nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, - system_counterval.cycles); + nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); @@ -1277,13 +1277,13 @@ int get_device_system_crosststamp(int (*get_time_fn) bool discontinuity; /* - * Check that the counter value occurs after the provided + * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || - !cycle_between(history_begin->cycles, - system_counterval.cycles, cycles) || + !timestamp_in_interval(history_begin->cycles, + cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 61c541c36596d..bcc97f1bd3833 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -1123,7 +1123,7 @@ config PREEMPTIRQ_DELAY_TEST config SYNTH_EVENT_GEN_TEST tristate "Test module for in-kernel synthetic event generation" - depends on SYNTH_EVENTS + depends on SYNTH_EVENTS && m help This option creates a test module to check the base functionality of in-kernel synthetic event definition and @@ -1136,7 +1136,7 @@ config SYNTH_EVENT_GEN_TEST config KPROBE_EVENT_GEN_TEST tristate "Test module for in-kernel kprobe event generation" - depends on KPROBE_EVENTS + depends on KPROBE_EVENTS && m help This option creates a test module to check the base functionality of in-kernel kprobe event definition. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7ac6c52b25ebc..003e8a89f1753 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2713,7 +2713,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .release = bpf_kprobe_multi_link_release, - .dealloc = bpf_kprobe_multi_link_dealloc, + .dealloc_deferred = bpf_kprobe_multi_link_dealloc, .fill_link_info = bpf_kprobe_multi_link_fill_link_info, }; @@ -3142,6 +3142,9 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link) umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt); + if (umulti_link->task) + put_task_struct(umulti_link->task); + path_put(&umulti_link->path); } static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) @@ -3149,9 +3152,6 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link) struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); - if (umulti_link->task) - put_task_struct(umulti_link->task); - path_put(&umulti_link->path); kvfree(umulti_link->uprobes); kfree(umulti_link); } @@ -3227,7 +3227,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_uprobe_multi_link_lops = { .release = bpf_uprobe_multi_link_release, - .dealloc = bpf_uprobe_multi_link_dealloc, + .dealloc_deferred = bpf_uprobe_multi_link_dealloc, .fill_link_info = bpf_uprobe_multi_link_fill_link_info, }; @@ -3245,7 +3245,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, struct bpf_run_ctx *old_run_ctx; int err = 0; - if (link->task && current != link->task) + if (link->task && current->mm != link->task->mm) return 0; if (sleepable) @@ -3346,8 +3346,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); cnt = attr->link_create.uprobe_multi.cnt; + pid = attr->link_create.uprobe_multi.pid; - if (!upath || !uoffsets || !cnt) + if (!upath || !uoffsets || !cnt || pid < 0) return -EINVAL; if (cnt > MAX_UPROBE_MULTI_CNT) return -E2BIG; @@ -3371,10 +3372,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error_path_put; } - pid = attr->link_create.uprobe_multi.pid; if (pid) { rcu_read_lock(); - task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); rcu_read_unlock(); if (!task) { err = -ESRCH; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 83ba342aef31f..175eba24f5629 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1595,12 +1595,15 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) unsigned long ftrace_location_range(unsigned long start, unsigned long end) { struct dyn_ftrace *rec; + unsigned long ip = 0; + rcu_read_lock(); rec = lookup_rec(start, end); if (rec) - return rec->ip; + ip = rec->ip; + rcu_read_unlock(); - return 0; + return ip; } /** @@ -1613,25 +1616,22 @@ unsigned long ftrace_location_range(unsigned long start, unsigned long end) */ unsigned long ftrace_location(unsigned long ip) { - struct dyn_ftrace *rec; + unsigned long loc; unsigned long offset; unsigned long size; - rec = lookup_rec(ip, ip); - if (!rec) { + loc = ftrace_location_range(ip, ip); + if (!loc) { if (!kallsyms_lookup_size_offset(ip, &size, &offset)) goto out; /* map sym+0 to __fentry__ */ if (!offset) - rec = lookup_rec(ip, ip + size - 1); + loc = ftrace_location_range(ip, ip + size - 1); } - if (rec) - return rec->ip; - out: - return 0; + return loc; } /** @@ -6593,6 +6593,8 @@ static int ftrace_process_locs(struct module *mod, /* We should have used all pages unless we skipped some */ if (pg_unuse) { WARN_ON(!skipped); + /* Need to synchronize with ftrace_location_range() */ + synchronize_rcu(); ftrace_free_pages(pg_unuse); } return ret; @@ -6806,6 +6808,9 @@ void ftrace_release_mod(struct module *mod) out_unlock: mutex_unlock(&ftrace_lock); + /* Need to synchronize with ftrace_location_range() */ + if (tmp_page) + synchronize_rcu(); for (pg = tmp_page; pg; pg = tmp_page) { /* Needs to be called outside of ftrace_lock */ @@ -7139,6 +7144,7 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) unsigned long start = (unsigned long)(start_ptr); unsigned long end = (unsigned long)(end_ptr); struct ftrace_page **last_pg = &ftrace_pages_start; + struct ftrace_page *tmp_page = NULL; struct ftrace_page *pg; struct dyn_ftrace *rec; struct dyn_ftrace key; @@ -7180,12 +7186,8 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) ftrace_update_tot_cnt--; if (!pg->index) { *last_pg = pg->next; - if (pg->records) { - free_pages((unsigned long)pg->records, pg->order); - ftrace_number_of_pages -= 1 << pg->order; - } - ftrace_number_of_groups--; - kfree(pg); + pg->next = tmp_page; + tmp_page = pg; pg = container_of(last_pg, struct ftrace_page, next); if (!(*last_pg)) ftrace_pages = pg; @@ -7202,6 +7204,11 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) clear_func_from_hashes(func); kfree(func); } + /* Need to synchronize with ftrace_location_range() */ + if (tmp_page) { + synchronize_rcu(); + ftrace_free_pages(tmp_page); + } } void __init ftrace_free_init_mem(void) @@ -7892,6 +7899,7 @@ void ftrace_kill(void) ftrace_disabled = 1; ftrace_enabled = 0; ftrace_trace_function = ftrace_stub; + kprobe_ftrace_kill(); } /** diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index 8c4ffd0761624..cb0871fbdb07f 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -215,4 +215,5 @@ static void __exit preemptirq_delay_exit(void) module_init(preemptirq_delay_init) module_exit(preemptirq_delay_exit) +MODULE_DESCRIPTION("Preempt / IRQ disable delay thread to test latency tracers"); MODULE_LICENSE("GPL v2"); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index aa332ace108b1..943850b25fcb7 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -384,6 +384,7 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; + atomic_t seq; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -753,6 +754,9 @@ static void rb_wake_up_waiters(struct irq_work *work) { struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work); + /* For waiters waiting for the first wake up */ + (void)atomic_fetch_inc_release(&rbwork->seq); + wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { /* Only cpu_buffer sets the above flags */ @@ -834,51 +838,24 @@ static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full) pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; ret = !pagebusy && full_hit(buffer, cpu, full); - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; + if (!ret && (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full)) { + cpu_buffer->shortest_full = full; + } raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } return ret; } -/** - * ring_buffer_wait - wait for input to the ring buffer - * @buffer: buffer to wait on - * @cpu: the cpu buffer to wait on - * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS - * - * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon - * as data is added to any of the @buffer's cpu buffers. Otherwise - * it will wait for data to be added to a specific cpu buffer. - */ -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) +static inline bool +rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer, + int cpu, int full, ring_buffer_cond_fn cond, void *data) { - struct ring_buffer_per_cpu *cpu_buffer; - DEFINE_WAIT(wait); - struct rb_irq_work *work; - int ret = 0; - - /* - * Depending on what the caller is waiting for, either any - * data in any cpu buffer, or a specific buffer, put the - * caller on the appropriate wait queue. - */ - if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; - /* Full only makes sense on per cpu reads */ - full = 0; - } else { - if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return -ENODEV; - cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; - } + if (rb_watermark_hit(buffer, cpu, full)) + return true; - if (full) - prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); - else - prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); + if (cond(data)) + return true; /* * The events can happen in critical sections where @@ -901,27 +878,82 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) * a task has been queued. It's OK for spurious wake ups. */ if (full) - work->full_waiters_pending = true; + rbwork->full_waiters_pending = true; else - work->waiters_pending = true; + rbwork->waiters_pending = true; - if (rb_watermark_hit(buffer, cpu, full)) - goto out; + return false; +} - if (signal_pending(current)) { - ret = -EINTR; - goto out; +struct rb_wait_data { + struct rb_irq_work *irq_work; + int seq; +}; + +/* + * The default wait condition for ring_buffer_wait() is to just to exit the + * wait loop the first time it is woken up. + */ +static bool rb_wait_once(void *data) +{ + struct rb_wait_data *rdata = data; + struct rb_irq_work *rbwork = rdata->irq_work; + + return atomic_read_acquire(&rbwork->seq) != rdata->seq; +} + +/** + * ring_buffer_wait - wait for input to the ring buffer + * @buffer: buffer to wait on + * @cpu: the cpu buffer to wait on + * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS + * @cond: condition function to break out of wait (NULL to run once) + * @data: the data to pass to @cond. + * + * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon + * as data is added to any of the @buffer's cpu buffers. Otherwise + * it will wait for data to be added to a specific cpu buffer. + */ +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct wait_queue_head *waitq; + struct rb_irq_work *rbwork; + struct rb_wait_data rdata; + int ret = 0; + + /* + * Depending on what the caller is waiting for, either any + * data in any cpu buffer, or a specific buffer, put the + * caller on the appropriate wait queue. + */ + if (cpu == RING_BUFFER_ALL_CPUS) { + rbwork = &buffer->irq_work; + /* Full only makes sense on per cpu reads */ + full = 0; + } else { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -ENODEV; + cpu_buffer = buffer->buffers[cpu]; + rbwork = &cpu_buffer->irq_work; } - schedule(); - out: if (full) - finish_wait(&work->full_waiters, &wait); + waitq = &rbwork->full_waiters; else - finish_wait(&work->waiters, &wait); + waitq = &rbwork->waiters; + + /* Set up to exit loop as soon as it is woken */ + if (!cond) { + cond = rb_wait_once; + rdata.irq_work = rbwork; + rdata.seq = atomic_read_acquire(&rbwork->seq); + data = &rdata; + } - if (!ret && !rb_watermark_hit(buffer, cpu, full) && signal_pending(current)) - ret = -EINTR; + ret = wait_event_interruptible((*waitq), + rb_wait_cond(rbwork, buffer, cpu, full, cond, data)); return ret; } @@ -964,16 +996,32 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, poll_wait(filp, &rbwork->full_waiters, poll_table); raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - rbwork->full_waiters_pending = true; if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - } else { - poll_wait(filp, &rbwork->waiters, poll_table); - rbwork->waiters_pending = true; + if (full_hit(buffer, cpu, full)) + return EPOLLIN | EPOLLRDNORM; + /* + * Only allow full_waiters_pending update to be seen after + * the shortest_full is set. If the writer sees the + * full_waiters_pending flag set, it will compare the + * amount in the ring buffer to shortest_full. If the amount + * in the ring buffer is greater than the shortest_full + * percent, it will call the irq_work handler to wake up + * this list. The irq_handler will reset shortest_full + * back to zero. That's done under the reader_lock, but + * the below smp_mb() makes sure that the update to + * full_waiters_pending doesn't leak up into the above. + */ + smp_mb(); + rbwork->full_waiters_pending = true; + return 0; } + poll_wait(filp, &rbwork->waiters, poll_table); + rbwork->waiters_pending = true; + /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit @@ -989,9 +1037,6 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, */ smp_mb(); - if (full) - return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; - if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; @@ -1355,7 +1400,6 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write); old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries); - local_inc(&cpu_buffer->pages_touched); /* * Just make sure we have seen our old_write and synchronize * with any interrupts that come in. @@ -1392,8 +1436,9 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, */ local_set(&next_page->page->commit, 0); - /* Again, either we update tail_page or an interrupt does */ - (void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page); + /* Either we update tail_page or an interrupt does */ + if (try_cmpxchg(&cpu_buffer->tail_page, &tail_page, next_page)) + local_inc(&cpu_buffer->pages_touched); } } @@ -1411,6 +1456,11 @@ static void rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, * * As a safety measure we check to make sure the data pages have not * been corrupted. + * + * Callers of this function need to guarantee that the list of pages doesn't get + * modified during the check. In particular, if it's possible that the function + * is invoked with concurrent readers which can swap in a new reader page then + * the caller should take cpu_buffer->reader_lock. */ static void rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { @@ -2160,8 +2210,12 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, */ synchronize_rcu(); for_each_buffer_cpu(buffer, cpu) { + unsigned long flags; + cpu_buffer = buffer->buffers[cpu]; + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_check_pages(cpu_buffer); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } atomic_dec(&buffer->record_disabled); } @@ -4350,7 +4404,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; - commit_page = cpu_buffer->commit_page; + commit_page = READ_ONCE(cpu_buffer->commit_page); commit_ts = commit_page->page->time_stamp; /* diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 2f68e93fff0bc..df0745a42a3f3 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -245,6 +245,7 @@ static int __rv_disable_monitor(struct rv_monitor_def *mdef, bool sync) /** * rv_disable_monitor - disable a given runtime monitor + * @mdef: Pointer to the monitor definition structure. * * Returns 0 on success. */ @@ -256,6 +257,7 @@ int rv_disable_monitor(struct rv_monitor_def *mdef) /** * rv_enable_monitor - enable a given runtime monitor + * @mdef: Pointer to the monitor definition structure. * * Returns 0 on success, error otherwise. */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c9c8983073485..d390fea3a6a52 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1955,15 +1955,36 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) #endif /* CONFIG_TRACER_MAX_TRACE */ +struct pipe_wait { + struct trace_iterator *iter; + int wait_index; +}; + +static bool wait_pipe_cond(void *data) +{ + struct pipe_wait *pwait = data; + struct trace_iterator *iter = pwait->iter; + + if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index) + return true; + + return iter->closed; +} + static int wait_on_pipe(struct trace_iterator *iter, int full) { + struct pipe_wait pwait; int ret; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + pwait.wait_index = atomic_read_acquire(&iter->wait_index); + pwait.iter = iter; + + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, + wait_pipe_cond, &pwait); #ifdef CONFIG_TRACER_MAX_TRACE /* @@ -8398,9 +8419,9 @@ static int tracing_buffers_flush(struct file *file, fl_owner_t id) struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; - iter->wait_index++; + iter->closed = true; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); @@ -8500,6 +8521,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; + bool woken = false; int page_size; int entries, i; ssize_t ret = 0; @@ -8573,17 +8595,17 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { - long wait_index; if (ret) goto out; + if (woken) + goto out; + ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; - wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; @@ -8592,10 +8614,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, if (!tracer_tracing_is_on(iter->tr)) goto out; - /* Make sure we see the new wait_index */ - smp_rmb(); - if (wait_index != iter->wait_index) - goto out; + /* Iterate one more time to collect any new data then exit */ + woken = true; goto again; } @@ -8618,9 +8638,8 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned mutex_lock(&trace_types_lock); - iter->wait_index++; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7c364b87352ee..6ef29eba90ceb 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1670,6 +1670,7 @@ static int trace_format_open(struct inode *inode, struct file *file) return 0; } +#ifdef CONFIG_PERF_EVENTS static ssize_t event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -1684,6 +1685,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } +#endif static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, @@ -2152,10 +2154,12 @@ static const struct file_operations ftrace_event_format_fops = { .release = seq_release, }; +#ifdef CONFIG_PERF_EVENTS static const struct file_operations ftrace_event_id_fops = { .read = event_id_read, .llseek = default_llseek, }; +#endif static const struct file_operations ftrace_event_filter_fops = { .open = tracing_open_file_tr, @@ -2548,6 +2552,14 @@ static int event_callback(const char *name, umode_t *mode, void **data, return 0; } +/* The file is incremented on creation and freeing the enable file decrements it */ +static void event_release(const char *name, void *data) +{ + struct trace_event_file *file = data; + + event_file_put(file); +} + static int event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) { @@ -2562,6 +2574,7 @@ event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) { .name = "enable", .callback = event_callback, + .release = event_release, }, { .name = "filter", @@ -2630,6 +2643,9 @@ event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) return ret; } + /* Gets decremented on freeing of the "enable" file */ + event_file_get(file); + return 0; } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index e76f5e1efdf2d..704de62f7ae16 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -202,6 +202,8 @@ static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm); static struct user_event_mm *user_event_mm_get_all(struct user_event *user); static void user_event_mm_put(struct user_event_mm *mm); static int destroy_user_event(struct user_event *user); +static bool user_fields_match(struct user_event *user, int argc, + const char **argv); static u32 user_event_key(char *name) { @@ -1493,17 +1495,24 @@ static int destroy_user_event(struct user_event *user) } static struct user_event *find_user_event(struct user_event_group *group, - char *name, u32 *outkey) + char *name, int argc, const char **argv, + u32 flags, u32 *outkey) { struct user_event *user; u32 key = user_event_key(name); *outkey = key; - hash_for_each_possible(group->register_table, user, node, key) - if (!strcmp(EVENT_NAME(user), name)) + hash_for_each_possible(group->register_table, user, node, key) { + if (strcmp(EVENT_NAME(user), name)) + continue; + + if (user_fields_match(user, argc, argv)) return user_event_get(user); + return ERR_PTR(-EADDRINUSE); + } + return NULL; } @@ -1860,6 +1869,9 @@ static bool user_fields_match(struct user_event *user, int argc, struct list_head *head = &user->fields; int i = 0; + if (argc == 0) + return list_empty(head); + list_for_each_entry_reverse(field, head, link) { if (!user_field_match(field, argc, argv, &i)) return false; @@ -1880,10 +1892,8 @@ static bool user_event_match(const char *system, const char *event, match = strcmp(EVENT_NAME(user), event) == 0 && (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0); - if (match && argc > 0) + if (match) match = user_fields_match(user, argc, argv); - else if (match && argc == 0) - match = list_empty(&user->fields); return match; } @@ -1913,6 +1923,80 @@ static int user_event_trace_register(struct user_event *user) return ret; } +/* + * Counts how many ';' without a trailing space are in the args. + */ +static int count_semis_no_space(char *args) +{ + int count = 0; + + while ((args = strchr(args, ';'))) { + args++; + + if (!isspace(*args)) + count++; + } + + return count; +} + +/* + * Copies the arguments while ensuring all ';' have a trailing space. + */ +static char *insert_space_after_semis(char *args, int count) +{ + char *fixed, *pos; + int len; + + len = strlen(args) + count; + fixed = kmalloc(len + 1, GFP_KERNEL); + + if (!fixed) + return NULL; + + pos = fixed; + + /* Insert a space after ';' if there is no trailing space. */ + while (*args) { + *pos = *args++; + + if (*pos++ == ';' && !isspace(*args)) + *pos++ = ' '; + } + + *pos = '\0'; + + return fixed; +} + +static char **user_event_argv_split(char *args, int *argc) +{ + char **split; + char *fixed; + int count; + + /* Count how many ';' without a trailing space */ + count = count_semis_no_space(args); + + /* No fixup is required */ + if (!count) + return argv_split(GFP_KERNEL, args, argc); + + /* We must fixup 'field;field' to 'field; field' */ + fixed = insert_space_after_semis(args, count); + + if (!fixed) + return NULL; + + /* We do a normal split afterwards */ + split = argv_split(GFP_KERNEL, fixed, argc); + + /* We can free since argv_split makes a copy */ + kfree(fixed); + + return split; +} + /* * Parses the event name, arguments and flags then registers if successful. * The name buffer lifetime is owned by this method for success cases only. @@ -1922,11 +2006,11 @@ static int user_event_parse(struct user_event_group *group, char *name, char *args, char *flags, struct user_event **newuser, int reg_flags) { - int ret; - u32 key; struct user_event *user; + char **argv = NULL; int argc = 0; - char **argv; + int ret; + u32 key; /* Currently don't support any text based flags */ if (flags != NULL) @@ -1935,41 +2019,34 @@ static int user_event_parse(struct user_event_group *group, char *name, if (!user_event_capable(reg_flags)) return -EPERM; + if (args) { + argv = user_event_argv_split(args, &argc); + + if (!argv) + return -ENOMEM; + } + /* Prevent dyn_event from racing */ mutex_lock(&event_mutex); - user = find_user_event(group, name, &key); + user = find_user_event(group, name, argc, (const char **)argv, + reg_flags, &key); mutex_unlock(&event_mutex); - if (user) { - if (args) { - argv = argv_split(GFP_KERNEL, args, &argc); - if (!argv) { - ret = -ENOMEM; - goto error; - } + if (argv) + argv_free(argv); - ret = user_fields_match(user, argc, (const char **)argv); - argv_free(argv); - - } else - ret = list_empty(&user->fields); - - if (ret) { - *newuser = user; - /* - * Name is allocated by caller, free it since it already exists. - * Caller only worries about failure cases for freeing. - */ - kfree(name); - } else { - ret = -EADDRINUSE; - goto error; - } + if (IS_ERR(user)) + return PTR_ERR(user); + + if (user) { + *newuser = user; + /* + * Name is allocated by caller, free it since it already exists. + * Caller only worries about failure cases for freeing. + */ + kfree(name); return 0; -error: - user_event_put(user, false); - return ret; } user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT); @@ -2052,25 +2129,33 @@ static int user_event_parse(struct user_event_group *group, char *name, } /* - * Deletes a previously created event if it is no longer being used. + * Deletes previously created events if they are no longer being used. */ static int delete_user_event(struct user_event_group *group, char *name) { - u32 key; - struct user_event *user = find_user_event(group, name, &key); + struct user_event *user; + struct hlist_node *tmp; + u32 key = user_event_key(name); + int ret = -ENOENT; - if (!user) - return -ENOENT; + /* Attempt to delete all event(s) with the name passed in */ + hash_for_each_possible_safe(group->register_table, user, tmp, node, key) { + if (strcmp(EVENT_NAME(user), name)) + continue; - user_event_put(user, true); + if (!user_event_last_ref(user)) + return -EBUSY; - if (!user_event_last_ref(user)) - return -EBUSY; + if (!user_event_capable(user->reg_flags)) + return -EPERM; - if (!user_event_capable(user->reg_flags)) - return -EPERM; + ret = destroy_user_event(user); - return destroy_user_event(user); + if (ret) + goto out; + } +out: + return ret; } /* diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 34289f9c67076..ae162ba36a480 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -553,6 +553,10 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type, anon_offs = 0; field = btf_find_struct_member(ctx->btf, type, fieldname, &anon_offs); + if (IS_ERR(field)) { + trace_probe_log_err(ctx->offset, BAD_BTF_TID); + return PTR_ERR(field); + } if (!field) { trace_probe_log_err(ctx->offset, NO_BTF_FIELD); return -ENOENT; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index ce4d99df5f0eb..eb7406b5d4d0a 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -22,6 +22,12 @@ #include #include +/* + * sysctl determining whether unprivileged users may unshare a new + * userns. Allowed by default + */ +int unprivileged_userns_clone = 1; + static struct kmem_cache *user_ns_cachep __ro_after_init; static DEFINE_MUTEX(userns_state_mutex); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 7b482a26d7419..223aa99bb71c1 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1141,8 +1141,12 @@ static bool kick_pool(struct worker_pool *pool) !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); - p->wake_cpu = cpumask_any_distribute(pool->attrs->__pod_cpumask); - get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; + int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, + cpu_online_mask); + if (wake_cpu < nr_cpu_ids) { + p->wake_cpu = wake_cpu; + get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; + } } #endif wake_up_process(p); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ef36b829ae1f5..6352d59c57461 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -375,7 +375,7 @@ config DEBUG_INFO_SPLIT Incompatible with older versions of ccache. config DEBUG_INFO_BTF - bool "Generate BTF typeinfo" + bool "Generate BTF type information" depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST depends on BPF_SYSCALL @@ -408,7 +408,8 @@ config PAHOLE_HAS_LANG_EXCLUDE using DEBUG_INFO_BTF_MODULES. config DEBUG_INFO_BTF_MODULES - def_bool y + bool "Generate BTF type information for kernel modules" + default y depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF help Generate compact split BTF type information for kernel modules. diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 59e21bfec188c..15f42841632fa 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -1,9 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only -config ARCH_HAS_UBSAN_SANITIZE_ALL +config ARCH_HAS_UBSAN bool menuconfig UBSAN bool "Undefined behaviour sanity checker" + depends on ARCH_HAS_UBSAN help This option enables the Undefined Behaviour sanity checker. Compile-time instrumentation is used to detect various undefined @@ -142,17 +143,6 @@ config UBSAN_ALIGNMENT Enabling this option on architectures that support unaligned accesses may produce a lot of false positives. -config UBSAN_SANITIZE_ALL - bool "Enable instrumentation for the entire kernel" - depends on ARCH_HAS_UBSAN_SANITIZE_ALL - default y - help - This option activates instrumentation for the entire kernel. - If you don't enable this option, you have to explicitly specify - UBSAN_SANITIZE := y for the files/directories you want to check for UB. - Enabling this option will get kernel image size increased - significantly. - config TEST_UBSAN tristate "Module for testing for undefined behavior detection" depends on m diff --git a/lib/bootconfig.c b/lib/bootconfig.c index c59d26068a640..8841554432d5b 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -61,9 +61,12 @@ static inline void * __init xbc_alloc_mem(size_t size) return memblock_alloc(size, SMP_CACHE_BYTES); } -static inline void __init xbc_free_mem(void *addr, size_t size) +static inline void __init xbc_free_mem(void *addr, size_t size, bool early) { - memblock_free(addr, size); + if (early) + memblock_free(addr, size); + else if (addr) + memblock_free_late(__pa(addr), size); } #else /* !__KERNEL__ */ @@ -73,7 +76,7 @@ static inline void *xbc_alloc_mem(size_t size) return malloc(size); } -static inline void xbc_free_mem(void *addr, size_t size) +static inline void xbc_free_mem(void *addr, size_t size, bool early) { free(addr); } @@ -904,13 +907,13 @@ static int __init xbc_parse_tree(void) * If you need to reuse xbc_init() with new boot config, you can * use this. */ -void __init xbc_exit(void) +void __init _xbc_exit(bool early) { - xbc_free_mem(xbc_data, xbc_data_size); + xbc_free_mem(xbc_data, xbc_data_size, early); xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); + xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX, early); xbc_nodes = NULL; brace_index = 0; } @@ -963,7 +966,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) if (!xbc_nodes) { if (emsg) *emsg = "Failed to allocate bootconfig nodes"; - xbc_exit(); + _xbc_exit(true); return -ENOMEM; } memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX); @@ -977,7 +980,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) *epos = xbc_err_pos; if (emsg) *emsg = xbc_err_msg; - xbc_exit(); + _xbc_exit(true); } else ret = xbc_node_num; diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c index bf70850035c76..404dba36bae38 100644 --- a/lib/checksum_kunit.c +++ b/lib/checksum_kunit.c @@ -594,13 +594,15 @@ static void test_ip_fast_csum(struct kunit *test) static void test_csum_ipv6_magic(struct kunit *test) { -#if defined(CONFIG_NET) const struct in6_addr *saddr; const struct in6_addr *daddr; unsigned int len; unsigned char proto; __wsum csum; + if (!IS_ENABLED(CONFIG_NET)) + return; + const int daddr_offset = sizeof(struct in6_addr); const int len_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr); const int proto_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr) + @@ -618,7 +620,6 @@ static void test_csum_ipv6_magic(struct kunit *test) CHECK_EQ(to_sum16(expected_csum_ipv6_magic[i]), csum_ipv6_magic(saddr, daddr, len, proto, csum)); } -#endif /* !CONFIG_NET */ } static struct kunit_case __refdata checksum_test_cases[] = { diff --git a/lib/cmdline_kunit.c b/lib/cmdline_kunit.c index d4572dbc91453..705b82736be08 100644 --- a/lib/cmdline_kunit.c +++ b/lib/cmdline_kunit.c @@ -124,7 +124,7 @@ static void cmdline_do_one_range_test(struct kunit *test, const char *in, n, e[0], r[0]); p = memchr_inv(&r[1], 0, sizeof(r) - sizeof(r[0])); - KUNIT_EXPECT_PTR_EQ_MSG(test, p, NULL, "in test %u at %u out of bound", n, p - r); + KUNIT_EXPECT_PTR_EQ_MSG(test, p, NULL, "in test %u at %td out of bound", n, p - r); } static void cmdline_test_range(struct kunit *test) diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 83471e81501a7..222c6d6c8281a 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -96,15 +96,25 @@ static void __dump_stack(const char *log_lvl) */ asmlinkage __visible void dump_stack_lvl(const char *log_lvl) { + bool in_panic = this_cpu_in_panic(); unsigned long flags; /* * Permit this cpu to perform nested stack dumps while serialising - * against other CPUs + * against other CPUs, unless this CPU is in panic. + * + * When in panic, non-panic CPUs are not permitted to store new + * printk messages so there is no need to synchronize the output. + * This avoids potential deadlock in panic() if another CPU is + * holding and unable to release the printk_cpu_sync. */ - printk_cpu_sync_get_irqsave(flags); + if (!in_panic) + printk_cpu_sync_get_irqsave(flags); + __dump_stack(log_lvl); - printk_cpu_sync_put_irqrestore(flags); + + if (!in_panic) + printk_cpu_sync_put_irqrestore(flags); } EXPORT_SYMBOL(dump_stack_lvl); diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 6fba6423cc10b..a5a687e1c9192 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -302,7 +302,11 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords) } else { for (end = buf; *end && !isspace(*end); end++) ; - BUG_ON(end == buf); + if (end == buf) { + pr_err("parse err after word:%d=%s\n", nwords, + nwords ? words[nwords - 1] : ""); + return -EINVAL; + } } /* `buf' is start of word, `end' is one past its end */ diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index 2e4fedc816210..7830a9e64ead7 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -229,28 +229,28 @@ DEFINE_ALLOC_SIZE_TEST_PAIR(vmalloc) \ checker((expected_pages) * PAGE_SIZE, \ kvmalloc((alloc_pages) * PAGE_SIZE, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvmalloc_node((alloc_pages) * PAGE_SIZE, gfp, NUMA_NO_NODE), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvzalloc((alloc_pages) * PAGE_SIZE, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvzalloc_node((alloc_pages) * PAGE_SIZE, gfp, NUMA_NO_NODE), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvcalloc(1, (alloc_pages) * PAGE_SIZE, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvcalloc((alloc_pages) * PAGE_SIZE, 1, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvmalloc_array(1, (alloc_pages) * PAGE_SIZE, gfp), \ - vfree(p)); \ + kvfree(p)); \ checker((expected_pages) * PAGE_SIZE, \ kvmalloc_array((alloc_pages) * PAGE_SIZE, 1, gfp), \ - vfree(p)); \ + kvfree(p)); \ \ prev_size = (expected_pages) * PAGE_SIZE; \ orig = kvmalloc(prev_size, gfp); \ diff --git a/lib/kunit/device.c b/lib/kunit/device.c index 644a38a1f5b1c..3a31fe9ed6fc5 100644 --- a/lib/kunit/device.c +++ b/lib/kunit/device.c @@ -10,6 +10,7 @@ */ #include +#include #include #include @@ -50,7 +51,7 @@ int kunit_bus_init(void) error = bus_register(&kunit_bus_type); if (error) - bus_unregister(&kunit_bus_type); + root_device_unregister(kunit_bus_device); return error; } @@ -133,6 +134,9 @@ static struct kunit_device *kunit_device_register_internal(struct kunit *test, return ERR_PTR(err); } + kunit_dev->dev.dma_mask = &kunit_dev->dev.coherent_dma_mask; + kunit_dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + kunit_add_action(test, device_unregister_wrapper, &kunit_dev->dev); return kunit_dev; diff --git a/lib/kunit/executor_test.c b/lib/kunit/executor_test.c index 22d4ee86dbedd..3f7f967e3688e 100644 --- a/lib/kunit/executor_test.c +++ b/lib/kunit/executor_test.c @@ -129,7 +129,7 @@ static void parse_filter_attr_test(struct kunit *test) GFP_KERNEL); for (j = 0; j < filter_count; j++) { parsed_filters[j] = kunit_next_attr_filter(&filter, &err); - KUNIT_ASSERT_EQ_MSG(test, err, 0, "failed to parse filter '%s'", filters[j]); + KUNIT_ASSERT_EQ_MSG(test, err, 0, "failed to parse filter from '%s'", filters); } KUNIT_EXPECT_STREQ(test, kunit_attr_filter_name(parsed_filters[0]), "speed"); diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 1d1475578515c..b8514dbb337c0 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -712,6 +712,9 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_ { unsigned int i; + if (num_suites == 0) + return 0; + if (!kunit_enabled() && num_suites > 0) { pr_info("kunit: disabled\n"); return 0; diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index f7825991d576a..d9d1df28cc52e 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "try-catch-impl.h" @@ -65,13 +66,14 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) try_catch->context = context; try_catch->try_completion = &try_completion; try_catch->try_result = 0; - task_struct = kthread_run(kunit_generic_run_threadfn_adapter, - try_catch, - "kunit_try_catch_thread"); + task_struct = kthread_create(kunit_generic_run_threadfn_adapter, + try_catch, "kunit_try_catch_thread"); if (IS_ERR(task_struct)) { try_catch->catch(try_catch->context); return; } + get_task_struct(task_struct); + wake_up_process(task_struct); time_remaining = wait_for_completion_timeout(&try_completion, kunit_test_timeout()); @@ -81,6 +83,7 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context) kthread_stop(task_struct); } + put_task_struct(task_struct); exit_code = try_catch->try_result; if (!exit_code) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 6f241bb387992..fe6092a1dc353 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4290,6 +4290,56 @@ static inline void *mas_insert(struct ma_state *mas, void *entry) } +/** + * mas_alloc_cyclic() - Internal call to find somewhere to store an entry + * @mas: The maple state. + * @startp: Pointer to ID. + * @range_lo: Lower bound of range to search. + * @range_hi: Upper bound of range to search. + * @entry: The entry to store. + * @next: Pointer to next ID to allocate. + * @gfp: The GFP_FLAGS to use for allocations. + * + * Return: 0 if the allocation succeeded without wrapping, 1 if the + * allocation succeeded after wrapping, or -EBUSY if there are no + * free entries. + */ +int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp) +{ + unsigned long min = range_lo; + int ret = 0; + + range_lo = max(min, *next); + ret = mas_empty_area(mas, range_lo, range_hi, 1); + if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) { + mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED; + ret = 1; + } + if (ret < 0 && range_lo > min) { + ret = mas_empty_area(mas, min, range_hi, 1); + if (ret == 0) + ret = 1; + } + if (ret < 0) + return ret; + + do { + mas_insert(mas, entry); + } while (mas_nomem(mas, gfp)); + if (mas_is_err(mas)) + return xa_err(mas->node); + + *startp = mas->index; + *next = *startp + 1; + if (*next == 0) + mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; + + return ret; +} +EXPORT_SYMBOL(mas_alloc_cyclic); + static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: @@ -5061,18 +5111,18 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, if (size == 0 || max - min < size - 1) return -EINVAL; - if (mas_is_start(mas)) { + if (mas_is_start(mas)) mas_start(mas); - mas->offset = mas_data_end(mas); - } else if (mas->offset >= 2) { - mas->offset -= 2; - } else if (!mas_rewind_node(mas)) { + else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; - } - /* Empty set. */ - if (mas_is_none(mas) || mas_is_ptr(mas)) + if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); + else if (mas->offset >= 2) + mas->offset -= 2; + else + mas->offset = mas_data_end(mas); + /* The start of the window can only be within these values. */ mas->index = min; @@ -6443,6 +6493,49 @@ int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, } EXPORT_SYMBOL(mtree_alloc_range); +/** + * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree. + * @mt: The maple tree. + * @startp: Pointer to ID. + * @range_lo: Lower bound of range to search. + * @range_hi: Upper bound of range to search. + * @entry: The entry to store. + * @next: Pointer to next ID to allocate. + * @gfp: The GFP_FLAGS to use for allocations. + * + * Finds an empty entry in @mt after @next, stores the new index into + * the @id pointer, stores the entry at that index, then updates @next. + * + * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag. + * + * Context: Any context. Takes and releases the mt.lock. May sleep if + * the @gfp flags permit. + * + * Return: 0 if the allocation succeeded without wrapping, 1 if the + * allocation succeeded after wrapping, -ENOMEM if memory could not be + * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no + * free entries. + */ +int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp) +{ + int ret; + + MA_STATE(mas, mt, 0, 0); + + if (!mt_is_alloc(mt)) + return -EINVAL; + if (WARN_ON_ONCE(mt_is_reserved(entry))) + return -EINVAL; + mtree_lock(mt); + ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi, + next, gfp); + mtree_unlock(mt); + return ret; +} +EXPORT_SYMBOL(mtree_alloc_cyclic); + int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index 440aee705ccca..30e00ef0bf2e0 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -32,7 +32,7 @@ struct some_bytes { BUILD_BUG_ON(sizeof(instance.data) != 32); \ for (size_t i = 0; i < sizeof(instance.data); i++) { \ KUNIT_ASSERT_EQ_MSG(test, instance.data[i], v, \ - "line %d: '%s' not initialized to 0x%02x @ %d (saw 0x%02x)\n", \ + "line %d: '%s' not initialized to 0x%02x @ %zu (saw 0x%02x)\n", \ __LINE__, #instance, v, i, instance.data[i]); \ } \ } while (0) @@ -41,7 +41,7 @@ struct some_bytes { BUILD_BUG_ON(sizeof(one) != sizeof(two)); \ for (size_t i = 0; i < sizeof(one); i++) { \ KUNIT_EXPECT_EQ_MSG(test, one.data[i], two.data[i], \ - "line %d: %s.data[%d] (0x%02x) != %s.data[%d] (0x%02x)\n", \ + "line %d: %s.data[%zu] (0x%02x) != %s.data[%zu] (0x%02x)\n", \ __LINE__, #one, i, one.data[i], #two, i, two.data[i]); \ } \ kunit_info(test, "ok: " TEST_OP "() " name "\n"); \ diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c index c527f6b757894..c85c8b121d350 100644 --- a/lib/overflow_kunit.c +++ b/lib/overflow_kunit.c @@ -1113,6 +1113,24 @@ static void castable_to_type_test(struct kunit *test) #undef TEST_CASTABLE_TO_TYPE } +struct foo { + int a; + u32 counter; + s16 array[] __counted_by(counter); +}; + +static void DEFINE_FLEX_test(struct kunit *test) +{ + DEFINE_RAW_FLEX(struct foo, two, array, 2); + DEFINE_FLEX(struct foo, eight, array, counter, 8); + DEFINE_FLEX(struct foo, empty, array, counter, 0); + + KUNIT_EXPECT_EQ(test, __struct_size(two), + sizeof(struct foo) + sizeof(s16) + sizeof(s16)); + KUNIT_EXPECT_EQ(test, __struct_size(eight), 24); + KUNIT_EXPECT_EQ(test, __struct_size(empty), sizeof(struct foo)); +} + static struct kunit_case overflow_test_cases[] = { KUNIT_CASE(u8_u8__u8_overflow_test), KUNIT_CASE(s8_s8__s8_overflow_test), @@ -1135,6 +1153,7 @@ static struct kunit_case overflow_test_cases[] = { KUNIT_CASE(overflows_type_test), KUNIT_CASE(same_type_test), KUNIT_CASE(castable_to_type_test), + KUNIT_CASE(DEFINE_FLEX_test), {} }; diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c index ce39ce9f3526e..2829ddb0e316b 100644 --- a/lib/pci_iomap.c +++ b/lib/pci_iomap.c @@ -170,8 +170,8 @@ void pci_iounmap(struct pci_dev *dev, void __iomem *p) if (addr >= start && addr < start + IO_SPACE_LIMIT) return; - iounmap(p); #endif + iounmap(p); } EXPORT_SYMBOL(pci_iounmap); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 68b45c82c37a6..7bc2220fea805 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -1124,7 +1124,7 @@ static ssize_t extract_user_to_sg(struct iov_iter *iter, do { res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, extraction_flags, &off); - if (res < 0) + if (res <= 0) goto failed; len = res; diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c index d4a3730b08fa7..4ce9604388069 100644 --- a/lib/slub_kunit.c +++ b/lib/slub_kunit.c @@ -55,7 +55,7 @@ static void test_next_pointer(struct kunit *test) ptr_addr = (unsigned long *)(p + s->offset); tmp = *ptr_addr; - p[s->offset] = 0x12; + p[s->offset] = ~p[s->offset]; /* * Expecting three errors. diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 4a7055a63d9f8..91d2301fdef79 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -36,53 +36,11 @@ #include #include -#define DEPOT_HANDLE_BITS (sizeof(depot_stack_handle_t) * 8) - -#define DEPOT_POOL_ORDER 2 /* Pool size order, 4 pages */ -#define DEPOT_POOL_SIZE (1LL << (PAGE_SHIFT + DEPOT_POOL_ORDER)) -#define DEPOT_STACK_ALIGN 4 -#define DEPOT_OFFSET_BITS (DEPOT_POOL_ORDER + PAGE_SHIFT - DEPOT_STACK_ALIGN) -#define DEPOT_POOL_INDEX_BITS (DEPOT_HANDLE_BITS - DEPOT_OFFSET_BITS - \ - STACK_DEPOT_EXTRA_BITS) #define DEPOT_POOLS_CAP 8192 +/* The pool_index is offset by 1 so the first record does not have a 0 handle. */ #define DEPOT_MAX_POOLS \ - (((1LL << (DEPOT_POOL_INDEX_BITS)) < DEPOT_POOLS_CAP) ? \ - (1LL << (DEPOT_POOL_INDEX_BITS)) : DEPOT_POOLS_CAP) - -/* Compact structure that stores a reference to a stack. */ -union handle_parts { - depot_stack_handle_t handle; - struct { - u32 pool_index : DEPOT_POOL_INDEX_BITS; - u32 offset : DEPOT_OFFSET_BITS; - u32 extra : STACK_DEPOT_EXTRA_BITS; - }; -}; - -struct stack_record { - struct list_head hash_list; /* Links in the hash table */ - u32 hash; /* Hash in hash table */ - u32 size; /* Number of stored frames */ - union handle_parts handle; /* Constant after initialization */ - refcount_t count; - union { - unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES]; /* Frames */ - struct { - /* - * An important invariant of the implementation is to - * only place a stack record onto the freelist iff its - * refcount is zero. Because stack records with a zero - * refcount are never considered as valid, it is safe to - * union @entries and freelist management state below. - * Conversely, as soon as an entry is off the freelist - * and its refcount becomes non-zero, the below must not - * be accessed until being placed back on the freelist. - */ - struct list_head free_list; /* Links in the freelist */ - unsigned long rcu_state; /* RCU cookie */ - }; - }; -}; + (((1LL << (DEPOT_POOL_INDEX_BITS)) - 1 < DEPOT_POOLS_CAP) ? \ + (1LL << (DEPOT_POOL_INDEX_BITS)) - 1 : DEPOT_POOLS_CAP) static bool stack_depot_disabled; static bool __stack_depot_early_init_requested __initdata = IS_ENABLED(CONFIG_STACKDEPOT_ALWAYS_INIT); @@ -372,7 +330,7 @@ static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size) stack = current_pool + pool_offset; /* Pre-initialize handle once. */ - stack->handle.pool_index = pool_index; + stack->handle.pool_index_plus_1 = pool_index + 1; stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN; stack->handle.extra = 0; INIT_LIST_HEAD(&stack->hash_list); @@ -483,18 +441,19 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle) const int pools_num_cached = READ_ONCE(pools_num); union handle_parts parts = { .handle = handle }; void *pool; + u32 pool_index = parts.pool_index_plus_1 - 1; size_t offset = parts.offset << DEPOT_STACK_ALIGN; struct stack_record *stack; lockdep_assert_not_held(&pool_lock); - if (parts.pool_index > pools_num_cached) { + if (pool_index >= pools_num_cached) { WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n", - parts.pool_index, pools_num_cached, handle); + pool_index, pools_num_cached, handle); return NULL; } - pool = stack_pools[parts.pool_index]; + pool = stack_pools[pool_index]; if (WARN_ON(!pool)) return NULL; @@ -668,10 +627,10 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic - * contexts and I/O. + * contexts, I/O, nolockdep. */ alloc_flags &= ~GFP_ZONEMASK; - alloc_flags &= (GFP_ATOMIC | GFP_KERNEL); + alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP); alloc_flags |= __GFP_NOWARN; page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER); if (page) diff --git a/lib/strcat_kunit.c b/lib/strcat_kunit.c index e21be95514afa..ca09f7f0e6a26 100644 --- a/lib/strcat_kunit.c +++ b/lib/strcat_kunit.c @@ -10,7 +10,7 @@ static volatile int unconst; -static void strcat_test(struct kunit *test) +static void test_strcat(struct kunit *test) { char dest[8]; @@ -29,7 +29,7 @@ static void strcat_test(struct kunit *test) KUNIT_EXPECT_STREQ(test, dest, "fourAB"); } -static void strncat_test(struct kunit *test) +static void test_strncat(struct kunit *test) { char dest[8]; @@ -56,7 +56,7 @@ static void strncat_test(struct kunit *test) KUNIT_EXPECT_STREQ(test, dest, "fourAB"); } -static void strlcat_test(struct kunit *test) +static void test_strlcat(struct kunit *test) { char dest[8] = ""; int len = sizeof(dest) + unconst; @@ -88,9 +88,9 @@ static void strlcat_test(struct kunit *test) } static struct kunit_case strcat_test_cases[] = { - KUNIT_CASE(strcat_test), - KUNIT_CASE(strncat_test), - KUNIT_CASE(strlcat_test), + KUNIT_CASE(test_strcat), + KUNIT_CASE(test_strncat), + KUNIT_CASE(test_strlcat), {} }; diff --git a/lib/strscpy_kunit.c b/lib/strscpy_kunit.c index a6b6344354ed5..b6d1d93a88832 100644 --- a/lib/strscpy_kunit.c +++ b/lib/strscpy_kunit.c @@ -8,22 +8,23 @@ #include #include -/* - * tc() - Run a specific test case. +/** + * strscpy_check() - Run a specific test case. + * @test: KUnit test context pointer * @src: Source string, argument to strscpy_pad() * @count: Size of destination buffer, argument to strscpy_pad() * @expected: Expected return value from call to strscpy_pad() - * @terminator: 1 if there should be a terminating null byte 0 otherwise. * @chars: Number of characters from the src string expected to be * written to the dst buffer. + * @terminator: 1 if there should be a terminating null byte 0 otherwise. * @pad: Number of pad characters expected (in the tail of dst buffer). * (@pad does not include the null terminator byte.) * * Calls strscpy_pad() and verifies the return value and state of the * destination buffer after the call returns. */ -static void tc(struct kunit *test, char *src, int count, int expected, - int chars, int terminator, int pad) +static void strscpy_check(struct kunit *test, char *src, int count, + int expected, int chars, int terminator, int pad) { int nr_bytes_poison; int max_expected; @@ -79,12 +80,12 @@ static void tc(struct kunit *test, char *src, int count, int expected, } } -static void strscpy_test(struct kunit *test) +static void test_strscpy(struct kunit *test) { char dest[8]; /* - * tc() uses a destination buffer of size 6 and needs at + * strscpy_check() uses a destination buffer of size 6 and needs at * least 2 characters spare (one for null and one to check for * overflow). This means we should only call tc() with * strings up to a maximum of 4 characters long and 'count' @@ -92,27 +93,27 @@ static void strscpy_test(struct kunit *test) * the buffer size in tc(). */ - /* tc(test, src, count, expected, chars, terminator, pad) */ - tc(test, "a", 0, -E2BIG, 0, 0, 0); - tc(test, "", 0, -E2BIG, 0, 0, 0); + /* strscpy_check(test, src, count, expected, chars, terminator, pad) */ + strscpy_check(test, "a", 0, -E2BIG, 0, 0, 0); + strscpy_check(test, "", 0, -E2BIG, 0, 0, 0); - tc(test, "a", 1, -E2BIG, 0, 1, 0); - tc(test, "", 1, 0, 0, 1, 0); + strscpy_check(test, "a", 1, -E2BIG, 0, 1, 0); + strscpy_check(test, "", 1, 0, 0, 1, 0); - tc(test, "ab", 2, -E2BIG, 1, 1, 0); - tc(test, "a", 2, 1, 1, 1, 0); - tc(test, "", 2, 0, 0, 1, 1); + strscpy_check(test, "ab", 2, -E2BIG, 1, 1, 0); + strscpy_check(test, "a", 2, 1, 1, 1, 0); + strscpy_check(test, "", 2, 0, 0, 1, 1); - tc(test, "abc", 3, -E2BIG, 2, 1, 0); - tc(test, "ab", 3, 2, 2, 1, 0); - tc(test, "a", 3, 1, 1, 1, 1); - tc(test, "", 3, 0, 0, 1, 2); + strscpy_check(test, "abc", 3, -E2BIG, 2, 1, 0); + strscpy_check(test, "ab", 3, 2, 2, 1, 0); + strscpy_check(test, "a", 3, 1, 1, 1, 1); + strscpy_check(test, "", 3, 0, 0, 1, 2); - tc(test, "abcd", 4, -E2BIG, 3, 1, 0); - tc(test, "abc", 4, 3, 3, 1, 0); - tc(test, "ab", 4, 2, 2, 1, 1); - tc(test, "a", 4, 1, 1, 1, 2); - tc(test, "", 4, 0, 0, 1, 3); + strscpy_check(test, "abcd", 4, -E2BIG, 3, 1, 0); + strscpy_check(test, "abc", 4, 3, 3, 1, 0); + strscpy_check(test, "ab", 4, 2, 2, 1, 1); + strscpy_check(test, "a", 4, 1, 1, 1, 2); + strscpy_check(test, "", 4, 0, 0, 1, 3); /* Compile-time-known source strings. */ KUNIT_EXPECT_EQ(test, strscpy(dest, "", ARRAY_SIZE(dest)), 0); @@ -127,7 +128,7 @@ static void strscpy_test(struct kunit *test) } static struct kunit_case strscpy_test_cases[] = { - KUNIT_CASE(strscpy_test), + KUNIT_CASE(test_strscpy), {} }; diff --git a/lib/test_blackhole_dev.c b/lib/test_blackhole_dev.c index 4c40580a99a36..f247089d63c08 100644 --- a/lib/test_blackhole_dev.c +++ b/lib/test_blackhole_dev.c @@ -29,7 +29,6 @@ static int __init test_blackholedev_init(void) { struct ipv6hdr *ip6h; struct sk_buff *skb; - struct ethhdr *ethh; struct udphdr *uh; int data_len; int ret; @@ -61,7 +60,7 @@ static int __init test_blackholedev_init(void) ip6h->saddr = in6addr_loopback; ip6h->daddr = in6addr_loopback; /* Ether */ - ethh = (struct ethhdr *)skb_push(skb, sizeof(struct ethhdr)); + skb_push(skb, sizeof(struct ethhdr)); skb_set_mac_header(skb, 0); skb->protocol = htons(ETH_P_IPV6); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 717dcb8301273..b823ba7cb6a15 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -1226,8 +1226,8 @@ static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) unsigned long *src_pfns; unsigned long *dst_pfns; - src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); - dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL); + dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL); migrate_device_range(src_pfns, start_pfn, npages); for (i = 0; i < npages; i++) { @@ -1250,8 +1250,8 @@ static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) } migrate_device_pages(src_pfns, dst_pfns, npages); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); + kvfree(src_pfns); + kvfree(dst_pfns); } /* Removes free pages from the free list so they can't be re-allocated */ diff --git a/lib/ubsan.h b/lib/ubsan.h index 5d99ab81913bb..30f224c302179 100644 --- a/lib/ubsan.h +++ b/lib/ubsan.h @@ -124,15 +124,28 @@ typedef s64 s_max; typedef u64 u_max; #endif -void __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs); -void __ubsan_handle_type_mismatch(struct type_mismatch_data *data, void *ptr); -void __ubsan_handle_type_mismatch_v1(void *_data, void *ptr); -void __ubsan_handle_out_of_bounds(void *_data, void *index); -void __ubsan_handle_shift_out_of_bounds(void *_data, void *lhs, void *rhs); -void __ubsan_handle_builtin_unreachable(void *_data); -void __ubsan_handle_load_invalid_value(void *_data, void *val); -void __ubsan_handle_alignment_assumption(void *_data, unsigned long ptr, - unsigned long align, - unsigned long offset); +/* + * When generating Runtime Calls, Clang doesn't respect the -mregparm=3 + * option used on i386: https://github.com/llvm/llvm-project/issues/89670 + * Fix this for earlier Clang versions by forcing the calling convention + * to use non-register arguments. + */ +#if defined(CONFIG_X86_32) && \ + defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 190000 +# define ubsan_linkage asmlinkage +#else +# define ubsan_linkage +#endif + +void ubsan_linkage __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs); +void ubsan_linkage __ubsan_handle_type_mismatch(struct type_mismatch_data *data, void *ptr); +void ubsan_linkage __ubsan_handle_type_mismatch_v1(void *_data, void *ptr); +void ubsan_linkage __ubsan_handle_out_of_bounds(void *_data, void *index); +void ubsan_linkage __ubsan_handle_shift_out_of_bounds(void *_data, void *lhs, void *rhs); +void ubsan_linkage __ubsan_handle_builtin_unreachable(void *_data); +void ubsan_linkage __ubsan_handle_load_invalid_value(void *_data, void *val); +void ubsan_linkage __ubsan_handle_alignment_assumption(void *_data, unsigned long ptr, + unsigned long align, + unsigned long offset); #endif diff --git a/mm/Makefile b/mm/Makefile index e4b5b75aaec9c..4abb40b911ec4 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -29,8 +29,7 @@ KCOV_INSTRUMENT_mmzone.o := n KCOV_INSTRUMENT_vmstat.o := n KCOV_INSTRUMENT_failslab.o := n -CFLAGS_init-mm.o += $(call cc-disable-warning, override-init) -CFLAGS_init-mm.o += $(call cc-disable-warning, initializer-overrides) +CFLAGS_init-mm.o += -Wno-override-init mmu-y := nommu.o mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \ diff --git a/mm/cma.c b/mm/cma.c index 7c09c47e530bf..633a54068f00f 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -187,10 +187,6 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, if (!size || !memblock_is_region_reserved(base, size)) return -EINVAL; - /* alignment should be aligned with order_per_bit */ - if (!IS_ALIGNED(CMA_MIN_ALIGNMENT_PAGES, 1 << order_per_bit)) - return -EINVAL; - /* ensure minimal alignment required by mm core */ if (!IS_ALIGNED(base | size, CMA_MIN_ALIGNMENT_BYTES)) return -EINVAL; diff --git a/mm/filemap.c b/mm/filemap.c index 4a30de98a8c75..bf9f85e3f3734 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -969,10 +969,12 @@ struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) n = cpuset_mem_spread_node(); folio = __folio_alloc_node(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); - - return folio; + } else { + folio = folio_alloc(gfp, order); } - return folio_alloc(gfp, order); + if (folio) + VM_BUG_ON_FOLIO(folio->private, folio); + return folio; } EXPORT_SYMBOL(filemap_alloc_folio); #endif @@ -4153,7 +4155,23 @@ static void filemap_cachestat(struct address_space *mapping, /* shmem file - in swap cache */ swp_entry_t swp = radix_to_swp_entry(folio); + /* swapin error results in poisoned entry */ + if (non_swap_entry(swp)) + goto resched; + + /* + * Getting a swap entry from the shmem + * inode means we beat + * shmem_unuse(). rcu_read_lock() + * ensures swapoff waits for us before + * freeing the swapper space. However, + * we can race with swapping and + * invalidation, so there might not be + * a shadow in the swapcache (yet). + */ shadow = get_shadow_from_swap_cache(swp); + if (!shadow) + goto resched; } #endif if (workingset_test_recent(shadow, true, &workingset)) diff --git a/mm/gup.c b/mm/gup.c index df83182ec72d5..f6d55635742f5 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1206,6 +1206,22 @@ static long __get_user_pages(struct mm_struct *mm, /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { + /* + * MADV_POPULATE_(READ|WRITE) wants to handle VMA + * lookups+error reporting differently. + */ + if (gup_flags & FOLL_MADV_POPULATE) { + vma = vma_lookup(mm, start); + if (!vma) { + ret = -ENOMEM; + goto out; + } + if (check_vma_flags(vma, gup_flags)) { + ret = -EINVAL; + goto out; + } + goto retry; + } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, @@ -1683,35 +1699,35 @@ long populate_vma_page_range(struct vm_area_struct *vma, } /* - * faultin_vma_page_range() - populate (prefault) page tables inside the - * given VMA range readable/writable + * faultin_page_range() - populate (prefault) page tables inside the + * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * - * @vma: target vma + * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * - * Returns either number of processed pages in the vma, or a negative error - * code on error (see __get_user_pages()). + * Returns either number of processed pages in the MM, or a negative error + * code on error (see __get_user_pages()). Note that this function reports + * errors related to VMAs, such as incompatible mappings, as expected by + * MADV_POPULATE_(READ|WRITE). * - * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and - * covered by the VMA. If it's released, *@locked will be set to 0. + * The range must be page-aligned. + * + * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ -long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, bool write, int *locked) +long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked) { - struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); - VM_BUG_ON_VMA(start < vma->vm_start, vma); - VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* @@ -1723,19 +1739,13 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ - gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE; + gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | + FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; - /* - * We want to report -EINVAL instead of -EFAULT for any permission - * problems or incompatible mappings. - */ - if (check_vma_flags(vma, gup_flags)) - return -EINVAL; - - ret = __get_user_pages(mm, start, nr_pages, gup_flags, - NULL, locked); + ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, + gup_flags); lru_add_drain(); return ret; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 94c958f7ebb50..d6686dd357410 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2244,9 +2244,6 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } - folio_move_anon_rmap(src_folio, dst_vma); - WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); - src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { @@ -2255,6 +2252,9 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } + folio_move_anon_rmap(src_folio, dst_vma); + WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); @@ -2470,32 +2470,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, return __split_huge_zero_page_pmd(vma, haddr, pmd); } - /* - * Up to this point the pmd is present and huge and userland has the - * whole access to the hugepage during the split (which happens in - * place). If we overwrite the pmd with the not-huge version pointing - * to the pte here (which of course we could if all CPUs were bug - * free), userland could trigger a small page size TLB miss on the - * small sized TLB while the hugepage TLB entry is still established in - * the huge TLB. Some CPU doesn't like that. - * See http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum - * 383 on page 105. Intel should be safe but is also warns that it's - * only safe if the permission and cache attributes of the two entries - * loaded in the two TLB is identical (which should be the case here). - * But it is generally safer to never allow small and huge TLB entries - * for the same virtual address to be loaded simultaneously. So instead - * of doing "pmd_populate(); flush_pmd_tlb_range();" we first mark the - * current pmd notpresent (atomically because here the pmd_trans_huge - * must remain set at all times on the pmd until the split is complete - * for this pmd), then we flush the SMP TLB and finally we write the - * non-huge version of the pmd entry with pmd_populate. - */ - old_pmd = pmdp_invalidate(vma, haddr, pmd); - - pmd_migration = is_pmd_migration_entry(old_pmd); + pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) { swp_entry_t entry; + old_pmd = *pmd; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); @@ -2506,6 +2485,30 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { + /* + * Up to this point the pmd is present and huge and userland has + * the whole access to the hugepage during the split (which + * happens in place). If we overwrite the pmd with the not-huge + * version pointing to the pte here (which of course we could if + * all CPUs were bug free), userland could trigger a small page + * size TLB miss on the small sized TLB while the hugepage TLB + * entry is still established in the huge TLB. Some CPU doesn't + * like that. See + * http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum + * 383 on page 105. Intel should be safe but is also warns that + * it's only safe if the permission and cache attributes of the + * two entries loaded in the two TLB is identical (which should + * be the case here). But it is generally safer to never allow + * small and huge TLB entries for the same virtual address to be + * loaded simultaneously. So instead of doing "pmd_populate(); + * flush_pmd_tlb_range();" we first mark the current pmd + * notpresent (atomically because here the pmd_trans_huge must + * remain set at all times on the pmd until the split is + * complete for this pmd), then we flush the SMP TLB and finally + * we write the non-huge version of the pmd entry with + * pmd_populate. + */ + old_pmd = pmdp_invalidate(vma, haddr, pmd); page = pmd_page(old_pmd); folio = page_folio(page); if (pmd_dirty(old_pmd)) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ed1581b670d42..f20e00c677212 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1623,7 +1623,7 @@ static inline void __clear_hugetlb_destructor(struct hstate *h, { lockdep_assert_held(&hugetlb_lock); - folio_clear_hugetlb(folio); + __folio_clear_hugetlb(folio); } /* @@ -1710,7 +1710,7 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, h->surplus_huge_pages_node[nid]++; } - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above @@ -1780,7 +1780,7 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, * If vmemmap pages were allocated above, then we need to clear the * hugetlb destructor under the hugetlb lock. */ - if (clear_dtor) { + if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __clear_hugetlb_destructor(h, folio); spin_unlock_irq(&hugetlb_lock); @@ -2048,7 +2048,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); @@ -2158,22 +2158,6 @@ static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, return __prep_compound_gigantic_folio(folio, order, true); } -/* - * PageHuge() only returns true for hugetlbfs pages, but not for normal or - * transparent huge pages. See the PageTransHuge() documentation for more - * details. - */ -int PageHuge(struct page *page) -{ - struct folio *folio; - - if (!PageCompound(page)) - return 0; - folio = page_folio(page); - return folio_test_hugetlb(folio); -} -EXPORT_SYMBOL_GPL(PageHuge); - /* * Find and lock address space (mapping) in write mode. * @@ -3266,9 +3250,12 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); - if (deferred_reserve) + if (deferred_reserve) { + spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); + spin_unlock_irq(&hugetlb_lock); + } } if (!memcg_charge_ret) @@ -6943,9 +6930,13 @@ long hugetlb_change_protection(struct vm_area_struct *vma, if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { - /* No other markers apply for now. */ - WARN_ON_ONCE(!pte_marker_uffd_wp(pte)); - if (uffd_wp_resolve) + /* + * Do nothing on a poison marker; page is + * corrupted, permissons do not apply. Here + * pte_marker_uffd_wp()==true implies !poison + * because they're mutual exclusive. + */ + if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { @@ -7765,9 +7756,9 @@ void __init hugetlb_cma_reserve(int order) * huge page demotion. */ res = cma_declare_contiguous_nid(0, size, 0, - PAGE_SIZE << HUGETLB_PAGE_ORDER, - 0, false, name, - &hugetlb_cma[nid], nid); + PAGE_SIZE << HUGETLB_PAGE_ORDER, + HUGETLB_PAGE_ORDER, false, name, + &hugetlb_cma[nid], nid); if (res) { pr_warn("hugetlb_cma: reservation failed: err %d, node %d", res, nid); diff --git a/mm/internal.h b/mm/internal.h index f309a010d50fb..c3f3e0f191151 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -590,9 +590,8 @@ struct anon_vma *folio_anon_vma(struct folio *folio); void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); -extern long faultin_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - bool write, int *locked); +extern long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); @@ -1031,10 +1030,13 @@ enum { FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, + /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ + FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ - FOLL_FAST_ONLY | FOLL_UNLOCKABLE) + FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ + FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index 971cfff4ca0b7..e26a2583a6643 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -440,7 +440,8 @@ static void kmalloc_oob_16(struct kunit *test) /* This test is specifically crafted for the generic mode. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); - ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL); + /* RELOC_HIDE to prevent gcc from warning about short alloc */ + ptr1 = RELOC_HIDE(kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL), 0); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1); ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL); diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index cf2d70e9c9a5f..95f859e38c533 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -196,8 +196,7 @@ void kmsan_internal_set_shadow_origin(void *addr, size_t size, int b, u32 origin, bool checked) { u64 address = (u64)addr; - void *shadow_start; - u32 *origin_start; + u32 *shadow_start, *origin_start; size_t pad = 0; KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(addr, size)); @@ -225,8 +224,16 @@ void kmsan_internal_set_shadow_origin(void *addr, size_t size, int b, origin_start = (u32 *)kmsan_get_metadata((void *)address, KMSAN_META_ORIGIN); - for (int i = 0; i < size / KMSAN_ORIGIN_SIZE; i++) - origin_start[i] = origin; + /* + * If the new origin is non-zero, assume that the shadow byte is also non-zero, + * and unconditionally overwrite the old origin slot. + * If the new origin is zero, overwrite the old origin slot iff the + * corresponding shadow slot is zero. + */ + for (int i = 0; i < size / KMSAN_ORIGIN_SIZE; i++) { + if (origin || !shadow_start[i]) + origin_start[i] = origin; + } } struct page *kmsan_vmalloc_to_page_or_null(void *vaddr) diff --git a/mm/ksm.c b/mm/ksm.c index 8c001819cf10f..27c6ddf2a4002 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -296,7 +296,7 @@ static bool ksm_use_zero_pages __read_mostly; static bool ksm_smart_scan = true; /* The number of zero pages which is placed by KSM */ -unsigned long ksm_zero_pages; +atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0); /* The number of pages that have been skipped due to "smart scanning" */ static unsigned long ksm_pages_skipped; @@ -1428,8 +1428,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, * the dirty bit in zero page's PTE is set. */ newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot))); - ksm_zero_pages++; - mm->ksm_zero_pages++; + ksm_map_zero_page(mm); /* * We're replacing an anonymous page with a zero page, which is * not anonymous. We need to do proper accounting otherwise we @@ -2747,18 +2746,16 @@ static void ksm_do_scan(unsigned int scan_npages) { struct ksm_rmap_item *rmap_item; struct page *page; - unsigned int npages = scan_npages; - while (npages-- && likely(!freezing(current))) { + while (scan_npages-- && likely(!freezing(current))) { cond_resched(); rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) return; cmp_and_merge_page(page, rmap_item); put_page(page); + ksm_pages_scanned++; } - - ksm_pages_scanned += scan_npages - npages; } static int ksmd_should_run(void) @@ -2782,9 +2779,14 @@ static int ksm_scan_thread(void *nothing) if (ksmd_should_run()) { sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs); - wait_event_freezable_timeout(ksm_iter_wait, - sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs), - msecs_to_jiffies(sleep_ms)); + if (sleep_ms >= 1000) + wait_event_freezable_timeout(ksm_iter_wait, + sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs), + msecs_to_jiffies(round_jiffies_relative(sleep_ms))); + else + wait_event_freezable_timeout(ksm_iter_wait, + sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs), + msecs_to_jiffies(sleep_ms)); } else { wait_event_freezable(ksm_thread_wait, ksmd_should_run() || kthread_should_stop()); @@ -3370,7 +3372,7 @@ static void wait_while_offlining(void) #ifdef CONFIG_PROC_FS long ksm_process_profit(struct mm_struct *mm) { - return (long)(mm->ksm_merging_pages + mm->ksm_zero_pages) * PAGE_SIZE - + return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); } #endif /* CONFIG_PROC_FS */ @@ -3659,7 +3661,7 @@ KSM_ATTR_RO(pages_skipped); static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sysfs_emit(buf, "%ld\n", ksm_zero_pages); + return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages)); } KSM_ATTR_RO(ksm_zero_pages); @@ -3668,7 +3670,7 @@ static ssize_t general_profit_show(struct kobject *kobj, { long general_profit; - general_profit = (ksm_pages_sharing + ksm_zero_pages) * PAGE_SIZE - + general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE - ksm_rmap_items * sizeof(struct ksm_rmap_item); return sysfs_emit(buf, "%ld\n", general_profit); diff --git a/mm/madvise.c b/mm/madvise.c index cfa5e72882611..f2c818af0b66e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -908,27 +908,14 @@ static long madvise_populate(struct vm_area_struct *vma, { const bool write = behavior == MADV_POPULATE_WRITE; struct mm_struct *mm = vma->vm_mm; - unsigned long tmp_end; int locked = 1; long pages; *prev = vma; while (start < end) { - /* - * We might have temporarily dropped the lock. For example, - * our VMA might have been split. - */ - if (!vma || start >= vma->vm_end) { - vma = vma_lookup(mm, start); - if (!vma) - return -ENOMEM; - } - - tmp_end = min_t(unsigned long, end, vma->vm_end); /* Populate (prefault) page tables readable/writable. */ - pages = faultin_vma_page_range(vma, start, tmp_end, write, - &locked); + pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; @@ -949,7 +936,7 @@ static long madvise_populate(struct vm_area_struct *vma, pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; - case -ENOMEM: + case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } diff --git a/mm/memblock.c b/mm/memblock.c index d09136e040d3c..08e9806b1cf91 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1339,6 +1339,10 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, int start_rgn, end_rgn; int i, ret; + if (WARN_ONCE(nid == MAX_NUMNODES, + "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n")) + nid = NUMA_NO_NODE; + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 61932c9215e77..1028619f379a8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7530,8 +7530,7 @@ void __mem_cgroup_uncharge_list(struct list_head *page_list) * @new: Replacement folio. * * Charge @new as a replacement folio for @old. @old will - * be uncharged upon free. This is only used by the page cache - * (in replace_page_cache_folio()). + * be uncharged upon free. * * Both folios must be locked, @new->mapping must be set up. */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9349948f1abfd..7751bd78fbcb2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -154,11 +154,23 @@ static int __page_handle_poison(struct page *page) { int ret; - zone_pcp_disable(page_zone(page)); + /* + * zone_pcp_disable() can't be used here. It will + * hold pcp_batch_high_lock and dissolve_free_huge_page() might hold + * cpu_hotplug_lock via static_key_slow_dec() when hugetlb vmemmap + * optimization is enabled. This will break current lock dependency + * chain and leads to deadlock. + * Disabling pcp before dissolving the page was a deterministic + * approach because we made sure that those pages cannot end up in any + * PCP list. Draining PCP lists expels those pages to the buddy system, + * but nothing guarantees that those pages do not get back to a PCP + * queue if we need to refill those. + */ ret = dissolve_free_huge_page(page); - if (!ret) + if (!ret) { + drain_all_pages(page_zone(page)); ret = take_page_off_buddy(page); - zone_pcp_enable(page_zone(page)); + } return ret; } @@ -1206,7 +1218,7 @@ static int me_huge_page(struct page_state *ps, struct page *p) * subpages. */ folio_put(folio); - if (__page_handle_poison(p) >= 0) { + if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { @@ -2085,7 +2097,7 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb */ if (res == 0) { folio_unlock(folio); - if (__page_handle_poison(p) >= 0) { + if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { @@ -2538,6 +2550,13 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } + if (is_huge_zero_page(&folio->page)) { + unpoison_pr_info("Unpoison: huge zero page is not supported %#lx\n", + pfn, &unpoison_rs); + ret = -EOPNOTSUPP; + goto unlock_mutex; + } + if (!PageHWPoison(p)) { unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", pfn, &unpoison_rs); diff --git a/mm/memory.c b/mm/memory.c index 0bfc8b007c01a..d5753ed81fc71 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1795,6 +1795,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, tlb_finish_mmu(&tlb); hugetlb_zap_end(vma, details); } +EXPORT_SYMBOL(zap_page_range_single); /** * zap_vma_ptes - remove ptes mapping the vma @@ -5837,6 +5838,10 @@ int follow_phys(struct vm_area_struct *vma, goto out; pte = ptep_get(ptep); + /* Never return PFNs of anon folios in COW mappings. */ + if (vm_normal_folio(vma, address, pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 21890994c1d3c..707027f691503 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1087,7 +1087,7 @@ void adjust_present_page_count(struct page *page, struct memory_group *group, } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, - struct zone *zone) + struct zone *zone, bool mhp_off_inaccessible) { unsigned long end_pfn = pfn + nr_pages; int ret, i; @@ -1096,6 +1096,15 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, if (ret) return ret; + /* + * Memory block is accessible at this stage and hence poison the struct + * pages now. If the memory block is accessible during memory hotplug + * addition phase, then page poisining is already performed in + * sparse_add_section(). + */ + if (mhp_off_inaccessible) + page_init_poison(pfn_to_page(pfn), sizeof(struct page) * nr_pages); + move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE); for (i = 0; i < nr_pages; i++) @@ -1415,7 +1424,7 @@ static void __ref remove_memory_blocks_and_altmaps(u64 start, u64 size) } static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group, - u64 start, u64 size) + u64 start, u64 size, mhp_t mhp_flags) { unsigned long memblock_size = memory_block_size_bytes(); u64 cur_start; @@ -1431,6 +1440,8 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group, }; mhp_altmap.free = memory_block_memmap_on_memory_pages(); + if (mhp_flags & MHP_OFFLINE_INACCESSIBLE) + mhp_altmap.inaccessible = true; params.altmap = kmemdup(&mhp_altmap, sizeof(struct vmem_altmap), GFP_KERNEL); if (!params.altmap) { @@ -1516,7 +1527,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) */ if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) && mhp_supports_memmap_on_memory(memory_block_size_bytes())) { - ret = create_altmaps_and_memory_blocks(nid, group, start, size); + ret = create_altmaps_and_memory_blocks(nid, group, start, size, mhp_flags); if (ret) goto error; } else { diff --git a/mm/memtest.c b/mm/memtest.c index 32f3e9dda8370..c2c609c391199 100644 --- a/mm/memtest.c +++ b/mm/memtest.c @@ -51,10 +51,10 @@ static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size last_bad = 0; for (p = start; p < end; p++) - *p = pattern; + WRITE_ONCE(*p, pattern); for (p = start; p < end; p++, start_phys_aligned += incr) { - if (*p == pattern) + if (READ_ONCE(*p) == pattern) continue; if (start_phys_aligned == last_bad + incr) { last_bad += incr; diff --git a/mm/page_table_check.c b/mm/page_table_check.c index af69c3c8f7c2d..6363f93a47c69 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -71,6 +71,9 @@ static void page_table_check_clear(unsigned long pfn, unsigned long pgcnt) page = pfn_to_page(pfn); page_ext = page_ext_get(page); + if (!page_ext) + return; + BUG_ON(PageSlab(page)); anon = PageAnon(page); @@ -108,6 +111,9 @@ static void page_table_check_set(unsigned long pfn, unsigned long pgcnt, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + if (!page_ext) + return; + BUG_ON(PageSlab(page)); anon = PageAnon(page); @@ -138,7 +144,10 @@ void __page_table_check_zero(struct page *page, unsigned int order) BUG_ON(PageSlab(page)); page_ext = page_ext_get(page); - BUG_ON(!page_ext); + + if (!page_ext) + return; + for (i = 0; i < (1ul << order); i++) { struct page_table_check *ptc = get_page_table_check(page_ext); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4fcd959dcc4d0..a78a4adf711ac 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -198,6 +198,7 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return old; @@ -208,6 +209,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); return pmdp_invalidate(vma, address, pmdp); } #endif diff --git a/mm/readahead.c b/mm/readahead.c index 2648ec4f04947..89139a8721941 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -490,6 +490,7 @@ void page_cache_ra_order(struct readahead_control *ractl, pgoff_t index = readahead_index(ractl); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; + unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); @@ -506,6 +507,8 @@ void page_cache_ra_order(struct readahead_control *ractl, new_order--; } + /* See comment in page_cache_ra_unbounded() */ + nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); while (index <= limit) { unsigned int order = new_order; @@ -532,6 +535,7 @@ void page_cache_ra_order(struct readahead_control *ractl, read_pages(ractl); filemap_invalidate_unlock_shared(mapping); + memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have diff --git a/mm/shmem.c b/mm/shmem.c index d7c84ff621860..6a62e2e550377 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -311,7 +311,7 @@ static void shmem_disable_quotas(struct super_block *sb) dquot_quota_off(sb, type); } -static struct dquot **shmem_get_dquots(struct inode *inode) +static struct dquot __rcu **shmem_get_dquots(struct inode *inode) { return SHMEM_I(inode)->i_dquot; } @@ -742,12 +742,6 @@ static long shmem_unused_huge_count(struct super_block *sb, #define shmem_huge SHMEM_HUGE_DENY -bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags) -{ - return false; -} - static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { @@ -1786,7 +1780,7 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, old, new); if (!error) { - mem_cgroup_migrate(old, new); + mem_cgroup_replace_folio(old, new); __lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1); __lruvec_stat_mod_folio(new, NR_SHMEM, 1); __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1); @@ -3374,7 +3368,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) static int shmem_rmdir(struct inode *dir, struct dentry *dentry) { - if (!simple_empty(dentry)) + if (!simple_offset_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); @@ -3431,7 +3425,7 @@ static int shmem_rename2(struct mnt_idmap *idmap, return simple_offset_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); - if (!simple_empty(new_dentry)) + if (!simple_offset_empty(new_dentry)) return -ENOTEMPTY; if (flags & RENAME_WHITEOUT) { @@ -3440,8 +3434,7 @@ static int shmem_rename2(struct mnt_idmap *idmap, return error; } - simple_offset_remove(shmem_get_offset_ctx(old_dir), old_dentry); - error = simple_offset_add(shmem_get_offset_ctx(new_dir), old_dentry); + error = simple_offset_rename(old_dir, old_dentry, new_dir, new_dentry); if (error) return error; diff --git a/mm/shmem_quota.c b/mm/shmem_quota.c index 062d1c1097ae3..ce514e700d2f6 100644 --- a/mm/shmem_quota.c +++ b/mm/shmem_quota.c @@ -116,7 +116,7 @@ static int shmem_free_file_info(struct super_block *sb, int type) static int shmem_get_next_id(struct super_block *sb, struct kqid *qid) { struct mem_dqinfo *info = sb_dqinfo(sb, qid->type); - struct rb_node *node = ((struct rb_root *)info->dqi_priv)->rb_node; + struct rb_node *node; qid_t id = from_kqid(&init_user_ns, *qid); struct quota_info *dqopt = sb_dqopt(sb); struct quota_id *entry = NULL; @@ -126,6 +126,7 @@ static int shmem_get_next_id(struct super_block *sb, struct kqid *qid) return -ESRCH; down_read(&dqopt->dqio_sem); + node = ((struct rb_root *)info->dqi_priv)->rb_node; while (node) { entry = rb_entry(node, struct quota_id, node); @@ -165,7 +166,7 @@ static int shmem_get_next_id(struct super_block *sb, struct kqid *qid) static int shmem_acquire_dquot(struct dquot *dquot) { struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type); - struct rb_node **n = &((struct rb_root *)info->dqi_priv)->rb_node; + struct rb_node **n; struct shmem_sb_info *sbinfo = dquot->dq_sb->s_fs_info; struct rb_node *parent = NULL, *new_node = NULL; struct quota_id *new_entry, *entry; @@ -176,6 +177,8 @@ static int shmem_acquire_dquot(struct dquot *dquot) mutex_lock(&dquot->dq_lock); down_write(&dqopt->dqio_sem); + n = &((struct rb_root *)info->dqi_priv)->rb_node; + while (*n) { parent = *n; entry = rb_entry(parent, struct quota_id, node); @@ -264,7 +267,7 @@ static bool shmem_is_empty_dquot(struct dquot *dquot) static int shmem_release_dquot(struct dquot *dquot) { struct mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type); - struct rb_node *node = ((struct rb_root *)info->dqi_priv)->rb_node; + struct rb_node *node; qid_t id = from_kqid(&init_user_ns, dquot->dq_id); struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); struct quota_id *entry = NULL; @@ -275,6 +278,7 @@ static int shmem_release_dquot(struct dquot *dquot) goto out_dqlock; down_write(&dqopt->dqio_sem); + node = ((struct rb_root *)info->dqi_priv)->rb_node; while (node) { entry = rb_entry(node, struct quota_id, node); diff --git a/mm/slub.c b/mm/slub.c index 2ef88bbf56a37..914c35a7d4ef0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -557,6 +557,26 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp) *(freeptr_t *)freeptr_addr = freelist_ptr_encode(s, fp, freeptr_addr); } +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + /* Loop over all objects in a slab */ #define for_each_object(__p, __s, __addr, __objects) \ for (__p = fixup_red_left(__s, __addr); \ @@ -845,26 +865,6 @@ static void print_section(char *level, char *text, u8 *addr, metadata_access_disable(); } -/* - * See comment in calculate_sizes(). - */ -static inline bool freeptr_outside_object(struct kmem_cache *s) -{ - return s->offset >= s->inuse; -} - -/* - * Return offset of the end of info block which is inuse + free pointer if - * not overlapping with object. - */ -static inline unsigned int get_info_end(struct kmem_cache *s) -{ - if (freeptr_outside_object(s)) - return s->inuse + sizeof(void *); - else - return s->inuse; -} - static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { @@ -2107,15 +2107,20 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init) * * The initialization memset's clear the object and the metadata, * but don't touch the SLAB redzone. + * + * The object's freepointer is also avoided if stored outside the + * object. */ if (unlikely(init)) { int rsize; + unsigned int inuse; + inuse = get_info_end(s); if (!kasan_has_integrated_init()) memset(kasan_reset_tag(x), 0, s->object_size); rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad : 0; - memset((char *)kasan_reset_tag(x) + s->inuse, 0, - s->size - s->inuse - rsize); + memset((char *)kasan_reset_tag(x) + inuse, 0, + s->size - inuse - rsize); } /* KASAN might put x into memory quarantine, delaying its reuse. */ return !kasan_slab_free(s, x, init); @@ -3737,7 +3742,8 @@ static void *__slab_alloc_node(struct kmem_cache *s, static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, void *obj) { - if (unlikely(slab_want_init_on_free(s)) && obj) + if (unlikely(slab_want_init_on_free(s)) && obj && + !freeptr_outside_object(s)) memset((void *)((char *)kasan_reset_tag(obj) + s->offset), 0, sizeof(void *)); } diff --git a/mm/sparse.c b/mm/sparse.c index 338cf946dee8d..aed0951b87fa0 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -908,7 +908,8 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, * Poison uninitialized struct pages in order to catch invalid flags * combinations. */ - page_init_poison(memmap, sizeof(struct page) * nr_pages); + if (!altmap || !altmap->inaccessible) + page_init_poison(memmap, sizeof(struct page) * nr_pages); ms = __nr_to_section(section_nr); set_section_nid(section_nr, nid); diff --git a/mm/swapfile.c b/mm/swapfile.c index 746aa9da53025..6fe0cc25535f5 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1227,6 +1227,11 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, * with get_swap_device() and put_swap_device(), unless the swap * functions call get/put_swap_device() by themselves. * + * Note that when only holding the PTL, swapoff might succeed immediately + * after freeing a swap entry. Therefore, immediately after + * __swap_entry_free(), the swap info might become stale and should not + * be touched without a prior get_swap_device(). + * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until @@ -1604,13 +1609,19 @@ int free_swap_and_cache(swp_entry_t entry) if (non_swap_entry(entry)) return 1; - p = _swap_info_get(entry); + p = get_swap_device(entry); if (p) { + if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { + put_swap_device(p); + return 0; + } + count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); + put_swap_device(p); } return p != NULL; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 313f1c42768a6..aa8f5a6c324ee 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -213,6 +213,38 @@ static int mfill_atomic_pte_copy(pmd_t *dst_pmd, goto out; } +static int mfill_atomic_pte_zeroed_folio(pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr) +{ + struct folio *folio; + int ret = -ENOMEM; + + folio = vma_alloc_zeroed_movable_folio(dst_vma, dst_addr); + if (!folio) + return ret; + + if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL)) + goto out_put; + + /* + * The memory barrier inside __folio_mark_uptodate makes sure that + * zeroing out the folio become visible before mapping the page + * using set_pte_at(). See do_anonymous_page(). + */ + __folio_mark_uptodate(folio); + + ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, + &folio->page, true, 0); + if (ret) + goto out_put; + + return 0; +out_put: + folio_put(folio); + return ret; +} + static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) @@ -221,6 +253,9 @@ static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd, spinlock_t *ptl; int ret; + if (mm_forbids_zeropage(dst_vma->vm_mm)) + return mfill_atomic_pte_zeroed_folio(dst_pmd, dst_vma, dst_addr); + _dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); ret = -EAGAIN; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d12a17fc0c171..7e288cc89ac5d 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2641,6 +2641,7 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); } +EXPORT_SYMBOL(get_vm_area); struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) @@ -2994,7 +2995,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, { unsigned int nr_allocated = 0; gfp_t alloc_gfp = gfp; - bool nofail = false; + bool nofail = gfp & __GFP_NOFAIL; struct page *page; int i; @@ -3051,12 +3052,11 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * and compaction etc. */ alloc_gfp &= ~__GFP_NOFAIL; - nofail = true; } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { - if (fatal_signal_pending(current)) + if (!nofail && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) diff --git a/mm/zswap.c b/mm/zswap.c index db4625af65fb7..69766f2c5a6c4 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -645,15 +645,30 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg)) return 0; -#ifdef CONFIG_MEMCG_KMEM - mem_cgroup_flush_stats(memcg); - nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; - nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); -#else - /* use pool stats instead of memcg stats */ - nr_backing = get_zswap_pool_size(pool) >> PAGE_SHIFT; - nr_stored = atomic_read(&pool->nr_stored); -#endif + /* + * The shrinker resumes swap writeback, which will enter block + * and may enter fs. XXX: Harmonize with vmscan.c __GFP_FS + * rules (may_enter_fs()), which apply on a per-folio basis. + */ + if (!gfp_has_io_fs(sc->gfp_mask)) + return 0; + + /* + * For memcg, use the cgroup-wide ZSWAP stats since we don't + * have them per-node and thus per-lruvec. Careful if memcg is + * runtime-disabled: we can get sc->memcg == NULL, which is ok + * for the lruvec, but not for memcg_page_state(). + * + * Without memcg, use the zswap pool-wide metrics. + */ + if (!mem_cgroup_disabled()) { + mem_cgroup_flush_stats(memcg); + nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; + nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); + } else { + nr_backing = get_zswap_pool_size(pool) >> PAGE_SHIFT; + nr_stored = atomic_read(&pool->nr_stored); + } if (!nr_stored) return 0; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index f001582345052..9404dd551dfd2 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -478,6 +478,8 @@ static struct sk_buff *vlan_gro_receive(struct list_head *head, if (unlikely(!vhdr)) goto out; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = hlen; + type = vhdr->h_vlan_encapsulated_proto; ptype = gro_find_receive_by_type(type); diff --git a/net/9p/client.c b/net/9p/client.c index e265a0ca6bddd..b05f73c291b4b 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -235,6 +235,8 @@ static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc, if (!fc->sdata) return -ENOMEM; fc->capacity = alloc_msize; + fc->id = 0; + fc->tag = P9_NOTAG; return 0; } @@ -1583,7 +1585,7 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, received = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", received); if (non_zc) { int n = copy_to_iter(dataptr, received, to); @@ -1609,9 +1611,6 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) int total = 0; *err = 0; - p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n", - fid->fid, offset, iov_iter_count(from)); - while (iov_iter_count(from)) { int count = iov_iter_count(from); int rsize = fid->iounit; @@ -1623,6 +1622,9 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) if (count < rsize) rsize = count; + p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d (/%d)\n", + fid->fid, offset, rsize, count); + /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0, @@ -1650,7 +1652,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) written = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", written); p9_req_put(clnt, req); iov_iter_revert(from, count - written - iov_iter_count(from)); diff --git a/net/atm/clip.c b/net/atm/clip.c index 294cb9efe3d38..015fb679be425 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -345,7 +345,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, dev->stats.tx_dropped++; return NETDEV_TX_OK; } - rt = (struct rtable *) dst; + rt = dst_rtable(dst); if (rt->rt_gw_family == AF_INET) daddr = &rt->rt_gw4; else diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 558e158c98d01..5fff5930e4deb 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -103,7 +103,7 @@ static void ax25_kill_by_device(struct net_device *dev) s->ax25_dev = NULL; if (sk->sk_socket) { netdev_put(ax25_dev->dev, - &ax25_dev->dev_tracker); + &s->dev_tracker); ax25_dev_put(ax25_dev); } ax25_cb_del(s); @@ -1378,8 +1378,10 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, { struct sk_buff *skb; struct sock *newsk; + ax25_dev *ax25_dev; DEFINE_WAIT(wait); struct sock *sk; + ax25_cb *ax25; int err = 0; if (sock->state != SS_UNCONNECTED) @@ -1434,6 +1436,10 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, kfree_skb(skb); sk_acceptq_removed(sk); newsock->state = SS_CONNECTED; + ax25 = sk_to_ax25(newsk); + ax25_dev = ax25->ax25_dev; + netdev_hold(ax25_dev->dev, &ax25->dev_tracker, GFP_ATOMIC); + ax25_dev_hold(ax25_dev); out: release_sock(sk); diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index c5462486dbca1..67ae6b8c52989 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -22,11 +22,12 @@ #include #include #include +#include #include #include #include -ax25_dev *ax25_dev_list; +static LIST_HEAD(ax25_dev_list); DEFINE_SPINLOCK(ax25_dev_lock); ax25_dev *ax25_addr_ax25dev(ax25_address *addr) @@ -34,10 +35,11 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr) ax25_dev *ax25_dev, *res = NULL; spin_lock_bh(&ax25_dev_lock); - for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next) + list_for_each_entry(ax25_dev, &ax25_dev_list, list) if (ax25cmp(addr, (const ax25_address *)ax25_dev->dev->dev_addr) == 0) { res = ax25_dev; ax25_dev_hold(ax25_dev); + break; } spin_unlock_bh(&ax25_dev_lock); @@ -59,7 +61,6 @@ void ax25_dev_device_up(struct net_device *dev) } refcount_set(&ax25_dev->refcount, 1); - dev->ax25_ptr = ax25_dev; ax25_dev->dev = dev; netdev_hold(dev, &ax25_dev->dev_tracker, GFP_KERNEL); ax25_dev->forward = NULL; @@ -85,10 +86,9 @@ void ax25_dev_device_up(struct net_device *dev) #endif spin_lock_bh(&ax25_dev_lock); - ax25_dev->next = ax25_dev_list; - ax25_dev_list = ax25_dev; + list_add(&ax25_dev->list, &ax25_dev_list); + dev->ax25_ptr = ax25_dev; spin_unlock_bh(&ax25_dev_lock); - ax25_dev_hold(ax25_dev); ax25_register_dev_sysctl(ax25_dev); } @@ -105,38 +105,25 @@ void ax25_dev_device_down(struct net_device *dev) spin_lock_bh(&ax25_dev_lock); #ifdef CONFIG_AX25_DAMA_SLAVE - ax25_ds_del_timer(ax25_dev); + timer_shutdown_sync(&ax25_dev->dama.slave_timer); #endif /* * Remove any packet forwarding that points to this device. */ - for (s = ax25_dev_list; s != NULL; s = s->next) + list_for_each_entry(s, &ax25_dev_list, list) if (s->forward == dev) s->forward = NULL; - if ((s = ax25_dev_list) == ax25_dev) { - ax25_dev_list = s->next; - goto unlock_put; - } - - while (s != NULL && s->next != NULL) { - if (s->next == ax25_dev) { - s->next = ax25_dev->next; - goto unlock_put; + list_for_each_entry(s, &ax25_dev_list, list) { + if (s == ax25_dev) { + list_del(&s->list); + break; } - - s = s->next; } - spin_unlock_bh(&ax25_dev_lock); - dev->ax25_ptr = NULL; - ax25_dev_put(ax25_dev); - return; -unlock_put: - spin_unlock_bh(&ax25_dev_lock); - ax25_dev_put(ax25_dev); dev->ax25_ptr = NULL; + spin_unlock_bh(&ax25_dev_lock); netdev_put(dev, &ax25_dev->dev_tracker); ax25_dev_put(ax25_dev); } @@ -200,16 +187,13 @@ struct net_device *ax25_fwd_dev(struct net_device *dev) */ void __exit ax25_dev_free(void) { - ax25_dev *s, *ax25_dev; + ax25_dev *s, *n; spin_lock_bh(&ax25_dev_lock); - ax25_dev = ax25_dev_list; - while (ax25_dev != NULL) { - s = ax25_dev; - netdev_put(ax25_dev->dev, &ax25_dev->dev_tracker); - ax25_dev = ax25_dev->next; - kfree(s); + list_for_each_entry_safe(s, n, &ax25_dev_list, list) { + netdev_put(s->dev, &s->dev_tracker); + list_del(&s->list); + ax25_dev_put(s); } - ax25_dev_list = NULL; spin_unlock_bh(&ax25_dev_lock); } diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 71c143d4b6d05..ac74f6ead62d5 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1266,6 +1266,8 @@ void batadv_purge_orig_ref(struct batadv_priv *bat_priv) /* for all origins... */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; + if (hlist_empty(head)) + continue; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b95c36765d045..2243cec18ecc8 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -3948,7 +3948,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface) spin_lock_bh(&bat_priv->tt.commit_lock); - while (true) { + while (timeout) { table_size = batadv_tt_local_table_transmit_size(bat_priv); if (packet_size_max >= table_size) break; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 4eb1b3ced0d27..0fcaa4d832c98 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -133,7 +133,7 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_btle_dev *dev, struct in6_addr *daddr, struct sk_buff *skb) { - struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int count = atomic_read(&dev->peer_count); const struct in6_addr *nexthop; struct lowpan_peer *peer; @@ -892,7 +892,7 @@ static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type) chan->ops = &bt_6lowpan_chan_ops; err = l2cap_chan_connect(chan, cpu_to_le16(L2CAP_PSM_IPSP), 0, - addr, dst_type); + addr, dst_type, L2CAP_CONN_TIMEOUT); BT_DBG("chan %p err %d", chan, err); if (err < 0) diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index da7cac0a1b716..6b2b65a667008 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -62,14 +62,6 @@ source "net/bluetooth/cmtp/Kconfig" source "net/bluetooth/hidp/Kconfig" -config BT_HS - bool "Bluetooth High Speed (HS) features" - depends on BT_BREDR - help - Bluetooth High Speed includes support for off-loading - Bluetooth connections via 802.11 (wifi) physical layer - available with Bluetooth version 3.0 or later. - config BT_LE bool "Bluetooth Low Energy (LE) features" depends on BT diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 141ac1fda0bfa..628d448d78be3 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -21,7 +21,6 @@ bluetooth-$(CONFIG_DEV_COREDUMP) += coredump.o bluetooth-$(CONFIG_BT_BREDR) += sco.o bluetooth-$(CONFIG_BT_LE) += iso.o -bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o bluetooth-$(CONFIG_BT_LEDS) += leds.o bluetooth-$(CONFIG_BT_MSFTEXT) += msft.o bluetooth-$(CONFIG_BT_AOSPEXT) += aosp.o diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c deleted file mode 100644 index e7adb8a98cf90..0000000000000 --- a/net/bluetooth/a2mp.c +++ /dev/null @@ -1,1054 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - Copyright (c) 2010,2011 Code Aurora Forum. All rights reserved. - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#include -#include -#include - -#include "hci_request.h" -#include "a2mp.h" -#include "amp.h" - -#define A2MP_FEAT_EXT 0x8000 - -/* Global AMP Manager list */ -static LIST_HEAD(amp_mgr_list); -static DEFINE_MUTEX(amp_mgr_list_lock); - -/* A2MP build & send command helper functions */ -static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data) -{ - struct a2mp_cmd *cmd; - int plen; - - plen = sizeof(*cmd) + len; - cmd = kzalloc(plen, GFP_KERNEL); - if (!cmd) - return NULL; - - cmd->code = code; - cmd->ident = ident; - cmd->len = cpu_to_le16(len); - - memcpy(cmd->data, data, len); - - return cmd; -} - -static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) -{ - struct l2cap_chan *chan = mgr->a2mp_chan; - struct a2mp_cmd *cmd; - u16 total_len = len + sizeof(*cmd); - struct kvec iv; - struct msghdr msg; - - cmd = __a2mp_build(code, ident, len, data); - if (!cmd) - return; - - iv.iov_base = cmd; - iv.iov_len = total_len; - - memset(&msg, 0, sizeof(msg)); - - iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iv, 1, total_len); - - l2cap_chan_send(chan, &msg, total_len); - - kfree(cmd); -} - -static u8 __next_ident(struct amp_mgr *mgr) -{ - if (++mgr->ident == 0) - mgr->ident = 1; - - return mgr->ident; -} - -static struct amp_mgr *amp_mgr_lookup_by_state(u8 state) -{ - struct amp_mgr *mgr; - - mutex_lock(&_mgr_list_lock); - list_for_each_entry(mgr, &_mgr_list, list) { - if (test_and_clear_bit(state, &mgr->state)) { - amp_mgr_get(mgr); - mutex_unlock(&_mgr_list_lock); - return mgr; - } - } - mutex_unlock(&_mgr_list_lock); - - return NULL; -} - -/* hci_dev_list shall be locked */ -static void __a2mp_add_cl(struct amp_mgr *mgr, struct a2mp_cl *cl) -{ - struct hci_dev *hdev; - int i = 1; - - cl[0].id = AMP_ID_BREDR; - cl[0].type = AMP_TYPE_BREDR; - cl[0].status = AMP_STATUS_BLUETOOTH_ONLY; - - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->dev_type == HCI_AMP) { - cl[i].id = hdev->id; - cl[i].type = hdev->amp_type; - if (test_bit(HCI_UP, &hdev->flags)) - cl[i].status = hdev->amp_status; - else - cl[i].status = AMP_STATUS_POWERED_DOWN; - i++; - } - } -} - -/* Processing A2MP messages */ -static int a2mp_command_rej(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_cmd_rej *rej = (void *) skb->data; - - if (le16_to_cpu(hdr->len) < sizeof(*rej)) - return -EINVAL; - - BT_DBG("ident %u reason %d", hdr->ident, le16_to_cpu(rej->reason)); - - skb_pull(skb, sizeof(*rej)); - - return 0; -} - -static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_discov_req *req = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct a2mp_discov_rsp *rsp; - u16 ext_feat; - u8 num_ctrl; - struct hci_dev *hdev; - - if (len < sizeof(*req)) - return -EINVAL; - - skb_pull(skb, sizeof(*req)); - - ext_feat = le16_to_cpu(req->ext_feat); - - BT_DBG("mtu %d efm 0x%4.4x", le16_to_cpu(req->mtu), ext_feat); - - /* check that packet is not broken for now */ - while (ext_feat & A2MP_FEAT_EXT) { - if (len < sizeof(ext_feat)) - return -EINVAL; - - ext_feat = get_unaligned_le16(skb->data); - BT_DBG("efm 0x%4.4x", ext_feat); - len -= sizeof(ext_feat); - skb_pull(skb, sizeof(ext_feat)); - } - - read_lock(&hci_dev_list_lock); - - /* at minimum the BR/EDR needs to be listed */ - num_ctrl = 1; - - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->dev_type == HCI_AMP) - num_ctrl++; - } - - len = struct_size(rsp, cl, num_ctrl); - rsp = kmalloc(len, GFP_ATOMIC); - if (!rsp) { - read_unlock(&hci_dev_list_lock); - return -ENOMEM; - } - - rsp->mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); - rsp->ext_feat = 0; - - __a2mp_add_cl(mgr, rsp->cl); - - read_unlock(&hci_dev_list_lock); - - a2mp_send(mgr, A2MP_DISCOVER_RSP, hdr->ident, len, rsp); - - kfree(rsp); - return 0; -} - -static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_discov_rsp *rsp = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct a2mp_cl *cl; - u16 ext_feat; - bool found = false; - - if (len < sizeof(*rsp)) - return -EINVAL; - - len -= sizeof(*rsp); - skb_pull(skb, sizeof(*rsp)); - - ext_feat = le16_to_cpu(rsp->ext_feat); - - BT_DBG("mtu %d efm 0x%4.4x", le16_to_cpu(rsp->mtu), ext_feat); - - /* check that packet is not broken for now */ - while (ext_feat & A2MP_FEAT_EXT) { - if (len < sizeof(ext_feat)) - return -EINVAL; - - ext_feat = get_unaligned_le16(skb->data); - BT_DBG("efm 0x%4.4x", ext_feat); - len -= sizeof(ext_feat); - skb_pull(skb, sizeof(ext_feat)); - } - - cl = (void *) skb->data; - while (len >= sizeof(*cl)) { - BT_DBG("Remote AMP id %u type %u status %u", cl->id, cl->type, - cl->status); - - if (cl->id != AMP_ID_BREDR && cl->type != AMP_TYPE_BREDR) { - struct a2mp_info_req req; - - found = true; - - memset(&req, 0, sizeof(req)); - - req.id = cl->id; - a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr), - sizeof(req), &req); - } - - len -= sizeof(*cl); - cl = skb_pull(skb, sizeof(*cl)); - } - - /* Fall back to L2CAP init sequence */ - if (!found) { - struct l2cap_conn *conn = mgr->l2cap_conn; - struct l2cap_chan *chan; - - mutex_lock(&conn->chan_lock); - - list_for_each_entry(chan, &conn->chan_l, list) { - - BT_DBG("chan %p state %s", chan, - state_to_string(chan->state)); - - if (chan->scid == L2CAP_CID_A2MP) - continue; - - l2cap_chan_lock(chan); - - if (chan->state == BT_CONNECT) - l2cap_send_conn_req(chan); - - l2cap_chan_unlock(chan); - } - - mutex_unlock(&conn->chan_lock); - } - - return 0; -} - -static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_cl *cl = (void *) skb->data; - - while (skb->len >= sizeof(*cl)) { - BT_DBG("Controller id %u type %u status %u", cl->id, cl->type, - cl->status); - cl = skb_pull(skb, sizeof(*cl)); - } - - /* TODO send A2MP_CHANGE_RSP */ - - return 0; -} - -static void read_local_amp_info_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - a2mp_send_getinfo_rsp(hdev); -} - -static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_info_req *req = (void *) skb->data; - struct hci_dev *hdev; - struct hci_request hreq; - int err = 0; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("id %u", req->id); - - hdev = hci_dev_get(req->id); - if (!hdev || hdev->dev_type != HCI_AMP) { - struct a2mp_info_rsp rsp; - - memset(&rsp, 0, sizeof(rsp)); - - rsp.id = req->id; - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - - a2mp_send(mgr, A2MP_GETINFO_RSP, hdr->ident, sizeof(rsp), - &rsp); - - goto done; - } - - set_bit(READ_LOC_AMP_INFO, &mgr->state); - hci_req_init(&hreq, hdev); - hci_req_add(&hreq, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); - err = hci_req_run(&hreq, read_local_amp_info_complete); - if (err < 0) - a2mp_send_getinfo_rsp(hdev); - -done: - if (hdev) - hci_dev_put(hdev); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_info_rsp *rsp = (struct a2mp_info_rsp *) skb->data; - struct a2mp_amp_assoc_req req; - struct amp_ctrl *ctrl; - - if (le16_to_cpu(hdr->len) < sizeof(*rsp)) - return -EINVAL; - - BT_DBG("id %u status 0x%2.2x", rsp->id, rsp->status); - - if (rsp->status) - return -EINVAL; - - ctrl = amp_ctrl_add(mgr, rsp->id); - if (!ctrl) - return -ENOMEM; - - memset(&req, 0, sizeof(req)); - - req.id = rsp->id; - a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req), - &req); - - skb_pull(skb, sizeof(*rsp)); - return 0; -} - -static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_amp_assoc_req *req = (void *) skb->data; - struct hci_dev *hdev; - struct amp_mgr *tmp; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("id %u", req->id); - - /* Make sure that other request is not processed */ - tmp = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); - - hdev = hci_dev_get(req->id); - if (!hdev || hdev->amp_type == AMP_TYPE_BREDR || tmp) { - struct a2mp_amp_assoc_rsp rsp; - - memset(&rsp, 0, sizeof(rsp)); - rsp.id = req->id; - - if (tmp) { - rsp.status = A2MP_STATUS_COLLISION_OCCURED; - amp_mgr_put(tmp); - } else { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - } - - a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, hdr->ident, sizeof(rsp), - &rsp); - - goto done; - } - - amp_read_loc_assoc(hdev, mgr); - -done: - if (hdev) - hci_dev_put(hdev); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_amp_assoc_rsp *rsp = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct hci_dev *hdev; - struct amp_ctrl *ctrl; - struct hci_conn *hcon; - size_t assoc_len; - - if (len < sizeof(*rsp)) - return -EINVAL; - - assoc_len = len - sizeof(*rsp); - - BT_DBG("id %u status 0x%2.2x assoc len %zu", rsp->id, rsp->status, - assoc_len); - - if (rsp->status) - return -EINVAL; - - /* Save remote ASSOC data */ - ctrl = amp_ctrl_lookup(mgr, rsp->id); - if (ctrl) { - u8 *assoc; - - assoc = kmemdup(rsp->amp_assoc, assoc_len, GFP_KERNEL); - if (!assoc) { - amp_ctrl_put(ctrl); - return -ENOMEM; - } - - ctrl->assoc = assoc; - ctrl->assoc_len = assoc_len; - ctrl->assoc_rem_len = assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - } - - /* Create Phys Link */ - hdev = hci_dev_get(rsp->id); - if (!hdev) - return -EINVAL; - - hcon = phylink_add(hdev, mgr, rsp->id, true); - if (!hcon) - goto done; - - BT_DBG("Created hcon %p: loc:%u -> rem:%u", hcon, hdev->id, rsp->id); - - mgr->bredr_chan->remote_amp_id = rsp->id; - - amp_create_phylink(hdev, mgr, hcon); - -done: - hci_dev_put(hdev); - skb_pull(skb, len); - return 0; -} - -static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; - struct hci_dev *hdev; - struct hci_conn *hcon; - struct amp_ctrl *ctrl; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("local_id %u, remote_id %u", req->local_id, req->remote_id); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.local_id = req->remote_id; - rsp.remote_id = req->local_id; - - hdev = hci_dev_get(req->remote_id); - if (!hdev || hdev->amp_type == AMP_TYPE_BREDR) { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - goto send_rsp; - } - - ctrl = amp_ctrl_lookup(mgr, rsp.remote_id); - if (!ctrl) { - ctrl = amp_ctrl_add(mgr, rsp.remote_id); - if (ctrl) { - amp_ctrl_get(ctrl); - } else { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - goto send_rsp; - } - } - - if (ctrl) { - size_t assoc_len = le16_to_cpu(hdr->len) - sizeof(*req); - u8 *assoc; - - assoc = kmemdup(req->amp_assoc, assoc_len, GFP_KERNEL); - if (!assoc) { - amp_ctrl_put(ctrl); - hci_dev_put(hdev); - return -ENOMEM; - } - - ctrl->assoc = assoc; - ctrl->assoc_len = assoc_len; - ctrl->assoc_rem_len = assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - } - - hcon = phylink_add(hdev, mgr, req->local_id, false); - if (hcon) { - amp_accept_phylink(hdev, mgr, hcon); - rsp.status = A2MP_STATUS_SUCCESS; - } else { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - } - -send_rsp: - if (hdev) - hci_dev_put(hdev); - - /* Reply error now and success after HCI Write Remote AMP Assoc - command complete with success status - */ - if (rsp.status != A2MP_STATUS_SUCCESS) { - a2mp_send(mgr, A2MP_CREATEPHYSLINK_RSP, hdr->ident, - sizeof(rsp), &rsp); - } else { - set_bit(WRITE_REMOTE_AMP_ASSOC, &mgr->state); - mgr->ident = hdr->ident; - } - - skb_pull(skb, le16_to_cpu(hdr->len)); - return 0; -} - -static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; - struct hci_dev *hdev; - struct hci_conn *hcon; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("local_id %u remote_id %u", req->local_id, req->remote_id); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.local_id = req->remote_id; - rsp.remote_id = req->local_id; - rsp.status = A2MP_STATUS_SUCCESS; - - hdev = hci_dev_get(req->remote_id); - if (!hdev) { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - goto send_rsp; - } - - hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, - &mgr->l2cap_conn->hcon->dst); - if (!hcon) { - bt_dev_err(hdev, "no phys link exist"); - rsp.status = A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS; - goto clean; - } - - /* TODO Disconnect Phys Link here */ - -clean: - hci_dev_put(hdev); - -send_rsp: - a2mp_send(mgr, A2MP_DISCONNPHYSLINK_RSP, hdr->ident, sizeof(rsp), &rsp); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static inline int a2mp_cmd_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - BT_DBG("ident %u code 0x%2.2x", hdr->ident, hdr->code); - - skb_pull(skb, le16_to_cpu(hdr->len)); - return 0; -} - -/* Handle A2MP signalling */ -static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) -{ - struct a2mp_cmd *hdr; - struct amp_mgr *mgr = chan->data; - int err = 0; - - amp_mgr_get(mgr); - - while (skb->len >= sizeof(*hdr)) { - u16 len; - - hdr = (void *) skb->data; - len = le16_to_cpu(hdr->len); - - BT_DBG("code 0x%2.2x id %u len %u", hdr->code, hdr->ident, len); - - skb_pull(skb, sizeof(*hdr)); - - if (len > skb->len || !hdr->ident) { - err = -EINVAL; - break; - } - - mgr->ident = hdr->ident; - - switch (hdr->code) { - case A2MP_COMMAND_REJ: - a2mp_command_rej(mgr, skb, hdr); - break; - - case A2MP_DISCOVER_REQ: - err = a2mp_discover_req(mgr, skb, hdr); - break; - - case A2MP_CHANGE_NOTIFY: - err = a2mp_change_notify(mgr, skb, hdr); - break; - - case A2MP_GETINFO_REQ: - err = a2mp_getinfo_req(mgr, skb, hdr); - break; - - case A2MP_GETAMPASSOC_REQ: - err = a2mp_getampassoc_req(mgr, skb, hdr); - break; - - case A2MP_CREATEPHYSLINK_REQ: - err = a2mp_createphyslink_req(mgr, skb, hdr); - break; - - case A2MP_DISCONNPHYSLINK_REQ: - err = a2mp_discphyslink_req(mgr, skb, hdr); - break; - - case A2MP_DISCOVER_RSP: - err = a2mp_discover_rsp(mgr, skb, hdr); - break; - - case A2MP_GETINFO_RSP: - err = a2mp_getinfo_rsp(mgr, skb, hdr); - break; - - case A2MP_GETAMPASSOC_RSP: - err = a2mp_getampassoc_rsp(mgr, skb, hdr); - break; - - case A2MP_CHANGE_RSP: - case A2MP_CREATEPHYSLINK_RSP: - case A2MP_DISCONNPHYSLINK_RSP: - err = a2mp_cmd_rsp(mgr, skb, hdr); - break; - - default: - BT_ERR("Unknown A2MP sig cmd 0x%2.2x", hdr->code); - err = -EINVAL; - break; - } - } - - if (err) { - struct a2mp_cmd_rej rej; - - memset(&rej, 0, sizeof(rej)); - - rej.reason = cpu_to_le16(0); - hdr = (void *) skb->data; - - BT_DBG("Send A2MP Rej: cmd 0x%2.2x err %d", hdr->code, err); - - a2mp_send(mgr, A2MP_COMMAND_REJ, hdr->ident, sizeof(rej), - &rej); - } - - /* Always free skb and return success error code to prevent - from sending L2CAP Disconnect over A2MP channel */ - kfree_skb(skb); - - amp_mgr_put(mgr); - - return 0; -} - -static void a2mp_chan_close_cb(struct l2cap_chan *chan) -{ - l2cap_chan_put(chan); -} - -static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state, - int err) -{ - struct amp_mgr *mgr = chan->data; - - if (!mgr) - return; - - BT_DBG("chan %p state %s", chan, state_to_string(state)); - - chan->state = state; - - switch (state) { - case BT_CLOSED: - if (mgr) - amp_mgr_put(mgr); - break; - } -} - -static struct sk_buff *a2mp_chan_alloc_skb_cb(struct l2cap_chan *chan, - unsigned long hdr_len, - unsigned long len, int nb) -{ - struct sk_buff *skb; - - skb = bt_skb_alloc(hdr_len + len, GFP_KERNEL); - if (!skb) - return ERR_PTR(-ENOMEM); - - return skb; -} - -static const struct l2cap_ops a2mp_chan_ops = { - .name = "L2CAP A2MP channel", - .recv = a2mp_chan_recv_cb, - .close = a2mp_chan_close_cb, - .state_change = a2mp_chan_state_change_cb, - .alloc_skb = a2mp_chan_alloc_skb_cb, - - /* Not implemented for A2MP */ - .new_connection = l2cap_chan_no_new_connection, - .teardown = l2cap_chan_no_teardown, - .ready = l2cap_chan_no_ready, - .defer = l2cap_chan_no_defer, - .resume = l2cap_chan_no_resume, - .set_shutdown = l2cap_chan_no_set_shutdown, - .get_sndtimeo = l2cap_chan_no_get_sndtimeo, -}; - -static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) -{ - struct l2cap_chan *chan; - int err; - - chan = l2cap_chan_create(); - if (!chan) - return NULL; - - BT_DBG("chan %p", chan); - - chan->chan_type = L2CAP_CHAN_FIXED; - chan->scid = L2CAP_CID_A2MP; - chan->dcid = L2CAP_CID_A2MP; - chan->omtu = L2CAP_A2MP_DEFAULT_MTU; - chan->imtu = L2CAP_A2MP_DEFAULT_MTU; - chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; - - chan->ops = &a2mp_chan_ops; - - l2cap_chan_set_defaults(chan); - chan->remote_max_tx = chan->max_tx; - chan->remote_tx_win = chan->tx_win; - - chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; - chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; - - skb_queue_head_init(&chan->tx_q); - - chan->mode = L2CAP_MODE_ERTM; - - err = l2cap_ertm_init(chan); - if (err < 0) { - l2cap_chan_del(chan, 0); - return NULL; - } - - chan->conf_state = 0; - - if (locked) - __l2cap_chan_add(conn, chan); - else - l2cap_chan_add(conn, chan); - - chan->remote_mps = chan->omtu; - chan->mps = chan->omtu; - - chan->state = BT_CONNECTED; - - return chan; -} - -/* AMP Manager functions */ -struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr) -{ - BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref)); - - kref_get(&mgr->kref); - - return mgr; -} - -static void amp_mgr_destroy(struct kref *kref) -{ - struct amp_mgr *mgr = container_of(kref, struct amp_mgr, kref); - - BT_DBG("mgr %p", mgr); - - mutex_lock(&_mgr_list_lock); - list_del(&mgr->list); - mutex_unlock(&_mgr_list_lock); - - amp_ctrl_list_flush(mgr); - kfree(mgr); -} - -int amp_mgr_put(struct amp_mgr *mgr) -{ - BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref)); - - return kref_put(&mgr->kref, &_mgr_destroy); -} - -static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn, bool locked) -{ - struct amp_mgr *mgr; - struct l2cap_chan *chan; - - mgr = kzalloc(sizeof(*mgr), GFP_KERNEL); - if (!mgr) - return NULL; - - BT_DBG("conn %p mgr %p", conn, mgr); - - mgr->l2cap_conn = conn; - - chan = a2mp_chan_open(conn, locked); - if (!chan) { - kfree(mgr); - return NULL; - } - - mgr->a2mp_chan = chan; - chan->data = mgr; - - conn->hcon->amp_mgr = mgr; - - kref_init(&mgr->kref); - - /* Remote AMP ctrl list initialization */ - INIT_LIST_HEAD(&mgr->amp_ctrls); - mutex_init(&mgr->amp_ctrls_lock); - - mutex_lock(&_mgr_list_lock); - list_add(&mgr->list, &_mgr_list); - mutex_unlock(&_mgr_list_lock); - - return mgr; -} - -struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb) -{ - struct amp_mgr *mgr; - - if (conn->hcon->type != ACL_LINK) - return NULL; - - mgr = amp_mgr_create(conn, false); - if (!mgr) { - BT_ERR("Could not create AMP manager"); - return NULL; - } - - BT_DBG("mgr: %p chan %p", mgr, mgr->a2mp_chan); - - return mgr->a2mp_chan; -} - -void a2mp_send_getinfo_rsp(struct hci_dev *hdev) -{ - struct amp_mgr *mgr; - struct a2mp_info_rsp rsp; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_INFO); - if (!mgr) - return; - - BT_DBG("%s mgr %p", hdev->name, mgr); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.id = hdev->id; - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - - if (hdev->amp_type != AMP_TYPE_BREDR) { - rsp.status = 0; - rsp.total_bw = cpu_to_le32(hdev->amp_total_bw); - rsp.max_bw = cpu_to_le32(hdev->amp_max_bw); - rsp.min_latency = cpu_to_le32(hdev->amp_min_latency); - rsp.pal_cap = cpu_to_le16(hdev->amp_pal_cap); - rsp.assoc_size = cpu_to_le16(hdev->amp_assoc_size); - } - - a2mp_send(mgr, A2MP_GETINFO_RSP, mgr->ident, sizeof(rsp), &rsp); - amp_mgr_put(mgr); -} - -void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct a2mp_amp_assoc_rsp *rsp; - size_t len; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); - if (!mgr) - return; - - BT_DBG("%s mgr %p", hdev->name, mgr); - - len = sizeof(struct a2mp_amp_assoc_rsp) + loc_assoc->len; - rsp = kzalloc(len, GFP_KERNEL); - if (!rsp) { - amp_mgr_put(mgr); - return; - } - - rsp->id = hdev->id; - - if (status) { - rsp->status = A2MP_STATUS_INVALID_CTRL_ID; - } else { - rsp->status = A2MP_STATUS_SUCCESS; - memcpy(rsp->amp_assoc, loc_assoc->data, loc_assoc->len); - } - - a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, mgr->ident, len, rsp); - amp_mgr_put(mgr); - kfree(rsp); -} - -void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct a2mp_physlink_req *req; - struct l2cap_chan *bredr_chan; - size_t len; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC_FINAL); - if (!mgr) - return; - - len = sizeof(*req) + loc_assoc->len; - - BT_DBG("%s mgr %p assoc_len %zu", hdev->name, mgr, len); - - req = kzalloc(len, GFP_KERNEL); - if (!req) { - amp_mgr_put(mgr); - return; - } - - bredr_chan = mgr->bredr_chan; - if (!bredr_chan) - goto clean; - - req->local_id = hdev->id; - req->remote_id = bredr_chan->remote_amp_id; - memcpy(req->amp_assoc, loc_assoc->data, loc_assoc->len); - - a2mp_send(mgr, A2MP_CREATEPHYSLINK_REQ, __next_ident(mgr), len, req); - -clean: - amp_mgr_put(mgr); - kfree(req); -} - -void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct a2mp_physlink_rsp rsp; - struct hci_conn *hs_hcon; - - mgr = amp_mgr_lookup_by_state(WRITE_REMOTE_AMP_ASSOC); - if (!mgr) - return; - - memset(&rsp, 0, sizeof(rsp)); - - hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT); - if (!hs_hcon) { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - } else { - rsp.remote_id = hs_hcon->remote_id; - rsp.status = A2MP_STATUS_SUCCESS; - } - - BT_DBG("%s mgr %p hs_hcon %p status %u", hdev->name, mgr, hs_hcon, - status); - - rsp.local_id = hdev->id; - a2mp_send(mgr, A2MP_CREATEPHYSLINK_RSP, mgr->ident, sizeof(rsp), &rsp); - amp_mgr_put(mgr); -} - -void a2mp_discover_amp(struct l2cap_chan *chan) -{ - struct l2cap_conn *conn = chan->conn; - struct amp_mgr *mgr = conn->hcon->amp_mgr; - struct a2mp_discov_req req; - - BT_DBG("chan %p conn %p mgr %p", chan, conn, mgr); - - if (!mgr) { - mgr = amp_mgr_create(conn, true); - if (!mgr) - return; - } - - mgr->bredr_chan = chan; - - memset(&req, 0, sizeof(req)); - - req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); - req.ext_feat = 0; - a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req); -} diff --git a/net/bluetooth/a2mp.h b/net/bluetooth/a2mp.h deleted file mode 100644 index 2fd253a61a2a1..0000000000000 --- a/net/bluetooth/a2mp.h +++ /dev/null @@ -1,154 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - Copyright (c) 2010,2011 Code Aurora Forum. All rights reserved. - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#ifndef __A2MP_H -#define __A2MP_H - -#include - -enum amp_mgr_state { - READ_LOC_AMP_INFO, - READ_LOC_AMP_ASSOC, - READ_LOC_AMP_ASSOC_FINAL, - WRITE_REMOTE_AMP_ASSOC, -}; - -struct amp_mgr { - struct list_head list; - struct l2cap_conn *l2cap_conn; - struct l2cap_chan *a2mp_chan; - struct l2cap_chan *bredr_chan; - struct kref kref; - __u8 ident; - __u8 handle; - unsigned long state; - unsigned long flags; - - struct list_head amp_ctrls; - struct mutex amp_ctrls_lock; -}; - -struct a2mp_cmd { - __u8 code; - __u8 ident; - __le16 len; - __u8 data[]; -} __packed; - -/* A2MP command codes */ -#define A2MP_COMMAND_REJ 0x01 -struct a2mp_cmd_rej { - __le16 reason; - __u8 data[]; -} __packed; - -#define A2MP_DISCOVER_REQ 0x02 -struct a2mp_discov_req { - __le16 mtu; - __le16 ext_feat; -} __packed; - -struct a2mp_cl { - __u8 id; - __u8 type; - __u8 status; -} __packed; - -#define A2MP_DISCOVER_RSP 0x03 -struct a2mp_discov_rsp { - __le16 mtu; - __le16 ext_feat; - struct a2mp_cl cl[]; -} __packed; - -#define A2MP_CHANGE_NOTIFY 0x04 -#define A2MP_CHANGE_RSP 0x05 - -#define A2MP_GETINFO_REQ 0x06 -struct a2mp_info_req { - __u8 id; -} __packed; - -#define A2MP_GETINFO_RSP 0x07 -struct a2mp_info_rsp { - __u8 id; - __u8 status; - __le32 total_bw; - __le32 max_bw; - __le32 min_latency; - __le16 pal_cap; - __le16 assoc_size; -} __packed; - -#define A2MP_GETAMPASSOC_REQ 0x08 -struct a2mp_amp_assoc_req { - __u8 id; -} __packed; - -#define A2MP_GETAMPASSOC_RSP 0x09 -struct a2mp_amp_assoc_rsp { - __u8 id; - __u8 status; - __u8 amp_assoc[]; -} __packed; - -#define A2MP_CREATEPHYSLINK_REQ 0x0A -#define A2MP_DISCONNPHYSLINK_REQ 0x0C -struct a2mp_physlink_req { - __u8 local_id; - __u8 remote_id; - __u8 amp_assoc[]; -} __packed; - -#define A2MP_CREATEPHYSLINK_RSP 0x0B -#define A2MP_DISCONNPHYSLINK_RSP 0x0D -struct a2mp_physlink_rsp { - __u8 local_id; - __u8 remote_id; - __u8 status; -} __packed; - -/* A2MP response status */ -#define A2MP_STATUS_SUCCESS 0x00 -#define A2MP_STATUS_INVALID_CTRL_ID 0x01 -#define A2MP_STATUS_UNABLE_START_LINK_CREATION 0x02 -#define A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS 0x02 -#define A2MP_STATUS_COLLISION_OCCURED 0x03 -#define A2MP_STATUS_DISCONN_REQ_RECVD 0x04 -#define A2MP_STATUS_PHYS_LINK_EXISTS 0x05 -#define A2MP_STATUS_SECURITY_VIOLATION 0x06 - -struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr); - -#if IS_ENABLED(CONFIG_BT_HS) -int amp_mgr_put(struct amp_mgr *mgr); -struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb); -void a2mp_discover_amp(struct l2cap_chan *chan); -#else -static inline int amp_mgr_put(struct amp_mgr *mgr) -{ - return 0; -} - -static inline struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb) -{ - return NULL; -} - -static inline void a2mp_discover_amp(struct l2cap_chan *chan) -{ -} -#endif - -void a2mp_send_getinfo_rsp(struct hci_dev *hdev); -void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status); -void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status); -void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status); - -#endif /* __A2MP_H */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index b93464ac3517f..67604ccec2f42 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -309,14 +309,11 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & MSG_OOB) return -EOPNOTSUPP; - lock_sock(sk); - skb = skb_recv_datagram(sk, flags, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; - release_sock(sk); return err; } @@ -346,8 +343,6 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - release_sock(sk); - if (flags & MSG_TRUNC) copied = skblen; @@ -570,10 +565,11 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (sk->sk_state == BT_LISTEN) return -EINVAL; - lock_sock(sk); + spin_lock(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; - release_sock(sk); + spin_unlock(&sk->sk_receive_queue.lock); + err = put_user(amount, (int __user *)arg); break; diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c deleted file mode 100644 index 5d698f19868c5..0000000000000 --- a/net/bluetooth/amp.c +++ /dev/null @@ -1,590 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#include -#include -#include -#include - -#include "hci_request.h" -#include "a2mp.h" -#include "amp.h" - -/* Remote AMP Controllers interface */ -void amp_ctrl_get(struct amp_ctrl *ctrl) -{ - BT_DBG("ctrl %p orig refcnt %d", ctrl, - kref_read(&ctrl->kref)); - - kref_get(&ctrl->kref); -} - -static void amp_ctrl_destroy(struct kref *kref) -{ - struct amp_ctrl *ctrl = container_of(kref, struct amp_ctrl, kref); - - BT_DBG("ctrl %p", ctrl); - - kfree(ctrl->assoc); - kfree(ctrl); -} - -int amp_ctrl_put(struct amp_ctrl *ctrl) -{ - BT_DBG("ctrl %p orig refcnt %d", ctrl, - kref_read(&ctrl->kref)); - - return kref_put(&ctrl->kref, &_ctrl_destroy); -} - -struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id) -{ - struct amp_ctrl *ctrl; - - ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); - if (!ctrl) - return NULL; - - kref_init(&ctrl->kref); - ctrl->id = id; - - mutex_lock(&mgr->amp_ctrls_lock); - list_add(&ctrl->list, &mgr->amp_ctrls); - mutex_unlock(&mgr->amp_ctrls_lock); - - BT_DBG("mgr %p ctrl %p", mgr, ctrl); - - return ctrl; -} - -void amp_ctrl_list_flush(struct amp_mgr *mgr) -{ - struct amp_ctrl *ctrl, *n; - - BT_DBG("mgr %p", mgr); - - mutex_lock(&mgr->amp_ctrls_lock); - list_for_each_entry_safe(ctrl, n, &mgr->amp_ctrls, list) { - list_del(&ctrl->list); - amp_ctrl_put(ctrl); - } - mutex_unlock(&mgr->amp_ctrls_lock); -} - -struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id) -{ - struct amp_ctrl *ctrl; - - BT_DBG("mgr %p id %u", mgr, id); - - mutex_lock(&mgr->amp_ctrls_lock); - list_for_each_entry(ctrl, &mgr->amp_ctrls, list) { - if (ctrl->id == id) { - amp_ctrl_get(ctrl); - mutex_unlock(&mgr->amp_ctrls_lock); - return ctrl; - } - } - mutex_unlock(&mgr->amp_ctrls_lock); - - return NULL; -} - -/* Physical Link interface */ -static u8 __next_handle(struct amp_mgr *mgr) -{ - if (++mgr->handle == 0) - mgr->handle = 1; - - return mgr->handle; -} - -struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, - u8 remote_id, bool out) -{ - bdaddr_t *dst = &mgr->l2cap_conn->hcon->dst; - struct hci_conn *hcon; - u8 role = out ? HCI_ROLE_MASTER : HCI_ROLE_SLAVE; - - hcon = hci_conn_add(hdev, AMP_LINK, dst, role, __next_handle(mgr)); - if (!hcon) - return NULL; - - BT_DBG("hcon %p dst %pMR", hcon, dst); - - hcon->state = BT_CONNECT; - hcon->attempt++; - hcon->remote_id = remote_id; - hcon->amp_mgr = amp_mgr_get(mgr); - - return hcon; -} - -/* AMP crypto key generation interface */ -static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output) -{ - struct crypto_shash *tfm; - struct shash_desc *shash; - int ret; - - if (!ksize) - return -EINVAL; - - tfm = crypto_alloc_shash("hmac(sha256)", 0, 0); - if (IS_ERR(tfm)) { - BT_DBG("crypto_alloc_ahash failed: err %ld", PTR_ERR(tfm)); - return PTR_ERR(tfm); - } - - ret = crypto_shash_setkey(tfm, key, ksize); - if (ret) { - BT_DBG("crypto_ahash_setkey failed: err %d", ret); - goto failed; - } - - shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(tfm), - GFP_KERNEL); - if (!shash) { - ret = -ENOMEM; - goto failed; - } - - shash->tfm = tfm; - - ret = crypto_shash_digest(shash, plaintext, psize, output); - - kfree(shash); - -failed: - crypto_free_shash(tfm); - return ret; -} - -int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) -{ - struct hci_dev *hdev = conn->hdev; - struct link_key *key; - u8 keybuf[HCI_AMP_LINK_KEY_SIZE]; - u8 gamp_key[HCI_AMP_LINK_KEY_SIZE]; - int err; - - if (!hci_conn_check_link_mode(conn)) - return -EACCES; - - BT_DBG("conn %p key_type %d", conn, conn->key_type); - - /* Legacy key */ - if (conn->key_type < 3) { - bt_dev_err(hdev, "legacy key type %u", conn->key_type); - return -EACCES; - } - - *type = conn->key_type; - *len = HCI_AMP_LINK_KEY_SIZE; - - key = hci_find_link_key(hdev, &conn->dst); - if (!key) { - BT_DBG("No Link key for conn %p dst %pMR", conn, &conn->dst); - return -EACCES; - } - - /* BR/EDR Link Key concatenated together with itself */ - memcpy(&keybuf[0], key->val, HCI_LINK_KEY_SIZE); - memcpy(&keybuf[HCI_LINK_KEY_SIZE], key->val, HCI_LINK_KEY_SIZE); - - /* Derive Generic AMP Link Key (gamp) */ - err = hmac_sha256(keybuf, HCI_AMP_LINK_KEY_SIZE, "gamp", 4, gamp_key); - if (err) { - bt_dev_err(hdev, "could not derive Generic AMP Key: err %d", err); - return err; - } - - if (conn->key_type == HCI_LK_DEBUG_COMBINATION) { - BT_DBG("Use Generic AMP Key (gamp)"); - memcpy(data, gamp_key, HCI_AMP_LINK_KEY_SIZE); - return err; - } - - /* Derive Dedicated AMP Link Key: "802b" is 802.11 PAL keyID */ - return hmac_sha256(gamp_key, HCI_AMP_LINK_KEY_SIZE, "802b", 4, data); -} - -static void read_local_amp_assoc_complete(struct hci_dev *hdev, u8 status, - u16 opcode, struct sk_buff *skb) -{ - struct hci_rp_read_local_amp_assoc *rp = (void *)skb->data; - struct amp_assoc *assoc = &hdev->loc_assoc; - size_t rem_len, frag_len; - - BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - - if (rp->status) - goto send_rsp; - - frag_len = skb->len - sizeof(*rp); - rem_len = __le16_to_cpu(rp->rem_len); - - if (rem_len > frag_len) { - BT_DBG("frag_len %zu rem_len %zu", frag_len, rem_len); - - memcpy(assoc->data + assoc->offset, rp->frag, frag_len); - assoc->offset += frag_len; - - /* Read other fragments */ - amp_read_loc_assoc_frag(hdev, rp->phy_handle); - - return; - } - - memcpy(assoc->data + assoc->offset, rp->frag, rem_len); - assoc->len = assoc->offset + rem_len; - assoc->offset = 0; - -send_rsp: - /* Send A2MP Rsp when all fragments are received */ - a2mp_send_getampassoc_rsp(hdev, rp->status); - a2mp_send_create_phy_link_req(hdev, rp->status); -} - -void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) -{ - struct hci_cp_read_local_amp_assoc cp; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct hci_request req; - int err; - - BT_DBG("%s handle %u", hdev->name, phy_handle); - - cp.phy_handle = phy_handle; - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - cp.len_so_far = cpu_to_le16(loc_assoc->offset); - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr) -{ - struct hci_cp_read_local_amp_assoc cp; - struct hci_request req; - int err; - - memset(&hdev->loc_assoc, 0, sizeof(struct amp_assoc)); - memset(&cp, 0, sizeof(cp)); - - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - - set_bit(READ_LOC_AMP_ASSOC, &mgr->state); - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -void amp_read_loc_assoc_final_data(struct hci_dev *hdev, - struct hci_conn *hcon) -{ - struct hci_cp_read_local_amp_assoc cp; - struct amp_mgr *mgr = hcon->amp_mgr; - struct hci_request req; - int err; - - if (!mgr) - return; - - cp.phy_handle = hcon->handle; - cp.len_so_far = cpu_to_le16(0); - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - - set_bit(READ_LOC_AMP_ASSOC_FINAL, &mgr->state); - - /* Read Local AMP Assoc final link information data */ - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -static void write_remote_amp_assoc_complete(struct hci_dev *hdev, u8 status, - u16 opcode, struct sk_buff *skb) -{ - struct hci_rp_write_remote_amp_assoc *rp = (void *)skb->data; - - BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x", - hdev->name, rp->status, rp->phy_handle); - - if (rp->status) - return; - - amp_write_rem_assoc_continue(hdev, rp->phy_handle); -} - -/* Write AMP Assoc data fragments, returns true with last fragment written*/ -static bool amp_write_rem_assoc_frag(struct hci_dev *hdev, - struct hci_conn *hcon) -{ - struct hci_cp_write_remote_amp_assoc *cp; - struct amp_mgr *mgr = hcon->amp_mgr; - struct amp_ctrl *ctrl; - struct hci_request req; - u16 frag_len, len; - - ctrl = amp_ctrl_lookup(mgr, hcon->remote_id); - if (!ctrl) - return false; - - if (!ctrl->assoc_rem_len) { - BT_DBG("all fragments are written"); - ctrl->assoc_rem_len = ctrl->assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - return true; - } - - frag_len = min_t(u16, 248, ctrl->assoc_rem_len); - len = frag_len + sizeof(*cp); - - cp = kzalloc(len, GFP_KERNEL); - if (!cp) { - amp_ctrl_put(ctrl); - return false; - } - - BT_DBG("hcon %p ctrl %p frag_len %u assoc_len %u rem_len %u", - hcon, ctrl, frag_len, ctrl->assoc_len, ctrl->assoc_rem_len); - - cp->phy_handle = hcon->handle; - cp->len_so_far = cpu_to_le16(ctrl->assoc_len_so_far); - cp->rem_len = cpu_to_le16(ctrl->assoc_rem_len); - memcpy(cp->frag, ctrl->assoc, frag_len); - - ctrl->assoc_len_so_far += frag_len; - ctrl->assoc_rem_len -= frag_len; - - amp_ctrl_put(ctrl); - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_WRITE_REMOTE_AMP_ASSOC, len, cp); - hci_req_run_skb(&req, write_remote_amp_assoc_complete); - - kfree(cp); - - return false; -} - -void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle) -{ - struct hci_conn *hcon; - - BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle); - - hcon = hci_conn_hash_lookup_handle(hdev, handle); - if (!hcon) - return; - - /* Send A2MP create phylink rsp when all fragments are written */ - if (amp_write_rem_assoc_frag(hdev, hcon)) - a2mp_send_create_phy_link_rsp(hdev, 0); -} - -void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle) -{ - struct hci_conn *hcon; - - BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle); - - hcon = hci_conn_hash_lookup_handle(hdev, handle); - if (!hcon) - return; - - BT_DBG("%s phy handle 0x%2.2x hcon %p", hdev->name, handle, hcon); - - amp_write_rem_assoc_frag(hdev, hcon); -} - -static void create_phylink_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - struct hci_cp_create_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK); - if (!cp) - return; - - hci_dev_lock(hdev); - - if (status) { - struct hci_conn *hcon; - - hcon = hci_conn_hash_lookup_handle(hdev, cp->phy_handle); - if (hcon) - hci_conn_del(hcon); - } else { - amp_write_remote_assoc(hdev, cp->phy_handle); - } - - hci_dev_unlock(hdev); -} - -void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon) -{ - struct hci_cp_create_phy_link cp; - struct hci_request req; - - cp.phy_handle = hcon->handle; - - BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon, - hcon->handle); - - if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len, - &cp.key_type)) { - BT_DBG("Cannot create link key"); - return; - } - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp); - hci_req_run(&req, create_phylink_complete); -} - -static void accept_phylink_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - struct hci_cp_accept_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - if (status) - return; - - cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK); - if (!cp) - return; - - amp_write_remote_assoc(hdev, cp->phy_handle); -} - -void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon) -{ - struct hci_cp_accept_phy_link cp; - struct hci_request req; - - cp.phy_handle = hcon->handle; - - BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon, - hcon->handle); - - if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len, - &cp.key_type)) { - BT_DBG("Cannot create link key"); - return; - } - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp); - hci_req_run(&req, accept_phylink_complete); -} - -void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon) -{ - struct hci_dev *bredr_hdev = hci_dev_hold(bredr_hcon->hdev); - struct amp_mgr *mgr = hs_hcon->amp_mgr; - struct l2cap_chan *bredr_chan; - - BT_DBG("bredr_hcon %p hs_hcon %p mgr %p", bredr_hcon, hs_hcon, mgr); - - if (!bredr_hdev || !mgr || !mgr->bredr_chan) - return; - - bredr_chan = mgr->bredr_chan; - - l2cap_chan_lock(bredr_chan); - - set_bit(FLAG_EFS_ENABLE, &bredr_chan->flags); - bredr_chan->remote_amp_id = hs_hcon->remote_id; - bredr_chan->local_amp_id = hs_hcon->hdev->id; - bredr_chan->hs_hcon = hs_hcon; - bredr_chan->conn->mtu = hs_hcon->hdev->block_mtu; - - __l2cap_physical_cfm(bredr_chan, 0); - - l2cap_chan_unlock(bredr_chan); - - hci_dev_put(bredr_hdev); -} - -void amp_create_logical_link(struct l2cap_chan *chan) -{ - struct hci_conn *hs_hcon = chan->hs_hcon; - struct hci_cp_create_accept_logical_link cp; - struct hci_dev *hdev; - - BT_DBG("chan %p hs_hcon %p dst %pMR", chan, hs_hcon, - &chan->conn->hcon->dst); - - if (!hs_hcon) - return; - - hdev = hci_dev_hold(chan->hs_hcon->hdev); - if (!hdev) - return; - - cp.phy_handle = hs_hcon->handle; - - cp.tx_flow_spec.id = chan->local_id; - cp.tx_flow_spec.stype = chan->local_stype; - cp.tx_flow_spec.msdu = cpu_to_le16(chan->local_msdu); - cp.tx_flow_spec.sdu_itime = cpu_to_le32(chan->local_sdu_itime); - cp.tx_flow_spec.acc_lat = cpu_to_le32(chan->local_acc_lat); - cp.tx_flow_spec.flush_to = cpu_to_le32(chan->local_flush_to); - - cp.rx_flow_spec.id = chan->remote_id; - cp.rx_flow_spec.stype = chan->remote_stype; - cp.rx_flow_spec.msdu = cpu_to_le16(chan->remote_msdu); - cp.rx_flow_spec.sdu_itime = cpu_to_le32(chan->remote_sdu_itime); - cp.rx_flow_spec.acc_lat = cpu_to_le32(chan->remote_acc_lat); - cp.rx_flow_spec.flush_to = cpu_to_le32(chan->remote_flush_to); - - if (hs_hcon->out) - hci_send_cmd(hdev, HCI_OP_CREATE_LOGICAL_LINK, sizeof(cp), - &cp); - else - hci_send_cmd(hdev, HCI_OP_ACCEPT_LOGICAL_LINK, sizeof(cp), - &cp); - - hci_dev_put(hdev); -} - -void amp_disconnect_logical_link(struct hci_chan *hchan) -{ - struct hci_conn *hcon = hchan->conn; - struct hci_cp_disconn_logical_link cp; - - if (hcon->state != BT_CONNECTED) { - BT_DBG("hchan %p not connected", hchan); - return; - } - - cp.log_handle = cpu_to_le16(hchan->handle); - hci_send_cmd(hcon->hdev, HCI_OP_DISCONN_LOGICAL_LINK, sizeof(cp), &cp); -} - -void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason) -{ - BT_DBG("hchan %p", hchan); - - hci_chan_del(hchan); -} diff --git a/net/bluetooth/amp.h b/net/bluetooth/amp.h deleted file mode 100644 index 97c87abd129f6..0000000000000 --- a/net/bluetooth/amp.h +++ /dev/null @@ -1,60 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#ifndef __AMP_H -#define __AMP_H - -struct amp_ctrl { - struct list_head list; - struct kref kref; - __u8 id; - __u16 assoc_len_so_far; - __u16 assoc_rem_len; - __u16 assoc_len; - __u8 *assoc; -}; - -int amp_ctrl_put(struct amp_ctrl *ctrl); -void amp_ctrl_get(struct amp_ctrl *ctrl); -struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id); -struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id); -void amp_ctrl_list_flush(struct amp_mgr *mgr); - -struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, - u8 remote_id, bool out); - -int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type); - -void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle); -void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr); -void amp_read_loc_assoc_final_data(struct hci_dev *hdev, - struct hci_conn *hcon); -void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon); -void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon); - -#if IS_ENABLED(CONFIG_BT_HS) -void amp_create_logical_link(struct l2cap_chan *chan); -void amp_disconnect_logical_link(struct hci_chan *hchan); -#else -static inline void amp_create_logical_link(struct l2cap_chan *chan) -{ -} - -static inline void amp_disconnect_logical_link(struct hci_chan *hchan) -{ -} -#endif - -void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle); -void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle); -void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon); -void amp_create_logical_link(struct l2cap_chan *chan); -void amp_disconnect_logical_link(struct hci_chan *hchan); -void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason); - -#endif /* __AMP_H */ diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c index 9214189279e80..1bc51e2b05a34 100644 --- a/net/bluetooth/eir.c +++ b/net/bluetooth/eir.c @@ -13,48 +13,33 @@ #define PNP_INFO_SVCLASS_ID 0x1200 -static u8 eir_append_name(u8 *eir, u16 eir_len, u8 type, u8 *data, u8 data_len) -{ - u8 name[HCI_MAX_SHORT_NAME_LENGTH + 1]; - - /* If data is already NULL terminated just pass it directly */ - if (data[data_len - 1] == '\0') - return eir_append_data(eir, eir_len, type, data, data_len); - - memcpy(name, data, HCI_MAX_SHORT_NAME_LENGTH); - name[HCI_MAX_SHORT_NAME_LENGTH] = '\0'; - - return eir_append_data(eir, eir_len, type, name, sizeof(name)); -} - u8 eir_append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len) { size_t short_len; size_t complete_len; - /* no space left for name (+ NULL + type + len) */ - if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3) + /* no space left for name (+ type + len) */ + if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 2) return ad_len; /* use complete name if present and fits */ complete_len = strnlen(hdev->dev_name, sizeof(hdev->dev_name)); if (complete_len && complete_len <= HCI_MAX_SHORT_NAME_LENGTH) - return eir_append_name(ptr, ad_len, EIR_NAME_COMPLETE, - hdev->dev_name, complete_len + 1); + return eir_append_data(ptr, ad_len, EIR_NAME_COMPLETE, + hdev->dev_name, complete_len); /* use short name if present */ short_len = strnlen(hdev->short_name, sizeof(hdev->short_name)); if (short_len) - return eir_append_name(ptr, ad_len, EIR_NAME_SHORT, + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, hdev->short_name, - short_len == HCI_MAX_SHORT_NAME_LENGTH ? - short_len : short_len + 1); + short_len); /* use shortened full name if present, we already know that name * is longer then HCI_MAX_SHORT_NAME_LENGTH */ if (complete_len) - return eir_append_name(ptr, ad_len, EIR_NAME_SHORT, + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, hdev->dev_name, HCI_MAX_SHORT_NAME_LENGTH); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index a41d2693f4d8c..7f78fc6c29cf5 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1,7 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. - Copyright 2023 NXP + Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky @@ -36,7 +36,6 @@ #include "hci_request.h" #include "smp.h" -#include "a2mp.h" #include "eir.h" struct sco_param { @@ -69,7 +68,7 @@ static const struct sco_param esco_param_msbc[] = { }; /* This function requires the caller holds hdev->lock */ -static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) +void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; @@ -179,64 +178,6 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_dev_put(hdev); } -static void hci_acl_create_connection(struct hci_conn *conn) -{ - struct hci_dev *hdev = conn->hdev; - struct inquiry_entry *ie; - struct hci_cp_create_conn cp; - - BT_DBG("hcon %p", conn); - - /* Many controllers disallow HCI Create Connection while it is doing - * HCI Inquiry. So we cancel the Inquiry first before issuing HCI Create - * Connection. This may cause the MGMT discovering state to become false - * without user space's request but it is okay since the MGMT Discovery - * APIs do not promise that discovery should be done forever. Instead, - * the user space monitors the status of MGMT discovering and it may - * request for discovery again when this flag becomes false. - */ - if (test_bit(HCI_INQUIRY, &hdev->flags)) { - /* Put this connection to "pending" state so that it will be - * executed after the inquiry cancel command complete event. - */ - conn->state = BT_CONNECT2; - hci_send_cmd(hdev, HCI_OP_INQUIRY_CANCEL, 0, NULL); - return; - } - - conn->state = BT_CONNECT; - conn->out = true; - conn->role = HCI_ROLE_MASTER; - - conn->attempt++; - - conn->link_policy = hdev->link_policy; - - memset(&cp, 0, sizeof(cp)); - bacpy(&cp.bdaddr, &conn->dst); - cp.pscan_rep_mode = 0x02; - - ie = hci_inquiry_cache_lookup(hdev, &conn->dst); - if (ie) { - if (inquiry_entry_age(ie) <= INQUIRY_ENTRY_AGE_MAX) { - cp.pscan_rep_mode = ie->data.pscan_rep_mode; - cp.pscan_mode = ie->data.pscan_mode; - cp.clock_offset = ie->data.clock_offset | - cpu_to_le16(0x8000); - } - - memcpy(conn->dev_class, ie->data.dev_class, 3); - } - - cp.pkt_type = cpu_to_le16(conn->pkt_type); - if (lmp_rswitch_capable(hdev) && !(hdev->link_mode & HCI_LM_MASTER)) - cp.role_switch = 0x01; - else - cp.role_switch = 0x00; - - hci_send_cmd(hdev, HCI_OP_CREATE_CONN, sizeof(cp), &cp); -} - int hci_disconnect(struct hci_conn *conn, __u8 reason) { BT_DBG("hcon %p", conn); @@ -968,11 +909,37 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, { struct hci_conn *conn; + switch (type) { + case ACL_LINK: + if (!hdev->acl_mtu) + return ERR_PTR(-ECONNREFUSED); + break; + case ISO_LINK: + if (hdev->iso_mtu) + /* Dedicated ISO Buffer exists */ + break; + fallthrough; + case LE_LINK: + if (hdev->le_mtu && hdev->le_mtu < HCI_MIN_LE_MTU) + return ERR_PTR(-ECONNREFUSED); + if (!hdev->le_mtu && hdev->acl_mtu < HCI_MIN_LE_MTU) + return ERR_PTR(-ECONNREFUSED); + break; + case SCO_LINK: + case ESCO_LINK: + if (!hdev->sco_pkts) + /* Controller does not support SCO or eSCO over HCI */ + return ERR_PTR(-ECONNREFUSED); + break; + default: + return ERR_PTR(-ECONNREFUSED); + } + bt_dev_dbg(hdev, "dst %pMR handle 0x%4.4x", dst, handle); conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) - return NULL; + return ERR_PTR(-ENOMEM); bacpy(&conn->dst, dst); bacpy(&conn->src, &hdev->bdaddr); @@ -1003,10 +970,12 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, switch (type) { case ACL_LINK: conn->pkt_type = hdev->pkt_type & ACL_PTYPE_MASK; + conn->mtu = hdev->acl_mtu; break; case LE_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type); + conn->mtu = hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; break; case ISO_LINK: /* conn->src should reflect the local identity address */ @@ -1018,6 +987,8 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, else if (conn->role == HCI_ROLE_MASTER) conn->cleanup = cis_cleanup; + conn->mtu = hdev->iso_mtu ? hdev->iso_mtu : + hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; break; case SCO_LINK: if (lmp_esco_capable(hdev)) @@ -1025,9 +996,12 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, (hdev->esco_type & EDR_ESCO_MASK); else conn->pkt_type = hdev->pkt_type & SCO_PTYPE_MASK; + + conn->mtu = hdev->sco_mtu; break; case ESCO_LINK: conn->pkt_type = hdev->esco_type & ~EDR_ESCO_MASK; + conn->mtu = hdev->sco_mtu; break; } @@ -1070,7 +1044,7 @@ struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, handle = hci_conn_hash_alloc_unset(hdev); if (unlikely(handle < 0)) - return NULL; + return ERR_PTR(-ECONNREFUSED); return hci_conn_add(hdev, type, dst, role, handle); } @@ -1175,9 +1149,6 @@ void hci_conn_del(struct hci_conn *conn) } } - if (conn->amp_mgr) - amp_mgr_put(conn->amp_mgr); - skb_queue_purge(&conn->data_q); /* Remove the connection from the list and cleanup its remaining @@ -1186,6 +1157,9 @@ void hci_conn_del(struct hci_conn *conn) * rest of hci_conn_del. */ hci_conn_cleanup(conn); + + /* Dequeue callbacks using connection pointer as data */ + hci_cmd_sync_dequeue(hdev, NULL, conn, NULL); } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) @@ -1199,8 +1173,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) list_for_each_entry(d, &hci_dev_list, list) { if (!test_bit(HCI_UP, &d->flags) || - hci_dev_test_flag(d, HCI_USER_CHANNEL) || - d->dev_type != HCI_PRIMARY) + hci_dev_test_flag(d, HCI_USER_CHANNEL)) continue; /* Simple routing: @@ -1320,56 +1293,9 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) return 0; } -static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) -{ - struct hci_conn *conn; - u16 handle = PTR_UINT(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return; - - bt_dev_dbg(hdev, "err %d", err); - - hci_dev_lock(hdev); - - if (!err) { - hci_connect_le_scan_cleanup(conn, 0x00); - goto done; - } - - /* Check if connection is still pending */ - if (conn != hci_lookup_le_connect(hdev)) - goto done; - - /* Flush to make sure we send create conn cancel command if needed */ - flush_delayed_work(&conn->le_conn_timeout); - hci_conn_failed(conn, bt_status(err)); - -done: - hci_dev_unlock(hdev); -} - -static int hci_connect_le_sync(struct hci_dev *hdev, void *data) -{ - struct hci_conn *conn; - u16 handle = PTR_UINT(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; - - bt_dev_dbg(hdev, "conn %p", conn); - - clear_bit(HCI_CONN_SCANNING, &conn->flags); - conn->state = BT_CONNECT; - - return hci_le_create_conn_sync(hdev, conn); -} - struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, - u16 conn_timeout, u8 role) + u16 conn_timeout, u8 role, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct smp_irk *irk; @@ -1423,8 +1349,8 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, bacpy(&conn->dst, dst); } else { conn = hci_conn_add_unset(hdev, LE_LINK, dst, role); - if (!conn) - return ERR_PTR(-ENOMEM); + if (IS_ERR(conn)) + return conn; hci_conn_hold(conn); conn->pending_sec_level = sec_level; } @@ -1432,10 +1358,10 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, conn->dst_type = dst_type; conn->sec_level = BT_SECURITY_LOW; conn->conn_timeout = conn_timeout; + conn->le_adv_phy = phy; + conn->le_adv_sec_phy = sec_phy; - err = hci_cmd_sync_queue(hdev, hci_connect_le_sync, - UINT_PTR(conn->handle), - create_le_conn_complete); + err = hci_connect_le_sync(hdev, conn); if (err) { hci_conn_del(conn); return ERR_PTR(err); @@ -1600,8 +1526,8 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-EADDRINUSE); conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); - if (!conn) - return ERR_PTR(-ENOMEM); + if (IS_ERR(conn)) + return conn; conn->state = BT_CONNECT; @@ -1644,8 +1570,8 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, BT_DBG("requesting refresh of dst_addr"); conn = hci_conn_add_unset(hdev, LE_LINK, dst, HCI_ROLE_MASTER); - if (!conn) - return ERR_PTR(-ENOMEM); + if (IS_ERR(conn)) + return conn; if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) { hci_conn_del(conn); @@ -1669,7 +1595,7 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, - enum conn_reasons conn_reason) + enum conn_reasons conn_reason, u16 timeout) { struct hci_conn *acl; @@ -1692,18 +1618,26 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { acl = hci_conn_add_unset(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); - if (!acl) - return ERR_PTR(-ENOMEM); + if (IS_ERR(acl)) + return acl; } hci_conn_hold(acl); acl->conn_reason = conn_reason; if (acl->state == BT_OPEN || acl->state == BT_CLOSED) { + int err; + acl->sec_level = BT_SECURITY_LOW; acl->pending_sec_level = sec_level; acl->auth_type = auth_type; - hci_acl_create_connection(acl); + acl->conn_timeout = timeout; + + err = hci_connect_acl_sync(hdev, acl); + if (err) { + hci_conn_del(acl); + return ERR_PTR(err); + } } return acl; @@ -1738,23 +1672,24 @@ static struct hci_link *hci_conn_link(struct hci_conn *parent, } struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u16 setting, struct bt_codec *codec) + __u16 setting, struct bt_codec *codec, + u16 timeout) { struct hci_conn *acl; struct hci_conn *sco; struct hci_link *link; acl = hci_connect_acl(hdev, dst, BT_SECURITY_LOW, HCI_AT_NO_BONDING, - CONN_REASON_SCO_CONNECT); + CONN_REASON_SCO_CONNECT, timeout); if (IS_ERR(acl)) return acl; sco = hci_conn_hash_lookup_ba(hdev, type, dst); if (!sco) { sco = hci_conn_add_unset(hdev, type, dst, HCI_ROLE_MASTER); - if (!sco) { + if (IS_ERR(sco)) { hci_conn_drop(acl); - return ERR_PTR(-ENOMEM); + return sco; } } @@ -1944,8 +1879,8 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, qos->ucast.cis); if (!cis) { cis = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); - if (!cis) - return ERR_PTR(-ENOMEM); + if (IS_ERR(cis)) + return cis; cis->cleanup = cis_cleanup; cis->dst_type = dst_type; cis->iso_qos.ucast.cig = BT_ISO_QOS_CIG_UNSET; @@ -2080,14 +2015,8 @@ static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, struct bt_iso_io_qos *qos, __u8 phy) { /* Only set MTU if PHY is enabled */ - if (!qos->sdu && qos->phy) { - if (hdev->iso_mtu > 0) - qos->sdu = hdev->iso_mtu; - else if (hdev->le_mtu > 0) - qos->sdu = hdev->le_mtu; - else - qos->sdu = hdev->acl_mtu; - } + if (!qos->sdu && qos->phy) + qos->sdu = conn->mtu; /* Use the same PHY as ACL if set to any */ if (qos->phy == BT_ISO_PHY_ANY) @@ -2156,18 +2085,31 @@ static int create_pa_sync(struct hci_dev *hdev, void *data) return hci_update_passive_scan_sync(hdev); } -int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, - __u8 sid, struct bt_iso_qos *qos) +struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, + __u8 dst_type, __u8 sid, + struct bt_iso_qos *qos) { struct hci_cp_le_pa_create_sync *cp; + struct hci_conn *conn; + int err; if (hci_dev_test_and_set_flag(hdev, HCI_PA_SYNC)) - return -EBUSY; + return ERR_PTR(-EBUSY); + + conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_SLAVE); + if (!conn) + return ERR_PTR(-ENOMEM); + + conn->iso_qos = *qos; + conn->state = BT_LISTEN; + + hci_conn_hold(conn); cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) { hci_dev_clear_flag(hdev, HCI_PA_SYNC); - return -ENOMEM; + hci_conn_drop(conn); + return ERR_PTR(-ENOMEM); } cp->options = qos->bcast.options; @@ -2179,7 +2121,14 @@ int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, cp->sync_cte_type = qos->bcast.sync_cte_type; /* Queue start pa_create_sync and scan */ - return hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete); + err = hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete); + if (err < 0) { + hci_conn_drop(conn); + kfree(cp); + return ERR_PTR(err); + } + + return conn; } int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, @@ -2352,7 +2301,7 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, le = hci_connect_le(hdev, dst, dst_type, false, BT_SECURITY_LOW, HCI_LE_CONN_TIMEOUT, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, 0, 0); else le = hci_connect_le_scan(hdev, dst, dst_type, BT_SECURITY_LOW, @@ -2647,22 +2596,6 @@ void hci_conn_hash_flush(struct hci_dev *hdev) } } -/* Check pending connect attempts */ -void hci_conn_check_pending(struct hci_dev *hdev) -{ - struct hci_conn *conn; - - BT_DBG("hdev %s", hdev->name); - - hci_dev_lock(hdev); - - conn = hci_conn_hash_lookup_state(hdev, ACL_LINK, BT_CONNECT2); - if (conn) - hci_acl_create_connection(conn); - - hci_dev_unlock(hdev); -} - static u32 get_link_mode(struct hci_conn *conn) { u32 link_mode = 0; @@ -2978,12 +2911,10 @@ u32 hci_conn_get_phy(struct hci_conn *conn) static int abort_conn_sync(struct hci_dev *hdev, void *data) { - struct hci_conn *conn; - u16 handle = PTR_UINT(data); + struct hci_conn *conn = data; - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; return hci_abort_conn_sync(hdev, conn, conn->abort_reason); } @@ -3011,14 +2942,17 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) */ if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { switch (hci_skb_event(hdev->sent_cmd)) { + case HCI_EV_CONN_COMPLETE: case HCI_EV_LE_CONN_COMPLETE: case HCI_EV_LE_ENHANCED_CONN_COMPLETE: case HCI_EVT_LE_CIS_ESTABLISHED: - hci_cmd_sync_cancel(hdev, -ECANCELED); + hci_cmd_sync_cancel(hdev, ECANCELED); break; } + /* Cancel connect attempt if still queued/pending */ + } else if (!hci_cancel_connect_sync(hdev, conn)) { + return 0; } - return hci_cmd_sync_queue(hdev, abort_conn_sync, UINT_PTR(conn->handle), - NULL); + return hci_cmd_sync_queue_once(hdev, abort_conn_sync, conn, NULL); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2821a42cefdc6..e946ac46a1762 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -395,11 +395,6 @@ int hci_inquiry(void __user *arg) goto done; } - if (hdev->dev_type != HCI_PRIMARY) { - err = -EOPNOTSUPP; - goto done; - } - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; @@ -752,11 +747,6 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) goto done; } - if (hdev->dev_type != HCI_PRIMARY) { - err = -EOPNOTSUPP; - goto done; - } - if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; @@ -908,9 +898,9 @@ int hci_get_dev_info(void __user *arg) else flags = hdev->flags; - strcpy(di.name, hdev->name); + strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; - di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); + di.type = (hdev->bus & 0x0f); di.flags = flags; di.pkt_type = hdev->pkt_type; if (lmp_bredr_capable(hdev)) { @@ -995,8 +985,7 @@ static void hci_power_on(struct work_struct *work) */ if (hci_dev_test_flag(hdev, HCI_RFKILLED) || hci_dev_test_flag(hdev, HCI_UNCONFIGURED) || - (hdev->dev_type == HCI_PRIMARY && - !bacmp(&hdev->bdaddr, BDADDR_ANY) && + (!bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { hci_dev_clear_flag(hdev, HCI_AUTO_OFF); hci_dev_do_close(hdev); @@ -1491,11 +1480,12 @@ static void hci_cmd_timeout(struct work_struct *work) struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_timer.work); - if (hdev->sent_cmd) { - struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data; - u16 opcode = __le16_to_cpu(sent->opcode); + if (hdev->req_skb) { + u16 opcode = hci_skb_opcode(hdev->req_skb); bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode); + + hci_cmd_sync_cancel_sync(hdev, ETIMEDOUT); } else { bt_dev_err(hdev, "command tx timeout"); } @@ -1737,6 +1727,15 @@ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance, adv->pending = true; adv->instance = instance; + + /* If controller support only one set and the instance is set to + * 1 then there is no option other than using handle 0x00. + */ + if (hdev->le_num_of_adv_sets == 1 && instance == 1) + adv->handle = 0x00; + else + adv->handle = instance; + list_add(&adv->list, &hdev->adv_instances); hdev->adv_instance_cnt++; } @@ -2603,20 +2602,7 @@ int hci_register_dev(struct hci_dev *hdev) if (!hdev->open || !hdev->close || !hdev->send) return -EINVAL; - /* Do not allow HCI_AMP devices to register at index 0, - * so the index can be used as the AMP controller ID. - */ - switch (hdev->dev_type) { - case HCI_PRIMARY: - id = ida_simple_get(&hci_index_ida, 0, HCI_MAX_ID, GFP_KERNEL); - break; - case HCI_AMP: - id = ida_simple_get(&hci_index_ida, 1, HCI_MAX_ID, GFP_KERNEL); - break; - default: - return -EINVAL; - } - + id = ida_alloc_max(&hci_index_ida, HCI_MAX_ID - 1, GFP_KERNEL); if (id < 0) return id; @@ -2668,12 +2654,10 @@ int hci_register_dev(struct hci_dev *hdev) hci_dev_set_flag(hdev, HCI_SETUP); hci_dev_set_flag(hdev, HCI_AUTO_OFF); - if (hdev->dev_type == HCI_PRIMARY) { - /* Assume BR/EDR support until proven otherwise (such as - * through reading supported features during init. - */ - hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); - } + /* Assume BR/EDR support until proven otherwise (such as + * through reading supported features during init. + */ + hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); write_lock(&hci_dev_list_lock); list_add(&hdev->list, &hci_dev_list); @@ -2710,7 +2694,7 @@ int hci_register_dev(struct hci_dev *hdev) destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); err: - ida_simple_remove(&hci_index_ida, hdev->id); + ida_free(&hci_index_ida, hdev->id); return error; } @@ -2735,8 +2719,6 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_unregister_suspend_notifier(hdev); - msft_unregister(hdev); - hci_dev_do_close(hdev); if (!test_bit(HCI_INIT, &hdev->flags) && @@ -2790,11 +2772,13 @@ void hci_release_dev(struct hci_dev *hdev) hci_discovery_filter_clear(hdev); hci_blocked_keys_clear(hdev); hci_codec_list_clear(&hdev->local_codecs); + msft_release(hdev); hci_dev_unlock(hdev); ida_destroy(&hdev->unset_handle_ida); - ida_simple_remove(&hci_index_ida, hdev->id); + ida_free(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); + kfree_skb(hdev->req_skb); kfree_skb(hdev->recv_event); kfree(hdev); } @@ -2826,6 +2810,23 @@ int hci_unregister_suspend_notifier(struct hci_dev *hdev) return ret; } +/* Cancel ongoing command synchronously: + * + * - Cancel command timer + * - Reset command counter + * - Cancel command request + */ +static void hci_cancel_cmd_sync(struct hci_dev *hdev, int err) +{ + bt_dev_dbg(hdev, "err 0x%2.2x", err); + + cancel_delayed_work_sync(&hdev->cmd_timer); + cancel_delayed_work_sync(&hdev->ncmd_timer); + atomic_set(&hdev->cmd_cnt, 1); + + hci_cmd_sync_cancel_sync(hdev, err); +} + /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) { @@ -2843,7 +2844,7 @@ int hci_suspend_dev(struct hci_dev *hdev) return 0; /* Cancel potentially blocking sync operation before suspend */ - __hci_cmd_sync_cancel(hdev, -EHOSTDOWN); + hci_cancel_cmd_sync(hdev, EHOSTDOWN); hci_req_sync_lock(hdev); ret = hci_suspend_sync(hdev); @@ -3107,21 +3108,33 @@ int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, EXPORT_SYMBOL(__hci_cmd_send); /* Get data from the previously sent command */ -void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) +static void *hci_cmd_data(struct sk_buff *skb, __u16 opcode) { struct hci_command_hdr *hdr; - if (!hdev->sent_cmd) + if (!skb || skb->len < HCI_COMMAND_HDR_SIZE) return NULL; - hdr = (void *) hdev->sent_cmd->data; + hdr = (void *)skb->data; if (hdr->opcode != cpu_to_le16(opcode)) return NULL; - BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); + return skb->data + HCI_COMMAND_HDR_SIZE; +} - return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; +/* Get data from the previously sent command */ +void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) +{ + void *data; + + /* Check if opcode matches last sent command */ + data = hci_cmd_data(hdev->sent_cmd, opcode); + if (!data) + /* Check if opcode matches last request */ + data = hci_cmd_data(hdev->req_skb, opcode); + + return data; } /* Get data from last received event */ @@ -3180,17 +3193,7 @@ static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue, hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT; - switch (hdev->dev_type) { - case HCI_PRIMARY: - hci_add_acl_hdr(skb, conn->handle, flags); - break; - case HCI_AMP: - hci_add_acl_hdr(skb, chan->handle, flags); - break; - default: - bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type); - return; - } + hci_add_acl_hdr(skb, conn->handle, flags); list = skb_shinfo(skb)->frag_list; if (!list) { @@ -3350,9 +3353,6 @@ static inline void hci_quote_sent(struct hci_conn *conn, int num, int *quote) case ACL_LINK: cnt = hdev->acl_cnt; break; - case AMP_LINK: - cnt = hdev->block_cnt; - break; case SCO_LINK: case ESCO_LINK: cnt = hdev->sco_cnt; @@ -3550,12 +3550,6 @@ static void hci_prio_recalculate(struct hci_dev *hdev, __u8 type) } -static inline int __get_blocks(struct hci_dev *hdev, struct sk_buff *skb) -{ - /* Calculate count of blocks used by this packet */ - return DIV_ROUND_UP(skb->len - HCI_ACL_HDR_SIZE, hdev->block_len); -} - static void __check_timeout(struct hci_dev *hdev, unsigned int cnt, u8 type) { unsigned long last_tx; @@ -3669,81 +3663,15 @@ static void hci_sched_acl_pkt(struct hci_dev *hdev) hci_prio_recalculate(hdev, ACL_LINK); } -static void hci_sched_acl_blk(struct hci_dev *hdev) -{ - unsigned int cnt = hdev->block_cnt; - struct hci_chan *chan; - struct sk_buff *skb; - int quote; - u8 type; - - BT_DBG("%s", hdev->name); - - if (hdev->dev_type == HCI_AMP) - type = AMP_LINK; - else - type = ACL_LINK; - - __check_timeout(hdev, cnt, type); - - while (hdev->block_cnt > 0 && - (chan = hci_chan_sent(hdev, type, "e))) { - u32 priority = (skb_peek(&chan->data_q))->priority; - while (quote > 0 && (skb = skb_peek(&chan->data_q))) { - int blocks; - - BT_DBG("chan %p skb %p len %d priority %u", chan, skb, - skb->len, skb->priority); - - /* Stop if priority has changed */ - if (skb->priority < priority) - break; - - skb = skb_dequeue(&chan->data_q); - - blocks = __get_blocks(hdev, skb); - if (blocks > hdev->block_cnt) - return; - - hci_conn_enter_active_mode(chan->conn, - bt_cb(skb)->force_active); - - hci_send_frame(hdev, skb); - hdev->acl_last_tx = jiffies; - - hdev->block_cnt -= blocks; - quote -= blocks; - - chan->sent += blocks; - chan->conn->sent += blocks; - } - } - - if (cnt != hdev->block_cnt) - hci_prio_recalculate(hdev, type); -} - static void hci_sched_acl(struct hci_dev *hdev) { BT_DBG("%s", hdev->name); /* No ACL link over BR/EDR controller */ - if (!hci_conn_num(hdev, ACL_LINK) && hdev->dev_type == HCI_PRIMARY) - return; - - /* No AMP link over AMP controller */ - if (!hci_conn_num(hdev, AMP_LINK) && hdev->dev_type == HCI_AMP) + if (!hci_conn_num(hdev, ACL_LINK)) return; - switch (hdev->flow_ctl_mode) { - case HCI_FLOW_CTL_MODE_PACKET_BASED: - hci_sched_acl_pkt(hdev); - break; - - case HCI_FLOW_CTL_MODE_BLOCK_BASED: - hci_sched_acl_blk(hdev); - break; - } + hci_sched_acl_pkt(hdev); } static void hci_sched_le(struct hci_dev *hdev) @@ -4022,17 +3950,19 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, if (!status && !hci_req_is_complete(hdev)) return; + skb = hdev->req_skb; + /* If this was the last command in a request the complete - * callback would be found in hdev->sent_cmd instead of the + * callback would be found in hdev->req_skb instead of the * command queue (hdev->cmd_q). */ - if (bt_cb(hdev->sent_cmd)->hci.req_flags & HCI_REQ_SKB) { - *req_complete_skb = bt_cb(hdev->sent_cmd)->hci.req_complete_skb; + if (skb && bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) { + *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; return; } - if (bt_cb(hdev->sent_cmd)->hci.req_complete) { - *req_complete = bt_cb(hdev->sent_cmd)->hci.req_complete; + if (skb && bt_cb(skb)->hci.req_complete) { + *req_complete = bt_cb(skb)->hci.req_complete; return; } @@ -4128,6 +4058,36 @@ static void hci_rx_work(struct work_struct *work) } } +static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) +{ + int err; + + bt_dev_dbg(hdev, "skb %p", skb); + + kfree_skb(hdev->sent_cmd); + + hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); + if (!hdev->sent_cmd) { + skb_queue_head(&hdev->cmd_q, skb); + queue_work(hdev->workqueue, &hdev->cmd_work); + return; + } + + err = hci_send_frame(hdev, skb); + if (err < 0) { + hci_cmd_sync_cancel_sync(hdev, -err); + return; + } + + if (hci_req_status_pend(hdev) && + !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { + kfree_skb(hdev->req_skb); + hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); + } + + atomic_dec(&hdev->cmd_cnt); +} + static void hci_cmd_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); @@ -4142,30 +4102,15 @@ static void hci_cmd_work(struct work_struct *work) if (!skb) return; - kfree_skb(hdev->sent_cmd); - - hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); - if (hdev->sent_cmd) { - int res; - if (hci_req_status_pend(hdev)) - hci_dev_set_flag(hdev, HCI_CMD_PENDING); - atomic_dec(&hdev->cmd_cnt); + hci_send_cmd_sync(hdev, skb); - res = hci_send_frame(hdev, skb); - if (res < 0) - __hci_cmd_sync_cancel(hdev, -res); - - rcu_read_lock(); - if (test_bit(HCI_RESET, &hdev->flags) || - hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) - cancel_delayed_work(&hdev->cmd_timer); - else - queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, - HCI_CMD_TIMEOUT); - rcu_read_unlock(); - } else { - skb_queue_head(&hdev->cmd_q, skb); - queue_work(hdev->workqueue, &hdev->cmd_work); - } + rcu_read_lock(); + if (test_bit(HCI_RESET, &hdev->flags) || + hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) + cancel_delayed_work(&hdev->cmd_timer); + else + queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, + HCI_CMD_TIMEOUT); + rcu_read_unlock(); } } diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 233453807b509..ce3ff2fa72e58 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -218,10 +218,12 @@ static int conn_info_min_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val > hdev->conn_info_max_age) + hci_dev_lock(hdev); + if (val == 0 || val > hdev->conn_info_max_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_min_age = val; hci_dev_unlock(hdev); @@ -246,10 +248,12 @@ static int conn_info_max_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val < hdev->conn_info_min_age) + hci_dev_lock(hdev); + if (val == 0 || val < hdev->conn_info_min_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_max_age = val; hci_dev_unlock(hdev); @@ -567,10 +571,12 @@ static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val > hdev->sniff_max_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val > hdev->sniff_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_min_interval = val; hci_dev_unlock(hdev); @@ -595,10 +601,12 @@ static int sniff_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val < hdev->sniff_min_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val < hdev->sniff_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_max_interval = val; hci_dev_unlock(hdev); @@ -850,10 +858,12 @@ static int conn_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_min_interval = val; hci_dev_unlock(hdev); @@ -878,10 +888,12 @@ static int conn_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_max_interval = val; hci_dev_unlock(hdev); @@ -990,10 +1002,12 @@ static int adv_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_min_interval = val; hci_dev_unlock(hdev); @@ -1018,10 +1032,12 @@ static int adv_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_max_interval = val; hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 2a5f5a7d2412b..1ed734a7fb313 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1,7 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. - Copyright 2023 NXP + Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky @@ -36,8 +36,6 @@ #include "hci_request.h" #include "hci_debugfs.h" #include "hci_codec.h" -#include "a2mp.h" -#include "amp.h" #include "smp.h" #include "msft.h" #include "eir.h" @@ -95,11 +93,11 @@ static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data, /* It is possible that we receive Inquiry Complete event right * before we receive Inquiry Cancel Command Complete event, in * which case the latter event should have status of Command - * Disallowed (0x0c). This should not be treated as error, since + * Disallowed. This should not be treated as error, since * we actually achieve what Inquiry Cancel wants to achieve, * which is to end the last Inquiry session. */ - if (rp->status == 0x0c && !test_bit(HCI_INQUIRY, &hdev->flags)) { + if (rp->status == HCI_ERROR_COMMAND_DISALLOWED && !test_bit(HCI_INQUIRY, &hdev->flags)) { bt_dev_warn(hdev, "Ignoring error of Inquiry Cancel command"); rp->status = 0x00; } @@ -120,8 +118,6 @@ static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data, hci_discovery_set_state(hdev, DISCOVERY_STOPPED); hci_dev_unlock(hdev); - hci_conn_check_pending(hdev); - return rp->status; } @@ -152,8 +148,6 @@ static u8 hci_cc_exit_periodic_inq(struct hci_dev *hdev, void *data, hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); - hci_conn_check_pending(hdev); - return rp->status; } @@ -919,21 +913,6 @@ static u8 hci_cc_read_local_ext_features(struct hci_dev *hdev, void *data, return rp->status; } -static u8 hci_cc_read_flow_control_mode(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_rp_read_flow_control_mode *rp = data; - - bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); - - if (rp->status) - return rp->status; - - hdev->flow_ctl_mode = rp->mode; - - return rp->status; -} - static u8 hci_cc_read_buffer_size(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -960,6 +939,9 @@ static u8 hci_cc_read_buffer_size(struct hci_dev *hdev, void *data, BT_DBG("%s acl mtu %d:%d sco mtu %d:%d", hdev->name, hdev->acl_mtu, hdev->acl_pkts, hdev->sco_mtu, hdev->sco_pkts); + if (!hdev->acl_mtu || !hdev->acl_pkts) + return HCI_ERROR_INVALID_PARAMETERS; + return rp->status; } @@ -1074,28 +1056,6 @@ static u8 hci_cc_write_page_scan_type(struct hci_dev *hdev, void *data, return rp->status; } -static u8 hci_cc_read_data_block_size(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_rp_read_data_block_size *rp = data; - - bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); - - if (rp->status) - return rp->status; - - hdev->block_mtu = __le16_to_cpu(rp->max_acl_len); - hdev->block_len = __le16_to_cpu(rp->block_len); - hdev->num_blocks = __le16_to_cpu(rp->num_blocks); - - hdev->block_cnt = hdev->num_blocks; - - BT_DBG("%s blk mtu %d cnt %d len %d", hdev->name, hdev->block_mtu, - hdev->block_cnt, hdev->block_len); - - return rp->status; -} - static u8 hci_cc_read_clock(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -1130,30 +1090,6 @@ static u8 hci_cc_read_clock(struct hci_dev *hdev, void *data, return rp->status; } -static u8 hci_cc_read_local_amp_info(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_rp_read_local_amp_info *rp = data; - - bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); - - if (rp->status) - return rp->status; - - hdev->amp_status = rp->amp_status; - hdev->amp_total_bw = __le32_to_cpu(rp->total_bw); - hdev->amp_max_bw = __le32_to_cpu(rp->max_bw); - hdev->amp_min_latency = __le32_to_cpu(rp->min_latency); - hdev->amp_max_pdu = __le32_to_cpu(rp->max_pdu); - hdev->amp_type = rp->amp_type; - hdev->amp_pal_cap = __le16_to_cpu(rp->pal_cap); - hdev->amp_assoc_size = __le16_to_cpu(rp->max_assoc_size); - hdev->amp_be_flush_to = __le32_to_cpu(rp->be_flush_to); - hdev->amp_max_flush_to = __le32_to_cpu(rp->max_flush_to); - - return rp->status; -} - static u8 hci_cc_read_inq_rsp_tx_power(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -1269,6 +1205,9 @@ static u8 hci_cc_le_read_buffer_size(struct hci_dev *hdev, void *data, BT_DBG("%s le mtu %d:%d", hdev->name, hdev->le_mtu, hdev->le_pkts); + if (hdev->le_mtu && hdev->le_mtu < HCI_MIN_LE_MTU) + return HCI_ERROR_INVALID_PARAMETERS; + return rp->status; } @@ -2314,10 +2253,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { bt_dev_dbg(hdev, "status 0x%2.2x", status); - if (status) { - hci_conn_check_pending(hdev); + if (status) return; - } if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY)) set_bit(HCI_INQUIRY, &hdev->flags); @@ -2342,19 +2279,16 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) if (status) { if (conn && conn->state == BT_CONNECT) { - if (status != 0x0c || conn->attempt > 2) { - conn->state = BT_CLOSED; - hci_connect_cfm(conn, status); - hci_conn_del(conn); - } else - conn->state = BT_CONNECT2; + conn->state = BT_CLOSED; + hci_connect_cfm(conn, status); + hci_conn_del(conn); } } else { if (!conn) { conn = hci_conn_add_unset(hdev, ACL_LINK, &cp->bdaddr, HCI_ROLE_MASTER); - if (!conn) - bt_dev_err(hdev, "no memory for new connection"); + if (IS_ERR(conn)) + bt_dev_err(hdev, "connection err: %ld", PTR_ERR(conn)); } } @@ -2526,9 +2460,7 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn, * Only those in BT_CONFIG or BT_CONNECTED states can be * considered connected. */ - if (conn && - (conn->state == BT_CONFIG || conn->state == BT_CONNECTED) && - !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + if (conn && (conn->state == BT_CONFIG || conn->state == BT_CONNECTED)) mgmt_device_connected(hdev, conn, name, name_len); if (discov->state == DISCOVERY_STOPPED) @@ -3039,8 +2971,6 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - hci_conn_check_pending(hdev); - if (!test_and_clear_bit(HCI_INQUIRY, &hdev->flags)) return; @@ -3169,8 +3099,8 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, BDADDR_BREDR)) { conn = hci_conn_add_unset(hdev, ev->link_type, &ev->bdaddr, HCI_ROLE_SLAVE); - if (!conn) { - bt_dev_err(hdev, "no memory for new conn"); + if (IS_ERR(conn)) { + bt_dev_err(hdev, "connection err: %ld", PTR_ERR(conn)); goto unlock; } } else { @@ -3223,6 +3153,31 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, if (test_bit(HCI_ENCRYPT, &hdev->flags)) set_bit(HCI_CONN_ENCRYPT, &conn->flags); + /* "Link key request" completed ahead of "connect request" completes */ + if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) && + ev->link_type == ACL_LINK) { + struct link_key *key; + struct hci_cp_read_enc_key_size cp; + + key = hci_find_link_key(hdev, &ev->bdaddr); + if (key) { + set_bit(HCI_CONN_ENCRYPT, &conn->flags); + + if (!read_key_size_capable(hdev)) { + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } else { + cp.handle = cpu_to_le16(conn->handle); + if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, + sizeof(cp), &cp)) { + bt_dev_err(hdev, "sending read key size failed"); + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } + } + + hci_encrypt_cfm(conn, ev->status); + } + } + /* Get remote features */ if (conn->type == ACL_LINK) { struct hci_cp_read_remote_features cp; @@ -3262,8 +3217,6 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, unlock: hci_dev_unlock(hdev); - - hci_conn_check_pending(hdev); } static void hci_reject_conn(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -3335,8 +3288,8 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, if (!conn) { conn = hci_conn_add_unset(hdev, ev->link_type, &ev->bdaddr, HCI_ROLE_SLAVE); - if (!conn) { - bt_dev_err(hdev, "no memory for new connection"); + if (IS_ERR(conn)) { + bt_dev_err(hdev, "connection err: %ld", PTR_ERR(conn)); goto unlock; } } @@ -3556,8 +3509,6 @@ static void hci_remote_name_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - hci_conn_check_pending(hdev); - hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); @@ -3660,7 +3611,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, * controller really supports it. If it doesn't, assume * the default size (16). */ - if (!(hdev->commands[20] & 0x10)) { + if (!read_key_size_capable(hdev)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; goto notify; } @@ -3762,8 +3713,9 @@ static void hci_remote_features_evt(struct hci_dev *hdev, void *data, bacpy(&cp.bdaddr, &conn->dst); cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); - } else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + } else { mgmt_device_connected(hdev, conn, NULL, 0); + } if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -3814,6 +3766,9 @@ static u8 hci_cc_le_read_buffer_size_v2(struct hci_dev *hdev, void *data, BT_DBG("%s acl mtu %d:%d iso mtu %d:%d", hdev->name, hdev->acl_mtu, hdev->acl_pkts, hdev->iso_mtu, hdev->iso_pkts); + if (hdev->le_mtu && hdev->le_mtu < HCI_MIN_LE_MTU) + return HCI_ERROR_INVALID_PARAMETERS; + return rp->status; } @@ -3936,6 +3891,11 @@ static u8 hci_cc_le_setup_iso_path(struct hci_dev *hdev, void *data, * last. */ hci_connect_cfm(conn, rp->status); + + /* Notify device connected in case it is a BIG Sync */ + if (!rp->status && test_bit(HCI_CONN_BIG_SYNC, &conn->flags)) + mgmt_device_connected(hdev, conn, NULL, 0); + break; } @@ -4100,12 +4060,6 @@ static const struct hci_cc { HCI_CC(HCI_OP_READ_PAGE_SCAN_TYPE, hci_cc_read_page_scan_type, sizeof(struct hci_rp_read_page_scan_type)), HCI_CC_STATUS(HCI_OP_WRITE_PAGE_SCAN_TYPE, hci_cc_write_page_scan_type), - HCI_CC(HCI_OP_READ_DATA_BLOCK_SIZE, hci_cc_read_data_block_size, - sizeof(struct hci_rp_read_data_block_size)), - HCI_CC(HCI_OP_READ_FLOW_CONTROL_MODE, hci_cc_read_flow_control_mode, - sizeof(struct hci_rp_read_flow_control_mode)), - HCI_CC(HCI_OP_READ_LOCAL_AMP_INFO, hci_cc_read_local_amp_info, - sizeof(struct hci_rp_read_local_amp_info)), HCI_CC(HCI_OP_READ_CLOCK, hci_cc_read_clock, sizeof(struct hci_rp_read_clock)), HCI_CC(HCI_OP_READ_ENC_KEY_SIZE, hci_cc_read_enc_key_size, @@ -4296,7 +4250,7 @@ static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status) hci_dev_lock(hdev); /* Remove connection if command failed */ - for (i = 0; cp->num_cis; cp->num_cis--, i++) { + for (i = 0; i < cp->num_cis; i++) { struct hci_conn *conn; u16 handle; @@ -4312,6 +4266,7 @@ static void hci_cs_le_create_cis(struct hci_dev *hdev, u8 status) hci_conn_del(conn); } } + cp->num_cis = 0; if (pending) hci_le_create_cis_pending(hdev); @@ -4381,7 +4336,7 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, void *data, * (since for this kind of commands there will not be a command * complete event). */ - if (ev->status || (hdev->sent_cmd && !hci_skb_event(hdev->sent_cmd))) { + if (ev->status || (hdev->req_skb && !hci_skb_event(hdev->req_skb))) { hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete, req_complete_skb); if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { @@ -4440,11 +4395,6 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data, flex_array_size(ev, handles, ev->num))) return; - if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_PACKET_BASED) { - bt_dev_err(hdev, "wrong event for mode %d", hdev->flow_ctl_mode); - return; - } - bt_dev_dbg(hdev, "num %d", ev->num); for (i = 0; i < ev->num; i++) { @@ -4512,78 +4462,6 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data, queue_work(hdev->workqueue, &hdev->tx_work); } -static struct hci_conn *__hci_conn_lookup_handle(struct hci_dev *hdev, - __u16 handle) -{ - struct hci_chan *chan; - - switch (hdev->dev_type) { - case HCI_PRIMARY: - return hci_conn_hash_lookup_handle(hdev, handle); - case HCI_AMP: - chan = hci_chan_lookup_handle(hdev, handle); - if (chan) - return chan->conn; - break; - default: - bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type); - break; - } - - return NULL; -} - -static void hci_num_comp_blocks_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_num_comp_blocks *ev = data; - int i; - - if (!hci_ev_skb_pull(hdev, skb, HCI_EV_NUM_COMP_BLOCKS, - flex_array_size(ev, handles, ev->num_hndl))) - return; - - if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_BLOCK_BASED) { - bt_dev_err(hdev, "wrong event for mode %d", - hdev->flow_ctl_mode); - return; - } - - bt_dev_dbg(hdev, "num_blocks %d num_hndl %d", ev->num_blocks, - ev->num_hndl); - - for (i = 0; i < ev->num_hndl; i++) { - struct hci_comp_blocks_info *info = &ev->handles[i]; - struct hci_conn *conn = NULL; - __u16 handle, block_count; - - handle = __le16_to_cpu(info->handle); - block_count = __le16_to_cpu(info->blocks); - - conn = __hci_conn_lookup_handle(hdev, handle); - if (!conn) - continue; - - conn->sent -= block_count; - - switch (conn->type) { - case ACL_LINK: - case AMP_LINK: - hdev->block_cnt += block_count; - if (hdev->block_cnt > hdev->num_blocks) - hdev->block_cnt = hdev->num_blocks; - break; - - default: - bt_dev_err(hdev, "unknown type %d conn %p", - conn->type, conn); - break; - } - } - - queue_work(hdev->workqueue, &hdev->tx_work); -} - static void hci_mode_change_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -5010,8 +4888,9 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev, void *data, bacpy(&cp.bdaddr, &conn->dst); cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); - } else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + } else { mgmt_device_connected(hdev, conn, NULL, 0); + } if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -5675,150 +5554,6 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, void *edata, hci_dev_unlock(hdev); } -#if IS_ENABLED(CONFIG_BT_HS) -static void hci_chan_selected_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_channel_selected *ev = data; - struct hci_conn *hcon; - - bt_dev_dbg(hdev, "handle 0x%2.2x", ev->phy_handle); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - return; - - amp_read_loc_assoc_final_data(hdev, hcon); -} - -static void hci_phy_link_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_phy_link_complete *ev = data; - struct hci_conn *hcon, *bredr_hcon; - - bt_dev_dbg(hdev, "handle 0x%2.2x status 0x%2.2x", ev->phy_handle, - ev->status); - - hci_dev_lock(hdev); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - goto unlock; - - if (!hcon->amp_mgr) - goto unlock; - - if (ev->status) { - hci_conn_del(hcon); - goto unlock; - } - - bredr_hcon = hcon->amp_mgr->l2cap_conn->hcon; - - hcon->state = BT_CONNECTED; - bacpy(&hcon->dst, &bredr_hcon->dst); - - hci_conn_hold(hcon); - hcon->disc_timeout = HCI_DISCONN_TIMEOUT; - hci_conn_drop(hcon); - - hci_debugfs_create_conn(hcon); - hci_conn_add_sysfs(hcon); - - amp_physical_cfm(bredr_hcon, hcon); - -unlock: - hci_dev_unlock(hdev); -} - -static void hci_loglink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_logical_link_complete *ev = data; - struct hci_conn *hcon; - struct hci_chan *hchan; - struct amp_mgr *mgr; - - bt_dev_dbg(hdev, "log_handle 0x%4.4x phy_handle 0x%2.2x status 0x%2.2x", - le16_to_cpu(ev->handle), ev->phy_handle, ev->status); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - return; - - /* Create AMP hchan */ - hchan = hci_chan_create(hcon); - if (!hchan) - return; - - hchan->handle = le16_to_cpu(ev->handle); - hchan->amp = true; - - BT_DBG("hcon %p mgr %p hchan %p", hcon, hcon->amp_mgr, hchan); - - mgr = hcon->amp_mgr; - if (mgr && mgr->bredr_chan) { - struct l2cap_chan *bredr_chan = mgr->bredr_chan; - - l2cap_chan_lock(bredr_chan); - - bredr_chan->conn->mtu = hdev->block_mtu; - l2cap_logical_cfm(bredr_chan, hchan, 0); - hci_conn_hold(hcon); - - l2cap_chan_unlock(bredr_chan); - } -} - -static void hci_disconn_loglink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_disconn_logical_link_complete *ev = data; - struct hci_chan *hchan; - - bt_dev_dbg(hdev, "handle 0x%4.4x status 0x%2.2x", - le16_to_cpu(ev->handle), ev->status); - - if (ev->status) - return; - - hci_dev_lock(hdev); - - hchan = hci_chan_lookup_handle(hdev, le16_to_cpu(ev->handle)); - if (!hchan || !hchan->amp) - goto unlock; - - amp_destroy_logical_link(hchan, ev->reason); - -unlock: - hci_dev_unlock(hdev); -} - -static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_disconn_phy_link_complete *ev = data; - struct hci_conn *hcon; - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - - if (ev->status) - return; - - hci_dev_lock(hdev); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (hcon && hcon->type == AMP_LINK) { - hcon->state = BT_CLOSED; - hci_disconn_cfm(hcon, ev->reason); - hci_conn_del(hcon); - } - - hci_dev_unlock(hdev); -} -#endif - static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *local_rpa) { @@ -5899,8 +5634,8 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, goto unlock; conn = hci_conn_add_unset(hdev, LE_LINK, bdaddr, role); - if (!conn) { - bt_dev_err(hdev, "no memory for new connection"); + if (IS_ERR(conn)) { + bt_dev_err(hdev, "connection err: %ld", PTR_ERR(conn)); goto unlock; } @@ -5984,8 +5719,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, goto unlock; } - if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); conn->sec_level = BT_SECURITY_LOW; conn->state = BT_CONFIG; @@ -6169,7 +5903,7 @@ static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, void *data, static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, bool addr_resolved, - u8 adv_type) + u8 adv_type, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct hci_conn_params *params; @@ -6224,7 +5958,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, conn = hci_connect_le(hdev, addr, addr_type, addr_resolved, BT_SECURITY_LOW, hdev->def_le_autoconnect_timeout, - HCI_ROLE_MASTER); + HCI_ROLE_MASTER, phy, sec_phy); if (!IS_ERR(conn)) { /* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned * by higher layer that tried to connect, if no then @@ -6259,8 +5993,9 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len, - bool ext_adv, bool ctl_time, u64 instant) + u8 direct_addr_type, u8 phy, u8 sec_phy, s8 rssi, + u8 *data, u8 len, bool ext_adv, bool ctl_time, + u64 instant) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -6348,7 +6083,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * for advertising reports) and is already verified to be RPA above. */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved, - type); + type, phy, sec_phy); if (!ext_adv && conn && type == LE_ADV_IND && len <= max_adv_len(hdev)) { /* Store report for later inclusion by @@ -6494,7 +6229,8 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, - info->bdaddr_type, NULL, 0, rssi, + info->bdaddr_type, NULL, 0, + HCI_ADV_PHY_1M, 0, rssi, info->data, info->length, false, false, instant); } else { @@ -6579,6 +6315,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &info->bdaddr, info->bdaddr_type, NULL, 0, + info->primary_phy, + info->secondary_phy, info->rssi, info->data, info->length, !(evt_type & LE_EXT_ADV_LEGACY_PDU), false, instant); @@ -6621,14 +6359,16 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data, if (!(flags & HCI_PROTO_DEFER)) goto unlock; - if (ev->status) { - /* Add connection to indicate the failed PA sync event */ - pa_sync = hci_conn_add_unset(hdev, ISO_LINK, BDADDR_ANY, - HCI_ROLE_SLAVE); + /* Add connection to indicate PA sync event */ + pa_sync = hci_conn_add_unset(hdev, ISO_LINK, BDADDR_ANY, + HCI_ROLE_SLAVE); - if (!pa_sync) - goto unlock; + if (IS_ERR(pa_sync)) + goto unlock; + + pa_sync->sync_handle = le16_to_cpu(ev->handle); + if (ev->status) { set_bit(HCI_CONN_PA_SYNC_FAILED, &pa_sync->flags); /* Notify iso layer */ @@ -6645,6 +6385,7 @@ static void hci_le_per_adv_report_evt(struct hci_dev *hdev, void *data, struct hci_ev_le_per_adv_report *ev = data; int mask = hdev->link_mode; __u8 flags = 0; + struct hci_conn *pa_sync; bt_dev_dbg(hdev, "sync_handle 0x%4.4x", le16_to_cpu(ev->sync_handle)); @@ -6652,8 +6393,28 @@ static void hci_le_per_adv_report_evt(struct hci_dev *hdev, void *data, mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, ISO_LINK, &flags); if (!(mask & HCI_LM_ACCEPT)) - hci_le_pa_term_sync(hdev, ev->sync_handle); + goto unlock; + if (!(flags & HCI_PROTO_DEFER)) + goto unlock; + + pa_sync = hci_conn_hash_lookup_pa_sync_handle + (hdev, + le16_to_cpu(ev->sync_handle)); + + if (!pa_sync) + goto unlock; + + if (ev->data_status == LE_PA_DATA_COMPLETE && + !test_and_set_bit(HCI_CONN_PA_SYNC, &pa_sync->flags)) { + /* Notify iso layer */ + hci_connect_cfm(pa_sync, 0); + + /* Notify MGMT layer */ + mgmt_device_connected(hdev, pa_sync, NULL, 0); + } + +unlock: hci_dev_unlock(hdev); } @@ -6684,7 +6445,7 @@ static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, void *data, * transition into connected state and mark it as * successful. */ - if (!conn->out && ev->status == 0x1a && + if (!conn->out && ev->status == HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE && (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) status = 0x00; else @@ -6861,8 +6622,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data, process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, &info->direct_addr, - info->direct_addr_type, info->rssi, NULL, 0, - false, false, instant); + info->direct_addr_type, HCI_ADV_PHY_1M, 0, + info->rssi, NULL, 0, false, false, instant); } hci_dev_unlock(hdev); @@ -7026,7 +6787,7 @@ static void hci_le_cis_req_evt(struct hci_dev *hdev, void *data, if (!cis) { cis = hci_conn_add(hdev, ISO_LINK, &acl->dst, HCI_ROLE_SLAVE, cis_handle); - if (!cis) { + if (IS_ERR(cis)) { hci_le_reject_cis(hdev, ev->cis_handle); goto unlock; } @@ -7135,7 +6896,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, if (!bis) { bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY, HCI_ROLE_SLAVE, handle); - if (!bis) + if (IS_ERR(bis)) continue; } @@ -7165,6 +6926,8 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, u16 handle = le16_to_cpu(ev->bis[i]); bis = hci_conn_hash_lookup_handle(hdev, handle); + if (!bis) + continue; set_bit(HCI_CONN_BIG_SYNC_FAILED, &bis->flags); hci_connect_cfm(bis, ev->status); @@ -7186,10 +6949,8 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, ISO_LINK, &flags); - if (!(mask & HCI_LM_ACCEPT)) { - hci_le_pa_term_sync(hdev, ev->sync_handle); + if (!(mask & HCI_LM_ACCEPT)) goto unlock; - } if (!(flags & HCI_PROTO_DEFER)) goto unlock; @@ -7198,21 +6959,11 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, (hdev, le16_to_cpu(ev->sync_handle)); - if (pa_sync) + if (IS_ERR(pa_sync)) goto unlock; - /* Add connection to indicate the PA sync event */ - pa_sync = hci_conn_add_unset(hdev, ISO_LINK, BDADDR_ANY, - HCI_ROLE_SLAVE); - - if (!pa_sync) - goto unlock; - - pa_sync->sync_handle = le16_to_cpu(ev->sync_handle); - set_bit(HCI_CONN_PA_SYNC, &pa_sync->flags); - /* Notify iso layer */ - hci_connect_cfm(pa_sync, 0x00); + hci_connect_cfm(pa_sync, 0); unlock: hci_dev_unlock(hdev); @@ -7324,10 +7075,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "subevent 0x%2.2x", ev->subevent); /* Only match event if command OGF is for LE */ - if (hdev->sent_cmd && - hci_opcode_ogf(hci_skb_opcode(hdev->sent_cmd)) == 0x08 && - hci_skb_event(hdev->sent_cmd) == ev->subevent) { - *opcode = hci_skb_opcode(hdev->sent_cmd); + if (hdev->req_skb && + hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) == 0x08 && + hci_skb_event(hdev->req_skb) == ev->subevent) { + *opcode = hci_skb_opcode(hdev->req_skb); hci_req_cmd_complete(hdev, *opcode, 0x00, req_complete, req_complete_skb); } @@ -7626,28 +7377,6 @@ static const struct hci_ev { /* [0x3e = HCI_EV_LE_META] */ HCI_EV_REQ_VL(HCI_EV_LE_META, hci_le_meta_evt, sizeof(struct hci_ev_le_meta), HCI_MAX_EVENT_SIZE), -#if IS_ENABLED(CONFIG_BT_HS) - /* [0x40 = HCI_EV_PHY_LINK_COMPLETE] */ - HCI_EV(HCI_EV_PHY_LINK_COMPLETE, hci_phy_link_complete_evt, - sizeof(struct hci_ev_phy_link_complete)), - /* [0x41 = HCI_EV_CHANNEL_SELECTED] */ - HCI_EV(HCI_EV_CHANNEL_SELECTED, hci_chan_selected_evt, - sizeof(struct hci_ev_channel_selected)), - /* [0x42 = HCI_EV_DISCONN_PHY_LINK_COMPLETE] */ - HCI_EV(HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE, - hci_disconn_loglink_complete_evt, - sizeof(struct hci_ev_disconn_logical_link_complete)), - /* [0x45 = HCI_EV_LOGICAL_LINK_COMPLETE] */ - HCI_EV(HCI_EV_LOGICAL_LINK_COMPLETE, hci_loglink_complete_evt, - sizeof(struct hci_ev_logical_link_complete)), - /* [0x46 = HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE] */ - HCI_EV(HCI_EV_DISCONN_PHY_LINK_COMPLETE, - hci_disconn_phylink_complete_evt, - sizeof(struct hci_ev_disconn_phy_link_complete)), -#endif - /* [0x48 = HCI_EV_NUM_COMP_BLOCKS] */ - HCI_EV(HCI_EV_NUM_COMP_BLOCKS, hci_num_comp_blocks_evt, - sizeof(struct hci_ev_num_comp_blocks)), /* [0xff = HCI_EV_VENDOR] */ HCI_EV_VL(HCI_EV_VENDOR, msft_vendor_evt, 0, HCI_MAX_EVENT_SIZE), }; @@ -7714,10 +7443,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) } /* Only match event if command OGF is not for LE */ - if (hdev->sent_cmd && - hci_opcode_ogf(hci_skb_opcode(hdev->sent_cmd)) != 0x08 && - hci_skb_event(hdev->sent_cmd) == event) { - hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->sent_cmd), + if (hdev->req_skb && + hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) != 0x08 && + hci_skb_event(hdev->req_skb) == event) { + hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->req_skb), status, &req_complete, &req_complete_skb); req_evt = event; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 6e023b0104b03..efea25eb56ce0 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -105,8 +105,10 @@ void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (hdev->req_status == HCI_REQ_PEND) { hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; - if (skb) + if (skb) { + kfree_skb(hdev->req_skb); hdev->req_skb = skb_get(skb); + } wake_up_interruptible(&hdev->req_wait_q); } } @@ -895,7 +897,7 @@ void hci_request_setup(struct hci_dev *hdev) void hci_request_cancel_all(struct hci_dev *hdev) { - __hci_cmd_sync_cancel(hdev, ENODEV); + hci_cmd_sync_cancel_sync(hdev, ENODEV); cancel_interleave_scan(hdev); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 3e7cd330d731a..69c2ba1e843eb 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -101,7 +101,7 @@ static bool hci_sock_gen_cookie(struct sock *sk) int id = hci_pi(sk)->cookie; if (!id) { - id = ida_simple_get(&sock_cookie_ida, 1, 0, GFP_KERNEL); + id = ida_alloc_min(&sock_cookie_ida, 1, GFP_KERNEL); if (id < 0) id = 0xffffffff; @@ -119,7 +119,7 @@ static void hci_sock_free_cookie(struct sock *sk) if (id) { hci_pi(sk)->cookie = 0xffffffff; - ida_simple_remove(&sock_cookie_ida, id); + ida_free(&sock_cookie_ida, id); } } @@ -485,7 +485,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) return NULL; ni = skb_put(skb, HCI_MON_NEW_INDEX_SIZE); - ni->type = hdev->dev_type; + ni->type = 0x00; /* Old hdev->dev_type */ ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name, @@ -1007,9 +1007,6 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) return -EOPNOTSUPP; - if (hdev->dev_type != HCI_PRIMARY) - return -EOPNOTSUPP; - switch (cmd) { case HCISETRAW: if (!capable(CAP_NET_ADMIN)) @@ -1946,10 +1943,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, switch (optname) { case HCI_DATA_DIR: - if (copy_from_sockptr(&opt, optval, sizeof(opt))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + if (err) break; - } if (opt) hci_pi(sk)->cmsg_mask |= HCI_CMSG_DIR; @@ -1958,10 +1954,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, break; case HCI_TIME_STAMP: - if (copy_from_sockptr(&opt, optval, sizeof(opt))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + if (err) break; - } if (opt) hci_pi(sk)->cmsg_mask |= HCI_CMSG_TSTAMP; @@ -1979,11 +1974,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, uf.event_mask[1] = *((u32 *) f->event_mask + 1); } - len = min_t(unsigned int, len, sizeof(uf)); - if (copy_from_sockptr(&uf, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&uf, sizeof(uf), optval, len); + if (err) break; - } if (!capable(CAP_NET_RAW)) { uf.type_mask &= hci_sec_filter.type_mask; @@ -2042,10 +2035,9 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname, goto done; } - if (copy_from_sockptr(&opt, optval, sizeof(opt))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + if (err) break; - } hci_pi(sk)->mtu = opt; break; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5716345a26dfb..3870bc0236833 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -32,6 +32,10 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; + /* Free the request command so it is not used as response */ + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + if (skb) { struct sock *sk = hci_skb_sk(skb); @@ -39,7 +43,7 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (sk) sock_put(sk); - hdev->req_skb = skb_get(skb); + hdev->req_rsp = skb_get(skb); } wake_up_interruptible(&hdev->req_wait_q); @@ -187,8 +191,8 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, hdev->req_status = 0; hdev->req_result = 0; - skb = hdev->req_skb; - hdev->req_skb = NULL; + skb = hdev->req_rsp; + hdev->req_rsp = NULL; bt_dev_dbg(hdev, "end: err %d", err); @@ -566,6 +570,17 @@ void hci_cmd_sync_init(struct hci_dev *hdev) INIT_DELAYED_WORK(&hdev->adv_instance_expire, adv_timeout_expire); } +static void _hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry, + int err) +{ + if (entry->destroy) + entry->destroy(hdev, entry->data, err); + + list_del(&entry->list); + kfree(entry); +} + void hci_cmd_sync_clear(struct hci_dev *hdev) { struct hci_cmd_sync_work_entry *entry, *tmp; @@ -574,17 +589,12 @@ void hci_cmd_sync_clear(struct hci_dev *hdev) cancel_work_sync(&hdev->reenable_adv_work); mutex_lock(&hdev->cmd_sync_work_lock); - list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) { - if (entry->destroy) - entry->destroy(hdev, entry->data, -ECANCELED); - - list_del(&entry->list); - kfree(entry); - } + list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); mutex_unlock(&hdev->cmd_sync_work_lock); } -void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) +void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); @@ -592,26 +602,31 @@ void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) hdev->req_result = err; hdev->req_status = HCI_REQ_CANCELED; - cancel_delayed_work_sync(&hdev->cmd_timer); - cancel_delayed_work_sync(&hdev->ncmd_timer); - atomic_set(&hdev->cmd_cnt, 1); - - wake_up_interruptible(&hdev->req_wait_q); + queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); } } +EXPORT_SYMBOL(hci_cmd_sync_cancel); -void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) +/* Cancel ongoing command request synchronously: + * + * - Set result and mark status to HCI_REQ_CANCELED + * - Wakeup command sync thread + */ +void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); if (hdev->req_status == HCI_REQ_PEND) { - hdev->req_result = err; + /* req_result is __u32 so error must be positive to be properly + * propagated. + */ + hdev->req_result = err < 0 ? -err : err; hdev->req_status = HCI_REQ_CANCELED; - queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); + wake_up_interruptible(&hdev->req_wait_q); } } -EXPORT_SYMBOL(hci_cmd_sync_cancel); +EXPORT_SYMBOL(hci_cmd_sync_cancel_sync); /* Submit HCI command to be run in as cmd_sync_work: * @@ -667,6 +682,115 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, } EXPORT_SYMBOL(hci_cmd_sync_queue); +static struct hci_cmd_sync_work_entry * +_hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) { + if (func && entry->func != func) + continue; + + if (data && entry->data != data) + continue; + + if (destroy && entry->destroy != destroy) + continue; + + return entry; + } + + return NULL; +} + +/* Queue HCI command entry once: + * + * - Lookup if an entry already exist and only if it doesn't creates a new entry + * and queue it. + */ +int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy)) + return 0; + + return hci_cmd_sync_queue(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_queue_once); + +/* Lookup HCI command entry: + * + * - Return first entry that matches by function callback or data or + * destroy callback. + */ +struct hci_cmd_sync_work_entry * +hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + + mutex_lock(&hdev->cmd_sync_work_lock); + entry = _hci_cmd_sync_lookup_entry(hdev, func, data, destroy); + mutex_unlock(&hdev->cmd_sync_work_lock); + + return entry; +} +EXPORT_SYMBOL(hci_cmd_sync_lookup_entry); + +/* Cancel HCI command entry */ +void hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry) +{ + mutex_lock(&hdev->cmd_sync_work_lock); + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + mutex_unlock(&hdev->cmd_sync_work_lock); +} +EXPORT_SYMBOL(hci_cmd_sync_cancel_entry); + +/* Dequeue one HCI command entry: + * + * - Lookup and cancel first entry that matches. + */ +bool hci_cmd_sync_dequeue_once(struct hci_dev *hdev, + hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + + entry = hci_cmd_sync_lookup_entry(hdev, func, data, destroy); + if (!entry) + return false; + + hci_cmd_sync_cancel_entry(hdev, entry); + + return true; +} +EXPORT_SYMBOL(hci_cmd_sync_dequeue_once); + +/* Dequeue HCI command entry: + * + * - Lookup and cancel any entry that matches by function callback or data or + * destroy callback. + */ +bool hci_cmd_sync_dequeue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + bool ret = false; + + mutex_lock(&hdev->cmd_sync_work_lock); + while ((entry = _hci_cmd_sync_lookup_entry(hdev, func, data, + destroy))) { + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + ret = true; + } + mutex_unlock(&hdev->cmd_sync_work_lock); + + return ret; +} +EXPORT_SYMBOL(hci_cmd_sync_dequeue); + int hci_update_eir_sync(struct hci_dev *hdev) { struct hci_cp_write_eir cp; @@ -919,11 +1043,10 @@ static int hci_disable_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) struct hci_cp_ext_adv_set *set; u8 data[sizeof(*cp) + sizeof(*set) * 1]; u8 size; + struct adv_info *adv = NULL; /* If request specifies an instance that doesn't exist, fail */ if (instance > 0) { - struct adv_info *adv; - adv = hci_find_adv_instance(hdev, instance); if (!adv) return -EINVAL; @@ -942,7 +1065,7 @@ static int hci_disable_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) cp->num_of_sets = !!instance; cp->enable = 0x00; - set->handle = instance; + set->handle = adv ? adv->handle : instance; size = sizeof(*cp) + sizeof(*set) * cp->num_of_sets; @@ -1071,7 +1194,7 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) cp.own_addr_type = own_addr_type; cp.channel_map = hdev->le_adv_channel_map; - cp.handle = instance; + cp.handle = adv ? adv->handle : instance; if (flags & MGMT_ADV_FLAG_SEC_2M) { cp.primary_phy = HCI_ADV_PHY_1M; @@ -1111,31 +1234,27 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) static int hci_set_ext_scan_rsp_data_sync(struct hci_dev *hdev, u8 instance) { - struct { - struct hci_cp_le_set_ext_scan_rsp_data cp; - u8 data[HCI_MAX_EXT_AD_LENGTH]; - } pdu; + DEFINE_FLEX(struct hci_cp_le_set_ext_scan_rsp_data, pdu, data, length, + HCI_MAX_EXT_AD_LENGTH); u8 len; struct adv_info *adv = NULL; int err; - memset(&pdu, 0, sizeof(pdu)); - if (instance) { adv = hci_find_adv_instance(hdev, instance); if (!adv || !adv->scan_rsp_changed) return 0; } - len = eir_create_scan_rsp(hdev, instance, pdu.data); + len = eir_create_scan_rsp(hdev, instance, pdu->data); - pdu.cp.handle = instance; - pdu.cp.length = len; - pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; - pdu.cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + pdu->handle = adv ? adv->handle : instance; + pdu->length = len; + pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu->frag_pref = LE_SET_ADV_DATA_NO_FRAG; err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, - sizeof(pdu.cp) + len, &pdu.cp, + struct_size(pdu, data, len), pdu, HCI_CMD_TIMEOUT); if (err) return err; @@ -1143,7 +1262,7 @@ static int hci_set_ext_scan_rsp_data_sync(struct hci_dev *hdev, u8 instance) if (adv) { adv->scan_rsp_changed = false; } else { - memcpy(hdev->scan_rsp_data, pdu.data, len); + memcpy(hdev->scan_rsp_data, pdu->data, len); hdev->scan_rsp_data_len = len; } @@ -1211,7 +1330,7 @@ int hci_enable_ext_advertising_sync(struct hci_dev *hdev, u8 instance) memset(set, 0, sizeof(*set)); - set->handle = instance; + set->handle = adv ? adv->handle : instance; /* Set duration per instance since controller is responsible for * scheduling it. @@ -1287,29 +1406,25 @@ static int hci_set_per_adv_params_sync(struct hci_dev *hdev, u8 instance, static int hci_set_per_adv_data_sync(struct hci_dev *hdev, u8 instance) { - struct { - struct hci_cp_le_set_per_adv_data cp; - u8 data[HCI_MAX_PER_AD_LENGTH]; - } pdu; + DEFINE_FLEX(struct hci_cp_le_set_per_adv_data, pdu, data, length, + HCI_MAX_PER_AD_LENGTH); u8 len; - - memset(&pdu, 0, sizeof(pdu)); + struct adv_info *adv = NULL; if (instance) { - struct adv_info *adv = hci_find_adv_instance(hdev, instance); - + adv = hci_find_adv_instance(hdev, instance); if (!adv || !adv->periodic) return 0; } - len = eir_create_per_adv_data(hdev, instance, pdu.data); + len = eir_create_per_adv_data(hdev, instance, pdu->data); - pdu.cp.length = len; - pdu.cp.handle = instance; - pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu->length = len; + pdu->handle = adv ? adv->handle : instance; + pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_PER_ADV_DATA, - sizeof(pdu.cp) + len, &pdu, + struct_size(pdu, data, len), pdu, HCI_CMD_TIMEOUT); } @@ -1603,31 +1718,27 @@ int hci_le_terminate_big_sync(struct hci_dev *hdev, u8 handle, u8 reason) static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance) { - struct { - struct hci_cp_le_set_ext_adv_data cp; - u8 data[HCI_MAX_EXT_AD_LENGTH]; - } pdu; + DEFINE_FLEX(struct hci_cp_le_set_ext_adv_data, pdu, data, length, + HCI_MAX_EXT_AD_LENGTH); u8 len; struct adv_info *adv = NULL; int err; - memset(&pdu, 0, sizeof(pdu)); - if (instance) { adv = hci_find_adv_instance(hdev, instance); if (!adv || !adv->adv_data_changed) return 0; } - len = eir_create_adv_data(hdev, instance, pdu.data); + len = eir_create_adv_data(hdev, instance, pdu->data); - pdu.cp.length = len; - pdu.cp.handle = instance; - pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; - pdu.cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + pdu->length = len; + pdu->handle = adv ? adv->handle : instance; + pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu->frag_pref = LE_SET_ADV_DATA_NO_FRAG; err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_DATA, - sizeof(pdu.cp) + len, &pdu.cp, + struct_size(pdu, data, len), pdu, HCI_CMD_TIMEOUT); if (err) return err; @@ -1636,7 +1747,7 @@ static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance) if (adv) { adv->adv_data_changed = false; } else { - memcpy(hdev->adv_data, pdu.data, len); + memcpy(hdev->adv_data, pdu->data, len); hdev->adv_data_len = len; } @@ -2602,6 +2713,14 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) return filter_policy; } +static void hci_le_scan_phy_params(struct hci_cp_le_scan_phy_params *cp, + u8 type, u16 interval, u16 window) +{ + cp->type = type; + cp->interval = cpu_to_le16(interval); + cp->window = cpu_to_le16(window); +} + static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, u16 interval, u16 window, u8 own_addr_type, u8 filter_policy) @@ -2609,7 +2728,7 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, struct hci_cp_le_set_ext_scan_params *cp; struct hci_cp_le_scan_phy_params *phy; u8 data[sizeof(*cp) + sizeof(*phy) * 2]; - u8 num_phy = 0; + u8 num_phy = 0x00; cp = (void *)data; phy = (void *)cp->data; @@ -2619,28 +2738,64 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, cp->own_addr_type = own_addr_type; cp->filter_policy = filter_policy; + /* Check if PA Sync is in progress then select the PHY based on the + * hci_conn.iso_qos. + */ + if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) { + struct hci_cp_le_add_to_accept_list *sent; + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_ACCEPT_LIST); + if (sent) { + struct hci_conn *conn; + + conn = hci_conn_hash_lookup_ba(hdev, ISO_LINK, + &sent->bdaddr); + if (conn) { + struct bt_iso_qos *qos = &conn->iso_qos; + + if (qos->bcast.in.phy & BT_ISO_PHY_1M || + qos->bcast.in.phy & BT_ISO_PHY_2M) { + cp->scanning_phys |= LE_SCAN_PHY_1M; + hci_le_scan_phy_params(phy, type, + interval, + window); + num_phy++; + phy++; + } + + if (qos->bcast.in.phy & BT_ISO_PHY_CODED) { + cp->scanning_phys |= LE_SCAN_PHY_CODED; + hci_le_scan_phy_params(phy, type, + interval * 3, + window * 3); + num_phy++; + phy++; + } + + if (num_phy) + goto done; + } + } + } + if (scan_1m(hdev) || scan_2m(hdev)) { cp->scanning_phys |= LE_SCAN_PHY_1M; - - phy->type = type; - phy->interval = cpu_to_le16(interval); - phy->window = cpu_to_le16(window); - + hci_le_scan_phy_params(phy, type, interval, window); num_phy++; phy++; } if (scan_coded(hdev)) { cp->scanning_phys |= LE_SCAN_PHY_CODED; - - phy->type = type; - phy->interval = cpu_to_le16(interval); - phy->window = cpu_to_le16(window); - + hci_le_scan_phy_params(phy, type, interval * 3, window * 3); num_phy++; phy++; } +done: + if (!num_phy) + return -EINVAL; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_SCAN_PARAMS, sizeof(*cp) + sizeof(*phy) * num_phy, data, HCI_CMD_TIMEOUT); @@ -2879,7 +3034,8 @@ int hci_update_passive_scan(struct hci_dev *hdev) hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; - return hci_cmd_sync_queue(hdev, update_passive_scan_sync, NULL, NULL); + return hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL, + NULL); } int hci_write_sc_support_sync(struct hci_dev *hdev, u8 val) @@ -3215,7 +3371,10 @@ static void hci_dev_get_bd_addr_from_property(struct hci_dev *hdev) if (ret < 0 || !bacmp(&ba, BDADDR_ANY)) return; - bacpy(&hdev->public_addr, &ba); + if (test_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks)) + baswap(&hdev->public_addr, &ba); + else + bacpy(&hdev->public_addr, &ba); } struct hci_init_stage { @@ -3316,10 +3475,6 @@ static int hci_unconf_init_sync(struct hci_dev *hdev) /* Read Local Supported Features. */ static int hci_read_local_features_sync(struct hci_dev *hdev) { - /* Not all AMP controllers support this command */ - if (hdev->dev_type == HCI_AMP && !(hdev->commands[14] & 0x20)) - return 0; - return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCAL_FEATURES, 0, NULL, HCI_CMD_TIMEOUT); } @@ -3354,51 +3509,6 @@ static int hci_read_local_cmds_sync(struct hci_dev *hdev) return 0; } -/* Read Local AMP Info */ -static int hci_read_local_amp_info_sync(struct hci_dev *hdev) -{ - return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCAL_AMP_INFO, - 0, NULL, HCI_CMD_TIMEOUT); -} - -/* Read Data Blk size */ -static int hci_read_data_block_size_sync(struct hci_dev *hdev) -{ - return __hci_cmd_sync_status(hdev, HCI_OP_READ_DATA_BLOCK_SIZE, - 0, NULL, HCI_CMD_TIMEOUT); -} - -/* Read Flow Control Mode */ -static int hci_read_flow_control_mode_sync(struct hci_dev *hdev) -{ - return __hci_cmd_sync_status(hdev, HCI_OP_READ_FLOW_CONTROL_MODE, - 0, NULL, HCI_CMD_TIMEOUT); -} - -/* Read Location Data */ -static int hci_read_location_data_sync(struct hci_dev *hdev) -{ - return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCATION_DATA, - 0, NULL, HCI_CMD_TIMEOUT); -} - -/* AMP Controller init stage 1 command sequence */ -static const struct hci_init_stage amp_init1[] = { - /* HCI_OP_READ_LOCAL_VERSION */ - HCI_INIT(hci_read_local_version_sync), - /* HCI_OP_READ_LOCAL_COMMANDS */ - HCI_INIT(hci_read_local_cmds_sync), - /* HCI_OP_READ_LOCAL_AMP_INFO */ - HCI_INIT(hci_read_local_amp_info_sync), - /* HCI_OP_READ_DATA_BLOCK_SIZE */ - HCI_INIT(hci_read_data_block_size_sync), - /* HCI_OP_READ_FLOW_CONTROL_MODE */ - HCI_INIT(hci_read_flow_control_mode_sync), - /* HCI_OP_READ_LOCATION_DATA */ - HCI_INIT(hci_read_location_data_sync), - {} -}; - static int hci_init1_sync(struct hci_dev *hdev) { int err; @@ -3412,28 +3522,9 @@ static int hci_init1_sync(struct hci_dev *hdev) return err; } - switch (hdev->dev_type) { - case HCI_PRIMARY: - hdev->flow_ctl_mode = HCI_FLOW_CTL_MODE_PACKET_BASED; - return hci_init_stage_sync(hdev, br_init1); - case HCI_AMP: - hdev->flow_ctl_mode = HCI_FLOW_CTL_MODE_BLOCK_BASED; - return hci_init_stage_sync(hdev, amp_init1); - default: - bt_dev_err(hdev, "Unknown device type %d", hdev->dev_type); - break; - } - - return 0; + return hci_init_stage_sync(hdev, br_init1); } -/* AMP Controller init stage 2 command sequence */ -static const struct hci_init_stage amp_init2[] = { - /* HCI_OP_READ_LOCAL_FEATURES */ - HCI_INIT(hci_read_local_features_sync), - {} -}; - /* Read Buffer Size (ACL mtu, max pkt, etc.) */ static int hci_read_buffer_size_sync(struct hci_dev *hdev) { @@ -3691,9 +3782,6 @@ static int hci_init2_sync(struct hci_dev *hdev) bt_dev_dbg(hdev, ""); - if (hdev->dev_type == HCI_AMP) - return hci_init_stage_sync(hdev, amp_init2); - err = hci_init_stage_sync(hdev, hci_init2); if (err) return err; @@ -4531,13 +4619,6 @@ static int hci_init_sync(struct hci_dev *hdev) if (err < 0) return err; - /* HCI_PRIMARY covers both single-mode LE, BR/EDR and dual-mode - * BR/EDR/LE type controllers. AMP controllers only need the - * first two stages of init. - */ - if (hdev->dev_type != HCI_PRIMARY) - return 0; - err = hci_init3_sync(hdev); if (err < 0) return err; @@ -4766,12 +4847,8 @@ int hci_dev_open_sync(struct hci_dev *hdev) * In case of user channel usage, it is not important * if a public address or static random address is * available. - * - * This check is only valid for BR/EDR controllers - * since AMP controllers do not have an address. */ if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && - hdev->dev_type == HCI_PRIMARY && !bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY)) { ret = -EADDRNOTAVAIL; @@ -4806,8 +4883,7 @@ int hci_dev_open_sync(struct hci_dev *hdev) !hci_dev_test_flag(hdev, HCI_CONFIG) && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && - hci_dev_test_flag(hdev, HCI_MGMT) && - hdev->dev_type == HCI_PRIMARY) { + hci_dev_test_flag(hdev, HCI_MGMT)) { ret = hci_powered_update_sync(hdev); mgmt_power_on(hdev, ret); } @@ -4834,6 +4910,11 @@ int hci_dev_open_sync(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + if (hdev->req_skb) { + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + } + clear_bit(HCI_RUNNING, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_CLOSE); @@ -4947,8 +5028,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) auto_off = hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF); - if (!auto_off && hdev->dev_type == HCI_PRIMARY && - !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + if (!auto_off && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && hci_dev_test_flag(hdev, HCI_MGMT)) __mgmt_power_off(hdev); @@ -4994,6 +5074,12 @@ int hci_dev_close_sync(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + /* Drop last request */ + if (hdev->req_skb) { + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + } + clear_bit(HCI_RUNNING, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_CLOSE); @@ -5004,9 +5090,6 @@ int hci_dev_close_sync(struct hci_dev *hdev) hdev->flags &= BIT(HCI_RAW); hci_dev_clear_volatile_flags(hdev); - /* Controller radio is available but is currently powered down */ - hdev->amp_status = AMP_STATUS_POWERED_DOWN; - memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); bacpy(&hdev->random_addr, BDADDR_ANY); @@ -5043,8 +5126,7 @@ static int hci_power_on_sync(struct hci_dev *hdev) */ if (hci_dev_test_flag(hdev, HCI_RFKILLED) || hci_dev_test_flag(hdev, HCI_UNCONFIGURED) || - (hdev->dev_type == HCI_PRIMARY && - !bacmp(&hdev->bdaddr, BDADDR_ANY) && + (!bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { hci_dev_clear_flag(hdev, HCI_AUTO_OFF); hci_dev_close_sync(hdev); @@ -5146,27 +5228,11 @@ int hci_stop_discovery_sync(struct hci_dev *hdev) return 0; } -static int hci_disconnect_phy_link_sync(struct hci_dev *hdev, u16 handle, - u8 reason) -{ - struct hci_cp_disconn_phy_link cp; - - memset(&cp, 0, sizeof(cp)); - cp.phy_handle = HCI_PHY_HANDLE(handle); - cp.reason = reason; - - return __hci_cmd_sync_status(hdev, HCI_OP_DISCONN_PHY_LINK, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); -} - static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { struct hci_cp_disconnect cp; - if (conn->type == AMP_LINK) - return hci_disconnect_phy_link_sync(hdev, conn->handle, reason); - if (test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) { /* This is a BIS connection, hci_conn_del will * do the necessary cleanup. @@ -6132,7 +6198,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen = sizeof(*cp); - if (scan_1m(hdev)) { + if (scan_1m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_1M || + conn->le_adv_sec_phy == HCI_ADV_PHY_1M)) { cp->phys |= LE_SCAN_PHY_1M; set_ext_conn_params(conn, p); @@ -6140,7 +6207,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen += sizeof(*p); } - if (scan_2m(hdev)) { + if (scan_2m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_2M || + conn->le_adv_sec_phy == HCI_ADV_PHY_2M)) { cp->phys |= LE_SCAN_PHY_2M; set_ext_conn_params(conn, p); @@ -6148,7 +6216,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen += sizeof(*p); } - if (scan_coded(hdev)) { + if (scan_coded(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_CODED || + conn->le_adv_sec_phy == HCI_ADV_PHY_CODED)) { cp->phys |= LE_SCAN_PHY_CODED; set_ext_conn_params(conn, p); @@ -6161,12 +6230,21 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, conn->conn_timeout, NULL); } -int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) +static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) { struct hci_cp_le_create_conn cp; struct hci_conn_params *params; u8 own_addr_type; int err; + struct hci_conn *conn = data; + + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; + + bt_dev_dbg(hdev, "conn %p", conn); + + clear_bit(HCI_CONN_SCANNING, &conn->flags); + conn->state = BT_CONNECT; /* If requested to connect as peripheral use directed advertising */ if (conn->role == HCI_ROLE_SLAVE) { @@ -6267,10 +6345,8 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) int hci_le_create_cis_sync(struct hci_dev *hdev) { - struct { - struct hci_cp_le_create_cis cp; - struct hci_cis cis[0x1f]; - } cmd; + DEFINE_FLEX(struct hci_cp_le_create_cis, cmd, cis, num_cis, 0x1f); + size_t aux_num_cis = 0; struct hci_conn *conn; u8 cig = BT_ISO_QOS_CIG_UNSET; @@ -6297,8 +6373,6 @@ int hci_le_create_cis_sync(struct hci_dev *hdev) * remains pending. */ - memset(&cmd, 0, sizeof(cmd)); - hci_dev_lock(hdev); rcu_read_lock(); @@ -6335,7 +6409,7 @@ int hci_le_create_cis_sync(struct hci_dev *hdev) goto done; list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { - struct hci_cis *cis = &cmd.cis[cmd.cp.num_cis]; + struct hci_cis *cis = &cmd->cis[aux_num_cis]; if (hci_conn_check_create_cis(conn) || conn->iso_qos.ucast.cig != cig) @@ -6344,25 +6418,25 @@ int hci_le_create_cis_sync(struct hci_dev *hdev) set_bit(HCI_CONN_CREATE_CIS, &conn->flags); cis->acl_handle = cpu_to_le16(conn->parent->handle); cis->cis_handle = cpu_to_le16(conn->handle); - cmd.cp.num_cis++; + aux_num_cis++; - if (cmd.cp.num_cis >= ARRAY_SIZE(cmd.cis)) + if (aux_num_cis >= 0x1f) break; } + cmd->num_cis = aux_num_cis; done: rcu_read_unlock(); hci_dev_unlock(hdev); - if (!cmd.cp.num_cis) + if (!aux_num_cis) return 0; /* Wait for HCI_LE_CIS_Established */ return __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_CREATE_CIS, - sizeof(cmd.cp) + sizeof(cmd.cis[0]) * - cmd.cp.num_cis, &cmd, - HCI_EVT_LE_CIS_ESTABLISHED, + struct_size(cmd, cis, cmd->num_cis), + cmd, HCI_EVT_LE_CIS_ESTABLISHED, conn->conn_timeout, NULL); } @@ -6484,3 +6558,125 @@ int hci_update_adv_data(struct hci_dev *hdev, u8 instance) return hci_cmd_sync_queue(hdev, _update_adv_data_sync, UINT_PTR(instance), NULL); } + +static int hci_acl_create_conn_sync(struct hci_dev *hdev, void *data) +{ + struct hci_conn *conn = data; + struct inquiry_entry *ie; + struct hci_cp_create_conn cp; + int err; + + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; + + /* Many controllers disallow HCI Create Connection while it is doing + * HCI Inquiry. So we cancel the Inquiry first before issuing HCI Create + * Connection. This may cause the MGMT discovering state to become false + * without user space's request but it is okay since the MGMT Discovery + * APIs do not promise that discovery should be done forever. Instead, + * the user space monitors the status of MGMT discovering and it may + * request for discovery again when this flag becomes false. + */ + if (test_bit(HCI_INQUIRY, &hdev->flags)) { + err = __hci_cmd_sync_status(hdev, HCI_OP_INQUIRY_CANCEL, 0, + NULL, HCI_CMD_TIMEOUT); + if (err) + bt_dev_warn(hdev, "Failed to cancel inquiry %d", err); + } + + conn->state = BT_CONNECT; + conn->out = true; + conn->role = HCI_ROLE_MASTER; + + conn->attempt++; + + conn->link_policy = hdev->link_policy; + + memset(&cp, 0, sizeof(cp)); + bacpy(&cp.bdaddr, &conn->dst); + cp.pscan_rep_mode = 0x02; + + ie = hci_inquiry_cache_lookup(hdev, &conn->dst); + if (ie) { + if (inquiry_entry_age(ie) <= INQUIRY_ENTRY_AGE_MAX) { + cp.pscan_rep_mode = ie->data.pscan_rep_mode; + cp.pscan_mode = ie->data.pscan_mode; + cp.clock_offset = ie->data.clock_offset | + cpu_to_le16(0x8000); + } + + memcpy(conn->dev_class, ie->data.dev_class, 3); + } + + cp.pkt_type = cpu_to_le16(conn->pkt_type); + if (lmp_rswitch_capable(hdev) && !(hdev->link_mode & HCI_LM_MASTER)) + cp.role_switch = 0x01; + else + cp.role_switch = 0x00; + + return __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN, + sizeof(cp), &cp, + HCI_EV_CONN_COMPLETE, + conn->conn_timeout, NULL); +} + +int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + return hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn, + NULL); +} + +static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) +{ + struct hci_conn *conn = data; + + bt_dev_dbg(hdev, "err %d", err); + + if (err == -ECANCELED) + return; + + hci_dev_lock(hdev); + + if (!hci_conn_valid(hdev, conn)) + goto done; + + if (!err) { + hci_connect_le_scan_cleanup(conn, 0x00); + goto done; + } + + /* Check if connection is still pending */ + if (conn != hci_lookup_le_connect(hdev)) + goto done; + + /* Flush to make sure we send create conn cancel command if needed */ + flush_delayed_work(&conn->le_conn_timeout); + hci_conn_failed(conn, bt_status(err)); + +done: + hci_dev_unlock(hdev); +} + +int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + return hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn, + create_le_conn_complete); +} + +int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + if (conn->state != BT_OPEN) + return -EINVAL; + + switch (conn->type) { + case ACL_LINK: + return !hci_cmd_sync_dequeue_once(hdev, + hci_acl_create_conn_sync, + conn, NULL); + case LE_LINK: + return !hci_cmd_sync_dequeue_once(hdev, hci_le_create_conn_sync, + conn, create_le_conn_complete); + } + + return -ENOENT; +} diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 04f6572d35f17..00c0d8413c638 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -3,7 +3,7 @@ * BlueZ - Bluetooth protocol stack for Linux * * Copyright (C) 2022 Intel Corporation - * Copyright 2023 NXP + * Copyright 2023-2024 NXP */ #include @@ -54,7 +54,6 @@ static void iso_sock_kill(struct sock *sk); enum { BT_SK_BIG_SYNC, BT_SK_PA_SYNC, - BT_SK_PA_SYNC_TERM, }; struct iso_pinfo { @@ -81,12 +80,14 @@ static bool check_ucast_qos(struct bt_iso_qos *qos); static bool check_bcast_qos(struct bt_iso_qos *qos); static bool iso_match_sid(struct sock *sk, void *data); static bool iso_match_sync_handle(struct sock *sk, void *data); +static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data); static void iso_sock_disconn(struct sock *sk); typedef bool (*iso_sock_match_t)(struct sock *sk, void *data); -static struct sock *iso_get_sock_listen(bdaddr_t *src, bdaddr_t *dst, - iso_sock_match_t match, void *data); +static struct sock *iso_get_sock(bdaddr_t *src, bdaddr_t *dst, + enum bt_sock_state state, + iso_sock_match_t match, void *data); /* ---- ISO timers ---- */ #define ISO_CONN_TIMEOUT (HZ * 40) @@ -196,21 +197,10 @@ static void iso_chan_del(struct sock *sk, int err) sock_set_flag(sk, SOCK_ZAPPED); } -static bool iso_match_conn_sync_handle(struct sock *sk, void *data) -{ - struct hci_conn *hcon = data; - - if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) - return false; - - return hcon->sync_handle == iso_pi(sk)->sync_handle; -} - static void iso_conn_del(struct hci_conn *hcon, int err) { struct iso_conn *conn = hcon->iso_data; struct sock *sk; - struct sock *parent; if (!conn) return; @@ -226,25 +216,6 @@ static void iso_conn_del(struct hci_conn *hcon, int err) if (sk) { lock_sock(sk); - - /* While a PA sync hcon is in the process of closing, - * mark parent socket with a flag, so that any residual - * BIGInfo adv reports that arrive before PA sync is - * terminated are not processed anymore. - */ - if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { - parent = iso_get_sock_listen(&hcon->src, - &hcon->dst, - iso_match_conn_sync_handle, - hcon); - - if (parent) { - set_bit(BT_SK_PA_SYNC_TERM, - &iso_pi(parent)->flags); - sock_put(parent); - } - } - iso_sock_clear_timer(sk); iso_chan_del(sk, err); release_sock(sk); @@ -581,22 +552,23 @@ static struct sock *__iso_get_sock_listen_by_sid(bdaddr_t *ba, bdaddr_t *bc, return NULL; } -/* Find socket listening: +/* Find socket in given state: * source bdaddr (Unicast) * destination bdaddr (Broadcast only) * match func - pass NULL to ignore * match func data - pass -1 to ignore * Returns closest match. */ -static struct sock *iso_get_sock_listen(bdaddr_t *src, bdaddr_t *dst, - iso_sock_match_t match, void *data) +static struct sock *iso_get_sock(bdaddr_t *src, bdaddr_t *dst, + enum bt_sock_state state, + iso_sock_match_t match, void *data) { struct sock *sk = NULL, *sk1 = NULL; read_lock(&iso_sk_list.lock); sk_for_each(sk, &iso_sk_list.head) { - if (sk->sk_state != BT_LISTEN) + if (sk->sk_state != state) continue; /* Match Broadcast destination */ @@ -690,11 +662,8 @@ static void iso_sock_cleanup_listen(struct sock *parent) iso_sock_kill(sk); } - /* If listening socket stands for a PA sync connection, - * properly disconnect the hcon and socket. - */ - if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon && - test_bit(HCI_CONN_PA_SYNC, &iso_pi(parent)->conn->hcon->flags)) { + /* If listening socket has a hcon, properly disconnect it */ + if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon) { iso_sock_disconn(parent); return; } @@ -837,10 +806,10 @@ static struct bt_iso_qos default_qos = { .bcode = {0x00}, .options = 0x00, .skip = 0x0000, - .sync_timeout = 0x4000, + .sync_timeout = BT_ISO_SYNC_TIMEOUT, .sync_cte_type = 0x00, .mse = 0x00, - .timeout = 0x4000, + .timeout = BT_ISO_SYNC_TIMEOUT, }, }; @@ -860,6 +829,7 @@ static struct sock *iso_sock_alloc(struct net *net, struct socket *sock, iso_pi(sk)->src_type = BDADDR_LE_PUBLIC; iso_pi(sk)->qos = default_qos; + iso_pi(sk)->sync_handle = -1; bt_sock_link(&iso_sk_list, sk); return sk; @@ -907,7 +877,6 @@ static int iso_sock_bind_bc(struct socket *sock, struct sockaddr *addr, return -EINVAL; iso_pi(sk)->dst_type = sa->iso_bc->bc_bdaddr_type; - iso_pi(sk)->sync_handle = -1; if (sa->iso_bc->bc_sid > 0x0f) return -EINVAL; @@ -984,7 +953,8 @@ static int iso_sock_bind(struct socket *sock, struct sockaddr *addr, /* Allow the user to bind a PA sync socket to a number * of BISes to sync to. */ - if (sk->sk_state == BT_CONNECT2 && + if ((sk->sk_state == BT_CONNECT2 || + sk->sk_state == BT_CONNECTED) && test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { err = iso_sock_bind_pa_sk(sk, sa, addr_len); goto done; @@ -1076,6 +1046,8 @@ static int iso_listen_bis(struct sock *sk) { struct hci_dev *hdev; int err = 0; + struct iso_conn *conn; + struct hci_conn *hcon; BT_DBG("%pMR -> %pMR (SID 0x%2.2x)", &iso_pi(sk)->src, &iso_pi(sk)->dst, iso_pi(sk)->bc_sid); @@ -1096,18 +1068,40 @@ static int iso_listen_bis(struct sock *sk) if (!hdev) return -EHOSTUNREACH; + hci_dev_lock(hdev); + /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; - return -EINVAL; + err = -EINVAL; + goto unlock; + } + + hcon = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, + le_addr_type(iso_pi(sk)->dst_type), + iso_pi(sk)->bc_sid, &iso_pi(sk)->qos); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; } - err = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, - le_addr_type(iso_pi(sk)->dst_type), - iso_pi(sk)->bc_sid, &iso_pi(sk)->qos); + conn = iso_conn_add(hcon); + if (!conn) { + hci_conn_drop(hcon); + err = -ENOMEM; + goto unlock; + } + + err = iso_chan_add(conn, sk, NULL); + if (err) { + hci_conn_drop(hcon); + goto unlock; + } hci_dev_put(hdev); +unlock: + hci_dev_unlock(hdev); return err; } @@ -1264,7 +1258,7 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, return -ENOTCONN; } - mtu = iso_pi(sk)->conn->hcon->hdev->iso_mtu; + mtu = iso_pi(sk)->conn->hcon->mtu; release_sock(sk); @@ -1372,6 +1366,16 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, } release_sock(sk); return 0; + case BT_CONNECTED: + if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { + iso_conn_big_sync(sk); + sk->sk_state = BT_LISTEN; + release_sock(sk); + return 0; + } + + release_sock(sk); + break; case BT_CONNECT: release_sock(sk); return iso_connect_cis(sk); @@ -1430,8 +1434,8 @@ static bool check_ucast_qos(struct bt_iso_qos *qos) static bool check_bcast_qos(struct bt_iso_qos *qos) { - if (qos->bcast.sync_factor == 0x00) - return false; + if (!qos->bcast.sync_factor) + qos->bcast.sync_factor = 0x01; if (qos->bcast.packing > 0x01) return false; @@ -1454,6 +1458,9 @@ static bool check_bcast_qos(struct bt_iso_qos *qos) if (qos->bcast.skip > 0x01f3) return false; + if (!qos->bcast.sync_timeout) + qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; + if (qos->bcast.sync_timeout < 0x000a || qos->bcast.sync_timeout > 0x4000) return false; @@ -1463,6 +1470,9 @@ static bool check_bcast_qos(struct bt_iso_qos *qos) if (qos->bcast.mse > 0x1f) return false; + if (!qos->bcast.timeout) + qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; + if (qos->bcast.timeout < 0x000a || qos->bcast.timeout > 0x4000) return false; @@ -1473,7 +1483,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - int len, err = 0; + int err = 0; struct bt_iso_qos qos = default_qos; u32 opt; @@ -1488,10 +1498,9 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -1500,10 +1509,9 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); @@ -1513,22 +1521,16 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, case BT_ISO_QOS: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && - sk->sk_state != BT_CONNECT2) { + sk->sk_state != BT_CONNECT2 && + (!test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags) || + sk->sk_state != BT_CONNECTED)) { err = -EINVAL; break; } - len = min_t(unsigned int, sizeof(qos), optlen); - - if (copy_from_sockptr(&qos, optval, len)) { - err = -EFAULT; - break; - } - - if (len == sizeof(qos.ucast) && !check_ucast_qos(&qos)) { - err = -EINVAL; + err = bt_copy_from_sockptr(&qos, sizeof(qos), optval, optlen); + if (err) break; - } iso_pi(sk)->qos = qos; iso_pi(sk)->qos_user_set = true; @@ -1543,18 +1545,16 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, } if (optlen > sizeof(iso_pi(sk)->base)) { - err = -EOVERFLOW; + err = -EINVAL; break; } - len = min_t(unsigned int, sizeof(iso_pi(sk)->base), optlen); - - if (copy_from_sockptr(iso_pi(sk)->base, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(iso_pi(sk)->base, optlen, optval, + optlen); + if (err) break; - } - iso_pi(sk)->base_len = len; + iso_pi(sk)->base_len = optlen; break; @@ -1744,7 +1744,7 @@ static void iso_conn_ready(struct iso_conn *conn) struct sock *sk = conn->sk; struct hci_ev_le_big_sync_estabilished *ev = NULL; struct hci_ev_le_pa_sync_established *ev2 = NULL; - struct hci_evt_le_big_info_adv_report *ev3 = NULL; + struct hci_ev_le_per_adv_report *ev3 = NULL; struct hci_conn *hcon; BT_DBG("conn %p", conn); @@ -1762,32 +1762,37 @@ static void iso_conn_ready(struct iso_conn *conn) HCI_EVT_LE_BIG_SYNC_ESTABILISHED); /* Get reference to PA sync parent socket, if it exists */ - parent = iso_get_sock_listen(&hcon->src, - &hcon->dst, - iso_match_pa_sync_flag, NULL); + parent = iso_get_sock(&hcon->src, &hcon->dst, + BT_LISTEN, + iso_match_pa_sync_flag, + NULL); if (!parent && ev) - parent = iso_get_sock_listen(&hcon->src, - &hcon->dst, - iso_match_big, ev); + parent = iso_get_sock(&hcon->src, + &hcon->dst, + BT_LISTEN, + iso_match_big, ev); } else if (test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { ev2 = hci_recv_event_data(hcon->hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev2) - parent = iso_get_sock_listen(&hcon->src, - &hcon->dst, - iso_match_sid, ev2); + parent = iso_get_sock(&hcon->src, + &hcon->dst, + BT_LISTEN, + iso_match_sid, ev2); } else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags)) { ev3 = hci_recv_event_data(hcon->hdev, - HCI_EVT_LE_BIG_INFO_ADV_REPORT); + HCI_EV_LE_PER_ADV_REPORT); if (ev3) - parent = iso_get_sock_listen(&hcon->src, - &hcon->dst, - iso_match_sync_handle, ev3); + parent = iso_get_sock(&hcon->src, + &hcon->dst, + BT_LISTEN, + iso_match_sync_handle_pa_report, + ev3); } if (!parent) - parent = iso_get_sock_listen(&hcon->src, - BDADDR_ANY, NULL, NULL); + parent = iso_get_sock(&hcon->src, BDADDR_ANY, + BT_LISTEN, NULL, NULL); if (!parent) return; @@ -1824,7 +1829,6 @@ static void iso_conn_ready(struct iso_conn *conn) if (ev3) { iso_pi(sk)->qos = iso_pi(parent)->qos; - iso_pi(sk)->qos.bcast.encryption = ev3->encryption; hcon->iso_qos = iso_pi(sk)->qos; iso_pi(sk)->bc_num_bis = iso_pi(parent)->bc_num_bis; memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis, ISO_MAX_NUM_BIS); @@ -1889,7 +1893,6 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) struct hci_evt_le_big_info_adv_report *ev2; struct hci_ev_le_per_adv_report *ev3; struct sock *sk; - int lm = 0; bt_dev_dbg(hdev, "bdaddr %pMR", bdaddr); @@ -1909,8 +1912,8 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) */ ev1 = hci_recv_event_data(hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev1) { - sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, iso_match_sid, - ev1); + sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_LISTEN, + iso_match_sid, ev1); if (sk && !ev1->status) iso_pi(sk)->sync_handle = le16_to_cpu(ev1->handle); @@ -1919,26 +1922,29 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) ev2 = hci_recv_event_data(hdev, HCI_EVT_LE_BIG_INFO_ADV_REPORT); if (ev2) { - /* Try to get PA sync listening socket, if it exists */ - sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, - iso_match_pa_sync_flag, NULL); - - if (!sk) { - sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, - iso_match_sync_handle, ev2); - - /* If PA Sync is in process of terminating, - * do not handle any more BIGInfo adv reports. - */ - - if (sk && test_bit(BT_SK_PA_SYNC_TERM, - &iso_pi(sk)->flags)) - return lm; + /* Check if BIGInfo report has already been handled */ + sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_CONNECTED, + iso_match_sync_handle, ev2); + if (sk) { + sock_put(sk); + sk = NULL; + goto done; } + /* Try to get PA sync socket, if it exists */ + sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_CONNECT2, + iso_match_sync_handle, ev2); + if (!sk) + sk = iso_get_sock(&hdev->bdaddr, bdaddr, + BT_LISTEN, + iso_match_sync_handle, + ev2); + if (sk) { int err; + iso_pi(sk)->qos.bcast.encryption = ev2->encryption; + if (ev2->num_bis < iso_pi(sk)->bc_num_bis) iso_pi(sk)->bc_num_bis = ev2->num_bis; @@ -1957,37 +1963,80 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) } } } + + goto done; } ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) { - size_t base_len = ev3->length; + size_t base_len = 0; u8 *base; + struct hci_conn *hcon; + + sk = iso_get_sock(&hdev->bdaddr, bdaddr, BT_LISTEN, + iso_match_sync_handle_pa_report, ev3); + if (!sk) + goto done; + + hcon = iso_pi(sk)->conn->hcon; + if (!hcon) + goto done; + + if (ev3->data_status == LE_PA_DATA_TRUNCATED) { + /* The controller was unable to retrieve PA data. */ + memset(hcon->le_per_adv_data, 0, + HCI_MAX_PER_AD_TOT_LEN); + hcon->le_per_adv_data_len = 0; + hcon->le_per_adv_data_offset = 0; + goto done; + } + + if (hcon->le_per_adv_data_offset + ev3->length > + HCI_MAX_PER_AD_TOT_LEN) + goto done; + + memcpy(hcon->le_per_adv_data + hcon->le_per_adv_data_offset, + ev3->data, ev3->length); + hcon->le_per_adv_data_offset += ev3->length; + + if (ev3->data_status == LE_PA_DATA_COMPLETE) { + /* All PA data has been received. */ + hcon->le_per_adv_data_len = + hcon->le_per_adv_data_offset; + hcon->le_per_adv_data_offset = 0; + + /* Extract BASE */ + base = eir_get_service_data(hcon->le_per_adv_data, + hcon->le_per_adv_data_len, + EIR_BAA_SERVICE_UUID, + &base_len); + + if (!base || base_len > BASE_MAX_LENGTH) + goto done; - sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, - iso_match_sync_handle_pa_report, ev3); - base = eir_get_service_data(ev3->data, ev3->length, - EIR_BAA_SERVICE_UUID, &base_len); - if (base && sk && base_len <= sizeof(iso_pi(sk)->base)) { memcpy(iso_pi(sk)->base, base, base_len); iso_pi(sk)->base_len = base_len; + } else { + /* This is a PA data fragment. Keep pa_data_len set to 0 + * until all data has been reassembled. + */ + hcon->le_per_adv_data_len = 0; } } else { - sk = iso_get_sock_listen(&hdev->bdaddr, BDADDR_ANY, NULL, NULL); + sk = iso_get_sock(&hdev->bdaddr, BDADDR_ANY, + BT_LISTEN, NULL, NULL); } done: if (!sk) - return lm; - - lm |= HCI_LM_ACCEPT; + return 0; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; sock_put(sk); - return lm; + return HCI_LM_ACCEPT; } static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 656f49b299d20..9394a158d1b1a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -39,8 +39,6 @@ #include #include "smp.h" -#include "a2mp.h" -#include "amp.h" #define LE_FLOWCTL_MAX_CREDITS 65535 @@ -167,24 +165,6 @@ static struct l2cap_chan *__l2cap_get_chan_by_ident(struct l2cap_conn *conn, return NULL; } -static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn, - u8 ident) -{ - struct l2cap_chan *c; - - mutex_lock(&conn->chan_lock); - c = __l2cap_get_chan_by_ident(conn, ident); - if (c) { - /* Only lock if chan reference is not 0 */ - c = l2cap_chan_hold_unless_zero(c); - if (c) - l2cap_chan_lock(c); - } - mutex_unlock(&conn->chan_lock); - - return c; -} - static struct l2cap_chan *__l2cap_global_chan_by_addr(__le16 psm, bdaddr_t *src, u8 src_type) { @@ -435,6 +415,9 @@ static void l2cap_chan_timeout(struct work_struct *work) BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); + if (!conn) + return; + mutex_lock(&conn->chan_lock); /* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling * this work. No need to call l2cap_chan_hold(chan) here again. @@ -474,6 +457,9 @@ struct l2cap_chan *l2cap_chan_create(void) /* Set default lock nesting level */ atomic_set(&chan->nesting, L2CAP_NESTING_NORMAL); + /* Available receive buffer space is initially unknown */ + chan->rx_avail = -1; + write_lock(&chan_list_lock); list_add(&chan->global_l, &chan_list); write_unlock(&chan_list_lock); @@ -555,6 +541,28 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) } EXPORT_SYMBOL_GPL(l2cap_chan_set_defaults); +static __u16 l2cap_le_rx_credits(struct l2cap_chan *chan) +{ + size_t sdu_len = chan->sdu ? chan->sdu->len : 0; + + if (chan->mps == 0) + return 0; + + /* If we don't know the available space in the receiver buffer, give + * enough credits for a full packet. + */ + if (chan->rx_avail == -1) + return (chan->imtu / chan->mps) + 1; + + /* If we know how much space is available in the receive buffer, give + * out as many credits as would fill the buffer. + */ + if (chan->rx_avail <= sdu_len) + return 0; + + return DIV_ROUND_UP(chan->rx_avail - sdu_len, chan->mps); +} + static void l2cap_le_flowctl_init(struct l2cap_chan *chan, u16 tx_credits) { chan->sdu = NULL; @@ -563,8 +571,7 @@ static void l2cap_le_flowctl_init(struct l2cap_chan *chan, u16 tx_credits) chan->tx_credits = tx_credits; /* Derive MPS from connection MTU to stop HCI fragmentation */ chan->mps = min_t(u16, chan->imtu, chan->conn->mtu - L2CAP_HDR_SIZE); - /* Give enough credits for a full packet */ - chan->rx_credits = (chan->imtu / chan->mps) + 1; + chan->rx_credits = l2cap_le_rx_credits(chan); skb_queue_head_init(&chan->tx_q); } @@ -576,7 +583,7 @@ static void l2cap_ecred_init(struct l2cap_chan *chan, u16 tx_credits) /* L2CAP implementations shall support a minimum MPS of 64 octets */ if (chan->mps < L2CAP_ECRED_MIN_MPS) { chan->mps = L2CAP_ECRED_MIN_MPS; - chan->rx_credits = (chan->imtu / chan->mps) + 1; + chan->rx_credits = l2cap_le_rx_credits(chan); } } @@ -651,7 +658,6 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) chan->ops->teardown(chan, err); if (conn) { - struct amp_mgr *mgr = conn->hcon->amp_mgr; /* Delete from channel list */ list_del(&chan->list); @@ -666,16 +672,6 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) if (chan->chan_type != L2CAP_CHAN_FIXED || test_bit(FLAG_HOLD_HCI_CONN, &chan->flags)) hci_conn_drop(conn->hcon); - - if (mgr && mgr->bredr_chan == chan) - mgr->bredr_chan = NULL; - } - - if (chan->hs_hchan) { - struct hci_chan *hs_hchan = chan->hs_hchan; - - BT_DBG("chan %p disconnect hs_hchan %p", chan, hs_hchan); - amp_disconnect_logical_link(hs_hchan); } if (test_bit(CONF_NOT_COMPLETE, &chan->conf_state)) @@ -977,12 +973,6 @@ static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, hci_send_acl(conn->hchan, skb, flags); } -static bool __chan_is_moving(struct l2cap_chan *chan) -{ - return chan->move_state != L2CAP_MOVE_STABLE && - chan->move_state != L2CAP_MOVE_WAIT_PREPARE; -} - static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) { struct hci_conn *hcon = chan->conn->hcon; @@ -991,15 +981,6 @@ static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) BT_DBG("chan %p, skb %p len %d priority %u", chan, skb, skb->len, skb->priority); - if (chan->hs_hcon && !__chan_is_moving(chan)) { - if (chan->hs_hchan) - hci_send_acl(chan->hs_hchan, skb, ACL_COMPLETE); - else - kfree_skb(skb); - - return; - } - /* Use NO_FLUSH for LE links (where this is the only option) or * if the BR/EDR link supports it and flushing has not been * explicitly requested (through FLAG_FLUSHABLE). @@ -1180,9 +1161,6 @@ static void l2cap_send_sframe(struct l2cap_chan *chan, if (!control->sframe) return; - if (__chan_is_moving(chan)) - return; - if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state) && !control->poll) control->final = 1; @@ -1237,40 +1215,6 @@ static inline int __l2cap_no_conn_pending(struct l2cap_chan *chan) return !test_bit(CONF_CONNECT_PEND, &chan->conf_state); } -static bool __amp_capable(struct l2cap_chan *chan) -{ - struct l2cap_conn *conn = chan->conn; - struct hci_dev *hdev; - bool amp_available = false; - - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) - return false; - - if (!(conn->remote_fixed_chan & L2CAP_FC_A2MP)) - return false; - - read_lock(&hci_dev_list_lock); - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->amp_type != AMP_TYPE_BREDR && - test_bit(HCI_UP, &hdev->flags)) { - amp_available = true; - break; - } - } - read_unlock(&hci_dev_list_lock); - - if (chan->chan_policy == BT_CHANNEL_POLICY_AMP_PREFERRED) - return amp_available; - - return false; -} - -static bool l2cap_check_efs(struct l2cap_chan *chan) -{ - /* Check EFS parameters */ - return true; -} - void l2cap_send_conn_req(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; @@ -1286,76 +1230,6 @@ void l2cap_send_conn_req(struct l2cap_chan *chan) l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_REQ, sizeof(req), &req); } -static void l2cap_send_create_chan_req(struct l2cap_chan *chan, u8 amp_id) -{ - struct l2cap_create_chan_req req; - req.scid = cpu_to_le16(chan->scid); - req.psm = chan->psm; - req.amp_id = amp_id; - - chan->ident = l2cap_get_ident(chan->conn); - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_REQ, - sizeof(req), &req); -} - -static void l2cap_move_setup(struct l2cap_chan *chan) -{ - struct sk_buff *skb; - - BT_DBG("chan %p", chan); - - if (chan->mode != L2CAP_MODE_ERTM) - return; - - __clear_retrans_timer(chan); - __clear_monitor_timer(chan); - __clear_ack_timer(chan); - - chan->retry_count = 0; - skb_queue_walk(&chan->tx_q, skb) { - if (bt_cb(skb)->l2cap.retries) - bt_cb(skb)->l2cap.retries = 1; - else - break; - } - - chan->expected_tx_seq = chan->buffer_seq; - - clear_bit(CONN_REJ_ACT, &chan->conn_state); - clear_bit(CONN_SREJ_ACT, &chan->conn_state); - l2cap_seq_list_clear(&chan->retrans_list); - l2cap_seq_list_clear(&chan->srej_list); - skb_queue_purge(&chan->srej_q); - - chan->tx_state = L2CAP_TX_STATE_XMIT; - chan->rx_state = L2CAP_RX_STATE_MOVE; - - set_bit(CONN_REMOTE_BUSY, &chan->conn_state); -} - -static void l2cap_move_done(struct l2cap_chan *chan) -{ - u8 move_role = chan->move_role; - BT_DBG("chan %p", chan); - - chan->move_state = L2CAP_MOVE_STABLE; - chan->move_role = L2CAP_MOVE_ROLE_NONE; - - if (chan->mode != L2CAP_MODE_ERTM) - return; - - switch (move_role) { - case L2CAP_MOVE_ROLE_INITIATOR: - l2cap_tx(chan, NULL, NULL, L2CAP_EV_EXPLICIT_POLL); - chan->rx_state = L2CAP_RX_STATE_WAIT_F; - break; - case L2CAP_MOVE_ROLE_RESPONDER: - chan->rx_state = L2CAP_RX_STATE_WAIT_P; - break; - } -} - static void l2cap_chan_ready(struct l2cap_chan *chan) { /* The channel may have already been flagged as connected in @@ -1505,10 +1379,7 @@ static void l2cap_le_start(struct l2cap_chan *chan) static void l2cap_start_connection(struct l2cap_chan *chan) { - if (__amp_capable(chan)) { - BT_DBG("chan %p AMP capable: discover AMPs", chan); - a2mp_discover_amp(chan); - } else if (chan->conn->hcon->type == LE_LINK) { + if (chan->conn->hcon->type == LE_LINK) { l2cap_le_start(chan); } else { l2cap_send_conn_req(chan); @@ -1611,11 +1482,6 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err) __clear_ack_timer(chan); } - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_state_change(chan, BT_DISCONN); - return; - } - req.dcid = cpu_to_le16(chan->dcid); req.scid = cpu_to_le16(chan->scid); l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_DISCONN_REQ, @@ -1754,11 +1620,6 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) l2cap_chan_lock(chan); - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_chan_unlock(chan); - continue; - } - if (hcon->type == LE_LINK) { l2cap_le_start(chan); } else if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { @@ -2067,9 +1928,6 @@ static void l2cap_streaming_send(struct l2cap_chan *chan, BT_DBG("chan %p, skbs %p", chan, skbs); - if (__chan_is_moving(chan)) - return; - skb_queue_splice_tail_init(skbs, &chan->tx_q); while (!skb_queue_empty(&chan->tx_q)) { @@ -2112,9 +1970,6 @@ static int l2cap_ertm_send(struct l2cap_chan *chan) if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return 0; - if (__chan_is_moving(chan)) - return 0; - while (chan->tx_send_head && chan->unacked_frames < chan->remote_tx_win && chan->tx_state == L2CAP_TX_STATE_XMIT) { @@ -2180,9 +2035,6 @@ static void l2cap_ertm_resend(struct l2cap_chan *chan) if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return; - if (__chan_is_moving(chan)) - return; - while (chan->retrans_list.head != L2CAP_SEQ_LIST_CLEAR) { seq = l2cap_seq_list_pop(&chan->retrans_list); @@ -2522,8 +2374,7 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, pdu_len = chan->conn->mtu; /* Constrain PDU size for BR/EDR connections */ - if (!chan->hs_hcon) - pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); + pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); /* Adjust for largest possible L2CAP overhead. */ if (chan->fcs) @@ -3287,11 +3138,6 @@ int l2cap_ertm_init(struct l2cap_chan *chan) skb_queue_head_init(&chan->tx_q); - chan->local_amp_id = AMP_ID_BREDR; - chan->move_id = AMP_ID_BREDR; - chan->move_state = L2CAP_MOVE_STABLE; - chan->move_role = L2CAP_MOVE_ROLE_NONE; - if (chan->mode != L2CAP_MODE_ERTM) return 0; @@ -3326,52 +3172,19 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask) static inline bool __l2cap_ews_supported(struct l2cap_conn *conn) { - return ((conn->local_fixed_chan & L2CAP_FC_A2MP) && - (conn->feat_mask & L2CAP_FEAT_EXT_WINDOW)); + return (conn->feat_mask & L2CAP_FEAT_EXT_WINDOW); } static inline bool __l2cap_efs_supported(struct l2cap_conn *conn) { - return ((conn->local_fixed_chan & L2CAP_FC_A2MP) && - (conn->feat_mask & L2CAP_FEAT_EXT_FLOW)); + return (conn->feat_mask & L2CAP_FEAT_EXT_FLOW); } static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan, struct l2cap_conf_rfc *rfc) { - if (chan->local_amp_id != AMP_ID_BREDR && chan->hs_hcon) { - u64 ertm_to = chan->hs_hcon->hdev->amp_be_flush_to; - - /* Class 1 devices have must have ERTM timeouts - * exceeding the Link Supervision Timeout. The - * default Link Supervision Timeout for AMP - * controllers is 10 seconds. - * - * Class 1 devices use 0xffffffff for their - * best-effort flush timeout, so the clamping logic - * will result in a timeout that meets the above - * requirement. ERTM timeouts are 16-bit values, so - * the maximum timeout is 65.535 seconds. - */ - - /* Convert timeout to milliseconds and round */ - ertm_to = DIV_ROUND_UP_ULL(ertm_to, 1000); - - /* This is the recommended formula for class 2 devices - * that start ERTM timers when packets are sent to the - * controller. - */ - ertm_to = 3 * ertm_to + 500; - - if (ertm_to > 0xffff) - ertm_to = 0xffff; - - rfc->retrans_timeout = cpu_to_le16((u16) ertm_to); - rfc->monitor_timeout = rfc->retrans_timeout; - } else { - rfc->retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); - rfc->monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); - } + rfc->retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); + rfc->monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); } static inline void l2cap_txwin_setup(struct l2cap_chan *chan) @@ -3623,13 +3436,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data case L2CAP_CONF_EWS: if (olen != 2) break; - if (!(chan->conn->local_fixed_chan & L2CAP_FC_A2MP)) - return -ECONNREFUSED; - set_bit(FLAG_EXT_CTRL, &chan->flags); - set_bit(CONF_EWS_RECV, &chan->conf_state); - chan->tx_win_max = L2CAP_DEFAULT_EXT_WINDOW; - chan->remote_tx_win = val; - break; + return -ECONNREFUSED; default: if (hint) @@ -4027,11 +3834,7 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) rsp.dcid = cpu_to_le16(chan->scid); rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - - if (chan->hs_hcon) - rsp_code = L2CAP_CREATE_CHAN_RSP; - else - rsp_code = L2CAP_CONN_RSP; + rsp_code = L2CAP_CONN_RSP; BT_DBG("chan %p rsp_code %u", chan, rsp_code); @@ -4126,13 +3929,12 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, return 0; } -static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u8 *data, u8 rsp_code, u8 amp_id) +static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, + u8 *data, u8 rsp_code) { struct l2cap_conn_req *req = (struct l2cap_conn_req *) data; struct l2cap_conn_rsp rsp; - struct l2cap_chan *chan = NULL, *pchan; + struct l2cap_chan *chan = NULL, *pchan = NULL; int result, status = L2CAP_CS_NO_INFO; u16 dcid = 0, scid = __le16_to_cpu(req->scid); @@ -4145,7 +3947,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, &conn->hcon->dst, ACL_LINK); if (!pchan) { result = L2CAP_CR_BAD_PSM; - goto sendresp; + goto response; } mutex_lock(&conn->chan_lock); @@ -4190,7 +3992,6 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, chan->dst_type = bdaddr_dst_type(conn->hcon); chan->psm = psm; chan->dcid = scid; - chan->local_amp_id = amp_id; __l2cap_chan_add(conn, chan); @@ -4208,17 +4009,8 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, status = L2CAP_CS_AUTHOR_PEND; chan->ops->defer(chan); } else { - /* Force pending result for AMP controllers. - * The connection will succeed after the - * physical link is up. - */ - if (amp_id == AMP_ID_BREDR) { - l2cap_state_change(chan, BT_CONFIG); - result = L2CAP_CR_SUCCESS; - } else { - l2cap_state_change(chan, BT_CONNECT2); - result = L2CAP_CR_PEND; - } + l2cap_state_change(chan, BT_CONFIG); + result = L2CAP_CR_SUCCESS; status = L2CAP_CS_NO_INFO; } } else { @@ -4233,17 +4025,15 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, } response: - l2cap_chan_unlock(pchan); - mutex_unlock(&conn->chan_lock); - l2cap_chan_put(pchan); - -sendresp: rsp.scid = cpu_to_le16(scid); rsp.dcid = cpu_to_le16(dcid); rsp.result = cpu_to_le16(result); rsp.status = cpu_to_le16(status); l2cap_send_cmd(conn, cmd->ident, rsp_code, sizeof(rsp), &rsp); + if (!pchan) + return; + if (result == L2CAP_CR_PEND && status == L2CAP_CS_NO_INFO) { struct l2cap_info_req info; info.type = cpu_to_le16(L2CAP_IT_FEAT_MASK); @@ -4266,7 +4056,9 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, chan->num_conf_req++; } - return chan; + l2cap_chan_unlock(pchan); + mutex_unlock(&conn->chan_lock); + l2cap_chan_put(pchan); } static int l2cap_connect_req(struct l2cap_conn *conn, @@ -4279,12 +4071,11 @@ static int l2cap_connect_req(struct l2cap_conn *conn, return -EPROTO; hci_dev_lock(hdev); - if (hci_dev_test_flag(hdev, HCI_MGMT) && - !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_device_connected(hdev, hcon, NULL, 0); hci_dev_unlock(hdev); - l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0); + l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP); return 0; } @@ -4516,10 +4307,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, /* check compatibility */ /* Send rsp for BR/EDR channel */ - if (!chan->hs_hcon) - l2cap_send_efs_conf_rsp(chan, rsp, cmd->ident, flags); - else - chan->ident = cmd->ident; + l2cap_send_efs_conf_rsp(chan, rsp, cmd->ident, flags); } unlock: @@ -4571,15 +4359,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, goto done; } - if (!chan->hs_hcon) { - l2cap_send_efs_conf_rsp(chan, buf, cmd->ident, - 0); - } else { - if (l2cap_check_efs(chan)) { - amp_create_logical_link(chan); - chan->ident = cmd->ident; - } - } + l2cap_send_efs_conf_rsp(chan, buf, cmd->ident, 0); } goto done; @@ -4750,9 +4530,6 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, if (!disable_ertm) feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING | L2CAP_FEAT_FCS; - if (conn->local_fixed_chan & L2CAP_FC_A2MP) - feat_mask |= L2CAP_FEAT_EXT_FLOW - | L2CAP_FEAT_EXT_WINDOW; put_unaligned_le32(feat_mask, rsp->data); l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf), @@ -4841,860 +4618,109 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, return 0; } -static int l2cap_create_channel_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) +static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, + u16 cmd_len, u8 *data) { - struct l2cap_create_chan_req *req = data; - struct l2cap_create_chan_rsp rsp; - struct l2cap_chan *chan; - struct hci_dev *hdev; - u16 psm, scid; - - if (cmd_len != sizeof(*req)) - return -EPROTO; + struct hci_conn *hcon = conn->hcon; + struct l2cap_conn_param_update_req *req; + struct l2cap_conn_param_update_rsp rsp; + u16 min, max, latency, to_multiplier; + int err; - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) + if (hcon->role != HCI_ROLE_MASTER) return -EINVAL; - psm = le16_to_cpu(req->psm); - scid = le16_to_cpu(req->scid); - - BT_DBG("psm 0x%2.2x, scid 0x%4.4x, amp_id %d", psm, scid, req->amp_id); - - /* For controller id 0 make BR/EDR connection */ - if (req->amp_id == AMP_ID_BREDR) { - l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP, - req->amp_id); - return 0; - } - - /* Validate AMP controller id */ - hdev = hci_dev_get(req->amp_id); - if (!hdev) - goto error; + if (cmd_len != sizeof(struct l2cap_conn_param_update_req)) + return -EPROTO; - if (hdev->dev_type != HCI_AMP || !test_bit(HCI_UP, &hdev->flags)) { - hci_dev_put(hdev); - goto error; - } + req = (struct l2cap_conn_param_update_req *) data; + min = __le16_to_cpu(req->min); + max = __le16_to_cpu(req->max); + latency = __le16_to_cpu(req->latency); + to_multiplier = __le16_to_cpu(req->to_multiplier); - chan = l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP, - req->amp_id); - if (chan) { - struct amp_mgr *mgr = conn->hcon->amp_mgr; - struct hci_conn *hs_hcon; - - hs_hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, - &conn->hcon->dst); - if (!hs_hcon) { - hci_dev_put(hdev); - cmd_reject_invalid_cid(conn, cmd->ident, chan->scid, - chan->dcid); - return 0; - } + BT_DBG("min 0x%4.4x max 0x%4.4x latency: 0x%4.4x Timeout: 0x%4.4x", + min, max, latency, to_multiplier); - BT_DBG("mgr %p bredr_chan %p hs_hcon %p", mgr, chan, hs_hcon); + memset(&rsp, 0, sizeof(rsp)); - mgr->bredr_chan = chan; - chan->hs_hcon = hs_hcon; - chan->fcs = L2CAP_FCS_NONE; - conn->mtu = hdev->block_mtu; - } + err = hci_check_conn_params(min, max, latency, to_multiplier); + if (err) + rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); + else + rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED); - hci_dev_put(hdev); + l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP, + sizeof(rsp), &rsp); - return 0; + if (!err) { + u8 store_hint; -error: - rsp.dcid = 0; - rsp.scid = cpu_to_le16(scid); - rsp.result = cpu_to_le16(L2CAP_CR_BAD_AMP); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); + store_hint = hci_le_conn_update(hcon, min, max, latency, + to_multiplier); + mgmt_new_conn_param(hcon->hdev, &hcon->dst, hcon->dst_type, + store_hint, min, max, latency, + to_multiplier); - l2cap_send_cmd(conn, cmd->ident, L2CAP_CREATE_CHAN_RSP, - sizeof(rsp), &rsp); + } return 0; } -static void l2cap_send_move_chan_req(struct l2cap_chan *chan, u8 dest_amp_id) +static int l2cap_le_connect_rsp(struct l2cap_conn *conn, + struct l2cap_cmd_hdr *cmd, u16 cmd_len, + u8 *data) { - struct l2cap_move_chan_req req; - u8 ident; - - BT_DBG("chan %p, dest_amp_id %d", chan, dest_amp_id); + struct l2cap_le_conn_rsp *rsp = (struct l2cap_le_conn_rsp *) data; + struct hci_conn *hcon = conn->hcon; + u16 dcid, mtu, mps, credits, result; + struct l2cap_chan *chan; + int err, sec_level; - ident = l2cap_get_ident(chan->conn); - chan->ident = ident; + if (cmd_len < sizeof(*rsp)) + return -EPROTO; - req.icid = cpu_to_le16(chan->scid); - req.dest_amp_id = dest_amp_id; + dcid = __le16_to_cpu(rsp->dcid); + mtu = __le16_to_cpu(rsp->mtu); + mps = __le16_to_cpu(rsp->mps); + credits = __le16_to_cpu(rsp->credits); + result = __le16_to_cpu(rsp->result); - l2cap_send_cmd(chan->conn, ident, L2CAP_MOVE_CHAN_REQ, sizeof(req), - &req); + if (result == L2CAP_CR_LE_SUCCESS && (mtu < 23 || mps < 23 || + dcid < L2CAP_CID_DYN_START || + dcid > L2CAP_CID_LE_DYN_END)) + return -EPROTO; - __set_chan_timer(chan, L2CAP_MOVE_TIMEOUT); -} + BT_DBG("dcid 0x%4.4x mtu %u mps %u credits %u result 0x%2.2x", + dcid, mtu, mps, credits, result); -static void l2cap_send_move_chan_rsp(struct l2cap_chan *chan, u16 result) -{ - struct l2cap_move_chan_rsp rsp; + mutex_lock(&conn->chan_lock); - BT_DBG("chan %p, result 0x%4.4x", chan, result); + chan = __l2cap_get_chan_by_ident(conn, cmd->ident); + if (!chan) { + err = -EBADSLT; + goto unlock; + } - rsp.icid = cpu_to_le16(chan->dcid); - rsp.result = cpu_to_le16(result); + err = 0; - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_RSP, - sizeof(rsp), &rsp); -} + l2cap_chan_lock(chan); -static void l2cap_send_move_chan_cfm(struct l2cap_chan *chan, u16 result) -{ - struct l2cap_move_chan_cfm cfm; + switch (result) { + case L2CAP_CR_LE_SUCCESS: + if (__l2cap_get_chan_by_dcid(conn, dcid)) { + err = -EBADSLT; + break; + } - BT_DBG("chan %p, result 0x%4.4x", chan, result); - - chan->ident = l2cap_get_ident(chan->conn); - - cfm.icid = cpu_to_le16(chan->scid); - cfm.result = cpu_to_le16(result); - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_CFM, - sizeof(cfm), &cfm); - - __set_chan_timer(chan, L2CAP_MOVE_TIMEOUT); -} - -static void l2cap_send_move_chan_cfm_icid(struct l2cap_conn *conn, u16 icid) -{ - struct l2cap_move_chan_cfm cfm; - - BT_DBG("conn %p, icid 0x%4.4x", conn, icid); - - cfm.icid = cpu_to_le16(icid); - cfm.result = cpu_to_le16(L2CAP_MC_UNCONFIRMED); - - l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_MOVE_CHAN_CFM, - sizeof(cfm), &cfm); -} - -static void l2cap_send_move_chan_cfm_rsp(struct l2cap_conn *conn, u8 ident, - u16 icid) -{ - struct l2cap_move_chan_cfm_rsp rsp; - - BT_DBG("icid 0x%4.4x", icid); - - rsp.icid = cpu_to_le16(icid); - l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_CFM_RSP, sizeof(rsp), &rsp); -} - -static void __release_logical_link(struct l2cap_chan *chan) -{ - chan->hs_hchan = NULL; - chan->hs_hcon = NULL; - - /* Placeholder - release the logical link */ -} - -static void l2cap_logical_fail(struct l2cap_chan *chan) -{ - /* Logical link setup failed */ - if (chan->state != BT_CONNECTED) { - /* Create channel failure, disconnect */ - l2cap_send_disconn_req(chan, ECONNRESET); - return; - } - - switch (chan->move_role) { - case L2CAP_MOVE_ROLE_RESPONDER: - l2cap_move_done(chan); - l2cap_send_move_chan_rsp(chan, L2CAP_MR_NOT_SUPP); - break; - case L2CAP_MOVE_ROLE_INITIATOR: - if (chan->move_state == L2CAP_MOVE_WAIT_LOGICAL_COMP || - chan->move_state == L2CAP_MOVE_WAIT_LOGICAL_CFM) { - /* Remote has only sent pending or - * success responses, clean up - */ - l2cap_move_done(chan); - } - - /* Other amp move states imply that the move - * has already aborted - */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - break; - } -} - -static void l2cap_logical_finish_create(struct l2cap_chan *chan, - struct hci_chan *hchan) -{ - struct l2cap_conf_rsp rsp; - - chan->hs_hchan = hchan; - chan->hs_hcon->l2cap_data = chan->conn; - - l2cap_send_efs_conf_rsp(chan, &rsp, chan->ident, 0); - - if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) { - int err; - - set_default_fcs(chan); - - err = l2cap_ertm_init(chan); - if (err < 0) - l2cap_send_disconn_req(chan, -err); - else - l2cap_chan_ready(chan); - } -} - -static void l2cap_logical_finish_move(struct l2cap_chan *chan, - struct hci_chan *hchan) -{ - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - - BT_DBG("move_state %d", chan->move_state); - - switch (chan->move_state) { - case L2CAP_MOVE_WAIT_LOGICAL_COMP: - /* Move confirm will be sent after a success - * response is received - */ - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - break; - case L2CAP_MOVE_WAIT_LOGICAL_CFM: - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - } else if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP; - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } else if (chan->move_role == L2CAP_MOVE_ROLE_RESPONDER) { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - l2cap_send_move_chan_rsp(chan, L2CAP_MR_SUCCESS); - } - break; - default: - /* Move was not in expected state, free the channel */ - __release_logical_link(chan); - - chan->move_state = L2CAP_MOVE_STABLE; - } -} - -/* Call with chan locked */ -void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, - u8 status) -{ - BT_DBG("chan %p, hchan %p, status %d", chan, hchan, status); - - if (status) { - l2cap_logical_fail(chan); - __release_logical_link(chan); - return; - } - - if (chan->state != BT_CONNECTED) { - /* Ignore logical link if channel is on BR/EDR */ - if (chan->local_amp_id != AMP_ID_BREDR) - l2cap_logical_finish_create(chan, hchan); - } else { - l2cap_logical_finish_move(chan, hchan); - } -} - -void l2cap_move_start(struct l2cap_chan *chan) -{ - BT_DBG("chan %p", chan); - - if (chan->local_amp_id == AMP_ID_BREDR) { - if (chan->chan_policy != BT_CHANNEL_POLICY_AMP_PREFERRED) - return; - chan->move_role = L2CAP_MOVE_ROLE_INITIATOR; - chan->move_state = L2CAP_MOVE_WAIT_PREPARE; - /* Placeholder - start physical link setup */ - } else { - chan->move_role = L2CAP_MOVE_ROLE_INITIATOR; - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - chan->move_id = 0; - l2cap_move_setup(chan); - l2cap_send_move_chan_req(chan, 0); - } -} - -static void l2cap_do_create(struct l2cap_chan *chan, int result, - u8 local_amp_id, u8 remote_amp_id) -{ - BT_DBG("chan %p state %s %u -> %u", chan, state_to_string(chan->state), - local_amp_id, remote_amp_id); - - chan->fcs = L2CAP_FCS_NONE; - - /* Outgoing channel on AMP */ - if (chan->state == BT_CONNECT) { - if (result == L2CAP_CR_SUCCESS) { - chan->local_amp_id = local_amp_id; - l2cap_send_create_chan_req(chan, remote_amp_id); - } else { - /* Revert to BR/EDR connect */ - l2cap_send_conn_req(chan); - } - - return; - } - - /* Incoming channel on AMP */ - if (__l2cap_no_conn_pending(chan)) { - struct l2cap_conn_rsp rsp; - char buf[128]; - rsp.scid = cpu_to_le16(chan->dcid); - rsp.dcid = cpu_to_le16(chan->scid); - - if (result == L2CAP_CR_SUCCESS) { - /* Send successful response */ - rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - } else { - /* Send negative response */ - rsp.result = cpu_to_le16(L2CAP_CR_NO_MEM); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - } - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_RSP, - sizeof(rsp), &rsp); - - if (result == L2CAP_CR_SUCCESS) { - l2cap_state_change(chan, BT_CONFIG); - set_bit(CONF_REQ_SENT, &chan->conf_state); - l2cap_send_cmd(chan->conn, l2cap_get_ident(chan->conn), - L2CAP_CONF_REQ, - l2cap_build_conf_req(chan, buf, sizeof(buf)), buf); - chan->num_conf_req++; - } - } -} - -static void l2cap_do_move_initiate(struct l2cap_chan *chan, u8 local_amp_id, - u8 remote_amp_id) -{ - l2cap_move_setup(chan); - chan->move_id = local_amp_id; - chan->move_state = L2CAP_MOVE_WAIT_RSP; - - l2cap_send_move_chan_req(chan, remote_amp_id); -} - -static void l2cap_do_move_respond(struct l2cap_chan *chan, int result) -{ - struct hci_chan *hchan = NULL; - - /* Placeholder - get hci_chan for logical link */ - - if (hchan) { - if (hchan->state == BT_CONNECTED) { - /* Logical link is ready to go */ - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - l2cap_send_move_chan_rsp(chan, L2CAP_MR_SUCCESS); - - l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS); - } else { - /* Wait for logical link to be ready */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - } - } else { - /* Logical link not available */ - l2cap_send_move_chan_rsp(chan, L2CAP_MR_NOT_ALLOWED); - } -} - -static void l2cap_do_move_cancel(struct l2cap_chan *chan, int result) -{ - if (chan->move_role == L2CAP_MOVE_ROLE_RESPONDER) { - u8 rsp_result; - if (result == -EINVAL) - rsp_result = L2CAP_MR_BAD_ID; - else - rsp_result = L2CAP_MR_NOT_ALLOWED; - - l2cap_send_move_chan_rsp(chan, rsp_result); - } - - chan->move_role = L2CAP_MOVE_ROLE_NONE; - chan->move_state = L2CAP_MOVE_STABLE; - - /* Restart data transmission */ - l2cap_ertm_send(chan); -} - -/* Invoke with locked chan */ -void __l2cap_physical_cfm(struct l2cap_chan *chan, int result) -{ - u8 local_amp_id = chan->local_amp_id; - u8 remote_amp_id = chan->remote_amp_id; - - BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d", - chan, result, local_amp_id, remote_amp_id); - - if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) - return; - - if (chan->state != BT_CONNECTED) { - l2cap_do_create(chan, result, local_amp_id, remote_amp_id); - } else if (result != L2CAP_MR_SUCCESS) { - l2cap_do_move_cancel(chan, result); - } else { - switch (chan->move_role) { - case L2CAP_MOVE_ROLE_INITIATOR: - l2cap_do_move_initiate(chan, local_amp_id, - remote_amp_id); - break; - case L2CAP_MOVE_ROLE_RESPONDER: - l2cap_do_move_respond(chan, result); - break; - default: - l2cap_do_move_cancel(chan, result); - break; - } - } -} - -static inline int l2cap_move_channel_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_req *req = data; - struct l2cap_move_chan_rsp rsp; - struct l2cap_chan *chan; - u16 icid = 0; - u16 result = L2CAP_MR_NOT_ALLOWED; - - if (cmd_len != sizeof(*req)) - return -EPROTO; - - icid = le16_to_cpu(req->icid); - - BT_DBG("icid 0x%4.4x, dest_amp_id %d", icid, req->dest_amp_id); - - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) - return -EINVAL; - - chan = l2cap_get_chan_by_dcid(conn, icid); - if (!chan) { - rsp.icid = cpu_to_le16(icid); - rsp.result = cpu_to_le16(L2CAP_MR_NOT_ALLOWED); - l2cap_send_cmd(conn, cmd->ident, L2CAP_MOVE_CHAN_RSP, - sizeof(rsp), &rsp); - return 0; - } - - chan->ident = cmd->ident; - - if (chan->scid < L2CAP_CID_DYN_START || - chan->chan_policy == BT_CHANNEL_POLICY_BREDR_ONLY || - (chan->mode != L2CAP_MODE_ERTM && - chan->mode != L2CAP_MODE_STREAMING)) { - result = L2CAP_MR_NOT_ALLOWED; - goto send_move_response; - } - - if (chan->local_amp_id == req->dest_amp_id) { - result = L2CAP_MR_SAME_ID; - goto send_move_response; - } - - if (req->dest_amp_id != AMP_ID_BREDR) { - struct hci_dev *hdev; - hdev = hci_dev_get(req->dest_amp_id); - if (!hdev || hdev->dev_type != HCI_AMP || - !test_bit(HCI_UP, &hdev->flags)) { - if (hdev) - hci_dev_put(hdev); - - result = L2CAP_MR_BAD_ID; - goto send_move_response; - } - hci_dev_put(hdev); - } - - /* Detect a move collision. Only send a collision response - * if this side has "lost", otherwise proceed with the move. - * The winner has the larger bd_addr. - */ - if ((__chan_is_moving(chan) || - chan->move_role != L2CAP_MOVE_ROLE_NONE) && - bacmp(&conn->hcon->src, &conn->hcon->dst) > 0) { - result = L2CAP_MR_COLLISION; - goto send_move_response; - } - - chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; - l2cap_move_setup(chan); - chan->move_id = req->dest_amp_id; - - if (req->dest_amp_id == AMP_ID_BREDR) { - /* Moving to BR/EDR */ - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - result = L2CAP_MR_PEND; - } else { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - result = L2CAP_MR_SUCCESS; - } - } else { - chan->move_state = L2CAP_MOVE_WAIT_PREPARE; - /* Placeholder - uncomment when amp functions are available */ - /*amp_accept_physical(chan, req->dest_amp_id);*/ - result = L2CAP_MR_PEND; - } - -send_move_response: - l2cap_send_move_chan_rsp(chan, result); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - -static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result) -{ - struct l2cap_chan *chan; - struct hci_chan *hchan = NULL; - - chan = l2cap_get_chan_by_scid(conn, icid); - if (!chan) { - l2cap_send_move_chan_cfm_icid(conn, icid); - return; - } - - __clear_chan_timer(chan); - if (result == L2CAP_MR_PEND) - __set_chan_timer(chan, L2CAP_MOVE_ERTX_TIMEOUT); - - switch (chan->move_state) { - case L2CAP_MOVE_WAIT_LOGICAL_COMP: - /* Move confirm will be sent when logical link - * is complete. - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - break; - case L2CAP_MOVE_WAIT_RSP_SUCCESS: - if (result == L2CAP_MR_PEND) { - break; - } else if (test_bit(CONN_LOCAL_BUSY, - &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - } else { - /* Logical link is up or moving to BR/EDR, - * proceed with move - */ - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP; - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } - break; - case L2CAP_MOVE_WAIT_RSP: - /* Moving to AMP */ - if (result == L2CAP_MR_SUCCESS) { - /* Remote is ready, send confirm immediately - * after logical link is ready - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - } else { - /* Both logical link and move success - * are required to confirm - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_COMP; - } - - /* Placeholder - get hci_chan for logical link */ - if (!hchan) { - /* Logical link not available */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - break; - } - - /* If the logical link is not yet connected, do not - * send confirmation. - */ - if (hchan->state != BT_CONNECTED) - break; - - /* Logical link is already ready to go */ - - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - - if (result == L2CAP_MR_SUCCESS) { - /* Can confirm now */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } else { - /* Now only need move success - * to confirm - */ - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - } - - l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS); - break; - default: - /* Any other amp move state means the move failed. */ - chan->move_id = chan->local_amp_id; - l2cap_move_done(chan); - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - } - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); -} - -static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, - u16 result) -{ - struct l2cap_chan *chan; - - chan = l2cap_get_chan_by_ident(conn, ident); - if (!chan) { - /* Could not locate channel, icid is best guess */ - l2cap_send_move_chan_cfm_icid(conn, icid); - return; - } - - __clear_chan_timer(chan); - - if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) { - if (result == L2CAP_MR_COLLISION) { - chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; - } else { - /* Cleanup - cancel move */ - chan->move_id = chan->local_amp_id; - l2cap_move_done(chan); - } - } - - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); -} - -static int l2cap_move_channel_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_rsp *rsp = data; - u16 icid, result; - - if (cmd_len != sizeof(*rsp)) - return -EPROTO; - - icid = le16_to_cpu(rsp->icid); - result = le16_to_cpu(rsp->result); - - BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); - - if (result == L2CAP_MR_SUCCESS || result == L2CAP_MR_PEND) - l2cap_move_continue(conn, icid, result); - else - l2cap_move_fail(conn, cmd->ident, icid, result); - - return 0; -} - -static int l2cap_move_channel_confirm(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_cfm *cfm = data; - struct l2cap_chan *chan; - u16 icid, result; - - if (cmd_len != sizeof(*cfm)) - return -EPROTO; - - icid = le16_to_cpu(cfm->icid); - result = le16_to_cpu(cfm->result); - - BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); - - chan = l2cap_get_chan_by_dcid(conn, icid); - if (!chan) { - /* Spec requires a response even if the icid was not found */ - l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); - return 0; - } - - if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM) { - if (result == L2CAP_MC_CONFIRMED) { - chan->local_amp_id = chan->move_id; - if (chan->local_amp_id == AMP_ID_BREDR) - __release_logical_link(chan); - } else { - chan->move_id = chan->local_amp_id; - } - - l2cap_move_done(chan); - } - - l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - -static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_cfm_rsp *rsp = data; - struct l2cap_chan *chan; - u16 icid; - - if (cmd_len != sizeof(*rsp)) - return -EPROTO; - - icid = le16_to_cpu(rsp->icid); - - BT_DBG("icid 0x%4.4x", icid); - - chan = l2cap_get_chan_by_scid(conn, icid); - if (!chan) - return 0; - - __clear_chan_timer(chan); - - if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM_RSP) { - chan->local_amp_id = chan->move_id; - - if (chan->local_amp_id == AMP_ID_BREDR && chan->hs_hchan) - __release_logical_link(chan); - - l2cap_move_done(chan); - } - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - -static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, u8 *data) -{ - struct hci_conn *hcon = conn->hcon; - struct l2cap_conn_param_update_req *req; - struct l2cap_conn_param_update_rsp rsp; - u16 min, max, latency, to_multiplier; - int err; - - if (hcon->role != HCI_ROLE_MASTER) - return -EINVAL; - - if (cmd_len != sizeof(struct l2cap_conn_param_update_req)) - return -EPROTO; - - req = (struct l2cap_conn_param_update_req *) data; - min = __le16_to_cpu(req->min); - max = __le16_to_cpu(req->max); - latency = __le16_to_cpu(req->latency); - to_multiplier = __le16_to_cpu(req->to_multiplier); - - BT_DBG("min 0x%4.4x max 0x%4.4x latency: 0x%4.4x Timeout: 0x%4.4x", - min, max, latency, to_multiplier); - - memset(&rsp, 0, sizeof(rsp)); - - if (max > hcon->le_conn_max_interval) { - BT_DBG("requested connection interval exceeds current bounds."); - err = -EINVAL; - } else { - err = hci_check_conn_params(min, max, latency, to_multiplier); - } - - if (err) - rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); - else - rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED); - - l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP, - sizeof(rsp), &rsp); - - if (!err) { - u8 store_hint; - - store_hint = hci_le_conn_update(hcon, min, max, latency, - to_multiplier); - mgmt_new_conn_param(hcon->hdev, &hcon->dst, hcon->dst_type, - store_hint, min, max, latency, - to_multiplier); - - } - - return 0; -} - -static int l2cap_le_connect_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, u16 cmd_len, - u8 *data) -{ - struct l2cap_le_conn_rsp *rsp = (struct l2cap_le_conn_rsp *) data; - struct hci_conn *hcon = conn->hcon; - u16 dcid, mtu, mps, credits, result; - struct l2cap_chan *chan; - int err, sec_level; - - if (cmd_len < sizeof(*rsp)) - return -EPROTO; - - dcid = __le16_to_cpu(rsp->dcid); - mtu = __le16_to_cpu(rsp->mtu); - mps = __le16_to_cpu(rsp->mps); - credits = __le16_to_cpu(rsp->credits); - result = __le16_to_cpu(rsp->result); - - if (result == L2CAP_CR_LE_SUCCESS && (mtu < 23 || mps < 23 || - dcid < L2CAP_CID_DYN_START || - dcid > L2CAP_CID_LE_DYN_END)) - return -EPROTO; - - BT_DBG("dcid 0x%4.4x mtu %u mps %u credits %u result 0x%2.2x", - dcid, mtu, mps, credits, result); - - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_ident(conn, cmd->ident); - if (!chan) { - err = -EBADSLT; - goto unlock; - } - - err = 0; - - l2cap_chan_lock(chan); - - switch (result) { - case L2CAP_CR_LE_SUCCESS: - if (__l2cap_get_chan_by_dcid(conn, dcid)) { - err = -EBADSLT; - break; - } - - chan->ident = 0; - chan->dcid = dcid; - chan->omtu = mtu; - chan->remote_mps = mps; - chan->tx_credits = credits; - l2cap_chan_ready(chan); - break; + chan->ident = 0; + chan->dcid = dcid; + chan->omtu = mtu; + chan->remote_mps = mps; + chan->tx_credits = credits; + l2cap_chan_ready(chan); + break; case L2CAP_CR_LE_AUTHENTICATION: case L2CAP_CR_LE_ENCRYPTION: @@ -5745,7 +4771,6 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, break; case L2CAP_CONN_RSP: - case L2CAP_CREATE_CHAN_RSP: l2cap_connect_create_rsp(conn, cmd, cmd_len, data); break; @@ -5780,26 +4805,6 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, l2cap_information_rsp(conn, cmd, cmd_len, data); break; - case L2CAP_CREATE_CHAN_REQ: - err = l2cap_create_channel_req(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_REQ: - err = l2cap_move_channel_req(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_RSP: - l2cap_move_channel_rsp(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_CFM: - err = l2cap_move_channel_confirm(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_CFM_RSP: - l2cap_move_channel_confirm_rsp(conn, cmd, cmd_len, data); - break; - default: BT_ERR("Unknown BR/EDR signaling command 0x%2.2x", cmd->code); err = -EINVAL; @@ -7051,8 +6056,8 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, if (control->final) { clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state) && - !__chan_is_moving(chan)) { + if (!test_and_clear_bit(CONN_REJ_ACT, + &chan->conn_state)) { control->final = 0; l2cap_retransmit_all(chan, control); } @@ -7245,11 +6250,7 @@ static int l2cap_finish_move(struct l2cap_chan *chan) BT_DBG("chan %p", chan); chan->rx_state = L2CAP_RX_STATE_RECV; - - if (chan->hs_hcon) - chan->conn->mtu = chan->hs_hcon->hdev->block_mtu; - else - chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; + chan->conn->mtu = chan->conn->hcon->mtu; return l2cap_resegment(chan); } @@ -7316,11 +6317,7 @@ static int l2cap_rx_state_wait_f(struct l2cap_chan *chan, */ chan->next_tx_seq = control->reqseq; chan->unacked_frames = 0; - - if (chan->hs_hcon) - chan->conn->mtu = chan->hs_hcon->hdev->block_mtu; - else - chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; + chan->conn->mtu = chan->conn->hcon->mtu; err = l2cap_resegment(chan); @@ -7525,9 +6522,7 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; struct l2cap_le_credits pkt; - u16 return_credits; - - return_credits = (chan->imtu / chan->mps) + 1; + u16 return_credits = l2cap_le_rx_credits(chan); if (chan->rx_credits >= return_credits) return; @@ -7546,6 +6541,19 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt); } +void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail) +{ + if (chan->rx_avail == rx_avail) + return; + + BT_DBG("chan %p has %zd bytes avail for rx", chan, rx_avail); + + chan->rx_avail = rx_avail; + + if (chan->state == BT_CONNECTED) + l2cap_chan_le_send_credits(chan); +} + static int l2cap_ecred_recv(struct l2cap_chan *chan, struct sk_buff *skb) { int err; @@ -7555,6 +6563,12 @@ static int l2cap_ecred_recv(struct l2cap_chan *chan, struct sk_buff *skb) /* Wait recv to confirm reception before updating the credits */ err = chan->ops->recv(chan, skb); + if (err < 0 && chan->rx_avail != -1) { + BT_ERR("Queueing received LE L2CAP data failed"); + l2cap_send_disconn_req(chan, ECONNRESET); + return err; + } + /* Update credits whenever an SDU is received */ l2cap_chan_le_send_credits(chan); @@ -7577,7 +6591,8 @@ static int l2cap_ecred_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) } chan->rx_credits--; - BT_DBG("rx_credits %u -> %u", chan->rx_credits + 1, chan->rx_credits); + BT_DBG("chan %p: rx_credits %u -> %u", + chan, chan->rx_credits + 1, chan->rx_credits); /* Update if remote had run out of credits, this should only happens * if the remote is not using the entire MPS. @@ -7672,21 +6687,10 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, chan = l2cap_get_chan_by_scid(conn, cid); if (!chan) { - if (cid == L2CAP_CID_A2MP) { - chan = a2mp_channel_create(conn, skb); - if (!chan) { - kfree_skb(skb); - return; - } - - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - } else { - BT_DBG("unknown cid 0x%4.4x", cid); - /* Drop packet and return */ - kfree_skb(skb); - return; - } + BT_DBG("unknown cid 0x%4.4x", cid); + /* Drop packet and return */ + kfree_skb(skb); + return; } BT_DBG("chan %p, len %d", chan, skb->len); @@ -7871,26 +6875,11 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan); - switch (hcon->type) { - case LE_LINK: - if (hcon->hdev->le_mtu) { - conn->mtu = hcon->hdev->le_mtu; - break; - } - fallthrough; - default: - conn->mtu = hcon->hdev->acl_mtu; - break; - } - + conn->mtu = hcon->mtu; conn->feat_mask = 0; conn->local_fixed_chan = L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS; - if (hcon->type == ACL_LINK && - hci_dev_test_flag(hcon->hdev, HCI_HS_ENABLED)) - conn->local_fixed_chan |= L2CAP_FC_A2MP; - if (hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED) && (bredr_sc_enabled(hcon->hdev) || hci_dev_test_flag(hcon->hdev, HCI_FORCE_BREDR_SMP))) @@ -7953,7 +6942,7 @@ static void l2cap_chan_by_pid(struct l2cap_chan *chan, void *data) } int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, - bdaddr_t *dst, u8 dst_type) + bdaddr_t *dst, u8 dst_type, u16 timeout) { struct l2cap_conn *conn; struct hci_conn *hcon; @@ -8046,19 +7035,17 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) hcon = hci_connect_le(hdev, dst, dst_type, false, - chan->sec_level, - HCI_LE_CONN_TIMEOUT, - HCI_ROLE_SLAVE); + chan->sec_level, timeout, + HCI_ROLE_SLAVE, 0, 0); else hcon = hci_connect_le_scan(hdev, dst, dst_type, - chan->sec_level, - HCI_LE_CONN_TIMEOUT, + chan->sec_level, timeout, CONN_REASON_L2CAP_CHAN); } else { u8 auth_type = l2cap_get_auth_type(chan); hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type, - CONN_REASON_L2CAP_CHAN); + CONN_REASON_L2CAP_CHAN, timeout); } if (IS_ERR(hcon)) { @@ -8355,11 +7342,6 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) BT_DBG("chan %p scid 0x%4.4x state %s", chan, chan->scid, state_to_string(chan->state)); - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_chan_unlock(chan); - continue; - } - if (!status && encrypt) chan->sec_level = hcon->sec_level; @@ -8498,10 +7480,6 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) struct l2cap_conn *conn = hcon->l2cap_data; int len; - /* For AMP controller do not create l2cap conn */ - if (!conn && hcon->hdev->dev_type != HCI_PRIMARY) - goto drop; - if (!conn) conn = l2cap_conn_add(hcon); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index e50d3d102078e..8645461d45e81 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -254,7 +254,8 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, chan->mode = L2CAP_MODE_LE_FLOWCTL; err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid), - &la.l2_bdaddr, la.l2_bdaddr_type); + &la.l2_bdaddr, la.l2_bdaddr_type, + sk->sk_sndtimeo); if (err) return err; @@ -438,7 +439,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; struct l2cap_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -485,7 +487,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mode 0x%2.2x", chan->mode); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *) &opts, len)) err = -EFAULT; @@ -535,7 +537,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = chan->conn->hcon->handle; memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *) &cinfo, len)) err = -EFAULT; @@ -726,7 +728,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; - int len, err = 0; + int err = 0; u32 opt; BT_DBG("sk %p", sk); @@ -753,11 +755,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, opts.max_tx = chan->max_tx; opts.txwin_size = chan->tx_win; - len = min_t(unsigned int, sizeof(opts), optlen); - if (copy_from_sockptr(&opts, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen); + if (err) break; - } if (opts.txwin_size > L2CAP_DEFAULT_EXT_WINDOW) { err = -EINVAL; @@ -800,10 +800,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; case L2CAP_LM: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt & L2CAP_LM_FIPS) { err = -EINVAL; @@ -884,7 +883,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, struct bt_security sec; struct bt_power pwr; struct l2cap_conn *conn; - int len, err = 0; + int err = 0; u32 opt; u16 mtu; u8 mode; @@ -910,11 +909,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - len = min_t(unsigned int, sizeof(sec), optlen); - if (copy_from_sockptr(&sec, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + if (err) break; - } if (sec.level < BT_SECURITY_LOW || sec.level > BT_SECURITY_FIPS) { @@ -959,10 +956,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) { set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -974,10 +970,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_FLUSHABLE: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt > BT_FLUSHABLE_ON) { err = -EINVAL; @@ -1009,11 +1004,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, pwr.force_active = BT_POWER_FORCE_ACTIVE_ON; - len = min_t(unsigned int, sizeof(pwr), optlen); - if (copy_from_sockptr(&pwr, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen); + if (err) break; - } if (pwr.force_active) set_bit(FLAG_FORCE_ACTIVE, &chan->flags); @@ -1022,28 +1015,11 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_CHANNEL_POLICY: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; - break; - } - - if (opt > BT_CHANNEL_POLICY_AMP_PREFERRED) { - err = -EINVAL; - break; - } - - if (chan->mode != L2CAP_MODE_ERTM && - chan->mode != L2CAP_MODE_STREAMING) { - err = -EOPNOTSUPP; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } - - chan->chan_policy = (u8) opt; - - if (sk->sk_state == BT_CONNECTED && - chan->move_role == L2CAP_MOVE_ROLE_NONE) - l2cap_move_start(chan); + err = -EOPNOTSUPP; break; case BT_SNDMTU: @@ -1070,10 +1046,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&mtu, optval, sizeof(u16))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen); + if (err) break; - } if (chan->mode == L2CAP_MODE_EXT_FLOWCTL && sk->sk_state == BT_CONNECTED) @@ -1101,10 +1076,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&mode, optval, sizeof(u8))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen); + if (err) break; - } BT_DBG("mode %u", mode); @@ -1157,6 +1131,34 @@ static int l2cap_sock_sendmsg(struct socket *sock, struct msghdr *msg, return err; } +static void l2cap_publish_rx_avail(struct l2cap_chan *chan) +{ + struct sock *sk = chan->data; + ssize_t avail = sk->sk_rcvbuf - atomic_read(&sk->sk_rmem_alloc); + int expected_skbs, skb_overhead; + + if (avail <= 0) { + l2cap_chan_rx_avail(chan, 0); + return; + } + + if (!chan->mps) { + l2cap_chan_rx_avail(chan, -1); + return; + } + + /* Correct available memory by estimated sk_buff overhead. + * This is significant due to small transfer sizes. However, accept + * at least one full packet if receive space is non-zero. + */ + expected_skbs = DIV_ROUND_UP(avail, chan->mps); + skb_overhead = expected_skbs * sizeof(struct sk_buff); + if (skb_overhead < avail) + l2cap_chan_rx_avail(chan, avail - skb_overhead); + else + l2cap_chan_rx_avail(chan, -1); +} + static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { @@ -1193,28 +1195,33 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, else err = bt_sock_recvmsg(sock, msg, len, flags); - if (pi->chan->mode != L2CAP_MODE_ERTM) + if (pi->chan->mode != L2CAP_MODE_ERTM && + pi->chan->mode != L2CAP_MODE_LE_FLOWCTL && + pi->chan->mode != L2CAP_MODE_EXT_FLOWCTL) return err; - /* Attempt to put pending rx data in the socket buffer */ - lock_sock(sk); - if (!test_bit(CONN_LOCAL_BUSY, &pi->chan->conn_state)) - goto done; + l2cap_publish_rx_avail(pi->chan); - if (pi->rx_busy_skb) { - if (!__sock_queue_rcv_skb(sk, pi->rx_busy_skb)) - pi->rx_busy_skb = NULL; - else + /* Attempt to put pending rx data in the socket buffer */ + while (!list_empty(&pi->rx_busy)) { + struct l2cap_rx_busy *rx_busy = + list_first_entry(&pi->rx_busy, + struct l2cap_rx_busy, + list); + if (__sock_queue_rcv_skb(sk, rx_busy->skb) < 0) goto done; + list_del(&rx_busy->list); + kfree(rx_busy); } /* Restore data flow when half of the receive buffer is * available. This avoids resending large numbers of * frames. */ - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf >> 1) + if (test_bit(CONN_LOCAL_BUSY, &pi->chan->conn_state) && + atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf >> 1) l2cap_chan_busy(pi->chan, 0); done: @@ -1475,17 +1482,20 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) { struct sock *sk = chan->data; + struct l2cap_pinfo *pi = l2cap_pi(sk); int err; lock_sock(sk); - if (l2cap_pi(sk)->rx_busy_skb) { + if (chan->mode == L2CAP_MODE_ERTM && !list_empty(&pi->rx_busy)) { err = -ENOMEM; goto done; } if (chan->mode != L2CAP_MODE_ERTM && - chan->mode != L2CAP_MODE_STREAMING) { + chan->mode != L2CAP_MODE_STREAMING && + chan->mode != L2CAP_MODE_LE_FLOWCTL && + chan->mode != L2CAP_MODE_EXT_FLOWCTL) { /* Even if no filter is attached, we could potentially * get errors from security modules, etc. */ @@ -1496,7 +1506,9 @@ static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) err = __sock_queue_rcv_skb(sk, skb); - /* For ERTM, handle one skb that doesn't fit into the recv + l2cap_publish_rx_avail(chan); + + /* For ERTM and LE, handle a skb that doesn't fit into the recv * buffer. This is important to do because the data frames * have already been acked, so the skb cannot be discarded. * @@ -1505,8 +1517,18 @@ static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) * acked and reassembled until there is buffer space * available. */ - if (err < 0 && chan->mode == L2CAP_MODE_ERTM) { - l2cap_pi(sk)->rx_busy_skb = skb; + if (err < 0 && + (chan->mode == L2CAP_MODE_ERTM || + chan->mode == L2CAP_MODE_LE_FLOWCTL || + chan->mode == L2CAP_MODE_EXT_FLOWCTL)) { + struct l2cap_rx_busy *rx_busy = + kmalloc(sizeof(*rx_busy), GFP_KERNEL); + if (!rx_busy) { + err = -ENOMEM; + goto done; + } + rx_busy->skb = skb; + list_add_tail(&rx_busy->list, &pi->rx_busy); l2cap_chan_busy(chan, 1); err = 0; } @@ -1732,6 +1754,8 @@ static const struct l2cap_ops l2cap_chan_ops = { static void l2cap_sock_destruct(struct sock *sk) { + struct l2cap_rx_busy *rx_busy, *next; + BT_DBG("sk %p", sk); if (l2cap_pi(sk)->chan) { @@ -1739,9 +1763,10 @@ static void l2cap_sock_destruct(struct sock *sk) l2cap_chan_put(l2cap_pi(sk)->chan); } - if (l2cap_pi(sk)->rx_busy_skb) { - kfree_skb(l2cap_pi(sk)->rx_busy_skb); - l2cap_pi(sk)->rx_busy_skb = NULL; + list_for_each_entry_safe(rx_busy, next, &l2cap_pi(sk)->rx_busy, list) { + kfree_skb(rx_busy->skb); + list_del(&rx_busy->list); + kfree(rx_busy); } skb_queue_purge(&sk->sk_receive_queue); @@ -1825,6 +1850,8 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->data = sk; chan->ops = &l2cap_chan_ops; + + l2cap_publish_rx_avail(chan); } static struct proto l2cap_proto = { @@ -1846,6 +1873,8 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, sk->sk_destruct = l2cap_sock_destruct; sk->sk_sndtimeo = L2CAP_CONN_TIMEOUT; + INIT_LIST_HEAD(&l2cap_pi(sk)->rx_busy); + chan = l2cap_chan_create(); if (!chan) { sk_free(sk); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ee3b4aad8bd8d..d58d3e13910fa 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -443,8 +443,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, count = 0; list_for_each_entry(d, &hci_dev_list, list) { - if (d->dev_type == HCI_PRIMARY && - !hci_dev_test_flag(d, HCI_UNCONFIGURED)) + if (!hci_dev_test_flag(d, HCI_UNCONFIGURED)) count++; } @@ -468,8 +467,7 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data, if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) continue; - if (d->dev_type == HCI_PRIMARY && - !hci_dev_test_flag(d, HCI_UNCONFIGURED)) { + if (!hci_dev_test_flag(d, HCI_UNCONFIGURED)) { rp->index[count++] = cpu_to_le16(d->id); bt_dev_dbg(hdev, "Added hci%u", d->id); } @@ -503,8 +501,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, count = 0; list_for_each_entry(d, &hci_dev_list, list) { - if (d->dev_type == HCI_PRIMARY && - hci_dev_test_flag(d, HCI_UNCONFIGURED)) + if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) count++; } @@ -528,8 +525,7 @@ static int read_unconf_index_list(struct sock *sk, struct hci_dev *hdev, if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) continue; - if (d->dev_type == HCI_PRIMARY && - hci_dev_test_flag(d, HCI_UNCONFIGURED)) { + if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) { rp->index[count++] = cpu_to_le16(d->id); bt_dev_dbg(hdev, "Added hci%u", d->id); } @@ -561,10 +557,8 @@ static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev, read_lock(&hci_dev_list_lock); count = 0; - list_for_each_entry(d, &hci_dev_list, list) { - if (d->dev_type == HCI_PRIMARY || d->dev_type == HCI_AMP) - count++; - } + list_for_each_entry(d, &hci_dev_list, list) + count++; rp = kmalloc(struct_size(rp, entry, count), GFP_ATOMIC); if (!rp) { @@ -585,16 +579,10 @@ static int read_ext_index_list(struct sock *sk, struct hci_dev *hdev, if (test_bit(HCI_QUIRK_RAW_DEVICE, &d->quirks)) continue; - if (d->dev_type == HCI_PRIMARY) { - if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) - rp->entry[count].type = 0x01; - else - rp->entry[count].type = 0x00; - } else if (d->dev_type == HCI_AMP) { - rp->entry[count].type = 0x02; - } else { - continue; - } + if (hci_dev_test_flag(d, HCI_UNCONFIGURED)) + rp->entry[count].type = 0x01; + else + rp->entry[count].type = 0x00; rp->entry[count].bus = d->bus; rp->entry[count++].index = cpu_to_le16(d->id); @@ -835,8 +823,6 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (lmp_ssp_capable(hdev)) { settings |= MGMT_SETTING_SSP; - if (IS_ENABLED(CONFIG_BT_HS)) - settings |= MGMT_SETTING_HS; } if (lmp_sc_capable(hdev)) @@ -901,9 +887,6 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) settings |= MGMT_SETTING_SSP; - if (hci_dev_test_flag(hdev, HCI_HS_ENABLED)) - settings |= MGMT_SETTING_HS; - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) settings |= MGMT_SETTING_ADVERTISING; @@ -1409,7 +1392,7 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, /* Cancel potentially blocking sync operation before power off */ if (cp->val == 0x00) { - __hci_cmd_sync_cancel(hdev, -EHOSTDOWN); + hci_cmd_sync_cancel_sync(hdev, -EHOSTDOWN); err = hci_cmd_sync_queue(hdev, set_powered_sync, cmd, mgmt_set_powered_complete); } else { @@ -1930,7 +1913,6 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) if (enable && hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED)) { - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); new_settings(hdev, NULL); } @@ -1943,12 +1925,6 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) changed = !hci_dev_test_and_set_flag(hdev, HCI_SSP_ENABLED); } else { changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED); - - if (!changed) - changed = hci_dev_test_and_clear_flag(hdev, - HCI_HS_ENABLED); - else - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, settings_rsp, &match); @@ -2012,11 +1988,6 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) } else { changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED); - if (!changed) - changed = hci_dev_test_and_clear_flag(hdev, - HCI_HS_ENABLED); - else - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } err = send_settings_rsp(sk, MGMT_OP_SET_SSP, hdev); @@ -2062,63 +2033,10 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { - struct mgmt_mode *cp = data; - bool changed; - u8 status; - int err; - bt_dev_dbg(hdev, "sock %p", sk); - if (!IS_ENABLED(CONFIG_BT_HS)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_NOT_SUPPORTED); - - status = mgmt_bredr_support(hdev); - if (status) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status); - - if (!lmp_ssp_capable(hdev)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, MGMT_STATUS_NOT_SUPPORTED); - - if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_REJECTED); - - if (cp->val != 0x00 && cp->val != 0x01) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_INVALID_PARAMS); - - hci_dev_lock(hdev); - - if (pending_find(MGMT_OP_SET_SSP, hdev)) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_BUSY); - goto unlock; - } - - if (cp->val) { - changed = !hci_dev_test_and_set_flag(hdev, HCI_HS_ENABLED); - } else { - if (hdev_is_powered(hdev)) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_REJECTED); - goto unlock; - } - - changed = hci_dev_test_and_clear_flag(hdev, HCI_HS_ENABLED); - } - - err = send_settings_rsp(sk, MGMT_OP_SET_HS, hdev); - if (err < 0) - goto unlock; - - if (changed) - err = new_settings(hdev, sk); - -unlock: - hci_dev_unlock(hdev); - return err; } static void set_le_complete(struct hci_dev *hdev, void *data, int err) @@ -2686,7 +2604,11 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) goto failed; } - err = hci_cmd_sync_queue(hdev, add_uuid_sync, cmd, mgmt_class_complete); + /* MGMT_OP_ADD_UUID don't require adapter the UP/Running so use + * hci_cmd_sync_submit instead of hci_cmd_sync_queue. + */ + err = hci_cmd_sync_submit(hdev, add_uuid_sync, cmd, + mgmt_class_complete); if (err < 0) { mgmt_pending_free(cmd); goto failed; @@ -2780,8 +2702,11 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - err = hci_cmd_sync_queue(hdev, remove_uuid_sync, cmd, - mgmt_class_complete); + /* MGMT_OP_REMOVE_UUID don't require adapter the UP/Running so use + * hci_cmd_sync_submit instead of hci_cmd_sync_queue. + */ + err = hci_cmd_sync_submit(hdev, remove_uuid_sync, cmd, + mgmt_class_complete); if (err < 0) mgmt_pending_free(cmd); @@ -2847,8 +2772,11 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - err = hci_cmd_sync_queue(hdev, set_class_sync, cmd, - mgmt_class_complete); + /* MGMT_OP_SET_DEV_CLASS don't require adapter the UP/Running so use + * hci_cmd_sync_submit instead of hci_cmd_sync_queue. + */ + err = hci_cmd_sync_submit(hdev, set_class_sync, cmd, + mgmt_class_complete); if (err < 0) mgmt_pending_free(cmd); @@ -3188,6 +3116,7 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, static u8 link_to_bdaddr(u8 link_type, u8 addr_type) { switch (link_type) { + case ISO_LINK: case LE_LINK: switch (addr_type) { case ADDR_LE_DEV_PUBLIC: @@ -3505,7 +3434,8 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->addr.type == BDADDR_BREDR) { conn = hci_connect_acl(hdev, &cp->addr.bdaddr, sec_level, - auth_type, CONN_REASON_PAIR_DEVICE); + auth_type, CONN_REASON_PAIR_DEVICE, + HCI_ACL_CONN_TIMEOUT); } else { u8 addr_type = le_addr_type(cp->addr.type); struct hci_conn_params *p; @@ -5536,8 +5466,8 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, goto unlock; } - err = hci_cmd_sync_queue(hdev, mgmt_remove_adv_monitor_sync, cmd, - mgmt_remove_adv_monitor_complete); + err = hci_cmd_sync_submit(hdev, mgmt_remove_adv_monitor_sync, cmd, + mgmt_remove_adv_monitor_complete); if (err) { mgmt_pending_remove(cmd); @@ -6766,7 +6696,6 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) hci_dev_clear_flag(hdev, HCI_SSP_ENABLED); hci_dev_clear_flag(hdev, HCI_LINK_SECURITY); hci_dev_clear_flag(hdev, HCI_FAST_CONNECTABLE); - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } hci_dev_change_flag(hdev, HCI_BREDR_ENABLED); @@ -8470,7 +8399,7 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, static u8 calculate_name_len(struct hci_dev *hdev) { - u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 3]; + u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 2]; /* len + type + name */ return eir_append_local_name(hdev, buf, 0); } @@ -9384,23 +9313,14 @@ void mgmt_index_added(struct hci_dev *hdev) if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) return; - switch (hdev->dev_type) { - case HCI_PRIMARY: - if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { - mgmt_index_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev, - NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS); - ev.type = 0x01; - } else { - mgmt_index_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, - HCI_MGMT_INDEX_EVENTS); - ev.type = 0x00; - } - break; - case HCI_AMP: - ev.type = 0x02; - break; - default: - return; + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { + mgmt_index_event(MGMT_EV_UNCONF_INDEX_ADDED, hdev, NULL, 0, + HCI_MGMT_UNCONF_INDEX_EVENTS); + ev.type = 0x01; + } else { + mgmt_index_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, + HCI_MGMT_INDEX_EVENTS); + ev.type = 0x00; } ev.bus = hdev->bus; @@ -9417,25 +9337,16 @@ void mgmt_index_removed(struct hci_dev *hdev) if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) return; - switch (hdev->dev_type) { - case HCI_PRIMARY: - mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); + mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &status); - if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { - mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, - NULL, 0, HCI_MGMT_UNCONF_INDEX_EVENTS); - ev.type = 0x01; - } else { - mgmt_index_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, - HCI_MGMT_INDEX_EVENTS); - ev.type = 0x00; - } - break; - case HCI_AMP: - ev.type = 0x02; - break; - default: - return; + if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { + mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, NULL, 0, + HCI_MGMT_UNCONF_INDEX_EVENTS); + ev.type = 0x01; + } else { + mgmt_index_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, + HCI_MGMT_INDEX_EVENTS); + ev.type = 0x00; } ev.bus = hdev->bus; @@ -9681,6 +9592,9 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u16 eir_len = 0; u32 flags = 0; + if (test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + return; + /* allocate buff for LE or BR/EDR adv */ if (conn->le_adv_data_len > 0) skb = mgmt_alloc_skb(hdev, MGMT_EV_DEVICE_CONNECTED, @@ -9766,14 +9680,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, struct mgmt_ev_device_disconnected ev; struct sock *sk = NULL; - /* The connection is still in hci_conn_hash so test for 1 - * instead of 0 to know if this is the last one. - */ - if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) { - cancel_delayed_work(&hdev->power_off); - queue_work(hdev->req_workqueue, &hdev->power_off.work); - } - if (!mgmt_connected) return; @@ -9830,14 +9736,6 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, { struct mgmt_ev_connect_failed ev; - /* The connection is still in hci_conn_hash so test for 1 - * instead of 0 to know if this is the last one. - */ - if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) { - cancel_delayed_work(&hdev->power_off); - queue_work(hdev->req_workqueue, &hdev->power_off.work); - } - bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); ev.status = mgmt_status(status); diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 630e3023273b2..d039683d3bdd4 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -769,7 +769,7 @@ void msft_register(struct hci_dev *hdev) mutex_init(&msft->filter_lock); } -void msft_unregister(struct hci_dev *hdev) +void msft_release(struct hci_dev *hdev) { struct msft_data *msft = hdev->msft_data; @@ -875,6 +875,7 @@ static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) remove = true; goto done; } + cp->sub_opcode = MSFT_OP_LE_MONITOR_ADVERTISEMENT; cp->rssi_high = address_filter->rssi_high; cp->rssi_low = address_filter->rssi_low; @@ -887,6 +888,8 @@ static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, size, cp, HCI_CMD_TIMEOUT); + kfree(cp); + if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to enable address %pMR filter", &address_filter->bdaddr); diff --git a/net/bluetooth/msft.h b/net/bluetooth/msft.h index 2a63205b377b7..fe538e9c91c01 100644 --- a/net/bluetooth/msft.h +++ b/net/bluetooth/msft.h @@ -14,7 +14,7 @@ bool msft_monitor_supported(struct hci_dev *hdev); void msft_register(struct hci_dev *hdev); -void msft_unregister(struct hci_dev *hdev); +void msft_release(struct hci_dev *hdev); void msft_do_open(struct hci_dev *hdev); void msft_do_close(struct hci_dev *hdev); void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb); @@ -35,7 +35,7 @@ static inline bool msft_monitor_supported(struct hci_dev *hdev) } static inline void msft_register(struct hci_dev *hdev) {} -static inline void msft_unregister(struct hci_dev *hdev) {} +static inline void msft_release(struct hci_dev *hdev) {} static inline void msft_do_open(struct hci_dev *hdev) {} static inline void msft_do_close(struct hci_dev *hdev) {} static inline void msft_vendor_evt(struct hci_dev *hdev, void *data, diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index b54e8a530f55a..29aa07e9db9d7 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -629,7 +629,7 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, switch (optname) { case RFCOMM_LM: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { + if (bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen)) { err = -EFAULT; break; } @@ -664,7 +664,6 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct bt_security sec; int err = 0; - size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -686,11 +685,9 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - len = min_t(unsigned int, sizeof(sec), optlen); - if (copy_from_sockptr(&sec, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + if (err) break; - } if (sec.level > BT_SECURITY_HIGH) { err = -EINVAL; @@ -706,10 +703,9 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index c736186aba26b..71d36582d4efa 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -83,6 +83,10 @@ static void sco_sock_timeout(struct work_struct *work) struct sock *sk; sco_conn_lock(conn); + if (!conn->hcon) { + sco_conn_unlock(conn); + return; + } sk = conn->sk; if (sk) sock_hold(sk); @@ -122,7 +126,6 @@ static void sco_sock_clear_timer(struct sock *sk) /* ---- SCO connections ---- */ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) { - struct hci_dev *hdev = hcon->hdev; struct sco_conn *conn = hcon->sco_data; if (conn) { @@ -140,9 +143,10 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) hcon->sco_data = conn; conn->hcon = hcon; + conn->mtu = hcon->mtu; - if (hdev->sco_mtu > 0) - conn->mtu = hdev->sco_mtu; + if (hcon->mtu > 0) + conn->mtu = hcon->mtu; else conn->mtu = 60; @@ -264,7 +268,8 @@ static int sco_connect(struct sock *sk) } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, - sco_pi(sk)->setting, &sco_pi(sk)->codec); + sco_pi(sk)->setting, &sco_pi(sk)->codec, + sk->sk_sndtimeo); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; @@ -823,7 +828,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - int len, err = 0; + int err = 0; struct bt_voice voice; u32 opt; struct bt_codecs *codecs; @@ -842,10 +847,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -862,11 +866,10 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, voice.setting = sco_pi(sk)->setting; - len = min_t(unsigned int, sizeof(voice), optlen); - if (copy_from_sockptr(&voice, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, + optlen); + if (err) break; - } /* Explicitly check for these values */ if (voice.setting != BT_VOICE_TRANSPARENT && @@ -889,10 +892,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); @@ -933,9 +935,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(buffer, optval, optlen)) { + err = bt_copy_from_sockptr(buffer, optlen, optval, optlen); + if (err) { hci_dev_put(hdev); - err = -EFAULT; break; } @@ -966,7 +968,8 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; BT_DBG("sk %p", sk); @@ -988,7 +991,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mtu %u", opts.mtu); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; @@ -1006,7 +1009,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index dfd9193740178..2c6d53ae42803 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -717,10 +717,16 @@ static void __bpf_prog_test_run_raw_tp(void *data) { struct bpf_raw_tp_test_run_info *info = data; + struct bpf_trace_run_ctx run_ctx = {}; + struct bpf_run_ctx *old_run_ctx; + + old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); rcu_read_lock(); info->retval = bpf_prog_run(info->prog, info->ctx); rcu_read_unlock(); + + bpf_reset_run_ctx(old_run_ctx); } int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 65cee0ad3c1b6..79b822be6c2e5 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -27,6 +27,7 @@ EXPORT_SYMBOL_GPL(nf_br_ops); /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { + enum skb_drop_reason reason = pskb_may_pull_reason(skb, ETH_HLEN); struct net_bridge_mcast_port *pmctx_null = NULL; struct net_bridge *br = netdev_priv(dev); struct net_bridge_mcast *brmctx = &br->multicast_ctx; @@ -38,6 +39,11 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const unsigned char *dest; u16 vid = 0; + if (unlikely(reason != SKB_NOT_DROPPED_YET)) { + kfree_skb_reason(skb, reason); + return NETDEV_TX_OK; + } + memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); br_tc_skb_miss_set(skb, false); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 7431f89e897b9..d97064d460dc7 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -258,6 +258,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, { struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; const unsigned char *src = eth_hdr(skb)->h_source; + struct sk_buff *nskb; if (!should_deliver(p, skb)) return; @@ -266,12 +267,16 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, if (skb->dev == p->dev && ether_addr_equal(src, addr)) return; - skb = skb_copy(skb, GFP_ATOMIC); - if (!skb) { + __skb_push(skb, ETH_HLEN); + nskb = pskb_copy(skb, GFP_ATOMIC); + __skb_pull(skb, ETH_HLEN); + if (!nskb) { DEV_STATS_INC(dev, tx_dropped); return; } + skb = nskb; + __skb_pull(skb, ETH_HLEN); if (!is_broadcast_ether_addr(addr)) memcpy(eth_hdr(skb)->h_dest, addr, ETH_ALEN); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f21097e734827..ceaa5a89b947f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -30,7 +30,7 @@ br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) return netif_receive_skb(skb); } -static int br_pass_frame_up(struct sk_buff *skb) +static int br_pass_frame_up(struct sk_buff *skb, bool promisc) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); @@ -65,6 +65,8 @@ static int br_pass_frame_up(struct sk_buff *skb) br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb), BR_MCAST_DIR_TX); + BR_INPUT_SKB_CB(skb)->promisc = promisc; + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(indev), NULL, skb, indev, NULL, br_netif_receive_skb); @@ -82,6 +84,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_mcast *brmctx; struct net_bridge_vlan *vlan; struct net_bridge *br; + bool promisc; u16 vid = 0; u8 state; @@ -137,7 +140,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (p->flags & BR_LEARNING) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0); - local_rcv = !!(br->dev->flags & IFF_PROMISC); + promisc = !!(br->dev->flags & IFF_PROMISC); + local_rcv = promisc; + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) { @@ -200,7 +205,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb unsigned long now = jiffies; if (test_bit(BR_FDB_LOCAL, &dst->flags)) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, false); if (now != dst->used) dst->used = now; @@ -213,7 +218,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb } if (local_rcv) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, promisc); out: return 0; @@ -386,6 +391,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto forward; } + BR_INPUT_SKB_CB(skb)->promisc = false; + /* The else clause should be hit when nf_hook(): * - returns < 0 (drop/error) * - returns = 0 (stolen/nf_queue) diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c index ee680adcee179..1820f09ff59ce 100644 --- a/net/bridge/br_mst.c +++ b/net/bridge/br_mst.c @@ -73,12 +73,11 @@ int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state) } EXPORT_SYMBOL_GPL(br_mst_get_state); -static void br_mst_vlan_set_state(struct net_bridge_port *p, struct net_bridge_vlan *v, +static void br_mst_vlan_set_state(struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *v, u8 state) { - struct net_bridge_vlan_group *vg = nbp_vlan_group(p); - - if (v->state == state) + if (br_vlan_get_state(v) == state) return; br_vlan_set_state(v, state); @@ -100,11 +99,12 @@ int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, }; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; - int err; + int err = 0; - vg = nbp_vlan_group(p); + rcu_read_lock(); + vg = nbp_vlan_group_rcu(p); if (!vg) - return 0; + goto out; /* MSTI 0 (CST) state changes are notified via the regular * SWITCHDEV_ATTR_ID_PORT_STP_STATE. @@ -112,17 +112,20 @@ int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, if (msti) { err = switchdev_port_attr_set(p->dev, &attr, extack); if (err && err != -EOPNOTSUPP) - return err; + goto out; } - list_for_each_entry(v, &vg->vlan_list, vlist) { + err = 0; + list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (v->brvlan->msti != msti) continue; - br_mst_vlan_set_state(p, v, state); + br_mst_vlan_set_state(vg, v, state); } - return 0; +out: + rcu_read_unlock(); + return err; } static void br_mst_vlan_sync_state(struct net_bridge_vlan *pv, u16 msti) @@ -136,13 +139,13 @@ static void br_mst_vlan_sync_state(struct net_bridge_vlan *pv, u16 msti) * it. */ if (v != pv && v->brvlan->msti == msti) { - br_mst_vlan_set_state(pv->port, pv, v->state); + br_mst_vlan_set_state(vg, pv, v->state); return; } } /* Otherwise, start out in a new MSTI with all ports disabled. */ - return br_mst_vlan_set_state(pv->port, pv, BR_STATE_DISABLED); + return br_mst_vlan_set_state(vg, pv, BR_STATE_DISABLED); } int br_mst_vlan_set_msti(struct net_bridge_vlan *mv, u16 msti) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 35e10c5a766d5..22e35623c148a 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -600,11 +600,17 @@ static unsigned int br_nf_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; struct nf_conntrack *nfct = skb_nfct(skb); const struct nf_ct_hook *ct_hook; struct nf_conn *ct; int ret; + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5ad4abfcb7ba3..f17dbac7d8284 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -455,7 +455,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, u32 filter_mask, const struct net_device *dev, bool getlink) { - u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + u8 operstate = netif_running(dev) ? READ_ONCE(dev->operstate) : + IF_OPER_DOWN; struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; @@ -666,7 +667,7 @@ void br_ifinfo_notify(int event, const struct net_bridge *br, { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; - return br_info_notify(event, br, port, filter); + br_info_notify(event, br, port, filter); } /* diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 86ea5e6689b5c..d4bedc87b1d8f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -589,6 +589,7 @@ struct br_input_skb_cb { #endif u8 proxyarp_replied:1; u8 src_port_isolated:1; + u8 promisc:1; #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_filtered:1; #endif diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 99d82676f780a..cbd0e3586c3f6 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1111,6 +1111,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) struct ebt_table_info *newinfo; struct ebt_replace tmp; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1423,6 +1425,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len) { struct ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; @@ -2352,6 +2356,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg, { struct compat_ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 6f877e31709ba..c3c51b9a68265 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -294,18 +294,24 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - enum ip_conntrack_info ctinfo; + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; + struct nf_conntrack *nfct = skb_nfct(skb); struct nf_conn *ct; - if (skb->pkt_type == PACKET_HOST) + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + + if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; /* nf_conntrack_confirm() cannot handle concurrent clones, * this happens for broad/multicast frames with e.g. macvlan on top * of the bridge device. */ - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) + ct = container_of(nfct, struct nf_conn, ct_general); + if (nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) return NF_ACCEPT; /* let inet prerouting call conntrack again */ diff --git a/net/core/dev.c b/net/core/dev.c index 76e6438f4858e..a32811aebde59 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2261,7 +2261,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { - if (ptype->ignore_outgoing) + if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket @@ -3791,6 +3791,10 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } + if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { + kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); + return NET_XMIT_DROP; + } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. @@ -3830,7 +3834,9 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { + WRITE_ONCE(q->owner, smp_processor_id()); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); + WRITE_ONCE(q->owner, -1); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -6708,6 +6714,8 @@ static int napi_threaded_poll(void *data) void *have; while (!napi_thread_wait(napi)) { + unsigned long last_qs = jiffies; + for (;;) { bool repoll = false; @@ -6732,6 +6740,7 @@ static int napi_threaded_poll(void *data) if (!repoll) break; + rcu_softirq_qs_periodic(last_qs); cond_resched(); } } @@ -10446,8 +10455,9 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) rebroadcast_time = jiffies; } + rcu_barrier(); + if (!wait) { - rcu_barrier(); wait = WAIT_REFS_MIN_MSECS; } else { msleep(wait); @@ -11631,11 +11641,12 @@ static void __init net_dev_struct_check(void) /* TXRX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); - CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38); + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index b0f221d658be8..430ed18f8584c 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -74,7 +74,7 @@ struct net_dm_hw_entries { }; struct per_cpu_dm_data { - spinlock_t lock; /* Protects 'skb', 'hw_entries' and + raw_spinlock_t lock; /* Protects 'skb', 'hw_entries' and * 'send_timer' */ union { @@ -168,9 +168,9 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) err: mod_timer(&data->send_timer, jiffies + HZ / 10); out: - spin_lock_irqsave(&data->lock, flags); + raw_spin_lock_irqsave(&data->lock, flags); swap(data->skb, skb); - spin_unlock_irqrestore(&data->lock, flags); + raw_spin_unlock_irqrestore(&data->lock, flags); if (skb) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data; @@ -225,7 +225,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location) local_irq_save(flags); data = this_cpu_ptr(&dm_cpu_data); - spin_lock(&data->lock); + raw_spin_lock(&data->lock); dskb = data->skb; if (!dskb) @@ -259,7 +259,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location) } out: - spin_unlock_irqrestore(&data->lock, flags); + raw_spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, @@ -314,9 +314,9 @@ net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data) mod_timer(&hw_data->send_timer, jiffies + HZ / 10); } - spin_lock_irqsave(&hw_data->lock, flags); + raw_spin_lock_irqsave(&hw_data->lock, flags); swap(hw_data->hw_entries, hw_entries); - spin_unlock_irqrestore(&hw_data->lock, flags); + raw_spin_unlock_irqrestore(&hw_data->lock, flags); return hw_entries; } @@ -448,7 +448,7 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, return; hw_data = this_cpu_ptr(&dm_hw_cpu_data); - spin_lock_irqsave(&hw_data->lock, flags); + raw_spin_lock_irqsave(&hw_data->lock, flags); hw_entries = hw_data->hw_entries; if (!hw_entries) @@ -477,7 +477,7 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, } out: - spin_unlock_irqrestore(&hw_data->lock, flags); + raw_spin_unlock_irqrestore(&hw_data->lock, flags); } static const struct net_dm_alert_ops net_dm_alert_summary_ops = { @@ -1673,7 +1673,7 @@ static struct notifier_block dropmon_net_notifier = { static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data) { - spin_lock_init(&data->lock); + raw_spin_lock_init(&data->lock); skb_queue_head_init(&data->drop_queue); u64_stats_init(&data->stats.syncp); } diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c index 0ccfd5fa5cb9b..0c0bdb058c5b1 100644 --- a/net/core/dst_cache.c +++ b/net/core/dst_cache.c @@ -83,7 +83,7 @@ struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr) return NULL; *saddr = idst->in_saddr.s_addr; - return container_of(dst, struct rtable, dst); + return dst_rtable(dst); } EXPORT_SYMBOL_GPL(dst_cache_get_ip4); @@ -112,7 +112,7 @@ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, idst = this_cpu_ptr(dst_cache->cache); dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst, - rt6_get_cookie((struct rt6_info *)dst)); + rt6_get_cookie(dst_rt6_info(dst))); idst->in6_saddr = *saddr; } EXPORT_SYMBOL_GPL(dst_cache_set_ip6); diff --git a/net/core/filter.c b/net/core/filter.c index ef3e78b6a39c4..ab277810e22be 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1662,6 +1662,11 @@ static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp); static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { +#ifdef CONFIG_DEBUG_NET + /* Avoid a splat in pskb_may_pull_reason() */ + if (write_len > INT_MAX) + return -EINVAL; +#endif return skb_ensure_writable(skb, write_len); } @@ -2215,7 +2220,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, rcu_read_lock(); if (!nh) { dst = skb_dst(skb); - nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst), + nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); } else { nexthop = &nh->ipv6_nh; @@ -2314,8 +2319,7 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, rcu_read_lock(); if (!nh) { - struct dst_entry *dst = skb_dst(skb); - struct rtable *rt = container_of(dst, struct rtable, dst); + struct rtable *rt = skb_rtable(skb); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { @@ -4360,10 +4364,12 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { @@ -4375,11 +4381,20 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } @@ -4442,9 +4457,9 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, - void *fwd, - enum bpf_map_type map_type, u32 map_id) + struct bpf_prog *xdp_prog, void *fwd, + enum bpf_map_type map_type, u32 map_id, + u32 flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map; @@ -4454,11 +4469,20 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } @@ -4495,9 +4519,11 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { @@ -4517,7 +4543,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, return 0; } - return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id); + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; diff --git a/net/core/gro.c b/net/core/gro.c index 0759277dc14ee..31e40f25fdf10 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -195,8 +195,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) } merge: - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; @@ -372,6 +373,7 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) const struct skb_shared_info *pinfo = skb_shinfo(skb); const skb_frag_t *frag0 = &pinfo->frags[0]; + NAPI_GRO_CB(skb)->network_offset = 0; NAPI_GRO_CB(skb)->data_offset = 0; NAPI_GRO_CB(skb)->frag0 = NULL; NAPI_GRO_CB(skb)->frag0_len = 0; diff --git a/net/core/gso_test.c b/net/core/gso_test.c index 4c2e77bd12f4b..358c44680d917 100644 --- a/net/core/gso_test.c +++ b/net/core/gso_test.c @@ -225,7 +225,7 @@ static void gso_test_func(struct kunit *test) segs = skb_segment(skb, features); if (IS_ERR(segs)) { - KUNIT_FAIL(test, "segs error %lld", PTR_ERR(segs)); + KUNIT_FAIL(test, "segs error %pe", segs); goto free_gso_skb; } else if (!segs) { KUNIT_FAIL(test, "no segments"); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 429571c258da7..1b93e054c9a3c 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -67,7 +67,7 @@ static void rfc2863_policy(struct net_device *dev) { unsigned char operstate = default_operstate(dev); - if (operstate == dev->operstate) + if (operstate == READ_ONCE(dev->operstate)) return; write_lock(&dev_base_lock); @@ -87,7 +87,7 @@ static void rfc2863_policy(struct net_device *dev) break; } - dev->operstate = operstate; + WRITE_ONCE(dev->operstate, operstate); write_unlock(&dev_base_lock); } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index a09d507c5b03d..676048ae11831 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -318,11 +318,9 @@ static ssize_t operstate_show(struct device *dev, const struct net_device *netdev = to_net_dev(dev); unsigned char operstate; - read_lock(&dev_base_lock); - operstate = netdev->operstate; + operstate = READ_ONCE(netdev->operstate); if (!netif_running(netdev)) operstate = IF_OPER_DOWN; - read_unlock(&dev_base_lock); if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 72799533426b6..3ff4e64a5e6de 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -69,12 +69,15 @@ DEFINE_COOKIE(net_cookie); static struct net_generic *net_alloc_generic(void) { + unsigned int gen_ptrs = READ_ONCE(max_gen_ptrs); + unsigned int generic_size; struct net_generic *ng; - unsigned int generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]); + + generic_size = offsetof(struct net_generic, ptr[gen_ptrs]); ng = kzalloc(generic_size, GFP_KERNEL); if (ng) - ng->s.len = max_gen_ptrs; + ng->s.len = gen_ptrs; return ng; } @@ -671,11 +674,16 @@ EXPORT_SYMBOL_GPL(__put_net); * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * - * Returns the net's common namespace. + * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { - return &get_net(container_of(ns, struct net, ns))->ns; + struct net *net; + + net = maybe_get_net(container_of(ns, struct net, ns)); + if (net) + return &net->ns; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); @@ -1278,7 +1286,11 @@ static int register_pernet_operations(struct list_head *list, if (error < 0) return error; *ops->id = error; - max_gen_ptrs = max(max_gen_ptrs, *ops->id + 1); + /* This does not require READ_ONCE as writers already hold + * pernet_ops_rwsem. But WRITE_ONCE is needed to protect + * net_alloc_generic. + */ + WRITE_ONCE(max_gen_ptrs, max(max_gen_ptrs, *ops->id + 1)); } error = __register_pernet_operations(list, ops); if (error) { diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index fd98936da3aec..06c884af15698 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -58,22 +58,22 @@ XDP_METADATA_KFUNC_xxx nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, xdp_rx_meta, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES, - xsk_features, NETDEV_A_DEV_PAD)) { - genlmsg_cancel(rsp, hdr); - return -EINVAL; - } + xsk_features, NETDEV_A_DEV_PAD)) + goto err_cancel_msg; if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) { if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, - netdev->xdp_zc_max_segs)) { - genlmsg_cancel(rsp, hdr); - return -EINVAL; - } + netdev->xdp_zc_max_segs)) + goto err_cancel_msg; } genlmsg_end(rsp, hdr); return 0; + +err_cancel_msg: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; } static void @@ -152,10 +152,7 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; - - return skb->len; + return err; } static int @@ -287,10 +284,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; - - return skb->len; + return err; } static int @@ -463,10 +457,7 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; - - return skb->len; + return err; } static int netdev_genl_netdevice_event(struct notifier_block *nb, diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 543007f159f99..55bcacf67df3b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -316,7 +316,7 @@ static int netpoll_owner_active(struct net_device *dev) struct napi_struct *napi; list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { - if (napi->poll_owner == smp_processor_id()) + if (READ_ONCE(napi->poll_owner) == smp_processor_id()) return 1; } return 0; diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 278294aca66ab..3a3277ba167b1 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -103,8 +103,6 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, mutex_unlock(&page_pools_lock); rtnl_unlock(); - if (skb->len && err == -EMSGSIZE) - return skb->len; return err; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bd50e9fe3234b..95e62235b5410 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -875,9 +875,9 @@ static void set_operstate(struct net_device *dev, unsigned char transition) break; } - if (dev->operstate != operstate) { + if (READ_ONCE(dev->operstate) != operstate) { write_lock(&dev_base_lock); - dev->operstate = operstate; + WRITE_ONCE(dev->operstate, operstate); write_unlock(&dev_base_lock); netdev_state_change(dev); } @@ -2552,7 +2552,7 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) nla_for_each_nested(attr, tb[IFLA_VF_VLAN_LIST], rem) { if (nla_type(attr) != IFLA_VF_VLAN_INFO || - nla_len(attr) < NLA_HDRLEN) { + nla_len(attr) < sizeof(struct ifla_vf_vlan_info)) { return -EINVAL; } if (len >= MAX_VLAN_LIST_LEN) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index edbbef563d4d9..570269c477549 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2014,11 +2014,17 @@ static inline int skb_alloc_rx_flag(const struct sk_buff *skb) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { - int headerlen = skb_headroom(skb); - unsigned int size = skb_end_offset(skb) + skb->data_len; - struct sk_buff *n = __alloc_skb(size, gfp_mask, - skb_alloc_rx_flag(skb), NUMA_NO_NODE); + struct sk_buff *n; + unsigned int size; + int headerlen; + + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + headerlen = skb_headroom(skb); + size = skb_end_offset(skb) + skb->data_len; + n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -2346,12 +2352,17 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask, skb_alloc_rx_flag(skb), - NUMA_NO_NODE); - int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; + struct sk_buff *n; + int oldheadroom; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + + oldheadroom = skb_headroom(skb); + n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (!n) return NULL; @@ -6736,6 +6747,14 @@ static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } +#endif +#ifdef CONFIG_MCTP_FLOWS + if (old_active & (1 << SKB_EXT_MCTP)) { + struct mctp_flow *flow = skb_ext_get_ptr(old, SKB_EXT_MCTP); + + if (flow->key) + refcount_inc(&flow->key->refs); + } #endif __skb_ext_put(old); return new; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 4d75ef9d24bfa..fd20aae30be23 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1226,11 +1226,8 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); - if (psock) { - read_lock_bh(&sk->sk_callback_lock); + if (psock) sk_psock_data_ready(sk, psock); - read_unlock_bh(&sk->sk_callback_lock); - } rcu_read_unlock(); } } diff --git a/net/core/sock.c b/net/core/sock.c index 5e78798456fd8..c0aeee7f42a60 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -283,6 +283,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; +int sysctl_mem_pcpu_rsv __read_mostly = SK_MEMORY_PCPU_RESERVE; int sysctl_tstamp_allow_data __read_mostly = 1; @@ -481,7 +482,7 @@ int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; - if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { + if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; @@ -551,7 +552,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, skb->dev = NULL; - if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { + if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } @@ -3731,6 +3732,9 @@ void sk_common_release(struct sock *sk) sk->sk_prot->unhash(sk); + if (sk->sk_socket) + sk->sk_socket->sk = NULL; + /* * In this point socket cannot receive new packets, but it is possible * that some packets are in flight because some CPU runs receiver and diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index b1e29e18d1d60..c53b731f2d672 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -193,7 +193,7 @@ int sock_diag_register(const struct sock_diag_handler *hndl) if (sock_diag_handlers[hndl->family]) err = -EBUSY; else - sock_diag_handlers[hndl->family] = hndl; + WRITE_ONCE(sock_diag_handlers[hndl->family], hndl); mutex_unlock(&sock_diag_table_mutex); return err; @@ -209,7 +209,7 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld) mutex_lock(&sock_diag_table_mutex); BUG_ON(sock_diag_handlers[family] != hnld); - sock_diag_handlers[family] = NULL; + WRITE_ONCE(sock_diag_handlers[family], NULL); mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister); @@ -227,7 +227,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX); - if (sock_diag_handlers[req->sdiag_family] == NULL) + if (READ_ONCE(sock_diag_handlers[req->sdiag_family]) == NULL) sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); @@ -286,12 +286,12 @@ static int sock_diag_bind(struct net *net, int group) switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET]) + if (!READ_ONCE(sock_diag_handlers[AF_INET])) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET6]) + if (!READ_ONCE(sock_diag_handlers[AF_INET6])) sock_load_diag_module(AF_INET6, 0); break; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 27d733c0f65e1..01be07b485fad 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -411,6 +411,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -933,6 +936,9 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); @@ -1633,19 +1639,23 @@ void sock_map_close(struct sock *sk, long timeout) lock_sock(sk); rcu_read_lock(); - psock = sk_psock_get(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - saved_close = READ_ONCE(sk->sk_prot)->close; - } else { + psock = sk_psock(sk); + if (likely(psock)) { saved_close = psock->saved_close; sock_map_remove_links(sk, psock); + psock = sk_psock_get(sk); + if (unlikely(!psock)) + goto no_psock; rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); + } else { + saved_close = READ_ONCE(sk->sk_prot)->close; +no_psock: + rcu_read_unlock(); + release_sock(sk); } /* Make sure we do not recurse. This is a bug. diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 0f0cb1465e089..986f15e5d6c41 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -30,6 +30,7 @@ static int int_3600 = 3600; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; +static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -407,6 +408,14 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, }, + { + .procname = "mem_pcpu_rsv", + .data = &sysctl_mem_pcpu_rsv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_mem_pcpu_rsv, + }, { .procname = "dev_weight", .data = &weight_p, diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 64d805b27adde..d2e356fde31fb 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -94,6 +94,8 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; + newdp->dccps_hc_rx_ccid = NULL; + newdp->dccps_hc_tx_ccid = NULL; newdp->dccps_service_list = NULL; newdp->dccps_hc_rx_ccid = NULL; newdp->dccps_hc_tx_ccid = NULL; diff --git a/net/devlink/core.c b/net/devlink/core.c index 7f0b093208d75..f49cd83f1955f 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -314,7 +314,7 @@ static void devlink_release(struct work_struct *work) mutex_destroy(&devlink->lock); lockdep_unregister_key(&devlink->lock_key); put_device(devlink->dev); - kfree(devlink); + kvfree(devlink); } void devlink_put(struct devlink *devlink) @@ -420,7 +420,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, if (!devlink_reload_actions_valid(ops)) return NULL; - devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); + devlink = kvzalloc(struct_size(devlink, priv, priv_size), GFP_KERNEL); if (!devlink) return NULL; @@ -455,7 +455,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, return devlink; err_xa_alloc: - kfree(devlink); + kvfree(devlink); return NULL; } EXPORT_SYMBOL_GPL(devlink_alloc_ns); diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index 499885c8b9cae..593605c1b1ef4 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -193,12 +193,13 @@ devlink_get_from_attrs_lock(struct net *net, struct nlattr **attrs, devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); devlinks_xa_for_each_registered_get(net, index, devlink) { - devl_dev_lock(devlink, dev_lock); - if (devl_is_registered(devlink) && - strcmp(devlink->dev->bus->name, busname) == 0 && - strcmp(dev_name(devlink->dev), devname) == 0) - return devlink; - devl_dev_unlock(devlink, dev_lock); + if (strcmp(devlink->dev->bus->name, busname) == 0 && + strcmp(dev_name(devlink->dev), devname) == 0) { + devl_dev_lock(devlink, dev_lock); + if (devl_is_registered(devlink)) + return devlink; + devl_dev_unlock(devlink, dev_lock); + } devlink_put(devlink); } diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index c81cf2dd154f3..f9786d51f68f9 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -198,7 +198,7 @@ static const struct nla_policy devlink_eswitch_set_nl_policy[DEVLINK_ATTR_ESWITC [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_MAX(NLA_U16, 1), - [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = NLA_POLICY_MAX(NLA_U16, 3), + [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = NLA_POLICY_MAX(NLA_U8, 3), [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = NLA_POLICY_MAX(NLA_U8, 1), }; diff --git a/net/devlink/port.c b/net/devlink/port.c index 4b2d46ccfe484..118d130d2afd5 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -889,7 +889,7 @@ int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info) err = -ENOMEM; goto err_out_port_del; } - err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, NULL); if (WARN_ON_ONCE(err)) goto err_out_msg_free; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 2edc8b796a4e7..4e3651101b866 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -161,20 +161,8 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - eth = (struct ethhdr *)skb->data; - skb_pull_inline(skb, ETH_HLEN); - - if (unlikely(!ether_addr_equal_64bits(eth->h_dest, - dev->dev_addr))) { - if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { - if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) - skb->pkt_type = PACKET_BROADCAST; - else - skb->pkt_type = PACKET_MULTICAST; - } else { - skb->pkt_type = PACKET_OTHERHOST; - } - } + eth = eth_skb_pull_mac(skb); + eth_skb_pkt_type(skb, dev); /* * Some variants of DSA tagging don't have an ethertype field diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7519b0818b913..60453ac6f17e7 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2182,7 +2182,7 @@ static int ethtool_get_phy_stats_ethtool(struct net_device *dev, const struct ethtool_ops *ops = dev->ethtool_ops; int n_stats, ret; - if (!ops || !ops->get_sset_count || ops->get_ethtool_phy_stats) + if (!ops || !ops->get_sset_count || !ops->get_ethtool_phy_stats) return -EOPNOTSUPP; n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 9d71b66183daf..03a42de7511e8 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -31,8 +31,8 @@ static bool is_slave_up(struct net_device *dev) static void __hsr_set_operstate(struct net_device *dev, int transition) { write_lock(&dev_base_lock); - if (dev->operstate != transition) { - dev->operstate = transition; + if (READ_ONCE(dev->operstate) != transition) { + WRITE_ONCE(dev->operstate, transition); write_unlock(&dev_base_lock); netdev_state_change(dev); } else { @@ -71,39 +71,36 @@ static bool hsr_check_carrier(struct hsr_port *master) return false; } -static void hsr_check_announce(struct net_device *hsr_dev, - unsigned char old_operstate) +static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); - - if (hsr_dev->operstate == IF_OPER_UP && old_operstate != IF_OPER_UP) { - /* Went up */ - hsr->announce_count = 0; - mod_timer(&hsr->announce_timer, - jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); + if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { + /* Enable announce timer and start sending supervisory frames */ + if (!timer_pending(&hsr->announce_timer)) { + hsr->announce_count = 0; + mod_timer(&hsr->announce_timer, jiffies + + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); + } + } else { + /* Deactivate the announce timer */ + timer_delete(&hsr->announce_timer); } - - if (hsr_dev->operstate != IF_OPER_UP && old_operstate == IF_OPER_UP) - /* Went down */ - del_timer(&hsr->announce_timer); } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; - unsigned char old_operstate; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ - old_operstate = master->dev->operstate; has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); - hsr_check_announce(master->dev, old_operstate); + hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 6d14d935ee828..26329db09210b 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -228,6 +228,10 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return NULL; + /* Use the existing sequence_nr from the tag as starting point * for filtering duplicate frames. */ diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index cb83c8feb7465..9756e657bab97 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -148,14 +148,21 @@ static struct notifier_block hsr_nb = { static int __init hsr_init(void) { - int res; + int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); - register_netdevice_notifier(&hsr_nb); - res = hsr_netlink_init(); + err = register_netdevice_notifier(&hsr_nb); + if (err) + return err; + + err = hsr_netlink_init(); + if (err) { + unregister_netdevice_notifier(&hsr_nb); + return err; + } - return res; + return 0; } static void __exit hsr_exit(void) diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index e5742f2a2d522..1b6457f357bdb 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -220,7 +220,8 @@ void hsr_del_port(struct hsr_port *port) netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); - dev_set_promiscuity(port->dev, -1); + if (!port->hsr->fwd_offloaded) + dev_set_promiscuity(port->dev, -1); netdev_upper_dev_unlink(port->dev, master->dev); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a5a820ee20266..88966ae7f9c4c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -757,7 +757,9 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new sock_rps_record_flow(newsk); WARN_ON(!((1 << newsk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_RECV | - TCPF_CLOSE_WAIT | TCPF_CLOSE))); + TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | + TCPF_CLOSING | TCPF_CLOSE_WAIT | + TCPF_CLOSE))); if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) set_bit(SOCK_SUPPORT_ZC, &newsock->flags); @@ -1305,8 +1307,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) int inet_sk_rebuild_header(struct sock *sk) { + struct rtable *rt = dst_rtable(__sk_dst_check(sk, 0)); struct inet_sock *inet = inet_sk(sk); - struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0); __be32 daddr; struct ip_options_rcu *inet_opt; struct flowi4 *fl4; @@ -1571,6 +1573,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) /* The above will be needed by the transport layer if there is one * immediately following this IP hdr. */ + NAPI_GRO_CB(skb)->inner_network_offset = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index d048aa8332938..685474ef11c40 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -2015,12 +2015,16 @@ static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) * from there we can determine the new total option length */ iter = 0; optlen_new = 0; - while (iter < opt->opt.optlen) - if (opt->opt.__data[iter] != IPOPT_NOP) { + while (iter < opt->opt.optlen) { + if (opt->opt.__data[iter] == IPOPT_END) { + break; + } else if (opt->opt.__data[iter] == IPOPT_NOP) { + iter++; + } else { iter += opt->opt.__data[iter + 1]; optlen_new = iter; - } else - iter++; + } + } hdr_delta = opt->opt.optlen; opt->opt.optlen = (optlen_new + 3) & ~3; hdr_delta -= opt->opt.optlen; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 4dd9e50406720..d33d124218140 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -95,7 +95,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static void esp_ssg_unref(struct xfrm_state *x, void *tmp) +static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; @@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - put_page(sg_page(sg)); + skb_page_unref(skb, sg_page(sg), false); } #ifdef CONFIG_INET_ESPINTCP @@ -260,7 +260,7 @@ static void esp_output_done(void *data, int err) } tmp = ESP_SKB_CB(skb)->tmp; - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); kfree(tmp); if (xo && (xo->flags & XFRM_DEV_RESUME)) { @@ -639,7 +639,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * } if (sg != dsg) - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index e63a3bf996176..207482d30dc7e 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -92,6 +92,7 @@ #include #include #include +#include /* * Build xmit assembly blocks @@ -482,6 +483,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct icmp_bxm *param) { struct net_device *route_lookup_dev; + struct dst_entry *dst, *dst2; struct rtable *rt, *rt2; struct flowi4 fl4_dec; int err; @@ -507,16 +509,17 @@ static struct rtable *icmp_route_lookup(struct net *net, /* No need to clone since we're just using its address. */ rt2 = rt; - rt = (struct rtable *) xfrm_lookup(net, &rt->dst, - flowi4_to_flowi(fl4), NULL, 0); - if (!IS_ERR(rt)) { + dst = xfrm_lookup(net, &rt->dst, + flowi4_to_flowi(fl4), NULL, 0); + rt = dst_rtable(dst); + if (!IS_ERR(dst)) { if (rt != rt2) return rt; - } else if (PTR_ERR(rt) == -EPERM) { + } else if (PTR_ERR(dst) == -EPERM) { rt = NULL; - } else + } else { return rt; - + } err = xfrm_decode_session_reverse(net, skb_in, flowi4_to_flowi(&fl4_dec), AF_INET); if (err) goto relookup_failed; @@ -550,19 +553,19 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst, - flowi4_to_flowi(&fl4_dec), NULL, - XFRM_LOOKUP_ICMP); - if (!IS_ERR(rt2)) { + dst2 = xfrm_lookup(net, &rt2->dst, flowi4_to_flowi(&fl4_dec), NULL, + XFRM_LOOKUP_ICMP); + rt2 = dst_rtable(dst2); + if (!IS_ERR(dst2)) { dst_release(&rt->dst); memcpy(fl4, &fl4_dec, sizeof(*fl4)); rt = rt2; - } else if (PTR_ERR(rt2) == -EPERM) { + } else if (PTR_ERR(dst2) == -EPERM) { if (rt) dst_release(&rt->dst); return rt2; } else { - err = PTR_ERR(rt2); + err = PTR_ERR(dst2); goto relookup_failed; } return rt; @@ -1032,6 +1035,8 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) struct icmp_ext_hdr *ext_hdr, _ext_hdr; struct icmp_ext_echo_iio *iio, _iio; struct net *net = dev_net(skb->dev); + struct inet6_dev *in6_dev; + struct in_device *in_dev; struct net_device *dev; char buff[IFNAMSIZ]; u16 ident_len; @@ -1115,10 +1120,15 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) /* Fill bits in reply message */ if (dev->flags & IFF_UP) status |= ICMP_EXT_ECHOREPLY_ACTIVE; - if (__in_dev_get_rcu(dev) && __in_dev_get_rcu(dev)->ifa_list) + + in_dev = __in_dev_get_rcu(dev); + if (in_dev && rcu_access_pointer(in_dev->ifa_list)) status |= ICMP_EXT_ECHOREPLY_IPV4; - if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list)) + + in6_dev = __in6_dev_get(dev); + if (in6_dev && !list_empty(&in6_dev->addr_list)) status |= ICMP_EXT_ECHOREPLY_IPV6; + dev_put(dev); icmphdr->un.echo.sequence |= htons(status); return true; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 459af1f897395..d1492c649aea0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -203,8 +203,15 @@ static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { - if (sk->sk_family == AF_INET && ipv6_only_sock(sk2)) - return false; + if (ipv6_only_sock(sk2)) { + if (sk->sk_family == AF_INET) + return false; + +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) + return false; +#endif + } return inet_bind_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok); @@ -287,6 +294,7 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l struct sock_reuseport *reuseport_cb; struct inet_bind_hashbucket *head2; struct inet_bind2_bucket *tb2; + bool conflict = false; bool reuseport_cb_ok; rcu_read_lock(); @@ -299,18 +307,20 @@ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l spin_lock(&head2->lock); - inet_bind_bucket_for_each(tb2, &head2->chain) - if (inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) - break; + inet_bind_bucket_for_each(tb2, &head2->chain) { + if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) + continue; - if (tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok)) { - spin_unlock(&head2->lock); - return true; + if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok)) + continue; + + conflict = true; + break; } spin_unlock(&head2->lock); - return false; + + return conflict; } /* @@ -771,6 +781,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk) } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); +void inet_csk_clear_xmit_timers_sync(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + /* ongoing timer handlers need to acquire socket lock. */ + sock_not_owned_by_me(sk); + + icsk->icsk_pending = icsk->icsk_ack.pending = 0; + + sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); + sk_stop_timer_sync(sk, &sk->sk_timer); +} + void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8e6b6aa0579e1..9804e9608a5a0 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -57,7 +57,7 @@ static const struct inet_diag_handler *inet_diag_lock_handler(int proto) return ERR_PTR(-ENOENT); } - if (!inet_diag_table[proto]) + if (!READ_ONCE(inet_diag_table[proto])) sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); @@ -1503,7 +1503,7 @@ int inet_diag_register(const struct inet_diag_handler *h) mutex_lock(&inet_diag_table_mutex); err = -EEXIST; if (!inet_diag_table[type]) { - inet_diag_table[type] = h; + WRITE_ONCE(inet_diag_table[type], h); err = 0; } mutex_unlock(&inet_diag_table_mutex); @@ -1520,7 +1520,7 @@ void inet_diag_unregister(const struct inet_diag_handler *h) return; mutex_lock(&inet_diag_table_mutex); - inet_diag_table[type] = NULL; + WRITE_ONCE(inet_diag_table[type], NULL); mutex_unlock(&inet_diag_table_mutex); } EXPORT_SYMBOL_GPL(inet_diag_unregister); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 7072fc0783ef5..c88c9034d6300 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -24,6 +24,8 @@ #include #include +#include "../core/sock_destructor.h" + /* Use skb->cb to track consecutive/adjacent fragments coming at * the end of the queue. Nodes in the rb-tree queue will * contain "runs" of one or more adjacent fragments. @@ -39,6 +41,7 @@ struct ipfrag_skb_cb { }; struct sk_buff *next_frag; int frag_run_len; + int ip_defrag_offset; }; #define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) @@ -396,12 +399,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, */ if (!last) fragrun_create(q, skb); /* First fragment. */ - else if (last->ip_defrag_offset + last->len < end) { + else if (FRAG_CB(last)->ip_defrag_offset + last->len < end) { /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ - if (offset < last->ip_defrag_offset + last->len) + if (offset < FRAG_CB(last)->ip_defrag_offset + last->len) return IPFRAG_OVERLAP; - if (offset == last->ip_defrag_offset + last->len) + if (offset == FRAG_CB(last)->ip_defrag_offset + last->len) fragrun_append_to_last(q, skb); else fragrun_create(q, skb); @@ -418,13 +421,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, parent = *rbn; curr = rb_to_skb(parent); - curr_run_end = curr->ip_defrag_offset + + curr_run_end = FRAG_CB(curr)->ip_defrag_offset + FRAG_CB(curr)->frag_run_len; - if (end <= curr->ip_defrag_offset) + if (end <= FRAG_CB(curr)->ip_defrag_offset) rbn = &parent->rb_left; else if (offset >= curr_run_end) rbn = &parent->rb_right; - else if (offset >= curr->ip_defrag_offset && + else if (offset >= FRAG_CB(curr)->ip_defrag_offset && end <= curr_run_end) return IPFRAG_DUP; else @@ -438,7 +441,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, rb_insert_color(&skb->rbnode, &q->rb_fragments); } - skb->ip_defrag_offset = offset; + FRAG_CB(skb)->ip_defrag_offset = offset; return IPFRAG_OK; } @@ -448,13 +451,28 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent) { struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); - struct sk_buff **nextp; + void (*destructor)(struct sk_buff *); + unsigned int orig_truesize = 0; + struct sk_buff **nextp = NULL; + struct sock *sk = skb->sk; int delta; + if (sk && is_skb_wmem(skb)) { + /* TX: skb->sk might have been passed as argument to + * dst->output and must remain valid until tx completes. + * + * Move sk to reassembled skb and fix up wmem accounting. + */ + orig_truesize = skb->truesize; + destructor = skb->destructor; + } + if (head != skb) { fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - return NULL; + if (!fp) { + head = skb; + goto out_restore_sk; + } FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; if (RB_EMPTY_NODE(&skb->rbnode)) FRAG_CB(parent)->next_frag = fp; @@ -463,6 +481,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, &q->rb_fragments); if (q->fragments_tail == skb) q->fragments_tail = fp; + + if (orig_truesize) { + /* prevent skb_morph from releasing sk */ + skb->sk = NULL; + skb->destructor = NULL; + } skb_morph(skb, head); FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; rb_replace_node(&head->rbnode, &skb->rbnode, @@ -470,13 +494,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, consume_skb(head); head = skb; } - WARN_ON(head->ip_defrag_offset != 0); + WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0); delta = -head->truesize; /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) - return NULL; + goto out_restore_sk; delta += head->truesize; if (delta) @@ -492,7 +516,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, clone = alloc_skb(0, GFP_ATOMIC); if (!clone) - return NULL; + goto out_restore_sk; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) @@ -509,6 +533,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, nextp = &skb_shinfo(head)->frag_list; } +out_restore_sk: + if (orig_truesize) { + int ts_delta = head->truesize - orig_truesize; + + /* if this reassembled skb is fragmented later, + * fraglist skbs will get skb->sk assigned from head->sk, + * and each frag skb will be released via sock_wfree. + * + * Update sk_wmem_alloc. + */ + head->sk = sk; + head->destructor = destructor; + refcount_add(ts_delta, &sk->sk_wmem_alloc); + } + return nextp; } EXPORT_SYMBOL(inet_frag_reasm_prepare); @@ -516,6 +555,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce) { + struct sock *sk = is_skb_wmem(head) ? head->sk : NULL; + const unsigned int head_truesize = head->truesize; struct sk_buff **nextp = reasm_data; struct rb_node *rbn; struct sk_buff *fp; @@ -579,6 +620,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, head->prev = NULL; head->tstamp = q->stamp; head->mono_delivery_time = q->mono_delivery_time; + + if (sk) + refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(inet_frag_reasm_finish); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 308ff34002ea6..4e470f18487f6 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1136,7 +1136,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(lock); - sk_nulls_del_node_init_rcu(sk); + __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); sk->sk_hash = 0; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 5befa4de5b241..e8de45d34d56a 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -263,12 +263,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); +/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) { - struct inet_timewait_sock *tw; - struct sock *sk; struct hlist_nulls_node *node; unsigned int slot; + struct sock *sk; for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; @@ -277,38 +277,35 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (sk->sk_state != TCP_TIME_WAIT) { - /* A kernel listener socket might not hold refcnt for net, - * so reqsk_timer_handler() could be fired after net is - * freed. Userspace listener and reqsk never exist here. - */ - if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV && - hashinfo->pernet)) { - struct request_sock *req = inet_reqsk(sk); - - inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); - } + int state = inet_sk_state_load(sk); + if ((1 << state) & ~(TCPF_TIME_WAIT | + TCPF_NEW_SYN_RECV)) continue; - } - tw = inet_twsk(sk); - if ((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count)) + if (sk->sk_family != family || + refcount_read(&sock_net(sk)->ns.count)) continue; - if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count))) { - inet_twsk_put(tw); + if (unlikely(sk->sk_family != family || + refcount_read(&sock_net(sk)->ns.count))) { + sock_gen_put(sk); goto restart; } rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule_put(tw); + if (state == TCP_TIME_WAIT) { + inet_twsk_deschedule_put(inet_twsk(sk)); + } else { + struct request_sock *req = inet_reqsk(sk); + + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, + req); + } local_bh_enable(); goto restart_rcu; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index a4941f53b5237..fb947d1613fe2 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -384,6 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -487,7 +488,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); - skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 6b9cf5a24c19f..1954a56fec6ba 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -280,8 +280,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, tpi->flags | TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); } else { + if (unlikely(!pskb_may_pull(skb, + gre_hdr_len + sizeof(*ershdr)))) + return PACKET_REJECT; + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; + iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 5e9c8156656a7..d6fbcbd2358a5 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -616,7 +616,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, dst = skb_dst(skb); if (curr_dst != dst) { hint = ip_extract_route_hint(net, skb, - ((struct rtable *)dst)->rt_type); + dst_rtable(dst)->rt_type); /* dispatch old sublist */ if (!list_empty(&sublist)) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 67d846622365e..3e6ea4318d1e3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -198,7 +198,7 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct rtable *rt = (struct rtable *)dst; + struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; @@ -475,7 +475,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, goto packet_routed; /* Make sure we can route this packet. */ - rt = (struct rtable *)__sk_dst_check(sk, 0); + rt = dst_rtable(__sk_dst_check(sk, 0)); if (!rt) { __be32 daddr; @@ -971,7 +971,7 @@ static int __ip_append_data(struct sock *sk, bool zc = false; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; - struct rtable *rt = (struct rtable *)cork->dst; + struct rtable *rt = dst_rtable(cork->dst); bool paged, hold_tskey, extra_uref = false; unsigned int wmem_alloc_delta = 0; u32 tskey = 0; @@ -1390,7 +1390,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options *opt = NULL; - struct rtable *rt = (struct rtable *)cork->dst; + struct rtable *rt = dst_rtable(cork->dst); struct iphdr *iph; u8 pmtudisc, ttl; __be16 df = 0; @@ -1473,7 +1473,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * by icmp_hdr(skb)->type. */ if (sk->sk_type == SOCK_RAW && - !inet_test_bit(HDRINCL, sk)) + !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 21d2ffa919e98..5e196aec51423 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -128,20 +128,20 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) { - char *secdata; - u32 seclen, secid; + struct lsmcontext ctx; + u32 secid; int err; err = security_socket_getpeersec_dgram(NULL, skb, &secid); if (err) return; - err = security_secid_to_secctx(secid, &secdata, &seclen); - if (err) + err = security_secid_to_secctx(secid, &ctx); + if (err < 0) return; - put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata); - security_release_secctx(secdata, seclen); + put_cmsg(msg, SOL_IP, SCM_SECURITY, ctx.len, ctx.context); + security_release_secctx(&ctx); } static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 1b6981de3f295..2bf31d0cb7898 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -378,7 +378,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); - int err; + int nh, err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { @@ -404,8 +404,21 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + iph = (struct iphdr *)(skb->head + nh); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -531,7 +544,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rt6_info *rt6; __be32 daddr; - rt6 = skb_valid_dst(skb) ? (struct rt6_info *)skb_dst(skb) : + rt6 = skb_valid_dst(skb) ? dst_rt6_info(skb_dst(skb)) : NULL; daddr = md ? dst : tunnel->parms.iph.daddr; @@ -1223,7 +1236,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id); if (dev == itn->fb_tunnel_dev) - return -EINVAL; + return fan_has_map(&tunnel->fan) ? 0 : -EINVAL; t = ip_tunnel_find(itn, p, dev->type); @@ -1285,6 +1298,7 @@ int ip_tunnel_init(struct net_device *dev) if (tunnel->collect_md) netif_keep_dst(dev); + netdev_lockdep_set_classes(dev); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 03afa3871efc5..6025822763bf0 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -101,6 +101,8 @@ #include #include #include +#include +#include #include #include @@ -267,6 +269,147 @@ static int mplsip_rcv(struct sk_buff *skb) } #endif +static struct ip_fan_map *ipip_fan_find_map(struct ip_tunnel *t, __be32 daddr) +{ + struct ip_fan_map *fan_map; + + rcu_read_lock(); + list_for_each_entry_rcu(fan_map, &t->fan.fan_maps, list) { + if (fan_map->overlay == + (daddr & inet_make_mask(fan_map->overlay_prefix))) { + rcu_read_unlock(); + return fan_map; + } + } + rcu_read_unlock(); + + return NULL; +} + +/* Determine fan tunnel endpoint to send packet to, based on the inner IP + * address. + * + * Given a /8 overlay and /16 underlay, for an overlay (inner) address + * Y.A.B.C, the transformation is F.G.A.B, where "F" and "G" are the first + * two octets of the underlay network (the network portion of a /16), "A" + * and "B" are the low order two octets of the underlay network host (the + * host portion of a /16), and "Y" is a configured first octet of the + * overlay network. + * + * E.g., underlay host 10.88.3.4/16 with an overlay of 99.0.0.0/8 would + * host overlay subnet 99.3.4.0/24. An overlay network datagram from + * 99.3.4.5 to 99.6.7.8, would be directed to underlay host 10.88.6.7, + * which hosts overlay network subnet 99.6.7.0/24. This transformation is + * described in detail further below. + * + * Using netmasks for the overlay and underlay other than /8 and /16, as + * shown above, can yield larger (or smaller) overlay subnets, with the + * trade-off of allowing fewer (or more) underlay hosts to participate. + * + * The size of each overlay network subnet is defined by the total of the + * network mask of the overlay plus the size of host portion of the + * underlay network. In the above example, /8 + /16 = /24. + * + * E.g., consider underlay host 10.99.238.5/20 and overlay 99.0.0.0/8. In + * this case, the network portion of the underlay is 10.99.224.0/20, and + * the host portion is 0.0.14.5 (12 bits). To determine the overlay + * network subnet, the 12 bits of host portion are left shifted 12 bits + * (/20 - /8) and ORed with the overlay subnet prefix. This yields an + * overlay subnet of 99.224.80/20, composed of 8 bits overlay, followed by + * 12 bits underlay. This yields 12 bits in the overlay network portion, + * allowing for 4094 addresses in each overlay network subnet. The + * trade-off is that fewer hosts may participate in the underlay network, + * as its host address size has shrunk from 16 bits (65534 addresses) in + * the first example to 12 bits (4094 addresses) here. + * + * For fewer hosts per overlay subnet (permitting a larger number of + * underlay hosts to participate), the underlay netmask may be made + * smaller. + * + * E.g., underlay host 10.111.1.2/12 (network 10.96.0.0/12, host portion + * is 0.15.1.2, 20 bits) with an overlay of 33.0.0.0/8 would left shift + * the 20 bits of host by 4 (so that it's highest order bit is adjacent to + * the lowest order bit of the /8 overlay). This yields an overlay subnet + * of 33.240.16.32/28 (8 bits overlay, 20 bits from the host portion of + * the underlay). This provides more addresses for the underlay network + * (approximately 2^20), but each host's segment of the overlay provides + * only 4 bits of addresses (14 usable). + * + * It is also possible to adjust the overlay subnet. + * + * For an overlay of 240.0.0.0/5 and underlay of 10.88.0.0/20, consider + * underlay host 10.88.129.2; the 12 bits of host, 0.0.1.2, are left + * shifted 15 bits (/20 - /5), yielding an overlay network of + * 240.129.0.0/17. An underlay host of 10.88.244.215 would yield an + * overlay network of 242.107.128.0/17. + * + * For an overlay of 100.64.0.0/10 and underlay of 10.224.220.0/24, for + * underlay host 10.224.220.10, the underlay host portion (.10) is left + * shifted 14 bits, yielding an overlay network subnet of 100.66.128.0/18. + * This would permit 254 addresses on the underlay, with each overlay + * segment providing approximately 2^14 - 2 addresses (16382). + * + * For packets being encapsulated, the overlay network destination IP + * address is deconstructed into its overlay and underlay-derived + * portions. The underlay portion (determined by the overlay mask and + * overlay subnet mask) is right shifted according to the size of the + * underlay network mask. This value is then ORed with the network + * portion of the underlay network to produce the underlay network + * destination for the encapsulated datagram. + * + * For example, using the initial example of underlay 10.88.3.4/16 and + * overlay 99.0.0.0/8, with underlay host 10.88.3.4/16 providing overlay + * subnet 99.3.4.0/24 with specfic host 99.3.4.5. A datagram from + * 99.3.4.5 to 99.6.7.8 would first have the underlay host derived portion + * of the address extracted. This is a number of bits equal to underlay + * network host portion. In the destination address, the highest order of + * these bits is one bit lower than the lowest order bit from the overlay + * network mask. + * + * Using the sample value, 99.6.7.8, the overlay mask is /8, and the + * underlay mask is /16 (leaving 16 bits for the host portion). The bits + * to be shifted are the middle two octets, 0.6.7.0, as this is 99.6.7.8 + * ANDed with the mask 0x00ffff00 (which is 16 bits, the highest order of + * which is 1 bit lower than the lowest order overlay address bit). + * + * These octets, 0.6.7.0, are then right shifted 8 bits, yielding 0.0.6.7. + * This value is then ORed with the underlay network portion, + * 10.88.0.0/16, providing 10.88.6.7 as the final underlay destination for + * the encapuslated datagram. + * + * Another transform using the final example: overlay 100.64.0.0/10 and + * underlay 10.224.220.0/24. Consider overlay address 100.66.128.1 + * sending a datagram to 100.66.200.5. In this case, 8 bits (the host + * portion size of 10.224.220.0/24) beginning after the 100.64/10 overlay + * prefix are masked off, yielding 0.2.192.0. This is right shifted 14 + * (32 - 10 - (32 - 24), i.e., the number of bits between the overlay + * network portion and the underlay host portion) bits, yielding 0.0.0.11. + * This is ORed with the underlay network portion, 10.224.220.0/24, giving + * the underlay destination of 10.224.220.11 for overlay destination + * 100.66.200.5. + */ +static int ipip_build_fan_iphdr(struct ip_tunnel *tunnel, struct sk_buff *skb, struct iphdr *iph) +{ + struct ip_fan_map *f_map; + u32 daddr, underlay; + + f_map = ipip_fan_find_map(tunnel, ip_hdr(skb)->daddr); + if (!f_map) + return -ENOENT; + + daddr = ntohl(ip_hdr(skb)->daddr); + underlay = ntohl(f_map->underlay); + if (!underlay) + return -EINVAL; + + *iph = tunnel->parms.iph; + iph->daddr = htonl(underlay | + ((daddr & ~f_map->overlay_mask) >> + (32 - f_map->overlay_prefix - + (32 - f_map->underlay_prefix)))); + return 0; +} + /* * This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. @@ -277,6 +420,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto; + struct iphdr fiph; if (!pskb_inet_may_pull(skb)) goto tx_error; @@ -300,6 +444,14 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; + if (fan_has_map(&tunnel->fan)) { + if (ipip_build_fan_iphdr(tunnel, skb, &fiph)) + goto tx_error; + tiph = &fiph; + } else { + tiph = &tunnel->parms.iph; + } + skb_set_inner_ipproto(skb, ipproto); if (tunnel->collect_md) @@ -363,6 +515,8 @@ static const struct net_device_ops ipip_netdev_ops = { static void ipip_tunnel_setup(struct net_device *dev) { + struct ip_tunnel *t = netdev_priv(dev); + dev->netdev_ops = &ipip_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; @@ -375,6 +529,7 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->features |= IPIP_FEATURES; dev->hw_features |= IPIP_FEATURES; ip_tunnel_setup(dev, ipip_net_id); + INIT_LIST_HEAD(&t->fan.fan_maps); } static int ipip_tunnel_init(struct net_device *dev) @@ -427,6 +582,92 @@ static void ipip_netlink_parms(struct nlattr *data[], *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } +static void ipip_fan_flush_map(struct ip_tunnel *t) +{ + struct ip_fan_map *fan_map; + + list_for_each_entry_rcu(fan_map, &t->fan.fan_maps, list) { + list_del_rcu(&fan_map->list); + kfree_rcu(fan_map, rcu); + } +} + +static int ipip_fan_del_map(struct ip_tunnel *t, __be32 overlay) +{ + struct ip_fan_map *fan_map; + + fan_map = ipip_fan_find_map(t, overlay); + if (!fan_map) + return -ENOENT; + + list_del_rcu(&fan_map->list); + kfree_rcu(fan_map, rcu); + + return 0; +} + +static int ipip_fan_add_map(struct ip_tunnel *t, struct ifla_fan_map *map) +{ + __be32 overlay_mask, underlay_mask; + struct ip_fan_map *fan_map; + + overlay_mask = inet_make_mask(map->overlay_prefix); + underlay_mask = inet_make_mask(map->underlay_prefix); + + if ((map->overlay & ~overlay_mask) || (map->underlay & ~underlay_mask)) + return -EINVAL; + + if (!(map->overlay & overlay_mask) && (map->underlay & underlay_mask)) + return -EINVAL; + + /* Special case: overlay 0 and underlay 0: flush all mappings */ + if (!map->overlay && !map->underlay) { + ipip_fan_flush_map(t); + return 0; + } + + /* Special case: overlay set and underlay 0: clear map for overlay */ + if (!map->underlay) + return ipip_fan_del_map(t, map->overlay); + + if (ipip_fan_find_map(t, map->overlay)) + return -EEXIST; + + fan_map = kmalloc(sizeof(*fan_map), GFP_KERNEL); + fan_map->underlay = map->underlay; + fan_map->overlay = map->overlay; + fan_map->underlay_prefix = map->underlay_prefix; + fan_map->overlay_mask = ntohl(overlay_mask); + fan_map->overlay_prefix = map->overlay_prefix; + + list_add_tail_rcu(&fan_map->list, &t->fan.fan_maps); + + return 0; +} + +static int ipip_netlink_fan(struct nlattr *data[], struct ip_tunnel *t, + struct ip_tunnel_parm *parms) +{ + struct ifla_fan_map *map; + struct nlattr *attr; + int rem, rv; + + if (data == NULL || !data[IFLA_IPTUN_FAN_MAP]) + return 0; + + if (parms->iph.daddr) + return -EINVAL; + + nla_for_each_nested(attr, data[IFLA_IPTUN_FAN_MAP], rem) { + map = nla_data(attr); + rv = ipip_fan_add_map(t, map); + if (rv) + return rv; + } + + return 0; +} + static int ipip_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -435,15 +676,19 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; __u32 fwmark = 0; + int err; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { - int err = ip_tunnel_encap_setup(t, &ipencap); + err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip_netlink_parms(data, &p, &t->collect_md, &fwmark); + err = ipip_netlink_fan(data, t, &p); + if (err < 0) + return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } @@ -456,9 +701,10 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_encap ipencap; bool collect_md; __u32 fwmark = t->fwmark; + int err; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { - int err = ip_tunnel_encap_setup(t, &ipencap); + err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; @@ -467,6 +713,9 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], ipip_netlink_parms(data, &p, &collect_md, &fwmark); if (collect_md) return -EINVAL; + err = ipip_netlink_fan(data, t, &p); + if (err < 0) + return err; if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) @@ -504,6 +753,8 @@ static size_t ipip_get_size(const struct net_device *dev) nla_total_size(0) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + + /* IFLA_IPTUN_FAN_MAP */ + nla_total_size(sizeof(struct ifla_fan_map)) * 256 + 0; } @@ -536,6 +787,26 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) if (tunnel->collect_md) if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) goto nla_put_failure; + if (fan_has_map(&tunnel->fan)) { + struct nlattr *fan_nest; + struct ip_fan_map *fan_map; + + fan_nest = nla_nest_start(skb, IFLA_IPTUN_FAN_MAP); + if (!fan_nest) + goto nla_put_failure; + list_for_each_entry_rcu(fan_map, &tunnel->fan.fan_maps, list) { + struct ifla_fan_map map; + + map.underlay = fan_map->underlay; + map.underlay_prefix = fan_map->underlay_prefix; + map.overlay = fan_map->overlay; + map.overlay_prefix = fan_map->overlay_prefix; + if (nla_put(skb, IFLA_FAN_MAPPING, sizeof(map), &map)) + goto nla_put_failure; + } + nla_nest_end(skb, fan_nest); + } + return 0; nla_put_failure: @@ -556,6 +827,9 @@ static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, + + [__IFLA_IPTUN_VENDOR_BREAK ... IFLA_IPTUN_MAX] = { .type = NLA_BINARY }, + [IFLA_IPTUN_FAN_MAP] = { .type = NLA_NESTED }, }; static struct rtnl_link_ops ipip_link_ops __read_mostly = { @@ -604,6 +878,23 @@ static struct pernet_operations ipip_net_ops = { .size = sizeof(struct ip_tunnel_net), }; +#ifdef CONFIG_SYSCTL +static struct ctl_table_header *ipip_fan_header; +static unsigned int ipip_fan_version = 3; + +static struct ctl_table ipip_fan_sysctls[] = { + { + .procname = "version", + .data = &ipip_fan_version, + .maxlen = sizeof(ipip_fan_version), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + {}, +}; + +#endif /* CONFIG_SYSCTL */ + static int __init ipip_init(void) { int err; @@ -629,9 +920,22 @@ static int __init ipip_init(void) if (err < 0) goto rtnl_link_failed; +#ifdef CONFIG_SYSCTL + ipip_fan_header = register_net_sysctl(&init_net, "net/fan", + ipip_fan_sysctls); + if (!ipip_fan_header) { + err = -ENOMEM; + goto sysctl_failed; + } +#endif /* CONFIG_SYSCTL */ + out: return err; +#ifdef CONFIG_SYSCTL +sysctl_failed: + rtnl_link_unregister(&ipip_link_ops); +#endif /* CONFIG_SYSCTL */ rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); @@ -646,6 +950,9 @@ static int __init ipip_init(void) static void __exit ipip_fini(void) { +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(ipip_fan_header); +#endif /* CONFIG_SYSCTL */ rtnl_link_unregister(&ipip_link_ops); if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) pr_info("%s: can't deregister tunnel\n", __func__); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3622298365105..b53c36c473a5b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1603,9 +1603,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; - olr = min_t(unsigned int, olr, sizeof(int)); if (olr < 0) return -EINVAL; + + olr = min_t(unsigned int, olr, sizeof(int)); + if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 2407066b0fec1..04e0d84b93dbb 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -296,6 +296,17 @@ static inline bool unconditional(const struct arpt_entry *e) memcmp(&e->arp, &uncond, sizeof(uncond)) == 0; } +static bool next_offset_ok(const struct xt_table_info *t, unsigned int newpos) +{ + if (newpos > t->size - sizeof(struct arpt_entry)) + return false; + + if (newpos % __alignof__(struct arpt_entry) != 0) + return false; + + return true; +} + /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. */ @@ -354,6 +365,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo, /* Move along one */ size = e->next_offset; + if (!next_offset_ok(newinfo, pos + size)) + return 0; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; @@ -375,6 +388,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo, if (newpos >= newinfo->size) return 0; } + + if (!next_offset_ok(newinfo, newpos)) + return 0; + e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; @@ -956,6 +973,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -964,6 +983,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1254,6 +1275,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1262,6 +1285,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 7da1df4997d05..cef08244b6fb8 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -361,6 +361,17 @@ ipt_do_table(void *priv, else return verdict; } +static bool next_offset_ok(const struct xt_table_info *t, unsigned int newpos) +{ + if (newpos > t->size - sizeof(struct ipt_entry)) + return false; + + if (newpos % __alignof__(struct ipt_entry) != 0) + return false; + + return true; +} + /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int @@ -416,6 +427,8 @@ mark_source_chains(const struct xt_table_info *newinfo, /* Move along one */ size = e->next_offset; + if (!next_offset_ok(newinfo, pos + size)) + return 0; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; @@ -437,6 +450,10 @@ mark_source_chains(const struct xt_table_info *newinfo, if (newpos >= newinfo->size) return 0; } + + if (!next_offset_ok(newinfo, newpos)) + return 0; + e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; @@ -1108,6 +1125,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1116,6 +1135,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1492,6 +1513,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1500,6 +1523,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 69e3317996043..73e66a088e25e 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) laddr = 0; indev = __in_dev_get_rcu(skb->dev); + if (!indev) + return daddr; in_dev_for_each_ifa_rcu(ifa, indev) { if (ifa->ifa_flags & IFA_F_SECONDARY) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index aea89326c6979..a1d8218fa1a2d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -350,6 +350,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, goto error; skb_reserve(skb, hlen); + skb->protocol = htons(ETH_P_IP); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; @@ -604,6 +605,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = 0; + fl4.fl4_icmp_code = 0; + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 16615d107cf06..cab30af5be348 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -132,7 +132,8 @@ struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, @@ -831,28 +832,21 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf u32 mark = skb->mark; __u8 tos = iph->tos; - rt = (struct rtable *) dst; + rt = dst_rtable(dst); __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); __ip_do_redirect(rt, skb, &fl4, true); } -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst) { - struct rtable *rt = (struct rtable *)dst; - struct dst_entry *ret = dst; + struct rtable *rt = dst_rtable(dst); - if (rt) { - if (dst->obsolete > 0) { - ip_rt_put(rt); - ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) { - ip_rt_put(rt); - ret = NULL; - } - } - return ret; + if ((dst->obsolete > 0) || + (rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) + sk_dst_reset(sk); } /* @@ -926,13 +920,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; -#ifdef CONFIG_IP_ROUTE_VERBOSE - if (log_martians && + if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); -#endif } out_put_peer: inet_putpeer(peer); @@ -1058,7 +1050,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { - struct rtable *rt = (struct rtable *) dst; + struct rtable *rt = dst_rtable(dst); struct flowi4 fl4; ip_rt_build_flow_key(&fl4, sk, skb); @@ -1129,7 +1121,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); - rt = (struct rtable *)odst; + rt = dst_rtable(odst); if (odst->obsolete && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) @@ -1138,7 +1130,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) new = true; } - __ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu); + __ip_rt_update_pmtu(dst_rtable(xfrm_dst_path(&rt->dst)), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) @@ -1195,7 +1187,7 @@ EXPORT_SYMBOL_GPL(ipv4_sk_redirect); INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { - struct rtable *rt = (struct rtable *) dst; + struct rtable *rt = dst_rtable(dst); /* All IPV4 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down @@ -1530,10 +1522,8 @@ void rt_del_uncached_list(struct rtable *rt) static void ipv4_dst_destroy(struct dst_entry *dst) { - struct rtable *rt = (struct rtable *)dst; - ip_dst_metrics_put(dst); - rt_del_uncached_list(rt); + rt_del_uncached_list(dst_rtable(dst)); } void rt_flush_dev(struct net_device *dev) @@ -2168,6 +2158,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, int err = -EINVAL; u32 tag = 0; + if (!in_dev) + return -EINVAL; + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; @@ -2831,7 +2824,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rtable *ort = (struct rtable *) dst_orig; + struct rtable *ort = dst_rtable(dst_orig); struct rtable *rt; rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, DST_OBSOLETE_DEAD, 0); @@ -2876,9 +2869,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, if (flp4->flowi4_proto) { flp4->flowi4_oif = rt->dst.dev->ifindex; - rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, - flowi4_to_flowi(flp4), - sk, 0); + rt = dst_rtable(xfrm_lookup_route(net, &rt->dst, + flowi4_to_flowi(flp4), + sk, 0)); } return rt; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c82dc42f57c65..901f1d8944e45 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1158,6 +1158,9 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) process_backlog++; +#ifdef CONFIG_SKB_DECRYPTED + skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); +#endif tcp_skb_entail(sk, skb); copy = size_goal; @@ -2636,6 +2639,10 @@ void tcp_set_state(struct sock *sk, int state) if (oldstate != TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; + case TCP_CLOSE_WAIT: + if (oldstate == TCP_SYN_RECV) + TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); + break; case TCP_CLOSE: if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED) @@ -2647,7 +2654,7 @@ void tcp_set_state(struct sock *sk, int state) inet_put_port(sk); fallthrough; default: - if (oldstate == TCP_ESTABLISHED) + if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); } @@ -2709,7 +2716,7 @@ void tcp_shutdown(struct sock *sk, int how) /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | - TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) { + TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); @@ -2818,7 +2825,7 @@ void __tcp_close(struct sock *sk, long timeout) * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 - * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible) + * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), @@ -2930,6 +2937,8 @@ void tcp_close(struct sock *sk, long timeout) lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); + if (!sk->sk_net_refcnt) + inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); @@ -4010,11 +4019,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 87db432c6bb4a..8e9b7587cc605 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -933,6 +933,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, struct tcp_ao_key *key; __be32 sisn, disn; u8 *traffic_key; + int state; u32 sne = 0; info = rcu_dereference(tcp_sk(sk)->ao_info); @@ -948,8 +949,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, disn = 0; } + state = READ_ONCE(sk->sk_state); /* Fast-path */ - if (likely((1 << sk->sk_state) & TCP_AO_ESTABLISHED)) { + if (likely((1 << state) & TCP_AO_ESTABLISHED)) { enum skb_drop_reason err; struct tcp_ao_key *current_key; @@ -988,6 +990,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, return SKB_NOT_DROPPED_YET; } + if (unlikely(state == TCP_CLOSE)) + return SKB_DROP_REASON_TCP_CLOSE; + /* Lookup key based on peer address and keyid. * current_key and rnext_key must not be used on tcp listen * sockets as otherwise: @@ -1001,7 +1006,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, if (th->syn && !th->ack) goto verify_hash; - if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) { + if ((1 << state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV)) { /* Make the initial syn the likely case here */ if (unlikely(req)) { sne = tcp_ao_compute_sne(0, tcp_rsk(req)->rcv_isn, @@ -1018,14 +1023,14 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, /* no way to figure out initial sisn/disn - drop */ return SKB_DROP_REASON_TCP_FLAGS; } - } else if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { + } else if ((1 << state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { disn = info->lisn; if (th->syn || th->rst) sisn = th->seq; else sisn = info->risn; } else { - WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", sk->sk_state); + WARN_ONCE(1, "TCP-AO: Unexpected sk_state %d", state); return SKB_DROP_REASON_TCP_AOFAILURE; } verify_hash: @@ -1068,6 +1073,7 @@ void tcp_ao_connect_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_ao_info *ao_info; + struct hlist_node *next; union tcp_ao_addr *addr; struct tcp_ao_key *key; int family, l3index; @@ -1090,7 +1096,7 @@ void tcp_ao_connect_init(struct sock *sk) l3index = l3mdev_master_ifindex_by_index(sock_net(sk), sk->sk_bound_dev_if); - hlist_for_each_entry_rcu(key, &ao_info->head, node) { + hlist_for_each_entry_safe(key, next, &ao_info->head, node) { if (!tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, family, -1, -1)) continue; @@ -1962,8 +1968,10 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, first = true; } - if (cmd.ao_required && tcp_ao_required_verify(sk)) - return -EKEYREJECTED; + if (cmd.ao_required && tcp_ao_required_verify(sk)) { + err = -EKEYREJECTED; + goto out; + } /* For sockets in TCP_CLOSED it's possible set keys that aren't * matching the future peer (address/port/VRF/etc), diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index bb23bb5b387a0..8ad62713b0ba2 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -58,7 +58,18 @@ struct dctcp { }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ -module_param(dctcp_shift_g, uint, 0644); + +static int dctcp_shift_g_set(const char *val, const struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, 0, 10); +} + +static const struct kernel_param_ops dctcp_shift_g_ops = { + .set = dctcp_shift_g_set, + .get = param_get_uint, +}; + +module_param_cb(dctcp_shift_g, &dctcp_shift_g_ops, &dctcp_shift_g, 0644); MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha"); static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index df7b13f0e5e0d..555c8064f52a3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6289,6 +6289,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, skb_rbtree_walk_from(data) tcp_mark_skb_lost(sk, data); tcp_xmit_retransmit_queue(sk); + tp->retrans_stamp = 0; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; @@ -6752,6 +6753,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); + if (sk->sk_shutdown & SEND_SHUTDOWN) + tcp_shutdown(sk, SEND_SHUTDOWN); break; case TCP_FIN_WAIT1: { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0c50c5a32b84a..abd47159d7e4d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -154,6 +154,12 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && time_after32(ktime_get_seconds(), tcptw->tw_ts_recent_stamp)))) { + /* inet_twsk_hashdance() sets sk_refcnt after putting twsk + * and releasing the bucket lock. + */ + if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) + return 0; + /* In case of repair and re-using TIME-WAIT sockets we still * want to be sure that it is safe as above but honor the * sequence numbers and time stamps set as part of the repair @@ -174,7 +180,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } - sock_hold(sktw); + return 1; } @@ -1994,7 +2000,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { - u32 limit, tail_gso_size, tail_gso_segs; + u32 tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -2003,6 +2009,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, bool fragstolen; u32 gso_segs; u32 gso_size; + u64 limit; int delta; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), @@ -2100,7 +2107,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, __skb_push(skb, hdrlen); no_coalesce: - limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1); + /* sk->sk_backlog.len is reset only at the end of __release_sock(). + * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach + * sk_rcvbuf in normal conditions. + */ + limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1; + + limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1; /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. @@ -2108,6 +2121,8 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, */ limit += 64 * 1024; + limit = min_t(u64, limit, UINT_MAX); + if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); *reason = SKB_DROP_REASON_SOCKET_BACKLOG; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c2a925538542b..e0883ba709b0b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -619,6 +619,7 @@ static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = [TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, }, [TCP_METRICS_ATTR_ADDR_IPV6] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr), }, + [TCP_METRICS_ATTR_SADDR_IPV4] = { .type = NLA_U32, }, /* Following attributes are not received for GET/DEL, * we keep them for reference */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 9e85f2a0bddd4..0ecc7311dc6ce 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -398,10 +398,6 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family) /* Even if tw_refcount == 1, we must clean up kernel reqsk */ inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family); } else if (!purged_once) { - /* The last refcount is decremented in tcp_sk_exit_batch() */ - if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1) - continue; - inet_twsk_purge(&tcp_hashinfo, family); purged_once = true; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e3167ad965676..02caeb7bcf634 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3563,7 +3563,9 @@ void tcp_send_fin(struct sock *sk) return; } } else { - skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | + __GFP_NOWARN)); if (unlikely(!skb)) return; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index d1ad20ce1c8c7..f96f68cf7961c 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -483,8 +483,12 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, { const struct tcp_sock *tp = tcp_sk(sk); const int timeout = TCP_RTO_MAX * 2; - u32 rcv_delta; + s32 rcv_delta; + /* Note: timer interrupt might have been delayed by at least one jiffy, + * and tp->rcv_tstamp might very well have been written recently. + * rcv_delta can thus be negative. + */ rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e474b201900f9..b2e1bfa0f625a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -429,15 +429,21 @@ static struct sock *udp4_lib_lookup2(struct net *net, { struct sock *sk, *result; int score, badness; + bool need_rescore; result = NULL; badness = 0; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - score = compute_score(sk, net, saddr, sport, - daddr, hnum, dif, sdif); + need_rescore = false; +rescore: + score = compute_score(need_rescore ? result : sk, net, saddr, + sport, daddr, hnum, dif, sdif); if (score > badness) { badness = score; + if (need_rescore) + continue; + if (sk->sk_state == TCP_ESTABLISHED) { result = sk; continue; @@ -458,9 +464,14 @@ static struct sock *udp4_lib_lookup2(struct net *net, if (IS_ERR(result)) continue; - badness = compute_score(result, net, saddr, sport, - daddr, hnum, dif, sdif); - + /* compute_score is too long of a function to be + * inlined, and calling it again here yields + * measureable overhead for some + * workloads. Work around it by jumping + * backwards to rescore 'result'. + */ + need_rescore = true; + goto rescore; } } return result; @@ -534,7 +545,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct net *net = dev_net(skb->dev); int iif, sdif; @@ -584,6 +596,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); @@ -1118,16 +1137,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); - if (err > 0) + if (err > 0) { err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); + connected = 0; + } if (unlikely(err < 0)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; - connected = 0; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; @@ -1200,7 +1220,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } if (connected) - rt = (struct rtable *)sk_dst_check(sk, 0); + rt = dst_rtable(sk_dst_check(sk, 0)); if (!rt) { struct net *net = sock_net(sk); @@ -2792,11 +2812,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case UDP_CORK: val = udp_test_bit(CORK, sk); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6c95d28d0c4a7..e5971890d637d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -449,8 +449,9 @@ static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) NAPI_GRO_CB(p)->count++; p->data_len += skb->len; - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; p->truesize += skb->truesize; p->len += skb->len; @@ -470,6 +471,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *p; unsigned int ulen; int ret = 0; + int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { @@ -503,13 +505,22 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return p; } + flush = NAPI_GRO_CB(p)->flush; + + if (NAPI_GRO_CB(p)->flush_id != 1 || + NAPI_GRO_CB(p)->count != 1 || + !NAPI_GRO_CB(p)->is_atomic) + flush |= NAPI_GRO_CB(p)->flush_id; + else + NAPI_GRO_CB(p)->is_atomic = false; + /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ - if (ulen > ntohs(uh2->len)) { + if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { @@ -551,11 +562,19 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - /* we can do L4 aggregation only if the packet can't land in a tunnel - * otherwise we could corrupt the inner stream + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { + /* If the packet was locally encapsulated in a UDP tunnel that + * wasn't detected above, do not GRO. + */ + if (skb->encapsulation) + goto out; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; @@ -709,7 +728,8 @@ EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ @@ -719,13 +739,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index c54676998eb60..801404f7d6574 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -63,7 +63,11 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) ip_send_check(iph); if (xo && (xo->flags & XFRM_GRO)) { - skb_mac_header_rebuild(skb); + /* The full l2 header needs to be preserved so that re-injecting the packet at l2 + * works correctly in the presence of vlan tags. + */ + skb_mac_header_rebuild_full(skb, xo->orig_mac_len); + skb_reset_network_header(skb); skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c33bca2c38415..1853a8415d9f1 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -69,7 +69,7 @@ static int xfrm4_get_saddr(struct net *net, int oif, static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { - struct rtable *rt = (struct rtable *)xdst->route; + struct rtable *rt = dst_rtable(xdst->route); const struct flowi4 *fl4 = &fl->u.ip4; xdst->u.rt.rt_iif = fl4->flowi4_iif; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 055230b669cf2..c4e2f9d35e687 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2061,9 +2061,10 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { - result = ifp; - in6_ifa_hold(ifp); - break; + if (in6_ifa_hold_safe(ifp)) { + result = ifp; + break; + } } } } @@ -4163,7 +4164,7 @@ static void addrconf_dad_work(struct work_struct *w) if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && ipv6_addr_equal(&ifp->addr, &addr)) { /* DAD failed for link-local based on MAC */ - idev->cnf.disable_ipv6 = 1; + WRITE_ONCE(idev->cnf.disable_ipv6, 1); pr_info("%s: IPv6 being disabled!\n", ifp->idev->dev->name); @@ -6014,7 +6015,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || nla_put_u8(skb, IFLA_OPERSTATE, - netif_running(dev) ? dev->operstate : IF_OPER_DOWN)) + netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN)) goto nla_put_failure; protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO); if (!protoinfo) @@ -6324,7 +6325,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf) idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); - idev->cnf.disable_ipv6 = newf; + + WRITE_ONCE(idev->cnf.disable_ipv6, newf); if (changed) dev_disable_change(idev); } @@ -6341,7 +6343,7 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) net = (struct net *)table->extra2; old = *p; - *p = newf; + WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_dflt->disable_ipv6) { rtnl_unlock(); @@ -6349,7 +6351,7 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) } if (p == &net->ipv6.devconf_all->disable_ipv6) { - net->ipv6.devconf_dflt->disable_ipv6 = newf; + WRITE_ONCE(net->ipv6.devconf_dflt->disable_ipv6, newf); addrconf_disable_change(net, newf); } else if ((!newf) ^ (!old)) dev_disable_change((struct inet6_dev *)table->extra1); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 6e6efe026cdcc..7371886d4f9f4 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -112,7 +112,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, __alignof__(struct scatterlist)); } -static void esp_ssg_unref(struct xfrm_state *x, void *tmp) +static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; @@ -131,7 +131,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - put_page(sg_page(sg)); + skb_page_unref(skb, sg_page(sg), false); } #ifdef CONFIG_INET6_ESPINTCP @@ -294,7 +294,7 @@ static void esp_output_done(void *data, int err) } tmp = ESP_SKB_CB(skb)->tmp; - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); kfree(tmp); esp_output_encap_csum(skb); @@ -677,7 +677,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info } if (sg != dsg) - esp_ssg_unref(x, tmp); + esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 7523c4baef35e..9e254de7462fb 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -233,8 +233,12 @@ static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp, rt = pol_lookup_func(lookup, net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { + struct inet6_dev *idev = ip6_dst_idev(&rt->dst); + + if (!idev) + goto again; err = fib6_rule_saddr(net, rule, flags, flp6, - ip6_dst_idev(&rt->dst)->dev); + idev->dev); if (err == -EAGAIN) goto again; @@ -449,6 +453,11 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) + nla_total_size(16); /* src */ } +static void fib6_rule_flush_cache(struct fib_rules_ops *ops) +{ + rt_genid_bump_ipv6(ops->fro_net); +} + static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), @@ -461,6 +470,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, + .flush_cache = fib6_rule_flush_cache, .nlgroup = RTNLGRP_IPV6_RULE, .owner = THIS_MODULE, .fro_net = &init_net, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 1635da07285f2..d285c1f6f1a61 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -212,7 +212,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) { res = true; } else { - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt = dst_rt6_info(dst); int tmo = net->ipv6.sysctl.icmpv6_time; struct inet_peer *peer; @@ -241,7 +241,7 @@ static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type, dst = ip6_route_output(net, sk, fl6); if (!dst->error) { - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt = dst_rt6_info(dst); struct in6_addr prefsrc; rt6_get_prefsrc(rt, &prefsrc); @@ -616,7 +616,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), - &ipc6, &fl6, (struct rt6_info *)dst, + &ipc6, &fl6, dst_rt6_info(dst), MSG_DONTWAIT)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); @@ -803,7 +803,7 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, - (struct rt6_info *)dst, MSG_DONTWAIT)) { + dst_rt6_info(dst), MSG_DONTWAIT)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 8c1ce78956bae..0601bad798221 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -38,7 +38,7 @@ static inline struct ila_params *ila_params_lwtunnel( static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); - struct rt6_info *rt = (struct rt6_info *)orig_dst; + struct rt6_info *rt = dst_rt6_info(orig_dst); struct ila_lwt *ilwt = ila_lwt_lwtunnel(orig_dst->lwtstate); struct dst_entry *dst; int err = -EINVAL; @@ -70,7 +70,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = orig_dst->dev->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; - fl6.daddr = *rt6_nexthop((struct rt6_info *)orig_dst, + fl6.daddr = *rt6_nexthop(dst_rt6_info(orig_dst), &ip6h->daddr); dst = ip6_route_output(net, NULL, &fl6); diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index 7563f8c6aa87c..bf7120ecea1eb 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -351,9 +351,9 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop; if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) { - preempt_disable(); + local_bh_disable(); dst = dst_cache_get(&ilwt->cache); - preempt_enable(); + local_bh_enable(); if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -373,9 +373,9 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop; } - preempt_disable(); + local_bh_disable(); dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr); - preempt_enable(); + local_bh_enable(); } skb_dst_drop(skb); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 4fc2cae0d116c..4356806b52bd5 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -645,19 +645,19 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (!w) { /* New dump: * - * 1. hook callback destructor. - */ - cb->args[3] = (long)cb->done; - cb->done = fib6_dump_done; - - /* - * 2. allocate and initialize walker. + * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_dump_node; cb->args[2] = (long)w; + + /* 2. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + } arg.skb = skb; @@ -961,6 +961,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, if (!fib6_nh->rt6i_pcpu) return; + rcu_read_lock(); /* release the reference to this fib entry from * all of its cached pcpu routes */ @@ -969,7 +970,9 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, struct rt6_info *pcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); - pcpu_rt = *ppcpu_rt; + + /* Paired with xchg() in rt6_get_pcpu_route() */ + pcpu_rt = READ_ONCE(*ppcpu_rt); /* only dropping the 'from' reference if the cached route * is using 'match'. The cached pcpu_rt->from only changes @@ -983,6 +986,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, fib6_info_release(from); } } + rcu_read_unlock(); } struct fib6_nh_pcpu_arg { @@ -1375,7 +1379,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; - struct fib6_node *fn, *pn = NULL; + struct fib6_node *fn; +#ifdef CONFIG_IPV6_SUBTREES + struct fib6_node *pn = NULL; +#endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; @@ -1399,9 +1406,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, goto out; } +#ifdef CONFIG_IPV6_SUBTREES pn = fn; -#ifdef CONFIG_IPV6_SUBTREES if (rt->fib6_src.plen) { struct fib6_node *sn; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 070d87abf7c02..289b83347d9d5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -528,6 +528,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, struct ip6_tnl *tunnel; u8 ver; + if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) + return PACKET_REJECT; + ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; @@ -1511,6 +1514,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) ip6gre_tnl_init_features(dev); netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; cleanup_dst_cache_init: @@ -1903,6 +1907,7 @@ static int ip6erspan_tap_init(struct net_device *dev) ip6erspan_tnl_link_config(tunnel, 1); netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; cleanup_dst_cache_init: diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index b8378814532ce..1ba97933c74fb 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -168,9 +168,9 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, SKB_DR_SET(reason, NOT_SPECIFIED); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || - !idev || unlikely(idev->cnf.disable_ipv6)) { + !idev || unlikely(READ_ONCE(idev->cnf.disable_ipv6))) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); - if (idev && unlikely(idev->cnf.disable_ipv6)) + if (idev && unlikely(READ_ONCE(idev->cnf.disable_ipv6))) SKB_DR_SET(reason, IPV6DISABLED); goto drop; } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index cca64c7809bee..19ae2d4cd2021 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -237,6 +237,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, goto out; skb_set_network_header(skb, off); + NAPI_GRO_CB(skb)->inner_network_offset = off; flush += ntohs(iph->payload_len) != skb->len - hlen; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 31b86fe661aa6..9e8f56177c841 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -120,7 +120,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); rcu_read_lock(); - nexthop = rt6_nexthop((struct rt6_info *)dst, daddr); + nexthop = rt6_nexthop(dst_rt6_info(dst), daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); if (unlikely(IS_ERR_OR_NULL(neigh))) { @@ -234,7 +234,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - if (unlikely(idev->cnf.disable_ipv6)) { + if (unlikely(!idev || READ_ONCE(idev->cnf.disable_ipv6))) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); return 0; @@ -501,6 +501,9 @@ int ip6_forward(struct sk_buff *skb) u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); + if (unlikely(!idev)) + idev = __in6_dev_get_safely(skb->dev); + if (net->ipv6.devconf_all->forwarding == 0) goto error; @@ -599,7 +602,7 @@ int ip6_forward(struct sk_buff *skb) * send a redirect. */ - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) target = &rt->rt6i_gateway; else @@ -856,7 +859,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *frag; - struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; bool mono_delivery_time = skb->mono_delivery_time; @@ -1063,7 +1066,7 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, return NULL; } - rt = (struct rt6_info *)dst; + rt = dst_rt6_info(dst); /* Yes, checking route validity in not connected * case is not very simple. Take into account, * that we do not support routing by source, TOS, @@ -1118,7 +1121,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct rt6_info *rt; *dst = ip6_route_output(net, sk, fl6); - rt = (*dst)->error ? NULL : (struct rt6_info *)*dst; + rt = (*dst)->error ? NULL : dst_rt6_info(*dst); rcu_read_lock(); from = rt ? rcu_dereference(rt->from) : NULL; @@ -1159,7 +1162,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * dst entry and replace it instead with the * dst entry of the nexthop router */ - rt = (struct rt6_info *) *dst; + rt = dst_rt6_info(*dst); rcu_read_lock(); n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); @@ -1423,7 +1426,7 @@ static int __ip6_append_data(struct sock *sk, int offset = 0; bool zc = false; u32 tskey = 0; - struct rt6_info *rt = (struct rt6_info *)cork->dst; + struct rt6_info *rt = dst_rt6_info(cork->dst); bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; @@ -1877,7 +1880,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = v6_cork->opt; - struct rt6_info *rt = (struct rt6_info *)cork->base.dst; + struct rt6_info *rt = dst_rt6_info(cork->base.dst); struct flowi6 *fl6 = &cork->fl.u.ip6; unsigned char proto = fl6->flowi6_proto; @@ -1933,7 +1936,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, u8 icmp6_type; if (sk->sk_socket->type == SOCK_RAW && - !inet_test_bit(HDRINCL, sk)) + !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; @@ -1949,7 +1952,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, int ip6_send_skb(struct sk_buff *skb) { struct net *net = sock_net(skb->sk); - struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; err = ip6_local_out(net, skb->sk, skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9bbabf750a21e..70478027a7af7 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1898,6 +1898,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev) dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; destroy_dst: diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index e550240c85e1c..1163ca6ea4af1 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -935,6 +935,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev) if (!dev->tstats) return -ENOMEM; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9782c180fee64..5f841b5c1c59e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2276,7 +2276,7 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int err; struct mr_table *mrt; struct mfc6_cache *cache; - struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index bc6e0a0bad3c1..76ee1615ff2a0 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2719,7 +2719,6 @@ void ipv6_mc_down(struct inet6_dev *idev) /* Should stop work after group drop. or we will * start work again in mld_ifc_event() */ - synchronize_net(); mld_query_stop_work(idev); mld_report_stop_work(idev); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index a19999b30bc07..acf33fb83942a 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1708,7 +1708,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) if (IS_ERR(dst)) return; - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) { ND_PRINTK(2, warn, diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index fd9f049d6d41e..d10aeaae7907b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -379,6 +379,17 @@ ip6t_do_table(void *priv, struct sk_buff *skb, else return verdict; } +static bool next_offset_ok(const struct xt_table_info *t, unsigned int newpos) +{ + if (newpos > t->size - sizeof(struct ip6t_entry)) + return false; + + if (newpos % __alignof__(struct ip6t_entry) != 0) + return false; + + return true; +} + /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int @@ -434,6 +445,8 @@ mark_source_chains(const struct xt_table_info *newinfo, /* Move along one */ size = e->next_offset; + if (!next_offset_ok(newinfo, pos + size)) + return 0; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; @@ -455,6 +468,10 @@ mark_source_chains(const struct xt_table_info *newinfo, if (newpos >= newinfo->size) return 0; } + + if (!next_offset_ok(newinfo, newpos)) + return 0; + e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; @@ -1125,6 +1142,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1133,6 +1152,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1501,6 +1522,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1509,6 +1532,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b2dd48911c8d6..efbec7ee27d0a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -294,6 +294,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -469,7 +470,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); if (fq == NULL) { diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index ef2059c889554..88b3fcacd4f94 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -154,7 +154,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false); if (IS_ERR(dst)) return PTR_ERR(dst); - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 03dbb874c363b..b97a5eb0b0bc8 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -592,7 +592,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct ipv6hdr *iph; struct sk_buff *skb; int err; - struct rt6_info *rt = (struct rt6_info *)*dstp; + struct rt6_info *rt = dst_rt6_info(*dstp); int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; @@ -911,7 +911,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, - len, 0, &ipc6, &fl6, (struct rt6_info *)dst, + len, 0, &ipc6, &fl6, dst_rt6_info(dst), msg->msg_flags); if (err) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5ebc47da1000c..2af98edef87ee 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -369,7 +369,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) * the source of the fragment, with the Pointer field set to zero. */ nexthdr = hdr->nexthdr; - if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) { + if (ipv6frag_thdr_truncated(skb, skb_network_offset(skb) + sizeof(struct ipv6hdr), &nexthdr)) { __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ef815ba583a8f..9f16625ccd497 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -87,7 +87,8 @@ struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); -static struct dst_entry *ip6_negative_advice(struct dst_entry *); +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); @@ -226,7 +227,7 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { - const struct rt6_info *rt = container_of(dst, struct rt6_info, dst); + const struct rt6_info *rt = dst_rt6_info(dst); return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), dst->dev, skb, daddr); @@ -234,8 +235,8 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) { + const struct rt6_info *rt = dst_rt6_info(dst); struct net_device *dev = dst->dev; - struct rt6_info *rt = (struct rt6_info *)dst; daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr); if (!daddr) @@ -354,7 +355,7 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt = dst_rt6_info(dst); struct fib6_info *from; struct inet6_dev *idev; @@ -373,7 +374,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { - struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_info *rt = dst_rt6_info(dst); struct inet6_dev *idev = rt->rt6i_idev; if (idev && idev->dev != blackhole_netdev) { @@ -637,6 +638,8 @@ static void rt6_probe(struct fib6_nh *fib6_nh) rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); + if (!idev) + goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) @@ -1278,7 +1281,7 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) - return (struct rt6_info *) dst; + return dst_rt6_info(dst); dst_release(dst); @@ -1398,6 +1401,7 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) struct rt6_info *prev, **p; p = this_cpu_ptr(res->nh->rt6i_pcpu); + /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ prev = xchg(p, NULL); if (prev) { dst_dev_put(&prev->dst); @@ -2637,7 +2641,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, rcu_read_lock(); dst = ip6_route_output_flags_noref(net, sk, fl6, flags); - rt6 = (struct rt6_info *)dst; + rt6 = dst_rt6_info(dst); /* For dst cached in uncached_list, refcnt is already taken. */ if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) { dst = &net->ipv6.ip6_null_entry->dst; @@ -2651,7 +2655,7 @@ EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { - struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig; + struct rt6_info *rt, *ort = dst_rt6_info(dst_orig); struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; @@ -2734,7 +2738,7 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, struct fib6_info *from; struct rt6_info *rt; - rt = container_of(dst, struct rt6_info, dst); + rt = dst_rt6_info(dst); if (rt->sernum) return rt6_is_valid(rt) ? dst : NULL; @@ -2760,24 +2764,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); -static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst) { - struct rt6_info *rt = (struct rt6_info *) dst; + struct rt6_info *rt = dst_rt6_info(dst); - if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - rcu_read_lock(); - if (rt6_check_expired(rt)) { - rt6_remove_exception_rt(rt); - dst = NULL; - } - rcu_read_unlock(); - } else { - dst_release(dst); - dst = NULL; + if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); + if (rt6_check_expired(rt)) { + /* counteract the dst_release() in sk_dst_reset() */ + dst_hold(dst); + sk_dst_reset(sk); + + rt6_remove_exception_rt(rt); } + rcu_read_unlock(); + return; } - return dst; + sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) @@ -2786,7 +2790,7 @@ static void ip6_link_failure(struct sk_buff *skb) icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); - rt = (struct rt6_info *) skb_dst(skb); + rt = dst_rt6_info(skb_dst(skb)); if (rt) { rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { @@ -2842,7 +2846,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, bool confirm_neigh) { const struct in6_addr *daddr, *saddr; - struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6_info *rt6 = dst_rt6_info(dst); /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. @@ -3591,7 +3595,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, if (!dev) goto out; - if (idev->cnf.disable_ipv6) { + if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; @@ -4165,7 +4169,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu } } - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_REJECT) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); return; @@ -4434,7 +4438,7 @@ static void rtmsg_to_fib6_config(struct net *net, .fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? : RT6_TABLE_MAIN, .fc_ifindex = rtmsg->rtmsg_ifindex, - .fc_metric = rtmsg->rtmsg_metric ? : IP6_RT_PRIO_USER, + .fc_metric = rtmsg->rtmsg_metric, .fc_expires = rtmsg->rtmsg_info, .fc_dst_len = rtmsg->rtmsg_dst_len, .fc_src_len = rtmsg->rtmsg_src_len, @@ -4464,6 +4468,9 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) rtnl_lock(); switch (cmd) { case SIOCADDRT: + /* Only do the default setting of fc_metric in route adding */ + if (cfg.fc_metric == 0) + cfg.fc_metric = IP6_RT_PRIO_USER; err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: @@ -5597,7 +5604,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6_info *rt6 = dst_rt6_info(dst); struct rt6key *rt6_dst, *rt6_src; u32 *pmetrics, table, rt6_flags; unsigned char nh_flags = 0; @@ -6100,7 +6107,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, } - rt = container_of(dst, struct rt6_info, dst); + rt = dst_rt6_info(dst); if (rt->dst.error) { err = rt->dst.error; ip6_rt_put(rt); @@ -6327,12 +6334,12 @@ static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, if (!write) return -EINVAL; - net = (struct net *)ctl->extra1; - delay = net->ipv6.sysctl.flush_delay; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (ret) return ret; + net = (struct net *)ctl->extra1; + delay = net->ipv6.sysctl.flush_delay; fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 35508abd76f43..a31521e270f78 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -551,6 +551,8 @@ int __init seg6_init(void) #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL out_unregister_genl: +#endif +#if IS_ENABLED(CONFIG_IPV6_SEG6_LWTUNNEL) || IS_ENABLED(CONFIG_IPV6_SEG6_HMAC) genl_unregister_family(&seg6_genl_family); #endif out_unregister_pernet: @@ -564,8 +566,9 @@ void seg6_exit(void) seg6_hmac_exit(); #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL + seg6_local_exit(); seg6_iptunnel_exit(); #endif - unregister_pernet_subsys(&ip6_segments_ops); genl_unregister_family(&seg6_genl_family); + unregister_pernet_subsys(&ip6_segments_ops); } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index d43c50a7310d6..3c3800223e0e0 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -354,6 +354,7 @@ static int seg6_hmac_init_algo(void) struct crypto_shash *tfm; struct shash_desc *shash; int i, alg_count, cpu; + int ret = -ENOMEM; alg_count = ARRAY_SIZE(hmac_algos); @@ -364,12 +365,14 @@ static int seg6_hmac_init_algo(void) algo = &hmac_algos[i]; algo->tfms = alloc_percpu(struct crypto_shash *); if (!algo->tfms) - return -ENOMEM; + goto error_out; for_each_possible_cpu(cpu) { tfm = crypto_alloc_shash(algo->name, 0, 0); - if (IS_ERR(tfm)) - return PTR_ERR(tfm); + if (IS_ERR(tfm)) { + ret = PTR_ERR(tfm); + goto error_out; + } p_tfm = per_cpu_ptr(algo->tfms, cpu); *p_tfm = tfm; } @@ -381,18 +384,22 @@ static int seg6_hmac_init_algo(void) algo->shashs = alloc_percpu(struct shash_desc *); if (!algo->shashs) - return -ENOMEM; + goto error_out; for_each_possible_cpu(cpu) { shash = kzalloc_node(shsize, GFP_KERNEL, cpu_to_node(cpu)); if (!shash) - return -ENOMEM; + goto error_out; *per_cpu_ptr(algo->shashs, cpu) = shash; } } return 0; + +error_out: + seg6_hmac_exit(); + return ret; } int __init seg6_hmac_init(void) @@ -410,22 +417,29 @@ int __net_init seg6_hmac_net_init(struct net *net) void seg6_hmac_exit(void) { struct seg6_hmac_algo *algo = NULL; + struct crypto_shash *tfm; + struct shash_desc *shash; int i, alg_count, cpu; alg_count = ARRAY_SIZE(hmac_algos); for (i = 0; i < alg_count; i++) { algo = &hmac_algos[i]; - for_each_possible_cpu(cpu) { - struct crypto_shash *tfm; - struct shash_desc *shash; - shash = *per_cpu_ptr(algo->shashs, cpu); - kfree(shash); - tfm = *per_cpu_ptr(algo->tfms, cpu); - crypto_free_shash(tfm); + if (algo->shashs) { + for_each_possible_cpu(cpu) { + shash = *per_cpu_ptr(algo->shashs, cpu); + kfree(shash); + } + free_percpu(algo->shashs); + } + + if (algo->tfms) { + for_each_possible_cpu(cpu) { + tfm = *per_cpu_ptr(algo->tfms, cpu); + crypto_free_shash(tfm); + } + free_percpu(algo->tfms); } - free_percpu(algo->tfms); - free_percpu(algo->shashs); } } EXPORT_SYMBOL(seg6_hmac_exit); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 03b877ff45588..098632adc9b5a 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -459,34 +459,30 @@ static int seg6_input_core(struct net *net, struct sock *sk, int err; err = seg6_do_srh(skb); - if (unlikely(err)) { - kfree_skb(skb); - return err; - } + if (unlikely(err)) + goto drop; slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); - preempt_disable(); + local_bh_disable(); dst = dst_cache_get(&slwt->cache); - preempt_enable(); if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); if (!dst->error) { - preempt_disable(); dst_cache_set_ip6(&slwt->cache, dst, &ipv6_hdr(skb)->saddr); - preempt_enable(); } } else { skb_dst_drop(skb); skb_dst_set(skb, dst); } + local_bh_enable(); err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) - return err; + goto drop; if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, @@ -494,6 +490,9 @@ static int seg6_input_core(struct net *net, struct sock *sk, skb_dst(skb)->dev, seg6_input_finish); return seg6_input_finish(dev_net(skb->dev), NULL, skb); +drop: + kfree_skb(skb); + return err; } static int seg6_input_nf(struct sk_buff *skb) @@ -535,9 +534,9 @@ static int seg6_output_core(struct net *net, struct sock *sk, slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); - preempt_disable(); + local_bh_disable(); dst = dst_cache_get(&slwt->cache); - preempt_enable(); + local_bh_enable(); if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -557,9 +556,9 @@ static int seg6_output_core(struct net *net, struct sock *sk, goto drop; } - preempt_disable(); + local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); - preempt_enable(); + local_bh_enable(); } skb_dst_drop(skb); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 24e2b4b494cb0..c434940131b1d 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -941,8 +941,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx6_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx6_finish); return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb); drop: @@ -991,8 +991,8 @@ static int input_action_end_dx4(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx4_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx4_finish); return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb); drop: diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5e9f625b76e36..fbad6e1c970e4 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1460,6 +1460,7 @@ static int ipip6_tunnel_init(struct net_device *dev) return err; } netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 57b25b1fc9d9d..100b6a83dfc97 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -94,11 +94,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { - const struct rt6_info *rt = (const struct rt6_info *)dst; - rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; - sk->sk_rx_dst_cookie = rt6_get_cookie(rt); + sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } } @@ -1439,7 +1437,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * */ newsk->sk_gso_type = SKB_GSO_TCPV6; - ip6_dst_store(newsk, dst, NULL, NULL); inet6_sk_rx_dst_set(newsk, skb); inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); @@ -1450,6 +1447,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + ip6_dst_store(newsk, dst, NULL, NULL); + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; newnp->saddr = ireq->ir_v6_loc_addr; newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3f2249b4cd5f6..9a9434c4cc893 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -171,15 +171,21 @@ static struct sock *udp6_lib_lookup2(struct net *net, { struct sock *sk, *result; int score, badness; + bool need_rescore; result = NULL; badness = -1; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - score = compute_score(sk, net, saddr, sport, - daddr, hnum, dif, sdif); + need_rescore = false; +rescore: + score = compute_score(need_rescore ? result : sk, net, saddr, + sport, daddr, hnum, dif, sdif); if (score > badness) { badness = score; + if (need_rescore) + continue; + if (sk->sk_state == TCP_ESTABLISHED) { result = sk; continue; @@ -200,8 +206,14 @@ static struct sock *udp6_lib_lookup2(struct net *net, if (IS_ERR(result)) continue; - badness = compute_score(sk, net, saddr, sport, - daddr, hnum, dif, sdif); + /* compute_score is too long of a function to be + * inlined, and calling it again here yields + * measureable overhead for some + * workloads. Work around it by jumping + * backwards to rescore 'result'. + */ + need_rescore = true; + goto rescore; } } return result; @@ -275,7 +287,8 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { - const struct ipv6hdr *iph = ipv6_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset); struct net *net = dev_net(skb->dev); int iif, sdif; @@ -450,7 +463,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); @@ -900,11 +913,8 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { - if (udp_sk_rx_dst_set(sk, dst)) { - const struct rt6_info *rt = (const struct rt6_info *)dst; - - sk->sk_rx_dst_cookie = rt6_get_cookie(rt); - } + if (udp_sk_rx_dst_set(sk, dst)) + sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and @@ -1476,9 +1486,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.opt = opt; err = udp_cmsg_send(sk, msg, &ipc6.gso_size); - if (err > 0) + if (err > 0) { err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6, &ipc6); + connected = false; + } if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1490,7 +1502,6 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; - connected = false; } if (!opt) { opt = txopt_get(np); @@ -1573,7 +1584,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, - (struct rt6_info *)dst, + dst_rt6_info(dst), msg->msg_flags, &cork); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) @@ -1600,7 +1611,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk); up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), - &ipc6, fl6, (struct rt6_info *)dst, + &ipc6, fl6, dst_rt6_info(dst), corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 6b95ba241ebe2..639a4b506f9b5 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -164,7 +164,8 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) { - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ @@ -174,13 +175,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 6e36e5047fbab..4e6dcefd635c8 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -58,7 +58,11 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) skb_postpush_rcsum(skb, skb_network_header(skb), nhlen); if (xo && (xo->flags & XFRM_GRO)) { - skb_mac_header_rebuild(skb); + /* The full l2 header needs to be preserved so that re-injecting the packet at l2 + * works correctly in the presence of vlan tags. + */ + skb_mac_header_rebuild_full(skb, xo->orig_mac_len); + skb_reset_network_header(skb); skb_reset_transport_header(skb); return 0; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 42fb6996b0777..4332d4b82b1dc 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -56,12 +56,18 @@ static int xfrm6_get_saddr(struct net *net, int oif, { struct dst_entry *dst; struct net_device *dev; + struct inet6_dev *idev; dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; - dev = ip6_dst_idev(dst)->dev; + idev = ip6_dst_idev(dst); + if (!idev) { + dst_release(dst); + return -EHOSTUNREACH; + } + dev = idev->dev; ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6); dst_release(dst); return 0; @@ -70,7 +76,7 @@ static int xfrm6_get_saddr(struct net *net, int oif, static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { - struct rt6_info *rt = (struct rt6_info *)xdst->route; + struct rt6_info *rt = dst_rt6_info(xdst->route); xdst->u.dst.dev = dev; netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 1184d40167b86..eda933c097926 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1152,10 +1152,11 @@ static int kcm_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 8d21ff25f1602..4a0fb8731eee9 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -887,22 +887,20 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) return 1; } -/* UDP encapsulation receive handler. See net/ipv4/udp.c. - * Return codes: - * 0 : success. - * <0: error - * >0: skb should be passed up to userspace as UDP. +/* UDP encapsulation receive and error receive handlers. + * See net/ipv4/udp.c for details. + * + * Note that these functions are called from inside an + * RCU-protected region, but without the socket being locked. + * + * Hence we use rcu_dereference_sk_user_data to access the + * tunnel data structure rather the usual l2tp_sk_to_tunnel + * accessor function. */ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; - /* Note that this is called from the encap_rcv hook inside an - * RCU-protected region, but without the socket being locked. - * Hence we use rcu_dereference_sk_user_data to access the - * tunnel data structure rather the usual l2tp_sk_to_tunnel - * accessor function. - */ tunnel = rcu_dereference_sk_user_data(sk); if (!tunnel) goto pass_up; @@ -919,6 +917,29 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv); +static void l2tp_udp_encap_err_recv(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) +{ + struct l2tp_tunnel *tunnel; + + tunnel = rcu_dereference_sk_user_data(sk); + if (!tunnel || tunnel->fd < 0) + return; + + sk->sk_err = err; + sk_error_report(sk); + + if (ip_hdr(skb)->version == IPVERSION) { + if (inet_test_bit(RECVERR, sk)) + return ip_icmp_error(sk, skb, err, port, info, payload); +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (inet6_test_bit(RECVERR6, sk)) + return ipv6_icmp_error(sk, skb, err, port, info, payload); +#endif + } +} + /************************************************************************ * Transmit handling ***********************************************************************/ @@ -1493,6 +1514,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, .sk_user_data = tunnel, .encap_type = UDP_ENCAP_L2TPINUDP, .encap_rcv = l2tp_udp_encap_recv, + .encap_err_rcv = l2tp_udp_encap_err_recv, .encap_destroy = l2tp_udp_encap_destroy, }; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 25ca89f804145..9dacfa91acc78 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -127,6 +127,9 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, /* checksums verified by L2TP */ skb->ip_summed = CHECKSUM_NONE; + /* drop outer flow-hash */ + skb_clear_hash(skb); + skb_dst_drop(skb); nf_reset_ct(skb); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 9a2a9ed3ba478..4b4bd83353d5d 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -459,7 +459,7 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl4 = &inet->cork.fl.u.ip4; if (connected) - rt = (struct rtable *)__sk_dst_check(sk, 0); + rt = dst_rtable(__sk_dst_check(sk, 0)); rcu_read_lock(); if (!rt) { diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 7bf14cf9ffaa9..8780ec64f3769 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -630,7 +630,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, - &fl6, (struct rt6_info *)dst, + &fl6, dst_rt6_info(dst), msg->msg_flags); if (err) ip6_flush_pending_frames(sk); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f011af6601c9c..6146e4e67bbb5 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1356,11 +1356,11 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + err = -ENOTCONN; if (!sk->sk_user_data) goto end; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 327682995c926..1d43a80064721 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1869,7 +1869,7 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, sband->band); } - ieee80211_sta_set_rx_nss(link_sta); + ieee80211_sta_init_nss(link_sta); return ret; } @@ -2164,15 +2164,14 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && - sta->sdata->u.vlan.sta) { - ieee80211_clear_fast_rx(sta); + sta->sdata->u.vlan.sta) RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); - } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; + ieee80211_check_fast_rx(sta); ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 9f5ffdc9db284..ecbb042dd0433 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -230,15 +230,21 @@ ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif, if (!he_spr_ie_elem) return; + + he_obss_pd->sr_ctrl = he_spr_ie_elem->he_sr_control; data = he_spr_ie_elem->optional; if (he_spr_ie_elem->he_sr_control & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) - data++; + he_obss_pd->non_srg_max_offset = *data++; + if (he_spr_ie_elem->he_sr_control & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) { - he_obss_pd->max_offset = *data++; he_obss_pd->min_offset = *data++; + he_obss_pd->max_offset = *data++; + memcpy(he_obss_pd->bss_color_bitmap, data, 8); + data += 8; + memcpy(he_obss_pd->partial_bssid_bitmap, data, 8); he_obss_pd->enable = true; } } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 0b2b53550bd99..399fcb66658da 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -131,7 +131,7 @@ struct ieee80211_bss { }; /** - * enum ieee80211_corrupt_data_flags - BSS data corruption flags + * enum ieee80211_bss_corrupt_data_flags - BSS data corruption flags * @IEEE80211_BSS_CORRUPT_BEACON: last beacon frame received was corrupted * @IEEE80211_BSS_CORRUPT_PROBE_RESP: last probe response received was corrupted * @@ -144,7 +144,7 @@ enum ieee80211_bss_corrupt_data_flags { }; /** - * enum ieee80211_valid_data_flags - BSS valid data flags + * enum ieee80211_bss_valid_data_flags - BSS valid data flags * @IEEE80211_BSS_VALID_WMM: WMM/UAPSD data was gathered from non-corrupt IE * @IEEE80211_BSS_VALID_RATES: Supported rates were gathered from non-corrupt IE * @IEEE80211_BSS_VALID_ERP: ERP flag was gathered from non-corrupt IE @@ -2112,7 +2112,7 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta); -void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta); +void ieee80211_sta_init_nss(struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width); enum nl80211_chan_width diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 11c4caa4748e4..2b6133bcc96ae 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -686,6 +686,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do ieee80211_del_virtual_monitor(local); ieee80211_recalc_idle(local); + ieee80211_recalc_offload(local); if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) break; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index fccbcde3359af..3d4806b7ff6c4 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -769,6 +769,9 @@ bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 ctrl_flags) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + struct ieee80211_mesh_fast_tx_key key = { + .type = MESH_FAST_TX_TYPE_LOCAL + }; struct ieee80211_mesh_fast_tx *entry; struct ieee80211s_hdr *meshhdr; u8 sa[ETH_ALEN] __aligned(2); @@ -804,7 +807,10 @@ bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata, return false; } - entry = mesh_fast_tx_get(sdata, skb->data); + ether_addr_copy(key.addr, skb->data); + if (!ether_addr_equal(skb->data + ETH_ALEN, sdata->vif.addr)) + key.type = MESH_FAST_TX_TYPE_PROXIED; + entry = mesh_fast_tx_get(sdata, &key); if (!entry) return false; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index ad8469293d712..58c619874ca6a 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -133,10 +133,39 @@ struct mesh_path { #define MESH_FAST_TX_CACHE_THRESHOLD_SIZE 384 #define MESH_FAST_TX_CACHE_TIMEOUT 8000 /* msecs */ +/** + * enum ieee80211_mesh_fast_tx_type - cached mesh fast tx entry type + * + * @MESH_FAST_TX_TYPE_LOCAL: tx from the local vif address as SA + * @MESH_FAST_TX_TYPE_PROXIED: local tx with a different SA (e.g. bridged) + * @MESH_FAST_TX_TYPE_FORWARDED: forwarded from a different mesh point + * @NUM_MESH_FAST_TX_TYPE: number of entry types + */ +enum ieee80211_mesh_fast_tx_type { + MESH_FAST_TX_TYPE_LOCAL, + MESH_FAST_TX_TYPE_PROXIED, + MESH_FAST_TX_TYPE_FORWARDED, + + /* must be last */ + NUM_MESH_FAST_TX_TYPE +}; + + +/** + * struct ieee80211_mesh_fast_tx_key - cached mesh fast tx entry key + * + * @addr: The Ethernet DA for this entry + * @type: cache entry type + */ +struct ieee80211_mesh_fast_tx_key { + u8 addr[ETH_ALEN] __aligned(2); + u16 type; +}; + /** * struct ieee80211_mesh_fast_tx - cached mesh fast tx entry * @rhash: rhashtable pointer - * @addr_key: The Ethernet DA which is the key for this entry + * @key: the lookup key for this cache entry * @fast_tx: base fast_tx data * @hdr: cached mesh and rfc1042 headers * @hdrlen: length of mesh + rfc1042 @@ -147,7 +176,7 @@ struct mesh_path { */ struct ieee80211_mesh_fast_tx { struct rhash_head rhash; - u8 addr_key[ETH_ALEN] __aligned(2); + struct ieee80211_mesh_fast_tx_key key; struct ieee80211_fast_tx fast_tx; u8 hdr[sizeof(struct ieee80211s_hdr) + sizeof(rfc1042_header)]; @@ -333,7 +362,8 @@ void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata); bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt); struct ieee80211_mesh_fast_tx * -mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, const u8 *addr); +mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mesh_fast_tx_key *key); bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 ctrl_flags); void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 735edde1bd819..c0a5c75cddcb9 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -37,8 +37,8 @@ static const struct rhashtable_params mesh_rht_params = { static const struct rhashtable_params fast_tx_rht_params = { .nelem_hint = 10, .automatic_shrinking = true, - .key_len = ETH_ALEN, - .key_offset = offsetof(struct ieee80211_mesh_fast_tx, addr_key), + .key_len = sizeof_field(struct ieee80211_mesh_fast_tx, key), + .key_offset = offsetof(struct ieee80211_mesh_fast_tx, key), .head_offset = offsetof(struct ieee80211_mesh_fast_tx, rhash), .hashfn = mesh_table_hash, }; @@ -431,20 +431,21 @@ static void mesh_fast_tx_entry_free(struct mesh_tx_cache *cache, } struct ieee80211_mesh_fast_tx * -mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, const u8 *addr) +mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mesh_fast_tx_key *key) { struct ieee80211_mesh_fast_tx *entry; struct mesh_tx_cache *cache; cache = &sdata->u.mesh.tx_cache; - entry = rhashtable_lookup(&cache->rht, addr, fast_tx_rht_params); + entry = rhashtable_lookup(&cache->rht, key, fast_tx_rht_params); if (!entry) return NULL; if (!(entry->mpath->flags & MESH_PATH_ACTIVE) || mpath_expired(entry->mpath)) { spin_lock_bh(&cache->walk_lock); - entry = rhashtable_lookup(&cache->rht, addr, fast_tx_rht_params); + entry = rhashtable_lookup(&cache->rht, key, fast_tx_rht_params); if (entry) mesh_fast_tx_entry_free(cache, entry); spin_unlock_bh(&cache->walk_lock); @@ -489,18 +490,24 @@ void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, if (!sta) return; + build.key.type = MESH_FAST_TX_TYPE_LOCAL; if ((meshhdr->flags & MESH_FLAGS_AE) == MESH_FLAGS_AE_A5_A6) { /* This is required to keep the mppath alive */ mppath = mpp_path_lookup(sdata, meshhdr->eaddr1); if (!mppath) return; build.mppath = mppath; + if (!ether_addr_equal(meshhdr->eaddr2, sdata->vif.addr)) + build.key.type = MESH_FAST_TX_TYPE_PROXIED; } else if (ieee80211_has_a4(hdr->frame_control)) { mppath = mpath; } else { return; } + if (!ether_addr_equal(hdr->addr4, sdata->vif.addr)) + build.key.type = MESH_FAST_TX_TYPE_FORWARDED; + /* rate limit, in case fast xmit can't be enabled */ if (mppath->fast_tx_check == jiffies) return; @@ -547,7 +554,7 @@ void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, } } - memcpy(build.addr_key, mppath->dst, ETH_ALEN); + memcpy(build.key.addr, mppath->dst, ETH_ALEN); build.timestamp = jiffies; build.fast_tx.band = info->band; build.fast_tx.da_offs = offsetof(struct ieee80211_hdr, addr3); @@ -600,11 +607,10 @@ void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, void mesh_fast_tx_gc(struct ieee80211_sub_if_data *sdata) { unsigned long timeout = msecs_to_jiffies(MESH_FAST_TX_CACHE_TIMEOUT); - struct mesh_tx_cache *cache; + struct mesh_tx_cache *cache = &sdata->u.mesh.tx_cache; struct ieee80211_mesh_fast_tx *entry; struct hlist_node *n; - cache = &sdata->u.mesh.tx_cache; if (atomic_read(&cache->rht.nelems) < MESH_FAST_TX_CACHE_THRESHOLD_SIZE) return; @@ -622,7 +628,6 @@ void mesh_fast_tx_flush_mpath(struct mesh_path *mpath) struct ieee80211_mesh_fast_tx *entry; struct hlist_node *n; - cache = &sdata->u.mesh.tx_cache; spin_lock_bh(&cache->walk_lock); hlist_for_each_entry_safe(entry, n, &cache->walk_head, walk_list) if (entry->mpath == mpath) @@ -637,7 +642,6 @@ void mesh_fast_tx_flush_sta(struct ieee80211_sub_if_data *sdata, struct ieee80211_mesh_fast_tx *entry; struct hlist_node *n; - cache = &sdata->u.mesh.tx_cache; spin_lock_bh(&cache->walk_lock); hlist_for_each_entry_safe(entry, n, &cache->walk_head, walk_list) if (rcu_access_pointer(entry->mpath->next_hop) == sta) @@ -649,13 +653,18 @@ void mesh_fast_tx_flush_addr(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct mesh_tx_cache *cache = &sdata->u.mesh.tx_cache; + struct ieee80211_mesh_fast_tx_key key = {}; struct ieee80211_mesh_fast_tx *entry; + int i; - cache = &sdata->u.mesh.tx_cache; + ether_addr_copy(key.addr, addr); spin_lock_bh(&cache->walk_lock); - entry = rhashtable_lookup_fast(&cache->rht, addr, fast_tx_rht_params); - if (entry) - mesh_fast_tx_entry_free(cache, entry); + for (i = 0; i < NUM_MESH_FAST_TX_TYPE; i++) { + key.type = i; + entry = rhashtable_lookup_fast(&cache->rht, &key, fast_tx_rht_params); + if (entry) + mesh_fast_tx_entry_free(cache, entry); + } spin_unlock_bh(&cache->walk_lock); } @@ -1008,10 +1017,23 @@ void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, */ void mesh_path_flush_pending(struct mesh_path *mpath) { + struct ieee80211_sub_if_data *sdata = mpath->sdata; + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; + struct mesh_preq_queue *preq, *tmp; struct sk_buff *skb; while ((skb = skb_dequeue(&mpath->frame_queue)) != NULL) mesh_path_discard_frame(mpath->sdata, skb); + + spin_lock_bh(&ifmsh->mesh_preq_queue_lock); + list_for_each_entry_safe(preq, tmp, &ifmsh->preq_queue.list, list) { + if (ether_addr_equal(mpath->dst, preq->dst)) { + list_del(&preq->list); + kfree(preq); + --ifmsh->preq_queue_len; + } + } + spin_unlock_bh(&ifmsh->mesh_preq_queue_lock); } /** diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2022a26eb8811..df26672fb3383 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5848,7 +5848,7 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, */ if (control & IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT) - link_removal_timeout[link_id] = le16_to_cpu(*(__le16 *)pos); + link_removal_timeout[link_id] = get_unaligned_le16(pos); } removed_links &= sdata->vif.valid_links; @@ -5873,8 +5873,11 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, continue; } - link_delay = link_conf->beacon_int * - link_removal_timeout[link_id]; + if (link_removal_timeout[link_id] < 1) + link_delay = 0; + else + link_delay = link_conf->beacon_int * + (link_removal_timeout[link_id] - 1); if (!delay) delay = link_delay; @@ -6181,7 +6184,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, link->u.mgd.dtim_period = elems->dtim_period; link->u.mgd.have_beacon = true; ifmgd->assoc_data->need_beacon = false; - if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY)) { + if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY) && + !ieee80211_is_s1g_beacon(hdr->frame_control)) { link->conf->sync_tsf = le64_to_cpu(mgmt->u.beacon.timestamp); link->conf->sync_device_ts = @@ -7291,7 +7295,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, sdata_info(sdata, "failed to insert STA entry for the AP (error %d)\n", err); - goto out_err; + goto out_release_chan; } } else WARN_ON_ONCE(!ether_addr_equal(link->u.mgd.bssid, cbss->bssid)); @@ -7302,8 +7306,9 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, return 0; +out_release_chan: + ieee80211_link_release_channel(link); out_err: - ieee80211_link_release_channel(&sdata->deflink); ieee80211_vif_set_links(sdata, 0, 0); return err; } @@ -7523,10 +7528,10 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, if (err) goto err_clear; - if (req->link_id > 0) + if (req->link_id >= 0) link = sdata_dereference(sdata->link[req->link_id], sdata); else - link = sdata_dereference(sdata->link[0], sdata); + link = &sdata->deflink; if (WARN_ON(!link)) { err = -ENOLINK; diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 9d33fd2377c88..3cf252418bd38 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -37,7 +37,7 @@ void rate_control_rate_init(struct sta_info *sta) struct ieee80211_supported_band *sband; struct ieee80211_chanctx_conf *chanctx_conf; - ieee80211_sta_set_rx_nss(&sta->deflink); + ieee80211_sta_init_nss(&sta->deflink); if (!ref) return; @@ -877,6 +877,7 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, struct ieee80211_sub_if_data *sdata; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_supported_band *sband; + u32 mask = ~0; rate_control_fill_sta_table(sta, info, dest, max_rates); @@ -889,9 +890,12 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, if (ieee80211_is_tx_data(skb)) rate_control_apply_mask(sdata, sta, sband, dest, max_rates); + if (!(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX)) + mask = sdata->rc_rateidx_mask[info->band]; + if (dest[0].idx < 0) __rate_control_send_low(&sdata->local->hw, sband, sta, info, - sdata->rc_rateidx_mask[info->band]); + mask); if (sta) rate_fixup_ratelist(vif, sband, info, dest, max_rates); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0bf72928ccfca..541b0f53c6c35 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2746,7 +2746,10 @@ ieee80211_rx_mesh_fast_forward(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int hdrlen) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - struct ieee80211_mesh_fast_tx *entry = NULL; + struct ieee80211_mesh_fast_tx_key key = { + .type = MESH_FAST_TX_TYPE_FORWARDED + }; + struct ieee80211_mesh_fast_tx *entry; struct ieee80211s_hdr *mesh_hdr; struct tid_ampdu_tx *tid_tx; struct sta_info *sta; @@ -2755,9 +2758,13 @@ ieee80211_rx_mesh_fast_forward(struct ieee80211_sub_if_data *sdata, mesh_hdr = (struct ieee80211s_hdr *)(skb->data + sizeof(eth)); if ((mesh_hdr->flags & MESH_FLAGS_AE) == MESH_FLAGS_AE_A5_A6) - entry = mesh_fast_tx_get(sdata, mesh_hdr->eaddr1); + ether_addr_copy(key.addr, mesh_hdr->eaddr1); else if (!(mesh_hdr->flags & MESH_FLAGS_AE)) - entry = mesh_fast_tx_get(sdata, skb->data); + ether_addr_copy(key.addr, skb->data); + else + return false; + + entry = mesh_fast_tx_get(sdata, &key); if (!entry) return false; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index f9d5842601fa9..d613a9e3ae1fd 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -638,6 +638,7 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, cpu_to_le16(IEEE80211_SN_TO_SEQ(sn)); } IEEE80211_SKB_CB(skb)->flags |= tx_flags; + IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_SCAN_TX; ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band); } } @@ -694,19 +695,11 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, return -EBUSY; /* For an MLO connection, if a link ID was specified, validate that it - * is indeed active. If no link ID was specified, select one of the - * active links. + * is indeed active. */ - if (ieee80211_vif_is_mld(&sdata->vif)) { - if (req->tsf_report_link_id >= 0) { - if (!(sdata->vif.active_links & - BIT(req->tsf_report_link_id))) - return -EINVAL; - } else { - req->tsf_report_link_id = - __ffs(sdata->vif.active_links); - } - } + if (ieee80211_vif_is_mld(&sdata->vif) && req->tsf_report_link_id >= 0 && + !(sdata->vif.active_links & BIT(req->tsf_report_link_id))) + return -EINVAL; if (!__ieee80211_can_leave_ch(sdata)) return -EBUSY; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4391d8dd634bb..da53272102f31 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1717,7 +1717,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) skb_queue_head_init(&pending); /* sync with ieee80211_tx_h_unicast_ps_buf */ - spin_lock(&sta->ps_lock); + spin_lock_bh(&sta->ps_lock); /* Send all buffered frames to the station */ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { int count = skb_queue_len(&pending), tmp; @@ -1746,7 +1746,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) */ clear_sta_flag(sta, WLAN_STA_PSPOLL); clear_sta_flag(sta, WLAN_STA_UAPSD); - spin_unlock(&sta->ps_lock); + spin_unlock_bh(&sta->ps_lock); atomic_dec(&ps->num_sta_ps); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 5ef1554f991f6..ac4c7a6f962ea 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -3,7 +3,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright(c) 2020-2023 Intel Corporation + * Copyright(c) 2020-2024 Intel Corporation */ #ifndef STA_INFO_H @@ -482,6 +482,8 @@ struct ieee80211_fragment_cache { * same for non-MLD STA. This is used as key for searching link STA * @link_id: Link ID uniquely identifying the link STA. This is 0 for non-MLD * and set to the corresponding vif LinkId for MLD STA + * @op_mode_nss: NSS limit as set by operating mode notification, or 0 + * @capa_nss: NSS limit as determined by local and peer capabilities * @link_hash_node: hash node for rhashtable * @sta: Points to the STA info * @gtk: group keys negotiated with this station, if any @@ -518,6 +520,8 @@ struct link_sta_info { u8 addr[ETH_ALEN]; u8 link_id; + u8 op_mode_nss, capa_nss; + struct rhlist_head link_hash_node; struct sta_info *sta; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 6fbb15b65902c..a8a4912bf2cb4 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -701,11 +701,16 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) txrc.bss_conf = &tx->sdata->vif.bss_conf; txrc.skb = tx->skb; txrc.reported_rate.idx = -1; - txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band]; - if (tx->sdata->rc_has_mcs_mask[info->band]) - txrc.rate_idx_mcs_mask = - tx->sdata->rc_rateidx_mcs_mask[info->band]; + if (unlikely(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX)) { + txrc.rate_idx_mask = ~0; + } else { + txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band]; + + if (tx->sdata->rc_has_mcs_mask[info->band]) + txrc.rate_idx_mcs_mask = + tx->sdata->rc_rateidx_mcs_mask[info->band]; + } txrc.bss = (tx->sdata->vif.type == NL80211_IFTYPE_AP || tx->sdata->vif.type == NL80211_IFTYPE_MESH_POINT || diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index b3a5c3e96a720..bc13b1419981a 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -4,7 +4,7 @@ * * Portions of this file * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2018 - 2023 Intel Corporation + * Copyright (C) 2018 - 2024 Intel Corporation */ #include @@ -541,15 +541,11 @@ ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta) return bw; } -void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta) +void ieee80211_sta_init_nss(struct link_sta_info *link_sta) { u8 ht_rx_nss = 0, vht_rx_nss = 0, he_rx_nss = 0, eht_rx_nss = 0, rx_nss; bool support_160; - /* if we received a notification already don't overwrite it */ - if (link_sta->pub->rx_nss) - return; - if (link_sta->pub->eht_cap.has_eht) { int i; const u8 *rx_nss_mcs = (void *)&link_sta->pub->eht_cap.eht_mcs_nss_supp; @@ -627,7 +623,15 @@ void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta) rx_nss = max(vht_rx_nss, ht_rx_nss); rx_nss = max(he_rx_nss, rx_nss); rx_nss = max(eht_rx_nss, rx_nss); - link_sta->pub->rx_nss = max_t(u8, 1, rx_nss); + rx_nss = max_t(u8, 1, rx_nss); + link_sta->capa_nss = rx_nss; + + /* that shouldn't be set yet, but we can handle it anyway */ + if (link_sta->op_mode_nss) + link_sta->pub->rx_nss = + min_t(u8, rx_nss, link_sta->op_mode_nss); + else + link_sta->pub->rx_nss = rx_nss; } u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, @@ -637,7 +641,7 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, enum ieee80211_sta_rx_bandwidth new_bw; struct sta_opmode_info sta_opmode = {}; u32 changed = 0; - u8 nss, cur_nss; + u8 nss; /* ignore - no support for BF yet */ if (opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF) @@ -647,23 +651,17 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, nss >>= IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT; nss += 1; - if (link_sta->pub->rx_nss != nss) { - cur_nss = link_sta->pub->rx_nss; - /* Reset rx_nss and call ieee80211_sta_set_rx_nss() which - * will set the same to max nss value calculated based on capability. - */ - link_sta->pub->rx_nss = 0; - ieee80211_sta_set_rx_nss(link_sta); - /* Do not allow an nss change to rx_nss greater than max_nss - * negotiated and capped to APs capability during association. - */ - if (nss <= link_sta->pub->rx_nss) { - link_sta->pub->rx_nss = nss; - sta_opmode.rx_nss = nss; - changed |= IEEE80211_RC_NSS_CHANGED; - sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; + if (link_sta->op_mode_nss != nss) { + if (nss <= link_sta->capa_nss) { + link_sta->op_mode_nss = nss; + + if (nss != link_sta->pub->rx_nss) { + link_sta->pub->rx_nss = nss; + changed |= IEEE80211_RC_NSS_CHANGED; + sta_opmode.rx_nss = link_sta->pub->rx_nss; + sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; + } } else { - link_sta->pub->rx_nss = cur_nss; pr_warn_ratelimited("Ignoring NSS change in VHT Operating Mode Notification from %pM with invalid nss %d", link_sta->pub->addr, nss); } diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 8d2eabc71bbeb..f13b07ebfb98a 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -265,19 +265,27 @@ int mac802154_llsec_key_add(struct mac802154_llsec *sec, return -ENOMEM; } +static void mac802154_llsec_key_del_rcu(struct rcu_head *rcu) +{ + struct ieee802154_llsec_key_entry *pos; + struct mac802154_llsec_key *mkey; + + pos = container_of(rcu, struct ieee802154_llsec_key_entry, rcu); + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + llsec_key_put(mkey); + kfree_sensitive(pos); +} + int mac802154_llsec_key_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_key_entry *pos; list_for_each_entry(pos, &sec->table.keys, list) { - struct mac802154_llsec_key *mkey; - - mkey = container_of(pos->key, struct mac802154_llsec_key, key); - if (llsec_key_id_equal(&pos->id, key)) { list_del_rcu(&pos->list); - llsec_key_put(mkey); + call_rcu(&pos->rcu, mac802154_llsec_key_del_rcu); return 0; } } diff --git a/net/mctp/route.c b/net/mctp/route.c index ceee44ea09d97..01c530dbc1a65 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -843,6 +843,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* copy message payload */ skb_copy_bits(skb, pos, skb_transport_header(skb2), size); + /* we need to copy the extensions, for MCTP flow data */ + skb_ext_copy(skb2, skb); + /* do route */ rc = rt->output(rt, skb2); if (rc) diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 533d082f0701e..45d1e6a157fc7 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -27,6 +27,9 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, __be16 mpls_protocol; unsigned int mpls_hlen; + if (!skb_inner_network_header_was_set(skb)) + goto out; + skb_reset_network_header(skb); mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN)) diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index ef59e25dc4827..89d0fa560d8fc 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -83,7 +83,7 @@ static int mpls_xmit(struct sk_buff *skb) ttl = net->mpls.default_ttl; else ttl = ip_hdr(skb)->ttl; - rt = (struct rtable *)dst; + rt = dst_rtable(dst); } else if (dst->ops->family == AF_INET6) { if (tun_encap_info->ttl_propagate == MPLS_TTL_PROP_DISABLED) ttl = tun_encap_info->default_ttl; @@ -92,7 +92,7 @@ static int mpls_xmit(struct sk_buff *skb) ttl = net->mpls.default_ttl; else ttl = ipv6_hdr(skb)->hop_limit; - rt6 = (struct rt6_info *)dst; + rt6 = dst_rt6_info(dst); } else { goto drop; } diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 13fe0748dde83..2963ba84e2ee4 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -96,6 +96,43 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) } #ifdef CONFIG_SYSCTL +static int mptcp_set_scheduler(const struct net *net, const char *name) +{ + struct mptcp_pernet *pernet = mptcp_get_pernet(net); + struct mptcp_sched_ops *sched; + int ret = 0; + + rcu_read_lock(); + sched = mptcp_sched_find(name); + if (sched) + strscpy(pernet->scheduler, name, MPTCP_SCHED_NAME_MAX); + else + ret = -ENOENT; + rcu_read_unlock(); + + return ret; +} + +static int proc_scheduler(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + const struct net *net = current->nsproxy->net_ns; + char val[MPTCP_SCHED_NAME_MAX]; + struct ctl_table tbl = { + .data = val, + .maxlen = MPTCP_SCHED_NAME_MAX, + }; + int ret; + + strscpy(val, mptcp_get_scheduler(net), MPTCP_SCHED_NAME_MAX); + + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) + ret = mptcp_set_scheduler(net, val); + + return ret; +} + static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", @@ -148,7 +185,7 @@ static struct ctl_table mptcp_sysctl_table[] = { .procname = "scheduler", .maxlen = MPTCP_SCHED_NAME_MAX, .mode = 0644, - .proc_handler = proc_dostring, + .proc_handler = proc_scheduler, }, { .procname = "close_timeout", diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 58d17d9604e78..e5d6d1a1d45a4 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -685,6 +685,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) unsigned int add_addr_accept_max; struct mptcp_addr_info remote; unsigned int subflows_max; + bool sf_created = false; int i, nr; add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); @@ -712,15 +713,18 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) if (nr == 0) return; - msk->pm.add_addr_accepted++; - if (msk->pm.add_addr_accepted >= add_addr_accept_max || - msk->pm.subflows >= subflows_max) - WRITE_ONCE(msk->pm.accept_addr, false); - spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - __mptcp_subflow_connect(sk, &addrs[i], &remote); + if (__mptcp_subflow_connect(sk, &addrs[i], &remote) == 0) + sf_created = true; spin_lock_bh(&msk->pm.lock); + + if (sf_created) { + msk->pm.add_addr_accepted++; + if (msk->pm.add_addr_accepted >= add_addr_accept_max || + msk->pm.subflows >= subflows_max) + WRITE_ONCE(msk->pm.accept_addr, false); + } } void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) @@ -822,10 +826,13 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); removed = true; - __MPTCP_INC_STATS(sock_net(sk), rm_type); + if (rm_type == MPTCP_MIB_RMSUBFLOW) + __MPTCP_INC_STATS(sock_net(sk), rm_type); } if (rm_type == MPTCP_MIB_RMSUBFLOW) __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap); + else if (rm_type == MPTCP_MIB_RMADDR) + __MPTCP_INC_STATS(sock_net(sk), rm_type); if (!removed) continue; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7833a49f6214a..af5144942286f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1687,15 +1687,6 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool } } -static void mptcp_set_nospace(struct sock *sk) -{ - /* enable autotune */ - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - - /* will be cleared on avail space */ - set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags); -} - static int mptcp_disconnect(struct sock *sk, int flags); static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, @@ -1766,6 +1757,30 @@ static int do_copy_data_nocache(struct sock *sk, int copy, return 0; } +/* open-code sk_stream_memory_free() plus sent limit computation to + * avoid indirect calls in fast-path. + * Called under the msk socket lock, so we can avoid a bunch of ONCE + * annotations. + */ +static u32 mptcp_send_limit(const struct sock *sk) +{ + const struct mptcp_sock *msk = mptcp_sk(sk); + u32 limit, not_sent; + + if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf)) + return 0; + + limit = mptcp_notsent_lowat(sk); + if (limit == UINT_MAX) + return UINT_MAX; + + not_sent = msk->write_seq - msk->snd_nxt; + if (not_sent >= limit) + return 0; + + return limit - not_sent; +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1810,6 +1825,12 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct mptcp_data_frag *dfrag; bool dfrag_collapsed; size_t psize, offset; + u32 copy_limit; + + /* ensure fitting the notsent_lowat() constraint */ + copy_limit = mptcp_send_limit(sk); + if (!copy_limit) + goto wait_for_memory; /* reuse tail pfrag, if possible, or carve a new one from the * page allocator @@ -1817,9 +1838,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) dfrag = mptcp_pending_tail(sk); dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag); if (!dfrag_collapsed) { - if (!sk_stream_memory_free(sk)) - goto wait_for_memory; - if (!mptcp_page_frag_refill(sk, pfrag)) goto wait_for_memory; @@ -1834,6 +1852,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) offset = dfrag->offset + dfrag->data_len; psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); + psize = min_t(size_t, psize, copy_limit); total_ts = psize + frag_truesize; if (!sk_wmem_schedule(sk, total_ts)) @@ -1869,7 +1888,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) continue; wait_for_memory: - mptcp_set_nospace(sk); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); __mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) @@ -2884,9 +2903,14 @@ void mptcp_set_state(struct sock *sk, int state) if (oldstate != TCP_ESTABLISHED) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); break; - + case TCP_CLOSE_WAIT: + /* Unlike TCP, MPTCP sk would not have the TCP_SYN_RECV state: + * MPTCP "accepted" sockets will be created later on. So no + * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT. + */ + break; default: - if (oldstate == TCP_ESTABLISHED) + if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); } @@ -3703,6 +3727,10 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT); mptcp_subflow_early_fallback(msk, subflow); } + + WRITE_ONCE(msk->write_seq, subflow->idsn); + WRITE_ONCE(msk->snd_nxt, subflow->idsn); + WRITE_ONCE(msk->snd_una, subflow->idsn); if (likely(!__mptcp_check_fallback(msk))) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); @@ -3767,6 +3795,7 @@ static struct proto mptcp_prot = { .unhash = mptcp_unhash, .get_port = mptcp_get_port, .forward_alloc_get = mptcp_forward_alloc_get, + .stream_memory_free = mptcp_stream_memory_free, .sockets_allocated = &mptcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, @@ -3916,8 +3945,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, mptcp_set_state(newsk, TCP_CLOSE); } } else { - MPTCP_INC_STATS(sock_net(ssk), - MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); tcpfallback: newsk->sk_kern_sock = kern; lock_sock(newsk); @@ -3940,12 +3967,12 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - if (sk_stream_is_writeable(sk)) + if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; - mptcp_set_nospace(sk); - smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */ - if (sk_stream_is_writeable(sk)) + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + smp_mb__after_atomic(); /* NOSPACE is changed by mptcp_write_space() */ + if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; return 0; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 07f6242afc1ae..5f4c10c41c77d 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -113,10 +113,9 @@ #define MPTCP_RST_TRANSIENT BIT(0) /* MPTCP socket atomic flags */ -#define MPTCP_NOSPACE 1 -#define MPTCP_WORK_RTX 2 -#define MPTCP_FALLBACK_DONE 4 -#define MPTCP_WORK_CLOSE_SUBFLOW 5 +#define MPTCP_WORK_RTX 1 +#define MPTCP_FALLBACK_DONE 2 +#define MPTCP_WORK_CLOSE_SUBFLOW 3 /* MPTCP socket release cb flags */ #define MPTCP_PUSH_PENDING 1 @@ -306,6 +305,10 @@ struct mptcp_sock { in_accept_queue:1, free_first:1, rcvspace_init:1; + u32 notsent_lowat; + int keepalive_cnt; + int keepalive_idle; + int keepalive_intvl; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -790,14 +793,36 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } +static inline u32 mptcp_notsent_lowat(const struct sock *sk) +{ + struct net *net = sock_net(sk); + u32 val; + + val = READ_ONCE(mptcp_sk(sk)->notsent_lowat); + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); +} + +static inline bool mptcp_stream_memory_free(const struct sock *sk, int wake) +{ + const struct mptcp_sock *msk = mptcp_sk(sk); + u32 notsent_bytes; + + notsent_bytes = READ_ONCE(msk->write_seq) - READ_ONCE(msk->snd_nxt); + return (notsent_bytes << wake) < mptcp_notsent_lowat(sk); +} + +static inline bool __mptcp_stream_is_writeable(const struct sock *sk, int wake) +{ + return mptcp_stream_memory_free(sk, wake) && + __sk_stream_is_writeable(sk, wake); +} + static inline void mptcp_write_space(struct sock *sk) { - if (sk_stream_is_writeable(sk)) { - /* pairs with memory barrier in mptcp_poll */ - smp_mb(); - if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags)) - sk_stream_write_space(sk); - } + /* pairs with memory barrier in mptcp_poll */ + smp_mb(); + if (mptcp_stream_memory_free(sk, 1)) + sk_stream_write_space(sk); } static inline void __mptcp_sync_sndbuf(struct sock *sk) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index c40f1428e6020..47aa826ba5fea 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -181,8 +181,6 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, switch (optname) { case SO_KEEPALIVE: - mptcp_sol_socket_sync_intval(msk, optname, val); - return 0; case SO_DEBUG: case SO_MARK: case SO_PRIORITY: @@ -624,20 +622,36 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t return ret; } -static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optval, - unsigned int optlen) +static int __mptcp_setsockopt_set_val(struct mptcp_sock *msk, int max, + int (*set_val)(struct sock *, int), + int *msk_val, int val) { struct mptcp_subflow_context *subflow; - struct sock *sk = (struct sock *)msk; - int val; + int err = 0; - if (optlen < sizeof(int)) - return -EINVAL; + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int ret; - if (copy_from_sockptr(&val, optval, sizeof(val))) - return -EFAULT; + lock_sock(ssk); + ret = set_val(ssk, val); + err = err ? : ret; + release_sock(ssk); + } + + if (!err) { + *msk_val = val; + sockopt_seq_inc(msk); + } + + return err; +} + +static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; - lock_sock(sk); sockopt_seq_inc(msk); msk->cork = !!val; mptcp_for_each_subflow(msk, subflow) { @@ -649,25 +663,15 @@ static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optva } if (!val) mptcp_check_and_set_pending(sk); - release_sock(sk); return 0; } -static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t optval, - unsigned int optlen) +static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - int val; - if (optlen < sizeof(int)) - return -EINVAL; - - if (copy_from_sockptr(&val, optval, sizeof(val))) - return -EFAULT; - - lock_sock(sk); sockopt_seq_inc(msk); msk->nodelay = !!val; mptcp_for_each_subflow(msk, subflow) { @@ -679,8 +683,6 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op } if (val) mptcp_check_and_set_pending(sk); - release_sock(sk); - return 0; } @@ -803,25 +805,10 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, int ret, val; switch (optname) { - case TCP_INQ: - ret = mptcp_get_int_option(msk, optval, optlen, &val); - if (ret) - return ret; - if (val < 0 || val > 1) - return -EINVAL; - - lock_sock(sk); - msk->recvmsg_inq = !!val; - release_sock(sk); - return 0; case TCP_ULP: return -EOPNOTSUPP; case TCP_CONGESTION: return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen); - case TCP_CORK: - return mptcp_setsockopt_sol_tcp_cork(msk, optval, optlen); - case TCP_NODELAY: - return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen); case TCP_DEFER_ACCEPT: /* See tcp.c: TCP_DEFER_ACCEPT does not fail */ mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen); @@ -834,7 +821,50 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, optval, optlen); } - return -EOPNOTSUPP; + ret = mptcp_get_int_option(msk, optval, optlen, &val); + if (ret) + return ret; + + lock_sock(sk); + switch (optname) { + case TCP_INQ: + if (val < 0 || val > 1) + ret = -EINVAL; + else + msk->recvmsg_inq = !!val; + break; + case TCP_NOTSENT_LOWAT: + WRITE_ONCE(msk->notsent_lowat, val); + mptcp_write_space(sk); + break; + case TCP_CORK: + ret = __mptcp_setsockopt_sol_tcp_cork(msk, val); + break; + case TCP_NODELAY: + ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val); + break; + case TCP_KEEPIDLE: + ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPIDLE, + &tcp_sock_set_keepidle_locked, + &msk->keepalive_idle, val); + break; + case TCP_KEEPINTVL: + ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPINTVL, + &tcp_sock_set_keepintvl, + &msk->keepalive_intvl, val); + break; + case TCP_KEEPCNT: + ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPCNT, + &tcp_sock_set_keepcnt, + &msk->keepalive_cnt, + val); + break; + default: + ret = -ENOPROTOOPT; + } + + release_sock(sk); + return ret; } int mptcp_setsockopt(struct sock *sk, int level, int optname, @@ -1331,6 +1361,8 @@ static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval, static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { + struct sock *sk = (void *)msk; + switch (optname) { case TCP_ULP: case TCP_CONGESTION: @@ -1349,6 +1381,20 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return mptcp_put_int_option(msk, optval, optlen, msk->cork); case TCP_NODELAY: return mptcp_put_int_option(msk, optval, optlen, msk->nodelay); + case TCP_KEEPIDLE: + return mptcp_put_int_option(msk, optval, optlen, + msk->keepalive_idle ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_time) / HZ); + case TCP_KEEPINTVL: + return mptcp_put_int_option(msk, optval, optlen, + msk->keepalive_intvl ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_intvl) / HZ); + case TCP_KEEPCNT: + return mptcp_put_int_option(msk, optval, optlen, + msk->keepalive_cnt ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_probes)); + case TCP_NOTSENT_LOWAT: + return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat); } return -EOPNOTSUPP; } @@ -1464,6 +1510,9 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) tcp_set_congestion_control(ssk, msk->ca_name, false, true); __tcp_sock_set_cork(ssk, !!msk->cork); __tcp_sock_set_nodelay(ssk, !!msk->nodelay); + tcp_sock_set_keepidle_locked(ssk, msk->keepalive_idle); + tcp_sock_set_keepintvl(ssk, msk->keepalive_intvl); + tcp_sock_set_keepcnt(ssk, msk->keepalive_cnt); inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk)); inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); @@ -1500,6 +1549,10 @@ int mptcp_set_rcvlowat(struct sock *sk, int val) struct mptcp_subflow_context *subflow; int space, cap; + /* bpf can land here with a wrong sk type */ + if (sk->sk_protocol == IPPROTO_TCP) + return -EINVAL; + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 71ba86246ff89..13f66d11b7a0b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -905,6 +905,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, return child; fallback: + if (fallback) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); mptcp_subflow_drop_ctx(child); return child; } diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 374412ed780b6..ef0f8f73826f5 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -325,6 +325,7 @@ struct ncsi_dev_priv { spinlock_t lock; /* Protect the NCSI device */ unsigned int package_probe_id;/* Current ID during probe */ unsigned int package_num; /* Number of packages */ + unsigned int channel_probe_id;/* Current cahnnel ID during probe */ struct list_head packages; /* List of packages */ struct ncsi_channel *hot_channel; /* Channel was ever active */ struct ncsi_request requests[256]; /* Request table */ @@ -343,6 +344,7 @@ struct ncsi_dev_priv { bool multi_package; /* Enable multiple packages */ bool mlx_multi_host; /* Enable multi host Mellanox */ u32 package_whitelist; /* Packages to configure */ + unsigned char channel_count; /* Num of channels to probe */ }; struct ncsi_cmd_arg { diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 745c788f1d1df..5ecf611c88200 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -510,17 +510,19 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp) break; case ncsi_dev_state_suspend_gls: - ndp->pending_req_num = np->channel_num; + ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_GLS; nca.package = np->id; + nca.channel = ndp->channel_probe_id; + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + ndp->channel_probe_id++; - nd->state = ncsi_dev_state_suspend_dcnt; - NCSI_FOR_EACH_CHANNEL(np, nc) { - nca.channel = nc->id; - ret = ncsi_xmit_cmd(&nca); - if (ret) - goto error; + if (ndp->channel_probe_id == ndp->channel_count) { + ndp->channel_probe_id = 0; + nd->state = ncsi_dev_state_suspend_dcnt; } break; @@ -1345,7 +1347,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) { struct ncsi_dev *nd = &ndp->ndev; struct ncsi_package *np; - struct ncsi_channel *nc; struct ncsi_cmd_arg nca; unsigned char index; int ret; @@ -1423,23 +1424,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nd->state = ncsi_dev_state_probe_cis; break; - case ncsi_dev_state_probe_cis: - ndp->pending_req_num = NCSI_RESERVED_CHANNEL; - - /* Clear initial state */ - nca.type = NCSI_PKT_CMD_CIS; - nca.package = ndp->active_package->id; - for (index = 0; index < NCSI_RESERVED_CHANNEL; index++) { - nca.channel = index; - ret = ncsi_xmit_cmd(&nca); - if (ret) - goto error; - } - - nd->state = ncsi_dev_state_probe_gvi; - if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)) - nd->state = ncsi_dev_state_probe_keep_phy; - break; case ncsi_dev_state_probe_keep_phy: ndp->pending_req_num = 1; @@ -1452,14 +1436,17 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nd->state = ncsi_dev_state_probe_gvi; break; + case ncsi_dev_state_probe_cis: case ncsi_dev_state_probe_gvi: case ncsi_dev_state_probe_gc: case ncsi_dev_state_probe_gls: np = ndp->active_package; - ndp->pending_req_num = np->channel_num; + ndp->pending_req_num = 1; - /* Retrieve version, capability or link status */ - if (nd->state == ncsi_dev_state_probe_gvi) + /* Clear initial state Retrieve version, capability or link status */ + if (nd->state == ncsi_dev_state_probe_cis) + nca.type = NCSI_PKT_CMD_CIS; + else if (nd->state == ncsi_dev_state_probe_gvi) nca.type = NCSI_PKT_CMD_GVI; else if (nd->state == ncsi_dev_state_probe_gc) nca.type = NCSI_PKT_CMD_GC; @@ -1467,19 +1454,29 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nca.type = NCSI_PKT_CMD_GLS; nca.package = np->id; - NCSI_FOR_EACH_CHANNEL(np, nc) { - nca.channel = nc->id; - ret = ncsi_xmit_cmd(&nca); - if (ret) - goto error; - } + nca.channel = ndp->channel_probe_id; - if (nd->state == ncsi_dev_state_probe_gvi) + ret = ncsi_xmit_cmd(&nca); + if (ret) + goto error; + + if (nd->state == ncsi_dev_state_probe_cis) { + nd->state = ncsi_dev_state_probe_gvi; + if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) && ndp->channel_probe_id == 0) + nd->state = ncsi_dev_state_probe_keep_phy; + } else if (nd->state == ncsi_dev_state_probe_gvi) { nd->state = ncsi_dev_state_probe_gc; - else if (nd->state == ncsi_dev_state_probe_gc) + } else if (nd->state == ncsi_dev_state_probe_gc) { nd->state = ncsi_dev_state_probe_gls; - else + } else { + nd->state = ncsi_dev_state_probe_cis; + ndp->channel_probe_id++; + } + + if (ndp->channel_probe_id == ndp->channel_count) { + ndp->channel_probe_id = 0; nd->state = ncsi_dev_state_probe_dp; + } break; case ncsi_dev_state_probe_dp: ndp->pending_req_num = 1; @@ -1780,6 +1777,7 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, ndp->requests[i].ndp = ndp; timer_setup(&ndp->requests[i].timer, ncsi_request_timeout, 0); } + ndp->channel_count = NCSI_RESERVED_CHANNEL; spin_lock_irqsave(&ncsi_dev_lock, flags); list_add_tail_rcu(&ndp->node, &ncsi_dev_list); @@ -1813,6 +1811,7 @@ int ncsi_start_dev(struct ncsi_dev *nd) if (!(ndp->flags & NCSI_DEV_PROBED)) { ndp->package_probe_id = 0; + ndp->channel_probe_id = 0; nd->state = ncsi_dev_state_probe; schedule_work(&ndp->work); return 0; diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index bee290d0f48b6..e28be33bdf2c4 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -795,12 +795,13 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr) struct ncsi_rsp_gc_pkt *rsp; struct ncsi_dev_priv *ndp = nr->ndp; struct ncsi_channel *nc; + struct ncsi_package *np; size_t size; /* Find the channel */ rsp = (struct ncsi_rsp_gc_pkt *)skb_network_header(nr->rsp); ncsi_find_package_and_channel(ndp, rsp->rsp.common.channel, - NULL, &nc); + &np, &nc); if (!nc) return -ENODEV; @@ -835,6 +836,7 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr) */ nc->vlan_filter.bitmap = U64_MAX; nc->vlan_filter.n_vids = rsp->vlan_cnt; + np->ndp->channel_count = rsp->channel_cnt; return 0; } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 3126911f50425..b00fc285b3349 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -815,12 +815,21 @@ int __init netfilter_init(void) if (ret < 0) goto err; +#ifdef CONFIG_LWTUNNEL + ret = netfilter_lwtunnel_init(); + if (ret < 0) + goto err_lwtunnel_pernet; +#endif ret = netfilter_log_init(); if (ret < 0) - goto err_pernet; + goto err_log_pernet; return 0; -err_pernet: +err_log_pernet: +#ifdef CONFIG_LWTUNNEL + netfilter_lwtunnel_fini(); +err_lwtunnel_pernet: +#endif unregister_pernet_subsys(&netfilter_net_ops); err: return ret; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 3184cc6be4c9d..61431690cbd5f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -53,12 +53,13 @@ MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); /* When the nfnl mutex or ip_set_ref_lock is held: */ -#define ip_set_dereference(p) \ - rcu_dereference_protected(p, \ +#define ip_set_dereference(inst) \ + rcu_dereference_protected((inst)->ip_set_list, \ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ - lockdep_is_held(&ip_set_ref_lock)) + lockdep_is_held(&ip_set_ref_lock) || \ + (inst)->is_deleted) #define ip_set(inst, id) \ - ip_set_dereference((inst)->ip_set_list)[id] + ip_set_dereference(inst)[id] #define ip_set_ref_netlink(inst,id) \ rcu_dereference_raw((inst)->ip_set_list)[id] #define ip_set_dereference_nfnl(p) \ @@ -1133,7 +1134,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ - tmp = ip_set_dereference(inst->ip_set_list); + tmp = ip_set_dereference(inst); memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max); rcu_assign_pointer(inst->ip_set_list, list); /* Make sure all current packets have passed through */ @@ -1172,23 +1173,50 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { .len = IPSET_MAXNAMELEN - 1 }, }; +/* In order to return quickly when destroying a single set, it is split + * into two stages: + * - Cancel garbage collector + * - Destroy the set itself via call_rcu() + */ + static void -ip_set_destroy_set(struct ip_set *set) +ip_set_destroy_set_rcu(struct rcu_head *head) { - pr_debug("set: %s\n", set->name); + struct ip_set *set = container_of(head, struct ip_set, rcu); - /* Must call it without holding any lock */ set->variant->destroy(set); module_put(set->type->me); kfree(set); } static void -ip_set_destroy_set_rcu(struct rcu_head *head) +_destroy_all_sets(struct ip_set_net *inst) { - struct ip_set *set = container_of(head, struct ip_set, rcu); + struct ip_set *set; + ip_set_id_t i; + bool need_wait = false; - ip_set_destroy_set(set); + /* First cancel gc's: set:list sets are flushed as well */ + for (i = 0; i < inst->ip_set_max; i++) { + set = ip_set(inst, i); + if (set) { + set->variant->cancel_gc(set); + if (set->type->features & IPSET_TYPE_NAME) + need_wait = true; + } + } + /* Must wait for flush to be really finished */ + if (need_wait) + rcu_barrier(); + for (i = 0; i < inst->ip_set_max; i++) { + set = ip_set(inst, i); + if (set) { + ip_set(inst, i) = NULL; + set->variant->destroy(set); + module_put(set->type->me); + kfree(set); + } + } } static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, @@ -1202,11 +1230,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Commands are serialized and references are * protected by the ip_set_ref_lock. * External systems (i.e. xt_set) must call - * ip_set_put|get_nfnl_* functions, that way we + * ip_set_nfnl_get_* functions, that way we * can safely check references here. * * list:set timer can only decrement the reference @@ -1214,8 +1241,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, * without holding the lock. */ if (!attr[IPSET_ATTR_SETNAME]) { - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); @@ -1226,15 +1251,7 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, } inst->is_destroyed = true; read_unlock_bh(&ip_set_ref_lock); - for (i = 0; i < inst->ip_set_max; i++) { - s = ip_set(inst, i); - if (s) { - ip_set(inst, i) = NULL; - /* Must cancel garbage collectors */ - s->variant->cancel_gc(s); - ip_set_destroy_set(s); - } - } + _destroy_all_sets(inst); /* Modified by ip_set_destroy() only, which is serialized */ inst->is_destroyed = false; } else { @@ -1255,12 +1272,12 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); if (features & IPSET_TYPE_NAME) { /* Must wait for flush to be really finished */ rcu_barrier(); } - /* Must cancel garbage collectors */ - s->variant->cancel_gc(s); call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; @@ -2365,30 +2382,25 @@ ip_set_net_init(struct net *net) } static void __net_exit -ip_set_net_exit(struct net *net) +ip_set_net_pre_exit(struct net *net) { struct ip_set_net *inst = ip_set_pernet(net); - struct ip_set *set = NULL; - ip_set_id_t i; - inst->is_deleted = true; /* flag for ip_set_nfnl_put */ +} - nfnl_lock(NFNL_SUBSYS_IPSET); - for (i = 0; i < inst->ip_set_max; i++) { - set = ip_set(inst, i); - if (set) { - ip_set(inst, i) = NULL; - set->variant->cancel_gc(set); - ip_set_destroy_set(set); - } - } - nfnl_unlock(NFNL_SUBSYS_IPSET); +static void __net_exit +ip_set_net_exit(struct net *net) +{ + struct ip_set_net *inst = ip_set_pernet(net); + + _destroy_all_sets(inst); kvfree(rcu_dereference_protected(inst->ip_set_list, 1)); } static struct pernet_operations ip_set_net_ops = { .init = ip_set_net_init, + .pre_exit = ip_set_net_pre_exit, .exit = ip_set_net_exit, .id = &ip_set_net_id, .size = sizeof(struct ip_set_net), diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 6c3f28bc59b32..bfae7066936bb 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -79,7 +79,7 @@ list_set_kadd(struct ip_set *set, const struct sk_buff *skb, struct set_elem *e; int ret; - list_for_each_entry(e, &map->members, list) { + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -99,7 +99,7 @@ list_set_kdel(struct ip_set *set, const struct sk_buff *skb, struct set_elem *e; int ret; - list_for_each_entry(e, &map->members, list) { + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -188,9 +188,10 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct list_set *map = set->data; struct set_adt_elem *d = value; struct set_elem *e, *next, *prev = NULL; - int ret; + int ret = 0; - list_for_each_entry(e, &map->members, list) { + rcu_read_lock(); + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -201,6 +202,7 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (d->before == 0) { ret = 1; + goto out; } else if (d->before > 0) { next = list_next_entry(e, list); ret = !list_is_last(&e->list, &map->members) && @@ -208,9 +210,11 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, } else { ret = prev && prev->id == d->refid; } - return ret; + goto out; } - return 0; +out: + rcu_read_unlock(); + return ret; } static void @@ -239,7 +243,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, /* Find where to add the new entry */ n = prev = next = NULL; - list_for_each_entry(e, &map->members, list) { + list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -316,9 +320,9 @@ list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext, { struct list_set *map = set->data; struct set_adt_elem *d = value; - struct set_elem *e, *next, *prev = NULL; + struct set_elem *e, *n, *next, *prev = NULL; - list_for_each_entry(e, &map->members, list) { + list_for_each_entry_safe(e, n, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; @@ -424,14 +428,8 @@ static void list_set_destroy(struct ip_set *set) { struct list_set *map = set->data; - struct set_elem *e, *n; - list_for_each_entry_safe(e, n, &map->members, list) { - list_del(&e->list); - ip_set_put_byindex(map->net, e->id); - ip_set_ext_destroy(set, e); - kfree(e); - } + WARN_ON_ONCE(!list_empty(&map->members)); kfree(map); set->data = NULL; @@ -549,6 +547,9 @@ list_set_cancel_gc(struct ip_set *set) if (SET_WITH_TIMEOUT(set)) timer_shutdown_sync(&map->gc); + + /* Flush list to drop references to other ipsets */ + list_set_flush(set); } static const struct ip_set_type_variant set_variant = { diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index a0921adc31a9f..1e689c7141271 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,8 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -174,7 +175,8 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 65e0259178da4..e1f17392f58c1 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -180,7 +180,7 @@ static inline bool crosses_local_route_boundary(int skb_af, struct sk_buff *skb, (!skb->dev || skb->dev->flags & IFF_LOOPBACK) && (addr_type & IPV6_ADDR_LOOPBACK); old_rt_is_local = __ip_vs_is_local_route6( - (struct rt6_info *)skb_dst(skb)); + dst_rt6_info(skb_dst(skb))); } else #endif { @@ -318,7 +318,7 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, if (dest) { dest_dst = __ip_vs_dst_check(dest); if (likely(dest_dst)) - rt = (struct rtable *) dest_dst->dst_cache; + rt = dst_rtable(dest_dst->dst_cache); else { dest_dst = ip_vs_dest_dst_alloc(); spin_lock_bh(&dest->dst_lock); @@ -481,7 +481,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, if (dest) { dest_dst = __ip_vs_dst_check(dest); if (likely(dest_dst)) - rt = (struct rt6_info *) dest_dst->dst_cache; + rt = dst_rt6_info(dest_dst->dst_cache); else { u32 cookie; @@ -501,7 +501,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, ip_vs_dest_dst_free(dest_dst); goto err_unreach; } - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); cookie = rt6_get_cookie(rt); __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie); spin_unlock_bh(&dest->dst_lock); @@ -517,7 +517,7 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, rt_mode); if (!dst) goto err_unreach; - rt = (struct rt6_info *) dst; + rt = dst_rt6_info(dst); } local = __ip_vs_is_local_route6(rt); @@ -862,7 +862,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_RDR); if (local < 0) goto tx_error; - rt = (struct rt6_info *) skb_dst(skb); + rt = dst_rt6_info(skb_dst(skb)); /* * Avoid duplicate tuple in reply direction for NAT traffic * to local address when connection is sync-ed @@ -1288,7 +1288,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (local) return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1); - rt = (struct rt6_info *) skb_dst(skb); + rt = dst_rt6_info(skb_dst(skb)); tdev = rt->dst.dev; /* @@ -1590,7 +1590,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, &cp->daddr.in6, NULL, ipvsh, 0, rt_mode); if (local < 0) goto tx_error; - rt = (struct rt6_info *) skb_dst(skb); + rt = dst_rt6_info(skb_dst(skb)); /* * Avoid duplicate tuple in reply direction for NAT traffic * to local address when connection is sync-ed diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 3b846cbdc050d..27b116976a0e2 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -357,11 +357,11 @@ static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct, static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_secctx; - int len, ret; - char *secctx; + struct lsmcontext ctx; + int ret; - ret = security_secid_to_secctx(ct->secmark, &secctx, &len); - if (ret) + ret = security_secid_to_secctx(ct->secmark, &ctx); + if (ret < 0) return 0; ret = -1; @@ -369,13 +369,13 @@ static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) if (!nest_secctx) goto nla_put_failure; - if (nla_put_string(skb, CTA_SECCTX_NAME, secctx)) + if (nla_put_string(skb, CTA_SECCTX_NAME, ctx.context)) goto nla_put_failure; nla_nest_end(skb, nest_secctx); ret = 0; nla_put_failure: - security_release_secctx(secctx, len); + security_release_secctx(&ctx); return ret; } #else @@ -669,8 +669,8 @@ static inline int ctnetlink_secctx_size(const struct nf_conn *ct) #ifdef CONFIG_NF_CONNTRACK_SECMARK int len, ret; - ret = security_secid_to_secctx(ct->secmark, NULL, &len); - if (ret) + ret = security_secid_to_secctx(ct->secmark, NULL); + if (ret < 0) return 0; return nla_total_size(0) /* CTA_SECCTX */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 0ee98ce5b8165..25b8d2d028806 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -22,9 +22,6 @@ #include #include #include -#ifdef CONFIG_LWTUNNEL -#include -#endif #include static bool enable_hooks __read_mostly; @@ -175,17 +172,16 @@ static void ct_seq_stop(struct seq_file *s, void *v) #ifdef CONFIG_NF_CONNTRACK_SECMARK static void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { + struct lsmcontext ctx; int ret; - u32 len; - char *secctx; - ret = security_secid_to_secctx(ct->secmark, &secctx, &len); - if (ret) + ret = security_secid_to_secctx(ct->secmark, &ctx); + if (ret < 0) return; - seq_printf(s, "secctx=%s ", secctx); + seq_printf(s, "secctx=%s ", ctx.context); - security_release_secctx(secctx, len); + security_release_secctx(&ctx); } #else static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) @@ -612,9 +608,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif -#ifdef CONFIG_LWTUNNEL - NF_SYSCTL_CT_LWTUNNEL, -#endif __NF_SYSCTL_CT_LAST_SYSCTL, }; @@ -947,15 +940,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, -#endif -#ifdef CONFIG_LWTUNNEL - [NF_SYSCTL_CT_LWTUNNEL] = { - .procname = "nf_hooks_lwtunnel", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = nf_hooks_lwtunnel_sysctl_handler, - }, #endif {} }; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index a0571339239c4..5c1ff07eaee0b 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -77,12 +77,8 @@ EXPORT_SYMBOL_GPL(flow_offload_alloc); static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) { - const struct rt6_info *rt; - - if (flow_tuple->l3proto == NFPROTO_IPV6) { - rt = (const struct rt6_info *)flow_tuple->dst_cache; - return rt6_get_cookie(rt); - } + if (flow_tuple->l3proto == NFPROTO_IPV6) + return rt6_get_cookie(dst_rt6_info(flow_tuple->dst_cache)); return 0; } diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 9505f9d188ff2..6eef15648b7b0 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -21,7 +21,8 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, proto = veth->h_vlan_encapsulated_proto; break; case htons(ETH_P_PPP_SES): - proto = nf_flow_pppoe_proto(skb); + if (!nf_flow_pppoe_proto(skb, &proto)) + return NF_ACCEPT; break; default: proto = skb->protocol; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index e45fade764096..c2c005234dcd3 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -157,7 +157,7 @@ static void nf_flow_tuple_encap(struct sk_buff *skb, tuple->encap[i].proto = skb->protocol; break; case htons(ETH_P_PPP_SES): - phdr = (struct pppoe_hdr *)skb_mac_header(skb); + phdr = (struct pppoe_hdr *)skb_network_header(skb); tuple->encap[i].id = ntohs(phdr->sid); tuple->encap[i].proto = skb->protocol; break; @@ -273,10 +273,11 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } -static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, +static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, u32 *offset) { struct vlan_ethhdr *veth; + __be16 inner_proto; switch (skb->protocol) { case htons(ETH_P_8021Q): @@ -287,7 +288,8 @@ static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, } break; case htons(ETH_P_PPP_SES): - if (nf_flow_pppoe_proto(skb) == proto) { + if (nf_flow_pppoe_proto(skb, &inner_proto) && + inner_proto == proto) { *offset += PPPOE_SES_HLEN; return true; } @@ -316,7 +318,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb, skb_reset_network_header(skb); break; case htons(ETH_P_PPP_SES): - skb->protocol = nf_flow_pppoe_proto(skb); + skb->protocol = __nf_flow_pppoe_proto(skb); skb_pull(skb, PPPOE_SES_HLEN); skb_reset_network_header(skb); break; @@ -432,7 +434,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, return NF_ACCEPT; if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) { - rt = (struct rtable *)tuplehash->tuple.dst_cache; + rt = dst_rtable(tuplehash->tuple.dst_cache); memset(skb->cb, 0, sizeof(struct inet_skb_parm)); IPCB(skb)->iif = skb->dev->ifindex; IPCB(skb)->flags = IPSKB_FORWARDED; @@ -444,7 +446,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: - rt = (struct rtable *)tuplehash->tuple.dst_cache; + rt = dst_rtable(tuplehash->tuple.dst_cache); outdev = rt->dst.dev; skb->dev = outdev; nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); @@ -727,7 +729,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, return NF_ACCEPT; if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) { - rt = (struct rt6_info *)tuplehash->tuple.dst_cache; + rt = dst_rt6_info(tuplehash->tuple.dst_cache); memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); IP6CB(skb)->iif = skb->dev->ifindex; IP6CB(skb)->flags = IP6SKB_FORWARDED; @@ -739,7 +741,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: - rt = (struct rt6_info *)tuplehash->tuple.dst_cache; + rt = dst_rt6_info(tuplehash->tuple.dst_cache); outdev = rt->dst.dev; skb->dev = outdev; nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c index 00e89ffd78f69..7cdb59bb4459f 100644 --- a/net/netfilter/nf_hooks_lwtunnel.c +++ b/net/netfilter/nf_hooks_lwtunnel.c @@ -3,6 +3,9 @@ #include #include #include +#include + +#include "nf_internals.h" static inline int nf_hooks_lwtunnel_get(void) { @@ -50,4 +53,68 @@ int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, return ret; } EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_sysctl_handler); + +static struct ctl_table nf_lwtunnel_sysctl_table[] = { + { + .procname = "nf_hooks_lwtunnel", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = nf_hooks_lwtunnel_sysctl_handler, + }, +}; + +static int __net_init nf_lwtunnel_net_init(struct net *net) +{ + struct ctl_table_header *hdr; + struct ctl_table *table; + + table = nf_lwtunnel_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(nf_lwtunnel_sysctl_table, + sizeof(nf_lwtunnel_sysctl_table), + GFP_KERNEL); + if (!table) + goto err_alloc; + } + + hdr = register_net_sysctl_sz(net, "net/netfilter", table, + ARRAY_SIZE(nf_lwtunnel_sysctl_table)); + if (!hdr) + goto err_reg; + + net->nf.nf_lwtnl_dir_header = hdr; + + return 0; +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit nf_lwtunnel_net_exit(struct net *net) +{ + const struct ctl_table *table; + + table = net->nf.nf_lwtnl_dir_header->ctl_table_arg; + unregister_net_sysctl_table(net->nf.nf_lwtnl_dir_header); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations nf_lwtunnel_net_ops = { + .init = nf_lwtunnel_net_init, + .exit = nf_lwtunnel_net_exit, +}; + +int __init netfilter_lwtunnel_init(void) +{ + return register_pernet_subsys(&nf_lwtunnel_net_ops); +} + +void netfilter_lwtunnel_fini(void) +{ + unregister_pernet_subsys(&nf_lwtunnel_net_ops); +} #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 832ae64179f0f..25403023060b6 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -29,6 +29,12 @@ void nf_queue_nf_hook_drop(struct net *net); /* nf_log.c */ int __init netfilter_log_init(void); +#ifdef CONFIG_LWTUNNEL +/* nf_hooks_lwtunnel.c */ +int __init netfilter_lwtunnel_init(void); +void netfilter_lwtunnel_fini(void); +#endif + /* core.c */ void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1683dc196b592..0e697e53a7902 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -594,6 +594,12 @@ static int nft_mapelem_deactivate(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + + nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, elem_priv); return 0; @@ -617,6 +623,7 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; + nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); break; } @@ -626,6 +633,7 @@ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, .fn = nft_mapelem_deactivate, }; @@ -1198,6 +1206,26 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ __NFT_TABLE_F_WAS_AWAKEN) +static bool nft_table_pending_update(const struct nft_ctx *ctx) +{ + struct nftables_pernet *nft_net = nft_pernet(ctx->net); + struct nft_trans *trans; + + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return true; + + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->ctx.table == ctx->table && + ((trans->msg_type == NFT_MSG_NEWCHAIN && + nft_trans_chain_update(trans)) || + (trans->msg_type == NFT_MSG_DELCHAIN && + nft_is_base_chain(trans->ctx.chain)))) + return true; + } + + return false; +} + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -1211,7 +1239,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags & ~NFT_TABLE_F_MASK) return -EOPNOTSUPP; - if (flags == ctx->table->flags) + if (flags == (ctx->table->flags & NFT_TABLE_F_MASK)) return 0; if ((nft_table_has_owner(ctx->table) && @@ -1221,7 +1249,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return -EOPNOTSUPP; /* No dormant off/on/off/on games in single transaction */ - if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, @@ -2418,6 +2446,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook = {}; + if (table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; @@ -2619,17 +2650,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, } } - if (nla[NFTA_CHAIN_COUNTERS]) { - if (!nft_is_base_chain(chain)) { - err = -EOPNOTSUPP; - goto err_hooks; - } - - stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); - if (IS_ERR(stats)) { - err = PTR_ERR(stats); - goto err_hooks; - } + if (table->flags & __NFT_TABLE_F_UPDATE && + !list_empty(&hook.list)) { + NL_SET_BAD_ATTR(extack, attr); + err = -EOPNOTSUPP; + goto err_hooks; } if (!(table->flags & NFT_TABLE_F_DORMANT) && @@ -2646,6 +2671,20 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, } unregister = true; + + if (nla[NFTA_CHAIN_COUNTERS]) { + if (!nft_is_base_chain(chain)) { + err = -EOPNOTSUPP; + goto err_hooks; + } + + stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); + if (IS_ERR(stats)) { + err = PTR_ERR(stats); + goto err_hooks; + } + } + err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); @@ -2847,6 +2886,9 @@ static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_trans *trans; int err; + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return -EOPNOTSUPP; + err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook, ctx->family, chain->flags, extack); if (err < 0) @@ -2931,7 +2973,8 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (nla[NFTA_CHAIN_HOOK]) { - if (chain->flags & NFT_CHAIN_HW_OFFLOAD) + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYCHAIN || + chain->flags & NFT_CHAIN_HW_OFFLOAD) return -EOPNOTSUPP; if (nft_is_base_chain(chain)) { @@ -3013,7 +3056,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, { const struct nft_expr_type *type, *candidate = NULL; - list_for_each_entry(type, &nf_tables_expressions, list) { + list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; @@ -3045,9 +3088,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); + rcu_read_lock(); type = __nft_expr_type_get(family, nla); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -3828,6 +3875,9 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_data *data; int err; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; @@ -3851,17 +3901,20 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { - u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_iter dummy_iter = { + .genmask = nft_genmask_next(ctx->net), + }; struct nft_set_elem_catchall *catchall; + struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) + if (!nft_set_elem_active(ext, dummy_iter.genmask)) continue; - ret = nft_setelem_validate(ctx, set, NULL, catchall->elem); + ret = nft_setelem_validate(ctx, set, &dummy_iter, catchall->elem); if (ret < 0) return ret; } @@ -5007,6 +5060,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) return -EOPNOTSUPP; + if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == + (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; } desc.dtype = 0; @@ -5355,6 +5411,11 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + return nft_setelem_data_validate(ctx, set, elem_priv); } @@ -5399,6 +5460,7 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, } iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; @@ -5446,6 +5508,13 @@ static int nft_mapelem_activate(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + /* called from abort path, reverse check to undo changes. */ + if (nft_set_elem_active(ext, iter->genmask)) + return 0; + + nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, elem_priv); return 0; @@ -5463,6 +5532,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; + nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); break; } @@ -5472,6 +5542,7 @@ static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, .fn = nft_mapelem_activate, }; @@ -5736,6 +5807,9 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; @@ -5846,6 +5920,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.skb = skb; args.reset = dump_ctx->reset; args.iter.genmask = nft_genmask_cur(net); + args.iter.type = NFT_ITER_READ; args.iter.skip = cb->args[0]; args.iter.count = 0; args.iter.err = 0; @@ -6585,7 +6660,7 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_setelem_is_catchall(set, elem_priv)) { - nft_set_elem_change_active(net, set, ext); + nft_clear(net, ext); } else { set->ops->activate(net, set, elem_priv); } @@ -7144,6 +7219,16 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) } } +static int nft_setelem_active_next(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + u8 genmask = nft_genmask_next(net); + + return nft_set_elem_active(ext, genmask); +} + static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) @@ -7267,8 +7352,12 @@ static int nft_setelem_flush(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_trans *trans; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, sizeof(struct nft_trans_elem), GFP_ATOMIC); if (!trans) @@ -7330,6 +7419,7 @@ static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { struct nft_set_iter iter = { .genmask = genmask, + .type = NFT_ITER_UPDATE, .fn = nft_setelem_flush, }; @@ -7565,7 +7655,7 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; - list_for_each_entry(type, &nf_tables_objects, list) { + list_for_each_entry_rcu(type, &nf_tables_objects, list) { if (type->family != NFPROTO_UNSPEC && type->family != family) continue; @@ -7581,9 +7671,13 @@ nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; + rcu_read_lock(); type = __nft_obj_type_get(objtype, family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -8255,11 +8349,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, return err; } +/* call under rcu_read_lock */ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family) { const struct nf_flowtable_type *type; - list_for_each_entry(type, &nf_tables_flowtables, list) { + list_for_each_entry_rcu(type, &nf_tables_flowtables, list) { if (family == type->family) return type; } @@ -8271,9 +8366,13 @@ nft_flowtable_type_get(struct net *net, u8 family) { const struct nf_flowtable_type *type; + rcu_read_lock(); type = __nft_flowtable_type_get(family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -10174,9 +10273,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) if (nft_trans_chain_update(trans)) { nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, &nft_trans_chain_hooks(trans)); - nft_netdev_unregister_hooks(net, - &nft_trans_chain_hooks(trans), - true); + if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) { + nft_netdev_unregister_hooks(net, + &nft_trans_chain_hooks(trans), + true); + } } else { nft_chain_del(trans->ctx.chain); nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, @@ -10415,10 +10516,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; + int err = 0; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) - return -EAGAIN; + err = -EAGAIN; list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { @@ -10448,9 +10550,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { - nft_netdev_unregister_hooks(net, - &nft_trans_chain_hooks(trans), - true); + if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) { + nft_netdev_unregister_hooks(net, + &nft_trans_chain_hooks(trans), + true); + } free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); @@ -10542,8 +10646,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_setelem_data_activate(net, te->set, te->elem_priv); - nft_setelem_activate(net, te->set, te->elem_priv); + if (!nft_setelem_active_next(net, te->set, te->elem_priv)) { + nft_setelem_data_activate(net, te->set, te->elem_priv); + nft_setelem_activate(net, te->set, te->elem_priv); + } if (!nft_setelem_is_catchall(te->set, te->elem_priv)) te->set->ndeact--; @@ -10604,12 +10710,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_abort_release(trans); } - if (action == NFNL_ABORT_AUTOLOAD) - nf_tables_module_autoload(net); - else - nf_tables_module_autoload_cleanup(net); - - return 0; + return err; } static int nf_tables_abort(struct net *net, struct sk_buff *skb, @@ -10622,6 +10723,17 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb, gc_seq = nft_gc_seq_begin(nft_net); ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); + + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + /* module autoload needs to happen after GC sequence update because it + * temporarily releases and grabs mutex again. + */ + if (action == NFNL_ABORT_AUTOLOAD) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + mutex_unlock(&nft_net->commit_mutex); return ret; @@ -10725,6 +10837,9 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; @@ -10809,6 +10924,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, continue; iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; @@ -11423,9 +11539,10 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); - if (!list_empty(&nft_net->commit_list) || - !list_empty(&nft_net->module_list)) - __nf_tables_abort(net, NFNL_ABORT_NONE); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + if (!list_empty(&nft_net->module_list)) + nf_tables_module_autoload_cleanup(net); __nft_release_tables(net); @@ -11517,6 +11634,7 @@ static void __exit nf_tables_module_exit(void) unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); + nf_tables_trans_destroy_flush_work(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5cf38fc0a366a..5845810378fe8 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -169,7 +169,9 @@ instance_destroy_rcu(struct rcu_head *head) struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance, rcu); + rcu_read_lock(); nfqnl_flush(inst, NULL, 0); + rcu_read_unlock(); kfree(inst); module_put(THIS_MODULE); } @@ -326,18 +328,18 @@ static int nfqnl_put_sk_classid(struct sk_buff *skb, struct sock *sk) return 0; } -static u32 nfqnl_get_sk_secctx(struct sk_buff *skb, char **secdata) +static u32 nfqnl_get_sk_secctx(struct sk_buff *skb, struct lsmcontext *ctx) { u32 seclen = 0; #if IS_ENABLED(CONFIG_NETWORK_SECMARK) + if (!skb || !sk_fullsock(skb->sk)) return 0; read_lock_bh(&skb->sk->sk_callback_lock); if (skb->secmark) - security_secid_to_secctx(skb->secmark, secdata, &seclen); - + seclen = security_secid_to_secctx(skb->secmark, ctx); read_unlock_bh(&skb->sk->sk_callback_lock); #endif return seclen; @@ -415,7 +417,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, enum ip_conntrack_info ctinfo = 0; const struct nfnl_ct_hook *nfnl_ct; bool csum_verify; - char *secdata = NULL; + struct lsmcontext ctx; u32 seclen = 0; ktime_t tstamp; @@ -490,8 +492,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, } if ((queue->flags & NFQA_CFG_F_SECCTX) && entskb->sk) { - seclen = nfqnl_get_sk_secctx(entskb, &secdata); - if (seclen) + seclen = nfqnl_get_sk_secctx(entskb, &ctx); + if (seclen >= 0) size += nla_total_size(seclen); } @@ -630,7 +632,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (nfqnl_put_sk_classid(skb, entskb->sk) < 0) goto nla_put_failure; - if (seclen && nla_put(skb, NFQA_SECCTX, seclen, secdata)) + if (seclen && nla_put(skb, NFQA_SECCTX, ctx.len, ctx.context)) goto nla_put_failure; if (ct && nfnl_ct->build(skb, ct, ctinfo, NFQA_CT, NFQA_CT_INFO) < 0) @@ -658,8 +660,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, } nlh->nlmsg_len = skb->len; - if (seclen) - security_release_secctx(secdata, seclen); + if (seclen >= 0) + security_release_secctx(&ctx); return skb; nla_put_failure: @@ -667,8 +669,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); nlmsg_failure: - if (seclen) - security_release_secctx(secdata, seclen); + if (seclen >= 0) + security_release_secctx(&ctx); return NULL; } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 274b6f7e6bb57..d170758a1eb5d 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -338,7 +338,9 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, return; if (n > 1) { - nf_unregister_net_hook(ctx->net, &found->ops); + if (!(ctx->chain->table->flags & NFT_TABLE_F_DORMANT)) + nf_unregister_net_hook(ctx->net, &found->ops); + list_del_rcu(&found->list); kfree_rcu(found, rcu); return; diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 37cfe6dd712d8..b58f62195ff3e 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -35,11 +35,9 @@ int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: - hooks = (1 << NF_INET_PRE_ROUTING); - if (priv->flags & NFTA_FIB_F_IIF) { - hooks |= (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_FORWARD); - } + hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD); break; case NFT_FIB_RESULT_ADDRTYPE: if (priv->flags & NFTA_FIB_F_IIF) diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 870e5b113d13e..87c18eddb0689 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -216,6 +216,7 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, return 0; iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index ba0d3683a45d3..9139ce38ea7b9 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -839,6 +839,9 @@ static int nft_meta_inner_init(const struct nft_ctx *ctx, struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; + if (!tb[NFTA_META_KEY] || !tb[NFTA_META_DREG]) + return -EINVAL; + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_PROTOCOL: diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 0a689c8e0295d..50429cbd42da4 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -45,36 +45,27 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) int mac_off = skb_mac_header(skb) - skb->data; u8 *vlanh, *dst_u8 = (u8 *) d; struct vlan_ethhdr veth; - u8 vlan_hlen = 0; - - if ((skb->protocol == htons(ETH_P_8021AD) || - skb->protocol == htons(ETH_P_8021Q)) && - offset >= VLAN_ETH_HLEN && offset < VLAN_ETH_HLEN + VLAN_HLEN) - vlan_hlen += VLAN_HLEN; vlanh = (u8 *) &veth; - if (offset < VLAN_ETH_HLEN + vlan_hlen) { + if (offset < VLAN_ETH_HLEN) { u8 ethlen = len; - if (vlan_hlen && - skb_copy_bits(skb, mac_off, &veth, VLAN_ETH_HLEN) < 0) - return false; - else if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth)) + if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth)) return false; - if (offset + len > VLAN_ETH_HLEN + vlan_hlen) - ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen; + if (offset + len > VLAN_ETH_HLEN) + ethlen -= offset + len - VLAN_ETH_HLEN; - memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen); + memcpy(dst_u8, vlanh + offset, ethlen); len -= ethlen; if (len == 0) return true; dst_u8 += ethlen; - offset = ETH_HLEN + vlan_hlen; + offset = ETH_HLEN; } else { - offset -= VLAN_HLEN + vlan_hlen; + offset -= VLAN_HLEN; } return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; @@ -154,12 +145,12 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt) return pkt->inneroff; } -static bool nft_payload_need_vlan_copy(const struct nft_payload *priv) +static bool nft_payload_need_vlan_adjust(u32 offset, u32 len) { - unsigned int len = priv->offset + priv->len; + unsigned int boundary = offset + len; /* data past ether src/dst requested, copy needed */ - if (len > offsetof(struct ethhdr, h_proto)) + if (boundary > offsetof(struct ethhdr, h_proto)) return true; return false; @@ -183,7 +174,7 @@ void nft_payload_eval(const struct nft_expr *expr, goto err; if (skb_vlan_tag_present(skb) && - nft_payload_need_vlan_copy(priv)) { + nft_payload_need_vlan_adjust(priv->offset, priv->len)) { if (!nft_payload_copy_vlan(dest, skb, priv->offset, priv->len)) goto err; @@ -659,6 +650,10 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx, struct nft_payload *priv = nft_expr_priv(expr); u32 base; + if (!tb[NFTA_PAYLOAD_BASE] || !tb[NFTA_PAYLOAD_OFFSET] || + !tb[NFTA_PAYLOAD_LEN] || !tb[NFTA_PAYLOAD_DREG]) + return -EINVAL; + base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); switch (base) { case NFT_PAYLOAD_TUN_HEADER: @@ -810,21 +805,79 @@ struct nft_payload_set { u8 csum_flags; }; +/* This is not struct vlan_hdr. */ +struct nft_payload_vlan_hdr { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; +}; + +static bool +nft_payload_set_vlan(const u32 *src, struct sk_buff *skb, u8 offset, u8 len, + int *vlan_hlen) +{ + struct nft_payload_vlan_hdr *vlanh; + __be16 vlan_proto; + u16 vlan_tci; + + if (offset >= offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto)) { + *vlan_hlen = VLAN_HLEN; + return true; + } + + switch (offset) { + case offsetof(struct vlan_ethhdr, h_vlan_proto): + if (len == 2) { + vlan_proto = nft_reg_load_be16(src); + skb->vlan_proto = vlan_proto; + } else if (len == 4) { + vlanh = (struct nft_payload_vlan_hdr *)src; + __vlan_hwaccel_put_tag(skb, vlanh->h_vlan_proto, + ntohs(vlanh->h_vlan_TCI)); + } else { + return false; + } + break; + case offsetof(struct vlan_ethhdr, h_vlan_TCI): + if (len != 2) + return false; + + vlan_tci = ntohs(nft_reg_load_be16(src)); + skb->vlan_tci = vlan_tci; + break; + default: + return false; + } + + return true; +} + static void nft_payload_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_payload_set *priv = nft_expr_priv(expr); - struct sk_buff *skb = pkt->skb; const u32 *src = ®s->data[priv->sreg]; - int offset, csum_offset; + int offset, csum_offset, vlan_hlen = 0; + struct sk_buff *skb = pkt->skb; __wsum fsum, tsum; switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: if (!skb_mac_header_was_set(skb)) goto err; - offset = skb_mac_header(skb) - skb->data; + + if (skb_vlan_tag_present(skb) && + nft_payload_need_vlan_adjust(priv->offset, priv->len)) { + if (!nft_payload_set_vlan(src, skb, + priv->offset, priv->len, + &vlan_hlen)) + goto err; + + if (!vlan_hlen) + return; + } + + offset = skb_mac_header(skb) - skb->data - vlan_hlen; break; case NFT_PAYLOAD_NETWORK_HEADER: offset = skb_network_offset(skb); diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 24d9771385729..14d88394bcb7f 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -73,14 +73,14 @@ void nft_rt_get_eval(const struct nft_expr *expr, if (nft_pf(pkt) != NFPROTO_IPV4) goto err; - *dest = (__force u32)rt_nexthop((const struct rtable *)dst, + *dest = (__force u32)rt_nexthop(dst_rtable(dst), ip_hdr(skb)->daddr); break; case NFT_RT_NEXTHOP6: if (nft_pf(pkt) != NFPROTO_IPV6) goto err; - memcpy(dest, rt6_nexthop((struct rt6_info *)dst, + memcpy(dest, rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr), sizeof(struct in6_addr)); break; diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 32df7a16835da..1caa04619dc6d 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -172,7 +172,7 @@ static void nft_bitmap_activate(const struct net *net, nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 11 state. */ priv->bitmap[idx] |= (genmask << off); - nft_set_elem_change_active(net, set, &be->ext); + nft_clear(net, &be->ext); } static void nft_bitmap_flush(const struct net *net, @@ -222,8 +222,6 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, list_for_each_entry_rcu(be, &priv->list, head) { if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&be->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &be->priv); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6968a3b342367..daa56dda737ae 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -199,7 +199,7 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, { struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &he->ext); + nft_clear(net, &he->ext); } static void nft_rhash_flush(const struct net *net, @@ -286,8 +286,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) @@ -599,7 +597,7 @@ static void nft_hash_activate(const struct net *net, const struct nft_set *set, { struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &he->ext); + nft_clear(net, &he->ext); } static void nft_hash_flush(const struct net *net, @@ -652,8 +650,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, hlist_for_each_entry_rcu(he, &priv->table[i], node) { if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index aa1d9e93a9a04..b42a34087e807 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -360,7 +360,7 @@ * Return: -1 on no match, bit position on 'match_only', 0 otherwise. */ int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, - union nft_pipapo_map_bucket *mt, bool match_only) + const union nft_pipapo_map_bucket *mt, bool match_only) { unsigned long bitset; int k, ret = -1; @@ -412,9 +412,9 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; u8 genmask = nft_genmask_cur(net); + const struct nft_pipapo_match *m; + const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; - struct nft_pipapo_match *m; - struct nft_pipapo_field *f; bool map_index; int i; @@ -519,11 +519,13 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); struct nft_pipapo *priv = nft_set_priv(set); - struct nft_pipapo_match *m = priv->clone; unsigned long *res_map, *fill_map = NULL; - struct nft_pipapo_field *f; + const struct nft_pipapo_match *m; + const struct nft_pipapo_field *f; int i; + m = priv->clone; + res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), GFP_ATOMIC); if (!res_map) { ret = ERR_PTR(-ENOMEM); @@ -1597,7 +1599,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; - struct nft_pipapo_field *f; + const struct nft_pipapo_field *f; int i, start, rules_fx; start = first_rule; @@ -1771,7 +1773,7 @@ static void nft_pipapo_activate(const struct net *net, { struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &e->ext); + nft_clear(net, &e->ext); } /** @@ -2000,6 +2002,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -2012,16 +2016,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** @@ -2038,13 +2044,15 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_pipapo *priv = nft_set_priv(set); - struct net *net = read_pnet(&set->net); - struct nft_pipapo_match *m; - struct nft_pipapo_field *f; + const struct nft_pipapo_match *m; + const struct nft_pipapo_field *f; int i, r; + WARN_ON_ONCE(iter->type != NFT_ITER_READ && + iter->type != NFT_ITER_UPDATE); + rcu_read_lock(); - if (iter->genmask == nft_genmask_cur(net)) + if (iter->type == NFT_ITER_READ) m = rcu_dereference(priv->match); else m = priv->clone; @@ -2066,9 +2074,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; - if (!nft_set_elem_active(&e->ext, iter->genmask)) - goto cont; - iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) goto out; @@ -2244,8 +2249,6 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(ctx, set, m); - for_each_possible_cpu(cpu) pipapo_free_scratch(m, cpu); free_percpu(m->scratch); @@ -2257,8 +2260,7 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (priv->clone) { m = priv->clone; - if (priv->dirty) - nft_set_pipapo_match_destroy(ctx, set, m); + nft_set_pipapo_match_destroy(ctx, set, m); for_each_possible_cpu(cpu) pipapo_free_scratch(priv->clone, cpu); diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 3842c7341a9f4..42464e7c24ac0 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -187,7 +187,7 @@ struct nft_pipapo_elem { }; int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, - union nft_pipapo_map_bucket *mt, bool match_only); + const union nft_pipapo_map_bucket *mt, bool match_only); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets @@ -195,7 +195,7 @@ int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, * @dst: Area to store result * @data: Input data selecting table buckets */ -static inline void pipapo_and_field_buckets_4bit(struct nft_pipapo_field *f, +static inline void pipapo_and_field_buckets_4bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { @@ -223,7 +223,7 @@ static inline void pipapo_and_field_buckets_4bit(struct nft_pipapo_field *f, * @dst: Area to store result * @data: Input data selecting table buckets */ -static inline void pipapo_and_field_buckets_8bit(struct nft_pipapo_field *f, +static inline void pipapo_and_field_buckets_8bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index a3a8ddca99189..d08407d589eac 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -212,8 +212,9 @@ static int nft_pipapo_avx2_refill(int offset, unsigned long *map, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_2(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; u8 pg[2] = { pkt[0] >> 4, pkt[0] & 0xf }; @@ -274,8 +275,9 @@ static int nft_pipapo_avx2_lookup_4b_2(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_4(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; u8 pg[4] = { pkt[0] >> 4, pkt[0] & 0xf, pkt[1] >> 4, pkt[1] & 0xf }; @@ -350,8 +352,9 @@ static int nft_pipapo_avx2_lookup_4b_4(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_8(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { u8 pg[8] = { pkt[0] >> 4, pkt[0] & 0xf, pkt[1] >> 4, pkt[1] & 0xf, pkt[2] >> 4, pkt[2] & 0xf, pkt[3] >> 4, pkt[3] & 0xf, @@ -445,8 +448,9 @@ static int nft_pipapo_avx2_lookup_4b_8(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_12(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { u8 pg[12] = { pkt[0] >> 4, pkt[0] & 0xf, pkt[1] >> 4, pkt[1] & 0xf, pkt[2] >> 4, pkt[2] & 0xf, pkt[3] >> 4, pkt[3] & 0xf, @@ -534,8 +538,9 @@ static int nft_pipapo_avx2_lookup_4b_12(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_32(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { u8 pg[32] = { pkt[0] >> 4, pkt[0] & 0xf, pkt[1] >> 4, pkt[1] & 0xf, pkt[2] >> 4, pkt[2] & 0xf, pkt[3] >> 4, pkt[3] & 0xf, @@ -669,8 +674,9 @@ static int nft_pipapo_avx2_lookup_4b_32(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_1(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -726,8 +732,9 @@ static int nft_pipapo_avx2_lookup_8b_1(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_2(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -790,8 +797,9 @@ static int nft_pipapo_avx2_lookup_8b_2(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_4(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -865,8 +873,9 @@ static int nft_pipapo_avx2_lookup_8b_4(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -950,8 +959,9 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -1042,8 +1052,9 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { unsigned long bsize = f->bsize; int i, ret = -1, b; @@ -1119,9 +1130,9 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); + const struct nft_pipapo_match *m; + const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; - struct nft_pipapo_match *m; - struct nft_pipapo_field *f; unsigned long *res, *fill; bool map_index; int i, ret = 0; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 9944fe479e536..b7ea21327549b 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -532,7 +532,7 @@ static void nft_rbtree_activate(const struct net *net, { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &rbe->ext); + nft_clear(net, &rbe->ext); } static void nft_rbtree_flush(const struct net *net, @@ -600,8 +600,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&rbe->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { diff --git a/net/netfilter/xt_dscp.c b/net/netfilter/xt_dscp.c index fb0169a8f9bbd..cfa44515ab72d 100644 --- a/net/netfilter/xt_dscp.c +++ b/net/netfilter/xt_dscp.c @@ -1,8 +1,11 @@ // SPDX-License-Identifier: GPL-2.0-only -/* IP tables module for matching the value of the IPv4/IPv6 DSCP field +/* x_tables module for setting the IPv4/IPv6 DSCP field, Version 1.8 * * (C) 2002 by Harald Welte - */ + * based on ipt_FTOS.c (C) 2000 by Matthew G. Marsh + * + * See RFC2474 for a description of the DSCP field within the IP Header. +*/ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include @@ -11,100 +14,148 @@ #include #include -#include +#include MODULE_AUTHOR("Harald Welte "); -MODULE_DESCRIPTION("Xtables: DSCP/TOS field match"); +MODULE_DESCRIPTION("Xtables: DSCP/TOS field modification"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("ipt_dscp"); -MODULE_ALIAS("ip6t_dscp"); -MODULE_ALIAS("ipt_tos"); -MODULE_ALIAS("ip6t_tos"); +MODULE_ALIAS("ipt_DSCP"); +MODULE_ALIAS("ip6t_DSCP"); +MODULE_ALIAS("ipt_TOS"); +MODULE_ALIAS("ip6t_TOS"); + +#define XT_DSCP_ECN_MASK 3u -static bool -dscp_mt(const struct sk_buff *skb, struct xt_action_param *par) +static unsigned int +dscp_tg(struct sk_buff *skb, const struct xt_action_param *par) { - const struct xt_dscp_info *info = par->matchinfo; + const struct xt_DSCP_info *dinfo = par->targinfo; u_int8_t dscp = ipv4_get_dsfield(ip_hdr(skb)) >> XT_DSCP_SHIFT; - return (dscp == info->dscp) ^ !!info->invert; + if (dscp != dinfo->dscp) { + if (skb_ensure_writable(skb, sizeof(struct iphdr))) + return NF_DROP; + + ipv4_change_dsfield(ip_hdr(skb), XT_DSCP_ECN_MASK, + dinfo->dscp << XT_DSCP_SHIFT); + + } + return XT_CONTINUE; } -static bool -dscp_mt6(const struct sk_buff *skb, struct xt_action_param *par) +static unsigned int +dscp_tg6(struct sk_buff *skb, const struct xt_action_param *par) { - const struct xt_dscp_info *info = par->matchinfo; + const struct xt_DSCP_info *dinfo = par->targinfo; u_int8_t dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> XT_DSCP_SHIFT; - return (dscp == info->dscp) ^ !!info->invert; + if (dscp != dinfo->dscp) { + if (skb_ensure_writable(skb, sizeof(struct ipv6hdr))) + return NF_DROP; + + ipv6_change_dsfield(ipv6_hdr(skb), XT_DSCP_ECN_MASK, + dinfo->dscp << XT_DSCP_SHIFT); + } + return XT_CONTINUE; } -static int dscp_mt_check(const struct xt_mtchk_param *par) +static int dscp_tg_check(const struct xt_tgchk_param *par) { - const struct xt_dscp_info *info = par->matchinfo; + const struct xt_DSCP_info *info = par->targinfo; if (info->dscp > XT_DSCP_MAX) return -EDOM; - return 0; } -static bool tos_mt(const struct sk_buff *skb, struct xt_action_param *par) +static unsigned int +tos_tg(struct sk_buff *skb, const struct xt_action_param *par) { - const struct xt_tos_match_info *info = par->matchinfo; - - if (xt_family(par) == NFPROTO_IPV4) - return ((ip_hdr(skb)->tos & info->tos_mask) == - info->tos_value) ^ !!info->invert; - else - return ((ipv6_get_dsfield(ipv6_hdr(skb)) & info->tos_mask) == - info->tos_value) ^ !!info->invert; + const struct xt_tos_target_info *info = par->targinfo; + struct iphdr *iph = ip_hdr(skb); + u_int8_t orig, nv; + + orig = ipv4_get_dsfield(iph); + nv = (orig & ~info->tos_mask) ^ info->tos_value; + + if (orig != nv) { + if (skb_ensure_writable(skb, sizeof(struct iphdr))) + return NF_DROP; + iph = ip_hdr(skb); + ipv4_change_dsfield(iph, 0, nv); + } + + return XT_CONTINUE; +} + +static unsigned int +tos_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_tos_target_info *info = par->targinfo; + struct ipv6hdr *iph = ipv6_hdr(skb); + u_int8_t orig, nv; + + orig = ipv6_get_dsfield(iph); + nv = (orig & ~info->tos_mask) ^ info->tos_value; + + if (orig != nv) { + if (skb_ensure_writable(skb, sizeof(struct iphdr))) + return NF_DROP; + iph = ipv6_hdr(skb); + ipv6_change_dsfield(iph, 0, nv); + } + + return XT_CONTINUE; } -static struct xt_match dscp_mt_reg[] __read_mostly = { +static struct xt_target dscp_tg_reg[] __read_mostly = { { - .name = "dscp", + .name = "DSCP", .family = NFPROTO_IPV4, - .checkentry = dscp_mt_check, - .match = dscp_mt, - .matchsize = sizeof(struct xt_dscp_info), + .checkentry = dscp_tg_check, + .target = dscp_tg, + .targetsize = sizeof(struct xt_DSCP_info), + .table = "mangle", .me = THIS_MODULE, }, { - .name = "dscp", + .name = "DSCP", .family = NFPROTO_IPV6, - .checkentry = dscp_mt_check, - .match = dscp_mt6, - .matchsize = sizeof(struct xt_dscp_info), + .checkentry = dscp_tg_check, + .target = dscp_tg6, + .targetsize = sizeof(struct xt_DSCP_info), + .table = "mangle", .me = THIS_MODULE, }, { - .name = "tos", + .name = "TOS", .revision = 1, .family = NFPROTO_IPV4, - .match = tos_mt, - .matchsize = sizeof(struct xt_tos_match_info), + .table = "mangle", + .target = tos_tg, + .targetsize = sizeof(struct xt_tos_target_info), .me = THIS_MODULE, }, { - .name = "tos", + .name = "TOS", .revision = 1, .family = NFPROTO_IPV6, - .match = tos_mt, - .matchsize = sizeof(struct xt_tos_match_info), + .table = "mangle", + .target = tos_tg6, + .targetsize = sizeof(struct xt_tos_target_info), .me = THIS_MODULE, }, }; -static int __init dscp_mt_init(void) +static int __init dscp_tg_init(void) { - return xt_register_matches(dscp_mt_reg, ARRAY_SIZE(dscp_mt_reg)); + return xt_register_targets(dscp_tg_reg, ARRAY_SIZE(dscp_tg_reg)); } -static void __exit dscp_mt_exit(void) +static void __exit dscp_tg_exit(void) { - xt_unregister_matches(dscp_mt_reg, ARRAY_SIZE(dscp_mt_reg)); + xt_unregister_targets(dscp_tg_reg, ARRAY_SIZE(dscp_tg_reg)); } -module_init(dscp_mt_init); -module_exit(dscp_mt_exit); +module_init(dscp_tg_init); +module_exit(dscp_tg_exit); diff --git a/net/netfilter/xt_hl.c b/net/netfilter/xt_hl.c index c1a70f8f04417..7873b834c3004 100644 --- a/net/netfilter/xt_hl.c +++ b/net/netfilter/xt_hl.c @@ -1,93 +1,159 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * IP tables module for matching the value of the TTL - * (C) 2000,2001 by Harald Welte + * TTL modification target for IP tables + * (C) 2000,2005 by Harald Welte * - * Hop Limit matching module - * (C) 2001-2002 Maciej Soltysiak + * Hop Limit modification target for ip6tables + * Maciej Soltysiak */ - -#include -#include +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include +#include +#include +#include #include -#include -#include +#include +#include +MODULE_AUTHOR("Harald Welte "); MODULE_AUTHOR("Maciej Soltysiak "); -MODULE_DESCRIPTION("Xtables: Hoplimit/TTL field match"); +MODULE_DESCRIPTION("Xtables: Hoplimit/TTL Limit field modification target"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("ipt_ttl"); -MODULE_ALIAS("ip6t_hl"); -static bool ttl_mt(const struct sk_buff *skb, struct xt_action_param *par) +static unsigned int +ttl_tg(struct sk_buff *skb, const struct xt_action_param *par) { - const struct ipt_ttl_info *info = par->matchinfo; - const u8 ttl = ip_hdr(skb)->ttl; + struct iphdr *iph; + const struct ipt_TTL_info *info = par->targinfo; + int new_ttl; + + if (skb_ensure_writable(skb, sizeof(*iph))) + return NF_DROP; + + iph = ip_hdr(skb); switch (info->mode) { - case IPT_TTL_EQ: - return ttl == info->ttl; - case IPT_TTL_NE: - return ttl != info->ttl; - case IPT_TTL_LT: - return ttl < info->ttl; - case IPT_TTL_GT: - return ttl > info->ttl; + case IPT_TTL_SET: + new_ttl = info->ttl; + break; + case IPT_TTL_INC: + new_ttl = iph->ttl + info->ttl; + if (new_ttl > 255) + new_ttl = 255; + break; + case IPT_TTL_DEC: + new_ttl = iph->ttl - info->ttl; + if (new_ttl < 0) + new_ttl = 0; + break; + default: + new_ttl = iph->ttl; + break; } - return false; + if (new_ttl != iph->ttl) { + csum_replace2(&iph->check, htons(iph->ttl << 8), + htons(new_ttl << 8)); + iph->ttl = new_ttl; + } + + return XT_CONTINUE; } -static bool hl_mt6(const struct sk_buff *skb, struct xt_action_param *par) +static unsigned int +hl_tg6(struct sk_buff *skb, const struct xt_action_param *par) { - const struct ip6t_hl_info *info = par->matchinfo; - const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct ipv6hdr *ip6h; + const struct ip6t_HL_info *info = par->targinfo; + int new_hl; + + if (skb_ensure_writable(skb, sizeof(*ip6h))) + return NF_DROP; + + ip6h = ipv6_hdr(skb); switch (info->mode) { - case IP6T_HL_EQ: - return ip6h->hop_limit == info->hop_limit; - case IP6T_HL_NE: - return ip6h->hop_limit != info->hop_limit; - case IP6T_HL_LT: - return ip6h->hop_limit < info->hop_limit; - case IP6T_HL_GT: - return ip6h->hop_limit > info->hop_limit; + case IP6T_HL_SET: + new_hl = info->hop_limit; + break; + case IP6T_HL_INC: + new_hl = ip6h->hop_limit + info->hop_limit; + if (new_hl > 255) + new_hl = 255; + break; + case IP6T_HL_DEC: + new_hl = ip6h->hop_limit - info->hop_limit; + if (new_hl < 0) + new_hl = 0; + break; + default: + new_hl = ip6h->hop_limit; + break; } - return false; + ip6h->hop_limit = new_hl; + + return XT_CONTINUE; +} + +static int ttl_tg_check(const struct xt_tgchk_param *par) +{ + const struct ipt_TTL_info *info = par->targinfo; + + if (info->mode > IPT_TTL_MAXMODE) + return -EINVAL; + if (info->mode != IPT_TTL_SET && info->ttl == 0) + return -EINVAL; + return 0; +} + +static int hl_tg6_check(const struct xt_tgchk_param *par) +{ + const struct ip6t_HL_info *info = par->targinfo; + + if (info->mode > IP6T_HL_MAXMODE) + return -EINVAL; + if (info->mode != IP6T_HL_SET && info->hop_limit == 0) + return -EINVAL; + return 0; } -static struct xt_match hl_mt_reg[] __read_mostly = { +static struct xt_target hl_tg_reg[] __read_mostly = { { - .name = "ttl", + .name = "TTL", .revision = 0, .family = NFPROTO_IPV4, - .match = ttl_mt, - .matchsize = sizeof(struct ipt_ttl_info), + .target = ttl_tg, + .targetsize = sizeof(struct ipt_TTL_info), + .table = "mangle", + .checkentry = ttl_tg_check, .me = THIS_MODULE, }, { - .name = "hl", + .name = "HL", .revision = 0, .family = NFPROTO_IPV6, - .match = hl_mt6, - .matchsize = sizeof(struct ip6t_hl_info), + .target = hl_tg6, + .targetsize = sizeof(struct ip6t_HL_info), + .table = "mangle", + .checkentry = hl_tg6_check, .me = THIS_MODULE, }, }; -static int __init hl_mt_init(void) +static int __init hl_tg_init(void) { - return xt_register_matches(hl_mt_reg, ARRAY_SIZE(hl_mt_reg)); + return xt_register_targets(hl_tg_reg, ARRAY_SIZE(hl_tg_reg)); } -static void __exit hl_mt_exit(void) +static void __exit hl_tg_exit(void) { - xt_unregister_matches(hl_mt_reg, ARRAY_SIZE(hl_mt_reg)); + xt_unregister_targets(hl_tg_reg, ARRAY_SIZE(hl_tg_reg)); } -module_init(hl_mt_init); -module_exit(hl_mt_exit); +module_init(hl_tg_init); +module_exit(hl_tg_exit); +MODULE_ALIAS("ipt_TTL"); +MODULE_ALIAS("ip6t_HL"); diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c index 72324bd976af8..80f6624e23554 100644 --- a/net/netfilter/xt_rateest.c +++ b/net/netfilter/xt_rateest.c @@ -5,149 +5,229 @@ #include #include #include +#include +#include +#include +#include +#include +#include +#include #include -#include +#include #include +#define RATEEST_HSIZE 16 -static bool -xt_rateest_mt(const struct sk_buff *skb, struct xt_action_param *par) +struct xt_rateest_net { + struct mutex hash_lock; + struct hlist_head hash[RATEEST_HSIZE]; +}; + +static unsigned int xt_rateest_id; + +static unsigned int jhash_rnd __read_mostly; + +static unsigned int xt_rateest_hash(const char *name) { - const struct xt_rateest_match_info *info = par->matchinfo; - struct gnet_stats_rate_est64 sample = {0}; - u_int32_t bps1, bps2, pps1, pps2; - bool ret = true; - - gen_estimator_read(&info->est1->rate_est, &sample); - - if (info->flags & XT_RATEEST_MATCH_DELTA) { - bps1 = info->bps1 >= sample.bps ? info->bps1 - sample.bps : 0; - pps1 = info->pps1 >= sample.pps ? info->pps1 - sample.pps : 0; - } else { - bps1 = sample.bps; - pps1 = sample.pps; - } + return jhash(name, sizeof_field(struct xt_rateest, name), jhash_rnd) & + (RATEEST_HSIZE - 1); +} + +static void xt_rateest_hash_insert(struct xt_rateest_net *xn, + struct xt_rateest *est) +{ + unsigned int h; + + h = xt_rateest_hash(est->name); + hlist_add_head(&est->list, &xn->hash[h]); +} - if (info->flags & XT_RATEEST_MATCH_ABS) { - bps2 = info->bps2; - pps2 = info->pps2; - } else { - gen_estimator_read(&info->est2->rate_est, &sample); - - if (info->flags & XT_RATEEST_MATCH_DELTA) { - bps2 = info->bps2 >= sample.bps ? info->bps2 - sample.bps : 0; - pps2 = info->pps2 >= sample.pps ? info->pps2 - sample.pps : 0; - } else { - bps2 = sample.bps; - pps2 = sample.pps; +static struct xt_rateest *__xt_rateest_lookup(struct xt_rateest_net *xn, + const char *name) +{ + struct xt_rateest *est; + unsigned int h; + + h = xt_rateest_hash(name); + hlist_for_each_entry(est, &xn->hash[h], list) { + if (strcmp(est->name, name) == 0) { + est->refcnt++; + return est; } } - switch (info->mode) { - case XT_RATEEST_MATCH_LT: - if (info->flags & XT_RATEEST_MATCH_BPS) - ret &= bps1 < bps2; - if (info->flags & XT_RATEEST_MATCH_PPS) - ret &= pps1 < pps2; - break; - case XT_RATEEST_MATCH_GT: - if (info->flags & XT_RATEEST_MATCH_BPS) - ret &= bps1 > bps2; - if (info->flags & XT_RATEEST_MATCH_PPS) - ret &= pps1 > pps2; - break; - case XT_RATEEST_MATCH_EQ: - if (info->flags & XT_RATEEST_MATCH_BPS) - ret &= bps1 == bps2; - if (info->flags & XT_RATEEST_MATCH_PPS) - ret &= pps1 == pps2; - break; - } + return NULL; +} - ret ^= info->flags & XT_RATEEST_MATCH_INVERT ? true : false; - return ret; +struct xt_rateest *xt_rateest_lookup(struct net *net, const char *name) +{ + struct xt_rateest_net *xn = net_generic(net, xt_rateest_id); + struct xt_rateest *est; + + mutex_lock(&xn->hash_lock); + est = __xt_rateest_lookup(xn, name); + mutex_unlock(&xn->hash_lock); + return est; } +EXPORT_SYMBOL_GPL(xt_rateest_lookup); -static int xt_rateest_mt_checkentry(const struct xt_mtchk_param *par) +void xt_rateest_put(struct net *net, struct xt_rateest *est) { - struct xt_rateest_match_info *info = par->matchinfo; - struct xt_rateest *est1, *est2; - int ret = -EINVAL; + struct xt_rateest_net *xn = net_generic(net, xt_rateest_id); + + mutex_lock(&xn->hash_lock); + if (--est->refcnt == 0) { + hlist_del(&est->list); + gen_kill_estimator(&est->rate_est); + /* + * gen_estimator est_timer() might access est->lock or bstats, + * wait a RCU grace period before freeing 'est' + */ + kfree_rcu(est, rcu); + } + mutex_unlock(&xn->hash_lock); +} +EXPORT_SYMBOL_GPL(xt_rateest_put); - if (hweight32(info->flags & (XT_RATEEST_MATCH_ABS | - XT_RATEEST_MATCH_REL)) != 1) - goto err1; +static unsigned int +xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_rateest_target_info *info = par->targinfo; + struct gnet_stats_basic_sync *stats = &info->est->bstats; - if (!(info->flags & (XT_RATEEST_MATCH_BPS | XT_RATEEST_MATCH_PPS))) - goto err1; + spin_lock_bh(&info->est->lock); + u64_stats_add(&stats->bytes, skb->len); + u64_stats_inc(&stats->packets); + spin_unlock_bh(&info->est->lock); - switch (info->mode) { - case XT_RATEEST_MATCH_EQ: - case XT_RATEEST_MATCH_LT: - case XT_RATEEST_MATCH_GT: - break; - default: - goto err1; + return XT_CONTINUE; +} + +static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) +{ + struct xt_rateest_net *xn = net_generic(par->net, xt_rateest_id); + struct xt_rateest_target_info *info = par->targinfo; + struct xt_rateest *est; + struct { + struct nlattr opt; + struct gnet_estimator est; + } cfg; + int ret; + + if (strnlen(info->name, sizeof(est->name)) >= sizeof(est->name)) + return -ENAMETOOLONG; + + net_get_random_once(&jhash_rnd, sizeof(jhash_rnd)); + + mutex_lock(&xn->hash_lock); + est = __xt_rateest_lookup(xn, info->name); + if (est) { + mutex_unlock(&xn->hash_lock); + /* + * If estimator parameters are specified, they must match the + * existing estimator. + */ + if ((!info->interval && !info->ewma_log) || + (info->interval != est->params.interval || + info->ewma_log != est->params.ewma_log)) { + xt_rateest_put(par->net, est); + return -EINVAL; + } + info->est = est; + return 0; } - ret = -ENOENT; - est1 = xt_rateest_lookup(par->net, info->name1); - if (!est1) + ret = -ENOMEM; + est = kzalloc(sizeof(*est), GFP_KERNEL); + if (!est) goto err1; - est2 = NULL; - if (info->flags & XT_RATEEST_MATCH_REL) { - est2 = xt_rateest_lookup(par->net, info->name2); - if (!est2) - goto err2; - } - - info->est1 = est1; - info->est2 = est2; + gnet_stats_basic_sync_init(&est->bstats); + strscpy(est->name, info->name, sizeof(est->name)); + spin_lock_init(&est->lock); + est->refcnt = 1; + est->params.interval = info->interval; + est->params.ewma_log = info->ewma_log; + + cfg.opt.nla_len = nla_attr_size(sizeof(cfg.est)); + cfg.opt.nla_type = TCA_STATS_RATE_EST; + cfg.est.interval = info->interval; + cfg.est.ewma_log = info->ewma_log; + + ret = gen_new_estimator(&est->bstats, NULL, &est->rate_est, + &est->lock, NULL, &cfg.opt); + if (ret < 0) + goto err2; + + info->est = est; + xt_rateest_hash_insert(xn, est); + mutex_unlock(&xn->hash_lock); return 0; err2: - xt_rateest_put(par->net, est1); + kfree(est); err1: + mutex_unlock(&xn->hash_lock); return ret; } -static void xt_rateest_mt_destroy(const struct xt_mtdtor_param *par) +static void xt_rateest_tg_destroy(const struct xt_tgdtor_param *par) { - struct xt_rateest_match_info *info = par->matchinfo; + struct xt_rateest_target_info *info = par->targinfo; - xt_rateest_put(par->net, info->est1); - if (info->est2) - xt_rateest_put(par->net, info->est2); + xt_rateest_put(par->net, info->est); } -static struct xt_match xt_rateest_mt_reg __read_mostly = { - .name = "rateest", +static struct xt_target xt_rateest_tg_reg __read_mostly = { + .name = "RATEEST", .revision = 0, .family = NFPROTO_UNSPEC, - .match = xt_rateest_mt, - .checkentry = xt_rateest_mt_checkentry, - .destroy = xt_rateest_mt_destroy, - .matchsize = sizeof(struct xt_rateest_match_info), - .usersize = offsetof(struct xt_rateest_match_info, est1), + .target = xt_rateest_tg, + .checkentry = xt_rateest_tg_checkentry, + .destroy = xt_rateest_tg_destroy, + .targetsize = sizeof(struct xt_rateest_target_info), + .usersize = offsetof(struct xt_rateest_target_info, est), .me = THIS_MODULE, }; -static int __init xt_rateest_mt_init(void) +static __net_init int xt_rateest_net_init(struct net *net) { - return xt_register_match(&xt_rateest_mt_reg); + struct xt_rateest_net *xn = net_generic(net, xt_rateest_id); + int i; + + mutex_init(&xn->hash_lock); + for (i = 0; i < ARRAY_SIZE(xn->hash); i++) + INIT_HLIST_HEAD(&xn->hash[i]); + return 0; } -static void __exit xt_rateest_mt_fini(void) +static struct pernet_operations xt_rateest_net_ops = { + .init = xt_rateest_net_init, + .id = &xt_rateest_id, + .size = sizeof(struct xt_rateest_net), +}; + +static int __init xt_rateest_tg_init(void) { - xt_unregister_match(&xt_rateest_mt_reg); + int err = register_pernet_subsys(&xt_rateest_net_ops); + + if (err) + return err; + return xt_register_target(&xt_rateest_tg_reg); } +static void __exit xt_rateest_tg_fini(void) +{ + xt_unregister_target(&xt_rateest_tg_reg); + unregister_pernet_subsys(&xt_rateest_net_ops); +} + + MODULE_AUTHOR("Patrick McHardy "); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("xtables rate estimator match"); -MODULE_ALIAS("ipt_rateest"); -MODULE_ALIAS("ip6t_rateest"); -module_init(xt_rateest_mt_init); -module_exit(xt_rateest_mt_fini); +MODULE_DESCRIPTION("Xtables: packet rate estimator"); +MODULE_ALIAS("ipt_RATEEST"); +MODULE_ALIAS("ip6t_RATEEST"); +module_init(xt_rateest_tg_init); +module_exit(xt_rateest_tg_fini); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 9996883bf2b78..b43cfb4fe4f18 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -374,8 +374,7 @@ int netlbl_unlhsh_add(struct net *net, struct net_device *dev; struct netlbl_unlhsh_iface *iface; struct audit_buffer *audit_buf = NULL; - char *secctx = NULL; - u32 secctx_len; + struct lsmcontext ctx; if (addr_len != sizeof(struct in_addr) && addr_len != sizeof(struct in6_addr)) @@ -438,11 +437,9 @@ int netlbl_unlhsh_add(struct net *net, unlhsh_add_return: rcu_read_unlock(); if (audit_buf != NULL) { - if (security_secid_to_secctx(secid, - &secctx, - &secctx_len) == 0) { - audit_log_format(audit_buf, " sec_obj=%s", secctx); - security_release_secctx(secctx, secctx_len); + if (security_secid_to_secctx(secid, &ctx) >= 0) { + audit_log_format(audit_buf, " sec_obj=%s", ctx.context); + security_release_secctx(&ctx); } audit_log_format(audit_buf, " res=%u", ret_val == 0 ? 1 : 0); audit_log_end(audit_buf); @@ -473,8 +470,7 @@ static int netlbl_unlhsh_remove_addr4(struct net *net, struct netlbl_unlhsh_addr4 *entry; struct audit_buffer *audit_buf; struct net_device *dev; - char *secctx; - u32 secctx_len; + struct lsmcontext ctx; spin_lock(&netlbl_unlhsh_lock); list_entry = netlbl_af4list_remove(addr->s_addr, mask->s_addr, @@ -494,10 +490,9 @@ static int netlbl_unlhsh_remove_addr4(struct net *net, addr->s_addr, mask->s_addr); dev_put(dev); if (entry != NULL && - security_secid_to_secctx(entry->secid, - &secctx, &secctx_len) == 0) { - audit_log_format(audit_buf, " sec_obj=%s", secctx); - security_release_secctx(secctx, secctx_len); + security_secid_to_secctx(entry->secid, &ctx) >= 0) { + audit_log_format(audit_buf, " sec_obj=%s", ctx.context); + security_release_secctx(&ctx); } audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0); audit_log_end(audit_buf); @@ -534,8 +529,7 @@ static int netlbl_unlhsh_remove_addr6(struct net *net, struct netlbl_unlhsh_addr6 *entry; struct audit_buffer *audit_buf; struct net_device *dev; - char *secctx; - u32 secctx_len; + struct lsmcontext ctx; spin_lock(&netlbl_unlhsh_lock); list_entry = netlbl_af6list_remove(addr, mask, &iface->addr6_list); @@ -554,10 +548,9 @@ static int netlbl_unlhsh_remove_addr6(struct net *net, addr, mask); dev_put(dev); if (entry != NULL && - security_secid_to_secctx(entry->secid, - &secctx, &secctx_len) == 0) { - audit_log_format(audit_buf, " sec_obj=%s", secctx); - security_release_secctx(secctx, secctx_len); + security_secid_to_secctx(entry->secid, &ctx) >= 0) { + audit_log_format(audit_buf, " sec_obj=%s", ctx.context); + security_release_secctx(&ctx); } audit_log_format(audit_buf, " res=%u", entry != NULL ? 1 : 0); audit_log_end(audit_buf); @@ -1069,10 +1062,9 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd, int ret_val = -ENOMEM; struct netlbl_unlhsh_walk_arg *cb_arg = arg; struct net_device *dev; + struct lsmcontext ctx; void *data; u32 secid; - char *secctx; - u32 secctx_len; data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_unlabel_gnl_family, @@ -1127,14 +1119,14 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd, secid = addr6->secid; } - ret_val = security_secid_to_secctx(secid, &secctx, &secctx_len); - if (ret_val != 0) + ret_val = security_secid_to_secctx(secid, &ctx); + if (ret_val < 0) goto list_cb_failure; ret_val = nla_put(cb_arg->skb, NLBL_UNLABEL_A_SECCTX, - secctx_len, - secctx); - security_release_secctx(secctx, secctx_len); + ctx.len, + ctx.context); + security_release_secctx(&ctx); if (ret_val != 0) goto list_cb_failure; @@ -1538,7 +1530,7 @@ int __init netlbl_unlabel_defconf(void) /* Only the kernel is allowed to call this function and the only time * it is called is at bootup before the audit subsystem is reporting * messages so don't worry to much about these values. */ - security_current_getsecid_subj(&audit_info.secid); + security_current_getlsmblob_subj(&audit_info.blob); audit_info.loginuid = GLOBAL_ROOT_UID; audit_info.sessionid = 0; diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c index 3ed4fea2a2de3..4dd0f453bb4e9 100644 --- a/net/netlabel/netlabel_user.c +++ b/net/netlabel/netlabel_user.c @@ -84,8 +84,6 @@ struct audit_buffer *netlbl_audit_start_common(int type, struct netlbl_audit *audit_info) { struct audit_buffer *audit_buf; - char *secctx; - u32 secctx_len; if (audit_enabled == AUDIT_OFF) return NULL; @@ -98,13 +96,7 @@ struct audit_buffer *netlbl_audit_start_common(int type, from_kuid(&init_user_ns, audit_info->loginuid), audit_info->sessionid); - if (audit_info->secid != 0 && - security_secid_to_secctx(audit_info->secid, - &secctx, - &secctx_len) == 0) { - audit_log_format(audit_buf, " subj=%s", secctx); - security_release_secctx(secctx, secctx_len); - } + audit_log_subject_context(audit_buf, &audit_info->blob); return audit_buf; } diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index d6c5b31eb4eb8..1a9639005d098 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -32,7 +32,7 @@ */ static inline void netlbl_netlink_auditinfo(struct netlbl_audit *audit_info) { - security_current_getsecid_subj(&audit_info->secid); + security_current_getlsmblob_subj(&audit_info->blob); audit_info->loginuid = audit_get_loginuid(current); audit_info->sessionid = audit_get_sessionid(current); } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 70480869ad1c5..bd2b17b219ae9 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -285,22 +285,14 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, return 0; } -static inline void __nr_remove_node(struct nr_node *nr_node) +static void nr_remove_node_locked(struct nr_node *nr_node) { + lockdep_assert_held(&nr_node_list_lock); + hlist_del_init(&nr_node->node_node); nr_node_put(nr_node); } -#define nr_remove_node_locked(__node) \ - __nr_remove_node(__node) - -static void nr_remove_node(struct nr_node *nr_node) -{ - spin_lock_bh(&nr_node_list_lock); - __nr_remove_node(nr_node); - spin_unlock_bh(&nr_node_list_lock); -} - static inline void __nr_remove_neigh(struct nr_neigh *nr_neigh) { hlist_del_init(&nr_neigh->neigh_node); @@ -339,6 +331,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n return -EINVAL; } + spin_lock_bh(&nr_node_list_lock); nr_node_lock(nr_node); for (i = 0; i < nr_node->count; i++) { if (nr_node->routes[i].neighbour == nr_neigh) { @@ -352,7 +345,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n nr_node->count--; if (nr_node->count == 0) { - nr_remove_node(nr_node); + nr_remove_node_locked(nr_node); } else { switch (i) { case 0: @@ -367,12 +360,14 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n nr_node_put(nr_node); } nr_node_unlock(nr_node); + spin_unlock_bh(&nr_node_list_lock); return 0; } } nr_neigh_put(nr_neigh); nr_node_unlock(nr_node); + spin_unlock_bh(&nr_node_list_lock); nr_node_put(nr_node); return -EINVAL; diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 4e7c968cde2dc..5e3ca068f04e0 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,7 +121,8 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { - sock_hold(sk); + if (sk->sk_state == TCP_LISTEN) + sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); goto out; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 819157bbb5a2c..d5344563e525c 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -252,10 +252,10 @@ static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = copy_safe_from_sockptr(&opt, sizeof(opt), + optval, optlen); + if (err) break; - } if (opt > LLCP_MAX_RW) { err = -EINVAL; @@ -274,10 +274,10 @@ static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = copy_safe_from_sockptr(&opt, sizeof(opt), + optval, optlen); + if (err) break; - } if (opt > LLCP_MAX_MIUX) { err = -EINVAL; diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index cdad47b140fa4..f456a5911e7d1 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1463,6 +1463,19 @@ int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode, ndev->ops->n_core_ops); } +static bool nci_valid_size(struct sk_buff *skb) +{ + BUILD_BUG_ON(NCI_CTRL_HDR_SIZE != NCI_DATA_HDR_SIZE); + unsigned int hdr_size = NCI_CTRL_HDR_SIZE; + + if (skb->len < hdr_size || + !nci_plen(skb->data) || + skb->len < hdr_size + nci_plen(skb->data)) { + return false; + } + return true; +} + /* ---- NCI TX Data worker thread ---- */ static void nci_tx_work(struct work_struct *work) @@ -1516,6 +1529,11 @@ static void nci_rx_work(struct work_struct *work) nfc_send_to_raw_sock(ndev->nfc_dev, skb, RAW_PAYLOAD_NCI, NFC_DIRECTION_RX); + if (!nci_valid_size(skb)) { + kfree_skb(skb); + continue; + } + /* Process frame */ switch (nci_mt(skb->data)) { case NCI_MT_RSP_PKT: diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index f4a38bd6a7e04..bfb7758063f31 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,15 @@ EXPORT_SYMBOL_GPL(nsh_pop); static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { + unsigned int outer_hlen, mac_len, nsh_len; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; - unsigned int nsh_len, mac_len; - __be16 proto; + __be16 outer_proto, proto; skb_reset_network_header(skb); + outer_proto = skb->protocol; + outer_hlen = skb_mac_header_len(skb); mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -113,10 +115,10 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, } for (skb = segs; skb; skb = skb->next) { - skb->protocol = htons(ETH_P_NSH); - __skb_push(skb, nsh_len); - skb->mac_header = mac_offset; - skb->network_header = skb->mac_header + mac_len; + skb->protocol = outer_proto; + __skb_push(skb, nsh_len + outer_hlen); + skb_reset_mac_header(skb); + skb_set_network_header(skb, outer_hlen); skb->mac_len = mac_len; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 6fcd7e2ca81fe..9642255808247 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -936,6 +936,12 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, pskb_trim(skb, ovs_mac_header_len(key)); } + /* Need to set the pkt_type to involve the routing layer. The + * packet movement through the OVS datapath doesn't generally + * use routing, but this is needed for tunnel cases. + */ + skb->pkt_type = PACKET_OUTGOING; + if (likely(!mru || (skb->len <= mru + vport->dev->hard_header_len))) { ovs_vport_send(vport, skb, ovs_key_mac_proto(key)); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 3019a4406ca4f..2928c142a2ddb 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1380,8 +1380,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) - pr_info_ratelimited("Failed to associated timeout " - "policy `%s'\n", ct_info.timeout); + OVS_NLERR(log, + "Failed to associated timeout policy '%s'", + ct_info.timeout); else ct_info.nf_ct_timeout = rcu_dereference( nf_ct_timeout_find(ct_info.ct)->timeout); @@ -1592,9 +1593,9 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; + struct hlist_node *next; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node, - lockdep_ovsl_is_held()) + hlist_for_each_entry_safe(ct_limit, next, head, hlist_node) kfree_rcu(ct_limit, rcu); } kfree(info->limits); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 33b21a0c05481..8a848ce72e291 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -561,7 +561,6 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key, */ key->tp.src = htons(icmp->icmp6_type); key->tp.dst = htons(icmp->icmp6_code); - memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd)); if (icmp->icmp6_code == 0 && (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION || @@ -570,6 +569,8 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key, struct nd_msg *nd; int offset; + memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd)); + /* In order to process neighbor discovery options, we need the * entire packet. */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c9bbc26866907..a473b8e1a52ce 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2522,8 +2522,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb) ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); - if (!packet_read_pending(&po->tx_ring)) - complete(&po->skb_completion); + complete(&po->skb_completion); } sock_wfree(skb); @@ -3800,28 +3799,30 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, case PACKET_TX_RING: { union tpacket_req_u req_u; - int len; + ret = -EINVAL; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: - len = sizeof(req_u.req); + if (optlen < sizeof(req_u.req)) + break; + ret = copy_from_sockptr(&req_u.req, optval, + sizeof(req_u.req)) ? + -EINVAL : 0; break; case TPACKET_V3: default: - len = sizeof(req_u.req3); + if (optlen < sizeof(req_u.req3)) + break; + ret = copy_from_sockptr(&req_u.req3, optval, + sizeof(req_u.req3)) ? + -EINVAL : 0; break; } - if (optlen < len) { - ret = -EINVAL; - } else { - if (copy_from_sockptr(&req_u.req, optval, len)) - ret = -EFAULT; - else - ret = packet_set_ring(sk, &req_u, 0, - optname == PACKET_TX_RING); - } + if (!ret) + ret = packet_set_ring(sk, &req_u, 0, + optname == PACKET_TX_RING); release_sock(sk); return ret; } @@ -3998,7 +3999,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (val < 0 || val > 1) return -EINVAL; - po->prot_hook.ignore_outgoing = !!val; + WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: @@ -4129,7 +4130,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, 0); break; case PACKET_IGNORE_OUTGOING: - val = po->prot_hook.ignore_outgoing; + val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 59aebe2968907..dd4c7e9a634fb 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -193,7 +193,7 @@ void rtm_phonet_notify(int event, struct net_device *dev, u8 dst) struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(1) + nla_total_size(4), GFP_KERNEL); if (skb == NULL) goto errout; diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index abb0c70ffc8b0..654a3cc0d3479 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -725,6 +725,24 @@ int qrtr_ns_init(void) if (ret < 0) goto err_wq; + /* As the qrtr ns socket owner and creator is the same module, we have + * to decrease the qrtr module reference count to guarantee that it + * remains zero after the ns socket is created, otherwise, executing + * "rmmod" command is unable to make the qrtr module deleted after the + * qrtr module is inserted successfully. + * + * However, the reference count is increased twice in + * sock_create_kern(): one is to increase the reference count of owner + * of qrtr socket's proto_ops struct; another is to increment the + * reference count of owner of qrtr proto struct. Therefore, we must + * decrement the module reference count twice to ensure that it keeps + * zero after server's listening socket is created. Of course, we + * must bump the module reference count twice as well before the socket + * is closed. + */ + module_put(qrtr_ns.sock->ops->owner); + module_put(qrtr_ns.sock->sk->sk_prot_creator->owner); + return 0; err_wq: @@ -739,6 +757,15 @@ void qrtr_ns_remove(void) { cancel_work_sync(&qrtr_ns.work); destroy_workqueue(qrtr_ns.workqueue); + + /* sock_release() expects the two references that were put during + * qrtr_ns_init(). This function is only called during module remove, + * so try_stop_module() has already set the refcnt to 0. Use + * __module_get() instead of try_module_get() to successfully take two + * references. + */ + __module_get(qrtr_ns.sock->ops->owner); + __module_get(qrtr_ns.sock->sk->sk_prot_creator->owner); sock_release(qrtr_ns.sock); } EXPORT_SYMBOL_GPL(qrtr_ns_remove); diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 4190b90ff3b18..2f57869e64d1b 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -503,7 +503,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, int flow_controlled = 0; int nr_sig = 0; - BUG_ON(off % RDS_FRAG_SIZE); + BUG_ON(!conn->c_loopback && off % RDS_FRAG_SIZE); BUG_ON(hdr_off != 0 && hdr_off != sizeof(struct rds_header)); /* Do not send cong updates to IB loopback */ diff --git a/net/rds/rdma.c b/net/rds/rdma.c index a4e3c5de998be..00dbcd4d28e68 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -302,7 +302,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, } ret = PTR_ERR(trans_private); /* Trigger connection so that its ready for the next retry */ - if (ret == -ENODEV) + if (ret == -ENODEV && cp) rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/rds/send.c b/net/rds/send.c index 2899def23865f..09a2801106549 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset); static int acquire_in_xmit(struct rds_conn_path *cp) { - return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0; + return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0; } static void release_in_xmit(struct rds_conn_path *cp) { - clear_bit(RDS_IN_XMIT, &cp->cp_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); /* * We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk diff --git a/net/rfkill/core.c b/net/rfkill/core.c index c3feb4f49d09c..4a18bc7142ddb 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -79,7 +79,6 @@ struct rfkill_data { struct mutex mtx; wait_queue_head_t read_wait; bool input_handler; - u8 max_size; }; @@ -1173,8 +1172,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) if (!data) return -ENOMEM; - data->max_size = RFKILL_EVENT_SIZE_V1; - INIT_LIST_HEAD(&data->events); mutex_init(&data->mtx); init_waitqueue_head(&data->read_wait); @@ -1257,7 +1254,6 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, list); sz = min_t(unsigned long, sizeof(ev->ev), count); - sz = min_t(unsigned long, sz, data->max_size); ret = sz; if (copy_to_user(buf, &ev->ev, sz)) ret = -EFAULT; @@ -1272,7 +1268,6 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct rfkill_data *data = file->private_data; struct rfkill *rfkill; struct rfkill_event_ext ev; int ret; @@ -1287,7 +1282,6 @@ static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, * our API version even in a write() call, if it cares. */ count = min(count, sizeof(ev)); - count = min_t(size_t, count, data->max_size); if (copy_from_user(&ev, buf, count)) return -EFAULT; @@ -1347,47 +1341,31 @@ static int rfkill_fop_release(struct inode *inode, struct file *file) return 0; } +#ifdef CONFIG_RFKILL_INPUT static long rfkill_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct rfkill_data *data = file->private_data; - int ret = -ENOTTY; - u32 size; if (_IOC_TYPE(cmd) != RFKILL_IOC_MAGIC) return -ENOTTY; + if (_IOC_NR(cmd) != RFKILL_IOC_NOINPUT) + return -ENOSYS; + mutex_lock(&data->mtx); - switch (_IOC_NR(cmd)) { -#ifdef CONFIG_RFKILL_INPUT - case RFKILL_IOC_NOINPUT: - if (!data->input_handler) { - if (atomic_inc_return(&rfkill_input_disabled) == 1) - printk(KERN_DEBUG "rfkill: input handler disabled\n"); - data->input_handler = true; - } - ret = 0; - break; -#endif - case RFKILL_IOC_MAX_SIZE: - if (get_user(size, (__u32 __user *)arg)) { - ret = -EFAULT; - break; - } - if (size < RFKILL_EVENT_SIZE_V1 || size > U8_MAX) { - ret = -EINVAL; - break; - } - data->max_size = size; - ret = 0; - break; - default: - break; + + if (!data->input_handler) { + if (atomic_inc_return(&rfkill_input_disabled) == 1) + printk(KERN_DEBUG "rfkill: input handler disabled\n"); + data->input_handler = true; } + mutex_unlock(&data->mtx); - return ret; + return 0; } +#endif static const struct file_operations rfkill_fops = { .owner = THIS_MODULE, @@ -1396,8 +1374,10 @@ static const struct file_operations rfkill_fops = { .write = rfkill_fop_write, .poll = rfkill_fop_poll, .release = rfkill_fop_release, +#ifdef CONFIG_RFKILL_INPUT .unlocked_ioctl = rfkill_fop_ioctl, .compat_ioctl = compat_ptr_ioctl, +#endif .llseek = no_llseek, }; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7818aae1be8e0..4301dd20b4eaa 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -692,7 +692,7 @@ struct rxrpc_call { * packets) rather than bytes. */ #define RXRPC_TX_SMSS RXRPC_JUMBO_DATALEN -#define RXRPC_MIN_CWND (RXRPC_TX_SMSS > 2190 ? 2 : RXRPC_TX_SMSS > 1095 ? 3 : 4) +#define RXRPC_MIN_CWND 4 u8 cong_cwnd; /* Congestion window size */ u8 cong_extra; /* Extra to send for congestion management */ u8 cong_ssthresh; /* Slow-start threshold */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 9fc9a6c3f6858..3847b14af7f3c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -175,12 +175,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->rx_winsize = rxrpc_rx_window_size; call->tx_winsize = 16; - if (RXRPC_TX_SMSS > 2190) - call->cong_cwnd = 2; - else if (RXRPC_TX_SMSS > 1095) - call->cong_cwnd = 3; - else - call->cong_cwnd = 4; + call->cong_cwnd = RXRPC_MIN_CWND; call->cong_ssthresh = RXRPC_TX_MAX_WINDOW; call->rxnet = rxnet; diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 1f251d758cb9d..598b4ee389fc1 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -88,7 +88,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct rxrpc_ackpacket ack; }; } __attribute__((packed)) pkt; - struct rxrpc_ackinfo ack_info; + struct rxrpc_acktrailer trailer; size_t len; int ret, ioc; u32 serial, mtu, call_id, padding; @@ -122,8 +122,8 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[0].iov_len = sizeof(pkt.whdr); iov[1].iov_base = &padding; iov[1].iov_len = 3; - iov[2].iov_base = &ack_info; - iov[2].iov_len = sizeof(ack_info); + iov[2].iov_base = &trailer; + iov[2].iov_len = sizeof(trailer); serial = rxrpc_get_next_serial(conn); @@ -158,14 +158,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0); pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE; pkt.ack.nAcks = 0; - ack_info.rxMTU = htonl(rxrpc_rx_mtu); - ack_info.maxMTU = htonl(mtu); - ack_info.rwind = htonl(rxrpc_rx_window_size); - ack_info.jumbo_max = htonl(rxrpc_rx_jumbo_max); + trailer.maxMTU = htonl(rxrpc_rx_mtu); + trailer.ifMTU = htonl(mtu); + trailer.rwind = htonl(rxrpc_rx_window_size); + trailer.jumbo_max = htonl(rxrpc_rx_jumbo_max); pkt.whdr.flags |= RXRPC_SLOW_START_OK; padding = 0; iov[0].iov_len += sizeof(pkt.ack); - len += sizeof(pkt.ack) + 3 + sizeof(ack_info); + len += sizeof(pkt.ack) + 3 + sizeof(trailer); ioc = 3; trace_rxrpc_tx_ack(chan->call_debug_id, serial, diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index df8a271948a1c..7aa58129ae455 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -118,18 +118,13 @@ struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *lo switch (srx->transport.family) { case AF_INET: if (peer->srx.transport.sin.sin_port != - srx->transport.sin.sin_port || - peer->srx.transport.sin.sin_addr.s_addr != - srx->transport.sin.sin_addr.s_addr) + srx->transport.sin.sin_port) goto not_found; break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: if (peer->srx.transport.sin6.sin6_port != - srx->transport.sin6.sin6_port || - memcmp(&peer->srx.transport.sin6.sin6_addr, - &srx->transport.sin6.sin6_addr, - sizeof(struct in6_addr)) != 0) + srx->transport.sin6.sin6_port) goto not_found; break; #endif diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9691de00ade75..5dfda1ac51dda 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -9,6 +9,17 @@ #include "ar-internal.h" +/* Override priority when generating ACKs for received DATA */ +static const u8 rxrpc_ack_priority[RXRPC_ACK__INVALID] = { + [RXRPC_ACK_IDLE] = 1, + [RXRPC_ACK_DELAY] = 2, + [RXRPC_ACK_REQUESTED] = 3, + [RXRPC_ACK_DUPLICATE] = 4, + [RXRPC_ACK_EXCEEDS_WINDOW] = 5, + [RXRPC_ACK_NOSPACE] = 6, + [RXRPC_ACK_OUT_OF_SEQUENCE] = 7, +}; + static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq, enum rxrpc_abort_reason why) { @@ -366,7 +377,7 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, * Process a DATA packet. */ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, - bool *_notify) + bool *_notify, rxrpc_serial_t *_ack_serial, int *_ack_reason) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct sk_buff *oos; @@ -419,8 +430,6 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, /* Send an immediate ACK if we fill in a hole */ else if (!skb_queue_empty(&call->rx_oos_queue)) ack_reason = RXRPC_ACK_DELAY; - else - call->ackr_nr_unacked++; window++; if (after(window, wtop)) { @@ -498,12 +507,16 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, } send_ack: - if (ack_reason >= 0) - rxrpc_send_ACK(call, ack_reason, serial, - rxrpc_propose_ack_input_data); - else - rxrpc_propose_delay_ACK(call, serial, - rxrpc_propose_ack_input_data); + if (ack_reason >= 0) { + if (rxrpc_ack_priority[ack_reason] > rxrpc_ack_priority[*_ack_reason]) { + *_ack_serial = serial; + *_ack_reason = ack_reason; + } else if (rxrpc_ack_priority[ack_reason] == rxrpc_ack_priority[*_ack_reason] && + ack_reason == RXRPC_ACK_REQUESTED) { + *_ack_serial = serial; + *_ack_reason = ack_reason; + } + } } /* @@ -514,9 +527,11 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb struct rxrpc_jumbo_header jhdr; struct rxrpc_skb_priv *sp = rxrpc_skb(skb), *jsp; struct sk_buff *jskb; + rxrpc_serial_t ack_serial = 0; unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len = skb->len - offset; bool notify = false; + int ack_reason = 0; while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { if (len < RXRPC_JUMBO_SUBPKTLEN) @@ -536,7 +551,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb jsp = rxrpc_skb(jskb); jsp->offset = offset; jsp->len = RXRPC_JUMBO_DATALEN; - rxrpc_input_data_one(call, jskb, ¬ify); + rxrpc_input_data_one(call, jskb, ¬ify, &ack_serial, &ack_reason); rxrpc_free_skb(jskb, rxrpc_skb_put_jumbo_subpacket); sp->hdr.flags = jhdr.flags; @@ -549,7 +564,16 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb sp->offset = offset; sp->len = len; - rxrpc_input_data_one(call, skb, ¬ify); + rxrpc_input_data_one(call, skb, ¬ify, &ack_serial, &ack_reason); + + if (ack_reason > 0) { + rxrpc_send_ACK(call, ack_reason, ack_serial, + rxrpc_propose_ack_input_data); + } else { + call->ackr_nr_unacked++; + rxrpc_propose_delay_ACK(call, sp->hdr.serial, + rxrpc_propose_ack_input_data); + } if (notify) { trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial); rxrpc_notify_socket(call); @@ -670,14 +694,14 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, /* * Process the extra information that may be appended to an ACK packet */ -static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, - struct rxrpc_ackinfo *ackinfo) +static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb, + struct rxrpc_acktrailer *trailer) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; unsigned int mtu; bool wake = false; - u32 rwind = ntohl(ackinfo->rwind); + u32 rwind = ntohl(trailer->rwind); if (rwind > RXRPC_TX_MAX_WINDOW) rwind = RXRPC_TX_MAX_WINDOW; @@ -688,10 +712,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, call->tx_winsize = rwind; } - if (call->cong_ssthresh > rwind) - call->cong_ssthresh = rwind; - - mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU)); + mtu = min(ntohl(trailer->maxMTU), ntohl(trailer->ifMTU)); peer = call->peer; if (mtu < peer->maxdata) { @@ -837,7 +858,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ack_summary summary = { 0 }; struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_ackinfo info; + struct rxrpc_acktrailer trailer; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since; int nr_acks, offset, ioffset; @@ -917,11 +938,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto send_response; } - info.rxMTU = 0; + trailer.maxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(info) && - skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) - return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info); + if (skb->len >= ioffset + sizeof(trailer) && + skb_copy_bits(skb, ioffset, &trailer, sizeof(trailer)) < 0) + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_trailer); if (nr_acks > 0) skb_condense(skb); @@ -950,8 +971,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } /* Parse rwind and mtu sizes if provided. */ - if (info.rxMTU) - rxrpc_input_ackinfo(call, skb, &info); + if (trailer.maxMTU) + rxrpc_input_ack_trailer(call, skb, &trailer); if (first_soft_ack == 0) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 4a292f860ae37..cad6a7d18e040 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -83,7 +83,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_txbuf *txb, u16 *_rwind) { - struct rxrpc_ackinfo ackinfo; + struct rxrpc_acktrailer trailer; unsigned int qsize, sack, wrap, to; rxrpc_seq_t window, wtop; int rsize; @@ -126,16 +126,16 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, qsize = (window - 1) - call->rx_consumed; rsize = max_t(int, call->rx_winsize - qsize, 0); *_rwind = rsize; - ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(rsize); - ackinfo.jumbo_max = htonl(jmax); + trailer.maxMTU = htonl(rxrpc_rx_mtu); + trailer.ifMTU = htonl(mtu); + trailer.rwind = htonl(rsize); + trailer.jumbo_max = htonl(jmax); *ackp++ = 0; *ackp++ = 0; *ackp++ = 0; - memcpy(ackp, &ackinfo, sizeof(ackinfo)); - return txb->ack.nAcks + 3 + sizeof(ackinfo); + memcpy(ackp, &trailer, sizeof(trailer)); + return txb->ack.nAcks + 3 + sizeof(trailer); } /* diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index e8ee4af43ca89..4fe6b4d20ada9 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -135,9 +135,9 @@ struct rxrpc_ackpacket { /* * ACK packets can have a further piece of information tagged on the end */ -struct rxrpc_ackinfo { - __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ - __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ +struct rxrpc_acktrailer { + __be32 maxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ + __be32 ifMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ __be32 rwind; /* Rx window size (packets) [AFS 3.4] */ __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */ }; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 3e30d7260493e..c2c9ee33d1385 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -830,7 +830,6 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, u32 max; if (*index) { -again: rcu_read_lock(); p = idr_find(&idrinfo->action_idr, *index); @@ -839,7 +838,7 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, * index but did not assign the pointer yet. */ rcu_read_unlock(); - goto again; + return -EAGAIN; } if (!p) { diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 6124d8b128d16..0359714c426b3 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -41,21 +41,26 @@ static struct workqueue_struct *act_ct_wq; static struct rhashtable zones_ht; static DEFINE_MUTEX(zones_mutex); +struct zones_ht_key { + struct net *net; + u16 zone; +}; + struct tcf_ct_flow_table { struct rhash_head node; /* In zones tables */ struct rcu_work rwork; struct nf_flowtable nf_ft; refcount_t ref; - u16 zone; + struct zones_ht_key key; bool dying; }; static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), - .key_offset = offsetof(struct tcf_ct_flow_table, zone), - .key_len = sizeof_field(struct tcf_ct_flow_table, zone), + .key_offset = offsetof(struct tcf_ct_flow_table, key), + .key_len = sizeof_field(struct tcf_ct_flow_table, key), .automatic_shrinking = true, }; @@ -316,11 +321,12 @@ static struct nf_flowtable_type flowtable_ct = { static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) { + struct zones_ht_key key = { .net = net, .zone = params->zone }; struct tcf_ct_flow_table *ct_ft; int err = -ENOMEM; mutex_lock(&zones_mutex); - ct_ft = rhashtable_lookup_fast(&zones_ht, ¶ms->zone, zones_params); + ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params); if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) goto out_unlock; @@ -329,7 +335,7 @@ static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) goto err_alloc; refcount_set(&ct_ft->ref, 1); - ct_ft->zone = params->zone; + ct_ft->key = key; err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params); if (err) goto err_insert; @@ -1071,6 +1077,14 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, */ if (nf_conntrack_confirm(skb) != NF_ACCEPT) goto drop; + + /* The ct may be dropped if a clash has been resolved, + * so it's necessary to retrieve it from skb again to + * prevent UAF. + */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + skip_add = true; } if (!skip_add) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index bcb673ab0008d..0015393910823 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -241,13 +241,13 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); struct tcf_skbmod_params *p; - struct tc_skbmod opt = { - .index = d->tcf_index, - .refcnt = refcount_read(&d->tcf_refcnt) - ref, - .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - }; + struct tc_skbmod opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + opt.index = d->tcf_index; + opt.refcnt = refcount_read(&d->tcf_refcnt) - ref, + opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; p = rcu_dereference_protected(d->skbmod_p, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 36b025cc4fd26..a1463f24be5fd 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -809,7 +809,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) notify = !sch->q.qlen && !WARN_ON_ONCE(!n && !qdisc_is_offloaded); /* TODO: perform the search on a per txq basis */ - sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); + sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { WARN_ON_ONCE(parentid != TC_H_ROOT); break; @@ -1389,6 +1389,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, ops->destroy(sch); qdisc_put_stab(rtnl_dereference(sch->stab)); err_out3: + lockdep_unregister_key(&sch->root_lock_key); netdev_put(dev, &sch->dev_tracker); qdisc_free(sch); err_out2: diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 9b3e9262040b6..4a7a6e9c4e4fb 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -672,6 +672,7 @@ struct Qdisc noop_qdisc = { .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock), }, + .owner = -1, }; EXPORT_SYMBOL(noop_qdisc); @@ -944,7 +945,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, __skb_queue_head_init(&sch->gso_skb); __skb_queue_head_init(&sch->skb_bad_txq); gnet_stats_basic_sync_init(&sch->bstats); + lockdep_register_key(&sch->root_lock_key); spin_lock_init(&sch->q.lock); + lockdep_set_class(&sch->q.lock, &sch->root_lock_key); if (ops->static_flags & TCQ_F_CPUSTATS) { sch->cpu_bstats = @@ -973,11 +976,13 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; + sch->owner = -1; netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); return sch; errout1: + lockdep_unregister_key(&sch->root_lock_key); kfree(sch); errout: return ERR_PTR(err); @@ -1066,6 +1071,7 @@ static void __qdisc_destroy(struct Qdisc *qdisc) if (ops->destroy) ops->destroy(qdisc); + lockdep_unregister_key(&qdisc->root_lock_key); module_put(ops->owner); netdev_put(dev, &qdisc->dev_tracker); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 7349233eaa9b6..19a578c31a91f 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1039,13 +1039,6 @@ static void htb_work_func(struct work_struct *work) rcu_read_unlock(); } -static void htb_set_lockdep_class_child(struct Qdisc *q) -{ - static struct lock_class_key child_key; - - lockdep_set_class(qdisc_lock(q), &child_key); -} - static int htb_offload(struct net_device *dev, struct tc_htb_qopt_offload *opt) { return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_HTB, opt); @@ -1132,7 +1125,6 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, return -ENOMEM; } - htb_set_lockdep_class_child(qdisc); q->direct_qdiscs[ntx] = qdisc; qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } @@ -1468,7 +1460,6 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, } if (q->offload) { - htb_set_lockdep_class_child(new); /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ qdisc_refcount_inc(new); old_q = htb_graft_helper(dev_queue, new); @@ -1733,11 +1724,8 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, cl->parent->common.classid, NULL); - if (q->offload) { - if (new_q) - htb_set_lockdep_class_child(new_q); + if (q->offload) htb_parent_to_leaf_offload(sch, dev_queue, new_q); - } } sch_tree_lock(sch); @@ -1947,13 +1935,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, classid, NULL); if (q->offload) { - if (new_q) { - htb_set_lockdep_class_child(new_q); - /* One ref for cl->leaf.q, the other for - * dev_queue->qdisc. - */ + /* One ref for cl->leaf.q, the other for dev_queue->qdisc. */ + if (new_q) qdisc_refcount_inc(new_q); - } old_q = htb_graft_helper(dev_queue, new_q); /* No qdisc_put needed. */ WARN_ON(!(old_q->flags & TCQ_F_BUILTIN)); diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index d66d5f0ec0805..387a5013bd966 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -185,7 +185,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, qopt->bands = qdisc_dev(sch)->real_num_tx_queues; - removed = kmalloc(sizeof(*removed) * (q->max_bands - q->bands), + removed = kmalloc(sizeof(*removed) * (q->max_bands - qopt->bands), GFP_KERNEL); if (!removed) return -ENOMEM; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index fa678eb885284..0d29d0ccf8cb2 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; - struct sk_buff *skb2; + struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; - int rc = NET_XMIT_SUCCESS; - int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_orphan_partial(skb); /* - * If we need to duplicate packet, then re-insert at top of the - * qdisc tree, since parent queuer expects that only one - * skb will be queued. + * If we need to duplicate packet, then clone it before + * original is modified. */ - if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root_bh(sch); - u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - - q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); - q->duplicate = dupsave; - rc_drop = NET_XMIT_SUCCESS; - } + if (count > 1) + skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. @@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) - return rc_drop; + goto finish_segs; + segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; @@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); - return rc_drop; + if (skb2) + __qdisc_drop(skb2, to_free); + return NET_XMIT_DROP; + } + + /* + * If doing duplication then re-insert at top of the + * qdisc tree, since parent queuer expects that only one + * skb will be queued. + */ + if (skb2) { + struct Qdisc *rootq = qdisc_root_bh(sch); + u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ + + q->duplicate = 0; + rootq->enqueue(skb2, rootq, to_free); + q->duplicate = dupsave; + skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); @@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } finish_segs: + if (skb2) + __qdisc_drop(skb2, to_free); + if (segs) { unsigned int len, last_len; - int nb; + int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 31a8252bd09c9..7a9a6e880b825 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1008,7 +1008,8 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { - [TCA_TAPRIO_TC_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_TAPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32, + TC_QOPT_MAX_QUEUE), [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, [TCA_TAPRIO_TC_ENTRY_FP] = NLA_POLICY_RANGE(NLA_U32, TC_FP_EXPRESS, @@ -1160,11 +1161,6 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, list_for_each_entry(entry, &new->entries, list) cycle = ktime_add_ns(cycle, entry->interval); - if (!cycle) { - NL_SET_ERR_MSG(extack, "'cycle_time' can never be 0"); - return -EINVAL; - } - if (cycle < 0 || cycle > INT_MAX) { NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); return -EINVAL; @@ -1173,6 +1169,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, new->cycle_time = cycle; } + if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too small"); + return -EINVAL; + } + taprio_calculate_gate_durations(q, new); return 0; @@ -1185,16 +1186,13 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, { bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags); - if (!qopt && !dev->num_tc) { - NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); - return -EINVAL; - } - - /* If num_tc is already set, it means that the user already - * configured the mqprio part - */ - if (dev->num_tc) + if (!qopt) { + if (!dev->num_tc) { + NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); + return -EINVAL; + } return 0; + } /* taprio imposes that traffic classes map 1:n to tx queues */ if (qopt->num_tc > dev->num_tx_queues) { @@ -1870,6 +1868,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, q->flags = err; + /* Needed for length_to_duration() during netlink attribute parsing */ + taprio_set_picos_per_byte(dev, q); + err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) return err; @@ -1929,7 +1930,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (err < 0) goto free_sched; - taprio_set_picos_per_byte(dev, q); taprio_update_queue_max_sdu(q, new_admin, stab); if (FULL_OFFLOAD_IS_ENABLED(q->flags)) diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 24368f755ab19..f7b809c0d142c 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -415,7 +415,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if (!IS_ERR_OR_NULL(dst)) { struct rt6_info *rt; - rt = (struct rt6_info *)dst; + rt = dst_rt6_info(dst); t->dst_cookie = rt6_get_cookie(rt); pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n", &rt->rt6i_dst.addr, rt->rt6i_dst.plen, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 94c6dd53cd62d..ae68b48cebbe5 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -552,7 +552,7 @@ static void sctp_v4_get_saddr(struct sctp_sock *sk, struct flowi *fl) { union sctp_addr *saddr = &t->saddr; - struct rtable *rt = (struct rtable *)t->dst; + struct rtable *rt = dst_rtable(t->dst); if (rt) { saddr->v4.sin_family = AF_INET; @@ -1085,7 +1085,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t) skb_reset_inner_mac_header(skb); skb_reset_inner_transport_header(skb); skb_set_inner_ipproto(skb, IPPROTO_SCTP); - udp_tunnel_xmit_skb((struct rtable *)dst, sk, skb, fl4->saddr, + udp_tunnel_xmit_skb(dst_rtable(dst), sk, skb, fl4->saddr, fl4->daddr, dscp, ip4_dst_hoplimit(dst), df, sctp_sk(sk)->udp_port, t->encap_port, false, false); return 0; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 0f53a5c6fd9d9..8f6ae43625870 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -460,29 +460,11 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr, static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, unsigned long mask) { - struct net *nnet = sock_net(nsk); - nsk->sk_userlocks = osk->sk_userlocks; - if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) { + if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) nsk->sk_sndbuf = osk->sk_sndbuf; - } else { - if (mask == SK_FLAGS_SMC_TO_CLC) - WRITE_ONCE(nsk->sk_sndbuf, - READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1])); - else - WRITE_ONCE(nsk->sk_sndbuf, - 2 * READ_ONCE(nnet->smc.sysctl_wmem)); - } - if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) { + if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) nsk->sk_rcvbuf = osk->sk_rcvbuf; - } else { - if (mask == SK_FLAGS_SMC_TO_CLC) - WRITE_ONCE(nsk->sk_rcvbuf, - READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1])); - else - WRITE_ONCE(nsk->sk_rcvbuf, - 2 * READ_ONCE(nnet->smc.sysctl_rmem)); - } } static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 97704a9e84c70..9297dc20bfe23 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -209,13 +209,18 @@ int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, if (IS_ERR(rt)) goto out; if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET) - goto out; - neigh = rt->dst.ops->neigh_lookup(&rt->dst, NULL, &fl4.daddr); - if (neigh) { - memcpy(nexthop_mac, neigh->ha, ETH_ALEN); - *uses_gateway = rt->rt_uses_gateway; - return 0; - } + goto out_rt; + neigh = dst_neigh_lookup(&rt->dst, &fl4.daddr); + if (!neigh) + goto out_rt; + memcpy(nexthop_mac, neigh->ha, ETH_ALEN); + *uses_gateway = rt->rt_uses_gateway; + neigh_release(neigh); + ip_rt_put(rt); + return 0; + +out_rt: + ip_rt_put(rt); out: return -ENOENT; } diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 9f2c58c5a86b7..2adb92b8c4699 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -806,6 +806,16 @@ static void smc_pnet_create_pnetids_list(struct net *net) u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; + /* Newly created netns do not have devices. + * Do not even acquire rtnl. + */ + if (list_empty(&net->dev_base_head)) + return; + + /* Note: This might not be needed, because smc_pnet_netdev_event() + * is also calling smc_pnet_add_base_pnetid() when handling + * NETDEV_UP event. + */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index d435bffc61999..97ff11973c493 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -284,10 +284,10 @@ char *rpc_sockaddr2uaddr(const struct sockaddr *sap, gfp_t gfp_flags) } if (snprintf(portbuf, sizeof(portbuf), - ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf)) + ".%u.%u", port >> 8, port & 0xff) >= (int)sizeof(portbuf)) return NULL; - if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) + if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) >= sizeof(addrbuf)) return NULL; return kstrdup(addrbuf, gfp_flags); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index c7af0220f82f4..369310909fc98 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1875,8 +1875,10 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0].iov_base; maj_stat = gss_wrap(ctx->gc_gss_ctx, offset, snd_buf, inpages); /* slack space should prevent this ever happening: */ - if (unlikely(snd_buf->len > snd_buf->buflen)) + if (unlikely(snd_buf->len > snd_buf->buflen)) { + status = -EIO; goto wrap_failed; + } /* We're assuming that when GSS_S_CONTEXT_EXPIRED, the encryption was * done anyway, so it's safe to put the request on the wire: */ if (maj_stat == GSS_S_CONTEXT_EXPIRED) diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 64cff717c3d9b..3366505bc669a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -398,6 +398,7 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, u64 seq_send64; int keylen; u32 time32; + int ret; p = simple_get_bytes(p, end, &ctx->flags, sizeof(ctx->flags)); if (IS_ERR(p)) @@ -450,8 +451,16 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, } ctx->mech_used.len = gss_kerberos_mech.gm_oid.len; - return gss_krb5_import_ctx_v2(ctx, gfp_mask); + ret = gss_krb5_import_ctx_v2(ctx, gfp_mask); + if (ret) { + p = ERR_PTR(ret); + goto out_free; + } + return 0; + +out_free: + kfree(ctx->mech_used.data); out_err: return PTR_ERR(p); } diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index d79f12c2550ac..cb32ab9a83952 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -250,8 +250,8 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL); if (!creds) { - kfree(oa->data); - return -ENOMEM; + err = -ENOMEM; + goto free_oa; } oa->data[0].option.data = CREDS_VALUE; @@ -265,29 +265,40 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, /* option buffer */ p = xdr_inline_decode(xdr, 4); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto free_creds; + } length = be32_to_cpup(p); p = xdr_inline_decode(xdr, length); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto free_creds; + } if (length == sizeof(CREDS_VALUE) && memcmp(p, CREDS_VALUE, sizeof(CREDS_VALUE)) == 0) { /* We have creds here. parse them */ err = gssx_dec_linux_creds(xdr, creds); if (err) - return err; + goto free_creds; oa->data[0].value.len = 1; /* presence */ } else { /* consume uninteresting buffer */ err = gssx_dec_buffer(xdr, &dummy); if (err) - return err; + goto free_creds; } } return 0; + +free_creds: + kfree(creds); +free_oa: + kfree(oa->data); + oa->data = NULL; + return err; } static int gssx_dec_status(struct xdr_stream *xdr, diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 24de941847003..73a90ad873fb9 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1033,17 +1033,11 @@ svcauth_gss_proc_init_verf(struct cache_detail *cd, struct svc_rqst *rqstp, static void gss_free_in_token_pages(struct gssp_in_token *in_token) { - u32 inlen; int i; i = 0; - inlen = in_token->page_len; - while (inlen) { - if (in_token->pages[i]) - put_page(in_token->pages[i]); - inlen -= inlen > PAGE_SIZE ? PAGE_SIZE : inlen; - } - + while (in_token->pages[i]) + put_page(in_token->pages[i++]); kfree(in_token->pages); in_token->pages = NULL; } @@ -1075,7 +1069,7 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, goto out_denied_free; pages = DIV_ROUND_UP(inlen, PAGE_SIZE); - in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL); + in_token->pages = kcalloc(pages + 1, sizeof(struct page *), GFP_KERNEL); if (!in_token->pages) goto out_denied_free; in_token->page_base = 0; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cda0935a68c9d..59b2fbd88e5eb 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -405,7 +405,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, clnt->cl_maxproc = version->nrprocs; clnt->cl_prog = args->prognumber ? : program->number; clnt->cl_vers = version->number; - clnt->cl_stats = program->stats; + clnt->cl_stats = args->stats ? : program->stats; clnt->cl_metrics = rpc_alloc_iostats(clnt); rpc_init_pipe_dir_head(&clnt->cl_pipedir_objects); err = -ENOMEM; @@ -691,6 +691,7 @@ struct rpc_clnt *rpc_clone_client(struct rpc_clnt *clnt) .version = clnt->cl_vers, .authflavor = clnt->cl_auth->au_flavor, .cred = clnt->cl_cred, + .stats = clnt->cl_stats, }; return __rpc_clone_client(&args, clnt); } @@ -713,6 +714,7 @@ rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor) .version = clnt->cl_vers, .authflavor = flavor, .cred = clnt->cl_cred, + .stats = clnt->cl_stats, }; return __rpc_clone_client(&args, clnt); } @@ -1068,6 +1070,8 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old, .version = vers, .authflavor = old->cl_auth->au_flavor, .cred = old->cl_cred, + .stats = old->cl_stats, + .timeout = old->cl_timeout, }; struct rpc_clnt *clnt; int err; diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 65fc1297c6dfa..383860cb1d5b0 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -314,7 +314,7 @@ EXPORT_SYMBOL_GPL(rpc_proc_unregister); struct proc_dir_entry * svc_proc_register(struct net *net, struct svc_stat *statp, const struct proc_ops *proc_ops) { - return do_register(net, statp->program->pg_name, statp, proc_ops); + return do_register(net, statp->program->pg_name, net, proc_ops); } EXPORT_SYMBOL_GPL(svc_proc_register); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index b969e505c7b77..bd61e257cda6a 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1263,8 +1263,6 @@ svc_generic_init_request(struct svc_rqst *rqstp, if (rqstp->rq_proc >= versp->vs_nproc) goto err_bad_proc; rqstp->rq_procinfo = procp = &versp->vs_proc[rqstp->rq_proc]; - if (!procp) - goto err_bad_proc; /* Initialize storage for argp and resp */ memset(rqstp->rq_argp, 0, procp->pc_argzero); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 545017a3daa4d..6b3f01beb294b 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1206,15 +1206,6 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) * MSG_SPLICE_PAGES is used exclusively to reduce the number of * copy operations in this path. Therefore the caller must ensure * that the pages backing @xdr are unchanging. - * - * Note that the send is non-blocking. The caller has incremented - * the reference count on each page backing the RPC message, and - * the network layer will "put" these pages when transmission is - * complete. - * - * This is safe for our RPC services because the memory backing - * the head and tail components is never kmalloc'd. These always - * come from pages in the svc_rqst::rq_pages array. */ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, rpc_fraghdr marker, unsigned int *sentp) @@ -1244,6 +1235,7 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, 1 + count, sizeof(marker) + rqstp->rq_res.len); ret = sock_sendmsg(svsk->sk_sock, &msg); + page_frag_free(buf); if (ret < 0) return ret; *sentp += ret; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 4f8d7efa469f0..432557a553e7e 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -244,7 +244,11 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DEVICE_REMOVAL: pr_info("rpcrdma: removing device %s for %pISpc\n", ep->re_id->device->name, sap); - fallthrough; + switch (xchg(&ep->re_connect_status, -ENODEV)) { + case 0: goto wake_connect_worker; + case 1: goto disconnected; + } + return 0; case RDMA_CM_EVENT_ADDR_CHANGE: ep->re_connect_status = -ENODEV; goto disconnected; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 58f3dc8d0d71c..004d2bd8b49ec 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2645,6 +2645,7 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) .xprtsec = { .policy = RPC_XPRTSEC_NONE, }, + .stats = upper_clnt->cl_stats, }; unsigned int pflags = current->flags; struct rpc_clnt *lower_clnt; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 5c9fd4791c4ba..76284fc538ebd 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -142,9 +142,9 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; - *buf = NULL; if (skb_has_frag_list(frag) && __skb_linearize(frag)) goto err; + *buf = NULL; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; @@ -156,6 +156,11 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (!head) goto err; + /* Either the input skb ownership is transferred to headskb + * or the input skb is freed, clear the reference to avoid + * bad access on error path. + */ + *buf = NULL; if (skb_try_coalesce(head, frag, &headstolen, &delta)) { kfree_skb_partial(frag, headstolen); } else { @@ -179,7 +184,6 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) *headbuf = NULL; return 1; } - *buf = NULL; return 0; err: kfree_skb(*buf); diff --git a/net/tipc/node.c b/net/tipc/node.c index 3105abe97bb9c..69053c0398252 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2107,6 +2107,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) } else { n = tipc_node_find_by_id(net, ehdr->id); } + skb_dst_force(skb); tipc_crypto_rcv(net, (n) ? n->crypto_rx : NULL, &skb, b); if (!skb) return; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index f892b0903dbaf..b849a3d133a01 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -174,7 +174,7 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, local_bh_disable(); ndst = dst_cache_get(cache); if (dst->proto == htons(ETH_P_IP)) { - struct rtable *rt = (struct rtable *)ndst; + struct rtable *rt = dst_rtable(ndst); if (!rt) { struct flowi4 fl = { diff --git a/net/tls/tls.h b/net/tls/tls.h index 762f424ff2d59..e5e47452308ab 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -215,7 +215,7 @@ static inline struct sk_buff *tls_strp_msg(struct tls_sw_context_rx *ctx) static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) { - return ctx->strp.msg_ready; + return READ_ONCE(ctx->strp.msg_ready); } static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b4674f03d71a9..90b7f253d3632 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -816,9 +816,17 @@ struct tls_context *tls_ctx_create(struct sock *sk) return NULL; mutex_init(&ctx->tx_lock); - rcu_assign_pointer(icsk->icsk_ulp_data, ctx); ctx->sk_proto = READ_ONCE(sk->sk_prot); ctx->sk = sk; + /* Release semantic of rcu_assign_pointer() ensures that + * ctx->sk_proto is visible before changing sk->sk_prot in + * update_sk_prot(), and prevents reading uninitialized value in + * tls_{getsockopt, setsockopt}. Note that we do not need a + * read barrier in tls_{getsockopt,setsockopt} as there is an + * address dependency between sk->sk_proto->{getsockopt,setsockopt} + * and ctx->sk_proto. + */ + rcu_assign_pointer(icsk->icsk_ulp_data, ctx); return ctx; } diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index ca1e0e198ceb4..5df08d848b5c9 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -360,7 +360,7 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0; - strp->msg_ready = 1; + WRITE_ONCE(strp->msg_ready, 1); tls_rx_msg_ready(strp); } @@ -528,7 +528,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); - strp->msg_ready = 1; + WRITE_ONCE(strp->msg_ready, 1); tls_rx_msg_ready(strp); return 0; @@ -580,7 +580,7 @@ void tls_strp_msg_done(struct tls_strparser *strp) else tls_strp_flush_anchor_copy(strp); - strp->msg_ready = 0; + WRITE_ONCE(strp->msg_ready, 0); memset(&strp->stm, 0, sizeof(strp->stm)); tls_strp_check_rcv(strp); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 211f57164cb61..b783231668c65 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1976,10 +1976,10 @@ int tls_sw_recvmsg(struct sock *sk, if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR); - psock = sk_psock_get(sk); err = tls_rx_reader_lock(sk, ctx, flags & MSG_DONTWAIT); if (err < 0) return err; + psock = sk_psock_get(sk); bpf_strp_enabled = sk_psock_strp_enabled(psock); /* If crypto failed the connection is broken */ @@ -2152,12 +2152,15 @@ int tls_sw_recvmsg(struct sock *sk, } /* Drain records from the rx_list & copy if required */ - if (is_peek || is_kvec) + if (is_peek) err = process_rx_list(ctx, msg, &control, copied + peeked, decrypted - peeked, is_peek, NULL); else err = process_rx_list(ctx, msg, &control, 0, async_copy_bytes, is_peek, NULL); + + /* we could have copied less than we wanted, and possibly nothing */ + decrypted += max(err, 0) - async_copy_bytes; } copied += decrypted; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0748e7ea5210e..a39de277f43d3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -223,15 +223,9 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk) return unix_peer(osk) == NULL || unix_our_peer(sk, osk); } -static inline int unix_recvq_full(const struct sock *sk) -{ - return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; -} - static inline int unix_recvq_full_lockless(const struct sock *sk) { - return skb_queue_len_lockless(&sk->sk_receive_queue) > - READ_ONCE(sk->sk_max_ack_backlog); + return skb_queue_len_lockless(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; } struct sock *unix_peer_get(struct sock *s) @@ -532,10 +526,10 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) return 0; } -static int unix_writable(const struct sock *sk) +static int unix_writable(const struct sock *sk, unsigned char state) { - return sk->sk_state != TCP_LISTEN && - (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; + return state != TCP_LISTEN && + (refcount_read(&sk->sk_wmem_alloc) << 2) <= READ_ONCE(sk->sk_sndbuf); } static void unix_write_space(struct sock *sk) @@ -543,7 +537,7 @@ static void unix_write_space(struct sock *sk) struct socket_wq *wq; rcu_read_lock(); - if (unix_writable(sk)) { + if (unix_writable(sk, READ_ONCE(sk->sk_state))) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, @@ -572,7 +566,6 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) sk_error_report(other); } } - other->sk_state = TCP_CLOSE; } static void unix_sock_destructor(struct sock *sk) @@ -619,7 +612,7 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.dentry = NULL; u->path.mnt = NULL; state = sk->sk_state; - sk->sk_state = TCP_CLOSE; + WRITE_ONCE(sk->sk_state, TCP_CLOSE); skpair = unix_peer(sk); unix_peer(sk) = NULL; @@ -640,7 +633,7 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_state_lock(skpair); /* No more writes */ WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); - if (!skb_queue_empty(&sk->sk_receive_queue) || embrion) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion) WRITE_ONCE(skpair->sk_err, ECONNRESET); unix_state_unlock(skpair); skpair->sk_state_change(skpair); @@ -733,7 +726,7 @@ static int unix_listen(struct socket *sock, int backlog) if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) goto out; /* Only stream/seqpacket sockets accept */ err = -EINVAL; - if (!u->addr) + if (!READ_ONCE(u->addr)) goto out; /* No listens on an unbound socket */ unix_state_lock(sk); if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN) @@ -741,7 +734,8 @@ static int unix_listen(struct socket *sock, int backlog) if (backlog > sk->sk_max_ack_backlog) wake_up_interruptible_all(&u->peer_wait); sk->sk_max_ack_backlog = backlog; - sk->sk_state = TCP_LISTEN; + WRITE_ONCE(sk->sk_state, TCP_LISTEN); + /* set credentials so connect can copy them */ init_peercred(sk); err = 0; @@ -978,13 +972,13 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_hash = unix_unbound_hash(sk); sk->sk_allocation = GFP_KERNEL_ACCOUNT; sk->sk_write_space = unix_write_space; - sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; + sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; - u = unix_sk(sk); + u = unix_sk(sk); + u->inflight = 0; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ @@ -1133,8 +1127,8 @@ static struct sock *unix_find_other(struct net *net, static int unix_autobind(struct sock *sk) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; u32 lastnum, ordernum; @@ -1157,6 +1151,7 @@ static int unix_autobind(struct sock *sk) addr->name->sun_family = AF_UNIX; refcount_set(&addr->refcnt, 1); + old_hash = sk->sk_hash; ordernum = get_random_u32(); lastnum = ordernum & 0xFFFFF; retry: @@ -1197,8 +1192,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, { umode_t mode = S_IFSOCK | (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask()); - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct mnt_idmap *idmap; struct unix_address *addr; @@ -1236,6 +1231,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, if (u->addr) goto out_unlock; + old_hash = sk->sk_hash; new_hash = unix_bsd_hash(d_backing_inode(dentry)); unix_table_double_lock(net, old_hash, new_hash); u->path.mnt = mntget(parent.mnt); @@ -1263,8 +1259,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, int addr_len) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; int err; @@ -1282,6 +1278,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, goto out_mutex; } + old_hash = sk->sk_hash; new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type); unix_table_double_lock(net, old_hash, new_hash); @@ -1371,7 +1368,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && - !unix_sk(sk)->addr) { + !READ_ONCE(unix_sk(sk)->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1401,7 +1398,8 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out_unlock; - sk->sk_state = other->sk_state = TCP_ESTABLISHED; + WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED); + WRITE_ONCE(other->sk_state, TCP_ESTABLISHED); } else { /* * 1003.1g breaking connected state with AF_UNSPEC @@ -1418,13 +1416,20 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, unix_peer(sk) = other; if (!other) - sk->sk_state = TCP_CLOSE; + WRITE_ONCE(sk->sk_state, TCP_CLOSE); unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer); unix_state_double_unlock(sk, other); - if (other != old_peer) + if (other != old_peer) { unix_dgram_disconnected(sk, old_peer); + + unix_state_lock(old_peer); + if (!unix_peer(old_peer)) + WRITE_ONCE(old_peer->sk_state, TCP_CLOSE); + unix_state_unlock(old_peer); + } + sock_put(old_peer); } else { unix_peer(sk) = other; @@ -1472,7 +1477,6 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, struct sk_buff *skb = NULL; long timeo; int err; - int st; err = unix_validate_addr(sunaddr, addr_len); if (err) @@ -1483,7 +1487,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto out; if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + test_bit(SOCK_PASSPIDFD, &sock->flags)) && + !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1536,7 +1541,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (other->sk_shutdown & RCV_SHUTDOWN) goto out_unlock; - if (unix_recvq_full(other)) { + if (unix_recvq_full_lockless(other)) { err = -EAGAIN; if (!timeo) goto out_unlock; @@ -1561,9 +1566,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, Well, and we have to recheck the state after socket locked. */ - st = sk->sk_state; - - switch (st) { + switch (READ_ONCE(sk->sk_state)) { case TCP_CLOSE: /* This is ok... continue with connect */ break; @@ -1578,7 +1581,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, unix_state_lock_nested(sk, U_LOCK_SECOND); - if (sk->sk_state != st) { + if (sk->sk_state != TCP_CLOSE) { unix_state_unlock(sk); unix_state_unlock(other); sock_put(other); @@ -1630,7 +1633,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, copy_peercred(sk, other); sock->state = SS_CONNECTED; - sk->sk_state = TCP_ESTABLISHED; + WRITE_ONCE(sk->sk_state, TCP_ESTABLISHED); sock_hold(newsk); smp_mb__after_atomic(); /* sock_hold() does an atomic_inc() */ @@ -1703,7 +1706,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, goto out; err = -EINVAL; - if (sk->sk_state != TCP_LISTEN) + if (READ_ONCE(sk->sk_state) != TCP_LISTEN) goto out; /* If socket state is TCP_LISTEN it cannot change (for now...), @@ -1937,14 +1940,15 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, } if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + test_bit(SOCK_PASSPIDFD, &sock->flags)) && + !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; } err = -EMSGSIZE; - if (len > sk->sk_sndbuf - 32) + if (len > READ_ONCE(sk->sk_sndbuf) - 32) goto out; if (len > SKB_MAX_ALLOC) { @@ -2026,7 +2030,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, unix_peer(sk) = NULL; unix_dgram_peer_wake_disconnect_wakeup(sk, other); - sk->sk_state = TCP_CLOSE; + WRITE_ONCE(sk->sk_state, TCP_CLOSE); unix_state_unlock(sk); unix_dgram_disconnected(sk, other); @@ -2157,13 +2161,15 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other maybe_add_creds(skb, sock, other); skb_get(skb); + scm_stat_add(other, skb); + + spin_lock(&other->sk_receive_queue.lock); if (ousk->oob_skb) consume_skb(ousk->oob_skb); - WRITE_ONCE(ousk->oob_skb, skb); + __skb_queue_tail(&other->sk_receive_queue, skb); + spin_unlock(&other->sk_receive_queue.lock); - scm_stat_add(other, skb); - skb_queue_tail(&other->sk_receive_queue, skb); sk_send_sigurg(other); unix_state_unlock(other); other->sk_data_ready(other); @@ -2200,7 +2206,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, } if (msg->msg_namelen) { - err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; + err = READ_ONCE(sk->sk_state) == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out_err; } else { err = -ENOTCONN; @@ -2209,7 +2215,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_err; } - if (sk->sk_shutdown & SEND_SHUTDOWN) + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto pipe_err; while (sent < len) { @@ -2221,7 +2227,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, &err, 0); } else { /* Keep two messages in the pipe so it schedules better */ - size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64); + size = min_t(int, size, (READ_ONCE(sk->sk_sndbuf) >> 1) - 64); /* allow fallback to order-0 allocations */ size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ); @@ -2314,7 +2320,7 @@ static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg, if (err) return err; - if (sk->sk_state != TCP_ESTABLISHED) + if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED) return -ENOTCONN; if (msg->msg_namelen) @@ -2328,7 +2334,7 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; - if (sk->sk_state != TCP_ESTABLISHED) + if (READ_ONCE(sk->sk_state) != TCP_ESTABLISHED) return -ENOTCONN; return unix_dgram_recvmsg(sock, msg, size, flags); @@ -2553,8 +2559,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) mutex_lock(&u->iolock); unix_state_lock(sk); + spin_lock(&sk->sk_receive_queue.lock); if (sock_flag(sk, SOCK_URGINLINE) || !u->oob_skb) { + spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); mutex_unlock(&u->iolock); return -EINVAL; @@ -2566,6 +2574,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) WRITE_ONCE(u->oob_skb, NULL); else skb_get(oob_skb); + + spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); chunk = state->recv_actor(oob_skb, 0, chunk, state); @@ -2594,20 +2604,34 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, consume_skb(skb); skb = NULL; } else { + struct sk_buff *unlinked_skb = NULL; + + spin_lock(&sk->sk_receive_queue.lock); + if (skb == u->oob_skb) { if (copied) { skb = NULL; - } else if (sock_flag(sk, SOCK_URGINLINE)) { - if (!(flags & MSG_PEEK)) { + } else if (!(flags & MSG_PEEK)) { + if (sock_flag(sk, SOCK_URGINLINE)) { WRITE_ONCE(u->oob_skb, NULL); consume_skb(skb); + } else { + __skb_unlink(skb, &sk->sk_receive_queue); + WRITE_ONCE(u->oob_skb, NULL); + unlinked_skb = skb; + skb = skb_peek(&sk->sk_receive_queue); } - } else if (!(flags & MSG_PEEK)) { - skb_unlink(skb, &sk->sk_receive_queue); - consume_skb(skb); - skb = skb_peek(&sk->sk_receive_queue); + } else if (!sock_flag(sk, SOCK_URGINLINE)) { + skb = skb_peek_next(skb, &sk->sk_receive_queue); } } + + spin_unlock(&sk->sk_receive_queue.lock); + + if (unlinked_skb) { + WARN_ON_ONCE(skb_unref(unlinked_skb)); + kfree_skb(unlinked_skb); + } } return skb; } @@ -2615,7 +2639,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - if (unlikely(sk->sk_state != TCP_ESTABLISHED)) + if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) return -ENOTCONN; return unix_read_skb(sk, recv_actor); @@ -2639,7 +2663,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, size_t size = state->size; unsigned int last_len; - if (unlikely(sk->sk_state != TCP_ESTABLISHED)) { + if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) { err = -EINVAL; goto out; } @@ -2678,18 +2702,16 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, last = skb = skb_peek(&sk->sk_receive_queue); last_len = last ? last->len : 0; +again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { skb = manage_oob(skb, sk, flags, copied); - if (!skb) { + if (!skb && copied) { unix_state_unlock(sk); - if (copied) - break; - goto redo; + break; } } #endif -again: if (skb == NULL) { if (copied >= target) goto unlock; @@ -2972,7 +2994,7 @@ long unix_inq_len(struct sock *sk) struct sk_buff *skb; long amount = 0; - if (sk->sk_state == TCP_LISTEN) + if (READ_ONCE(sk->sk_state) == TCP_LISTEN) return -EINVAL; spin_lock(&sk->sk_receive_queue.lock); @@ -3084,12 +3106,14 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; + unsigned char state; __poll_t mask; u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; shutdown = READ_ONCE(sk->sk_shutdown); + state = READ_ONCE(sk->sk_state); /* exceptional events? */ if (READ_ONCE(sk->sk_err)) @@ -3111,14 +3135,14 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa /* Connection-based need to check for termination and startup */ if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && - sk->sk_state == TCP_CLOSE) + state == TCP_CLOSE) mask |= EPOLLHUP; /* * we set writable also when the other side has shut down the * connection. This prevents stuck sockets. */ - if (unix_writable(sk)) + if (unix_writable(sk, state)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; return mask; @@ -3129,12 +3153,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk, *other; unsigned int writable; + unsigned char state; __poll_t mask; u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; shutdown = READ_ONCE(sk->sk_shutdown); + state = READ_ONCE(sk->sk_state); /* exceptional events? */ if (READ_ONCE(sk->sk_err) || @@ -3154,19 +3180,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ - if (sk->sk_type == SOCK_SEQPACKET) { - if (sk->sk_state == TCP_CLOSE) - mask |= EPOLLHUP; - /* connection hasn't started yet? */ - if (sk->sk_state == TCP_SYN_SENT) - return mask; - } + if (sk->sk_type == SOCK_SEQPACKET && state == TCP_CLOSE) + mask |= EPOLLHUP; /* No write status requested, avoid expensive OUT tests. */ if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT))) return mask; - writable = unix_writable(sk); + writable = unix_writable(sk, state); if (writable) { unix_state_lock(sk); diff --git a/net/unix/diag.c b/net/unix/diag.c index be19827eca36d..84b98ba05e7e5 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -65,7 +65,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) u32 *buf; int i; - if (sk->sk_state == TCP_LISTEN) { + if (READ_ONCE(sk->sk_state) == TCP_LISTEN) { spin_lock(&sk->sk_receive_queue.lock); attr = nla_reserve(nlskb, UNIX_DIAG_ICONS, @@ -103,8 +103,8 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) { struct unix_diag_rqlen rql; - if (sk->sk_state == TCP_LISTEN) { - rql.udiag_rqueue = sk->sk_receive_queue.qlen; + if (READ_ONCE(sk->sk_state) == TCP_LISTEN) { + rql.udiag_rqueue = skb_queue_len_lockless(&sk->sk_receive_queue); rql.udiag_wqueue = sk->sk_max_ack_backlog; } else { rql.udiag_rqueue = (u32) unix_inq_len(sk); @@ -136,7 +136,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r rep = nlmsg_data(nlh); rep->udiag_family = AF_UNIX; rep->udiag_type = sk->sk_type; - rep->udiag_state = sk->sk_state; + rep->udiag_state = READ_ONCE(sk->sk_state); rep->pad = 0; rep->udiag_ino = sk_ino; sock_diag_save_cookie(sk, rep->udiag_cookie); @@ -165,7 +165,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO)) goto out_nlmsg_trim; - if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown)) + if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, READ_ONCE(sk->sk_shutdown))) goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_UID) && @@ -215,7 +215,7 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) sk_for_each(sk, &net->unx.table.buckets[slot]) { if (num < s_num) goto next; - if (!(req->udiag_states & (1 << sk->sk_state))) + if (!(req->udiag_states & (1 << READ_ONCE(sk->sk_state)))) goto next; if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk), NETLINK_CB(cb->skb).portid, diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2a81880dac7b7..2a758531e1027 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -166,17 +166,18 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), static void dec_inflight(struct unix_sock *usk) { - atomic_long_dec(&usk->inflight); + usk->inflight--; } static void inc_inflight(struct unix_sock *usk) { - atomic_long_inc(&usk->inflight); + usk->inflight++; } static void inc_inflight_move_tail(struct unix_sock *u) { - atomic_long_inc(&u->inflight); + u->inflight++; + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over @@ -198,7 +199,7 @@ void wait_for_unix_gc(void) if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && !READ_ONCE(gc_in_progress)) unix_gc(); - wait_event(unix_gc_wait, gc_in_progress == false); + wait_event(unix_gc_wait, !READ_ONCE(gc_in_progress)); } /* The external entry point: unix_gc() */ @@ -234,20 +235,34 @@ void unix_gc(void) * receive queues. Other, non candidate sockets _can_ be * added to queue, so we must make sure only to touch * candidates. + * + * Embryos, though never candidates themselves, affect which + * candidates are reachable by the garbage collector. Before + * being added to a listener's queue, an embryo may already + * receive data carrying SCM_RIGHTS, potentially making the + * passed socket a candidate that is not yet reachable by the + * collector. It becomes reachable once the embryo is + * enqueued. Therefore, we must ensure that no SCM-laden + * embryo appears in a (candidate) listener's queue between + * consecutive scan_children() calls. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { + struct sock *sk = &u->sk; long total_refs; - long inflight_refs; - total_refs = file_count(u->sk.sk_socket->file); - inflight_refs = atomic_long_read(&u->inflight); + total_refs = file_count(sk->sk_socket->file); - BUG_ON(inflight_refs < 1); - BUG_ON(total_refs < inflight_refs); - if (total_refs == inflight_refs) { + BUG_ON(!u->inflight); + BUG_ON(total_refs < u->inflight); + if (total_refs == u->inflight) { list_move_tail(&u->link, &gc_candidates); __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); + + if (sk->sk_state == TCP_LISTEN) { + unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); + unix_state_unlock(sk); + } } } @@ -271,7 +286,7 @@ void unix_gc(void) /* Move cursor to after the current position. */ list_move(&cursor, &u->link); - if (atomic_long_read(&u->inflight) > 0) { + if (u->inflight) { list_move_tail(&u->link, ¬_cycle_list); __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); scan_children(&u->sk, inc_inflight_move_tail, NULL); diff --git a/net/unix/scm.c b/net/unix/scm.c index 822ce0d0d7915..e92f2fad64105 100644 --- a/net/unix/scm.c +++ b/net/unix/scm.c @@ -53,12 +53,13 @@ void unix_inflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); - if (atomic_long_inc_return(&u->inflight) == 1) { + if (!u->inflight) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); } else { BUG_ON(list_empty(&u->link)); } + u->inflight++; /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); } @@ -75,10 +76,11 @@ void unix_notinflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); - BUG_ON(!atomic_long_read(&u->inflight)); + BUG_ON(!u->inflight); BUG_ON(list_empty(&u->link)); - if (atomic_long_dec_and_test(&u->inflight)) + u->inflight--; + if (!u->inflight) list_del_init(&u->link); /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 1748268e0694f..ee5d306a96d0f 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -120,7 +120,6 @@ virtio_transport_send_pkt_work(struct work_struct *work) if (!skb) break; - virtio_transport_deliver_tap_pkt(skb); reply = virtio_vsock_skb_reply(skb); sgs = vsock->out_sgs; sg_init_one(sgs[out_sg], virtio_vsock_hdr(skb), @@ -170,6 +169,8 @@ virtio_transport_send_pkt_work(struct work_struct *work) break; } + virtio_transport_deliver_tap_pkt(skb); + if (reply) { struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; int val; diff --git a/net/wireless/core.c b/net/wireless/core.c index 3fb1b637352a9..4b1f45e3070e0 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -431,7 +431,7 @@ static void cfg80211_wiphy_work(struct work_struct *work) if (wk) { list_del_init(&wk->entry); if (!list_empty(&rdev->wiphy_work_list)) - schedule_work(work); + queue_work(system_unbound_wq, work); spin_unlock_irq(&rdev->wiphy_work_lock); wk->func(&rdev->wiphy, wk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index bd54a928bab41..4e7b517c78bfd 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9148,6 +9148,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) struct wiphy *wiphy; int err, tmp, n_ssids = 0, n_channels, i; size_t ie_len, size; + size_t ssids_offset, ie_offset; wiphy = &rdev->wiphy; @@ -9193,21 +9194,20 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) return -EINVAL; size = struct_size(request, channels, n_channels); + ssids_offset = size; size = size_add(size, array_size(sizeof(*request->ssids), n_ssids)); + ie_offset = size; size = size_add(size, ie_len); request = kzalloc(size, GFP_KERNEL); if (!request) return -ENOMEM; + request->n_channels = n_channels; if (n_ssids) - request->ssids = (void *)&request->channels[n_channels]; + request->ssids = (void *)request + ssids_offset; request->n_ssids = n_ssids; - if (ie_len) { - if (n_ssids) - request->ie = (void *)(request->ssids + n_ssids); - else - request->ie = (void *)(request->channels + n_channels); - } + if (ie_len) + request->ie = (void *)request + ie_offset; i = 0; if (scan_freqs) { @@ -14092,6 +14092,8 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info) error: for (i = 0; i < new_coalesce.n_rules; i++) { tmp_rule = &new_coalesce.rules[i]; + if (!tmp_rule) + continue; for (j = 0; j < tmp_rule->n_patterns; j++) kfree(tmp_rule->patterns[j].mask); kfree(tmp_rule->patterns); diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index e106dcea39778..c569c37da3175 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -56,7 +56,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.burst_period = 0; if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]) out->ftm.burst_period = - nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]); + nla_get_u16(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]); out->ftm.asap = !!tb[NL80211_PMSR_FTM_REQ_ATTR_ASAP]; if (out->ftm.asap && !capa->ftm.asap) { @@ -75,7 +75,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.num_bursts_exp = 0; if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]) out->ftm.num_bursts_exp = - nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]); + nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]); if (capa->ftm.max_bursts_exponent >= 0 && out->ftm.num_bursts_exp > capa->ftm.max_bursts_exponent) { @@ -88,7 +88,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.burst_duration = 15; if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]) out->ftm.burst_duration = - nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]); + nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]); out->ftm.ftms_per_burst = 0; if (tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]) @@ -107,7 +107,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.ftmr_retries = 3; if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]) out->ftm.ftmr_retries = - nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]); + nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]); out->ftm.request_lci = !!tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI]; if (out->ftm.request_lci && !capa->ftm.request_lci) { diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 389a52c29bfc7..af39962d45a43 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2602,9 +2602,9 @@ cfg80211_defrag_mle(const struct element *mle, const u8 *ie, size_t ielen, } static u8 -cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, - const struct ieee80211_neighbor_ap_info **ap_info, - const u8 **tbtt_info) +cfg80211_rnr_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, + const struct ieee80211_neighbor_ap_info **ap_info, + u8 *param_ch_count) { const struct ieee80211_neighbor_ap_info *info; const struct element *rnr; @@ -2661,7 +2661,9 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, if (mld_id == mld_params->mld_id && link_id == lid) { *ap_info = info; - *tbtt_info = pos; + *param_ch_count = + le16_get_bits(mld_params->params, + IEEE80211_RNR_MLD_PARAMS_BSS_CHANGE_COUNT); return use_for; } @@ -2674,6 +2676,103 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, return 0; } +static struct element * +cfg80211_gen_reporter_rnr(struct cfg80211_bss *source_bss, bool is_mbssid, + bool same_mld, u8 link_id, u8 bss_change_count, + gfp_t gfp) +{ + const struct cfg80211_bss_ies *ies; + struct ieee80211_neighbor_ap_info ap_info; + struct ieee80211_tbtt_info_ge_11 tbtt_info; + u32 short_ssid; + const struct element *elem; + struct element *res; + + /* + * We only generate the RNR to permit ML lookups. For that we do not + * need an entry for the corresponding transmitting BSS, lets just skip + * it even though it would be easy to add. + */ + if (!same_mld) + return NULL; + + /* We could use tx_data->ies if we change cfg80211_calc_short_ssid */ + rcu_read_lock(); + ies = rcu_dereference(source_bss->ies); + + ap_info.tbtt_info_len = offsetofend(typeof(tbtt_info), mld_params); + ap_info.tbtt_info_hdr = + u8_encode_bits(IEEE80211_TBTT_INFO_TYPE_TBTT, + IEEE80211_AP_INFO_TBTT_HDR_TYPE) | + u8_encode_bits(0, IEEE80211_AP_INFO_TBTT_HDR_COUNT); + + ap_info.channel = ieee80211_frequency_to_channel(source_bss->channel->center_freq); + + /* operating class */ + elem = cfg80211_find_elem(WLAN_EID_SUPPORTED_REGULATORY_CLASSES, + ies->data, ies->len); + if (elem && elem->datalen >= 1) { + ap_info.op_class = elem->data[0]; + } else { + struct cfg80211_chan_def chandef; + + /* The AP is not providing us with anything to work with. So + * make up a somewhat reasonable operating class, but don't + * bother with it too much as no one will ever use the + * information. + */ + cfg80211_chandef_create(&chandef, source_bss->channel, + NL80211_CHAN_NO_HT); + + if (!ieee80211_chandef_to_operating_class(&chandef, + &ap_info.op_class)) + goto out_unlock; + } + + /* Just set TBTT offset and PSD 20 to invalid/unknown */ + tbtt_info.tbtt_offset = 255; + tbtt_info.psd_20 = IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED; + + memcpy(tbtt_info.bssid, source_bss->bssid, ETH_ALEN); + if (cfg80211_calc_short_ssid(ies, &elem, &short_ssid)) + goto out_unlock; + + rcu_read_unlock(); + + tbtt_info.short_ssid = cpu_to_le32(short_ssid); + + tbtt_info.bss_params = IEEE80211_RNR_TBTT_PARAMS_SAME_SSID; + + if (is_mbssid) { + tbtt_info.bss_params |= IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID; + tbtt_info.bss_params |= IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID; + } + + tbtt_info.mld_params.mld_id = 0; + tbtt_info.mld_params.params = + le16_encode_bits(link_id, IEEE80211_RNR_MLD_PARAMS_LINK_ID) | + le16_encode_bits(bss_change_count, + IEEE80211_RNR_MLD_PARAMS_BSS_CHANGE_COUNT); + + res = kzalloc(struct_size(res, data, + sizeof(ap_info) + ap_info.tbtt_info_len), + gfp); + if (!res) + return NULL; + + /* Copy the data */ + res->id = WLAN_EID_REDUCED_NEIGHBOR_REPORT; + res->datalen = sizeof(ap_info) + ap_info.tbtt_info_len; + memcpy(res->data, &ap_info, sizeof(ap_info)); + memcpy(res->data + sizeof(ap_info), &tbtt_info, ap_info.tbtt_info_len); + + return res; + +out_unlock: + rcu_read_unlock(); + return NULL; +} + static void cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, struct cfg80211_inform_single_bss_data *tx_data, @@ -2687,13 +2786,14 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, .source_bss = source_bss, .bss_source = BSS_SOURCE_STA_PROFILE, }; + struct element *reporter_rnr = NULL; struct ieee80211_multi_link_elem *ml_elem; struct cfg80211_mle *mle; u16 control; u8 ml_common_len; - u8 *new_ie; + u8 *new_ie = NULL; struct cfg80211_bss *bss; - int mld_id; + u8 mld_id, reporter_link_id, bss_change_count; u16 seen_links = 0; const u8 *pos; u8 i; @@ -2715,8 +2815,14 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, ml_common_len = ml_elem->variable[0]; - /* length + MLD MAC address + link ID info + BSS Params Change Count */ - pos = ml_elem->variable + 1 + 6 + 1 + 1; + /* length + MLD MAC address */ + pos = ml_elem->variable + 1 + 6; + + reporter_link_id = pos[0]; + pos += 1; + + bss_change_count = pos[0]; + pos += 1; if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)) pos += 2; @@ -2747,17 +2853,28 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, if (!mle) return; + /* No point in doing anything if there is no per-STA profile */ + if (!mle->sta_prof[0]) + goto out; + new_ie = kmalloc(IEEE80211_MAX_DATA_LEN, gfp); if (!new_ie) goto out; + reporter_rnr = cfg80211_gen_reporter_rnr(source_bss, + u16_get_bits(control, + IEEE80211_MLC_BASIC_PRES_MLD_ID), + mld_id == 0, reporter_link_id, + bss_change_count, + gfp); + for (i = 0; i < ARRAY_SIZE(mle->sta_prof) && mle->sta_prof[i]; i++) { const struct ieee80211_neighbor_ap_info *ap_info; enum nl80211_band band; u32 freq; const u8 *profile; - const u8 *tbtt_info; ssize_t profile_len; + u8 param_ch_count; u8 link_id, use_for; if (!ieee80211_mle_basic_sta_prof_size_ok((u8 *)mle->sta_prof[i], @@ -2800,10 +2917,11 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, profile_len -= 2; /* Find in RNR to look up channel information */ - use_for = cfg80211_tbtt_info_for_mld_ap(tx_data->ie, - tx_data->ielen, - mld_id, link_id, - &ap_info, &tbtt_info); + use_for = cfg80211_rnr_info_for_mld_ap(tx_data->ie, + tx_data->ielen, + mld_id, link_id, + &ap_info, + ¶m_ch_count); if (!use_for) continue; @@ -2846,7 +2964,8 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, continue; /* Copy the Basic Multi-Link element including the common - * information, and then fix up the link ID. + * information, and then fix up the link ID and BSS param + * change count. * Note that the ML element length has been verified and we * also checked that it contains the link ID. */ @@ -2857,10 +2976,21 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, sizeof(*ml_elem) + ml_common_len); new_ie[data.ielen + sizeof(*ml_elem) + 1 + ETH_ALEN] = link_id; + new_ie[data.ielen + sizeof(*ml_elem) + 1 + ETH_ALEN + 1] = + param_ch_count; data.ielen += sizeof(*ml_elem) + ml_common_len; - /* TODO: Add an RNR containing only the reporting AP */ + if (reporter_rnr && (use_for & NL80211_BSS_USE_FOR_NORMAL)) { + if (data.ielen + sizeof(struct element) + + reporter_rnr->datalen > IEEE80211_MAX_DATA_LEN) + continue; + + memcpy(new_ie + data.ielen, reporter_rnr, + sizeof(struct element) + reporter_rnr->datalen); + data.ielen += sizeof(struct element) + + reporter_rnr->datalen; + } bss = cfg80211_inform_single_bss_data(wiphy, &data, gfp); if (!bss) @@ -2869,6 +2999,7 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, } out: + kfree(reporter_rnr); kfree(new_ie); kfree(mle); } @@ -2937,7 +3068,8 @@ static bool cfg80211_uhb_power_type_valid(const u8 *ie, struct ieee80211_he_operation *he_oper; tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ielen); - if (tmp && tmp->datalen >= sizeof(*he_oper) + 1) { + if (tmp && tmp->datalen >= sizeof(*he_oper) + 1 && + tmp->datalen >= ieee80211_he_oper_size(tmp->data + 1)) { const struct ieee80211_he_6ghz_oper *he_6ghz_oper; he_oper = (void *)&tmp->data[1]; diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 565511a3f461e..62f26618f6747 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -5,7 +5,7 @@ * * Copyright 2005-2006 Jiri Benc * Copyright 2006 Johannes Berg - * Copyright (C) 2020-2021, 2023 Intel Corporation + * Copyright (C) 2020-2021, 2023-2024 Intel Corporation */ #include @@ -137,7 +137,7 @@ static int wiphy_resume(struct device *dev) if (rdev->wiphy.registered && rdev->ops->resume) ret = rdev_resume(rdev); rdev->suspended = false; - schedule_work(&rdev->wiphy_work); + queue_work(system_unbound_wq, &rdev->wiphy_work); wiphy_unlock(&rdev->wiphy); if (ret) diff --git a/net/wireless/tests/scan.c b/net/wireless/tests/scan.c index 77854161cd22b..f9ea44aee9952 100644 --- a/net/wireless/tests/scan.c +++ b/net/wireless/tests/scan.c @@ -2,7 +2,7 @@ /* * KUnit tests for inform_bss functions * - * Copyright (C) 2023 Intel Corporation + * Copyright (C) 2023-2024 Intel Corporation */ #include #include @@ -406,9 +406,27 @@ static struct inform_bss_ml_sta_case { const char *desc; int mld_id; bool sta_prof_vendor_elems; + bool include_oper_class; } inform_bss_ml_sta_cases[] = { - { .desc = "no_mld_id", .mld_id = 0, .sta_prof_vendor_elems = false }, - { .desc = "mld_id_eq_1", .mld_id = 1, .sta_prof_vendor_elems = true }, + { + .desc = "zero_mld_id", + .mld_id = 0, + .sta_prof_vendor_elems = false, + }, { + .desc = "zero_mld_id_with_oper_class", + .mld_id = 0, + .sta_prof_vendor_elems = false, + .include_oper_class = true, + }, { + .desc = "mld_id_eq_1", + .mld_id = 1, + .sta_prof_vendor_elems = true, + }, { + .desc = "mld_id_eq_1_with_oper_class", + .mld_id = 1, + .sta_prof_vendor_elems = true, + .include_oper_class = true, + }, }; KUNIT_ARRAY_PARAM_DESC(inform_bss_ml_sta, inform_bss_ml_sta_cases, desc) @@ -515,6 +533,12 @@ static void test_inform_bss_ml_sta(struct kunit *test) skb_put_u8(input, 4); skb_put_data(input, "TEST", 4); + if (params->include_oper_class) { + skb_put_u8(input, WLAN_EID_SUPPORTED_REGULATORY_CLASSES); + skb_put_u8(input, 1); + skb_put_u8(input, 81); + } + skb_put_u8(input, WLAN_EID_REDUCED_NEIGHBOR_REPORT); skb_put_u8(input, sizeof(rnr)); skb_put_data(input, &rnr, sizeof(rnr)); @@ -582,15 +606,21 @@ static void test_inform_bss_ml_sta(struct kunit *test) KUNIT_EXPECT_EQ(test, ies->tsf, tsf + le64_to_cpu(sta_prof.tsf_offset)); /* Resulting length should be: * SSID (inherited) + RNR (inherited) + vendor element(s) + + * operating class (if requested) + + * generated RNR (if MLD ID == 0) + * MLE common info + MLE header and control */ if (params->sta_prof_vendor_elems) KUNIT_EXPECT_EQ(test, ies->len, 6 + 2 + sizeof(rnr) + 2 + 160 + 2 + 165 + + (params->include_oper_class ? 3 : 0) + + (!params->mld_id ? 22 : 0) + mle_basic_common_info.var_len + 5); else KUNIT_EXPECT_EQ(test, ies->len, 6 + 2 + sizeof(rnr) + 2 + 155 + + (params->include_oper_class ? 3 : 0) + + (!params->mld_id ? 22 : 0) + mle_basic_common_info.var_len + 5); rcu_read_unlock(); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 1f374c8a17a50..0cf8f958081eb 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1013,7 +1013,7 @@ TRACE_EVENT(rdev_get_mpp, TRACE_EVENT(rdev_dump_mpp, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx, u8 *dst, u8 *mpp), - TP_ARGS(wiphy, netdev, _idx, mpp, dst), + TP_ARGS(wiphy, netdev, _idx, dst, mpp), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY @@ -1747,7 +1747,7 @@ TRACE_EVENT(rdev_return_void_tx_rx, DECLARE_EVENT_CLASS(tx_rx_evt, TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx), - TP_ARGS(wiphy, rx, tx), + TP_ARGS(wiphy, tx, rx), TP_STRUCT__entry( WIPHY_ENTRY __field(u32, tx) @@ -1764,7 +1764,7 @@ DECLARE_EVENT_CLASS(tx_rx_evt, DEFINE_EVENT(tx_rx_evt, rdev_set_antenna, TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx), - TP_ARGS(wiphy, rx, tx) + TP_ARGS(wiphy, tx, rx) ); DECLARE_EVENT_CLASS(wiphy_netdev_id_evt, diff --git a/net/wireless/util.c b/net/wireless/util.c index d1ce3bee27973..8b7a650495c21 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -791,15 +791,19 @@ ieee80211_amsdu_subframe_length(void *field, u8 mesh_flags, u8 hdr_type) bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) { - int offset = 0, remaining, subframe_len, padding; + int offset = 0, subframe_len, padding; for (offset = 0; offset < skb->len; offset += subframe_len + padding) { + int remaining = skb->len - offset; struct { __be16 len; u8 mesh_flags; } hdr; u16 len; + if (sizeof(hdr) > remaining) + return false; + if (skb_copy_bits(skb, offset + 2 * ETH_ALEN, &hdr, sizeof(hdr)) < 0) return false; @@ -807,7 +811,6 @@ bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) mesh_hdr); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; - remaining = skb->len - offset; if (subframe_len > remaining) return false; @@ -825,7 +828,7 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, { unsigned int hlen = ALIGN(extra_headroom, 4); struct sk_buff *frame = NULL; - int offset = 0, remaining; + int offset = 0; struct { struct ethhdr eth; uint8_t flags; @@ -839,10 +842,14 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, copy_len = sizeof(hdr); while (!last) { + int remaining = skb->len - offset; unsigned int subframe_len; int len, mesh_len = 0; u8 padding; + if (copy_len > remaining) + goto purge; + skb_copy_bits(skb, offset, &hdr, copy_len); if (iftype == NL80211_IFTYPE_MESH_POINT) mesh_len = __ieee80211_get_mesh_hdrlen(hdr.flags); @@ -852,7 +859,6 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, padding = (4 - subframe_len) & 0x3; /* the last MSDU has no padding */ - remaining = skb->len - offset; if (subframe_len > remaining) goto purge; /* mitigate A-MSDU aggregation injection attacks */ @@ -2467,6 +2473,7 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; + int ret; wdev = dev->ieee80211_ptr; if (!wdev) @@ -2478,7 +2485,11 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, memset(sinfo, 0, sizeof(*sinfo)); - return rdev_get_station(rdev, dev, mac_addr, sinfo); + wiphy_lock(&rdev->wiphy); + ret = rdev_get_station(rdev, dev, mac_addr, sinfo); + wiphy_unlock(&rdev->wiphy); + + return ret; } EXPORT_SYMBOL(cfg80211_get_station); diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index a161c64d1765e..838ad6541a17d 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -4,6 +4,7 @@ * Authors : Jean Tourrilhes - HPL - * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * Copyright 2009 Johannes Berg + * Copyright (C) 2024 Intel Corporation * * (As all part of the Linux kernel, this file is GPL) */ @@ -662,7 +663,8 @@ struct iw_statistics *get_wireless_stats(struct net_device *dev) dev->ieee80211_ptr->wiphy->wext && dev->ieee80211_ptr->wiphy->wext->get_wireless_stats) { wireless_warn_cfg80211_wext(); - if (dev->ieee80211_ptr->wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO) + if (dev->ieee80211_ptr->wiphy->flags & (WIPHY_FLAG_SUPPORTS_MLO | + WIPHY_FLAG_DISABLE_WEXT)) return NULL; return dev->ieee80211_ptr->wiphy->wext->get_wireless_stats(dev); } @@ -704,7 +706,8 @@ static iw_handler get_handler(struct net_device *dev, unsigned int cmd) #ifdef CONFIG_CFG80211_WEXT if (dev->ieee80211_ptr && dev->ieee80211_ptr->wiphy) { wireless_warn_cfg80211_wext(); - if (dev->ieee80211_ptr->wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO) + if (dev->ieee80211_ptr->wiphy->flags & (WIPHY_FLAG_SUPPORTS_MLO | + WIPHY_FLAG_DISABLE_WEXT)) return NULL; handlers = dev->ieee80211_ptr->wiphy->wext; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index f7a7c7798c3b2..d18d51412cc00 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -460,12 +460,12 @@ static int x25_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) goto out; - len = min_t(unsigned int, len, sizeof(int)); - rc = -EINVAL; if (len < 0) goto out; + len = min_t(unsigned int, len, sizeof(int)); + rc = -EFAULT; if (put_user(len, optlen)) goto out; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b78c0e095e221..7d1c0986f9bb3 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1414,6 +1414,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, struct xsk_queue **q; int entries; + if (optlen < sizeof(entries)) + return -EINVAL; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 653e51ae39648..6346690d5c699 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -407,7 +407,8 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; - if (!x->type_offload) + if (!x->type_offload || + (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index bd4ce21d76d75..b2f7af63b7dae 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -388,11 +388,15 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) */ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) { + struct xfrm_offload *xo = xfrm_offload(skb); int ihl = skb->data - skb_transport_header(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), skb_network_header(skb), ihl); + if (xo) + xo->orig_mac_len = + skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0; skb->network_header = skb->transport_header; } ip_hdr(skb)->tot_len = htons(skb->len + ihl); @@ -403,11 +407,15 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) + struct xfrm_offload *xo = xfrm_offload(skb); int ihl = skb->data - skb_transport_header(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), skb_network_header(skb), ihl); + if (xo) + xo->orig_mac_len = + skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0; skb->network_header = skb->transport_header; } ipv6_hdr(skb)->payload_len = htons(skb->len + ihl - diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index da6ecc6b3e153..947a6e695b296 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2597,8 +2597,7 @@ static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { if (dst->ops->family == AF_INET6) { - struct rt6_info *rt = (struct rt6_info *)dst; - path->path_cookie = rt6_get_cookie(rt); + path->path_cookie = rt6_get_cookie(dst_rt6_info(dst)); path->u.rt6.rt6i_nfheader_len = nfheader_len; } } @@ -3765,15 +3764,10 @@ static void xfrm_link_failure(struct sk_buff *skb) /* Impossible. Such dst must be popped before reaches point of failure. */ } -static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) +static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { - if (dst) { - if (dst->obsolete) { - dst_release(dst); - dst = NULL; - } - } - return dst; + if (dst->obsolete) + sk_dst_reset(sk); } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) diff --git a/rust/Makefile b/rust/Makefile index 9d2a16cc91cb4..cd9e5e3fcee86 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -175,7 +175,6 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $< mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \ OBJTREE=$(abspath $(objtree)) \ $(RUSTDOC) --test $(rust_flags) \ - @$(objtree)/include/generated/rustc_cfg \ -L$(objtree)/$(obj) --extern alloc --extern kernel \ --extern build_error --extern macros \ --extern bindings --extern uapi \ diff --git a/rust/alloc/alloc.rs b/rust/alloc/alloc.rs index 150e13750ff70..8a6be8c981731 100644 --- a/rust/alloc/alloc.rs +++ b/rust/alloc/alloc.rs @@ -379,13 +379,20 @@ pub const fn handle_alloc_error(layout: Layout) -> ! { panic!("allocation failed"); } + #[inline] fn rt_error(layout: Layout) -> ! { unsafe { __rust_alloc_error_handler(layout.size(), layout.align()); } } - unsafe { core::intrinsics::const_eval_select((layout,), ct_error, rt_error) } + #[cfg(not(feature = "panic_immediate_abort"))] + unsafe { + core::intrinsics::const_eval_select((layout,), ct_error, rt_error) + } + + #[cfg(feature = "panic_immediate_abort")] + ct_error(layout) } // For alloc test `std::alloc::handle_alloc_error` can be used directly. diff --git a/rust/alloc/boxed.rs b/rust/alloc/boxed.rs index 9620eba172687..f5f40778a1937 100644 --- a/rust/alloc/boxed.rs +++ b/rust/alloc/boxed.rs @@ -161,7 +161,7 @@ use core::marker::Tuple; use core::marker::Unsize; use core::mem::{self, SizedTypeProperties}; use core::ops::{ - CoerceUnsized, Deref, DerefMut, DispatchFromDyn, Generator, GeneratorState, Receiver, + CoerceUnsized, Coroutine, CoroutineState, Deref, DerefMut, DispatchFromDyn, Receiver, }; use core::pin::Pin; use core::ptr::{self, NonNull, Unique}; @@ -211,7 +211,7 @@ impl Box { /// ``` /// let five = Box::new(5); /// ``` - #[cfg(all(not(no_global_oom_handling)))] + #[cfg(not(no_global_oom_handling))] #[inline(always)] #[stable(feature = "rust1", since = "1.0.0")] #[must_use] @@ -2110,28 +2110,28 @@ impl AsMut for Box { #[stable(feature = "pin", since = "1.33.0")] impl Unpin for Box where A: 'static {} -#[unstable(feature = "generator_trait", issue = "43122")] -impl + Unpin, R, A: Allocator> Generator for Box +#[unstable(feature = "coroutine_trait", issue = "43122")] +impl + Unpin, R, A: Allocator> Coroutine for Box where A: 'static, { type Yield = G::Yield; type Return = G::Return; - fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState { + fn resume(mut self: Pin<&mut Self>, arg: R) -> CoroutineState { G::resume(Pin::new(&mut *self), arg) } } -#[unstable(feature = "generator_trait", issue = "43122")] -impl, R, A: Allocator> Generator for Pin> +#[unstable(feature = "coroutine_trait", issue = "43122")] +impl, R, A: Allocator> Coroutine for Pin> where A: 'static, { type Yield = G::Yield; type Return = G::Return; - fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState { + fn resume(mut self: Pin<&mut Self>, arg: R) -> CoroutineState { G::resume((*self).as_mut(), arg) } } @@ -2448,4 +2448,8 @@ impl core::error::Error for Box { fn source(&self) -> Option<&(dyn core::error::Error + 'static)> { core::error::Error::source(&**self) } + + fn provide<'b>(&'b self, request: &mut core::error::Request<'b>) { + core::error::Error::provide(&**self, request); + } } diff --git a/rust/alloc/lib.rs b/rust/alloc/lib.rs index 9c7ea73da1080..345cf5c9cf92d 100644 --- a/rust/alloc/lib.rs +++ b/rust/alloc/lib.rs @@ -80,6 +80,8 @@ not(no_sync), target_has_atomic = "ptr" ))] +#![cfg_attr(not(bootstrap), doc(rust_logo))] +#![cfg_attr(not(bootstrap), feature(rustdoc_internals))] #![no_std] #![needs_allocator] // Lints: @@ -115,7 +117,6 @@ #![feature(const_eval_select)] #![feature(const_maybe_uninit_as_mut_ptr)] #![feature(const_maybe_uninit_write)] -#![feature(const_maybe_uninit_zeroed)] #![feature(const_pin)] #![feature(const_refs_to_cell)] #![feature(const_size_of_val)] @@ -141,7 +142,7 @@ #![feature(maybe_uninit_uninit_array)] #![feature(maybe_uninit_uninit_array_transpose)] #![feature(pattern)] -#![feature(pointer_byte_offsets)] +#![feature(ptr_addr_eq)] #![feature(ptr_internals)] #![feature(ptr_metadata)] #![feature(ptr_sub_ptr)] @@ -168,7 +169,7 @@ // // Language features: // tidy-alphabetical-start -#![cfg_attr(not(test), feature(generator_trait))] +#![cfg_attr(not(test), feature(coroutine_trait))] #![cfg_attr(test, feature(panic_update_hook))] #![cfg_attr(test, feature(test))] #![feature(allocator_internals)] diff --git a/rust/alloc/raw_vec.rs b/rust/alloc/raw_vec.rs index a7425582a323f..f1b8cec8cc626 100644 --- a/rust/alloc/raw_vec.rs +++ b/rust/alloc/raw_vec.rs @@ -338,10 +338,13 @@ impl RawVec { /// The same as `reserve`, but returns on errors instead of panicking or aborting. pub fn try_reserve(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> { if self.needs_to_grow(len, additional) { - self.grow_amortized(len, additional) - } else { - Ok(()) + self.grow_amortized(len, additional)?; + } + unsafe { + // Inform the optimizer that the reservation has succeeded or wasn't needed + core::intrinsics::assume(!self.needs_to_grow(len, additional)); } + Ok(()) } /// The same as `reserve_for_push`, but returns on errors instead of panicking or aborting. @@ -378,7 +381,14 @@ impl RawVec { len: usize, additional: usize, ) -> Result<(), TryReserveError> { - if self.needs_to_grow(len, additional) { self.grow_exact(len, additional) } else { Ok(()) } + if self.needs_to_grow(len, additional) { + self.grow_exact(len, additional)?; + } + unsafe { + // Inform the optimizer that the reservation has succeeded or wasn't needed + core::intrinsics::assume(!self.needs_to_grow(len, additional)); + } + Ok(()) } /// Shrinks the buffer down to the specified capacity. If the given amount @@ -569,6 +579,7 @@ fn alloc_guard(alloc_size: usize) -> Result<(), TryReserveError> { // ensure that the code generation related to these panics is minimal as there's // only one location which panics rather than a bunch throughout the module. #[cfg(not(no_global_oom_handling))] +#[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))] fn capacity_overflow() -> ! { panic!("capacity overflow"); } diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs index 41ca71805ef09..0d95fd7ef3375 100644 --- a/rust/alloc/vec/mod.rs +++ b/rust/alloc/vec/mod.rs @@ -1376,7 +1376,7 @@ impl Vec { /// [`as_mut_ptr`]: Vec::as_mut_ptr /// [`as_ptr`]: Vec::as_ptr #[stable(feature = "vec_as_ptr", since = "1.37.0")] - #[cfg_attr(not(bootstrap), rustc_never_returns_null_ptr)] + #[rustc_never_returns_null_ptr] #[inline] pub fn as_ptr(&self) -> *const T { // We shadow the slice method of the same name to avoid going through @@ -1436,7 +1436,7 @@ impl Vec { /// [`as_mut_ptr`]: Vec::as_mut_ptr /// [`as_ptr`]: Vec::as_ptr #[stable(feature = "vec_as_ptr", since = "1.37.0")] - #[cfg_attr(not(bootstrap), rustc_never_returns_null_ptr)] + #[rustc_never_returns_null_ptr] #[inline] pub fn as_mut_ptr(&mut self) -> *mut T { // We shadow the slice method of the same name to avoid going through @@ -1565,7 +1565,8 @@ impl Vec { #[stable(feature = "rust1", since = "1.0.0")] pub fn swap_remove(&mut self, index: usize) -> T { #[cold] - #[inline(never)] + #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))] + #[track_caller] fn assert_failed(index: usize, len: usize) -> ! { panic!("swap_remove index (is {index}) should be < len (is {len})"); } @@ -1606,7 +1607,8 @@ impl Vec { #[stable(feature = "rust1", since = "1.0.0")] pub fn insert(&mut self, index: usize, element: T) { #[cold] - #[inline(never)] + #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))] + #[track_caller] fn assert_failed(index: usize, len: usize) -> ! { panic!("insertion index (is {index}) should be <= len (is {len})"); } @@ -1667,7 +1669,7 @@ impl Vec { #[track_caller] pub fn remove(&mut self, index: usize) -> T { #[cold] - #[inline(never)] + #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))] #[track_caller] fn assert_failed(index: usize, len: usize) -> ! { panic!("removal index (is {index}) should be < len (is {len})"); @@ -2097,6 +2099,7 @@ impl Vec { } else { unsafe { self.len -= 1; + core::intrinsics::assume(self.len < self.capacity()); Some(ptr::read(self.as_ptr().add(self.len()))) } } @@ -2299,7 +2302,8 @@ impl Vec { A: Clone, { #[cold] - #[inline(never)] + #[cfg_attr(not(feature = "panic_immediate_abort"), inline(never))] + #[track_caller] fn assert_failed(at: usize, len: usize) -> ! { panic!("`at` split index (is {at}) should be <= len (is {len})"); } diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 65be9ae57b80b..cf9575f156a63 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -1292,8 +1292,15 @@ impl_zeroable! { i8, i16, i32, i64, i128, isize, f32, f64, - // SAFETY: These are ZSTs, there is nothing to zero. - {} PhantomData, core::marker::PhantomPinned, Infallible, (), + // Note: do not add uninhabited types (such as `!` or `core::convert::Infallible`) to this list; + // creating an instance of an uninhabited type is immediate undefined behavior. For more on + // uninhabited/empty types, consult The Rustonomicon: + // . The Rust Reference + // also has information on undefined behavior: + // . + // + // SAFETY: These are inhabited ZSTs; there is nothing to zero and a valid value exists. + {} PhantomData, core::marker::PhantomPinned, (), // SAFETY: Type is allowed to take any value, including all zeros. {} MaybeUninit, diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 7ac39874aeac3..780c5a1130b1e 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -14,7 +14,6 @@ #![no_std] #![feature(allocator_api)] #![feature(coerce_unsized)] -#![feature(const_maybe_uninit_zeroed)] #![feature(dispatch_from_dyn)] #![feature(new_uninit)] #![feature(offset_of)] @@ -66,7 +65,7 @@ const __LOG_PREFIX: &[u8] = b"rust_kernel\0"; /// The top level entrypoint to implementing a kernel module. /// /// For any teardown or cleanup operations, your type may implement [`Drop`]. -pub trait Module: Sized + Sync { +pub trait Module: Sized + Sync + Send { /// Called at module initialization time. /// /// Use this method to perform whatever setup or registration your module diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index e457b3c7cb2fc..869797745b82a 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -640,6 +640,10 @@ pub struct Registration { drivers: Pin<&'static mut [DriverVTable]>, } +// SAFETY: The only action allowed in a `Registration` instance is dropping it, which is safe to do +// from any thread because `phy_drivers_unregister` can be called from any thread context. +unsafe impl Send for Registration {} + impl Registration { /// Registers a PHY driver. pub fn register( diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index f489f31573832..520eae5fd7928 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -35,18 +35,6 @@ use proc_macro::TokenStream; /// author: "Rust for Linux Contributors", /// description: "My very own kernel module!", /// license: "GPL", -/// params: { -/// my_i32: i32 { -/// default: 42, -/// permissions: 0o000, -/// description: "Example of i32", -/// }, -/// writeable_i32: i32 { -/// default: 42, -/// permissions: 0o644, -/// description: "Example of i32", -/// }, -/// }, /// } /// /// struct MyModule; diff --git a/rust/macros/module.rs b/rust/macros/module.rs index d62d8710d77ab..acd0393b50957 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -199,17 +199,6 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { /// Used by the printing macros, e.g. [`info!`]. const __LOG_PREFIX: &[u8] = b\"{name}\\0\"; - /// The \"Rust loadable module\" mark. - // - // This may be best done another way later on, e.g. as a new modinfo - // key or a new section. For the moment, keep it simple. - #[cfg(MODULE)] - #[doc(hidden)] - #[used] - static __IS_RUST_MODULE: () = (); - - static mut __MOD: Option<{type_}> = None; - // SAFETY: `__this_module` is constructed by the kernel at load time and will not be // freed until the module is unloaded. #[cfg(MODULE)] @@ -221,76 +210,132 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { kernel::ThisModule::from_ptr(core::ptr::null_mut()) }}; - // Loadable modules need to export the `{{init,cleanup}}_module` identifiers. - #[cfg(MODULE)] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn init_module() -> core::ffi::c_int {{ - __init() - }} - - #[cfg(MODULE)] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn cleanup_module() {{ - __exit() - }} + // Double nested modules, since then nobody can access the public items inside. + mod __module_init {{ + mod __module_init {{ + use super::super::{type_}; + + /// The \"Rust loadable module\" mark. + // + // This may be best done another way later on, e.g. as a new modinfo + // key or a new section. For the moment, keep it simple. + #[cfg(MODULE)] + #[doc(hidden)] + #[used] + static __IS_RUST_MODULE: () = (); + + static mut __MOD: Option<{type_}> = None; + + // Loadable modules need to export the `{{init,cleanup}}_module` identifiers. + /// # Safety + /// + /// This function must not be called after module initialization, because it may be + /// freed after that completes. + #[cfg(MODULE)] + #[doc(hidden)] + #[no_mangle] + #[link_section = \".init.text\"] + pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{ + // SAFETY: This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name. + unsafe {{ __init() }} + }} - // Built-in modules are initialized through an initcall pointer - // and the identifiers need to be unique. - #[cfg(not(MODULE))] - #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] - #[doc(hidden)] - #[link_section = \"{initcall_section}\"] - #[used] - pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init; + #[cfg(MODULE)] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn cleanup_module() {{ + // SAFETY: + // - This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name, + // - furthermore it is only called after `init_module` has returned `0` + // (which delegates to `__init`). + unsafe {{ __exit() }} + }} - #[cfg(not(MODULE))] - #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)] - core::arch::global_asm!( - r#\".section \"{initcall_section}\", \"a\" - __{name}_initcall: - .long __{name}_init - . - .previous - \"# - ); + // Built-in modules are initialized through an initcall pointer + // and the identifiers need to be unique. + #[cfg(not(MODULE))] + #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] + #[doc(hidden)] + #[link_section = \"{initcall_section}\"] + #[used] + pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init; + + #[cfg(not(MODULE))] + #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)] + core::arch::global_asm!( + r#\".section \"{initcall_section}\", \"a\" + __{name}_initcall: + .long __{name}_init - . + .previous + \"# + ); + + #[cfg(not(MODULE))] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{ + // SAFETY: This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // placement above in the initcall section. + unsafe {{ __init() }} + }} - #[cfg(not(MODULE))] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{ - __init() - }} + #[cfg(not(MODULE))] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn __{name}_exit() {{ + // SAFETY: + // - This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name, + // - furthermore it is only called after `__{name}_init` has returned `0` + // (which delegates to `__init`). + unsafe {{ __exit() }} + }} - #[cfg(not(MODULE))] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn __{name}_exit() {{ - __exit() - }} + /// # Safety + /// + /// This function must only be called once. + unsafe fn __init() -> core::ffi::c_int {{ + match <{type_} as kernel::Module>::init(&super::super::THIS_MODULE) {{ + Ok(m) => {{ + // SAFETY: No data race, since `__MOD` can only be accessed by this + // module and there only `__init` and `__exit` access it. These + // functions are only called once and `__exit` cannot be called + // before or during `__init`. + unsafe {{ + __MOD = Some(m); + }} + return 0; + }} + Err(e) => {{ + return e.to_errno(); + }} + }} + }} - fn __init() -> core::ffi::c_int {{ - match <{type_} as kernel::Module>::init(&THIS_MODULE) {{ - Ok(m) => {{ + /// # Safety + /// + /// This function must + /// - only be called once, + /// - be called after `__init` has been called and returned `0`. + unsafe fn __exit() {{ + // SAFETY: No data race, since `__MOD` can only be accessed by this module + // and there only `__init` and `__exit` access it. These functions are only + // called once and `__init` was already called. unsafe {{ - __MOD = Some(m); + // Invokes `drop()` on `__MOD`, which should be used for cleanup. + __MOD = None; }} - return 0; - }} - Err(e) => {{ - return e.to_errno(); }} - }} - }} - fn __exit() {{ - unsafe {{ - // Invokes `drop()` on `__MOD`, which should be used for cleanup. - __MOD = None; + {modinfo} }} }} - - {modinfo} ", type_ = info.type_, name = info.name, diff --git a/samples/landlock/sandboxer.c b/samples/landlock/sandboxer.c index 08596c0ef0707..e6c59f688573a 100644 --- a/samples/landlock/sandboxer.c +++ b/samples/landlock/sandboxer.c @@ -151,7 +151,7 @@ static int populate_ruleset_net(const char *const env_var, const int ruleset_fd, const __u64 allowed_access) { int ret = 1; - char *env_port_name, *strport; + char *env_port_name, *env_port_name_next, *strport; struct landlock_net_port_attr net_port = { .allowed_access = allowed_access, .port = 0, @@ -163,7 +163,8 @@ static int populate_ruleset_net(const char *const env_var, const int ruleset_fd, env_port_name = strdup(env_port_name); unsetenv(env_var); - while ((strport = strsep(&env_port_name, ENV_DELIMITER))) { + env_port_name_next = env_port_name; + while ((strport = strsep(&env_port_name_next, ENV_DELIMITER))) { net_port.port = atoi(strport); if (landlock_add_rule(ruleset_fd, LANDLOCK_RULE_NET_PORT, &net_port, 0)) { diff --git a/scripts/Makefile.build b/scripts/Makefile.build index dae447a1ad30c..1633175846dfc 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -272,7 +272,7 @@ rust_common_cmd = \ -Zallow-features=$(rust_allowed_features) \ -Zcrate-attr=no_std \ -Zcrate-attr='feature($(rust_allowed_features))' \ - --extern alloc --extern kernel \ + -Zunstable-options --extern force:alloc --extern kernel \ --crate-type rlib -L $(objtree)/rust/ \ --crate-name $(basename $(notdir $@)) \ --sysroot=/dev/null \ diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index a9e552a1e9105..5660b96213e4b 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -114,6 +114,8 @@ KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) +KBUILD_CFLAGS += -Wno-override-init # alias for -Wno-initializer-overrides in clang + ifdef CONFIG_CC_IS_CLANG # Clang before clang-16 would warn on default argument promotions. ifneq ($(call clang-min-version, 160000),y) @@ -132,6 +134,8 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) KBUILD_CFLAGS += $(call cc-disable-warning, cast-function-type-strict) +KBUILD_CFLAGS += -Wno-enum-compare-conditional +KBUILD_CFLAGS += -Wno-enum-enum-conversion endif endif @@ -149,10 +153,6 @@ KBUILD_CFLAGS += -Wtype-limits KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized) KBUILD_CFLAGS += $(call cc-option, -Wunused-macros) -ifdef CONFIG_CC_IS_CLANG -KBUILD_CFLAGS += -Winitializer-overrides -endif - KBUILD_CPPFLAGS += -DKBUILD_EXTRA_WARN2 else @@ -162,9 +162,7 @@ KBUILD_CFLAGS += -Wno-missing-field-initializers KBUILD_CFLAGS += -Wno-type-limits KBUILD_CFLAGS += -Wno-shift-negative-value -ifdef CONFIG_CC_IS_CLANG -KBUILD_CFLAGS += -Wno-initializer-overrides -else +ifdef CONFIG_CC_IS_GCC KBUILD_CFLAGS += -Wno-maybe-uninitialized endif diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index cd5b181060f15..52efc520ae4fa 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -175,7 +175,7 @@ endif ifeq ($(CONFIG_UBSAN),y) _c_flags += $(if $(patsubst n%,, \ - $(UBSAN_SANITIZE_$(basetarget).o)$(UBSAN_SANITIZE)$(CONFIG_UBSAN_SANITIZE_ALL)), \ + $(UBSAN_SANITIZE_$(basetarget).o)$(UBSAN_SANITIZE)y), \ $(CFLAGS_UBSAN)) endif diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 8568d256d6fbf..79fcf27316864 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -23,7 +23,7 @@ modname = $(notdir $(@:.mod.o=)) part-of-module = y quiet_cmd_cc_o_c = CC [M] $@ - cmd_cc_o_c = $(CC) $(filter-out $(CC_FLAGS_CFI) $(CFLAGS_GCOV), $(c_flags)) -c -o $@ $< + cmd_cc_o_c = $(CC) $(filter-out $(CC_FLAGS_CFI) $(CFLAGS_GCOV) $(CFLAGS_KCSAN), $(c_flags)) -c -o $@ $< %.mod.o: %.mod.c FORCE $(call if_changed_dep,cc_o_c) diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 0afd75472679f..f573ec14e9aee 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -53,7 +53,9 @@ $(foreach x, % :, $(if $(findstring $x, $(dst)), \ suffix-y := suffix-$(CONFIG_MODULE_COMPRESS_GZIP) := .gz suffix-$(CONFIG_MODULE_COMPRESS_XZ) := .xz -suffix-$(CONFIG_MODULE_COMPRESS_ZSTD) := .zst +## UBUNTU: Support, but do not require zstd compressed modules +# Many external dkms and signing rely on uncompressed modules +# suffix-$(CONFIG_MODULE_COMPRESS_ZSTD) := .zst modules := $(patsubst $(extmod_prefix)%.o, $(dst)/%.ko$(suffix-y), $(modules)) install-$(CONFIG_MODULES) += $(modules) @@ -101,8 +103,11 @@ else sig-key := $(CONFIG_MODULE_SIG_KEY) endif quiet_cmd_sign = SIGN $@ - cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \ - $(if $(KBUILD_EXTMOD),|| true) + cmd_sign = if test -e $(srctree)/debian/scripts/sign-module && \ + $(srctree)/debian/scripts/sign-module $@ ; \ + then scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(sig-key) certs/signing_key.x509 $@ \ + $(if $(KBUILD_EXTMOD),|| true) ; \ + fi ifeq ($(sign-only),) diff --git a/scripts/Makefile.vdsoinst b/scripts/Makefile.vdsoinst index c477d17b0aa5b..a81ca735003e4 100644 --- a/scripts/Makefile.vdsoinst +++ b/scripts/Makefile.vdsoinst @@ -21,7 +21,7 @@ $$(dest): $$(src) FORCE $$(call cmd,install) # Some architectures create .build-id symlinks -ifneq ($(filter arm sparc x86, $(SRCARCH)),) +ifneq ($(filter arm s390 sparc x86, $(SRCARCH)),) link := $(install-dir)/.build-id/$$(shell $(READELF) -n $$(src) | sed -n 's@^.*Build ID: \(..\)\(.*\)@\1/\2@p').debug __default: $$(link) diff --git a/scripts/atomic/kerneldoc/sub_and_test b/scripts/atomic/kerneldoc/sub_and_test index d3760f7749d4e..96615e50836b0 100644 --- a/scripts/atomic/kerneldoc/sub_and_test +++ b/scripts/atomic/kerneldoc/sub_and_test @@ -1,7 +1,7 @@ cat < ) { chomp; if ($state == 0) { - $state = 1 if ($_ =~ /static const struct modversion_info/); + $state = 1 if ($_ =~ /static const char ____versions/); next; } if ($state == 1) { - $state = 2 if ($_ =~ /__attribute__\(\(section\("__versions"\)\)\)/); + $state = 2 if ($_ =~ /__used __section\("__versions"\)/); next; } if ($state == 2) { - if ( $_ !~ /0x[0-9a-f]+,/ ) { + if ( $_ !~ /\\0"/ ) { + last if ($_ =~ /;/); next; } - my $sym = (split /([,"])/,)[4]; + my $sym = (split /(["\\])/,)[2]; my ($module, $value, $symbol, $gpl) = @{$SYMBOL{$sym}}; $SYMBOL{ $sym } = [ $module, $value+1, $symbol, $gpl]; push(@{$MODULE{$thismod}} , $sym); diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c index c5c2ce113c923..d20c47d21ad83 100644 --- a/scripts/gcc-plugins/stackleak_plugin.c +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -467,6 +467,8 @@ static bool stackleak_gate(void) return false; if (STRING_EQUAL(section, ".entry.text")) return false; + if (STRING_EQUAL(section, ".head.text")) + return false; } return track_frame_size >= 0; diff --git a/scripts/insert-sys-cert.c b/scripts/insert-sys-cert.c index 8902836c23424..6c6120dad676a 100644 --- a/scripts/insert-sys-cert.c +++ b/scripts/insert-sys-cert.c @@ -7,7 +7,8 @@ * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. * - * Usage: insert-sys-cert [-s -b -c + * Usage: insert-sys-cert [-s ] -b -c + * [-s ] -z -c */ #define _GNU_SOURCE @@ -257,6 +258,169 @@ static char *read_file(char *file_name, int *size) return buf; } +static void get_payload_info(char *bzimage, int *offset, int *size) +{ + unsigned int system_offset; + unsigned char setup_sectors; + + setup_sectors = bzimage[0x1f1] + 1; + system_offset = setup_sectors * 512; + *offset = system_offset + *((int*)&bzimage[0x248]); + *size = *((int*)&bzimage[0x24c]); +} + +static void update_payload_info(char* bzimage, int new_size) +{ + int offset, size; + get_payload_info(bzimage, &offset, &size); + *((int*)&bzimage[0x24c]) = new_size; + if (new_size < size) + memset(bzimage + offset + new_size, 0, size - new_size); +} + +struct zipper { + unsigned char pattern[10]; + int length; + char *command; + char *compress; +}; + +struct zipper zippers[] = { + {{0x7F,'E','L','F'}, 4, "cat", "cat"}, + {{0x1F,0x8B}, 2, "gunzip", "gzip -n -f -9"}, + {{0xFD,'7','z','X','Z',0}, 6, "unxz", "xz"}, + {{'B','Z','h'},3, "bunzip2", "bzip2 -9"}, + {{0xFF,'L','Z','M','A',0}, 6, "unlzma", "lzma -9"}, + {{0xD3,'L','Z','O',0,'\r','\n',0x20,'\n'}, 9, "lzop -d", "lzop -9"} +}; + +static struct zipper* get_zipper(char *p) { + int i; + for (i = 0; i < sizeof(zippers)/sizeof(struct zipper); i++) { + if (memcmp(p, zippers[i].pattern, zippers[i].length) == 0) + return &zippers[i]; + } + return NULL; +} + +/* + * This only works for x86 bzImage + */ +static void extract_vmlinux(char *bzimage, int bzimage_size, + char **file, struct zipper **zipper) +{ + int r; + char src[15] = "vmlinux-XXXXXX"; + char dest[15] = "vmlinux-XXXXXX"; + char cmd[100]; + int src_fd, dest_fd; + int offset, size; + struct zipper *z; + + /* TODO: verify that bzImage is supported */ + + get_payload_info(bzimage, &offset, &size); + z = get_zipper(bzimage + offset); + if (z == NULL) { + err("Unable to determine the compression of vmlinux\n"); + return; + } + + src_fd = mkstemp(src); + if (src_fd == -1) { + perror("Could not create temp file"); + return; + } + + r = write(src_fd, bzimage + offset, size); + if (r != size) { + perror("Could not write vmlinux"); + return; + } + dest_fd = mkstemp(dest); + if (dest_fd == -1) { + perror("Could not create temp file"); + return; + } + + snprintf(cmd, sizeof(cmd), "%s <%s >%s", z->command, src, dest); + info("Executing: %s\n", cmd); + r = system(cmd); + if (r!=0) + warn("Possible errors when extracting\n"); + + r = remove(src); + if (r!=0) + perror(src); + + *file = strdup(dest); + *zipper = z; +} + +static void repack_image(char *bzimage, int bzimage_size, + char* vmlinux_file, struct zipper *z) +{ + char tmp[15] = "vmlinux-XXXXXX"; + char cmd[100]; + int fd; + struct stat st; + int new_size; + int r; + int offset, size; + + get_payload_info(bzimage, &offset, &size); + + fd = mkstemp(tmp); + if (fd == -1) { + perror("Could not create temp file"); + return; + } + snprintf(cmd, sizeof(cmd), "%s <%s >%s", + z->compress, vmlinux_file, tmp); + + info("Executing: %s\n", cmd); + r = system(cmd); + if (r!=0) + warn("Possible errors when compressing\n"); + + r = remove(vmlinux_file); + if (r!=0) + perror(vmlinux_file); + + if (fstat(fd, &st)) { + perror("Could not determine file size"); + close(fd); + + } + new_size = st.st_size; + if (new_size > size) { + err("Increase in compressed size is not supported.\n"); + err("Old size was %d, new size is %d\n", size, new_size); + exit(EXIT_FAILURE); + } + + r = read(fd, bzimage + offset, new_size); + if (r != new_size) + perror(tmp); + + r = remove(tmp); + if (r!=0) + perror(tmp); + + /* x86 specific patching of bzimage */ + update_payload_info(bzimage, new_size); + + /* TODO: update CRC */ + +} + +static void fill_random(unsigned char *p, int n) { + srand(0); + int i; + for (i = 0; i < n; i++) + p[i] = rand(); +} + static void print_sym(Elf_Ehdr *hdr, struct sym *s) { info("sym: %s\n", s->name); @@ -267,18 +431,23 @@ static void print_sym(Elf_Ehdr *hdr, struct sym *s) static void print_usage(char *e) { - printf("Usage %s [-s ] -b -c \n", e); + printf("Usage: %s [-s ] -b -c \n", e); + printf(" %s [-s ] -z -c \n", e); } int main(int argc, char **argv) { char *system_map_file = NULL; char *vmlinux_file = NULL; + char *bzimage_file = NULL; char *cert_file = NULL; int vmlinux_size; + int bzimage_size; int cert_size; Elf_Ehdr *hdr; char *cert; + char *bzimage = NULL; + struct zipper *z = NULL; FILE *system_map; unsigned long *lsize; int *used; @@ -286,7 +455,7 @@ int main(int argc, char **argv) Elf_Shdr *symtab = NULL; struct sym cert_sym, lsize_sym, used_sym; - while ((opt = getopt(argc, argv, "b:c:s:")) != -1) { + while ((opt = getopt(argc, argv, "b:z:c:s:")) != -1) { switch (opt) { case 's': system_map_file = optarg; @@ -294,6 +463,9 @@ int main(int argc, char **argv) case 'b': vmlinux_file = optarg; break; + case 'z': + bzimage_file = optarg; + break; case 'c': cert_file = optarg; break; @@ -302,7 +474,9 @@ int main(int argc, char **argv) } } - if (!vmlinux_file || !cert_file) { + if (!cert_file || + (!vmlinux_file && !bzimage_file) || + (vmlinux_file && bzimage_file)) { print_usage(argv[0]); exit(EXIT_FAILURE); } @@ -311,6 +485,16 @@ int main(int argc, char **argv) if (!cert) exit(EXIT_FAILURE); + if (bzimage_file) { + bzimage = map_file(bzimage_file, &bzimage_size); + if (!bzimage) + exit(EXIT_FAILURE); + + extract_vmlinux(bzimage, bzimage_size, &vmlinux_file, &z); + if (!vmlinux_file) + exit(EXIT_FAILURE); + } + hdr = map_file(vmlinux_file, &vmlinux_size); if (!hdr) exit(EXIT_FAILURE); @@ -386,7 +570,7 @@ int main(int argc, char **argv) } /* If the existing cert is the same, don't overwrite */ - if (cert_size == *used && + if (cert_size > 0 && cert_size == *used && strncmp(cert_sym.content, cert, cert_size) == 0) { warn("Certificate was already inserted.\n"); exit(EXIT_SUCCESS); @@ -396,9 +580,11 @@ int main(int argc, char **argv) warn("Replacing previously inserted certificate.\n"); memcpy(cert_sym.content, cert, cert_size); + if (cert_size < cert_sym.size) - memset(cert_sym.content + cert_size, - 0, cert_sym.size - cert_size); + /* This makes the reserved space incompressable */ + fill_random(cert_sym.content + cert_size, + cert_sym.size - cert_size); *lsize = *lsize + cert_size - *used; *used = cert_size; @@ -406,5 +592,15 @@ int main(int argc, char **argv) cert_sym.address); info("Used %d bytes out of %d bytes reserved.\n", *used, cert_sym.size); + + if (munmap(hdr, vmlinux_size) == -1) { + perror(vmlinux_file); + exit(EXIT_FAILURE); + } + + if (bzimage) { + repack_image(bzimage, bzimage_size, vmlinux_file, z); + } + exit(EXIT_SUCCESS); } diff --git a/scripts/kconfig/lexer.l b/scripts/kconfig/lexer.l index cc386e4436834..2c2b3e6f248ca 100644 --- a/scripts/kconfig/lexer.l +++ b/scripts/kconfig/lexer.l @@ -302,8 +302,11 @@ static char *expand_token(const char *in, size_t n) new_string(); append_string(in, n); - /* get the whole line because we do not know the end of token. */ - while ((c = input()) != EOF) { + /* + * get the whole line because we do not know the end of token. + * input() returns 0 (not EOF!) when it reachs the end of file. + */ + while ((c = input()) != 0) { if (c == '\n') { unput(c); break; diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h index 5cdc8f5e6446a..f0fb64790992b 100644 --- a/scripts/kconfig/lkc.h +++ b/scripts/kconfig/lkc.h @@ -46,7 +46,9 @@ void set_all_choice_values(struct symbol *csym); /* confdata.c and expr.c */ static inline void xfwrite(const void *str, size_t len, size_t count, FILE *out) { - assert(len != 0); + //assert(len != 0); + if (len == 0) + return; if (fwrite(str, len, count, out) != count) fprintf(stderr, "Error in writing or end of file.\n"); diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index e9e9fb8d86746..0d419b2c4ac58 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -13,18 +13,21 @@ struct symbol symbol_yes = { .name = "y", + .type = S_TRISTATE, .curr = { "y", yes }, .flags = SYMBOL_CONST|SYMBOL_VALID, }; struct symbol symbol_mod = { .name = "m", + .type = S_TRISTATE, .curr = { "m", mod }, .flags = SYMBOL_CONST|SYMBOL_VALID, }; struct symbol symbol_no = { .name = "n", + .type = S_TRISTATE, .curr = { "n", no }, .flags = SYMBOL_CONST|SYMBOL_VALID, }; @@ -786,8 +789,7 @@ const char *sym_get_string_value(struct symbol *sym) case no: return "n"; case mod: - sym_calc_value(modules_sym); - return (modules_sym->curr.tri == no) ? "n" : "m"; + return "m"; case yes: return "y"; } diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh index 9faa4d3d91e35..ef6f286a4d47f 100755 --- a/scripts/min-tool-version.sh +++ b/scripts/min-tool-version.sh @@ -33,7 +33,7 @@ llvm) fi ;; rustc) - echo 1.74.1 + echo 1.75.0 ;; bindgen) echo 0.65.1 diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 267b9a0a3abcd..00c464dd33c4a 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1007,6 +1007,8 @@ static Elf_Sym *find_fromsym(struct elf_info *elf, Elf_Addr addr, static Elf_Sym *find_tosym(struct elf_info *elf, Elf_Addr addr, Elf_Sym *sym) { + Elf_Sym *new_sym; + /* If the supplied symbol has a valid name, return it */ if (is_valid_name(elf, sym)) return sym; @@ -1015,8 +1017,9 @@ static Elf_Sym *find_tosym(struct elf_info *elf, Elf_Addr addr, Elf_Sym *sym) * Strive to find a better symbol name, but the resulting name may not * match the symbol referenced in the original code. */ - return symsearch_find_nearest(elf, addr, get_secindex(elf, sym), - true, 20); + new_sym = symsearch_find_nearest(elf, addr, get_secindex(elf, sym), + true, 20); + return new_sym ? new_sym : sym; } static bool is_executable_section(struct elf_info *elf, unsigned int secndx) @@ -1050,7 +1053,9 @@ static void default_mismatch_handler(const char *modname, struct elf_info *elf, sec_mismatch_count++; warn("%s: section mismatch in reference: %s+0x%x (section: %s) -> %s (section: %s)\n", - modname, fromsym, (unsigned int)(faddr - from->st_value), fromsec, tosym, tosec); + modname, fromsym, + (unsigned int)(faddr - (from ? from->st_value : 0)), + fromsec, tosym, tosec); if (mismatch->mismatch == EXTABLE_TO_NON_TEXT) { if (match(tosec, mismatch->bad_tosec)) @@ -1647,10 +1652,11 @@ static void read_symbols(const char *modname) namespace = get_next_modinfo(&info, "import_ns", namespace); } + + if (extra_warn && !get_modinfo(&info, "description")) + warn("missing MODULE_DESCRIPTION() in %s\n", modname); } - if (extra_warn && !get_modinfo(&info, "description")) - warn("missing MODULE_DESCRIPTION() in %s\n", modname); for (sym = info.symtab_start; sym < info.symtab_stop; sym++) { symname = remove_dot(info.strtab + sym->st_name); @@ -1900,13 +1906,17 @@ static void add_exported_symbols(struct buffer *buf, struct module *mod) static void add_versions(struct buffer *b, struct module *mod) { struct symbol *s; + unsigned int name_len; + unsigned int name_len_padded; + unsigned int tmp; + unsigned char *tmp_view = (unsigned char *)&tmp; if (!modversions) return; buf_printf(b, "\n"); - buf_printf(b, "static const struct modversion_info ____versions[]\n"); - buf_printf(b, "__used __section(\"__versions\") = {\n"); + buf_printf(b, "static const char ____versions[]\n"); + buf_printf(b, "__used __section(\"__versions\") =\n"); list_for_each_entry(s, &mod->unresolved_symbols, list) { if (!s->module) @@ -1916,16 +1926,27 @@ static void add_versions(struct buffer *b, struct module *mod) s->name, mod->name); continue; } - if (strlen(s->name) >= MODULE_NAME_LEN) { - error("too long symbol \"%s\" [%s.ko]\n", - s->name, mod->name); - break; - } - buf_printf(b, "\t{ %#8x, \"%s\" },\n", - s->crc, s->name); + name_len = strlen(s->name); + name_len_padded = (name_len + 1 + 3) & ~3; + + /* Offset to next entry */ + tmp = 8 + name_len_padded; + tmp = TO_NATIVE(tmp); + buf_printf(b, "\t\"\\x%02x\\x%02x\\x%02x\\x%02x", + tmp_view[0], tmp_view[1], tmp_view[2], tmp_view[3]); + + tmp = TO_NATIVE(s->crc); + buf_printf(b, "\\x%02x\\x%02x\\x%02x\\x%02x\"\n", + tmp_view[0], tmp_view[1], tmp_view[2], tmp_view[3]); + + buf_printf(b, "\t\"%s", s->name); + for (; name_len < name_len_padded; name_len++) + buf_printf(b, "\\0"); + buf_printf(b, "\"\n"); } - buf_printf(b, "};\n"); + /* Always end with a NULL entry */ + buf_printf(b, "\t\"\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\";\n"); } static void add_depends(struct buffer *b, struct module *mod) diff --git a/scripts/module.lds.S b/scripts/module.lds.S index bf5bcf2836d81..89ff01a22634f 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -13,6 +13,7 @@ SECTIONS { /DISCARD/ : { *(.discard) *(.discard.*) + *(.export_symbol) } __ksymtab 0 : { *(SORT(___ksymtab+*)) } diff --git a/security/Kconfig b/security/Kconfig index 52c9af08ad35d..2a4686048fffd 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -19,6 +19,15 @@ config SECURITY_DMESG_RESTRICT If you are unsure how to answer this question, answer N. +config SECURITY_PERF_EVENTS_RESTRICT + bool "Restrict unprivileged use of performance events" + depends on PERF_EVENTS + help + If you say Y here, the kernel.perf_event_paranoid sysctl + will be set to 3 by default, and no unprivileged use of the + perf_event_open syscall will be permitted unless it is + changed. + config SECURITY bool "Enable different security models" depends on SYSFS diff --git a/security/apparmor/Kconfig b/security/apparmor/Kconfig index 64cc3044a42ce..daa459a971d4e 100644 --- a/security/apparmor/Kconfig +++ b/security/apparmor/Kconfig @@ -105,6 +105,18 @@ config SECURITY_APPARMOR_PARANOID_LOAD includes policy, and has some form of integrity check. Disabling the check will speed up policy loads. +config SECURITY_APPARMOR_RESTRICT_USERNS + bool "Restrict user namespace creation to confined domains" + depends on SECURITY_APPARMOR && USER_NS + default y + help + This options allows controlling whether apparmor restricts + the creation of new user namespaces to confined tasks by + default. If set unconfined tasks without CAP_SYS_ADMIN + will not be allowed to create new user namespaces. Confined + tasks ability to create new user namespaces will be controlled + by their profile. + config SECURITY_APPARMOR_KUNIT_TEST tristate "Build KUnit tests for policy_unpack.c" if !KUNIT_ALL_TESTS depends on KUNIT && SECURITY_APPARMOR diff --git a/security/apparmor/Makefile b/security/apparmor/Makefile index b9c5879dd5995..fd72f6b7702ec 100644 --- a/security/apparmor/Makefile +++ b/security/apparmor/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_SECURITY_APPARMOR) += apparmor.o apparmor-y := apparmorfs.o audit.o capability.o task.o ipc.o lib.o match.o \ path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \ resource.o secid.o file.o policy_ns.o label.o mount.o net.o \ - policy_compat.o + policy_compat.o af_unix.o af_inet.o notify.o apparmor-$(CONFIG_SECURITY_APPARMOR_HASH) += crypto.o obj-$(CONFIG_SECURITY_APPARMOR_KUNIT_TEST) += apparmor_policy_unpack_test.o diff --git a/security/apparmor/af_inet.c b/security/apparmor/af_inet.c new file mode 100644 index 0000000000000..57b710054a765 --- /dev/null +++ b/security/apparmor/af_inet.c @@ -0,0 +1,856 @@ +/* + * AppArmor security module + * + * This file contains AppArmor inet fine grained mediation + * + * Copyright 2024 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include + +#include "include/audit.h" +#include "include/af_inet.h" +#include "include/apparmor.h" +#include "include/file.h" +#include "include/label.h" +#include "include/path.h" +#include "include/policy.h" +#include "include/cred.h" + + + +static inline aa_state_t RULE_MEDIATES_SK(struct aa_ruleset *rules, + struct sock *sk) +{ + return RULE_MEDIATES_AF(rules, sk->sk_family); +} + + +enum addr_type { + ADDR_LOCAL = 0, + ADDR_LOCAL_PRIV = 1, + ADDR_REMOTE = 2, +}; + +struct match_addr { + const char *addrp; + enum addr_type addrtype; + int len; + __be16 port; +}; + +struct stored_match_addr { + union { + struct sockaddr addr; + struct sockaddr_in addr4; + struct sockaddr_in6 addr6; + }; + int addrlen; + struct match_addr maddr; +}; + +static void set_ad_create(struct apparmor_audit_data *ad, + int family, int type, int protocol) +{ + ad->common.u.net->family = family; + ad->net.type = type; + ad->net.protocol = protocol; +} + +static int set_ad_addr(struct apparmor_audit_data *ad, + u16 family, bool source, struct match_addr *maddr) +{ + ad->common.u.net->family = family; + + if (source) { + ad->common.u.net->sport = maddr->port; + if (maddr->addrp) { + if (family == AF_INET) + //ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; + ad->common.u.net->v4info.saddr = *(__be32 *)maddr->addrp; + else + //ad.u.net->v4info.saddr = addr6->sin6_addr.s6_addr; + ad->common.u.net->v6info.saddr = *(struct in6_addr *)maddr->addrp; + } + } else { + ad->common.u.net->dport = maddr->port; + if (maddr->addrp) { + if (family == AF_INET) + //ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; + ad->common.u.net->v4info.daddr = *(__be32 *)maddr->addrp; + else + //ad.u.net->v4info.saddr = addr6->sin6_addr.s6_addr; + ad->common.u.net->v6info.daddr = *(struct in6_addr *)maddr->addrp; + } + } + return 0; +} + +/* returns 0 on success +* raw_port - if set raw_port (protocol) when SOCK_RAW */ +static int map_addr(struct sockaddr *addr, int addrlen, u16 raw_port, + enum addr_type addrtype, struct match_addr *maddr, + struct apparmor_audit_data *ad) +{ + struct sockaddr_in *addr4 = NULL; + struct sockaddr_in6 *addr6 = NULL; + + AA_BUG(!maddr); + + maddr->addrtype = addrtype; + if (!addr || addrlen < offsetofend(struct sockaddr, sa_family)) { + maddr->addrp = NULL; + maddr->port = 0; + maddr->len = 0; + return 0; + } + + /* + * its possibly to have sk->sk_family == PF_INET6 and + * addr->sa_family == AF_INET. sk_family is used for socket + * mediation, sa_family for when we have address ... + */ + switch (addr->sa_family) { + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + if (addrlen < sizeof(struct sockaddr_in)) + return -EINVAL; + maddr->port = addr4->sin_port; + maddr->addrp = (char *)&addr4->sin_addr.s_addr; + maddr->len = 4; + break; + case AF_INET6: + addr6 = (struct sockaddr_in6 *)addr; + if (addrlen < SIN6_LEN_RFC2133) + return -EINVAL; + maddr->port = addr6->sin6_port; + maddr->addrp = (char *)&addr6->sin6_addr.s6_addr; + maddr->len = 16; + break; + default: + return -EAFNOSUPPORT; + } + /* per ip spec, && sk->sk_type == SOCK_RAW*/ + if (raw_port && addrtype != ADDR_REMOTE) + maddr->port = raw_port; + if (ad) + set_ad_addr(ad, addr->sa_family, addrtype != ADDR_REMOTE, maddr); + + return 0; +} + +/* -ENOTCONN if not connected */ +static int map_sock_addr(struct socket *sock, enum addr_type addrtype, + struct stored_match_addr *maddr, + struct apparmor_audit_data *ad) +{ + /* do we need early bailout for !family ... */ + maddr->addrlen = sock->ops->getname(sock, (struct sockaddr *) &maddr->addr, addrtype != ADDR_REMOTE ? 0 : 1); + if (maddr->addrlen == -ENOTCONN) { + maddr->addrlen = 0; + return map_addr(NULL, 0, 0, addrtype, &maddr->maddr, ad); + } else if (maddr->addrlen < 0) + return maddr->addrlen; + return map_addr(&maddr->addr, maddr->addrlen, 0, addrtype, + &maddr->maddr, ad); +} + +/* TODO: combine with connect map addr */ +/* TODO: raw_port */ +static int bind_map_addr(struct sock *sk, struct sockaddr *addr, int addrlen, + struct match_addr *maddr, + struct apparmor_audit_data *ad) +{ + struct sockaddr_in *addr4 = NULL; + struct sockaddr_in6 *addr6 = NULL; + u16 family; + + AA_BUG(!addr); + AA_BUG(!maddr); + + if (addrlen < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; + + maddr->addrtype = ADDR_LOCAL; + /* + * its possibly to have sk->sk_family == PF_INET6 and + * addr->sa_family == AF_INET. sk_family is used for socket + * mediation, sa_family for when we have address ... + */ + family = addr->sa_family; + switch (addr->sa_family) { + case AF_UNSPEC: + if (sk->sk_family == PF_INET6) { + /* Length check from inet6_bind_sk() */ + if (addrlen < SIN6_LEN_RFC2133) + return -EINVAL; + /* Family check from __inet6_bind() */ + return -EAFNOSUPPORT; + } + /* see __inet_bind(), we only want to allow + * AF_UNSPEC if the address is INADDR_ANY + */ + if (addr4->sin_addr.s_addr != htonl(INADDR_ANY)) + return -EAFNOSUPPORT; + family = AF_INET; + fallthrough; + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + if (addrlen < sizeof(struct sockaddr_in)) + return -EINVAL; + maddr->port = addr4->sin_port; + maddr->addrp = (char *)&addr4->sin_addr.s_addr; + maddr->len = 4; + break; + case AF_INET6: + addr6 = (struct sockaddr_in6 *)addr; + if (addrlen < SIN6_LEN_RFC2133) + return -EINVAL; + maddr->port = addr6->sin6_port; + maddr->addrp = (char *)&addr6->sin6_addr.s6_addr; + maddr->len = 16; + break; + default: + return -EAFNOSUPPORT; + } + + if (ad) + set_ad_addr(ad, family, true, maddr); + + return 0; +} + +/* only continue match if + * insufficient current perms at current state + * indicates there are more perms in later state + * Returns: perms struct if early match + */ +static struct aa_perms *early_match(struct aa_policydb *policy, + aa_state_t state, u32 request) +{ + struct aa_perms *p; + + p = aa_lookup_perms(policy, state); + if (((p->allow & request) != request) && (p->allow & AA_CONT_MATCH)) + return NULL; + return p; +} + +static int do_perms(struct aa_profile *profile, aa_state_t state, u32 request, + struct aa_perms *p, struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_perms perms; + + AA_BUG(!profile); + + if (state || !p) + p = aa_lookup_perms(rules->policy, state); + perms = *p; + aa_apply_modes_to_perms(profile, &perms); + return aa_check_perms(profile, &perms, request, ad, + audit_net_cb); +} + +static aa_state_t match_addr(struct aa_dfa *dfa, aa_state_t state, + struct match_addr *maddr) +{ + char l = (char) maddr->addrtype; + + state = aa_dfa_match_len(dfa, state, &l, 1); + state = aa_dfa_match_len(dfa, state, (char *)&maddr->port, 2); + if (maddr->len == 0 && !maddr->addrp) { + l = 0; + } else if (maddr->len == 4) { + l = 1; + } else if (maddr->len == 16) { + l = 2; + } else { + AA_BUG("address length unsupported"); + return 0; + } + state = aa_dfa_match_len(dfa, state, &l, 1); + if (maddr->addrp) + state = aa_dfa_match_len(dfa, state, maddr->addrp, maddr->len); + /* null transition between addr and label */ + state = aa_dfa_null_transition(dfa, state); + + return state; +} + + +static aa_state_t match_addr_info(struct aa_dfa *dfa, aa_state_t state, + struct match_addr *maddr, + const char **info) +{ + state = match_addr(dfa, state, maddr); + if (!state) { + *info = maddr->addrtype == ADDR_REMOTE ? + "failed remote addr match" : + "failed local addr match"; + } + + return state; +} + +static aa_state_t match_addr_label(struct aa_policydb *policy, aa_state_t state, + u32 request, struct match_addr *maddr, + struct aa_perms **p, const char **info) +{ + state = match_addr_info(policy->dfa, state, maddr, info); + *p = early_match(policy, state, request); + if (!*p) { + /* TODO: actual label match: */ + if (!state) { + *info = maddr->addrtype == ADDR_REMOTE ? + "failed remote label match" : + "failed local label match"; + } + + /* null transition after label match */ + state = aa_dfa_null_transition(policy->dfa, state); + } + + return state; +} + + +/* passing in state returned by PROFILE_MEDIATES_AF */ +static aa_state_t match_to_prot(struct aa_policydb *policy, aa_state_t state, + u32 request, int type, int protocol, + struct aa_perms **p, const char **info) +{ + __be16 buffer; + buffer = cpu_to_be16((u16)type); + state = aa_dfa_match_len(policy->dfa, state, (char *) &buffer, 2); + if (!state) + *info = "failed type match"; + *p = early_match(policy, state, request); + if (!*p) { + buffer = cpu_to_be16((u16)protocol); + state = aa_dfa_match_len(policy->dfa, state, (char *) &buffer, + 2); + if (!state) + *info = "failed protocol match"; + } + return state; +} + +static aa_state_t match_to_sk(struct aa_policydb *policy, aa_state_t state, + u32 request, struct sock *sk, + struct match_addr *maddr, + struct aa_perms **p, const char **info) +{ + *p = NULL; + state = match_to_prot(policy, state, request, sk->sk_type, + sk->sk_protocol, p, info); + if (*p || !state) + return state; + return match_addr_label(policy, state, request, maddr, p, info); +} + +enum cmd_type { + CMD_ADDR = 1, + CMD_LISTEN = 2, + CMD_OPT = 4, +}; + +static inline aa_state_t match_to_cmd(struct aa_policydb *policy, + aa_state_t state, u32 request, + struct sock *sk, enum cmd_type cmd, + struct match_addr *maddr, + struct aa_perms **p, const char **info) +{ + state = match_to_sk(policy, state, request, sk, maddr, p, info); + if (!*p && state) { + char c = (char) cmd; + state = aa_dfa_match_len(policy->dfa, state, &c, 1); + if (!state) + *info = "failed cmd selection match"; + } + + return state; +} + +/* +static int match_label(struct aa_profile *profile, struct aa_profile *peer, + aa_state_t state, u32 request, + struct apparmor_audit_data *ad) +{ + AA_BUG(!profile); + AA_BUG(!peer); + + ad->peer = &peer->label; + + if (state) { + state = aa_dfa_match(profile->policy.dfa, state, + peer->base.hname); + if (!state) + ad->info = "failed peer label match"; + } + return do_perms(profile, state, request, ad); +} +*/ + +/* ---------------------------------------------------------------------- */ + + + +static inline int profile_sk_perm(struct aa_profile *profile, u32 request, + struct sock *sk, struct match_addr *maddr, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), + list); + struct aa_perms *p = NULL; + aa_state_t state; + + AA_BUG(!profile); + AA_BUG(!sk); + + state = RULE_MEDIATES_AF(rules, sk->sk_family); + if (state) { + state = match_to_sk(rules->policy, state, request, sk, + maddr, &p, &ad->info); + return do_perms(profile, state, request, p, ad); + } + + return aa_profile_af_sk_perm(profile, ad, request, sk); +} + +/* no kernel_t bailout */ +static int profile_create_perm(struct aa_profile *profile, int family, + int type, int protocol, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_perms *p = NULL; + aa_state_t state; + + AA_BUG(!profile); + + state = RULE_MEDIATES_AF(rules, family); + if (state) { + state = match_to_prot(rules->policy, state, AA_MAY_CREATE, + type, protocol, &p, &ad->info); + return do_perms(profile, state, AA_MAY_CREATE, p, ad); + } + + return aa_profile_af_perm(profile, ad, AA_MAY_CREATE, family, type); +} + + +/* sendmsg/rcvmsg/connect */ +static int profile_remote_perm(struct aa_profile *profile, struct sock *sk, + u32 request, struct match_addr *raddr, + struct match_addr *laddr, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_perms *p = NULL; + aa_state_t state; + + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(!raddr); + AA_BUG(!laddr); + AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6, + "family=%d", sk->sk_family); + + state = RULE_MEDIATES_SK(rules, sk); + if (!state) + return aa_profile_af_sk_perm(profile, ad, request, sk); + + /* TODO: deal with sa_family vs. sk_family */ + state = match_to_cmd(rules->policy, state, request, sk, CMD_ADDR, + raddr, &p, &ad->info); + if (state && !p) + /* check if perm is restricted to a pairing */ + state = match_addr_label(rules->policy, state, request, + laddr, &p, &ad->info); + return do_perms(profile, state, request, p, ad); +} + +static int profile_bind_perm(struct aa_profile *profile, struct sock *sk, + struct match_addr *maddr, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_perms *p = NULL; + aa_state_t state; + unsigned short sport; + + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(!maddr); + AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6, + "family=%d", sk->sk_family); + + state = RULE_MEDIATES_SK(rules, sk); + if (!state) + return aa_profile_af_sk_perm(profile, ad, AA_MAY_BIND, sk); + + /* + * its possibly to have sk->sk_family == PF_INET6 and + * addr->sa_family == AF_INET + */ + sport = ntohs(maddr->port); + if (sport) { + if (inet_port_requires_bind_service(sock_net(sk), sport)) { + /* cap NET_BIND_SERVICE will get raised */ + maddr->addrtype = ADDR_LOCAL_PRIV; + } + } + state = match_to_sk(rules->policy, state, AA_MAY_BIND, sk, + maddr, &p, &ad->info); + return do_perms(profile, state, AA_MAY_BIND, p, ad); +} + +static int profile_listen_perm(struct aa_profile *profile, struct sock *sk, + struct match_addr *maddr, int backlog, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_perms *p = NULL; + aa_state_t state; + + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(!maddr); + AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6, + "family=%d", sk->sk_family); + + state = RULE_MEDIATES_SK(rules, sk); + if (state) { + __be16 b = htons(backlog); + + state = match_to_cmd(rules->policy, state, AA_MAY_LISTEN, sk, + CMD_LISTEN, maddr, &p, &ad->info); + if (state && !p) { + state = aa_dfa_match_len(rules->policy->dfa, state, + (char *) &b, 2); + if (!state) + ad->info = "failed listen backlog match"; + } + return do_perms(profile, state, AA_MAY_LISTEN, p, ad); + } + + return aa_profile_af_sk_perm(profile, ad, AA_MAY_LISTEN, sk); +} + +static inline int profile_accept_perm(struct aa_profile *profile, + struct sock *sk, struct match_addr *maddr, + struct sock *newsk, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_perms *p = NULL; + aa_state_t state; + + AA_BUG(!profile); + AA_BUG(!sk); + /* AA_BUG(!newsk); newsk can be null here, since not using atm ... */ + AA_BUG(!maddr); + AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6, + "family=%d", sk->sk_family); + + state = RULE_MEDIATES_SK(rules, sk); + if (state) { + state = match_to_sk(rules->policy, state, AA_MAY_ACCEPT, sk, + maddr, &p, &ad->info); + return do_perms(profile, state, AA_MAY_ACCEPT, p, ad); + } + + return aa_profile_af_sk_perm(profile, ad, AA_MAY_ACCEPT, sk); +} + +/* getopt/setopt */ +static int profile_opt_perm(struct aa_profile *profile, u32 request, + struct sock *sk, struct match_addr *maddr, + int level, int optname, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_perms *p = NULL; + aa_state_t state; + + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(!maddr); + AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6, + "family=%d", sk->sk_family); + + state = RULE_MEDIATES_SK(rules, sk); + if (state) { + __be16 l = htons(l); + __be16 n = htons(optname); + + state = match_to_cmd(rules->policy, state, request, sk, + CMD_OPT, maddr, &p, &ad->info); + if (state && !p) { + state = aa_dfa_match_len(rules->policy->dfa, state, + (char *) &l, 2); + state = aa_dfa_match_len(rules->policy->dfa, state, + (char *) &n, 2); + if (!state) + ad->info = "failed sockopt match"; + } + return do_perms(profile, state, request, p, ad); + } + + return aa_profile_af_sk_perm(profile, ad, request, sk); +} + +/* ---------------------------------------------------------------------- */ + +// TODO: cleanup init to use recursion, so we can have N init fns, in 1 macro +// TODO: lift DEFINE_AUDIT out of macro into init fn??? + +/* no kernel_t bailout */ +#define label_sk_has_perm2(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, XXXX, YYYY, CALLBACKFN) \ +({ \ + int __EERROR = 0; \ + if (label_mediates(LABEL, AA_CLASS_NET)) { \ + struct aa_profile *PROFILE; \ + DEFINE_AUDIT_SK(AAD, OP, SOCKSK); \ + (AAD).subj_cred = (CRED); \ + __EERROR = (XXXX); \ + if (__EERROR == 0) { \ + __EERROR = (YYYY); \ + if (__EERROR == 0) { \ + __EERROR = fn_for_each(label, PROFILE, \ + (CALLBACKFN)); \ + } \ + } \ + } \ + __EERROR; \ +}) + +/* no kernel_t bailout */ +#define label_sk_has_perm(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, CALLBACKFN) \ + label_sk_has_perm2(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, \ + 0, 0, CALLBACKFN) + +/* no kernel_t bailout */ +#define label_sk_has_perm1(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, XXXX, CALLBACKFN) \ + label_sk_has_perm2(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, \ + XXXX, 0, CALLBACKFN) + + +/* Early bailout for kernel_t - 2 init args before callback */ +#define sk_has_perm2(SOCKSK, OP, REQUEST, PROFILE, AAD, XXXXY, YYYYX, CALLBACKFN) \ +({ \ + struct aa_label *label; \ + struct aa_sk_ctx *ctx= aa_sock(SOCKSK); \ + int __ERROR = 0; \ + if (ctx->label != kernel_t) { \ + \ + label = begin_current_label_crit_section(); \ + __ERROR = label_sk_has_perm2(current_cred(), label, SOCKSK, OP, REQUEST, PROFILE, AAD, XXXXY, YYYYX, CALLBACKFN); \ + end_current_label_crit_section(label); \ + } \ + __ERROR; \ +}) + +/* Early bailout for kernel_t - no init args before callback */ +#define sk_has_perm(SOCKSK, OP, REQUEST, PROFILE, AAD, CALLBACKFN) \ + sk_has_perm2(SOCKSK, OP, REQUEST, PROFILE, AAD, 0, 0, CALLBACKFN) + + +/* Early bailout for kernel_t - 1 init arg before callback */ +#define sk_has_perm1(SOCKSK, OP, REQUEST, PROFILE, AAD, XXXXY, CALLBACKFN) \ + sk_has_perm2(SOCKSK, OP, REQUEST, PROFILE, AAD, XXXXY, 0, CALLBACKFN) + + + +/* no kernel_t early bailout */ +/* NOTE: already lifted label_mediates into lsm.c */ +int aa_inet_create_perm(struct aa_label *label, int family, int type, + int protocol) +{ + struct aa_profile *profile; + int error = 0; + DEFINE_AUDIT_NET(ad, OP_CREATE, NULL, family, type, protocol); + + ad.subj_cred = current_cred(); + set_ad_create(&ad, family, type, protocol); + error = fn_for_each(label, profile, + profile_create_perm(profile, family, type, + protocol, &ad)); + + + return error; +} + +int aa_inet_bind_perm(struct socket *sock, struct sockaddr *addr, + int addrlen) +{ + struct match_addr maddr; + + return sk_has_perm1(sock->sk, OP_BIND, AA_MAY_BIND, profile, ad, + bind_map_addr(sock->sk, addr, addrlen, &maddr, + &ad), + profile_bind_perm(profile, sock->sk, &maddr, &ad)); +} + + +int aa_inet_connect_perm(struct socket *sock, struct sockaddr *addr, + int addrlen) +{ + struct stored_match_addr laddr; + struct match_addr raddr; + + /* disconnect socket */ + if (addr->sa_family == AF_UNSPEC) + return 0; + if (addrlen < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; + + /* do we need early bailout for !family ... */ + return sk_has_perm2(sock->sk, OP_CONNECT, AA_MAY_CONNECT, profile, ad, + map_sock_addr(sock, ADDR_LOCAL, &laddr, &ad), + map_addr(addr, addrlen, 0, ADDR_REMOTE, &raddr, + &ad), + profile_remote_perm(profile, sock->sk, + AA_MAY_CONNECT, &raddr, + &laddr.maddr, &ad)); +} + +int aa_inet_listen_perm(struct socket *sock, int backlog) +{ + struct stored_match_addr maddr; + + /* do we need early bailout for !family ... */ + return sk_has_perm1(sock->sk, OP_LISTEN, AA_MAY_LISTEN, profile, ad, + map_sock_addr(sock, ADDR_LOCAL, &maddr, &ad), + profile_listen_perm(profile, sock->sk, &maddr.maddr, + backlog, &ad)); +} + +/* ability of sock to connect, not peer address binding */ +int aa_inet_accept_perm(struct socket *sock, struct socket *newsock) +{ + struct stored_match_addr maddr; + int error; + + error = sk_has_perm1(sock->sk, OP_ACCEPT, AA_MAY_ACCEPT, profile, ad, + map_sock_addr(sock, ADDR_LOCAL, &maddr, &ad), + profile_accept_perm(profile, sock->sk, + &maddr.maddr, + newsock->sk, &ad)); + + /* selinux updates inode - need to investigate this more */ + return error; +} + +/* sendmsg, recvmsg. */ +int aa_inet_msg_perm(const char *op, u32 request, struct socket *sock, + struct msghdr *msg, int size) +{ + struct stored_match_addr laddr; + struct match_addr raddr; + + /* do we need early bailout for !family ... */ + return sk_has_perm2(sock->sk, op, request, profile, ad, + map_sock_addr(sock, ADDR_LOCAL, &laddr, &ad), + map_addr(msg->msg_name, msg->msg_namelen, 0, + ADDR_REMOTE, &raddr, &ad), + profile_remote_perm(profile, sock->sk, request, + &raddr, &laddr.maddr, &ad)); +} + +/* getopt, setopt */ +int aa_inet_opt_perm(const char *op, u32 request, struct socket *sock, + int level, int optname) +{ + struct stored_match_addr maddr; + + return sk_has_perm1(sock->sk, op, request, profile, ad, + map_sock_addr(sock, ADDR_LOCAL, &maddr, &ad), + profile_opt_perm(profile, request, sock->sk, + &maddr.maddr, level, optname, &ad)); +} + +static int inet_label_sock_perm(const struct cred *cred, struct aa_label *label, + const char *op, u32 request, + struct socket *sock) +{ + struct stored_match_addr maddr; + + return label_sk_has_perm1(cred, label, sock->sk, op, request, profile, + ad, + map_sock_addr(sock, ADDR_LOCAL, &maddr, &ad), + profile_sk_perm(profile, request, sock->sk, + &maddr.maddr, &ad)); +} + +/* revaliation, get/set attr/getsockname/peername */ +int aa_inet_sock_perm(const char *op, u32 request, struct socket *sock) +{ + struct aa_sk_ctx *ctx= aa_sock(sock->sk); + struct aa_label *label; + int error; + + if (ctx->label == kernel_t) + return 0; + + label = begin_current_label_crit_section(); + error = inet_label_sock_perm(current_cred(), label, op, request, sock); + end_current_label_crit_section(label); + + return error; +} + +int aa_inet_file_perm(const struct cred *subj_cred, struct aa_label *label, + const char *op, u32 request, struct socket *sock) +{ + u32 sk_req = request & ~NET_PEER_MASK; + struct stored_match_addr laddr; + struct sock *sk = sock->sk; + int error = 0; + + AA_BUG(!label); + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6, + "family=%d", sk->sk_family); + + /* access to the local sock */ + error = label_sk_has_perm1(subj_cred, label, sock->sk, op, request, + profile, ad, + map_sock_addr(sock, ADDR_LOCAL, &laddr, &ad), + profile_sk_perm(profile, sk_req, sock->sk, &laddr.maddr, + &ad)); + + if (!error) { + struct stored_match_addr laddr, raddr; + + /* TODO: have ad here: instead of in CB so we do have to redo */ + error = map_sock_addr(sock, ADDR_REMOTE, &raddr, NULL); + if (!error && raddr.maddr.addrp) { + error = label_sk_has_perm1(subj_cred, label, sock->sk, + op, request, profile, ad, + set_ad_addr(&ad, raddr.addr.sa_family, + false, &raddr.maddr), + profile_remote_perm(profile, sock->sk, + request, + &raddr.maddr, + &laddr.maddr, &ad)); + } + } + + return error; +} diff --git a/security/apparmor/af_unix.c b/security/apparmor/af_unix.c new file mode 100644 index 0000000000000..5b24b864854e3 --- /dev/null +++ b/security/apparmor/af_unix.c @@ -0,0 +1,702 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AppArmor security module + * + * This file contains AppArmor af_unix fine grained mediation + * + * Copyright 2018 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include + +#include "include/audit.h" +#include "include/af_unix.h" +#include "include/apparmor.h" +#include "include/file.h" +#include "include/label.h" +#include "include/path.h" +#include "include/policy.h" +#include "include/cred.h" + +static inline struct sock *aa_unix_sk(struct unix_sock *u) +{ + return &u->sk; +} + +static umode_t sock_i_mode(struct sock *sk) +{ + umode_t mode; + + read_lock_bh(&sk->sk_callback_lock); + mode = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_mode : 0; + read_unlock_bh(&sk->sk_callback_lock); + return mode; +} + +static inline int unix_fs_perm(const char *op, u32 mask, + const struct cred *subj_cred, + struct aa_label *label, + struct unix_sock *u, int flags) +{ + AA_BUG(!label); + AA_BUG(!u); + AA_BUG(!UNIX_FS(aa_unix_sk(u))); + + if (unconfined(label) || !label_mediates(label, AA_CLASS_FILE)) + return 0; + + mask &= NET_FS_PERMS; + if (!u->path.dentry) { + struct path_cond cond = { + .uid = sock_i_uid(&u->sk), + .mode = sock_i_mode(&u->sk), + }; + struct aa_perms perms = { }; + struct aa_profile *profile; + + /* socket path has been cleared because it is being shutdown + * can only fall back to original sun_path request + */ + struct aa_sk_ctx *ctx = aa_sock(&u->sk); + + if (ctx->path.dentry) + return aa_path_perm(op, subj_cred, label, &ctx->path, + flags, mask, + &cond); + return fn_for_each_confined(label, profile, + ((flags | profile->path_flags) & PATH_MEDIATE_DELETED) ? + __aa_path_perm(op, subj_cred, profile, + u->addr->name->sun_path, mask, + &cond, flags, &perms, false) : + aa_audit_file(subj_cred, profile, &nullperms, + op, mask, + u->addr->name->sun_path, NULL, + NULL, cond.uid, + "Failed name lookup - deleted entry", + -EACCES, false)); + } else { + /* the sunpath may not be valid for this ns so use the path */ + struct path_cond cond = { u->path.dentry->d_inode->i_uid, + u->path.dentry->d_inode->i_mode + }; + + return aa_path_perm(op, subj_cred, label, &u->path, flags, + mask, &cond); + } + + return 0; +} + +/* passing in state returned by PROFILE_MEDIATES_AF */ +static unsigned int match_to_prot(struct aa_dfa *dfa, + unsigned int state, int type, int protocol, + const char **info) +{ + __be16 buffer[2]; + + buffer[0] = cpu_to_be16(type); + buffer[1] = cpu_to_be16(protocol); + state = aa_dfa_match_len(dfa, state, (char *) &buffer, 4); + if (!state) + *info = "failed type and protocol match"; + return state; +} + +static unsigned int match_addr(struct aa_dfa *dfa, unsigned int state, + struct sockaddr_un *addr, int addrlen) +{ + if (addr) + /* include leading \0 */ + state = aa_dfa_match_len(dfa, state, addr->sun_path, + unix_addr_len(addrlen)); + else + /* anonymous end point */ + state = aa_dfa_match_len(dfa, state, "\x01", 1); + /* todo change to out of band */ + state = aa_dfa_null_transition(dfa, state); + return state; +} + +static unsigned int match_to_local(struct aa_dfa *dfa, + unsigned int state, int type, int protocol, + struct sockaddr_un *addr, int addrlen, + const char **info) +{ + state = match_to_prot(dfa, state, type, protocol, info); + if (state) { + state = match_addr(dfa, state, addr, addrlen); + if (state) { + /* todo: local label matching */ + state = aa_dfa_null_transition(dfa, state); + if (!state) + *info = "failed local label match"; + } else + *info = "failed local address match"; + } + + return state; +} + +static unsigned int match_to_sk(struct aa_dfa *dfa, + unsigned int state, struct unix_sock *u, + const char **info) +{ + struct sockaddr_un *addr = NULL; + int addrlen = 0; + + if (u->addr) { + addr = u->addr->name; + addrlen = u->addr->len; + } + + return match_to_local(dfa, state, u->sk.sk_type, u->sk.sk_protocol, + addr, addrlen, info); +} + +#define CMD_ADDR 1 +#define CMD_LISTEN 2 +#define CMD_OPT 4 + +static inline unsigned int match_to_cmd(struct aa_dfa *dfa, + unsigned int state, struct unix_sock *u, + char cmd, const char **info) +{ + state = match_to_sk(dfa, state, u, info); + if (state) { + state = aa_dfa_match_len(dfa, state, &cmd, 1); + if (!state) + *info = "failed cmd selection match"; + } + + return state; +} + +static inline unsigned int match_to_peer(struct aa_dfa *dfa, + unsigned int state, + struct unix_sock *u, + struct sockaddr_un *peer_addr, + int peer_addrlen, + const char **info) +{ + state = match_to_cmd(dfa, state, u, CMD_ADDR, info); + if (state) { + state = match_addr(dfa, state, peer_addr, peer_addrlen); + if (!state) + *info = "failed peer address match"; + } + return state; +} + +static int do_perms(struct aa_profile *profile, struct aa_ruleset *rule, + unsigned int state, u32 request, + struct apparmor_audit_data *ad) +{ + struct aa_perms perms; + + AA_BUG(!profile); + + perms = *aa_lookup_perms(rule->policy, state); + aa_apply_modes_to_perms(profile, &perms); + return aa_check_perms(profile, &perms, request, ad, + audit_net_cb); +} + +static int match_label(struct aa_profile *profile, struct aa_ruleset *rule, + struct aa_profile *peer, unsigned int state, u32 request, + struct apparmor_audit_data *ad) +{ + AA_BUG(!profile); + AA_BUG(!peer); + + ad->peer = &peer->label; + + if (state) { + state = aa_dfa_match(rule->policy->dfa, state, + peer->base.hname); + if (!state) + ad->info = "failed peer label match"; + } + return do_perms(profile, rule, state, request, ad); +} + + +/* unix sock creation comes before we know if the socket will be an fs + * socket + * v6 - semantics are handled by mapping in profile load + * v7 - semantics require sock create for tasks creating an fs socket. + */ +static int profile_create_perm(struct aa_profile *profile, int family, + int type, int protocol) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + aa_state_t state; + DEFINE_AUDIT_NET(ad, OP_CREATE, NULL, family, type, protocol); + + AA_BUG(!profile); + AA_BUG(profile_unconfined(profile)); + + state = RULE_MEDIATES_AF(rules, AF_UNIX); + if (state) { + state = match_to_prot(rules->policy->dfa, state, type, + protocol, &ad.info); + return do_perms(profile, rules, state, AA_MAY_CREATE, &ad); + } + + return aa_profile_af_perm(profile, &ad, AA_MAY_CREATE, family, type); +} + +int aa_unix_create_perm(struct aa_label *label, int family, int type, + int protocol) +{ + struct aa_profile *profile; + + if (unconfined(label)) + return 0; + + return fn_for_each_confined(label, profile, + profile_create_perm(profile, family, type, protocol)); +} + + +static inline int profile_sk_perm(struct aa_profile *profile, + struct apparmor_audit_data *ad, + u32 request, struct sock *sk) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), + list); + unsigned int state; + + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(UNIX_FS(sk)); + AA_BUG(profile_unconfined(profile)); + + state = RULE_MEDIATES_AF(rules, AF_UNIX); + if (state) { + state = match_to_sk(rules->policy->dfa, state, unix_sk(sk), + &ad->info); + return do_perms(profile, rules, state, request, ad); + } + + return aa_profile_af_sk_perm(profile, ad, request, sk); +} + +int aa_unix_label_sk_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, u32 request, + struct sock *sk) +{ + if (!unconfined(label)) { + struct aa_profile *profile; + DEFINE_AUDIT_SK(ad, op, sk); + + ad.subj_cred = subj_cred; + return fn_for_each_confined(label, profile, + profile_sk_perm(profile, &ad, request, sk)); + } + return 0; +} + +static int unix_label_sock_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, + u32 request, struct socket *sock) +{ + if (unconfined(label)) + return 0; + if (UNIX_FS(sock->sk)) + return unix_fs_perm(op, request, subj_cred, label, + unix_sk(sock->sk), 0); + + return aa_unix_label_sk_perm(subj_cred, label, op, request, sock->sk); +} + +/* revaliation, get/set attr */ +int aa_unix_sock_perm(const char *op, u32 request, struct socket *sock) +{ + struct aa_label *label; + int error; + + label = begin_current_label_crit_section(); + error = unix_label_sock_perm(current_cred(), label, op, request, sock); + end_current_label_crit_section(label); + + return error; +} + +static int profile_bind_perm(struct aa_profile *profile, struct sock *sk, + struct sockaddr *addr, int addrlen) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + unsigned int state; + DEFINE_AUDIT_SK(ad, OP_BIND, sk); + + ad.subj_cred = current_cred(); + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(addr->sa_family != AF_UNIX); + AA_BUG(profile_unconfined(profile)); + AA_BUG(unix_addr_fs(addr, addrlen)); + + state = RULE_MEDIATES_AF(rules, AF_UNIX); + if (state) { + /* bind for abstract socket */ + ad.net.addr = unix_addr(addr); + ad.net.addrlen = addrlen; + + state = match_to_local(rules->policy->dfa, state, + sk->sk_type, sk->sk_protocol, + unix_addr(addr), addrlen, + &ad.info); + return do_perms(profile, rules, state, AA_MAY_BIND, &ad); + } + + return aa_profile_af_sk_perm(profile, &ad, AA_MAY_BIND, sk); +} + +int aa_unix_bind_perm(struct socket *sock, struct sockaddr *address, + int addrlen) +{ + struct aa_profile *profile; + struct aa_label *label; + int error = 0; + + label = begin_current_label_crit_section(); + /* fs bind is handled by mknod */ + if (!(unconfined(label) || unix_addr_fs(address, addrlen))) + error = fn_for_each_confined(label, profile, + profile_bind_perm(profile, sock->sk, address, + addrlen)); + end_current_label_crit_section(label); + + return error; +} + +int aa_unix_connect_perm(struct socket *sock, struct sockaddr *address, + int addrlen) +{ + /* unix connections are covered by the + * - unix_stream_connect (stream) and unix_may_send hooks (dgram) + * - fs connect is handled by open + */ + return 0; +} + +static int profile_listen_perm(struct aa_profile *profile, struct sock *sk, + int backlog) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + unsigned int state; + DEFINE_AUDIT_SK(ad, OP_LISTEN, sk); + + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(UNIX_FS(sk)); + AA_BUG(profile_unconfined(profile)); + + state = RULE_MEDIATES_AF(rules, AF_UNIX); + if (state) { + __be16 b = cpu_to_be16(backlog); + + state = match_to_cmd(rules->policy->dfa, state, unix_sk(sk), + CMD_LISTEN, &ad.info); + if (state) { + state = aa_dfa_match_len(rules->policy->dfa, state, + (char *) &b, 2); + if (!state) + ad.info = "failed listen backlog match"; + } + return do_perms(profile, rules, state, AA_MAY_LISTEN, &ad); + } + + return aa_profile_af_sk_perm(profile, &ad, AA_MAY_LISTEN, sk); +} + +int aa_unix_listen_perm(struct socket *sock, int backlog) +{ + struct aa_profile *profile; + struct aa_label *label; + int error = 0; + + label = begin_current_label_crit_section(); + if (!(unconfined(label) || UNIX_FS(sock->sk))) + error = fn_for_each_confined(label, profile, + profile_listen_perm(profile, sock->sk, + backlog)); + end_current_label_crit_section(label); + + return error; +} + + +static inline int profile_accept_perm(struct aa_profile *profile, + struct sock *sk, + struct sock *newsk) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + unsigned int state; + DEFINE_AUDIT_SK(ad, OP_ACCEPT, sk); + + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(UNIX_FS(sk)); + AA_BUG(profile_unconfined(profile)); + + state = RULE_MEDIATES_AF(rules, AF_UNIX); + if (state) { + state = match_to_sk(rules->policy->dfa, state, unix_sk(sk), + &ad.info); + return do_perms(profile, rules, state, AA_MAY_ACCEPT, &ad); + } + + return aa_profile_af_sk_perm(profile, &ad, AA_MAY_ACCEPT, sk); +} + +/* ability of sock to connect, not peer address binding */ +int aa_unix_accept_perm(struct socket *sock, struct socket *newsock) +{ + struct aa_profile *profile; + struct aa_label *label; + int error = 0; + + label = begin_current_label_crit_section(); + if (!(unconfined(label) || UNIX_FS(sock->sk))) + error = fn_for_each_confined(label, profile, + profile_accept_perm(profile, sock->sk, + newsock->sk)); + end_current_label_crit_section(label); + + return error; +} + + +/* dgram handled by unix_may_sendmsg, right to send on stream done at connect + * could do per msg unix_stream here + */ +/* sendmsg, recvmsg */ +int aa_unix_msg_perm(const char *op, u32 request, struct socket *sock, + struct msghdr *msg, int size) +{ + return 0; +} + + +static int profile_opt_perm(struct aa_profile *profile, const char *op, u32 request, + struct sock *sk, int level, int optname) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + unsigned int state; + DEFINE_AUDIT_SK(ad, op, sk); + + AA_BUG(!profile); + AA_BUG(!sk); + AA_BUG(UNIX_FS(sk)); + AA_BUG(profile_unconfined(profile)); + + state = RULE_MEDIATES_AF(rules, AF_UNIX); + if (state) { + __be16 b = cpu_to_be16(optname); + + state = match_to_cmd(rules->policy->dfa, state, unix_sk(sk), + CMD_OPT, &ad.info); + if (state) { + state = aa_dfa_match_len(rules->policy->dfa, state, + (char *) &b, 2); + if (!state) + ad.info = "failed sockopt match"; + } + return do_perms(profile, rules, state, request, &ad); + } + + return aa_profile_af_sk_perm(profile, &ad, request, sk); +} + +int aa_unix_opt_perm(const char *op, u32 request, struct socket *sock, int level, + int optname) +{ + struct aa_profile *profile; + struct aa_label *label; + int error = 0; + + label = begin_current_label_crit_section(); + if (!(unconfined(label) || UNIX_FS(sock->sk))) + error = fn_for_each_confined(label, profile, + profile_opt_perm(profile, op, request, + sock->sk, level, optname)); + end_current_label_crit_section(label); + + return error; +} + +/* null peer_label is allowed, in which case the peer_sk label is used */ +static int profile_peer_perm(struct aa_profile *profile, const char *op, u32 request, + struct sock *sk, struct sock *peer_sk, + struct aa_label *peer_label, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + unsigned int state; + + AA_BUG(!profile); + AA_BUG(profile_unconfined(profile)); + AA_BUG(!sk); + AA_BUG(!peer_sk); + AA_BUG(UNIX_FS(peer_sk)); + + state = RULE_MEDIATES_AF(rules, AF_UNIX); + if (state) { + struct aa_sk_ctx *peer_ctx = aa_sock(peer_sk); + struct aa_profile *peerp; + struct sockaddr_un *addr = NULL; + int len = 0; + + if (unix_sk(peer_sk)->addr) { + addr = unix_sk(peer_sk)->addr->name; + len = unix_sk(peer_sk)->addr->len; + } + state = match_to_peer(rules->policy->dfa, state, unix_sk(sk), + addr, len, &ad->info); + if (!peer_label) + peer_label = peer_ctx->label; + return fn_for_each_in_ns(peer_label, peerp, + match_label(profile, rules, peerp, state, + request, ad)); + } + + return aa_profile_af_sk_perm(profile, ad, request, sk); +} + +/** + * + * Requires: lock held on both @sk and @peer_sk + */ +int aa_unix_peer_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, u32 request, + struct sock *sk, struct sock *peer_sk, + struct aa_label *peer_label) +{ + struct unix_sock *peeru = unix_sk(peer_sk); + struct unix_sock *u = unix_sk(sk); + + AA_BUG(!label); + AA_BUG(!sk); + AA_BUG(!peer_sk); + + if (UNIX_FS(aa_unix_sk(peeru))) { + return unix_fs_perm(op, request, subj_cred, label, peeru, 0); + } else if (UNIX_FS(aa_unix_sk(u))) { + return unix_fs_perm(op, request, subj_cred, label, u, 0); + } else { + struct aa_profile *profile; + DEFINE_AUDIT_SK(ad, op, sk); + + ad.net.peer_sk = peer_sk; + ad.subj_cred = subj_cred; + /* TODO: ns!!! */ + if (!net_eq(sock_net(sk), sock_net(peer_sk))) + ; + + if (unconfined(label)) + return 0; + + return fn_for_each_confined(label, profile, + profile_peer_perm(profile, op, request, sk, + peer_sk, peer_label, &ad)); + } +} + + +/* from net/unix/af_unix.c */ +static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) +{ + if (unlikely(sk1 == sk2) || !sk2) { + unix_state_lock(sk1); + return; + } + if (sk1 < sk2) { + unix_state_lock(sk1); + unix_state_lock_nested(sk2, U_LOCK_SECOND); + } else { + unix_state_lock(sk2); + unix_state_lock_nested(sk1, U_LOCK_SECOND); + } +} + +static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) +{ + if (unlikely(sk1 == sk2) || !sk2) { + unix_state_unlock(sk1); + return; + } + unix_state_unlock(sk1); + unix_state_unlock(sk2); +} + +int aa_unix_file_perm(const struct cred *subj_cred, struct aa_label *label, + const char *op, u32 request, struct socket *sock) +{ + struct sock *peer_sk = NULL; + u32 sk_req = request & ~NET_PEER_MASK; + int error = 0; + + AA_BUG(!label); + AA_BUG(!sock); + AA_BUG(!sock->sk); + AA_BUG(sock->sk->sk_family != AF_UNIX); + + /* TODO: update sock label with new task label */ + unix_state_lock(sock->sk); + peer_sk = unix_peer(sock->sk); + if (peer_sk) + sock_hold(peer_sk); + if (!unix_connected(sock) && sk_req) { + error = unix_label_sock_perm(subj_cred, label, op, sk_req, + sock); + if (!error) + ; // TODO: update label + } + unix_state_unlock(sock->sk); + if (!peer_sk) + return error; + + unix_state_double_lock(sock->sk, peer_sk); + if (UNIX_FS(sock->sk)) { + error = unix_fs_perm(op, request, subj_cred, label, + unix_sk(sock->sk), + PATH_SOCK_COND); + } else if (UNIX_FS(peer_sk)) { + error = unix_fs_perm(op, request, subj_cred, label, + unix_sk(peer_sk), + PATH_SOCK_COND); + } else { + struct aa_sk_ctx *pctx = aa_sock(peer_sk); + + if (sk_req) + error = aa_unix_label_sk_perm(subj_cred, + label, op, sk_req, + sock->sk); + last_error(error, + xcheck(aa_unix_peer_perm(subj_cred, label, op, + MAY_READ | MAY_WRITE, + sock->sk, peer_sk, NULL), + aa_unix_peer_perm(sock->file ? sock->file->f_cred : NULL, + pctx->label, op, + MAY_READ | MAY_WRITE, + peer_sk, sock->sk, label))); + } + + unix_state_double_unlock(sock->sk, peer_sk); + sock_put(peer_sk); + + return error; +} diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index bcfea073e3f2e..be6c3293c9e03 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "include/apparmor.h" #include "include/apparmorfs.h" @@ -35,6 +36,7 @@ #include "include/policy.h" #include "include/policy_ns.h" #include "include/resource.h" +#include "include/path.h" #include "include/policy_unpack.h" #include "include/task.h" @@ -609,6 +611,215 @@ static const struct file_operations aa_fs_ns_revision_fops = { .release = ns_revision_release, }; + +/* file hook fn for notificaions of policy actions */ +static int listener_release(struct inode *inode, struct file *file) +{ + struct aa_listener *listener = file->private_data; + + if (!aa_current_policy_admin_capable(NULL)) + return -EPERM; + if (listener) + aa_put_listener(listener); + + return 0; +} + +static int listener_open(struct inode *inode, struct file *file) +{ + struct aa_listener *listener; + + if (!aa_current_policy_admin_capable(NULL)) + return -EPERM; + listener = aa_new_listener(NULL, GFP_KERNEL); + if (!listener) + return -ENOMEM; + file->private_data = listener; + return 0; +} + +/* todo: separate register and set filter */ +static long notify_set_filter(struct aa_listener *listener, + unsigned long arg) +{ + struct apparmor_notif_filter *unotif; + struct aa_ns *ns = NULL; + long ret; + u16 size; + void __user *buf = (void __user *)arg; + + if (copy_from_user(&size, buf, sizeof(size))) + return -EFAULT; + if (size < sizeof(unotif)) + return -EINVAL; + /* size is capped at U16_MAX by data type */ + unotif = kzalloc(size, GFP_KERNEL); + if (!unotif) + return -ENOMEM; + + if (copy_from_user(unotif, buf, size)) { + ret = -EFAULT; + goto out; + } + ret = size; + + /* todo validate to known modes */ + listener->mask = unotif->modeset; + AA_DEBUG(DEBUG_UPCALL, "setting filter mask to 0x%x", listener->mask); + if (unotif->ns) + /* todo */ + ns = NULL; + if (unotif->filter) { + struct aa_dfa *dfa; + void *pos = (void *) unotif + unotif->filter; + + if (unotif->filter >= size || + ALIGN((size_t) pos, 8) != (size_t)pos) { + ret = -EINVAL; + goto out; + } + dfa = aa_dfa_unpack(pos, size - ((void *) unotif - pos), + DFA_FLAG_VERIFY_STATES | + TO_ACCEPT1_FLAG(YYTD_DATA32)); + if (IS_ERR(dfa)) { + ret = PTR_ERR(dfa); + goto out; + } + listener->filter = dfa; + } + if (!aa_register_listener_proxy(listener, ns)) + ret = -ENOMEM; + +out: + kfree(unotif); + + return ret; +} + + +static long notify_user_recv(struct aa_listener *listener, + unsigned long arg) +{ + u16 max_size; + void __user *buf = (void __user *)arg; + + if (copy_from_user(&max_size, buf, sizeof(max_size))) + return -EFAULT; + /* size check handled by individual message handlers */ + return aa_listener_unotif_recv(listener, buf, max_size); +} + +static long notify_user_response(struct aa_listener *listener, + unsigned long arg) +{ + union apparmor_notif_resp uresp = {}; + union apparmor_notif_resp *big_resp = NULL; + long error; + u16 size; + void __user *buf = (void __user *)arg; + + if (copy_from_user(&size, buf, sizeof(size))) + return -EFAULT; + if (size > aa_g_path_max) + return -EMSGSIZE; + if (size > sizeof(uresp)) { + /* TODO: put max size on message */ + big_resp = (union apparmor_notif_resp *) aa_get_buffer(false); + if (big_resp) + return -ENOMEM; + if (copy_from_user(big_resp, buf, size)) { + kfree(big_resp); + return -EFAULT; + } + } else { + size = min_t(size_t, size, sizeof(uresp)); + if (copy_from_user(&uresp, buf, size)) + return -EFAULT; + } + + error = aa_listener_unotif_response(listener, &uresp, size); + aa_put_buffer((char *) big_resp); + + return error; +} + +static long notify_is_id_valid(struct aa_listener *listener, + unsigned long arg) +{ + void __user *buf = (void __user *)arg; + u64 id; + long ret = -ENOENT; + + if (copy_from_user(&id, buf, sizeof(id))) + return -EFAULT; + + spin_lock(&listener->lock); + if (__aa_find_notif(listener, id)) + ret = 0; + spin_unlock(&listener->lock); + + return ret; +} + +static long listener_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct aa_listener *listener = file->private_data; + + if (!aa_current_policy_admin_capable(NULL)) + return -EPERM; + if (!listener) + return -EINVAL; + + /* todo permission to issue these commands */ + switch (cmd) { + case APPARMOR_NOTIF_SET_FILTER: + return notify_set_filter(listener, arg); + case APPARMOR_NOTIF_RECV: + return notify_user_recv(listener, arg); + case APPARMOR_NOTIF_SEND: + return notify_user_response(listener, arg); + case APPARMOR_NOTIF_IS_ID_VALID: + return notify_is_id_valid(listener, arg); + default: + return -EINVAL; + + } + + return -EINVAL; +} + +static __poll_t listener_poll(struct file *file, poll_table *pt) +{ + struct aa_listener *listener = file->private_data; + __poll_t mask = 0; + + if (!aa_current_policy_admin_capable(NULL)) + return -EPERM; + + if (listener) { + spin_lock(&listener->lock); + poll_wait(file, &listener->wait, pt); + if (!list_empty(&listener->notifications)) + mask |= EPOLLIN | EPOLLRDNORM; + if (!list_empty(&listener->pending)) + mask |= EPOLLOUT | EPOLLWRNORM; + spin_unlock(&listener->lock); + } + + return mask; +} + +static const struct file_operations aa_sfs_notify_fops = { + .owner = THIS_MODULE, + .open = listener_open, + .poll = listener_poll, +// .read = notification_read, + .llseek = generic_file_llseek, + .release = listener_release, + .unlocked_ioctl = listener_ioctl, +}; + static void profile_query_cb(struct aa_profile *profile, struct aa_perms *perms, const char *match_str, size_t match_len) { @@ -617,7 +828,7 @@ static void profile_query_cb(struct aa_profile *profile, struct aa_perms *perms, struct aa_perms tmp = { }; aa_state_t state = DFA_NOMATCH; - if (profile_unconfined(profile)) + if (!profile_mediates_safe(profile, *match_str)) return; if (rules->file->dfa && *match_str == AA_CLASS_FILE) { state = aa_dfa_match_len(rules->file->dfa, @@ -626,7 +837,8 @@ static void profile_query_cb(struct aa_profile *profile, struct aa_perms *perms, if (state) { struct path_cond cond = { }; - tmp = *(aa_lookup_fperms(rules->file, state, &cond)); + tmp = *(aa_lookup_condperms(current_fsuid(), + rules->file, state, &cond)); } } else if (rules->policy->dfa) { if (!RULE_MEDIATES(rules, *match_str)) @@ -1005,6 +1217,9 @@ static int aa_sfs_seq_show(struct seq_file *seq, void *v) case AA_SFS_TYPE_U64: seq_printf(seq, "%#08lx\n", fs_file->v.u64); break; + case AA_SFS_TYPE_INTPTR: + seq_printf(seq, "%d\n", READ_ONCE(*fs_file->v.intptr)); + break; default: /* Ignore unpritable entry types. */ break; @@ -1122,10 +1337,24 @@ static int seq_profile_hash_show(struct seq_file *seq, void *v) return 0; } +static int seq_profile_learning_count_show(struct seq_file *seq, void *v) +{ + struct aa_proxy *proxy = seq->private; + struct aa_label *label = aa_get_label_rcu(&proxy->label); + struct aa_profile *profile = labels_profile(label); + int count = READ_ONCE(profile->learning_cache.size); + + seq_printf(seq, "%d\n", count); + aa_put_label(label); + + return 0; +} + SEQ_PROFILE_FOPS(name); SEQ_PROFILE_FOPS(mode); SEQ_PROFILE_FOPS(attach); SEQ_PROFILE_FOPS(hash); +SEQ_PROFILE_FOPS(learning_count); /* * namespace based files @@ -1737,6 +1966,12 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent) goto fail; profile->dents[AAFS_PROF_ATTACH] = dent; + dent = create_profile_file(dir, "learning_count", profile, + &seq_profile_learning_count_fops); + if (IS_ERR(dent)) + goto fail; + profile->dents[AAFS_PROF_LEARNING_COUNT] = dent; + if (profile->hash) { dent = create_profile_file(dir, "sha256", profile, &seq_profile_hash_fops); @@ -2311,6 +2546,12 @@ static struct aa_sfs_entry aa_sfs_entry_file[] = { { } }; +static struct aa_sfs_entry aa_sfs_entry_ipc[] = { + AA_SFS_FILE_STRING("posix_mqueue", + "create read write open delete setattr getattr"), + { } +}; + static struct aa_sfs_entry aa_sfs_entry_ptrace[] = { AA_SFS_FILE_STRING("mask", "read trace"), { } @@ -2328,6 +2569,7 @@ static struct aa_sfs_entry aa_sfs_entry_attach[] = { static struct aa_sfs_entry aa_sfs_entry_domain[] = { AA_SFS_FILE_BOOLEAN("change_hat", 1), AA_SFS_FILE_BOOLEAN("change_hatv", 1), + AA_SFS_FILE_BOOLEAN("unconfined_allowed_children", 1), AA_SFS_FILE_BOOLEAN("change_onexec", 1), AA_SFS_FILE_BOOLEAN("change_profile", 1), AA_SFS_FILE_BOOLEAN("stack", 1), @@ -2335,13 +2577,18 @@ static struct aa_sfs_entry aa_sfs_entry_domain[] = { AA_SFS_FILE_BOOLEAN("post_nnp_subset", 1), AA_SFS_FILE_BOOLEAN("computed_longest_left", 1), AA_SFS_DIR("attach_conditions", aa_sfs_entry_attach), + AA_SFS_FILE_BOOLEAN("interruptible", 1), AA_SFS_FILE_BOOLEAN("disconnected.path", 1), + AA_SFS_FILE_BOOLEAN("kill.signal", 1), AA_SFS_FILE_STRING("version", "1.2"), { } }; static struct aa_sfs_entry aa_sfs_entry_unconfined[] = { AA_SFS_FILE_BOOLEAN("change_profile", 1), + AA_SFS_FILE_INTPTR("userns", aa_unprivileged_userns_restricted), + AA_SFS_FILE_INTPTR("io_uring", + aa_unprivileged_uring_restricted), { } }; @@ -2354,13 +2601,17 @@ static struct aa_sfs_entry aa_sfs_entry_versions[] = { { } }; +/* permstable v1: skipped + v2: accept1 index, no accept2 + v3: accept1 index, accept2 flags +*/ #define PERMS32STR "allow deny subtree cond kill complain prompt audit quiet hide xindex tag label" static struct aa_sfs_entry aa_sfs_entry_policy[] = { AA_SFS_DIR("versions", aa_sfs_entry_versions), AA_SFS_FILE_BOOLEAN("set_load", 1), /* number of out of band transitions supported */ AA_SFS_FILE_U64("outofband", MAX_OOB_SUPPORTED), - AA_SFS_FILE_U64("permstable32_version", 1), + AA_SFS_FILE_U64("permstable32_version", 3), AA_SFS_FILE_STRING("permstable32", PERMS32STR), AA_SFS_DIR("unconfined_restrictions", aa_sfs_entry_unconfined), { } @@ -2376,6 +2627,12 @@ static struct aa_sfs_entry aa_sfs_entry_ns[] = { AA_SFS_FILE_BOOLEAN("profile", 1), AA_SFS_FILE_BOOLEAN("pivot_root", 0), AA_SFS_FILE_STRING("mask", "userns_create"), + AA_SFS_FILE_STRING("userns_create", "pciu&"), + { } +}; + +static struct aa_sfs_entry aa_sfs_entry_dbus[] = { + AA_SFS_FILE_STRING("mask", "acquire send receive"), { } }; @@ -2400,7 +2657,9 @@ static struct aa_sfs_entry aa_sfs_entry_features[] = { AA_SFS_DIR("policy", aa_sfs_entry_policy), AA_SFS_DIR("domain", aa_sfs_entry_domain), AA_SFS_DIR("file", aa_sfs_entry_file), + AA_SFS_DIR("ipc", aa_sfs_entry_ipc), AA_SFS_DIR("network_v8", aa_sfs_entry_network), + AA_SFS_DIR("network", aa_sfs_entry_network_compat), AA_SFS_DIR("mount", aa_sfs_entry_mount), AA_SFS_DIR("namespaces", aa_sfs_entry_ns), AA_SFS_FILE_U64("capability", VFS_CAP_FLAGS_MASK), @@ -2408,6 +2667,7 @@ static struct aa_sfs_entry aa_sfs_entry_features[] = { AA_SFS_DIR("caps", aa_sfs_entry_caps), AA_SFS_DIR("ptrace", aa_sfs_entry_ptrace), AA_SFS_DIR("signal", aa_sfs_entry_signal), + AA_SFS_DIR("dbus", aa_sfs_entry_dbus), AA_SFS_DIR("query", aa_sfs_entry_query), AA_SFS_DIR("io_uring", aa_sfs_entry_io_uring), { } @@ -2415,6 +2675,7 @@ static struct aa_sfs_entry aa_sfs_entry_features[] = { static struct aa_sfs_entry aa_sfs_entry_apparmor[] = { AA_SFS_FILE_FOPS(".access", 0666, &aa_sfs_access), + AA_SFS_FILE_FOPS(".notify", 0666, &aa_sfs_notify_fops), AA_SFS_FILE_FOPS(".stacked", 0444, &seq_ns_stacked_fops), AA_SFS_FILE_FOPS(".ns_stacked", 0444, &seq_ns_nsstacked_fops), AA_SFS_FILE_FOPS(".ns_level", 0444, &seq_ns_level_fops), diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c index 45beb1c5f747a..9ecc1bc941f8e 100644 --- a/security/apparmor/audit.c +++ b/security/apparmor/audit.c @@ -192,7 +192,7 @@ int aa_audit(int type, struct aa_profile *profile, aa_audit_msg(type, ad, cb); if (ad->type == AUDIT_APPARMOR_KILL) - (void)send_sig_info(SIGKILL, NULL, + (void)send_sig_info(profile->signal, NULL, ad->common.type == LSM_AUDIT_DATA_TASK && ad->common.u.tsk ? ad->common.u.tsk : current); @@ -206,10 +206,14 @@ struct aa_audit_rule { struct aa_label *label; }; -void aa_audit_rule_free(void *vrule) +/****************************** audit rules *******************************/ + +void aa_audit_rule_free(void *vrule, int lsmid) { struct aa_audit_rule *rule = vrule; + if (lsmid != LSM_ID_UNDEF || lsmid != LSM_ID_APPARMOR) + return; if (rule) { if (!IS_ERR(rule->label)) aa_put_label(rule->label); @@ -217,10 +221,13 @@ void aa_audit_rule_free(void *vrule) } } -int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, + int lsmid, gfp_t gfp) { struct aa_audit_rule *rule; + if (lsmid != LSM_ID_UNDEF || lsmid != LSM_ID_APPARMOR) + return 0; switch (field) { case AUDIT_SUBJ_ROLE: if (op != Audit_equal && op != Audit_not_equal) @@ -230,17 +237,17 @@ int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) return -EINVAL; } - rule = kzalloc(sizeof(struct aa_audit_rule), GFP_KERNEL); + rule = kzalloc(sizeof(struct aa_audit_rule), gfp); if (!rule) return -ENOMEM; /* Currently rules are treated as coming from the root ns */ rule->label = aa_label_parse(&root_ns->unconfined->label, rulestr, - GFP_KERNEL, true, false); + gfp, true, false); if (IS_ERR(rule->label)) { int err = PTR_ERR(rule->label); - aa_audit_rule_free(rule); + aa_audit_rule_free(rule, LSM_ID_APPARMOR); return err; } @@ -264,13 +271,17 @@ int aa_audit_rule_known(struct audit_krule *rule) return 0; } -int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) +int aa_audit_rule_match(struct lsmblob *blob, u32 field, u32 op, void *vrule, + int lsmid) { struct aa_audit_rule *rule = vrule; struct aa_label *label; int found = 0; - label = aa_secid_to_label(sid); + if (lsmid != LSM_ID_UNDEF || lsmid != LSM_ID_APPARMOR) + return 0; + + label = blob->apparmor.label; if (!label) return -ENOENT; @@ -289,3 +300,259 @@ int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) } return 0; } + +/****************************** audit cache *******************************/ + +static int uid_cmp(kuid_t lhs, kuid_t rhs) +{ + if (uid_lt(lhs, rhs)) + return -1; + if (uid_gt(lhs, rhs)) + return 1; + return 0; +} + +/* std C cmp. negative is less than, 0 is equal, positive greater than */ +long aa_audit_data_cmp(struct apparmor_audit_data *lhs, + struct apparmor_audit_data *rhs) +{ + long res; + + /* don't compare type */ + res = lhs->class - rhs->class; + if (res) + return res; + /* don't compare op */ + if (lhs->flags & AUDIT_TAILGLOB_NAME) + /* lhs glob matches strings longer than it */ + res = strncmp(lhs->name, rhs->name, strlen(lhs->name)); + else + res = strcmp(lhs->name, rhs->name); + if (res) + return res; + res = aa_label_cmp(lhs->subj_label, rhs->subj_label); + if (res) + return res; + switch (lhs->class) { + case AA_CLASS_FILE: + if (lhs->subj_cred) { + if (rhs->subj_cred) { + return uid_cmp(lhs->subj_cred->fsuid, + rhs->subj_cred->fsuid); + } else { + return 1; + } + } else if (rhs->subj_cred) { + return -1; + } + res = uid_cmp(lhs->fs.ouid, rhs->fs.ouid); + if (res) + return res; + res = lhs->fs.target - rhs->fs.target; + if (res) + return res; + } + return 0; +} + +static void audit_node_free(struct aa_audit_node *node) +{ + if (!node) + return; + + AA_BUG(!list_empty(&node->list)); + + /* common data that needs freed */ + kfree(node->data.name); + aa_put_label(node->data.subj_label); + if (node->data.subj_cred) + put_cred(node->data.subj_cred); + + /* class specific data that needs freed */ + switch (node->data.class) { + case AA_CLASS_FILE: + aa_put_label(node->data.peer); + kfree(node->data.fs.target); + } + + kmem_cache_free(aa_audit_slab, node); +} + +void aa_audit_node_free_kref(struct kref *kref) +{ + struct aa_audit_node *node = container_of(kref, struct aa_audit_node, + count); + audit_node_free(node); +} + +struct aa_audit_node *aa_dup_audit_data(struct apparmor_audit_data *orig, + gfp_t gfp) +{ + struct aa_audit_node *copy; + + copy = kmem_cache_zalloc(aa_audit_slab, gfp); + if (!copy) + return NULL; + kref_init(©->count); + + copy->knotif.ad = ©->data; + INIT_LIST_HEAD(©->list); + /* copy class early so aa_free_audit_node can use switch on failure */ + copy->data.class = orig->class; + copy->data.flags = orig->flags; + + /* handle anything with possible failure first */ + if (orig->name) { + copy->data.name = kstrdup(orig->name, gfp); + if (!copy->data.name) + goto fail; + } + /* don't dup info */ + switch (orig->class) { + case AA_CLASS_FILE: + if (orig->fs.target) { + copy->data.fs.target = kstrdup(orig->fs.target, gfp); + if (!copy->data.fs.target) + goto fail; + } + break; + case AA_CLASS_MOUNT: + if (orig->mnt.src_name) { + copy->data.mnt.src_name = kstrdup(orig->mnt.src_name, gfp); + if (!copy->data.mnt.src_name) + goto fail; + } + if (orig->mnt.type) { + copy->data.mnt.type = kstrdup(orig->mnt.type, gfp); + if (!copy->data.mnt.type) + goto fail; + } + // copy->mnt.trans; not used atm + if (orig->mnt.data) { + copy->data.mnt.data = kstrdup(orig->mnt.data, gfp); + if (!copy->data.mnt.data) + goto fail; + } + break; + } + + /* now inc counts, and copy data that can't fail */ + copy->data.error = orig->error; + copy->data.type = orig->type; + copy->data.request = orig->request; + copy->data.denied = orig->denied; + copy->data.subj_label = aa_get_label(orig->subj_label); + + if (orig->subj_cred) + copy->data.subj_cred = get_cred(orig->subj_cred); + + switch (orig->class) { + case AA_CLASS_NET: + /* + * peer_sk; + * addr; + */ + fallthrough; + case AA_CLASS_FILE: + copy->data.fs.ouid = orig->fs.ouid; + break; + case AA_CLASS_RLIMITS: + case AA_CLASS_SIGNAL: + case AA_CLASS_POSIX_MQUEUE: + copy->data.peer = aa_get_label(orig->peer); + break; +/* + * case AA_CLASS_IFACE: + * copy->data.iface.profile = aa_get_label(orig.iface.profile); + * break; + */ + }; + + + return copy; +fail: + audit_node_free(copy); + return NULL; +} + +#define __audit_cache_find(C, AD, COND...) \ +({ \ + struct aa_audit_node *__node; \ + list_for_each_entry_rcu(__node, &(C)->head, list, COND) { \ + if (aa_audit_data_cmp(&__node->data, AD) == 0) \ + goto __out_skip; \ + } \ + __node = NULL; \ +__out_skip: \ + __node; \ +}) + +// increments refcount on node +struct aa_audit_node *aa_audit_cache_find(struct aa_audit_cache *cache, + struct apparmor_audit_data *ad) +{ + struct aa_audit_node *node; + + rcu_read_lock(); + node = __audit_cache_find(cache, ad); + aa_get_audit_node(node); + rcu_read_unlock(); + + return node; +} + +/** + * aa_audit_cache_insert - insert an audit node into the cache + * @cache: the cache to insert into + * @node: the audit node to insert into the cache + * + * Returns: refcounted matching node in cache OR @node if @node was inserted. + * + * Increments refcount on node if successfully inserted. Assumes caller + * already has valid ref count. + * Increments refcount on existing node if returned + */ +struct aa_audit_node *aa_audit_cache_insert(struct aa_audit_cache *cache, + struct aa_audit_node *node) + +{ + struct aa_audit_node *tmp; + + spin_lock(&cache->lock); + tmp = __audit_cache_find(cache, &node->data, + spin_is_lock(&cache->lock)); + if (!tmp) { + list_add_rcu(&node->list, &cache->head); + tmp = node; + cache->size++; + } + + aa_get_audit_node(tmp); + /* else raced another insert */ + spin_unlock(&cache->lock); + + return tmp; +} + +void aa_audit_cache_update_ent(struct aa_audit_cache *cache, + struct aa_audit_node *node, + struct apparmor_audit_data *data) +{ + spin_lock(&cache->lock); + node->data.denied |= data->denied; + node->data.request = (node->data.request | data->request) & + ~node->data.denied; + spin_unlock(&cache->lock); +} + +/* assumes rcu callback has already happened and list can not be walked */ +void aa_audit_cache_destroy(struct aa_audit_cache *cache) +{ + struct aa_audit_node *node, *tmp; + + list_for_each_entry_safe(node, tmp, &cache->head, list) { + list_del_init(&node->list); + aa_put_audit_node(node); + } + cache->size = 0; +} diff --git a/security/apparmor/capability.c b/security/apparmor/capability.c index 9934df16c8431..7c0f66f1b2976 100644 --- a/security/apparmor/capability.c +++ b/security/apparmor/capability.c @@ -26,6 +26,7 @@ struct aa_sfs_entry aa_sfs_entry_caps[] = { AA_SFS_FILE_STRING("mask", AA_SFS_CAPS_MASK), + AA_SFS_FILE_BOOLEAN("extended", 1), { } }; @@ -118,8 +119,31 @@ static int profile_capable(struct aa_profile *profile, int cap, { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); + aa_state_t state; int error; + state = RULE_MEDIATES(rules, ad->class); + if (state) { + struct aa_perms perms = { }; + u32 request; + + /* caps broken into 256 x 32 bit permission chunks */ + state = aa_dfa_next(rules->policy->dfa, state, cap >> 5); + request = 1 << (cap & 0x1f); + perms = *aa_lookup_perms(rules->policy, state); + aa_apply_modes_to_perms(profile, &perms); + + if (opts & CAP_OPT_NOAUDIT) { + if (perms.complain & request) + ad->info = "optional: no audit"; + else + ad = NULL; + } + return aa_check_perms(profile, &perms, request, ad, + audit_cb); + } + + /* fallback to old caps mediation that doesn't support conditionals */ if (cap_raised(rules->caps.allow, cap) && !cap_raised(rules->caps.denied, cap)) error = 0; @@ -163,3 +187,35 @@ int aa_capable(const struct cred *subj_cred, struct aa_label *label, return error; } + +kernel_cap_t aa_profile_capget(struct aa_profile *profile) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + aa_state_t state; + + state = RULE_MEDIATES(rules, AA_CLASS_CAP); + if (state) { + kernel_cap_t caps = CAP_EMPTY_SET; + int i; + + /* caps broken into up to 256, 32 bit permission chunks */ + for (i = 0; i < (CAP_LAST_CAP >> 5); i++) { + struct aa_perms perms = { }; + aa_state_t tmp; + + tmp = aa_dfa_next(rules->policy->dfa, state, i); + perms = *aa_lookup_perms(rules->policy, tmp); + aa_apply_modes_to_perms(profile, &perms); + caps.val |= ((u64)(perms.allow)) << (i *5); + caps.val |= ((u64)(perms.complain)) << (i *5); + } + return caps; + } + + /* fallback to old caps */ + if (COMPLAIN_MODE(profile)) + return CAP_FULL_SET; + + return rules->caps.allow; +} diff --git a/security/apparmor/crypto.c b/security/apparmor/crypto.c index aad486b2fca65..2902fbeb96e55 100644 --- a/security/apparmor/crypto.c +++ b/security/apparmor/crypto.c @@ -25,6 +25,26 @@ unsigned int aa_hash_size(void) return apparmor_hash_size; } +void aa_snprint_hashstr(char *out, unsigned char *hash, unsigned int hsize) +{ + unsigned int i; + + for (i = 0; i < hsize; i++) + sprintf(out + i*2, "%.2x", hash[i]); + out[hsize*2] = 0; +} + +char *aa_asprint_hashstr(unsigned char *hash, unsigned int hsize, gfp_t gfp) +{ + char *buffer = kmalloc(hsize*2 + 1, gfp); + + if (!buffer) + return NULL; + aa_snprint_hashstr(buffer, hash, hsize); + + return buffer; +} + char *aa_calc_hash(void *data, size_t len) { SHASH_DESC_ON_STACK(desc, apparmor_tfm); diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 571158ec6188f..dd457eaedab8b 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -155,7 +155,8 @@ static int label_compound_match(struct aa_profile *profile, if (!state) goto fail; } - *perms = *(aa_lookup_fperms(rules->file, state, &cond)); + *perms = *(aa_lookup_condperms(current_fsuid(), rules->file, state, + &cond)); aa_apply_modes_to_perms(profile, perms); if ((perms->allow & request) != request) return -EACCES; @@ -210,7 +211,8 @@ static int label_components_match(struct aa_profile *profile, return 0; next: - tmp = *(aa_lookup_fperms(rules->file, state, &cond)); + tmp = *(aa_lookup_condperms(current_fsuid(), rules->file, state, + &cond)); aa_apply_modes_to_perms(profile, &tmp); aa_perms_accum(perms, &tmp); label_for_each_cont(i, label, tp) { @@ -219,7 +221,8 @@ static int label_components_match(struct aa_profile *profile, state = match_component(profile, tp, stack, start); if (!state) goto fail; - tmp = *(aa_lookup_fperms(rules->file, state, &cond)); + tmp = *(aa_lookup_condperms(current_fsuid(), rules->file, state, + &cond)); aa_apply_modes_to_perms(profile, &tmp); aa_perms_accum(perms, &tmp); } @@ -285,7 +288,7 @@ static int change_profile_perms(struct aa_profile *profile, u32 request, aa_state_t start, struct aa_perms *perms) { - if (profile_unconfined(profile)) { + if (!profile_mediates(profile, AA_CLASS_FILE)) { perms->allow = AA_MAY_CHANGE_PROFILE | AA_MAY_ONEXEC; perms->audit = perms->quiet = perms->kill = 0; return 0; @@ -324,7 +327,7 @@ static int aa_xattrs_match(const struct linux_binprm *bprm, size = vfs_getxattr_alloc(&nop_mnt_idmap, d, attach->xattrs[i], &value, value_size, GFP_KERNEL); if (size >= 0) { - u32 index, perm; + struct aa_perms *perms; /* * Check the xattr presence before value. This ensure @@ -336,9 +339,8 @@ static int aa_xattrs_match(const struct linux_binprm *bprm, /* Check xattr value */ state = aa_dfa_match_len(attach->xmatch->dfa, state, value, size); - index = ACCEPT_TABLE(attach->xmatch->dfa)[state]; - perm = attach->xmatch->perms[index].allow; - if (!(perm & MAY_EXEC)) { + perms = aa_lookup_perms(attach->xmatch, state); + if (!(perms->allow & MAY_EXEC)) { ret = -EINVAL; goto out; } @@ -416,15 +418,14 @@ static struct aa_label *find_attach(const struct linux_binprm *bprm, if (attach->xmatch->dfa) { unsigned int count; aa_state_t state; - u32 index, perm; + struct aa_perms *perms; state = aa_dfa_leftmatch(attach->xmatch->dfa, attach->xmatch->start[AA_CLASS_XMATCH], name, &count); - index = ACCEPT_TABLE(attach->xmatch->dfa)[state]; - perm = attach->xmatch->perms[index].allow; + perms = aa_lookup_perms(attach->xmatch, state); /* any accepting state means a valid match. */ - if (perm & MAY_EXEC) { + if (perms->allow & MAY_EXEC) { int ret = 0; if (count < candidate_len) @@ -509,6 +510,7 @@ static const char *next_name(int xtype, const char *name) * @name: returns: name tested to find label (NOT NULL) * * Returns: refcounted label, or NULL on failure (MAYBE NULL) + * @name will always be set with the last name tried */ struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex, const char **name) @@ -518,6 +520,7 @@ struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex, struct aa_label *label = NULL; u32 xtype = xindex & AA_X_TYPE_MASK; int index = xindex & AA_X_INDEX_MASK; + const char *next; AA_BUG(!name); @@ -525,25 +528,26 @@ struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex, /* TODO: move lookup parsing to unpack time so this is a straight * index into the resultant label */ - for (*name = rules->file->trans.table[index]; !label && *name; - *name = next_name(xtype, *name)) { + for (next = rules->file->trans.table[index]; next; + next = next_name(xtype, next)) { + const char *lookup = (*next == '&') ? next + 1 : next; + *name = next; if (xindex & AA_X_CHILD) { - struct aa_profile *new_profile; - /* release by caller */ - new_profile = aa_find_child(profile, *name); - if (new_profile) - label = &new_profile->label; + /* TODO: switich to parse to get stack of child */ + struct aa_profile *new = aa_find_child(profile, lookup); + if (new) + /* release by caller */ + return &new->label; continue; } - label = aa_label_parse(&profile->label, *name, GFP_KERNEL, + label = aa_label_parse(&profile->label, lookup, GFP_KERNEL, true, false); - if (IS_ERR(label)) - label = NULL; + if (!IS_ERR_OR_NULL(label)) + /* release by caller */ + return label; } - /* released by caller */ - - return label; + return NULL; } /** @@ -568,9 +572,9 @@ static struct aa_label *x_to_label(struct aa_profile *profile, struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); struct aa_label *new = NULL; + struct aa_label *stack = NULL; struct aa_ns *ns = profile->ns; u32 xtype = xindex & AA_X_TYPE_MASK; - const char *stack = NULL; switch (xtype) { case AA_X_NONE: @@ -579,13 +583,13 @@ static struct aa_label *x_to_label(struct aa_profile *profile, break; case AA_X_TABLE: /* TODO: fix when perm mapping done at unload */ - stack = rules->file->trans.table[xindex & AA_X_INDEX_MASK]; - if (*stack != '&') { - /* released by caller */ - new = x_table_lookup(profile, xindex, lookupname); - stack = NULL; + /* released by caller + * if null for both stack and direct want to try fallback*/ + new = x_table_lookup(profile, xindex, lookupname); + if (!new || **lookupname != '&') break; - } + stack = new; + new = NULL; fallthrough; /* to X_NAME */ case AA_X_NAME: if (xindex & AA_X_CHILD) @@ -600,6 +604,7 @@ static struct aa_label *x_to_label(struct aa_profile *profile, break; } + /* fallback transition check */ if (!new) { if (xindex & AA_X_INHERIT) { /* (p|c|n)ix - don't change profile but do @@ -618,12 +623,12 @@ static struct aa_label *x_to_label(struct aa_profile *profile, /* base the stack on post domain transition */ struct aa_label *base = new; - new = aa_label_parse(base, stack, GFP_KERNEL, true, false); - if (IS_ERR(new)) - new = NULL; + new = aa_label_merge(base, stack, GFP_KERNEL); + /* null on error */ aa_put_label(base); } + aa_put_label(stack); /* released by caller */ return new; } @@ -650,9 +655,9 @@ static struct aa_label *profile_transition(const struct cred *subj_cred, error = aa_path_name(&bprm->file->f_path, profile->path_flags, buffer, &name, &info, profile->disconnected); if (error) { - if (profile_unconfined(profile) || + if (!profile_mediates(profile, AA_CLASS_FILE) || (profile->label.flags & FLAG_IX_ON_NAME_ERROR)) { - AA_DEBUG("name lookup ix on error"); + AA_DEBUG(DEBUG_DOMAIN, "name lookup ix on error"); error = 0; new = aa_get_newest_label(&profile->label); } @@ -660,14 +665,14 @@ static struct aa_label *profile_transition(const struct cred *subj_cred, goto audit; } - if (profile_unconfined(profile)) { + if (!profile_mediates(profile, AA_CLASS_FILE)) { new = find_attach(bprm, profile->ns, &profile->ns->base.profiles, name, &info); if (new) { - AA_DEBUG("unconfined attached to new label"); + AA_DEBUG(DEBUG_DOMAIN, "unconfined attached to new label"); return new; } - AA_DEBUG("unconfined exec no attachment"); + AA_DEBUG(DEBUG_DOMAIN, "unconfined exec no attachment"); return aa_get_newest_label(&profile->label); } @@ -719,9 +724,8 @@ static struct aa_label *profile_transition(const struct cred *subj_cred, } audit: - aa_audit_file(subj_cred, profile, &perms, OP_EXEC, MAY_EXEC, name, - target, new, - cond->uid, info, error); + aa_audit_file(subj_cred, profile, &perms, OP_EXEC, MAY_EXEC, name, target, new, + cond->uid, info, error, true); if (!new || nonewprivs) { aa_put_label(new); return ERR_PTR(error); @@ -748,7 +752,7 @@ static int profile_onexec(const struct cred *subj_cred, AA_BUG(!bprm); AA_BUG(!buffer); - if (profile_unconfined(profile)) { + if (!profile_mediates(profile, AA_CLASS_FILE)) { /* change_profile on exec already granted */ /* * NOTE: Domain transitions from unconfined are allowed @@ -761,9 +765,9 @@ static int profile_onexec(const struct cred *subj_cred, error = aa_path_name(&bprm->file->f_path, profile->path_flags, buffer, &xname, &info, profile->disconnected); if (error) { - if (profile_unconfined(profile) || + if (!profile_mediates(profile, AA_CLASS_FILE) || (profile->label.flags & FLAG_IX_ON_NAME_ERROR)) { - AA_DEBUG("name lookup ix on error"); + AA_DEBUG(DEBUG_DOMAIN, "name lookup ix on error"); error = 0; } xname = bprm->filename; @@ -801,7 +805,7 @@ static int profile_onexec(const struct cred *subj_cred, audit: return aa_audit_file(subj_cred, profile, &perms, OP_EXEC, AA_MAY_ONEXEC, xname, - NULL, onexec, cond->uid, info, error); + NULL, onexec, cond->uid, info, error, false); } /* ensure none ns domain transitions are correctly applied with onexec */ @@ -858,7 +862,7 @@ static struct aa_label *handle_onexec(const struct cred *subj_cred, OP_CHANGE_ONEXEC, AA_MAY_ONEXEC, bprm->filename, NULL, onexec, GLOBAL_ROOT_UID, - "failed to build target label", -ENOMEM)); + "failed to build target label", -ENOMEM, false)); return ERR_PTR(error); } @@ -901,8 +905,8 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) * * Testing for unconfined must be done before the subset test */ - if ((bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) && !unconfined(label) && - !ctx->nnp) + if ((bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) && + label_mediates(label, AA_CLASS_FILE) && !ctx->nnp) ctx->nnp = aa_get_label(label); /* buffer freed below, name is pointer into buffer */ @@ -940,7 +944,7 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) * aways results in a further reduction of permissions. */ if ((bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) && - !unconfined(label) && + label_mediates(label, AA_CLASS_FILE) && !aa_label_is_unconfined_subset(new, ctx->nnp)) { error = -EPERM; info = "no new privs"; @@ -994,7 +998,8 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) aa_audit_file(current_cred(), profile, &nullperms, OP_EXEC, MAY_EXEC, bprm->filename, NULL, new, - vfsuid_into_kuid(vfsuid), info, error)); + vfsuid_into_kuid(vfsuid), info, error, + false)); aa_put_label(new); goto done; } @@ -1045,7 +1050,7 @@ static struct aa_label *build_change_hat(const struct cred *subj_cred, AA_MAY_CHANGEHAT, name, hat ? hat->base.hname : NULL, hat ? &hat->label : NULL, GLOBAL_ROOT_UID, info, - error); + error, false); if (!hat || (error && error != -ENOENT)) return ERR_PTR(error); /* if hat && error - complain mode, already audited and we adjust for @@ -1138,7 +1143,7 @@ static struct aa_label *change_hat(const struct cred *subj_cred, aa_audit_file(subj_cred, profile, &nullperms, OP_CHANGE_HAT, AA_MAY_CHANGEHAT, name, NULL, NULL, - GLOBAL_ROOT_UID, info, error); + GLOBAL_ROOT_UID, info, error, false); } } return ERR_PTR(error); @@ -1189,20 +1194,40 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) label = aa_get_newest_cred_label(subj_cred); previous = aa_get_newest_label(ctx->previous); + if (!label_mediates(label, AA_CLASS_FILE)) { + info = "unconfined can not change_hat"; + error = -EPERM; + goto fail; + } + /* * Detect no new privs being set, and store the label it * occurred under. Ideally this would happen when nnp * is set but there isn't a good way to do that yet. * - * Testing for unconfined must be done before the subset test + * Testing for mediation must be done before the subset test */ - if (task_no_new_privs(current) && !unconfined(label) && !ctx->nnp) + if (task_no_new_privs(current) && !ctx->nnp) ctx->nnp = aa_get_label(label); + /* return -EPERM when unconfined doesn't have children to avoid + * changing the traditional error code for unconfined. + */ if (unconfined(label)) { - info = "unconfined can not change_hat"; - error = -EPERM; - goto fail; + struct label_it i; + bool empty = true; + + rcu_read_lock(); + label_for_each_in_ns(i, labels_ns(label), label, profile) { + empty &= list_empty(&profile->base.profiles); + } + rcu_read_unlock(); + + if (empty) { + info = "unconfined can not change_hat"; + error = -EPERM; + goto fail; + } } if (count) { @@ -1223,11 +1248,13 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) /* * no new privs prevents domain transitions that would * reduce restrictions. + * label_mediates(label, AA_CLASS_FILE) == true here */ - if (task_no_new_privs(current) && !unconfined(label) && + if (task_no_new_privs(current) && !aa_label_is_unconfined_subset(new, ctx->nnp)) { /* not an apparmor denial per se, so don't log it */ - AA_DEBUG("no_new_privs - change_hat denied"); + AA_DEBUG(DEBUG_DOMAIN, + "no_new_privs - change_hat denied"); error = -EPERM; goto out; } @@ -1244,11 +1271,13 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) /* * no new privs prevents domain transitions that would * reduce restrictions. + * label_mediates(label, AA_CLASS_FILE) == true here */ - if (task_no_new_privs(current) && !unconfined(label) && + if (task_no_new_privs(current) && !aa_label_is_unconfined_subset(previous, ctx->nnp)) { /* not an apparmor denial per se, so don't log it */ - AA_DEBUG("no_new_privs - change_hat denied"); + AA_DEBUG(DEBUG_DOMAIN, + "no_new_privs - change_hat denied"); error = -EPERM; goto out; } @@ -1281,7 +1310,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) fn_for_each_in_ns(label, profile, aa_audit_file(subj_cred, profile, &perms, OP_CHANGE_HAT, AA_MAY_CHANGEHAT, NULL, NULL, target, - GLOBAL_ROOT_UID, info, error)); + GLOBAL_ROOT_UID, info, error, false)); goto out; } @@ -1306,7 +1335,7 @@ static int change_profile_perms_wrapper(const char *op, const char *name, error = aa_audit_file(subj_cred, profile, perms, op, request, name, NULL, target, GLOBAL_ROOT_UID, info, - error); + error, false); return error; } @@ -1349,12 +1378,13 @@ int aa_change_profile(const char *fqname, int flags) * * Testing for unconfined must be done before the subset test */ - if (task_no_new_privs(current) && !unconfined(label) && !ctx->nnp) + if (task_no_new_privs(current) && + label_mediates(label, AA_CLASS_FILE) && !ctx->nnp) ctx->nnp = aa_get_label(label); if (!fqname || !*fqname) { aa_put_label(label); - AA_DEBUG("no profile name"); + AA_DEBUG(DEBUG_DOMAIN, "no profile name"); return -EINVAL; } @@ -1375,7 +1405,7 @@ int aa_change_profile(const char *fqname, int flags) /* This should move to a per profile test. Requires pushing build * into callback */ - if (!stack && unconfined(label) && + if (!stack && !label_mediates(label, AA_CLASS_FILE) && label == &labels_ns(label)->unconfined->label && aa_unprivileged_unconfined_restricted && /* TODO: refactor so this check is a fn */ @@ -1390,7 +1420,8 @@ int aa_change_profile(const char *fqname, int flags) (void) fn_for_each_in_ns(label, profile, aa_audit_file(subj_cred, profile, &perms, op, request, auditname, NULL, target, - GLOBAL_ROOT_UID, stack_msg, 0)); + GLOBAL_ROOT_UID, stack_msg, 0, + false)); perms.audit = 0; } @@ -1470,10 +1501,12 @@ int aa_change_profile(const char *fqname, int flags) * no new privs prevents domain transitions that would * reduce restrictions. */ - if (task_no_new_privs(current) && !unconfined(label) && + if (task_no_new_privs(current) && + label_mediates(label, AA_CLASS_FILE) && !aa_label_is_unconfined_subset(new, ctx->nnp)) { /* not an apparmor denial per se, so don't log it */ - AA_DEBUG("no_new_privs - change_hat denied"); + AA_DEBUG(DEBUG_DOMAIN, + "no_new_privs - change_hat denied"); error = -EPERM; goto out; } @@ -1509,7 +1542,7 @@ int aa_change_profile(const char *fqname, int flags) aa_audit_file(subj_cred, profile, &perms, op, request, auditname, NULL, new ? new : target, - GLOBAL_ROOT_UID, info, error)); + GLOBAL_ROOT_UID, info, error, false)); out: aa_put_label(new); diff --git a/security/apparmor/file.c b/security/apparmor/file.c index c03eb7c19f162..3da8d79a7017a 100644 --- a/security/apparmor/file.c +++ b/security/apparmor/file.c @@ -13,13 +13,17 @@ #include #include #include +#include +#include "include/af_unix.h" #include "include/apparmor.h" #include "include/audit.h" #include "include/cred.h" #include "include/file.h" +#include "include/ipc.h" #include "include/match.h" #include "include/net.h" +#include "include/notify.h" #include "include/path.h" #include "include/policy.h" #include "include/label.h" @@ -75,6 +79,104 @@ static void file_audit_cb(struct audit_buffer *ab, void *va) } } +// ??? differentiate between +// cached - allow : no audit == 1 +// cached - deny : no audit < 0 +// cached - complain : no audit +// cached - partial : audit missing part : as miss +// not cached = 0 +static int check_cache(struct aa_profile *profile, + struct apparmor_audit_data *ad) +{ + struct aa_audit_node *hit; + + AA_BUG(!profile); + ad->subj_label = &profile->label; // normally set in aa_audit + + /* TODO: need rcu locking around whole check once we allow + * removing node from cache + */ + AA_DEBUG(DEBUG_UPCALL, "cache check: profile '%s', pid %d name:'%s'", + profile->base.hname, current->pid, ad->name); + hit = aa_audit_cache_find(&profile->learning_cache, ad); + if (hit) { + AA_DEBUG(DEBUG_UPCALL, " matched node in audit cache"); + if (ad->request & hit->data.denied) { + /* this request could only partly succeed prompting for + * the part and failing makes no sense + */ + AA_DEBUG(DEBUG_UPCALL, + " hit denied, request: 0x%x by cached deny 0x%x\n", + ad->request, hit->data.denied); + aa_put_audit_node(hit); + return ad->error; + } else if (ad->request & ~hit->data.request) { + /* asking for more perms than is cached */ + AA_DEBUG(DEBUG_UPCALL, + " miss insufficient perms, request: 0x%x cached 0x%x\n", + ad->request, hit->data.request); + /* continue to do prompt */ + } else { + AA_DEBUG(DEBUG_UPCALL, "cache hit->error %d. returning 0", + hit->data.error); + aa_put_audit_node(hit); + /* don't audit: if its in the cache already audited */ + return 0; + } + aa_put_audit_node(hit); + } else { + AA_DEBUG(DEBUG_UPCALL, "cache miss"); + } + + return 1; +} + +// error - immediate return +// - debug message do audit +// caching is handled on listener task side +static int check_user(struct aa_profile *profile, + struct apparmor_audit_data *ad, + struct aa_perms *perms) +{ + struct aa_audit_node *node = NULL; + int err; + + /* assume we are going to dispatch */ + node = aa_dup_audit_data(ad, GFP_KERNEL); + if (!node) { + AA_DEBUG(DEBUG_UPCALL, + "notifcation failed to duplicate with error -ENOMEM\n"); + /* do audit */ + return -ENOMEM; + } + + get_task_struct(current); + node->data.subjtsk = current; + node->data.type = AUDIT_APPARMOR_USER; + node->data.request = ad->request; + node->data.denied = ad->request & ~perms->allow; + err = aa_do_notification(APPARMOR_NOTIF_OP, node); + put_task_struct(node->data.subjtsk); + + if (err) { + // do we want to do something special with -ERESTARTSYS + AA_DEBUG(DEBUG_UPCALL, "notifcation failed with error %d\n", + err); + goto return_to_audit; + } + + /* update based on node data for audit */ + perms->deny = node->data.denied; + perms->allow = node->data.request & ~node->data.denied; + ad->request |= node->data.request; + ad->denied = node->data.denied; + ad->error = node->data.error; + +return_to_audit: + aa_put_audit_node(node); + return err; +} + /** * aa_audit_file - handle the auditing of file operations * @subj_cred: cred of the subject @@ -95,9 +197,10 @@ int aa_audit_file(const struct cred *subj_cred, struct aa_profile *profile, struct aa_perms *perms, const char *op, u32 request, const char *name, const char *target, struct aa_label *tlabel, - kuid_t ouid, const char *info, int error) + kuid_t ouid, const char *info, int error, bool prompt) { int type = AUDIT_APPARMOR_AUTO; + int err; DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_FILE, op); ad.subj_cred = subj_cred; @@ -109,6 +212,45 @@ int aa_audit_file(const struct cred *subj_cred, ad.info = info; ad.error = error; ad.common.u.tsk = NULL; + ad.subjtsk = NULL; + + ad.denied = denied_perms(perms, ad.request); + + if (unlikely(ad.error)) { + u32 implicit_deny; + + /* learning cache - not audit dedup yet */ + err = check_cache(profile, &ad); + if (err <= 0) { + AA_DEBUG(DEBUG_UPCALL, "cache early bail %d\n", err); + /* cached */ + return err; + } + implicit_deny = (ad.request & ~perms->allow) & ~perms->deny; + if (USER_MODE(profile)) + perms->prompt = ALL_PERMS_MASK; + + if (ad.request & MAY_EXEC) + AA_DEBUG(DEBUG_UPCALL, + "do prompt %d: exec req 0x%x, allow 0x%x, deny 0x%x, ideny 0x%x, prompt 0x%x", + prompt, ad.request, perms->allow, perms->deny, + implicit_deny, perms->prompt); + + /* don't prompt + * - if explicit deny + * - if implicit_deny is not entirely covered by prompt + * as no point asking user to just deny it anyway. + */ + if (prompt && !(request & perms->deny) && + (perms->prompt & implicit_deny) == implicit_deny) { + err = check_user(profile, &ad, perms); + if (err == -ERESTARTSYS) { + AA_DEBUG(DEBUG_UPCALL, " check user returned -ERESTART_SYS"); + /* are there other errors we should bail on */ + return err; + } + } + } if (likely(!ad.error)) { u32 mask = perms->audit; @@ -140,8 +282,8 @@ int aa_audit_file(const struct cred *subj_cred, return ad.error; } - ad.denied = ad.request & ~perms->allow; - return aa_audit(type, profile, &ad, file_audit_cb); + err = aa_audit(type, profile, &ad, file_audit_cb); + return err; } /** @@ -172,7 +314,7 @@ static int path_name(const char *op, const struct cred *subj_cred, fn_for_each_confined(label, profile, aa_audit_file(subj_cred, profile, &nullperms, op, request, *name, - NULL, NULL, cond->uid, info, error)); + NULL, NULL, cond->uid, info, error, true)); return error; } @@ -182,7 +324,8 @@ static int path_name(const char *op, const struct cred *subj_cred, struct aa_perms default_perms = {}; /** * aa_lookup_fperms - convert dfa compressed perms to internal perms - * @file_rules: the aa_policydb to lookup perms for (NOT NULL) + * @subj_uid: uid to use for subject owner test + * @rules: the aa_policydb to lookup perms for (NOT NULL) * @state: state in dfa * @cond: conditions to consider (NOT NULL) * @@ -190,18 +333,21 @@ struct aa_perms default_perms = {}; * * Returns: a pointer to a file permission set */ -struct aa_perms *aa_lookup_fperms(struct aa_policydb *file_rules, - aa_state_t state, struct path_cond *cond) +struct aa_perms *aa_lookup_condperms(kuid_t subj_uid, struct aa_policydb *rules, + aa_state_t state, struct path_cond *cond) { - unsigned int index = ACCEPT_TABLE(file_rules->dfa)[state]; + unsigned int index = ACCEPT_TABLE(rules->dfa)[state]; - if (!(file_rules->perms)) + if (!(rules->perms)) return &default_perms; - if (uid_eq(current_fsuid(), cond->uid)) - return &(file_rules->perms[index]); + if ((ACCEPT_TABLE2(rules->dfa)[state] & ACCEPT_FLAG_OWNER)) { + if (uid_eq(subj_uid, cond->uid)) + return &(rules->perms[index]); + return &(rules->perms[index + 1]); + } - return &(file_rules->perms[index + 1]); + return &(rules->perms[index]); } /** @@ -220,21 +366,23 @@ aa_state_t aa_str_perms(struct aa_policydb *file_rules, aa_state_t start, { aa_state_t state; state = aa_dfa_match(file_rules->dfa, start, name); - *perms = *(aa_lookup_fperms(file_rules, state, cond)); + *perms = *(aa_lookup_condperms(current_fsuid(), file_rules, state, + cond)); return state; } -static int __aa_path_perm(const char *op, const struct cred *subj_cred, - struct aa_profile *profile, const char *name, - u32 request, struct path_cond *cond, int flags, - struct aa_perms *perms) +int __aa_path_perm(const char *op, const struct cred *subj_cred, + struct aa_profile *profile, const char *name, + u32 request, struct path_cond *cond, int flags, + struct aa_perms *perms, bool prompt) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); int e = 0; - if (profile_unconfined(profile)) + if (!profile_mediates(profile, AA_CLASS_FILE) || + ((flags & PATH_SOCK_COND) && !RULE_MEDIATES_AF(rules, AF_UNIX))) return 0; aa_str_perms(rules->file, rules->file->start[AA_CLASS_FILE], name, cond, perms); @@ -242,7 +390,7 @@ static int __aa_path_perm(const char *op, const struct cred *subj_cred, e = -EACCES; return aa_audit_file(subj_cred, profile, perms, op, request, name, NULL, NULL, - cond->uid, NULL, e); + cond->uid, NULL, e, prompt); } @@ -250,12 +398,12 @@ static int profile_path_perm(const char *op, const struct cred *subj_cred, struct aa_profile *profile, const struct path *path, char *buffer, u32 request, struct path_cond *cond, int flags, - struct aa_perms *perms) + struct aa_perms *perms, bool prompt) { const char *name; int error; - if (profile_unconfined(profile)) + if (!profile_mediates(profile, AA_CLASS_FILE)) return 0; error = path_name(op, subj_cred, &profile->label, path, @@ -264,7 +412,7 @@ static int profile_path_perm(const char *op, const struct cred *subj_cred, if (error) return error; return __aa_path_perm(op, subj_cred, profile, name, request, cond, - flags, perms); + flags, perms, prompt); } /** @@ -295,8 +443,9 @@ int aa_path_perm(const char *op, const struct cred *subj_cred, if (!buffer) return -ENOMEM; error = fn_for_each_confined(label, profile, - profile_path_perm(op, subj_cred, profile, path, buffer, - request, cond, flags, &perms)); + profile_path_perm(op, subj_cred, profile, path, + buffer, request, + cond, flags, &perms, true)); aa_put_buffer(buffer); @@ -406,9 +555,9 @@ static int profile_path_link(const struct cred *subj_cred, error = 0; audit: - return aa_audit_file(subj_cred, - profile, &lperms, OP_LINK, request, lname, tname, - NULL, cond->uid, info, error); + return aa_audit_file(subj_cred, profile, &lperms, OP_LINK, request, + lname, tname, + NULL, cond->uid, info, error, false); } /** @@ -511,7 +660,7 @@ static int __file_path_perm(const char *op, const struct cred *subj_cred, error = fn_for_each_not_in_set(flabel, label, profile, profile_path_perm(op, subj_cred, profile, &file->f_path, buffer, - request, &cond, flags, &perms)); + request, &cond, flags, &perms, false)); if (denied && !error) { /* * check every profile in file label that was not tested @@ -526,13 +675,13 @@ static int __file_path_perm(const char *op, const struct cred *subj_cred, profile_path_perm(op, subj_cred, profile, &file->f_path, buffer, request, &cond, flags, - &perms)); + &perms, false)); else error = fn_for_each_not_in_set(label, flabel, profile, profile_path_perm(op, subj_cred, profile, &file->f_path, buffer, request, &cond, flags, - &perms)); + &perms, false)); } if (!error) update_file_ctx(file_ctx(file), label, request); @@ -570,6 +719,74 @@ static int __file_sock_perm(const char *op, const struct cred *subj_cred, return error; } +/* TODO: combine with __file_path_perm */ +static int __file_mqueue_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, + struct aa_label *flabel, struct file *file, + u32 request, u32 denied, bool in_atomic) +{ + struct aa_profile *profile; + char *buffer; + int error; + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_POSIX_MQUEUE, op); + + /* revalidation due to label out of date. No revocation at this time */ + if (!denied && aa_label_is_subset(flabel, label)) + /* TODO: check for revocation on stale profiles */ + return 0; + + buffer = aa_get_buffer(in_atomic); + if (!buffer) + return -ENOMEM; + + ad.subj_cred = subj_cred; + ad.request = request; + ad.peer = NULL; + ad.mq.ouid = file_inode(file)->i_uid; + + /* check every profile in task label not in current cache */ + error = fn_for_each_not_in_set(flabel, label, profile, + aa_profile_mqueue_perm(profile, &file->f_path, + request, buffer, &ad)); + if (denied && !error) { + /* + * check every profile in file label that was not tested + * in the initial check above. + * + * TODO: cache full perms so this only happens because of + * conditionals + * TODO: don't audit here + */ + if (label == flabel) + error = fn_for_each(label, profile, + aa_profile_mqueue_perm(profile, &file->f_path, + request, buffer, &ad)); + else + error = fn_for_each_not_in_set(label, flabel, profile, + aa_profile_mqueue_perm(profile, &file->f_path, + request, buffer, &ad)); + } + if (!error) + update_file_ctx(file_ctx(file), label, request); + + aa_put_buffer(buffer); + + return error; +} + +/* wrapper fn to indicate semantics of the check */ +bool __subj_label_is_cached(struct aa_label *subj_label, + struct aa_label *obj_label) +{ + return aa_label_is_subset(obj_label, subj_label); +} + +/* for now separate fn to indicate semantics of the check */ +bool __file_is_delegated(struct aa_label *obj_label) +{ + return unconfined(obj_label); +} + /** * aa_file_perm - do permission revalidation check & audit for @file * @op: operation being checked @@ -607,8 +824,8 @@ int aa_file_perm(const char *op, const struct cred *subj_cred, * delegation from unconfined tasks */ denied = request & ~fctx->allow; - if (unconfined(label) || unconfined(flabel) || - (!denied && aa_label_is_subset(flabel, label))) { + if (unconfined(label) || __file_is_delegated(flabel) || + (!denied && __subj_label_is_cached(label, flabel))) { rcu_read_unlock(); goto done; } @@ -617,7 +834,10 @@ int aa_file_perm(const char *op, const struct cred *subj_cred, rcu_read_unlock(); /* TODO: label cross check */ - if (file->f_path.mnt && path_mediated_fs(file->f_path.dentry)) + if (is_mqueue_inode(file_inode(file))) { + error = __file_mqueue_perm(op, subj_cred, label, flabel, file, + request, denied, in_atomic); + } else if (file->f_path.mnt && path_mediated_fs(file->f_path.dentry)) error = __file_path_perm(op, subj_cred, label, flabel, file, request, denied, in_atomic); diff --git a/security/apparmor/include/af_inet.h b/security/apparmor/include/af_inet.h new file mode 100644 index 0000000000000..c0e32ec55c054 --- /dev/null +++ b/security/apparmor/include/af_inet.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * AppArmor security module + * + * This file contains AppArmor af_unix fine grained mediation + * + * Copyright 2024 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ +#ifndef __AA_AF_INET_H + +#include "label.h" + +int aa_inet_peer_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, u32 request, + struct sock *sk, struct sock *peer_sk, + struct aa_label *peer_label); +int aa_inet_label_sk_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, u32 request, + struct sock *sk); +int aa_inet_sock_perm(const char *op, u32 request, struct socket *sock); +int aa_inet_create_perm(struct aa_label *label, int family, int type, + int protocol); +int aa_inet_bind_perm(struct socket *sock, struct sockaddr *address, + int addrlen); +int aa_inet_connect_perm(struct socket *sock, struct sockaddr *address, + int addrlen); +int aa_inet_listen_perm(struct socket *sock, int backlog); +int aa_inet_accept_perm(struct socket *sock, struct socket *newsock); +int aa_inet_msg_perm(const char *op, u32 request, struct socket *sock, + struct msghdr *msg, int size); +int aa_inet_opt_perm(const char *op, u32 request, struct socket *sock, int level, + int optname); +int aa_inet_file_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, u32 request, + struct socket *sock); + +#endif /* __AA_AF_INET_H */ diff --git a/security/apparmor/include/af_unix.h b/security/apparmor/include/af_unix.h new file mode 100644 index 0000000000000..bd0fb49bea966 --- /dev/null +++ b/security/apparmor/include/af_unix.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * AppArmor security module + * + * This file contains AppArmor af_unix fine grained mediation + * + * Copyright 2014 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ +#ifndef __AA_AF_UNIX_H + +#include + +#include "label.h" +//#include "include/net.h" + +#define unix_addr_len(L) ((L) - sizeof(sa_family_t)) +#define unix_abstract_name_len(L) (unix_addr_len(L) - 1) +#define unix_abstract_len(U) (unix_abstract_name_len((U)->addr->len)) +#define addr_unix_abstract_name(B) ((B)[0] == 0) +#define addr_unix_anonymous(U) (addr_unix_len(U) <= 0) +#define addr_unix_abstract(U) (!addr_unix_anonymous(U) && addr_unix_abstract_name((U)->addr)) +//#define unix_addr_fs(U) (!unix_addr_anonymous(U) && !unix_addr_abstract_name((U)->addr)) + +#define unix_addr(A) ((struct sockaddr_un *)(A)) +#define unix_addr_anon(A, L) ((A) && unix_addr_len(L) <= 0) +#define unix_addr_fs(A, L) (!unix_addr_anon(A, L) && \ + !addr_unix_abstract_name(unix_addr(A)->sun_path)) + +#define UNIX_ANONYMOUS(U) (!unix_sk(U)->addr) +/* from net/unix/af_unix.c */ +#define UNIX_ABSTRACT(U) (!UNIX_ANONYMOUS(U) && \ + unix_sk(U)->addr->hash < UNIX_HASH_SIZE) +#define UNIX_FS(U) (!UNIX_ANONYMOUS(U) && unix_sk(U)->addr->name->sun_path[0]) +#define unix_peer(sk) (unix_sk(sk)->peer) +#define unix_connected(S) ((S)->state == SS_CONNECTED) + +static inline void print_unix_addr(struct sockaddr_un *A, int L) +{ + char *buf = (A) ? (char *) &(A)->sun_path : NULL; + int len = unix_addr_len(L); + + if (!buf || len <= 0) + pr_warn(" "); + else if (buf[0]) + pr_warn(" %s", buf); + else + /* abstract name len includes leading \0 */ + pr_warn(" %d @%.*s", len - 1, len - 1, buf+1); +}; + +#define print_unix_sk(SK) \ +do { \ + struct unix_sock *u = unix_sk(SK); \ + \ + pr_warn("%s: f %d, t %d, p %d", #SK, \ + (SK)->sk_family, (SK)->sk_type, (SK)->sk_protocol); \ + if (u->addr) \ + print_unix_addr(u->addr->name, u->addr->len); \ + else \ + print_unix_addr(NULL, sizeof(sa_family_t)); \ +} while (0) + +#define print_sk(SK) \ +do { \ + if (!(SK)) { \ + pr_warn("%s: %s is null\n", __func__, #SK); \ + } else if ((SK)->sk_family == PF_UNIX) { \ + print_unix_sk(SK); \ + pr_warn("\n"); \ + } else { \ + pr_warn("%s: %s: family %d\n", __func__, #SK, \ + (SK)->sk_family); \ + } \ +} while (0) + +#define print_sock_addr(U) \ +do { \ + pr_warn("%s:\n", __func__); \ + pr_warn" sock %s:", sock_ctx && sock_ctx->label ? \ + aa_label_printk(sock_ctx->label, GFP_ATOMIC); : \ + ""); print_sk(sock); \ + pr_warn(" other %s:", other_ctx && other_ctx->label ? \ + aa_label_printk(other_ctx->label, GFP_ATOMIC); : \ + ""); print_sk(other); \ + pr_warn(" new %s", new_ctx && new_ctx->label ? \ + aa_label_printk(new_ctx->label, GFP_ATOMIC); : \ + ""); print_sk(newsk); \ +} while (0) + + + + +int aa_unix_peer_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, u32 request, + struct sock *sk, struct sock *peer_sk, + struct aa_label *peer_label); +int aa_unix_label_sk_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, u32 request, + struct sock *sk); +int aa_unix_sock_perm(const char *op, u32 request, struct socket *sock); +int aa_unix_create_perm(struct aa_label *label, int family, int type, + int protocol); +int aa_unix_bind_perm(struct socket *sock, struct sockaddr *address, + int addrlen); +int aa_unix_connect_perm(struct socket *sock, struct sockaddr *address, + int addrlen); +int aa_unix_listen_perm(struct socket *sock, int backlog); +int aa_unix_accept_perm(struct socket *sock, struct socket *newsock); +int aa_unix_msg_perm(const char *op, u32 request, struct socket *sock, + struct msghdr *msg, int size); +int aa_unix_opt_perm(const char *op, u32 request, struct socket *sock, int level, + int optname); +int aa_unix_file_perm(const struct cred *subj_cred, + struct aa_label *label, const char *op, u32 request, + struct socket *sock); + +#endif /* __AA_AF_UNIX_H */ diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h index f83934913b0fd..6b85f51b6e20f 100644 --- a/security/apparmor/include/apparmor.h +++ b/security/apparmor/include/apparmor.h @@ -20,7 +20,7 @@ #define AA_CLASS_UNKNOWN 1 #define AA_CLASS_FILE 2 #define AA_CLASS_CAP 3 -#define AA_CLASS_DEPRECATED 4 +#define AA_CLASS_NET_COMPAT 4 #define AA_CLASS_RLIMITS 5 #define AA_CLASS_DOMAIN 6 #define AA_CLASS_MOUNT 7 @@ -38,12 +38,13 @@ #define AA_CLASS_X 31 #define AA_CLASS_DBUS 32 +/* NOTE: if AA_CLASS_LAST > 63 need to update label->mediates */ #define AA_CLASS_LAST AA_CLASS_DBUS /* Control parameters settable through module/boot flags */ extern enum audit_mode aa_g_audit; extern bool aa_g_audit_header; -extern bool aa_g_debug; +extern int aa_g_debug; extern bool aa_g_hash_policy; extern bool aa_g_export_binary; extern int aa_g_rawdata_compression_level; diff --git a/security/apparmor/include/apparmorfs.h b/security/apparmor/include/apparmorfs.h index 1e94904f68d90..3f954194a0e78 100644 --- a/security/apparmor/include/apparmorfs.h +++ b/security/apparmor/include/apparmorfs.h @@ -17,6 +17,7 @@ enum aa_sfs_type { AA_SFS_TYPE_BOOLEAN, AA_SFS_TYPE_STRING, AA_SFS_TYPE_U64, + AA_SFS_TYPE_INTPTR, AA_SFS_TYPE_FOPS, AA_SFS_TYPE_DIR, }; @@ -33,6 +34,7 @@ struct aa_sfs_entry { char *string; unsigned long u64; struct aa_sfs_entry *files; + int *intptr; } v; const struct file_operations *file_ops; }; @@ -51,6 +53,10 @@ extern const struct file_operations aa_sfs_seq_file_ops; { .name = (_name), .mode = 0444, \ .v_type = AA_SFS_TYPE_U64, .v.u64 = (_value), \ .file_ops = &aa_sfs_seq_file_ops } +#define AA_SFS_FILE_INTPTR(_name, _value) \ + { .name = (_name), .mode = 0444, \ + .v_type = AA_SFS_TYPE_INTPTR, .v.intptr = &(_value), \ + .file_ops = &aa_sfs_seq_file_ops } #define AA_SFS_FILE_FOPS(_name, _mode, _fops) \ { .name = (_name), .v_type = AA_SFS_TYPE_FOPS, \ .mode = (_mode), .file_ops = (_fops) } @@ -89,6 +95,7 @@ enum aafs_prof_type { AAFS_PROF_RAW_DATA, AAFS_PROF_RAW_HASH, AAFS_PROF_RAW_ABI, + AAFS_PROF_LEARNING_COUNT, AAFS_PROF_SIZEOF, }; diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h index acbb03b9bd25c..2fb888090a973 100644 --- a/security/apparmor/include/audit.h +++ b/security/apparmor/include/audit.h @@ -19,6 +19,7 @@ #include "file.h" #include "label.h" +#include "notify.h" extern const char *const audit_mode_names[]; #define AUDIT_MAX_INDEX 5 @@ -38,6 +39,7 @@ enum audit_type { AUDIT_APPARMOR_STATUS, AUDIT_APPARMOR_ERROR, AUDIT_APPARMOR_KILL, + AUDIT_APPARMOR_USER, AUDIT_APPARMOR_AUTO }; @@ -108,7 +110,9 @@ enum audit_type { #define OP_URING_OVERRIDE "uring_override" #define OP_URING_SQPOLL "uring_sqpoll" +#define AUDIT_TAILGLOB_NAME 1 struct apparmor_audit_data { + u32 flags; /* control flags not part of actual data */ int error; int type; u16 class; @@ -119,6 +123,9 @@ struct apparmor_audit_data { const char *info; u32 request; u32 denied; + + struct task_struct *subjtsk; + union { /* these entries require a custom callback fn */ struct { @@ -142,6 +149,13 @@ struct apparmor_audit_data { void *addr; int addrlen; } net; + struct { + kuid_t fsuid; + kuid_t ouid; + } mq; + struct { + const char *target; + } ns; }; }; struct { @@ -164,6 +178,44 @@ struct apparmor_audit_data { struct common_audit_data common; }; +struct aa_audit_node { + struct kref count; + struct apparmor_audit_data data; + struct list_head list; + struct aa_knotif knotif; +}; +extern struct kmem_cache *aa_audit_slab; + +static inline struct aa_audit_node *aa_alloc_audit_node(gfp_t gfp) +{ + return kmem_cache_zalloc(aa_audit_slab, gfp); +} + + +struct aa_audit_cache { + spinlock_t lock; + int size; + struct list_head head; +}; + +static inline void aa_audit_cache_init(struct aa_audit_cache *cache) +{ + cache->size = 0; + spin_lock_init(&cache->lock); + INIT_LIST_HEAD(&cache->head); +} + +struct aa_audit_node *aa_audit_cache_find(struct aa_audit_cache *cache, + struct apparmor_audit_data *ad); +struct aa_audit_node *aa_audit_cache_insert(struct aa_audit_cache *cache, + struct aa_audit_node *node); +void aa_audit_cache_update_ent(struct aa_audit_cache *cache, + struct aa_audit_node *node, + struct apparmor_audit_data *data); +void aa_audit_cache_destroy(struct aa_audit_cache *cache); + + + /* macros for dealing with apparmor_audit_data structure */ #define aad(SA) (container_of(SA, struct apparmor_audit_data, common)) #define aad_of_va(VA) aad((struct common_audit_data *)(VA)) @@ -173,6 +225,7 @@ struct apparmor_audit_data { struct apparmor_audit_data NAME = { \ .class = (C), \ .op = (X), \ + .subjtsk = NULL, \ .common.type = (T), \ .common.u.tsk = NULL, \ .common.apparmor_audit_data = &NAME, \ @@ -199,9 +252,34 @@ static inline int complain_error(int error) return error; } -void aa_audit_rule_free(void *vrule); -int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule); +void aa_audit_rule_free(void *vrule, int lsmid); +int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, + int lsmid, gfp_t gfp); int aa_audit_rule_known(struct audit_krule *rule); -int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule); +int aa_audit_rule_match(struct lsmblob *blob, u32 field, u32 op, void *vrule, + int lsmid); + + +void aa_audit_node_free_kref(struct kref *kref); +struct aa_audit_node *aa_dup_audit_data(struct apparmor_audit_data *orig, + gfp_t gfp); +long aa_audit_data_cmp(struct apparmor_audit_data *lhs, + struct apparmor_audit_data *rhs); + + +static inline struct aa_audit_node *aa_get_audit_node(struct aa_audit_node *node) +{ + if (node) + kref_get(&(node->count)); + + return node; +} + +static inline void aa_put_audit_node(struct aa_audit_node *node) +{ + if (node) + kref_put(&node->count, aa_audit_node_free_kref); +} + #endif /* __AA_AUDIT_H */ diff --git a/security/apparmor/include/capability.h b/security/apparmor/include/capability.h index d6dcc604ec0cc..1ddcec2d1160d 100644 --- a/security/apparmor/include/capability.h +++ b/security/apparmor/include/capability.h @@ -36,6 +36,7 @@ struct aa_caps { extern struct aa_sfs_entry aa_sfs_entry_caps[]; +kernel_cap_t aa_profile_capget(struct aa_profile *profile); int aa_capable(const struct cred *subj_cred, struct aa_label *label, int cap, unsigned int opts); diff --git a/security/apparmor/include/crypto.h b/security/apparmor/include/crypto.h index 636a04e20d918..ceee04f4b4282 100644 --- a/security/apparmor/include/crypto.h +++ b/security/apparmor/include/crypto.h @@ -14,6 +14,8 @@ #ifdef CONFIG_SECURITY_APPARMOR_HASH unsigned int aa_hash_size(void); +void aa_snprint_hashstr(char *out, unsigned char *hash, unsigned int hsize); +char *aa_asprint_hashstr(unsigned char *hash, unsigned int hsize, gfp_t gfp); char *aa_calc_hash(void *data, size_t len); int aa_calc_profile_hash(struct aa_profile *profile, u32 version, void *start, size_t len); @@ -32,6 +34,15 @@ static inline unsigned int aa_hash_size(void) { return 0; } + +void aa_snprint_hashstr(char *out, unsigned char *hash, unsigned int hsize) +{ +} + +char *aa_asprint_hashstr(unsigned char *hash, unsigned int hsize, gfp_t gfp); +{ + return NULL; +} #endif #endif /* __APPARMOR_CRYPTO_H */ diff --git a/security/apparmor/include/file.h b/security/apparmor/include/file.h index 6e8f2aa66cd63..5bf87b0c2009d 100644 --- a/security/apparmor/include/file.h +++ b/security/apparmor/include/file.h @@ -75,14 +75,19 @@ int aa_audit_file(const struct cred *cred, struct aa_profile *profile, struct aa_perms *perms, const char *op, u32 request, const char *name, const char *target, struct aa_label *tlabel, kuid_t ouid, - const char *info, int error); + const char *info, int error, bool prompt); -struct aa_perms *aa_lookup_fperms(struct aa_policydb *file_rules, - aa_state_t state, struct path_cond *cond); +struct aa_perms *aa_lookup_condperms(kuid_t subj_uid, + struct aa_policydb *file_rules, + aa_state_t state, struct path_cond *cond); aa_state_t aa_str_perms(struct aa_policydb *file_rules, aa_state_t start, const char *name, struct path_cond *cond, struct aa_perms *perms); +int __aa_path_perm(const char *op, const struct cred *subj_cred, + struct aa_profile *profile, const char *name, + u32 request, struct path_cond *cond, int flags, + struct aa_perms *perms, bool prompt); int aa_path_perm(const char *op, const struct cred *subj_cred, struct aa_label *label, const struct path *path, int flags, u32 request, struct path_cond *cond); diff --git a/security/apparmor/include/inode.h b/security/apparmor/include/inode.h new file mode 100644 index 0000000000000..a9b3e4d6c968b --- /dev/null +++ b/security/apparmor/include/inode.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * AppArmor security module + * + * This file contains AppArmor file mediation function definitions. + * + * Copyright 2022 Canonical Ltd. + */ + +#ifndef __AA_INODE_H +#define __AA_INODE_H + +#include + +#include "lib.h" + +struct aa_inode_sec { + struct inode *inode; /* back pointer to inode object */ + struct aa_label *label; + u16 sclass; /* security class of this object */ + bool initialized; /* initialization flag */ + spinlock_t lock; +}; + +struct aa_superblock_sec { + struct aa_label *label; +}; + +static inline struct aa_inode_sec *apparmor_inode(const struct inode *inode) +{ + if (unlikely(!inode->i_security)) + return NULL; + return inode->i_security + apparmor_blob_sizes.lbs_inode; +} + +static inline struct aa_superblock_sec *apparmor_superblock( + const struct super_block *sb) +{ + return sb->s_security + apparmor_blob_sizes.lbs_superblock; +} + +#endif /* __AA_INODE_H */ diff --git a/security/apparmor/include/ipc.h b/security/apparmor/include/ipc.h index 74d17052f76bc..9df8563a4de5e 100644 --- a/security/apparmor/include/ipc.h +++ b/security/apparmor/include/ipc.h @@ -11,10 +11,71 @@ #ifndef __AA_IPC_H #define __AA_IPC_H +#include #include +#include "inode.h" +#include "perms.h" + +#define SIGUNKNOWN 0 +#define MAXMAPPED_SIG 35 + +struct aa_msg_sec { + struct aa_label *label; +}; + +struct aa_ipc_sec { + struct aa_label *label; +}; + +static inline struct aa_ipc_sec *apparmor_ipc(const struct kern_ipc_perm *ipc) +{ + return ipc->security + apparmor_blob_sizes.lbs_ipc; +} + +static inline struct aa_msg_sec *apparmor_msg_msg(const struct msg_msg *msg_msg) +{ + return msg_msg->security + apparmor_blob_sizes.lbs_msg_msg; +} + + +static inline bool is_mqueue_sb(struct super_block *sb) +{ + if (!sb) + pr_warn("mqueue sb == NULL\n"); + if (!sb && !sb->s_type->name) + pr_warn("mqueue sb name == NULL\n"); + return sb && sb->s_type->name && strcmp(sb->s_type->name, "mqueue") == 0; +} + +static inline bool is_mqueue_inode(struct inode *i) +{ + struct aa_inode_sec *isec; + + if (!i) + return false; + + isec = apparmor_inode(i); + return isec && isec->sclass == AA_CLASS_POSIX_MQUEUE; +} + int aa_may_signal(const struct cred *subj_cred, struct aa_label *sender, const struct cred *target_cred, struct aa_label *target, int sig); +#define AA_AUDIT_POSIX_MQUEUE_MASK (AA_MAY_WRITE | AA_MAY_READ | \ + AA_MAY_CREATE | AA_MAY_DELETE | \ + AA_MAY_OPEN | AA_MAY_SETATTR | \ + AA_MAY_GETATTR) + + +int aa_profile_mqueue_perm(struct aa_profile *profile, + const struct path *path, + u32 request, char *buffer, + struct apparmor_audit_data *ad); + +int aa_mqueue_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, + const struct path *path, u32 request); + #endif /* __AA_IPC_H */ diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h index 2a72e6b17d68b..e475ee5291e97 100644 --- a/security/apparmor/include/label.h +++ b/security/apparmor/include/label.h @@ -90,7 +90,7 @@ enum label_flags { FLAG_PROFILE = 0x200, /* label is a profile */ FLAG_EXPLICIT = 0x400, /* explicit static label */ FLAG_STALE = 0x800, /* replaced/removed */ - FLAG_RENAMED = 0x1000, /* label has renaming in it */ + FLAG_INTERRUPTIBLE = 0x1000, FLAG_REVOKED = 0x2000, /* label has revocation in it */ FLAG_DEBUG1 = 0x4000, FLAG_DEBUG2 = 0x8000, @@ -129,6 +129,7 @@ struct aa_label { long flags; u32 secid; int size; + u64 mediates; struct aa_profile *vec[]; }; @@ -255,21 +256,19 @@ for ((I).i = (I).j = 0; \ #define fn_for_each_not_in_set(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _not_in_set) -#define LABEL_MEDIATES(L, C) \ -({ \ - struct aa_profile *profile; \ - struct label_it i; \ - int ret = 0; \ - label_for_each(i, (L), profile) { \ - if (RULE_MEDIATES(&profile->rules, (C))) { \ - ret = 1; \ - break; \ - } \ - } \ - ret; \ -}) +static inline bool label_mediates(struct aa_label *L, unsigned char C) +{ + return (L)->mediates & (((u64) 1) << (C)); +} +static inline bool label_mediates_safe(struct aa_label *L, unsigned char C) +{ + if (C > AA_CLASS_LAST) + return false; + return label_mediates(L, C); +} +int aa_label_cmp(struct aa_label *a, struct aa_label *b); void aa_labelset_destroy(struct aa_labelset *ls); void aa_labelset_init(struct aa_labelset *ls); void __aa_labelset_update_subtree(struct aa_ns *ns); diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h index d7a894b1031ff..e76d4273141f0 100644 --- a/security/apparmor/include/lib.h +++ b/security/apparmor/include/lib.h @@ -18,23 +18,42 @@ extern struct aa_dfa *stacksplitdfa; -/* - * DEBUG remains global (no per profile flag) since it is mostly used in sysctl - * which is not related to profile accesses. - */ +#define list_add_entry(ent, list, member) list_add(&(ent)->member, (list)) +#define list_add_tail_entry(ent, list, member) list_add_tail(&(ent)->member, (list)) -#define DEBUG_ON (aa_g_debug) /* * split individual debug cases out in preparation for finer grained * debug controls in the future. */ -#define AA_DEBUG_LABEL DEBUG_ON #define dbg_printk(__fmt, __args...) pr_debug(__fmt, ##__args) -#define AA_DEBUG(fmt, args...) \ + +#define DEBUG_PROMPT 2 + +#define DEBUG_NONE 0 +#define DEBUG_LABEL_ABS_ROOT 1 +#define DEBUG_LABEL 2 +#define DEBUG_DOMAIN 4 +#define DEBUG_POLICY 8 +#define DEBUG_INTERFACE 0x10 +#define DEBUG_UPCALL 0x20 + +#define DEBUG_ALL 0x3f /* update if new DEBUG_X added */ +#define DEBUG_PARSE_ERROR (-1) + +#define DEBUG_ON (aa_g_debug != DEBUG_NONE) +#define DEBUG_ABS_ROOT (aa_g_debug & DEBUG_LABEL_ABS_ROOT) + +#define AA_DEBUG(opt, fmt, args...) \ do { \ - if (DEBUG_ON) \ - pr_debug_ratelimited("AppArmor: " fmt, ##args); \ + if (aa_g_debug & opt) \ + pr_warn("%s: " fmt, __func__, ##args); \ } while (0) +#define AA_DEBUG_ON(C, args...) do { if (C) AA_DEBUG(args); } while (0) +#define AA_DEBUG_LABEL(LAB, X, fmt, args) \ +do { \ + if ((LAB)->flags & FLAG_DEBUG1) \ + AA_DEBUG(X, fmt, args); \ +} while (0) #define AA_WARN(X) WARN((X), "APPARMOR WARN %s: %s\n", __func__, #X) @@ -51,6 +70,9 @@ extern struct aa_dfa *stacksplitdfa; #define AA_BUG_FMT(X, fmt, args...) no_printk(fmt, ##args) #endif +int aa_parse_debug_params(const char *str); +int aa_print_debug_params(char *buffer); + #define AA_ERROR(fmt, args...) \ pr_err_ratelimited("AppArmor: " fmt, ##args) @@ -96,6 +118,14 @@ static inline aa_state_t aa_dfa_null_transition(struct aa_dfa *dfa, return aa_dfa_next(dfa, start, 0); } +static inline aa_state_t aa_dfa_match_u16(struct aa_dfa *dfa, aa_state_t state, + u16 data) +{ + __be16 buffer = cpu_to_be16(data); + + return aa_dfa_match_len(dfa, state, (char *) &buffer, 2); +} + static inline bool path_mediated_fs(struct dentry *dentry) { return !(dentry->d_sb->s_flags & SB_NOUSER); @@ -282,7 +312,7 @@ __do_cleanup: \ } \ __done: \ if (!__new_) \ - AA_DEBUG("label build failed\n"); \ + AA_DEBUG(DEBUG_LABEL, "label build failed\n"); \ (__new_); \ }) diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h index 67bf888c3bd6b..dafc62dc72edf 100644 --- a/security/apparmor/include/net.h +++ b/security/apparmor/include/net.h @@ -49,12 +49,17 @@ struct aa_sk_ctx { struct aa_label *label; struct aa_label *peer; + struct path path; }; -#define SK_CTX(X) ((X)->sk_security) +static inline bool aa_secmark(void) +{ + return apparmor_blob_sizes.lbs_secmark; +} + static inline struct aa_sk_ctx *aa_sock(const struct sock *sk) { - return sk->sk_security; + return sk->sk_security + apparmor_blob_sizes.lbs_sock; } #define DEFINE_AUDIT_NET(NAME, OP, SK, F, T, P) \ @@ -74,10 +79,29 @@ static inline struct aa_sk_ctx *aa_sock(const struct sock *sk) (SK)->sk_protocol) + +/* struct aa_net - network confinement data + * @allow: basic network families permissions + * @audit: which network permissions to force audit + * @quiet: which network permissions to quiet rejects + */ +struct aa_net_compat { + u16 allow[AF_MAX]; + u16 audit[AF_MAX]; + u16 quiet[AF_MAX]; +}; + #define af_select(FAMILY, FN, DEF_FN) \ ({ \ int __e; \ switch ((FAMILY)) { \ + case PF_UNIX: \ + __e = aa_unix_ ## FN; \ + break; \ + case PF_INET: \ + case PF_INET6: \ + __e = aa_inet_ ## FN; \ + break; \ default: \ __e = DEF_FN; \ } \ @@ -92,6 +116,7 @@ struct aa_secmark { }; extern struct aa_sfs_entry aa_sfs_entry_network[]; +extern struct aa_sfs_entry aa_sfs_entry_network_compat[]; void audit_net_cb(struct audit_buffer *ab, void *va); int aa_profile_af_perm(struct aa_profile *profile, diff --git a/security/apparmor/include/notify.h b/security/apparmor/include/notify.h new file mode 100644 index 0000000000000..32061258e852f --- /dev/null +++ b/security/apparmor/include/notify.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * AppArmor security module + * + * This file contains AppArmor notifications function definitions. + * + * Copyright 2019 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#ifndef __AA_NOTIFY_H +#define __AA_NOTIFY_H + +#include +#include +#include +#include +#include + +#include + +#include "match.h" + +struct aa_ns; +struct aa_audit_node; +struct apparmor_audit_data; + +struct aa_listener { + struct kref count; + spinlock_t lock; + wait_queue_head_t wait; + struct list_head ns_proxies; /* aa_listener_proxy */ + struct list_head notifications; /* aa_audit_proxy */ + struct list_head pending; /* aa_audit_proxy */ + struct aa_ns *ns; /* counted - ns of listener */ + struct aa_dfa *filter; + u64 last_id; + u32 mask; + u32 flags; +}; + +struct aa_listener_proxy { + struct aa_ns *ns; /* counted - ns listening to */ + struct aa_listener *listener; + struct list_head llist; + struct list_head nslist; +}; + +#define KNOTIF_ON_LIST 1 +#define KNOTIF_PULSE +#define KNOTIF_PENDING +#define KNOTIF_CANCELLED +/* need to split knofif into audit_proxy + * prompt notifications only go to first taker so no need for completion + * in the proxy, it increases size of proxy in non-prompt case + */ +struct aa_knotif { + struct apparmor_audit_data *ad; /* counted */ + struct list_head list; + struct completion ready; + u64 id; + u16 ntype; + u16 flags; +}; + +void aa_free_listener_proxy(struct aa_listener_proxy *proxy); +bool aa_register_listener_proxy(struct aa_listener *listener, struct aa_ns *ns); +struct aa_listener *aa_new_listener(struct aa_ns *ns, gfp_t gfp); +struct aa_knotif *__aa_find_notif(struct aa_listener *listener, u64 id); +int aa_do_notification(u16 ntype, struct aa_audit_node *node); + +long aa_listener_unotif_recv(struct aa_listener *listener, void __user *buf, + u16 max_size); +long aa_listener_unotif_response(struct aa_listener *listener, + union apparmor_notif_resp *uresp, + u16 size); + +void aa_listener_kref(struct kref *kref); + +static inline struct aa_listener *aa_get_listener(struct aa_listener *listener) +{ + if (listener) + kref_get(&(listener->count)); + + return listener; +} + +static inline void aa_put_listener(struct aa_listener *listener) +{ + if (listener) + kref_put(&listener->count, aa_listener_kref); +} + +#endif /* __AA_NOTIFY_H */ diff --git a/security/apparmor/include/path.h b/security/apparmor/include/path.h index 343189903dbaf..8bb915d48dc7f 100644 --- a/security/apparmor/include/path.h +++ b/security/apparmor/include/path.h @@ -13,6 +13,7 @@ enum path_flags { PATH_IS_DIR = 0x1, /* path is a directory */ + PATH_SOCK_COND = 0x2, PATH_CONNECT_PATH = 0x4, /* connect disconnected paths to / */ PATH_CHROOT_REL = 0x8, /* do path lookup relative to chroot */ PATH_CHROOT_NSCONNECT = 0x10, /* connect paths that are at ns root */ diff --git a/security/apparmor/include/perms.h b/security/apparmor/include/perms.h index 0f7e913c3fc21..a8c43f4f6da04 100644 --- a/security/apparmor/include/perms.h +++ b/security/apparmor/include/perms.h @@ -204,6 +204,9 @@ void aa_perm_mask_to_str(char *str, size_t str_size, const char *chrs, u32 mask); void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names, u32 mask); +void aa_audit_perms(struct audit_buffer *ab, struct apparmor_audit_data *ad, + const char *chrs, u32 chrsmask, const char * const *names, + u32 namesmask); void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, u32 chrsmask, const char * const *names, u32 namesmask); void aa_apply_modes_to_perms(struct aa_profile *profile, @@ -216,6 +219,12 @@ void aa_profile_match_label(struct aa_profile *profile, int aa_profile_label_perm(struct aa_profile *profile, struct aa_profile *target, u32 request, int type, u32 *deny, struct apparmor_audit_data *ad); + +static inline u32 denied_perms(struct aa_perms *perms, u32 request) +{ + return request & (~perms->allow | perms->deny); +} + int aa_check_perms(struct aa_profile *profile, struct aa_perms *perms, u32 request, struct apparmor_audit_data *ad, void (*cb)(struct audit_buffer *, void *)); diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index 75088cc310b67..d5aeb7b71d296 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -34,7 +34,11 @@ struct aa_ns; extern int unprivileged_userns_apparmor_policy; +extern int aa_unprivileged_userns_restricted; +extern int aa_unprivileged_userns_restricted_force; +extern int aa_unprivileged_userns_restricted_complain; extern int aa_unprivileged_unconfined_restricted; +extern int aa_unprivileged_uring_restricted; extern const char *const aa_profile_mode_names[]; #define APPARMOR_MODE_NAMES_MAX_INDEX 4 @@ -59,6 +63,11 @@ extern const char *const aa_profile_mode_names[]; #define on_list_rcu(X) (!list_empty(X) && (X)->prev != LIST_POISON2) +/* flags in the dfa accept2 table */ +enum dfa_accept_flags { + ACCEPT_FLAG_OWNER = 1, +}; + /* * FIXME: currently need a clean way to replace and remove profiles as a * set. It should be done at the namespace level. @@ -124,6 +133,7 @@ static inline void aa_put_pdb(struct aa_policydb *pdb) kref_put(&pdb->count, aa_pdb_free_kref); } +/* lookup perm that doesn't have and object conditional */ static inline struct aa_perms *aa_lookup_perms(struct aa_policydb *policy, aa_state_t state) { @@ -135,7 +145,6 @@ static inline struct aa_perms *aa_lookup_perms(struct aa_policydb *policy, return &(policy->perms[index]); } - /* struct aa_data - generic data structure * key: name for retrieving this data * size: size of data in bytes @@ -175,6 +184,10 @@ struct aa_ruleset { struct aa_secmark *secmark; }; +void aa_free_ruleset(struct aa_ruleset *rules); +struct aa_ruleset *aa_new_ruleset(gfp_t gfp); +struct aa_ruleset *aa_clone_ruleset(struct aa_ruleset *rules); + /* struct aa_attachment - data and rules for a profiles attachment * @list: * @xmatch_str: human readable attachment string @@ -204,6 +217,7 @@ struct aa_attachment { * @disconnected: what to prepend if attach_disconnected is specified * @attach: attachment rules for the profile * @rules: rules to be enforced + * @net_compat: v2 compat network controls for the profile * * @dents: dentries for the profiles file entries in apparmorfs * @dirname: name of the profile dir in apparmorfs @@ -231,10 +245,14 @@ struct aa_profile { enum audit_mode audit; long mode; u32 path_flags; + int signal; const char *disconnected; struct aa_attachment attach; struct list_head rules; + struct aa_net_compat *net_compat; + + struct aa_audit_cache learning_cache; struct aa_loaddata *rawdata; unsigned char *hash; @@ -304,8 +322,11 @@ static inline aa_state_t RULE_MEDIATES_AF(struct aa_ruleset *rules, u16 AF) aa_state_t state = RULE_MEDIATES(rules, AA_CLASS_NET); __be16 be_af = cpu_to_be16(AF); - if (!state) - return DFA_NOMATCH; + if (!state) { + state = RULE_MEDIATES(rules, AA_CLASS_NET_COMPAT); + if (!state) + return DFA_NOMATCH; + } return aa_dfa_match_len(rules->policy->dfa, state, (char *) &be_af, 2); } @@ -319,6 +340,19 @@ static inline aa_state_t ANY_RULE_MEDIATES(struct list_head *head, return RULE_MEDIATES(rule, class); } +void aa_compute_profile_mediates(struct aa_profile *profile); +static inline bool profile_mediates(struct aa_profile *profile, + unsigned char class) +{ + return label_mediates(&profile->label, class); +} + +static inline bool profile_mediates_safe(struct aa_profile *profile, + unsigned char class) +{ + return label_mediates_safe(&profile->label, class); +} + /** * aa_get_profile - increment refcount on profile @p * @p: profile (MAYBE NULL) diff --git a/security/apparmor/include/policy_ns.h b/security/apparmor/include/policy_ns.h index d646070fd966b..733046c132cab 100644 --- a/security/apparmor/include/policy_ns.h +++ b/security/apparmor/include/policy_ns.h @@ -12,6 +12,7 @@ #define __AA_NAMESPACE_H #include +#include #include "apparmor.h" #include "apparmorfs.h" @@ -42,6 +43,12 @@ struct aa_ns_acct { * @uniq_null: uniq value used for null learning profiles * @uniq_id: a unique id count for the profiles in the namespace * @level: level of ns within the tree hierarchy + * @revision: policy revision for this ns + * @wait: waitq for tasks waiting on revision changes + * @listener_lock: lock for listeners + * @listeners: notification listeners' proxies list + * @labels: all the labels associated with this ns + * @rawdata_list: raw policy data for policy * @dents: dentries for the namespaces file entries in apparmorfs * * An aa_ns defines the set profiles that are searched to determine which @@ -65,9 +72,13 @@ struct aa_ns { atomic_t uniq_null; long uniq_id; int level; + long revision; wait_queue_head_t wait; + spinlock_t listener_lock; + struct list_head listeners; + struct aa_labelset labels; struct list_head rawdata_list; diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h index a6f4611ee50cf..1cb72267ea0f1 100644 --- a/security/apparmor/include/policy_unpack.h +++ b/security/apparmor/include/policy_unpack.h @@ -31,6 +31,7 @@ struct aa_load_ent *aa_load_ent_alloc(void); #define PACKED_FLAG_HAT 1 #define PACKED_FLAG_DEBUG1 2 #define PACKED_FLAG_DEBUG2 4 +#define PACKED_FLAG_INTERRUPTIBLE 8 #define PACKED_MODE_ENFORCE 0 #define PACKED_MODE_COMPLAIN 1 diff --git a/security/apparmor/include/secid.h b/security/apparmor/include/secid.h index a912a5d5d04f5..568820a11efcd 100644 --- a/security/apparmor/include/secid.h +++ b/security/apparmor/include/secid.h @@ -25,9 +25,10 @@ struct aa_label; extern int apparmor_display_secid_mode; struct aa_label *aa_secid_to_label(u32 secid); -int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); +int apparmor_secid_to_secctx(u32 secid, struct lsmcontext *cp); +int apparmor_lsmblob_to_secctx(struct lsmblob *blob, struct lsmcontext *cp); int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid); -void apparmor_release_secctx(char *secdata, u32 seclen); +void apparmor_release_secctx(struct lsmcontext *cp); int aa_alloc_secid(struct aa_label *label, gfp_t gfp); diff --git a/security/apparmor/include/sig_names.h b/security/apparmor/include/sig_names.h index cbf7a997ed841..c772668cdc629 100644 --- a/security/apparmor/include/sig_names.h +++ b/security/apparmor/include/sig_names.h @@ -1,9 +1,5 @@ #include - -#define SIGUNKNOWN 0 -#define MAXMAPPED_SIG 35 -#define MAXMAPPED_SIGNAME (MAXMAPPED_SIG + 1) -#define SIGRT_BASE 128 +#include "signal.h" /* provide a mapping of arch signal to internal signal # for mediation * those that are always an alias SIGCLD for SIGCLHD and SIGPOLL for SIGIO diff --git a/security/apparmor/include/signal.h b/security/apparmor/include/signal.h new file mode 100644 index 0000000000000..729763fa7ce6f --- /dev/null +++ b/security/apparmor/include/signal.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * AppArmor security module + * + * This file contains AppArmor ipc mediation function definitions. + * + * Copyright 2023 Canonical Ltd. + */ + +#ifndef __AA_SIGNAL_H +#define __AA_SIGNAL_H + +#define SIGUNKNOWN 0 +#define MAXMAPPED_SIG 35 + +#define MAXMAPPED_SIGNAME (MAXMAPPED_SIG + 1) +#define SIGRT_BASE 128 + +#endif /* __AA_SIGNAL_H */ diff --git a/security/apparmor/include/task.h b/security/apparmor/include/task.h index b1aaaf60fa8b8..ff8bed8f60b27 100644 --- a/security/apparmor/include/task.h +++ b/security/apparmor/include/task.h @@ -99,7 +99,8 @@ int aa_may_ptrace(const struct cred *tracer_cred, struct aa_label *tracer, #define AA_USERNS_CREATE 8 -int aa_profile_ns_perm(struct aa_profile *profile, - struct apparmor_audit_data *ad, u32 request); +struct aa_label *aa_profile_ns_perm(struct aa_profile *profile, + struct apparmor_audit_data *ad, + u32 request); #endif /* __AA_TASK_H */ diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c index 0cdf4340b02d5..b7ea40d3de330 100644 --- a/security/apparmor/ipc.c +++ b/security/apparmor/ipc.c @@ -9,10 +9,13 @@ */ #include +#include +#include #include "include/audit.h" #include "include/capability.h" #include "include/cred.h" +#include "include/path.h" #include "include/policy.h" #include "include/ipc.h" #include "include/sig_names.h" @@ -85,16 +88,16 @@ static int profile_signal_perm(const struct cred *cred, struct aa_perms perms; aa_state_t state; - if (profile_unconfined(profile) || - !ANY_RULE_MEDIATES(&profile->rules, AA_CLASS_SIGNAL)) + if (!profile_mediates(profile, AA_CLASS_SIGNAL)) return 0; ad->subj_cred = cred; ad->peer = peer; /* TODO: secondary cache check */ - state = aa_dfa_next(rules->policy->dfa, - rules->policy->start[AA_CLASS_SIGNAL], - ad->signal); + state = RULE_MEDIATES(rules, AA_CLASS_SIGNAL); + if (!state) + return 0; + state = aa_dfa_next(rules->policy->dfa, state, ad->signal); aa_label_match(profile, rules, peer, state, false, request, &perms); aa_apply_modes_to_perms(profile, &perms); return aa_check_perms(profile, &perms, request, ad, audit_signal_cb); @@ -115,3 +118,108 @@ int aa_may_signal(const struct cred *subj_cred, struct aa_label *sender, profile_signal_perm(target_cred, profile, sender, MAY_READ, &ad)); } + + +static void audit_mqueue_cb(struct audit_buffer *ab, void *va) +{ + struct apparmor_audit_data *ad = aad_of_va(va); + + aa_audit_perms(ab, ad, NULL, 0, NULL, AA_AUDIT_POSIX_MQUEUE_MASK); + + /* move class into generic audit framse work */ + audit_log_format(ab, "class=\"posix_mqueue\""); + if (ad->request & AA_AUDIT_FILE_MASK) { + audit_log_format(ab, " fsuid=%u", + from_kuid(&init_user_ns, ad->subj_cred->fsuid)); + audit_log_format(ab, " ouid=%u", + from_kuid(&init_user_ns, ad->mq.ouid)); + } + if (ad->peer) { + audit_log_format(ab, " olabel="); + aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, + FLAGS_NONE, GFP_ATOMIC); + } +} + +int aa_profile_mqueue_perm(struct aa_profile *profile, const struct path *path, + u32 request, char *buffer, + struct apparmor_audit_data *ad) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_perms perms = { }; + unsigned int state; + char *name; + + if (profile_unconfined(profile) || + !RULE_MEDIATES(rules, AA_CLASS_POSIX_MQUEUE)) + return 0; + + ad->subj_label = &profile->label; + + name = dentry_path_raw(path->dentry, buffer, aa_g_path_max); + if (IS_ERR(name)) + return PTR_ERR(name); + if (path->mnt != current->nsproxy->ipc_ns->mq_mnt) { + /* TODO: disconnected path detection */ + pr_warn("apparmor mqueue disconnected TODO\n"); + } + + ad->name = name; + + state = aa_dfa_match(rules->policy->dfa, + rules->policy->start[AA_CLASS_POSIX_MQUEUE], + name); + perms = *aa_lookup_perms(rules->policy, state); + aa_apply_modes_to_perms(profile, &perms); + if (!denied_perms(&perms, request)) { + /* early bailout sufficient perms no need to do further + * checks + */ + return aa_check_perms(profile, &perms, request, ad, + audit_mqueue_cb); + } + /* continue check to see if we have label perms */ + //aa_label_match(profile, peer??, state false, request, &perms); + //aa_apply_modes_to_perms(profile, &perms); + + // this will just cause failure without above label check + return aa_check_perms(profile, &perms, request, ad, audit_mqueue_cb); +} + +/* mqueue - no label caching test */ +int aa_mqueue_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, + const struct path *path, u32 request) +{ + struct aa_profile *profile; + char *buffer; + int error; + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_POSIX_MQUEUE, op); + + // do we need delegate deleted with mqueues? probably + //flags |= PATH_DELEGATE_DELETED; + + /* sadly due to rcu walk hairiness, we use dentry_path_raw instead + * of just accessing the name directly, which means we need to + * do the whole buffer allocation mess + */ + buffer = aa_get_buffer(false); + if (!buffer) + return -ENOMEM; + + /* audit fields that won't change during iteration */ + ad.subj_cred = subj_cred; + ad.request = request; + ad.peer = NULL; + ad.mq.ouid = d_backing_inode(path->dentry) ? + d_backing_inode(path->dentry)->i_uid : + subj_cred->fsuid; + + error = fn_for_each_confined(label, profile, + aa_profile_mqueue_perm(profile, path, request, + buffer, &ad)); + aa_put_buffer(buffer); + + return error; +} diff --git a/security/apparmor/label.c b/security/apparmor/label.c index c71e4615dd460..25511d42cce84 100644 --- a/security/apparmor/label.c +++ b/security/apparmor/label.c @@ -198,21 +198,25 @@ static bool vec_is_stale(struct aa_profile **vec, int n) return false; } -static long accum_vec_flags(struct aa_profile **vec, int n) +static void accum_label_info(struct aa_label *new) { long u = FLAG_UNCONFINED; int i; - AA_BUG(!vec); + AA_BUG(!new || !new->vec); - for (i = 0; i < n; i++) { - u |= vec[i]->label.flags & (FLAG_DEBUG1 | FLAG_DEBUG2 | - FLAG_STALE); - if (!(u & vec[i]->label.flags & FLAG_UNCONFINED)) + /* size == 1 is a profile and flags must be set as part of creation */ + if (new->size == 1) + return; + + for (i = 0; i < new->size; i++) { + u |= new->vec[i]->label.flags & (FLAG_DEBUG1 | FLAG_DEBUG2 | + FLAG_STALE); + if (!(u & new->vec[i]->label.flags & FLAG_UNCONFINED)) u &= ~FLAG_UNCONFINED; + new->mediates |= new->vec[i]->label.mediates; } - - return u; + new->flags |= u; } static int sort_cmp(const void *a, const void *b) @@ -431,7 +435,7 @@ struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp) /* + 1 for null terminator entry on vec */ new = kzalloc(struct_size(new, vec, size + 1), gfp); - AA_DEBUG("%s (%p)\n", __func__, new); + AA_DEBUG(DEBUG_LABEL, "%s (%p)\n", __func__, new); if (!new) goto fail; @@ -457,7 +461,7 @@ struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp) /** - * label_cmp - label comparison for set ordering + * aa_label_cmp - label comparison for set ordering * @a: label to compare (NOT NULL) * @b: label to compare (NOT NULL) * @@ -465,7 +469,7 @@ struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp) * ==0 if a == b * >0 if a > b */ -static int label_cmp(struct aa_label *a, struct aa_label *b) +int aa_label_cmp(struct aa_label *a, struct aa_label *b) { AA_BUG(!b); @@ -645,6 +649,7 @@ static bool __label_replace(struct aa_label *old, struct aa_label *new) rb_replace_node(&old->node, &new->node, &ls->root); old->flags &= ~FLAG_IN_TREE; new->flags |= FLAG_IN_TREE; + accum_label_info(new); return true; } @@ -679,7 +684,7 @@ static struct aa_label *__label_insert(struct aa_labelset *ls, new = &ls->root.rb_node; while (*new) { struct aa_label *this = rb_entry(*new, struct aa_label, node); - int result = label_cmp(label, this); + int result = aa_label_cmp(label, this); parent = *new; if (result == 0) { @@ -705,6 +710,7 @@ static struct aa_label *__label_insert(struct aa_labelset *ls, rb_link_node(&label->node, parent, new); rb_insert_color(&label->node, &ls->root); label->flags |= FLAG_IN_TREE; + accum_label_info(label); return aa_get_label(label); } @@ -879,7 +885,6 @@ static struct aa_label *vec_create_and_insert_label(struct aa_profile **vec, for (i = 0; i < len; i++) new->vec[i] = aa_get_profile(vec[i]); - write_lock_irqsave(&ls->lock, flags); label = __label_insert(ls, new, false); write_unlock_irqrestore(&ls->lock, flags); @@ -1102,7 +1107,6 @@ static struct aa_label *label_merge_insert(struct aa_label *new, else if (k == b->size) return aa_get_label(b); } - new->flags |= accum_vec_flags(new->vec, new->size); ls = labels_set(new); write_lock_irqsave(&ls->lock, flags); label = __label_insert(labels_set(new), new, false); @@ -1634,7 +1638,7 @@ int aa_label_snxprint(char *str, size_t size, struct aa_ns *ns, AA_BUG(!str && size != 0); AA_BUG(!label); - if (AA_DEBUG_LABEL && (flags & FLAG_ABS_ROOT)) { + if (DEBUG_ABS_ROOT && (flags & FLAG_ABS_ROOT)) { ns = root_ns; len = snprintf(str, size, "_"); update_for_len(total, len, size, str); @@ -1748,7 +1752,7 @@ void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns, display_mode(ns, label, flags)) { len = aa_label_asxprint(&name, ns, label, flags, gfp); if (len < 0) { - AA_DEBUG("label print error"); + AA_DEBUG(DEBUG_LABEL, "label print error"); return; } str = name; @@ -1776,7 +1780,7 @@ void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns, len = aa_label_asxprint(&str, ns, label, flags, gfp); if (len < 0) { - AA_DEBUG("label print error"); + AA_DEBUG(DEBUG_LABEL, "label print error"); return; } seq_puts(f, str); @@ -1799,7 +1803,7 @@ void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags, len = aa_label_asxprint(&str, ns, label, flags, gfp); if (len < 0) { - AA_DEBUG("label print error"); + AA_DEBUG(DEBUG_LABEL, "label print error"); return; } pr_info("%s", str); @@ -1898,7 +1902,7 @@ struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str, AA_BUG(!str); str = skipn_spaces(str, n); - if (str == NULL || (AA_DEBUG_LABEL && *str == '_' && + if (str == NULL || (DEBUG_ABS_ROOT && *str == '_' && base != &root_ns->unconfined->label)) return ERR_PTR(-EINVAL); @@ -2089,6 +2093,7 @@ static struct aa_label *__label_update(struct aa_label *label) AA_BUG(tmp == label); goto remove; } + if (labels_set(label) != labels_set(new)) { write_unlock_irqrestore(&ls->lock, flags); tmp = aa_label_insert(labels_set(new), new); diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index cd569fbbfe36d..e69db64993210 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -25,6 +25,98 @@ struct aa_perms allperms = { .allow = ALL_PERMS_MASK, .quiet = ALL_PERMS_MASK, .hide = ALL_PERMS_MASK }; +struct val_table_ent { + const char *str; + int value; +}; + +struct val_table_ent debug_values_table[] = { + { "N", DEBUG_NONE }, + { "none", DEBUG_NONE }, + { "n", DEBUG_NONE }, + { "0", DEBUG_NONE }, + { "all", DEBUG_ALL }, + { "Y", DEBUG_ALL }, + { "y", DEBUG_ALL }, + { "1", DEBUG_ALL }, + { "abs_root", DEBUG_LABEL_ABS_ROOT }, + { "label", DEBUG_LABEL }, + { "domain", DEBUG_DOMAIN }, + { "policy", DEBUG_POLICY }, + { "interface", DEBUG_INTERFACE }, + { "upcall", DEBUG_UPCALL }, + { NULL, 0 } +}; + +static struct val_table_ent *val_table_find_ent(struct val_table_ent *table, + const char *name, size_t len) +{ + struct val_table_ent *entry; + + for (entry = table; entry->str != NULL; entry++) { + if (strncmp(entry->str, name, len) == 0 && + strlen(entry->str) == len) + return entry; + } + return NULL; +} + +int aa_parse_debug_params(const char *str) +{ + struct val_table_ent *ent; + const char *next; + int val = 0; + + do { + size_t n = strcspn(str, "\r\n,"); + + next = str + n; + ent = val_table_find_ent(debug_values_table, str, next - str); + if (ent) + val |= ent->value; + else + AA_DEBUG(DEBUG_INTERFACE, "unknown debug type '%.*s'", + (int)(next - str), str); + str = next + 1; + } while (*next != 0); + return val; +} + +/** + * aa_mask_to_str - convert a perm mask to its short string + * @str: character buffer to store string in (at least 10 characters) + * @str_size: size of the @str buffer + * @chrs: NUL-terminated character buffer of permission characters + * @mask: permission mask to convert + */ +static int val_mask_to_str(char *str, size_t size, + const struct val_table_ent *table, u32 mask) +{ + const struct val_table_ent *ent; + int total = 0; + + for (ent = table; ent->str; ent++) { + if (ent->value && (ent->value & mask) == ent->value) { + int len = scnprintf(str, size, "%s%s", total ? "," : "", + ent->str); + size -= len; + str += len; + total += len; + mask &= ~ent->value; + } + } + + return total; +} + +int aa_print_debug_params(char *buffer) +{ + if (!aa_g_debug) + return sprintf(buffer, "N"); + return val_mask_to_str(buffer, PAGE_SIZE, debug_values_table, + aa_g_debug); +} + /** * aa_free_str_table - free entries str table * @t: the string table to free (MAYBE NULL) @@ -172,7 +264,7 @@ void aa_str_kref(struct kref *kref) const char aa_file_perm_chrs[] = "xwracd km l "; -const char *aa_file_perm_names[] = { +const char *aa_base_perm_names[] = { "exec", "write", "read", @@ -262,6 +354,10 @@ void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, { char str[33]; + if (!chrs) + chrs = aa_file_perm_chrs; + if (!names) + names = aa_base_perm_names; audit_log_format(ab, "\""); if ((mask & chrsmask) && chrs) { aa_perm_mask_to_str(str, sizeof(str), chrs, mask & chrsmask); @@ -275,6 +371,22 @@ void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, audit_log_format(ab, "\""); } +void aa_audit_perms(struct audit_buffer *ab, struct apparmor_audit_data *ad, + const char *chrs, u32 chrsmask, const char * const *names, + u32 namesmask) +{ + if (ad->request) { + audit_log_format(ab, " requested="); + aa_audit_perm_mask(ab, ad->request, chrs, chrsmask, + names, namesmask); + } + if (ad->denied) { + audit_log_format(ab, " denied="); + aa_audit_perm_mask(ab, ad->denied, chrs, chrsmask, + names, namesmask); + } +} + /** * aa_audit_perms_cb - generic callback fn for auditing perms * @ab: audit buffer (NOT NULL) @@ -282,21 +394,10 @@ void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, */ static void aa_audit_perms_cb(struct audit_buffer *ab, void *va) { - struct common_audit_data *sa = va; - struct apparmor_audit_data *ad = aad(sa); + struct apparmor_audit_data *ad = aad_of_va(va); - if (ad->request) { - audit_log_format(ab, " requested_mask="); - aa_audit_perm_mask(ab, ad->request, aa_file_perm_chrs, - PERMS_CHRS_MASK, aa_file_perm_names, - PERMS_NAMES_MASK); - } - if (ad->denied) { - audit_log_format(ab, "denied_mask="); - aa_audit_perm_mask(ab, ad->denied, aa_file_perm_chrs, - PERMS_CHRS_MASK, aa_file_perm_names, - PERMS_NAMES_MASK); - } + aa_audit_perms(ab, ad, aa_file_perm_chrs, PERMS_CHRS_MASK, + aa_base_perm_names, PERMS_NAMES_MASK); audit_log_format(ab, " peer="); aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAGS_NONE, GFP_ATOMIC); @@ -390,7 +491,7 @@ int aa_check_perms(struct aa_profile *profile, struct aa_perms *perms, void (*cb)(struct audit_buffer *, void *)) { int type, error; - u32 denied = request & (~perms->allow | perms->deny); + u32 denied = denied_perms(perms, request); if (likely(!denied)) { /* mask off perms that are not being force audited */ @@ -419,6 +520,7 @@ int aa_check_perms(struct aa_profile *profile, struct aa_perms *perms, } if (ad) { + // do_notification() ad->subj_label = &profile->label; ad->request = request; ad->denied = denied; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 9a3dcaafb5b1e..314c49d6591d9 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -18,6 +18,8 @@ #include #include #include +#include +#include #include #include #include @@ -26,12 +28,15 @@ #include #include +#include "include/af_unix.h" +#include "include/af_inet.h" #include "include/apparmor.h" #include "include/apparmorfs.h" #include "include/audit.h" #include "include/capability.h" #include "include/cred.h" #include "include/file.h" +#include "include/inode.h" #include "include/ipc.h" #include "include/net.h" #include "include/path.h" @@ -64,6 +69,13 @@ static LIST_HEAD(aa_global_buffers); static DEFINE_SPINLOCK(aa_buffers_lock); static DEFINE_PER_CPU(struct aa_local_cache, aa_local_buffers); +struct kmem_cache *aa_audit_slab; + +static bool is_mqueue_dentry(struct dentry *dentry) +{ + return dentry && is_mqueue_inode(d_backing_inode(dentry)); +} + /* * LSM hook functions */ @@ -177,14 +189,13 @@ static int apparmor_capget(const struct task_struct *target, kernel_cap_t *effec label_for_each_confined(i, label, profile) { struct aa_ruleset *rules; - if (COMPLAIN_MODE(profile)) - continue; + kernel_cap_t allowed; + rules = list_first_entry(&profile->rules, typeof(*rules), list); - *effective = cap_intersect(*effective, - rules->caps.allow); - *permitted = cap_intersect(*permitted, - rules->caps.allow); + allowed = aa_profile_capget(profile); + *effective = cap_intersect(*effective, allowed); + *permitted = cap_intersect(*permitted, allowed); } } rcu_read_unlock(); @@ -223,7 +234,7 @@ static int common_perm(const char *op, const struct path *path, u32 mask, int error = 0; label = __begin_current_label_crit_section(); - if (!unconfined(label)) + if (label_mediates(label, AA_CLASS_FILE)) error = aa_path_perm(op, current_cred(), label, path, 0, mask, cond); __end_current_label_crit_section(label); @@ -370,7 +381,7 @@ static int apparmor_path_link(struct dentry *old_dentry, const struct path *new_ return 0; label = begin_current_label_crit_section(); - if (!unconfined(label)) + if (label_mediates(label, AA_CLASS_FILE)) error = aa_path_link(current_cred(), label, old_dentry, new_dir, new_dentry); end_current_label_crit_section(label); @@ -391,7 +402,7 @@ static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_d return 0; label = begin_current_label_crit_section(); - if (!unconfined(label)) { + if (label_mediates(label, AA_CLASS_FILE)) { struct mnt_idmap *idmap = mnt_idmap(old_dir->mnt); vfsuid_t vfsuid; struct path old_path = { .mnt = old_dir->mnt, @@ -451,11 +462,168 @@ static int apparmor_path_chown(const struct path *path, kuid_t uid, kgid_t gid) return common_perm_cond(OP_CHOWN, path, AA_MAY_CHOWN); } +static int common_mqueue_path_perm(const char *op, u32 request, + const struct path *path) +{ + struct aa_label *label; + int error = 0; + + label = begin_current_label_crit_section(); + if (!unconfined(label)) + error = aa_mqueue_perm(OP_UNLINK, current_cred(), label, path, + request); + + end_current_label_crit_section(label); + + return error; +} + static int apparmor_inode_getattr(const struct path *path) { + if (is_mqueue_dentry(path->dentry)) + /* TODO: fn() for d_parent */ + return common_mqueue_path_perm(OP_UNLINK, AA_MAY_GETATTR, path); + return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR); } +/* inode security operations */ + +/* alloced by infrastructure */ +static int apparmor_inode_alloc_security(struct inode *inode) +{ + struct aa_inode_sec *isec = apparmor_inode(inode); + + spin_lock_init(&isec->lock); + isec->inode = inode; + isec->label = NULL; + isec->sclass = 0; + isec->initialized = false; + + return 0; +} + +/* freed by infrastructure */ +static void apparmor_inode_free_security(struct inode *inode) +{ + struct aa_inode_sec *isec = apparmor_inode(inode); + + if (!isec) + return; + + aa_put_label(isec->label); +} + + +/* this is broken, in that we must make it work for ALL xattr fs + * or it will bail early, so this does not work with LSM stacking + */ +static int apparmor_inode_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr, + struct xattr *xattrs, int *xattr_count) +{ + struct aa_inode_sec *isec = apparmor_inode(inode); + + if (is_mqueue_inode(dir)) { + /* only initialize based on implied label atm */ + isec->label = aa_get_current_label(); + isec->sclass = AA_CLASS_POSIX_MQUEUE; + isec->initialized = true; + } + + /* we aren't setting xattrs yet so pretend it isn't supported, + * note bug in LSM means other LSMs won't get to init inode either + */ + return -EOPNOTSUPP; +} + +static int inode_init_with_dentry(struct inode *inode, struct dentry *dentry) +{ + struct aa_inode_sec *isec = apparmor_inode(inode); + + if (isec->initialized) + return 0; + spin_lock(&isec->lock); + /* recheck under lock */ + if (isec->initialized) + goto unlock; + + if (is_mqueue_sb(inode->i_sb)) { + /* only initialize based on implied label atm */ + isec->label = aa_get_current_label(); + isec->sclass = AA_CLASS_POSIX_MQUEUE; + isec->initialized = true; + } + +unlock: + spin_unlock(&isec->lock); + + return 0; +} + +static void apparmor_d_instantiate(struct dentry *dentry, struct inode *inode) +{ + if (inode) + inode_init_with_dentry(inode, dentry); +} + +static int apparmor_inode_create(struct inode *dir, struct dentry *dentry, + umode_t mode) +{ + struct aa_label *label; + int error = 0; + + label = begin_current_label_crit_section(); + if (!unconfined(label)) { + struct path path = { + .dentry = dentry, + .mnt = current->nsproxy->ipc_ns->mq_mnt, + }; + if (is_mqueue_inode(dir)) + error = aa_mqueue_perm(OP_CREATE, current_cred(), + label, &path, AA_MAY_CREATE); + } + end_current_label_crit_section(label); + + return error; +} + +static int common_mqueue_perm(const char *op, u32 request, struct inode *dir, struct dentry *dentry) +{ + /* can't directly determine ipc ns, but know for mqueues dir is mnt_root */ + bool isdir = d_inode(current->nsproxy->ipc_ns->mq_mnt->mnt_root) == dir; + struct path path = { + .dentry = dentry, + .mnt = isdir ? current->nsproxy->ipc_ns->mq_mnt : NULL, + }; + + if (dir != d_inode(current->nsproxy->ipc_ns->mq_mnt->mnt_root)) + pr_warn("apparmor: unlink dir != mnt_root - disconnected"); + + return common_mqueue_path_perm(op, request, &path); +} + +static int apparmor_inode_unlink(struct inode *dir, struct dentry *dentry) +{ + int error = 0; + + if (is_mqueue_dentry(dentry)) + error = common_mqueue_perm(OP_UNLINK, AA_MAY_DELETE, dir, dentry); + + return error; +} + +static int apparmor_inode_setattr(struct dentry *dentry, struct iattr *iattr) +{ + /* TODO: extend to support iattr as a parameter */ + if (is_mqueue_dentry(dentry)) + /* TODO: fn() for d_parent */ + return common_mqueue_perm(OP_UNLINK, AA_MAY_SETATTR, + d_backing_inode(dentry->d_parent), dentry); + + return 0; +} + static int apparmor_file_open(struct file *file) { struct aa_file_ctx *fctx = file_ctx(file); @@ -478,7 +646,7 @@ static int apparmor_file_open(struct file *file) } label = aa_get_newest_cred_label(file->f_cred); - if (!unconfined(label)) { + if (label_mediates(label, AA_CLASS_FILE)) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct inode *inode = file_inode(file); vfsuid_t vfsuid; @@ -488,11 +656,17 @@ static int apparmor_file_open(struct file *file) vfsuid = i_uid_into_vfsuid(idmap, inode); cond.uid = vfsuid_into_kuid(vfsuid); - error = aa_path_perm(OP_OPEN, file->f_cred, - label, &file->f_path, 0, - aa_map_file_to_perms(file), &cond); + if (is_mqueue_inode(file_inode(file))) + error = aa_mqueue_perm(OP_OPEN, file->f_cred, + label, &file->f_path, + aa_map_file_to_perms(file)); + else + error = aa_path_perm(OP_OPEN, file->f_cred, + label, &file->f_path, 0, + aa_map_file_to_perms(file), &cond); /* todo cache full allowed permissions set and state */ - fctx->allow = aa_map_file_to_perms(file); + if (!error) + fctx->allow = aa_map_file_to_perms(file); } aa_put_label(label); @@ -504,6 +678,7 @@ static int apparmor_file_alloc_security(struct file *file) struct aa_file_ctx *ctx = file_ctx(file); struct aa_label *label = begin_current_label_crit_section(); + /* no inode available here */ spin_lock_init(&ctx->lock); rcu_assign_pointer(ctx->label, aa_get_label(label)); end_current_label_crit_section(label); @@ -628,13 +803,41 @@ static int profile_uring(struct aa_profile *profile, u32 request, { unsigned int state; struct aa_ruleset *rules; - int error = 0; AA_BUG(!profile); rules = list_first_entry(&profile->rules, typeof(*rules), list); + + /* TODO: rework unconfined profile/dfa to mediate user ns, then + * we can drop the unconfined test + */ state = RULE_MEDIATES(rules, AA_CLASS_IO_URING); - if (state) { + if (!state) { + /* TODO: this gets replaced when the default unconfined + * profile dfa gets updated to handle this + */ + if (profile_unconfined(profile) && + profile == profiles_ns(profile)->unconfined) { + if (!aa_unprivileged_uring_restricted || + ns_capable_noaudit(current_user_ns(), cap)) + /* unconfined early bail out */ + return 0; + /* unconfined unprivileged user */ + /* don't just return: allow complain mode to override */ + } else { + /* Fallback to capability check if profile doesn't + * support io_uring rules. Note: special unconfined + * profiles as well. + */ + return aa_capable(current_cred(), &profile->label, + cap, CAP_OPT_NONE); + } + /* continue to mediation - !state means non-accepting + * but can be overidden by complain + */ + } + /* block so perms is not initialized unless mediating */ + do { struct aa_perms perms = { }; if (new) { @@ -644,11 +847,11 @@ static int profile_uring(struct aa_profile *profile, u32 request, perms = *aa_lookup_perms(rules->policy, state); } aa_apply_modes_to_perms(profile, &perms); - error = aa_check_perms(profile, &perms, request, ad, + return aa_check_perms(profile, &perms, request, ad, audit_uring_cb); - } + } while (0); - return error; + return 0; } /** @@ -713,7 +916,7 @@ static int apparmor_sb_mount(const char *dev_name, const struct path *path, flags &= ~AA_MS_IGNORE_MASK; label = __begin_current_label_crit_section(); - if (!unconfined(label)) { + if (label_mediates(label, AA_CLASS_MOUNT)) { if (flags & MS_REMOUNT) error = aa_remount(current_cred(), label, path, flags, data); @@ -743,7 +946,7 @@ static int apparmor_move_mount(const struct path *from_path, int error = 0; label = __begin_current_label_crit_section(); - if (!unconfined(label)) + if (label_mediates(label, AA_CLASS_MOUNT)) error = aa_move_mount(current_cred(), label, from_path, to_path); __end_current_label_crit_section(label); @@ -757,7 +960,7 @@ static int apparmor_sb_umount(struct vfsmount *mnt, int flags) int error = 0; label = __begin_current_label_crit_section(); - if (!unconfined(label)) + if (label_mediates(label, AA_CLASS_MOUNT)) error = aa_umount(current_cred(), label, mnt, flags); __end_current_label_crit_section(label); @@ -771,7 +974,7 @@ static int apparmor_sb_pivotroot(const struct path *old_path, int error = 0; label = aa_get_current_label(); - if (!unconfined(label)) + if (label_mediates(label, AA_CLASS_MOUNT)) error = aa_pivotroot(current_cred(), label, old_path, new_path); aa_put_label(label); @@ -779,7 +982,7 @@ static int apparmor_sb_pivotroot(const struct path *old_path, } static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx, - size_t *size, u32 flags) + u32 *size, u32 flags) { int error = -ENOENT; struct aa_task_ctx *ctx = task_ctx(current); @@ -924,7 +1127,7 @@ static int do_setattr(u64 attr, void *value, size_t size) } static int apparmor_setselfattr(unsigned int attr, struct lsm_ctx *ctx, - size_t size, u32 flags) + u32 size, u32 flags) { int rc; @@ -981,17 +1184,20 @@ static void apparmor_bprm_committed_creds(const struct linux_binprm *bprm) return; } -static void apparmor_current_getsecid_subj(u32 *secid) +static void apparmor_current_getlsmblob_subj(struct lsmblob *blob) { struct aa_label *label = __begin_current_label_crit_section(); - *secid = label->secid; + + blob->apparmor.label = label; __end_current_label_crit_section(label); } -static void apparmor_task_getsecid_obj(struct task_struct *p, u32 *secid) +static void apparmor_task_getlsmblob_obj(struct task_struct *p, + struct lsmblob *blob) { struct aa_label *label = aa_get_task_label(p); - *secid = label->secid; + + blob->apparmor.label = label; aa_put_label(label); } @@ -1036,48 +1242,48 @@ static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo return error; } -static int apparmor_userns_create(const struct cred *cred) +static int apparmor_userns_create(const struct cred *new_cred) { struct aa_label *label; struct aa_profile *profile; int error = 0; - DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_NS, - OP_USERNS_CREATE); - - ad.subj_cred = current_cred(); label = begin_current_label_crit_section(); - if (!unconfined(label)) { - error = fn_for_each(label, profile, - aa_profile_ns_perm(profile, &ad, - AA_USERNS_CREATE)); + /* remove unprivileged_userns_restricted check when unconfined is updated */ + if (aa_unprivileged_userns_restricted || + label_mediates(label, AA_CLASS_NS)) { + struct aa_label *new; + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_NS, + OP_USERNS_CREATE); + ad.subj_cred = current_cred(); + + new = fn_label_build(label, profile, GFP_KERNEL, + aa_profile_ns_perm(profile, &ad, + AA_USERNS_CREATE)); + if (IS_ERR(new)) { + error = PTR_ERR(new); + } else if (new && cred_label(new_cred) != new) { + aa_put_label(cred_label(new_cred)); + set_cred_label(new_cred, new); + } else { + aa_put_label(new); + } } end_current_label_crit_section(label); return error; } -static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags) -{ - struct aa_sk_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), flags); - if (!ctx) - return -ENOMEM; - - sk->sk_security = ctx; - - return 0; -} - +/** + * apparmor_sk_free_security - free the sk_security field + */ static void apparmor_sk_free_security(struct sock *sk) { struct aa_sk_ctx *ctx = aa_sock(sk); - sk->sk_security = NULL; aa_put_label(ctx->label); aa_put_label(ctx->peer); - kfree(ctx); + path_put(&ctx->path); } /** @@ -1098,6 +1304,102 @@ static void apparmor_sk_clone_security(const struct sock *sk, if (new->peer) aa_put_label(new->peer); new->peer = aa_get_label(ctx->peer); + new->path = ctx->path; + path_get(&new->path); +} + +static struct path *UNIX_FS_CONN_PATH(struct sock *sk, struct sock *newsk) +{ + if (sk->sk_family == PF_UNIX && UNIX_FS(sk)) + return &unix_sk(sk)->path; + else if (newsk->sk_family == PF_UNIX && UNIX_FS(newsk)) + return &unix_sk(newsk)->path; + return NULL; +} + +/** + * apparmor_unix_stream_connect - check perms before making unix domain conn + * + * peer is locked when this hook is called + */ +static int apparmor_unix_stream_connect(struct sock *sk, struct sock *peer_sk, + struct sock *newsk) +{ + struct aa_sk_ctx *sk_ctx = aa_sock(sk); + struct aa_sk_ctx *peer_ctx = aa_sock(peer_sk); + struct aa_sk_ctx *new_ctx = aa_sock(newsk); + struct aa_label *label; + struct path *path; + int error; + + label = __begin_current_label_crit_section(); + error = aa_unix_peer_perm(current_cred(), label, OP_CONNECT, + (AA_MAY_CONNECT | AA_MAY_SEND | AA_MAY_RECEIVE), + sk, peer_sk, NULL); + if (!UNIX_FS(peer_sk)) { + last_error(error, + aa_unix_peer_perm(current_cred(), + peer_ctx->label, OP_CONNECT, + (AA_MAY_ACCEPT | AA_MAY_SEND | AA_MAY_RECEIVE), + peer_sk, sk, label)); + } + __end_current_label_crit_section(label); + + if (error) + return error; + + /* label newsk if it wasn't labeled in post_create. Normally this + * would be done in sock_graft, but because we are directly looking + * at the peer_sk to obtain peer_labeling for unix socks this + * does not work + */ + if (!new_ctx->label) + new_ctx->label = aa_get_label(peer_ctx->label); + + /* Cross reference the peer labels for SO_PEERSEC */ + if (new_ctx->peer) + aa_put_label(new_ctx->peer); + + if (sk_ctx->peer) + aa_put_label(sk_ctx->peer); + + new_ctx->peer = aa_get_label(sk_ctx->label); + sk_ctx->peer = aa_get_label(peer_ctx->label); + + path = UNIX_FS_CONN_PATH(sk, peer_sk); + if (path) { + new_ctx->path = *path; + sk_ctx->path = *path; + path_get(path); + path_get(path); + } + return 0; +} + +/** + * apparmor_unix_may_send - check perms before conn or sending unix dgrams + * + * other is locked when this hook is called + * + * dgram connect calls may_send, peer setup but path not copied????? + */ +static int apparmor_unix_may_send(struct socket *sock, struct socket *peer) +{ + struct aa_sk_ctx *peer_ctx = aa_sock(peer->sk); + struct aa_label *label; + int error; + + label = __begin_current_label_crit_section(); + error = xcheck(aa_unix_peer_perm(current_cred(), + label, OP_SENDMSG, AA_MAY_SEND, + sock->sk, peer->sk, NULL), + aa_unix_peer_perm(peer->file ? peer->file->f_cred : NULL, + peer_ctx->label, OP_SENDMSG, + AA_MAY_RECEIVE, + peer->sk, sock->sk, label)); + __end_current_label_crit_section(label); + + return error; } static int apparmor_socket_create(int family, int type, int protocol, int kern) @@ -1107,8 +1409,11 @@ static int apparmor_socket_create(int family, int type, int protocol, int kern) AA_BUG(in_interrupt()); + if (kern) + return 0; + label = begin_current_label_crit_section(); - if (!(kern || unconfined(label))) + if (label_mediates(label, AA_CLASS_NET)) error = af_select(family, create_perm(label, family, type, protocol), aa_af_perm(current_cred(), label, @@ -1301,7 +1606,7 @@ static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct aa_sk_ctx *ctx = aa_sock(sk); - if (!skb->secmark) + if (!aa_secmark() || !skb->secmark) return 0; return apparmor_secmark_check(ctx->label, OP_RECVMSG, AA_MAY_RECEIVE, @@ -1310,14 +1615,30 @@ static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) #endif -static struct aa_label *sk_peer_label(struct sock *sk) +static struct aa_label *sk_peer_get_label(struct sock *sk) { + struct sock *peer_sk; struct aa_sk_ctx *ctx = aa_sock(sk); + struct aa_label *label = ERR_PTR(-ENOPROTOOPT); if (ctx->peer) - return ctx->peer; + return aa_get_label(ctx->peer); + + if (sk->sk_family != PF_UNIX) + return ERR_PTR(-ENOPROTOOPT); - return ERR_PTR(-ENOPROTOOPT); + /* check for sockpair peering which does not go through + * security_unix_stream_connect + */ + peer_sk = unix_peer_get(sk); + if (peer_sk) { + ctx = aa_sock(peer_sk); + if (ctx->label) + label = aa_get_label(ctx->label); + sock_put(peer_sk); + } + + return label; } /** @@ -1340,7 +1661,7 @@ static int apparmor_socket_getpeersec_stream(struct socket *sock, struct aa_label *peer; label = begin_current_label_crit_section(); - peer = sk_peer_label(sock->sk); + peer = sk_peer_get_label(sock->sk); if (IS_ERR(peer)) { error = PTR_ERR(peer); goto done; @@ -1351,7 +1672,7 @@ static int apparmor_socket_getpeersec_stream(struct socket *sock, /* don't include terminating \0 in slen, it breaks some apps */ if (slen < 0) { error = -ENOMEM; - goto done; + goto done_put; } if (slen > len) { error = -ERANGE; @@ -1363,28 +1684,15 @@ static int apparmor_socket_getpeersec_stream(struct socket *sock, done_len: if (copy_to_sockptr(optlen, &slen, sizeof(slen))) error = -EFAULT; + +done_put: + aa_put_label(peer); done: end_current_label_crit_section(label); kfree(name); return error; } -/** - * apparmor_socket_getpeersec_dgram - get security label of packet - * @sock: the peer socket - * @skb: packet data - * @secid: pointer to where to put the secid of the packet - * - * Sets the netlabel socket state on sk from parent - */ -static int apparmor_socket_getpeersec_dgram(struct socket *sock, - struct sk_buff *skb, u32 *secid) - -{ - /* TODO: requires secid support */ - return -ENOPROTOOPT; -} - /** * apparmor_sock_graft - Initialize newly created socket * @sk: child sock @@ -1410,7 +1718,7 @@ static int apparmor_inet_conn_request(const struct sock *sk, struct sk_buff *skb { struct aa_sk_ctx *ctx = aa_sock(sk); - if (!skb->secmark) + if (!aa_secmark() || !skb->secmark) return 0; return apparmor_secmark_check(ctx->label, OP_CONNECT, AA_MAY_CONNECT, @@ -1424,12 +1732,19 @@ static int apparmor_inet_conn_request(const struct sock *sk, struct sk_buff *skb struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = { .lbs_cred = sizeof(struct aa_label *), .lbs_file = sizeof(struct aa_file_ctx), + .lbs_inode = sizeof(struct aa_inode_sec), .lbs_task = sizeof(struct aa_task_ctx), + .lbs_sock = sizeof(struct aa_sk_ctx), + .lbs_secmark = true, + .lbs_ipc = sizeof(struct aa_ipc_sec), + .lbs_msg_msg = sizeof(struct aa_msg_sec), + .lbs_superblock = sizeof(struct aa_superblock_sec), }; static const struct lsm_id apparmor_lsmid = { .name = "apparmor", .id = LSM_ID_APPARMOR, + .lsmblob = true, }; static struct security_hook_list apparmor_hooks[] __ro_after_init = { @@ -1455,6 +1770,16 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = { LSM_HOOK_INIT(path_truncate, apparmor_path_truncate), LSM_HOOK_INIT(inode_getattr, apparmor_inode_getattr), + LSM_HOOK_INIT(inode_alloc_security, apparmor_inode_alloc_security), + LSM_HOOK_INIT(inode_free_security, apparmor_inode_free_security), + LSM_HOOK_INIT(inode_init_security, apparmor_inode_init_security), + LSM_HOOK_INIT(d_instantiate, apparmor_d_instantiate), + + LSM_HOOK_INIT(inode_create, apparmor_inode_create), + LSM_HOOK_INIT(inode_unlink, apparmor_inode_unlink), + LSM_HOOK_INIT(inode_setattr, apparmor_inode_setattr), + LSM_HOOK_INIT(inode_getattr, apparmor_inode_getattr), + LSM_HOOK_INIT(file_open, apparmor_file_open), LSM_HOOK_INIT(file_receive, apparmor_file_receive), LSM_HOOK_INIT(file_permission, apparmor_file_permission), @@ -1470,10 +1795,12 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = { LSM_HOOK_INIT(getprocattr, apparmor_getprocattr), LSM_HOOK_INIT(setprocattr, apparmor_setprocattr), - LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security), LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security), LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security), + LSM_HOOK_INIT(unix_stream_connect, apparmor_unix_stream_connect), + LSM_HOOK_INIT(unix_may_send, apparmor_unix_may_send), + LSM_HOOK_INIT(socket_create, apparmor_socket_create), LSM_HOOK_INIT(socket_post_create, apparmor_socket_post_create), LSM_HOOK_INIT(socket_bind, apparmor_socket_bind), @@ -1492,8 +1819,6 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = { #endif LSM_HOOK_INIT(socket_getpeersec_stream, apparmor_socket_getpeersec_stream), - LSM_HOOK_INIT(socket_getpeersec_dgram, - apparmor_socket_getpeersec_dgram), LSM_HOOK_INIT(sock_graft, apparmor_sock_graft), #ifdef CONFIG_NETWORK_SECMARK LSM_HOOK_INIT(inet_conn_request, apparmor_inet_conn_request), @@ -1510,8 +1835,9 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = { LSM_HOOK_INIT(task_free, apparmor_task_free), LSM_HOOK_INIT(task_alloc, apparmor_task_alloc), - LSM_HOOK_INIT(current_getsecid_subj, apparmor_current_getsecid_subj), - LSM_HOOK_INIT(task_getsecid_obj, apparmor_task_getsecid_obj), + LSM_HOOK_INIT(current_getlsmblob_subj, + apparmor_current_getlsmblob_subj), + LSM_HOOK_INIT(task_getlsmblob_obj, apparmor_task_getlsmblob_obj), LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit), LSM_HOOK_INIT(task_kill, apparmor_task_kill), LSM_HOOK_INIT(userns_create, apparmor_userns_create), @@ -1524,6 +1850,7 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = { #endif LSM_HOOK_INIT(secid_to_secctx, apparmor_secid_to_secctx), + LSM_HOOK_INIT(lsmblob_to_secctx, apparmor_lsmblob_to_secctx), LSM_HOOK_INIT(secctx_to_secid, apparmor_secctx_to_secid), LSM_HOOK_INIT(release_secctx, apparmor_release_secctx), @@ -1573,6 +1900,9 @@ static const struct kernel_param_ops param_ops_aalockpolicy = { .get = param_get_aalockpolicy }; +static int param_set_debug(const char *val, const struct kernel_param *kp); +static int param_get_debug(char *buffer, const struct kernel_param *kp); + static int param_set_audit(const char *val, const struct kernel_param *kp); static int param_get_audit(char *buffer, const struct kernel_param *kp); @@ -1606,8 +1936,9 @@ module_param_named(rawdata_compression_level, aa_g_rawdata_compression_level, aacompressionlevel, 0400); /* Debug mode */ -bool aa_g_debug = IS_ENABLED(CONFIG_SECURITY_APPARMOR_DEBUG_MESSAGES); -module_param_named(debug, aa_g_debug, aabool, S_IRUSR | S_IWUSR); +int aa_g_debug; +module_param_call(debug, param_set_debug, param_get_debug, + &aa_g_debug, S_IRUSR | S_IWUSR); /* Audit mode */ enum audit_mode aa_g_audit; @@ -1800,6 +2131,34 @@ static int param_get_aacompressionlevel(char *buffer, return param_get_int(buffer, kp); } +static int param_get_debug(char *buffer, const struct kernel_param *kp) +{ + if (!apparmor_enabled) + return -EINVAL; + if (apparmor_initialized && !aa_current_policy_view_capable(NULL)) + return -EPERM; + return aa_print_debug_params(buffer); +} + +static int param_set_debug(const char *val, const struct kernel_param *kp) +{ + int i; + + if (!apparmor_enabled) + return -EINVAL; + if (!val) + return -EINVAL; + if (apparmor_initialized && !aa_current_policy_admin_capable(NULL)) + return -EPERM; + + i = aa_parse_debug_params(val); + if (i == DEBUG_PARSE_ERROR) + return -EINVAL; + + aa_g_debug = i; + return 0; +} + static int param_get_audit(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) @@ -2040,6 +2399,17 @@ static int apparmor_dointvec(struct ctl_table *table, int write, return proc_dointvec(table, write, buffer, lenp, ppos); } +static int userns_restrict_dointvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + if (!apparmor_enabled) + return -EINVAL; + if (write && !aa_current_policy_admin_capable(NULL)) + return -EPERM; + + return proc_dointvec(table, write, buffer, lenp, ppos); +} + static struct ctl_table apparmor_sysctl_table[] = { #ifdef CONFIG_USER_NS { @@ -2057,10 +2427,40 @@ static struct ctl_table apparmor_sysctl_table[] = { .mode = 0600, .proc_handler = apparmor_dointvec, }, +#ifdef CONFIG_USER_NS + { + .procname = "apparmor_restrict_unprivileged_userns", + .data = &aa_unprivileged_userns_restricted, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = userns_restrict_dointvec, + }, + { + .procname = "apparmor_restrict_unprivileged_userns_force", + .data = &aa_unprivileged_userns_restricted_force, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = apparmor_dointvec, + }, + { + .procname = "apparmor_restrict_unprivileged_userns_complain", + .data = &aa_unprivileged_userns_restricted_complain, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = apparmor_dointvec, + }, +#endif /* CONFIG_USER_NS */ { .procname = "apparmor_restrict_unprivileged_unconfined", .data = &aa_unprivileged_unconfined_restricted, .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = userns_restrict_dointvec, + }, + { + .procname = "apparmor_restrict_unprivileged_io_uring", + .data = &aa_unprivileged_uring_restricted, + .maxlen = sizeof(int), .mode = 0600, .proc_handler = apparmor_dointvec, }, @@ -2086,7 +2486,7 @@ static unsigned int apparmor_ip_postroute(void *priv, struct aa_sk_ctx *ctx; struct sock *sk; - if (!skb->secmark) + if (!aa_secmark() || !skb->secmark) return NF_ACCEPT; sk = skb_to_full_sk(skb); @@ -2217,7 +2617,16 @@ static void __init aa_teardown_dfa_engine(void) static int __init apparmor_init(void) { - int error; + int error = -ENOMEM; + + /* setup allocation caches */ + aa_audit_slab = kmem_cache_create("apparmor_auditcache", + sizeof(struct aa_audit_node), + 0, SLAB_PANIC, NULL); + if (!aa_audit_slab) { + AA_ERROR("Unable to setup auditdata slab cache\n"); + goto alloc_out; + } error = aa_setup_dfa_engine(); if (error) { @@ -2269,6 +2678,7 @@ static int __init apparmor_init(void) alloc_out: aa_destroy_aafs(); aa_teardown_dfa_engine(); + kmem_cache_destroy(aa_audit_slab); apparmor_enabled = false; return error; @@ -2276,7 +2686,7 @@ static int __init apparmor_init(void) DEFINE_LSM(apparmor) = { .name = "apparmor", - .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, + .flags = LSM_FLAG_LEGACY_MAJOR, .enabled = &apparmor_enabled, .blobs = &apparmor_blob_sizes, .init = apparmor_init, diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c index 49fe8da6fea45..74b7293ab9713 100644 --- a/security/apparmor/mount.c +++ b/security/apparmor/mount.c @@ -678,8 +678,7 @@ static struct aa_label *build_pivotroot(const struct cred *subj_cred, AA_BUG(!new_path); AA_BUG(!old_path); - if (profile_unconfined(profile) || - !RULE_MEDIATES(rules, AA_CLASS_MOUNT)) + if (!RULE_MEDIATES(rules, AA_CLASS_MOUNT)) return aa_get_newest_label(&profile->label); error = aa_path_name(old_path, path_flags(profile, old_path), diff --git a/security/apparmor/net.c b/security/apparmor/net.c index 87e934b2b5488..7e6c17fd7190c 100644 --- a/security/apparmor/net.c +++ b/security/apparmor/net.c @@ -8,6 +8,8 @@ * Copyright 2009-2017 Canonical Ltd. */ +#include "include/af_unix.h" +#include "include/af_inet.h" #include "include/apparmor.h" #include "include/audit.h" #include "include/cred.h" @@ -21,6 +23,13 @@ struct aa_sfs_entry aa_sfs_entry_network[] = { AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK), + AA_SFS_FILE_BOOLEAN("af_inet", 1), + { } +}; + +struct aa_sfs_entry aa_sfs_entry_network_compat[] = { + AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK), + AA_SFS_FILE_BOOLEAN("af_unix", 1), { } }; @@ -66,6 +75,37 @@ static const char * const net_mask_names[] = { "unknown", }; +static void audit_unix_addr(struct audit_buffer *ab, const char *str, + struct sockaddr_un *addr, int addrlen) +{ + int len = unix_addr_len(addrlen); + + if (!addr || len <= 0) { + audit_log_format(ab, " %s=none", str); + } else if (addr->sun_path[0]) { + audit_log_format(ab, " %s=", str); + audit_log_untrustedstring(ab, addr->sun_path); + } else { + audit_log_format(ab, " %s=\"@", str); + if (audit_string_contains_control(&addr->sun_path[1], len - 1)) + audit_log_n_hex(ab, &addr->sun_path[1], len - 1); + else + audit_log_format(ab, "%.*s", len - 1, + &addr->sun_path[1]); + audit_log_format(ab, "\""); + } +} + +static void audit_unix_sk_addr(struct audit_buffer *ab, const char *str, + const struct sock *sk) +{ + const struct unix_sock *u = unix_sk(sk); + + if (u && u->addr) + audit_unix_addr(ab, str, u->addr->name, u->addr->len); + else + audit_unix_addr(ab, str, NULL, 0); +} /* audit callback for net specific fields */ void audit_net_cb(struct audit_buffer *ab, void *va) @@ -73,12 +113,12 @@ void audit_net_cb(struct audit_buffer *ab, void *va) struct common_audit_data *sa = va; struct apparmor_audit_data *ad = aad(sa); - if (address_family_names[sa->u.net->family]) + if (address_family_names[ad->common.u.net->family]) audit_log_format(ab, " family=\"%s\"", - address_family_names[sa->u.net->family]); + address_family_names[ad->common.u.net->family]); else audit_log_format(ab, " family=\"unknown(%d)\"", - sa->u.net->family); + ad->common.u.net->family); if (sock_type_names[ad->net.type]) audit_log_format(ab, " sock_type=\"%s\"", sock_type_names[ad->net.type]); @@ -88,16 +128,33 @@ void audit_net_cb(struct audit_buffer *ab, void *va) audit_log_format(ab, " protocol=%d", ad->net.protocol); if (ad->request & NET_PERMS_MASK) { - audit_log_format(ab, " requested_mask="); + audit_log_format(ab, " requested="); aa_audit_perm_mask(ab, ad->request, NULL, 0, net_mask_names, NET_PERMS_MASK); if (ad->denied & NET_PERMS_MASK) { - audit_log_format(ab, " denied_mask="); + audit_log_format(ab, " denied="); aa_audit_perm_mask(ab, ad->denied, NULL, 0, net_mask_names, NET_PERMS_MASK); } } + if (ad->common.u.net->family == AF_UNIX) { + if ((ad->request & ~NET_PEER_MASK) && ad->net.addr) + audit_unix_addr(ab, "addr", + unix_addr(ad->net.addr), + ad->net.addrlen); + else + audit_unix_sk_addr(ab, "addr", ad->common.u.net->sk); + if (ad->request & NET_PEER_MASK) { + if (ad->net.addr) + audit_unix_addr(ab, "peer_addr", + unix_addr(ad->net.addr), + ad->net.addrlen); + else + audit_unix_sk_addr(ab, "peer_addr", + ad->net.peer_sk); + } + } if (ad->peer) { audit_log_format(ab, " peer="); aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, @@ -118,18 +175,28 @@ int aa_profile_af_perm(struct aa_profile *profile, AA_BUG(family >= AF_MAX); AA_BUG(type < 0 || type >= SOCK_MAX); + AA_BUG(profile_unconfined(profile)); - if (profile_unconfined(profile)) - return 0; state = RULE_MEDIATES(rules, AA_CLASS_NET); - if (!state) + if (state) { + buffer[0] = cpu_to_be16(family); + buffer[1] = cpu_to_be16((u16) type); + state = aa_dfa_match_len(rules->policy->dfa, state, + (char *) &buffer, 4); + perms = *aa_lookup_perms(rules->policy, state); + } else if (profile->net_compat) { + + /* 2.x socket mediation compat */ + perms.allow = (profile->net_compat->allow[family] & (1 << type)) ? + ALL_PERMS_MASK : 0; + perms.audit = (profile->net_compat->audit[family] & (1 << type)) ? + ALL_PERMS_MASK : 0; + perms.quiet = (profile->net_compat->quiet[family] & (1 << type)) ? + ALL_PERMS_MASK : 0; + + } else { return 0; - - buffer[0] = cpu_to_be16(family); - buffer[1] = cpu_to_be16((u16) type); - state = aa_dfa_match_len(rules->policy->dfa, state, (char *) &buffer, - 4); - perms = *aa_lookup_perms(rules->policy, state); + } aa_apply_modes_to_perms(profile, &perms); return aa_check_perms(profile, &perms, request, ad, audit_net_cb); @@ -151,13 +218,13 @@ static int aa_label_sk_perm(const struct cred *subj_cred, const char *op, u32 request, struct sock *sk) { - struct aa_sk_ctx *ctx = SK_CTX(sk); + struct aa_sk_ctx *ctx = aa_sock(sk); int error = 0; AA_BUG(!label); AA_BUG(!sk); - if (ctx->label != kernel_t && !unconfined(label)) { + if (ctx->label != kernel_t && label_mediates(label, AA_CLASS_NET)) { struct aa_profile *profile; DEFINE_AUDIT_SK(ad, op, sk); @@ -193,7 +260,10 @@ int aa_sock_file_perm(const struct cred *subj_cred, struct aa_label *label, AA_BUG(!sock); AA_BUG(!sock->sk); - return aa_label_sk_perm(subj_cred, label, op, request, sock->sk); + return af_select(sock->sk->sk_family, + file_perm(subj_cred, label, op, request, sock), + aa_label_sk_perm(subj_cred, label, op, request, + sock->sk)); } #ifdef CONFIG_NETWORK_SECMARK diff --git a/security/apparmor/notify.c b/security/apparmor/notify.c new file mode 100644 index 0000000000000..374fe897374fa --- /dev/null +++ b/security/apparmor/notify.c @@ -0,0 +1,1062 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AppArmor security module + * + * This file contains AppArmor notifications function definitions. + * + * Copyright 2019 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ +#include +#include +#include + +#include + +#include "include/audit.h" +#include "include/cred.h" +#include "include/lib.h" +#include "include/notify.h" +#include "include/policy_ns.h" + +/* TODO: when adding listener or ns propagate, on recursive add to child ns */ + +// TODO: currently all knotif will have audit_node but not all in future +static inline struct aa_knotif *aa_get_knotif(struct aa_knotif *knotif) +{ + if (knotif) + aa_get_audit_node(container_of(knotif, struct aa_audit_node, + knotif)); + + return knotif; +} + +static inline void aa_put_knotif(struct aa_knotif *knotif) +{ + if (knotif) + aa_put_audit_node(container_of(knotif, struct aa_audit_node, + knotif)); +} + +static void put_refs(struct aa_listener *listener, struct aa_knotif *knotif) +{ + aa_put_listener(listener); + aa_put_knotif(knotif); +} + +static void get_refs(struct aa_listener *listener, struct aa_knotif *knotif) +{ + aa_get_listener(listener); + aa_get_knotif(knotif); +} + +static void __knotif_del_and_hold(struct aa_knotif *knotif) +{ + list_del_init(&knotif->list); + knotif->flags &= ~KNOTIF_ON_LIST; + /* keep list refcounts */ +} + +static void __list_append_held(struct list_head *lh, struct aa_knotif *knotif) +{ + AA_BUG(!lh); + AA_BUG(!knotif); + + list_add_tail_entry(knotif, lh, list); + knotif->flags |= KNOTIF_ON_LIST; +} + +/* +static void __list_push_held(struct list_head *lh, struct aa_knotif *knotif) +{ + AA_BUG(!lh); + AA_BUG(!knotif); + + list_add_entry(knotif, lh, list); + knotif->flags |= KNOTIF_ON_LIST; +} +*/ + +static void __listener_add_knotif(struct aa_listener *listener, + struct aa_knotif *knotif) +{ + AA_BUG(!listener); + AA_BUG(!knotif); + lockdep_assert_held(&listener->lock); + + get_refs(listener, knotif); + __list_append_held(&listener->notifications, knotif); +} + +// drops refs +static void __listener_del_knotif(struct aa_listener *listener, + struct aa_knotif *knotif) +{ + AA_BUG(!listener); + AA_BUG(!knotif); + lockdep_assert_held(&listener->lock); + + list_del_init(&knotif->list); + if (knotif->flags & KNOTIF_ON_LIST) { + knotif->flags &= ~KNOTIF_ON_LIST; + put_refs(listener, knotif); + } +} + +void aa_free_listener_proxy(struct aa_listener_proxy *proxy) +{ + if (proxy) { + AA_BUG(!list_empty(&proxy->llist)); + AA_BUG(!list_empty(&proxy->nslist)); + + aa_put_ns(proxy->ns); + /* listener is owned by file, handled there */ + kfree_sensitive(proxy); + } +} + +static struct aa_listener_proxy *new_listener_proxy(struct aa_listener *listener, + struct aa_ns *ns) +{ + struct aa_listener_proxy *proxy; + + AA_BUG(!listener); + lockdep_assert_not_held(&listener->lock); + + proxy = kzalloc(sizeof(*proxy), GFP_KERNEL); + if (!proxy) + return NULL; + INIT_LIST_HEAD(&proxy->llist); + INIT_LIST_HEAD(&proxy->nslist); + + proxy->listener = listener; + if (ns) + ns = aa_get_ns(ns); + else + ns = aa_get_current_ns(); + proxy->ns = ns; + + spin_lock(&listener->lock); + list_add_tail_entry(proxy, &listener->ns_proxies, llist); + spin_unlock(&listener->lock); + + spin_lock(&ns->listener_lock); + list_add_tail_entry(proxy, &ns->listeners, nslist); + spin_unlock(&ns->listener_lock); + + return proxy; +} + + +bool aa_register_listener_proxy(struct aa_listener *listener, struct aa_ns *ns) +{ + struct aa_listener_proxy *proxy; + + AA_BUG(!listener); + + proxy = new_listener_proxy(listener, ns); + if (!proxy) + return false; + + return true; +} + +static void free_listener(struct aa_listener *listener) +{ + struct aa_listener_proxy *proxy; + struct aa_knotif *knotif; + + if (!listener) + return; + + wake_up_interruptible_poll(&listener->wait, EPOLLIN | EPOLLRDNORM); + + spin_lock(&listener->lock); + while (!list_empty(&listener->ns_proxies)) { + proxy = list_first_entry(&listener->ns_proxies, + struct aa_listener_proxy, + llist); + list_del_init(&proxy->llist); + spin_unlock(&listener->lock); + + spin_lock(&proxy->ns->listener_lock); + list_del_init(&proxy->nslist); + spin_unlock(&proxy->ns->listener_lock); + + aa_put_ns(proxy->ns); + kfree_sensitive(proxy); + + spin_lock(&listener->lock); + } + spin_unlock(&listener->lock); + + spin_lock(&listener->lock); + while (!list_empty(&listener->notifications)) { + knotif = list_first_entry(&listener->notifications, + struct aa_knotif, + list); + __listener_del_knotif(listener, knotif); + complete(&knotif->ready); + put_refs(listener, knotif); + } + spin_unlock(&listener->lock); + + spin_lock(&listener->lock); + while (!list_empty(&listener->pending)) { + knotif = list_first_entry(&listener->pending, + struct aa_knotif, + list); + __listener_del_knotif(listener, knotif); + complete(&knotif->ready); + put_refs(listener, knotif); + } + spin_unlock(&listener->lock); + + /* todo count on audit_data */ + aa_put_ns(listener->ns); + aa_put_dfa(listener->filter); + + kfree_sensitive(listener); +} + +void aa_listener_kref(struct kref *kref) +{ + struct aa_listener *l = container_of(kref, struct aa_listener, count); + + free_listener(l); +} + +struct aa_listener *aa_new_listener(struct aa_ns *ns, gfp_t gfp) +{ + struct aa_listener *listener = kzalloc(sizeof(*listener), gfp); + + if (!listener) + return NULL; + + kref_init(&listener->count); + spin_lock_init(&listener->lock); + init_waitqueue_head(&listener->wait); + INIT_LIST_HEAD(&listener->ns_proxies); + INIT_LIST_HEAD(&listener->notifications); + INIT_LIST_HEAD(&listener->pending); + kref_init(&listener->count); + + if (ns) + ns = aa_get_ns(ns); + else + ns = aa_get_current_ns(); + listener->ns = ns; + listener->last_id = 1; + + return listener; +} + +static struct aa_knotif *__aa_find_notif_pending(struct aa_listener *listener, + u64 id) +{ + struct aa_knotif *knotif; + + AA_BUG(!listener); + lockdep_assert_held(&listener->lock); + + list_for_each_entry(knotif, &listener->pending, list) { + if (knotif->id == id) + return knotif; + } + + return NULL; +} + +struct aa_knotif *__aa_find_notif(struct aa_listener *listener, u64 id) +{ + struct aa_knotif *knotif; + + AA_BUG(!listener); + lockdep_assert_held(&listener->lock); + + list_for_each_entry(knotif, &listener->notifications, list) { + if (knotif->id == id) + goto out; + } + + knotif = __aa_find_notif_pending(listener, id); +out: + + return knotif; +} + +// don't drop refcounts +static struct aa_knotif * +listener_pop_and_hold_knotif(struct aa_listener *listener) +{ + struct aa_knotif *knotif = NULL; + + spin_lock(&listener->lock); + if (!list_empty(&listener->notifications)) { + knotif = list_first_entry(&listener->notifications, typeof(*knotif), list); + __knotif_del_and_hold(knotif); + } + spin_unlock(&listener->lock); + + return knotif; +} + +// require refcounts held +/* +static void listener_push_held_knotif(struct aa_listener *listener, + struct aa_knotif *knotif) +{ + spin_lock(&listener->lock); + // listener ref held from pop and hold + __list_push_held(&listener->notifications, knotif); + spin_unlock(&listener->lock); + wake_up_interruptible_poll(&listener->wait, EPOLLIN | EPOLLRDNORM); +} +*/ + +// require refcounts held +// list of knotifs waiting for response +static void listener_append_held_user_pending(struct aa_listener *listener, + struct aa_knotif *knotif) +{ + spin_lock(&listener->lock); + __list_append_held(&listener->pending, knotif); + spin_unlock(&listener->lock); + //extraneous wakeup, called after reading notification + //wake_up_interruptible_poll(&listener->wait, EPOLLOUT | EPOLLWRNORM); +} + +// don't drop refcounts +static struct aa_knotif * +__del_and_hold_user_pending(struct aa_listener *listener, u64 id) +{ + struct aa_knotif *knotif; + + AA_BUG(!listener); + lockdep_assert_held(&listener->lock); + + list_for_each_entry(knotif, &listener->pending, list) { + if (knotif->id == id) { + __knotif_del_and_hold(knotif); + return knotif; + } + } + + return NULL; +} + + +/***************** kernel dispatching notification ********************/ + +/* + * cancelled notification message due to non-timer wake-up vs. + * keep alive message + * cancel notification because ns removed? + * - proxy pins ns + * - ns can remove its list of proxies + * - and remove queued notifications + */ + +/* TODO: allow registering on multiple namespaces */ +static bool notification_match(struct aa_listener *listener, + struct aa_audit_node *ad) +{ + if (!(listener->mask & (1 << ad->data.type))) + return false; + + if (listener->filter) { + aa_state_t state; + unsigned int mask; + + AA_DEBUG(DEBUG_UPCALL, "using filter"); + if (!aa_ns_visible(listener->ns, labels_ns(ad->data.subj_label), + false)) + return false; + state = aa_dfa_next(listener->filter, DFA_START, ad->data.type); + state = aa_dfa_match(listener->filter, state, ad->data.subj_label->hname); + if (!state) + return false; + state = aa_dfa_null_transition(listener->filter, state); + state = aa_dfa_match_u16(listener->filter, state, ad->data.class); + mask = ACCEPT_TABLE(listener->filter)[state]; + if (ad->data.request & mask) + return true; + + /* allow for enhanced match conditions in the future + * if (mask & AA_MATCH_CONT) { + * // TODO: match extensions + * } + */ + return false; + } + AA_DEBUG(DEBUG_UPCALL, "matched type mask filter"); + return true; +} + +/* Add a notification to the listener queue and wake up listener??? */ +static void dispatch_notif(struct aa_listener *listener, + u16 ntype, + struct aa_knotif *knotif) +{ + AA_BUG(!listener); + AA_BUG(!knotif); + lockdep_assert_held(&listener->lock); + + AA_DEBUG_ON(knotif->id, DEBUG_UPCALL, + "id %lld: redispatching notification as new id %lld", + knotif->id, listener->last_id); + knotif->ntype = ntype; + knotif->id = ++listener->last_id; + knotif->flags = 0; + // only needed if syncrhonous notit + init_completion(&knotif->ready); + INIT_LIST_HEAD(&knotif->list); + __listener_add_knotif(listener, knotif); + AA_DEBUG(DEBUG_UPCALL, "id %lld: %s wake_up_interruptible", + knotif->id, __func__); + wake_up_interruptible_poll(&listener->wait, EPOLLIN | EPOLLRDNORM); +} + + +/* handle waiting for a user space reply to a notification + * Returns: <0 : error or -ERESTARTSYS if interrupted + * 0 : success + */ +static int handle_synchronous_notif(struct aa_listener *listener, + struct aa_knotif *knotif) +{ + long werr; + int err; + + if (knotif->ad->subj_label->flags & FLAG_INTERRUPTIBLE) + werr = wait_for_completion_interruptible_timeout(&knotif->ready, + msecs_to_jiffies(60000)); + else + /* do not use close to long jiffies so cast is safe */ + werr = (long) wait_for_completion_timeout(&knotif->ready, + msecs_to_jiffies(60000)); + /* time out OR interrupt */ + if (werr <= 0) { + /* ensure knotif is not on list because of early exit */ + spin_lock(&listener->lock); + // puts refs but still have calling refs + __listener_del_knotif(listener, knotif); + spin_unlock(&listener->lock); + if (werr == 0) { + AA_DEBUG(DEBUG_UPCALL, "id %lld: prompt timed out", + knotif->id); + //err = -1; // TODO: ???; + err = 0; + } else if (werr == -ERESTARTSYS) { + // interrupt fired syscall needs to be restarted + // instead of mediated + AA_DEBUG(DEBUG_UPCALL, "id %lld: prompt interrupted, error %ld", + knotif->id, werr); + err = -ERESTARTSYS; + } else { + AA_DEBUG(DEBUG_UPCALL, "id %lld: prompt errored out error %ld", + knotif->id, werr); + err = (int) werr; + } + /* time out is not considered an error and will fallback + * to regular mediation + */ + } else { + err = 0; + spin_lock(&listener->lock); + if (!list_empty(&knotif->list)) { + // puts refs but still have calling refs + __listener_del_knotif(listener, knotif); + AA_DEBUG(DEBUG_UPCALL, + "id %lld: bug prompt knotif still on listener list at notif completion", + knotif->id); + } + spin_unlock(&listener->lock); + } + + return err; +} + +// permissions changed in ad +int aa_do_notification(u16 ntype, struct aa_audit_node *node) +{ + struct aa_ns *ns = labels_ns(node->data.subj_label); + struct aa_listener_proxy *proxy; + struct aa_listener *listener; + struct aa_knotif *knotif; + int count = 0, err = 0; + + AA_BUG(!node); + AA_BUG(!ns); + + knotif = &node->knotif; + + /* TODO: make read side of list walk lockless */ + spin_lock(&ns->listener_lock); + list_for_each_entry(proxy, &ns->listeners, nslist) { + + AA_BUG(!proxy); + listener = aa_get_listener(proxy->listener); + AA_BUG(!listener); + spin_lock(&listener->lock); + if (!notification_match(listener, node)) { + spin_unlock(&listener->lock); + aa_put_listener(listener); + continue; + } + /* delvier notification - dispatch determines if we break */ + dispatch_notif(listener, ntype, knotif); // count); + spin_unlock(&listener->lock); + AA_DEBUG(DEBUG_UPCALL, "id %lld: found listener\n", + knotif->id); + + /* break to prompt */ + if (node->data.type == AUDIT_APPARMOR_USER) { + spin_unlock(&ns->listener_lock); + err = handle_synchronous_notif(listener, knotif); + aa_put_listener(listener); + return err; + } + count++; + aa_put_listener(listener); + } + spin_unlock(&ns->listener_lock); + AA_DEBUG(DEBUG_UPCALL, "id %lld: %d listener matches\n", + knotif->id, count); + + /* count == 0 is no match found. No change to audit params + * long term need to fold prompt perms into denied + **/ + return err; +} + +/******************** task responding to notification **********************/ + +// drop references +// complete anything pending on ready +static void __listener_complete_held_user_pending(struct aa_listener *listener, + struct aa_knotif *knotif) +{ + AA_BUG(!listener); + lockdep_assert_held(&listener->lock); + + __knotif_del_and_hold(knotif); + complete(&knotif->ready); + put_refs(listener, knotif); +} + +static void listener_complete_held_user_pending(struct aa_listener *listener, + struct aa_knotif *knotif) +{ + spin_lock(&listener->lock); + __listener_complete_held_user_pending(listener, knotif); + spin_unlock(&listener->lock); +} + +static bool response_is_valid_perm(struct apparmor_notif_resp_perm *reply, + struct aa_knotif *knotif, u16 size) +{ + if ((knotif->ad->denied) & ~(reply->allow | reply->deny)) { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: response does not cover permission bits in the upcall request/reply 0x%x/0x%x deny/reply 0x%x/0x%x", + knotif->id, knotif->ad->request, reply->allow, knotif->ad->denied, + reply->deny); + return false; + } + return true; + /* TODO: this was disabled per snapd request, setup flag to do check + * // allow bits that were never requested + * if (reply->allow & ~knotif->ad->request) { + * AA_DEBUG(DEBUG_UPCALL, "response allows more than requested"); + * return false; + * } + * // denying perms not in either permission set in the original + * // notification + * if (reply->deny & ~(knotif->ad->request | knotif->ad->denied)) { + * AA_DEBUG(DEBUG_UPCALL, "response denies more than requested"); + * return false; + * } + */ +} + +static bool response_is_valid_name(struct apparmor_notif_resp_name *reply, + struct aa_knotif *knotif, u16 size) +{ + long i; + + if (size <= sizeof(*reply)) { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: reply bad size %u < %ld", + knotif->id, size, sizeof(*reply)); + return -EMSGSIZE; + } + if (reply->name < sizeof(*reply)) { + /* inside of data declared fields */ + AA_DEBUG(DEBUG_UPCALL, + "id %lld: reply bad name offset in fields %u < %ld", + knotif->id, reply->name, sizeof(*reply)); + return -EINVAL; + } + if (reply->name > size) { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: reply name pasted end of data size %u > %ld", + knotif->id, reply->name, sizeof(*reply)); + return -EINVAL; + } + /* currently supported flags */ + if ((reply->perm.base.flags != (URESPONSE_LOOKUP | URESPONSE_PROFILE))) { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: reply bad flags 0x%x expected 0x%x", + knotif->id, reply->perm.base.flags, + URESPONSE_LOOKUP | URESPONSE_PROFILE); + return -EINVAL; + } + + if ((reply->perm.base.flags == URESPONSE_TAILGLOB) && + !response_is_valid_perm(&reply->perm, knotif, size)) { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: reply bad tail glob perms", + knotif->id); + return false; + } + + /* check name for terminating null */ + for (i = reply->name - sizeof(*reply); i < size - sizeof(*reply); i++) { + if (reply->data[i] == 0) + return true; + } + /* reached end of data without finding null */ + AA_DEBUG(DEBUG_UPCALL, + "id %lld: reply bad no terminating null on name", + knotif->id); + + return false; +} + +/* base checks userspace respnse to a notification is valid */ +static bool response_is_valid(union apparmor_notif_resp *reply, + struct aa_knotif *knotif, u16 size) +{ + if (reply->base.ntype == APPARMOR_NOTIF_RESP_PERM) + return response_is_valid_perm(&reply->perm, knotif, size); + else if (reply->base.ntype == APPARMOR_NOTIF_RESP_NAME) + return response_is_valid_name(&reply->name, knotif, size); + else + return false; + return false; +} + + +/* copy uresponse into knotif */ +static void knotif_update_from_uresp_perm(struct aa_knotif *knotif, + struct apparmor_notif_resp_perm *uresp) +{ + u16 flags; + + if (uresp) { + AA_DEBUG(DEBUG_UPCALL, + "notif %lld: response allow/reply 0x%x/0x%x, denied/reply 0x%x/0x%x, error %d/%d", + knotif->id, knotif->ad->request, uresp->allow, + knotif->ad->denied, uresp->deny, knotif->ad->error, + uresp->base.error); + + knotif->ad->denied = uresp->deny; + knotif->ad->request = (knotif->ad->request | uresp->allow) & + ~uresp->deny; + flags = uresp->base.flags; + if (!knotif->ad->denied) { + /* no more denial, clear the error*/ + knotif->ad->error = 0; + AA_DEBUG(DEBUG_UPCALL, + "notif %lld: response allowed, clearing error\n", + knotif->id); + } else { + AA_DEBUG(DEBUG_UPCALL, + "notif %lld: response denied returning error %d\n", + knotif->id, knotif->ad->error); + } + } else { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: respons bad going with: allow 0x%x, denied 0x%x, error %d", + knotif->id, knotif->ad->request, knotif->ad->denied, + knotif->ad->error); + } + + if (!(flags & URESPONSE_NO_CACHE)) { + /* cache of response requested */ + struct aa_audit_node *node = container_of(knotif, + struct aa_audit_node, + knotif); + struct aa_audit_node *hit; + struct aa_profile *profile = labels_profile(node->data.subj_label); + + AA_DEBUG(DEBUG_UPCALL, "id %lld: inserting cache entry requ 0x%x denied 0x%x", + knotif->id, node->data.request, node->data.denied); + hit = aa_audit_cache_insert(&profile->learning_cache, + node); + AA_DEBUG(DEBUG_UPCALL, + "id %lld: (node %p, hit %p) cache insert %s: name %s node %s\n", + knotif->id, node, hit, hit != node ? "entry already exists" : "", + hit->data.name, node->data.name); + if (hit != node) { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: updating existing cache entry", + knotif->id); + aa_audit_cache_update_ent(&profile->learning_cache, + hit, &node->data); + aa_put_audit_node(hit); + } else { + + AA_DEBUG(DEBUG_UPCALL, "inserted into cache"); + } + /* now to audit */ + } /* cache_response */ +} + + +void aa_free_ruleset(struct aa_ruleset *rules) +{ + if (!rules) + return; + aa_put_pdb(rules->policy); + aa_put_pdb(rules->file); + kfree_sensitive(rules); +} + +struct aa_ruleset *aa_new_ruleset(gfp_t gfp) +{ + struct aa_ruleset *rules = kzalloc(sizeof(*rules), gfp); + + INIT_LIST_HEAD(&rules->list); + + return rules; +} + +struct aa_ruleset *aa_clone_ruleset(struct aa_ruleset *rules) +{ + struct aa_ruleset *clone; + + clone = aa_new_ruleset(GFP_KERNEL); + if (!clone) + return NULL; + clone->size = rules->size; + clone->policy = aa_get_pdb(rules->policy); + clone->file = aa_get_pdb(rules->file); + clone->caps = rules->caps; + clone->rlimits = rules->rlimits; + + /* TODO: secmark */ + return clone; +} + +static long knotif_update_from_uresp_name(struct aa_knotif *knotif, + struct apparmor_notif_resp_name *reply, + u16 size) +{ + struct aa_ruleset *rules; + struct aa_profile *profile; + struct aa_ns *ns; + char *name, *glob; + struct aa_audit_node *clone; + struct aa_audit_node *node = container_of(knotif, + struct aa_audit_node, + knotif); + + ns = aa_get_current_ns(); + name = (char *) &reply->data[reply->name - sizeof(*reply)]; + + if (reply->perm.base.flags == (URESPONSE_LOOKUP | URESPONSE_PROFILE)) { + profile = aa_lookup_profile(ns, name); + if (!profile) { + aa_put_ns(ns); + return -ENOENT; + } + aa_put_ns(ns); + + rules = aa_clone_ruleset(list_first_entry(&profile->rules, + typeof(*rules), list)); + if (!rules) { + aa_put_profile(profile); + return -ENOMEM; + } + AA_DEBUG(DEBUG_UPCALL, + "id %lld: cloned profile '%s' rule set", knotif->id, + profile->base.hname); + aa_put_profile(profile); + + /* add list to profile rules TODO: improve locking*/ + profile = labels_profile(node->data.subj_label); + list_add_tail_entry(rules, &profile->rules, list); + } else if (reply->perm.base.flags == URESPONSE_TAILGLOB) { + // TODO: dedup with cache update in perm + struct aa_audit_node *node = container_of(knotif, + struct aa_audit_node, + knotif); + struct aa_audit_node *hit; + struct aa_profile *profile = labels_profile(node->data.subj_label); + + clone = aa_dup_audit_data(&node->data, GFP_KERNEL); + glob = kstrdup(name, GFP_KERNEL); + if (!name) + return -ENOMEM; + if (!clone) { + kfree(name); + return -ENOMEM; + } + kfree(clone->data.name); + clone->data.name = glob; + clone->data.flags = AUDIT_TAILGLOB_NAME; + clone->knotif.id = knotif->id; + clone->knotif.ntype = knotif->ntype; + node = clone; + knotif = &clone->knotif; + + // now add it to the cache + AA_DEBUG(DEBUG_UPCALL, + "notif %lld: response allow/reply 0x%x/0x%x, denied/reply 0x%x/0x%x, error %d/%d", + knotif->id, knotif->ad->request, reply->perm.allow, + knotif->ad->denied, reply->perm.deny, knotif->ad->error, + reply->base.error); + + knotif->ad->denied = reply->perm.deny; + knotif->ad->request = reply->perm.allow | reply->perm.deny; + + if (!knotif->ad->denied) { + /* no more denial, clear the error*/ + knotif->ad->error = 0; + AA_DEBUG(DEBUG_UPCALL, + "notif %lld: response allowed, clearing error\n", + knotif->id); + } else { + AA_DEBUG(DEBUG_UPCALL, + "notif %lld: response denied returning error %d\n", + knotif->id, knotif->ad->error); + } + + AA_DEBUG(DEBUG_UPCALL, "id %lld: inserting cache entry requ 0x%x denied 0x%x", + knotif->id, node->data.request, node->data.denied); + hit = aa_audit_cache_insert(&profile->learning_cache, + node); + AA_DEBUG(DEBUG_UPCALL, "id %lld: cache insert %s: name %s node %s\n", + knotif->id, hit != node ? "lost race" : "", + hit->data.name, node->data.name); + if (hit != node) { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: updating existing cache entry", + knotif->id); + aa_audit_cache_update_ent(&profile->learning_cache, + hit, &node->data); + aa_put_audit_node(hit); + } else { + + AA_DEBUG(DEBUG_UPCALL, "inserted into cache"); + } + aa_put_audit_node(clone); + } + return size; +} + +/* handle userspace responding to a synchronous notification */ +long aa_listener_unotif_response(struct aa_listener *listener, + union apparmor_notif_resp *uresp, + u16 size) +{ + struct aa_knotif *knotif = NULL; + long ret; + + spin_lock(&listener->lock); + knotif = __del_and_hold_user_pending(listener, uresp->base.id); + if (!knotif) { + ret = -ENOENT; + AA_DEBUG(DEBUG_UPCALL, "could not find id %lld", + uresp->base.id); + goto out; + } + if (!response_is_valid(uresp, knotif, size)) { + ret = -EINVAL; + AA_DEBUG(DEBUG_UPCALL, "id %lld: response not valid", knotif->id); + __listener_complete_held_user_pending(listener, knotif); + goto out; + } + + if (uresp->perm.base.ntype == APPARMOR_NOTIF_RESP_PERM) { + knotif_update_from_uresp_perm(knotif, &uresp->perm); + } else if (uresp->perm.base.ntype == APPARMOR_NOTIF_RESP_NAME) { + size = knotif_update_from_uresp_name(knotif, &uresp->name, size); + } else { + AA_DEBUG(DEBUG_UPCALL, "id %lld: unknown response type", knotif->id); + size = -EINVAL; + } + ret = size; + + AA_DEBUG(DEBUG_UPCALL, "id %lld: completing notif", knotif->id); + __listener_complete_held_user_pending(listener, knotif); +out: + spin_unlock(&listener->lock); + + return ret; +} + +/******************** task reading notification to userspace ****************/ + +static long append_str(void __user *pos, long remaining, const char *str) +{ + long size; + + if (!str) + return 0; + size = strlen(str) + 1; + if (size > remaining) + return -EMSGSIZE; + if (copy_to_user(pos, str, size)) + return -EFAULT; + + return size; +} + +#define build_append_str(__BUF, __POS, __MAX, __STR, __FIELD, __SIZE) \ +({ \ + typeof(__SIZE) __tmp_size; \ + __FIELD = __POS - __BUF; \ + __tmp_size = append_str(__POS, max_size - (__POS - __BUF), __STR); \ + if (__tmp_size >= 0) { \ + __POS += __tmp_size; \ + __SIZE += __tmp_size; \ + } else { \ + __SIZE = __tmp_size; \ + } \ + (__tmp_size >= 0); \ +}) + +/* copy to userspace: notification data */ +static long build_v3_unotif(struct aa_knotif *knotif, void __user *buf, + u16 max_size) +{ + union apparmor_notif_all unotif = { }; + struct user_namespace *user_ns; + struct aa_profile *profile; + void __user *pos; + long size; + + AA_DEBUG(DEBUG_UPCALL, "building notif max size %d", max_size); + size = sizeof(unotif); + profile = labels_profile(knotif->ad->subj_label); + AA_BUG(profile == NULL); + if (size > max_size) + return -EMSGSIZE; + + user_ns = get_user_ns(current->nsproxy->uts_ns->user_ns); + + /* build response */ + unotif.common.len = size; + unotif.common.version = APPARMOR_NOTIFY_VERSION; + unotif.base.ntype = knotif->ntype; + unotif.base.id = knotif->id; + unotif.base.error = knotif->ad->error; + unotif.op.allow = knotif->ad->request & knotif->ad->denied; + unotif.op.deny = knotif->ad->denied; + AA_DEBUG(DEBUG_UPCALL, + "notif %lld: sent to user read request 0x%x, denied 0x%x, error %d", + knotif->id, knotif->ad->request, knotif->ad->denied, knotif->ad->error); + + if (knotif->ad->subjtsk != NULL) { + unotif.op.pid = task_pid_vnr(knotif->ad->subjtsk); + unotif.file.subj_uid = from_kuid(user_ns, task_uid(knotif->ad->subjtsk)); + } + unotif.op.class = knotif->ad->class; + unotif.file.obj_uid = from_kuid(user_ns, knotif->ad->fs.ouid); + + put_user_ns(user_ns); + + pos = buf + sizeof(unotif); + if (!build_append_str(buf, pos, max_size, profile->base.hname, + unotif.op.label, size)) + return -EMSGSIZE; + if (!build_append_str(buf, pos, max_size, knotif->ad->name, + unotif.file.name, size)) + return -EMSGSIZE; + + /* set size after appending strings */ + unotif.common.len = size; + /* now the struct, at the start of user mem */ + if (copy_to_user(buf, &unotif, sizeof(unotif))) + return -EFAULT; + + return pos - buf; +} + +// return < 0 == error +// 0 == repeat +// > 0 == built notification successfully +static long build_mediation_unotif(struct aa_listener *listener, + struct aa_knotif *knotif, + void __user *buf, u16 max_size) +{ + long ret; + + switch (knotif->ad->class) { + case AA_CLASS_FILE: + ret = build_v3_unotif(knotif, buf, max_size); + if (ret < 0) { + AA_DEBUG(DEBUG_UPCALL, + "id %lld: (error=%ld) failed to copy data to user reading size %ld, maxsize %d", + knotif->id, ret, + sizeof(union apparmor_notif_all), max_size); + goto out; + } + break; + default: + AA_BUG("unknown notification class"); + AA_DEBUG(DEBUG_UPCALL, "id %lld: unknown notification class", knotif->id); + /* skip and move onto the next notification */ + return 0; + } +out: + return ret; +} + +/* Handle the listener reading a notification into userspace */ +// TODO: output multiple messages in one recv +long aa_listener_unotif_recv(struct aa_listener *listener, void __user *buf, + u16 max_size) +{ + struct aa_knotif *knotif; + long ret; + + do { + knotif = listener_pop_and_hold_knotif(listener); + if (!knotif) { + return -ENOENT; + } + AA_DEBUG(DEBUG_UPCALL, "id %lld: removed notif from listener queue", + knotif->id); + + ret = build_mediation_unotif(listener, knotif, buf, max_size); + if (ret < 0) { + /* failed - drop notif and return error to reader */ + listener_complete_held_user_pending(listener, knotif); + return ret; + } else if (ret > 0) { + /* else notification copied */ + break; + } + /* unknown notification: drop and try next */ + listener_complete_held_user_pending(listener, knotif); + } while (ret == 0); + + /* success */ + if (knotif->ad->type == AUDIT_APPARMOR_USER) { + AA_DEBUG(DEBUG_UPCALL, "id %lld: adding notif to pending", knotif->id); + listener_append_held_user_pending(listener, knotif); + } else { + /* no one waiting on this notification drop it */ + AA_DEBUG(DEBUG_UPCALL, "id %lld: non-prompt audit notif delivered", knotif->id); + listener_complete_held_user_pending(listener, knotif); + } + + return ret; +} diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 957654d253dd7..f503dcd3ac747 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -88,7 +88,11 @@ #include "include/resource.h" int unprivileged_userns_apparmor_policy = 1; +int aa_unprivileged_userns_restricted = IS_ENABLED(CONFIG_SECURITY_APPARMOR_RESTRICT_USERNS); +int aa_unprivileged_userns_restricted_force; +int aa_unprivileged_userns_restricted_complain; int aa_unprivileged_unconfined_restricted; +int aa_unprivileged_uring_restricted; const char *const aa_profile_mode_names[] = { "enforce", @@ -281,7 +285,7 @@ void aa_free_profile(struct aa_profile *profile) struct aa_ruleset *rule, *tmp; struct rhashtable *rht; - AA_DEBUG("%s(%p)\n", __func__, profile); + AA_DEBUG(DEBUG_POLICY, "%s(%p)\n", __func__, profile); if (!profile) return; @@ -295,6 +299,7 @@ void aa_free_profile(struct aa_profile *profile) kfree_sensitive(profile->disconnected); free_attachment(&profile->attach); + kfree_sensitive(profile->net_compat); /* * at this point there are no tasks that can have a reference @@ -316,6 +321,7 @@ void aa_free_profile(struct aa_profile *profile) kfree_sensitive(profile->hash); aa_put_loaddata(profile->rawdata); aa_label_destroy(&profile->label); + aa_audit_cache_destroy(&profile->learning_cache); kfree_sensitive(profile); } @@ -365,6 +371,9 @@ struct aa_profile *aa_alloc_profile(const char *hname, struct aa_proxy *proxy, profile->label.flags |= FLAG_PROFILE; profile->label.vec[0] = profile; + profile->signal = SIGKILL; + aa_audit_cache_init(&profile->learning_cache); + /* refcount released by caller */ return profile; @@ -374,6 +383,30 @@ struct aa_profile *aa_alloc_profile(const char *hname, struct aa_proxy *proxy, return NULL; } +/* set of rules that are mediated by unconfined */ +static int unconfined_mediates[] = { AA_CLASS_NS, AA_CLASS_IO_URING, 0 }; + +/* must be called after profile rulesets and start information is setup */ +void aa_compute_profile_mediates(struct aa_profile *profile) +{ + int c; + + if (profile_unconfined(profile)) { + int *pos; + + for (pos = unconfined_mediates; *pos; pos++) { + if (ANY_RULE_MEDIATES(&profile->rules, AA_CLASS_NS) != + DFA_NOMATCH) + profile->label.mediates |= ((u64) 1) << AA_CLASS_NS; + } + return; + } + for (c = 0; c <= AA_CLASS_LAST; c++) { + if (ANY_RULE_MEDIATES(&profile->rules, c) != DFA_NOMATCH) + profile->label.mediates |= ((u64) 1) << c; + } +} + /* TODO: profile accounting - setup in remove */ /** @@ -629,10 +662,12 @@ struct aa_profile *aa_alloc_null(struct aa_profile *parent, const char *name, rules = list_first_entry(&profile->rules, typeof(*rules), list); rules->file = aa_get_pdb(nullpdb); rules->policy = aa_get_pdb(nullpdb); + aa_compute_profile_mediates(profile); if (parent) { profile->path_flags = parent->path_flags; - + /* override/inherit what is mediated from parent */ + profile->label.mediates = parent->label.mediates; /* released on free_profile */ rcu_assign_pointer(profile->parent, aa_get_profile(parent)); profile->ns = aa_get_ns(parent->ns); @@ -838,8 +873,8 @@ bool aa_policy_admin_capable(const struct cred *subj_cred, bool capable = policy_ns_capable(subj_cred, label, user_ns, CAP_MAC_ADMIN) == 0; - AA_DEBUG("cap_mac_admin? %d\n", capable); - AA_DEBUG("policy locked? %d\n", aa_g_lock_policy); + AA_DEBUG(DEBUG_POLICY, "cap_mac_admin? %d\n", capable); + AA_DEBUG(DEBUG_POLICY, "policy locked? %d\n", aa_g_lock_policy); return aa_policy_view_capable(subj_cred, label, ns) && capable && !aa_g_lock_policy; @@ -1224,7 +1259,8 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label, list_del_init(&ent->list); op = (!ent->old && !ent->rename) ? OP_PROF_LOAD : OP_PROF_REPL; - if (ent->old && ent->old->rawdata == ent->new->rawdata && + if (ent->old && ent->old->learning_cache.size == 0 && + ent->old->rawdata == ent->new->rawdata && ent->new->rawdata) { /* dedup actual profile replacement */ audit_policy(label, op, ns_name, ent->new->base.hname, diff --git a/security/apparmor/policy_compat.c b/security/apparmor/policy_compat.c index 423227670e685..59e3cb57e979a 100644 --- a/security/apparmor/policy_compat.c +++ b/security/apparmor/policy_compat.c @@ -107,6 +107,8 @@ static void compute_fperms_allow(struct aa_perms *perms, struct aa_dfa *dfa, perms->allow |= AA_MAY_CHANGE_PROFILE; if (ACCEPT_TABLE(dfa)[state] & 0x40000000) perms->allow |= AA_MAY_ONEXEC; + if (ACCEPT_TABLE(dfa)[state] & 0x10000000) + perms->allow |= AA_CONT_MATCH; } static struct aa_perms compute_fperms_user(struct aa_dfa *dfa, @@ -216,6 +218,8 @@ static struct aa_perms compute_perms_entry(struct aa_dfa *dfa, perms.allow = dfa_user_allow(dfa, state); perms.audit = dfa_user_audit(dfa, state); perms.quiet = dfa_user_quiet(dfa, state); + if (ACCEPT_TABLE(dfa)[state] & 0x10000000) + perms.allow |= AA_CONT_MATCH; /* * This mapping is convulated due to history. @@ -286,10 +290,10 @@ static void remap_dfa_accept(struct aa_dfa *dfa, unsigned int factor) AA_BUG(!dfa); - for (state = 0; state < state_count; state++) + for (state = 0; state < state_count; state++) { ACCEPT_TABLE(dfa)[state] = state * factor; - kvfree(dfa->tables[YYTD_ID_ACCEPT2]); - dfa->tables[YYTD_ID_ACCEPT2] = NULL; + ACCEPT_TABLE2(dfa)[state] = factor > 1 ? ACCEPT_FLAG_OWNER : 0; + } } /* TODO: merge different dfa mappings into single map_policy fn */ diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c index 1f02cfe1d974d..9d923901ee808 100644 --- a/security/apparmor/policy_ns.c +++ b/security/apparmor/policy_ns.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "include/apparmor.h" #include "include/cred.h" @@ -107,7 +108,7 @@ static struct aa_ns *alloc_ns(const char *prefix, const char *name) struct aa_ns *ns; ns = kzalloc(sizeof(*ns), GFP_KERNEL); - AA_DEBUG("%s(%p)\n", __func__, ns); + AA_DEBUG(DEBUG_POLICY, "%s(%p)\n", __func__, ns); if (!ns) return NULL; if (!aa_policy_init(&ns->base, prefix, name, GFP_KERNEL)) @@ -117,6 +118,8 @@ static struct aa_ns *alloc_ns(const char *prefix, const char *name) INIT_LIST_HEAD(&ns->rawdata_list); mutex_init(&ns->lock); init_waitqueue_head(&ns->wait); + spin_lock_init(&ns->listener_lock); + INIT_LIST_HEAD(&ns->listeners); /* released by aa_free_ns() */ ns->unconfined = alloc_unconfined("unconfined"); diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 5e578ef0ddffb..44e69e06e0aa6 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -29,6 +29,7 @@ #include "include/policy.h" #include "include/policy_unpack.h" #include "include/policy_compat.h" +#include "include/signal.h" /* audit callback for unpack fields */ static void audit_cb(struct audit_buffer *ab, void *va) @@ -270,6 +271,19 @@ static bool unpack_u8(struct aa_ext *e, u8 *data, const char *name) return false; } +VISIBLE_IF_KUNIT bool unpack_u16(struct aa_ext *e, u16 *data, const char *name) +{ + if (aa_unpack_nameX(e, AA_U16, name)) { + if (!aa_inbounds(e, sizeof(u16))) + return 0; + if (data) + *data = le16_to_cpu(get_unaligned((__le16 *) e->pos)); + e->pos += sizeof(u16); + return 1; + } + return 0; +} + VISIBLE_IF_KUNIT bool aa_unpack_u32(struct aa_ext *e, u32 *data, const char *name) { void *pos = e->pos; @@ -713,6 +727,7 @@ static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy, void *pos = e->pos; int i, flags, error = -EPROTO; ssize_t size; + u32 version = 0; pdb = aa_alloc_pdb(GFP_KERNEL); if (!pdb) @@ -730,6 +745,9 @@ static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy, if (pdb->perms) { /* perms table present accept is index */ flags = TO_ACCEPT1_FLAG(YYTD_DATA32); + if (aa_unpack_u32(e, &version, "permsv") && version > 2) + /* accept2 used for dfa flags */ + flags |= TO_ACCEPT2_FLAG(YYTD_DATA32); } else { /* packed perms in accept1 and accept2 */ flags = TO_ACCEPT1_FLAG(YYTD_DATA32) | @@ -750,6 +768,19 @@ static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy, goto out; } + if (pdb->perms && version <= 2) { + /* add dfa flags table missing in v2 */ + u32 noents = pdb->dfa->tables[YYTD_ID_ACCEPT]->td_lolen; + u16 tdflags = pdb->dfa->tables[YYTD_ID_ACCEPT]->td_flags; + size_t tsize = table_size(noents, tdflags); + pdb->dfa->tables[YYTD_ID_ACCEPT2] = kvzalloc(tsize, GFP_KERNEL); + if (!pdb->dfa->tables[YYTD_ID_ACCEPT2]) { + *info = "failed to alloc dfa flags table"; + goto out; + } + pdb->dfa->tables[YYTD_ID_ACCEPT2]->td_lolen = noents; + pdb->dfa->tables[YYTD_ID_ACCEPT2]->td_flags = tdflags; + } /* * only unpack the following if a dfa is present * @@ -812,6 +843,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) struct aa_profile *profile = NULL; const char *tmpname, *tmpns = NULL, *name = NULL; const char *info = "failed to unpack profile"; + u16 size = 0; size_t ns_len; struct rhashtable_params params = { 0 }; char *key = NULL, *disconnected = NULL; @@ -887,6 +919,12 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) (void) aa_unpack_strdup(e, &disconnected, "disconnected"); profile->disconnected = disconnected; + /* optional */ + (void) aa_unpack_u32(e, &profile->signal, "kill"); + if (profile->signal < 1 && profile->signal > MAXMAPPED_SIG) { + info = "profile kill.signal invalid value"; + goto fail; + } /* per profile debug flags (complain, audit) */ if (!aa_unpack_nameX(e, AA_STRUCT, "flags")) { info = "profile missing flags"; @@ -901,6 +939,8 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) profile->label.flags |= FLAG_DEBUG1; if (tmp & PACKED_FLAG_DEBUG2) profile->label.flags |= FLAG_DEBUG2; + if (tmp & PACKED_FLAG_INTERRUPTIBLE) + profile->label.flags |= FLAG_INTERRUPTIBLE; if (!aa_unpack_u32(e, &tmp, NULL)) goto fail; if (tmp == PACKED_MODE_COMPLAIN || (e->version & FORCE_COMPLAIN_FLAG)) { @@ -984,6 +1024,45 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) goto fail; } + if (aa_unpack_array(e, "net_allowed_af", &size) || + VERSION_LT(e->version, v8)) { + u16 i; + + profile->net_compat = kzalloc(sizeof(struct aa_net_compat), + GFP_KERNEL); + if (!profile->net_compat) { + info = "out of memory"; + goto fail; + } + for (i = 0; i < size; i++) { + /* discard extraneous rules that this kernel will + * never request + */ + if (i >= AF_MAX) { + u16 tmp; + + if (!unpack_u16(e, &tmp, NULL) || + !unpack_u16(e, &tmp, NULL) || + !unpack_u16(e, &tmp, NULL)) + goto fail; + continue; + } + if (!unpack_u16(e, &profile->net_compat->allow[i], NULL)) + goto fail; + if (!unpack_u16(e, &profile->net_compat->audit[i], NULL)) + goto fail; + if (!unpack_u16(e, &profile->net_compat->quiet[i], NULL)) + goto fail; + } + if (size && !aa_unpack_nameX(e, AA_ARRAYEND, NULL)) + goto fail; + if (VERSION_LT(e->version, v7)) { + /* pre v7 policy always allowed these */ + profile->net_compat->allow[AF_UNIX] = 0xffff; + profile->net_compat->allow[AF_NETLINK] = 0xffff; + } + } + if (aa_unpack_nameX(e, AA_STRUCT, "policydb")) { /* generic policy dfa - optional and may be NULL */ info = "failed to unpack policydb"; @@ -1089,6 +1168,8 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) goto fail; } + aa_compute_profile_mediates(profile); + return profile; fail: diff --git a/security/apparmor/procattr.c b/security/apparmor/procattr.c index e3857e3d7c6c2..ce40f15d4952d 100644 --- a/security/apparmor/procattr.c +++ b/security/apparmor/procattr.c @@ -125,12 +125,14 @@ int aa_setprocattr_changehat(char *args, size_t size, int flags) for (count = 0; (hat < end) && count < 16; ++count) { char *next = hat + strlen(hat) + 1; hats[count] = hat; - AA_DEBUG("%s: (pid %d) Magic 0x%llx count %d hat '%s'\n" + AA_DEBUG(DEBUG_DOMAIN, + "%s: (pid %d) Magic 0x%llx count %d hat '%s'\n" , __func__, current->pid, token, count, hat); hat = next; } } else - AA_DEBUG("%s: (pid %d) Magic 0x%llx count %d Hat '%s'\n", + AA_DEBUG(DEBUG_DOMAIN, + "%s: (pid %d) Magic 0x%llx count %d Hat '%s'\n", __func__, current->pid, token, count, ""); return aa_change_hat(hats, count, token, flags); diff --git a/security/apparmor/secid.c b/security/apparmor/secid.c index 83d3d1e6d9dcb..6b360d1247c27 100644 --- a/security/apparmor/secid.c +++ b/security/apparmor/secid.c @@ -61,14 +61,44 @@ struct aa_label *aa_secid_to_label(u32 secid) return xa_load(&aa_secids, secid); } -int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +int apparmor_secid_to_secctx(u32 secid, struct lsmcontext *cp) { /* TODO: cache secctx and ref count so we don't have to recreate */ struct aa_label *label = aa_secid_to_label(secid); int flags = FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED | FLAG_ABS_ROOT; int len; - AA_BUG(!seclen); + if (!label) + return -EINVAL; + + if (apparmor_display_secid_mode) + flags |= FLAG_SHOW_MODE; + + if (cp) + len = aa_label_asxprint(&cp->context, root_ns, label, + flags, GFP_ATOMIC); + else + len = aa_label_snxprint(NULL, 0, root_ns, label, flags); + + if (len < 0) + return -ENOMEM; + + if (cp) { + cp->len = len; + cp->id = LSM_ID_APPARMOR; + } + + return len; +} + +int apparmor_lsmblob_to_secctx(struct lsmblob *blob, struct lsmcontext *cp) +{ + /* TODO: cache secctx and ref count so we don't have to recreate */ + struct aa_label *label; + int flags = FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED | FLAG_ABS_ROOT; + int len; + + label = blob->apparmor.label; if (!label) return -EINVAL; @@ -76,8 +106,8 @@ int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) if (apparmor_display_secid_mode) flags |= FLAG_SHOW_MODE; - if (secdata) - len = aa_label_asxprint(secdata, root_ns, label, + if (cp) + len = aa_label_asxprint(&cp->context, root_ns, label, flags, GFP_ATOMIC); else len = aa_label_snxprint(NULL, 0, root_ns, label, flags); @@ -85,9 +115,12 @@ int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) if (len < 0) return -ENOMEM; - *seclen = len; + if (cp) { + cp->len = len; + cp->id = LSM_ID_APPARMOR; + } - return 0; + return len; } int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) @@ -103,9 +136,10 @@ int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) return 0; } -void apparmor_release_secctx(char *secdata, u32 seclen) +void apparmor_release_secctx(struct lsmcontext *cp) { - kfree(secdata); + if (cp->id == LSM_ID_APPARMOR) + kfree(cp->context); } /** diff --git a/security/apparmor/task.c b/security/apparmor/task.c index c87fb9f4ac18a..56f7d7686c14d 100644 --- a/security/apparmor/task.c +++ b/security/apparmor/task.c @@ -245,8 +245,8 @@ static int profile_tracee_perm(const struct cred *cred, struct aa_label *tracer, u32 request, struct apparmor_audit_data *ad) { - if (profile_unconfined(tracee) || unconfined(tracer) || - !ANY_RULE_MEDIATES(&tracee->rules, AA_CLASS_PTRACE)) + if (!profile_mediates(tracee, AA_CLASS_PTRACE) || + !label_mediates(tracer, AA_CLASS_PTRACE)) return 0; return profile_ptrace_perm(cred, tracee, tracer, request, ad); @@ -257,14 +257,11 @@ static int profile_tracer_perm(const struct cred *cred, struct aa_label *tracee, u32 request, struct apparmor_audit_data *ad) { - if (profile_unconfined(tracer)) - return 0; - - if (ANY_RULE_MEDIATES(&tracer->rules, AA_CLASS_PTRACE)) + if (profile_mediates(tracer, AA_CLASS_PTRACE)) return profile_ptrace_perm(cred, tracer, tracee, request, ad); /* profile uses the old style capability check for ptrace */ - if (&tracer->label == tracee) + if (&tracer->label == tracee || !profile_mediates(tracer, AA_CLASS_CAP)) return 0; ad->subj_label = &tracer->label; @@ -311,33 +308,171 @@ static void audit_ns_cb(struct audit_buffer *ab, void *va) if (ad->denied & AA_USERNS_CREATE) audit_log_format(ab, " denied=\"userns_create\""); + + if (ad->peer) { + audit_log_format(ab, " target="); + aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, + FLAG_VIEW_SUBNS, GFP_KERNEL); + } else if (ad->ns.target) { + audit_log_format(ab, " target="); + audit_log_untrustedstring(ab, ad->ns.target); + } + } -int aa_profile_ns_perm(struct aa_profile *profile, - struct apparmor_audit_data *ad, - u32 request) +/* + * Returns: refcounted label to change to, even if no change + * PTR_ERR on failure + */ +static struct aa_label *ns_x_to_label(struct aa_profile *profile, + u32 xindex, const char **lookupname, + const char **info) { + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_label *new = NULL; + u32 xtype = xindex & AA_X_TYPE_MASK; + struct aa_label *stack = NULL; + + /* must be none or table */ + switch (xtype) { + case AA_X_NONE: + /* default not failure */ + *lookupname = NULL; + return NULL; + break; + case AA_X_TABLE: + /* TODO: fix when perm mapping done at unload */ + /* released by caller + * if null for both stack and direct want to try fallback + */ + new = x_table_lookup(profile, xindex, lookupname); + if (!new) { + *info = "failed to find transition profile"; + return ERR_PTR(-ENOMEM); + } + if (**lookupname == '&') { + stack = new; + new = NULL; + } + break; + default: + *info = "invalid profile transition type"; + return ERR_PTR(-EINVAL); + break; + } + + /* stack is true if !new */ + if (!new) { + if (xindex & AA_X_UNCONFINED) { + new = aa_get_newest_label(ns_unconfined(profile->ns)); + *info = "ux fallback"; + } else { + if (xindex & AA_X_INHERIT) { + /* (p|c|n)ix - don't change profile but do + * use the newest version + */ + *info = "ix fallback"; + /* no profile && no error */ + } /* else, stack is implicitly against current */ + new = aa_get_newest_label(&profile->label); + } + } + + if (stack) { + /* base the stack on post domain transition */ + struct aa_label *base = new; + + new = aa_label_merge(base, stack, GFP_KERNEL); + /* null on error */ + aa_put_label(base); + aa_put_label(stack); + if (!new) + return ERR_PTR(-ENOMEM); + } + + /* released by caller */ + return new; +} + +struct aa_label *aa_profile_ns_perm(struct aa_profile *profile, + struct apparmor_audit_data *ad, + u32 request) +{ + struct aa_ruleset *rules = list_first_entry(&profile->rules, + typeof(*rules), list); + struct aa_label *new; struct aa_perms perms = { }; - int error = 0; + aa_state_t state; ad->subj_label = &profile->label; ad->request = request; + int error; - if (!profile_unconfined(profile)) { - struct aa_ruleset *rules = list_first_entry(&profile->rules, - typeof(*rules), - list); - aa_state_t state; - - state = RULE_MEDIATES(rules, ad->class); - if (!state) - /* TODO: add flag to complain about unmediated */ - return 0; - perms = *aa_lookup_perms(rules->policy, state); - aa_apply_modes_to_perms(profile, &perms); - error = aa_check_perms(profile, &perms, request, ad, - audit_ns_cb); + /* TODO: rework unconfined profile/dfa to mediate user ns, then + * we can drop the unconfined test + */ + state = RULE_MEDIATES(rules, ad->class); + if (!state) { + /* TODO: this gets replaced when the default unconfined + * profile dfa gets updated to handle this + */ + if (profile_unconfined(profile) && + profile == profiles_ns(profile)->unconfined) { + if (!aa_unprivileged_userns_restricted || + ns_capable_noaudit(current_user_ns(), + CAP_SYS_ADMIN)) + return aa_get_newest_label(&profile->label); + ad->info = "User namespace creation restricted"; + /* unconfined unprivileged user */ + /* don't just return: allow complain mode to override */ +// hardcode unconfined transition for now + new = aa_label_parse(&profile->label, + "unprivileged_userns", GFP_KERNEL, + true, false); + if (IS_ERR(new)) { + ad->info = "Userns create restricted - failed to find unprivileged_userns profile"; + ad->error = PTR_ERR(new); + ad->ns.target = "unprivileged_userns"; + new = NULL; + perms.deny |= request; + goto hard_coded; + } + ad->info = "Userns create - transitioning profile"; + perms.audit = request; + perms.allow = request; + goto hard_coded; +// once we have special unconfined profile, jump to ns_x_to_label() +// end hardcode + } else if (!aa_unprivileged_userns_restricted_force) { + return aa_get_newest_label(&profile->label); + } + /* continue to mediation */ + } + + perms = *aa_lookup_perms(rules->policy, state); + new = ns_x_to_label(profile, perms.xindex, &ad->ns.target, &ad->info); + if (IS_ERR(new)) { + ad->error = PTR_ERR(new); + new = NULL; + perms.deny |= request; + } else if (!new) { + /* no transition - not done in x_to_label so we can track */ + new = aa_get_label(&profile->label); + } else { +hard_coded: + ad->peer = new; } + if (aa_unprivileged_userns_restricted_complain) + perms.complain = ALL_PERMS_MASK; + // TODO: nnp + // TODO: complain mode support for transitions - return error; + aa_apply_modes_to_perms(profile, &perms); + error = aa_check_perms(profile, &perms, request, ad, audit_ns_cb); + if (error) { + aa_put_label(new); + return ERR_PTR(error); + } + return new; } diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c index 57b9ffd53c98a..2da40774dd203 100644 --- a/security/bpf/hooks.c +++ b/security/bpf/hooks.c @@ -19,6 +19,7 @@ static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = { static const struct lsm_id bpf_lsmid = { .name = "bpf", .id = LSM_ID_BPF, + .lsmblob = true, }; static int __init bpf_lsm_init(void) diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 45c3e5dda355e..0956197004ea9 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -201,7 +201,7 @@ int __init integrity_load_x509(const unsigned int id, const char *path) rc = kernel_read_file_from_path(path, 0, &data, INT_MAX, NULL, READING_X509_CERTIFICATE); if (rc < 0) { - pr_err("Unable to open file: %s (%d)", path, rc); + pr_warn("Unable to open file: %s (%d)", path, rc); return rc; } size = rc; diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index c29db699c996e..53f794b75bf90 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -256,7 +256,7 @@ static inline void ima_process_queued_keys(void) {} /* LIM API function definitions */ int ima_get_action(struct mnt_idmap *idmap, struct inode *inode, - const struct cred *cred, u32 secid, int mask, + const struct cred *cred, struct lsmblob *blob, int mask, enum ima_hooks func, int *pcr, struct ima_template_desc **template_desc, const char *func_data, unsigned int *allowed_algos); @@ -287,8 +287,8 @@ const char *ima_d_path(const struct path *path, char **pathbuf, char *filename); /* IMA policy related functions */ int ima_match_policy(struct mnt_idmap *idmap, struct inode *inode, - const struct cred *cred, u32 secid, enum ima_hooks func, - int mask, int flags, int *pcr, + const struct cred *cred, struct lsmblob *blob, + enum ima_hooks func, int mask, int flags, int *pcr, struct ima_template_desc **template_desc, const char *func_data, unsigned int *allowed_algos); void ima_init_policy(void); @@ -420,32 +420,6 @@ static inline void ima_free_modsig(struct modsig *modsig) } #endif /* CONFIG_IMA_APPRAISE_MODSIG */ -/* LSM based policy rules require audit */ -#ifdef CONFIG_IMA_LSM_RULES - -#define ima_filter_rule_init security_audit_rule_init -#define ima_filter_rule_free security_audit_rule_free -#define ima_filter_rule_match security_audit_rule_match - -#else - -static inline int ima_filter_rule_init(u32 field, u32 op, char *rulestr, - void **lsmrule) -{ - return -EINVAL; -} - -static inline void ima_filter_rule_free(void *lsmrule) -{ -} - -static inline int ima_filter_rule_match(u32 secid, u32 field, u32 op, - void *lsmrule) -{ - return -EINVAL; -} -#endif /* CONFIG_IMA_LSM_RULES */ - #ifdef CONFIG_IMA_READ_POLICY #define POLICY_FILE_FLAGS (S_IWUSR | S_IRUSR) #else diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index 597ea0c4d72f7..af894d1e4d853 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -165,7 +165,7 @@ void ima_add_violation(struct file *file, const unsigned char *filename, * @idmap: idmap of the mount the inode was found from * @inode: pointer to the inode associated with the object being validated * @cred: pointer to credentials structure to validate - * @secid: secid of the task being validated + * @blob: secid(s) of the task being validated * @mask: contains the permission mask (MAY_READ, MAY_WRITE, MAY_EXEC, * MAY_APPEND) * @func: caller identifier @@ -187,7 +187,7 @@ void ima_add_violation(struct file *file, const unsigned char *filename, * */ int ima_get_action(struct mnt_idmap *idmap, struct inode *inode, - const struct cred *cred, u32 secid, int mask, + const struct cred *cred, struct lsmblob *blob, int mask, enum ima_hooks func, int *pcr, struct ima_template_desc **template_desc, const char *func_data, unsigned int *allowed_algos) @@ -196,7 +196,7 @@ int ima_get_action(struct mnt_idmap *idmap, struct inode *inode, flags &= ima_policy_flag; - return ima_match_policy(idmap, inode, cred, secid, func, mask, + return ima_match_policy(idmap, inode, cred, blob, func, mask, flags, pcr, template_desc, func_data, allowed_algos); } @@ -244,8 +244,8 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, const char *audit_cause = "failed"; struct inode *inode = file_inode(file); struct inode *real_inode = d_real_inode(file_dentry(file)); - const char *filename = file->f_path.dentry->d_name.name; struct ima_max_digest_data hash; + struct name_snapshot filename; struct kstat stat; int result = 0; int length; @@ -316,9 +316,13 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, if (file->f_flags & O_DIRECT) audit_cause = "failed(directio)"; + take_dentry_name_snapshot(&filename, file->f_path.dentry); + integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, - filename, "collect_data", audit_cause, - result, 0); + filename.name.name, "collect_data", + audit_cause, result, 0); + + release_dentry_name_snapshot(&filename); } return result; } @@ -431,6 +435,7 @@ void ima_audit_measurement(struct integrity_iint_cache *iint, */ const char *ima_d_path(const struct path *path, char **pathbuf, char *namebuf) { + struct name_snapshot filename; char *pathname = NULL; *pathbuf = __getname(); @@ -444,7 +449,10 @@ const char *ima_d_path(const struct path *path, char **pathbuf, char *namebuf) } if (!pathname) { - strscpy(namebuf, path->dentry->d_name.name, NAME_MAX); + take_dentry_name_snapshot(&filename, path->dentry); + strscpy(namebuf, filename.name.name, NAME_MAX); + release_dentry_name_snapshot(&filename); + pathname = namebuf; } diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 870dde67707b1..41cf92d159729 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -73,13 +73,13 @@ bool is_ima_appraise_enabled(void) int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func) { - u32 secid; + struct lsmblob blob; if (!ima_appraise) return 0; - security_current_getsecid_subj(&secid); - return ima_match_policy(idmap, inode, current_cred(), secid, + security_current_getlsmblob_subj(&blob); + return ima_match_policy(idmap, inode, current_cred(), &blob, func, mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL, NULL); } diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index cd1683dad3bf0..e2aee95532460 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -287,7 +287,7 @@ static ssize_t ima_read_policy(char *path) rc = kernel_read_file_from_path(path, 0, &data, INT_MAX, NULL, READING_POLICY); if (rc < 0) { - pr_err("Unable to open file: %s (%d)", path, rc); + pr_warn("Unable to open file: %s (%d)", path, rc); return rc; } size = rc; diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index cc1217ac2c6fa..c69eb9665cc15 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -205,8 +205,8 @@ void ima_file_free(struct file *file) } static int process_measurement(struct file *file, const struct cred *cred, - u32 secid, char *buf, loff_t size, int mask, - enum ima_hooks func) + struct lsmblob *blob, char *buf, loff_t size, + int mask, enum ima_hooks func) { struct inode *backing_inode, *inode = file_inode(file); struct integrity_iint_cache *iint = NULL; @@ -230,7 +230,7 @@ static int process_measurement(struct file *file, const struct cred *cred, * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ - action = ima_get_action(file_mnt_idmap(file), inode, cred, secid, + action = ima_get_action(file_mnt_idmap(file), inode, cred, blob, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || @@ -430,23 +430,23 @@ static int process_measurement(struct file *file, const struct cred *cred, int ima_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { - u32 secid; + struct lsmblob blob; int ret; if (!file) return 0; - security_current_getsecid_subj(&secid); + security_current_getlsmblob_subj(&blob); if (reqprot & PROT_EXEC) { - ret = process_measurement(file, current_cred(), secid, NULL, + ret = process_measurement(file, current_cred(), &blob, NULL, 0, MAY_EXEC, MMAP_CHECK_REQPROT); if (ret) return ret; } if (prot & PROT_EXEC) - return process_measurement(file, current_cred(), secid, NULL, + return process_measurement(file, current_cred(), &blob, NULL, 0, MAY_EXEC, MMAP_CHECK); return 0; @@ -473,9 +473,9 @@ int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot) char *pathbuf = NULL; const char *pathname = NULL; struct inode *inode; + struct lsmblob blob; int result = 0; int action; - u32 secid; int pcr; /* Is mprotect making an mmap'ed file executable? */ @@ -483,13 +483,13 @@ int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot) !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; - security_current_getsecid_subj(&secid); + security_current_getlsmblob_subj(&blob); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, - current_cred(), secid, MAY_EXEC, MMAP_CHECK, + current_cred(), &blob, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode, - current_cred(), secid, MAY_EXEC, + current_cred(), &blob, MAY_EXEC, MMAP_CHECK_REQPROT, &pcr, &template, NULL, NULL); @@ -526,16 +526,16 @@ int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot) int ima_bprm_check(struct linux_binprm *bprm) { int ret; - u32 secid; + struct lsmblob blob; - security_current_getsecid_subj(&secid); - ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0, - MAY_EXEC, BPRM_CHECK); + security_current_getlsmblob_subj(&blob); + ret = process_measurement(bprm->file, current_cred(), + &blob, NULL, 0, MAY_EXEC, BPRM_CHECK); if (ret) return ret; - security_cred_getsecid(bprm->cred, &secid); - return process_measurement(bprm->file, bprm->cred, secid, NULL, 0, + security_cred_getlsmblob(bprm->cred, &blob); + return process_measurement(bprm->file, bprm->cred, &blob, NULL, 0, MAY_EXEC, CREDS_CHECK); } @@ -551,10 +551,10 @@ int ima_bprm_check(struct linux_binprm *bprm) */ int ima_file_check(struct file *file, int mask) { - u32 secid; + struct lsmblob blob; - security_current_getsecid_subj(&secid); - return process_measurement(file, current_cred(), secid, NULL, 0, + security_current_getlsmblob_subj(&blob); + return process_measurement(file, current_cred(), &blob, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); } @@ -755,7 +755,7 @@ int ima_read_file(struct file *file, enum kernel_read_file_id read_id, bool contents) { enum ima_hooks func; - u32 secid; + struct lsmblob blob; /* * Do devices using pre-allocated memory run the risk of the @@ -775,9 +775,9 @@ int ima_read_file(struct file *file, enum kernel_read_file_id read_id, /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; - security_current_getsecid_subj(&secid); - return process_measurement(file, current_cred(), secid, NULL, - 0, MAY_READ, func); + security_current_getlsmblob_subj(&blob); + return process_measurement(file, current_cred(), &blob, NULL, 0, + MAY_READ, func); } const int read_idmap[READING_MAX_ID] = { @@ -805,7 +805,7 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id read_id) { enum ima_hooks func; - u32 secid; + struct lsmblob blob; /* permit signed certs */ if (!file && read_id == READING_X509_CERTIFICATE) @@ -818,8 +818,8 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, } func = read_idmap[read_id] ?: FILE_CHECK; - security_current_getsecid_subj(&secid); - return process_measurement(file, current_cred(), secid, buf, size, + security_current_getlsmblob_subj(&blob); + return process_measurement(file, current_cred(), &blob, buf, size, MAY_READ, func); } @@ -945,7 +945,7 @@ int process_buffer_measurement(struct mnt_idmap *idmap, int digest_hash_len = hash_digest_size[ima_hash_algo]; int violation = 0; int action = 0; - u32 secid; + struct lsmblob blob; if (digest && digest_len < digest_hash_len) return -EINVAL; @@ -968,9 +968,9 @@ int process_buffer_measurement(struct mnt_idmap *idmap, * buffer measurements. */ if (func) { - security_current_getsecid_subj(&secid); + security_current_getlsmblob_subj(&blob); action = ima_get_action(idmap, inode, current_cred(), - secid, 0, func, &pcr, &template, + &blob, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) return -ENOENT; diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index f690626177546..71de4cb5bbaa8 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -117,6 +117,8 @@ struct ima_rule_entry { void *rule; /* LSM file metadata specific */ char *args_p; /* audit value */ int type; /* audit type */ + int lsm_id; /* which LSM rule applies to */ + bool lsm_specific; /* true if lsm is specified */ } lsm[MAX_LSM_RULES]; char *fsname; struct ima_rule_opt_list *keyrings; /* Measure keys added to these keyrings */ @@ -309,6 +311,25 @@ static int __init default_appraise_policy_setup(char *str) } __setup("ima_appraise_tcb", default_appraise_policy_setup); +static int default_rules_lsm __ro_after_init = LSM_ID_UNDEF; + +static int __init ima_rules_lsm_init(char *str) +{ + int newdrl; + + newdrl = lsm_name_to_id(str); + if (newdrl >= 0) { + default_rules_lsm = newdrl; + return 1; + } + + pr_err("default ima rule lsm \"%s\" not registered, value unchanged.", + str); + + return 1; +} +__setup("ima_rules_lsm=", ima_rules_lsm_init); + static struct ima_rule_opt_list *ima_alloc_rule_opt_list(const substring_t *src) { struct ima_rule_opt_list *opt_list; @@ -380,7 +401,8 @@ static void ima_lsm_free_rule(struct ima_rule_entry *entry) int i; for (i = 0; i < MAX_LSM_RULES; i++) { - ima_filter_rule_free(entry->lsm[i].rule); + ima_filter_rule_free(entry->lsm[i].rule, + entry->lsm[i].lsm_id); kfree(entry->lsm[i].args_p); } } @@ -401,7 +423,8 @@ static void ima_free_rule(struct ima_rule_entry *entry) kfree(entry); } -static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) +static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry, + gfp_t gfp) { struct ima_rule_entry *nentry; int i; @@ -410,7 +433,7 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) * Immutable elements are copied over as pointers and data; only * lsm rules can change */ - nentry = kmemdup(entry, sizeof(*nentry), GFP_KERNEL); + nentry = kmemdup(entry, sizeof(*nentry), gfp); if (!nentry) return NULL; @@ -425,7 +448,9 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) ima_filter_rule_init(nentry->lsm[i].type, Audit_equal, nentry->lsm[i].args_p, - &nentry->lsm[i].rule); + &nentry->lsm[i].rule, + entry->lsm[i].lsm_id, + gfp); if (!nentry->lsm[i].rule) pr_warn("rule for LSM \'%s\' is undefined\n", nentry->lsm[i].args_p); @@ -438,7 +463,7 @@ static int ima_lsm_update_rule(struct ima_rule_entry *entry) int i; struct ima_rule_entry *nentry; - nentry = ima_lsm_copy_rule(entry); + nentry = ima_lsm_copy_rule(entry, GFP_KERNEL); if (!nentry) return -ENOMEM; @@ -451,7 +476,8 @@ static int ima_lsm_update_rule(struct ima_rule_entry *entry) * be owned by nentry. */ for (i = 0; i < MAX_LSM_RULES; i++) - ima_filter_rule_free(entry->lsm[i].rule); + ima_filter_rule_free(entry->lsm[i].rule, + entry->lsm[i].lsm_id); kfree(entry); return 0; @@ -555,7 +581,7 @@ static bool ima_match_rule_data(struct ima_rule_entry *rule, * @idmap: idmap of the mount the inode was found from * @inode: a pointer to an inode * @cred: a pointer to a credentials structure for user validation - * @secid: the secid of the task to be validated + * @blob: the secid(s) of the task to be validated * @func: LIM hook identifier * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC) * @func_data: func specific data, may be NULL @@ -565,7 +591,7 @@ static bool ima_match_rule_data(struct ima_rule_entry *rule, static bool ima_match_rules(struct ima_rule_entry *rule, struct mnt_idmap *idmap, struct inode *inode, const struct cred *cred, - u32 secid, enum ima_hooks func, int mask, + struct lsmblob *blob, enum ima_hooks func, int mask, const char *func_data) { int i; @@ -633,7 +659,7 @@ static bool ima_match_rules(struct ima_rule_entry *rule, return false; for (i = 0; i < MAX_LSM_RULES; i++) { int rc = 0; - u32 osid; + struct lsmblob blob = { }; if (!lsm_rule->lsm[i].rule) { if (!lsm_rule->lsm[i].args_p) @@ -647,24 +673,26 @@ static bool ima_match_rules(struct ima_rule_entry *rule, case LSM_OBJ_USER: case LSM_OBJ_ROLE: case LSM_OBJ_TYPE: - security_inode_getsecid(inode, &osid); - rc = ima_filter_rule_match(osid, lsm_rule->lsm[i].type, + security_inode_getlsmblob(inode, &blob); + rc = ima_filter_rule_match(&blob, lsm_rule->lsm[i].type, Audit_equal, - lsm_rule->lsm[i].rule); + lsm_rule->lsm[i].rule, + lsm_rule->lsm[i].lsm_id); break; case LSM_SUBJ_USER: case LSM_SUBJ_ROLE: case LSM_SUBJ_TYPE: - rc = ima_filter_rule_match(secid, lsm_rule->lsm[i].type, + rc = ima_filter_rule_match(&blob, lsm_rule->lsm[i].type, Audit_equal, - lsm_rule->lsm[i].rule); + lsm_rule->lsm[i].rule, + lsm_rule->lsm[i].lsm_id); break; default: break; } if (rc == -ESTALE && !rule_reinitialized) { - lsm_rule = ima_lsm_copy_rule(rule); + lsm_rule = ima_lsm_copy_rule(rule, GFP_ATOMIC); if (lsm_rule) { rule_reinitialized = true; goto retry; @@ -680,7 +708,8 @@ static bool ima_match_rules(struct ima_rule_entry *rule, out: if (rule_reinitialized) { for (i = 0; i < MAX_LSM_RULES; i++) - ima_filter_rule_free(lsm_rule->lsm[i].rule); + ima_filter_rule_free(lsm_rule->lsm[i].rule, + lsm_rule->lsm[i].lsm_id); kfree(lsm_rule); } return result; @@ -718,7 +747,7 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func) * @inode: pointer to an inode for which the policy decision is being made * @cred: pointer to a credentials structure for which the policy decision is * being made - * @secid: LSM secid of the task to be validated + * @blob: LSM secid(s) of the task to be validated * @func: IMA hook identifier * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC) * @flags: IMA actions to consider (e.g. IMA_MEASURE | IMA_APPRAISE) @@ -735,8 +764,8 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func) * than writes so ima_match_policy() is classical RCU candidate. */ int ima_match_policy(struct mnt_idmap *idmap, struct inode *inode, - const struct cred *cred, u32 secid, enum ima_hooks func, - int mask, int flags, int *pcr, + const struct cred *cred, struct lsmblob *blob, + enum ima_hooks func, int mask, int flags, int *pcr, struct ima_template_desc **template_desc, const char *func_data, unsigned int *allowed_algos) { @@ -754,7 +783,7 @@ int ima_match_policy(struct mnt_idmap *idmap, struct inode *inode, if (!(entry->action & actmask)) continue; - if (!ima_match_rules(entry, idmap, inode, cred, secid, + if (!ima_match_rules(entry, idmap, inode, cred, blob, func, mask, func_data)) continue; @@ -1073,7 +1102,7 @@ enum policy_opt { Opt_digest_type, Opt_appraise_type, Opt_appraise_flag, Opt_appraise_algos, Opt_permit_directio, Opt_pcr, Opt_template, Opt_keyrings, - Opt_label, Opt_err + Opt_lsm, Opt_label, Opt_err }; static const match_table_t policy_tokens = { @@ -1121,6 +1150,7 @@ static const match_table_t policy_tokens = { {Opt_pcr, "pcr=%s"}, {Opt_template, "template=%s"}, {Opt_keyrings, "keyrings=%s"}, + {Opt_lsm, "lsm=%s"}, {Opt_label, "label=%s"}, {Opt_err, NULL} }; @@ -1140,7 +1170,9 @@ static int ima_lsm_rule_init(struct ima_rule_entry *entry, entry->lsm[lsm_rule].type = audit_type; result = ima_filter_rule_init(entry->lsm[lsm_rule].type, Audit_equal, entry->lsm[lsm_rule].args_p, - &entry->lsm[lsm_rule].rule); + &entry->lsm[lsm_rule].rule, + entry->lsm[lsm_rule].lsm_id, + GFP_KERNEL); if (!entry->lsm[lsm_rule].rule) { pr_warn("rule for LSM \'%s\' is undefined\n", entry->lsm[lsm_rule].args_p); @@ -1878,6 +1910,23 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry) &(template_desc->num_fields)); entry->template = template_desc; break; + case Opt_lsm: { + int i; + + result = lsm_name_to_id(args[0].from); + if (result < 0) { + for (i = 0; i < MAX_LSM_RULES; i++) + entry->lsm[i].args_p = NULL; + result = -EINVAL; + break; + } + for (i = 0; i < MAX_LSM_RULES; i++) { + entry->lsm[i].lsm_id = result; + entry->lsm[i].lsm_specific = true; + } + result = 0; + break; + } case Opt_err: ima_log_string(ab, "UNKNOWN", p); result = -EINVAL; @@ -1923,6 +1972,7 @@ ssize_t ima_parse_add_rule(char *rule) struct ima_rule_entry *entry; ssize_t result, len; int audit_info = 0; + int i; p = strsep(&rule, "\n"); len = strlen(p) + 1; @@ -1940,6 +1990,11 @@ ssize_t ima_parse_add_rule(char *rule) INIT_LIST_HEAD(&entry->list); + for (i = 0; i < MAX_LSM_RULES; i++) { + entry->lsm[i].lsm_id = default_rules_lsm; + entry->lsm[i].lsm_specific = false; + } + result = ima_parse_rule(p, entry); if (result) { ima_free_rule(entry); @@ -2251,6 +2306,9 @@ int ima_policy_show(struct seq_file *m, void *v) entry->lsm[i].args_p); break; } + if (entry->lsm[i].lsm_specific) + seq_printf(m, pt(Opt_lsm), + lsm_id_to_name(entry->lsm[i].lsm_id)); seq_puts(m, " "); } } diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 6cd0add524cdc..3b2cb8f1002e6 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -483,7 +483,10 @@ static int ima_eventname_init_common(struct ima_event_data *event_data, bool size_limit) { const char *cur_filename = NULL; + struct name_snapshot filename; u32 cur_filename_len = 0; + bool snapshot = false; + int ret; BUG_ON(event_data->filename == NULL && event_data->file == NULL); @@ -496,7 +499,10 @@ static int ima_eventname_init_common(struct ima_event_data *event_data, } if (event_data->file) { - cur_filename = event_data->file->f_path.dentry->d_name.name; + take_dentry_name_snapshot(&filename, + event_data->file->f_path.dentry); + snapshot = true; + cur_filename = filename.name.name; cur_filename_len = strlen(cur_filename); } else /* @@ -505,8 +511,13 @@ static int ima_eventname_init_common(struct ima_event_data *event_data, */ cur_filename_len = IMA_EVENT_NAME_LEN_MAX; out: - return ima_write_template_field_data(cur_filename, cur_filename_len, - DATA_FMT_STRING, field_data); + ret = ima_write_template_field_data(cur_filename, cur_filename_len, + DATA_FMT_STRING, field_data); + + if (snapshot) + release_dentry_name_snapshot(&filename); + + return ret; } /* diff --git a/security/integrity/platform_certs/keyring_handler.c b/security/integrity/platform_certs/keyring_handler.c index 13ea172079029..327c20154f0f4 100644 --- a/security/integrity/platform_certs/keyring_handler.c +++ b/security/integrity/platform_certs/keyring_handler.c @@ -40,6 +40,7 @@ static __init void uefi_blacklist_binary(const char *source, static __init void uefi_revocation_list_x509(const char *source, const void *data, size_t len) { + pr_info("Revoking X.509 certificate: %s\n", source); add_key_to_revocation_list(data, len); } diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c index d1fdd113450a6..667aa28d91255 100644 --- a/security/integrity/platform_certs/load_uefi.c +++ b/security/integrity/platform_certs/load_uefi.c @@ -74,7 +74,8 @@ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, return NULL; if (*status != EFI_BUFFER_TOO_SMALL) { - pr_err("Couldn't get size: 0x%lx\n", *status); + pr_err("Couldn't get size: %s (0x%lx)\n", + efi_status_to_str(*status), *status); return NULL; } @@ -85,7 +86,8 @@ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, *status = efi.get_variable(name, guid, NULL, &lsize, db); if (*status != EFI_SUCCESS) { kfree(db); - pr_err("Error reading db var: 0x%lx\n", *status); + pr_err("Error reading db var: %s (0x%lx)\n", + efi_status_to_str(*status), *status); return NULL; } @@ -94,17 +96,18 @@ static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, } /* - * load_moklist_certs() - Load MokList certs + * load_moklist_certs() - Load Mok(X)List certs + * @load_db: Load MokListRT into db when true; MokListXRT into dbx when false * - * Load the certs contained in the UEFI MokListRT database into the - * platform trusted keyring. + * Load the certs contained in the UEFI MokList(X)RT database into the + * platform trusted/denied keyring. * * This routine checks the EFI MOK config table first. If and only if - * that fails, this routine uses the MokListRT ordinary UEFI variable. + * that fails, this routine uses the MokList(X)RT ordinary UEFI variable. * * Return: Status */ -static int __init load_moklist_certs(void) +static int __init load_moklist_certs(const bool load_db) { struct efi_mokvar_table_entry *mokvar_entry; efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; @@ -112,41 +115,55 @@ static int __init load_moklist_certs(void) unsigned long moksize; efi_status_t status; int rc; + const char *mokvar_name = "MokListRT"; + /* Should be const, but get_cert_list() doesn't have it as const yet */ + efi_char16_t *efivar_name = L"MokListRT"; + const char *parse_mokvar_name = "UEFI:MokListRT (MOKvar table)"; + const char *parse_efivar_name = "UEFI:MokListRT"; + efi_element_handler_t (*get_handler_for_guid)(const efi_guid_t *) = get_handler_for_db; + + if (!load_db) { + mokvar_name = "MokListXRT"; + efivar_name = L"MokListXRT"; + parse_mokvar_name = "UEFI:MokListXRT (MOKvar table)"; + parse_efivar_name = "UEFI:MokListXRT"; + get_handler_for_guid = get_handler_for_dbx; + } /* First try to load certs from the EFI MOKvar config table. * It's not an error if the MOKvar config table doesn't exist * or the MokListRT entry is not found in it. */ - mokvar_entry = efi_mokvar_entry_find("MokListRT"); + mokvar_entry = efi_mokvar_entry_find(mokvar_name); if (mokvar_entry) { - rc = parse_efi_signature_list("UEFI:MokListRT (MOKvar table)", + rc = parse_efi_signature_list(parse_mokvar_name, mokvar_entry->data, mokvar_entry->data_size, - get_handler_for_mok); + get_handler_for_guid); /* All done if that worked. */ if (!rc) return rc; - pr_err("Couldn't parse MokListRT signatures from EFI MOKvar config table: %d\n", - rc); + pr_err("Couldn't parse %s signatures from EFI MOKvar config table: %d\n", + mokvar_name, rc); } /* Get MokListRT. It might not exist, so it isn't an error * if we can't get it. */ - mok = get_cert_list(L"MokListRT", &mok_var, &moksize, &status); + mok = get_cert_list(efivar_name, &mok_var, &moksize, &status); if (mok) { - rc = parse_efi_signature_list("UEFI:MokListRT", - mok, moksize, get_handler_for_mok); + rc = parse_efi_signature_list(parse_efivar_name, + mok, moksize, get_handler_for_guid); kfree(mok); if (rc) - pr_err("Couldn't parse MokListRT signatures: %d\n", rc); + pr_err("Couldn't parse %s signatures: %d\n", mokvar_name, rc); return rc; } if (status == EFI_NOT_FOUND) - pr_debug("MokListRT variable wasn't found\n"); + pr_debug("%s variable wasn't found\n", mokvar_name); else - pr_info("Couldn't get UEFI MokListRT\n"); + pr_info("Couldn't get UEFI %s\n", mokvar_name); return 0; } @@ -160,9 +177,8 @@ static int __init load_moklist_certs(void) static int __init load_uefi_certs(void) { efi_guid_t secure_var = EFI_IMAGE_SECURITY_DATABASE_GUID; - efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; - void *db = NULL, *dbx = NULL, *mokx = NULL; - unsigned long dbsize = 0, dbxsize = 0, mokxsize = 0; + void *db = NULL, *dbx = NULL; + unsigned long dbsize = 0, dbxsize = 0; efi_status_t status; int rc = 0; const struct dmi_system_id *dmi_id; @@ -215,23 +231,15 @@ static int __init load_uefi_certs(void) if (!arch_ima_get_secureboot()) return 0; - mokx = get_cert_list(L"MokListXRT", &mok_var, &mokxsize, &status); - if (!mokx) { - if (status == EFI_NOT_FOUND) - pr_debug("mokx variable wasn't found\n"); - else - pr_info("Couldn't get mokx list\n"); - } else { - rc = parse_efi_signature_list("UEFI:MokListXRT", - mokx, mokxsize, - get_handler_for_dbx); - if (rc) - pr_err("Couldn't parse mokx signatures %d\n", rc); - kfree(mokx); - } + /* Load the MokListXRT certs */ + rc = load_moklist_certs(false); + if (rc) + pr_err("Couldn't parse mokx signatures: %d\n", rc); /* Load the MokListRT certs */ - rc = load_moklist_certs(); + rc = load_moklist_certs(true); + if (rc) + pr_err("Couldn't parse mok signatures: %d\n", rc); return rc; } diff --git a/security/keys/key.c b/security/keys/key.c index 5b10641debd54..74dfd961af96a 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -464,7 +464,8 @@ static int __key_instantiate_and_link(struct key *key, if (authkey) key_invalidate(authkey); - key_set_expiry(key, prep->expiry); + if (prep->expiry != TIME64_MAX) + key_set_expiry(key, prep->expiry); } } diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index bc700f85f80be..ea277c55a38db 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -38,6 +38,7 @@ static int tpm2_key_encode(struct trusted_key_payload *payload, u8 *end_work = scratch + SCRATCH_SIZE; u8 *priv, *pub; u16 priv_len, pub_len; + int ret; priv_len = get_unaligned_be16(src) + 2; priv = src; @@ -57,8 +58,10 @@ static int tpm2_key_encode(struct trusted_key_payload *payload, unsigned char bool[3], *w = bool; /* tag 0 is emptyAuth */ w = asn1_encode_boolean(w, w + sizeof(bool), true); - if (WARN(IS_ERR(w), "BUG: Boolean failed to encode")) - return PTR_ERR(w); + if (WARN(IS_ERR(w), "BUG: Boolean failed to encode")) { + ret = PTR_ERR(w); + goto err; + } work = asn1_encode_tag(work, end_work, 0, bool, w - bool); } @@ -69,8 +72,10 @@ static int tpm2_key_encode(struct trusted_key_payload *payload, * trigger, so if it does there's something nefarious going on */ if (WARN(work - scratch + pub_len + priv_len + 14 > SCRATCH_SIZE, - "BUG: scratch buffer is too small")) - return -EINVAL; + "BUG: scratch buffer is too small")) { + ret = -EINVAL; + goto err; + } work = asn1_encode_integer(work, end_work, options->keyhandle); work = asn1_encode_octet_string(work, end_work, pub, pub_len); @@ -79,10 +84,18 @@ static int tpm2_key_encode(struct trusted_key_payload *payload, work1 = payload->blob; work1 = asn1_encode_sequence(work1, work1 + sizeof(payload->blob), scratch, work - scratch); - if (WARN(IS_ERR(work1), "BUG: ASN.1 encoder failed")) - return PTR_ERR(work1); + if (IS_ERR(work1)) { + ret = PTR_ERR(work1); + pr_err("BUG: ASN.1 encoder failed with %d\n", ret); + goto err; + } + kfree(scratch); return work1 - payload->blob; + +err: + kfree(scratch); + return ret; } struct tpm2_key_context { diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 0171f7eb6ee15..70465879badcd 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -737,6 +737,7 @@ static int current_check_refer_path(struct dentry *const old_dentry, bool allow_parent1, allow_parent2; access_mask_t access_request_parent1, access_request_parent2; struct path mnt_dir; + struct dentry *old_parent; layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {}, layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {}; @@ -784,9 +785,17 @@ static int current_check_refer_path(struct dentry *const old_dentry, mnt_dir.mnt = new_dir->mnt; mnt_dir.dentry = new_dir->mnt->mnt_root; + /* + * old_dentry may be the root of the common mount point and + * !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and + * OPEN_TREE_CLONE). We do not need to call dget(old_parent) because + * we keep a reference to old_dentry. + */ + old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry : + old_dentry->d_parent; + /* new_dir->dentry is equal to new_dentry->d_parent */ - allow_parent1 = collect_domain_accesses(dom, mnt_dir.dentry, - old_dentry->d_parent, + allow_parent1 = collect_domain_accesses(dom, mnt_dir.dentry, old_parent, &layer_masks_parent1); allow_parent2 = collect_domain_accesses( dom, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2); diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 898358f57fa08..6788e73b6681b 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -33,6 +33,18 @@ #include "ruleset.h" #include "setup.h" +static bool is_initialized(void) +{ + if (likely(landlock_initialized)) + return true; + + pr_warn_once( + "Disabled but requested by user space. " + "You should enable Landlock at boot time: " + "https://docs.kernel.org/userspace-api/landlock.html#boot-time-configuration\n"); + return false; +} + /** * copy_min_struct_from_user - Safe future-proof argument copying * @@ -173,7 +185,7 @@ SYSCALL_DEFINE3(landlock_create_ruleset, /* Build-time checks. */ build_check_abi(); - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; if (flags) { @@ -398,7 +410,7 @@ SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd, struct landlock_ruleset *ruleset; int err; - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; /* No flag for now. */ @@ -458,7 +470,7 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, struct landlock_cred_security *new_llcred; int err; - if (!landlock_initialized) + if (!is_initialized()) return -EOPNOTSUPP; /* diff --git a/security/lockdown/Kconfig b/security/lockdown/Kconfig index e84ddf4840101..a598a4f95ee8d 100644 --- a/security/lockdown/Kconfig +++ b/security/lockdown/Kconfig @@ -16,6 +16,19 @@ config SECURITY_LOCKDOWN_LSM_EARLY subsystem is fully initialised. If enabled, lockdown will unconditionally be called before any other LSMs. +config LOCK_DOWN_IN_SECURE_BOOT + bool "Lock down the kernel in Secure Boot mode" + default n + depends on (EFI || S390 || PPC) && SECURITY_LOCKDOWN_LSM_EARLY + help + Secure Boot provides a mechanism for ensuring that the firmware will + only load signed bootloaders and kernels. Secure boot mode + determination is platform-specific; examples include EFI secure boot + and SIPL on s390. + + Enabling this option results in kernel lockdown being triggered if + booted under secure boot. + choice prompt "Kernel default lockdown mode" default LOCK_DOWN_KERNEL_FORCE_NONE diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c index cd84d8ea1dfbf..e4c70a0312bc8 100644 --- a/security/lockdown/lockdown.c +++ b/security/lockdown/lockdown.c @@ -74,6 +74,7 @@ static int lockdown_is_locked_down(enum lockdown_reason what) static struct security_hook_list lockdown_hooks[] __ro_after_init = { LSM_HOOK_INIT(locked_down, lockdown_is_locked_down), + LSM_HOOK_INIT(lock_kernel_down, lock_kernel_down), }; const struct lsm_id lockdown_lsmid = { diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c index 5d391b1f7e694..8440948a690c9 100644 --- a/security/lsm_syscalls.c +++ b/security/lsm_syscalls.c @@ -53,7 +53,7 @@ u64 lsm_name_to_attr(const char *name) * value indicating the reason for the error is returned. */ SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *, - ctx, size_t, size, u32, flags) + ctx, u32, size, u32, flags) { return security_setselfattr(attr, ctx, size, flags); } @@ -75,7 +75,7 @@ SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *, * a negative value indicating the error is returned. */ SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *, - ctx, size_t __user *, size, u32, flags) + ctx, u32 __user *, size, u32, flags) { return security_getselfattr(attr, ctx, size, flags); } @@ -93,11 +93,11 @@ SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *, * required size. In all other cases a negative value indicating the * error is returned. */ -SYSCALL_DEFINE3(lsm_list_modules, u64 __user *, ids, size_t __user *, size, +SYSCALL_DEFINE3(lsm_list_modules, u64 __user *, ids, u32 __user *, size, u32, flags) { - size_t total_size = lsm_active_cnt * sizeof(*ids); - size_t usize; + u32 total_size = lsm_active_cnt * sizeof(*ids); + u32 usize; int i; if (flags) diff --git a/security/security.c b/security/security.c index 7035ee35a3930..8f82791920ddf 100644 --- a/security/security.c +++ b/security/security.c @@ -31,6 +31,7 @@ #include #include #include +#include /* How many LSMs were built into the kernel? */ #define LSM_COUNT (__end_lsm_info - __start_lsm_info) @@ -226,11 +227,28 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); +#ifdef CONFIG_KEYS + lsm_set_blob_size(&needed->lbs_key, &blob_sizes.lbs_key); +#endif lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); + lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock); lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); lsm_set_blob_size(&needed->lbs_xattr_count, &blob_sizes.lbs_xattr_count); + lsm_set_blob_size(&needed->lbs_mnt_opts, &blob_sizes.lbs_mnt_opts); + if (needed->lbs_secmark) { + if (!blob_sizes.lbs_secmark) + blob_sizes.lbs_secmark = true; + else + needed->lbs_secmark = false; + } + if (needed->lbs_netlabel) { + if (!blob_sizes.lbs_netlabel) + blob_sizes.lbs_netlabel = true; + else + needed->lbs_netlabel = false; + } } /* Prepare LSM for initialization. */ @@ -268,8 +286,49 @@ static void __init initialize_lsm(struct lsm_info *lsm) * Current index to use while initializing the lsm id list. */ u32 lsm_active_cnt __ro_after_init; +u32 lsm_blob_cnt __ro_after_init; const struct lsm_id *lsm_idlist[LSM_CONFIG_COUNT]; +/** + * lsm_name_to_id - get the LSM ID for a registered LSM + * @name: the name of the LSM + * + * Returns the LSM ID associated with the named LSM or + * LSM_ID_UNDEF if the name isn't recongnized. + */ +u64 lsm_name_to_id(const char *name) +{ + int i; + + for (i = 0; i < LSM_CONFIG_COUNT; i++) { + if (!lsm_idlist[i]->name) + return LSM_ID_UNDEF; + if (!strcmp(name, lsm_idlist[i]->name)) + return lsm_idlist[i]->id; + } + return LSM_ID_UNDEF; +} + +/** + * lsm_id_to_name - get the LSM name for a registered LSM ID + * @id: the ID of the LSM + * + * Returns the LSM name associated with the LSM ID or + * NULL if the ID isn't recongnized. + */ +const char *lsm_id_to_name(u64 id) +{ + int i; + + for (i = 0; i < LSM_CONFIG_COUNT; i++) { + if (!lsm_idlist[i]->name) + return NULL; + if (id == lsm_idlist[i]->id) + return lsm_idlist[i]->name; + } + return NULL; +} + /* Populate ordered LSMs list from comma-separated LSM name list. */ static void __init ordered_lsm_parse(const char *order, const char *origin) { @@ -400,10 +459,15 @@ static void __init ordered_lsm_init(void) init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); +#ifdef CONFIG_KEYS + init_debug("key blob size = %d\n", blob_sizes.lbs_key); +#endif /* CONFIG_KEYS */ init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); + init_debug("sock blob size = %d\n", blob_sizes.lbs_sock); init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock); init_debug("task blob size = %d\n", blob_sizes.lbs_task); init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count); + init_debug("mnt_opts blob size = %d\n", blob_sizes.lbs_mnt_opts); /* * Create any kmem_caches needed for blobs @@ -557,6 +621,8 @@ void __init security_add_hooks(struct security_hook_list *hooks, int count, if (lsm_active_cnt >= LSM_CONFIG_COUNT) panic("%s Too many LSMs registered.\n", __func__); lsm_idlist[lsm_active_cnt++] = lsmid; + if (lsmid->lsmblob) + lsm_blob_cnt++; } for (i = 0; i < count; i++) { @@ -715,6 +781,29 @@ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) return 0; } +#ifdef CONFIG_KEYS +/** + * lsm_key_alloc - allocate a composite key blob + * @key: the key that needs a blob + * + * Allocate the key blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +int lsm_key_alloc(struct key *key) +{ + if (blob_sizes.lbs_key == 0) { + key->security = NULL; + return 0; + } + + key->security = kzalloc(blob_sizes.lbs_key, GFP_KERNEL); + if (key->security == NULL) + return -ENOMEM; + return 0; +} +#endif /* CONFIG_KEYS */ + /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob @@ -780,12 +869,14 @@ static int lsm_superblock_alloc(struct super_block *sb) * @id: LSM id * @flags: LSM defined flags * - * Fill all of the fields in a userspace lsm_ctx structure. + * Fill all of the fields in a userspace lsm_ctx structure. If @uctx is NULL + * simply calculate the required size to output via @utc_len and return + * success. * * Returns 0 on success, -E2BIG if userspace buffer is not large enough, * -EFAULT on a copyout error, -ENOMEM if memory can't be allocated. */ -int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, size_t *uctx_len, +int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags) { @@ -799,6 +890,10 @@ int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, size_t *uctx_len, goto out; } + /* no buffer - return success/0 and set @uctx_len to the req size */ + if (!uctx) + goto out; + nctx = kzalloc(nctx_len, GFP_KERNEL); if (nctx == NULL) { rc = -ENOMEM; @@ -884,6 +979,7 @@ int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, 0, mgr); } +EXPORT_SYMBOL(security_binder_set_context_mgr); /** * security_binder_transaction() - Check if a binder transaction is allowed @@ -899,6 +995,7 @@ int security_binder_transaction(const struct cred *from, { return call_int_hook(binder_transaction, 0, from, to); } +EXPORT_SYMBOL(security_binder_transaction); /** * security_binder_transfer_binder() - Check if a binder transfer is allowed @@ -914,6 +1011,7 @@ int security_binder_transfer_binder(const struct cred *from, { return call_int_hook(binder_transfer_binder, 0, from, to); } +EXPORT_SYMBOL(security_binder_transfer_binder); /** * security_binder_transfer_file() - Check if a binder file xfer is allowed @@ -930,6 +1028,7 @@ int security_binder_transfer_file(const struct cred *from, { return call_int_hook(binder_transfer_file, 0, from, to, file); } +EXPORT_SYMBOL(security_binder_transfer_file); /** * security_ptrace_access_check() - Check if tracing is allowed @@ -1270,18 +1369,15 @@ int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct security_hook_list *hp; - int trc; - int rc = -ENOPARAM; + int rc; hlist_for_each_entry(hp, &security_hook_heads.fs_context_parse_param, list) { - trc = hp->hook.fs_context_parse_param(fc, param); - if (trc == 0) - rc = 0; - else if (trc != -ENOPARAM) - return trc; + rc = hp->hook.fs_context_parse_param(fc, param); + if (rc != -ENOPARAM) + return rc; } - return rc; + return -ENOPARAM; } /** @@ -1332,6 +1428,18 @@ void security_sb_free(struct super_block *sb) sb->s_security = NULL; } +/** + * lsm_mnt_opts_alloc - allocate a mnt_opts blob + * @priority: memory allocation priority + * + * Returns a newly allocated mnt_opts blob or NULL if + * memory isn't available. + */ +void *lsm_mnt_opts_alloc(gfp_t priority) +{ + return kzalloc(blob_sizes.lbs_mnt_opts, priority); +} + /** * security_free_mnt_opts() - Free memory associated with mount options * @mnt_opts: LSM processed mount options @@ -1343,6 +1451,7 @@ void security_free_mnt_opts(void **mnt_opts) if (!*mnt_opts) return; call_void_hook(sb_free_mnt_opts, *mnt_opts); + kfree(*mnt_opts); *mnt_opts = NULL; } EXPORT_SYMBOL(security_free_mnt_opts); @@ -1624,8 +1733,7 @@ void security_inode_free(struct inode *inode) * @mode: mode used to determine resource type * @name: name of the last path component * @xattr_name: name of the security/LSM xattr - * @ctx: pointer to the resulting LSM context - * @ctxlen: length of @ctx + * @lsmctx: pointer to the resulting LSM context * * Compute a context for a dentry as the inode is not yet available since NFSv4 * has no label backed by an EA anyway. It is important to note that @@ -1635,8 +1743,8 @@ void security_inode_free(struct inode *inode) */ int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, - const char **xattr_name, void **ctx, - u32 *ctxlen) + const char **xattr_name, + struct lsmcontext *lsmctx) { struct security_hook_list *hp; int rc; @@ -1647,7 +1755,7 @@ int security_dentry_init_security(struct dentry *dentry, int mode, hlist_for_each_entry(hp, &security_hook_heads.dentry_init_security, list) { rc = hp->hook.dentry_init_security(dentry, mode, name, - xattr_name, ctx, ctxlen); + xattr_name, lsmctx); if (rc != LSM_RET_DEFAULT(dentry_init_security)) return rc; } @@ -2255,24 +2363,25 @@ int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - int ret; + struct security_hook_list *hp; + int rc = -ENOSYS; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; - /* - * SELinux and Smack integrate the cap call, - * so assume that all LSMs supplying this call do so. - */ - ret = call_int_hook(inode_setxattr, 1, idmap, dentry, name, value, - size, flags); - if (ret == 1) - ret = cap_inode_setxattr(dentry, name, value, size, flags); - if (ret) - return ret; - ret = ima_inode_setxattr(dentry, name, value, size); - if (ret) - return ret; + hlist_for_each_entry(hp, &security_hook_heads.inode_setxattr, list) { + rc = hp->hook.inode_setxattr(idmap, dentry, name, value, size, + flags); + if (rc != -ENOSYS) + break; + } + if (rc == -ENOSYS) + rc = cap_inode_setxattr(dentry, name, value, size, flags); + if (rc) + return rc; + rc = ima_inode_setxattr(dentry, name, value, size); + if (rc) + return rc; return evm_inode_setxattr(idmap, dentry, name, value, size); } @@ -2565,16 +2674,15 @@ int security_inode_listsecurity(struct inode *inode, EXPORT_SYMBOL(security_inode_listsecurity); /** - * security_inode_getsecid() - Get an inode's secid + * security_inode_getlsmblob() - Get an inode's LSM data * @inode: inode - * @secid: secid to return + * @blob: lsm specific information to return * - * Get the secid associated with the node. In case of failure, @secid will be - * set to zero. + * Get the lsm specific information associated with the node. */ -void security_inode_getsecid(struct inode *inode, u32 *secid) +void security_inode_getlsmblob(struct inode *inode, struct lsmblob *blob) { - call_void_hook(inode_getsecid, inode, secid); + call_void_hook(inode_getlsmblob, inode, blob); } /** @@ -3072,16 +3180,38 @@ void security_transfer_creds(struct cred *new, const struct cred *old) * @c: credentials * @secid: secid value * - * Retrieve the security identifier of the cred structure @c. In case of - * failure, @secid will be set to zero. + * Retrieve the first available security identifier of the + * cred structure @c. In case of failure, @secid will be set to zero. + * Currently only used by binder. */ void security_cred_getsecid(const struct cred *c, u32 *secid) { + struct security_hook_list *hp; + + hlist_for_each_entry(hp, &security_hook_heads.cred_getsecid, list) { + hp->hook.cred_getsecid(c, secid); + return; + } + *secid = 0; - call_void_hook(cred_getsecid, c, secid); } EXPORT_SYMBOL(security_cred_getsecid); +/** + * security_cred_getlsmblob() - Get the LSM data from a set of credentials + * @c: credentials + * @blob: destination for the LSM data + * + * Retrieve the security data of the cred structure @c. In case of + * failure, @blob will be cleared. + */ +void security_cred_getlsmblob(const struct cred *c, struct lsmblob *blob) +{ + lsmblob_init(blob); + call_void_hook(cred_getlsmblob, c, blob); +} +EXPORT_SYMBOL(security_cred_getlsmblob); + /** * security_kernel_act_as() - Set the kernel credentials to act as secid * @new: credentials @@ -3327,33 +3457,33 @@ int security_task_getsid(struct task_struct *p) } /** - * security_current_getsecid_subj() - Get the current task's subjective secid - * @secid: secid value + * security_current_getlsmblob_subj() - Current task's subjective LSM data + * @blob: lsm specific information * * Retrieve the subjective security identifier of the current task and return - * it in @secid. In case of failure, @secid will be set to zero. + * it in @blob. */ -void security_current_getsecid_subj(u32 *secid) +void security_current_getlsmblob_subj(struct lsmblob *blob) { - *secid = 0; - call_void_hook(current_getsecid_subj, secid); + lsmblob_init(blob); + call_void_hook(current_getlsmblob_subj, blob); } -EXPORT_SYMBOL(security_current_getsecid_subj); +EXPORT_SYMBOL(security_current_getlsmblob_subj); /** - * security_task_getsecid_obj() - Get a task's objective secid + * security_task_getlsmblob_obj() - Get a task's objective LSM data * @p: target task - * @secid: secid value + * @blob: lsm specific information * * Retrieve the objective security identifier of the task_struct in @p and - * return it in @secid. In case of failure, @secid will be set to zero. + * return it in @blob. */ -void security_task_getsecid_obj(struct task_struct *p, u32 *secid) +void security_task_getlsmblob_obj(struct task_struct *p, struct lsmblob *blob) { - *secid = 0; - call_void_hook(task_getsecid_obj, p, secid); + lsmblob_init(blob); + call_void_hook(task_getlsmblob_obj, p, blob); } -EXPORT_SYMBOL(security_task_getsecid_obj); +EXPORT_SYMBOL(security_task_getlsmblob_obj); /** * security_task_setnice() - Check if setting a task's nice value is allowed @@ -3565,17 +3695,17 @@ int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag) } /** - * security_ipc_getsecid() - Get the sysv ipc object's secid + * security_ipc_getlsmblob() - Get the sysv ipc object LSM data * @ipcp: ipc permission structure - * @secid: secid pointer + * @blob: pointer to lsm information * - * Get the secid associated with the ipc object. In case of failure, @secid - * will be set to zero. + * Get the lsm information associated with the ipc object. */ -void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) + +void security_ipc_getlsmblob(struct kern_ipc_perm *ipcp, struct lsmblob *blob) { - *secid = 0; - call_void_hook(ipc_getsecid, ipcp, secid); + lsmblob_init(blob); + call_void_hook(ipc_getlsmblob, ipcp, blob); } /** @@ -3918,14 +4048,14 @@ EXPORT_SYMBOL(security_d_instantiate); * If @size is insufficient to contain the data -E2BIG is returned. */ int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, - size_t __user *size, u32 flags) + u32 __user *size, u32 flags) { struct security_hook_list *hp; struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, }; u8 __user *base = (u8 __user *)uctx; - size_t total = 0; - size_t entrysize; - size_t left; + u32 entrysize; + u32 total = 0; + u32 left; bool toobig = false; bool single = false; int count = 0; @@ -4011,7 +4141,7 @@ int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, * LSM specific failure. */ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx, - size_t size, u32 flags) + u32 size, u32 flags) { struct security_hook_list *hp; struct lsm_ctx *lctx; @@ -4063,11 +4193,10 @@ int security_getprocattr(struct task_struct *p, int lsmid, const char *name, { struct security_hook_list *hp; - hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) { - if (lsmid != 0 && lsmid != hp->lsmid->id) - continue; - return hp->hook.getprocattr(p, name, value); - } + hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) + if (lsmid == LSM_ID_UNDEF || lsmid == hp->lsmid->id) + return hp->hook.getprocattr(p, name, value); + return LSM_RET_DEFAULT(getprocattr); } @@ -4130,17 +4259,16 @@ EXPORT_SYMBOL(security_ismaclabel); /** * security_secid_to_secctx() - Convert a secid to a secctx * @secid: secid - * @secdata: secctx - * @seclen: secctx length + * @cp: the LSM context * - * Convert secid to security context. If @secdata is NULL the length of the - * result will be returned in @seclen, but no @secdata will be returned. This + * Convert secid to security context. If @cp is NULL the length of the + * result will be returned, but no data will be returned. This * does mean that the length could change between calls to check the length and - * the next call which actually allocates and returns the @secdata. + * the next call which actually allocates and returns the data. * - * Return: Return 0 on success, error on failure. + * Return: Return length of data on success, error on failure. */ -int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +int security_secid_to_secctx(u32 secid, struct lsmcontext *cp) { struct security_hook_list *hp; int rc; @@ -4150,7 +4278,7 @@ int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) * LSM hook is not "stackable"). */ hlist_for_each_entry(hp, &security_hook_heads.secid_to_secctx, list) { - rc = hp->hook.secid_to_secctx(secid, secdata, seclen); + rc = hp->hook.secid_to_secctx(secid, cp); if (rc != LSM_RET_DEFAULT(secid_to_secctx)) return rc; } @@ -4159,6 +4287,35 @@ int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) } EXPORT_SYMBOL(security_secid_to_secctx); +/** + * security_lsmblob_to_secctx() - Convert a lsmblob to a secctx + * @blob: lsm specific information + * @cp: the LSM context + * @lsmid: which security module to report + * + * Convert a @blob entry to security context. If @cp is NULL the + * length of the result will be returned, but no data will be returned. + * This does mean that the length could change between calls to check + * the length and the next call which actually allocates and returns + * the data. + * + * Return: Return length of data on success, error on failure. + */ +int security_lsmblob_to_secctx(struct lsmblob *blob, struct lsmcontext *cp, + int lsmid) +{ + struct security_hook_list *hp; + + hlist_for_each_entry(hp, &security_hook_heads.lsmblob_to_secctx, list) { + if (lsmid != hp->lsmid->id && lsmid != LSM_ID_UNDEF) + continue; + return hp->hook.lsmblob_to_secctx(blob, cp); + } + + return LSM_RET_DEFAULT(lsmblob_to_secctx); +} +EXPORT_SYMBOL(security_lsmblob_to_secctx); + /** * security_secctx_to_secid() - Convert a secctx to a secid * @secdata: secctx @@ -4171,21 +4328,26 @@ EXPORT_SYMBOL(security_secid_to_secctx); */ int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { + struct security_hook_list *hp; + *secid = 0; - return call_int_hook(secctx_to_secid, 0, secdata, seclen, secid); + hlist_for_each_entry(hp, &security_hook_heads.secctx_to_secid, list) + return hp->hook.secctx_to_secid(secdata, seclen, secid); + + return LSM_RET_DEFAULT(secctx_to_secid); } EXPORT_SYMBOL(security_secctx_to_secid); /** * security_release_secctx() - Free a secctx buffer - * @secdata: secctx - * @seclen: length of secctx + * @cp: the security context * * Release the security context. */ -void security_release_secctx(char *secdata, u32 seclen) +void security_release_secctx(struct lsmcontext *cp) { - call_void_hook(release_secctx, secdata, seclen); + call_void_hook(release_secctx, cp); + memset(cp, 0, sizeof(*cp)); } EXPORT_SYMBOL(security_release_secctx); @@ -4248,24 +4410,24 @@ EXPORT_SYMBOL(security_inode_setsecctx); /** * security_inode_getsecctx() - Get the security label of an inode * @inode: inode - * @ctx: secctx - * @ctxlen: length of secctx + * @cp: security context * - * On success, returns 0 and fills out @ctx and @ctxlen with the security - * context for the given @inode. + * On success, returns 0 and fills out @cp with the security context + * for the given @inode. * * Return: Returns 0 on success, error on failure. */ -int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +int security_inode_getsecctx(struct inode *inode, struct lsmcontext *cp) { struct security_hook_list *hp; int rc; + memset(cp, 0, sizeof(*cp)); /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) { - rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen); + rc = hp->hook.inode_getsecctx(inode, cp); if (rc != LSM_RET_DEFAULT(inode_getsecctx)) return rc; } @@ -4676,6 +4838,28 @@ int security_socket_getpeersec_dgram(struct socket *sock, } EXPORT_SYMBOL(security_socket_getpeersec_dgram); +/** + * lsm_sock_alloc - allocate a composite sock blob + * @sock: the sock that needs a blob + * @priority: allocation mode + * + * Allocate the sock blob for all the modules + * + * Returns 0, or -ENOMEM if memory can't be allocated. + */ +static int lsm_sock_alloc(struct sock *sock, gfp_t priority) +{ + if (blob_sizes.lbs_sock == 0) { + sock->sk_security = NULL; + return 0; + } + + sock->sk_security = kzalloc(blob_sizes.lbs_sock, priority); + if (sock->sk_security == NULL) + return -ENOMEM; + return 0; +} + /** * security_sk_alloc() - Allocate and initialize a sock's LSM blob * @sk: sock @@ -4689,7 +4873,14 @@ EXPORT_SYMBOL(security_socket_getpeersec_dgram); */ int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { - return call_int_hook(sk_alloc_security, 0, sk, family, priority); + int rc = lsm_sock_alloc(sk, priority); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(sk_alloc_security, 0, sk, family, priority); + if (unlikely(rc)) + security_sk_free(sk); + return rc; } /** @@ -4701,6 +4892,8 @@ int security_sk_alloc(struct sock *sk, int family, gfp_t priority) void security_sk_free(struct sock *sk) { call_void_hook(sk_free_security, sk); + kfree(sk->sk_security); + sk->sk_security = NULL; } /** @@ -5287,7 +5480,14 @@ EXPORT_SYMBOL(security_skb_classify_flow); int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { - return call_int_hook(key_alloc, 0, key, cred, flags); + int rc = lsm_key_alloc(key); + + if (unlikely(rc)) + return rc; + rc = call_int_hook(key_alloc, 0, key, cred, flags); + if (unlikely(rc)) + security_key_free(key); + return rc; } /** @@ -5298,7 +5498,8 @@ int security_key_alloc(struct key *key, const struct cred *cred, */ void security_key_free(struct key *key) { - call_void_hook(key_free, key); + kfree(key->security); + key->security = NULL; } /** @@ -5344,15 +5545,18 @@ int security_key_getsecurity(struct key *key, char **buffer) * @op: rule operator * @rulestr: rule context * @lsmrule: receive buffer for audit rule struct + * @gfp: GFP flag used for kmalloc * * Allocate and initialize an LSM audit rule structure. * * Return: Return 0 if @lsmrule has been successfully set, -EINVAL in case of * an invalid rule. */ -int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule) +int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + gfp_t gfp) { - return call_int_hook(audit_rule_init, 0, field, op, rulestr, lsmrule); + return call_int_hook(audit_rule_init, 0, field, op, rulestr, lsmrule, + LSM_ID_UNDEF, gfp); } /** @@ -5378,12 +5582,12 @@ int security_audit_rule_known(struct audit_krule *krule) */ void security_audit_rule_free(void *lsmrule) { - call_void_hook(audit_rule_free, lsmrule); + call_void_hook(audit_rule_free, lsmrule, LSM_ID_UNDEF); } /** * security_audit_rule_match() - Check if a label matches an audit rule - * @secid: security label + * @lsmblob: security label * @field: LSM audit field * @op: matching operator * @lsmrule: audit rule @@ -5394,12 +5598,38 @@ void security_audit_rule_free(void *lsmrule) * Return: Returns 1 if secid matches the rule, 0 if it does not, -ERRNO on * failure. */ -int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule) +int security_audit_rule_match(struct lsmblob *blob, u32 field, u32 op, void *lsmrule) { - return call_int_hook(audit_rule_match, 0, secid, field, op, lsmrule); + return call_int_hook(audit_rule_match, 0, blob, field, op, lsmrule, + LSM_ID_UNDEF); } #endif /* CONFIG_AUDIT */ +#ifdef CONFIG_IMA_LSM_RULES +/* + * The integrity subsystem uses the same hooks as + * the audit subsystem. + */ +int ima_filter_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + int lsmid, gfp_t gfp) +{ + return call_int_hook(audit_rule_init, 0, field, op, rulestr, lsmrule, + lsmid, gfp); +} + +void ima_filter_rule_free(void *lsmrule, int lsmid) +{ + call_void_hook(audit_rule_free, lsmrule, lsmid); +} + +int ima_filter_rule_match(struct lsmblob *blob, u32 field, u32 op, + void *lsmrule, int lsmid) +{ + return call_int_hook(audit_rule_match, 0, blob, field, op, lsmrule, + lsmid); +} +#endif /* CONFIG_IMA_LSM_RULES */ + #ifdef CONFIG_BPF_SYSCALL /** * security_bpf() - Check if the bpf syscall operation is allowed @@ -5511,6 +5741,12 @@ int security_locked_down(enum lockdown_reason what) } EXPORT_SYMBOL(security_locked_down); +int security_lock_kernel_down(const char *where, enum lockdown_reason level) +{ + return call_int_hook(lock_kernel_down, 0, where, level); +} +EXPORT_SYMBOL(security_lock_kernel_down); + #ifdef CONFIG_PERF_EVENTS /** * security_perf_event_open() - Check if a perf event open is allowed diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 338b023a8c3ed..d4212510970ba 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -165,7 +165,8 @@ __setup("checkreqprot=", checkreqprot_setup); */ static int selinux_secmark_enabled(void) { - return (selinux_policycap_alwaysnetwork() || + return selinux_blob_sizes.lbs_secmark && + (selinux_policycap_alwaysnetwork() || atomic_read(&selinux_secmark_refcount)); } @@ -182,7 +183,7 @@ static int selinux_secmark_enabled(void) static int selinux_peerlbl_enabled(void) { return (selinux_policycap_alwaysnetwork() || - netlbl_enabled() || selinux_xfrm_enabled()); + selinux_netlbl_enabled() || selinux_xfrm_enabled()); } static int selinux_netcache_avc_callback(u32 event) @@ -365,15 +366,28 @@ static void inode_free_security(struct inode *inode) } struct selinux_mnt_opts { + bool initialized; u32 fscontext_sid; u32 context_sid; u32 rootcontext_sid; u32 defcontext_sid; }; +static inline struct selinux_mnt_opts *selinux_mnt_opts(void *mnt_opts) +{ + if (mnt_opts) + return mnt_opts + selinux_blob_sizes.lbs_mnt_opts; + return NULL; +} + static void selinux_free_mnt_opts(void *mnt_opts) { - kfree(mnt_opts); + struct selinux_mnt_opts *opts; + + if (mnt_opts) { + opts = selinux_mnt_opts(mnt_opts); + opts->initialized = false; + } } enum { @@ -628,7 +642,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, const struct cred *cred = current_cred(); struct superblock_security_struct *sbsec = selinux_superblock(sb); struct dentry *root = sb->s_root; - struct selinux_mnt_opts *opts = mnt_opts; + struct selinux_mnt_opts *opts = selinux_mnt_opts(mnt_opts); struct inode_security_struct *root_isec; u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0; u32 defcontext_sid = 0; @@ -644,7 +658,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, mutex_lock(&sbsec->lock); if (!selinux_initialized()) { - if (!opts) { + if (!opts || !opts->initialized) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ @@ -682,7 +696,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, * also check if someone is trying to mount the same sb more * than once with different security options. */ - if (opts) { + if (opts && opts->initialized) { if (opts->fscontext_sid) { fscontext_sid = opts->fscontext_sid; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, @@ -991,7 +1005,7 @@ static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb, */ static int selinux_add_opt(int token, const char *s, void **mnt_opts) { - struct selinux_mnt_opts *opts = *mnt_opts; + struct selinux_mnt_opts *opts; u32 *dst_sid; int rc; @@ -1006,12 +1020,12 @@ static int selinux_add_opt(int token, const char *s, void **mnt_opts) return -EINVAL; } - if (!opts) { - opts = kzalloc(sizeof(*opts), GFP_KERNEL); - if (!opts) + if (!*mnt_opts) { + *mnt_opts = lsm_mnt_opts_alloc(GFP_KERNEL); + if (!*mnt_opts) return -ENOMEM; - *mnt_opts = opts; } + opts = selinux_mnt_opts(*mnt_opts); switch (token) { case Opt_context: @@ -1038,6 +1052,7 @@ static int selinux_add_opt(int token, const char *s, void **mnt_opts) WARN_ON(1); return -EINVAL; } + opts->initialized = true; rc = security_context_str_to_sid(s, dst_sid, GFP_KERNEL); if (rc) pr_warn("SELinux: security_context_str_to_sid (%s) failed with errno=%d\n", @@ -2640,10 +2655,7 @@ static int selinux_sb_eat_lsm_opts(char *options, void **mnt_opts) return 0; free_opt: - if (*mnt_opts) { - selinux_free_mnt_opts(*mnt_opts); - *mnt_opts = NULL; - } + selinux_free_mnt_opts(*mnt_opts); return rc; } @@ -2694,13 +2706,13 @@ static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) { - struct selinux_mnt_opts *opts = mnt_opts; + struct selinux_mnt_opts *opts = selinux_mnt_opts(mnt_opts); struct superblock_security_struct *sbsec = selinux_superblock(sb); if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; - if (!opts) + if (!opts || !opts->initialized) return 0; if (opts->fscontext_sid) { @@ -2798,9 +2810,13 @@ static int selinux_fs_context_submount(struct fs_context *fc, if (!(sbsec->flags & (FSCONTEXT_MNT|CONTEXT_MNT|DEFCONTEXT_MNT))) return 0; - opts = kzalloc(sizeof(*opts), GFP_KERNEL); - if (!opts) - return -ENOMEM; + if (!fc->security) { + fc->security = lsm_mnt_opts_alloc(GFP_KERNEL); + if (!fc->security) + return -ENOMEM; + } + opts = selinux_mnt_opts(fc->security); + opts->initialized = true; if (sbsec->flags & FSCONTEXT_MNT) opts->fscontext_sid = sbsec->sid; @@ -2808,20 +2824,25 @@ static int selinux_fs_context_submount(struct fs_context *fc, opts->context_sid = sbsec->mntpoint_sid; if (sbsec->flags & DEFCONTEXT_MNT) opts->defcontext_sid = sbsec->def_sid; - fc->security = opts; return 0; } static int selinux_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { - const struct selinux_mnt_opts *src = src_fc->security; + const struct selinux_mnt_opts *src = selinux_mnt_opts(src_fc->security); + struct selinux_mnt_opts *dst; if (!src) return 0; - fc->security = kmemdup(src, sizeof(*src), GFP_KERNEL); - return fc->security ? 0 : -ENOMEM; + fc->security = lsm_mnt_opts_alloc(GFP_KERNEL); + if (!fc->security) + return -ENOMEM; + + dst = selinux_mnt_opts(fc->security); + memcpy(dst, src, sizeof(*src)); + return 0; } static const struct fs_parameter_spec selinux_fs_parameters[] = { @@ -2871,8 +2892,8 @@ static void selinux_inode_free_security(struct inode *inode) static int selinux_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, - const char **xattr_name, void **ctx, - u32 *ctxlen) + const char **xattr_name, + struct lsmcontext *cp) { u32 newsid; int rc; @@ -2887,8 +2908,9 @@ static int selinux_dentry_init_security(struct dentry *dentry, int mode, if (xattr_name) *xattr_name = XATTR_NAME_SELINUX; - return security_sid_to_context(newsid, (char **)ctx, - ctxlen); + cp->id = LSM_ID_SELINUX; + return security_sid_to_context(newsid, (char **)cp->context, + &cp->len); } static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, @@ -3193,13 +3215,10 @@ static int selinux_inode_setxattr(struct mnt_idmap *idmap, int rc = 0; if (strcmp(name, XATTR_NAME_SELINUX)) { - rc = cap_inode_setxattr(dentry, name, value, size, flags); - if (rc) - return rc; - /* Not an attribute we recognize, so just check the ordinary setattr permission. */ - return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); + rc = dentry_has_perm(current_cred(), dentry, FILE__SETATTR); + return rc ? rc : -ENOSYS; } if (!selinux_initialized()) @@ -3504,15 +3523,16 @@ static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t return len; } -static void selinux_inode_getsecid(struct inode *inode, u32 *secid) +static void selinux_inode_getlsmblob(struct inode *inode, struct lsmblob *blob) { struct inode_security_struct *isec = inode_security_novalidate(inode); - *secid = isec->sid; + + blob->selinux.secid = isec->sid; } static int selinux_inode_copy_up(struct dentry *src, struct cred **new) { - u32 sid; + struct lsmblob blob; struct task_security_struct *tsec; struct cred *new_creds = *new; @@ -3524,8 +3544,8 @@ static int selinux_inode_copy_up(struct dentry *src, struct cred **new) tsec = selinux_cred(new_creds); /* Get label from overlay inode and set it in create_sid */ - selinux_inode_getsecid(d_inode(src), &sid); - tsec->create_sid = sid; + selinux_inode_getlsmblob(d_inode(src), &blob); + tsec->create_sid = blob.selinux.secid; *new = new_creds; return 0; } @@ -4024,6 +4044,11 @@ static void selinux_cred_getsecid(const struct cred *c, u32 *secid) *secid = cred_sid(c); } +static void selinux_cred_getlsmblob(const struct cred *c, struct lsmblob *blob) +{ + blob->selinux.secid = cred_sid(c); +} + /* * set the security data for a kernel service * - all the creation contexts are set to unlabelled @@ -4159,14 +4184,15 @@ static int selinux_task_getsid(struct task_struct *p) PROCESS__GETSESSION, NULL); } -static void selinux_current_getsecid_subj(u32 *secid) +static void selinux_current_getlsmblob_subj(struct lsmblob *blob) { - *secid = current_sid(); + blob->selinux.secid = current_sid(); } -static void selinux_task_getsecid_obj(struct task_struct *p, u32 *secid) +static void selinux_task_getlsmblob_obj(struct task_struct *p, + struct lsmblob *blob) { - *secid = task_sid_obj(p); + blob->selinux.secid = task_sid_obj(p); } static int selinux_task_setnice(struct task_struct *p, int nice) @@ -4582,7 +4608,7 @@ static int socket_sockcreate_sid(const struct task_security_struct *tsec, static int sock_has_perm(struct sock *sk, u32 perms) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct common_audit_data ad; struct lsm_network_audit net; @@ -4650,7 +4676,7 @@ static int selinux_socket_post_create(struct socket *sock, int family, isec->initialized = LABEL_INITIALIZED; if (sock->sk) { - sksec = sock->sk->sk_security; + sksec = selinux_sock(sock->sk); sksec->sclass = sclass; sksec->sid = sid; /* Allows detection of the first association on this socket */ @@ -4666,8 +4692,8 @@ static int selinux_socket_post_create(struct socket *sock, int family, static int selinux_socket_socketpair(struct socket *socka, struct socket *sockb) { - struct sk_security_struct *sksec_a = socka->sk->sk_security; - struct sk_security_struct *sksec_b = sockb->sk->sk_security; + struct sk_security_struct *sksec_a = selinux_sock(socka->sk); + struct sk_security_struct *sksec_b = selinux_sock(sockb->sk); sksec_a->peer_sid = sksec_b->sid; sksec_b->peer_sid = sksec_a->sid; @@ -4682,7 +4708,7 @@ static int selinux_socket_socketpair(struct socket *socka, static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); u16 family; int err; @@ -4822,7 +4848,7 @@ static int selinux_socket_connect_helper(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); int err; err = sock_has_perm(sk, SOCKET__CONNECT); @@ -5000,9 +5026,9 @@ static int selinux_socket_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { - struct sk_security_struct *sksec_sock = sock->sk_security; - struct sk_security_struct *sksec_other = other->sk_security; - struct sk_security_struct *sksec_new = newsk->sk_security; + struct sk_security_struct *sksec_sock = selinux_sock(sock); + struct sk_security_struct *sksec_other = selinux_sock(other); + struct sk_security_struct *sksec_new = selinux_sock(newsk); struct common_audit_data ad; struct lsm_network_audit net; int err; @@ -5031,8 +5057,8 @@ static int selinux_socket_unix_stream_connect(struct sock *sock, static int selinux_socket_unix_may_send(struct socket *sock, struct socket *other) { - struct sk_security_struct *ssec = sock->sk->sk_security; - struct sk_security_struct *osec = other->sk->sk_security; + struct sk_security_struct *ssec = selinux_sock(sock->sk); + struct sk_security_struct *osec = selinux_sock(other->sk); struct common_audit_data ad; struct lsm_network_audit net; @@ -5069,7 +5095,7 @@ static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { int err = 0; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net; @@ -5098,7 +5124,7 @@ static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err, peerlbl_active, secmark_active; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); u16 family = sk->sk_family; u32 sk_sid = sksec->sid; struct common_audit_data ad; @@ -5166,7 +5192,7 @@ static int selinux_socket_getpeersec_stream(struct socket *sock, int err = 0; char *scontext = NULL; u32 scontext_len; - struct sk_security_struct *sksec = sock->sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sock->sk); u32 peer_sid = SECSID_NULL; if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET || @@ -5224,34 +5250,27 @@ static int selinux_socket_getpeersec_dgram(struct socket *sock, struct sk_buff * static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority) { - struct sk_security_struct *sksec; - - sksec = kzalloc(sizeof(*sksec), priority); - if (!sksec) - return -ENOMEM; + struct sk_security_struct *sksec = selinux_sock(sk); sksec->peer_sid = SECINITSID_UNLABELED; sksec->sid = SECINITSID_UNLABELED; sksec->sclass = SECCLASS_SOCKET; selinux_netlbl_sk_security_reset(sksec); - sk->sk_security = sksec; return 0; } static void selinux_sk_free_security(struct sock *sk) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); - sk->sk_security = NULL; selinux_netlbl_sk_security_free(sksec); - kfree(sksec); } static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) { - struct sk_security_struct *sksec = sk->sk_security; - struct sk_security_struct *newsksec = newsk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); + struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->sid = sksec->sid; newsksec->peer_sid = sksec->peer_sid; @@ -5265,7 +5284,7 @@ static void selinux_sk_getsecid(const struct sock *sk, u32 *secid) if (!sk) *secid = SECINITSID_ANY_SOCKET; else { - const struct sk_security_struct *sksec = sk->sk_security; + const struct sk_security_struct *sksec = selinux_sock(sk); *secid = sksec->sid; } @@ -5275,7 +5294,7 @@ static void selinux_sock_graft(struct sock *sk, struct socket *parent) { struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(parent)); - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 || sk->sk_family == PF_UNIX) @@ -5292,7 +5311,7 @@ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc, { struct sock *sk = asoc->base.sk; u16 family = sk->sk_family; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct common_audit_data ad; struct lsm_network_audit net; int err; @@ -5347,7 +5366,7 @@ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc, static int selinux_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { - struct sk_security_struct *sksec = asoc->base.sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); u32 conn_sid; int err; @@ -5380,7 +5399,7 @@ static int selinux_sctp_assoc_request(struct sctp_association *asoc, static int selinux_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { - struct sk_security_struct *sksec = asoc->base.sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); if (!selinux_policycap_extsockclass()) return 0; @@ -5479,8 +5498,8 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { - struct sk_security_struct *sksec = sk->sk_security; - struct sk_security_struct *newsksec = newsk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); + struct sk_security_struct *newsksec = selinux_sock(newsk); /* If policy does not support SECCLASS_SCTP_SOCKET then call * the non-sctp clone version. @@ -5512,7 +5531,7 @@ static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk) static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); int err; u16 family = req->rsk_ops->family; u32 connsid; @@ -5533,7 +5552,7 @@ static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb, static void selinux_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { - struct sk_security_struct *newsksec = newsk->sk_security; + struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->sid = req->secid; newsksec->peer_sid = req->peer_secid; @@ -5550,7 +5569,7 @@ static void selinux_inet_csk_clone(struct sock *newsk, static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) @@ -5631,7 +5650,7 @@ static int selinux_tun_dev_attach_queue(void *security) static int selinux_tun_dev_attach(struct sock *sk, void *security) { struct tun_security_struct *tunsec = security; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); /* we don't currently perform any NetLabel based labeling here and it * isn't clear that we would want to do so anyway; while we could apply @@ -5711,7 +5730,7 @@ static unsigned int selinux_ip_forward(void *priv, struct sk_buff *skb, SECCLASS_PACKET, PACKET__FORWARD_IN, &ad)) return NF_DROP; - if (netlbl_enabled()) + if (selinux_netlbl_enabled()) /* we do this in the FORWARD path and not the POST_ROUTING * path because we want to make sure we apply the necessary * labeling before IPsec is applied so we can leverage AH @@ -5728,7 +5747,7 @@ static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb, struct sock *sk; u32 sid; - if (!netlbl_enabled()) + if (!selinux_netlbl_enabled()) return NF_ACCEPT; /* we do this in the LOCAL_OUT path and not the POST_ROUTING path @@ -5754,7 +5773,7 @@ static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb, return NF_ACCEPT; /* standard practice, label using the parent socket */ - sksec = sk->sk_security; + sksec = selinux_sock(sk); sid = sksec->sid; } else sid = SECINITSID_KERNEL; @@ -5777,7 +5796,7 @@ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, sk = skb_to_full_sk(skb); if (sk == NULL) return NF_ACCEPT; - sksec = sk->sk_security; + sksec = selinux_sock(sk); ad_net_init_from_iif(&ad, &net, state->out->ifindex, state->pf); if (selinux_parse_skb(skb, &ad, NULL, 0, &proto)) @@ -5866,7 +5885,7 @@ static unsigned int selinux_ip_postroute(void *priv, u32 skb_sid; struct sk_security_struct *sksec; - sksec = sk->sk_security; + sksec = selinux_sock(sk); if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL @@ -5895,7 +5914,7 @@ static unsigned int selinux_ip_postroute(void *priv, } else { /* Locally generated packet, fetch the security label from the * associated socket. */ - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); peer_sid = sksec->sid; secmark_perm = PACKET__SEND; } @@ -5938,7 +5957,7 @@ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) unsigned int data_len = skb->len; unsigned char *data = skb->data; struct nlmsghdr *nlh; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); u16 sclass = sksec->sclass; u32 perm; @@ -6330,10 +6349,11 @@ static int selinux_ipc_permission(struct kern_ipc_perm *ipcp, short flag) return ipc_has_perm(ipcp, av); } -static void selinux_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) +static void selinux_ipc_getlsmblob(struct kern_ipc_perm *ipcp, + struct lsmblob *blob) { struct ipc_security_struct *isec = selinux_ipc(ipcp); - *secid = isec->sid; + blob->selinux.secid = isec->sid; } static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) @@ -6556,7 +6576,7 @@ static int selinux_lsm_setattr(u64 attr, void *value, size_t size) * There will only ever be one attribute. */ static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, - size_t *size, u32 flags) + u32 *size, u32 flags) { int rc; char *val = NULL; @@ -6571,7 +6591,7 @@ static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, } static int selinux_setselfattr(unsigned int attr, struct lsm_ctx *ctx, - size_t size, u32 flags) + u32 size, u32 flags) { int rc; @@ -6610,10 +6630,42 @@ static int selinux_ismaclabel(const char *name) return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0); } -static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +static int selinux_secid_to_secctx(u32 secid, struct lsmcontext *cp) +{ + u32 seclen; + u32 ret; + + if (cp) { + cp->id = LSM_ID_SELINUX; + ret = security_sid_to_context(secid, &cp->context, &cp->len); + if (ret < 0) + return ret; + return cp->len; + } + ret = security_sid_to_context(secid, NULL, &seclen); + if (ret < 0) + return ret; + return seclen; +} + +static int selinux_lsmblob_to_secctx(struct lsmblob *blob, + struct lsmcontext *cp) { - return security_sid_to_context(secid, - secdata, seclen); + u32 secid = blob->selinux.secid; + u32 seclen; + u32 ret; + + if (cp) { + cp->id = LSM_ID_SELINUX; + ret = security_sid_to_context(secid, &cp->context, &cp->len); + if (ret < 0) + return ret; + return cp->len; + } + ret = security_sid_to_context(secid, NULL, &seclen); + if (ret < 0) + return ret; + return seclen; } static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) @@ -6622,9 +6674,10 @@ static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) secid, GFP_KERNEL); } -static void selinux_release_secctx(char *secdata, u32 seclen) +static void selinux_release_secctx(struct lsmcontext *cp) { - kfree(secdata); + if (cp->id == LSM_ID_SELINUX) + kfree(cp->context); } static void selinux_inode_invalidate_secctx(struct inode *inode) @@ -6656,14 +6709,16 @@ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) ctx, ctxlen, 0); } -static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +static int selinux_inode_getsecctx(struct inode *inode, struct lsmcontext *cp) { - int len = 0; + int len; len = selinux_inode_getsecurity(&nop_mnt_idmap, inode, - XATTR_SELINUX_SUFFIX, ctx, true); + XATTR_SELINUX_SUFFIX, + (void **)&cp->context, true); if (len < 0) return len; - *ctxlen = len; + cp->len = len; + cp->id = LSM_ID_SELINUX; return 0; } #ifdef CONFIG_KEYS @@ -6672,11 +6727,7 @@ static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { const struct task_security_struct *tsec; - struct key_security_struct *ksec; - - ksec = kzalloc(sizeof(struct key_security_struct), GFP_KERNEL); - if (!ksec) - return -ENOMEM; + struct key_security_struct *ksec = selinux_key(k); tsec = selinux_cred(cred); if (tsec->keycreate_sid) @@ -6684,18 +6735,9 @@ static int selinux_key_alloc(struct key *k, const struct cred *cred, else ksec->sid = tsec->sid; - k->security = ksec; return 0; } -static void selinux_key_free(struct key *k) -{ - struct key_security_struct *ksec = k->security; - - k->security = NULL; - kfree(ksec); -} - static int selinux_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) @@ -6736,14 +6778,14 @@ static int selinux_key_permission(key_ref_t key_ref, sid = cred_sid(cred); key = key_ref_to_ptr(key_ref); - ksec = key->security; + ksec = selinux_key(key); return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) { - struct key_security_struct *ksec = key->security; + struct key_security_struct *ksec = selinux_key(key); char *context = NULL; unsigned len; int rc; @@ -6970,9 +7012,16 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), +#ifdef CONFIG_KEYS + .lbs_key = sizeof(struct key_security_struct), +#endif /* CONFIG_KEYS */ .lbs_msg_msg = sizeof(struct msg_security_struct), + .lbs_sock = sizeof(struct sk_security_struct), .lbs_superblock = sizeof(struct superblock_security_struct), .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS, + .lbs_mnt_opts = sizeof(struct selinux_mnt_opts), + .lbs_secmark = true, + .lbs_netlabel = true, }; #ifdef CONFIG_PERF_EVENTS @@ -7090,6 +7139,7 @@ static int selinux_uring_cmd(struct io_uring_cmd *ioucmd) static const struct lsm_id selinux_lsmid = { .name = "selinux", .id = LSM_ID_SELINUX, + .lsmblob = true, }; /* @@ -7168,7 +7218,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_getsecurity, selinux_inode_getsecurity), LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity), LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity), - LSM_HOOK_INIT(inode_getsecid, selinux_inode_getsecid), + LSM_HOOK_INIT(inode_getlsmblob, selinux_inode_getlsmblob), LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up), LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr), LSM_HOOK_INIT(path_notify, selinux_path_notify), @@ -7194,6 +7244,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare), LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer), LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid), + LSM_HOOK_INIT(cred_getlsmblob, selinux_cred_getlsmblob), LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as), LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request), @@ -7202,8 +7253,8 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), - LSM_HOOK_INIT(current_getsecid_subj, selinux_current_getsecid_subj), - LSM_HOOK_INIT(task_getsecid_obj, selinux_task_getsecid_obj), + LSM_HOOK_INIT(current_getlsmblob_subj, selinux_current_getlsmblob_subj), + LSM_HOOK_INIT(task_getlsmblob_obj, selinux_task_getlsmblob_obj), LSM_HOOK_INIT(task_setnice, selinux_task_setnice), LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio), LSM_HOOK_INIT(task_getioprio, selinux_task_getioprio), @@ -7217,7 +7268,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(userns_create, selinux_userns_create), LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission), - LSM_HOOK_INIT(ipc_getsecid, selinux_ipc_getsecid), + LSM_HOOK_INIT(ipc_getlsmblob, selinux_ipc_getlsmblob), LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl), @@ -7306,7 +7357,6 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { #endif #ifdef CONFIG_KEYS - LSM_HOOK_INIT(key_free, selinux_key_free), LSM_HOOK_INIT(key_permission, selinux_key_permission), LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS @@ -7363,6 +7413,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx), + LSM_HOOK_INIT(lsmblob_to_secctx, selinux_lsmblob_to_secctx), LSM_HOOK_INIT(inode_getsecctx, selinux_inode_getsecctx), LSM_HOOK_INIT(sk_alloc_security, selinux_sk_alloc_security), LSM_HOOK_INIT(tun_dev_alloc_security, selinux_tun_dev_alloc_security), diff --git a/security/selinux/include/audit.h b/security/selinux/include/audit.h index 52aca71210b47..2fceeb59b0d77 100644 --- a/security/selinux/include/audit.h +++ b/security/selinux/include/audit.h @@ -21,33 +21,39 @@ * @op: the operator the rule uses * @rulestr: the text "target" of the rule * @rule: pointer to the new rule structure returned via this + * @lsmid: the relevant LSM + * @gfp: GFP flag used for kmalloc * * Returns 0 if successful, -errno if not. On success, the rule structure * will be allocated internally. The caller must free this structure with * selinux_audit_rule_free() after use. */ -int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **rule); +int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **rule, + int lsmid, gfp_t gfp); /** * selinux_audit_rule_free - free an selinux audit rule structure. * @rule: pointer to the audit rule to be freed + * @lsmid: which LSM this rule relates to * * This will free all memory associated with the given rule. * If @rule is NULL, no operation is performed. */ -void selinux_audit_rule_free(void *rule); +void selinux_audit_rule_free(void *rule, int lsmid); /** * selinux_audit_rule_match - determine if a context ID matches a rule. - * @sid: the context ID to check + * @blob: includes the context ID to check * @field: the field this rule refers to * @op: the operator the rule uses * @rule: pointer to the audit rule to check against + * @lsmid: the relevant LSM * * Returns 1 if the context id matches the rule, 0 if it does not, and * -errno on failure. */ -int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *rule); +int selinux_audit_rule_match(struct lsmblob *blob, u32 field, u32 op, + void *rule, int lsmid); /** * selinux_audit_rule_known - check to see if rule contains selinux fields. diff --git a/security/selinux/include/netlabel.h b/security/selinux/include/netlabel.h index 5731c0dcd3e8f..5be82aa8e7caf 100644 --- a/security/selinux/include/netlabel.h +++ b/security/selinux/include/netlabel.h @@ -134,4 +134,9 @@ static inline int selinux_netlbl_socket_connect_locked(struct sock *sk, } #endif /* CONFIG_NETLABEL */ +static inline bool selinux_netlbl_enabled(void) +{ + return selinux_blob_sizes.lbs_netlabel && netlbl_enabled(); +} + #endif diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index dea1d6f3ed2d3..83b9443d69190 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -195,4 +195,16 @@ selinux_superblock(const struct super_block *superblock) return superblock->s_security + selinux_blob_sizes.lbs_superblock; } +#ifdef CONFIG_KEYS +static inline struct key_security_struct *selinux_key(const struct key *key) +{ + return key->security + selinux_blob_sizes.lbs_key; +} +#endif /* CONFIG_KEYS */ + +static inline struct sk_security_struct *selinux_sock(const struct sock *sock) +{ + return sock->sk_security + selinux_blob_sizes.lbs_sock; +} + #endif /* _SELINUX_OBJSEC_H_ */ diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c index 8f182800e4124..1242296b5fe14 100644 --- a/security/selinux/netlabel.c +++ b/security/selinux/netlabel.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -68,7 +69,7 @@ static int selinux_netlbl_sidlookup_cached(struct sk_buff *skb, static struct netlbl_lsm_secattr *selinux_netlbl_sock_genattr(struct sock *sk) { int rc; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr *secattr; if (sksec->nlbl_secattr != NULL) @@ -100,7 +101,7 @@ static struct netlbl_lsm_secattr *selinux_netlbl_sock_getattr( const struct sock *sk, u32 sid) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr *secattr = sksec->nlbl_secattr; if (secattr == NULL) @@ -197,7 +198,7 @@ int selinux_netlbl_skbuff_getsid(struct sk_buff *skb, int rc; struct netlbl_lsm_secattr secattr; - if (!netlbl_enabled()) { + if (!selinux_netlbl_enabled()) { *type = NETLBL_NLTYPE_NONE; *sid = SECSID_NULL; return 0; @@ -240,7 +241,7 @@ int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, * being labeled by it's parent socket, if it is just exit */ sk = skb_to_full_sk(skb); if (sk != NULL) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); if (sksec->nlbl_state != NLBL_REQSKB) return 0; @@ -277,7 +278,7 @@ int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc, { int rc; struct netlbl_lsm_secattr secattr; - struct sk_security_struct *sksec = asoc->base.sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(asoc->base.sk); struct sockaddr_in addr4; struct sockaddr_in6 addr6; @@ -356,7 +357,7 @@ int selinux_netlbl_inet_conn_request(struct request_sock *req, u16 family) */ void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); if (family == PF_INET) sksec->nlbl_state = NLBL_LABELED; @@ -374,8 +375,8 @@ void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family) */ void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk) { - struct sk_security_struct *sksec = sk->sk_security; - struct sk_security_struct *newsksec = newsk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); + struct sk_security_struct *newsksec = selinux_sock(newsk); newsksec->nlbl_state = sksec->nlbl_state; } @@ -393,7 +394,7 @@ void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk) int selinux_netlbl_socket_post_create(struct sock *sk, u16 family) { int rc; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr *secattr; if (family != PF_INET && family != PF_INET6) @@ -439,7 +440,7 @@ int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec, u32 perm; struct netlbl_lsm_secattr secattr; - if (!netlbl_enabled()) + if (!selinux_netlbl_enabled()) return 0; netlbl_secattr_init(&secattr); @@ -507,7 +508,7 @@ int selinux_netlbl_socket_setsockopt(struct socket *sock, { int rc = 0; struct sock *sk = sock->sk; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr secattr; if (selinux_netlbl_option(level, optname) && @@ -545,7 +546,7 @@ static int selinux_netlbl_socket_connect_helper(struct sock *sk, struct sockaddr *addr) { int rc; - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); struct netlbl_lsm_secattr *secattr; /* connected sockets are allowed to disconnect when the address family @@ -584,7 +585,7 @@ static int selinux_netlbl_socket_connect_helper(struct sock *sk, int selinux_netlbl_socket_connect_locked(struct sock *sk, struct sockaddr *addr) { - struct sk_security_struct *sksec = sk->sk_security; + struct sk_security_struct *sksec = selinux_sock(sk); if (sksec->nlbl_state != NLBL_REQSKB && sksec->nlbl_state != NLBL_CONNLABELED) diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 0619a1cbbfbe4..074d6c2714eb5 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -2123,7 +2123,6 @@ static struct file_system_type sel_fs_type = { .kill_sb = sel_kill_sb, }; -static struct vfsmount *selinuxfs_mount __ro_after_init; struct path selinux_null __ro_after_init; static int __init init_sel_fs(void) @@ -2145,18 +2144,21 @@ static int __init init_sel_fs(void) return err; } - selinux_null.mnt = selinuxfs_mount = kern_mount(&sel_fs_type); - if (IS_ERR(selinuxfs_mount)) { + selinux_null.mnt = kern_mount(&sel_fs_type); + if (IS_ERR(selinux_null.mnt)) { pr_err("selinuxfs: could not mount!\n"); - err = PTR_ERR(selinuxfs_mount); - selinuxfs_mount = NULL; + err = PTR_ERR(selinux_null.mnt); + selinux_null.mnt = NULL; + return err; } + selinux_null.dentry = d_hash_and_lookup(selinux_null.mnt->mnt_root, &null_name); if (IS_ERR(selinux_null.dentry)) { pr_err("selinuxfs: could not lookup null!\n"); err = PTR_ERR(selinux_null.dentry); selinux_null.dentry = NULL; + return err; } return err; diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index e88b1b6c4adbb..d0267596f2ab1 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -3498,17 +3498,20 @@ struct selinux_audit_rule { struct context au_ctxt; }; -void selinux_audit_rule_free(void *vrule) +void selinux_audit_rule_free(void *vrule, int lsmid) { struct selinux_audit_rule *rule = vrule; + if (lsmid != LSM_ID_UNDEF || lsmid != LSM_ID_SELINUX) + return; if (rule) { context_destroy(&rule->au_ctxt); kfree(rule); } } -int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, + int lsmid, gfp_t gfp) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; @@ -3522,6 +3525,8 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) *rule = NULL; + if (lsmid != LSM_ID_UNDEF || lsmid != LSM_ID_SELINUX) + return 0; if (!selinux_initialized()) return -EOPNOTSUPP; @@ -3549,7 +3554,7 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) return -EINVAL; } - tmprule = kzalloc(sizeof(struct selinux_audit_rule), GFP_KERNEL); + tmprule = kzalloc(sizeof(struct selinux_audit_rule), gfp); if (!tmprule) return -ENOMEM; context_init(&tmprule->au_ctxt); @@ -3603,7 +3608,7 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) err: rcu_read_unlock(); - selinux_audit_rule_free(tmprule); + selinux_audit_rule_free(tmprule, LSM_ID_SELINUX); *rule = NULL; return rc; } @@ -3633,7 +3638,8 @@ int selinux_audit_rule_known(struct audit_krule *rule) return 0; } -int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) +int selinux_audit_rule_match(struct lsmblob *blob, u32 field, u32 op, + void *vrule, int lsmid) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; @@ -3642,6 +3648,8 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) struct selinux_audit_rule *rule = vrule; int match = 0; + if (lsmid != LSM_ID_UNDEF || lsmid != LSM_ID_SELINUX) + return 0; if (unlikely(!rule)) { WARN_ONCE(1, "selinux_audit_rule_match: missing rule\n"); return -ENOENT; @@ -3659,10 +3667,10 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) goto out; } - ctxt = sidtab_search(policy->sidtab, sid); + ctxt = sidtab_search(policy->sidtab, blob->selinux.secid); if (unlikely(!ctxt)) { WARN_ONCE(1, "selinux_audit_rule_match: unrecognized SID %d\n", - sid); + blob->selinux.secid); match = -ENOENT; goto out; } diff --git a/security/smack/smack.h b/security/smack/smack.h index 041688e5a77a3..2191f8304e4f2 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -355,6 +355,23 @@ static inline struct superblock_smack *smack_superblock( return superblock->s_security + smack_blob_sizes.lbs_superblock; } +static inline struct socket_smack *smack_sock(const struct sock *sock) +{ + return sock->sk_security + smack_blob_sizes.lbs_sock; +} + +#ifdef CONFIG_KEYS +static inline struct smack_known **smack_key(const struct key *key) +{ + return key->security + smack_blob_sizes.lbs_key; +} +#endif /* CONFIG_KEYS */ + +static inline bool smack_netlabel(void) +{ + return smack_blob_sizes.lbs_netlabel; +} + /* * Is the directory transmuting? */ @@ -364,6 +381,11 @@ static inline int smk_inode_transmutable(const struct inode *isp) return (sip->smk_flags & SMK_INODE_TRANSMUTE) != 0; } +static inline bool smack_secmark(void) +{ + return smack_blob_sizes.lbs_secmark; +} + /* * Present a pointer to the smack label entry in an inode blob. */ diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 0fdbf04cc2583..b33abdaf4b61d 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -561,6 +561,7 @@ static int smack_sb_alloc_security(struct super_block *sb) } struct smack_mnt_opts { + bool initialized; const char *fsdefault; const char *fsfloor; const char *fshat; @@ -568,24 +569,37 @@ struct smack_mnt_opts { const char *fstransmute; }; +static inline struct smack_mnt_opts *smack_mnt_opts(void *mnt_opts) +{ + if (mnt_opts) + return mnt_opts + smack_blob_sizes.lbs_mnt_opts; + return NULL; +} + static void smack_free_mnt_opts(void *mnt_opts) { - kfree(mnt_opts); + struct smack_mnt_opts *opts; + + if (mnt_opts) { + opts = smack_mnt_opts(mnt_opts); + opts->initialized = false; + } } static int smack_add_opt(int token, const char *s, void **mnt_opts) { - struct smack_mnt_opts *opts = *mnt_opts; + struct smack_mnt_opts *opts; struct smack_known *skp; - if (!opts) { - opts = kzalloc(sizeof(struct smack_mnt_opts), GFP_KERNEL); - if (!opts) + if (!s) + return -EINVAL; + + if (!*mnt_opts) { + *mnt_opts = lsm_mnt_opts_alloc(GFP_KERNEL); + if (!*mnt_opts) return -ENOMEM; - *mnt_opts = opts; } - if (!s) - return -ENOMEM; + opts = smack_mnt_opts(*mnt_opts); skp = smk_import_entry(s, 0); if (IS_ERR(skp)) @@ -618,6 +632,7 @@ static int smack_add_opt(int token, const char *s, void **mnt_opts) opts->fstransmute = skp->smk_known; break; } + opts->initialized = true; return 0; out_opt_err: @@ -639,10 +654,12 @@ static int smack_fs_context_submount(struct fs_context *fc, struct smack_mnt_opts *ctx; struct inode_smack *isp; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; - fc->security = ctx; + if (!fc->security) { + fc->security = lsm_mnt_opts_alloc(GFP_KERNEL); + if (!fc->security) + return -ENOMEM; + } + ctx = smack_mnt_opts(fc->security); sbsp = smack_superblock(reference); isp = smack_inode(reference->s_root->d_inode); @@ -672,6 +689,7 @@ static int smack_fs_context_submount(struct fs_context *fc, return -ENOMEM; } } + ctx->initialized = true; return 0; } @@ -685,16 +703,21 @@ static int smack_fs_context_submount(struct fs_context *fc, static int smack_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { - struct smack_mnt_opts *dst, *src = src_fc->security; + struct smack_mnt_opts *src; + struct smack_mnt_opts *dst; + src = smack_mnt_opts(src_fc->security); if (!src) return 0; - fc->security = kzalloc(sizeof(struct smack_mnt_opts), GFP_KERNEL); - if (!fc->security) - return -ENOMEM; + if (!fc->security) { + fc->security = lsm_mnt_opts_alloc(GFP_KERNEL); + if (!fc->security) + return -ENOMEM; + } - dst = fc->security; + dst = smack_mnt_opts(fc->security); + dst->initialized = src->initialized; dst->fsdefault = src->fsdefault; dst->fsfloor = src->fsfloor; dst->fshat = src->fshat; @@ -804,7 +827,7 @@ static int smack_set_mnt_opts(struct super_block *sb, struct superblock_smack *sp = smack_superblock(sb); struct inode_smack *isp; struct smack_known *skp; - struct smack_mnt_opts *opts = mnt_opts; + struct smack_mnt_opts *opts = smack_mnt_opts(mnt_opts); bool transmute = false; if (sp->smk_flags & SMK_SB_INITIALIZED) @@ -837,7 +860,7 @@ static int smack_set_mnt_opts(struct super_block *sb, sp->smk_flags |= SMK_SB_INITIALIZED; - if (opts) { + if (opts && opts->initialized) { if (opts->fsdefault) { skp = smk_import_entry(opts->fsdefault, 0); if (IS_ERR(skp)) @@ -1314,11 +1337,12 @@ static int smack_inode_setxattr(struct mnt_idmap *idmap, check_star = 1; } else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0) { check_priv = 1; - if (size != TRANS_TRUE_SIZE || + if (!S_ISDIR(d_backing_inode(dentry)->i_mode) || + size != TRANS_TRUE_SIZE || strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) rc = -EINVAL; } else - rc = cap_inode_setxattr(dentry, name, value, size, flags); + rc = -ENOSYS; if (check_priv && !smack_privileged(CAP_MAC_ADMIN)) rc = -EPERM; @@ -1332,11 +1356,11 @@ static int smack_inode_setxattr(struct mnt_idmap *idmap, rc = -EINVAL; } - smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY); - smk_ad_setfield_u_fs_path_dentry(&ad, dentry); - if (rc == 0) { - rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_WRITE, &ad); + smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY); + smk_ad_setfield_u_fs_path_dentry(&ad, dentry); + rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), + MAY_WRITE, &ad); rc = smk_bu_inode(d_backing_inode(dentry), MAY_WRITE, rc); } @@ -1573,7 +1597,7 @@ static int smack_inode_getsecurity(struct mnt_idmap *idmap, if (sock == NULL || sock->sk == NULL) return -EOPNOTSUPP; - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); if (strcmp(name, XATTR_SMACK_IPIN) == 0) isp = ssp->smk_in; @@ -1616,15 +1640,13 @@ static int smack_inode_listsecurity(struct inode *inode, char *buffer, } /** - * smack_inode_getsecid - Extract inode's security id + * smack_inode_getlsmblob - Extract inode's security id * @inode: inode to extract the info from - * @secid: where result will be saved + * @blob: where result will be saved */ -static void smack_inode_getsecid(struct inode *inode, u32 *secid) +static void smack_inode_getlsmblob(struct inode *inode, struct lsmblob *blob) { - struct smack_known *skp = smk_of_inode(inode); - - *secid = skp->smk_secid; + blob->smack.skp = smk_of_inode(inode); } /* @@ -1961,7 +1983,7 @@ static int smack_file_receive(struct file *file) if (inode->i_sb->s_magic == SOCKFS_MAGIC) { sock = SOCKET_I(inode); - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); tsp = smack_cred(current_cred()); /* * If the receiving process can't write to the @@ -2120,6 +2142,21 @@ static void smack_cred_getsecid(const struct cred *cred, u32 *secid) rcu_read_unlock(); } +/** + * smack_cred_getlsmblob - get the Smack label for a creds structure + * @cred: the object creds + * @blob: where to put the data + * + * Sets the Smack part of the blob + */ +static void smack_cred_getlsmblob(const struct cred *cred, + struct lsmblob *blob) +{ + rcu_read_lock(); + blob->smack.skp = smk_of_task(smack_cred(cred)); + rcu_read_unlock(); +} + /** * smack_kernel_act_as - Set the subjective context in a set of credentials * @new: points to the set of credentials to be modified. @@ -2211,30 +2248,27 @@ static int smack_task_getsid(struct task_struct *p) } /** - * smack_current_getsecid_subj - get the subjective secid of the current task - * @secid: where to put the result + * smack_current_getlsmblob_subj - get the subjective secid of the current task + * @blob: where to put the result * * Sets the secid to contain a u32 version of the task's subjective smack label. */ -static void smack_current_getsecid_subj(u32 *secid) +static void smack_current_getlsmblob_subj(struct lsmblob *blob) { - struct smack_known *skp = smk_of_current(); - - *secid = skp->smk_secid; + blob->smack.skp = smk_of_current(); } /** - * smack_task_getsecid_obj - get the objective secid of the task + * smack_task_getlsmblob_obj - get the objective data of the task * @p: the task * @secid: where to put the result * * Sets the secid to contain a u32 version of the task's objective smack label. */ -static void smack_task_getsecid_obj(struct task_struct *p, u32 *secid) +static void smack_task_getlsmblob_obj(struct task_struct *p, + struct lsmblob *blob) { - struct smack_known *skp = smk_of_task_struct_obj(p); - - *secid = skp->smk_secid; + blob->smack.skp = smk_of_task_struct_obj(p); } /** @@ -2381,11 +2415,7 @@ static void smack_task_to_inode(struct task_struct *p, struct inode *inode) static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags) { struct smack_known *skp = smk_of_current(); - struct socket_smack *ssp; - - ssp = kzalloc(sizeof(struct socket_smack), gfp_flags); - if (ssp == NULL) - return -ENOMEM; + struct socket_smack *ssp = smack_sock(sk); /* * Sockets created by kernel threads receive web label. @@ -2399,11 +2429,10 @@ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags) } ssp->smk_packet = NULL; - sk->sk_security = ssp; - return 0; } +#ifdef SMACK_IPV6_PORT_LABELING /** * smack_sk_free_security - Free a socket blob * @sk: the socket @@ -2412,7 +2441,6 @@ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags) */ static void smack_sk_free_security(struct sock *sk) { -#ifdef SMACK_IPV6_PORT_LABELING struct smk_port_label *spp; if (sk->sk_family == PF_INET6) { @@ -2425,9 +2453,8 @@ static void smack_sk_free_security(struct sock *sk) } rcu_read_unlock(); } -#endif - kfree(sk->sk_security); } +#endif /** * smack_sk_clone_security - Copy security context @@ -2438,8 +2465,8 @@ static void smack_sk_free_security(struct sock *sk) */ static void smack_sk_clone_security(const struct sock *sk, struct sock *newsk) { - struct socket_smack *ssp_old = sk->sk_security; - struct socket_smack *ssp_new = newsk->sk_security; + struct socket_smack *ssp_old = smack_sock(sk); + struct socket_smack *ssp_new = smack_sock(newsk); *ssp_new = *ssp_old; } @@ -2555,10 +2582,13 @@ static struct smack_known *smack_ipv6host_label(struct sockaddr_in6 *sip) */ static int smack_netlbl_add(struct sock *sk) { - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smack_known *skp = ssp->smk_out; int rc; + if (!smack_netlabel()) + return 0; + local_bh_disable(); bh_lock_sock_nested(sk); @@ -2587,7 +2617,10 @@ static int smack_netlbl_add(struct sock *sk) */ static void smack_netlbl_delete(struct sock *sk) { - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); + + if (!smack_netlabel()) + return; /* * Take the label off the socket if one is set. @@ -2619,7 +2652,7 @@ static int smk_ipv4_check(struct sock *sk, struct sockaddr_in *sap) struct smack_known *skp; int rc = 0; struct smack_known *hkp; - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smk_audit_info ad; rcu_read_lock(); @@ -2639,7 +2672,7 @@ static int smk_ipv4_check(struct sock *sk, struct sockaddr_in *sap) /* * Clear the socket netlabel if it's set. */ - if (!rc) + if (!rc && smack_netlabel()) smack_netlbl_delete(sk); } rcu_read_unlock(); @@ -2692,7 +2725,7 @@ static void smk_ipv6_port_label(struct socket *sock, struct sockaddr *address) { struct sock *sk = sock->sk; struct sockaddr_in6 *addr6; - struct socket_smack *ssp = sock->sk->sk_security; + struct socket_smack *ssp = smack_sock(sock->sk); struct smk_port_label *spp; unsigned short port = 0; @@ -2780,7 +2813,7 @@ static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address, int act) { struct smk_port_label *spp; - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smack_known *skp = NULL; unsigned short port; struct smack_known *object; @@ -2855,6 +2888,15 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name, if (value == NULL || size > SMK_LONGLABEL || size == 0) return -EINVAL; + if (strcmp(name, XATTR_SMACK_TRANSMUTE) == 0) { + if (!S_ISDIR(inode->i_mode) || size != TRANS_TRUE_SIZE || + strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) + return -EINVAL; + + nsp->smk_flags |= SMK_INODE_TRANSMUTE; + return 0; + } + skp = smk_import_entry(value, size); if (IS_ERR(skp)) return PTR_ERR(skp); @@ -2874,7 +2916,7 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name, if (sock == NULL || sock->sk == NULL) return -EOPNOTSUPP; - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); if (strcmp(name, XATTR_SMACK_IPIN) == 0) ssp->smk_in = skp; @@ -2922,7 +2964,7 @@ static int smack_socket_post_create(struct socket *sock, int family, * Sockets created by kernel threads receive web label. */ if (unlikely(current->flags & PF_KTHREAD)) { - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); ssp->smk_in = &smack_known_web; ssp->smk_out = &smack_known_web; } @@ -2947,8 +2989,8 @@ static int smack_socket_post_create(struct socket *sock, int family, static int smack_socket_socketpair(struct socket *socka, struct socket *sockb) { - struct socket_smack *asp = socka->sk->sk_security; - struct socket_smack *bsp = sockb->sk->sk_security; + struct socket_smack *asp = smack_sock(socka->sk); + struct socket_smack *bsp = smack_sock(sockb->sk); asp->smk_packet = bsp->smk_out; bsp->smk_packet = asp->smk_out; @@ -3011,7 +3053,7 @@ static int smack_socket_connect(struct socket *sock, struct sockaddr *sap, if (__is_defined(SMACK_IPV6_SECMARK_LABELING)) rsp = smack_ipv6host_label(sip); if (rsp != NULL) { - struct socket_smack *ssp = sock->sk->sk_security; + struct socket_smack *ssp = smack_sock(sock->sk); rc = smk_ipv6_check(ssp->smk_out, rsp, sip, SMK_CONNECTING); @@ -3404,16 +3446,16 @@ static int smack_ipc_permission(struct kern_ipc_perm *ipp, short flag) } /** - * smack_ipc_getsecid - Extract smack security id + * smack_ipc_getlsmblob - Extract smack security data * @ipp: the object permissions - * @secid: where result will be saved + * @blob: where result will be saved */ -static void smack_ipc_getsecid(struct kern_ipc_perm *ipp, u32 *secid) +static void smack_ipc_getlsmblob(struct kern_ipc_perm *ipp, + struct lsmblob *blob) { - struct smack_known **blob = smack_ipc(ipp); - struct smack_known *iskp = *blob; + struct smack_known **iskpp = smack_ipc(ipp); - *secid = iskp->smk_secid; + blob->smack.skp = *iskpp; } /** @@ -3641,7 +3683,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode) * There will only ever be one attribute. */ static int smack_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx, - size_t *size, u32 flags) + u32 *size, u32 flags) { int rc; struct smack_known *skp; @@ -3762,7 +3804,7 @@ static int do_setattr(u64 attr, void *value, size_t size) * Returns 0 on success, an error code otherwise. */ static int smack_setselfattr(unsigned int attr, struct lsm_ctx *ctx, - size_t size, u32 flags) + u32 size, u32 flags) { int rc; @@ -3806,9 +3848,9 @@ static int smack_unix_stream_connect(struct sock *sock, { struct smack_known *skp; struct smack_known *okp; - struct socket_smack *ssp = sock->sk_security; - struct socket_smack *osp = other->sk_security; - struct socket_smack *nsp = newsk->sk_security; + struct socket_smack *ssp = smack_sock(sock); + struct socket_smack *osp = smack_sock(other); + struct socket_smack *nsp = smack_sock(newsk); struct smk_audit_info ad; int rc = 0; #ifdef CONFIG_AUDIT @@ -3854,8 +3896,8 @@ static int smack_unix_stream_connect(struct sock *sock, */ static int smack_unix_may_send(struct socket *sock, struct socket *other) { - struct socket_smack *ssp = sock->sk->sk_security; - struct socket_smack *osp = other->sk->sk_security; + struct socket_smack *ssp = smack_sock(sock->sk); + struct socket_smack *osp = smack_sock(other->sk); struct smk_audit_info ad; int rc; @@ -3892,7 +3934,7 @@ static int smack_socket_sendmsg(struct socket *sock, struct msghdr *msg, struct sockaddr_in6 *sap = (struct sockaddr_in6 *) msg->msg_name; #endif #ifdef SMACK_IPV6_SECMARK_LABELING - struct socket_smack *ssp = sock->sk->sk_security; + struct socket_smack *ssp = smack_sock(sock->sk); struct smack_known *rsp; #endif int rc = 0; @@ -3945,6 +3987,8 @@ static struct smack_known *smack_from_secattr(struct netlbl_lsm_secattr *sap, int acat; int kcat; + if (!smack_netlabel()) + return smack_net_ambient; /* * Netlabel found it in the cache. */ @@ -4071,7 +4115,7 @@ static int smk_skb_to_addr_ipv6(struct sk_buff *skb, struct sockaddr_in6 *sip) #ifdef CONFIG_NETWORK_SECMARK static struct smack_known *smack_from_skb(struct sk_buff *skb) { - if (skb == NULL || skb->secmark == 0) + if (!smack_secmark() || skb == NULL || skb->secmark == 0) return NULL; return smack_from_secid(skb->secmark); @@ -4101,10 +4145,13 @@ static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family, struct socket_smack *ssp = NULL; struct smack_known *skp = NULL; + if (!smack_netlabel()) + return NULL; + netlbl_secattr_init(&secattr); if (sk) - ssp = sk->sk_security; + ssp = smack_sock(sk); if (netlbl_skbuff_getattr(skb, family, &secattr) == 0) { skp = smack_from_secattr(&secattr, ssp); @@ -4126,7 +4173,7 @@ static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family, */ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smack_known *skp = NULL; int rc = 0; struct smk_audit_info ad; @@ -4171,7 +4218,7 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) rc = smk_access(skp, ssp->smk_in, MAY_WRITE, &ad); rc = smk_bu_note("IPv4 delivery", skp, ssp->smk_in, MAY_WRITE, rc); - if (rc != 0) + if (rc != 0 && smack_netlabel()) netlbl_skbuff_err(skb, family, rc, 0); break; #if IS_ENABLED(CONFIG_IPV6) @@ -4230,7 +4277,7 @@ static int smack_socket_getpeersec_stream(struct socket *sock, u32 slen = 1; int rc = 0; - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); if (ssp->smk_packet != NULL) { rcp = ssp->smk_packet->smk_known; slen = strlen(rcp) + 1; @@ -4280,7 +4327,7 @@ static int smack_socket_getpeersec_dgram(struct socket *sock, switch (family) { case PF_UNIX: - ssp = sock->sk->sk_security; + ssp = smack_sock(sock->sk); s = ssp->smk_out->smk_secid; break; case PF_INET: @@ -4329,7 +4376,7 @@ static void smack_sock_graft(struct sock *sk, struct socket *parent) (sk->sk_family != PF_INET && sk->sk_family != PF_INET6)) return; - ssp = sk->sk_security; + ssp = smack_sock(sk); ssp->smk_in = skp; ssp->smk_out = skp; /* cssp->smk_packet is already set in smack_inet_csk_clone() */ @@ -4349,7 +4396,7 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb, { u16 family = sk->sk_family; struct smack_known *skp; - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct sockaddr_in addr; struct iphdr *hdr; struct smack_known *hskp; @@ -4382,7 +4429,7 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb, if (skp == NULL) { skp = smack_from_netlbl(sk, family, skb); if (skp == NULL) - skp = &smack_known_huh; + skp = smack_net_ambient; } #ifdef CONFIG_AUDIT @@ -4403,8 +4450,11 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb, /* * Save the peer's label in the request_sock so we can later setup * smk_packet in the child socket so that SO_PEERCRED can report it. + * + * Only do this if Smack is using netlabel. */ - req->peer_secid = skp->smk_secid; + if (smack_netlabel()) + req->peer_secid = skp->smk_secid; /* * We need to decide if we want to label the incoming connection here @@ -4417,10 +4467,12 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb, hskp = smack_ipv4host_label(&addr); rcu_read_unlock(); - if (hskp == NULL) - rc = netlbl_req_setattr(req, &skp->smk_netlabel); - else - netlbl_req_delattr(req); + if (smack_netlabel()) { + if (hskp == NULL) + rc = netlbl_req_setattr(req, &skp->smk_netlabel); + else + netlbl_req_delattr(req); + } return rc; } @@ -4435,10 +4487,10 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb, static void smack_inet_csk_clone(struct sock *sk, const struct request_sock *req) { - struct socket_smack *ssp = sk->sk_security; + struct socket_smack *ssp = smack_sock(sk); struct smack_known *skp; - if (req->peer_secid != 0) { + if (smack_netlabel() && req->peer_secid != 0) { skp = smack_from_secid(req->peer_secid); ssp->smk_packet = skp; } else @@ -4467,23 +4519,13 @@ static void smack_inet_csk_clone(struct sock *sk, static int smack_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { + struct smack_known **blob = smack_key(key); struct smack_known *skp = smk_of_task(smack_cred(cred)); - key->security = skp; + *blob = skp; return 0; } -/** - * smack_key_free - Clear the key security blob - * @key: the object - * - * Clear the blob pointer - */ -static void smack_key_free(struct key *key) -{ - key->security = NULL; -} - /** * smack_key_permission - Smack access on a key * @key_ref: gets to the object @@ -4497,6 +4539,8 @@ static int smack_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { + struct smack_known **blob; + struct smack_known *skp; struct key *keyp; struct smk_audit_info ad; struct smack_known *tkp = smk_of_task(smack_cred(cred)); @@ -4534,7 +4578,9 @@ static int smack_key_permission(key_ref_t key_ref, * If the key hasn't been initialized give it access so that * it may do so. */ - if (keyp->security == NULL) + blob = smack_key(keyp); + skp = *blob; + if (skp == NULL) return 0; /* * This should not occur @@ -4550,8 +4596,8 @@ static int smack_key_permission(key_ref_t key_ref, ad.a.u.key_struct.key = keyp->serial; ad.a.u.key_struct.key_desc = keyp->description; #endif - rc = smk_access(tkp, keyp->security, request, &ad); - rc = smk_bu_note("key access", tkp, keyp->security, request, rc); + rc = smk_access(tkp, skp, request, &ad); + rc = smk_bu_note("key access", tkp, skp, request, rc); return rc; } @@ -4566,11 +4612,12 @@ static int smack_key_permission(key_ref_t key_ref, */ static int smack_key_getsecurity(struct key *key, char **_buffer) { - struct smack_known *skp = key->security; + struct smack_known **blob = smack_key(key); + struct smack_known *skp = *blob; size_t length; char *copy; - if (key->security == NULL) { + if (skp == NULL) { *_buffer = NULL; return 0; } @@ -4680,16 +4727,21 @@ static int smack_post_notification(const struct cred *w_cred, * @op: required testing operator (=, !=, >, <, ...) * @rulestr: smack label to be audited * @vrule: pointer to save our own audit rule representation + * @lsmid: the relevant LSM + * @gfp: type of the memory for the allocation * * Prepare to audit cases where (@field @op @rulestr) is true. * The label to be audited is created if necessay. */ -static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, + int lsmid, gfp_t gfp) { struct smack_known *skp; char **rule = (char **)vrule; *rule = NULL; + if (lsmid != LSM_ID_UNDEF || lsmid != LSM_ID_SMACK) + return 0; if (field != AUDIT_SUBJ_USER && field != AUDIT_OBJ_USER) return -EINVAL; @@ -4730,19 +4782,23 @@ static int smack_audit_rule_known(struct audit_krule *krule) /** * smack_audit_rule_match - Audit given object ? - * @secid: security id for identifying the object to test + * @blob: security id for identifying the object to test * @field: audit rule flags given from user-space * @op: required testing operator * @vrule: smack internal rule presentation + * @lsmid: the relevant LSM * * The core Audit hook. It's used to take the decision of * whether to audit or not to audit a given object. */ -static int smack_audit_rule_match(u32 secid, u32 field, u32 op, void *vrule) +static int smack_audit_rule_match(struct lsmblob *blob, u32 field, u32 op, + void *vrule, int lsmid) { - struct smack_known *skp; + struct smack_known *skp = blob->smack.skp; char *rule = vrule; + if (lsmid != LSM_ID_UNDEF || lsmid != LSM_ID_SMACK) + return 0; if (unlikely(!rule)) { WARN_ONCE(1, "Smack: missing rule\n"); return -ENOENT; @@ -4751,8 +4807,6 @@ static int smack_audit_rule_match(u32 secid, u32 field, u32 op, void *vrule) if (field != AUDIT_SUBJ_USER && field != AUDIT_OBJ_USER) return 0; - skp = smack_from_secid(secid); - /* * No need to do string comparisons. If a match occurs, * both pointers will point to the same smack_known @@ -4782,23 +4836,47 @@ static int smack_ismaclabel(const char *name) return (strcmp(name, XATTR_SMACK_SUFFIX) == 0); } - /** * smack_secid_to_secctx - return the smack label for a secid * @secid: incoming integer - * @secdata: destination - * @seclen: how long it is + * @cp: destination * * Exists for networking code. */ -static int smack_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) +static int smack_secid_to_secctx(u32 secid, struct lsmcontext *cp) { struct smack_known *skp = smack_from_secid(secid); + int len = strlen(skp->smk_known); - if (secdata) - *secdata = skp->smk_known; - *seclen = strlen(skp->smk_known); - return 0; + if (cp) { + cp->context = skp->smk_known; + cp->len = len; + cp->id = LSM_ID_SMACK; + } + return len; +} + +/** + * smack_lsmblob_to_secctx - return the smack label + * @blob: includes incoming Smack data + * @secdata: destination + * @seclen: how long it is + * + * Exists for audit code. + */ +static int smack_lsmblob_to_secctx(struct lsmblob *blob, struct lsmcontext *cp) +{ + struct smack_known *skp = blob->smack.skp; + int len; + + len = strlen(skp->smk_known); + + if (cp) { + cp->context = skp->smk_known; + cp->len = len; + cp->id = LSM_ID_SMACK; + } + return len; } /** @@ -4838,12 +4916,13 @@ static int smack_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) ctx, ctxlen, 0); } -static int smack_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) +static int smack_inode_getsecctx(struct inode *inode, struct lsmcontext *cp) { struct smack_known *skp = smk_of_inode(inode); - *ctx = skp->smk_known; - *ctxlen = strlen(skp->smk_known); + cp->context = skp->smk_known; + cp->len = strlen(skp->smk_known); + cp->id = LSM_ID_SMACK; return 0; } @@ -5002,14 +5081,22 @@ struct lsm_blob_sizes smack_blob_sizes __ro_after_init = { .lbs_file = sizeof(struct smack_known *), .lbs_inode = sizeof(struct inode_smack), .lbs_ipc = sizeof(struct smack_known *), +#ifdef CONFIG_KEYS + .lbs_key = sizeof(struct smack_known *), +#endif /* CONFIG_KEYS */ .lbs_msg_msg = sizeof(struct smack_known *), + .lbs_sock = sizeof(struct socket_smack), .lbs_superblock = sizeof(struct superblock_smack), .lbs_xattr_count = SMACK_INODE_INIT_XATTRS, + .lbs_mnt_opts = sizeof(struct smack_mnt_opts), + .lbs_secmark = true, + .lbs_netlabel = true, }; static const struct lsm_id smack_lsmid = { .name = "smack", .id = LSM_ID_SMACK, + .lsmblob = true, }; static struct security_hook_list smack_hooks[] __ro_after_init = { @@ -5048,7 +5135,7 @@ static struct security_hook_list smack_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_getsecurity, smack_inode_getsecurity), LSM_HOOK_INIT(inode_setsecurity, smack_inode_setsecurity), LSM_HOOK_INIT(inode_listsecurity, smack_inode_listsecurity), - LSM_HOOK_INIT(inode_getsecid, smack_inode_getsecid), + LSM_HOOK_INIT(inode_getlsmblob, smack_inode_getlsmblob), LSM_HOOK_INIT(file_alloc_security, smack_file_alloc_security), LSM_HOOK_INIT(file_ioctl, smack_file_ioctl), @@ -5068,13 +5155,14 @@ static struct security_hook_list smack_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, smack_cred_prepare), LSM_HOOK_INIT(cred_transfer, smack_cred_transfer), LSM_HOOK_INIT(cred_getsecid, smack_cred_getsecid), + LSM_HOOK_INIT(cred_getlsmblob, smack_cred_getlsmblob), LSM_HOOK_INIT(kernel_act_as, smack_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, smack_kernel_create_files_as), LSM_HOOK_INIT(task_setpgid, smack_task_setpgid), LSM_HOOK_INIT(task_getpgid, smack_task_getpgid), LSM_HOOK_INIT(task_getsid, smack_task_getsid), - LSM_HOOK_INIT(current_getsecid_subj, smack_current_getsecid_subj), - LSM_HOOK_INIT(task_getsecid_obj, smack_task_getsecid_obj), + LSM_HOOK_INIT(current_getlsmblob_subj, smack_current_getlsmblob_subj), + LSM_HOOK_INIT(task_getlsmblob_obj, smack_task_getlsmblob_obj), LSM_HOOK_INIT(task_setnice, smack_task_setnice), LSM_HOOK_INIT(task_setioprio, smack_task_setioprio), LSM_HOOK_INIT(task_getioprio, smack_task_getioprio), @@ -5085,7 +5173,7 @@ static struct security_hook_list smack_hooks[] __ro_after_init = { LSM_HOOK_INIT(task_to_inode, smack_task_to_inode), LSM_HOOK_INIT(ipc_permission, smack_ipc_permission), - LSM_HOOK_INIT(ipc_getsecid, smack_ipc_getsecid), + LSM_HOOK_INIT(ipc_getlsmblob, smack_ipc_getlsmblob), LSM_HOOK_INIT(msg_msg_alloc_security, smack_msg_msg_alloc_security), @@ -5126,7 +5214,9 @@ static struct security_hook_list smack_hooks[] __ro_after_init = { LSM_HOOK_INIT(socket_getpeersec_stream, smack_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, smack_socket_getpeersec_dgram), LSM_HOOK_INIT(sk_alloc_security, smack_sk_alloc_security), +#ifdef SMACK_IPV6_PORT_LABELING LSM_HOOK_INIT(sk_free_security, smack_sk_free_security), +#endif LSM_HOOK_INIT(sk_clone_security, smack_sk_clone_security), LSM_HOOK_INIT(sock_graft, smack_sock_graft), LSM_HOOK_INIT(inet_conn_request, smack_inet_conn_request), @@ -5135,7 +5225,6 @@ static struct security_hook_list smack_hooks[] __ro_after_init = { /* key management security hooks */ #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_alloc, smack_key_alloc), - LSM_HOOK_INIT(key_free, smack_key_free), LSM_HOOK_INIT(key_permission, smack_key_permission), LSM_HOOK_INIT(key_getsecurity, smack_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS @@ -5156,6 +5245,7 @@ static struct security_hook_list smack_hooks[] __ro_after_init = { LSM_HOOK_INIT(ismaclabel, smack_ismaclabel), LSM_HOOK_INIT(secid_to_secctx, smack_secid_to_secctx), + LSM_HOOK_INIT(lsmblob_to_secctx, smack_lsmblob_to_secctx), LSM_HOOK_INIT(secctx_to_secid, smack_secctx_to_secid), LSM_HOOK_INIT(inode_notifysecctx, smack_inode_notifysecctx), LSM_HOOK_INIT(inode_setsecctx, smack_inode_setsecctx), @@ -5248,7 +5338,7 @@ static __init int smack_init(void) */ DEFINE_LSM(smack) = { .name = "smack", - .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, + .flags = LSM_FLAG_LEGACY_MAJOR, .blobs = &smack_blob_sizes, .init = smack_init, }; diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c index b945c1d3a7431..fd146e3a22860 100644 --- a/security/smack/smack_netfilter.c +++ b/security/smack/smack_netfilter.c @@ -26,8 +26,8 @@ static unsigned int smack_ip_output(void *priv, struct socket_smack *ssp; struct smack_known *skp; - if (sk && sk->sk_security) { - ssp = sk->sk_security; + if (smack_secmark() && sk) { + ssp = smack_sock(sk); skp = ssp->smk_out; skb->secmark = skp->smk_secid; } @@ -54,12 +54,18 @@ static const struct nf_hook_ops smack_nf_ops[] = { static int __net_init smack_nf_register(struct net *net) { + if (!smack_secmark()) + return 0; + return nf_register_net_hooks(net, smack_nf_ops, ARRAY_SIZE(smack_nf_ops)); } static void __net_exit smack_nf_unregister(struct net *net) { + if (!smack_secmark()) + return; + nf_unregister_net_hooks(net, smack_nf_ops, ARRAY_SIZE(smack_nf_ops)); } @@ -70,7 +76,7 @@ static struct pernet_operations smack_net_ops = { static int __init smack_nf_ip_init(void) { - if (smack_enabled == 0) + if (smack_enabled == 0 || !smack_secmark()) return 0; printk(KERN_DEBUG "Smack: Registering netfilter hooks\n"); diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index e22aad7604e8a..f8c0ea18b2fe0 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -77,7 +77,7 @@ static DEFINE_MUTEX(smk_net6addr_lock); * If it isn't somehow marked, use this. * It can be reset via smackfs/ambient */ -struct smack_known *smack_net_ambient; +struct smack_known *smack_net_ambient = &smack_known_floor; /* * This is the level in a CIPSO header that indicates a @@ -182,11 +182,9 @@ static inline void smack_catset_bit(unsigned int cat, char *catsetp) */ static void smk_netlabel_audit_set(struct netlbl_audit *nap) { - struct smack_known *skp = smk_of_current(); - nap->loginuid = audit_get_loginuid(current); nap->sessionid = audit_get_sessionid(current); - nap->secid = skp->smk_secid; + nap->blob.smack.skp = smk_of_current(); } /* @@ -687,6 +685,9 @@ static void smk_cipso_doi(void) struct cipso_v4_doi *doip; struct netlbl_audit nai; + if (!smack_netlabel()) + return; + smk_netlabel_audit_set(&nai); rc = netlbl_cfg_map_del(NULL, PF_INET, NULL, NULL, &nai); @@ -727,6 +728,9 @@ static void smk_unlbl_ambient(char *oldambient) int rc; struct netlbl_audit nai; + if (!smack_netlabel()) + return; + smk_netlabel_audit_set(&nai); if (oldambient != NULL) { @@ -850,6 +854,8 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf, */ if (!smack_privileged(CAP_MAC_ADMIN)) return -EPERM; + if (!smack_netlabel()) + return -EINVAL; if (*ppos != 0) return -EINVAL; if (format == SMK_FIXED24_FMT && @@ -1180,6 +1186,8 @@ static ssize_t smk_write_net4addr(struct file *file, const char __user *buf, */ if (!smack_privileged(CAP_MAC_ADMIN)) return -EPERM; + if (!smack_netlabel()) + return -EINVAL; if (*ppos != 0) return -EINVAL; if (count < SMK_NETLBLADDRMIN || count > PAGE_SIZE - 1) @@ -1439,6 +1447,8 @@ static ssize_t smk_write_net6addr(struct file *file, const char __user *buf, */ if (!smack_privileged(CAP_MAC_ADMIN)) return -EPERM; + if (!smack_netlabel()) + return -EINVAL; if (*ppos != 0) return -EINVAL; if (count < SMK_NETLBLADDRMIN || count > PAGE_SIZE - 1) @@ -1610,6 +1620,8 @@ static ssize_t smk_write_doi(struct file *file, const char __user *buf, if (!smack_privileged(CAP_MAC_ADMIN)) return -EPERM; + if (!smack_netlabel()) + return -EINVAL; if (count >= sizeof(temp) || count == 0) return -EINVAL; @@ -1677,6 +1689,8 @@ static ssize_t smk_write_direct(struct file *file, const char __user *buf, if (!smack_privileged(CAP_MAC_ADMIN)) return -EPERM; + if (!smack_netlabel()) + return -EINVAL; if (count >= sizeof(temp) || count == 0) return -EINVAL; @@ -1755,6 +1769,8 @@ static ssize_t smk_write_mapped(struct file *file, const char __user *buf, if (!smack_privileged(CAP_MAC_ADMIN)) return -EPERM; + if (!smack_netlabel()) + return -EINVAL; if (count >= sizeof(temp) || count == 0) return -EINVAL; diff --git a/sound/core/init.c b/sound/core/init.c index 22c0d217b8608..b2b7e50ff4cc3 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -312,8 +312,8 @@ static int snd_card_init(struct snd_card *card, struct device *parent, card->number = idx; #ifdef MODULE WARN_ON(!module); - card->module = module; #endif + card->module = module; INIT_LIST_HEAD(&card->devices); init_rwsem(&card->controls_rwsem); rwlock_init(&card->ctl_files_rwlock); @@ -523,6 +523,14 @@ void snd_card_disconnect(struct snd_card *card) } spin_unlock(&card->files_lock); +#ifdef CONFIG_PM + /* wake up sleepers here before other callbacks for avoiding potential + * deadlocks with other locks (e.g. in kctls); + * then this notifies the shutdown and sleepers would abort immediately + */ + wake_up_all(&card->power_sleep); +#endif + /* notify all connected devices about disconnection */ /* at this point, they cannot respond to any calls except release() */ @@ -538,6 +546,11 @@ void snd_card_disconnect(struct snd_card *card) synchronize_irq(card->sync_irq); snd_info_card_disconnect(card); +#ifdef CONFIG_SND_DEBUG + debugfs_remove(card->debugfs_root); + card->debugfs_root = NULL; +#endif + if (card->registered) { device_del(&card->card_dev); card->registered = false; @@ -550,7 +563,6 @@ void snd_card_disconnect(struct snd_card *card) mutex_unlock(&snd_card_mutex); #ifdef CONFIG_PM - wake_up(&card->power_sleep); snd_power_sync_ref(card); #endif } @@ -591,10 +603,6 @@ static int snd_card_do_free(struct snd_card *card) dev_warn(card->dev, "unable to free card info\n"); /* Not fatal error */ } -#ifdef CONFIG_SND_DEBUG - debugfs_remove(card->debugfs_root); - card->debugfs_root = NULL; -#endif if (card->release_completion) complete(card->release_completion); if (!card->managed) diff --git a/sound/core/jack.c b/sound/core/jack.c index e0f034e7275cd..e4bcecdf89b7e 100644 --- a/sound/core/jack.c +++ b/sound/core/jack.c @@ -37,16 +37,18 @@ static const int jack_switch_types[SND_JACK_SWITCH_TYPES] = { }; #endif /* CONFIG_SND_JACK_INPUT_DEV */ +static void snd_jack_remove_debugfs(struct snd_jack *jack); + static int snd_jack_dev_disconnect(struct snd_device *device) { -#ifdef CONFIG_SND_JACK_INPUT_DEV struct snd_jack *jack = device->device_data; - mutex_lock(&jack->input_dev_lock); - if (!jack->input_dev) { - mutex_unlock(&jack->input_dev_lock); + snd_jack_remove_debugfs(jack); + +#ifdef CONFIG_SND_JACK_INPUT_DEV + guard(mutex)(&jack->input_dev_lock); + if (!jack->input_dev) return 0; - } /* If the input device is registered with the input subsystem * then we need to use a different deallocator. */ @@ -55,7 +57,6 @@ static int snd_jack_dev_disconnect(struct snd_device *device) else input_free_device(jack->input_dev); jack->input_dev = NULL; - mutex_unlock(&jack->input_dev_lock); #endif /* CONFIG_SND_JACK_INPUT_DEV */ return 0; } @@ -92,11 +93,9 @@ static int snd_jack_dev_register(struct snd_device *device) snprintf(jack->name, sizeof(jack->name), "%s %s", card->shortname, jack->id); - mutex_lock(&jack->input_dev_lock); - if (!jack->input_dev) { - mutex_unlock(&jack->input_dev_lock); + guard(mutex)(&jack->input_dev_lock); + if (!jack->input_dev) return 0; - } jack->input_dev->name = jack->name; @@ -121,7 +120,6 @@ static int snd_jack_dev_register(struct snd_device *device) if (err == 0) jack->registered = 1; - mutex_unlock(&jack->input_dev_lock); return err; } #endif /* CONFIG_SND_JACK_INPUT_DEV */ @@ -387,10 +385,14 @@ static int snd_jack_debugfs_add_inject_node(struct snd_jack *jack, return 0; } -static void snd_jack_debugfs_clear_inject_node(struct snd_jack_kctl *jack_kctl) +static void snd_jack_remove_debugfs(struct snd_jack *jack) { - debugfs_remove(jack_kctl->jack_debugfs_root); - jack_kctl->jack_debugfs_root = NULL; + struct snd_jack_kctl *jack_kctl; + + list_for_each_entry(jack_kctl, &jack->kctl_list, list) { + debugfs_remove(jack_kctl->jack_debugfs_root); + jack_kctl->jack_debugfs_root = NULL; + } } #else /* CONFIG_SND_JACK_INJECTION_DEBUG */ static int snd_jack_debugfs_add_inject_node(struct snd_jack *jack, @@ -399,7 +401,7 @@ static int snd_jack_debugfs_add_inject_node(struct snd_jack *jack, return 0; } -static void snd_jack_debugfs_clear_inject_node(struct snd_jack_kctl *jack_kctl) +static void snd_jack_remove_debugfs(struct snd_jack *jack) { } #endif /* CONFIG_SND_JACK_INJECTION_DEBUG */ @@ -410,7 +412,6 @@ static void snd_jack_kctl_private_free(struct snd_kcontrol *kctl) jack_kctl = kctl->private_data; if (jack_kctl) { - snd_jack_debugfs_clear_inject_node(jack_kctl); list_del(&jack_kctl->list); kfree(jack_kctl); } @@ -503,8 +504,8 @@ int snd_jack_new(struct snd_card *card, const char *id, int type, .dev_free = snd_jack_dev_free, #ifdef CONFIG_SND_JACK_INPUT_DEV .dev_register = snd_jack_dev_register, - .dev_disconnect = snd_jack_dev_disconnect, #endif /* CONFIG_SND_JACK_INPUT_DEV */ + .dev_disconnect = snd_jack_dev_disconnect, }; if (initial_kctl) { @@ -586,14 +587,9 @@ EXPORT_SYMBOL(snd_jack_new); void snd_jack_set_parent(struct snd_jack *jack, struct device *parent) { WARN_ON(jack->registered); - mutex_lock(&jack->input_dev_lock); - if (!jack->input_dev) { - mutex_unlock(&jack->input_dev_lock); - return; - } - - jack->input_dev->dev.parent = parent; - mutex_unlock(&jack->input_dev_lock); + guard(mutex)(&jack->input_dev_lock); + if (jack->input_dev) + jack->input_dev->dev.parent = parent; } EXPORT_SYMBOL(snd_jack_set_parent); diff --git a/sound/core/seq/seq_midi.c b/sound/core/seq/seq_midi.c index 18320a248aa7d..78dcb0ea15582 100644 --- a/sound/core/seq/seq_midi.c +++ b/sound/core/seq/seq_midi.c @@ -113,6 +113,12 @@ static int dump_midi(struct snd_rawmidi_substream *substream, const char *buf, i return 0; } +/* callback for snd_seq_dump_var_event(), bridging to dump_midi() */ +static int __dump_midi(void *ptr, void *buf, int count) +{ + return dump_midi(ptr, buf, count); +} + static int event_process_midi(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop) { @@ -132,7 +138,7 @@ static int event_process_midi(struct snd_seq_event *ev, int direct, pr_debug("ALSA: seq_midi: invalid sysex event flags = 0x%x\n", ev->flags); return 0; } - snd_seq_dump_var_event(ev, (snd_seq_dump_func_t)dump_midi, substream); + snd_seq_dump_var_event(ev, __dump_midi, substream); snd_midi_event_reset_decode(msynth->parser); } else { if (msynth->parser == NULL) diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index b141024830ecc..d81f776a4c3dd 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -157,7 +157,7 @@ static void ump_system_to_one_param_ev(const union snd_ump_midi1_msg *val, static void ump_system_to_songpos_ev(const union snd_ump_midi1_msg *val, struct snd_seq_event *ev) { - ev->data.control.value = (val->system.parm1 << 7) | val->system.parm2; + ev->data.control.value = (val->system.parm2 << 7) | val->system.parm1; } /* Encoders for 0xf0 - 0xff */ @@ -368,6 +368,7 @@ static int cvt_ump_midi1_to_midi2(struct snd_seq_client *dest, struct snd_seq_ump_event ev_cvt; const union snd_ump_midi1_msg *midi1 = (const union snd_ump_midi1_msg *)event->ump; union snd_ump_midi2_msg *midi2 = (union snd_ump_midi2_msg *)ev_cvt.ump; + struct snd_seq_ump_midi2_bank *cc; ev_cvt = *event; memset(&ev_cvt.ump, 0, sizeof(ev_cvt.ump)); @@ -387,11 +388,29 @@ static int cvt_ump_midi1_to_midi2(struct snd_seq_client *dest, midi2->paf.data = upscale_7_to_32bit(midi1->paf.data); break; case UMP_MSG_STATUS_CC: + cc = &dest_port->midi2_bank[midi1->note.channel]; + switch (midi1->cc.index) { + case UMP_CC_BANK_SELECT: + cc->bank_set = 1; + cc->cc_bank_msb = midi1->cc.data; + return 0; // skip + case UMP_CC_BANK_SELECT_LSB: + cc->bank_set = 1; + cc->cc_bank_lsb = midi1->cc.data; + return 0; // skip + } midi2->cc.index = midi1->cc.index; midi2->cc.data = upscale_7_to_32bit(midi1->cc.data); break; case UMP_MSG_STATUS_PROGRAM: midi2->pg.program = midi1->pg.program; + cc = &dest_port->midi2_bank[midi1->note.channel]; + if (cc->bank_set) { + midi2->pg.bank_valid = 1; + midi2->pg.bank_msb = cc->cc_bank_msb; + midi2->pg.bank_lsb = cc->cc_bank_lsb; + cc->bank_set = 0; + } break; case UMP_MSG_STATUS_CHANNEL_PRESSURE: midi2->caf.data = upscale_7_to_32bit(midi1->caf.data); @@ -419,6 +438,7 @@ static int cvt_ump_midi2_to_midi1(struct snd_seq_client *dest, struct snd_seq_ump_event ev_cvt; union snd_ump_midi1_msg *midi1 = (union snd_ump_midi1_msg *)ev_cvt.ump; const union snd_ump_midi2_msg *midi2 = (const union snd_ump_midi2_msg *)event->ump; + int err; u16 v; ev_cvt = *event; @@ -428,7 +448,7 @@ static int cvt_ump_midi2_to_midi1(struct snd_seq_client *dest, midi1->note.group = midi2->note.group; midi1->note.status = midi2->note.status; midi1->note.channel = midi2->note.channel; - switch (midi2->note.status << 4) { + switch (midi2->note.status) { case UMP_MSG_STATUS_NOTE_ON: case UMP_MSG_STATUS_NOTE_OFF: midi1->note.note = midi2->note.note; @@ -443,6 +463,24 @@ static int cvt_ump_midi2_to_midi1(struct snd_seq_client *dest, midi1->cc.data = downscale_32_to_7bit(midi2->cc.data); break; case UMP_MSG_STATUS_PROGRAM: + if (midi2->pg.bank_valid) { + midi1->cc.status = UMP_MSG_STATUS_CC; + midi1->cc.index = UMP_CC_BANK_SELECT; + midi1->cc.data = midi2->pg.bank_msb; + err = __snd_seq_deliver_single_event(dest, dest_port, + (struct snd_seq_event *)&ev_cvt, + atomic, hop); + if (err < 0) + return err; + midi1->cc.index = UMP_CC_BANK_SELECT_LSB; + midi1->cc.data = midi2->pg.bank_lsb; + err = __snd_seq_deliver_single_event(dest, dest_port, + (struct snd_seq_event *)&ev_cvt, + atomic, hop); + if (err < 0) + return err; + midi1->note.status = midi2->note.status; + } midi1->pg.program = midi2->pg.program; break; case UMP_MSG_STATUS_CHANNEL_PRESSURE: @@ -691,6 +729,7 @@ static int system_ev_to_ump_midi1(const struct snd_seq_event *event, union snd_ump_midi1_msg *data, unsigned char status) { + data->system.type = UMP_MSG_TYPE_SYSTEM; // override data->system.status = status; return 1; } @@ -701,6 +740,7 @@ static int system_1p_ev_to_ump_midi1(const struct snd_seq_event *event, union snd_ump_midi1_msg *data, unsigned char status) { + data->system.type = UMP_MSG_TYPE_SYSTEM; // override data->system.status = status; data->system.parm1 = event->data.control.value & 0x7f; return 1; @@ -712,9 +752,10 @@ static int system_2p_ev_to_ump_midi1(const struct snd_seq_event *event, union snd_ump_midi1_msg *data, unsigned char status) { + data->system.type = UMP_MSG_TYPE_SYSTEM; // override data->system.status = status; - data->system.parm1 = (event->data.control.value >> 7) & 0x7f; - data->system.parm2 = event->data.control.value & 0x7f; + data->system.parm1 = event->data.control.value & 0x7f; + data->system.parm2 = (event->data.control.value >> 7) & 0x7f; return 1; } @@ -854,7 +895,6 @@ static int pgm_ev_to_ump_midi2(const struct snd_seq_event *event, data->pg.bank_msb = cc->cc_bank_msb; data->pg.bank_lsb = cc->cc_bank_lsb; cc->bank_set = 0; - cc->cc_bank_msb = cc->cc_bank_lsb = 0; } return 1; } @@ -1035,6 +1075,8 @@ static const struct seq_ev_to_ump seq_ev_ump_encoders[] = { system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, { SNDRV_SEQ_EVENT_SENSING, UMP_SYSTEM_STATUS_ACTIVE_SENSING, system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, + { SNDRV_SEQ_EVENT_RESET, UMP_SYSTEM_STATUS_RESET, + system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, }; static const struct seq_ev_to_ump *find_ump_encoder(int type) diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 1b9260108e482..1678737f11be7 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -62,6 +62,13 @@ static void snd_virmidi_init_event(struct snd_virmidi *vmidi, /* * decode input event and put to read buffer of each opened file */ + +/* callback for snd_seq_dump_var_event(), bridging to snd_rawmidi_receive() */ +static int dump_to_rawmidi(void *ptr, void *buf, int count) +{ + return snd_rawmidi_receive(ptr, buf, count); +} + static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, struct snd_seq_event *ev, bool atomic) @@ -80,7 +87,7 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) continue; - snd_seq_dump_var_event(ev, (snd_seq_dump_func_t)snd_rawmidi_receive, vmidi->substream); + snd_seq_dump_var_event(ev, dump_to_rawmidi, vmidi->substream); snd_midi_event_reset_decode(vmidi->parser); } else { len = snd_midi_event_decode(vmidi->parser, msg, sizeof(msg), ev); diff --git a/sound/core/timer.c b/sound/core/timer.c index e6e551d4a29e0..a0b515981ee9b 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -553,6 +553,16 @@ static int snd_timer_start1(struct snd_timer_instance *timeri, goto unlock; } + /* check the actual time for the start tick; + * bail out as error if it's way too low (< 100us) + */ + if (start) { + if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000) { + result = -EINVAL; + goto unlock; + } + } + if (start) timeri->ticks = timeri->cticks = ticks; else if (!timeri->cticks) diff --git a/sound/core/ump.c b/sound/core/ump.c index fe7911498cc43..3cd07c103d9ea 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -685,10 +685,17 @@ static void seq_notify_protocol(struct snd_ump_endpoint *ump) */ int snd_ump_switch_protocol(struct snd_ump_endpoint *ump, unsigned int protocol) { + unsigned int type; + protocol &= ump->info.protocol_caps; if (protocol == ump->info.protocol) return 0; + type = protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK; + if (type != SNDRV_UMP_EP_INFO_PROTO_MIDI1 && + type != SNDRV_UMP_EP_INFO_PROTO_MIDI2) + return 0; + ump->info.protocol = protocol; ump_dbg(ump, "New protocol = %x (caps = %x)\n", protocol, ump->info.protocol_caps); diff --git a/sound/core/ump_convert.c b/sound/core/ump_convert.c index de04799fdb69a..f67c44c83fde4 100644 --- a/sound/core/ump_convert.c +++ b/sound/core/ump_convert.c @@ -404,7 +404,6 @@ static int cvt_legacy_cmd_to_ump(struct ump_cvt_to_ump *cvt, midi2->pg.bank_msb = cc->cc_bank_msb; midi2->pg.bank_lsb = cc->cc_bank_lsb; cc->bank_set = 0; - cc->cc_bank_msb = cc->cc_bank_lsb = 0; } break; case UMP_MSG_STATUS_CHANNEL_PRESSURE: diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index 7be17bca257f0..c9f153f85ae6b 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -773,10 +773,14 @@ static int check_cip_header(struct amdtp_stream *s, const __be32 *buf, } else { unsigned int dbc_interval; - if (*data_blocks > 0 && s->ctx_data.tx.dbc_interval > 0) - dbc_interval = s->ctx_data.tx.dbc_interval; - else - dbc_interval = *data_blocks; + if (!(s->flags & CIP_DBC_IS_PAYLOAD_QUADLETS)) { + if (*data_blocks > 0 && s->ctx_data.tx.dbc_interval > 0) + dbc_interval = s->ctx_data.tx.dbc_interval; + else + dbc_interval = *data_blocks; + } else { + dbc_interval = payload_length / sizeof(__be32); + } lost = dbc != ((*data_block_counter + dbc_interval) & 0xff); } diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h index b7ff44751ab93..a1ed2e80f91a7 100644 --- a/sound/firewire/amdtp-stream.h +++ b/sound/firewire/amdtp-stream.h @@ -37,6 +37,9 @@ * the value of current SYT_INTERVAL; e.g. initial value is not zero. * @CIP_UNAWARE_SYT: For outgoing packet, the value in SYT field of CIP is 0xffff. * For incoming packet, the value in SYT field of CIP is not handled. + * @CIP_DBC_IS_PAYLOAD_QUADLETS: Available for incoming packet, and only effective with + * CIP_DBC_IS_END_EVENT flag. The value of dbc field is the number of accumulated quadlets + * in CIP payload, instead of the number of accumulated data blocks. */ enum cip_flags { CIP_NONBLOCKING = 0x00, @@ -51,6 +54,7 @@ enum cip_flags { CIP_NO_HEADER = 0x100, CIP_UNALIGHED_DBC = 0x200, CIP_UNAWARE_SYT = 0x400, + CIP_DBC_IS_PAYLOAD_QUADLETS = 0x800, }; /** diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 6a384b922e4fa..e7c2ef6c6b4cb 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -16,7 +16,7 @@ static int dsp_driver; module_param(dsp_driver, int, 0444); -MODULE_PARM_DESC(dsp_driver, "Force the DSP driver for Intel DSP (0=auto, 1=legacy, 2=SST, 3=SOF)"); +MODULE_PARM_DESC(dsp_driver, "Force the DSP driver for Intel DSP (0=auto, 1=legacy, 2=SST, 3=SOF, 4=AVS)"); #define FLAG_SST BIT(0) #define FLAG_SOF BIT(1) @@ -557,9 +557,32 @@ static const struct config_entry *snd_intel_dsp_find_config if (table->codec_hid) { int i; - for (i = 0; i < table->codec_hid->num_codecs; i++) - if (acpi_dev_present(table->codec_hid->codecs[i], NULL, -1)) + for (i = 0; i < table->codec_hid->num_codecs; i++) { + struct nhlt_acpi_table *nhlt; + bool ssp_found = false; + + if (!acpi_dev_present(table->codec_hid->codecs[i], NULL, -1)) + continue; + + nhlt = intel_nhlt_init(&pci->dev); + if (!nhlt) { + dev_warn(&pci->dev, "%s: NHLT table not found, skipped HID %s\n", + __func__, table->codec_hid->codecs[i]); + continue; + } + + if (intel_nhlt_has_endpoint_type(nhlt, NHLT_LINK_SSP) && + intel_nhlt_ssp_endpoint_mask(nhlt, NHLT_DEVICE_I2S)) + ssp_found = true; + + intel_nhlt_free(nhlt); + + if (ssp_found) break; + + dev_warn(&pci->dev, "%s: no valid SSP found for HID %s, skipped\n", + __func__, table->codec_hid->codecs[i]); + } if (i == table->codec_hid->num_codecs) continue; } diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c index b57d72ea4503f..4e376994bf78b 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -41,6 +41,8 @@ static bool is_link_enabled(struct fwnode_handle *fw_node, u8 idx) "intel-quirk-mask", &quirk_mask); + fwnode_handle_put(link); + if (quirk_mask & SDW_INTEL_QUIRK_MASK_BUS_DISABLE) return false; diff --git a/sound/oss/dmasound/dmasound_paula.c b/sound/oss/dmasound/dmasound_paula.c index 0ba8f0c4cd99a..3a593da09280d 100644 --- a/sound/oss/dmasound/dmasound_paula.c +++ b/sound/oss/dmasound/dmasound_paula.c @@ -725,7 +725,13 @@ static void __exit amiga_audio_remove(struct platform_device *pdev) dmasound_deinit(); } -static struct platform_driver amiga_audio_driver = { +/* + * amiga_audio_remove() lives in .exit.text. For drivers registered via + * module_platform_driver_probe() this is ok because they cannot get unbound at + * runtime. So mark the driver struct with __refdata to prevent modpost + * triggering a section mismatch warning. + */ +static struct platform_driver amiga_audio_driver __refdata = { .remove_new = __exit_p(amiga_audio_remove), .driver = { .name = "amiga-audio", diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c index fe72e7d772412..dadeda7758cee 100644 --- a/sound/pci/emu10k1/emu10k1.c +++ b/sound/pci/emu10k1/emu10k1.c @@ -189,8 +189,7 @@ static int snd_emu10k1_suspend(struct device *dev) emu->suspend = 1; - cancel_work_sync(&emu->emu1010.firmware_work); - cancel_work_sync(&emu->emu1010.clock_work); + cancel_work_sync(&emu->emu1010.work); snd_ac97_suspend(emu->ac97); diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c index d36234b88fb42..941bfbf812ed3 100644 --- a/sound/pci/emu10k1/emu10k1_callback.c +++ b/sound/pci/emu10k1/emu10k1_callback.c @@ -255,7 +255,7 @@ lookup_voices(struct snd_emux *emu, struct snd_emu10k1 *hw, /* check if sample is finished playing (non-looping only) */ if (bp != best + V_OFF && bp != best + V_FREE && (vp->reg.sample_mode & SNDRV_SFNT_SAMPLE_SINGLESHOT)) { - val = snd_emu10k1_ptr_read(hw, CCCA_CURRADDR, vp->ch) - 64; + val = snd_emu10k1_ptr_read(hw, CCCA_CURRADDR, vp->ch); if (val >= vp->reg.loopstart) bp = best + V_OFF; } @@ -362,7 +362,7 @@ start_voice(struct snd_emux_voice *vp) map = (hw->silent_page.addr << hw->address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); - addr = vp->reg.start + 64; + addr = vp->reg.start; temp = vp->reg.parm.filterQ; ccca = (temp << 28) | addr; if (vp->apitch < 0xe400) @@ -430,9 +430,6 @@ start_voice(struct snd_emux_voice *vp) /* Q & current address (Q 4bit value, MSB) */ CCCA, ccca, - /* cache */ - CCR, REG_VAL_PUT(CCR_CACHEINVALIDSIZE, 64), - /* reset volume */ VTFT, vtarget | vp->ftarget, CVCF, vtarget | CVCF_CURRENTFILTER_MASK, diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index de5c41e578e1f..ade90c7ecd922 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -732,69 +732,67 @@ static int snd_emu1010_load_firmware(struct snd_emu10k1 *emu, int dock, return snd_emu1010_load_firmware_entry(emu, *fw); } -static void emu1010_firmware_work(struct work_struct *work) +static void snd_emu1010_load_dock_firmware(struct snd_emu10k1 *emu) { - struct snd_emu10k1 *emu; - u32 tmp, tmp2, reg; + u32 tmp, tmp2; int err; - emu = container_of(work, struct snd_emu10k1, - emu1010.firmware_work); - if (emu->card->shutdown) + // The docking events clearly arrive prematurely - while the + // Dock's FPGA seems to be successfully programmed, the Dock + // fails to initialize subsequently if we don't give it some + // time to "warm up" here. + msleep(200); + + dev_info(emu->card->dev, "emu1010: Loading Audio Dock Firmware\n"); + /* Return to Audio Dock programming mode */ + snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, + EMU_HANA_FPGA_CONFIG_AUDIODOCK); + err = snd_emu1010_load_firmware(emu, 1, &emu->dock_fw); + if (err < 0) return; -#ifdef CONFIG_PM_SLEEP - if (emu->suspend) + snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, 0); + + snd_emu1010_fpga_read(emu, EMU_HANA_ID, &tmp); + dev_dbg(emu->card->dev, "emu1010: EMU_HANA+DOCK_ID = 0x%x\n", tmp); + if ((tmp & 0x1f) != 0x15) { + /* FPGA failed to be programmed */ + dev_err(emu->card->dev, + "emu1010: Loading Audio Dock Firmware failed, reg = 0x%x\n", + tmp); return; -#endif + } + dev_info(emu->card->dev, "emu1010: Audio Dock Firmware loaded\n"); + + snd_emu1010_fpga_read(emu, EMU_DOCK_MAJOR_REV, &tmp); + snd_emu1010_fpga_read(emu, EMU_DOCK_MINOR_REV, &tmp2); + dev_info(emu->card->dev, "Audio Dock ver: %u.%u\n", tmp, tmp2); + + /* Allow DLL to settle, to sync clocking between 1010 and Dock */ + msleep(10); +} + +static void emu1010_dock_event(struct snd_emu10k1 *emu) +{ + u32 reg; + snd_emu1010_fpga_read(emu, EMU_HANA_OPTION_CARDS, ®); /* OPTIONS: Which cards are attached to the EMU */ if (reg & EMU_HANA_OPTION_DOCK_OFFLINE) { /* Audio Dock attached */ - /* Return to Audio Dock programming mode */ - dev_info(emu->card->dev, - "emu1010: Loading Audio Dock Firmware\n"); - snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, - EMU_HANA_FPGA_CONFIG_AUDIODOCK); - err = snd_emu1010_load_firmware(emu, 1, &emu->dock_fw); - if (err < 0) - return; - snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, 0); - snd_emu1010_fpga_read(emu, EMU_HANA_ID, &tmp); - dev_info(emu->card->dev, - "emu1010: EMU_HANA+DOCK_ID = 0x%x\n", tmp); - if ((tmp & 0x1f) != 0x15) { - /* FPGA failed to be programmed */ - dev_info(emu->card->dev, - "emu1010: Loading Audio Dock Firmware file failed, reg = 0x%x\n", - tmp); - return; - } - dev_info(emu->card->dev, - "emu1010: Audio Dock Firmware loaded\n"); - snd_emu1010_fpga_read(emu, EMU_DOCK_MAJOR_REV, &tmp); - snd_emu1010_fpga_read(emu, EMU_DOCK_MINOR_REV, &tmp2); - dev_info(emu->card->dev, "Audio Dock ver: %u.%u\n", tmp, tmp2); - /* Sync clocking between 1010 and Dock */ - /* Allow DLL to settle */ - msleep(10); + snd_emu1010_load_dock_firmware(emu); /* Unmute all. Default is muted after a firmware load */ snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE); + } else if (!(reg & EMU_HANA_OPTION_DOCK_ONLINE)) { + /* Audio Dock removed */ + dev_info(emu->card->dev, "emu1010: Audio Dock detached\n"); + /* The hardware auto-mutes all, so we unmute again */ + snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE); } } -static void emu1010_clock_work(struct work_struct *work) +static void emu1010_clock_event(struct snd_emu10k1 *emu) { - struct snd_emu10k1 *emu; struct snd_ctl_elem_id id; - emu = container_of(work, struct snd_emu10k1, - emu1010.clock_work); - if (emu->card->shutdown) - return; -#ifdef CONFIG_PM_SLEEP - if (emu->suspend) - return; -#endif - spin_lock_irq(&emu->reg_lock); // This is the only thing that can actually happen. emu->emu1010.clock_source = emu->emu1010.clock_fallback; @@ -805,21 +803,40 @@ static void emu1010_clock_work(struct work_struct *work) snd_ctl_notify(emu->card, SNDRV_CTL_EVENT_MASK_VALUE, &id); } -static void emu1010_interrupt(struct snd_emu10k1 *emu) +static void emu1010_work(struct work_struct *work) { + struct snd_emu10k1 *emu; u32 sts; + emu = container_of(work, struct snd_emu10k1, emu1010.work); + if (emu->card->shutdown) + return; +#ifdef CONFIG_PM_SLEEP + if (emu->suspend) + return; +#endif + snd_emu1010_fpga_read(emu, EMU_HANA_IRQ_STATUS, &sts); - if (sts & EMU_HANA_IRQ_DOCK_LOST) { - /* Audio Dock removed */ - dev_info(emu->card->dev, "emu1010: Audio Dock detached\n"); - /* The hardware auto-mutes all, so we unmute again */ - snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE); - } else if (sts & EMU_HANA_IRQ_DOCK) { - schedule_work(&emu->emu1010.firmware_work); - } + + // The distinction of the IRQ status bits is unreliable, + // so we dispatch later based on option card status. + if (sts & (EMU_HANA_IRQ_DOCK | EMU_HANA_IRQ_DOCK_LOST)) + emu1010_dock_event(emu); + if (sts & EMU_HANA_IRQ_WCLK_CHANGED) - schedule_work(&emu->emu1010.clock_work); + emu1010_clock_event(emu); +} + +static void emu1010_interrupt(struct snd_emu10k1 *emu) +{ + // We get an interrupt on each GPIO input pin change, but we + // care only about the ones triggered by the dedicated pin. + u16 sts = inw(emu->port + A_GPIO); + u16 bit = emu->card_capabilities->ca0108_chip ? 0x2000 : 0x8000; + if (!(sts & bit)) + return; + + schedule_work(&emu->emu1010.work); } /* @@ -889,7 +906,7 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) snd_emu1010_fpga_read(emu, EMU_HANA_OPTION_CARDS, ®); dev_info(emu->card->dev, "emu1010: Card options = 0x%x\n", reg); if (reg & EMU_HANA_OPTION_DOCK_OFFLINE) - schedule_work(&emu->emu1010.firmware_work); + snd_emu1010_load_dock_firmware(emu); if (emu->card_capabilities->no_adat) { emu->emu1010.optical_in = 0; /* IN_SPDIF */ emu->emu1010.optical_out = 0; /* OUT_SPDIF */ @@ -960,8 +977,7 @@ static void snd_emu10k1_free(struct snd_card *card) /* Disable 48Volt power to Audio Dock */ snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_PWR, 0); } - cancel_work_sync(&emu->emu1010.firmware_work); - cancel_work_sync(&emu->emu1010.clock_work); + cancel_work_sync(&emu->emu1010.work); release_firmware(emu->firmware); release_firmware(emu->dock_fw); snd_util_memhdr_free(emu->memhdr); @@ -1540,8 +1556,7 @@ int snd_emu10k1_create(struct snd_card *card, emu->irq = -1; emu->synth = NULL; emu->get_synth_voice = NULL; - INIT_WORK(&emu->emu1010.firmware_work, emu1010_firmware_work); - INIT_WORK(&emu->emu1010.clock_work, emu1010_clock_work); + INIT_WORK(&emu->emu1010.work, emu1010_work); /* read revision & serial */ emu->revision = pci->revision; pci_read_config_dword(pci, PCI_SUBSYSTEM_VENDOR_ID, &emu->serial); diff --git a/sound/pci/emu10k1/io.c b/sound/pci/emu10k1/io.c index 74df2330015f6..5cb8acf5b158c 100644 --- a/sound/pci/emu10k1/io.c +++ b/sound/pci/emu10k1/io.c @@ -285,6 +285,7 @@ static void snd_emu1010_fpga_write_locked(struct snd_emu10k1 *emu, u32 reg, u32 outw(value, emu->port + A_GPIO); udelay(10); outw(value | 0x80 , emu->port + A_GPIO); /* High bit clocks the value into the fpga. */ + udelay(10); } void snd_emu1010_fpga_write(struct snd_emu10k1 *emu, u32 reg, u32 value) diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index d3fa6e136744d..ec688c60c153b 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -1362,7 +1362,7 @@ static void cs35l41_hda_unbind(struct device *dev, struct device *master, void * if (comps[cs35l41->index].dev == dev) { memset(&comps[cs35l41->index], 0, sizeof(*comps)); sleep_flags = lock_system_sleep(); - device_link_remove(&comps->codec->core.dev, cs35l41->dev); + device_link_remove(&cs35l41->codec->core.dev, cs35l41->dev); unlock_system_sleep(sleep_flags); } } @@ -1857,6 +1857,8 @@ void cs35l41_hda_remove(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + component_del(cs35l41->dev, &cs35l41_hda_comp_ops); + pm_runtime_get_sync(cs35l41->dev); pm_runtime_dont_use_autosuspend(cs35l41->dev); pm_runtime_disable(cs35l41->dev); @@ -1864,8 +1866,6 @@ void cs35l41_hda_remove(struct device *dev) if (cs35l41->halo_initialized) cs35l41_remove_dsp(cs35l41); - component_del(cs35l41->dev, &cs35l41_hda_comp_ops); - acpi_dev_put(cs35l41->dacpi); pm_runtime_put_noidle(cs35l41->dev); diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c index e436d4dab317f..c2067e8083c0f 100644 --- a/sound/pci/hda/cs35l41_hda_property.c +++ b/sound/pci/hda/cs35l41_hda_property.c @@ -97,7 +97,10 @@ static const struct cs35l41_config cs35l41_config_table[] = { { "10431F12", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 }, { "10431F1F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 }, { "10431F62", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 }, + { "10433A60", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 }, { "17AA386F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, + { "17AA3877", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, + { "17AA3878", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, { "17AA38A9", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, { "17AA38AB", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, { "17AA38B4", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, @@ -210,6 +213,7 @@ static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physde struct spi_device *spi; bool dsd_found; int ret; + int i; for (cfg = cs35l41_config_table; cfg->ssid; cfg++) { if (!strcasecmp(cfg->ssid, cs35l41->acpi_subsystem_id)) @@ -295,16 +299,6 @@ static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physde cs35l41->index = id == 0x40 ? 0 : 1; } - if (cfg->num_amps == 3) - /* 3 amps means a center channel, so no duplicate channels */ - cs35l41->channel_index = 0; - else - /* - * if 4 amps, there are duplicate channels, so they need different indexes - * if 2 amps, no duplicate channels, channel_index would be 0 - */ - cs35l41->channel_index = cs35l41->index / 2; - cs35l41->reset_gpio = fwnode_gpiod_get_index(acpi_fwnode_handle(cs35l41->dacpi), "reset", cs35l41->index, GPIOD_OUT_LOW, "cs35l41-reset"); @@ -312,6 +306,11 @@ static int generic_dsd_config(struct cs35l41_hda *cs35l41, struct device *physde hw_cfg->spk_pos = cfg->channel[cs35l41->index]; + cs35l41->channel_index = 0; + for (i = 0; i < cs35l41->index; i++) + if (cfg->channel[i] == hw_cfg->spk_pos) + cs35l41->channel_index++; + if (cfg->boost_type == INTERNAL) { hw_cfg->bst_type = CS35L41_INT_BOOST; hw_cfg->bst_ind = cfg->boost_ind_nanohenry; @@ -438,7 +437,10 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = { { "CSC3551", "10431F12", generic_dsd_config }, { "CSC3551", "10431F1F", generic_dsd_config }, { "CSC3551", "10431F62", generic_dsd_config }, + { "CSC3551", "10433A60", generic_dsd_config }, { "CSC3551", "17AA386F", generic_dsd_config }, + { "CSC3551", "17AA3877", generic_dsd_config }, + { "CSC3551", "17AA3878", generic_dsd_config }, { "CSC3551", "17AA38A9", generic_dsd_config }, { "CSC3551", "17AA38AB", generic_dsd_config }, { "CSC3551", "17AA38B4", generic_dsd_config }, diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 75a14ba54fcd1..f9edd0fcdce7a 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -629,6 +629,8 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56) ret = cs35l56_wait_for_firmware_boot(&cs35l56->base); if (ret) goto err_powered_up; + + regcache_cache_only(cs35l56->base.regmap, false); } /* Disable auto-hibernate so that runtime_pm has control */ @@ -710,8 +712,6 @@ static void cs35l56_hda_unbind(struct device *dev, struct device *master, void * if (cs35l56->base.fw_patched) cs_dsp_power_down(&cs35l56->cs_dsp); - cs_dsp_remove(&cs35l56->cs_dsp); - if (comps[cs35l56->index].dev == dev) memset(&comps[cs35l56->index], 0, sizeof(*comps)); @@ -978,6 +978,8 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int id) if (ret) goto err; + regcache_cache_only(cs35l56->base.regmap, false); + ret = cs35l56_set_patch(&cs35l56->base); if (ret) goto err; @@ -1003,7 +1005,7 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int id) ARRAY_SIZE(cs35l56_hda_dai_config)); ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base); if (ret) - goto err; + goto dsp_err; /* * By default only enable one ASP1TXn, where n=amplifier index, @@ -1017,18 +1019,20 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int id) pm_runtime_mark_last_busy(cs35l56->base.dev); pm_runtime_enable(cs35l56->base.dev); + cs35l56->base.init_done = true; + ret = component_add(cs35l56->base.dev, &cs35l56_hda_comp_ops); if (ret) { dev_err(cs35l56->base.dev, "Register component failed: %d\n", ret); goto pm_err; } - cs35l56->base.init_done = true; - return 0; pm_err: pm_runtime_disable(cs35l56->base.dev); +dsp_err: + cs_dsp_remove(&cs35l56->cs_dsp); err: gpiod_set_value_cansleep(cs35l56->base.reset_gpio, 0); @@ -1040,11 +1044,13 @@ void cs35l56_hda_remove(struct device *dev) { struct cs35l56_hda *cs35l56 = dev_get_drvdata(dev); + component_del(cs35l56->base.dev, &cs35l56_hda_comp_ops); + pm_runtime_dont_use_autosuspend(cs35l56->base.dev); pm_runtime_get_sync(cs35l56->base.dev); pm_runtime_disable(cs35l56->base.dev); - component_del(cs35l56->base.dev, &cs35l56_hda_comp_ops); + cs_dsp_remove(&cs35l56->cs_dsp); kfree(cs35l56->system_name); pm_runtime_put_noidle(cs35l56->base.dev); diff --git a/sound/pci/hda/cs35l56_hda_i2c.c b/sound/pci/hda/cs35l56_hda_i2c.c index a9ef6d86de839..09a810a50a12b 100644 --- a/sound/pci/hda/cs35l56_hda_i2c.c +++ b/sound/pci/hda/cs35l56_hda_i2c.c @@ -53,10 +53,19 @@ static const struct i2c_device_id cs35l56_hda_i2c_id[] = { {} }; +static const struct acpi_device_id cs35l56_acpi_hda_match[] = { + { "CSC3554", 0 }, + { "CSC3556", 0 }, + { "CSC3557", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, cs35l56_acpi_hda_match); + static struct i2c_driver cs35l56_hda_i2c_driver = { .driver = { - .name = "cs35l56-hda", - .pm = &cs35l56_hda_pm_ops, + .name = "cs35l56-hda", + .acpi_match_table = cs35l56_acpi_hda_match, + .pm = &cs35l56_hda_pm_ops, }, .id_table = cs35l56_hda_i2c_id, .probe = cs35l56_hda_i2c_probe, diff --git a/sound/pci/hda/cs35l56_hda_spi.c b/sound/pci/hda/cs35l56_hda_spi.c index 080426de90830..04f9fe6197dc5 100644 --- a/sound/pci/hda/cs35l56_hda_spi.c +++ b/sound/pci/hda/cs35l56_hda_spi.c @@ -53,10 +53,19 @@ static const struct spi_device_id cs35l56_hda_spi_id[] = { {} }; +static const struct acpi_device_id cs35l56_acpi_hda_match[] = { + { "CSC3554", 0 }, + { "CSC3556", 0 }, + { "CSC3557", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, cs35l56_acpi_hda_match); + static struct spi_driver cs35l56_hda_spi_driver = { .driver = { - .name = "cs35l56-hda", - .pm = &cs35l56_hda_pm_ops, + .name = "cs35l56-hda", + .acpi_match_table = cs35l56_acpi_hda_match, + .pm = &cs35l56_hda_pm_ops, }, .id_table = cs35l56_hda_spi_id, .probe = cs35l56_hda_spi_probe, diff --git a/sound/pci/hda/hda_cs_dsp_ctl.c b/sound/pci/hda/hda_cs_dsp_ctl.c index 463ca06036bfe..9db45d7c17e5f 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.c +++ b/sound/pci/hda/hda_cs_dsp_ctl.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include "hda_cs_dsp_ctl.h" @@ -97,11 +98,23 @@ static unsigned int wmfw_convert_flags(unsigned int in) return out; } -static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char *name) +static void hda_cs_dsp_free_kcontrol(struct snd_kcontrol *kctl) { + struct hda_cs_dsp_coeff_ctl *ctl = (struct hda_cs_dsp_coeff_ctl *)snd_kcontrol_chip(kctl); struct cs_dsp_coeff_ctl *cs_ctl = ctl->cs_ctl; + + /* NULL priv to prevent a double-free in hda_cs_dsp_control_remove() */ + cs_ctl->priv = NULL; + kfree(ctl); +} + +static void hda_cs_dsp_add_kcontrol(struct cs_dsp_coeff_ctl *cs_ctl, + const struct hda_cs_dsp_ctl_info *info, + const char *name) +{ struct snd_kcontrol_new kcontrol = {0}; struct snd_kcontrol *kctl; + struct hda_cs_dsp_coeff_ctl *ctl __free(kfree) = NULL; int ret = 0; if (cs_ctl->len > ADSP_MAX_STD_CTRL_SIZE) { @@ -110,6 +123,13 @@ static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char return; } + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return; + + ctl->cs_ctl = cs_ctl; + ctl->card = info->card; + kcontrol.name = name; kcontrol.info = hda_cs_dsp_coeff_info; kcontrol.iface = SNDRV_CTL_ELEM_IFACE_MIXER; @@ -117,20 +137,22 @@ static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char kcontrol.get = hda_cs_dsp_coeff_get; kcontrol.put = hda_cs_dsp_coeff_put; - /* Save ctl inside private_data, ctl is owned by cs_dsp, - * and will be freed when cs_dsp removes the control */ kctl = snd_ctl_new1(&kcontrol, (void *)ctl); if (!kctl) return; - ret = snd_ctl_add(ctl->card, kctl); + kctl->private_free = hda_cs_dsp_free_kcontrol; + ctl->kctl = kctl; + + /* snd_ctl_add() calls our private_free on error, which will kfree(ctl) */ + cs_ctl->priv = no_free_ptr(ctl); + ret = snd_ctl_add(info->card, kctl); if (ret) { dev_err(cs_ctl->dsp->dev, "Failed to add KControl %s = %d\n", kcontrol.name, ret); return; } dev_dbg(cs_ctl->dsp->dev, "Added KControl: %s\n", kcontrol.name); - ctl->kctl = kctl; } static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, @@ -138,7 +160,6 @@ static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, { struct cs_dsp *cs_dsp = cs_ctl->dsp; char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - struct hda_cs_dsp_coeff_ctl *ctl; const char *region_name; int ret; @@ -163,15 +184,7 @@ static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, " %.*s", cs_ctl->subname_len - skip, cs_ctl->subname + skip); } - ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); - if (!ctl) - return; - - ctl->cs_ctl = cs_ctl; - ctl->card = info->card; - cs_ctl->priv = ctl; - - hda_cs_dsp_add_kcontrol(ctl, name); + hda_cs_dsp_add_kcontrol(cs_ctl, info, name); } void hda_cs_dsp_add_controls(struct cs_dsp *dsp, const struct hda_cs_dsp_ctl_info *info) @@ -203,7 +216,9 @@ void hda_cs_dsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl) { struct hda_cs_dsp_coeff_ctl *ctl = cs_ctl->priv; - kfree(ctl); + /* ctl and kctl may already have been removed by ALSA private_free */ + if (ctl && ctl->kctl) + snd_ctl_remove(ctl->card, ctl->kctl); } EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_control_remove, SND_HDA_CS_DSP_CONTROLS); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a1facdb98d9a0..31b00a2682c99 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2646,6 +2646,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x65f1, "Clevo PC50HS", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65f5, "Clevo PD50PN[NRT]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x66a2, "Clevo PE60RNE", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x66a6, "Clevo PE60SN[CDE]-[GS]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e5, "Clevo PC70D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), @@ -6696,6 +6697,60 @@ static void alc285_fixup_hp_spectre_x360(struct hda_codec *codec, } } +static void alc285_fixup_hp_envy_x360(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + static const struct coef_fw coefs[] = { + WRITE_COEF(0x08, 0x6a0c), WRITE_COEF(0x0d, 0xa023), + WRITE_COEF(0x10, 0x0320), WRITE_COEF(0x1a, 0x8c03), + WRITE_COEF(0x25, 0x1800), WRITE_COEF(0x26, 0x003a), + WRITE_COEF(0x28, 0x1dfe), WRITE_COEF(0x29, 0xb014), + WRITE_COEF(0x2b, 0x1dfe), WRITE_COEF(0x37, 0xfe15), + WRITE_COEF(0x38, 0x7909), WRITE_COEF(0x45, 0xd489), + WRITE_COEF(0x46, 0x00f4), WRITE_COEF(0x4a, 0x21e0), + WRITE_COEF(0x66, 0x03f0), WRITE_COEF(0x67, 0x1000), + WRITE_COEF(0x6e, 0x1005), { } + }; + + static const struct hda_pintbl pincfgs[] = { + { 0x12, 0xb7a60130 }, /* Internal microphone*/ + { 0x14, 0x90170150 }, /* B&O soundbar speakers */ + { 0x17, 0x90170153 }, /* Side speakers */ + { 0x19, 0x03a11040 }, /* Headset microphone */ + { } + }; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + snd_hda_apply_pincfgs(codec, pincfgs); + + /* Fixes volume control problem for side speakers */ + alc295_fixup_disable_dac3(codec, fix, action); + + /* Fixes no sound from headset speaker */ + snd_hda_codec_amp_stereo(codec, 0x21, HDA_OUTPUT, 0, -1, 0); + + /* Auto-enable headset mic when plugged */ + snd_hda_jack_set_gating_jack(codec, 0x19, 0x21); + + /* Headset mic volume enhancement */ + snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREF50); + break; + case HDA_FIXUP_ACT_INIT: + alc_process_coef_fw(codec, coefs); + break; + case HDA_FIXUP_ACT_BUILD: + rename_ctl(codec, "Bass Speaker Playback Volume", + "B&O-Tuned Playback Volume"); + rename_ctl(codec, "Front Playback Switch", + "B&O Soundbar Playback Switch"); + rename_ctl(codec, "Bass Speaker Playback Switch", + "Side Speaker Playback Switch"); + break; + } +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -6844,30 +6899,12 @@ static void comp_generic_playback_hook(struct hda_pcm_stream *hinfo, struct hda_ struct scodec_dev_name { const char *bus; const char *hid; + const char *match_str; int index; }; /* match the device name in a slightly relaxed manner */ -static int comp_match_cs35l41_dev_name(struct device *dev, void *data) -{ - struct scodec_dev_name *p = data; - const char *d = dev_name(dev); - int n = strlen(p->bus); - char tmp[32]; - - /* check the bus name */ - if (strncmp(d, p->bus, n)) - return 0; - /* skip the bus number */ - if (isdigit(d[n])) - n++; - /* the rest must be exact matching */ - snprintf(tmp, sizeof(tmp), "-%s:00-cs35l41-hda.%d", p->hid, p->index); - return !strcmp(d + n, tmp); -} - -static int comp_match_tas2781_dev_name(struct device *dev, - void *data) +static int comp_match_dev_name(struct device *dev, void *data) { struct scodec_dev_name *p = data; const char *d = dev_name(dev); @@ -6881,13 +6918,12 @@ static int comp_match_tas2781_dev_name(struct device *dev, if (isdigit(d[n])) n++; /* the rest must be exact matching */ - snprintf(tmp, sizeof(tmp), "-%s:00", p->hid); - + snprintf(tmp, sizeof(tmp), p->match_str, p->hid, p->index); return !strcmp(d + n, tmp); } -static void cs35l41_generic_fixup(struct hda_codec *cdc, int action, const char *bus, - const char *hid, int count) +static void comp_generic_fixup(struct hda_codec *cdc, int action, const char *bus, + const char *hid, const char *match_str, int count) { struct device *dev = hda_codec_dev(cdc); struct alc_spec *spec = cdc->spec; @@ -6902,10 +6938,11 @@ static void cs35l41_generic_fixup(struct hda_codec *cdc, int action, const char return; rec->bus = bus; rec->hid = hid; + rec->match_str = match_str; rec->index = i; spec->comps[i].codec = cdc; component_match_add(dev, &spec->match, - comp_match_cs35l41_dev_name, rec); + comp_match_dev_name, rec); } ret = component_master_add_with_match(dev, &comp_master_ops, spec->match); if (ret) @@ -6919,83 +6956,53 @@ static void cs35l41_generic_fixup(struct hda_codec *cdc, int action, const char } } -static void tas2781_generic_fixup(struct hda_codec *cdc, int action, - const char *bus, const char *hid) -{ - struct device *dev = hda_codec_dev(cdc); - struct alc_spec *spec = cdc->spec; - struct scodec_dev_name *rec; - int ret; - - switch (action) { - case HDA_FIXUP_ACT_PRE_PROBE: - rec = devm_kmalloc(dev, sizeof(*rec), GFP_KERNEL); - if (!rec) - return; - rec->bus = bus; - rec->hid = hid; - rec->index = 0; - spec->comps[0].codec = cdc; - component_match_add(dev, &spec->match, - comp_match_tas2781_dev_name, rec); - ret = component_master_add_with_match(dev, &comp_master_ops, - spec->match); - if (ret) - codec_err(cdc, - "Fail to register component aggregator %d\n", - ret); - else - spec->gen.pcm_playback_hook = - comp_generic_playback_hook; - break; - case HDA_FIXUP_ACT_FREE: - component_master_del(dev, &comp_master_ops); - break; - } -} - static void cs35l41_fixup_i2c_two(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { - cs35l41_generic_fixup(cdc, action, "i2c", "CSC3551", 2); + comp_generic_fixup(cdc, action, "i2c", "CSC3551", "-%s:00-cs35l41-hda.%d", 2); } static void cs35l41_fixup_i2c_four(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { - cs35l41_generic_fixup(cdc, action, "i2c", "CSC3551", 4); + comp_generic_fixup(cdc, action, "i2c", "CSC3551", "-%s:00-cs35l41-hda.%d", 4); } static void cs35l41_fixup_spi_two(struct hda_codec *codec, const struct hda_fixup *fix, int action) { - cs35l41_generic_fixup(codec, action, "spi", "CSC3551", 2); + comp_generic_fixup(codec, action, "spi", "CSC3551", "-%s:00-cs35l41-hda.%d", 2); } static void cs35l41_fixup_spi_four(struct hda_codec *codec, const struct hda_fixup *fix, int action) { - cs35l41_generic_fixup(codec, action, "spi", "CSC3551", 4); + comp_generic_fixup(codec, action, "spi", "CSC3551", "-%s:00-cs35l41-hda.%d", 4); } static void alc287_fixup_legion_16achg6_speakers(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { - cs35l41_generic_fixup(cdc, action, "i2c", "CLSA0100", 2); + comp_generic_fixup(cdc, action, "i2c", "CLSA0100", "-%s:00-cs35l41-hda.%d", 2); } static void alc287_fixup_legion_16ithg6_speakers(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { - cs35l41_generic_fixup(cdc, action, "i2c", "CLSA0101", 2); + comp_generic_fixup(cdc, action, "i2c", "CLSA0101", "-%s:00-cs35l41-hda.%d", 2); +} + +static void cs35l56_fixup_spi_four(struct hda_codec *cdc, const struct hda_fixup *fix, int action) +{ + comp_generic_fixup(cdc, action, "spi", "CSC3556", "-%s:00-cs35l56-hda.%d", 4); } static void tas2781_fixup_i2c(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { - tas2781_generic_fixup(cdc, action, "i2c", "TIAS2781"); + comp_generic_fixup(cdc, action, "i2c", "TIAS2781", "-%s:00", 1); } static void yoga7_14arb7_fixup_i2c(struct hda_codec *cdc, const struct hda_fixup *fix, int action) { - tas2781_generic_fixup(cdc, action, "i2c", "INT8866"); + comp_generic_fixup(cdc, action, "i2c", "INT8866", "-%s:00", 1); } /* for alc295_fixup_hp_top_speakers */ @@ -7064,6 +7071,25 @@ static void alc256_fixup_mic_no_presence_and_resume(struct hda_codec *codec, } } +static void alc256_decrease_headphone_amp_val(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + u32 caps; + u8 nsteps, offs; + + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + caps = query_amp_caps(codec, 0x3, HDA_OUTPUT); + nsteps = ((caps & AC_AMPCAP_NUM_STEPS) >> AC_AMPCAP_NUM_STEPS_SHIFT) - 10; + offs = ((caps & AC_AMPCAP_OFFSET) >> AC_AMPCAP_OFFSET_SHIFT) - 10; + caps &= ~AC_AMPCAP_NUM_STEPS & ~AC_AMPCAP_OFFSET; + caps |= (nsteps << AC_AMPCAP_NUM_STEPS_SHIFT) | (offs << AC_AMPCAP_OFFSET_SHIFT); + + if (snd_hda_override_amp_caps(codec, 0x3, HDA_OUTPUT, caps)) + codec_warn(codec, "failed to override amp caps for NID 0x3\n"); +} + static void alc_fixup_dell4_mic_no_presence_quiet(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -7297,6 +7323,7 @@ enum { ALC280_FIXUP_HP_9480M, ALC245_FIXUP_HP_X360_AMP, ALC285_FIXUP_HP_SPECTRE_X360_EB1, + ALC285_FIXUP_HP_ENVY_X360, ALC288_FIXUP_DELL_HEADSET_MODE, ALC288_FIXUP_DELL1_MIC_NO_PRESENCE, ALC288_FIXUP_DELL_XPS_13, @@ -7446,6 +7473,7 @@ enum { ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, ALC298_FIXUP_LENOVO_C940_DUET7, ALC287_FIXUP_LENOVO_14IRP8_DUETITL, + ALC287_FIXUP_LENOVO_LEGION_7, ALC287_FIXUP_13S_GEN2_SPEAKERS, ALC256_FIXUP_SET_COEF_DEFAULTS, ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, @@ -7466,6 +7494,7 @@ enum { ALC287_FIXUP_LEGION_16ITHG6, ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK, ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, + ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN, ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS, ALC236_FIXUP_DELL_DUAL_CODECS, ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI, @@ -7478,6 +7507,8 @@ enum { ALC2XX_FIXUP_HEADSET_MIC, ALC289_FIXUP_DELL_CS35L41_SPI_2, ALC294_FIXUP_CS35L41_I2C_2, + ALC256_FIXUP_HEADPHONE_AMP_VOL, + ALC245_FIXUP_CS35L56_SPI_4_HP_GPIO_LED, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -7517,6 +7548,23 @@ static void alc287_fixup_lenovo_14irp8_duetitl(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +/* Another hilarious PCI SSID conflict with Lenovo Legion Pro 7 16ARX8H (with + * TAS2781 codec) and Legion 7i 16IAX7 (with CS35L41 codec); + * we apply a corresponding fixup depending on the codec SSID instead + */ +static void alc287_fixup_lenovo_legion_7(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + int id; + + if (codec->core.subsystem_id == 0x17aa38a8) + id = ALC287_FIXUP_TAS2781_I2C; /* Legion Pro 7 16ARX8H */ + else + id = ALC287_FIXUP_CS35L41_I2C_2; /* Legion 7i 16IAX7 */ + __snd_hda_apply_fixup(codec, id, action, 0); +} + static const struct hda_fixup alc269_fixups[] = { [ALC269_FIXUP_GPIO2] = { .type = HDA_FIXUP_FUNC, @@ -9273,6 +9321,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_spectre_x360_eb1 }, + [ALC285_FIXUP_HP_ENVY_X360] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_envy_x360, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_AMP_INIT, + }, [ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_ideapad_s740_coef, @@ -9405,6 +9459,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_lenovo_14irp8_duetitl, }, + [ALC287_FIXUP_LENOVO_LEGION_7] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_lenovo_legion_7, + }, [ALC287_FIXUP_13S_GEN2_SPEAKERS] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -9589,6 +9647,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK, }, + [ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_yoga9_14iap7_bass_spk_pin, + .chained = true, + .chain_id = ALC287_FIXUP_CS35L41_I2C_2, + }, [ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS] = { .type = HDA_FIXUP_FUNC, .v.func = alc295_fixup_dell_inspiron_top_speakers, @@ -9655,6 +9719,16 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, }, + [ALC256_FIXUP_HEADPHONE_AMP_VOL] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc256_decrease_headphone_amp_val, + }, + [ALC245_FIXUP_CS35L56_SPI_4_HP_GPIO_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l56_fixup_spi_four, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_LED, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -9861,9 +9935,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x86c1, "HP Laptop 15-da3001TU", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO), SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), @@ -9988,16 +10064,32 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8bb3, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8bb4, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c46, "HP EliteBook 830 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c47, "HP EliteBook 840 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c48, "HP EliteBook 860 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c49, "HP Elite x360 830 2-in-1 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c4d, "HP Omen", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8c4e, "HP Omen", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8c52, "HP EliteBook 1040 G11", ALC245_FIXUP_CS35L56_SPI_4_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c53, "HP Elite x360 1040 2-in-1 G11", ALC245_FIXUP_CS35L56_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c7b, "HP ProBook 445 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7c, "HP ProBook 445 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7d, "HP ProBook 465 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7e, "HP ProBook 465 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7f, "HP EliteBook 645 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c80, "HP EliteBook 645 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c81, "HP EliteBook 665 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c89, "HP ProBook 460 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8a, "HP EliteBook 630", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c8d, "HP ProBook 440 G11", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c8e, "HP ProBook 460 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c90, "HP EliteBook 640", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), @@ -10100,9 +10192,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC), @@ -10127,7 +10219,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x12cc, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), - SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), + SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP), @@ -10145,12 +10237,15 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x152d, 0x1082, "Quanta NL3", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x152d, 0x1262, "Huawei NBLB-WAX9N", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x0353, "Clevo V35[05]SN[CDE]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1325, "Clevo N15[01][CW]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1401, "Clevo L140[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1403, "Clevo N140CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x2624, "Clevo L240TU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -10248,6 +10343,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x222e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), + SND_PCI_QUIRK(0x17aa, 0x2234, "Thinkpad ICE-1", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x2245, "Thinkpad T470", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2246, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2247, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), @@ -10285,7 +10381,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940 / Yoga Duet 7", ALC298_FIXUP_LENOVO_C940_DUET7), SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), - SND_PCI_QUIRK(0x17aa, 0x3820, "Yoga Duet 7 13ITL6", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3820, "IdeaPad 330-17IKB 81DM", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3824, "Legion Y9000X 2020", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), @@ -10296,19 +10392,24 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3855, "Legion 7 16ITHG6", ALC287_FIXUP_LEGION_16ITHG6), + SND_PCI_QUIRK(0x17aa, 0x3865, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x3866, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), - SND_PCI_QUIRK(0x17aa, 0x386f, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7/7i", ALC287_FIXUP_LENOVO_LEGION_7), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), + SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x3878, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3881, "YB9 dual power mode2 YC", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3882, "Lenovo Yoga Pro 7 14APH8", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3884, "Y780 YG DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x17aa, 0x3891, "Lenovo Yoga Pro 7 14AHP9", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a8, "Y780P AMD VECO dual", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2), @@ -10320,6 +10421,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38c3, "Y980 DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38cb, "Y790 YG DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38cd, "Y790 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x17aa, 0x38d2, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), + SND_PCI_QUIRK(0x17aa, 0x38d7, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), @@ -10347,6 +10450,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x9e56, "Lenovo ZhaoYang CF4620Z", ALC286_FIXUP_SONY_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK), SND_PCI_QUIRK(0x1849, 0xa233, "Positivo Master C6300", ALC269_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1854, 0x0440, "LG CQ6", ALC256_FIXUP_HEADPHONE_AMP_VOL), + SND_PCI_QUIRK(0x1854, 0x0441, "LG CQ6 AIO", ALC256_FIXUP_HEADPHONE_AMP_VOL), SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS), SND_PCI_QUIRK(0x19e5, 0x320f, "Huawei WRT-WX9 ", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20), @@ -10355,6 +10460,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), + SND_PCI_QUIRK(0x1c6c, 0x122a, "Positivo N14AP7", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1c6c, 0x1251, "Positivo N14KP6-TG", ALC288_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS), SND_PCI_QUIRK(0x1d05, 0x1096, "TongFang GMxMRxx", ALC269_FIXUP_NO_SHUTUP), @@ -10365,6 +10471,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x1147, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), + SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), @@ -10377,7 +10485,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), - SND_PCI_QUIRK(0xf111, 0x0005, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 @@ -10559,6 +10666,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360_EB1, .name = "alc285-hp-spectre-x360-eb1"}, + {.id = ALC285_FIXUP_HP_ENVY_X360, .name = "alc285-hp-envy-x360"}, {.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"}, {.id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, .name = "alc287-yoga9-bass-spk-pin"}, {.id = ALC623_FIXUP_LENOVO_THINKSTATION_P340, .name = "alc623-lenovo-thinkstation-p340"}, diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 1bfb00102a77a..73dc50f499455 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -89,7 +89,7 @@ struct tas2781_hda { struct snd_kcontrol *dsp_prog_ctl; struct snd_kcontrol *dsp_conf_ctl; struct snd_kcontrol *prof_ctl; - struct snd_kcontrol *snd_ctls[3]; + struct snd_kcontrol *snd_ctls[2]; }; static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data) @@ -160,11 +160,13 @@ static void tas2781_hda_playback_hook(struct device *dev, int action) pm_runtime_get_sync(dev); mutex_lock(&tas_hda->priv->codec_lock); tasdevice_tuning_switch(tas_hda->priv, 0); + tas_hda->priv->playback_started = true; mutex_unlock(&tas_hda->priv->codec_lock); break; case HDA_GEN_PCM_ACT_CLOSE: mutex_lock(&tas_hda->priv->codec_lock); tasdevice_tuning_switch(tas_hda->priv, 1); + tas_hda->priv->playback_started = false; mutex_unlock(&tas_hda->priv->codec_lock); pm_runtime_mark_last_busy(dev); @@ -195,8 +197,12 @@ static int tasdevice_get_profile_id(struct snd_kcontrol *kcontrol, { struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + mutex_lock(&tas_priv->codec_lock); + ucontrol->value.integer.value[0] = tas_priv->rcabin.profile_cfg_id; + mutex_unlock(&tas_priv->codec_lock); + return 0; } @@ -210,11 +216,15 @@ static int tasdevice_set_profile_id(struct snd_kcontrol *kcontrol, val = clamp(nr_profile, 0, max); + mutex_lock(&tas_priv->codec_lock); + if (tas_priv->rcabin.profile_cfg_id != val) { tas_priv->rcabin.profile_cfg_id = val; ret = 1; } + mutex_unlock(&tas_priv->codec_lock); + return ret; } @@ -251,8 +261,12 @@ static int tasdevice_program_get(struct snd_kcontrol *kcontrol, { struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + mutex_lock(&tas_priv->codec_lock); + ucontrol->value.integer.value[0] = tas_priv->cur_prog; + mutex_unlock(&tas_priv->codec_lock); + return 0; } @@ -267,11 +281,15 @@ static int tasdevice_program_put(struct snd_kcontrol *kcontrol, val = clamp(nr_program, 0, max); + mutex_lock(&tas_priv->codec_lock); + if (tas_priv->cur_prog != val) { tas_priv->cur_prog = val; ret = 1; } + mutex_unlock(&tas_priv->codec_lock); + return ret; } @@ -280,8 +298,12 @@ static int tasdevice_config_get(struct snd_kcontrol *kcontrol, { struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + mutex_lock(&tas_priv->codec_lock); + ucontrol->value.integer.value[0] = tas_priv->cur_conf; + mutex_unlock(&tas_priv->codec_lock); + return 0; } @@ -296,33 +318,16 @@ static int tasdevice_config_put(struct snd_kcontrol *kcontrol, val = clamp(nr_config, 0, max); + mutex_lock(&tas_priv->codec_lock); + if (tas_priv->cur_conf != val) { tas_priv->cur_conf = val; ret = 1; } - return ret; -} - -/* - * tas2781_digital_getvol - get the volum control - * @kcontrol: control pointer - * @ucontrol: User data - * Customer Kcontrol for tas2781 is primarily for regmap booking, paging - * depends on internal regmap mechanism. - * tas2781 contains book and page two-level register map, especially - * book switching will set the register BXXP00R7F, after switching to the - * correct book, then leverage the mechanism for paging to access the - * register. - */ -static int tas2781_digital_getvol(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); - struct soc_mixer_control *mc = - (struct soc_mixer_control *)kcontrol->private_value; + mutex_unlock(&tas_priv->codec_lock); - return tasdevice_digital_getvol(tas_priv, ucontrol, mc); + return ret; } static int tas2781_amp_getvol(struct snd_kcontrol *kcontrol, @@ -331,19 +336,15 @@ static int tas2781_amp_getvol(struct snd_kcontrol *kcontrol, struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; + int ret; - return tasdevice_amp_getvol(tas_priv, ucontrol, mc); -} + mutex_lock(&tas_priv->codec_lock); -static int tas2781_digital_putvol(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); - struct soc_mixer_control *mc = - (struct soc_mixer_control *)kcontrol->private_value; + ret = tasdevice_amp_getvol(tas_priv, ucontrol, mc); - /* The check of the given value is in tasdevice_digital_putvol. */ - return tasdevice_digital_putvol(tas_priv, ucontrol, mc); + mutex_unlock(&tas_priv->codec_lock); + + return ret; } static int tas2781_amp_putvol(struct snd_kcontrol *kcontrol, @@ -352,9 +353,16 @@ static int tas2781_amp_putvol(struct snd_kcontrol *kcontrol, struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value; + int ret; + + mutex_lock(&tas_priv->codec_lock); /* The check of the given value is in tasdevice_amp_putvol. */ - return tasdevice_amp_putvol(tas_priv, ucontrol, mc); + ret = tasdevice_amp_putvol(tas_priv, ucontrol, mc); + + mutex_unlock(&tas_priv->codec_lock); + + return ret; } static int tas2781_force_fwload_get(struct snd_kcontrol *kcontrol, @@ -362,10 +370,14 @@ static int tas2781_force_fwload_get(struct snd_kcontrol *kcontrol, { struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); + mutex_lock(&tas_priv->codec_lock); + ucontrol->value.integer.value[0] = (int)tas_priv->force_fwload_status; dev_dbg(tas_priv->dev, "%s : Force FWload %s\n", __func__, tas_priv->force_fwload_status ? "ON" : "OFF"); + mutex_unlock(&tas_priv->codec_lock); + return 0; } @@ -375,6 +387,8 @@ static int tas2781_force_fwload_put(struct snd_kcontrol *kcontrol, struct tasdevice_priv *tas_priv = snd_kcontrol_chip(kcontrol); bool change, val = (bool)ucontrol->value.integer.value[0]; + mutex_lock(&tas_priv->codec_lock); + if (tas_priv->force_fwload_status == val) change = false; else { @@ -384,6 +398,8 @@ static int tas2781_force_fwload_put(struct snd_kcontrol *kcontrol, dev_dbg(tas_priv->dev, "%s : Force FWload %s\n", __func__, tas_priv->force_fwload_status ? "ON" : "OFF"); + mutex_unlock(&tas_priv->codec_lock); + return change; } @@ -391,9 +407,6 @@ static const struct snd_kcontrol_new tas2781_snd_controls[] = { ACARD_SINGLE_RANGE_EXT_TLV("Speaker Analog Gain", TAS2781_AMP_LEVEL, 1, 0, 20, 0, tas2781_amp_getvol, tas2781_amp_putvol, amp_vol_tlv), - ACARD_SINGLE_RANGE_EXT_TLV("Speaker Digital Gain", TAS2781_DVC_LVL, - 0, 0, 200, 1, tas2781_digital_getvol, - tas2781_digital_putvol, dvc_tlv), ACARD_SINGLE_BOOL_EXT("Speaker Force Firmware Load", 0, tas2781_force_fwload_get, tas2781_force_fwload_put), }; @@ -488,10 +501,10 @@ static int tas2563_save_calibration(struct tasdevice_priv *tas_priv) static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) { static const unsigned char page_array[CALIB_MAX] = { - 0x17, 0x18, 0x18, 0x0d, 0x18 + 0x17, 0x18, 0x18, 0x13, 0x18, }; static const unsigned char rgno_array[CALIB_MAX] = { - 0x74, 0x0c, 0x14, 0x3c, 0x7c + 0x74, 0x0c, 0x14, 0x70, 0x7c, }; unsigned char *data; int i, j, rc; @@ -666,6 +679,7 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) tasdevice_save_calibration(tas_priv); tasdevice_tuning_switch(tas_hda->priv, 0); + tas_hda->priv->playback_started = true; out: mutex_unlock(&tas_hda->priv->codec_lock); @@ -750,11 +764,11 @@ static void tas2781_hda_remove(struct device *dev) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + component_del(tas_hda->dev, &tas2781_hda_comp_ops); + pm_runtime_get_sync(tas_hda->dev); pm_runtime_disable(tas_hda->dev); - component_del(tas_hda->dev, &tas2781_hda_comp_ops); - pm_runtime_put_noidle(tas_hda->dev); tasdevice_remove(tas_hda->priv); @@ -832,23 +846,19 @@ static void tas2781_hda_i2c_remove(struct i2c_client *clt) static int tas2781_runtime_suspend(struct device *dev) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); - int i; dev_dbg(tas_hda->dev, "Runtime Suspend\n"); mutex_lock(&tas_hda->priv->codec_lock); + /* The driver powers up the amplifiers at module load time. + * Stop the playback if it's unused. + */ if (tas_hda->priv->playback_started) { tasdevice_tuning_switch(tas_hda->priv, 1); tas_hda->priv->playback_started = false; } - for (i = 0; i < tas_hda->priv->ndev; i++) { - tas_hda->priv->tasdevice[i].cur_book = -1; - tas_hda->priv->tasdevice[i].cur_prog = -1; - tas_hda->priv->tasdevice[i].cur_conf = -1; - } - mutex_unlock(&tas_hda->priv->codec_lock); return 0; @@ -877,16 +887,16 @@ static int tas2781_runtime_resume(struct device *dev) static int tas2781_system_suspend(struct device *dev) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); - int ret; dev_dbg(tas_hda->priv->dev, "System Suspend\n"); - ret = pm_runtime_force_suspend(dev); - if (ret) - return ret; + mutex_lock(&tas_hda->priv->codec_lock); /* Shutdown chip before system suspend */ - tasdevice_tuning_switch(tas_hda->priv, 1); + if (tas_hda->priv->playback_started) + tasdevice_tuning_switch(tas_hda->priv, 1); + + mutex_unlock(&tas_hda->priv->codec_lock); /* * Reset GPIO may be shared, so cannot reset here. @@ -898,13 +908,9 @@ static int tas2781_system_suspend(struct device *dev) static int tas2781_system_resume(struct device *dev) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); - int i, ret; + int i; - dev_info(tas_hda->priv->dev, "System Resume\n"); - - ret = pm_runtime_force_resume(dev); - if (ret) - return ret; + dev_dbg(tas_hda->priv->dev, "System Resume\n"); mutex_lock(&tas_hda->priv->codec_lock); @@ -920,6 +926,10 @@ static int tas2781_system_resume(struct device *dev) * calibrated data inside algo. */ tasdevice_apply_calibration(tas_hda->priv); + + if (tas_hda->priv->playback_started) + tasdevice_tuning_switch(tas_hda->priv, 0); + mutex_unlock(&tas_hda->priv->codec_lock); return 0; diff --git a/sound/sh/aica.c b/sound/sh/aica.c index 320ac792c7fe2..3182c634464d4 100644 --- a/sound/sh/aica.c +++ b/sound/sh/aica.c @@ -278,7 +278,8 @@ static void run_spu_dma(struct work_struct *work) dreamcastcard->clicks++; if (unlikely(dreamcastcard->clicks >= AICA_PERIOD_NUMBER)) dreamcastcard->clicks %= AICA_PERIOD_NUMBER; - mod_timer(&dreamcastcard->timer, jiffies + 1); + if (snd_pcm_running(dreamcastcard->substream)) + mod_timer(&dreamcastcard->timer, jiffies + 1); } } @@ -290,6 +291,8 @@ static void aica_period_elapsed(struct timer_list *t) /*timer function - so cannot sleep */ int play_period; struct snd_pcm_runtime *runtime; + if (!snd_pcm_running(substream)) + return; runtime = substream->runtime; dreamcastcard = substream->pcm->private_data; /* Have we played out an additional period? */ @@ -350,12 +353,19 @@ static int snd_aicapcm_pcm_open(struct snd_pcm_substream return 0; } +static int snd_aicapcm_pcm_sync_stop(struct snd_pcm_substream *substream) +{ + struct snd_card_aica *dreamcastcard = substream->pcm->private_data; + + del_timer_sync(&dreamcastcard->timer); + cancel_work_sync(&dreamcastcard->spu_dma_work); + return 0; +} + static int snd_aicapcm_pcm_close(struct snd_pcm_substream *substream) { struct snd_card_aica *dreamcastcard = substream->pcm->private_data; - flush_work(&(dreamcastcard->spu_dma_work)); - del_timer(&dreamcastcard->timer); dreamcastcard->substream = NULL; kfree(dreamcastcard->channel); spu_disable(); @@ -401,6 +411,7 @@ static const struct snd_pcm_ops snd_aicapcm_playback_ops = { .prepare = snd_aicapcm_pcm_prepare, .trigger = snd_aicapcm_pcm_trigger, .pointer = snd_aicapcm_pcm_pointer, + .sync_stop = snd_aicapcm_pcm_sync_stop, }; /* TO DO: set up to handle more than one pcm instance */ diff --git a/sound/soc/amd/acp/acp-legacy-common.c b/sound/soc/amd/acp/acp-legacy-common.c index b5aff3f230be5..3be7c6d55a6f8 100644 --- a/sound/soc/amd/acp/acp-legacy-common.c +++ b/sound/soc/amd/acp/acp-legacy-common.c @@ -358,11 +358,25 @@ int smn_read(struct pci_dev *dev, u32 smn_addr) } EXPORT_SYMBOL_NS_GPL(smn_read, SND_SOC_ACP_COMMON); -int check_acp_pdm(struct pci_dev *pci, struct acp_chip_info *chip) +static void check_acp3x_config(struct acp_chip_info *chip) { - struct acpi_device *pdm_dev; - const union acpi_object *obj; - u32 pdm_addr, val; + u32 val; + + val = readl(chip->base + ACP3X_PIN_CONFIG); + switch (val) { + case ACP_CONFIG_4: + chip->is_i2s_config = true; + chip->is_pdm_config = true; + break; + default: + chip->is_pdm_config = true; + break; + } +} + +static void check_acp6x_config(struct acp_chip_info *chip) +{ + u32 val; val = readl(chip->base + ACP_PIN_CONFIG); switch (val) { @@ -371,42 +385,94 @@ int check_acp_pdm(struct pci_dev *pci, struct acp_chip_info *chip) case ACP_CONFIG_6: case ACP_CONFIG_7: case ACP_CONFIG_8: - case ACP_CONFIG_10: case ACP_CONFIG_11: + case ACP_CONFIG_14: + chip->is_pdm_config = true; + break; + case ACP_CONFIG_9: + chip->is_i2s_config = true; + break; + case ACP_CONFIG_10: case ACP_CONFIG_12: case ACP_CONFIG_13: + chip->is_i2s_config = true; + chip->is_pdm_config = true; + break; + default: + break; + } +} + +static void check_acp70_config(struct acp_chip_info *chip) +{ + u32 val; + + val = readl(chip->base + ACP_PIN_CONFIG); + switch (val) { + case ACP_CONFIG_4: + case ACP_CONFIG_5: + case ACP_CONFIG_6: + case ACP_CONFIG_7: + case ACP_CONFIG_8: + case ACP_CONFIG_11: case ACP_CONFIG_14: + case ACP_CONFIG_17: + case ACP_CONFIG_18: + chip->is_pdm_config = true; + break; + case ACP_CONFIG_9: + chip->is_i2s_config = true; + break; + case ACP_CONFIG_10: + case ACP_CONFIG_12: + case ACP_CONFIG_13: + case ACP_CONFIG_19: + case ACP_CONFIG_20: + chip->is_i2s_config = true; + chip->is_pdm_config = true; break; default: - return -EINVAL; + break; } +} + +void check_acp_config(struct pci_dev *pci, struct acp_chip_info *chip) +{ + struct acpi_device *pdm_dev; + const union acpi_object *obj; + u32 pdm_addr; switch (chip->acp_rev) { case ACP3X_DEV: pdm_addr = ACP_RENOIR_PDM_ADDR; + check_acp3x_config(chip); break; case ACP6X_DEV: pdm_addr = ACP_REMBRANDT_PDM_ADDR; + check_acp6x_config(chip); break; case ACP63_DEV: pdm_addr = ACP63_PDM_ADDR; + check_acp6x_config(chip); break; case ACP70_DEV: pdm_addr = ACP70_PDM_ADDR; + check_acp70_config(chip); break; default: - return -EINVAL; + break; } - pdm_dev = acpi_find_child_device(ACPI_COMPANION(&pci->dev), pdm_addr, 0); - if (pdm_dev) { - if (!acpi_dev_get_property(pdm_dev, "acp-audio-device-type", - ACPI_TYPE_INTEGER, &obj) && - obj->integer.value == pdm_addr) - return 0; + if (chip->is_pdm_config) { + pdm_dev = acpi_find_child_device(ACPI_COMPANION(&pci->dev), pdm_addr, 0); + if (pdm_dev) { + if (!acpi_dev_get_property(pdm_dev, "acp-audio-device-type", + ACPI_TYPE_INTEGER, &obj) && + obj->integer.value == pdm_addr) + chip->is_pdm_dev = true; + } } - return -ENODEV; } -EXPORT_SYMBOL_NS_GPL(check_acp_pdm, SND_SOC_ACP_COMMON); +EXPORT_SYMBOL_NS_GPL(check_acp_config, SND_SOC_ACP_COMMON); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/sound/soc/amd/acp/acp-pci.c b/sound/soc/amd/acp/acp-pci.c index 8c8b1dcac6281..ad320b29e87dc 100644 --- a/sound/soc/amd/acp/acp-pci.c +++ b/sound/soc/amd/acp/acp-pci.c @@ -100,7 +100,6 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id ret = -EINVAL; goto release_regions; } - dmic_dev = platform_device_register_data(dev, "dmic-codec", PLATFORM_DEVID_NONE, NULL, 0); if (IS_ERR(dmic_dev)) { dev_err(dev, "failed to create DMIC device\n"); @@ -115,7 +114,14 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id goto unregister_dmic_dev; } - acp_init(chip); + ret = acp_init(chip); + if (ret) + goto unregister_dmic_dev; + + check_acp_config(pci, chip); + if (!chip->is_pdm_dev && !chip->is_i2s_config) + goto skip_pdev_creation; + res = devm_kcalloc(&pci->dev, num_res, sizeof(struct resource), GFP_KERNEL); if (!res) { ret = -ENOMEM; @@ -133,12 +139,6 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id } } - if (flag == FLAG_AMD_LEGACY_ONLY_DMIC) { - ret = check_acp_pdm(pci, chip); - if (ret < 0) - goto skip_pdev_creation; - } - chip->flag = flag; memset(&pdevinfo, 0, sizeof(pdevinfo)); diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c index 20b94814a0462..b86f65d420054 100644 --- a/sound/soc/amd/acp/acp-sof-mach.c +++ b/sound/soc/amd/acp/acp-sof-mach.c @@ -126,16 +126,14 @@ static int acp_sof_probe(struct platform_device *pdev) if (dmi_id && dmi_id->driver_data) acp_card_drvdata->tdm_mode = dmi_id->driver_data; - acp_sofdsp_dai_links_create(card); + ret = acp_sofdsp_dai_links_create(card); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to create DAI links\n"); ret = devm_snd_soc_register_card(&pdev->dev, card); - if (ret) { - dev_err(&pdev->dev, - "devm_snd_soc_register_card(%s) failed: %d\n", - card->name, ret); - return ret; - } - + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Failed to register card(%s)\n", card->name); return 0; } diff --git a/sound/soc/amd/acp/amd.h b/sound/soc/amd/acp/amd.h index 5017e868f39b9..d75b4eb34de8d 100644 --- a/sound/soc/amd/acp/amd.h +++ b/sound/soc/amd/acp/amd.h @@ -138,6 +138,9 @@ struct acp_chip_info { void __iomem *base; /* ACP memory PCI base */ struct platform_device *chip_pdev; unsigned int flag; /* Distinguish b/w Legacy or Only PDM */ + bool is_pdm_dev; /* flag set to true when ACP PDM controller exists */ + bool is_pdm_config; /* flag set to true when PDM configuration is selected from BIOS */ + bool is_i2s_config; /* flag set to true when I2S configuration is selected from BIOS */ }; struct acp_stream { @@ -212,6 +215,11 @@ enum acp_config { ACP_CONFIG_13, ACP_CONFIG_14, ACP_CONFIG_15, + ACP_CONFIG_16, + ACP_CONFIG_17, + ACP_CONFIG_18, + ACP_CONFIG_19, + ACP_CONFIG_20, }; extern const struct snd_soc_dai_ops asoc_acp_cpu_dai_ops; @@ -240,7 +248,7 @@ void restore_acp_pdm_params(struct snd_pcm_substream *substream, int restore_acp_i2s_params(struct snd_pcm_substream *substream, struct acp_dev_data *adata, struct acp_stream *stream); -int check_acp_pdm(struct pci_dev *pci, struct acp_chip_info *chip); +void check_acp_config(struct pci_dev *pci, struct acp_chip_info *chip); static inline u64 acp_get_byte_count(struct acp_dev_data *adata, int dai_id, int direction) { diff --git a/sound/soc/amd/acp/chip_offset_byte.h b/sound/soc/amd/acp/chip_offset_byte.h index cfd6c4d075944..18da734c0e9e7 100644 --- a/sound/soc/amd/acp/chip_offset_byte.h +++ b/sound/soc/amd/acp/chip_offset_byte.h @@ -20,6 +20,7 @@ #define ACP_SOFT_RESET 0x1000 #define ACP_CONTROL 0x1004 #define ACP_PIN_CONFIG 0x1440 +#define ACP3X_PIN_CONFIG 0x1400 #define ACP_EXTERNAL_INTR_REG_ADDR(adata, offset, ctrl) \ (adata->acp_base + adata->rsrc->irq_reg_offset + offset + (ctrl * 0x04)) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 90360f8b3e81b..1760b5d42460a 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -199,13 +199,6 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "21HY"), } }, - { - .driver_data = &acp6x_card, - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "21J2"), - } - }, { .driver_data = &acp6x_card, .matches = { @@ -318,6 +311,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "E1504FA"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M7600RE"), + } + }, { .driver_data = &acp6x_card, .matches = { @@ -430,6 +430,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_BOARD_NAME, "MRID6"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "MDC"), + DMI_MATCH(DMI_BOARD_NAME, "Herbag_MDU"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/amd/yc/pci-acp6x.c b/sound/soc/amd/yc/pci-acp6x.c index 694b8e3139024..7af6a349b1d41 100644 --- a/sound/soc/amd/yc/pci-acp6x.c +++ b/sound/soc/amd/yc/pci-acp6x.c @@ -162,7 +162,6 @@ static int snd_acp6x_probe(struct pci_dev *pci, /* Yellow Carp device check */ switch (pci->revision) { case 0x60: - case 0x63: case 0x6f: break; default: diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index dfb4ce53491bb..f8e57a2fc3e32 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -1094,6 +1094,7 @@ static int cs35l41_handle_pdata(struct device *dev, struct cs35l41_hw_cfg *hw_cf static int cs35l41_dsp_init(struct cs35l41_private *cs35l41) { struct wm_adsp *dsp; + uint32_t dsp1rx5_src; int ret; dsp = &cs35l41->dsp; @@ -1113,16 +1114,29 @@ static int cs35l41_dsp_init(struct cs35l41_private *cs35l41) return ret; } - ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC, - CS35L41_INPUT_SRC_VPMON); + switch (cs35l41->hw_cfg.bst_type) { + case CS35L41_INT_BOOST: + case CS35L41_SHD_BOOST_ACTV: + dsp1rx5_src = CS35L41_INPUT_SRC_VPMON; + break; + case CS35L41_EXT_BOOST: + case CS35L41_SHD_BOOST_PASS: + dsp1rx5_src = CS35L41_INPUT_SRC_VBSTMON; + break; + default: + dev_err(cs35l41->dev, "wm_halo_init failed - Invalid Boost Type: %d\n", + cs35l41->hw_cfg.bst_type); + goto err_dsp; + } + + ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC, dsp1rx5_src); if (ret < 0) { - dev_err(cs35l41->dev, "Write INPUT_SRC_VPMON failed: %d\n", ret); + dev_err(cs35l41->dev, "Write DSP1RX5_SRC: %d failed: %d\n", dsp1rx5_src, ret); goto err_dsp; } - ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC, - CS35L41_INPUT_SRC_CLASSH); + ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC, CS35L41_INPUT_SRC_VBSTMON); if (ret < 0) { - dev_err(cs35l41->dev, "Write INPUT_SRC_CLASSH failed: %d\n", ret); + dev_err(cs35l41->dev, "Write CS35L41_INPUT_SRC_VBSTMON failed: %d\n", ret); goto err_dsp; } ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX7_SRC, diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 6dd0319bc843c..ea72afe3f906f 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -1297,6 +1297,7 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 "spk-id-gpios", ACPI_TYPE_PACKAGE, &obj); if (ret) { dev_dbg(cs35l56->base.dev, "Could not get spk-id-gpios package: %d\n", ret); + fwnode_handle_put(af01_fwnode); return -ENOENT; } @@ -1304,6 +1305,7 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 if (obj->package.count != 4) { dev_warn(cs35l56->base.dev, "Unexpected spk-id element count %d\n", obj->package.count); + fwnode_handle_put(af01_fwnode); return -ENOENT; } @@ -1318,6 +1320,7 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 */ ret = acpi_dev_add_driver_gpios(adev, cs35l56_af01_spkid_gpios_mapping); if (ret) { + fwnode_handle_put(af01_fwnode); return dev_err_probe(cs35l56->base.dev, ret, "Failed to add gpio mapping to AF01\n"); } @@ -1325,14 +1328,17 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 ret = devm_add_action_or_reset(cs35l56->base.dev, cs35l56_acpi_dev_release_driver_gpios, adev); - if (ret) + if (ret) { + fwnode_handle_put(af01_fwnode); return ret; + } dev_dbg(cs35l56->base.dev, "Added spk-id-gpios mapping to AF01\n"); } desc = fwnode_gpiod_get_index(af01_fwnode, "spk-id", 0, GPIOD_IN, NULL); if (IS_ERR(desc)) { + fwnode_handle_put(af01_fwnode); ret = PTR_ERR(desc); return dev_err_probe(cs35l56->base.dev, ret, "Get GPIO from AF01 failed\n"); } @@ -1341,9 +1347,12 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 gpiod_put(desc); if (ret < 0) { + fwnode_handle_put(af01_fwnode); dev_err_probe(cs35l56->base.dev, ret, "Error reading spk-id GPIO\n"); return ret; - } + } + + fwnode_handle_put(af01_fwnode); dev_info(cs35l56->base.dev, "Got spk-id from AF01\n"); diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c index a97ccb512deba..193ef7543930a 100644 --- a/sound/soc/codecs/cs42l43.c +++ b/sound/soc/codecs/cs42l43.c @@ -300,8 +300,9 @@ static int cs42l43_startup(struct snd_pcm_substream *substream, struct snd_soc_d struct snd_soc_component *component = dai->component; struct cs42l43_codec *priv = snd_soc_component_get_drvdata(component); struct cs42l43 *cs42l43 = priv->core; - int provider = !!regmap_test_bits(cs42l43->regmap, CS42L43_ASP_CLK_CONFIG2, - CS42L43_ASP_MASTER_MODE_MASK); + int provider = !dai->id || !!regmap_test_bits(cs42l43->regmap, + CS42L43_ASP_CLK_CONFIG2, + CS42L43_ASP_MASTER_MODE_MASK); if (provider) priv->constraint.mask = CS42L43_PROVIDER_RATE_MASK; @@ -2338,7 +2339,8 @@ static int cs42l43_codec_runtime_resume(struct device *dev) static int cs42l43_codec_suspend(struct device *dev) { - struct cs42l43 *cs42l43 = dev_get_drvdata(dev); + struct cs42l43_codec *priv = dev_get_drvdata(dev); + struct cs42l43 *cs42l43 = priv->core; disable_irq(cs42l43->irq); @@ -2347,7 +2349,8 @@ static int cs42l43_codec_suspend(struct device *dev) static int cs42l43_codec_suspend_noirq(struct device *dev) { - struct cs42l43 *cs42l43 = dev_get_drvdata(dev); + struct cs42l43_codec *priv = dev_get_drvdata(dev); + struct cs42l43 *cs42l43 = priv->core; enable_irq(cs42l43->irq); @@ -2356,7 +2359,8 @@ static int cs42l43_codec_suspend_noirq(struct device *dev) static int cs42l43_codec_resume(struct device *dev) { - struct cs42l43 *cs42l43 = dev_get_drvdata(dev); + struct cs42l43_codec *priv = dev_get_drvdata(dev); + struct cs42l43 *cs42l43 = priv->core; enable_irq(cs42l43->irq); @@ -2365,7 +2369,8 @@ static int cs42l43_codec_resume(struct device *dev) static int cs42l43_codec_resume_noirq(struct device *dev) { - struct cs42l43 *cs42l43 = dev_get_drvdata(dev); + struct cs42l43_codec *priv = dev_get_drvdata(dev); + struct cs42l43 *cs42l43 = priv->core; disable_irq(cs42l43->irq); diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c index 6bc068cdcbe2a..15e5e3eb592b3 100644 --- a/sound/soc/codecs/da7219-aad.c +++ b/sound/soc/codecs/da7219-aad.c @@ -671,8 +671,10 @@ static struct da7219_aad_pdata *da7219_aad_fw_to_pdata(struct device *dev) return NULL; aad_pdata = devm_kzalloc(dev, sizeof(*aad_pdata), GFP_KERNEL); - if (!aad_pdata) + if (!aad_pdata) { + fwnode_handle_put(aad_np); return NULL; + } aad_pdata->irq = i2c->irq; @@ -753,6 +755,8 @@ static struct da7219_aad_pdata *da7219_aad_fw_to_pdata(struct device *dev) else aad_pdata->adc_1bit_rpt = DA7219_AAD_ADC_1BIT_RPT_1; + fwnode_handle_put(aad_np); + return aad_pdata; } diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c index cbcd02ec6ba42..a3dbeebaeb0c9 100644 --- a/sound/soc/codecs/es8326.c +++ b/sound/soc/codecs/es8326.c @@ -326,9 +326,9 @@ static const struct _coeff_div coeff_div_v3[] = { {125, 48000, 6000000, 0x04, 0x04, 0x1F, 0x2D, 0x8A, 0x0A, 0x27, 0x27}, {128, 8000, 1024000, 0x60, 0x00, 0x05, 0x75, 0x8A, 0x1B, 0x1F, 0x7F}, - {128, 16000, 2048000, 0x20, 0x00, 0x31, 0x35, 0x8A, 0x1B, 0x1F, 0x3F}, - {128, 44100, 5644800, 0xE0, 0x00, 0x01, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F}, - {128, 48000, 6144000, 0xE0, 0x00, 0x01, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F}, + {128, 16000, 2048000, 0x20, 0x00, 0x31, 0x35, 0x08, 0x19, 0x1F, 0x3F}, + {128, 44100, 5644800, 0xE0, 0x00, 0x01, 0x2D, 0x48, 0x08, 0x1F, 0x1F}, + {128, 48000, 6144000, 0xE0, 0x00, 0x01, 0x2D, 0x48, 0x08, 0x1F, 0x1F}, {144, 8000, 1152000, 0x20, 0x00, 0x03, 0x35, 0x8A, 0x1B, 0x23, 0x47}, {144, 16000, 2304000, 0x20, 0x00, 0x11, 0x35, 0x8A, 0x1B, 0x23, 0x47}, {192, 8000, 1536000, 0x60, 0x02, 0x0D, 0x75, 0x8A, 0x1B, 0x1F, 0x7F}, @@ -337,10 +337,10 @@ static const struct _coeff_div coeff_div_v3[] = { {200, 48000, 9600000, 0x04, 0x04, 0x0F, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F}, {250, 48000, 12000000, 0x04, 0x04, 0x0F, 0x2D, 0xCA, 0x0A, 0x27, 0x27}, - {256, 8000, 2048000, 0x60, 0x00, 0x31, 0x35, 0x8A, 0x1B, 0x1F, 0x7F}, - {256, 16000, 4096000, 0x20, 0x00, 0x01, 0x35, 0x8A, 0x1B, 0x1F, 0x3F}, - {256, 44100, 11289600, 0xE0, 0x00, 0x30, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F}, - {256, 48000, 12288000, 0xE0, 0x00, 0x30, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F}, + {256, 8000, 2048000, 0x60, 0x00, 0x31, 0x35, 0x08, 0x19, 0x1F, 0x7F}, + {256, 16000, 4096000, 0x20, 0x00, 0x01, 0x35, 0x08, 0x19, 0x1F, 0x3F}, + {256, 44100, 11289600, 0xE0, 0x01, 0x01, 0x2D, 0x48, 0x08, 0x1F, 0x1F}, + {256, 48000, 12288000, 0xE0, 0x01, 0x01, 0x2D, 0x48, 0x08, 0x1F, 0x1F}, {288, 8000, 2304000, 0x20, 0x00, 0x01, 0x35, 0x8A, 0x1B, 0x23, 0x47}, {384, 8000, 3072000, 0x60, 0x02, 0x05, 0x75, 0x8A, 0x1B, 0x1F, 0x7F}, {384, 16000, 6144000, 0x20, 0x02, 0x03, 0x35, 0x8A, 0x1B, 0x1F, 0x3F}, @@ -349,10 +349,10 @@ static const struct _coeff_div coeff_div_v3[] = { {400, 48000, 19200000, 0xE4, 0x04, 0x35, 0x6d, 0xCA, 0x0A, 0x1F, 0x1F}, {500, 48000, 24000000, 0xF8, 0x04, 0x3F, 0x6D, 0xCA, 0x0A, 0x1F, 0x1F}, - {512, 8000, 4096000, 0x60, 0x00, 0x01, 0x35, 0x8A, 0x1B, 0x1F, 0x7F}, - {512, 16000, 8192000, 0x20, 0x00, 0x30, 0x35, 0x8A, 0x1B, 0x1F, 0x3F}, - {512, 44100, 22579200, 0xE0, 0x00, 0x00, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F}, - {512, 48000, 24576000, 0xE0, 0x00, 0x00, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F}, + {512, 8000, 4096000, 0x60, 0x00, 0x01, 0x08, 0x19, 0x1B, 0x1F, 0x7F}, + {512, 16000, 8192000, 0x20, 0x00, 0x30, 0x35, 0x08, 0x19, 0x1F, 0x3F}, + {512, 44100, 22579200, 0xE0, 0x00, 0x00, 0x2D, 0x48, 0x08, 0x1F, 0x1F}, + {512, 48000, 24576000, 0xE0, 0x00, 0x00, 0x2D, 0x48, 0x08, 0x1F, 0x1F}, {768, 8000, 6144000, 0x60, 0x02, 0x11, 0x35, 0x8A, 0x1B, 0x1F, 0x7F}, {768, 16000, 12288000, 0x20, 0x02, 0x01, 0x35, 0x8A, 0x1B, 0x1F, 0x3F}, {768, 32000, 24576000, 0xE0, 0x02, 0x30, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F}, @@ -757,6 +757,7 @@ static void es8326_jack_detect_handler(struct work_struct *work) regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01); regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x0a); regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x03); + regmap_write(es8326->regmap, ES8326_INT_SOURCE, ES8326_INT_SRC_PIN9); /* * Inverted HPJACK_POL bit to trigger one IRQ to double check HP Removal event */ @@ -779,6 +780,8 @@ static void es8326_jack_detect_handler(struct work_struct *work) * set auto-check mode, then restart jack_detect_work after 400ms. * Don't report jack status. */ + regmap_write(es8326->regmap, ES8326_INT_SOURCE, + (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON)); regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01); es8326_enable_micbias(es8326->component); usleep_range(50000, 70000); @@ -901,7 +904,7 @@ static int es8326_resume(struct snd_soc_component *component) regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E); regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0); usleep_range(10000, 15000); - regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xe9); + regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xd9); regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0xcb); /* set headphone default type and detect pin */ regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x83); @@ -952,8 +955,7 @@ static int es8326_resume(struct snd_soc_component *component) es8326_enable_micbias(es8326->component); usleep_range(50000, 70000); regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00); - regmap_write(es8326->regmap, ES8326_INT_SOURCE, - (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON)); + regmap_write(es8326->regmap, ES8326_INT_SOURCE, ES8326_INT_SRC_PIN9); regmap_write(es8326->regmap, ES8326_INTOUT_IO, es8326->interrupt_clk); regmap_write(es8326->regmap, ES8326_SDINOUT1_IO, diff --git a/sound/soc/codecs/es8326.h b/sound/soc/codecs/es8326.h index 4234bbb900c45..dfef808673f4a 100644 --- a/sound/soc/codecs/es8326.h +++ b/sound/soc/codecs/es8326.h @@ -101,7 +101,7 @@ #define ES8326_MUTE (3 << 0) /* ES8326_CLK_CTL */ -#define ES8326_CLK_ON (0x7e << 0) +#define ES8326_CLK_ON (0x7f << 0) #define ES8326_CLK_OFF (0 << 0) /* ES8326_CLK_INV */ diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 20191a4473c2d..0384e237a548e 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -444,6 +444,7 @@ struct rt5645_priv { struct regmap *regmap; struct i2c_client *i2c; struct gpio_desc *gpiod_hp_det; + struct gpio_desc *gpiod_cbj_sleeve; struct snd_soc_jack *hp_jack; struct snd_soc_jack *mic_jack; struct snd_soc_jack *btn_jack; @@ -3186,6 +3187,9 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse regmap_update_bits(rt5645->regmap, RT5645_IN1_CTRL2, RT5645_CBJ_MN_JD, 0); + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 1); + msleep(600); regmap_read(rt5645->regmap, RT5645_IN1_CTRL3, &val); val &= 0x7; @@ -3202,6 +3206,8 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse snd_soc_dapm_disable_pin(dapm, "Mic Det Power"); snd_soc_dapm_sync(dapm); rt5645->jack_type = SND_JACK_HEADPHONE; + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } if (rt5645->pdata.level_trigger_irq) regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2, @@ -3229,6 +3235,9 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse if (rt5645->pdata.level_trigger_irq) regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2, RT5645_JD_1_1_MASK, RT5645_JD_1_1_INV); + + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } return rt5645->jack_type; @@ -4012,6 +4021,16 @@ static int rt5645_i2c_probe(struct i2c_client *i2c) return ret; } + rt5645->gpiod_cbj_sleeve = devm_gpiod_get_optional(&i2c->dev, "cbj-sleeve", + GPIOD_OUT_LOW); + + if (IS_ERR(rt5645->gpiod_cbj_sleeve)) { + ret = PTR_ERR(rt5645->gpiod_cbj_sleeve); + dev_info(&i2c->dev, "failed to initialize gpiod, ret=%d\n", ret); + if (ret != -ENOENT) + return ret; + } + for (i = 0; i < ARRAY_SIZE(rt5645->supplies); i++) rt5645->supplies[i].supply = rt5645_supply_names[i]; @@ -4259,6 +4278,9 @@ static void rt5645_i2c_remove(struct i2c_client *i2c) cancel_delayed_work_sync(&rt5645->jack_detect_work); cancel_delayed_work_sync(&rt5645->rcclock_work); + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); + regulator_bulk_disable(ARRAY_SIZE(rt5645->supplies), rt5645->supplies); } @@ -4274,6 +4296,9 @@ static void rt5645_i2c_shutdown(struct i2c_client *i2c) 0); msleep(20); regmap_write(rt5645->regmap, RT5645_RESET, 0); + + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } static int __maybe_unused rt5645_sys_suspend(struct device *dev) diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index e67c2e19cb1a7..1fdbef5fd6cba 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -763,12 +763,12 @@ static int __maybe_unused rt5682_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt5682->disable_irq_lock); if (rt5682->disable_irq == true) { - mutex_lock(&rt5682->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF); rt5682->disable_irq = false; - mutex_unlock(&rt5682->disable_irq_lock); } + mutex_unlock(&rt5682->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c index 935e597022d32..b8471b2d8f4f1 100644 --- a/sound/soc/codecs/rt711-sdca-sdw.c +++ b/sound/soc/codecs/rt711-sdca-sdw.c @@ -438,13 +438,13 @@ static int __maybe_unused rt711_sdca_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt711->disable_irq_lock); if (rt711->disable_irq == true) { - mutex_lock(&rt711->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8); rt711->disable_irq = false; - mutex_unlock(&rt711->disable_irq_lock); } + mutex_unlock(&rt711->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c index 3f5773310ae8c..988451f24a756 100644 --- a/sound/soc/codecs/rt711-sdw.c +++ b/sound/soc/codecs/rt711-sdw.c @@ -536,12 +536,12 @@ static int __maybe_unused rt711_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt711->disable_irq_lock); if (rt711->disable_irq == true) { - mutex_lock(&rt711->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF); rt711->disable_irq = false; - mutex_unlock(&rt711->disable_irq_lock); } + mutex_unlock(&rt711->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt712-sdca-sdw.c b/sound/soc/codecs/rt712-sdca-sdw.c index 6b644a89c5890..ba877432cea61 100644 --- a/sound/soc/codecs/rt712-sdca-sdw.c +++ b/sound/soc/codecs/rt712-sdca-sdw.c @@ -438,13 +438,14 @@ static int __maybe_unused rt712_sdca_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt712->disable_irq_lock); if (rt712->disable_irq == true) { - mutex_lock(&rt712->disable_irq_lock); + sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8); rt712->disable_irq = false; - mutex_unlock(&rt712->disable_irq_lock); } + mutex_unlock(&rt712->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt715-sdca.c b/sound/soc/codecs/rt715-sdca.c index 4533eedd7e189..27d17e3cc8027 100644 --- a/sound/soc/codecs/rt715-sdca.c +++ b/sound/soc/codecs/rt715-sdca.c @@ -316,7 +316,7 @@ static int rt715_sdca_set_amp_gain_8ch_get(struct snd_kcontrol *kcontrol, return 0; } -static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -17625, 375, 0); +static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -1725, 75, 0); static const DECLARE_TLV_DB_SCALE(mic_vol_tlv, 0, 1000, 0); static int rt715_sdca_get_volsw(struct snd_kcontrol *kcontrol, @@ -477,7 +477,7 @@ static const struct snd_kcontrol_new rt715_sdca_snd_controls[] = { RT715_SDCA_FU_VOL_CTRL, CH_01), SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_ADC7_27_VOL, RT715_SDCA_FU_VOL_CTRL, CH_02), - 0x2f, 0x7f, 0, + 0x2f, 0x3f, 0, rt715_sdca_set_amp_gain_get, rt715_sdca_set_amp_gain_put, in_vol_tlv), RT715_SDCA_EXT_TLV("FU02 Capture Volume", @@ -485,13 +485,13 @@ static const struct snd_kcontrol_new rt715_sdca_snd_controls[] = { RT715_SDCA_FU_VOL_CTRL, CH_01), rt715_sdca_set_amp_gain_4ch_get, rt715_sdca_set_amp_gain_4ch_put, - in_vol_tlv, 4, 0x7f), + in_vol_tlv, 4, 0x3f), RT715_SDCA_EXT_TLV("FU06 Capture Volume", SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_ADC10_11_VOL, RT715_SDCA_FU_VOL_CTRL, CH_01), rt715_sdca_set_amp_gain_4ch_get, rt715_sdca_set_amp_gain_4ch_put, - in_vol_tlv, 4, 0x7f), + in_vol_tlv, 4, 0x3f), /* MIC Boost Control */ RT715_SDCA_BOOST_EXT_TLV("FU0E Boost", SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_DMIC_GAIN_EN, diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c index 21f37babd148a..376585f5a8dd8 100644 --- a/sound/soc/codecs/rt715-sdw.c +++ b/sound/soc/codecs/rt715-sdw.c @@ -111,6 +111,7 @@ static bool rt715_readable_register(struct device *dev, unsigned int reg) case 0x839d: case 0x83a7: case 0x83a9: + case 0x752001: case 0x752039: return true; default: diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c index e24b9cbdc10c9..e33836fffd5f2 100644 --- a/sound/soc/codecs/rt722-sdca-sdw.c +++ b/sound/soc/codecs/rt722-sdca-sdw.c @@ -467,13 +467,13 @@ static int __maybe_unused rt722_sdca_dev_resume(struct device *dev) return 0; if (!slave->unattach_request) { + mutex_lock(&rt722->disable_irq_lock); if (rt722->disable_irq == true) { - mutex_lock(&rt722->disable_irq_lock); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_6); sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8); rt722->disable_irq = false; - mutex_unlock(&rt722->disable_irq_lock); } + mutex_unlock(&rt722->disable_irq_lock); goto regmap_sync; } diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c index 0e1c65a20392a..9ff607984ea19 100644 --- a/sound/soc/codecs/rt722-sdca.c +++ b/sound/soc/codecs/rt722-sdca.c @@ -1329,7 +1329,7 @@ static struct snd_soc_dai_driver rt722_sdca_dai[] = { .capture = { .stream_name = "DP6 DMic Capture", .channels_min = 1, - .channels_max = 2, + .channels_max = 4, .rates = RT722_STEREO_RATES, .formats = RT722_FORMATS, }, @@ -1438,9 +1438,12 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) int loop_check, chk_cnt = 100, ret; unsigned int calib_status = 0; - /* Read eFuse */ - rt722_sdca_index_write(rt722, RT722_VENDOR_SPK_EFUSE, RT722_DC_CALIB_CTRL, - 0x4808); + /* Config analog bias */ + rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_ANALOG_BIAS_CTL3, + 0xa081); + /* GE related settings */ + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_GE_RELATED_CTL2, + 0xa009); /* Button A, B, C, D bypass mode */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_UMP_HID_CTL4, 0xcf00); @@ -1474,9 +1477,6 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) if ((calib_status & 0x0040) == 0x0) break; } - /* Release HP-JD, EN_CBJ_TIE_GL/R open, en_osw gating auto done bit */ - rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4, - 0x0010); /* Set ADC09 power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ADC0A_08_PDE_FLOAT_CTL, 0x2a12); @@ -1489,8 +1489,21 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) /* Set DAC03 and HP power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_DAC03_HP_PDE_FLOAT_CTL, 0x4040); + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ENT_FLOAT_CTRL_1, + 0x4141); + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_FLOAT_CTRL_1, + 0x0101); /* Fine tune PDE40 latency */ regmap_write(rt722->regmap, 0x2f58, 0x07); + regmap_write(rt722->regmap, 0x2f03, 0x06); + /* MIC VRefo */ + rt722_sdca_index_update_bits(rt722, RT722_VENDOR_REG, + RT722_COMBO_JACK_AUTO_CTL1, 0x0200, 0x0200); + rt722_sdca_index_update_bits(rt722, RT722_VENDOR_REG, + RT722_VREFO_GAT, 0x4000, 0x4000); + /* Release HP-JD, EN_CBJ_TIE_GL/R open, en_osw gating auto done bit */ + rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4, + 0x0010); } int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave) diff --git a/sound/soc/codecs/rt722-sdca.h b/sound/soc/codecs/rt722-sdca.h index 44af8901352eb..2464361a7958c 100644 --- a/sound/soc/codecs/rt722-sdca.h +++ b/sound/soc/codecs/rt722-sdca.h @@ -69,6 +69,7 @@ struct rt722_sdca_dmic_kctrl_priv { #define RT722_COMBO_JACK_AUTO_CTL2 0x46 #define RT722_COMBO_JACK_AUTO_CTL3 0x47 #define RT722_DIGITAL_MISC_CTRL4 0x4a +#define RT722_VREFO_GAT 0x63 #define RT722_FSM_CTL 0x67 #define RT722_SDCA_INTR_REC 0x82 #define RT722_SW_CONFIG1 0x8a @@ -127,6 +128,8 @@ struct rt722_sdca_dmic_kctrl_priv { #define RT722_UMP_HID_CTL6 0x66 #define RT722_UMP_HID_CTL7 0x67 #define RT722_UMP_HID_CTL8 0x68 +#define RT722_FLOAT_CTRL_1 0x70 +#define RT722_ENT_FLOAT_CTRL_1 0x76 /* Parameter & Verb control 01 (0x1a)(NID:20h) */ #define RT722_HIDDEN_REG_SW_RESET (0x1 << 14) diff --git a/sound/soc/codecs/tas2552.c b/sound/soc/codecs/tas2552.c index 8c9dc318b0e82..c65a4219ecd6c 100644 --- a/sound/soc/codecs/tas2552.c +++ b/sound/soc/codecs/tas2552.c @@ -2,7 +2,8 @@ /* * tas2552.c - ALSA SoC Texas Instruments TAS2552 Mono Audio Amplifier * - * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com + * Copyright (C) 2014 - 2024 Texas Instruments Incorporated - + * https://www.ti.com * * Author: Dan Murphy */ @@ -119,12 +120,14 @@ static const struct snd_soc_dapm_widget tas2552_dapm_widgets[] = &tas2552_input_mux_control), SND_SOC_DAPM_AIF_IN("DAC IN", "DAC Playback", 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("ASI OUT", "DAC Capture", 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_DAC("DAC", NULL, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_OUT_DRV("ClassD", TAS2552_CFG_2, 7, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("PLL", TAS2552_CFG_2, 3, 0, NULL, 0), SND_SOC_DAPM_POST("Post Event", tas2552_post_event), - SND_SOC_DAPM_OUTPUT("OUT") + SND_SOC_DAPM_OUTPUT("OUT"), + SND_SOC_DAPM_INPUT("DMIC") }; static const struct snd_soc_dapm_route tas2552_audio_map[] = { @@ -134,6 +137,7 @@ static const struct snd_soc_dapm_route tas2552_audio_map[] = { {"ClassD", NULL, "Input selection"}, {"OUT", NULL, "ClassD"}, {"ClassD", NULL, "PLL"}, + {"ASI OUT", NULL, "DMIC"} }; #ifdef CONFIG_PM @@ -538,6 +542,13 @@ static struct snd_soc_dai_driver tas2552_dai[] = { .rates = SNDRV_PCM_RATE_8000_192000, .formats = TAS2552_FORMATS, }, + .capture = { + .stream_name = "Capture", + .channels_min = 2, + .channels_max = 2, + .rates = SNDRV_PCM_RATE_8000_192000, + .formats = TAS2552_FORMATS, + }, .ops = &tas2552_speaker_dai_ops, }, }; diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c index 85e14ff61769a..43a3cc5eeb974 100644 --- a/sound/soc/codecs/tas2781-fmwlib.c +++ b/sound/soc/codecs/tas2781-fmwlib.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // -// tasdevice-fmw.c -- TASDEVICE firmware support +// tas2781-fmwlib.c -- TASDEVICE firmware support // -// Copyright 2023 Texas Instruments, Inc. +// Copyright 2023 - 2024 Texas Instruments, Inc. // // Author: Shenghao Ding @@ -1878,7 +1878,7 @@ int tas2781_load_calibration(void *context, char *file_name, { struct tasdevice_priv *tas_priv = (struct tasdevice_priv *)context; struct tasdevice *tasdev = &(tas_priv->tasdevice[i]); - const struct firmware *fw_entry; + const struct firmware *fw_entry = NULL; struct tasdevice_fw *tas_fmw; struct firmware fmw; int offset = 0; @@ -2151,6 +2151,24 @@ static int tasdevice_load_data(struct tasdevice_priv *tas_priv, return ret; } +static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i) +{ + struct tasdevice_calibration *cal; + struct tasdevice_fw *cal_fmw; + + cal_fmw = priv->tasdevice[i].cali_data_fmw; + + /* No calibrated data for current devices, playback will go ahead. */ + if (!cal_fmw) + return; + + cal = cal_fmw->calibrations; + if (cal) + return; + + load_calib_data(priv, &cal->dev_data); +} + int tasdevice_select_tuningprm_cfg(void *context, int prm_no, int cfg_no, int rca_conf_no) { @@ -2210,21 +2228,9 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, for (i = 0; i < tas_priv->ndev; i++) { if (tas_priv->tasdevice[i].is_loaderr == true) continue; - else if (tas_priv->tasdevice[i].is_loaderr == false - && tas_priv->tasdevice[i].is_loading == true) { - struct tasdevice_fw *cal_fmw = - tas_priv->tasdevice[i].cali_data_fmw; - - if (cal_fmw) { - struct tasdevice_calibration - *cal = cal_fmw->calibrations; - - if (cal) - load_calib_data(tas_priv, - &(cal->dev_data)); - } + if (tas_priv->tasdevice[i].is_loaderr == false && + tas_priv->tasdevice[i].is_loading == true) tas_priv->tasdevice[i].cur_prog = prm_no; - } } } @@ -2245,11 +2251,15 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, tasdevice_load_data(tas_priv, &(conf->dev_data)); for (i = 0; i < tas_priv->ndev; i++) { if (tas_priv->tasdevice[i].is_loaderr == true) { - status |= 1 << (i + 4); + status |= BIT(i + 4); continue; - } else if (tas_priv->tasdevice[i].is_loaderr == false - && tas_priv->tasdevice[i].is_loading == true) + } + + if (tas_priv->tasdevice[i].is_loaderr == false && + tas_priv->tasdevice[i].is_loading == true) { + tasdev_load_calibrated_data(tas_priv, i); tas_priv->tasdevice[i].cur_conf = cfg_no; + } } } else dev_dbg(tas_priv->dev, "%s: Unneeded loading dsp conf %d\n", @@ -2308,65 +2318,6 @@ int tasdevice_prmg_load(void *context, int prm_no) } EXPORT_SYMBOL_NS_GPL(tasdevice_prmg_load, SND_SOC_TAS2781_FMWLIB); -int tasdevice_prmg_calibdata_load(void *context, int prm_no) -{ - struct tasdevice_priv *tas_priv = (struct tasdevice_priv *) context; - struct tasdevice_fw *tas_fmw = tas_priv->fmw; - struct tasdevice_prog *program; - int prog_status = 0; - int i; - - if (!tas_fmw) { - dev_err(tas_priv->dev, "%s: Firmware is NULL\n", __func__); - goto out; - } - - if (prm_no >= tas_fmw->nr_programs) { - dev_err(tas_priv->dev, - "%s: prm(%d) is not in range of Programs %u\n", - __func__, prm_no, tas_fmw->nr_programs); - goto out; - } - - for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) { - if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) { - tas_priv->tasdevice[i].cur_conf = -1; - tas_priv->tasdevice[i].is_loading = true; - prog_status++; - } - tas_priv->tasdevice[i].is_loaderr = false; - } - - if (prog_status) { - program = &(tas_fmw->programs[prm_no]); - tasdevice_load_data(tas_priv, &(program->dev_data)); - for (i = 0; i < tas_priv->ndev; i++) { - if (tas_priv->tasdevice[i].is_loaderr == true) - continue; - else if (tas_priv->tasdevice[i].is_loaderr == false - && tas_priv->tasdevice[i].is_loading == true) { - struct tasdevice_fw *cal_fmw = - tas_priv->tasdevice[i].cali_data_fmw; - - if (cal_fmw) { - struct tasdevice_calibration *cal = - cal_fmw->calibrations; - - if (cal) - load_calib_data(tas_priv, - &(cal->dev_data)); - } - tas_priv->tasdevice[i].cur_prog = prm_no; - } - } - } - -out: - return prog_status; -} -EXPORT_SYMBOL_NS_GPL(tasdevice_prmg_calibdata_load, - SND_SOC_TAS2781_FMWLIB); - void tasdevice_tuning_switch(void *context, int state) { struct tasdevice_priv *tas_priv = (struct tasdevice_priv *) context; diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index b5abff230e437..9350972dfefe7 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -2,7 +2,7 @@ // // ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier // -// Copyright (C) 2022 - 2023 Texas Instruments Incorporated +// Copyright (C) 2022 - 2024 Texas Instruments Incorporated // https://www.ti.com // // The TAS2563/TAS2781 driver implements a flexible and configurable @@ -414,7 +414,7 @@ static void tasdevice_fw_ready(const struct firmware *fmw, __func__, tas_priv->cal_binaryname[i]); } - tasdevice_prmg_calibdata_load(tas_priv, 0); + tasdevice_prmg_load(tas_priv, 0); tas_priv->cur_prog = 0; out: if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) { diff --git a/sound/soc/codecs/tlv320adc3xxx.c b/sound/soc/codecs/tlv320adc3xxx.c index 420bbf588efea..e100cc9f5c192 100644 --- a/sound/soc/codecs/tlv320adc3xxx.c +++ b/sound/soc/codecs/tlv320adc3xxx.c @@ -1429,7 +1429,7 @@ static int adc3xxx_i2c_probe(struct i2c_client *i2c) return ret; } -static void __exit adc3xxx_i2c_remove(struct i2c_client *client) +static void adc3xxx_i2c_remove(struct i2c_client *client) { struct adc3xxx *adc3xxx = i2c_get_clientdata(client); @@ -1452,7 +1452,7 @@ static struct i2c_driver adc3xxx_i2c_driver = { .of_match_table = tlv320adc3xxx_of_match, }, .probe = adc3xxx_i2c_probe, - .remove = __exit_p(adc3xxx_i2c_remove), + .remove = adc3xxx_i2c_remove, .id_table = adc3xxx_i2c_id, }; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 36ea0dcdc7ab0..9cb9068c0462a 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -683,11 +683,12 @@ static void wm_adsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl) int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type, unsigned int alg, void *buf, size_t len) { - struct cs_dsp_coeff_ctl *cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg); + struct cs_dsp_coeff_ctl *cs_ctl; struct wm_coeff_ctl *ctl; int ret; mutex_lock(&dsp->cs_dsp.pwr_lock); + cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg); ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len); mutex_unlock(&dsp->cs_dsp.pwr_lock); diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 3c025dabaf7a4..1253695bebd86 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -1155,6 +1155,7 @@ static int wsa881x_probe(struct sdw_slave *pdev, pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS, 0); pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop; pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY; + pdev->prop.clk_stop_mode1 = true; gpiod_direction_output(wsa881x->sd_n, !wsa881x->sd_n_val); wsa881x->regmap = devm_regmap_init_sdw(pdev, &wsa881x_regmap_config); diff --git a/sound/soc/intel/avs/board_selection.c b/sound/soc/intel/avs/board_selection.c index 8e91eece992db..8360ce557401c 100644 --- a/sound/soc/intel/avs/board_selection.c +++ b/sound/soc/intel/avs/board_selection.c @@ -236,6 +236,82 @@ static struct snd_soc_acpi_mach avs_gml_i2s_machines[] = { {}, }; +static struct snd_soc_acpi_mach avs_cnl_i2s_machines[] = { + { + .id = "INT34C2", + .drv_name = "avs_rt274", + .mach_params = { + .i2s_link_mask = AVS_SSP(0), + }, + .tplg_filename = "rt274-tplg.bin", + }, + { + .id = "10EC5682", + .drv_name = "avs_rt5682", + .mach_params = { + .i2s_link_mask = AVS_SSP(1), + }, + .tplg_filename = "rt5682-tplg.bin", + }, + {}, +}; + +static struct snd_soc_acpi_mach avs_icl_i2s_machines[] = { + { + .id = "INT343A", + .drv_name = "avs_rt298", + .mach_params = { + .i2s_link_mask = AVS_SSP(0), + }, + .tplg_filename = "rt298-tplg.bin", + }, + { + .id = "INT34C2", + .drv_name = "avs_rt274", + .mach_params = { + .i2s_link_mask = AVS_SSP(0), + }, + .tplg_filename = "rt274-tplg.bin", + }, + {}, +}; + +static struct snd_soc_acpi_mach avs_tgl_i2s_machines[] = { + { + .id = "INT34C2", + .drv_name = "avs_rt274", + .mach_params = { + .i2s_link_mask = AVS_SSP(0), + }, + .tplg_filename = "rt274-tplg.bin", + }, + { + .id = "10EC0298", + .drv_name = "avs_rt298", + .mach_params = { + .i2s_link_mask = AVS_SSP(0), + }, + .tplg_filename = "rt298-tplg.bin", + }, + { + .id = "10EC1308", + .drv_name = "avs_rt1308", + .mach_params = { + .i2s_link_mask = AVS_SSP(1), + }, + .tplg_filename = "rt1308-tplg.bin", + }, + { + .id = "ESSX8336", + .drv_name = "avs_es8336", + .mach_params = { + .i2s_link_mask = AVS_SSP(0), + }, + .tplg_filename = "es8336-tplg.bin", + }, + {}, +}; + static struct snd_soc_acpi_mach avs_test_i2s_machines[] = { { .drv_name = "avs_i2s_test", @@ -296,6 +372,15 @@ static const struct avs_acpi_boards i2s_boards[] = { AVS_MACH_ENTRY(HDA_KBL_LP, avs_kbl_i2s_machines), AVS_MACH_ENTRY(HDA_APL, avs_apl_i2s_machines), AVS_MACH_ENTRY(HDA_GML, avs_gml_i2s_machines), + AVS_MACH_ENTRY(HDA_CNL_LP, avs_cnl_i2s_machines), + AVS_MACH_ENTRY(HDA_CNL_H, avs_cnl_i2s_machines), + AVS_MACH_ENTRY(HDA_CML_LP, avs_cnl_i2s_machines), + AVS_MACH_ENTRY(HDA_ICL_LP, avs_icl_i2s_machines), + AVS_MACH_ENTRY(HDA_TGL_LP, avs_tgl_i2s_machines), + AVS_MACH_ENTRY(HDA_EHL_0, avs_tgl_i2s_machines), + AVS_MACH_ENTRY(HDA_ADL_P, avs_tgl_i2s_machines), + AVS_MACH_ENTRY(HDA_RPL_P_0, avs_tgl_i2s_machines), + AVS_MACH_ENTRY(HDA_RPL_M, avs_tgl_i2s_machines), {}, }; diff --git a/sound/soc/intel/avs/boards/ssm4567.c b/sound/soc/intel/avs/boards/ssm4567.c index 4a0e136835ff5..b64be685dc23b 100644 --- a/sound/soc/intel/avs/boards/ssm4567.c +++ b/sound/soc/intel/avs/boards/ssm4567.c @@ -172,7 +172,6 @@ static int avs_ssm4567_probe(struct platform_device *pdev) card->dapm_routes = card_base_routes; card->num_dapm_routes = ARRAY_SIZE(card_base_routes); card->fully_routed = true; - card->disable_route_checks = true; ret = snd_soc_fixup_dai_links_platform_name(card, pname); if (ret) diff --git a/sound/soc/intel/avs/cldma.c b/sound/soc/intel/avs/cldma.c index d7a9390b5e483..585579840b646 100644 --- a/sound/soc/intel/avs/cldma.c +++ b/sound/soc/intel/avs/cldma.c @@ -35,7 +35,7 @@ struct hda_cldma { unsigned int buffer_size; unsigned int num_periods; - unsigned int stream_tag; + unsigned char stream_tag; void __iomem *sd_addr; struct snd_dma_buffer dmab_data; diff --git a/sound/soc/intel/avs/path.c b/sound/soc/intel/avs/path.c index 3aa16ee8d34c1..2fae84727a3bd 100644 --- a/sound/soc/intel/avs/path.c +++ b/sound/soc/intel/avs/path.c @@ -367,6 +367,7 @@ static int avs_asrc_create(struct avs_dev *adev, struct avs_path_module *mod) struct avs_tplg_module *t = mod->template; struct avs_asrc_cfg cfg; + memset(&cfg, 0, sizeof(cfg)); cfg.base.cpc = t->cfg_base->cpc; cfg.base.ibs = t->cfg_base->ibs; cfg.base.obs = t->cfg_base->obs; diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c index 4dfc5a1ebb7c2..f25a293c0915d 100644 --- a/sound/soc/intel/avs/pcm.c +++ b/sound/soc/intel/avs/pcm.c @@ -356,6 +356,7 @@ static int avs_dai_hda_be_prepare(struct snd_pcm_substream *substream, struct sn stream_info->sig_bits); format_val = snd_hdac_stream_format(runtime->channels, bits, runtime->rate); + snd_hdac_ext_stream_decouple(bus, link_stream, true); snd_hdac_ext_stream_reset(link_stream); snd_hdac_ext_stream_setup(link_stream, format_val); @@ -611,6 +612,7 @@ static int avs_dai_fe_prepare(struct snd_pcm_substream *substream, struct snd_so struct avs_dev *adev = to_avs_dev(dai->dev); struct hdac_ext_stream *host_stream; unsigned int format_val; + struct hdac_bus *bus; unsigned int bits; int ret; @@ -620,6 +622,8 @@ static int avs_dai_fe_prepare(struct snd_pcm_substream *substream, struct snd_so if (hdac_stream(host_stream)->prepared) return 0; + bus = hdac_stream(host_stream)->bus; + snd_hdac_ext_stream_decouple(bus, data->host_stream, true); snd_hdac_stream_reset(hdac_stream(host_stream)); stream_info = snd_soc_dai_get_pcm_stream(dai, substream->stream); diff --git a/sound/soc/intel/avs/probes.c b/sound/soc/intel/avs/probes.c index 817e543036f29..7e781a3156909 100644 --- a/sound/soc/intel/avs/probes.c +++ b/sound/soc/intel/avs/probes.c @@ -19,8 +19,11 @@ static int avs_dsp_init_probe(struct avs_dev *adev, union avs_connector_node_id struct avs_probe_cfg cfg = {{0}}; struct avs_module_entry mentry; u8 dummy; + int ret; - avs_get_module_entry(adev, &AVS_PROBE_MOD_UUID, &mentry); + ret = avs_get_module_entry(adev, &AVS_PROBE_MOD_UUID, &mentry); + if (ret) + return ret; /* * Probe module uses no cycles, audio data format and input and output @@ -39,11 +42,12 @@ static int avs_dsp_init_probe(struct avs_dev *adev, union avs_connector_node_id static void avs_dsp_delete_probe(struct avs_dev *adev) { struct avs_module_entry mentry; + int ret; - avs_get_module_entry(adev, &AVS_PROBE_MOD_UUID, &mentry); - - /* There is only ever one probe module instance. */ - avs_dsp_delete_module(adev, mentry.module_id, 0, INVALID_PIPELINE_ID, 0); + ret = avs_get_module_entry(adev, &AVS_PROBE_MOD_UUID, &mentry); + if (!ret) + /* There is only ever one probe module instance. */ + avs_dsp_delete_module(adev, mentry.module_id, 0, INVALID_PIPELINE_ID, 0); } static inline struct hdac_ext_stream *avs_compr_get_host_stream(struct snd_compr_stream *cstream) diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c index 48b3c67c91032..d8223e2b4cfe2 100644 --- a/sound/soc/intel/avs/topology.c +++ b/sound/soc/intel/avs/topology.c @@ -1458,6 +1458,8 @@ static int avs_widget_load(struct snd_soc_component *comp, int index, if (!le32_to_cpu(dw->priv.size)) return 0; + w->no_wname_in_kcontrol_name = true; + if (w->ignore_suspend && !AVS_S0IX_SUPPORTED) { dev_info_once(comp->dev, "Device does not support S0IX, check BIOS settings\n"); w->ignore_suspend = false; diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c index 540f7a29310a9..3fe3f38c6cb69 100644 --- a/sound/soc/intel/boards/bxt_da7219_max98357a.c +++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c @@ -768,6 +768,7 @@ static struct snd_soc_card broxton_audio_card = { .dapm_routes = audio_map, .num_dapm_routes = ARRAY_SIZE(audio_map), .fully_routed = true, + .disable_route_checks = true, .late_probe = bxt_card_late_probe, }; diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c index c0eb65c14aa97..afc499be8db26 100644 --- a/sound/soc/intel/boards/bxt_rt298.c +++ b/sound/soc/intel/boards/bxt_rt298.c @@ -574,6 +574,7 @@ static struct snd_soc_card broxton_rt298 = { .dapm_routes = broxton_rt298_map, .num_dapm_routes = ARRAY_SIZE(broxton_rt298_map), .fully_routed = true, + .disable_route_checks = true, .late_probe = bxt_card_late_probe, }; diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 05f38d1f7d824..b41a1147f1c34 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -636,28 +636,30 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_USE_AMCR0F28), }, { + /* Asus T100TAF, unlike other T100TA* models this one has a mono speaker */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), }, .driver_data = (void *)(BYT_RT5640_IN1_MAP | BYT_RT5640_JD_SRC_JD2_IN4N | BYT_RT5640_OVCD_TH_2000UA | BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, { + /* Asus T100TA and T100TAM, must come after T100TAF (mono spk) match */ .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T100TA"), }, .driver_data = (void *)(BYT_RT5640_IN1_MAP | BYT_RT5640_JD_SRC_JD2_IN4N | BYT_RT5640_OVCD_TH_2000UA | BYT_RT5640_OVCD_SF_0P75 | - BYT_RT5640_MONO_SPEAKER | - BYT_RT5640_DIFF_MIC | - BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, { diff --git a/sound/soc/intel/boards/glk_rt5682_max98357a.c b/sound/soc/intel/boards/glk_rt5682_max98357a.c index 657e4658234ce..4098b2d32f9bc 100644 --- a/sound/soc/intel/boards/glk_rt5682_max98357a.c +++ b/sound/soc/intel/boards/glk_rt5682_max98357a.c @@ -649,6 +649,8 @@ static int geminilake_audio_probe(struct platform_device *pdev) card = &glk_audio_card_rt5682_m98357a; card->dev = &pdev->dev; snd_soc_card_set_drvdata(card, ctx); + if (!snd_soc_acpi_sof_parent(&pdev->dev)) + card->disable_route_checks = true; /* override platform name, if required */ mach = pdev->dev.platform_data; diff --git a/sound/soc/intel/boards/kbl_da7219_max98357a.c b/sound/soc/intel/boards/kbl_da7219_max98357a.c index a5d8965303a88..9dbc15f9d1c9b 100644 --- a/sound/soc/intel/boards/kbl_da7219_max98357a.c +++ b/sound/soc/intel/boards/kbl_da7219_max98357a.c @@ -639,6 +639,7 @@ static struct snd_soc_card kabylake_audio_card_da7219_m98357a = { .dapm_routes = kabylake_map, .num_dapm_routes = ARRAY_SIZE(kabylake_map), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; diff --git a/sound/soc/intel/boards/kbl_da7219_max98927.c b/sound/soc/intel/boards/kbl_da7219_max98927.c index 98c11ec0adc01..e662da5af83b5 100644 --- a/sound/soc/intel/boards/kbl_da7219_max98927.c +++ b/sound/soc/intel/boards/kbl_da7219_max98927.c @@ -1036,6 +1036,7 @@ static struct snd_soc_card kbl_audio_card_da7219_m98927 = { .codec_conf = max98927_codec_conf, .num_configs = ARRAY_SIZE(max98927_codec_conf), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; @@ -1054,6 +1055,7 @@ static struct snd_soc_card kbl_audio_card_max98927 = { .codec_conf = max98927_codec_conf, .num_configs = ARRAY_SIZE(max98927_codec_conf), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; @@ -1071,6 +1073,7 @@ static struct snd_soc_card kbl_audio_card_da7219_m98373 = { .codec_conf = max98373_codec_conf, .num_configs = ARRAY_SIZE(max98373_codec_conf), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; @@ -1088,6 +1091,7 @@ static struct snd_soc_card kbl_audio_card_max98373 = { .codec_conf = max98373_codec_conf, .num_configs = ARRAY_SIZE(max98373_codec_conf), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; diff --git a/sound/soc/intel/boards/kbl_rt5660.c b/sound/soc/intel/boards/kbl_rt5660.c index 30e0aca161cd5..894d127c482a3 100644 --- a/sound/soc/intel/boards/kbl_rt5660.c +++ b/sound/soc/intel/boards/kbl_rt5660.c @@ -518,6 +518,7 @@ static struct snd_soc_card kabylake_audio_card_rt5660 = { .dapm_routes = kabylake_rt5660_map, .num_dapm_routes = ARRAY_SIZE(kabylake_rt5660_map), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c index 9071b1f1cbd00..646e8ff8e9619 100644 --- a/sound/soc/intel/boards/kbl_rt5663_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c @@ -966,6 +966,7 @@ static struct snd_soc_card kabylake_audio_card_rt5663_m98927 = { .codec_conf = max98927_codec_conf, .num_configs = ARRAY_SIZE(max98927_codec_conf), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; @@ -982,6 +983,7 @@ static struct snd_soc_card kabylake_audio_card_rt5663 = { .dapm_routes = kabylake_5663_map, .num_dapm_routes = ARRAY_SIZE(kabylake_5663_map), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c index 178fe9c37df62..924d5d1de03ac 100644 --- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c @@ -791,6 +791,7 @@ static struct snd_soc_card kabylake_audio_card = { .codec_conf = max98927_codec_conf, .num_configs = ARRAY_SIZE(max98927_codec_conf), .fully_routed = true, + .disable_route_checks = true, .late_probe = kabylake_card_late_probe, }; diff --git a/sound/soc/intel/boards/skl_hda_dsp_generic.c b/sound/soc/intel/boards/skl_hda_dsp_generic.c index 6e172719c9795..4aa7fd2a05e46 100644 --- a/sound/soc/intel/boards/skl_hda_dsp_generic.c +++ b/sound/soc/intel/boards/skl_hda_dsp_generic.c @@ -227,6 +227,8 @@ static int skl_hda_audio_probe(struct platform_device *pdev) ctx->common_hdmi_codec_drv = mach->mach_params.common_hdmi_codec_drv; hda_soc_card.dev = &pdev->dev; + if (!snd_soc_acpi_sof_parent(&pdev->dev)) + hda_soc_card.disable_route_checks = true; if (mach->mach_params.dmic_num > 0) { snprintf(hda_soc_components, sizeof(hda_soc_components), diff --git a/sound/soc/intel/boards/skl_nau88l25_max98357a.c b/sound/soc/intel/boards/skl_nau88l25_max98357a.c index 0e7025834594a..e4630c33176e2 100644 --- a/sound/soc/intel/boards/skl_nau88l25_max98357a.c +++ b/sound/soc/intel/boards/skl_nau88l25_max98357a.c @@ -654,6 +654,7 @@ static struct snd_soc_card skylake_audio_card = { .dapm_routes = skylake_map, .num_dapm_routes = ARRAY_SIZE(skylake_map), .fully_routed = true, + .disable_route_checks = true, .late_probe = skylake_card_late_probe, }; diff --git a/sound/soc/intel/boards/skl_rt286.c b/sound/soc/intel/boards/skl_rt286.c index c59c60e280916..9a80442749081 100644 --- a/sound/soc/intel/boards/skl_rt286.c +++ b/sound/soc/intel/boards/skl_rt286.c @@ -523,6 +523,7 @@ static struct snd_soc_card skylake_rt286 = { .dapm_routes = skylake_rt286_map, .num_dapm_routes = ARRAY_SIZE(skylake_rt286_map), .fully_routed = true, + .disable_route_checks = true, .late_probe = skylake_card_late_probe, }; diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index cd50f26d1edbe..02705034e5713 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -154,46 +154,6 @@ static const struct dmi_system_id sof_rt5682_quirk_table[] = { SOF_RT5682_SSP_AMP(2) | SOF_RT5682_NUM_HDMIDEV(4)), }, - { - .callback = sof_rt5682_quirk_cb, - .matches = { - DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Rex"), - DMI_MATCH(DMI_OEM_STRING, "AUDIO-MAX98360_ALC5682I_I2S"), - }, - .driver_data = (void *)(SOF_RT5682_MCLK_EN | - SOF_RT5682_SSP_CODEC(2) | - SOF_RT5682_SSP_AMP(0) | - SOF_RT5682_NUM_HDMIDEV(3) | - SOF_BT_OFFLOAD_SSP(1) | - SOF_SSP_BT_OFFLOAD_PRESENT - ), - }, - { - .callback = sof_rt5682_quirk_cb, - .matches = { - DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Rex"), - DMI_MATCH(DMI_OEM_STRING, "AUDIO-MAX98360_ALC5682I_DISCRETE_I2S_BT"), - }, - .driver_data = (void *)(SOF_RT5682_MCLK_EN | - SOF_RT5682_SSP_CODEC(2) | - SOF_RT5682_SSP_AMP(0) | - SOF_RT5682_NUM_HDMIDEV(3) | - SOF_BT_OFFLOAD_SSP(1) | - SOF_SSP_BT_OFFLOAD_PRESENT - ), - }, - { - .callback = sof_rt5682_quirk_cb, - .matches = { - DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Rex"), - DMI_MATCH(DMI_OEM_STRING, "AUDIO-ALC1019_ALC5682I_I2S"), - }, - .driver_data = (void *)(SOF_RT5682_MCLK_EN | - SOF_RT5682_SSP_CODEC(2) | - SOF_RT5682_SSP_AMP(0) | - SOF_RT5682_NUM_HDMIDEV(3) - ), - }, { .callback = sof_rt5682_quirk_cb, .matches = { diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 300391fbc2fc2..9545e49d016dc 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -236,6 +236,17 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { SOF_SDW_PCH_DMIC | RT711_JD2_100K), }, + { + /* NUC15 LAPRC710 skews */ + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "LAPRC710"), + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + SOF_SDW_PCH_DMIC | + RT711_JD2_100K), + }, /* TigerLake-SDCA devices */ { .callback = sof_sdw_quirk_cb, @@ -418,6 +429,15 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { RT711_JD2 | SOF_SDW_FOUR_SPK), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), + DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0C0F") + }, + .driver_data = (void *)(SOF_SDW_TGL_HDMI | + RT711_JD2), + }, { .callback = sof_sdw_quirk_cb, .matches = { @@ -484,6 +504,15 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { SOF_BT_OFFLOAD_SSP(1) | SOF_SSP_BT_OFFLOAD_PRESENT), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "OMEN Transcend Gaming Laptop"), + }, + .driver_data = (void *)(RT711_JD2), + }, + /* LunarLake devices */ { .callback = sof_sdw_quirk_cb, diff --git a/sound/soc/intel/boards/sof_ssp_common.h b/sound/soc/intel/boards/sof_ssp_common.h index 6d827103479b5..d24888bc99fde 100644 --- a/sound/soc/intel/boards/sof_ssp_common.h +++ b/sound/soc/intel/boards/sof_ssp_common.h @@ -67,6 +67,14 @@ enum sof_ssp_codec { enum sof_ssp_codec sof_ssp_detect_codec_type(struct device *dev); enum sof_ssp_codec sof_ssp_detect_amp_type(struct device *dev); + +#if IS_ENABLED(CONFIG_SND_SOC_INTEL_SOF_SSP_COMMON) const char *sof_ssp_get_codec_name(enum sof_ssp_codec codec_type); +#else +static inline const char *sof_ssp_get_codec_name(enum sof_ssp_codec codec_type) +{ + return NULL; +} +#endif #endif /* __SOF_SSP_COMMON_H */ diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c index dd2f806526c10..ef00792e1d49a 100644 --- a/sound/soc/kirkwood/kirkwood-dma.c +++ b/sound/soc/kirkwood/kirkwood-dma.c @@ -182,6 +182,9 @@ static int kirkwood_dma_hw_params(struct snd_soc_component *component, const struct mbus_dram_target_info *dram = mv_mbus_dram_info(); unsigned long addr = substream->runtime->dma_addr; + if (!dram) + return 0; + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) kirkwood_dma_conf_mbus_windows(priv->io, KIRKWOOD_PLAYBACK_WIN, addr, dram); diff --git a/sound/soc/mediatek/common/mtk-soundcard-driver.c b/sound/soc/mediatek/common/mtk-soundcard-driver.c index a58e1e3674dec..000a086a8cf44 100644 --- a/sound/soc/mediatek/common/mtk-soundcard-driver.c +++ b/sound/soc/mediatek/common/mtk-soundcard-driver.c @@ -22,7 +22,11 @@ static int set_card_codec_info(struct snd_soc_card *card, codec_node = of_get_child_by_name(sub_node, "codec"); if (!codec_node) { - dev_dbg(dev, "%s no specified codec\n", dai_link->name); + dev_dbg(dev, "%s no specified codec: setting dummy.\n", dai_link->name); + + dai_link->codecs = &snd_soc_dummy_dlc; + dai_link->num_codecs = 1; + dai_link->dynamic = 1; return 0; } diff --git a/sound/soc/mediatek/mt8192/mt8192-dai-tdm.c b/sound/soc/mediatek/mt8192/mt8192-dai-tdm.c index 9ce06821c7d0f..49440db370af0 100644 --- a/sound/soc/mediatek/mt8192/mt8192-dai-tdm.c +++ b/sound/soc/mediatek/mt8192/mt8192-dai-tdm.c @@ -566,10 +566,10 @@ static int mtk_dai_tdm_hw_params(struct snd_pcm_substream *substream, tdm_con |= 1 << DELAY_DATA_SFT; tdm_con |= get_tdm_lrck_width(format) << LRCK_TDM_WIDTH_SFT; } else if (tdm_priv->tdm_out_mode == TDM_OUT_DSP_A) { - tdm_con |= 0 << DELAY_DATA_SFT; + tdm_con |= 1 << DELAY_DATA_SFT; tdm_con |= 0 << LRCK_TDM_WIDTH_SFT; } else if (tdm_priv->tdm_out_mode == TDM_OUT_DSP_B) { - tdm_con |= 1 << DELAY_DATA_SFT; + tdm_con |= 0 << DELAY_DATA_SFT; tdm_con |= 0 << LRCK_TDM_WIDTH_SFT; } diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig index b93ea33739f29..6458d5dc4902f 100644 --- a/sound/soc/meson/Kconfig +++ b/sound/soc/meson/Kconfig @@ -99,6 +99,7 @@ config SND_MESON_AXG_PDM config SND_MESON_CARD_UTILS tristate + select SND_DYNAMIC_MINORS config SND_MESON_CODEC_GLUE tristate diff --git a/sound/soc/meson/aiu.c b/sound/soc/meson/aiu.c index 7109b81cc3d0a..5d1419ed7a62d 100644 --- a/sound/soc/meson/aiu.c +++ b/sound/soc/meson/aiu.c @@ -212,11 +212,12 @@ static const char * const aiu_spdif_ids[] = { static int aiu_clk_get(struct device *dev) { struct aiu *aiu = dev_get_drvdata(dev); + struct clk *pclk; int ret; - aiu->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(aiu->pclk)) - return dev_err_probe(dev, PTR_ERR(aiu->pclk), "Can't get the aiu pclk\n"); + pclk = devm_clk_get_enabled(dev, "pclk"); + if (IS_ERR(pclk)) + return dev_err_probe(dev, PTR_ERR(pclk), "Can't get the aiu pclk\n"); aiu->spdif_mclk = devm_clk_get(dev, "spdif_mclk"); if (IS_ERR(aiu->spdif_mclk)) @@ -233,18 +234,6 @@ static int aiu_clk_get(struct device *dev) if (ret) return dev_err_probe(dev, ret, "Can't get the spdif clocks\n"); - ret = clk_prepare_enable(aiu->pclk); - if (ret) { - dev_err(dev, "peripheral clock enable failed\n"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - aiu->pclk); - if (ret) - dev_err(dev, "failed to add reset action on pclk"); - return ret; } diff --git a/sound/soc/meson/aiu.h b/sound/soc/meson/aiu.h index 393b6c2307e49..0f94c8bf60818 100644 --- a/sound/soc/meson/aiu.h +++ b/sound/soc/meson/aiu.h @@ -33,7 +33,6 @@ struct aiu_platform_data { }; struct aiu { - struct clk *pclk; struct clk *spdif_mclk; struct aiu_interface i2s; struct aiu_interface spdif; diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c index 3180aa4d3a157..8c5605c1e34e8 100644 --- a/sound/soc/meson/axg-card.c +++ b/sound/soc/meson/axg-card.c @@ -318,6 +318,7 @@ static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np, dai_link->cpus = cpu; dai_link->num_cpus = 1; + dai_link->nonatomic = true; ret = meson_card_parse_dai(card, np, dai_link->cpus); if (ret) diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c index 65541fdb0038a..ecb3eb7a9723d 100644 --- a/sound/soc/meson/axg-fifo.c +++ b/sound/soc/meson/axg-fifo.c @@ -3,6 +3,7 @@ // Copyright (c) 2018 BayLibre, SAS. // Author: Jerome Brunet +#include #include #include #include @@ -145,8 +146,8 @@ int axg_fifo_pcm_hw_params(struct snd_soc_component *component, /* Enable irq if necessary */ irq_en = runtime->no_period_wakeup ? 0 : FIFO_INT_COUNT_REPEAT; regmap_update_bits(fifo->map, FIFO_CTRL0, - CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT), - CTRL0_INT_EN(irq_en)); + CTRL0_INT_EN, + FIELD_PREP(CTRL0_INT_EN, irq_en)); return 0; } @@ -176,9 +177,9 @@ int axg_fifo_pcm_hw_free(struct snd_soc_component *component, { struct axg_fifo *fifo = axg_fifo_data(ss); - /* Disable the block count irq */ + /* Disable irqs */ regmap_update_bits(fifo->map, FIFO_CTRL0, - CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT), 0); + CTRL0_INT_EN, 0); return 0; } @@ -187,13 +188,13 @@ EXPORT_SYMBOL_GPL(axg_fifo_pcm_hw_free); static void axg_fifo_ack_irq(struct axg_fifo *fifo, u8 mask) { regmap_update_bits(fifo->map, FIFO_CTRL1, - CTRL1_INT_CLR(FIFO_INT_MASK), - CTRL1_INT_CLR(mask)); + CTRL1_INT_CLR, + FIELD_PREP(CTRL1_INT_CLR, mask)); /* Clear must also be cleared */ regmap_update_bits(fifo->map, FIFO_CTRL1, - CTRL1_INT_CLR(FIFO_INT_MASK), - 0); + CTRL1_INT_CLR, + FIELD_PREP(CTRL1_INT_CLR, 0)); } static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id) @@ -203,18 +204,26 @@ static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id) unsigned int status; regmap_read(fifo->map, FIFO_STATUS1, &status); + status = FIELD_GET(STATUS1_INT_STS, status); + axg_fifo_ack_irq(fifo, status); - status = STATUS1_INT_STS(status) & FIFO_INT_MASK; + /* Use the thread to call period elapsed on nonatomic links */ if (status & FIFO_INT_COUNT_REPEAT) - snd_pcm_period_elapsed(ss); - else - dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n", - status); + return IRQ_WAKE_THREAD; - /* Ack irqs */ - axg_fifo_ack_irq(fifo, status); + dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n", + status); + + return IRQ_NONE; +} + +static irqreturn_t axg_fifo_pcm_irq_block_thread(int irq, void *dev_id) +{ + struct snd_pcm_substream *ss = dev_id; + + snd_pcm_period_elapsed(ss); - return IRQ_RETVAL(status); + return IRQ_HANDLED; } int axg_fifo_pcm_open(struct snd_soc_component *component, @@ -242,8 +251,9 @@ int axg_fifo_pcm_open(struct snd_soc_component *component, if (ret) return ret; - ret = request_irq(fifo->irq, axg_fifo_pcm_irq_block, 0, - dev_name(dev), ss); + ret = request_threaded_irq(fifo->irq, axg_fifo_pcm_irq_block, + axg_fifo_pcm_irq_block_thread, + IRQF_ONESHOT, dev_name(dev), ss); if (ret) return ret; @@ -254,15 +264,15 @@ int axg_fifo_pcm_open(struct snd_soc_component *component, /* Setup status2 so it reports the memory pointer */ regmap_update_bits(fifo->map, FIFO_CTRL1, - CTRL1_STATUS2_SEL_MASK, - CTRL1_STATUS2_SEL(STATUS2_SEL_DDR_READ)); + CTRL1_STATUS2_SEL, + FIELD_PREP(CTRL1_STATUS2_SEL, STATUS2_SEL_DDR_READ)); /* Make sure the dma is initially disabled */ __dma_enable(fifo, false); /* Disable irqs until params are ready */ regmap_update_bits(fifo->map, FIFO_CTRL0, - CTRL0_INT_EN(FIFO_INT_MASK), 0); + CTRL0_INT_EN, 0); /* Clear any pending interrupt */ axg_fifo_ack_irq(fifo, FIFO_INT_MASK); diff --git a/sound/soc/meson/axg-fifo.h b/sound/soc/meson/axg-fifo.h index df528e8cb7c91..84a2664139905 100644 --- a/sound/soc/meson/axg-fifo.h +++ b/sound/soc/meson/axg-fifo.h @@ -42,21 +42,19 @@ struct snd_soc_pcm_runtime; #define FIFO_CTRL0 0x00 #define CTRL0_DMA_EN BIT(31) -#define CTRL0_INT_EN(x) ((x) << 16) +#define CTRL0_INT_EN GENMASK(23, 16) #define CTRL0_SEL_MASK GENMASK(2, 0) #define CTRL0_SEL_SHIFT 0 #define FIFO_CTRL1 0x04 -#define CTRL1_INT_CLR(x) ((x) << 0) -#define CTRL1_STATUS2_SEL_MASK GENMASK(11, 8) -#define CTRL1_STATUS2_SEL(x) ((x) << 8) +#define CTRL1_INT_CLR GENMASK(7, 0) +#define CTRL1_STATUS2_SEL GENMASK(11, 8) #define STATUS2_SEL_DDR_READ 0 -#define CTRL1_FRDDR_DEPTH_MASK GENMASK(31, 24) -#define CTRL1_FRDDR_DEPTH(x) ((x) << 24) +#define CTRL1_FRDDR_DEPTH GENMASK(31, 24) #define FIFO_START_ADDR 0x08 #define FIFO_FINISH_ADDR 0x0c #define FIFO_INT_ADDR 0x10 #define FIFO_STATUS1 0x14 -#define STATUS1_INT_STS(x) ((x) << 0) +#define STATUS1_INT_STS GENMASK(7, 0) #define FIFO_STATUS2 0x18 #define FIFO_INIT_ADDR 0x24 #define FIFO_CTRL2 0x28 diff --git a/sound/soc/meson/axg-frddr.c b/sound/soc/meson/axg-frddr.c index 8c166a5f338ce..747a900c0bb22 100644 --- a/sound/soc/meson/axg-frddr.c +++ b/sound/soc/meson/axg-frddr.c @@ -7,6 +7,7 @@ * This driver implements the frontend playback DAI of AXG and G12A based SoCs */ +#include #include #include #include @@ -59,8 +60,8 @@ static int axg_frddr_dai_hw_params(struct snd_pcm_substream *substream, /* Trim the FIFO depth if the period is small to improve latency */ depth = min(period, fifo->depth); val = (depth / AXG_FIFO_BURST) - 1; - regmap_update_bits(fifo->map, FIFO_CTRL1, CTRL1_FRDDR_DEPTH_MASK, - CTRL1_FRDDR_DEPTH(val)); + regmap_update_bits(fifo->map, FIFO_CTRL1, CTRL1_FRDDR_DEPTH, + FIELD_PREP(CTRL1_FRDDR_DEPTH, val)); return 0; } diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c index 1c3d433cefd23..a71790908e178 100644 --- a/sound/soc/meson/axg-tdm-interface.c +++ b/sound/soc/meson/axg-tdm-interface.c @@ -12,6 +12,9 @@ #include "axg-tdm.h" +/* Maximum bit clock frequency according the datasheets */ +#define MAX_SCLK 100000000 /* Hz */ + enum { TDM_IFACE_PAD, TDM_IFACE_LOOPBACK, @@ -153,19 +156,27 @@ static int axg_tdm_iface_startup(struct snd_pcm_substream *substream, return -EINVAL; } - /* Apply component wide rate symmetry */ if (snd_soc_component_active(dai->component)) { + /* Apply component wide rate symmetry */ ret = snd_pcm_hw_constraint_single(substream->runtime, SNDRV_PCM_HW_PARAM_RATE, iface->rate); - if (ret < 0) { - dev_err(dai->dev, - "can't set iface rate constraint\n"); - return ret; - } + + } else { + /* Limit rate according to the slot number and width */ + unsigned int max_rate = + MAX_SCLK / (iface->slots * iface->slot_width); + ret = snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_RATE, + 0, max_rate); } - return 0; + if (ret < 0) + dev_err(dai->dev, "can't set iface rate constraint\n"); + else + ret = 0; + + return ret; } static int axg_tdm_iface_set_stream(struct snd_pcm_substream *substream, @@ -264,8 +275,8 @@ static int axg_tdm_iface_set_sclk(struct snd_soc_dai *dai, srate = iface->slots * iface->slot_width * params_rate(params); if (!iface->mclk_rate) { - /* If no specific mclk is requested, default to bit clock * 4 */ - clk_set_rate(iface->mclk, 4 * srate); + /* If no specific mclk is requested, default to bit clock * 2 */ + clk_set_rate(iface->mclk, 2 * srate); } else { /* Check if we can actually get the bit clock from mclk */ if (iface->mclk_rate % srate) { @@ -338,26 +349,31 @@ static int axg_tdm_iface_hw_params(struct snd_pcm_substream *substream, return 0; } -static int axg_tdm_iface_hw_free(struct snd_pcm_substream *substream, +static int axg_tdm_iface_trigger(struct snd_pcm_substream *substream, + int cmd, struct snd_soc_dai *dai) { - struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream); + struct axg_tdm_stream *ts = + snd_soc_dai_get_dma_data(dai, substream); - /* Stop all attached formatters */ - axg_tdm_stream_stop(ts); + switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + case SNDRV_PCM_TRIGGER_RESUME: + case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + axg_tdm_stream_start(ts); + break; + case SNDRV_PCM_TRIGGER_SUSPEND: + case SNDRV_PCM_TRIGGER_PAUSE_PUSH: + case SNDRV_PCM_TRIGGER_STOP: + axg_tdm_stream_stop(ts); + break; + default: + return -EINVAL; + } return 0; } -static int axg_tdm_iface_prepare(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream); - - /* Force all attached formatters to update */ - return axg_tdm_stream_reset(ts); -} - static int axg_tdm_iface_remove_dai(struct snd_soc_dai *dai) { int stream; @@ -401,8 +417,7 @@ static const struct snd_soc_dai_ops axg_tdm_iface_ops = { .set_fmt = axg_tdm_iface_set_fmt, .startup = axg_tdm_iface_startup, .hw_params = axg_tdm_iface_hw_params, - .prepare = axg_tdm_iface_prepare, - .hw_free = axg_tdm_iface_hw_free, + .trigger = axg_tdm_iface_trigger, }; /* TDM Backend DAIs */ diff --git a/sound/soc/meson/axg-toddr.c b/sound/soc/meson/axg-toddr.c index 1a0be177b8fe7..972ad99f31be2 100644 --- a/sound/soc/meson/axg-toddr.c +++ b/sound/soc/meson/axg-toddr.c @@ -5,6 +5,7 @@ /* This driver implements the frontend capture DAI of AXG based SoCs */ +#include #include #include #include @@ -19,12 +20,9 @@ #define CTRL0_TODDR_EXT_SIGNED BIT(29) #define CTRL0_TODDR_PP_MODE BIT(28) #define CTRL0_TODDR_SYNC_CH BIT(27) -#define CTRL0_TODDR_TYPE_MASK GENMASK(15, 13) -#define CTRL0_TODDR_TYPE(x) ((x) << 13) -#define CTRL0_TODDR_MSB_POS_MASK GENMASK(12, 8) -#define CTRL0_TODDR_MSB_POS(x) ((x) << 8) -#define CTRL0_TODDR_LSB_POS_MASK GENMASK(7, 3) -#define CTRL0_TODDR_LSB_POS(x) ((x) << 3) +#define CTRL0_TODDR_TYPE GENMASK(15, 13) +#define CTRL0_TODDR_MSB_POS GENMASK(12, 8) +#define CTRL0_TODDR_LSB_POS GENMASK(7, 3) #define CTRL1_TODDR_FORCE_FINISH BIT(25) #define CTRL1_SEL_SHIFT 28 @@ -76,12 +74,12 @@ static int axg_toddr_dai_hw_params(struct snd_pcm_substream *substream, width = params_width(params); regmap_update_bits(fifo->map, FIFO_CTRL0, - CTRL0_TODDR_TYPE_MASK | - CTRL0_TODDR_MSB_POS_MASK | - CTRL0_TODDR_LSB_POS_MASK, - CTRL0_TODDR_TYPE(type) | - CTRL0_TODDR_MSB_POS(TODDR_MSB_POS) | - CTRL0_TODDR_LSB_POS(TODDR_MSB_POS - (width - 1))); + CTRL0_TODDR_TYPE | + CTRL0_TODDR_MSB_POS | + CTRL0_TODDR_LSB_POS, + FIELD_PREP(CTRL0_TODDR_TYPE, type) | + FIELD_PREP(CTRL0_TODDR_MSB_POS, TODDR_MSB_POS) | + FIELD_PREP(CTRL0_TODDR_LSB_POS, TODDR_MSB_POS - (width - 1))); return 0; } diff --git a/sound/soc/meson/t9015.c b/sound/soc/meson/t9015.c index 9c6b4dac68932..571f65788c592 100644 --- a/sound/soc/meson/t9015.c +++ b/sound/soc/meson/t9015.c @@ -48,7 +48,6 @@ #define POWER_CFG 0x10 struct t9015 { - struct clk *pclk; struct regulator *avdd; }; @@ -249,6 +248,7 @@ static int t9015_probe(struct platform_device *pdev) struct t9015 *priv; void __iomem *regs; struct regmap *regmap; + struct clk *pclk; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -256,26 +256,14 @@ static int t9015_probe(struct platform_device *pdev) return -ENOMEM; platform_set_drvdata(pdev, priv); - priv->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(priv->pclk)) - return dev_err_probe(dev, PTR_ERR(priv->pclk), "failed to get core clock\n"); + pclk = devm_clk_get_enabled(dev, "pclk"); + if (IS_ERR(pclk)) + return dev_err_probe(dev, PTR_ERR(pclk), "failed to get core clock\n"); priv->avdd = devm_regulator_get(dev, "AVDD"); if (IS_ERR(priv->avdd)) return dev_err_probe(dev, PTR_ERR(priv->avdd), "failed to AVDD\n"); - ret = clk_prepare_enable(priv->pclk); - if (ret) { - dev_err(dev, "core clock enable failed\n"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - priv->pclk); - if (ret) - return ret; - ret = device_reset(dev); if (ret) { dev_err(dev, "reset failed\n"); diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index 860e66ec85e8a..9fa020ef7eab9 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -25,8 +25,6 @@ #define DEFAULT_MCLK_FS 256 #define CH_GRP_MAX 4 /* The max channel 8 / 2 */ #define MULTIPLEX_CH_MAX 10 -#define CLK_PPM_MIN -1000 -#define CLK_PPM_MAX 1000 #define TRCM_TXRX 0 #define TRCM_TX 1 @@ -53,20 +51,6 @@ struct rk_i2s_tdm_dev { struct clk *hclk; struct clk *mclk_tx; struct clk *mclk_rx; - /* The mclk_tx_src is parent of mclk_tx */ - struct clk *mclk_tx_src; - /* The mclk_rx_src is parent of mclk_rx */ - struct clk *mclk_rx_src; - /* - * The mclk_root0 and mclk_root1 are root parent and supplies for - * the different FS. - * - * e.g: - * mclk_root0 is VPLL0, used for FS=48000Hz - * mclk_root1 is VPLL1, used for FS=44100Hz - */ - struct clk *mclk_root0; - struct clk *mclk_root1; struct regmap *regmap; struct regmap *grf; struct snd_dmaengine_dai_dma_data capture_dma_data; @@ -76,19 +60,11 @@ struct rk_i2s_tdm_dev { const struct rk_i2s_soc_data *soc_data; bool is_master_mode; bool io_multiplex; - bool mclk_calibrate; bool tdm_mode; - unsigned int mclk_rx_freq; - unsigned int mclk_tx_freq; - unsigned int mclk_root0_freq; - unsigned int mclk_root1_freq; - unsigned int mclk_root0_initial_freq; - unsigned int mclk_root1_initial_freq; unsigned int frame_width; unsigned int clk_trcm; unsigned int i2s_sdis[CH_GRP_MAX]; unsigned int i2s_sdos[CH_GRP_MAX]; - int clk_ppm; int refcount; spinlock_t lock; /* xfer lock */ bool has_playback; @@ -114,12 +90,6 @@ static void i2s_tdm_disable_unprepare_mclk(struct rk_i2s_tdm_dev *i2s_tdm) { clk_disable_unprepare(i2s_tdm->mclk_tx); clk_disable_unprepare(i2s_tdm->mclk_rx); - if (i2s_tdm->mclk_calibrate) { - clk_disable_unprepare(i2s_tdm->mclk_tx_src); - clk_disable_unprepare(i2s_tdm->mclk_rx_src); - clk_disable_unprepare(i2s_tdm->mclk_root0); - clk_disable_unprepare(i2s_tdm->mclk_root1); - } } /** @@ -142,29 +112,9 @@ static int i2s_tdm_prepare_enable_mclk(struct rk_i2s_tdm_dev *i2s_tdm) ret = clk_prepare_enable(i2s_tdm->mclk_rx); if (ret) goto err_mclk_rx; - if (i2s_tdm->mclk_calibrate) { - ret = clk_prepare_enable(i2s_tdm->mclk_tx_src); - if (ret) - goto err_mclk_rx; - ret = clk_prepare_enable(i2s_tdm->mclk_rx_src); - if (ret) - goto err_mclk_rx_src; - ret = clk_prepare_enable(i2s_tdm->mclk_root0); - if (ret) - goto err_mclk_root0; - ret = clk_prepare_enable(i2s_tdm->mclk_root1); - if (ret) - goto err_mclk_root1; - } return 0; -err_mclk_root1: - clk_disable_unprepare(i2s_tdm->mclk_root0); -err_mclk_root0: - clk_disable_unprepare(i2s_tdm->mclk_rx_src); -err_mclk_rx_src: - clk_disable_unprepare(i2s_tdm->mclk_tx_src); err_mclk_rx: clk_disable_unprepare(i2s_tdm->mclk_tx); err_mclk_tx: @@ -564,159 +514,6 @@ static void rockchip_i2s_tdm_xfer_resume(struct snd_pcm_substream *substream, I2S_XFER_RXS_START); } -static int rockchip_i2s_tdm_clk_set_rate(struct rk_i2s_tdm_dev *i2s_tdm, - struct clk *clk, unsigned long rate, - int ppm) -{ - unsigned long rate_target; - int delta, ret; - - if (ppm == i2s_tdm->clk_ppm) - return 0; - - if (ppm < 0) - delta = -1; - else - delta = 1; - - delta *= (int)div64_u64((u64)rate * (u64)abs(ppm) + 500000, - 1000000); - - rate_target = rate + delta; - - if (!rate_target) - return -EINVAL; - - ret = clk_set_rate(clk, rate_target); - if (ret) - return ret; - - i2s_tdm->clk_ppm = ppm; - - return 0; -} - -static int rockchip_i2s_tdm_calibrate_mclk(struct rk_i2s_tdm_dev *i2s_tdm, - struct snd_pcm_substream *substream, - unsigned int lrck_freq) -{ - struct clk *mclk_root; - struct clk *mclk_parent; - unsigned int mclk_root_freq; - unsigned int mclk_root_initial_freq; - unsigned int mclk_parent_freq; - unsigned int div, delta; - u64 ppm; - int ret; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - mclk_parent = i2s_tdm->mclk_tx_src; - else - mclk_parent = i2s_tdm->mclk_rx_src; - - switch (lrck_freq) { - case 8000: - case 16000: - case 24000: - case 32000: - case 48000: - case 64000: - case 96000: - case 192000: - mclk_root = i2s_tdm->mclk_root0; - mclk_root_freq = i2s_tdm->mclk_root0_freq; - mclk_root_initial_freq = i2s_tdm->mclk_root0_initial_freq; - mclk_parent_freq = DEFAULT_MCLK_FS * 192000; - break; - case 11025: - case 22050: - case 44100: - case 88200: - case 176400: - mclk_root = i2s_tdm->mclk_root1; - mclk_root_freq = i2s_tdm->mclk_root1_freq; - mclk_root_initial_freq = i2s_tdm->mclk_root1_initial_freq; - mclk_parent_freq = DEFAULT_MCLK_FS * 176400; - break; - default: - dev_err(i2s_tdm->dev, "Invalid LRCK frequency: %u Hz\n", - lrck_freq); - return -EINVAL; - } - - ret = clk_set_parent(mclk_parent, mclk_root); - if (ret) - return ret; - - ret = rockchip_i2s_tdm_clk_set_rate(i2s_tdm, mclk_root, - mclk_root_freq, 0); - if (ret) - return ret; - - delta = abs(mclk_root_freq % mclk_parent_freq - mclk_parent_freq); - ppm = div64_u64((uint64_t)delta * 1000000, (uint64_t)mclk_root_freq); - - if (ppm) { - div = DIV_ROUND_CLOSEST(mclk_root_initial_freq, mclk_parent_freq); - if (!div) - return -EINVAL; - - mclk_root_freq = mclk_parent_freq * round_up(div, 2); - - ret = clk_set_rate(mclk_root, mclk_root_freq); - if (ret) - return ret; - - i2s_tdm->mclk_root0_freq = clk_get_rate(i2s_tdm->mclk_root0); - i2s_tdm->mclk_root1_freq = clk_get_rate(i2s_tdm->mclk_root1); - } - - return clk_set_rate(mclk_parent, mclk_parent_freq); -} - -static int rockchip_i2s_tdm_set_mclk(struct rk_i2s_tdm_dev *i2s_tdm, - struct snd_pcm_substream *substream, - struct clk **mclk) -{ - unsigned int mclk_freq; - int ret; - - if (i2s_tdm->clk_trcm) { - if (i2s_tdm->mclk_tx_freq != i2s_tdm->mclk_rx_freq) { - dev_err(i2s_tdm->dev, - "clk_trcm, tx: %d and rx: %d should be the same\n", - i2s_tdm->mclk_tx_freq, - i2s_tdm->mclk_rx_freq); - return -EINVAL; - } - - ret = clk_set_rate(i2s_tdm->mclk_tx, i2s_tdm->mclk_tx_freq); - if (ret) - return ret; - - ret = clk_set_rate(i2s_tdm->mclk_rx, i2s_tdm->mclk_rx_freq); - if (ret) - return ret; - - /* mclk_rx is also ok. */ - *mclk = i2s_tdm->mclk_tx; - } else { - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { - *mclk = i2s_tdm->mclk_tx; - mclk_freq = i2s_tdm->mclk_tx_freq; - } else { - *mclk = i2s_tdm->mclk_rx; - mclk_freq = i2s_tdm->mclk_rx_freq; - } - - ret = clk_set_rate(*mclk, mclk_freq); - if (ret) - return ret; - } - - return 0; -} - static int rockchip_i2s_ch_to_io(unsigned int ch, bool substream_capture) { if (substream_capture) { @@ -853,19 +650,17 @@ static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct rk_i2s_tdm_dev *i2s_tdm = to_info(dai); - struct clk *mclk; - int ret = 0; unsigned int val = 0; unsigned int mclk_rate, bclk_rate, div_bclk = 4, div_lrck = 64; + int err; if (i2s_tdm->is_master_mode) { - if (i2s_tdm->mclk_calibrate) - rockchip_i2s_tdm_calibrate_mclk(i2s_tdm, substream, - params_rate(params)); + struct clk *mclk = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ? + i2s_tdm->mclk_tx : i2s_tdm->mclk_rx; - ret = rockchip_i2s_tdm_set_mclk(i2s_tdm, substream, &mclk); - if (ret) - return ret; + err = clk_set_rate(mclk, DEFAULT_MCLK_FS * params_rate(params)); + if (err) + return err; mclk_rate = clk_get_rate(mclk); bclk_rate = i2s_tdm->frame_width * params_rate(params); @@ -973,96 +768,6 @@ static int rockchip_i2s_tdm_trigger(struct snd_pcm_substream *substream, return 0; } -static int rockchip_i2s_tdm_set_sysclk(struct snd_soc_dai *cpu_dai, int stream, - unsigned int freq, int dir) -{ - struct rk_i2s_tdm_dev *i2s_tdm = to_info(cpu_dai); - - /* Put set mclk rate into rockchip_i2s_tdm_set_mclk() */ - if (i2s_tdm->clk_trcm) { - i2s_tdm->mclk_tx_freq = freq; - i2s_tdm->mclk_rx_freq = freq; - } else { - if (stream == SNDRV_PCM_STREAM_PLAYBACK) - i2s_tdm->mclk_tx_freq = freq; - else - i2s_tdm->mclk_rx_freq = freq; - } - - dev_dbg(i2s_tdm->dev, "The target mclk_%s freq is: %d\n", - stream ? "rx" : "tx", freq); - - return 0; -} - -static int rockchip_i2s_tdm_clk_compensation_info(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_info *uinfo) -{ - uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; - uinfo->count = 1; - uinfo->value.integer.min = CLK_PPM_MIN; - uinfo->value.integer.max = CLK_PPM_MAX; - uinfo->value.integer.step = 1; - - return 0; -} - -static int rockchip_i2s_tdm_clk_compensation_get(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_dai *dai = snd_kcontrol_chip(kcontrol); - struct rk_i2s_tdm_dev *i2s_tdm = snd_soc_dai_get_drvdata(dai); - - ucontrol->value.integer.value[0] = i2s_tdm->clk_ppm; - - return 0; -} - -static int rockchip_i2s_tdm_clk_compensation_put(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_dai *dai = snd_kcontrol_chip(kcontrol); - struct rk_i2s_tdm_dev *i2s_tdm = snd_soc_dai_get_drvdata(dai); - int ret = 0, ppm = 0; - int changed = 0; - unsigned long old_rate; - - if (ucontrol->value.integer.value[0] < CLK_PPM_MIN || - ucontrol->value.integer.value[0] > CLK_PPM_MAX) - return -EINVAL; - - ppm = ucontrol->value.integer.value[0]; - - old_rate = clk_get_rate(i2s_tdm->mclk_root0); - ret = rockchip_i2s_tdm_clk_set_rate(i2s_tdm, i2s_tdm->mclk_root0, - i2s_tdm->mclk_root0_freq, ppm); - if (ret) - return ret; - if (old_rate != clk_get_rate(i2s_tdm->mclk_root0)) - changed = 1; - - if (clk_is_match(i2s_tdm->mclk_root0, i2s_tdm->mclk_root1)) - return changed; - - old_rate = clk_get_rate(i2s_tdm->mclk_root1); - ret = rockchip_i2s_tdm_clk_set_rate(i2s_tdm, i2s_tdm->mclk_root1, - i2s_tdm->mclk_root1_freq, ppm); - if (ret) - return ret; - if (old_rate != clk_get_rate(i2s_tdm->mclk_root1)) - changed = 1; - - return changed; -} - -static struct snd_kcontrol_new rockchip_i2s_tdm_compensation_control = { - .iface = SNDRV_CTL_ELEM_IFACE_PCM, - .name = "PCM Clock Compensation in PPM", - .info = rockchip_i2s_tdm_clk_compensation_info, - .get = rockchip_i2s_tdm_clk_compensation_get, - .put = rockchip_i2s_tdm_clk_compensation_put, -}; - static int rockchip_i2s_tdm_dai_probe(struct snd_soc_dai *dai) { struct rk_i2s_tdm_dev *i2s_tdm = snd_soc_dai_get_drvdata(dai); @@ -1072,9 +777,6 @@ static int rockchip_i2s_tdm_dai_probe(struct snd_soc_dai *dai) if (i2s_tdm->has_playback) snd_soc_dai_dma_data_set_playback(dai, &i2s_tdm->playback_dma_data); - if (i2s_tdm->mclk_calibrate) - snd_soc_add_dai_controls(dai, &rockchip_i2s_tdm_compensation_control, 1); - return 0; } @@ -1115,7 +817,6 @@ static const struct snd_soc_dai_ops rockchip_i2s_tdm_dai_ops = { .probe = rockchip_i2s_tdm_dai_probe, .hw_params = rockchip_i2s_tdm_hw_params, .set_bclk_ratio = rockchip_i2s_tdm_set_bclk_ratio, - .set_sysclk = rockchip_i2s_tdm_set_sysclk, .set_fmt = rockchip_i2s_tdm_set_fmt, .set_tdm_slot = rockchip_dai_tdm_slot, .trigger = rockchip_i2s_tdm_trigger, @@ -1444,35 +1145,6 @@ static void rockchip_i2s_tdm_path_config(struct rk_i2s_tdm_dev *i2s_tdm, rockchip_i2s_tdm_tx_path_config(i2s_tdm, num); } -static int rockchip_i2s_tdm_get_calibrate_mclks(struct rk_i2s_tdm_dev *i2s_tdm) -{ - int num_mclks = 0; - - i2s_tdm->mclk_tx_src = devm_clk_get(i2s_tdm->dev, "mclk_tx_src"); - if (!IS_ERR(i2s_tdm->mclk_tx_src)) - num_mclks++; - - i2s_tdm->mclk_rx_src = devm_clk_get(i2s_tdm->dev, "mclk_rx_src"); - if (!IS_ERR(i2s_tdm->mclk_rx_src)) - num_mclks++; - - i2s_tdm->mclk_root0 = devm_clk_get(i2s_tdm->dev, "mclk_root0"); - if (!IS_ERR(i2s_tdm->mclk_root0)) - num_mclks++; - - i2s_tdm->mclk_root1 = devm_clk_get(i2s_tdm->dev, "mclk_root1"); - if (!IS_ERR(i2s_tdm->mclk_root1)) - num_mclks++; - - if (num_mclks < 4 && num_mclks != 0) - return -ENOENT; - - if (num_mclks == 4) - i2s_tdm->mclk_calibrate = 1; - - return 0; -} - static int rockchip_i2s_tdm_path_prepare(struct rk_i2s_tdm_dev *i2s_tdm, struct device_node *np, bool is_rx_path) @@ -1610,11 +1282,6 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev) i2s_tdm->io_multiplex = of_property_read_bool(node, "rockchip,io-multiplex"); - ret = rockchip_i2s_tdm_get_calibrate_mclks(i2s_tdm); - if (ret) - return dev_err_probe(i2s_tdm->dev, ret, - "mclk-calibrate clocks missing"); - regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(regs)) { return dev_err_probe(i2s_tdm->dev, PTR_ERR(regs), @@ -1667,13 +1334,6 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev) goto err_disable_hclk; } - if (i2s_tdm->mclk_calibrate) { - i2s_tdm->mclk_root0_initial_freq = clk_get_rate(i2s_tdm->mclk_root0); - i2s_tdm->mclk_root1_initial_freq = clk_get_rate(i2s_tdm->mclk_root1); - i2s_tdm->mclk_root0_freq = i2s_tdm->mclk_root0_initial_freq; - i2s_tdm->mclk_root1_freq = i2s_tdm->mclk_root1_initial_freq; - } - pm_runtime_enable(&pdev->dev); regmap_update_bits(i2s_tdm->regmap, I2S_DMACR, I2S_DMACR_TDL_MASK, diff --git a/sound/soc/sh/rz-ssi.c b/sound/soc/sh/rz-ssi.c index 14cf1a41fb0d1..9d103646973ad 100644 --- a/sound/soc/sh/rz-ssi.c +++ b/sound/soc/sh/rz-ssi.c @@ -1015,7 +1015,7 @@ static int rz_ssi_probe(struct platform_device *pdev) dev_name(&pdev->dev), ssi); if (ret < 0) return dev_err_probe(&pdev->dev, ret, - "irq request error (dma_tx)\n"); + "irq request error (dma_rt)\n"); } else { if (ssi->irq_tx < 0) return ssi->irq_tx; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 516350533e73f..8b5b583a2bad0 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1218,6 +1218,9 @@ static int snd_soc_add_pcm_runtime(struct snd_soc_card *card, if (!snd_soc_is_matching_component(platform, component)) continue; + if (snd_soc_component_is_dummy(component) && component->num_dai) + continue; + snd_soc_rtd_add_component(rtd, component); } } diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 2d25748ca7066..b27e89ff6a167 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -263,7 +263,7 @@ int snd_soc_get_volsw(struct snd_kcontrol *kcontrol, int max = mc->max; int min = mc->min; int sign_bit = mc->sign_bit; - unsigned int mask = (1 << fls(max)) - 1; + unsigned int mask = (1ULL << fls(max)) - 1; unsigned int invert = mc->invert; int val; int ret; diff --git a/sound/soc/sof/amd/acp-loader.c b/sound/soc/sof/amd/acp-loader.c index e05eb7a86dd44..aad904839b817 100644 --- a/sound/soc/sof/amd/acp-loader.c +++ b/sound/soc/sof/amd/acp-loader.c @@ -173,7 +173,7 @@ int acp_dsp_pre_fw_run(struct snd_sof_dev *sdev) adata = sdev->pdata->hw_pdata; - if (adata->signed_fw_image) + if (adata->quirks && adata->quirks->signed_fw_image) size_fw = adata->fw_bin_size - ACP_FIRMWARE_SIGNATURE; else size_fw = adata->fw_bin_size; @@ -267,29 +267,49 @@ int acp_sof_load_signed_firmware(struct snd_sof_dev *sdev) { struct snd_sof_pdata *plat_data = sdev->pdata; struct acp_dev_data *adata = plat_data->hw_pdata; + const char *fw_filename; int ret; - ret = request_firmware(&sdev->basefw.fw, adata->fw_code_bin, sdev->dev); + fw_filename = kasprintf(GFP_KERNEL, "%s/%s", + plat_data->fw_filename_prefix, + adata->fw_code_bin); + if (!fw_filename) + return -ENOMEM; + + ret = request_firmware(&sdev->basefw.fw, fw_filename, sdev->dev); if (ret < 0) { + kfree(fw_filename); dev_err(sdev->dev, "sof signed firmware code bin is missing\n"); return ret; } else { - dev_dbg(sdev->dev, "request_firmware %s successful\n", adata->fw_code_bin); + dev_dbg(sdev->dev, "request_firmware %s successful\n", fw_filename); } + kfree(fw_filename); + ret = snd_sof_dsp_block_write(sdev, SOF_FW_BLK_TYPE_IRAM, 0, - (void *)sdev->basefw.fw->data, sdev->basefw.fw->size); + (void *)sdev->basefw.fw->data, + sdev->basefw.fw->size); + + fw_filename = kasprintf(GFP_KERNEL, "%s/%s", + plat_data->fw_filename_prefix, + adata->fw_data_bin); + if (!fw_filename) + return -ENOMEM; - ret = request_firmware(&adata->fw_dbin, adata->fw_data_bin, sdev->dev); + ret = request_firmware(&adata->fw_dbin, fw_filename, sdev->dev); if (ret < 0) { + kfree(fw_filename); dev_err(sdev->dev, "sof signed firmware data bin is missing\n"); return ret; } else { - dev_dbg(sdev->dev, "request_firmware %s successful\n", adata->fw_data_bin); + dev_dbg(sdev->dev, "request_firmware %s successful\n", fw_filename); } + kfree(fw_filename); ret = snd_sof_dsp_block_write(sdev, SOF_FW_BLK_TYPE_DRAM, 0, - (void *)adata->fw_dbin->data, adata->fw_dbin->size); + (void *)adata->fw_dbin->data, + adata->fw_dbin->size); return ret; } EXPORT_SYMBOL_NS(acp_sof_load_signed_firmware, SND_SOC_SOF_AMD_COMMON); diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c index 07632ae6ccf5e..1b6f5724c82b0 100644 --- a/sound/soc/sof/amd/acp.c +++ b/sound/soc/sof/amd/acp.c @@ -20,21 +20,23 @@ #include "acp.h" #include "acp-dsp-offset.h" -#define SECURED_FIRMWARE 1 - static bool enable_fw_debug; module_param(enable_fw_debug, bool, 0444); MODULE_PARM_DESC(enable_fw_debug, "Enable Firmware debug"); +static struct acp_quirk_entry quirk_valve_galileo = { + .signed_fw_image = true, + .skip_iram_dram_size_mod = true, +}; + const struct dmi_system_id acp_sof_quirk_table[] = { { - /* Valve Jupiter device */ + /* Steam Deck OLED device */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Valve"), DMI_MATCH(DMI_PRODUCT_NAME, "Galileo"), - DMI_MATCH(DMI_PRODUCT_FAMILY, "Sephiroth"), }, - .driver_data = (void *)SECURED_FIRMWARE, + .driver_data = &quirk_valve_galileo, }, {} }; @@ -255,7 +257,7 @@ int configure_and_run_sha_dma(struct acp_dev_data *adata, void *image_addr, } } - if (adata->signed_fw_image) + if (adata->quirks && adata->quirks->signed_fw_image) snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_DMA_INCLUDE_HDR, ACP_SHA_HEADER); snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_DMA_STRT_ADDR, start_addr); @@ -279,7 +281,7 @@ int configure_and_run_sha_dma(struct acp_dev_data *adata, void *image_addr, } /* psp_send_cmd only required for vangogh platform (rev - 5) */ - if (desc->rev == 5) { + if (desc->rev == 5 && !(adata->quirks && adata->quirks->skip_iram_dram_size_mod)) { /* Modify IRAM and DRAM size */ ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | IRAM_DRAM_FENCE_2); if (ret) @@ -493,7 +495,6 @@ EXPORT_SYMBOL_NS(amd_sof_acp_resume, SND_SOC_SOF_AMD_COMMON); int amd_sof_acp_probe(struct snd_sof_dev *sdev) { struct pci_dev *pci = to_pci_dev(sdev->dev); - struct snd_sof_pdata *plat_data = sdev->pdata; struct acp_dev_data *adata; const struct sof_amd_acp_desc *chip; const struct dmi_system_id *dmi_id; @@ -535,6 +536,10 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev) goto unregister_dev; } + ret = acp_init(sdev); + if (ret < 0) + goto free_smn_dev; + sdev->ipc_irq = pci->irq; ret = request_threaded_irq(sdev->ipc_irq, acp_irq_handler, acp_irq_thread, IRQF_SHARED, "AudioDSP", sdev); @@ -544,10 +549,6 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev) goto free_smn_dev; } - ret = acp_init(sdev); - if (ret < 0) - goto free_ipc_irq; - sdev->dsp_box.offset = 0; sdev->dsp_box.size = BOX_SIZE_512; @@ -557,20 +558,29 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev) sdev->debug_box.offset = sdev->host_box.offset + sdev->host_box.size; sdev->debug_box.size = BOX_SIZE_1024; - adata->signed_fw_image = false; dmi_id = dmi_first_match(acp_sof_quirk_table); - if (dmi_id && dmi_id->driver_data) { - adata->fw_code_bin = kasprintf(GFP_KERNEL, "%s/sof-%s-code.bin", - plat_data->fw_filename_prefix, - chip->name); - adata->fw_data_bin = kasprintf(GFP_KERNEL, "%s/sof-%s-data.bin", - plat_data->fw_filename_prefix, - chip->name); - adata->signed_fw_image = dmi_id->driver_data; - - dev_dbg(sdev->dev, "fw_code_bin:%s, fw_data_bin:%s\n", adata->fw_code_bin, - adata->fw_data_bin); + if (dmi_id) { + adata->quirks = dmi_id->driver_data; + + if (adata->quirks->signed_fw_image) { + adata->fw_code_bin = devm_kasprintf(sdev->dev, GFP_KERNEL, + "sof-%s-code.bin", + chip->name); + if (!adata->fw_code_bin) { + ret = -ENOMEM; + goto free_ipc_irq; + } + + adata->fw_data_bin = devm_kasprintf(sdev->dev, GFP_KERNEL, + "sof-%s-data.bin", + chip->name); + if (!adata->fw_data_bin) { + ret = -ENOMEM; + goto free_ipc_irq; + } + } } + adata->enable_fw_debug = enable_fw_debug; acp_memory_init(sdev); diff --git a/sound/soc/sof/amd/acp.h b/sound/soc/sof/amd/acp.h index c645aee216fd0..7d4a8b6b3cc67 100644 --- a/sound/soc/sof/amd/acp.h +++ b/sound/soc/sof/amd/acp.h @@ -193,6 +193,11 @@ struct sof_amd_acp_desc { u32 probe_reg_offset; }; +struct acp_quirk_entry { + bool signed_fw_image; + bool skip_iram_dram_size_mod; +}; + /* Common device data struct for ACP devices */ struct acp_dev_data { struct snd_sof_dev *dev; @@ -213,7 +218,7 @@ struct acp_dev_data { u8 *data_buf; dma_addr_t sram_dma_addr; u8 *sram_data_buf; - bool signed_fw_image; + struct acp_quirk_entry *quirks; struct dma_descriptor dscr_info[ACP_MAX_DESC]; struct acp_dsp_stream stream_buf[ACP_MAX_STREAM]; struct acp_dsp_stream *dtrace_stream; diff --git a/sound/soc/sof/amd/vangogh.c b/sound/soc/sof/amd/vangogh.c index de15d21aa6d98..bc6ffdb5471a5 100644 --- a/sound/soc/sof/amd/vangogh.c +++ b/sound/soc/sof/amd/vangogh.c @@ -143,6 +143,7 @@ EXPORT_SYMBOL_NS(sof_vangogh_ops, SND_SOC_SOF_AMD_COMMON); int sof_vangogh_ops_init(struct snd_sof_dev *sdev) { const struct dmi_system_id *dmi_id; + struct acp_quirk_entry *quirks; /* common defaults */ memcpy(&sof_vangogh_ops, &sof_acp_common_ops, sizeof(struct snd_sof_dsp_ops)); @@ -151,8 +152,12 @@ int sof_vangogh_ops_init(struct snd_sof_dev *sdev) sof_vangogh_ops.num_drv = ARRAY_SIZE(vangogh_sof_dai); dmi_id = dmi_first_match(acp_sof_quirk_table); - if (dmi_id && dmi_id->driver_data) - sof_vangogh_ops.load_firmware = acp_sof_load_signed_firmware; + if (dmi_id) { + quirks = dmi_id->driver_data; + + if (quirks->signed_fw_image) + sof_vangogh_ops.load_firmware = acp_sof_load_signed_firmware; + } return 0; } diff --git a/sound/soc/sof/fw-file-profile.c b/sound/soc/sof/fw-file-profile.c index 138a1ca2c4a85..b56b14232444c 100644 --- a/sound/soc/sof/fw-file-profile.c +++ b/sound/soc/sof/fw-file-profile.c @@ -89,6 +89,12 @@ static int sof_test_topology_file(struct device *dev, return ret; } +static bool sof_platform_uses_generic_loader(struct snd_sof_dev *sdev) +{ + return (sdev->pdata->desc->ops->load_firmware == snd_sof_load_firmware_raw || + sdev->pdata->desc->ops->load_firmware == snd_sof_load_firmware_memcpy); +} + static int sof_file_profile_for_ipc_type(struct snd_sof_dev *sdev, enum sof_ipc_type ipc_type, @@ -130,7 +136,8 @@ sof_file_profile_for_ipc_type(struct snd_sof_dev *sdev, * For default path and firmware name do a verification before * continuing further. */ - if (base_profile->fw_path || base_profile->fw_name) { + if ((base_profile->fw_path || base_profile->fw_name) && + sof_platform_uses_generic_loader(sdev)) { ret = sof_test_firmware_file(dev, out_profile, &ipc_type); if (ret) return ret; @@ -181,7 +188,8 @@ sof_file_profile_for_ipc_type(struct snd_sof_dev *sdev, out_profile->ipc_type = ipc_type; /* Test only default firmware file */ - if (!base_profile->fw_path && !base_profile->fw_name) + if ((!base_profile->fw_path && !base_profile->fw_name) && + sof_platform_uses_generic_loader(sdev)) ret = sof_test_firmware_file(dev, out_profile, NULL); if (!ret) @@ -267,7 +275,11 @@ static void sof_print_profile_info(struct snd_sof_dev *sdev, dev_info(dev, "Firmware paths/files for ipc type %d:\n", profile->ipc_type); - dev_info(dev, " Firmware file: %s/%s\n", profile->fw_path, profile->fw_name); + /* The firmware path is only valid when generic loader is used */ + if (sof_platform_uses_generic_loader(sdev)) + dev_info(dev, " Firmware file: %s/%s\n", + profile->fw_path, profile->fw_name); + if (profile->fw_lib_path) dev_info(dev, " Firmware lib path: %s\n", profile->fw_lib_path); dev_info(dev, " Topology file: %s/%s\n", profile->tplg_path, profile->tplg_name); diff --git a/sound/soc/sof/intel/hda-common-ops.c b/sound/soc/sof/intel/hda-common-ops.c index 26105d8f1bdc7..88c236b9a0453 100644 --- a/sound/soc/sof/intel/hda-common-ops.c +++ b/sound/soc/sof/intel/hda-common-ops.c @@ -57,6 +57,9 @@ struct snd_sof_dsp_ops sof_hda_common_ops = { .pcm_pointer = hda_dsp_pcm_pointer, .pcm_ack = hda_dsp_pcm_ack, + .get_dai_frame_counter = hda_dsp_get_stream_llp, + .get_host_byte_counter = hda_dsp_get_stream_ldp, + /* firmware loading */ .load_firmware = snd_sof_load_firmware_raw, diff --git a/sound/soc/sof/intel/hda-dai-ops.c b/sound/soc/sof/intel/hda-dai-ops.c index 55ce75db23e52..92ec5db4677df 100644 --- a/sound/soc/sof/intel/hda-dai-ops.c +++ b/sound/soc/sof/intel/hda-dai-ops.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -362,6 +363,16 @@ static int hda_trigger(struct snd_sof_dev *sdev, struct snd_soc_dai *cpu_dai, case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: snd_hdac_ext_stream_clear(hext_stream); + + /* + * Save the LLP registers in case the stream is + * restarting due PAUSE_RELEASE, or START without a pcm + * close/open since in this case the LLP register is not reset + * to 0 and the delay calculation will return with invalid + * results. + */ + hext_stream->pplcllpl = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL); + hext_stream->pplcllpu = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU); break; default: dev_err(sdev->dev, "unknown trigger command %d\n", cmd); diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index f4cbc0ad5de3b..0e665c0840d71 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -434,10 +434,17 @@ int sdw_hda_dai_hw_params(struct snd_pcm_substream *substream, int link_id) { struct snd_soc_dapm_widget *w = snd_soc_dai_get_widget(cpu_dai, substream->stream); + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); const struct hda_dai_widget_dma_ops *ops; + struct snd_soc_dai_link_ch_map *ch_maps; struct hdac_ext_stream *hext_stream; + struct snd_soc_dai *dai; struct snd_sof_dev *sdev; + bool cpu_dai_found = false; + int cpu_dai_id; + int ch_mask; int ret; + int j; ret = non_hda_dai_hw_params(substream, params, cpu_dai); if (ret < 0) { @@ -452,9 +459,29 @@ int sdw_hda_dai_hw_params(struct snd_pcm_substream *substream, if (!hext_stream) return -ENODEV; - /* in the case of SoundWire we need to program the PCMSyCM registers */ + /* + * in the case of SoundWire we need to program the PCMSyCM registers. In case + * of aggregated devices, we need to define the channel mask for each sublink + * by reconstructing the split done in soc-pcm.c + */ + for_each_rtd_cpu_dais(rtd, cpu_dai_id, dai) { + if (dai == cpu_dai) { + cpu_dai_found = true; + break; + } + } + + if (!cpu_dai_found) + return -ENODEV; + + ch_mask = 0; + for_each_link_ch_maps(rtd->dai_link, j, ch_maps) { + if (ch_maps->cpu == cpu_dai_id) + ch_mask |= ch_maps->ch_mask; + } + ret = hdac_bus_eml_sdw_map_stream_ch(sof_to_bus(sdev), link_id, cpu_dai->id, - GENMASK(params_channels(params) - 1, 0), + ch_mask, hdac_stream(hext_stream)->stream_tag, substream->stream); if (ret < 0) { diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c index 2445ae7f6b2e9..1506982a56c30 100644 --- a/sound/soc/sof/intel/hda-dsp.c +++ b/sound/soc/sof/intel/hda-dsp.c @@ -681,17 +681,27 @@ static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend) struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata; const struct sof_intel_dsp_desc *chip = hda->desc; struct hdac_bus *bus = sof_to_bus(sdev); + bool imr_lost = false; int ret, j; /* - * The memory used for IMR boot loses its content in deeper than S3 state - * We must not try IMR boot on next power up (as it will fail). - * + * The memory used for IMR boot loses its content in deeper than S3 + * state on CAVS platforms. + * On ACE platforms due to the system architecture the IMR content is + * lost at S3 state already, they are tailored for s2idle use. + * We must not try IMR boot on next power up in these cases as it will + * fail. + */ + if (sdev->system_suspend_target > SOF_SUSPEND_S3 || + (chip->hw_ip_version >= SOF_INTEL_ACE_1_0 && + sdev->system_suspend_target == SOF_SUSPEND_S3)) + imr_lost = true; + + /* * In case of firmware crash or boot failure set the skip_imr_boot to true * as well in order to try to re-load the firmware to do a 'cold' boot. */ - if (sdev->system_suspend_target > SOF_SUSPEND_S3 || - sdev->fw_state == SOF_FW_CRASHED || + if (imr_lost || sdev->fw_state == SOF_FW_CRASHED || sdev->fw_state == SOF_FW_BOOT_FAILED) hda->skip_imr_boot = true; diff --git a/sound/soc/sof/intel/hda-pcm.c b/sound/soc/sof/intel/hda-pcm.c index 18f07364d2198..d7b446f3f973e 100644 --- a/sound/soc/sof/intel/hda-pcm.c +++ b/sound/soc/sof/intel/hda-pcm.c @@ -259,8 +259,37 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev, snd_pcm_hw_constraint_mask64(substream->runtime, SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S32); + /* + * The dsp_max_burst_size_in_ms is the length of the maximum burst size + * of the host DMA in the ALSA buffer. + * + * On playback start the DMA will transfer dsp_max_burst_size_in_ms + * amount of data in one initial burst to fill up the host DMA buffer. + * Consequent DMA burst sizes are shorter and their length can vary. + * To make sure that userspace allocate large enough ALSA buffer we need + * to place a constraint on the buffer time. + * + * On capture the DMA will transfer 1ms chunks. + * + * Exact dsp_max_burst_size_in_ms constraint is racy, so set the + * constraint to a minimum of 2x dsp_max_burst_size_in_ms. + */ + if (spcm->stream[direction].dsp_max_burst_size_in_ms) + snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_BUFFER_TIME, + spcm->stream[direction].dsp_max_burst_size_in_ms * USEC_PER_MSEC * 2, + UINT_MAX); + /* binding pcm substream to hda stream */ substream->runtime->private_data = &dsp_stream->hstream; + + /* + * Reset the llp cache values (they are used for LLP compensation in + * case the counter is not reset) + */ + dsp_stream->pplcllpl = 0; + dsp_stream->pplcllpu = 0; + return 0; } diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c index f2ebadbbcc10e..c603aaf0ca773 100644 --- a/sound/soc/sof/intel/hda-stream.c +++ b/sound/soc/sof/intel/hda-stream.c @@ -1054,3 +1054,73 @@ snd_pcm_uframes_t hda_dsp_stream_get_position(struct hdac_stream *hstream, return pos; } + +#define merge_u64(u32_u, u32_l) (((u64)(u32_u) << 32) | (u32_l)) + +/** + * hda_dsp_get_stream_llp - Retrieve the LLP (Linear Link Position) of the stream + * @sdev: SOF device + * @component: ASoC component + * @substream: PCM substream + * + * Returns the raw Linear Link Position value + */ +u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev, + struct snd_soc_component *component, + struct snd_pcm_substream *substream) +{ + struct hdac_stream *hstream = substream->runtime->private_data; + struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream); + u32 llp_l, llp_u; + + /* + * The pplc_addr have been calculated during probe in + * hda_dsp_stream_init(): + * pplc_addr = sdev->bar[HDA_DSP_PP_BAR] + + * SOF_HDA_PPLC_BASE + + * SOF_HDA_PPLC_MULTI * total_stream + + * SOF_HDA_PPLC_INTERVAL * stream_index + * + * Use this pre-calculated address to avoid repeated re-calculation. + */ + llp_l = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL); + llp_u = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU); + + /* Compensate the LLP counter with the saved offset */ + if (hext_stream->pplcllpl || hext_stream->pplcllpu) + return merge_u64(llp_u, llp_l) - + merge_u64(hext_stream->pplcllpu, hext_stream->pplcllpl); + + return merge_u64(llp_u, llp_l); +} + +/** + * hda_dsp_get_stream_ldp - Retrieve the LDP (Linear DMA Position) of the stream + * @sdev: SOF device + * @component: ASoC component + * @substream: PCM substream + * + * Returns the raw Linear Link Position value + */ +u64 hda_dsp_get_stream_ldp(struct snd_sof_dev *sdev, + struct snd_soc_component *component, + struct snd_pcm_substream *substream) +{ + struct hdac_stream *hstream = substream->runtime->private_data; + struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream); + u32 ldp_l, ldp_u; + + /* + * The pphc_addr have been calculated during probe in + * hda_dsp_stream_init(): + * pphc_addr = sdev->bar[HDA_DSP_PP_BAR] + + * SOF_HDA_PPHC_BASE + + * SOF_HDA_PPHC_INTERVAL * stream_index + * + * Use this pre-calculated address to avoid repeated re-calculation. + */ + ldp_l = readl(hext_stream->pphc_addr + AZX_REG_PPHCLDPL); + ldp_u = readl(hext_stream->pphc_addr + AZX_REG_PPHCLDPU); + + return ((u64)ldp_u << 32) | ldp_l; +} diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h index 1592e27bc14da..efb42117df793 100644 --- a/sound/soc/sof/intel/hda.h +++ b/sound/soc/sof/intel/hda.h @@ -657,6 +657,12 @@ bool hda_dsp_check_stream_irq(struct snd_sof_dev *sdev); snd_pcm_uframes_t hda_dsp_stream_get_position(struct hdac_stream *hstream, int direction, bool can_sleep); +u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev, + struct snd_soc_component *component, + struct snd_pcm_substream *substream); +u64 hda_dsp_get_stream_ldp(struct snd_sof_dev *sdev, + struct snd_soc_component *component, + struct snd_pcm_substream *substream); struct hdac_ext_stream * hda_dsp_stream_get(struct snd_sof_dev *sdev, int direction, u32 flags); diff --git a/sound/soc/sof/intel/lnl.c b/sound/soc/sof/intel/lnl.c index 30712ea05a7a5..d6c4d6cd20b05 100644 --- a/sound/soc/sof/intel/lnl.c +++ b/sound/soc/sof/intel/lnl.c @@ -16,6 +16,7 @@ #include "hda-ipc.h" #include "../sof-audio.h" #include "mtl.h" +#include "lnl.h" #include /* LunarLake ops */ @@ -118,8 +119,6 @@ int sof_lnl_ops_init(struct snd_sof_dev *sdev) sof_lnl_ops.resume = lnl_hda_dsp_resume; sof_lnl_ops.runtime_resume = lnl_hda_dsp_runtime_resume; - sof_lnl_ops.get_stream_position = mtl_dsp_get_stream_hda_link_position; - /* dsp core get/put */ sof_lnl_ops.core_get = mtl_dsp_core_get; sof_lnl_ops.core_put = mtl_dsp_core_put; @@ -178,7 +177,7 @@ const struct sof_intel_dsp_desc lnl_chip_info = { .ipc_ack = MTL_DSP_REG_HFIPCXIDA, .ipc_ack_mask = MTL_DSP_REG_HFIPCXIDA_DONE, .ipc_ctl = MTL_DSP_REG_HFIPCXCTL, - .rom_status_reg = MTL_DSP_ROM_STS, + .rom_status_reg = LNL_DSP_REG_HFDSC, .rom_init_timeout = 300, .ssp_count = MTL_SSP_COUNT, .d0i3_offset = MTL_HDA_VS_D0I3C, diff --git a/sound/soc/sof/intel/lnl.h b/sound/soc/sof/intel/lnl.h new file mode 100644 index 0000000000000..4f4734fe7e089 --- /dev/null +++ b/sound/soc/sof/intel/lnl.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * Copyright(c) 2024 Intel Corporation. All rights reserved. + */ + +#ifndef __SOF_INTEL_LNL_H +#define __SOF_INTEL_LNL_H + +#define LNL_DSP_REG_HFDSC 0x160200 /* DSP core0 status */ +#define LNL_DSP_REG_HFDEC 0x160204 /* DSP core0 error */ + +#endif /* __SOF_INTEL_LNL_H */ diff --git a/sound/soc/sof/intel/mtl.c b/sound/soc/sof/intel/mtl.c index df05dc77b8d5e..05023763080d9 100644 --- a/sound/soc/sof/intel/mtl.c +++ b/sound/soc/sof/intel/mtl.c @@ -439,7 +439,7 @@ int mtl_dsp_cl_init(struct snd_sof_dev *sdev, int stream_tag, bool imr_boot) { struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata; const struct sof_intel_dsp_desc *chip = hda->desc; - unsigned int status; + unsigned int status, target_status; u32 ipc_hdr, flags; char *dump_msg; int ret; @@ -485,13 +485,40 @@ int mtl_dsp_cl_init(struct snd_sof_dev *sdev, int stream_tag, bool imr_boot) mtl_enable_ipc_interrupts(sdev); + if (chip->rom_status_reg == MTL_DSP_ROM_STS) { + /* + * Workaround: when the ROM status register is pointing to + * the SRAM window (MTL_DSP_ROM_STS) the platform cannot catch + * ROM_INIT_DONE because of a very short timing window. + * Follow the recommendations and skip target state waiting. + */ + return 0; + } + /* - * ACE workaround: don't wait for ROM INIT. - * The platform cannot catch ROM_INIT_DONE because of a very short - * timing window. Follow the recommendations and skip this part. + * step 7: + * - Cold/Full boot: wait for ROM init to proceed to download the firmware + * - IMR boot: wait for ROM firmware entered (firmware booted up from IMR) */ + if (imr_boot) + target_status = FSR_STATE_FW_ENTERED; + else + target_status = FSR_STATE_INIT_DONE; - return 0; + ret = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR, + chip->rom_status_reg, status, + (FSR_TO_STATE_CODE(status) == target_status), + HDA_DSP_REG_POLL_INTERVAL_US, + chip->rom_init_timeout * + USEC_PER_MSEC); + + if (!ret) + return 0; + + if (hda->boot_iteration == HDA_FW_BOOT_ATTEMPTS) + dev_err(sdev->dev, + "%s: timeout with rom_status_reg (%#x) read\n", + __func__, chip->rom_status_reg); err: flags = SOF_DBG_DUMP_PCI | SOF_DBG_DUMP_MBOX | SOF_DBG_DUMP_OPTIONAL; @@ -503,6 +530,7 @@ int mtl_dsp_cl_init(struct snd_sof_dev *sdev, int stream_tag, bool imr_boot) dump_msg = kasprintf(GFP_KERNEL, "Boot iteration failed: %d/%d", hda->boot_iteration, HDA_FW_BOOT_ATTEMPTS); snd_sof_dsp_dbg_dump(sdev, dump_msg, flags); + mtl_enable_interrupts(sdev, false); mtl_dsp_core_power_down(sdev, SOF_DSP_PRIMARY_CORE); kfree(dump_msg); @@ -626,18 +654,6 @@ static int mtl_dsp_disable_interrupts(struct snd_sof_dev *sdev) return mtl_enable_interrupts(sdev, false); } -u64 mtl_dsp_get_stream_hda_link_position(struct snd_sof_dev *sdev, - struct snd_soc_component *component, - struct snd_pcm_substream *substream) -{ - struct hdac_stream *hstream = substream->runtime->private_data; - u32 llp_l, llp_u; - - llp_l = snd_sof_dsp_read(sdev, HDA_DSP_HDA_BAR, MTL_PPLCLLPL(hstream->index)); - llp_u = snd_sof_dsp_read(sdev, HDA_DSP_HDA_BAR, MTL_PPLCLLPU(hstream->index)); - return ((u64)llp_u << 32) | llp_l; -} - int mtl_dsp_core_get(struct snd_sof_dev *sdev, int core) { const struct sof_ipc_pm_ops *pm_ops = sdev->ipc->ops->pm; @@ -707,8 +723,6 @@ int sof_mtl_ops_init(struct snd_sof_dev *sdev) sof_mtl_ops.core_get = mtl_dsp_core_get; sof_mtl_ops.core_put = mtl_dsp_core_put; - sof_mtl_ops.get_stream_position = mtl_dsp_get_stream_hda_link_position; - sdev->private = kzalloc(sizeof(struct sof_ipc4_fw_data), GFP_KERNEL); if (!sdev->private) return -ENOMEM; @@ -741,7 +755,7 @@ const struct sof_intel_dsp_desc mtl_chip_info = { .ipc_ack = MTL_DSP_REG_HFIPCXIDA, .ipc_ack_mask = MTL_DSP_REG_HFIPCXIDA_DONE, .ipc_ctl = MTL_DSP_REG_HFIPCXCTL, - .rom_status_reg = MTL_DSP_ROM_STS, + .rom_status_reg = MTL_DSP_REG_HFFLGPXQWY, .rom_init_timeout = 300, .ssp_count = MTL_SSP_COUNT, .ssp_base_offset = CNL_SSP_BASE_OFFSET, @@ -769,7 +783,7 @@ const struct sof_intel_dsp_desc arl_s_chip_info = { .ipc_ack = MTL_DSP_REG_HFIPCXIDA, .ipc_ack_mask = MTL_DSP_REG_HFIPCXIDA_DONE, .ipc_ctl = MTL_DSP_REG_HFIPCXCTL, - .rom_status_reg = MTL_DSP_ROM_STS, + .rom_status_reg = MTL_DSP_REG_HFFLGPXQWY, .rom_init_timeout = 300, .ssp_count = MTL_SSP_COUNT, .ssp_base_offset = CNL_SSP_BASE_OFFSET, diff --git a/sound/soc/sof/intel/mtl.h b/sound/soc/sof/intel/mtl.h index cc5a1f46fd095..3c56427a966bf 100644 --- a/sound/soc/sof/intel/mtl.h +++ b/sound/soc/sof/intel/mtl.h @@ -6,12 +6,6 @@ * Copyright(c) 2020-2022 Intel Corporation. All rights reserved. */ -/* HDA Registers */ -#define MTL_PPLCLLPL_BASE 0x948 -#define MTL_PPLCLLPU_STRIDE 0x10 -#define MTL_PPLCLLPL(x) (MTL_PPLCLLPL_BASE + (x) * MTL_PPLCLLPU_STRIDE) -#define MTL_PPLCLLPU(x) (MTL_PPLCLLPL_BASE + 0x4 + (x) * MTL_PPLCLLPU_STRIDE) - /* DSP Registers */ #define MTL_HFDSSCS 0x1000 #define MTL_HFDSSCS_SPA_MASK BIT(16) @@ -76,8 +70,8 @@ #define MTL_DSP_ROM_STS MTL_SRAM_WINDOW_OFFSET(0) /* ROM status */ #define MTL_DSP_ROM_ERROR (MTL_SRAM_WINDOW_OFFSET(0) + 0x4) /* ROM error code */ -#define MTL_DSP_REG_HFFLGPXQWY 0x163200 /* ROM debug status */ -#define MTL_DSP_REG_HFFLGPXQWY_ERROR 0x163204 /* ROM debug error code */ +#define MTL_DSP_REG_HFFLGPXQWY 0x163200 /* DSP core0 status */ +#define MTL_DSP_REG_HFFLGPXQWY_ERROR 0x163204 /* DSP core0 error */ #define MTL_DSP_REG_HfIMRIS1 0x162088 #define MTL_DSP_REG_HfIMRIS1_IU_MASK BIT(0) @@ -103,9 +97,5 @@ int mtl_dsp_ipc_get_window_offset(struct snd_sof_dev *sdev, u32 id); void mtl_ipc_dump(struct snd_sof_dev *sdev); -u64 mtl_dsp_get_stream_hda_link_position(struct snd_sof_dev *sdev, - struct snd_soc_component *component, - struct snd_pcm_substream *substream); - int mtl_dsp_core_get(struct snd_sof_dev *sdev, int core); int mtl_dsp_core_put(struct snd_sof_dev *sdev, int core); diff --git a/sound/soc/sof/intel/pci-lnl.c b/sound/soc/sof/intel/pci-lnl.c index b26ffe767fab5..b14e508f1f315 100644 --- a/sound/soc/sof/intel/pci-lnl.c +++ b/sound/soc/sof/intel/pci-lnl.c @@ -35,6 +35,9 @@ static const struct sof_dev_desc lnl_desc = { .default_fw_path = { [SOF_IPC_TYPE_4] = "intel/sof-ipc4/lnl", }, + .default_lib_path = { + [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/lnl", + }, .default_tplg_path = { [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg", }, diff --git a/sound/soc/sof/ipc3-loader.c b/sound/soc/sof/ipc3-loader.c index 28218766d2114..6e3ef06721106 100644 --- a/sound/soc/sof/ipc3-loader.c +++ b/sound/soc/sof/ipc3-loader.c @@ -148,6 +148,8 @@ static size_t sof_ipc3_fw_parse_ext_man(struct snd_sof_dev *sdev) head = (struct sof_ext_man_header *)fw->data; remaining = head->full_size - head->header_size; + if (remaining < 0 || remaining > sdev->basefw.fw->size) + return -EINVAL; ext_man_size = ipc3_fw_ext_man_size(sdev, fw); /* Assert firmware starts with extended manifest */ diff --git a/sound/soc/sof/ipc3-pcm.c b/sound/soc/sof/ipc3-pcm.c index 330f04bcd75d2..a7cf52fd76455 100644 --- a/sound/soc/sof/ipc3-pcm.c +++ b/sound/soc/sof/ipc3-pcm.c @@ -409,4 +409,5 @@ const struct sof_ipc_pcm_ops ipc3_pcm_ops = { .trigger = sof_ipc3_pcm_trigger, .dai_link_fixup = sof_ipc3_pcm_dai_link_fixup, .reset_hw_params_during_stop = true, + .d0i3_supported_in_s0ix = true, }; diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c index 07eb5c6d4adf3..d07c1b06207a5 100644 --- a/sound/soc/sof/ipc4-pcm.c +++ b/sound/soc/sof/ipc4-pcm.c @@ -15,6 +15,44 @@ #include "ipc4-topology.h" #include "ipc4-fw-reg.h" +/** + * struct sof_ipc4_timestamp_info - IPC4 timestamp info + * @host_copier: the host copier of the pcm stream + * @dai_copier: the dai copier of the pcm stream + * @stream_start_offset: reported by fw in memory window (converted to frames) + * @stream_end_offset: reported by fw in memory window (converted to frames) + * @llp_offset: llp offset in memory window + * @boundary: wrap boundary should be used for the LLP frame counter + * @delay: Calculated and stored in pointer callback. The stored value is + * returned in the delay callback. + */ +struct sof_ipc4_timestamp_info { + struct sof_ipc4_copier *host_copier; + struct sof_ipc4_copier *dai_copier; + u64 stream_start_offset; + u64 stream_end_offset; + u32 llp_offset; + + u64 boundary; + snd_pcm_sframes_t delay; +}; + +/** + * struct sof_ipc4_pcm_stream_priv - IPC4 specific private data + * @time_info: pointer to time info struct if it is supported, otherwise NULL + */ +struct sof_ipc4_pcm_stream_priv { + struct sof_ipc4_timestamp_info *time_info; +}; + +static inline struct sof_ipc4_timestamp_info * +sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps) +{ + struct sof_ipc4_pcm_stream_priv *stream_priv = sps->private; + + return stream_priv->time_info; +} + static int sof_ipc4_set_multi_pipeline_state(struct snd_sof_dev *sdev, u32 state, struct ipc4_pipeline_set_state_data *trigger_list) { @@ -406,8 +444,19 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, } /* return if this is the final state */ - if (state == SOF_IPC4_PIPE_PAUSED) + if (state == SOF_IPC4_PIPE_PAUSED) { + struct sof_ipc4_timestamp_info *time_info; + + /* + * Invalidate the stream_start_offset to make sure that it is + * going to be updated if the stream resumes + */ + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); + if (time_info) + time_info->stream_start_offset = SOF_IPC4_INVALID_STREAM_POSITION; + goto free; + } skip_pause_transition: /* else set the RUNNING/RESET state in the DSP */ ret = sof_ipc4_set_multi_pipeline_state(sdev, state, trigger_list); @@ -447,14 +496,12 @@ static int sof_ipc4_pcm_trigger(struct snd_soc_component *component, /* determine the pipeline state */ switch (cmd) { - case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - state = SOF_IPC4_PIPE_PAUSED; - break; case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_START: state = SOF_IPC4_PIPE_RUNNING; break; + case SNDRV_PCM_TRIGGER_PAUSE_PUSH: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_STOP: state = SOF_IPC4_PIPE_PAUSED; @@ -658,12 +705,16 @@ static int sof_ipc4_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd, static void sof_ipc4_pcm_free(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm) { struct snd_sof_pcm_stream_pipeline_list *pipeline_list; + struct sof_ipc4_pcm_stream_priv *stream_priv; int stream; for_each_pcm_streams(stream) { pipeline_list = &spcm->stream[stream].pipeline_list; kfree(pipeline_list->pipelines); pipeline_list->pipelines = NULL; + + stream_priv = spcm->stream[stream].private; + kfree(stream_priv->time_info); kfree(spcm->stream[stream].private); spcm->stream[stream].private = NULL; } @@ -673,7 +724,8 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm { struct snd_sof_pcm_stream_pipeline_list *pipeline_list; struct sof_ipc4_fw_data *ipc4_data = sdev->private; - struct sof_ipc4_timestamp_info *stream_info; + struct sof_ipc4_pcm_stream_priv *stream_priv; + struct sof_ipc4_timestamp_info *time_info; bool support_info = true; u32 abi_version; u32 abi_offset; @@ -686,6 +738,10 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm if (abi_version < SOF_IPC4_FW_REGS_ABI_VER) support_info = false; + /* For delay reporting the get_host_byte_counter callback is needed */ + if (!sof_ops(sdev) || !sof_ops(sdev)->get_host_byte_counter) + support_info = false; + for_each_pcm_streams(stream) { pipeline_list = &spcm->stream[stream].pipeline_list; @@ -697,33 +753,41 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm return -ENOMEM; } + stream_priv = kzalloc(sizeof(*stream_priv), GFP_KERNEL); + if (!stream_priv) { + sof_ipc4_pcm_free(sdev, spcm); + return -ENOMEM; + } + + spcm->stream[stream].private = stream_priv; + if (!support_info) continue; - stream_info = kzalloc(sizeof(*stream_info), GFP_KERNEL); - if (!stream_info) { + time_info = kzalloc(sizeof(*time_info), GFP_KERNEL); + if (!time_info) { sof_ipc4_pcm_free(sdev, spcm); return -ENOMEM; } - spcm->stream[stream].private = stream_info; + stream_priv->time_info = time_info; } return 0; } -static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *spcm) +static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *sps) { struct sof_ipc4_copier *host_copier = NULL; struct sof_ipc4_copier *dai_copier = NULL; struct sof_ipc4_llp_reading_slot llp_slot; - struct sof_ipc4_timestamp_info *info; + struct sof_ipc4_timestamp_info *time_info; struct snd_soc_dapm_widget *widget; struct snd_sof_dai *dai; int i; /* find host & dai to locate info in memory window */ - for_each_dapm_widgets(spcm->list, i, widget) { + for_each_dapm_widgets(sps->list, i, widget) { struct snd_sof_widget *swidget = widget->dobj.private; if (!swidget) @@ -743,44 +807,44 @@ static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pc return; } - info = spcm->private; - info->host_copier = host_copier; - info->dai_copier = dai_copier; - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_gpdma_reading_slots) + - sdev->fw_info_box.offset; + time_info = sof_ipc4_sps_to_time_info(sps); + time_info->host_copier = host_copier; + time_info->dai_copier = dai_copier; + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_gpdma_reading_slots) + sdev->fw_info_box.offset; /* find llp slot used by current dai */ for (i = 0; i < SOF_IPC4_MAX_LLP_GPDMA_READING_SLOTS; i++) { - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id == dai_copier->data.gtw_cfg.node_id) break; - info->llp_offset += sizeof(llp_slot); + time_info->llp_offset += sizeof(llp_slot); } if (i < SOF_IPC4_MAX_LLP_GPDMA_READING_SLOTS) return; /* if no llp gpdma slot is used, check aggregated sdw slot */ - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_sndw_reading_slots) + - sdev->fw_info_box.offset; + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_sndw_reading_slots) + sdev->fw_info_box.offset; for (i = 0; i < SOF_IPC4_MAX_LLP_SNDW_READING_SLOTS; i++) { - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id == dai_copier->data.gtw_cfg.node_id) break; - info->llp_offset += sizeof(llp_slot); + time_info->llp_offset += sizeof(llp_slot); } if (i < SOF_IPC4_MAX_LLP_SNDW_READING_SLOTS) return; /* check EVAD slot */ - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_evad_reading_slot) + - sdev->fw_info_box.offset; - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_evad_reading_slot) + sdev->fw_info_box.offset; + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id) - info->llp_offset = 0; + time_info->llp_offset = 0; } static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, @@ -797,7 +861,7 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, if (!spcm) return -EINVAL; - time_info = spcm->stream[substream->stream].private; + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); /* delay calculation is not supported by current fw_reg ABI */ if (!time_info) return 0; @@ -812,13 +876,12 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream, - struct snd_sof_pcm_stream *stream, + struct snd_sof_pcm_stream *sps, struct sof_ipc4_timestamp_info *time_info) { struct sof_ipc4_copier *host_copier = time_info->host_copier; struct sof_ipc4_copier *dai_copier = time_info->dai_copier; struct sof_ipc4_pipeline_registers ppl_reg; - u64 stream_start_position; u32 dai_sample_size; u32 ch, node_index; u32 offset; @@ -835,38 +898,51 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, if (ppl_reg.stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION) return -EINVAL; - stream_start_position = ppl_reg.stream_start_offset; ch = dai_copier->data.out_format.fmt_cfg; ch = SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(ch); dai_sample_size = (dai_copier->data.out_format.bit_depth >> 3) * ch; - /* convert offset to sample count */ - do_div(stream_start_position, dai_sample_size); - time_info->stream_start_offset = stream_start_position; + + /* convert offsets to frame count */ + time_info->stream_start_offset = ppl_reg.stream_start_offset; + do_div(time_info->stream_start_offset, dai_sample_size); + time_info->stream_end_offset = ppl_reg.stream_end_offset; + do_div(time_info->stream_end_offset, dai_sample_size); + + /* + * Calculate the wrap boundary need to be used for delay calculation + * The host counter is in bytes, it will wrap earlier than the frames + * based link counter. + */ + time_info->boundary = div64_u64(~((u64)0), + frames_to_bytes(substream->runtime, 1)); + /* Initialize the delay value to 0 (no delay) */ + time_info->delay = 0; return 0; } -static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component, - struct snd_pcm_substream *substream) +static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, + struct snd_pcm_substream *substream, + snd_pcm_uframes_t *pointer) { struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component); struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct sof_ipc4_timestamp_info *time_info; struct sof_ipc4_llp_reading_slot llp; - snd_pcm_uframes_t head_ptr, tail_ptr; - struct snd_sof_pcm_stream *stream; + snd_pcm_uframes_t head_cnt, tail_cnt; + struct snd_sof_pcm_stream *sps; + u64 dai_cnt, host_cnt, host_ptr; struct snd_sof_pcm *spcm; - u64 tmp_ptr; int ret; spcm = snd_sof_find_spcm_dai(component, rtd); if (!spcm) - return 0; + return -EOPNOTSUPP; - stream = &spcm->stream[substream->stream]; - time_info = stream->private; + sps = &spcm->stream[substream->stream]; + time_info = sof_ipc4_sps_to_time_info(sps); if (!time_info) - return 0; + return -EOPNOTSUPP; /* * stream_start_offset is updated to memory window by FW based on @@ -874,47 +950,116 @@ static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component, * the statistics is complete. And it will not change after the first initiailization. */ if (time_info->stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION) { - ret = sof_ipc4_get_stream_start_offset(sdev, substream, stream, time_info); + ret = sof_ipc4_get_stream_start_offset(sdev, substream, sps, time_info); if (ret < 0) - return 0; + return -EOPNOTSUPP; } + /* For delay calculation we need the host counter */ + host_cnt = snd_sof_pcm_get_host_byte_counter(sdev, component, substream); + host_ptr = host_cnt; + + /* convert the host_cnt to frames */ + host_cnt = div64_u64(host_cnt, frames_to_bytes(substream->runtime, 1)); + /* - * HDaudio links don't support the LLP counter reported by firmware - * the link position is read directly from hardware registers. + * If the LLP counter is not reported by firmware in the SRAM window + * then read the dai (link) counter via host accessible means if + * available. */ if (!time_info->llp_offset) { - tmp_ptr = snd_sof_pcm_get_stream_position(sdev, component, substream); - if (!tmp_ptr) - return 0; + dai_cnt = snd_sof_pcm_get_dai_frame_counter(sdev, component, substream); + if (!dai_cnt) + return -EOPNOTSUPP; } else { sof_mailbox_read(sdev, time_info->llp_offset, &llp, sizeof(llp)); - tmp_ptr = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l; + dai_cnt = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l; } + dai_cnt += time_info->stream_end_offset; - /* In two cases dai dma position is not accurate + /* In two cases dai dma counter is not accurate * (1) dai pipeline is started before host pipeline - * (2) multiple streams mixed into one. Each stream has the same dai dma position + * (2) multiple streams mixed into one. Each stream has the same dai dma + * counter * - * Firmware calculates correct stream_start_offset for all cases including above two. - * Driver subtracts stream_start_offset from dai dma position to get accurate one + * Firmware calculates correct stream_start_offset for all cases + * including above two. + * Driver subtracts stream_start_offset from dai dma counter to get + * accurate one */ - tmp_ptr -= time_info->stream_start_offset; - /* Calculate the delay taking into account that both pointer can wrap */ - div64_u64_rem(tmp_ptr, substream->runtime->boundary, &tmp_ptr); + /* + * On stream start the dai counter might not yet have reached the + * stream_start_offset value which means that no frames have left the + * DSP yet from the audio stream (on playback, capture streams have + * offset of 0 as we start capturing right away). + * In this case we need to adjust the distance between the counters by + * increasing the host counter by (offset - dai_counter). + * Otherwise the dai_counter needs to be adjusted to reflect the number + * of valid frames passed on the DAI side. + * + * The delay is the difference between the counters on the two + * sides of the DSP. + */ + if (dai_cnt < time_info->stream_start_offset) { + host_cnt += time_info->stream_start_offset - dai_cnt; + dai_cnt = 0; + } else { + dai_cnt -= time_info->stream_start_offset; + } + + /* Wrap the dai counter at the boundary where the host counter wraps */ + div64_u64_rem(dai_cnt, time_info->boundary, &dai_cnt); + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { - head_ptr = substream->runtime->status->hw_ptr; - tail_ptr = tmp_ptr; + head_cnt = host_cnt; + tail_cnt = dai_cnt; } else { - head_ptr = tmp_ptr; - tail_ptr = substream->runtime->status->hw_ptr; + head_cnt = dai_cnt; + tail_cnt = host_cnt; } - if (head_ptr < tail_ptr) - return substream->runtime->boundary - tail_ptr + head_ptr; + if (head_cnt < tail_cnt) { + time_info->delay = time_info->boundary - tail_cnt + head_cnt; + goto out; + } + + time_info->delay = head_cnt - tail_cnt; + +out: + /* + * Convert the host byte counter to PCM pointer which wraps in buffer + * and it is in frames + */ + div64_u64_rem(host_ptr, snd_pcm_lib_buffer_bytes(substream), &host_ptr); + *pointer = bytes_to_frames(substream->runtime, host_ptr); + + return 0; +} + +static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component, + struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct sof_ipc4_timestamp_info *time_info; + struct snd_sof_pcm *spcm; + + spcm = snd_sof_find_spcm_dai(component, rtd); + if (!spcm) + return 0; + + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); + /* + * Report the stored delay value calculated in the pointer callback. + * In the unlikely event that the calculation was skipped/aborted, the + * default 0 delay returned. + */ + if (time_info) + return time_info->delay; + + /* No delay information available, report 0 as delay */ + return 0; - return head_ptr - tail_ptr; } const struct sof_ipc_pcm_ops ipc4_pcm_ops = { @@ -924,6 +1069,7 @@ const struct sof_ipc_pcm_ops ipc4_pcm_ops = { .dai_link_fixup = sof_ipc4_pcm_dai_link_fixup, .pcm_setup = sof_ipc4_pcm_setup, .pcm_free = sof_ipc4_pcm_free, + .pointer = sof_ipc4_pcm_pointer, .delay = sof_ipc4_pcm_delay, .ipc_first_on_start = true, .platform_stop_during_hw_free = true, diff --git a/sound/soc/sof/ipc4-priv.h b/sound/soc/sof/ipc4-priv.h index 1d39836d5efac..9db9002b44d68 100644 --- a/sound/soc/sof/ipc4-priv.h +++ b/sound/soc/sof/ipc4-priv.h @@ -88,20 +88,6 @@ struct sof_ipc4_fw_data { struct mutex pipeline_state_mutex; /* protect pipeline triggers, ref counts and states */ }; -/** - * struct sof_ipc4_timestamp_info - IPC4 timestamp info - * @host_copier: the host copier of the pcm stream - * @dai_copier: the dai copier of the pcm stream - * @stream_start_offset: reported by fw in memory window - * @llp_offset: llp offset in memory window - */ -struct sof_ipc4_timestamp_info { - struct sof_ipc4_copier *host_copier; - struct sof_ipc4_copier *dai_copier; - u64 stream_start_offset; - u32 llp_offset; -}; - extern const struct sof_ipc_fw_loader_ops ipc4_loader_ops; extern const struct sof_ipc_tplg_ops ipc4_tplg_ops; extern const struct sof_ipc_tplg_control_ops tplg_ipc4_control_ops; diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index f779156fe0e60..df774f26ebabf 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -217,6 +217,14 @@ sof_ipc4_get_input_pin_audio_fmt(struct snd_sof_widget *swidget, int pin_index) } process = swidget->private; + + /* + * For process modules without base config extension, base module config + * format is used for all input pins + */ + if (process->init_config != SOF_IPC4_MODULE_INIT_CONFIG_TYPE_BASE_CFG_WITH_EXT) + return &process->base_config.audio_fmt; + base_cfg_ext = process->base_config_ext; /* @@ -412,8 +420,9 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget) struct sof_ipc4_available_audio_format *available_fmt; struct snd_soc_component *scomp = swidget->scomp; struct sof_ipc4_copier *ipc4_copier; + struct snd_sof_pcm *spcm; int node_type = 0; - int ret; + int ret, dir; ipc4_copier = kzalloc(sizeof(*ipc4_copier), GFP_KERNEL); if (!ipc4_copier) @@ -447,6 +456,25 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget) } dev_dbg(scomp->dev, "host copier '%s' node_type %u\n", swidget->widget->name, node_type); + spcm = snd_sof_find_spcm_comp(scomp, swidget->comp_id, &dir); + if (!spcm) + goto skip_gtw_cfg; + + if (dir == SNDRV_PCM_STREAM_PLAYBACK) { + struct snd_sof_pcm_stream *sps = &spcm->stream[dir]; + + sof_update_ipc_object(scomp, &sps->dsp_max_burst_size_in_ms, + SOF_COPIER_DEEP_BUFFER_TOKENS, + swidget->tuples, + swidget->num_tuples, sizeof(u32), 1); + /* Set default DMA buffer size if it is not specified in topology */ + if (!sps->dsp_max_burst_size_in_ms) + sps->dsp_max_burst_size_in_ms = SOF_IPC4_MIN_DMA_BUFFER_SIZE; + } else { + /* Capture data is copied from DSP to host in 1ms bursts */ + spcm->stream[dir].dsp_max_burst_size_in_ms = 1; + } + skip_gtw_cfg: ipc4_copier->gtw_attr = kzalloc(sizeof(*ipc4_copier->gtw_attr), GFP_KERNEL); if (!ipc4_copier->gtw_attr) { diff --git a/sound/soc/sof/ops.h b/sound/soc/sof/ops.h index 6538d9f4fe96e..2505a1e1ce340 100644 --- a/sound/soc/sof/ops.h +++ b/sound/soc/sof/ops.h @@ -523,12 +523,26 @@ static inline int snd_sof_pcm_platform_ack(struct snd_sof_dev *sdev, return 0; } -static inline u64 snd_sof_pcm_get_stream_position(struct snd_sof_dev *sdev, - struct snd_soc_component *component, - struct snd_pcm_substream *substream) +static inline u64 +snd_sof_pcm_get_dai_frame_counter(struct snd_sof_dev *sdev, + struct snd_soc_component *component, + struct snd_pcm_substream *substream) { - if (sof_ops(sdev) && sof_ops(sdev)->get_stream_position) - return sof_ops(sdev)->get_stream_position(sdev, component, substream); + if (sof_ops(sdev) && sof_ops(sdev)->get_dai_frame_counter) + return sof_ops(sdev)->get_dai_frame_counter(sdev, component, + substream); + + return 0; +} + +static inline u64 +snd_sof_pcm_get_host_byte_counter(struct snd_sof_dev *sdev, + struct snd_soc_component *component, + struct snd_pcm_substream *substream) +{ + if (sof_ops(sdev) && sof_ops(sdev)->get_host_byte_counter) + return sof_ops(sdev)->get_host_byte_counter(sdev, component, + substream); return 0; } diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index 33d576b176478..8804e00e7251b 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -325,14 +325,13 @@ static int sof_pcm_trigger(struct snd_soc_component *component, ipc_first = true; break; case SNDRV_PCM_TRIGGER_SUSPEND: - if (sdev->system_suspend_target == SOF_SUSPEND_S0IX && + /* + * If DSP D0I3 is allowed during S0iX, set the suspend_ignored flag for + * D0I3-compatible streams to keep the firmware pipeline running + */ + if (pcm_ops && pcm_ops->d0i3_supported_in_s0ix && + sdev->system_suspend_target == SOF_SUSPEND_S0IX && spcm->stream[substream->stream].d0i3_compatible) { - /* - * trap the event, not sending trigger stop to - * prevent the FW pipelines from being stopped, - * and mark the flag to ignore the upcoming DAPM - * PM events. - */ spcm->stream[substream->stream].suspend_ignored = true; return 0; } @@ -388,13 +387,21 @@ static snd_pcm_uframes_t sof_pcm_pointer(struct snd_soc_component *component, { struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component); + const struct sof_ipc_pcm_ops *pcm_ops = sof_ipc_get_ops(sdev, pcm); struct snd_sof_pcm *spcm; snd_pcm_uframes_t host, dai; + int ret = -EOPNOTSUPP; /* nothing to do for BE */ if (rtd->dai_link->no_pcm) return 0; + if (pcm_ops && pcm_ops->pointer) + ret = pcm_ops->pointer(component, substream, &host); + + if (ret != -EOPNOTSUPP) + return ret ? ret : host; + /* use dsp ops pointer callback directly if set */ if (sof_ops(sdev)->pcm_pointer) return sof_ops(sdev)->pcm_pointer(sdev, substream); diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h index 8874ee5f557fb..05e2a899d746c 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -103,7 +103,10 @@ struct snd_sof_dai_config_data { * additional memory in the SOF PCM stream structure * @pcm_free: Function pointer for PCM free that can be used for freeing any * additional memory in the SOF PCM stream structure - * @delay: Function pointer for pcm delay calculation + * @pointer: Function pointer for pcm pointer + * Note: the @pointer callback may return -EOPNOTSUPP which should be + * handled in a same way as if the callback is not provided + * @delay: Function pointer for pcm delay reporting * @reset_hw_params_during_stop: Flag indicating whether the hw_params should be reset during the * STOP pcm trigger * @ipc_first_on_start: Send IPC before invoking platform trigger during @@ -113,6 +116,7 @@ struct snd_sof_dai_config_data { * triggers. The FW keeps the host DMA running in this case and * therefore the host must do the same and should stop the DMA during * hw_free. + * @d0i3_supported_in_s0ix: Allow DSP D0I3 during S0iX */ struct sof_ipc_pcm_ops { int (*hw_params)(struct snd_soc_component *component, struct snd_pcm_substream *substream, @@ -124,11 +128,15 @@ struct sof_ipc_pcm_ops { int (*dai_link_fixup)(struct snd_soc_pcm_runtime *rtd, struct snd_pcm_hw_params *params); int (*pcm_setup)(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm); void (*pcm_free)(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm); + int (*pointer)(struct snd_soc_component *component, + struct snd_pcm_substream *substream, + snd_pcm_uframes_t *pointer); snd_pcm_sframes_t (*delay)(struct snd_soc_component *component, struct snd_pcm_substream *substream); bool reset_hw_params_during_stop; bool ipc_first_on_start; bool platform_stop_during_hw_free; + bool d0i3_supported_in_s0ix; }; /** @@ -321,6 +329,7 @@ struct snd_sof_pcm_stream { struct work_struct period_elapsed_work; struct snd_soc_dapm_widget_list *list; /* list of connected DAPM widgets */ bool d0i3_compatible; /* DSP can be in D0I3 when this pcm is opened */ + unsigned int dsp_max_burst_size_in_ms; /* The maximum size of the host DMA burst in ms */ /* * flag to indicate that the DSP pipelines should be kept * active or not while suspending the stream diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h index 6d7897bf96075..09eb2de445fee 100644 --- a/sound/soc/sof/sof-priv.h +++ b/sound/soc/sof/sof-priv.h @@ -255,13 +255,25 @@ struct snd_sof_dsp_ops { int (*pcm_ack)(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream); /* optional */ /* - * optional callback to retrieve the link DMA position for the substream - * when the position is not reported in the shared SRAM windows but - * instead from a host-accessible hardware counter. + * optional callback to retrieve the number of frames left/arrived from/to + * the DSP on the DAI side (link/codec/DMIC/etc). + * + * The callback is used when the firmware does not provide this information + * via the shared SRAM window and it can be retrieved by host. */ - u64 (*get_stream_position)(struct snd_sof_dev *sdev, - struct snd_soc_component *component, - struct snd_pcm_substream *substream); /* optional */ + u64 (*get_dai_frame_counter)(struct snd_sof_dev *sdev, + struct snd_soc_component *component, + struct snd_pcm_substream *substream); /* optional */ + + /* + * Optional callback to retrieve the number of bytes left/arrived from/to + * the DSP on the host side (bytes between host ALSA buffer and DSP). + * + * The callback is needed for ALSA delay reporting. + */ + u64 (*get_host_byte_counter)(struct snd_sof_dev *sdev, + struct snd_soc_component *component, + struct snd_pcm_substream *substream); /* optional */ /* host read DSP stream data */ int (*ipc_msg_data)(struct snd_sof_dev *sdev, diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c index aa37c4ab0adbd..21cd41fec7a9c 100644 --- a/sound/soc/tegra/tegra186_dspk.c +++ b/sound/soc/tegra/tegra186_dspk.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only +// SPDX-FileCopyrightText: Copyright (c) 2020-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved. // // tegra186_dspk.c - Tegra186 DSPK driver -// -// Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved. #include #include @@ -241,14 +240,14 @@ static int tegra186_dspk_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - cif_conf.client_bits = TEGRA_ACIF_BITS_24; - switch (params_format(params)) { case SNDRV_PCM_FORMAT_S16_LE: cif_conf.audio_bits = TEGRA_ACIF_BITS_16; + cif_conf.client_bits = TEGRA_ACIF_BITS_16; break; case SNDRV_PCM_FORMAT_S32_LE: cif_conf.audio_bits = TEGRA_ACIF_BITS_32; + cif_conf.client_bits = TEGRA_ACIF_BITS_24; break; default: dev_err(dev, "unsupported format!\n"); diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c index b892d66f78470..1e760c3155213 100644 --- a/sound/soc/ti/davinci-mcasp.c +++ b/sound/soc/ti/davinci-mcasp.c @@ -2417,12 +2417,6 @@ static int davinci_mcasp_probe(struct platform_device *pdev) mcasp_reparent_fck(pdev); - ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component, - &davinci_mcasp_dai[mcasp->op_mode], 1); - - if (ret != 0) - goto err; - ret = davinci_mcasp_get_dma_type(mcasp); switch (ret) { case PCM_EDMA: @@ -2449,6 +2443,12 @@ static int davinci_mcasp_probe(struct platform_device *pdev) goto err; } + ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component, + &davinci_mcasp_dai[mcasp->op_mode], 1); + + if (ret != 0) + goto err; + no_audio: ret = davinci_mcasp_init_gpiochip(mcasp); if (ret) { diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index b67617b68e509..f4437015d43a7 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -202,7 +202,7 @@ int line6_send_raw_message_async(struct usb_line6 *line6, const char *buffer, struct urb *urb; /* create message: */ - msg = kmalloc(sizeof(struct message), GFP_ATOMIC); + msg = kzalloc(sizeof(struct message), GFP_ATOMIC); if (msg == NULL) return -ENOMEM; @@ -688,7 +688,7 @@ static int line6_init_cap_control(struct usb_line6 *line6) int ret; /* initialize USB buffers: */ - line6->buffer_listen = kmalloc(LINE6_BUFSIZE_LISTEN, GFP_KERNEL); + line6->buffer_listen = kzalloc(LINE6_BUFSIZE_LISTEN, GFP_KERNEL); if (!line6->buffer_listen) return -ENOMEM; @@ -697,7 +697,7 @@ static int line6_init_cap_control(struct usb_line6 *line6) return -ENOMEM; if (line6->properties->capabilities & LINE6_CAP_CONTROL_MIDI) { - line6->buffer_message = kmalloc(LINE6_MIDI_MESSAGE_MAXLEN, GFP_KERNEL); + line6->buffer_message = kzalloc(LINE6_MIDI_MESSAGE_MAXLEN, GFP_KERNEL); if (!line6->buffer_message) return -ENOMEM; diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index 6de605a601e5f..bd114be537d7a 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -173,7 +173,12 @@ /* some gui mixers can't handle negative ctl values */ #define SCARLETT2_VOLUME_BIAS 127 -#define SCARLETT2_GAIN_BIAS 70 + +/* maximum preamp input gain and value + * values are from 0 to 70, preamp gain is from 0 to 69 dB + */ +#define SCARLETT2_MAX_GAIN_VALUE 70 +#define SCARLETT2_MAX_GAIN_DB 69 /* mixer range from -80dB to +6dB in 0.5dB steps */ #define SCARLETT2_MIXER_MIN_DB -80 @@ -284,14 +289,22 @@ static const char *const scarlett2_dim_mute_names[SCARLETT2_DIM_MUTE_COUNT] = { "Mute Playback Switch", "Dim Playback Switch" }; -/* Autogain Status Values */ -enum { - SCARLETT2_AUTOGAIN_STATUS_STOPPED, - SCARLETT2_AUTOGAIN_STATUS_RUNNING, - SCARLETT2_AUTOGAIN_STATUS_FAILED, - SCARLETT2_AUTOGAIN_STATUS_CANCELLED, - SCARLETT2_AUTOGAIN_STATUS_UNKNOWN, - SCARLETT2_AUTOGAIN_STATUS_COUNT +/* The autogain_status is set based on the autogain_switch and + * raw_autogain_status values. + * + * If autogain_switch is set, autogain_status is set to 0 (Running). + * The other status values are from the raw_autogain_status value + 1. + */ +static const char *const scarlett2_autogain_status_texts[] = { + "Running", + "Success", + "SuccessDRover", + "WarnMinGainLimit", + "FailDRunder", + "FailMaxGainLimit", + "FailClipped", + "Cancelled", + "Invalid" }; /* Power Status Values */ @@ -415,7 +428,7 @@ enum { SCARLETT2_CONFIG_INPUT_SELECT_SWITCH, SCARLETT2_CONFIG_INPUT_LINK_SWITCH, SCARLETT2_CONFIG_POWER_EXT, - SCARLETT2_CONFIG_POWER_STATUS, + SCARLETT2_CONFIG_POWER_LOW, SCARLETT2_CONFIG_PCM_INPUT_SWITCH, SCARLETT2_CONFIG_DIRECT_MONITOR_GAIN, SCARLETT2_CONFIG_COUNT @@ -723,8 +736,8 @@ static const struct scarlett2_config_set scarlett2_config_set_gen4_4i4 = { [SCARLETT2_CONFIG_POWER_EXT] = { .offset = 0x168 }, - [SCARLETT2_CONFIG_POWER_STATUS] = { - .offset = 0x66 } + [SCARLETT2_CONFIG_POWER_LOW] = { + .offset = 0x16d } } }; @@ -2835,9 +2848,9 @@ static int scarlett2_autogain_is_running(struct scarlett2_data *private) { int i; + /* autogain_status[] is 0 if autogain is running */ for (i = 0; i < private->info->gain_input_count; i++) - if (private->autogain_status[i] == - SCARLETT2_AUTOGAIN_STATUS_RUNNING) + if (!private->autogain_status[i]) return 1; return 0; @@ -2867,25 +2880,25 @@ static int scarlett2_update_autogain(struct usb_mixer_interface *mixer) return err; /* Translate autogain_switch and raw_autogain_status into - * autogain_status + * autogain_status. + * + * When autogain_switch[] is set, the status is the first + * element in scarlett2_autogain_status_texts[] (Running). The + * subsequent elements correspond to the status value from the + * device (raw_autogain_status[]) + 1. The last element is + * "Invalid", in case the device reports a status outside the + * range of scarlett2_autogain_status_texts[]. */ for (i = 0; i < info->gain_input_count; i++) if (private->autogain_switch[i]) + private->autogain_status[i] = 0; + else if (raw_autogain_status[i] < + ARRAY_SIZE(scarlett2_autogain_status_texts) - 1) private->autogain_status[i] = - SCARLETT2_AUTOGAIN_STATUS_RUNNING; - else if (raw_autogain_status[i] == 0) - private->autogain_status[i] = - SCARLETT2_AUTOGAIN_STATUS_STOPPED; - else if (raw_autogain_status[i] >= 2 && - raw_autogain_status[i] <= 5) - private->autogain_status[i] = - SCARLETT2_AUTOGAIN_STATUS_FAILED; - else if (raw_autogain_status[i] == 6) - private->autogain_status[i] = - SCARLETT2_AUTOGAIN_STATUS_CANCELLED; + raw_autogain_status[i] + 1; else private->autogain_status[i] = - SCARLETT2_AUTOGAIN_STATUS_UNKNOWN; + ARRAY_SIZE(scarlett2_autogain_status_texts) - 1; return 0; } @@ -3111,12 +3124,10 @@ static int scarlett2_autogain_switch_ctl_put( static int scarlett2_autogain_status_ctl_info( struct snd_kcontrol *kctl, struct snd_ctl_elem_info *uinfo) { - static const char *const values[SCARLETT2_AUTOGAIN_STATUS_COUNT] = { - "Stopped", "Running", "Failed", "Cancelled", "Unknown" - }; - return snd_ctl_enum_info( - uinfo, 1, SCARLETT2_AUTOGAIN_STATUS_COUNT, values); + uinfo, 1, + ARRAY_SIZE(scarlett2_autogain_status_texts), + scarlett2_autogain_status_texts); } static const struct snd_kcontrol_new scarlett2_autogain_switch_ctl = { @@ -3458,7 +3469,7 @@ static int scarlett2_input_gain_ctl_info(struct snd_kcontrol *kctl, uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->count = elem->channels; uinfo->value.integer.min = 0; - uinfo->value.integer.max = SCARLETT2_GAIN_BIAS; + uinfo->value.integer.max = SCARLETT2_MAX_GAIN_VALUE; uinfo->value.integer.step = 1; unlock: @@ -3535,7 +3546,7 @@ static int scarlett2_input_gain_ctl_put(struct snd_kcontrol *kctl, } static const DECLARE_TLV_DB_MINMAX( - db_scale_scarlett2_gain, -SCARLETT2_GAIN_BIAS * 100, 0 + db_scale_scarlett2_gain, 0, SCARLETT2_MAX_GAIN_DB * 100 ); static const struct snd_kcontrol_new scarlett2_input_gain_ctl = { @@ -6294,8 +6305,7 @@ static int scarlett2_update_power_status(struct usb_mixer_interface *mixer) { struct scarlett2_data *private = mixer->private_data; int err; - u8 power_ext; - u8 power_status; + u8 power_ext, power_low; private->power_status_updated = 0; @@ -6304,12 +6314,12 @@ static int scarlett2_update_power_status(struct usb_mixer_interface *mixer) if (err < 0) return err; - err = scarlett2_usb_get_config(mixer, SCARLETT2_CONFIG_POWER_STATUS, - 1, &power_status); + err = scarlett2_usb_get_config(mixer, SCARLETT2_CONFIG_POWER_LOW, + 1, &power_low); if (err < 0) return err; - if (power_status > 1) + if (power_low) private->power_status = SCARLETT2_POWER_STATUS_FAIL; else if (power_ext) private->power_status = SCARLETT2_POWER_STATUS_EXT; diff --git a/sound/usb/stream.c b/sound/usb/stream.c index 3d4add94e367d..d5409f3879455 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -300,9 +300,12 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits, c = 0; if (bits) { - for (; bits && *maps; maps++, bits >>= 1) + for (; bits && *maps; maps++, bits >>= 1) { if (bits & 1) chmap->map[c++] = *maps; + if (c == chmap->channels) + break; + } } else { /* If we're missing wChannelConfig, then guess something to make sure the channel map is not skipped entirely */ diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h index ccc13e9913760..cd8420e8c3ad8 100644 --- a/tools/arch/arm64/include/asm/sysreg.h +++ b/tools/arch/arm64/include/asm/sysreg.h @@ -701,18 +701,18 @@ * Permission Indirection Extension (PIE) permission encodings. * Encodings with the _O suffix, have overlays applied (Permission Overlay Extension). */ -#define PIE_NONE_O 0x0 -#define PIE_R_O 0x1 -#define PIE_X_O 0x2 -#define PIE_RX_O 0x3 -#define PIE_RW_O 0x5 -#define PIE_RWnX_O 0x6 -#define PIE_RWX_O 0x7 -#define PIE_R 0x8 -#define PIE_GCS 0x9 -#define PIE_RX 0xa -#define PIE_RW 0xc -#define PIE_RWX 0xe +#define PIE_NONE_O UL(0x0) +#define PIE_R_O UL(0x1) +#define PIE_X_O UL(0x2) +#define PIE_RX_O UL(0x3) +#define PIE_RW_O UL(0x5) +#define PIE_RWnX_O UL(0x6) +#define PIE_RWX_O UL(0x7) +#define PIE_R UL(0x8) +#define PIE_GCS UL(0x9) +#define PIE_RX UL(0xa) +#define PIE_RW UL(0xc) +#define PIE_RWX UL(0xe) #define PIRx_ELx_PERM(idx, perm) ((perm) << ((idx) * 4)) diff --git a/tools/arch/x86/intel_sdsi/intel_sdsi.c b/tools/arch/x86/intel_sdsi/intel_sdsi.c index 2cd92761f1714..ba2a6b6645ae8 100644 --- a/tools/arch/x86/intel_sdsi/intel_sdsi.c +++ b/tools/arch/x86/intel_sdsi/intel_sdsi.c @@ -43,7 +43,6 @@ #define METER_CERT_MAX_SIZE 4096 #define STATE_MAX_NUM_LICENSES 16 #define STATE_MAX_NUM_IN_BUNDLE (uint32_t)8 -#define METER_MAX_NUM_BUNDLES 8 #define __round_mask(x, y) ((__typeof__(x))((y) - 1)) #define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) @@ -154,11 +153,12 @@ struct bundle_encoding { }; struct meter_certificate { - uint32_t block_signature; - uint32_t counter_unit; + uint32_t signature; + uint32_t version; uint64_t ppin; + uint32_t counter_unit; uint32_t bundle_length; - uint32_t reserved; + uint64_t reserved; uint32_t mmrc_encoding; uint32_t mmrc_counter; }; @@ -167,6 +167,11 @@ struct bundle_encoding_counter { uint32_t encoding; uint32_t counter; }; +#define METER_BUNDLE_SIZE sizeof(struct bundle_encoding_counter) +#define BUNDLE_COUNT(length) ((length) / METER_BUNDLE_SIZE) +#define METER_MAX_NUM_BUNDLES \ + ((METER_CERT_MAX_SIZE - sizeof(struct meter_certificate)) / \ + sizeof(struct bundle_encoding_counter)) struct sdsi_dev { struct sdsi_regs regs; @@ -334,6 +339,7 @@ static int sdsi_meter_cert_show(struct sdsi_dev *s) uint32_t count = 0; FILE *cert_ptr; int ret, size; + char name[4]; ret = sdsi_update_registers(s); if (ret) @@ -375,32 +381,40 @@ static int sdsi_meter_cert_show(struct sdsi_dev *s) printf("\n"); printf("Meter certificate for device %s\n", s->dev_name); printf("\n"); - printf("Block Signature: 0x%x\n", mc->block_signature); - printf("Count Unit: %dms\n", mc->counter_unit); - printf("PPIN: 0x%lx\n", mc->ppin); - printf("Feature Bundle Length: %d\n", mc->bundle_length); - printf("MMRC encoding: %d\n", mc->mmrc_encoding); - printf("MMRC counter: %d\n", mc->mmrc_counter); - if (mc->bundle_length % 8) { + + get_feature(mc->signature, name); + printf("Signature: %.4s\n", name); + + printf("Version: %d\n", mc->version); + printf("Count Unit: %dms\n", mc->counter_unit); + printf("PPIN: 0x%lx\n", mc->ppin); + printf("Feature Bundle Length: %d\n", mc->bundle_length); + + get_feature(mc->mmrc_encoding, name); + printf("MMRC encoding: %.4s\n", name); + + printf("MMRC counter: %d\n", mc->mmrc_counter); + if (mc->bundle_length % METER_BUNDLE_SIZE) { fprintf(stderr, "Invalid bundle length\n"); return -1; } - if (mc->bundle_length > METER_MAX_NUM_BUNDLES * 8) { - fprintf(stderr, "More than %d bundles: %d\n", - METER_MAX_NUM_BUNDLES, mc->bundle_length / 8); + if (mc->bundle_length > METER_MAX_NUM_BUNDLES * METER_BUNDLE_SIZE) { + fprintf(stderr, "More than %ld bundles: actual %ld\n", + METER_MAX_NUM_BUNDLES, BUNDLE_COUNT(mc->bundle_length)); return -1; } - bec = (void *)(mc) + sizeof(mc); + bec = (struct bundle_encoding_counter *)(mc + 1); - printf("Number of Feature Counters: %d\n", mc->bundle_length / 8); - while (count++ < mc->bundle_length / 8) { + printf("Number of Feature Counters: %ld\n", BUNDLE_COUNT(mc->bundle_length)); + while (count < BUNDLE_COUNT(mc->bundle_length)) { char feature[5]; feature[4] = '\0'; get_feature(bec[count].encoding, feature); printf(" %s: %d\n", feature, bec[count].counter); + ++count; } return 0; diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index 5168ee0360b24..d1ccd06c53127 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -148,7 +148,7 @@ AVXcode: 65: SEG=GS (Prefix) 66: Operand-Size (Prefix) 67: Address-Size (Prefix) -68: PUSH Iz (d64) +68: PUSH Iz 69: IMUL Gv,Ev,Iz 6a: PUSH Ib (d64) 6b: IMUL Gv,Ev,Ib @@ -698,10 +698,10 @@ AVXcode: 2 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) -50: vpdpbusd Vx,Hx,Wx (66),(ev) -51: vpdpbusds Vx,Hx,Wx (66),(ev) -52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) -53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) +50: vpdpbusd Vx,Hx,Wx (66) +51: vpdpbusds Vx,Hx,Wx (66) +52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev) +53: vpdpwssds Vx,Hx,Wx (66) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev) 54: vpopcntb/w Vx,Wx (66),(ev) 55: vpopcntd/q Vx,Wx (66),(ev) 58: vpbroadcastd Vx,Wx (66),(v) diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index cc6e6aae2447d..958e92acca8e2 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -244,29 +244,101 @@ int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) return fd; } -int mount_bpffs_for_pin(const char *name, bool is_dir) +int create_and_mount_bpffs_dir(const char *dir_name) { char err_str[ERR_MAX_LEN]; - char *file; - char *dir; + bool dir_exists; int err = 0; - if (is_dir && is_bpffs(name)) + if (is_bpffs(dir_name)) return err; - file = malloc(strlen(name) + 1); - if (!file) { + dir_exists = access(dir_name, F_OK) == 0; + + if (!dir_exists) { + char *temp_name; + char *parent_name; + + temp_name = strdup(dir_name); + if (!temp_name) { + p_err("mem alloc failed"); + return -1; + } + + parent_name = dirname(temp_name); + + if (is_bpffs(parent_name)) { + /* nothing to do if already mounted */ + free(temp_name); + return err; + } + + if (access(parent_name, F_OK) == -1) { + p_err("can't create dir '%s' to pin BPF object: parent dir '%s' doesn't exist", + dir_name, parent_name); + free(temp_name); + return -1; + } + + free(temp_name); + } + + if (block_mount) { + p_err("no BPF file system found, not mounting it due to --nomount option"); + return -1; + } + + if (!dir_exists) { + err = mkdir(dir_name, S_IRWXU); + if (err) { + p_err("failed to create dir '%s': %s", dir_name, strerror(errno)); + return err; + } + } + + err = mnt_fs(dir_name, "bpf", err_str, ERR_MAX_LEN); + if (err) { + err_str[ERR_MAX_LEN - 1] = '\0'; + p_err("can't mount BPF file system on given dir '%s': %s", + dir_name, err_str); + + if (!dir_exists) + rmdir(dir_name); + } + + return err; +} + +int mount_bpffs_for_file(const char *file_name) +{ + char err_str[ERR_MAX_LEN]; + char *temp_name; + char *dir; + int err = 0; + + if (access(file_name, F_OK) != -1) { + p_err("can't pin BPF object: path '%s' already exists", file_name); + return -1; + } + + temp_name = strdup(file_name); + if (!temp_name) { p_err("mem alloc failed"); return -1; } - strcpy(file, name); - dir = dirname(file); + dir = dirname(temp_name); if (is_bpffs(dir)) /* nothing to do if already mounted */ goto out_free; + if (access(dir, F_OK) == -1) { + p_err("can't pin BPF object: dir '%s' doesn't exist", dir); + err = -1; + goto out_free; + } + if (block_mount) { p_err("no BPF file system found, not mounting it due to --nomount option"); err = -1; @@ -276,12 +348,12 @@ int mount_bpffs_for_pin(const char *name, bool is_dir) err = mnt_fs(dir, "bpf", err_str, ERR_MAX_LEN); if (err) { err_str[ERR_MAX_LEN - 1] = '\0'; - p_err("can't mount BPF file system to pin the object (%s): %s", - name, err_str); + p_err("can't mount BPF file system to pin the object '%s': %s", + file_name, err_str); } out_free: - free(file); + free(temp_name); return err; } @@ -289,7 +361,7 @@ int do_pin_fd(int fd, const char *name) { int err; - err = mount_bpffs_for_pin(name, false); + err = mount_bpffs_for_file(name); if (err) return err; diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index 6b0e5202ca7a9..5c39c2ed36a2b 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -76,7 +76,7 @@ static int do_pin(int argc, char **argv) goto close_obj; } - err = mount_bpffs_for_pin(path, false); + err = mount_bpffs_for_file(path); if (err) goto close_link; diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index cb46667a6b2e7..35b6859dd7c3d 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -977,7 +977,7 @@ static int do_show_link(int fd) cookies = calloc(count, sizeof(__u64)); if (!cookies) { p_err("mem alloc failed"); - free(cookies); + free(ref_ctr_offsets); free(offsets); close(fd); return -ENOMEM; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index b8bb08d10dec9..9eb764fe4cc8b 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -142,7 +142,8 @@ const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); int open_obj_pinned(const char *path, bool quiet); int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); -int mount_bpffs_for_pin(const char *name, bool is_dir); +int mount_bpffs_for_file(const char *file_name); +int create_and_mount_bpffs_dir(const char *dir_name); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); int do_pin_fd(int fd, const char *name); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index feb8e305804fc..4c4cf16a40ba7 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1778,7 +1778,10 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - err = mount_bpffs_for_pin(pinfile, !first_prog_only); + if (first_prog_only) + err = mount_bpffs_for_file(pinfile); + else + err = create_and_mount_bpffs_dir(pinfile); if (err) goto err_close_obj; @@ -2298,7 +2301,7 @@ static int profile_open_perf_events(struct profiler_bpf *obj) int map_fd; profile_perf_events = calloc( - sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); + obj->rodata->num_cpu * obj->rodata->num_metric, sizeof(int)); if (!profile_perf_events) { p_err("failed to allocate memory for perf_event array: %s", strerror(errno)); diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index 26004f0c5a6ae..7bdbcac3cf628 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -102,8 +102,8 @@ int iter(struct bpf_iter__task_file *ctx) BPF_LINK_TYPE_PERF_EVENT___local)) { struct bpf_link *link = (struct bpf_link *) file->private_data; - if (link->type == bpf_core_enum_value(enum bpf_link_type___local, - BPF_LINK_TYPE_PERF_EVENT___local)) { + if (BPF_CORE_READ(link, type) == bpf_core_enum_value(enum bpf_link_type___local, + BPF_LINK_TYPE_PERF_EVENT___local)) { e.has_bpf_cookie = true; e.bpf_cookie = get_bpf_cookie(link); } diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index d573f2640d8e9..aa43dead249cb 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -515,7 +515,7 @@ static int do_register(int argc, char **argv) if (argc == 1) linkdir = GET_ARG(); - if (linkdir && mount_bpffs_for_pin(linkdir, true)) { + if (linkdir && create_and_mount_bpffs_dir(linkdir)) { p_err("can't mount bpffs for pinning"); return -1; } diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 27a23196d58e1..af393c7dee1f1 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -70,6 +70,7 @@ #include #include #include +#include #include #include #include @@ -78,7 +79,7 @@ #include #define BTF_IDS_SECTION ".BTF_ids" -#define BTF_ID "__BTF_ID__" +#define BTF_ID_PREFIX "__BTF_ID__" #define BTF_STRUCT "struct" #define BTF_UNION "union" @@ -89,6 +90,14 @@ #define ADDR_CNT 100 +#if __BYTE_ORDER == __LITTLE_ENDIAN +# define ELFDATANATIVE ELFDATA2LSB +#elif __BYTE_ORDER == __BIG_ENDIAN +# define ELFDATANATIVE ELFDATA2MSB +#else +# error "Unknown machine endianness!" +#endif + struct btf_id { struct rb_node rb_node; char *name; @@ -116,6 +125,7 @@ struct object { int idlist_shndx; size_t strtabidx; unsigned long idlist_addr; + int encoding; } efile; struct rb_root sets; @@ -161,7 +171,7 @@ static int eprintf(int level, int var, const char *fmt, ...) static bool is_btf_id(const char *name) { - return name && !strncmp(name, BTF_ID, sizeof(BTF_ID) - 1); + return name && !strncmp(name, BTF_ID_PREFIX, sizeof(BTF_ID_PREFIX) - 1); } static struct btf_id *btf_id__find(struct rb_root *root, const char *name) @@ -319,6 +329,7 @@ static int elf_collect(struct object *obj) { Elf_Scn *scn = NULL; size_t shdrstrndx; + GElf_Ehdr ehdr; int idx = 0; Elf *elf; int fd; @@ -350,6 +361,13 @@ static int elf_collect(struct object *obj) return -1; } + if (gelf_getehdr(obj->efile.elf, &ehdr) == NULL) { + pr_err("FAILED cannot get ELF header: %s\n", + elf_errmsg(-1)); + return -1; + } + obj->efile.encoding = ehdr.e_ident[EI_DATA]; + /* * Scan all the elf sections and look for save data * from .BTF_ids section and symbols. @@ -441,7 +459,7 @@ static int symbols_collect(struct object *obj) * __BTF_ID__TYPE__vfs_truncate__0 * prefix = ^ */ - prefix = name + sizeof(BTF_ID) - 1; + prefix = name + sizeof(BTF_ID_PREFIX) - 1; /* struct */ if (!strncmp(prefix, BTF_STRUCT, sizeof(BTF_STRUCT) - 1)) { @@ -649,19 +667,18 @@ static int cmp_id(const void *pa, const void *pb) static int sets_patch(struct object *obj) { Elf_Data *data = obj->efile.idlist; - int *ptr = data->d_buf; struct rb_node *next; next = rb_first(&obj->sets); while (next) { - unsigned long addr, idx; + struct btf_id_set8 *set8; + struct btf_id_set *set; + unsigned long addr, off; struct btf_id *id; - int *base; - int cnt; id = rb_entry(next, struct btf_id, rb_node); addr = id->addr[0]; - idx = addr - obj->efile.idlist_addr; + off = addr - obj->efile.idlist_addr; /* sets are unique */ if (id->addr_cnt != 1) { @@ -670,14 +687,39 @@ static int sets_patch(struct object *obj) return -1; } - idx = idx / sizeof(int); - base = &ptr[idx] + (id->is_set8 ? 2 : 1); - cnt = ptr[idx]; + if (id->is_set) { + set = data->d_buf + off; + qsort(set->ids, set->cnt, sizeof(set->ids[0]), cmp_id); + } else { + set8 = data->d_buf + off; + /* + * Make sure id is at the beginning of the pairs + * struct, otherwise the below qsort would not work. + */ + BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id); + qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id); - pr_debug("sorting addr %5lu: cnt %6d [%s]\n", - (idx + 1) * sizeof(int), cnt, id->name); + /* + * When ELF endianness does not match endianness of the + * host, libelf will do the translation when updating + * the ELF. This, however, corrupts SET8 flags which are + * already in the target endianness. So, let's bswap + * them to the host endianness and libelf will then + * correctly translate everything. + */ + if (obj->efile.encoding != ELFDATANATIVE) { + int i; + + set8->flags = bswap_32(set8->flags); + for (i = 0; i < set8->cnt; i++) { + set8->pairs[i].flags = + bswap_32(set8->pairs[i].flags); + } + } + } - qsort(base, cnt, id->is_set8 ? sizeof(uint64_t) : sizeof(int), cmp_id); + pr_debug("sorting addr %5lu: cnt %6d [%s]\n", + off, id->is_set ? set->cnt : set8->cnt, id->name); next = rb_next(next); } @@ -686,7 +728,7 @@ static int sets_patch(struct object *obj) static int symbols_patch(struct object *obj) { - int err; + off_t err; if (__symbols_patch(obj, &obj->structs) || __symbols_patch(obj, &obj->unions) || diff --git a/tools/hv/hv_kvp_daemon.8 b/tools/hv/hv_kvp_daemon.8 new file mode 100644 index 0000000000000..0fb4577a1f072 --- /dev/null +++ b/tools/hv/hv_kvp_daemon.8 @@ -0,0 +1,26 @@ +.\" This page Copyright (C) 2012 Andy Whitcroft +.\" Distributed under the GPL v2 or later. +.TH HV_KVP_DAEMON 8 +.SH NAME +hv_kvp_daemon \- Hyper-V Key Value Pair daemon +.SH SYNOPSIS +.ft B +.B hv_kvp_daemon +.br +.SH DESCRIPTION +\fBhv_kvp_daemon\fP +is the userspace component of the Hyper-V key value pair functionality, +communicating via a netlink socket with the kernel HV-KVP driver. +This pairing allows the Hyper-V host to pass configuration information +(such as IP addresses) to the guest and allows the host to obtain guest +version information. + +.SH FILES +.ta +.nf +/var/opt/hyperv/.kvp_pool_* +.fi + +.SH AUTHORS +.nf +Written by K. Y. Srinivasan diff --git a/tools/hv/lsvmbus b/tools/hv/lsvmbus index 099f2c44dbed2..f83698f14da28 100644 --- a/tools/hv/lsvmbus +++ b/tools/hv/lsvmbus @@ -1,4 +1,4 @@ -#!/usr/bin/env python +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 import os diff --git a/tools/hv/lsvmbus.8 b/tools/hv/lsvmbus.8 new file mode 100644 index 0000000000000..ba07d664950eb --- /dev/null +++ b/tools/hv/lsvmbus.8 @@ -0,0 +1,23 @@ +.\" This page Copyright (C) 2016 Andy Whitcroft +.\" Distributed under the GPL v2 or later. +.TH LSVMBUS 8 +.SH NAME +lsvmbus \- List Hyper-V VMBus devices +.SH SYNOPSIS +.ft B +.B lsvmbus [-vv] +.br +.SH DESCRIPTION +\fBlsvmbus\fP +displays devices attached to the Hyper-V VMBus. +.SH OPTIONS +.\" +.TP +.B -v +With -v more information is printed including the VMBus Rel_ID, class ID, +Rel_ID, and which channel is bound to which virtual processor. Use -vv +for additional detail including the Device_ID and the sysfs path. +.\" +.SH AUTHORS +.nf +Written by Dexuan Cui diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index 6a00a6eecaef0..c5c5082cb24e5 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -376,7 +376,7 @@ int build_channel_array(const char *device_dir, int buffer_idx, goto error_close_dir; } - seekdir(dp, 0); + rewinddir(dp); while (ent = readdir(dp), ent) { if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"), "_en") == 0) { diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 2f882d5cb30f5..72ea363d434db 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -3,11 +3,22 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; }; +struct btf_id_set8 { + u32 cnt; + u32 flags; + struct { + u32 id; + u32 flags; + } pairs[]; +}; + #ifdef CONFIG_DEBUG_INFO_BTF #include /* for __PASTE */ diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 4b0673bf52c2e..07cfad817d539 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index f3c82ab5b14cd..7d73da0980473 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -37,4 +37,9 @@ static inline void totalram_pages_add(long count) { } +static inline int early_pfn_to_nid(unsigned long pfn) +{ + return 0; +} + #endif diff --git a/tools/include/linux/panic.h b/tools/include/linux/panic.h new file mode 100644 index 0000000000000..9c8f17a41ce8e --- /dev/null +++ b/tools/include/linux/panic.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_LINUX_PANIC_H +#define _TOOLS_LINUX_PANIC_H + +#include +#include +#include + +static inline void panic(const char *fmt, ...) +{ + va_list argp; + + va_start(argp, fmt); + vfprintf(stderr, fmt, argp); + va_end(argp); + exit(-1); +} + +#endif diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index bacfd35c51565..5be9d3c7435a8 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -185,7 +185,7 @@ void *realloc(void *old_ptr, size_t new_size) if (__builtin_expect(!ret, 0)) return NULL; - memcpy(ret, heap->user_p, heap->len); + memcpy(ret, heap->user_p, user_p_len); munmap(heap, heap->len); return ret; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7f24d898efbb4..a12f597a1c47f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7039,7 +7039,7 @@ struct bpf_fib_lookup { /* output: MTU value */ __u16 mtu_result; - }; + } __attribute__((packed, aligned(2))); /* input: L3 device index for lookup * output: device index from FIB lookup */ diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index d0f53772bdc02..dad7917903d19 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -35,7 +35,7 @@ extern "C" { #endif -int libbpf_set_memlock_rlim(size_t memlock_bytes); +LIBBPF_API int libbpf_set_memlock_rlim(size_t memlock_bytes); struct bpf_map_create_opts { size_t sz; /* size of this struct for forward/backward compatibility */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index afd09571c482b..028d8f014c871 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -70,6 +71,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); +static int map_set_def_max_entries(struct bpf_map *map); static const char * const attach_type_name[] = { [BPF_CGROUP_INET_INGRESS] = "cgroup_inet_ingress", @@ -5172,6 +5174,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (bpf_map_type__is_map_in_map(def->type)) { if (map->inner_map) { + err = map_set_def_max_entries(map->inner_map); + if (err) + return err; err = bpf_object__create_map(obj, map->inner_map, true); if (err) { pr_warn("map '%s': failed to create inner map: %d\n", @@ -6695,6 +6700,14 @@ static struct { /* all other program types don't have "named" context structs */ }; +/* forward declarations for arch-specific underlying types of bpf_user_pt_regs_t typedef, + * for below __builtin_types_compatible_p() checks; + * with this approach we don't need any extra arch-specific #ifdef guards + */ +struct pt_regs; +struct user_pt_regs; +struct user_regs_struct; + static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_program *prog, const char *subprog_name, int arg_idx, int arg_type_id, const char *ctx_name) @@ -6735,11 +6748,21 @@ static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_pro /* special cases */ switch (prog->type) { case BPF_PROG_TYPE_KPROBE: - case BPF_PROG_TYPE_PERF_EVENT: /* `struct pt_regs *` is expected, but we need to fix up */ if (btf_is_struct(t) && strcmp(tname, "pt_regs") == 0) return true; break; + case BPF_PROG_TYPE_PERF_EVENT: + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) && + btf_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return true; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) && + btf_is_struct(t) && strcmp(tname, "user_pt_regs") == 0) + return true; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) && + btf_is_struct(t) && strcmp(tname, "user_regs_struct") == 0) + return true; + break; case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: /* allow u64* as ctx */ @@ -7433,9 +7456,9 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; char *log_buf = NULL, *tmp; - int btf_fd, ret, err; bool own_log_buf = true; __u32 log_level = prog->log_level; + int ret, err; if (prog->type == BPF_PROG_TYPE_UNSPEC) { /* @@ -7459,9 +7482,8 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.prog_ifindex = prog->prog_ifindex; /* specify func_info/line_info only if kernel supports them */ - btf_fd = btf__fd(obj->btf); - if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { - load_attr.prog_btf_fd = btf_fd; + if (obj->btf && btf__fd(obj->btf) >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { + load_attr.prog_btf_fd = btf__fd(obj->btf); load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; load_attr.func_info_cnt = prog->func_info_cnt; @@ -11539,7 +11561,7 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); if (n < 1) { - pr_warn("kprobe multi pattern is invalid: %s\n", pattern); + pr_warn("kprobe multi pattern is invalid: %s\n", spec); return -EINVAL; } diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 27e4e320e1a69..878a0d0b51f5c 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -18,6 +18,20 @@ #include #include "relo_core.h" +/* Android's libc doesn't support AT_EACCESS in faccessat() implementation + * ([0]), and just returns -EINVAL even if file exists and is accessible. + * See [1] for issues caused by this. + * + * So just redefine it to 0 on Android. + * + * [0] https://android.googlesource.com/platform/bionic/+/refs/heads/android13-release/libc/bionic/faccessat.cpp#50 + * [1] https://github.com/libbpf/libbpf-bootstrap/issues/250#issuecomment-1911324250 + */ +#ifdef __ANDROID__ +#undef AT_EACCESS +#define AT_EACCESS 0 +#endif + /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 090bcf6e3b3d5..68a2def171751 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -496,8 +496,8 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) if (err) return libbpf_err(err); - opts->feature_flags = md.flags; - opts->xdp_zc_max_segs = md.xdp_zc_max_segs; + OPTS_SET(opts, feature_flags, md.flags); + OPTS_SET(opts, xdp_zc_max_segs, md.xdp_zc_max_segs); skip_feature_flags: return 0; diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 058e3ff10f9b2..c6d67fc9e57ef 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -248,10 +248,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist) static void perf_evlist__id_hash(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { int hash; - struct perf_sample_id *sid = SID(evsel, cpu, thread); + struct perf_sample_id *sid = SID(evsel, cpu_map_idx, thread); sid->id = id; sid->evsel = evsel; @@ -269,21 +269,27 @@ void perf_evlist__reset_id_hash(struct perf_evlist *evlist) void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { - perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + if (!SID(evsel, cpu_map_idx, thread)) + return; + + perf_evlist__id_hash(evlist, evsel, cpu_map_idx, thread, id); evsel->id[evsel->ids++] = id; } int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd) + int cpu_map_idx, int thread, int fd) { u64 read_data[4] = { 0, }; int id_idx = 1; /* The first entry is the counter value */ u64 id; int ret; + if (!SID(evsel, cpu_map_idx, thread)) + return -1; + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); if (!ret) goto add; @@ -312,7 +318,7 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, id = read_data[id_idx]; add: - perf_evlist__id_add(evlist, evsel, cpu, thread, id); + perf_evlist__id_add(evlist, evsel, cpu_map_idx, thread, id); return 0; } diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index d86ffe8ed483e..f43bdb9b6227c 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -126,11 +126,11 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist); void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id); + int cpu_map_idx, int thread, u64 id); int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd); + int cpu_map_idx, int thread, int fd); void perf_evlist__reset_id_hash(struct perf_evlist *evlist); diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index 9fa75943f2ed1..d943d78b787ed 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -633,11 +633,10 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o const char *const subcommands[], const char *usagestr[], int flags) { struct parse_opt_ctx_t ctx; + char *buf = NULL; /* build usage string if it's not provided */ if (subcommands && !usagestr[0]) { - char *buf = NULL; - astrcatf(&buf, "%s %s [] {", subcmd_config.exec_name, argv[0]); for (int i = 0; subcommands[i]; i++) { @@ -679,7 +678,10 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o astrcatf(&error_buf, "unknown switch `%c'", *ctx.opt); usage_with_options(usagestr, options); } - + if (buf) { + usagestr[0] = NULL; + free(buf); + } return parse_options_end(&ctx); } diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus index 10a2aa04cd078..415248fb66990 100644 --- a/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus +++ b/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus @@ -1,11 +1,12 @@ -C Z6.0+pooncelock+pooncelock+pombonce +C Z6.0+pooncelock+poonceLock+pombonce (* - * Result: Sometimes + * Result: Never * - * This example demonstrates that a pair of accesses made by different - * processes each while holding a given lock will not necessarily be - * seen as ordered by a third process not holding that lock. + * This litmus test demonstrates how smp_mb__after_spinlock() may be + * used to ensure that accesses in different critical sections for a + * given lock running on different CPUs are nevertheless seen in order + * by CPUs not holding that lock. *) {} @@ -23,6 +24,7 @@ P1(int *y, int *z, spinlock_t *mylock) int r0; spin_lock(mylock); + smp_mb__after_spinlock(); r0 = READ_ONCE(*y); WRITE_ONCE(*z, 1); spin_unlock(mylock); diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 1e10512b2117c..571c2e218993f 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -208,6 +208,7 @@ def __init__(self, msg, offset, attr_space=None): self.done = 1 extack_off = 20 elif self.nl_type == Netlink.NLMSG_DONE: + self.error = struct.unpack("i", self.raw[0:4])[0] self.done = 1 extack_off = 4 diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 7fc1aa788f6f5..c19dec2394915 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -243,8 +243,11 @@ def setter(self, ri, space, direction, deref=False, ref=None): presence = '' for i in range(0, len(ref)): presence = f"{var}->{'.'.join(ref[:i] + [''])}_present.{ref[i]}" - if self.presence_type() == 'bit': - code.append(presence + ' = 1;') + # Every layer below last is a nest, so we know it uses bit presence + # last layer is "self" and may be a complex type + if i == len(ref) - 1 and self.presence_type() != 'bit': + continue + code.append(presence + ' = 1;') code += self._setter_lines(ri, member, presence) func_name = f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}" diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 548ec3cd7c00c..1611860148c5e 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3620,6 +3620,18 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, } if (!save_insn->visited) { + /* + * If the restore hint insn is at the + * beginning of a basic block and was + * branched to from elsewhere, and the + * save insn hasn't been visited yet, + * defer following this branch for now. + * It will be seen later via the + * straight-line path. + */ + if (!prev_insn) + return 0; + WARN_INSN(insn, "objtool isn't smart enough to handle this CFI save/restore combo"); return 1; } @@ -3991,7 +4003,10 @@ static int validate_retpoline(struct objtool_file *file) warnings++; } - return warnings; + /* RETPOLINE is an optional security safety feature, make it + * fatal to ensure no new code is introduced that fails + * RETPOLINE */ + return -warnings; } static bool is_kasan_insn(struct instruction *insn) @@ -4500,7 +4515,9 @@ static int validate_sls(struct objtool_file *file) } } - return warnings; + /* SLS is an optional security safety feature, make it fatal + * to ensure no new code is introduced that fails SLS */ + return -warnings; } static bool ignore_noreturn_call(struct instruction *insn) @@ -4677,8 +4694,10 @@ int check(struct objtool_file *file) init_cfi_state(&force_undefined_cfi); force_undefined_cfi.force_undefined = true; - if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3))) + if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3))) { + ret = -1; goto out; + } cfi_hash_add(&init_cfi); cfi_hash_add(&func_cfi); @@ -4695,7 +4714,7 @@ int check(struct objtool_file *file) if (opts.retpoline) { ret = validate_retpoline(file); if (ret < 0) - return ret; + goto out; warnings += ret; } @@ -4731,7 +4750,7 @@ int check(struct objtool_file *file) */ ret = validate_unrets(file); if (ret < 0) - return ret; + goto out; warnings += ret; } @@ -4794,7 +4813,7 @@ int check(struct objtool_file *file) if (opts.prefix) { ret = add_prefix_symbols(file); if (ret < 0) - return ret; + goto out; warnings += ret; } @@ -4825,10 +4844,5 @@ int check(struct objtool_file *file) } out: - /* - * For now, don't fail the kernel build on fatal warnings. These - * errors are still fairly common due to the growing matrix of - * supported toolchains and their recent pace of change. - */ - return 0; + return ret < 0 ? ret : 0; } diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 3b12595193c9f..6bf2468f59d31 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -71,6 +71,7 @@ counted. The following modifiers exist: D - pin the event to the PMU W - group is weak and will fallback to non-group if not schedulable, e - group or event are exclusive and do not share the PMU + b - use BPF aggregration (see perf stat --bpf-counters) The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times: diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index ff9a52e446884..66b633f3c6d26 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -441,9 +441,10 @@ include::itrace.txt[] will be printed. Each entry has function name and file/line. Enabled by default, disable with --no-inline. ---insn-trace:: - Show instruction stream for intel_pt traces. Combine with --xed to - show disassembly. +--insn-trace[=]:: + Show instruction stream in bytes (raw) or disassembled (disasm) + for intel_pt traces. The default is 'raw'. To use xed, combine + 'raw' with --xed to show disassembly done by xed. --xed:: Run xed disassembler on output. Requires installing the xed disassembler. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index aa55850fbc213..e7dfc6fa8a465 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -930,6 +930,11 @@ ifneq ($(NO_JEVENTS),1) endif endif +ifdef HAVE_NO_LIBBFD + feature-libbfd := 0 + $(info libbfd overidden OFF) +else + ifdef BUILD_NONDISTRO ifeq ($(feature-libbfd), 1) EXTLIBS += -lbfd -lopcodes @@ -966,6 +971,8 @@ ifdef BUILD_NONDISTRO endif endif +endif + ifndef NO_DEMANGLE $(call feature_check,cxa-demangle) ifeq ($(feature-cxa-demangle), 1) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index f8774a9b1377a..27705df2e2ba8 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -455,18 +455,19 @@ SHELL = $(SHELL_PATH) arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools ifneq ($(OUTPUT),) - arm64_gen_sysreg_outdir := $(OUTPUT) + arm64_gen_sysreg_outdir := $(abspath $(OUTPUT)) else arm64_gen_sysreg_outdir := $(CURDIR) endif arm64-sysreg-defs: FORCE - $(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) + $(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \ + prefix= subdir= arm64-sysreg-defs-clean: $(call QUIET_CLEAN,arm64-sysreg-defs) $(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \ - clean > /dev/null + prefix= subdir= clean > /dev/null beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/ linux_uapi_dir := $(srctree)/tools/include/uapi/linux @@ -1167,7 +1168,7 @@ bpf-skel: endif # CONFIG_PERF_BPF_SKEL bpf-skel-clean: - $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) + $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) $(SKEL_OUT)/vmlinux.h clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $(LIBPERF)-clean arm64-sysreg-defs-clean fixdep-clean python-clean bpf-skel-clean tests-coresight-targets-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-iostat $(LANG_BINDINGS) diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c index 49331743c7439..a759eb2328bea 100644 --- a/tools/perf/bench/inject-buildid.c +++ b/tools/perf/bench/inject-buildid.c @@ -362,7 +362,7 @@ static int inject_build_id(struct bench_data *data, u64 *max_rss) return -1; for (i = 0; i < nr_mmaps; i++) { - int idx = rand() % (nr_dsos - 1); + int idx = rand() % nr_dsos; struct bench_dso *dso = &dsos[idx]; u64 timestamp = rand() % 1000000; diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c index 5c71fdc419dd7..b722ff88fe7de 100644 --- a/tools/perf/bench/uprobe.c +++ b/tools/perf/bench/uprobe.c @@ -47,7 +47,7 @@ static const char * const bench_uprobe_usage[] = { #define bench_uprobe__attach_uprobe(prog) \ skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \ /*pid=*/-1, \ - /*binary_path=*/"/lib64/libc.so.6", \ + /*binary_path=*/"libc.so.6", \ /*func_offset=*/0, \ /*opts=*/&uprobe_opts); \ if (!skel->links.prog) { \ diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 6c1cc797692d9..9cd97fd76bb5e 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -809,8 +809,6 @@ int cmd_annotate(int argc, const char **argv) "Enable symbol demangling"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), - OPT_BOOLEAN(0, "group", &symbol_conf.event_group, - "Show event group information together"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index 83954af36753a..de76bbc50bfbc 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -523,7 +523,7 @@ static int daemon_session__control(struct daemon_session *session, session->base, SESSION_CONTROL); control = open(control_path, O_WRONLY|O_NONBLOCK); - if (!control) + if (control < 0) return -1; if (do_ack) { @@ -532,7 +532,7 @@ static int daemon_session__control(struct daemon_session *session, session->base, SESSION_ACK); ack = open(ack_path, O_RDONLY, O_NONBLOCK); - if (!ack) { + if (ack < 0) { close(control); return -1; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 86c9101251726..0de705289ba77 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1355,8 +1355,6 @@ static int record__open(struct record *rec) struct record_opts *opts = &rec->opts; int rc = 0; - evlist__config(evlist, opts, &callchain_param); - evlist__for_each_entry(evlist, pos) { try_again: if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) { @@ -1830,8 +1828,8 @@ static int record__switch_output(struct record *rec, bool at_exit) { struct perf_data *data = &rec->data; + char *new_filename = NULL; int fd, err; - char *new_filename; /* Same Size: "2015122520103046"*/ char timestamp[] = "InvalidTimestamp"; @@ -1954,8 +1952,7 @@ static void record__read_lost_samples(struct record *rec) if (count.lost) { if (!lost) { - lost = zalloc(sizeof(*lost) + - session->machines.host.id_hdr_size); + lost = zalloc(PERF_SAMPLE_MAX_SIZE); if (!lost) { pr_debug("Memory allocation failed\n"); return; @@ -1971,8 +1968,7 @@ static void record__read_lost_samples(struct record *rec) lost_count = perf_bpf_filter__lost_count(evsel); if (lost_count) { if (!lost) { - lost = zalloc(sizeof(*lost) + - session->machines.host.id_hdr_size); + lost = zalloc(PERF_SAMPLE_MAX_SIZE); if (!lost) { pr_debug("Memory allocation failed\n"); return; @@ -2472,8 +2468,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (data->is_pipe && rec->evlist->core.nr_entries == 1) rec->opts.sample_id = true; + if (rec->timestamp_filename && perf_data__is_pipe(data)) { + rec->timestamp_filename = false; + pr_warning("WARNING: --timestamp-filename option is not available in pipe mode.\n"); + } + evlist__uniquify_name(rec->evlist); + evlist__config(rec->evlist, opts, &callchain_param); + /* Debug message used by test scripts */ pr_debug3("perf record opening and mmapping events\n"); if (record__open(rec) != 0) { @@ -2872,10 +2875,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } #endif zstd_fini(&session->zstd_data); - perf_session__delete(session); - if (!opts->no_bpf_event) evlist__stop_sb_thread(rec->sb_evlist); + + perf_session__delete(session); return status; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f2ed2b7e80a32..ea8636abbb8db 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -427,7 +427,7 @@ static int report__setup_sample_type(struct report *rep) * compatibility, set the bit if it's an old perf data file. */ evlist__for_each_entry(session->evlist, evsel) { - if (strstr(evsel->name, "arm_spe") && + if (strstr(evsel__name(evsel), "arm_spe") && !(sample_type & PERF_SAMPLE_DATA_SRC)) { evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC; sample_type |= PERF_SAMPLE_DATA_SRC; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index dd6065afbbaf6..5c1badc4d8f2c 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3000,8 +3000,11 @@ static int timehist_check_attr(struct perf_sched *sched, return -1; } - if (sched->show_callchain && !evsel__has_callchain(evsel)) { - pr_info("Samples do not have callchains.\n"); + /* only need to save callchain related to sched_switch event */ + if (sched->show_callchain && + evsel__name_is(evsel, "sched:sched_switch") && + !evsel__has_callchain(evsel)) { + pr_info("Samples of sched_switch event do not have callchains.\n"); sched->show_callchain = 0; symbol_conf.use_callchain = 0; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index b1f57401ff239..8d460fd043b5e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3765,11 +3765,25 @@ static int perf_script__process_auxtrace_info(struct perf_session *session, #endif static int parse_insn_trace(const struct option *opt __maybe_unused, - const char *str __maybe_unused, - int unset __maybe_unused) + const char *str, int unset __maybe_unused) { - parse_output_fields(NULL, "+insn,-event,-period", 0); - itrace_parse_synth_opts(opt, "i0ns", 0); + const char *fields = "+insn,-event,-period"; + int ret; + + if (str) { + if (strcmp(str, "disasm") == 0) + fields = "+disasm,-event,-period"; + else if (strlen(str) != 0 && strcmp(str, "raw") != 0) { + fprintf(stderr, "Only accept raw|disasm\n"); + return -EINVAL; + } + } + + ret = parse_output_fields(NULL, fields, 0); + if (ret < 0) + return ret; + + itrace_parse_synth_opts(opt, "i0nse", 0); symbol_conf.nanosecs = true; return 0; } @@ -3914,7 +3928,7 @@ int cmd_script(int argc, const char **argv) "only consider these symbols"), OPT_INTEGER(0, "addr-range", &symbol_conf.addr_range, "Use with -S to list traced records within address range"), - OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL, + OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, "raw|disasm", "Decode instructions from itrace", parse_insn_trace), OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL, "Run xed disassembler on output", parse_xed), diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json index ec2ff78e2b5f2..3ab1d3a6638c4 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json @@ -2,71 +2,71 @@ { "BriefDescription": "Transaction count", "MetricName": "transaction", - "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL if has_event(TX_C_TEND) else 0" }, { "BriefDescription": "Cycles per Instruction", "MetricName": "cpi", - "MetricExpr": "CPU_CYCLES / INSTRUCTIONS" + "MetricExpr": "CPU_CYCLES / INSTRUCTIONS if has_event(INSTRUCTIONS) else 0" }, { "BriefDescription": "Problem State Instruction Ratio", "MetricName": "prbstate", - "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100" + "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100 if has_event(INSTRUCTIONS) else 0" }, { "BriefDescription": "Level One Miss per 100 Instructions", "MetricName": "l1mp", - "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" + "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100 if has_event(INSTRUCTIONS) else 0" }, { "BriefDescription": "Percentage sourced from Level 2 cache", "MetricName": "l2p", - "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ) else 0" }, { "BriefDescription": "Percentage sourced from Level 3 on same chip cache", "MetricName": "l3p", - "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ_CHIP_HIT) else 0" }, { "BriefDescription": "Percentage sourced from Level 4 Local cache on same book", "MetricName": "l4lp", - "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ_DRAWER_HIT) else 0" }, { "BriefDescription": "Percentage sourced from Level 4 Remote cache on different book", "MetricName": "l4rp", - "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_OFF_DRAWER) else 0" }, { "BriefDescription": "Percentage sourced from memory", "MetricName": "memp", - "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_ON_CHIP_MEMORY) else 0" }, { "BriefDescription": "Cycles per Instructions from Finite cache/memory", "MetricName": "finite_cpi", - "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS" + "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS if has_event(L1C_TLB2_MISSES) else 0" }, { "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1", "MetricName": "est_cpi", - "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)" + "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS) if has_event(INSTRUCTIONS) else 0" }, { "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss", "MetricName": "scpl1m", - "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)" + "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES) if has_event(L1C_TLB2_MISSES) else 0" }, { "BriefDescription": "Estimated TLB CPU percentage of Total CPU", "MetricName": "tlb_percent", - "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100" + "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100 if has_event(CPU_CYCLES) else 0" }, { "BriefDescription": "Estimated Cycles per TLB Miss", "MetricName": "tlb_miss", - "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))" + "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) if has_event(DTLB2_MISSES) else 0" } ] diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv index a918e1af77a57..b22648d127517 100644 --- a/tools/perf/pmu-events/arch/s390/mapfile.csv +++ b/tools/perf/pmu-events/arch/s390/mapfile.csv @@ -5,4 +5,4 @@ Family-model,Version,Filename,EventType ^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core ^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core ^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_z15,core -^IBM.393[12].*3\.7.[[:xdigit:]]+$,3,cf_z16,core +^IBM.393[12].*$,3,cf_z16,core diff --git a/tools/perf/pmu-events/arch/x86/amdzen4/cache.json b/tools/perf/pmu-events/arch/x86/amdzen4/cache.json index ecbe9660b2b31..e6d710cf3ce29 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen4/cache.json +++ b/tools/perf/pmu-events/arch/x86/amdzen4/cache.json @@ -676,6 +676,10 @@ "EventCode": "0xac", "BriefDescription": "Average sampled latency when data is sourced from DRAM in the same NUMA node.", "UMask": "0x01", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -683,6 +687,10 @@ "EventCode": "0xac", "BriefDescription": "Average sampled latency when data is sourced from DRAM in a different NUMA node.", "UMask": "0x02", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -690,6 +698,10 @@ "EventCode": "0xac", "BriefDescription": "Average sampled latency when data is sourced from another CCX's cache when the address was in the same NUMA node.", "UMask": "0x04", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -697,6 +709,10 @@ "EventCode": "0xac", "BriefDescription": "Average sampled latency when data is sourced from another CCX's cache when the address was in a different NUMA node.", "UMask": "0x08", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -704,6 +720,10 @@ "EventCode": "0xac", "BriefDescription": "Average sampled latency when data is sourced from extension memory (CXL) in the same NUMA node.", "UMask": "0x10", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -711,6 +731,10 @@ "EventCode": "0xac", "BriefDescription": "Average sampled latency when data is sourced from extension memory (CXL) in a different NUMA node.", "UMask": "0x20", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -718,6 +742,10 @@ "EventCode": "0xac", "BriefDescription": "Average sampled latency from all data sources.", "UMask": "0x3f", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -725,6 +753,10 @@ "EventCode": "0xad", "BriefDescription": "L3 cache fill requests sourced from DRAM in the same NUMA node.", "UMask": "0x01", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -732,6 +764,10 @@ "EventCode": "0xad", "BriefDescription": "L3 cache fill requests sourced from DRAM in a different NUMA node.", "UMask": "0x02", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -739,6 +775,10 @@ "EventCode": "0xad", "BriefDescription": "L3 cache fill requests sourced from another CCX's cache when the address was in the same NUMA node.", "UMask": "0x04", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -746,6 +786,10 @@ "EventCode": "0xad", "BriefDescription": "L3 cache fill requests sourced from another CCX's cache when the address was in a different NUMA node.", "UMask": "0x08", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -753,6 +797,10 @@ "EventCode": "0xad", "BriefDescription": "L3 cache fill requests sourced from extension memory (CXL) in the same NUMA node.", "UMask": "0x10", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -760,6 +808,10 @@ "EventCode": "0xad", "BriefDescription": "L3 cache fill requests sourced from extension memory (CXL) in a different NUMA node.", "UMask": "0x20", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" }, { @@ -767,6 +819,10 @@ "EventCode": "0xad", "BriefDescription": "L3 cache fill requests sourced from all data sources.", "UMask": "0x3f", + "EnAllCores": "0x1", + "EnAllSlices": "0x1", + "SliceId": "0x3", + "ThreadMask": "0x3", "Unit": "L3PMC" } ] diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 53ab050c8fa43..ce846f29c08d6 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -356,6 +356,10 @@ def unit_to_pmu(unit: str) -> Optional[str]: ('UMask', 'umask='), ('NodeType', 'type='), ('RdWrMask', 'rdwrmask='), + ('EnAllCores', 'enallcores='), + ('EnAllSlices', 'enallslices='), + ('SliceId', 'sliceid='), + ('ThreadMask', 'threadmask='), ] for key, value in event_fields: if key in jd and jd[key] != '0': diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 7a3a7bbbec714..29d2f3ee4e10f 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -637,11 +637,11 @@ static int do_test_code_reading(bool try_kcore) evlist__config(evlist, &opts, NULL); - evsel = evlist__first(evlist); - - evsel->core.attr.comm = 1; - evsel->core.attr.disabled = 1; - evsel->core.attr.enable_on_exec = 0; + evlist__for_each_entry(evlist, evsel) { + evsel->core.attr.comm = 1; + evsel->core.attr.disabled = 1; + evsel->core.attr.enable_on_exec = 0; + } ret = evlist__open(evlist); if (ret < 0) { diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 65dd852071250..3302ea0b96723 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -188,7 +188,7 @@ arm_cs_etm_snapshot_test() { arm_cs_etm_basic_test() { echo "Recording trace with '$*'" - perf record -o ${perfdata} "$@" -- ls > /dev/null 2>&1 + perf record -o ${perfdata} "$@" -m,8M -- ls > /dev/null 2>&1 perf_script_branch_samples ls && perf_report_branch_samples ls && diff --git a/tools/perf/tests/workloads/datasym.c b/tools/perf/tests/workloads/datasym.c index ddd40bc63448a..8e08fc75a973e 100644 --- a/tools/perf/tests/workloads/datasym.c +++ b/tools/perf/tests/workloads/datasym.c @@ -16,6 +16,22 @@ static int datasym(int argc __maybe_unused, const char **argv __maybe_unused) { for (;;) { buf1.data1++; + if (buf1.data1 == 123) { + /* + * Add some 'noise' in the loop to work around errata + * 1694299 on Arm N1. + * + * Bias exists in SPE sampling which can cause the load + * and store instructions to be skipped entirely. This + * comes and goes randomly depending on the offset the + * linker places the datasym loop at in the Perf binary. + * With an extra branch in the middle of the loop that + * isn't always taken, the instruction stream is no + * longer a continuous repeating pattern that interacts + * badly with the bias. + */ + buf1.data1++; + } buf1.data2 += buf1.data1; } return 0; diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 603d11283cbdc..19503e8387385 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -203,7 +203,7 @@ void ui_browser__refresh_dimensions(struct ui_browser *browser) void ui_browser__handle_resize(struct ui_browser *browser) { ui__refresh_dimensions(false); - ui_browser__show(browser, browser->title, ui_helpline__current); + ui_browser__show(browser, browser->title ?: "", ui_helpline__current); ui_browser__refresh(browser); } @@ -287,7 +287,8 @@ int ui_browser__show(struct ui_browser *browser, const char *title, mutex_lock(&ui__lock); __ui_browser__show_title(browser, title); - browser->title = title; + free(browser->title); + browser->title = strdup(title); zfree(&browser->helpline); va_start(ap, helpline); @@ -304,6 +305,7 @@ void ui_browser__hide(struct ui_browser *browser) mutex_lock(&ui__lock); ui_helpline__pop(); zfree(&browser->helpline); + zfree(&browser->title); mutex_unlock(&ui__lock); } diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 510ce45540501..6e98d5f8f71cc 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -21,7 +21,7 @@ struct ui_browser { u8 extra_title_lines; int current_color; void *priv; - const char *title; + char *title; char *helpline; const char *no_samples_msg; void (*refresh_dimensions)(struct ui_browser *browser); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ec5e219328760..4790c735599bd 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -970,7 +970,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, if (dso->annotate_warned) return -1; - if (not_annotated) { + if (not_annotated || !sym->annotate2) { err = symbol__annotate2(ms, evsel, &browser.arch); if (err) { char msg[BUFSIZ]; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 9b70ab110ce79..78088dd73248b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2435,6 +2435,9 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, if (parch) *parch = arch; + if (!list_empty(¬es->src->source)) + return 0; + args.arch = arch; args.ms = *ms; if (annotate_opts.full_addr) @@ -2985,7 +2988,7 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m annotation__update_column_widths(notes); } -static void annotation__calc_lines(struct annotation *notes, struct map *map, +static void annotation__calc_lines(struct annotation *notes, struct map_symbol *ms, struct rb_root *root) { struct annotation_line *al; @@ -2993,6 +2996,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, list_for_each_entry(al, ¬es->src->source, node) { double percent_max = 0.0; + u64 addr; int i; for (i = 0; i < al->data_nr; i++) { @@ -3008,8 +3012,9 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, if (percent_max <= 0.5) continue; - al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL, - false, true, notes->start + al->offset); + addr = map__rip_2objdump(ms->map, ms->sym->start); + al->path = get_srcline(map__dso(ms->map), addr + al->offset, NULL, + false, true, ms->sym->start + al->offset); insert_source_line(&tmp_root, al); } @@ -3020,7 +3025,7 @@ static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root) { struct annotation *notes = symbol__annotation(ms->sym); - annotation__calc_lines(notes, ms->map, root); + annotation__calc_lines(notes, ms, root); } int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 3684e6009b635..ef314a5797e30 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1466,6 +1466,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, char *endptr; bool period_type_set = false; bool period_set = false; + bool iy = false; synth_opts->set = true; @@ -1484,6 +1485,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, switch (*p++) { case 'i': case 'y': + iy = true; if (p[-1] == 'y') synth_opts->cycles = true; else @@ -1649,7 +1651,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, } } out: - if (synth_opts->instructions || synth_opts->cycles) { + if (iy) { if (!period_type_set) synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE; diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 95cd8414f6ef8..e5d78565f479f 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -289,6 +289,7 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) struct task_struct *curr; struct mm_struct___old *mm_old; struct mm_struct___new *mm_new; + struct sighand_struct *sighand; switch (flags) { case LCB_F_READ: /* rwsem */ @@ -310,7 +311,9 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) break; case LCB_F_SPIN: /* spinlock */ curr = bpf_get_current_task_btf(); - if (&curr->sighand->siglock == (void *)lock) + sighand = curr->sighand; + + if (sighand && &sighand->siglock == (void *)lock) return LCD_F_SIGHAND_LOCK; break; default: diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index c29d8a382b196..550675ce0b787 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -430,8 +430,6 @@ int perf_data__switch(struct perf_data *data, { int ret; - if (check_pipe(data)) - return -EINVAL; if (perf_data__is_read(data)) return -EINVAL; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 6d7c9c58a9bcb..727dae445da9f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2363,7 +2363,6 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->period = evsel->core.attr.sample_period; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; data->misc = event->header.misc; - data->id = -1ULL; data->data_src = PERF_MEM_DATA_SRC_NONE; data->vcpu = -1; diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 7be23b3ac0821..b8875aac8f870 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -500,7 +500,25 @@ double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const tmp = evlist__new(); if (!tmp) return NAN; - ret = parse_event(tmp, id) ? 0 : 1; + + if (strchr(id, '@')) { + char *tmp_id, *p; + + tmp_id = strdup(id); + if (!tmp_id) { + ret = NAN; + goto out; + } + p = strchr(tmp_id, '@'); + *p = '/'; + p = strrchr(tmp_id, '@'); + *p = '/'; + ret = parse_event(tmp, tmp_id) ? 0 : 1; + free(tmp_id); + } else { + ret = parse_event(tmp, id) ? 0 : 1; + } +out: evlist__delete(tmp); return ret; } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index b450178e3420b..e733f6b1f7ac5 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1319,6 +1319,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder, bool no_tip) bool ret = false; decoder->state.type &= ~INTEL_PT_BRANCH; + decoder->state.insn_op = INTEL_PT_OP_OTHER; + decoder->state.insn_len = 0; if (decoder->set_fup_cfe_ip || decoder->set_fup_cfe) { bool ip = decoder->set_fup_cfe_ip; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index f38893e0b0369..4db9a098f5926 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -764,6 +764,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, addr_location__init(&al); intel_pt_insn->length = 0; + intel_pt_insn->op = INTEL_PT_OP_OTHER; if (to_ip && *ip == to_ip) goto out_no_cache; @@ -898,6 +899,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, if (to_ip && *ip == to_ip) { intel_pt_insn->length = 0; + intel_pt_insn->op = INTEL_PT_OP_OTHER; goto out_no_cache; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b397a769006f4..cdb7f455ba6df 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1709,8 +1709,8 @@ static int machine__update_kernel_mmap(struct machine *machine, updated = map__get(orig); machine->vmlinux_map = updated; - machine__set_kernel_mmap(machine, start, end); maps__remove(machine__kernel_maps(machine), orig); + machine__set_kernel_mmap(machine, start, end); err = maps__insert(machine__kernel_maps(machine), updated); map__put(orig); diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index 8f04d3b7f3ec7..59fbbba796974 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -7,6 +7,8 @@ #include #include #include "util/evsel_fprintf.h" +#include "util/pmu.h" +#include "util/pmus.h" #include "trace-event.h" struct bit_names { @@ -75,9 +77,12 @@ static void __p_read_format(char *buf, size_t size, u64 value) } #define ENUM_ID_TO_STR_CASE(x) case x: return (#x); -static const char *stringify_perf_type_id(u64 value) +static const char *stringify_perf_type_id(struct perf_pmu *pmu, u32 type) { - switch (value) { + if (pmu) + return pmu->name; + + switch (type) { ENUM_ID_TO_STR_CASE(PERF_TYPE_HARDWARE) ENUM_ID_TO_STR_CASE(PERF_TYPE_SOFTWARE) ENUM_ID_TO_STR_CASE(PERF_TYPE_TRACEPOINT) @@ -175,9 +180,9 @@ do { \ #define print_id_unsigned(_s) PRINT_ID(_s, "%"PRIu64) #define print_id_hex(_s) PRINT_ID(_s, "%#"PRIx64) -static void __p_type_id(char *buf, size_t size, u64 value) +static void __p_type_id(struct perf_pmu *pmu, char *buf, size_t size, u64 value) { - print_id_unsigned(stringify_perf_type_id(value)); + print_id_unsigned(stringify_perf_type_id(pmu, value)); } static void __p_config_hw_id(char *buf, size_t size, u64 value) @@ -217,8 +222,14 @@ static void __p_config_tracepoint_id(char *buf, size_t size, u64 value) } #endif -static void __p_config_id(char *buf, size_t size, u32 type, u64 value) +static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 value) { + const char *name = perf_pmu__name_from_config(pmu, value); + + if (name) { + print_id_hex(name); + return; + } switch (type) { case PERF_TYPE_HARDWARE: return __p_config_hw_id(buf, size, value); @@ -246,8 +257,8 @@ static void __p_config_id(char *buf, size_t size, u32 type, u64 value) #define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) #define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val) #define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) -#define p_type_id(val) __p_type_id(buf, BUF_SIZE, val) -#define p_config_id(val) __p_config_id(buf, BUF_SIZE, attr->type, val) +#define p_type_id(val) __p_type_id(pmu, buf, BUF_SIZE, val) +#define p_config_id(val) __p_config_id(pmu, buf, BUF_SIZE, attr->type, val) #define PRINT_ATTRn(_n, _f, _p, _a) \ do { \ @@ -262,6 +273,7 @@ do { \ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, attr__fprintf_f attr__fprintf, void *priv) { + struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); char buf[BUF_SIZE]; int ret = 0; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 3c9609944a2f3..f1b58784bdffe 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -36,6 +36,18 @@ struct perf_pmu perf_pmu__fake = { #define UNIT_MAX_LEN 31 /* max length for event unit name */ +enum event_source { + /* An event loaded from /sys/devices//events. */ + EVENT_SRC_SYSFS, + /* An event loaded from a CPUID matched json file. */ + EVENT_SRC_CPU_JSON, + /* + * An event loaded from a /sys/devices//identifier matched json + * file. + */ + EVENT_SRC_SYS_JSON, +}; + /** * struct perf_pmu_alias - An event either read from sysfs or builtin in * pmu-events.c, created by parsing the pmu-events json files. @@ -425,9 +437,30 @@ static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu, { struct perf_pmu_alias *alias; - if (load && !pmu->sysfs_aliases_loaded) - pmu_aliases_parse(pmu); + if (load && !pmu->sysfs_aliases_loaded) { + bool has_sysfs_event; + char event_file_name[FILENAME_MAX + 8]; + + /* + * Test if alias/event 'name' exists in the PMU's sysfs/events + * directory. If not skip parsing the sysfs aliases. Sysfs event + * name must be all lower or all upper case. + */ + scnprintf(event_file_name, sizeof(event_file_name), "events/%s", name); + for (size_t i = 7, n = 7 + strlen(name); i < n; i++) + event_file_name[i] = tolower(event_file_name[i]); + + has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name); + if (!has_sysfs_event) { + for (size_t i = 7, n = 7 + strlen(name); i < n; i++) + event_file_name[i] = toupper(event_file_name[i]); + + has_sysfs_event = perf_pmu__file_exists(pmu, event_file_name); + } + if (has_sysfs_event) + pmu_aliases_parse(pmu); + } list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, name)) return alias; @@ -500,7 +533,7 @@ static int update_alias(const struct pmu_event *pe, static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, const char *desc, const char *val, FILE *val_fd, - const struct pmu_event *pe) + const struct pmu_event *pe, enum event_source src) { struct perf_pmu_alias *alias; int ret; @@ -552,25 +585,30 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, } snprintf(alias->unit, sizeof(alias->unit), "%s", unit); } - if (!pe) { - /* Update an event from sysfs with json data. */ - struct update_alias_data data = { - .pmu = pmu, - .alias = alias, - }; - + switch (src) { + default: + case EVENT_SRC_SYSFS: alias->from_sysfs = true; if (pmu->events_table) { + /* Update an event from sysfs with json data. */ + struct update_alias_data data = { + .pmu = pmu, + .alias = alias, + }; if (pmu_events_table__find_event(pmu->events_table, pmu, name, update_alias, &data) == 0) - pmu->loaded_json_aliases++; + pmu->cpu_json_aliases++; } - } - - if (!pe) pmu->sysfs_aliases++; - else - pmu->loaded_json_aliases++; + break; + case EVENT_SRC_CPU_JSON: + pmu->cpu_json_aliases++; + break; + case EVENT_SRC_SYS_JSON: + pmu->sys_json_aliases++; + break; + + } list_add_tail(&alias->list, &pmu->aliases); return 0; } @@ -646,7 +684,8 @@ static int pmu_aliases_parse(struct perf_pmu *pmu) } if (perf_pmu__new_alias(pmu, name, /*desc=*/ NULL, - /*val=*/ NULL, file, /*pe=*/ NULL) < 0) + /*val=*/ NULL, file, /*pe=*/ NULL, + EVENT_SRC_SYSFS) < 0) pr_debug("Cannot set up %s\n", name); fclose(file); } @@ -899,7 +938,8 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe, { struct perf_pmu *pmu = vdata; - perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe); + perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, + pe, EVENT_SRC_CPU_JSON); return 0; } @@ -934,13 +974,14 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, return 0; if (pmu_uncore_alias_match(pe->pmu, pmu->name) && - pmu_uncore_identifier_match(pe->compat, pmu->id)) { + pmu_uncore_identifier_match(pe->compat, pmu->id)) { perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, - pe); + pe, + EVENT_SRC_SYS_JSON); } return 0; @@ -1019,10 +1060,9 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char * type value and format definitions. Load both right * now. */ - if (pmu_format(pmu, dirfd, name)) { - free(pmu); - return NULL; - } + if (pmu_format(pmu, dirfd, name)) + goto err; + pmu->is_core = is_pmu_core(name); pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core); @@ -1033,6 +1073,12 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char pmu->max_precise = pmu_max_precise(dirfd, pmu); pmu->alias_name = pmu_find_alias_name(pmu, dirfd); pmu->events_table = perf_pmu__find_events_table(pmu); + /* + * Load the sys json events/aliases when loading the PMU as each event + * may have a different compat regular expression. We therefore can't + * know the number of sys json events/aliases without computing the + * regular expressions for them all. + */ pmu_add_sys_aliases(pmu); list_add_tail(&pmu->list, pmus); @@ -1630,15 +1676,15 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu) { size_t nr; - if (!pmu->sysfs_aliases_loaded) - pmu_aliases_parse(pmu); - - nr = pmu->sysfs_aliases; + pmu_aliases_parse(pmu); + nr = pmu->sysfs_aliases + pmu->sys_json_aliases;; if (pmu->cpu_aliases_added) - nr += pmu->loaded_json_aliases; + nr += pmu->cpu_json_aliases; else if (pmu->events_table) - nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->loaded_json_aliases; + nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->cpu_json_aliases; + else + assert(pmu->cpu_json_aliases == 0); return pmu->selectable ? nr + 1 : nr; } @@ -1691,6 +1737,7 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, struct strbuf sb; strbuf_init(&sb, /*hint=*/ 0); + pmu_aliases_parse(pmu); pmu_add_cpu_aliases(pmu); list_for_each_entry(event, &pmu->aliases, list) { size_t buf_used; @@ -1760,6 +1807,12 @@ bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name) bool perf_pmu__is_software(const struct perf_pmu *pmu) { + const char *known_sw_pmus[] = { + "kprobe", + "msr", + "uprobe", + }; + if (pmu->is_core || pmu->is_uncore || pmu->auxtrace) return false; switch (pmu->type) { @@ -1771,7 +1824,11 @@ bool perf_pmu__is_software(const struct perf_pmu *pmu) case PERF_TYPE_BREAKPOINT: return true; default: break; } - return !strcmp(pmu->name, "kprobe") || !strcmp(pmu->name, "uprobe"); + for (size_t i = 0; i < ARRAY_SIZE(known_sw_pmus); i++) { + if (!strcmp(pmu->name, known_sw_pmus[i])) + return true; + } + return false; } FILE *perf_pmu__open_file(const struct perf_pmu *pmu, const char *name) @@ -2073,3 +2130,22 @@ void perf_pmu__delete(struct perf_pmu *pmu) zfree(&pmu->id); free(pmu); } + +const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config) +{ + struct perf_pmu_alias *event; + + if (!pmu) + return NULL; + + pmu_aliases_parse(pmu); + pmu_add_cpu_aliases(pmu); + list_for_each_entry(event, &pmu->aliases, list) { + struct perf_event_attr attr = {.config = 0,}; + int ret = perf_pmu__config(pmu, &attr, &event->terms, NULL); + + if (ret == 0 && config == attr.config) + return event->name; + } + return NULL; +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 424c3fee09496..25803ea92ed34 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -121,8 +121,10 @@ struct perf_pmu { const struct pmu_events_table *events_table; /** @sysfs_aliases: Number of sysfs aliases loaded. */ uint32_t sysfs_aliases; - /** @sysfs_aliases: Number of json event aliases loaded. */ - uint32_t loaded_json_aliases; + /** @cpu_json_aliases: Number of json event aliases loaded specific to the CPUID. */ + uint32_t cpu_json_aliases; + /** @sys_json_aliases: Number of json event aliases loaded matching the PMU's identifier. */ + uint32_t sys_json_aliases; /** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */ bool sysfs_aliases_loaded; /** @@ -266,5 +268,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus); void perf_pmu__delete(struct perf_pmu *pmu); struct perf_pmu *perf_pmus__find_core_pmu(void); +const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config); #endif /* __PMU_H */ diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index 9e47712507cc2..b14d1a894abce 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -232,7 +232,6 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state) bool is_event_supported(u8 type, u64 config) { bool ret = true; - int open_return; struct evsel *evsel; struct perf_event_attr attr = { .type = type, @@ -246,20 +245,32 @@ bool is_event_supported(u8 type, u64 config) evsel = evsel__new(&attr); if (evsel) { - open_return = evsel__open(evsel, NULL, tmap); - ret = open_return >= 0; + ret = evsel__open(evsel, NULL, tmap) >= 0; - if (open_return == -EACCES) { + if (!ret) { /* - * This happens if the paranoid value + * The event may fail to open if the paranoid value * /proc/sys/kernel/perf_event_paranoid is set to 2 - * Re-run with exclude_kernel set; we don't do that - * by default as some ARM machines do not support it. - * + * Re-run with exclude_kernel set; we don't do that by + * default as some ARM machines do not support it. */ evsel->core.attr.exclude_kernel = 1; ret = evsel__open(evsel, NULL, tmap) >= 0; } + + if (!ret) { + /* + * The event may fail to open if the PMU requires + * exclude_guest to be set (e.g. as the Apple M1 PMU + * requires). + * Re-run with exclude_guest set; we don't do that by + * default as it's equally legitimate for another PMU + * driver to require that exclude_guest is clear. + */ + evsel->core.attr.exclude_guest = 1; + ret = evsel__open(evsel, NULL, tmap) >= 0; + } + evsel__delete(evsel); } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a1a796043691f..d8e70a54d9e5e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 8761f51b5c7c8..ae4b2cd2e1e95 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -103,6 +103,16 @@ int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char return EOF; } +const char *perf_pmu__name_from_config(struct perf_pmu *pmu __maybe_unused, u64 config __maybe_unused) +{ + return NULL; +} + +struct perf_pmu *perf_pmus__find_by_type(unsigned int type __maybe_unused) +{ + return NULL; +} + int perf_pmus__num_core_pmus(void) { return 1; diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 034b496df2978..7addc34afcf5d 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -399,6 +399,8 @@ static void addr2line_subprocess_cleanup(struct child_process *a2l) kill(a2l->pid, SIGKILL); finish_command(a2l); /* ignore result, we don't care */ a2l->pid = -1; + close(a2l->in); + close(a2l->out); } free(a2l); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 8c61f8627ebc9..5f2e20448a074 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -560,7 +560,7 @@ static void print_metric_only(struct perf_stat_config *config, if (color) mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; - color_snprintf(str, sizeof(str), color ?: "", fmt, val); + color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val); fprintf(out, "%*s ", mlen, str); os->first = false; } @@ -1207,6 +1207,9 @@ static void print_metric_headers(struct perf_stat_config *config, /* Print metrics headers only */ evlist__for_each_entry(evlist, counter) { + if (config->aggr_mode != AGGR_NONE && counter->metric_leader != counter) + continue; + os.evsel = counter; perf_stat__print_shadow_stats(config, counter, 0, diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index e31426167852a..cf573ff3fa84f 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -414,12 +414,7 @@ static int prepare_metric(struct evsel **metric_events, val = NAN; source_count = 0; } else { - /* - * If an event was scaled during stat gathering, - * reverse the scale before computing the - * metric. - */ - val = aggr->counts.val * (1.0 / metric_events[i]->scale); + val = aggr->counts.val; source_count = evsel__source_count(metric_events[i]); } } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index be212ba157dc3..8e09f7db933a6 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1255,7 +1255,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, { struct maps *kmaps = map__kmaps(map); struct kcore_mapfn_data md; - struct map *replacement_map = NULL; + struct map *map_ref, *replacement_map = NULL; struct machine *machine; bool is_64_bit; int err, fd; @@ -1333,6 +1333,24 @@ static int dso__load_kcore(struct dso *dso, struct map *map, if (!replacement_map) replacement_map = list_entry(md.maps.next, struct map_list_node, node)->map; + /* + * Update addresses of vmlinux map. Re-insert it to ensure maps are + * correctly ordered. Do this before using maps__merge_in() for the + * remaining maps so vmlinux gets split if necessary. + */ + map_ref = map__get(map); + maps__remove(kmaps, map_ref); + + map__set_start(map_ref, map__start(replacement_map)); + map__set_end(map_ref, map__end(replacement_map)); + map__set_pgoff(map_ref, map__pgoff(replacement_map)); + map__set_mapping_type(map_ref, map__mapping_type(replacement_map)); + + err = maps__insert(kmaps, map_ref); + map__put(map_ref); + if (err) + goto out_err; + /* Add new maps */ while (!list_empty(&md.maps)) { struct map_list_node *new_node = list_entry(md.maps.next, struct map_list_node, node); @@ -1340,22 +1358,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map, list_del_init(&new_node->node); - if (RC_CHK_EQUAL(new_map, replacement_map)) { - struct map *map_ref; - - map__set_start(map, map__start(new_map)); - map__set_end(map, map__end(new_map)); - map__set_pgoff(map, map__pgoff(new_map)); - map__set_mapping_type(map, map__mapping_type(new_map)); - /* Ensure maps are correctly ordered */ - map_ref = map__get(map); - maps__remove(kmaps, map_ref); - err = maps__insert(kmaps, map_ref); - map__put(map_ref); - map__put(new_map); - if (err) - goto out_err; - } else { + /* skip if replacement_map, already inserted above */ + if (!RC_CHK_EQUAL(new_map, replacement_map)) { /* * Merge kcore map into existing maps, * and ensure that current maps (eBPF) @@ -1937,6 +1941,10 @@ int dso__load(struct dso *dso, struct map *map) return ret; } +/* + * Always takes ownership of vmlinux when vmlinux_allocated == true, even if + * it returns an error. + */ int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) { @@ -1955,8 +1963,11 @@ int dso__load_vmlinux(struct dso *dso, struct map *map, else symtab_type = DSO_BINARY_TYPE__VMLINUX; - if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type)) + if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type)) { + if (vmlinux_allocated) + free((char *) vmlinux); return -1; + } /* * dso__load_sym() may copy 'dso' which will result in the copies having @@ -1999,7 +2010,6 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map) err = dso__load_vmlinux(dso, map, filename, true); if (err > 0) goto out; - free(filename); } out: return err; @@ -2151,7 +2161,6 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map) err = dso__load_vmlinux(dso, map, filename, true); if (err > 0) return err; - free(filename); } if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) { diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 89c47a5098e28..0170e4b5340df 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -39,12 +39,13 @@ int thread__init_maps(struct thread *thread, struct machine *machine) struct thread *thread__new(pid_t pid, pid_t tid) { - char *comm_str; - struct comm *comm; RC_STRUCT(thread) *_thread = zalloc(sizeof(*_thread)); struct thread *thread; if (ADD_RC_CHK(thread, _thread) != NULL) { + struct comm *comm; + char comm_str[32]; + thread__set_pid(thread, pid); thread__set_tid(thread, tid); thread__set_ppid(thread, -1); @@ -56,13 +57,8 @@ struct thread *thread__new(pid_t pid, pid_t tid) init_rwsem(thread__namespaces_lock(thread)); init_rwsem(thread__comm_lock(thread)); - comm_str = malloc(32); - if (!comm_str) - goto err_thread; - - snprintf(comm_str, 32, ":%d", tid); + snprintf(comm_str, sizeof(comm_str), ":%d", tid); comm = comm__new(comm_str, 0, false); - free(comm_str); if (!comm) goto err_thread; @@ -76,7 +72,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) return thread; err_thread: - free(thread); + thread__delete(thread); return NULL; } diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index e848579e61a86..ea3b431b97830 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -280,13 +280,13 @@ struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str) threads->nr = ntasks; } out: + strlist__delete(slist); if (threads) refcount_set(&threads->refcnt, 1); return threads; out_free_threads: zfree(&threads); - strlist__delete(slist); goto out; } diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules index b71aada776889..378543e4a71b4 100644 --- a/tools/power/acpi/Makefile.rules +++ b/tools/power/acpi/Makefile.rules @@ -9,7 +9,7 @@ objdir := $(OUTPUT)tools/$(TOOL)/ toolobjs := $(addprefix $(objdir),$(TOOL_OBJS)) $(OUTPUT)$(TOOL): $(toolobjs) FORCE $(ECHO) " LD " $(subst $(OUTPUT),,$@) - $(QUIET) $(LD) $(CFLAGS) $(toolobjs) $(LDFLAGS) -L$(OUTPUT) -o $@ + $(QUIET_LINK)$(CC) $(CFLAGS) $(toolobjs) $(LDFLAGS) -L$(OUTPUT) -o $@ $(ECHO) " STRIP " $(subst $(OUTPUT),,$@) $(QUIET) $(STRIPCMD) $@ diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 8f08c3fd498d5..1ba6340d3b3da 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -370,7 +370,7 @@ below the processor's base frequency. Busy% = MPERF_delta/TSC_delta -Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval +Bzy_MHz = TSC_delta*APERF_delta/MPERF_delta/measurement_interval Note that these calculations depend on TSC_delta, so they are not reliable during intervals when TSC_MHz is not running at the base frequency. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 7a334377f92b9..eff0a342304f8 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -53,6 +53,8 @@ #define NAME_BYTES 20 #define PATH_BYTES 128 +#define MAX_NOFILE 0x8000 + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT }; @@ -629,6 +631,23 @@ static const struct platform_features adl_features = { .enable_tsc_tweak = 1, }; +static const struct platform_features arl_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC10, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .has_msr_core_c1_res = 1, + .has_ext_cst_msrs = 1, + .trl_msrs = TRL_BASE, + .tcc_offset_bits = 6, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .enable_tsc_tweak = 1, +}; + static const struct platform_features skx_features = { .has_msr_misc_feature_control = 1, .has_msr_misc_pwr_mgmt = 1, @@ -870,8 +889,10 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_FAM6_RAPTORLAKE_S, &adl_features }, { INTEL_FAM6_METEORLAKE, &cnl_features }, { INTEL_FAM6_METEORLAKE_L, &cnl_features }, - { INTEL_FAM6_ARROWLAKE, &cnl_features }, - { INTEL_FAM6_LUNARLAKE_M, &cnl_features }, + { INTEL_FAM6_ARROWLAKE_H, &arl_features }, + { INTEL_FAM6_ARROWLAKE_U, &arl_features }, + { INTEL_FAM6_ARROWLAKE, &arl_features }, + { INTEL_FAM6_LUNARLAKE_M, &arl_features }, { INTEL_FAM6_ATOM_SILVERMONT, &slv_features }, { INTEL_FAM6_ATOM_SILVERMONT_D, &slvd_features }, { INTEL_FAM6_ATOM_AIRMONT, &amt_features }, @@ -989,8 +1010,8 @@ struct pkg_data { unsigned long long pc8; unsigned long long pc9; unsigned long long pc10; - unsigned long long cpu_lpi; - unsigned long long sys_lpi; + long long cpu_lpi; + long long sys_lpi; unsigned long long pkg_wtd_core_c0; unsigned long long pkg_any_core_c0; unsigned long long pkg_any_gfxe_c0; @@ -1976,12 +1997,22 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_Pkgpc10)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10 / tsc); - if (DO_BIC(BIC_CPU_LPI)) - outp += - sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float); - if (DO_BIC(BIC_SYS_LPI)) - outp += - sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float); + if (DO_BIC(BIC_CPU_LPI)) { + if (p->cpu_lpi >= 0) + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + 100.0 * p->cpu_lpi / 1000000.0 / interval_float); + else + outp += sprintf(outp, "%s(neg)", (printed++ ? delim : "")); + } + if (DO_BIC(BIC_SYS_LPI)) { + if (p->sys_lpi >= 0) + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + 100.0 * p->sys_lpi / 1000000.0 / interval_float); + else + outp += sprintf(outp, "%s(neg)", (printed++ ? delim : "")); + } if (DO_BIC(BIC_PkgWatt)) outp += @@ -2444,9 +2475,10 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) - continue; - average.packages.counter[i] += p->counter[i]; + if ((mp->format == FORMAT_RAW) && (topo.num_packages == 0)) + average.packages.counter[i] = p->counter[i]; + else + average.packages.counter[i] += p->counter[i]; } return 0; } @@ -2599,7 +2631,7 @@ unsigned long long get_uncore_mhz(int package, int die) { char path[128]; - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/current_freq_khz", package, + sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d/current_freq_khz", package, die); return (snapshot_sysfs_counter(path) / 1000); @@ -3829,7 +3861,8 @@ void re_initialize(void) { free_all_buffers(); setup_all_buffers(false); - fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus); + fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, + topo.allowed_cpus); } void set_max_cpu_num(void) @@ -4567,20 +4600,15 @@ static void dump_sysfs_file(char *path) static void probe_intel_uncore_frequency(void) { int i, j; - char path[128]; + char path[256]; if (!genuine_intel) return; - if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK)) - return; - - /* Cluster level sysfs not supported yet. */ - if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK)) - return; + if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK)) + goto probe_cluster; - if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK)) - BIC_PRESENT(BIC_UNCORE_MHZ); + BIC_PRESENT(BIC_UNCORE_MHZ); if (quiet) return; @@ -4588,26 +4616,73 @@ static void probe_intel_uncore_frequency(void) for (i = 0; i < topo.num_packages; ++i) { for (j = 0; j < topo.num_die; ++j) { int k, l; + char path_base[128]; + + sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d", i, + j); - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/min_freq_khz", - i, j); + sprintf(path, "%s/min_freq_khz", path_base); k = read_sysfs_int(path); - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/max_freq_khz", - i, j); + sprintf(path, "%s/max_freq_khz", path_base); l = read_sysfs_int(path); - fprintf(outf, "Uncore Frequency pkg%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000); + fprintf(outf, "Uncore Frequency package%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000); - sprintf(path, - "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_min_freq_khz", - i, j); + sprintf(path, "%s/initial_min_freq_khz", path_base); k = read_sysfs_int(path); - sprintf(path, - "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_max_freq_khz", - i, j); + sprintf(path, "%s/initial_max_freq_khz", path_base); l = read_sysfs_int(path); - fprintf(outf, "(%d - %d MHz)\n", k / 1000, l / 1000); + fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000); + + sprintf(path, "%s/current_freq_khz", path_base); + k = read_sysfs_int(path); + fprintf(outf, " %d MHz\n", k / 1000); } } + return; + +probe_cluster: + if (access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00/current_freq_khz", R_OK)) + return; + + if (quiet) + return; + + for (i = 0;; ++i) { + int k, l; + char path_base[128]; + int package_id, domain_id, cluster_id; + + sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/uncore%02d", i); + + if (access(path_base, R_OK)) + break; + + sprintf(path, "%s/package_id", path_base); + package_id = read_sysfs_int(path); + + sprintf(path, "%s/domain_id", path_base); + domain_id = read_sysfs_int(path); + + sprintf(path, "%s/fabric_cluster_id", path_base); + cluster_id = read_sysfs_int(path); + + sprintf(path, "%s/min_freq_khz", path_base); + k = read_sysfs_int(path); + sprintf(path, "%s/max_freq_khz", path_base); + l = read_sysfs_int(path); + fprintf(outf, "Uncore Frequency package%d domain%d cluster%d: %d - %d MHz ", package_id, domain_id, + cluster_id, k / 1000, l / 1000); + + sprintf(path, "%s/initial_min_freq_khz", path_base); + k = read_sysfs_int(path); + sprintf(path, "%s/initial_max_freq_khz", path_base); + l = read_sysfs_int(path); + fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000); + + sprintf(path, "%s/current_freq_khz", path_base); + k = read_sysfs_int(path); + fprintf(outf, " %d MHz\n", k / 1000); + } } static void probe_graphics(void) @@ -5489,7 +5564,8 @@ void print_dev_latency(void) fd = open(path, O_RDONLY); if (fd < 0) { - warnx("capget(CAP_SYS_ADMIN) failed, try \"# setcap cap_sys_admin=ep %s\"", progname); + if (debug) + warnx("Read %s failed", path); return; } @@ -5623,6 +5699,7 @@ void process_cpuid() unsigned int eax, ebx, ecx, edx; unsigned int fms, family, model, stepping, ecx_flags, edx_flags; unsigned long long ucode_patch = 0; + bool ucode_patch_valid = false; eax = ebx = ecx = edx = 0; @@ -5652,6 +5729,8 @@ void process_cpuid() if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) warnx("get_msr(UCODE)"); + else + ucode_patch_valid = true; /* * check max extended function levels of CPUID. @@ -5662,9 +5741,12 @@ void process_cpuid() __cpuid(0x80000000, max_extended_level, ebx, ecx, edx); if (!quiet) { - fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d) microcode 0x%x\n", - family, model, stepping, family, model, stepping, - (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF)); + fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)", + family, model, stepping, family, model, stepping); + if (ucode_patch_valid) + fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF)); + fputc('\n', outf); + fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level); fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", ecx_flags & (1 << 0) ? "SSE3" : "-", @@ -6142,6 +6224,7 @@ void topology_update(void) topo.allowed_packages = 0; for_all_cpus(update_topo, ODD_COUNTERS); } + void setup_all_buffers(bool startup) { topology_probe(startup); @@ -6704,6 +6787,22 @@ void cmdline(int argc, char **argv) } } +void set_rlimit(void) +{ + struct rlimit limit; + + if (getrlimit(RLIMIT_NOFILE, &limit) < 0) + err(1, "Failed to get rlimit"); + + if (limit.rlim_max < MAX_NOFILE) + limit.rlim_max = MAX_NOFILE; + if (limit.rlim_cur < MAX_NOFILE) + limit.rlim_cur = MAX_NOFILE; + + if (setrlimit(RLIMIT_NOFILE, &limit) < 0) + err(1, "Failed to set rlimit"); +} + int main(int argc, char **argv) { int fd, ret; @@ -6729,6 +6828,9 @@ int main(int argc, char **argv) probe_sysfs(); + if (!getuid()) + set_rlimit(); + turbostat_init(); msr_sum_record(); diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 5fd9e594079cf..ebda9c366b2ba 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -1241,6 +1241,7 @@ unsigned int get_pkg_num(int cpu) retval = fscanf(fp, "%d\n", &pkg); if (retval != 1) errx(1, "%s: failed to parse", pathname); + fclose(fp); return pkg; } diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 35ee41e435ab3..0d0ca63de8629 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -3,6 +3,7 @@ #include #include +#include #include #include #include diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 829f5bdfd2e43..24451f8f42910 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -843,6 +843,7 @@ sub set_value { if ($lvalue =~ /^(TEST|BISECT|CONFIG_BISECT)_TYPE(\[.*\])?$/ && $prvalue !~ /^(config_|)bisect$/ && $prvalue !~ /^build$/ && + $prvalue !~ /^make_warnings_file$/ && $buildonly) { # Note if a test is something other than build, then we diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 5af9ba8a4645b..c1ce39874e2b5 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # -CFLAGS += $(shell pkg-config --cflags alsa) +CFLAGS += $(shell pkg-config --cflags alsa) $(KHDR_INCLUDES) LDLIBS += $(shell pkg-config --libs alsa) ifeq ($(LDLIBS),) LDLIBS += -lasound diff --git a/tools/testing/selftests/arm64/tags/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c index 5701163460ef7..955f87c1170d7 100644 --- a/tools/testing/selftests/arm64/tags/tags_test.c +++ b/tools/testing/selftests/arm64/tags/tags_test.c @@ -6,6 +6,7 @@ #include #include #include +#include "../../kselftest.h" #define SHIFT_TAG(tag) ((uint64_t)(tag) << 56) #define SET_TAG(ptr, tag) (((uint64_t)(ptr) & ~SHIFT_TAG(0xff)) | \ @@ -21,6 +22,9 @@ int main(void) if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, 0, 0, 0) == 0) tbi_enabled = 1; ptr = (struct utsname *)malloc(sizeof(*ptr)); + if (!ptr) + ksft_exit_fail_msg("Failed to allocate utsname buffer\n"); + if (tbi_enabled) tag = 0x42; ptr = (struct utsname *)SET_TAG(ptr, tag); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index fd15017ed3b12..de302f8d4fe71 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -386,7 +386,8 @@ BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ # TODO: enable me -Wsign-compare CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ - -Wno-compare-distinct-pointer-types + -Wno-compare-distinct-pointer-types \ + -Wno-incompatible-pointer-types $(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 91907b321f913..e7c9e1c7fde04 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include #include +#include #include #include #include @@ -544,6 +545,14 @@ static int bpf_testmod_init(void) static void bpf_testmod_exit(void) { + /* Need to wait for all references to be dropped because + * bpf_kfunc_call_test_release() which currently resides in kernel can + * be called after bpf_testmod is unloaded. Once release function is + * moved into the module this wait can be removed. + */ + while (refcount_read(&prog_test_struct.cnt) > 1) + msleep(20); + return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 19be9c63d5e84..e812876d79c7e 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -508,6 +508,9 @@ int cgroup_setup_and_join(const char *path) { /** * setup_classid_environment() - Setup the cgroupv1 net_cls environment * + * This function should only be called in a custom mount namespace, e.g. + * created by running setup_cgroup_environment. + * * After calling this function, cleanup_classid_environment should be called * once testing is complete. * diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 6db27a9088e97..be96bf022316f 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -461,6 +461,8 @@ struct nstoken *open_netns(const char *name) return token; fail: + if (token->orig_netns_fd != -1) + close(token->orig_netns_fd); free(token); return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index 053f4d6da77a4..cc184e4420f6e 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -2,6 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include +#include #include #include "bloom_filter_map.skel.h" @@ -21,6 +22,11 @@ static void test_fail_cases(void) if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0")) close(fd); + /* Invalid value size: too big */ + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, INT32_MAX, 100, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value too large")) + close(fd); + /* Invalid max entries size */ fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL); if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size")) diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index a8b53b8736f01..f66ceccd7029c 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -25,7 +25,7 @@ static void test_lookup_update(void) int map1_fd, map2_fd, map3_fd, map4_fd, map5_fd, map1_id, map2_id; int outer_arr_fd, outer_hash_fd, outer_arr_dyn_fd; struct test_btf_map_in_map *skel; - int err, key = 0, val, i, fd; + int err, key = 0, val, i; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -102,30 +102,6 @@ static void test_lookup_update(void) CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); - test_btf_map_in_map__destroy(skel); - skel = NULL; - - /* we need to either wait for or force synchronize_rcu(), before - * checking for "still exists" condition, otherwise map could still be - * resolvable by ID, causing false positives. - * - * Older kernels (5.8 and earlier) freed map only after two - * synchronize_rcu()s, so trigger two, to be entirely sure. - */ - CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); - CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); - - fd = bpf_map_get_fd_by_id(map1_id); - if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { - close(fd); - goto cleanup; - } - fd = bpf_map_get_fd_by_id(map2_id); - if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { - close(fd); - goto cleanup; - } - cleanup: test_btf_map_in_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c index 74d6d7546f40f..25332e596750f 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c @@ -87,9 +87,12 @@ void test_cgroup1_hierarchy(void) goto destroy; /* Setup cgroup1 hierarchy */ + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto destroy; err = setup_classid_environment(); if (!ASSERT_OK(err, "setup_classid_environment")) - goto destroy; + goto cleanup_cgroup; err = join_classid(); if (!ASSERT_OK(err, "join_cgroup1")) @@ -153,6 +156,8 @@ void test_cgroup1_hierarchy(void) cleanup: cleanup_classid_environment(); +cleanup_cgroup: + cleanup_cgroup_environment(); destroy: test_cgroup1_hierarchy__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c index 59b38569f310b..2bc932a18c17e 100644 --- a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c @@ -203,6 +203,7 @@ static int setup_redirect_target(const char *target_dev, bool need_mac) if (!ASSERT_GE(target_index, 0, "if_nametoindex")) goto fail; + SYS(fail, "sysctl -w net.ipv6.conf.all.disable_ipv6=1"); SYS(fail, "ip link add link_err type dummy"); SYS(fail, "ip link set lo up"); SYS(fail, "ip addr add dev lo " LOCAL_SRC "/32"); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 518f143c5b0fe..dbe06aeaa2b27 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -188,6 +188,7 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) { struct nstoken *nstoken = NULL; char src_fwd_addr[IFADDR_STR_LEN+1] = {}; + char src_addr[IFADDR_STR_LEN + 1] = {}; int err; if (result->dev_mode == MODE_VETH) { @@ -208,6 +209,9 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) if (get_ifaddr("src_fwd", src_fwd_addr)) goto fail; + if (get_ifaddr("src", src_addr)) + goto fail; + result->ifindex_src = if_nametoindex("src"); if (!ASSERT_GT(result->ifindex_src, 0, "ifindex_src")) goto fail; @@ -270,6 +274,13 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) SYS(fail, "ip route add " IP4_DST "/32 dev dst_fwd scope global"); SYS(fail, "ip route add " IP6_DST "/128 dev dst_fwd scope global"); + if (result->dev_mode == MODE_VETH) { + SYS(fail, "ip neigh add " IP4_SRC " dev src_fwd lladdr %s", src_addr); + SYS(fail, "ip neigh add " IP6_SRC " dev src_fwd lladdr %s", src_addr); + SYS(fail, "ip neigh add " IP4_DST " dev dst_fwd lladdr %s", MAC_DST); + SYS(fail, "ip neigh add " IP6_DST " dev dst_fwd lladdr %s", MAC_DST); + } + close_netns(nstoken); /** setup in 'dst' namespace */ @@ -280,6 +291,7 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) SYS(fail, "ip addr add " IP4_DST "/32 dev dst"); SYS(fail, "ip addr add " IP6_DST "/128 dev dst nodad"); SYS(fail, "ip link set dev dst up"); + SYS(fail, "ip link set dev lo up"); SYS(fail, "ip route add " IP4_SRC "/32 dev dst scope global"); SYS(fail, "ip route add " IP4_NET "/16 dev dst scope global"); @@ -457,7 +469,7 @@ static int set_forwarding(bool enable) return 0; } -static void rcv_tstamp(int fd, const char *expected, size_t s) +static int __rcv_tstamp(int fd, const char *expected, size_t s, __u64 *tstamp) { struct __kernel_timespec pkt_ts = {}; char ctl[CMSG_SPACE(sizeof(pkt_ts))]; @@ -478,7 +490,7 @@ static void rcv_tstamp(int fd, const char *expected, size_t s) ret = recvmsg(fd, &msg, 0); if (!ASSERT_EQ(ret, s, "recvmsg")) - return; + return -1; ASSERT_STRNEQ(data, expected, s, "expected rcv data"); cmsg = CMSG_FIRSTHDR(&msg); @@ -487,6 +499,12 @@ static void rcv_tstamp(int fd, const char *expected, size_t s) memcpy(&pkt_ts, CMSG_DATA(cmsg), sizeof(pkt_ts)); pkt_ns = pkt_ts.tv_sec * NSEC_PER_SEC + pkt_ts.tv_nsec; + if (tstamp) { + /* caller will check the tstamp itself */ + *tstamp = pkt_ns; + return 0; + } + ASSERT_NEQ(pkt_ns, 0, "pkt rcv tstamp"); ret = clock_gettime(CLOCK_REALTIME, &now_ts); @@ -496,6 +514,60 @@ static void rcv_tstamp(int fd, const char *expected, size_t s) if (ASSERT_GE(now_ns, pkt_ns, "check rcv tstamp")) ASSERT_LT(now_ns - pkt_ns, 5 * NSEC_PER_SEC, "check rcv tstamp"); + return 0; +} + +static void rcv_tstamp(int fd, const char *expected, size_t s) +{ + __rcv_tstamp(fd, expected, s, NULL); +} + +static int wait_netstamp_needed_key(void) +{ + int opt = 1, srv_fd = -1, cli_fd = -1, nretries = 0, err, n; + char buf[] = "testing testing"; + struct nstoken *nstoken; + __u64 tstamp = 0; + + nstoken = open_netns(NS_DST); + if (!nstoken) + return -1; + + srv_fd = start_server(AF_INET6, SOCK_DGRAM, "::1", 0, 0); + if (!ASSERT_GE(srv_fd, 0, "start_server")) + goto done; + + err = setsockopt(srv_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + &opt, sizeof(opt)); + if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)")) + goto done; + + cli_fd = connect_to_fd(srv_fd, TIMEOUT_MILLIS); + if (!ASSERT_GE(cli_fd, 0, "connect_to_fd")) + goto done; + +again: + n = write(cli_fd, buf, sizeof(buf)); + if (!ASSERT_EQ(n, sizeof(buf), "send to server")) + goto done; + err = __rcv_tstamp(srv_fd, buf, sizeof(buf), &tstamp); + if (!ASSERT_OK(err, "__rcv_tstamp")) + goto done; + if (!tstamp && nretries++ < 5) { + sleep(1); + printf("netstamp_needed_key retry#%d\n", nretries); + goto again; + } + +done: + if (!tstamp && srv_fd != -1) { + close(srv_fd); + srv_fd = -1; + } + if (cli_fd != -1) + close(cli_fd); + close_netns(nstoken); + return srv_fd; } static void snd_tstamp(int fd, char *b, size_t s) @@ -832,11 +904,20 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result) { struct test_tc_dtime *skel; struct nstoken *nstoken; - int err; + int hold_tstamp_fd, err; + + /* Hold a sk with the SOCK_TIMESTAMP set to ensure there + * is no delay in the kernel net_enable_timestamp(). + * This ensures the following tests must have + * non zero rcv tstamp in the recvmsg(). + */ + hold_tstamp_fd = wait_netstamp_needed_key(); + if (!ASSERT_GE(hold_tstamp_fd, 0, "wait_netstamp_needed_key")) + return; skel = test_tc_dtime__open(); if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open")) - return; + goto done; skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd; skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; @@ -881,6 +962,7 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result) done: test_tc_dtime__destroy(skel); + close(hold_tstamp_fd); } static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result) diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 8269cdee33ae9..38fda42fd70f9 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -397,7 +397,7 @@ static void test_attach_api_fails(void) link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); if (!ASSERT_ERR(link_fd, "link_fd")) goto cleanup; - ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong"); + ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong"); cleanup: if (link_fd >= 0) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index 498d3bdaa4b0b..bad0ea167be70 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -107,8 +107,8 @@ void test_xdp_do_redirect(void) .attach_point = BPF_TC_INGRESS); memcpy(&data[sizeof(__u64)], &pkt_udp, sizeof(pkt_udp)); - *((__u32 *)data) = 0x42; /* metadata test value */ - *((__u32 *)data + 4) = 0; + ((__u32 *)data)[0] = 0x42; /* metadata test value */ + ((__u32 *)data)[1] = 0; skel = test_xdp_do_redirect__open(); if (!ASSERT_OK_PTR(skel, "skel")) diff --git a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c index e4bfbba6c1936..c8ec0d0368e4a 100644 --- a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c +++ b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c @@ -61,14 +61,15 @@ SEC("lsm.s/socket_post_create") int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, int protocol, int kern) { + struct sock *sk = sock->sk; struct storage *stg; __u32 pid; pid = bpf_get_current_pid_tgid() >> 32; - if (pid != bench_pid) + if (pid != bench_pid || !sk) return 0; - stg = bpf_sk_storage_get(&sk_storage_map, sock->sk, NULL, + stg = bpf_sk_storage_get(&sk_storage_map, sk, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE); if (stg) diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c index e5e3a8b8dd075..637e75df2e146 100644 --- a/tools/testing/selftests/bpf/progs/local_storage.c +++ b/tools/testing/selftests/bpf/progs/local_storage.c @@ -140,11 +140,12 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, { __u32 pid = bpf_get_current_pid_tgid() >> 32; struct local_storage *storage; + struct sock *sk = sock->sk; - if (pid != monitored_pid) + if (pid != monitored_pid || !sk) return 0; - storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, 0); + storage = bpf_sk_storage_get(&sk_storage_map, sk, 0, 0); if (!storage) return 0; @@ -155,24 +156,24 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, /* This tests that we can associate multiple elements * with the local storage. */ - storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!storage) return 0; - if (bpf_sk_storage_delete(&sk_storage_map2, sock->sk)) + if (bpf_sk_storage_delete(&sk_storage_map2, sk)) return 0; - storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!storage) return 0; - if (bpf_sk_storage_delete(&sk_storage_map, sock->sk)) + if (bpf_sk_storage_delete(&sk_storage_map, sk)) return 0; /* Ensure that the sk_storage_map is disconnected from the storage. */ - if (!sock->sk->sk_bpf_storage || sock->sk->sk_bpf_storage->smap) + if (!sk->sk_bpf_storage || sk->sk_bpf_storage->smap) return 0; sk_storage_result = 0; @@ -185,11 +186,12 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, { __u32 pid = bpf_get_current_pid_tgid() >> 32; struct local_storage *storage; + struct sock *sk = sock->sk; - if (pid != monitored_pid) + if (pid != monitored_pid || !sk) return 0; - storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0, + storage = bpf_sk_storage_get(&sk_storage_map, sk, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!storage) return 0; diff --git a/tools/testing/selftests/bpf/progs/lsm_cgroup.c b/tools/testing/selftests/bpf/progs/lsm_cgroup.c index 02c11d16b692a..d7598538aa2da 100644 --- a/tools/testing/selftests/bpf/progs/lsm_cgroup.c +++ b/tools/testing/selftests/bpf/progs/lsm_cgroup.c @@ -103,11 +103,15 @@ static __always_inline int real_bind(struct socket *sock, int addrlen) { struct sockaddr_ll sa = {}; + struct sock *sk = sock->sk; - if (sock->sk->__sk_common.skc_family != AF_PACKET) + if (!sk) + return 1; + + if (sk->__sk_common.skc_family != AF_PACKET) return 1; - if (sock->sk->sk_kern_sock) + if (sk->sk_kern_sock) return 1; bpf_probe_read_kernel(&sa, sizeof(sa), address); diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index de3b6e4e4d0a7..00380ac73ce01 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -63,11 +63,11 @@ volatile struct profiler_config_struct bpf_config = {}; #define READ_ENVIRON_FROM_EXEC (bpf_config.read_environ_from_exec) #define ENABLE_CGROUP_V1_RESOLVER (bpf_config.enable_cgroup_v1_resolver) -struct kernfs_iattrs___52 { +struct _kernfs_iattrs___52 { struct iattr ia_iattr; }; -struct kernfs_node___52 { +struct _kernfs_node___52 { union /* kernfs_node_id */ { struct { u32 ino; @@ -232,7 +232,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node, static ino_t get_inode_from_kernfs(struct kernfs_node* node) { - struct kernfs_node___52* node52 = (void*)node; + struct _kernfs_node___52* node52 = (void*)node; if (bpf_core_field_exists(node52->id.ino)) { barrier_var(node52); @@ -287,13 +287,13 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, cgroup_data->cgroup_proc_mtime = BPF_CORE_READ(proc_kernfs, iattr, ia_mtime.tv_nsec); } else { - struct kernfs_iattrs___52* root_iattr = - (struct kernfs_iattrs___52*)BPF_CORE_READ(root_kernfs, iattr); + struct _kernfs_iattrs___52* root_iattr = + (struct _kernfs_iattrs___52*)BPF_CORE_READ(root_kernfs, iattr); cgroup_data->cgroup_root_mtime = BPF_CORE_READ(root_iattr, ia_iattr.ia_mtime.tv_nsec); - struct kernfs_iattrs___52* proc_iattr = - (struct kernfs_iattrs___52*)BPF_CORE_READ(proc_kernfs, iattr); + struct _kernfs_iattrs___52* proc_iattr = + (struct _kernfs_iattrs___52*)BPF_CORE_READ(proc_kernfs, iattr); cgroup_data->cgroup_proc_mtime = BPF_CORE_READ(proc_iattr, ia_iattr.ia_mtime.tv_nsec); } diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index f416032ba858b..b295f9b721bf8 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -21,6 +21,32 @@ struct { __type(value, __u32); } mim_hash SEC(".maps"); +/* The following three maps are used to test + * perf_event_array map can be an inner + * map of hash/array_of_maps. + */ +struct perf_event_array { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __type(key, __u32); + __type(value, __u32); +} inner_map0 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, __u32); + __array(values, struct perf_event_array); +} mim_array_pe SEC(".maps") = { + .values = {&inner_map0}}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 1); + __type(key, __u32); + __array(values, struct perf_event_array); +} mim_hash_pe SEC(".maps") = { + .values = {&inner_map0}}; + SEC("xdp") int xdp_mimtest0(struct xdp_md *ctx) { diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index 67dddd9418911..27f4b2da131b1 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -8,6 +8,13 @@ #include "xdp_metadata.h" #include "bpf_kfuncs.h" +/* The compiler may be able to detect the access to uninitialized + memory in the routines performing out of bound memory accesses and + emit warnings about it. This is the case of GCC. */ +#if !defined(__clang__) +#pragma GCC diagnostic ignored "-Wmaybe-uninitialized" +#endif + int arr[1]; int unkn_idx; const volatile bool call_dead_subprog = false; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 767e0693df106..dfbab214f4d1c 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1190,7 +1190,11 @@ static void test_map_in_map(void) goto out_map_in_map; } - bpf_object__load(obj); + err = bpf_object__load(obj); + if (err) { + printf("Failed to load test prog\n"); + goto out_map_in_map; + } map = bpf_object__find_map_by_name(obj, "mim_array"); if (!map) { diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 024a0faafb3be..43612de44fbf5 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -2104,9 +2104,9 @@ int main(int argc, char **argv) free(options.whitelist); if (options.blacklist) free(options.blacklist); + close(cg_fd); if (cg_created) cleanup_cgroup_environment(); - close(cg_fd); return err; } diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index 910044f08908a..7989ec6084545 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -72,7 +72,6 @@ cleanup() { server_listen() { ip netns exec "${ns2}" nc "${netcat_opt}" -l "${port}" > "${outfile}" & server_pid=$! - sleep 0.2 } client_connect() { @@ -93,6 +92,16 @@ verify_data() { fi } +wait_for_port() { + for i in $(seq 20); do + if ip netns exec "${ns2}" ss ${2:--4}OHntl | grep -q "$1"; then + return 0 + fi + sleep 0.1 + done + return 1 +} + set -e # no arguments: automated test, run all @@ -193,6 +202,7 @@ setup # basic communication works echo "test basic connectivity" server_listen +wait_for_port ${port} ${netcat_opt} client_connect verify_data @@ -204,6 +214,7 @@ ip netns exec "${ns1}" tc filter add dev veth1 egress \ section "encap_${tuntype}_${mac}" echo "test bpf encap without decap (expect failure)" server_listen +wait_for_port ${port} ${netcat_opt} ! client_connect if [[ "$tuntype" =~ "udp" ]]; then diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 4faa898ff7fc4..27fd7ed3e4b0c 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -271,7 +271,7 @@ ssize_t get_uprobe_offset(const void *addr) * addi r2,r2,XXXX */ { - const u32 *insn = (const u32 *)(uintptr_t)addr; + const __u32 *insn = (const __u32 *)(uintptr_t)addr; if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) || ((*insn & OP_RT_RA_MASK) == LIS_R2)) && diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 0340d4ca8f51c..432db923bced0 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -195,10 +195,10 @@ int cg_write_numeric(const char *cgroup, const char *control, long value) return cg_write(cgroup, control, buf); } -int cg_find_unified_root(char *root, size_t len) +int cg_find_unified_root(char *root, size_t len, bool *nsdelegate) { char buf[10 * PAGE_SIZE]; - char *fs, *mount, *type; + char *fs, *mount, *type, *options; const char delim[] = "\n\t "; if (read_text("/proc/self/mounts", buf, sizeof(buf)) <= 0) @@ -211,12 +211,14 @@ int cg_find_unified_root(char *root, size_t len) for (fs = strtok(buf, delim); fs; fs = strtok(NULL, delim)) { mount = strtok(NULL, delim); type = strtok(NULL, delim); - strtok(NULL, delim); + options = strtok(NULL, delim); strtok(NULL, delim); strtok(NULL, delim); if (strcmp(type, "cgroup2") == 0) { strncpy(root, mount, len); + if (nsdelegate) + *nsdelegate = !!strstr(options, "nsdelegate"); return 0; } } diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 1df7f202214af..89e8519fb2719 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -21,7 +21,7 @@ static inline int values_close(long a, long b, int err) return abs(a - b) <= (a + b) / 100 * err; } -extern int cg_find_unified_root(char *root, size_t len); +extern int cg_find_unified_root(char *root, size_t len, bool *nsdelegate); extern char *cg_name(const char *root, const char *name); extern char *cg_name_indexed(const char *root, const char *name, int index); extern char *cg_control(const char *cgroup, const char *control); diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index 80aa6b2373b96..a5672a91d273c 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -18,6 +18,8 @@ #include "../kselftest.h" #include "cgroup_util.h" +static bool nsdelegate; + static int touch_anon(char *buf, size_t size) { int fd; @@ -775,6 +777,9 @@ static int test_cgcore_lesser_ns_open(const char *root) pid_t pid; int status; + if (!nsdelegate) + return KSFT_SKIP; + cg_test_a = cg_name(root, "cg_test_a"); cg_test_b = cg_name(root, "cg_test_b"); @@ -862,7 +867,7 @@ int main(int argc, char *argv[]) char root[PATH_MAX]; int i, ret = EXIT_SUCCESS; - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) ksft_exit_skip("cgroup v2 isn't mounted\n"); if (cg_read_strstr(root, "cgroup.subtree_control", "memory")) diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c index 24020a2c68dcd..186bf96f6a284 100644 --- a/tools/testing/selftests/cgroup/test_cpu.c +++ b/tools/testing/selftests/cgroup/test_cpu.c @@ -700,7 +700,7 @@ int main(int argc, char *argv[]) char root[PATH_MAX]; int i, ret = EXIT_SUCCESS; - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); if (cg_read_strstr(root, "cgroup.subtree_control", "cpu")) diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c index b061ed1e05b4d..4034d14ba69ac 100644 --- a/tools/testing/selftests/cgroup/test_cpuset.c +++ b/tools/testing/selftests/cgroup/test_cpuset.c @@ -249,7 +249,7 @@ int main(int argc, char *argv[]) char root[PATH_MAX]; int i, ret = EXIT_SUCCESS; - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); if (cg_read_strstr(root, "cgroup.subtree_control", "cpuset")) diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 8845353aca53b..8730645d363a7 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -827,7 +827,7 @@ int main(int argc, char *argv[]) char root[PATH_MAX]; int i, ret = EXIT_SUCCESS; - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c index f0fefeb4cc24c..856f9508ea562 100644 --- a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c +++ b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c @@ -214,7 +214,7 @@ int main(int argc, char **argv) return ret; } - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); switch (test_hugetlb_memcg(root)) { diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c index 6153690319c9c..0e5bb6c7307a5 100644 --- a/tools/testing/selftests/cgroup/test_kill.c +++ b/tools/testing/selftests/cgroup/test_kill.c @@ -276,7 +276,7 @@ int main(int argc, char *argv[]) char root[PATH_MAX]; int i, ret = EXIT_SUCCESS; - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index c82f974b85c94..137506db03127 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -420,7 +420,7 @@ int main(int argc, char **argv) char root[PATH_MAX]; int i, ret = EXIT_SUCCESS; - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); /* diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index c7c9572003a8c..b462416b38061 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -1314,7 +1314,7 @@ int main(int argc, char **argv) char root[PATH_MAX]; int i, proc_status, ret = EXIT_SUCCESS; - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); /* diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index 47fdaa1464430..e1169d3e620f0 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -324,7 +324,7 @@ int main(int argc, char **argv) char root[PATH_MAX]; int i, ret = EXIT_SUCCESS; - if (cg_find_unified_root(root, sizeof(root))) + if (cg_find_unified_root(root, sizeof(root), NULL)) ksft_exit_skip("cgroup v2 isn't mounted\n"); if (!zswap_configured()) diff --git a/tools/testing/selftests/damon/_damon_sysfs.py b/tools/testing/selftests/damon/_damon_sysfs.py index e98cf4b6a4b76..f9fead3d0f018 100644 --- a/tools/testing/selftests/damon/_damon_sysfs.py +++ b/tools/testing/selftests/damon/_damon_sysfs.py @@ -241,6 +241,8 @@ def stage(self): nr_schemes_file = os.path.join( self.sysfs_dir(), 'schemes', 'nr_schemes') content, err = read_file(nr_schemes_file) + if err is not None: + return err if int(content) != len(self.schemes): err = write_file(nr_schemes_file, '%d' % len(self.schemes)) if err != None: diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile index c2f7cef919c04..eb4c3b4119348 100644 --- a/tools/testing/selftests/filesystems/binderfs/Makefile +++ b/tools/testing/selftests/filesystems/binderfs/Makefile @@ -3,6 +3,4 @@ CFLAGS += $(KHDR_INCLUDES) -pthread TEST_GEN_PROGS := binderfs_test -binderfs_test: binderfs_test.c ../../kselftest.h ../../kselftest_harness.h - include ../../lib.mk diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc index b9c21a81d2481..c0cdad4c400e8 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_btfarg.tc @@ -53,7 +53,7 @@ fi echo > dynamic_events -if [ "$FIELDS" ] ; then +if [ "$FIELDS" -a "$FPROBES" ] ; then echo "t:tpevent ${TP2} obj_size=s->object_size" >> dynamic_events echo "f:fpevent ${TP3}%return path=\$retval->name:string" >> dynamic_events echo "t:tpevent2 ${TP4} p->se.group_node.next->prev" >> dynamic_events diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc index d3a79da215c8b..5f72abe6fa79b 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Generic dynamic event - check if duplicate events are caught -# requires: dynamic_events "e[:[/][]] . []":README +# requires: dynamic_events "e[:[/][]] . []":README events/syscalls/sys_enter_openat echo 0 > events/enable diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index b1ede62498667..b7c8f29c09a97 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -18,7 +18,7 @@ echo 'sched:*' > set_event yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -29,7 +29,7 @@ echo 1 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -40,7 +40,7 @@ echo 0 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -ne 0 ]; then fail "any of scheduler events should not be recorded" fi diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index 2de7c61d1ae30..118247b8dd84d 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -10,7 +10,6 @@ fail() { #msg } sample_events() { - echo > trace echo 1 > events/kmem/kmem_cache_free/enable echo 1 > tracing_on ls > /dev/null @@ -22,9 +21,10 @@ echo 0 > tracing_on echo 0 > events/enable echo "Get the most frequently calling function" +echo > trace sample_events -target_func=`cut -d: -f3 trace | sed 's/call_site=\([^+]*\)+0x.*/\1/' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` +target_func=`cat trace | grep -o 'call_site=\([^+]*\)' | sed 's/call_site=//' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` if [ -z "$target_func" ]; then exit_fail fi @@ -32,7 +32,16 @@ echo > trace echo "Test event filter function name" echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter + +sample_events +max_retry=10 +while [ `grep kmem_cache_free trace| wc -l` -eq 0 ]; do sample_events +max_retry=$((max_retry - 1)) +if [ $max_retry -eq 0 ]; then + exit_fail +fi +done hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` @@ -49,7 +58,16 @@ address=`grep " ${target_func}\$" /proc/kallsyms | cut -d' ' -f1` echo "Test event filter function address" echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter +echo > trace +sample_events +max_retry=10 +while [ `grep kmem_cache_free trace| wc -l` -eq 0 ]; do sample_events +max_retry=$((max_retry - 1)) +if [ $max_retry -eq 0 ]; then + exit_fail +fi +done hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc index 1f6981ef7afa0..ba19b81cef39a 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc @@ -30,7 +30,8 @@ find_dot_func() { fi grep " [tT] .*\.isra\..*" /proc/kallsyms | cut -f 3 -d " " | while read f; do - if grep -s $f available_filter_functions; then + cnt=`grep -s $f available_filter_functions | wc -l`; + if [ $cnt -eq 1 ]; then echo $f break fi diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc index 27da2dba9b9e3..e954bc8d254c7 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc @@ -14,12 +14,12 @@ test_trace() { x=$2 cat $file | while read line; do - comment=`echo $line | sed -e 's/^#//'` + comment=`echo "$line" | sed -e 's/^#//'` if [ "$line" != "$comment" ]; then continue fi echo "testing $line for >$x<" - match=`echo $line | sed -e "s/>$x$x$x< in it" fi diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config index 110d73917615d..02a2a1b267c1e 100644 --- a/tools/testing/selftests/iommu/config +++ b/tools/testing/selftests/iommu/config @@ -1,3 +1,5 @@ CONFIG_IOMMUFD=y +CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION=y CONFIG_IOMMUFD_TEST=y +CONFIG_FAILSLAB=y diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c index 25110c7c0b3ed..d7a8e321bb16b 100644 --- a/tools/testing/selftests/kcmp/kcmp_test.c +++ b/tools/testing/selftests/kcmp/kcmp_test.c @@ -91,7 +91,7 @@ int main(int argc, char **argv) ksft_print_header(); ksft_set_plan(3); - fd2 = open(kpath, O_RDWR, 0644); + fd2 = open(kpath, O_RDWR); if (fd2 < 0) { perror("Can't open file"); ksft_exit_fail(); diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index a781e6311810b..e3e260fe002f7 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -50,6 +50,7 @@ #include #include #include +#include #endif #ifndef ARRAY_SIZE @@ -78,6 +79,9 @@ #define KSFT_XPASS 3 #define KSFT_SKIP 4 +#ifndef __noreturn +#define __noreturn __attribute__((__noreturn__)) +#endif #define __printf(a, b) __attribute__((format(printf, a, b))) /* counters */ @@ -254,13 +258,13 @@ static inline __printf(1, 2) void ksft_test_result_error(const char *msg, ...) va_end(args); } -static inline int ksft_exit_pass(void) +static inline __noreturn int ksft_exit_pass(void) { ksft_print_cnts(); exit(KSFT_PASS); } -static inline int ksft_exit_fail(void) +static inline __noreturn int ksft_exit_fail(void) { ksft_print_cnts(); exit(KSFT_FAIL); @@ -287,7 +291,7 @@ static inline int ksft_exit_fail(void) ksft_cnt.ksft_xfail + \ ksft_cnt.ksft_xskip) -static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) +static inline __noreturn __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) { int saved_errno = errno; va_list args; @@ -302,19 +306,19 @@ static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) exit(KSFT_FAIL); } -static inline int ksft_exit_xfail(void) +static inline __noreturn int ksft_exit_xfail(void) { ksft_print_cnts(); exit(KSFT_XFAIL); } -static inline int ksft_exit_xpass(void) +static inline __noreturn int ksft_exit_xpass(void) { ksft_print_cnts(); exit(KSFT_XPASS); } -static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...) +static inline __noreturn __printf(1, 2) int ksft_exit_skip(const char *msg, ...) { int saved_errno = errno; va_list args; @@ -343,4 +347,21 @@ static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...) exit(KSFT_SKIP); } +static inline int ksft_min_kernel_version(unsigned int min_major, + unsigned int min_minor) +{ +#ifdef NOLIBC + ksft_print_msg("NOLIBC: Can't check kernel version: Function not implemented\n"); + return 0; +#else + unsigned int major, minor; + struct utsname info; + + if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2) + ksft_exit_fail_msg("Can't parse kernel version\n"); + + return major > min_major || (major == min_major && minor >= min_minor); +#endif +} + #endif /* __KSELFTEST_H */ diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 74954f6a8f94b..876c07489b653 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -36,7 +36,7 @@ tap_prefix() tap_timeout() { # Make sure tests will time out if utility is available. - if [ -x /usr/bin/timeout ] ; then + if [ -x /usr/bin/timeout ] && [ $kselftest_timeout -gt 0 ] ; then /usr/bin/timeout --foreground "$kselftest_timeout" \ /usr/bin/timeout "$kselftest_timeout" $1 else diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c index eef816b80993f..ca917c71ff602 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_init.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c @@ -84,6 +84,18 @@ static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, return v; } +static struct vm_gic vm_gic_create_barebones(uint32_t gic_dev_type) +{ + struct vm_gic v; + + v.gic_dev_type = gic_dev_type; + v.vm = vm_create_barebones(); + v.gic_fd = kvm_create_device(v.vm, gic_dev_type); + + return v; +} + + static void vm_gic_destroy(struct vm_gic *v) { close(v->gic_fd); @@ -357,6 +369,40 @@ static void test_vcpus_then_vgic(uint32_t gic_dev_type) vm_gic_destroy(&v); } +#define KVM_VGIC_V2_ATTR(offset, cpu) \ + (FIELD_PREP(KVM_DEV_ARM_VGIC_OFFSET_MASK, offset) | \ + FIELD_PREP(KVM_DEV_ARM_VGIC_CPUID_MASK, cpu)) + +#define GIC_CPU_CTRL 0x00 + +static void test_v2_uaccess_cpuif_no_vcpus(void) +{ + struct vm_gic v; + u64 val = 0; + int ret; + + v = vm_gic_create_barebones(KVM_DEV_TYPE_ARM_VGIC_V2); + subtest_dist_rdist(&v); + + ret = __kvm_has_device_attr(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS, + KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0)); + TEST_ASSERT(ret && errno == EINVAL, + "accessed non-existent CPU interface, want errno: %i", + EINVAL); + ret = __kvm_device_attr_get(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS, + KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0), &val); + TEST_ASSERT(ret && errno == EINVAL, + "accessed non-existent CPU interface, want errno: %i", + EINVAL); + ret = __kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS, + KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0), &val); + TEST_ASSERT(ret && errno == EINVAL, + "accessed non-existent CPU interface, want errno: %i", + EINVAL); + + vm_gic_destroy(&v); +} + static void test_v3_new_redist_regions(void) { struct kvm_vcpu *vcpus[NR_VCPUS]; @@ -675,6 +721,9 @@ void run_tests(uint32_t gic_dev_type) test_vcpus_then_vgic(gic_dev_type); test_vgic_then_vcpus(gic_dev_type); + if (VGIC_DEV_IS_V2(gic_dev_type)) + test_v2_uaccess_cpuif_no_vcpus(); + if (VGIC_DEV_IS_V3(gic_dev_type)) { test_v3_new_redist_regions(); test_v3_typer_accesses(); diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index aa646e0661f36..a8f0442a36bca 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -7,6 +7,8 @@ else ifneq ($(filter -%,$(LLVM)),) LLVM_SUFFIX := $(LLVM) endif +CLANG := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) + CLANG_TARGET_FLAGS_arm := arm-linux-gnueabi CLANG_TARGET_FLAGS_arm64 := aarch64-linux-gnu CLANG_TARGET_FLAGS_hexagon := hexagon-linux-musl @@ -18,7 +20,13 @@ CLANG_TARGET_FLAGS_riscv := riscv64-linux-gnu CLANG_TARGET_FLAGS_s390 := s390x-linux-gnu CLANG_TARGET_FLAGS_x86 := x86_64-linux-gnu CLANG_TARGET_FLAGS_x86_64 := x86_64-linux-gnu -CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH)) + +# Default to host architecture if ARCH is not explicitly given. +ifeq ($(ARCH),) +CLANG_TARGET_FLAGS := $(shell $(CLANG) -print-target-triple) +else +CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH)) +endif ifeq ($(CROSS_COMPILE),) ifeq ($(CLANG_TARGET_FLAGS),) @@ -30,7 +38,7 @@ else CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) endif # CROSS_COMPILE -CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as +CC := $(CLANG) $(CLANG_FLAGS) -fintegrated-as else CC := $(CROSS_COMPILE)gcc endif # LLVM diff --git a/tools/testing/selftests/lsm/common.h b/tools/testing/selftests/lsm/common.h index d404329e5eeb7..06d12110d241b 100644 --- a/tools/testing/selftests/lsm/common.h +++ b/tools/testing/selftests/lsm/common.h @@ -7,7 +7,7 @@ #ifndef lsm_get_self_attr static inline int lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx, - size_t *size, __u32 flags) + __u32 *size, __u32 flags) { return syscall(__NR_lsm_get_self_attr, attr, ctx, size, flags); } @@ -15,14 +15,14 @@ static inline int lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx, #ifndef lsm_set_self_attr static inline int lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx, - size_t size, __u32 flags) + __u32 size, __u32 flags) { return syscall(__NR_lsm_set_self_attr, attr, ctx, size, flags); } #endif #ifndef lsm_list_modules -static inline int lsm_list_modules(__u64 *ids, size_t *size, __u32 flags) +static inline int lsm_list_modules(__u64 *ids, __u32 *size, __u32 flags) { return syscall(__NR_lsm_list_modules, ids, size, flags); } diff --git a/tools/testing/selftests/lsm/lsm_get_self_attr_test.c b/tools/testing/selftests/lsm/lsm_get_self_attr_test.c index e0e313d9047a3..df215e4aa63fe 100644 --- a/tools/testing/selftests/lsm/lsm_get_self_attr_test.c +++ b/tools/testing/selftests/lsm/lsm_get_self_attr_test.c @@ -40,7 +40,7 @@ TEST(size_null_lsm_get_self_attr) TEST(ctx_null_lsm_get_self_attr) { const long page_size = sysconf(_SC_PAGESIZE); - size_t size = page_size; + __u32 size = page_size; int rc; rc = lsm_get_self_attr(LSM_ATTR_CURRENT, NULL, &size, 0); @@ -57,7 +57,7 @@ TEST(size_too_small_lsm_get_self_attr) { const long page_size = sysconf(_SC_PAGESIZE); struct lsm_ctx *ctx = calloc(page_size, 1); - size_t size = 1; + __u32 size = 1; ASSERT_NE(NULL, ctx); errno = 0; @@ -77,7 +77,7 @@ TEST(flags_zero_lsm_get_self_attr) const long page_size = sysconf(_SC_PAGESIZE); struct lsm_ctx *ctx = calloc(page_size, 1); __u64 *syscall_lsms = calloc(page_size, 1); - size_t size; + __u32 size; int lsmcount; int i; @@ -117,7 +117,7 @@ TEST(flags_overset_lsm_get_self_attr) { const long page_size = sysconf(_SC_PAGESIZE); struct lsm_ctx *ctx = calloc(page_size, 1); - size_t size; + __u32 size; ASSERT_NE(NULL, ctx); @@ -140,7 +140,7 @@ TEST(flags_overset_lsm_get_self_attr) TEST(basic_lsm_get_self_attr) { const long page_size = sysconf(_SC_PAGESIZE); - size_t size = page_size; + __u32 size = page_size; struct lsm_ctx *ctx = calloc(page_size, 1); struct lsm_ctx *tctx = NULL; __u64 *syscall_lsms = calloc(page_size, 1); diff --git a/tools/testing/selftests/lsm/lsm_list_modules_test.c b/tools/testing/selftests/lsm/lsm_list_modules_test.c index 9df29b1e34978..868641dbb309c 100644 --- a/tools/testing/selftests/lsm/lsm_list_modules_test.c +++ b/tools/testing/selftests/lsm/lsm_list_modules_test.c @@ -31,7 +31,7 @@ TEST(size_null_lsm_list_modules) TEST(ids_null_lsm_list_modules) { const long page_size = sysconf(_SC_PAGESIZE); - size_t size = page_size; + __u32 size = page_size; errno = 0; ASSERT_EQ(-1, lsm_list_modules(NULL, &size, 0)); @@ -43,7 +43,7 @@ TEST(size_too_small_lsm_list_modules) { const long page_size = sysconf(_SC_PAGESIZE); __u64 *syscall_lsms = calloc(page_size, 1); - size_t size = 1; + __u32 size = 1; ASSERT_NE(NULL, syscall_lsms); errno = 0; @@ -58,7 +58,7 @@ TEST(flags_set_lsm_list_modules) { const long page_size = sysconf(_SC_PAGESIZE); __u64 *syscall_lsms = calloc(page_size, 1); - size_t size = page_size; + __u32 size = page_size; ASSERT_NE(NULL, syscall_lsms); errno = 0; @@ -72,7 +72,7 @@ TEST(flags_set_lsm_list_modules) TEST(correct_lsm_list_modules) { const long page_size = sysconf(_SC_PAGESIZE); - size_t size = page_size; + __u32 size = page_size; __u64 *syscall_lsms = calloc(page_size, 1); char *sysfs_lsms = calloc(page_size, 1); char *name; diff --git a/tools/testing/selftests/lsm/lsm_set_self_attr_test.c b/tools/testing/selftests/lsm/lsm_set_self_attr_test.c index e9712c6cf5962..66dec47e3ca3f 100644 --- a/tools/testing/selftests/lsm/lsm_set_self_attr_test.c +++ b/tools/testing/selftests/lsm/lsm_set_self_attr_test.c @@ -25,7 +25,7 @@ TEST(size_too_small_lsm_set_self_attr) { const long page_size = sysconf(_SC_PAGESIZE); struct lsm_ctx *ctx = calloc(page_size, 1); - size_t size = page_size; + __u32 size = page_size; ASSERT_NE(NULL, ctx); if (attr_lsm_count()) { @@ -41,7 +41,7 @@ TEST(flags_zero_lsm_set_self_attr) { const long page_size = sysconf(_SC_PAGESIZE); struct lsm_ctx *ctx = calloc(page_size, 1); - size_t size = page_size; + __u32 size = page_size; ASSERT_NE(NULL, ctx); if (attr_lsm_count()) { @@ -57,7 +57,7 @@ TEST(flags_overset_lsm_set_self_attr) { const long page_size = sysconf(_SC_PAGESIZE); char *ctx = calloc(page_size, 1); - size_t size = page_size; + __u32 size = page_size; struct lsm_ctx *tctx = (struct lsm_ctx *)ctx; ASSERT_NE(NULL, ctx); diff --git a/tools/testing/selftests/memory-hotplug/settings b/tools/testing/selftests/memory-hotplug/settings new file mode 100644 index 0000000000000..a62d2fa1275c6 --- /dev/null +++ b/tools/testing/selftests/memory-hotplug/settings @@ -0,0 +1 @@ +timeout=600 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 2453add65d12f..c04a81535ed41 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -12,7 +12,7 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) else uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') endif -ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/powerpc/') endif # Without this, failed build products remain, with up-to-date timestamps, @@ -97,13 +97,13 @@ TEST_GEN_FILES += $(BINARIES_64) endif else -ifneq (,$(findstring $(ARCH),ppc64)) +ifneq (,$(findstring $(ARCH),powerpc)) TEST_GEN_FILES += protection_keys endif endif -ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64)) TEST_GEN_FILES += va_high_addr_switch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 656afba02dbcc..dcec533c1e50b 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -82,12 +82,16 @@ int prereq(void) return -1; } -int check_compaction(unsigned long mem_free, unsigned int hugepage_size) +int check_compaction(unsigned long mem_free, unsigned long hugepage_size, + unsigned long initial_nr_hugepages) { + unsigned long nr_hugepages_ul; int fd, ret = -1; int compaction_index = 0; - char initial_nr_hugepages[10] = {0}; - char nr_hugepages[10] = {0}; + char nr_hugepages[20] = {0}; + char init_nr_hugepages[20] = {0}; + + sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ @@ -95,71 +99,99 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_test_result_fail("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - return -1; - } - - if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { - ksft_test_result_fail("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - /* Start with the initial condition of 0 huge pages*/ - if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_test_result_fail("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + ret = -1; + goto out; } - lseek(fd, 0, SEEK_SET); - /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_test_result_fail("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } lseek(fd, 0, SEEK_SET); if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_test_result_fail("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } /* We should have been able to request at least 1/3 rd of the memory in huge pages */ - compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size); + nr_hugepages_ul = strtoul(nr_hugepages, NULL, 10); + if (!nr_hugepages_ul) { + ksft_print_msg("ERROR: No memory is available as huge pages\n"); + goto close_fd; + } + compaction_index = mem_free/(nr_hugepages_ul * hugepage_size); lseek(fd, 0, SEEK_SET); - if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) - != strlen(initial_nr_hugepages)) { - ksft_test_result_fail("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) + != strlen(init_nr_hugepages)) { + ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); goto close_fd; } + ksft_print_msg("Number of huge pages allocated = %d\n", + atoi(nr_hugepages)); + if (compaction_index > 3) { - ksft_print_msg("ERROR: Less that 1/%d of memory is available\n" + ksft_print_msg("ERROR: Less than 1/%d of memory is available\n" "as huge pages\n", compaction_index); - ksft_test_result_fail("No of huge pages allocated = %d\n", (atoi(nr_hugepages))); goto close_fd; } - ksft_test_result_pass("Memory compaction succeeded. No of huge pages allocated = %d\n", - (atoi(nr_hugepages))); ret = 0; close_fd: close(fd); + out: + ksft_test_result(ret == 0, "check_compaction\n"); return ret; } +int set_zero_hugepages(unsigned long *initial_nr_hugepages) +{ + int fd, ret = -1; + char nr_hugepages[20] = {0}; + + fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + if (fd < 0) { + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto out; + } + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { + ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + lseek(fd, 0, SEEK_SET); + + /* Start with the initial condition of 0 huge pages */ + if (write(fd, "0", sizeof(char)) != sizeof(char)) { + ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + *initial_nr_hugepages = strtoul(nr_hugepages, NULL, 10); + ret = 0; + + close_fd: + close(fd); + + out: + return ret; +} int main(int argc, char **argv) { @@ -170,14 +202,19 @@ int main(int argc, char **argv) unsigned long mem_free = 0; unsigned long hugepage_size = 0; long mem_fragmentable_MB = 0; + unsigned long initial_nr_hugepages; ksft_print_header(); if (prereq() || geteuid()) - return ksft_exit_pass(); + ksft_exit_skip("Prerequisites unsatisfied\n"); ksft_set_plan(1); + /* Start the test without hugepages reducing mem_free */ + if (set_zero_hugepages(&initial_nr_hugepages)) + ksft_exit_fail(); + lim.rlim_cur = RLIM_INFINITY; lim.rlim_max = RLIM_INFINITY; if (setrlimit(RLIMIT_MEMLOCK, &lim)) @@ -221,8 +258,9 @@ int main(int argc, char **argv) entry = entry->next; } - if (check_compaction(mem_free, hugepage_size) == 0) - return ksft_exit_pass(); + if (check_compaction(mem_free, hugepage_size, + initial_nr_hugepages) == 0) + ksft_exit_pass(); - return ksft_exit_fail(); + ksft_exit_fail(); } diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 363bf5f801be5..fe078d6e18064 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1779,5 +1779,5 @@ int main(int argc, char **argv) if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", err, ksft_test_num()); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index ad168d35b23b7..d7eaca5bbe9b1 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -456,5 +456,5 @@ int main(int argc, char **argv) if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", err, ksft_test_num()); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index cbe99594d319b..bdeaac67ff9aa 100644 --- a/tools/testing/selftests/mm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c @@ -1,3 +1,4 @@ +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include #include #include @@ -203,7 +204,7 @@ int main(int argc, char **argv) ksft_print_header(); ksft_set_plan(nthreads); - filed = open(file, O_RDWR|O_CREAT); + filed = open(file, O_RDWR|O_CREAT, 0664); if (filed < 0) ksft_exit_fail_msg("Unable to open %s: %s\n", file, strerror(errno)); @@ -228,7 +229,7 @@ int main(int argc, char **argv) break; } ksft_test_result_skip("Please run this test as root\n"); - return ksft_exit_pass(); + ksft_exit_pass(); } p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0); @@ -267,5 +268,5 @@ int main(int argc, char **argv) free(tid); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index fbff0dd09191f..f9c679914fc80 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -646,5 +646,5 @@ int main(int argc, char **argv) if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", err, ksft_test_num()); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index 17bcb07f19f34..ef7d911da13e0 100644 --- a/tools/testing/selftests/mm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c @@ -307,5 +307,5 @@ int main(int argc, char **argv) if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", err, ksft_test_num()); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c index 301abb99e027e..b8a7efe9204ea 100644 --- a/tools/testing/selftests/mm/mkdirty.c +++ b/tools/testing/selftests/mm/mkdirty.c @@ -375,5 +375,5 @@ int main(void) if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", err, ksft_test_num()); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index d59517ed3d48b..2d785aca72a5c 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -1484,7 +1484,7 @@ int main(int argc, char *argv[]) ksft_print_header(); if (init_uffd()) - return ksft_exit_pass(); + ksft_exit_pass(); ksft_set_plan(115); @@ -1660,5 +1660,5 @@ int main(int argc, char *argv[]) userfaultfd_tests(); close(pagemap_fd); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index cc5f144430d4d..d9dbf879748b2 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -137,7 +137,7 @@ static void test_mprotect(int pagemap_fd, int pagesize, bool anon) if (!map) ksft_exit_fail_msg("anon mmap failed\n"); } else { - test_fd = open(fname, O_RDWR | O_CREAT); + test_fd = open(fname, O_RDWR | O_CREAT, 0664); if (test_fd < 0) { ksft_test_result_skip("Test %s open() file failed\n", __func__); return; @@ -209,5 +209,5 @@ int main(int argc, char **argv) close(pagemap_fd); - return ksft_exit_pass(); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 0e74635c8c3d9..dff3be23488b4 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -253,7 +253,7 @@ void split_file_backed_thp(void) goto cleanup; } - fd = open(testfile, O_CREAT|O_WRONLY); + fd = open(testfile, O_CREAT|O_WRONLY, 0664); if (fd == -1) { perror("Cannot open testing file\n"); goto cleanup; diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index b0ac0ec2356d6..7ad6ba660c7d6 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -18,6 +18,7 @@ bool test_uffdio_wp = true; unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; uffd_test_case_ops_t *uffd_test_case_ops; +atomic_bool ready_for_fork; static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) { @@ -518,6 +519,8 @@ void *uffd_poll_thread(void *arg) pollfd[1].fd = pipefd[cpu*2]; pollfd[1].events = POLLIN; + ready_for_fork = true; + for (;;) { ret = poll(pollfd, 2, -1); if (ret <= 0) { diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index cb055282c89c9..a70ae10b5f620 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -8,6 +8,7 @@ #define __UFFD_COMMON_H__ #define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include #include #include @@ -32,6 +33,7 @@ #include #include #include +#include #include "../kselftest.h" #include "vm_util.h" @@ -103,6 +105,7 @@ extern bool map_shared; extern bool test_uffdio_wp; extern unsigned long long *count_verify; extern volatile bool test_uffdio_copy_eexist; +extern atomic_bool ready_for_fork; extern uffd_test_ops_t anon_uffd_test_ops; extern uffd_test_ops_t shmem_uffd_test_ops; diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 2b9f8cc52639d..21ec23206ab44 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -775,6 +775,8 @@ static void uffd_sigbus_test_common(bool wp) char c; struct uffd_args args = { 0 }; + ready_for_fork = false; + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); if (uffd_register(uffd, area_dst, nr_pages * page_size, @@ -790,6 +792,9 @@ static void uffd_sigbus_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); + while (!ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ + pid = fork(); if (pid < 0) err("fork"); @@ -829,6 +834,8 @@ static void uffd_events_test_common(bool wp) char c; struct uffd_args args = { 0 }; + ready_for_fork = false; + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); if (uffd_register(uffd, area_dst, nr_pages * page_size, true, wp, false)) @@ -838,6 +845,9 @@ static void uffd_events_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); + while (!ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ + pid = fork(); if (pid < 0) err("fork"); @@ -1427,7 +1437,8 @@ uffd_test_case_t uffd_tests[] = { .uffd_fn = uffd_sigbus_wp_test, .mem_targets = MEM_ALL, .uffd_feature_required = UFFD_FEATURE_SIGBUS | - UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_PAGEFAULT_FLAG_WP, + UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM, }, { .name = "events", diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index c02990bbd56f4..9007c420d52c5 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -3,7 +3,7 @@ #include #include #include -#include /* ffsl() */ +#include /* ffsl() */ #include /* _SC_PAGESIZE */ #define BIT_ULL(nr) (1ULL << (nr)) diff --git a/tools/testing/selftests/mqueue/setting b/tools/testing/selftests/mqueue/setting new file mode 100644 index 0000000000000..a953c96aa16e1 --- /dev/null +++ b/tools/testing/selftests/mqueue/setting @@ -0,0 +1 @@ +timeout=180 diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 75528788cb95e..7e7ed6c558da9 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -77,6 +77,7 @@ readonly LISTENER=$(mktemp -u listener-XXXXXXXX) readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX) readonly RELAY=$(mktemp -u relay-XXXXXXXX) readonly SOURCE=$(mktemp -u source-XXXXXXXX) +readonly SMCROUTEDIR="$(mktemp -d)" ERR=4 err=0 @@ -85,6 +86,11 @@ exit_cleanup() for ns in "$@"; do ip netns delete "${ns}" 2>/dev/null || true done + if [ -f "$SMCROUTEDIR/amt.pid" ]; then + smcpid=$(< $SMCROUTEDIR/amt.pid) + kill $smcpid + fi + rm -rf $SMCROUTEDIR exit $ERR } @@ -167,7 +173,7 @@ setup_iptables() setup_mcast_routing() { - ip netns exec "${RELAY}" smcrouted + ip netns exec "${RELAY}" smcrouted -P $SMCROUTEDIR/amt.pid ip netns exec "${RELAY}" smcroutectl a relay_src \ 172.17.0.2 239.0.0.1 amtr ip netns exec "${RELAY}" smcroutectl a relay_src \ @@ -210,8 +216,8 @@ check_features() test_ipv4_forward() { - RESULT4=$(ip netns exec "${LISTENER}" nc -w 1 -l -u 239.0.0.1 4000) - if [ "$RESULT4" == "172.17.0.2" ]; then + RESULT4=$(ip netns exec "${LISTENER}" timeout 15 socat - UDP4-LISTEN:4000,readbytes=128 || true) + if echo "$RESULT4" | grep -q "172.17.0.2"; then printf "TEST: %-60s [ OK ]\n" "IPv4 amt multicast forwarding" exit 0 else @@ -222,8 +228,8 @@ test_ipv4_forward() test_ipv6_forward() { - RESULT6=$(ip netns exec "${LISTENER}" nc -w 1 -l -u ff0e::5:6 6000) - if [ "$RESULT6" == "2001:db8:3::2" ]; then + RESULT6=$(ip netns exec "${LISTENER}" timeout 15 socat - UDP6-LISTEN:6000,readbytes=128 || true) + if echo "$RESULT6" | grep -q "2001:db8:3::2"; then printf "TEST: %-60s [ OK ]\n" "IPv6 amt multicast forwarding" exit 0 else @@ -236,14 +242,14 @@ send_mcast4() { sleep 2 ip netns exec "${SOURCE}" bash -c \ - 'echo 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' & + 'printf "%s %128s" 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' & } send_mcast6() { sleep 2 ip netns exec "${SOURCE}" bash -c \ - 'echo 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' & + 'printf "%s %128s" 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' & } check_features diff --git a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh index a40c0e9bd023c..eef5cbf6eecca 100755 --- a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh +++ b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh @@ -73,25 +73,19 @@ setup_v6() { # namespaces. veth0 is veth-router, veth1 is veth-host. # first, set up the inteface's link to the namespace # then, set the interface "up" - ip -6 -netns ${ROUTER_NS_V6} link add name ${ROUTER_INTF} \ - type veth peer name ${HOST_INTF} - - ip -6 -netns ${ROUTER_NS_V6} link set dev ${ROUTER_INTF} up - ip -6 -netns ${ROUTER_NS_V6} link set dev ${HOST_INTF} netns \ - ${HOST_NS_V6} + ip -n ${ROUTER_NS_V6} link add name ${ROUTER_INTF} \ + type veth peer name ${HOST_INTF} netns ${HOST_NS_V6} - ip -6 -netns ${HOST_NS_V6} link set dev ${HOST_INTF} up - ip -6 -netns ${ROUTER_NS_V6} addr add \ - ${ROUTER_ADDR_V6}/${PREFIX_WIDTH_V6} dev ${ROUTER_INTF} nodad + # Add tc rule to filter out host na message + tc -n ${ROUTER_NS_V6} qdisc add dev ${ROUTER_INTF} clsact + tc -n ${ROUTER_NS_V6} filter add dev ${ROUTER_INTF} \ + ingress protocol ipv6 pref 1 handle 101 \ + flower src_ip ${HOST_ADDR_V6} ip_proto icmpv6 type 136 skip_hw action pass HOST_CONF=net.ipv6.conf.${HOST_INTF} ip netns exec ${HOST_NS_V6} sysctl -qw ${HOST_CONF}.ndisc_notify=1 ip netns exec ${HOST_NS_V6} sysctl -qw ${HOST_CONF}.disable_ipv6=0 - ip -6 -netns ${HOST_NS_V6} addr add ${HOST_ADDR_V6}/${PREFIX_WIDTH_V6} \ - dev ${HOST_INTF} - ROUTER_CONF=net.ipv6.conf.${ROUTER_INTF} - ip netns exec ${ROUTER_NS_V6} sysctl -w \ ${ROUTER_CONF}.forwarding=1 >/dev/null 2>&1 ip netns exec ${ROUTER_NS_V6} sysctl -w \ @@ -99,6 +93,13 @@ setup_v6() { ip netns exec ${ROUTER_NS_V6} sysctl -w \ ${ROUTER_CONF}.accept_untracked_na=${accept_untracked_na} \ >/dev/null 2>&1 + + ip -n ${ROUTER_NS_V6} link set dev ${ROUTER_INTF} up + ip -n ${HOST_NS_V6} link set dev ${HOST_INTF} up + ip -n ${ROUTER_NS_V6} addr add ${ROUTER_ADDR_V6}/${PREFIX_WIDTH_V6} \ + dev ${ROUTER_INTF} nodad + ip -n ${HOST_NS_V6} addr add ${HOST_ADDR_V6}/${PREFIX_WIDTH_V6} \ + dev ${HOST_INTF} set +e } @@ -162,26 +163,6 @@ arp_test_gratuitous_combinations() { arp_test_gratuitous 2 1 } -cleanup_tcpdump() { - set -e - [[ ! -z ${tcpdump_stdout} ]] && rm -f ${tcpdump_stdout} - [[ ! -z ${tcpdump_stderr} ]] && rm -f ${tcpdump_stderr} - tcpdump_stdout= - tcpdump_stderr= - set +e -} - -start_tcpdump() { - set -e - tcpdump_stdout=`mktemp` - tcpdump_stderr=`mktemp` - ip netns exec ${ROUTER_NS_V6} timeout 15s \ - tcpdump --immediate-mode -tpni ${ROUTER_INTF} -c 1 \ - "icmp6 && icmp6[0] == 136 && src ${HOST_ADDR_V6}" \ - > ${tcpdump_stdout} 2> /dev/null - set +e -} - verify_ndisc() { local accept_untracked_na=$1 local same_subnet=$2 @@ -222,8 +203,9 @@ ndisc_test_untracked_advertisements() { HOST_ADDR_V6=2001:db8:abcd:0012::3 fi fi - setup_v6 $1 $2 - start_tcpdump + setup_v6 $1 + slowwait_for_counter 15 1 \ + tc_rule_handle_stats_get "dev ${ROUTER_INTF} ingress" 101 ".packets" "-n ${ROUTER_NS_V6}" if verify_ndisc $1 $2; then printf " TEST: %-60s [ OK ]\n" "${test_msg[*]}" @@ -231,7 +213,6 @@ ndisc_test_untracked_advertisements() { printf " TEST: %-60s [FAIL]\n" "${test_msg[*]}" fi - cleanup_tcpdump cleanup_v6 set +e } diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index c79e65581dc37..161db24e3c409 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -333,16 +333,17 @@ static const char *cs_ts_info2str(unsigned int info) return "unknown"; } -static void +static unsigned long cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) { struct sock_extended_err *see; struct scm_timestamping *ts; + unsigned long ts_seen = 0; struct cmsghdr *cmsg; int i, err; if (!opt.ts.ena) - return; + return 0; msg->msg_control = cbuf; msg->msg_controllen = cbuf_sz; @@ -396,8 +397,11 @@ cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) printf(" %5s ts%d %lluus\n", cs_ts_info2str(see->ee_info), i, rel_time); + ts_seen |= 1 << see->ee_info; } } + + return ts_seen; } static void ca_set_sockopts(int fd) @@ -509,10 +513,16 @@ int main(int argc, char *argv[]) err = ERN_SUCCESS; if (opt.ts.ena) { - /* Make sure all timestamps have time to loop back */ - usleep(opt.txtime.delay); + unsigned long seen; + int i; - cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + /* Make sure all timestamps have time to loop back */ + for (i = 0; i < 40; i++) { + seen = cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + if (seen & (1 << SCM_TSTAMP_SND)) + break; + usleep(opt.txtime.delay / 20); + } } err_out: diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 5e4390cac17ed..04de7a6ba6f31 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -30,6 +30,7 @@ CONFIG_IP_GRE=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m +CONFIG_IPV6_MROUTE=y CONFIG_IPV6_SIT=y CONFIG_IP_DCCP=m CONFIG_NF_NAT=m diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh index 2aa66d2a1702b..e6a3e04fd83f3 100755 --- a/tools/testing/selftests/net/forwarding/bridge_igmp.sh +++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh @@ -478,10 +478,10 @@ v3exc_timeout_test() RET=0 local X=("192.0.2.20" "192.0.2.30") - # GMI should be 3 seconds + # GMI should be 5 seconds ip link set dev br0 type bridge mcast_query_interval 100 \ mcast_query_response_interval 100 \ - mcast_membership_interval 300 + mcast_membership_interval 500 v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP ip link set dev br0 type bridge mcast_query_interval 500 \ @@ -489,7 +489,7 @@ v3exc_timeout_test() mcast_membership_interval 1500 $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q - sleep 3 + sleep 5 bridge -j -d -s mdb show dev br0 \ | jq -e ".[].mdb[] | \ select(.grp == \"$TEST_GROUP\" and \ diff --git a/tools/testing/selftests/net/forwarding/bridge_mld.sh b/tools/testing/selftests/net/forwarding/bridge_mld.sh index e2b9ff773c6b6..f84ab2e657547 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mld.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mld.sh @@ -478,10 +478,10 @@ mldv2exc_timeout_test() RET=0 local X=("2001:db8:1::20" "2001:db8:1::30") - # GMI should be 3 seconds + # GMI should be 5 seconds ip link set dev br0 type bridge mcast_query_interval 100 \ mcast_query_response_interval 100 \ - mcast_membership_interval 300 + mcast_membership_interval 500 mldv2exclude_prepare $h1 ip link set dev br0 type bridge mcast_query_interval 500 \ @@ -489,7 +489,7 @@ mldv2exc_timeout_test() mcast_membership_interval 1500 $MZ $h1 -c 1 $MZPKT_ALLOW2 -q - sleep 3 + sleep 5 bridge -j -d -s mdb show dev br0 \ | jq -e ".[].mdb[] | \ select(.grp == \"$TEST_GROUP\" and \ diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index 697994a9278bb..8d7a1a004b7c3 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -6,14 +6,49 @@ CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NET_VRF=m CONFIG_BPF_SYSCALL=y CONFIG_CGROUP_BPF=y +CONFIG_DUMMY=m +CONFIG_IPV6=y +CONFIG_IPV6_GRE=m +CONFIG_IPV6_MROUTE=y +CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y +CONFIG_IPV6_PIMSM_V2=y +CONFIG_IP_MROUTE=y +CONFIG_IP_MROUTE_MULTIPLE_TABLES=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_MACVLAN=m CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_MPLS=m +CONFIG_NET_ACT_PEDIT=m +CONFIG_NET_ACT_POLICE=m +CONFIG_NET_ACT_SAMPLE=m +CONFIG_NET_ACT_SKBEDIT=m +CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_VLAN=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_META=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IPIP=m +CONFIG_NET_SCH_ETS=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_ACT_GACT=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_TC_SKB_EXT=y +CONFIG_NET_TEAM=y +CONFIG_NET_TEAM_MODE_LOADBALANCE=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_TABLES=m CONFIG_VETH=m CONFIG_NAMESPACES=y CONFIG_NET_NS=y +CONFIG_VXLAN=m +CONFIG_XFRM_USER=m diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8a61464ab6eb0..7bae2a20f3a24 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -41,28 +41,6 @@ fi # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -busywait() -{ - local timeout=$1; shift - - local start_time="$(date -u +%s%3N)" - while true - do - local out - out=$("$@") - local ret=$? - if ((!ret)); then - echo -n "$out" - return 0 - fi - - local current_time="$(date -u +%s%3N)" - if ((current_time - start_time > timeout)); then - echo -n "$out" - return 1 - fi - done -} ############################################################################## # Sanity checks @@ -358,14 +336,24 @@ EXIT_STATUS=0 # Per-test return value. Clear at the beginning of each test. RET=0 +ret_set_ksft_status() +{ + local ksft_status=$1; shift + local msg=$1; shift + + RET=$(ksft_status_merge $RET $ksft_status) + if (( $? )); then + retmsg=$msg + fi +} + check_err() { local err=$1 local msg=$2 - if [[ $RET -eq 0 && $err -ne 0 ]]; then - RET=$err - retmsg=$msg + if ((err)); then + ret_set_ksft_status $ksft_fail "$msg" fi } @@ -374,10 +362,7 @@ check_fail() local err=$1 local msg=$2 - if [[ $RET -eq 0 && $err -eq 0 ]]; then - RET=1 - retmsg=$msg - fi + check_err $((!err)) "$msg" } check_err_fail() @@ -393,6 +378,62 @@ check_err_fail() fi } +log_test_result() +{ + local test_name=$1; shift + local opt_str=$1; shift + local result=$1; shift + local retmsg=$1; shift + + printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" + if [[ $retmsg ]]; then + printf "\t%s\n" "$retmsg" + fi +} + +pause_on_fail() +{ + if [[ $PAUSE_ON_FAIL == yes ]]; then + echo "Hit enter to continue, 'q' to quit" + read a + [[ $a == q ]] && exit 1 + fi +} + +handle_test_result_pass() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" " OK " +} + +handle_test_result_fail() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" FAIL "$retmsg" + pause_on_fail +} + +handle_test_result_xfail() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" XFAIL "$retmsg" + pause_on_fail +} + +handle_test_result_skip() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" SKIP "$retmsg" +} + log_test() { local test_name=$1 @@ -402,31 +443,23 @@ log_test() opt_str="($opt_str)" fi - if [[ $RET -ne 0 ]]; then - EXIT_STATUS=1 - printf "TEST: %-60s [FAIL]\n" "$test_name $opt_str" - if [[ ! -z "$retmsg" ]]; then - printf "\t%s\n" "$retmsg" - fi - if [ "${PAUSE_ON_FAIL}" = "yes" ]; then - echo "Hit enter to continue, 'q' to quit" - read a - [ "$a" = "q" ] && exit 1 - fi - return 1 + if ((RET == ksft_pass)); then + handle_test_result_pass "$test_name" "$opt_str" + elif ((RET == ksft_xfail)); then + handle_test_result_xfail "$test_name" "$opt_str" + elif ((RET == ksft_skip)); then + handle_test_result_skip "$test_name" "$opt_str" + else + handle_test_result_fail "$test_name" "$opt_str" fi - printf "TEST: %-60s [ OK ]\n" "$test_name $opt_str" - return 0 + EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET) + return $RET } log_test_skip() { - local test_name=$1 - local opt_str=$2 - - printf "TEST: %-60s [SKIP]\n" "$test_name $opt_str" - return 0 + RET=$ksft_skip retmsg= log_test "$@" } log_info() @@ -810,29 +843,6 @@ link_stats_rx_errors_get() link_stats_get $1 rx errors } -tc_rule_stats_get() -{ - local dev=$1; shift - local pref=$1; shift - local dir=$1; shift - local selector=${1:-.packets}; shift - - tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ - | jq ".[1].options.actions[].stats$selector" -} - -tc_rule_handle_stats_get() -{ - local id=$1; shift - local handle=$1; shift - local selector=${1:-.packets}; shift - local netns=${1:-""}; shift - - tc $netns -j -s filter show $id \ - | jq ".[] | select(.options.handle == $handle) | \ - .options.actions[0].stats$selector" -} - ethtool_stats_get() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh index ac97f07e5ce82..bd3f7d492af2b 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh @@ -354,7 +354,7 @@ __ping_ipv4() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome ARP noise. - PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100 @@ -410,7 +410,7 @@ __ping_ipv6() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome neighbor discovery noise. - PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping6_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 100 diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh index d880df89bc8bd..e83fde79f40d0 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_ipv6.sh @@ -457,7 +457,7 @@ __ping_ipv4() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome ARP noise. - PING_COUNT=100 PING_TIMEOUT=11 ping_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 10 100 @@ -522,7 +522,7 @@ __ping_ipv6() # Send 100 packets and verify that at least 100 packets hit the rule, # to overcome neighbor discovery noise. - PING_COUNT=100 PING_TIMEOUT=11 ping6_do $dev $dst_ip + PING_COUNT=100 PING_TIMEOUT=20 ping6_do $dev $dst_ip check_err $? "Ping failed" tc_check_at_least_x_packets "dev $rp1 egress" 101 100 diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index f9fe182dfbd44..16372ca167ba8 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -10,33 +10,116 @@ BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 # namespace list created by setup_ns -NS_LIST="" +NS_LIST=() ############################################################################## # Helpers -busywait() + +__ksft_status_merge() { - local timeout=$1; shift + local a=$1; shift + local b=$1; shift + local -A weights + local weight=0 + + local i + for i in "$@"; do + weights[$i]=$((weight++)) + done + + if [[ ${weights[$a]} > ${weights[$b]} ]]; then + echo "$a" + return 0 + else + echo "$b" + return 1 + fi +} + +ksft_status_merge() +{ + local a=$1; shift + local b=$1; shift + + __ksft_status_merge "$a" "$b" \ + $ksft_pass $ksft_xfail $ksft_skip $ksft_fail +} + +ksft_exit_status_merge() +{ + local a=$1; shift + local b=$1; shift + + __ksft_status_merge "$a" "$b" \ + $ksft_xfail $ksft_pass $ksft_skip $ksft_fail +} + +loopy_wait() +{ + local sleep_cmd=$1; shift + local timeout_ms=$1; shift local start_time="$(date -u +%s%3N)" while true do local out - out=$("$@") - local ret=$? - if ((!ret)); then + if out=$("$@"); then echo -n "$out" return 0 fi local current_time="$(date -u +%s%3N)" - if ((current_time - start_time > timeout)); then + if ((current_time - start_time > timeout_ms)); then echo -n "$out" return 1 fi + + $sleep_cmd done } +busywait() +{ + local timeout_ms=$1; shift + + loopy_wait : "$timeout_ms" "$@" +} + +# timeout in seconds +slowwait() +{ + local timeout_sec=$1; shift + + loopy_wait "sleep 0.1" "$((timeout_sec * 1000))" "$@" +} + +until_counter_is() +{ + local expr=$1; shift + local current=$("$@") + + echo $((current)) + ((current $expr)) +} + +busywait_for_counter() +{ + local timeout=$1; shift + local delta=$1; shift + + local base=$("$@") + busywait "$timeout" until_counter_is ">= $((base + delta))" "$@" +} + +slowwait_for_counter() +{ + local timeout=$1; shift + local delta=$1; shift + + local base=$("$@") + slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" +} + cleanup_ns() { local ns="" @@ -50,6 +133,7 @@ cleanup_ns() fi for ns in "$@"; do + [ -z "${ns}" ] && continue ip netns delete "${ns}" &> /dev/null if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" @@ -63,7 +147,7 @@ cleanup_ns() cleanup_all_ns() { - cleanup_ns $NS_LIST + cleanup_ns "${NS_LIST[@]}" } # setup netns with given names as prefix. e.g @@ -72,25 +156,50 @@ setup_ns() { local ns="" local ns_name="" - local ns_list="" + local ns_list=() + local ns_exist= for ns_name in "$@"; do # Some test may setup/remove same netns multi times if unset ${ns_name} 2> /dev/null; then ns="${ns_name,,}-$(mktemp -u XXXXXX)" eval readonly ${ns_name}="$ns" + ns_exist=false else eval ns='$'${ns_name} cleanup_ns "$ns" - + ns_exist=true fi if ! ip netns add "$ns"; then echo "Failed to create namespace $ns_name" - cleanup_ns "$ns_list" + cleanup_ns "${ns_list[@]}" return $ksft_skip fi ip -n "$ns" link set lo up - ns_list="$ns_list $ns" + ! $ns_exist && ns_list+=("$ns") done - NS_LIST="$NS_LIST $ns_list" + NS_LIST+=("${ns_list[@]}") +} + +tc_rule_stats_get() +{ + local dev=$1; shift + local pref=$1; shift + local dir=$1; shift + local selector=${1:-.packets}; shift + + tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ + | jq ".[1].options.actions[].stats$selector" +} + +tc_rule_handle_stats_get() +{ + local id=$1; shift + local handle=$1; shift + local selector=${1:-.packets}; shift + local netns=${1:-""}; shift + + tc $netns -j -s filter show $id \ + | jq ".[] | select(.options.handle == $handle) | \ + .options.actions[0].stats$selector" } diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 7898d62fce0b5..713de81822227 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" time_start=$(date +%s) @@ -13,7 +18,6 @@ sout="" cin_disconnect="" cin="" cout="" -ksft_skip=4 capture=false timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) @@ -131,6 +135,8 @@ ns4="ns4-$rndh" TEST_COUNT=0 TEST_GROUP="" +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { rm -f "$cin_disconnect" "$cout_disconnect" @@ -225,8 +231,9 @@ set_ethtool_flags() { local dev="$2" local flags="$3" - ip netns exec $ns ethtool -K $dev $flags 2>/dev/null - [ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags" + if ip netns exec $ns ethtool -K $dev $flags 2>/dev/null; then + echo "INFO: set $ns dev $dev: ethtool -K $flags" + fi } set_random_ethtool_flags() { @@ -321,19 +328,19 @@ do_transfer() local extra_args="$7" local port - port=$((10000+$TEST_COUNT)) + port=$((10000+TEST_COUNT)) TEST_COUNT=$((TEST_COUNT+1)) if [ "$rcvbuf" -gt 0 ]; then - extra_args="$extra_args -R $rcvbuf" + extra_args+=" -R $rcvbuf" fi if [ "$sndbuf" -gt 0 ]; then - extra_args="$extra_args -S $sndbuf" + extra_args+=" -S $sndbuf" fi if [ -n "$testmode" ]; then - extra_args="$extra_args -m $testmode" + extra_args+=" -m $testmode" fi if [ -n "$extra_args" ] && $options_log; then @@ -378,12 +385,20 @@ do_transfer() nstat -n fi - local stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local stat_synrx_last_l + local stat_ackrx_last_l + local stat_cookietx_last + local stat_cookierx_last + local stat_csum_err_s + local stat_csum_err_c + local stat_tcpfb_last_l + stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -446,11 +461,19 @@ do_transfer() mptcp_lib_check_transfer $cin $sout "file received by server" rets=$? - local stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + local extra="" + local stat_synrx_now_l + local stat_ackrx_now_l + local stat_cookietx_now + local stat_cookierx_now + local stat_ooo_now + local stat_tcpfb_now_l + stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -459,8 +482,8 @@ do_transfer() cookies=${cookies##*=} if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then - expect_synrx=$((stat_synrx_last_l+$connect_per_transfer)) - expect_ackrx=$((stat_ackrx_last_l+$connect_per_transfer)) + expect_synrx=$((stat_synrx_last_l+connect_per_transfer)) + expect_ackrx=$((stat_ackrx_last_l+connect_per_transfer)) fi if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then @@ -468,66 +491,75 @@ do_transfer() "${stat_synrx_now_l}" "${expect_synrx}" 1>&2 retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then + if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ] && [ ${stat_ooo_now} -eq 0 ]; then if [ ${stat_ooo_now} -eq 0 ]; then printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \ "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2 rets=1 else - printf "[ Note ] fallback due to TCP OoO" + extra+=" [ Note ] fallback due to TCP OoO" fi fi if $checksum; then - local csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local csum_err_s + local csum_err_c + csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) if [ $csum_err_s_nr -gt 0 ]; then - printf "[ FAIL ]\nserver got $csum_err_s_nr data checksum error[s]" + printf "[ FAIL ]\nserver got %d data checksum error[s]" ${csum_err_s_nr} rets=1 fi local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) if [ $csum_err_c_nr -gt 0 ]; then - printf "[ FAIL ]\nclient got $csum_err_c_nr data checksum error[s]" + printf "[ FAIL ]\nclient got %d data checksum error[s]" ${csum_err_c_nr} retc=1 fi fi - if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then - printf "[ OK ]" - mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}" - else - mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}" + if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + mptcp_lib_pr_fail "unexpected fallback to TCP" + rets=1 fi if [ $cookies -eq 2 ];then if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then - printf " WARN: CookieSent: did not advance" + extra+=" WARN: CookieSent: did not advance" fi if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then - printf " WARN: CookieRecv: did not advance" + extra+=" WARN: CookieRecv: did not advance" fi else if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then - printf " WARN: CookieSent: changed" + extra+=" WARN: CookieSent: changed" fi if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then - printf " WARN: CookieRecv: changed" + extra+=" WARN: CookieRecv: changed" fi fi if [ ${stat_synrx_now_l} -gt ${expect_synrx} ]; then - printf " WARN: SYNRX: expect %d, got %d (probably retransmissions)" \ - "${expect_synrx}" "${stat_synrx_now_l}" + extra+=" WARN: SYNRX: expect ${expect_synrx}," + extra+=" got ${stat_synrx_now_l} (probably retransmissions)" fi if [ ${stat_ackrx_now_l} -gt ${expect_ackrx} ]; then - printf " WARN: ACKRX: expect %d, got %d (probably retransmissions)" \ - "${expect_ackrx}" "${stat_ackrx_now_l}" + extra+=" WARN: ACKRX: expect ${expect_ackrx}," + extra+=" got ${stat_ackrx_now_l} (probably retransmissions)" + fi + + if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then + printf "[ OK ]%s\n" "${extra:1}" + mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}" + else + if [ -n "${extra}" ]; then + printf "%s\n" "${extra:1}" + fi + mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}" fi - echo cat "$capout" [ $retc -eq 0 ] && [ $rets -eq 0 ] } @@ -658,7 +690,7 @@ run_test_transparent() return fi -ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" + if ! ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" flush ruleset table inet mangle { chain divert { @@ -669,7 +701,7 @@ table inet mangle { } } EOF - if [ $? -ne 0 ]; then + then echo "SKIP: $msg, could not load nft ruleset" mptcp_lib_fail_if_expected_feature "nft rules" mptcp_lib_result_skip "${TEST_GROUP}" @@ -684,8 +716,7 @@ EOF local_addr="0.0.0.0" fi - ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100 - if [ $? -ne 0 ]; then + if ! ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100; then ip netns exec "$listener_ns" nft flush ruleset echo "SKIP: $msg, ip $r6flag rule failed" mptcp_lib_fail_if_expected_feature "ip rule" @@ -693,8 +724,7 @@ EOF return fi - ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100 - if [ $? -ne 0 ]; then + if ! ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100; then ip netns exec "$listener_ns" nft flush ruleset ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100 echo "SKIP: $msg, ip route add local $local_addr failed" @@ -854,10 +884,10 @@ mptcp_lib_result_code "${ret}" "ping tests" stop_if_error "Could not even run ping tests" [ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms -echo -n "INFO: Using loss of $tc_loss " -test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " +tc_info="loss of $tc_loss " +test "$tc_delay" -gt 0 && tc_info+="delay $tc_delay ms " -reorder_delay=$(($tc_delay / 4)) +reorder_delay=$((tc_delay / 4)) if [ -z "${tc_reorder}" ]; then reorder1=$((RANDOM%10)) @@ -866,17 +896,17 @@ if [ -z "${tc_reorder}" ]; then if [ $reorder_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then tc_reorder="reorder ${reorder1}% ${reorder2}%" - echo -n "$tc_reorder with delay ${reorder_delay}ms " + tc_info+="$tc_reorder with delay ${reorder_delay}ms " fi elif [ "$tc_reorder" = "0" ];then tc_reorder="" elif [ "$reorder_delay" -gt 0 ];then # reordering requires some delay tc_reorder="reorder $tc_reorder" - echo -n "$tc_reorder with delay ${reorder_delay}ms " + tc_info+="$tc_reorder with delay ${reorder_delay}ms " fi -echo "on ns3eth4" +echo "INFO: Using ${tc_info}on ns3eth4" tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index e4581b0dfb967..00053852ca157 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -135,8 +135,8 @@ init_shapers() { local i for i in $(seq 1 4); do - tc -n $ns1 qdisc add dev ns1eth$i root netem rate 20mbit delay 1 - tc -n $ns2 qdisc add dev ns2eth$i root netem rate 20mbit delay 1 + tc -n $ns1 qdisc add dev ns1eth$i root netem rate 20mbit delay 1ms + tc -n $ns2 qdisc add dev ns2eth$i root netem rate 20mbit delay 1ms done } @@ -307,6 +307,8 @@ reset() TEST_COUNT=$((TEST_COUNT+1)) + MPTCP_LIB_SUBTEST_FLAKY=0 # reset if modified + if skip_test; then last_test_ignored=1 return 1 @@ -499,6 +501,10 @@ fail_test() { ret=1 + if ! mptcp_lib_subtest_is_flaky; then + ret=${KSFT_FAIL} + fi + print_fail "${@}" # just in case a test is marked twice as failed @@ -773,7 +779,7 @@ pm_nl_check_endpoint() [ -n "$_flags" ]; flags="flags $_flags" shift elif [ $1 = "dev" ]; then - [ -n "$2" ]; dev="dev $1" + [ -n "$2" ]; dev="dev $2" shift elif [ $1 = "id" ]; then _id=$2 @@ -799,18 +805,18 @@ pm_nl_check_endpoint() line="${line% }" # the dump order is: address id flags port dev [ -n "$addr" ] && expected_line="$addr" - expected_line="$expected_line $id" - [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" - [ -n "$dev" ] && expected_line="$expected_line $dev" - [ -n "$port" ] && expected_line="$expected_line $port" + expected_line+=" $id" + [ -n "$_flags" ] && expected_line+=" ${_flags//","/" "}" + [ -n "$dev" ] && expected_line+=" $dev" + [ -n "$port" ] && expected_line+=" $port" else line=$(ip netns exec $ns ./pm_nl_ctl get $_id) # the dump order is: id flags dev address port expected_line="$id" - [ -n "$flags" ] && expected_line="$expected_line $flags" - [ -n "$dev" ] && expected_line="$expected_line $dev" - [ -n "$addr" ] && expected_line="$expected_line $addr" - [ -n "$_port" ] && expected_line="$expected_line $_port" + [ -n "$flags" ] && expected_line+=" $flags" + [ -n "$dev" ] && expected_line+=" $dev" + [ -n "$addr" ] && expected_line+=" $addr" + [ -n "$_port" ] && expected_line+=" $_port" fi if [ "$line" = "$expected_line" ]; then print_ok @@ -1261,7 +1267,7 @@ chk_csum_nr() print_check "sum" count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then - extra_msg="$extra_msg ns1=$count" + extra_msg+=" ns1=$count" fi if [ -z "$count" ]; then print_skip @@ -1274,7 +1280,7 @@ chk_csum_nr() print_check "csum" count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then - extra_msg="$extra_msg ns2=$count" + extra_msg+=" ns2=$count" fi if [ -z "$count" ]; then print_skip @@ -1318,7 +1324,7 @@ chk_fail_nr() print_check "ftx" count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then - extra_msg="$extra_msg,tx=$count" + extra_msg+=",tx=$count" fi if [ -z "$count" ]; then print_skip @@ -1332,7 +1338,7 @@ chk_fail_nr() print_check "failrx" count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then - extra_msg="$extra_msg,rx=$count" + extra_msg+=",rx=$count" fi if [ -z "$count" ]; then print_skip @@ -1367,7 +1373,7 @@ chk_fclose_nr() if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_tx" ]; then - extra_msg="$extra_msg,tx=$count" + extra_msg+=",tx=$count" fail_test "got $count MP_FASTCLOSE[s] TX expected $fclose_tx" else print_ok @@ -1378,7 +1384,7 @@ chk_fclose_nr() if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_rx" ]; then - extra_msg="$extra_msg,rx=$count" + extra_msg+=",rx=$count" fail_test "got $count MP_FASTCLOSE[s] RX expected $fclose_rx" else print_ok @@ -1747,7 +1753,7 @@ chk_rm_nr() count=$((count + cnt)) if [ "$count" != "$rm_subflow_nr" ]; then suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" - extra_msg="$extra_msg simult" + extra_msg+=" simult" fi if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then @@ -2398,9 +2404,10 @@ remove_tests() if reset "remove invalid addresses"; then pm_nl_set_limits $ns1 3 3 pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + # broadcast IP: no packet for this address will be received on ns1 + pm_nl_add_endpoint $ns1 224.0.0.1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.14.1 flags signal - pm_nl_set_limits $ns2 3 3 + pm_nl_set_limits $ns2 2 2 addr_nr_ns1=-3 speed=10 \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 @@ -3245,6 +3252,7 @@ fullmesh_tests() fastclose_tests() { if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=client \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 @@ -3253,6 +3261,7 @@ fastclose_tests() fi if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=server \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 0 0 0 1 @@ -3271,6 +3280,7 @@ fail_tests() { # single subflow if reset_with_fail "Infinite map" 1; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=128 \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)" @@ -3279,7 +3289,8 @@ fail_tests() # multiple subflows if reset_with_fail "MP_FAIL MP_RST" 2; then - tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5 + MPTCP_LIB_SUBTEST_FLAKY=1 + tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5ms pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow @@ -3589,6 +3600,8 @@ endpoint_tests() local tests_pid=$! wait_mpj $ns2 + pm_nl_check_endpoint "creation" \ + $ns2 10.0.2.2 id 2 flags subflow dev ns2eth2 chk_subflow_nr "before delete" 2 chk_mptcp_info subflows 1 subflows 1 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 8f9ddb3ad4fe8..9831d7655b987 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -218,8 +218,8 @@ run_test() shift 4 local msg=$* - [ $delay1 -gt 0 ] && delay1="delay $delay1" || delay1="" - [ $delay2 -gt 0 ] && delay2="delay $delay2" || delay2="" + [ $delay1 -gt 0 ] && delay1="delay ${delay1}ms" || delay1="" + [ $delay2 -gt 0 ] && delay2="delay ${delay2}ms" || delay2="" for dev in ns1eth1 ns1eth2; do tc -n $ns1 qdisc del dev $dev root >/dev/null 2>&1 @@ -245,7 +245,7 @@ run_test() do_transfer $small $large $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" - if [ $lret -ne 0 ]; then + if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then ret=$lret [ $bail -eq 0 ] || exit $ret fi @@ -255,7 +255,7 @@ run_test() do_transfer $large $small $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" - if [ $lret -ne 0 ]; then + if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then ret=$lret [ $bail -eq 0 ] || exit $ret fi @@ -288,7 +288,7 @@ run_test 10 10 0 0 "balanced bwidth" run_test 10 10 1 25 "balanced bwidth with unbalanced delay" # we still need some additional infrastructure to pass the following test-cases -run_test 10 3 0 0 "unbalanced bwidth" +MPTCP_LIB_SUBTEST_FLAKY=1 run_test 10 3 0 0 "unbalanced bwidth" run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay" run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 1b94a75604fee..2d0654c2559eb 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -174,10 +174,12 @@ make_connection() local is_v6=$1 local app_port=$app4_port local connect_addr="10.0.1.1" + local client_addr="10.0.1.2" local listen_addr="0.0.0.0" if [ "$is_v6" = "v6" ] then connect_addr="dead:beef:1::1" + client_addr="dead:beef:1::2" listen_addr="::" app_port=$app6_port else @@ -239,6 +241,7 @@ make_connection() [ "$server_serverside" = 1 ] then test_pass + print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}" else test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" mptcp_lib_result_print_all_tap @@ -359,7 +362,7 @@ test_announce() ip netns exec "$ns2"\ ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\ ns2eth1 - print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, reuse port" + print_test "ADD_ADDR id:client 10.0.2.2 (ns2) => ns1, reuse port" sleep 0.5 verify_announce_event $server_evts $ANNOUNCED $server4_token "10.0.2.2" $client_addr_id \ "$client4_port" @@ -368,7 +371,7 @@ test_announce() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl ann\ dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1 - print_test "ADD_ADDR6 id:${client_addr_id} dead:beef:2::2 (ns2) => ns1, reuse port" + print_test "ADD_ADDR6 id:client dead:beef:2::2 (ns2) => ns1, reuse port" sleep 0.5 verify_announce_event "$server_evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\ "$client_addr_id" "$client6_port" "v6" @@ -378,7 +381,7 @@ test_announce() client_addr_id=$((client_addr_id+1)) ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ $client_addr_id dev ns2eth1 port $new4_port - print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, new port" + print_test "ADD_ADDR id:client+1 10.0.2.2 (ns2) => ns1, new port" sleep 0.5 verify_announce_event "$server_evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\ "$client_addr_id" "$new4_port" @@ -389,7 +392,7 @@ test_announce() # ADD_ADDR from the server to client machine reusing the subflow port ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR id:server 10.0.2.1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ "$server_addr_id" "$app4_port" @@ -398,7 +401,7 @@ test_announce() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR6 id:${server_addr_id} dead:beef:2::1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR6 id:server dead:beef:2::1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\ "$server_addr_id" "$app6_port" "v6" @@ -408,7 +411,7 @@ test_announce() server_addr_id=$((server_addr_id+1)) ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ $server_addr_id dev ns1eth2 port $new4_port - print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, new port" + print_test "ADD_ADDR id:server+1 10.0.2.1 (ns1) => ns2, new port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ "$server_addr_id" "$new4_port" @@ -442,7 +445,7 @@ test_remove() local invalid_token=$(( client4_token - 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token $invalid_token id\ $client_addr_id > /dev/null 2>&1 - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1, invalid token" + print_test "RM_ADDR id:client ns2 => ns1, invalid token" local type type=$(mptcp_lib_evts_get_info type "$server_evts") if [ "$type" = "" ] @@ -456,7 +459,7 @@ test_remove() local invalid_id=$(( client_addr_id + 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $invalid_id > /dev/null 2>&1 - print_test "RM_ADDR id:${invalid_id} ns2 => ns1, invalid id" + print_test "RM_ADDR id:client+1 ns2 => ns1, invalid id" type=$(mptcp_lib_evts_get_info type "$server_evts") if [ "$type" = "" ] then @@ -469,7 +472,7 @@ test_remove() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $client_addr_id - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR id:client ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -478,7 +481,7 @@ test_remove() client_addr_id=$(( client_addr_id - 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $client_addr_id - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR id:client-1 ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -486,7 +489,7 @@ test_remove() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\ $client_addr_id - print_test "RM_ADDR6 id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR6 id:client-1 ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id" @@ -496,7 +499,7 @@ test_remove() # RM_ADDR from the server to client machine ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ $server_addr_id - print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR id:server ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -505,7 +508,7 @@ test_remove() server_addr_id=$(( server_addr_id - 1 )) ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ $server_addr_id - print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR id:server-1 ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -513,7 +516,7 @@ test_remove() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\ $server_addr_id - print_test "RM_ADDR6 id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR6 id:server-1 ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client6_token" "$server_addr_id" } @@ -541,8 +544,14 @@ verify_subflow_events() local locid local remid local info + local e_dport_txt - info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})" + # only display the fixed ports + if [ "${e_dport}" -ge "${app4_port}" ] && [ "${e_dport}" -le "${app6_port}" ]; then + e_dport_txt=":${e_dport}" + fi + + info="${e_saddr} (${e_from}) => ${e_daddr}${e_dport_txt} (${e_to})" if [ "$e_type" = "$SUB_ESTABLISHED" ] then @@ -828,7 +837,7 @@ test_subflows_v4_v6_mix() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR4 id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR4 id:server 10.0.2.1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\ "$server_addr_id" "$app6_port" @@ -907,12 +916,6 @@ verify_listener_events() local saddr local sport - if [ $e_type = $LISTENER_CREATED ]; then - print_test "CREATE_LISTENER $e_saddr:$e_sport" - elif [ $e_type = $LISTENER_CLOSED ]; then - print_test "CLOSE_LISTENER $e_saddr:$e_sport" - fi - type=$(mptcp_lib_evts_get_info type $evt $e_type) family=$(mptcp_lib_evts_get_info family $evt $e_type) sport=$(mptcp_lib_evts_get_info sport $evt $e_type) @@ -944,6 +947,7 @@ test_listener() local listener_pid=$! sleep 0.5 + print_test "CREATE_LISTENER 10.0.2.2 (client port)" verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port # ADD_ADDR from client to server machine reusing the subflow port @@ -960,12 +964,14 @@ test_listener() mptcp_lib_kill_wait $listener_pid sleep 0.5 + print_test "CLOSE_LISTENER 10.0.2.2 (client port)" verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } print_title "Make connections" make_connection make_connection "v6" +print_title "Will be using address IDs ${client_addr_id} (client) and ${server_addr_id} (server)" test_announce test_remove diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 36e40256ab92a..bab7436c68348 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # OVS kernel module self tests diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c index 7c5b12664b03b..bfb07dc495186 100644 --- a/tools/testing/selftests/net/reuseaddr_conflict.c +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -109,6 +109,6 @@ int main(void) fd1 = open_port(0, 1); if (fd1 >= 0) error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); - fprintf(stderr, "Success"); + fprintf(stderr, "Success\n"); return 0; } diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings index ed8418e8217a0..e7b9417537fbc 100644 --- a/tools/testing/selftests/net/settings +++ b/tools/testing/selftests/net/settings @@ -1 +1 @@ -timeout=3600 +timeout=0 diff --git a/tools/testing/selftests/net/socket.c b/tools/testing/selftests/net/socket.c index db1aeb8c5d1eb..96b1d7467ef50 100644 --- a/tools/testing/selftests/net/socket.c +++ b/tools/testing/selftests/net/socket.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "../kselftest.h" @@ -26,7 +27,10 @@ struct socket_testcase { }; static struct socket_testcase tests[] = { - { AF_MAX, 0, 0, -EAFNOSUPPORT, 0 }, + /* libc might have a smaller value of AF_MAX than the kernel + * actually supports, so use INT_MAX instead. + */ + { INT_MAX, 0, 0, -EAFNOSUPPORT, 0 }, { AF_INET, SOCK_STREAM, IPPROTO_TCP, 0, 1 }, { AF_INET, SOCK_DGRAM, IPPROTO_TCP, -EPROTONOSUPPORT, 1 }, { AF_INET, SOCK_DGRAM, IPPROTO_UDP, 0, 1 }, diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c index 2fb6dd8adba69..8b984fa042869 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/proc.c +++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c @@ -86,7 +86,7 @@ static void netstat_read_type(FILE *fnetstat, struct netstat **dest, char *line) pos = strchr(line, ' ') + 1; - if (fscanf(fnetstat, type->header_name) == EOF) + if (fscanf(fnetstat, "%[^ :]", type->header_name) == EOF) test_error("fscanf(%s)", type->header_name); if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != ':') test_error("Unexpected netstat format (%c)", tmp); diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c index 92276f916f2f3..e408b9243b2c5 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/setup.c +++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c @@ -17,37 +17,37 @@ static pthread_mutex_t ksft_print_lock = PTHREAD_MUTEX_INITIALIZER; void __test_msg(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_print_msg(buf); + ksft_print_msg("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_ok(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_pass(buf); + ksft_test_result_pass("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_fail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_fail(buf); + ksft_test_result_fail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_xfail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_xfail(buf); + ksft_test_result_xfail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_error(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_error(buf); + ksft_test_result_error("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_skip(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_skip(buf); + ksft_test_result_skip("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index 7df8b8700e39e..a2fe88d35ac06 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -256,8 +256,6 @@ static int test_wait_fds(int sk[], size_t nr, bool is_writable[], static void test_client_active_rst(unsigned int port) { - /* one in queue, another accept()ed */ - unsigned int wait_for = backlog + 2; int i, sk[3], err; bool is_writable[ARRAY_SIZE(sk)] = {false}; unsigned int last = ARRAY_SIZE(sk) - 1; @@ -275,16 +273,20 @@ static void test_client_active_rst(unsigned int port) for (i = 0; i < last; i++) { err = _test_connect_socket(sk[i], this_ip_dest, port, (i == 0) ? TEST_TIMEOUT_SEC : -1); - if (err < 0) test_error("failed to connect()"); } - synchronize_threads(); /* 2: connection accept()ed, another queued */ - err = test_wait_fds(sk, last, is_writable, wait_for, TEST_TIMEOUT_SEC); + synchronize_threads(); /* 2: two connections: one accept()ed, another queued */ + err = test_wait_fds(sk, last, is_writable, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("test_wait_fds(): %d", err); + /* async connect() with third sk to get into request_sock_queue */ + err = _test_connect_socket(sk[last], this_ip_dest, port, -1); + if (err < 0) + test_error("failed to connect()"); + synchronize_threads(); /* 3: close listen socket */ if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); @@ -292,13 +294,14 @@ static void test_client_active_rst(unsigned int port) test_ok("Verified established tcp connection"); synchronize_threads(); /* 4: finishing up */ - err = _test_connect_socket(sk[last], this_ip_dest, port, -1); - if (err < 0) - test_error("failed to connect()"); synchronize_threads(); /* 5: closed active sk */ - err = test_wait_fds(sk, ARRAY_SIZE(sk), NULL, - wait_for, TEST_TIMEOUT_SEC); + /* + * Wait for 2 connections: one accepted, another in the accept queue, + * the one in request_sock_queue won't get fully established, so + * doesn't receive an active RST, see inet_csk_listen_stop(). + */ + err = test_wait_fds(sk, last, NULL, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("select(): %d", err); diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c index 452de131fa3a9..517930f9721bd 100644 --- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c +++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c @@ -21,7 +21,7 @@ static void make_listen(int sk) static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info, const char *tst) { - struct tcp_ao_info_opt tmp; + struct tcp_ao_info_opt tmp = {}; socklen_t len = sizeof(tmp); if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, &tmp, &len)) diff --git a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh index 8533393a4f186..02b986c9c247d 100755 --- a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh +++ b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh @@ -154,17 +154,9 @@ setup_topo() setup_topo_ns $ns done - ip link add name veth0 type veth peer name veth1 - ip link set dev veth0 netns $h1 name eth0 - ip link set dev veth1 netns $sw1 name swp1 - - ip link add name veth0 type veth peer name veth1 - ip link set dev veth0 netns $sw1 name veth0 - ip link set dev veth1 netns $sw2 name veth0 - - ip link add name veth0 type veth peer name veth1 - ip link set dev veth0 netns $h2 name eth0 - ip link set dev veth1 netns $sw2 name swp1 + ip -n $h1 link add name eth0 type veth peer name swp1 netns $sw1 + ip -n $sw1 link add name veth0 type veth peer name veth0 netns $sw2 + ip -n $h2 link add name eth0 type veth peer name swp1 netns $sw2 } setup_host_common() diff --git a/tools/testing/selftests/net/test_vxlan_mdb.sh b/tools/testing/selftests/net/test_vxlan_mdb.sh index 84a05a9e46d86..04fb17a92e993 100755 --- a/tools/testing/selftests/net/test_vxlan_mdb.sh +++ b/tools/testing/selftests/net/test_vxlan_mdb.sh @@ -1177,6 +1177,7 @@ encap_params_common() local plen=$1; shift local enc_ethtype=$1; shift local grp=$1; shift + local grp_dmac=$1; shift local src=$1; shift local mz=$1; shift @@ -1195,11 +1196,11 @@ encap_params_common() run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent dst $vtep2_ip src_vni 10020" run_cmd "tc -n $ns2 filter replace dev vx0 ingress pref 1 handle 101 proto all flower enc_dst_ip $vtep1_ip action pass" - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Destination IP - match" - run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Destination IP - no match" @@ -1212,20 +1213,20 @@ encap_params_common() run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent dst $vtep1_ip dst_port 1111 src_vni 10020" run_cmd "tc -n $ns2 filter replace dev veth0 ingress pref 1 handle 101 proto $enc_ethtype flower ip_proto udp dst_port 4789 action pass" - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev veth0 ingress" 101 1 log_test $? 0 "Default destination port - match" - run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev veth0 ingress" 101 1 log_test $? 0 "Default destination port - no match" run_cmd "tc -n $ns2 filter replace dev veth0 ingress pref 1 handle 101 proto $enc_ethtype flower ip_proto udp dst_port 1111 action pass" - run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev veth0 ingress" 101 1 log_test $? 0 "Non-default destination port - match" - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev veth0 ingress" 101 1 log_test $? 0 "Non-default destination port - no match" @@ -1238,11 +1239,11 @@ encap_params_common() run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent dst $vtep1_ip src_vni 10020" run_cmd "tc -n $ns2 filter replace dev vx0 ingress pref 1 handle 101 proto all flower enc_key_id 10010 action pass" - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Default destination VNI - match" - run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Default destination VNI - no match" @@ -1250,11 +1251,11 @@ encap_params_common() run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent dst $vtep1_ip vni 10010 src_vni 10020" run_cmd "tc -n $ns2 filter replace dev vx0 ingress pref 1 handle 101 proto all flower enc_key_id 10020 action pass" - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Non-default destination VNI - match" - run_cmd "ip netns exec $ns1 $mz br0.20 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.20 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Non-default destination VNI - no match" @@ -1272,6 +1273,7 @@ encap_params_ipv4_ipv4() local plen=32 local enc_ethtype="ip" local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local src=192.0.2.129 echo @@ -1279,7 +1281,7 @@ encap_params_ipv4_ipv4() echo "------------------------------------------------------------------" encap_params_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $enc_ethtype \ - $grp $src "mausezahn" + $grp $grp_dmac $src "mausezahn" } encap_params_ipv6_ipv4() @@ -1291,6 +1293,7 @@ encap_params_ipv6_ipv4() local plen=32 local enc_ethtype="ip" local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local src=2001:db8:100::1 echo @@ -1298,7 +1301,7 @@ encap_params_ipv6_ipv4() echo "------------------------------------------------------------------" encap_params_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $enc_ethtype \ - $grp $src "mausezahn -6" + $grp $grp_dmac $src "mausezahn -6" } encap_params_ipv4_ipv6() @@ -1310,6 +1313,7 @@ encap_params_ipv4_ipv6() local plen=128 local enc_ethtype="ipv6" local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local src=192.0.2.129 echo @@ -1317,7 +1321,7 @@ encap_params_ipv4_ipv6() echo "------------------------------------------------------------------" encap_params_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $enc_ethtype \ - $grp $src "mausezahn" + $grp $grp_dmac $src "mausezahn" } encap_params_ipv6_ipv6() @@ -1329,6 +1333,7 @@ encap_params_ipv6_ipv6() local plen=128 local enc_ethtype="ipv6" local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local src=2001:db8:100::1 echo @@ -1336,7 +1341,7 @@ encap_params_ipv6_ipv6() echo "------------------------------------------------------------------" encap_params_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $enc_ethtype \ - $grp $src "mausezahn -6" + $grp $grp_dmac $src "mausezahn -6" } starg_exclude_ir_common() @@ -1347,6 +1352,7 @@ starg_exclude_ir_common() local vtep2_ip=$1; shift local plen=$1; shift local grp=$1; shift + local grp_dmac=$1; shift local valid_src=$1; shift local invalid_src=$1; shift local mz=$1; shift @@ -1368,14 +1374,14 @@ starg_exclude_ir_common() run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $invalid_src dst $vtep2_ip src_vni 10010" # Check that invalid source is not forwarded to any VTEP. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 0 log_test $? 0 "Block excluded source - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 0 log_test $? 0 "Block excluded source - second VTEP" # Check that valid source is forwarded to both VTEPs. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Forward valid source - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 1 @@ -1385,14 +1391,14 @@ starg_exclude_ir_common() run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep2_ip src_vni 10010" # Check that invalid source is not forwarded to any VTEP. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Block excluded source after removal - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 1 log_test $? 0 "Block excluded source after removal - second VTEP" # Check that valid source is forwarded to the remaining VTEP. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 2 log_test $? 0 "Forward valid source after removal - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 1 @@ -1407,6 +1413,7 @@ starg_exclude_ir_ipv4_ipv4() local vtep2_ip=198.51.100.200 local plen=32 local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local valid_src=192.0.2.129 local invalid_src=192.0.2.145 @@ -1415,7 +1422,7 @@ starg_exclude_ir_ipv4_ipv4() echo "-------------------------------------------------------------" starg_exclude_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \ - $valid_src $invalid_src "mausezahn" + $grp_dmac $valid_src $invalid_src "mausezahn" } starg_exclude_ir_ipv6_ipv4() @@ -1426,6 +1433,7 @@ starg_exclude_ir_ipv6_ipv4() local vtep2_ip=198.51.100.200 local plen=32 local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local valid_src=2001:db8:100::1 local invalid_src=2001:db8:200::1 @@ -1434,7 +1442,7 @@ starg_exclude_ir_ipv6_ipv4() echo "-------------------------------------------------------------" starg_exclude_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \ - $valid_src $invalid_src "mausezahn -6" + $grp_dmac $valid_src $invalid_src "mausezahn -6" } starg_exclude_ir_ipv4_ipv6() @@ -1445,6 +1453,7 @@ starg_exclude_ir_ipv4_ipv6() local vtep2_ip=2001:db8:2000::1 local plen=128 local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local valid_src=192.0.2.129 local invalid_src=192.0.2.145 @@ -1453,7 +1462,7 @@ starg_exclude_ir_ipv4_ipv6() echo "-------------------------------------------------------------" starg_exclude_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \ - $valid_src $invalid_src "mausezahn" + $grp_dmac $valid_src $invalid_src "mausezahn" } starg_exclude_ir_ipv6_ipv6() @@ -1464,6 +1473,7 @@ starg_exclude_ir_ipv6_ipv6() local vtep2_ip=2001:db8:2000::1 local plen=128 local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local valid_src=2001:db8:100::1 local invalid_src=2001:db8:200::1 @@ -1472,7 +1482,7 @@ starg_exclude_ir_ipv6_ipv6() echo "-------------------------------------------------------------" starg_exclude_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \ - $valid_src $invalid_src "mausezahn -6" + $grp_dmac $valid_src $invalid_src "mausezahn -6" } starg_include_ir_common() @@ -1483,6 +1493,7 @@ starg_include_ir_common() local vtep2_ip=$1; shift local plen=$1; shift local grp=$1; shift + local grp_dmac=$1; shift local valid_src=$1; shift local invalid_src=$1; shift local mz=$1; shift @@ -1504,14 +1515,14 @@ starg_include_ir_common() run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode include source_list $valid_src dst $vtep2_ip src_vni 10010" # Check that invalid source is not forwarded to any VTEP. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 0 log_test $? 0 "Block excluded source - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 0 log_test $? 0 "Block excluded source - second VTEP" # Check that valid source is forwarded to both VTEPs. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Forward valid source - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 1 @@ -1521,14 +1532,14 @@ starg_include_ir_common() run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep2_ip src_vni 10010" # Check that invalid source is not forwarded to any VTEP. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Block excluded source after removal - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 1 log_test $? 0 "Block excluded source after removal - second VTEP" # Check that valid source is forwarded to the remaining VTEP. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 2 log_test $? 0 "Forward valid source after removal - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 1 @@ -1543,6 +1554,7 @@ starg_include_ir_ipv4_ipv4() local vtep2_ip=198.51.100.200 local plen=32 local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local valid_src=192.0.2.129 local invalid_src=192.0.2.145 @@ -1551,7 +1563,7 @@ starg_include_ir_ipv4_ipv4() echo "-------------------------------------------------------------" starg_include_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \ - $valid_src $invalid_src "mausezahn" + $grp_dmac $valid_src $invalid_src "mausezahn" } starg_include_ir_ipv6_ipv4() @@ -1562,6 +1574,7 @@ starg_include_ir_ipv6_ipv4() local vtep2_ip=198.51.100.200 local plen=32 local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local valid_src=2001:db8:100::1 local invalid_src=2001:db8:200::1 @@ -1570,7 +1583,7 @@ starg_include_ir_ipv6_ipv4() echo "-------------------------------------------------------------" starg_include_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \ - $valid_src $invalid_src "mausezahn -6" + $grp_dmac $valid_src $invalid_src "mausezahn -6" } starg_include_ir_ipv4_ipv6() @@ -1581,6 +1594,7 @@ starg_include_ir_ipv4_ipv6() local vtep2_ip=2001:db8:2000::1 local plen=128 local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local valid_src=192.0.2.129 local invalid_src=192.0.2.145 @@ -1589,7 +1603,7 @@ starg_include_ir_ipv4_ipv6() echo "-------------------------------------------------------------" starg_include_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \ - $valid_src $invalid_src "mausezahn" + $grp_dmac $valid_src $invalid_src "mausezahn" } starg_include_ir_ipv6_ipv6() @@ -1600,6 +1614,7 @@ starg_include_ir_ipv6_ipv6() local vtep2_ip=2001:db8:2000::1 local plen=128 local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local valid_src=2001:db8:100::1 local invalid_src=2001:db8:200::1 @@ -1608,7 +1623,7 @@ starg_include_ir_ipv6_ipv6() echo "-------------------------------------------------------------" starg_include_ir_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $grp \ - $valid_src $invalid_src "mausezahn -6" + $grp_dmac $valid_src $invalid_src "mausezahn -6" } starg_exclude_p2mp_common() @@ -1618,6 +1633,7 @@ starg_exclude_p2mp_common() local mcast_grp=$1; shift local plen=$1; shift local grp=$1; shift + local grp_dmac=$1; shift local valid_src=$1; shift local invalid_src=$1; shift local mz=$1; shift @@ -1635,12 +1651,12 @@ starg_exclude_p2mp_common() run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode exclude source_list $invalid_src dst $mcast_grp src_vni 10010 via veth0" # Check that invalid source is not forwarded. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 0 log_test $? 0 "Block excluded source" # Check that valid source is forwarded. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Forward valid source" @@ -1648,7 +1664,7 @@ starg_exclude_p2mp_common() run_cmd "ip -n $ns2 address del $mcast_grp/$plen dev veth0" # Check that valid source is not received anymore. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Receive of valid source after removal from group" } @@ -1660,6 +1676,7 @@ starg_exclude_p2mp_ipv4_ipv4() local mcast_grp=238.1.1.1 local plen=32 local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local valid_src=192.0.2.129 local invalid_src=192.0.2.145 @@ -1667,7 +1684,7 @@ starg_exclude_p2mp_ipv4_ipv4() echo "Data path: (*, G) EXCLUDE - P2MP - IPv4 overlay / IPv4 underlay" echo "---------------------------------------------------------------" - starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \ + starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \ $valid_src $invalid_src "mausezahn" } @@ -1678,6 +1695,7 @@ starg_exclude_p2mp_ipv6_ipv4() local mcast_grp=238.1.1.1 local plen=32 local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local valid_src=2001:db8:100::1 local invalid_src=2001:db8:200::1 @@ -1685,7 +1703,7 @@ starg_exclude_p2mp_ipv6_ipv4() echo "Data path: (*, G) EXCLUDE - P2MP - IPv6 overlay / IPv4 underlay" echo "---------------------------------------------------------------" - starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \ + starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \ $valid_src $invalid_src "mausezahn -6" } @@ -1696,6 +1714,7 @@ starg_exclude_p2mp_ipv4_ipv6() local mcast_grp=ff0e::2 local plen=128 local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local valid_src=192.0.2.129 local invalid_src=192.0.2.145 @@ -1703,7 +1722,7 @@ starg_exclude_p2mp_ipv4_ipv6() echo "Data path: (*, G) EXCLUDE - P2MP - IPv4 overlay / IPv6 underlay" echo "---------------------------------------------------------------" - starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \ + starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \ $valid_src $invalid_src "mausezahn" } @@ -1714,6 +1733,7 @@ starg_exclude_p2mp_ipv6_ipv6() local mcast_grp=ff0e::2 local plen=128 local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local valid_src=2001:db8:100::1 local invalid_src=2001:db8:200::1 @@ -1721,7 +1741,7 @@ starg_exclude_p2mp_ipv6_ipv6() echo "Data path: (*, G) EXCLUDE - P2MP - IPv6 overlay / IPv6 underlay" echo "---------------------------------------------------------------" - starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \ + starg_exclude_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \ $valid_src $invalid_src "mausezahn -6" } @@ -1732,6 +1752,7 @@ starg_include_p2mp_common() local mcast_grp=$1; shift local plen=$1; shift local grp=$1; shift + local grp_dmac=$1; shift local valid_src=$1; shift local invalid_src=$1; shift local mz=$1; shift @@ -1749,12 +1770,12 @@ starg_include_p2mp_common() run_cmd "bridge -n $ns1 mdb replace dev vx0 port vx0 grp $grp permanent filter_mode include source_list $valid_src dst $mcast_grp src_vni 10010 via veth0" # Check that invalid source is not forwarded. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $invalid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 0 log_test $? 0 "Block excluded source" # Check that valid source is forwarded. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Forward valid source" @@ -1762,7 +1783,7 @@ starg_include_p2mp_common() run_cmd "ip -n $ns2 address del $mcast_grp/$plen dev veth0" # Check that valid source is not received anymore. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $valid_src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Receive of valid source after removal from group" } @@ -1774,6 +1795,7 @@ starg_include_p2mp_ipv4_ipv4() local mcast_grp=238.1.1.1 local plen=32 local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local valid_src=192.0.2.129 local invalid_src=192.0.2.145 @@ -1781,7 +1803,7 @@ starg_include_p2mp_ipv4_ipv4() echo "Data path: (*, G) INCLUDE - P2MP - IPv4 overlay / IPv4 underlay" echo "---------------------------------------------------------------" - starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \ + starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \ $valid_src $invalid_src "mausezahn" } @@ -1792,6 +1814,7 @@ starg_include_p2mp_ipv6_ipv4() local mcast_grp=238.1.1.1 local plen=32 local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local valid_src=2001:db8:100::1 local invalid_src=2001:db8:200::1 @@ -1799,7 +1822,7 @@ starg_include_p2mp_ipv6_ipv4() echo "Data path: (*, G) INCLUDE - P2MP - IPv6 overlay / IPv4 underlay" echo "---------------------------------------------------------------" - starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \ + starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \ $valid_src $invalid_src "mausezahn -6" } @@ -1810,6 +1833,7 @@ starg_include_p2mp_ipv4_ipv6() local mcast_grp=ff0e::2 local plen=128 local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local valid_src=192.0.2.129 local invalid_src=192.0.2.145 @@ -1817,7 +1841,7 @@ starg_include_p2mp_ipv4_ipv6() echo "Data path: (*, G) INCLUDE - P2MP - IPv4 overlay / IPv6 underlay" echo "---------------------------------------------------------------" - starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \ + starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \ $valid_src $invalid_src "mausezahn" } @@ -1828,6 +1852,7 @@ starg_include_p2mp_ipv6_ipv6() local mcast_grp=ff0e::2 local plen=128 local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local valid_src=2001:db8:100::1 local invalid_src=2001:db8:200::1 @@ -1835,7 +1860,7 @@ starg_include_p2mp_ipv6_ipv6() echo "Data path: (*, G) INCLUDE - P2MP - IPv6 overlay / IPv6 underlay" echo "---------------------------------------------------------------" - starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp \ + starg_include_p2mp_common $ns1 $ns2 $mcast_grp $plen $grp $grp_dmac \ $valid_src $invalid_src "mausezahn -6" } @@ -1847,6 +1872,7 @@ egress_vni_translation_common() local plen=$1; shift local proto=$1; shift local grp=$1; shift + local grp_dmac=$1; shift local src=$1; shift local mz=$1; shift @@ -1882,20 +1908,20 @@ egress_vni_translation_common() # Make sure that packets sent from the first VTEP over VLAN 10 are # received by the SVI corresponding to the L3VNI (14000 / VLAN 4000) on # the second VTEP, since it is configured as PVID. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev br0.4000 ingress" 101 1 log_test $? 0 "Egress VNI translation - PVID configured" # Remove PVID flag from VLAN 4000 on the second VTEP and make sure # packets are no longer received by the SVI interface. run_cmd "bridge -n $ns2 vlan add vid 4000 dev vx0" - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev br0.4000 ingress" 101 1 log_test $? 0 "Egress VNI translation - no PVID configured" # Reconfigure the PVID and make sure packets are received again. run_cmd "bridge -n $ns2 vlan add vid 4000 dev vx0 pvid" - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev br0.4000 ingress" 101 2 log_test $? 0 "Egress VNI translation - PVID reconfigured" } @@ -1908,6 +1934,7 @@ egress_vni_translation_ipv4_ipv4() local plen=32 local proto="ipv4" local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local src=192.0.2.129 echo @@ -1915,7 +1942,7 @@ egress_vni_translation_ipv4_ipv4() echo "----------------------------------------------------------------" egress_vni_translation_common $ns1 $ns2 $mcast_grp $plen $proto $grp \ - $src "mausezahn" + $grp_dmac $src "mausezahn" } egress_vni_translation_ipv6_ipv4() @@ -1926,6 +1953,7 @@ egress_vni_translation_ipv6_ipv4() local plen=32 local proto="ipv6" local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local src=2001:db8:100::1 echo @@ -1933,7 +1961,7 @@ egress_vni_translation_ipv6_ipv4() echo "----------------------------------------------------------------" egress_vni_translation_common $ns1 $ns2 $mcast_grp $plen $proto $grp \ - $src "mausezahn -6" + $grp_dmac $src "mausezahn -6" } egress_vni_translation_ipv4_ipv6() @@ -1944,6 +1972,7 @@ egress_vni_translation_ipv4_ipv6() local plen=128 local proto="ipv4" local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local src=192.0.2.129 echo @@ -1951,7 +1980,7 @@ egress_vni_translation_ipv4_ipv6() echo "----------------------------------------------------------------" egress_vni_translation_common $ns1 $ns2 $mcast_grp $plen $proto $grp \ - $src "mausezahn" + $grp_dmac $src "mausezahn" } egress_vni_translation_ipv6_ipv6() @@ -1962,6 +1991,7 @@ egress_vni_translation_ipv6_ipv6() local plen=128 local proto="ipv6" local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local src=2001:db8:100::1 echo @@ -1969,7 +1999,7 @@ egress_vni_translation_ipv6_ipv6() echo "----------------------------------------------------------------" egress_vni_translation_common $ns1 $ns2 $mcast_grp $plen $proto $grp \ - $src "mausezahn -6" + $grp_dmac $src "mausezahn -6" } all_zeros_mdb_common() @@ -1982,12 +2012,18 @@ all_zeros_mdb_common() local vtep4_ip=$1; shift local plen=$1; shift local ipv4_grp=239.1.1.1 + local ipv4_grp_dmac=01:00:5e:01:01:01 local ipv4_unreg_grp=239.2.2.2 + local ipv4_unreg_grp_dmac=01:00:5e:02:02:02 local ipv4_ll_grp=224.0.0.100 + local ipv4_ll_grp_dmac=01:00:5e:00:00:64 local ipv4_src=192.0.2.129 local ipv6_grp=ff0e::1 + local ipv6_grp_dmac=33:33:00:00:00:01 local ipv6_unreg_grp=ff0e::2 + local ipv6_unreg_grp_dmac=33:33:00:00:00:02 local ipv6_ll_grp=ff02::1 + local ipv6_ll_grp_dmac=33:33:00:00:00:01 local ipv6_src=2001:db8:100::1 # Install all-zeros (catchall) MDB entries for IPv4 and IPv6 traffic @@ -2023,7 +2059,7 @@ all_zeros_mdb_common() # Send registered IPv4 multicast and make sure it only arrives to the # first VTEP. - run_cmd "ip netns exec $ns1 mausezahn br0.10 -A $ipv4_src -B $ipv4_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 mausezahn br0.10 -a own -b $ipv4_grp_dmac -A $ipv4_src -B $ipv4_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "Registered IPv4 multicast - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 0 @@ -2031,7 +2067,7 @@ all_zeros_mdb_common() # Send unregistered IPv4 multicast that is not link-local and make sure # it arrives to the first and second VTEPs. - run_cmd "ip netns exec $ns1 mausezahn br0.10 -A $ipv4_src -B $ipv4_unreg_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 mausezahn br0.10 -a own -b $ipv4_unreg_grp_dmac -A $ipv4_src -B $ipv4_unreg_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 2 log_test $? 0 "Unregistered IPv4 multicast - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 1 @@ -2039,7 +2075,7 @@ all_zeros_mdb_common() # Send IPv4 link-local multicast traffic and make sure it does not # arrive to any VTEP. - run_cmd "ip netns exec $ns1 mausezahn br0.10 -A $ipv4_src -B $ipv4_ll_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 mausezahn br0.10 -a own -b $ipv4_ll_grp_dmac -A $ipv4_src -B $ipv4_ll_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 2 log_test $? 0 "Link-local IPv4 multicast - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 1 @@ -2074,7 +2110,7 @@ all_zeros_mdb_common() # Send registered IPv6 multicast and make sure it only arrives to the # third VTEP. - run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -A $ipv6_src -B $ipv6_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -a own -b $ipv6_grp_dmac -A $ipv6_src -B $ipv6_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 103 1 log_test $? 0 "Registered IPv6 multicast - third VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 104 0 @@ -2082,7 +2118,7 @@ all_zeros_mdb_common() # Send unregistered IPv6 multicast that is not link-local and make sure # it arrives to the third and fourth VTEPs. - run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -A $ipv6_src -B $ipv6_unreg_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -a own -b $ipv6_unreg_grp_dmac -A $ipv6_src -B $ipv6_unreg_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 103 2 log_test $? 0 "Unregistered IPv6 multicast - third VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 104 1 @@ -2090,7 +2126,7 @@ all_zeros_mdb_common() # Send IPv6 link-local multicast traffic and make sure it does not # arrive to any VTEP. - run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -A $ipv6_src -B $ipv6_ll_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 mausezahn -6 br0.10 -a own -b $ipv6_ll_grp_dmac -A $ipv6_src -B $ipv6_ll_grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 103 2 log_test $? 0 "Link-local IPv6 multicast - third VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 104 1 @@ -2165,6 +2201,7 @@ mdb_fdb_common() local plen=$1; shift local proto=$1; shift local grp=$1; shift + local grp_dmac=$1; shift local src=$1; shift local mz=$1; shift @@ -2188,7 +2225,7 @@ mdb_fdb_common() # Send IP multicast traffic and make sure it is forwarded by the MDB # and only arrives to the first VTEP. - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "IP multicast - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 0 @@ -2205,7 +2242,7 @@ mdb_fdb_common() # Remove the MDB entry and make sure that IP multicast is now forwarded # by the FDB to the second VTEP. run_cmd "bridge -n $ns1 mdb del dev vx0 port vx0 grp $grp dst $vtep1_ip src_vni 10010" - run_cmd "ip netns exec $ns1 $mz br0.10 -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" + run_cmd "ip netns exec $ns1 $mz br0.10 -a own -b $grp_dmac -A $src -B $grp -t udp sp=12345,dp=54321 -p 100 -c 1 -q" tc_check_packets "$ns2" "dev vx0 ingress" 101 1 log_test $? 0 "IP multicast after removal - first VTEP" tc_check_packets "$ns2" "dev vx0 ingress" 102 2 @@ -2221,14 +2258,15 @@ mdb_fdb_ipv4_ipv4() local plen=32 local proto="ipv4" local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local src=192.0.2.129 echo echo "Data path: MDB with FDB - IPv4 overlay / IPv4 underlay" echo "------------------------------------------------------" - mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp $src \ - "mausezahn" + mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp \ + $grp_dmac $src "mausezahn" } mdb_fdb_ipv6_ipv4() @@ -2240,14 +2278,15 @@ mdb_fdb_ipv6_ipv4() local plen=32 local proto="ipv6" local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local src=2001:db8:100::1 echo echo "Data path: MDB with FDB - IPv6 overlay / IPv4 underlay" echo "------------------------------------------------------" - mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp $src \ - "mausezahn -6" + mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp \ + $grp_dmac $src "mausezahn -6" } mdb_fdb_ipv4_ipv6() @@ -2259,14 +2298,15 @@ mdb_fdb_ipv4_ipv6() local plen=128 local proto="ipv4" local grp=239.1.1.1 + local grp_dmac=01:00:5e:01:01:01 local src=192.0.2.129 echo echo "Data path: MDB with FDB - IPv4 overlay / IPv6 underlay" echo "------------------------------------------------------" - mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp $src \ - "mausezahn" + mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp \ + $grp_dmac $src "mausezahn" } mdb_fdb_ipv6_ipv6() @@ -2278,14 +2318,15 @@ mdb_fdb_ipv6_ipv6() local plen=128 local proto="ipv6" local grp=ff0e::1 + local grp_dmac=33:33:00:00:00:01 local src=2001:db8:100::1 echo echo "Data path: MDB with FDB - IPv6 overlay / IPv6 underlay" echo "------------------------------------------------------" - mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp $src \ - "mausezahn -6" + mdb_fdb_common $ns1 $ns2 $vtep1_ip $vtep2_ip $plen $proto $grp \ + $grp_dmac $src "mausezahn -6" } mdb_grp1_loop() @@ -2320,7 +2361,9 @@ mdb_torture_common() local vtep1_ip=$1; shift local vtep2_ip=$1; shift local grp1=$1; shift + local grp1_dmac=$1; shift local grp2=$1; shift + local grp2_dmac=$1; shift local src=$1; shift local mz=$1; shift local pid1 @@ -2345,9 +2388,9 @@ mdb_torture_common() pid1=$! mdb_grp2_loop $ns1 $vtep1_ip $vtep2_ip $grp2 & pid2=$! - ip netns exec $ns1 $mz br0.10 -A $src -B $grp1 -t udp sp=12345,dp=54321 -p 100 -c 0 -q & + ip netns exec $ns1 $mz br0.10 -a own -b $grp1_dmac -A $src -B $grp1 -t udp sp=12345,dp=54321 -p 100 -c 0 -q & pid3=$! - ip netns exec $ns1 $mz br0.10 -A $src -B $grp2 -t udp sp=12345,dp=54321 -p 100 -c 0 -q & + ip netns exec $ns1 $mz br0.10 -a own -b $grp2_dmac -A $src -B $grp2 -t udp sp=12345,dp=54321 -p 100 -c 0 -q & pid4=$! sleep 30 @@ -2363,15 +2406,17 @@ mdb_torture_ipv4_ipv4() local vtep1_ip=198.51.100.100 local vtep2_ip=198.51.100.200 local grp1=239.1.1.1 + local grp1_dmac=01:00:5e:01:01:01 local grp2=239.2.2.2 + local grp2_dmac=01:00:5e:02:02:02 local src=192.0.2.129 echo echo "Data path: MDB torture test - IPv4 overlay / IPv4 underlay" echo "----------------------------------------------------------" - mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp2 $src \ - "mausezahn" + mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp1_dmac $grp2 \ + $grp2_dmac $src "mausezahn" } mdb_torture_ipv6_ipv4() @@ -2380,15 +2425,17 @@ mdb_torture_ipv6_ipv4() local vtep1_ip=198.51.100.100 local vtep2_ip=198.51.100.200 local grp1=ff0e::1 + local grp1_dmac=33:33:00:00:00:01 local grp2=ff0e::2 + local grp2_dmac=33:33:00:00:00:02 local src=2001:db8:100::1 echo echo "Data path: MDB torture test - IPv6 overlay / IPv4 underlay" echo "----------------------------------------------------------" - mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp2 $src \ - "mausezahn -6" + mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp1_dmac $grp2 \ + $grp2_dmac $src "mausezahn -6" } mdb_torture_ipv4_ipv6() @@ -2397,15 +2444,17 @@ mdb_torture_ipv4_ipv6() local vtep1_ip=2001:db8:1000::1 local vtep2_ip=2001:db8:2000::1 local grp1=239.1.1.1 + local grp1_dmac=01:00:5e:01:01:01 local grp2=239.2.2.2 + local grp2_dmac=01:00:5e:02:02:02 local src=192.0.2.129 echo echo "Data path: MDB torture test - IPv4 overlay / IPv6 underlay" echo "----------------------------------------------------------" - mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp2 $src \ - "mausezahn" + mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp1_dmac $grp2 \ + $grp2_dmac $src "mausezahn" } mdb_torture_ipv6_ipv6() @@ -2414,15 +2463,17 @@ mdb_torture_ipv6_ipv6() local vtep1_ip=2001:db8:1000::1 local vtep2_ip=2001:db8:2000::1 local grp1=ff0e::1 + local grp1_dmac=33:33:00:00:00:01 local grp2=ff0e::2 + local grp2_dmac=33:33:00:00:00:02 local src=2001:db8:100::1 echo echo "Data path: MDB torture test - IPv6 overlay / IPv6 underlay" echo "----------------------------------------------------------" - mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp2 $src \ - "mausezahn -6" + mdb_torture_common $ns1 $vtep1_ip $vtep2_ip $grp1 $grp1_dmac $grp2 \ + $grp2_dmac $src "mausezahn -6" } ################################################################################ diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index b95c249f81c25..0450b3ca8b7fe 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -429,64 +429,6 @@ TEST_F(tls, send_then_sendfile) EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size); } -static void chunked_sendfile(struct __test_metadata *_metadata, - struct _test_data_tls *self, - uint16_t chunk_size, - uint16_t extra_payload_size) -{ - char buf[TLS_PAYLOAD_MAX_LEN]; - uint16_t test_payload_size; - int size = 0; - int ret; - char filename[] = "/tmp/mytemp.XXXXXX"; - int fd = mkstemp(filename); - off_t offset = 0; - - unlink(filename); - ASSERT_GE(fd, 0); - EXPECT_GE(chunk_size, 1); - test_payload_size = chunk_size + extra_payload_size; - ASSERT_GE(TLS_PAYLOAD_MAX_LEN, test_payload_size); - memset(buf, 1, test_payload_size); - size = write(fd, buf, test_payload_size); - EXPECT_EQ(size, test_payload_size); - fsync(fd); - - while (size > 0) { - ret = sendfile(self->fd, fd, &offset, chunk_size); - EXPECT_GE(ret, 0); - size -= ret; - } - - EXPECT_EQ(recv(self->cfd, buf, test_payload_size, MSG_WAITALL), - test_payload_size); - - close(fd); -} - -TEST_F(tls, multi_chunk_sendfile) -{ - chunked_sendfile(_metadata, self, 4096, 4096); - chunked_sendfile(_metadata, self, 4096, 0); - chunked_sendfile(_metadata, self, 4096, 1); - chunked_sendfile(_metadata, self, 4096, 2048); - chunked_sendfile(_metadata, self, 8192, 2048); - chunked_sendfile(_metadata, self, 4096, 8192); - chunked_sendfile(_metadata, self, 8192, 4096); - chunked_sendfile(_metadata, self, 12288, 1024); - chunked_sendfile(_metadata, self, 12288, 2000); - chunked_sendfile(_metadata, self, 15360, 100); - chunked_sendfile(_metadata, self, 15360, 300); - chunked_sendfile(_metadata, self, 1, 4096); - chunked_sendfile(_metadata, self, 2048, 4096); - chunked_sendfile(_metadata, self, 2048, 8192); - chunked_sendfile(_metadata, self, 4096, 8192); - chunked_sendfile(_metadata, self, 1024, 12288); - chunked_sendfile(_metadata, self, 2000, 12288); - chunked_sendfile(_metadata, self, 100, 15360); - chunked_sendfile(_metadata, self, 300, 15360); -} - TEST_F(tls, recv_max) { unsigned int send_len = TLS_PAYLOAD_MAX_LEN; diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index 9cd5e885e91f7..f4549e6894dd9 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -241,7 +241,7 @@ for family in 4 6; do create_vxlan_pair ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on - run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1 + run_test "GRO frag list over UDP tunnel" $OL_NET$DST 10 10 cleanup # use NAT to circumvent GRO FWD check @@ -254,13 +254,7 @@ for family in 4 6; do # load arp cache before running the test to reduce the amount of # stray traffic on top of the UDP tunnel ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null - run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST - cleanup - - create_vxlan_pair - run_bench "UDP tunnel fwd perf" $OL_NET$DST - ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on - run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST + run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST cleanup done diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 7badaf215de28..b02080d09fbc0 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -34,7 +34,7 @@ #endif #ifndef UDP_MAX_SEGMENTS -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #endif #define CONST_MTU_TEST 1500 diff --git a/tools/testing/selftests/powerpc/dexcr/Makefile b/tools/testing/selftests/powerpc/dexcr/Makefile index 76210f2bcec3c..829ad075b4a44 100644 --- a/tools/testing/selftests/powerpc/dexcr/Makefile +++ b/tools/testing/selftests/powerpc/dexcr/Makefile @@ -3,7 +3,7 @@ TEST_GEN_FILES := lsdexcr include ../../lib.mk -$(OUTPUT)/hashchk_test: CFLAGS += -fno-pie $(call cc-option,-mno-rop-protect) +$(OUTPUT)/hashchk_test: CFLAGS += -fno-pie -no-pie $(call cc-option,-mno-rop-protect) $(TEST_GEN_PROGS): ../harness.c ../utils.c ./dexcr.c $(TEST_GEN_FILES): ../utils.c ./dexcr.c diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c index 505294da1b9fb..d6f99eb9be659 100644 --- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c +++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c @@ -154,7 +154,7 @@ static int dev_papr_vpd_null_handle(void) static int papr_vpd_close_handle_without_reading(void) { const int devfd = open(DEVPATH, O_RDONLY); - struct papr_location_code lc; + struct papr_location_code lc = { .str = "", }; int fd; SKIP_IF_MSG(devfd < 0 && errno == ENOENT, diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index 1b39b86849da5..30aacf2b3dc70 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -33,7 +33,7 @@ TESTS_64 := $(patsubst %,$(OUTPUT)/%,$(TESTS_64)) $(TESTS_64): CFLAGS += -m64 $(TM_TESTS): CFLAGS += -I../tm -mhtm -CFLAGS += $(KHDR_INCLUDES) -fno-pie +CFLAGS += $(KHDR_INCLUDES) -fno-pie -Wno-error=deprecated $(OUTPUT)/ptrace-gpr: ptrace-gpr.S $(OUTPUT)/ptrace-perf-hwbreak: ptrace-perf-asm.S diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile index 2deac2031de9e..021863f86053a 100644 --- a/tools/testing/selftests/resctrl/Makefile +++ b/tools/testing/selftests/resctrl/Makefile @@ -5,6 +5,8 @@ CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := resctrl_tests +LOCAL_HDRS += $(wildcard *.h) + include ../lib.mk -$(OUTPUT)/resctrl_tests: $(wildcard *.[ch]) +$(OUTPUT)/resctrl_tests: $(wildcard *.c) diff --git a/tools/testing/selftests/riscv/hwprobe/.gitignore b/tools/testing/selftests/riscv/hwprobe/.gitignore index 8113dc3bdd03a..6e384e80ea1a8 100644 --- a/tools/testing/selftests/riscv/hwprobe/.gitignore +++ b/tools/testing/selftests/riscv/hwprobe/.gitignore @@ -1 +1,3 @@ hwprobe +cbo +which-cpus diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c index c537d52fafc58..a40541bb7c7de 100644 --- a/tools/testing/selftests/riscv/hwprobe/cbo.c +++ b/tools/testing/selftests/riscv/hwprobe/cbo.c @@ -19,7 +19,7 @@ #include "hwprobe.h" #include "../../kselftest.h" -#define MK_CBO(fn) cpu_to_le32((fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15) +#define MK_CBO(fn) le32_bswap((uint32_t)(fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15) static char mem[4096] __aligned(4096) = { [0 ... 4095] = 0xa5 }; diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.h b/tools/testing/selftests/riscv/hwprobe/hwprobe.h index e3fccb390c4dc..f3de970c32227 100644 --- a/tools/testing/selftests/riscv/hwprobe/hwprobe.h +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h @@ -4,6 +4,16 @@ #include #include +#if __BYTE_ORDER == __BIG_ENDIAN +# define le32_bswap(_x) \ + ((((_x) & 0x000000ffU) << 24) | \ + (((_x) & 0x0000ff00U) << 8) | \ + (((_x) & 0x00ff0000U) >> 8) | \ + (((_x) & 0xff000000U) >> 24)) +#else +# define le32_bswap(_x) (_x) +#endif + /* * Rather than relying on having a new enough libc to define this, just do it * ourselves. This way we don't need to be coupled to a new-enough libc to diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 38f6514699682..cacf6507f6905 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -784,7 +784,7 @@ void *kill_thread(void *data) bool die = (bool)data; if (die) { - prctl(PR_GET_SECCOMP, 0, 0, 0, 0); + syscall(__NR_getpid); return (void *)SIBLING_EXIT_FAILURE; } @@ -803,11 +803,11 @@ void kill_thread_or_group(struct __test_metadata *_metadata, { pthread_t thread; void *status; - /* Kill only when calling __NR_prctl. */ + /* Kill only when calling __NR_getpid. */ struct sock_filter filter_thread[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_THREAD), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; @@ -819,7 +819,7 @@ void kill_thread_or_group(struct __test_metadata *_metadata, struct sock_filter filter_process[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1), BPF_STMT(BPF_RET|BPF_K, kill), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; @@ -3709,7 +3709,12 @@ TEST(user_notification_sibling_pid_ns) ASSERT_GE(pid, 0); if (pid == 0) { - ASSERT_EQ(unshare(CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWPID), 0) { + if (errno == EPERM) + SKIP(return, "CLONE_NEWPID requires CAP_SYS_ADMIN"); + else if (errno == EINVAL) + SKIP(return, "CLONE_NEWPID is invalid (missing CONFIG_PID_NS?)"); + } pid2 = fork(); ASSERT_GE(pid2, 0); @@ -3727,6 +3732,8 @@ TEST(user_notification_sibling_pid_ns) ASSERT_EQ(unshare(CLONE_NEWPID), 0) { if (errno == EPERM) SKIP(return, "CLONE_NEWPID requires CAP_SYS_ADMIN"); + else if (errno == EINVAL) + SKIP(return, "CLONE_NEWPID is invalid (missing CONFIG_PID_NS?)"); } ASSERT_EQ(errno, 0); @@ -4037,6 +4044,16 @@ TEST(user_notification_filter_empty_threaded) EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); } + +int get_next_fd(int prev_fd) +{ + for (int i = prev_fd + 1; i < FD_SETSIZE; ++i) { + if (fcntl(i, F_GETFD) == -1) + return i; + } + _exit(EXIT_FAILURE); +} + TEST(user_notification_addfd) { pid_t pid; @@ -4053,7 +4070,7 @@ TEST(user_notification_addfd) /* There may be arbitrary already-open fds at test start. */ memfd = memfd_create("test", 0); ASSERT_GE(memfd, 0); - nextfd = memfd + 1; + nextfd = get_next_fd(memfd); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret) { @@ -4064,7 +4081,8 @@ TEST(user_notification_addfd) /* Check that the basic notification machinery works */ listener = user_notif_syscall(__NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER); - ASSERT_EQ(listener, nextfd++); + ASSERT_EQ(listener, nextfd); + nextfd = get_next_fd(nextfd); pid = fork(); ASSERT_GE(pid, 0); @@ -4119,14 +4137,16 @@ TEST(user_notification_addfd) /* Verify we can set an arbitrary remote fd */ fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); - EXPECT_EQ(fd, nextfd++); + EXPECT_EQ(fd, nextfd); + nextfd = get_next_fd(nextfd); EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); /* Verify we can set an arbitrary remote fd with large size */ memset(&big, 0x0, sizeof(big)); big.addfd = addfd; fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big); - EXPECT_EQ(fd, nextfd++); + EXPECT_EQ(fd, nextfd); + nextfd = get_next_fd(nextfd); /* Verify we can set a specific remote fd */ addfd.newfd = 42; @@ -4164,7 +4184,8 @@ TEST(user_notification_addfd) * Child has earlier "low" fds and now 42, so we expect the next * lowest available fd to be assigned here. */ - EXPECT_EQ(fd, nextfd++); + EXPECT_EQ(fd, nextfd); + nextfd = get_next_fd(nextfd); ASSERT_EQ(filecmp(getpid(), pid, memfd, fd), 0); /* diff --git a/tools/testing/selftests/seccomp/settings b/tools/testing/selftests/seccomp/settings index 6091b45d226ba..694d70710ff08 100644 --- a/tools/testing/selftests/seccomp/settings +++ b/tools/testing/selftests/seccomp/settings @@ -1 +1 @@ -timeout=120 +timeout=300 diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index b5d592d4099e8..d975a67673299 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -158,6 +158,20 @@ static void handle_sigsys(int sig, siginfo_t *info, void *ucontext) /* In preparation for sigreturn. */ SYSCALL_DISPATCH_OFF(glob_sel); + + /* + * The tests for argument handling assume that `syscall(x) == x`. This + * is a NOP on x86 because the syscall number is passed in %rax, which + * happens to also be the function ABI return register. Other + * architectures may need to swizzle the arguments around. + */ +#if defined(__riscv) +/* REG_A7 is not defined in libc headers */ +# define REG_A7 (REG_A0 + 7) + + ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A0] = + ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A7]; +#endif } TEST(dispatch_and_return) diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index 2d603ef2e375c..74dba8c671889 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -132,6 +132,50 @@ "echo \"1\" > /sys/bus/netdevsim/del_device" ] }, + { + "id": "6f62", + "name": "Add taprio Qdisc with too short interval", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device" + ], + "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 300 sched-entry S 02 1700 clockid CLOCK_TAI", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, + { + "id": "831f", + "name": "Add taprio Qdisc with too short cycle-time", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device" + ], + "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 200000 sched-entry S 02 200000 cycle-time 100 clockid CLOCK_TAI", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, { "id": "3e1e", "name": "Add taprio Qdisc with an invalid cycle-time", diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index d49dd3ffd0d96..c001dd79179d5 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -66,7 +66,7 @@ static int check_diff(struct timeval start, struct timeval end) diff = end.tv_usec - start.tv_usec; diff += (end.tv_sec - start.tv_sec) * USECS_PER_SEC; - if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { + if (llabs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { printf("Diff too high: %lld..", diff); return -1; } @@ -184,80 +184,71 @@ static int check_timer_create(int which) return 0; } -int remain; -__thread int got_signal; +static pthread_t ctd_thread; +static volatile int ctd_count, ctd_failed; -static void *distribution_thread(void *arg) +static void ctd_sighandler(int sig) { - while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); - return NULL; + if (pthread_self() != ctd_thread) + ctd_failed = 1; + ctd_count--; } -static void distribution_handler(int nr) +static void *ctd_thread_func(void *arg) { - if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED)) - __atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED); -} - -/* - * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID - * timer signals. This primarily tests that the kernel does not favour any one. - */ -static int check_timer_distribution(void) -{ - int err, i; - timer_t id; - const int nthreads = 10; - pthread_t threads[nthreads]; struct itimerspec val = { .it_value.tv_sec = 0, .it_value.tv_nsec = 1000 * 1000, .it_interval.tv_sec = 0, .it_interval.tv_nsec = 1000 * 1000, }; + timer_t id; - remain = nthreads + 1; /* worker threads + this thread */ - signal(SIGALRM, distribution_handler); - err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); - if (err < 0) { - ksft_perror("Can't create timer"); - return -1; - } - err = timer_settime(id, 0, &val, NULL); - if (err < 0) { - ksft_perror("Can't set timer"); - return -1; - } + /* 1/10 seconds to ensure the leader sleeps */ + usleep(10000); - for (i = 0; i < nthreads; i++) { - err = pthread_create(&threads[i], NULL, distribution_thread, - NULL); - if (err) { - ksft_print_msg("Can't create thread: %s (%d)\n", - strerror(errno), errno); - return -1; - } - } + ctd_count = 100; + if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id)) + return "Can't create timer\n"; + if (timer_settime(id, 0, &val, NULL)) + return "Can't set timer\n"; - /* Wait for all threads to receive the signal. */ - while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); + while (ctd_count > 0 && !ctd_failed) + ; - for (i = 0; i < nthreads; i++) { - err = pthread_join(threads[i], NULL); - if (err) { - ksft_print_msg("Can't join thread: %s (%d)\n", - strerror(errno), errno); - return -1; - } - } + if (timer_delete(id)) + return "Can't delete timer\n"; - if (timer_delete(id)) { - ksft_perror("Can't delete timer"); - return -1; - } + return NULL; +} + +/* + * Test that only the running thread receives the timer signal. + */ +static int check_timer_distribution(void) +{ + const char *errmsg; - ksft_test_result_pass("check_timer_distribution\n"); + signal(SIGALRM, ctd_sighandler); + + errmsg = "Can't create thread\n"; + if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL)) + goto err; + + errmsg = "Can't join thread\n"; + if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg) + goto err; + + if (!ctd_failed) + ksft_test_result_pass("check signal distribution\n"); + else if (ksft_min_kernel_version(6, 3)) + ksft_test_result_fail("check signal distribution\n"); + else + ksft_test_result_skip("check signal distribution (old kernel)\n"); return 0; +err: + ksft_print_msg("%s", errmsg); + return -1; } int main(int argc, char **argv) diff --git a/tools/testing/selftests/timers/rtcpie.c b/tools/testing/selftests/timers/rtcpie.c index 4ef2184f15588..9e52dd5c3dcc4 100644 --- a/tools/testing/selftests/timers/rtcpie.c +++ b/tools/testing/selftests/timers/rtcpie.c @@ -111,11 +111,11 @@ int main(int argc, char **argv) timersub(&end, &start, &diff); if (diff.tv_sec > 0 || diff.tv_usec > ((1000000L / tmp) * 1.10)) { - fprintf(stderr, "\nPIE delta error: %ld.%06ld should be close to 0.%06ld\n", + fprintf(stderr, "\nUbuntu Testing Force Pass LP #1814234: PIE delta error: %ld.%06ld should be close to 0.%06ld\n", diff.tv_sec, diff.tv_usec, (1000000L / tmp)); fflush(stdout); - exit(-1); + break; // LP: #1814234 } fprintf(stderr, " %d",i); diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 48b9a803235a8..d13ebde203221 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -21,9 +21,6 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ - - - #include #include #include @@ -62,45 +59,47 @@ int clear_time_state(void) #define NUM_FREQ_OUTOFRANGE 4 #define NUM_FREQ_INVALID 2 +#define SHIFTED_PPM (1 << 16) + long valid_freq[NUM_FREQ_VALID] = { - -499<<16, - -450<<16, - -400<<16, - -350<<16, - -300<<16, - -250<<16, - -200<<16, - -150<<16, - -100<<16, - -75<<16, - -50<<16, - -25<<16, - -10<<16, - -5<<16, - -1<<16, + -499 * SHIFTED_PPM, + -450 * SHIFTED_PPM, + -400 * SHIFTED_PPM, + -350 * SHIFTED_PPM, + -300 * SHIFTED_PPM, + -250 * SHIFTED_PPM, + -200 * SHIFTED_PPM, + -150 * SHIFTED_PPM, + -100 * SHIFTED_PPM, + -75 * SHIFTED_PPM, + -50 * SHIFTED_PPM, + -25 * SHIFTED_PPM, + -10 * SHIFTED_PPM, + -5 * SHIFTED_PPM, + -1 * SHIFTED_PPM, -1000, - 1<<16, - 5<<16, - 10<<16, - 25<<16, - 50<<16, - 75<<16, - 100<<16, - 150<<16, - 200<<16, - 250<<16, - 300<<16, - 350<<16, - 400<<16, - 450<<16, - 499<<16, + 1 * SHIFTED_PPM, + 5 * SHIFTED_PPM, + 10 * SHIFTED_PPM, + 25 * SHIFTED_PPM, + 50 * SHIFTED_PPM, + 75 * SHIFTED_PPM, + 100 * SHIFTED_PPM, + 150 * SHIFTED_PPM, + 200 * SHIFTED_PPM, + 250 * SHIFTED_PPM, + 300 * SHIFTED_PPM, + 350 * SHIFTED_PPM, + 400 * SHIFTED_PPM, + 450 * SHIFTED_PPM, + 499 * SHIFTED_PPM, }; long outofrange_freq[NUM_FREQ_OUTOFRANGE] = { - -1000<<16, - -550<<16, - 550<<16, - 1000<<16, + -1000 * SHIFTED_PPM, + -550 * SHIFTED_PPM, + 550 * SHIFTED_PPM, + 1000 * SHIFTED_PPM, }; #define LONG_MAX (~0UL>>1) diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config index 2fc36efb166dc..a7f8e8a956259 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config @@ -3,6 +3,7 @@ CONFIG_ARCH_RV32I=y CONFIG_MMU=y CONFIG_FPU=y CONFIG_SOC_VIRT=y +CONFIG_RISCV_ISA_FALLBACK=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config index dc266f3b19155..daeb3e5e09658 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config @@ -2,6 +2,7 @@ CONFIG_ARCH_RV64I=y CONFIG_MMU=y CONFIG_FPU=y CONFIG_SOC_VIRT=y +CONFIG_RISCV_ISA_FALLBACK=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y diff --git a/tools/tracing/latency/latency-collector.c b/tools/tracing/latency/latency-collector.c index 0fd9c747d396d..cf263fe9deaf4 100644 --- a/tools/tracing/latency/latency-collector.c +++ b/tools/tracing/latency/latency-collector.c @@ -935,12 +935,12 @@ static void show_available(void) } if (!tracers) { - warnx(no_tracer_msg); + warnx("%s", no_tracer_msg); return; } if (!found) { - warnx(no_latency_tr_msg); + warnx("%s", no_latency_tr_msg); tracefs_list_free(tracers); return; } @@ -983,7 +983,7 @@ static const char *find_default_tracer(void) for (i = 0; relevant_tracers[i]; i++) { valid = tracer_valid(relevant_tracers[i], ¬racer); if (notracer) - errx(EXIT_FAILURE, no_tracer_msg); + errx(EXIT_FAILURE, "%s", no_tracer_msg); if (valid) return relevant_tracers[i]; } @@ -1878,7 +1878,7 @@ static void scan_arguments(int argc, char *argv[]) } valid = tracer_valid(current_tracer, ¬racer); if (notracer) - errx(EXIT_FAILURE, no_tracer_msg); + errx(EXIT_FAILURE, "%s", no_tracer_msg); if (!valid) errx(EXIT_FAILURE, "The tracer %s is not supported by your kernel!\n", current_tracer); diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index afd18c678ff5a..f4916d402c03c 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -111,6 +111,9 @@ warnings: $(WARNINGS) $(ERROR_OUT) endif +%.o: %.c + $(CC) $(CFLAGS) -c -o $@ $< + rtla: $(OBJ) $(CC) -o rtla $(LDFLAGS) $(OBJ) $(LIBS) diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c index 7093fd5333beb..7bd80ee2a5b48 100644 --- a/tools/tracing/rtla/src/timerlat_aa.c +++ b/tools/tracing/rtla/src/timerlat_aa.c @@ -16,6 +16,9 @@ enum timelat_state { TIMERLAT_WAITING_THREAD, }; +/* Used to fill spaces in the output */ +static const char *spaces = " "; + #define MAX_COMM 24 /* @@ -274,14 +277,17 @@ static int timerlat_aa_nmi_handler(struct trace_seq *s, struct tep_record *recor taa_data->prev_irq_timstamp = start; trace_seq_reset(taa_data->prev_irqs_seq); - trace_seq_printf(taa_data->prev_irqs_seq, "\t%24s \t\t\t%9.2f us\n", - "nmi", ns_to_usf(duration)); + trace_seq_printf(taa_data->prev_irqs_seq, " %24s %.*s %9.2f us\n", + "nmi", + 24, spaces, + ns_to_usf(duration)); return 0; } taa_data->thread_nmi_sum += duration; - trace_seq_printf(taa_data->nmi_seq, " %24s \t\t\t%9.2f us\n", - "nmi", ns_to_usf(duration)); + trace_seq_printf(taa_data->nmi_seq, " %24s %.*s %9.2f us\n", + "nmi", + 24, spaces, ns_to_usf(duration)); return 0; } @@ -323,8 +329,10 @@ static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *recor taa_data->prev_irq_timstamp = start; trace_seq_reset(taa_data->prev_irqs_seq); - trace_seq_printf(taa_data->prev_irqs_seq, "\t%24s:%-3llu \t\t%9.2f us\n", - desc, vector, ns_to_usf(duration)); + trace_seq_printf(taa_data->prev_irqs_seq, " %24s:%-3llu %.*s %9.2f us\n", + desc, vector, + 15, spaces, + ns_to_usf(duration)); return 0; } @@ -372,8 +380,10 @@ static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *recor * IRQ interference. */ taa_data->thread_irq_sum += duration; - trace_seq_printf(taa_data->irqs_seq, " %24s:%-3llu \t %9.2f us\n", - desc, vector, ns_to_usf(duration)); + trace_seq_printf(taa_data->irqs_seq, " %24s:%-3llu %.*s %9.2f us\n", + desc, vector, + 24, spaces, + ns_to_usf(duration)); return 0; } @@ -408,8 +418,10 @@ static int timerlat_aa_softirq_handler(struct trace_seq *s, struct tep_record *r taa_data->thread_softirq_sum += duration; - trace_seq_printf(taa_data->softirqs_seq, "\t%24s:%-3llu \t %9.2f us\n", - softirq_name[vector], vector, ns_to_usf(duration)); + trace_seq_printf(taa_data->softirqs_seq, " %24s:%-3llu %.*s %9.2f us\n", + softirq_name[vector], vector, + 24, spaces, + ns_to_usf(duration)); return 0; } @@ -452,8 +464,10 @@ static int timerlat_aa_thread_handler(struct trace_seq *s, struct tep_record *re } else { taa_data->thread_thread_sum += duration; - trace_seq_printf(taa_data->threads_seq, "\t%24s:%-3llu \t\t%9.2f us\n", - comm, pid, ns_to_usf(duration)); + trace_seq_printf(taa_data->threads_seq, " %24s:%-12llu %.*s %9.2f us\n", + comm, pid, + 15, spaces, + ns_to_usf(duration)); } return 0; @@ -482,7 +496,8 @@ static int timerlat_aa_stack_handler(struct trace_seq *s, struct tep_record *rec function = tep_find_function(taa_ctx->tool->trace.tep, caller[i]); if (!function) break; - trace_seq_printf(taa_data->stack_seq, "\t\t-> %s\n", function); + trace_seq_printf(taa_data->stack_seq, " %.*s -> %s\n", + 14, spaces, function); } } return 0; @@ -568,23 +583,24 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, exp_irq_ts = taa_data->timer_irq_start_time - taa_data->timer_irq_start_delay; if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) { if (taa_data->prev_irq_timstamp < taa_data->timer_irq_start_time) - printf(" Previous IRQ interference: \t\t up to %9.2f us\n", - ns_to_usf(taa_data->prev_irq_duration)); + printf(" Previous IRQ interference: %.*s up to %9.2f us\n", + 16, spaces, + ns_to_usf(taa_data->prev_irq_duration)); } /* * The delay that the IRQ suffered before starting. */ - printf(" IRQ handler delay: %16s %9.2f us (%.2f %%)\n", - (ns_to_usf(taa_data->timer_exit_from_idle) > 10) ? "(exit from idle)" : "", - ns_to_usf(taa_data->timer_irq_start_delay), - ns_to_per(total, taa_data->timer_irq_start_delay)); + printf(" IRQ handler delay: %.*s %16s %9.2f us (%.2f %%)\n", 16, spaces, + (ns_to_usf(taa_data->timer_exit_from_idle) > 10) ? "(exit from idle)" : "", + ns_to_usf(taa_data->timer_irq_start_delay), + ns_to_per(total, taa_data->timer_irq_start_delay)); /* * Timerlat IRQ. */ - printf(" IRQ latency: \t\t\t\t %9.2f us\n", - ns_to_usf(taa_data->tlat_irq_latency)); + printf(" IRQ latency: %.*s %9.2f us\n", 40, spaces, + ns_to_usf(taa_data->tlat_irq_latency)); if (irq) { /* @@ -595,15 +611,16 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * so it will be displayed, it is the key. */ printf(" Blocking thread:\n"); - printf(" %24s:%-9llu\n", - taa_data->run_thread_comm, taa_data->run_thread_pid); + printf(" %.*s %24s:%-9llu\n", 6, spaces, taa_data->run_thread_comm, + taa_data->run_thread_pid); } else { /* * The duration of the IRQ handler that handled the timerlat IRQ. */ - printf(" Timerlat IRQ duration: \t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->timer_irq_duration), - ns_to_per(total, taa_data->timer_irq_duration)); + printf(" Timerlat IRQ duration: %.*s %9.2f us (%.2f %%)\n", + 30, spaces, + ns_to_usf(taa_data->timer_irq_duration), + ns_to_per(total, taa_data->timer_irq_duration)); /* * The amount of time that the current thread postponed the scheduler. @@ -611,13 +628,13 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * Recalling that it is net from NMI/IRQ/Softirq interference, so there * is no need to compute values here. */ - printf(" Blocking thread: \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_blocking_duration), - ns_to_per(total, taa_data->thread_blocking_duration)); + printf(" Blocking thread: %.*s %9.2f us (%.2f %%)\n", 36, spaces, + ns_to_usf(taa_data->thread_blocking_duration), + ns_to_per(total, taa_data->thread_blocking_duration)); - printf(" %24s:%-9llu %9.2f us\n", - taa_data->run_thread_comm, taa_data->run_thread_pid, - ns_to_usf(taa_data->thread_blocking_duration)); + printf(" %.*s %24s:%-9llu %.*s %9.2f us\n", 6, spaces, + taa_data->run_thread_comm, taa_data->run_thread_pid, + 12, spaces, ns_to_usf(taa_data->thread_blocking_duration)); } /* @@ -629,9 +646,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * NMIs can happen during the IRQ, so they are always possible. */ if (taa_data->thread_nmi_sum) - printf(" NMI interference \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_nmi_sum), - ns_to_per(total, taa_data->thread_nmi_sum)); + printf(" NMI interference %.*s %9.2f us (%.2f %%)\n", 36, spaces, + ns_to_usf(taa_data->thread_nmi_sum), + ns_to_per(total, taa_data->thread_nmi_sum)); /* * If it is an IRQ latency, the other factors can be skipped. @@ -643,9 +660,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * Prints the interference caused by IRQs to the thread latency. */ if (taa_data->thread_irq_sum) { - printf(" IRQ interference \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_irq_sum), - ns_to_per(total, taa_data->thread_irq_sum)); + printf(" IRQ interference %.*s %9.2f us (%.2f %%)\n", 36, spaces, + ns_to_usf(taa_data->thread_irq_sum), + ns_to_per(total, taa_data->thread_irq_sum)); trace_seq_do_printf(taa_data->irqs_seq); } @@ -654,9 +671,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * Prints the interference caused by Softirqs to the thread latency. */ if (taa_data->thread_softirq_sum) { - printf(" Softirq interference \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_softirq_sum), - ns_to_per(total, taa_data->thread_softirq_sum)); + printf(" Softirq interference %.*s %9.2f us (%.2f %%)\n", 32, spaces, + ns_to_usf(taa_data->thread_softirq_sum), + ns_to_per(total, taa_data->thread_softirq_sum)); trace_seq_do_printf(taa_data->softirqs_seq); } @@ -670,9 +687,9 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, * timer handling latency. */ if (taa_data->thread_thread_sum) { - printf(" Thread interference \t\t\t %9.2f us (%.2f %%)\n", - ns_to_usf(taa_data->thread_thread_sum), - ns_to_per(total, taa_data->thread_thread_sum)); + printf(" Thread interference %.*s %9.2f us (%.2f %%)\n", 33, spaces, + ns_to_usf(taa_data->thread_thread_sum), + ns_to_per(total, taa_data->thread_thread_sum)); trace_seq_do_printf(taa_data->threads_seq); } @@ -682,8 +699,8 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, */ print_total: printf("------------------------------------------------------------------------\n"); - printf(" %s latency: \t\t\t %9.2f us (100%%)\n", irq ? "IRQ" : "Thread", - ns_to_usf(total)); + printf(" %s latency: %.*s %9.2f us (100%%)\n", irq ? " IRQ" : "Thread", + 37, spaces, ns_to_usf(total)); } static int timerlat_auto_analysis_collect_trace(struct timerlat_aa_context *taa_ctx) diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index dbf154082f958..1c8ecd4ebcbd3 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -323,17 +323,29 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_irq); + if (!params->no_irq) { + if (data->hist[cpu].irq_count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].min_irq); + else + trace_seq_printf(trace->seq, " - "); + } - if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_thread); + if (!params->no_thread) { + if (data->hist[cpu].thread_count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].min_thread); + else + trace_seq_printf(trace->seq, " - "); + } - if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_user); + if (params->user_hist) { + if (data->hist[cpu].user_count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].min_user); + else + trace_seq_printf(trace->seq, " - "); + } } trace_seq_printf(trace->seq, "\n"); @@ -383,17 +395,29 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_irq); + if (!params->no_irq) { + if (data->hist[cpu].irq_count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].max_irq); + else + trace_seq_printf(trace->seq, " - "); + } - if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_thread); + if (!params->no_thread) { + if (data->hist[cpu].thread_count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].max_thread); + else + trace_seq_printf(trace->seq, " - "); + } - if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_user); + if (params->user_hist) { + if (data->hist[cpu].user_count) + trace_seq_printf(trace->seq, "%9llu ", + data->hist[cpu].max_user); + else + trace_seq_printf(trace->seq, " - "); + } } trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index 3e9af2c386888..38d6965183d9f 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -211,6 +211,8 @@ static void timerlat_top_header(struct osnoise_tool *top) trace_seq_printf(s, "\n"); } +static const char *no_value = " -"; + /* * timerlat_top_print - prints the output of a given CPU */ @@ -238,10 +240,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu) trace_seq_printf(s, "%3d #%-9d |", cpu, cpu_data->irq_count); if (!cpu_data->irq_count) { - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - |"); + trace_seq_printf(s, "%s %s %s %s |", no_value, no_value, no_value, no_value); } else { trace_seq_printf(s, "%9llu ", cpu_data->cur_irq / params->output_divisor); trace_seq_printf(s, "%9llu ", cpu_data->min_irq / params->output_divisor); @@ -250,10 +249,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu) } if (!cpu_data->thread_count) { - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " -\n"); + trace_seq_printf(s, "%s %s %s %s", no_value, no_value, no_value, no_value); } else { trace_seq_printf(s, "%9llu ", cpu_data->cur_thread / divisor); trace_seq_printf(s, "%9llu ", cpu_data->min_thread / divisor); @@ -270,10 +266,7 @@ static void timerlat_top_print(struct osnoise_tool *top, int cpu) trace_seq_printf(s, " |"); if (!cpu_data->user_count) { - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " - "); - trace_seq_printf(s, " -\n"); + trace_seq_printf(s, "%s %s %s %s\n", no_value, no_value, no_value, no_value); } else { trace_seq_printf(s, "%9llu ", cpu_data->cur_user / divisor); trace_seq_printf(s, "%9llu ", cpu_data->min_user / divisor); diff --git a/tools/usb/usbip/configure.ac b/tools/usb/usbip/configure.ac index 8debf934f8b79..ef74eb7e56684 100644 --- a/tools/usb/usbip/configure.ac +++ b/tools/usb/usbip/configure.ac @@ -18,7 +18,7 @@ LT_INIT # Silent build for automake >= 1.11 m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])]) -AC_SUBST([EXTRA_CFLAGS], ["-Wall -Werror -Wextra -std=gnu99"]) +AC_SUBST([EXTRA_CFLAGS], ["-Wall -Werror -Wextra -Wno-address-of-packed-member -std=gnu99"]) # Checks for programs. AC_PROG_CC diff --git a/ubuntu/Kconfig b/ubuntu/Kconfig new file mode 100644 index 0000000000000..6be41b4644e10 --- /dev/null +++ b/ubuntu/Kconfig @@ -0,0 +1,24 @@ +menu "Ubuntu Supplied Third-Party Device Drivers" + + +config UBUNTU_ODM_DRIVERS + bool "Ubuntu ODM supplied drivers" + help + Turn on support for Ubuntu ODM supplied drivers + +# +# NOTE: to allow drivers to be added and removed without causing merge +# collisions you should add new entries in the middle of the six lines +# of ## at the bottom of the list. Always add three lines of ## above +# your new entry and maintain the six lines below. +# + +## +## +## +source "ubuntu/ubuntu-host/Kconfig" +## +## +## + +endmenu diff --git a/ubuntu/Makefile b/ubuntu/Makefile new file mode 100644 index 0000000000000..4a76de2f59eb9 --- /dev/null +++ b/ubuntu/Makefile @@ -0,0 +1,18 @@ +# +# Makefile for the Linux kernel ubuntu supplied third-party device drivers. +# + +# +# NOTE: to allow drivers to be added and removed without causing merge +# collisions you should add new entries in the middle of the six lines +# of ## at the bottom of the list. Always add three lines of ## above +# your new entry and maintain the six lines below. +# + +## +## +## +obj-$(CONFIG_UBUNTU_HOST) += ubuntu-host/ +## +## +## diff --git a/ubuntu/hio/Makefile b/ubuntu/hio/Makefile new file mode 100644 index 0000000000000..b03e6273a127d --- /dev/null +++ b/ubuntu/hio/Makefile @@ -0,0 +1,69 @@ +ifneq ($(KERNELRELEASE),) +# hio-y := hio_main.o +# obj-$(CONFIG_HIO_DRIVER) += hio.o + obj-m += hio.o +else + +KVER= +ifeq ($(KVER),) + KVER=$(shell uname -r) +endif + +PDIR= +ifeq ($(PDIR),) + PDIR=extra +endif + +PREFIX= + +MODDIR=/lib/modules/$(KVER)/$(PDIR)/hio/ +MOD=hio.ko + +ifeq ($(KVER),2.6.32-300.3.1.el6uek.x86_64) + FLAGS += -DSSD_QUEUE_PBIO +endif +ifeq ($(KVER),2.6.32-220.el6.x86_64) + FLAGS += -DSSD_QUEUE_PBIO +endif +ifeq ($(KVER),2.6.32-358.el6.x86_64) + FLAGS += -DSSD_QUEUE_PBIO +endif +ifeq ($(KVER),2.6.32-358.23.2.el6.x86_64) + FLAGS += -DSSD_QUEUE_PBIO +endif +ifeq ($(KVER),3.0.58-0.6.6-xen) + FLAGS += -DSSD_QUEUE_PBIO +endif +ifeq ($(KVER),3.2.0-4-amd64) + FLAGS += -DSSD_BIOVEC_PHYS_MERGEABLE_FIXED +endif +ifeq ($(KVER),2.6.39-400.209.1.el5uek) #Oracle Linux Server release 5.10 + FLAGS += -DSSD_BIOVEC_PHYS_MERGEABLE_FIXED +endif +ifeq ($(KVER),2.6.39-400.215.10.el5uek) #Oracle Linux Server release 5.11 + FLAGS += -DSSD_BIOVEC_PHYS_MERGEABLE_FIXED +endif +ifeq ($(KVER),2.6.39-200.24.1.el6uek.x86_64) #Oracle Linux Server release 6.3 + FLAGS += -DSSD_BIOVEC_PHYS_MERGEABLE_FIXED +endif +ifeq ($(KVER),2.6.39-400.17.1.el6uek.x86_64) #Oracle Linux Server release 6.4 + FLAGS += -DSSD_BIOVEC_PHYS_MERGEABLE_FIXED +endif + + +KERNELDIR ?= /lib/modules/$(KVER)/build +PWD := $(shell pwd) + +default: + $(MAKE) -C $(KERNELDIR) M=$(PWD) EXTRA_CFLAGS="$(FLAGS)" modules +clean: + rm -rf *.o *~ core .depend .*.cmd *.ko *.mod.c .tmp_versions Module.* + +install: default + mkdir -p $(PREFIX)/$(MODDIR) + install -m 444 $(MOD) $(PREFIX)/$(MODDIR) + @if [ "$(PREFIX)" = "" ]; then /sbin/depmod -a ;\ + else echo " *** Run 'depmod -a' to update the module database.";\ + fi +endif + diff --git a/ubuntu/hio/hio.c b/ubuntu/hio/hio.c new file mode 100644 index 0000000000000..4ea98d8647f34 --- /dev/null +++ b/ubuntu/hio/hio.c @@ -0,0 +1,12527 @@ +/* +* Huawei SSD device driver +* Copyright (c) 2016, Huawei Technologies Co., Ltd. +* +* This program is free software; you can redistribute it and/or modify it +* under the terms and conditions of the GNU General Public License, +* version 2, as published by the Free Software Foundation. +* +* This program is distributed in the hope it will be useful, but WITHOUT +* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +* more details. +*/ + +#ifndef LINUX_VERSION_CODE +#include +#endif +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,16)) +#include +#endif +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* HDIO_GETGEO */ +#include +#include +#include +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,2,0)) +#include +#endif +#include +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(4,2,0)) +#include +#include +#else +#include +#endif +#include +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,17)) +#include +#endif + +/* driver */ +#define MODULE_NAME "hio" +#define DRIVER_VERSION "2.1.0.23" +#define DRIVER_VERSION_LEN 16 + +#define SSD_FW_MIN 0x1 + +#define SSD_DEV_NAME MODULE_NAME +#define SSD_DEV_NAME_LEN 16 +#define SSD_CDEV_NAME "c"SSD_DEV_NAME +#define SSD_SDEV_NAME "s"SSD_DEV_NAME + + +#define SSD_CMAJOR 0 +#define SSD_MAJOR 0 +#define SSD_MAJOR_SL 0 +#define SSD_MINORS 16 + +#define SSD_MAX_DEV 702 +#define SSD_ALPHABET_NUM 26 + +#define hio_info(f, arg...) printk(KERN_INFO MODULE_NAME"info: " f , ## arg) +#define hio_note(f, arg...) printk(KERN_NOTICE MODULE_NAME"note: " f , ## arg) +#define hio_warn(f, arg...) printk(KERN_WARNING MODULE_NAME"warn: " f , ## arg) +#define hio_err(f, arg...) printk(KERN_ERR MODULE_NAME"err: " f , ## arg) + +/* slave port */ +#define SSD_SLAVE_PORT_DEVID 0x000a + +/* int mode */ + +/* 2.6.9 msi affinity bug, should turn msi & msi-x off */ +//#define SSD_MSI +#define SSD_ESCAPE_IRQ + +//#define SSD_MSIX +#ifndef MODULE +#define SSD_MSIX +#endif +#define SSD_MSIX_VEC 8 +#ifdef SSD_MSIX +#undef SSD_MSI +//#undef SSD_ESCAPE_IRQ +#define SSD_MSIX_AFFINITY_FORCE +#endif + +#define SSD_TRIM + +/* Over temperature protect */ +#define SSD_OT_PROTECT + +#ifdef SSD_QUEUE_PBIO +#define BIO_SSD_PBIO 20 +#endif + +/* debug */ +//#define SSD_DEBUG_ERR + +/* cmd timer */ +#define SSD_CMD_TIMEOUT (60*HZ) + +/* i2c & smbus */ +#define SSD_SPI_TIMEOUT (5*HZ) +#define SSD_I2C_TIMEOUT (5*HZ) + +#define SSD_I2C_MAX_DATA (127) +#define SSD_SMBUS_BLOCK_MAX (32) +#define SSD_SMBUS_DATA_MAX (SSD_SMBUS_BLOCK_MAX + 2) + +/* wait for init */ +#define SSD_INIT_WAIT (1000) //1s +#define SSD_CONTROLLER_WAIT (20*1000/SSD_INIT_WAIT) //20s +#define SSD_INIT_MAX_WAIT (500*1000/SSD_INIT_WAIT) //500s +#define SSD_INIT_MAX_WAIT_V3_2 (1400*1000/SSD_INIT_WAIT) //1400s +#define SSD_RAM_INIT_MAX_WAIT (10*1000/SSD_INIT_WAIT) //10s +#define SSD_CH_INFO_MAX_WAIT (10*1000/SSD_INIT_WAIT) //10s + +/* blkdev busy wait */ +#define SSD_DEV_BUSY_WAIT 1000 //ms +#define SSD_DEV_BUSY_MAX_WAIT (8*1000/SSD_DEV_BUSY_WAIT) //8s + +/* smbus retry */ +#define SSD_SMBUS_RETRY_INTERVAL (5) //ms +#define SSD_SMBUS_RETRY_MAX (1000/SSD_SMBUS_RETRY_INTERVAL) + +#define SSD_BM_RETRY_MAX 7 + +/* bm routine interval */ +#define SSD_BM_CAP_LEARNING_DELAY (10*60*1000) + +/* routine interval */ +#define SSD_ROUTINE_INTERVAL (10*1000) //10s +#define SSD_HWMON_ROUTINE_TICK (60*1000/SSD_ROUTINE_INTERVAL) +#define SSD_CAPMON_ROUTINE_TICK ((3600*1000/SSD_ROUTINE_INTERVAL)*24*30) +#define SSD_CAPMON2_ROUTINE_TICK (10*60*1000/SSD_ROUTINE_INTERVAL) //fault recover + +/* dma align */ +#define SSD_DMA_ALIGN (16) + +/* some hw defalut */ +#define SSD_LOG_MAX_SZ 4096 + +#define SSD_NAND_OOB_SZ 1024 +#define SSD_NAND_ID_SZ 8 +#define SSD_NAND_ID_BUFF_SZ 1024 +#define SSD_NAND_MAX_CE 2 + +#define SSD_BBT_RESERVED 8 + +#define SSD_ECC_MAX_FLIP (64+1) + +#define SSD_RAM_ALIGN 16 + + +#define SSD_RELOAD_FLAG 0x3333CCCC +#define SSD_RELOAD_FW 0xAA5555AA +#define SSD_RESET_NOINIT 0xAA5555AA +#define SSD_RESET 0x55AAAA55 +#define SSD_RESET_FULL 0x5A +//#define SSD_RESET_WAIT 1000 //1s +//#define SSD_RESET_MAX_WAIT (200*1000/SSD_RESET_WAIT) //200s + + +/* reverion 1 */ +#define SSD_PROTOCOL_V1 0x0 + +#define SSD_ROM_SIZE (16*1024*1024) +#define SSD_ROM_BLK_SIZE (256*1024) +#define SSD_ROM_PAGE_SIZE (256) +#define SSD_ROM_NR_BRIDGE_FW 2 +#define SSD_ROM_NR_CTRL_FW 2 +#define SSD_ROM_BRIDGE_FW_BASE 0 +#define SSD_ROM_BRIDGE_FW_SIZE (2*1024*1024) +#define SSD_ROM_CTRL_FW_BASE (SSD_ROM_NR_BRIDGE_FW*SSD_ROM_BRIDGE_FW_SIZE) +#define SSD_ROM_CTRL_FW_SIZE (5*1024*1024) +#define SSD_ROM_LABEL_BASE (SSD_ROM_CTRL_FW_BASE+SSD_ROM_CTRL_FW_SIZE*SSD_ROM_NR_CTRL_FW) +#define SSD_ROM_VP_BASE (SSD_ROM_LABEL_BASE+SSD_ROM_BLK_SIZE) + +/* reverion 3 */ +#define SSD_PROTOCOL_V3 0x3000000 +#define SSD_PROTOCOL_V3_1_1 0x3010001 +#define SSD_PROTOCOL_V3_1_3 0x3010003 +#define SSD_PROTOCOL_V3_2 0x3020000 +#define SSD_PROTOCOL_V3_2_1 0x3020001 /* <4KB improved */ +#define SSD_PROTOCOL_V3_2_2 0x3020002 /* ot protect */ +#define SSD_PROTOCOL_V3_2_4 0x3020004 + + +#define SSD_PV3_ROM_NR_BM_FW 1 +#define SSD_PV3_ROM_BM_FW_SZ (64*1024*8) + +#define SSD_ROM_LOG_SZ (64*1024*4) + +#define SSD_ROM_NR_SMART_MAX 2 +#define SSD_PV3_ROM_NR_SMART SSD_ROM_NR_SMART_MAX +#define SSD_PV3_ROM_SMART_SZ (64*1024) + +/* reverion 3.2 */ +#define SSD_PV3_2_ROM_LOG_SZ (64*1024*80) /* 5MB */ +#define SSD_PV3_2_ROM_SEC_SZ (256*1024) /* 256KB */ + + +/* register */ +#define SSD_REQ_FIFO_REG 0x0000 +#define SSD_RESP_FIFO_REG 0x0008 //0x0010 +#define SSD_RESP_PTR_REG 0x0010 //0x0018 +#define SSD_INTR_INTERVAL_REG 0x0018 +#define SSD_READY_REG 0x001C +#define SSD_BRIDGE_TEST_REG 0x0020 +#define SSD_STRIPE_SIZE_REG 0x0028 +#define SSD_CTRL_VER_REG 0x0030 //controller +#define SSD_BRIDGE_VER_REG 0x0034 //bridge +#define SSD_PCB_VER_REG 0x0038 +#define SSD_BURN_FLAG_REG 0x0040 +#define SSD_BRIDGE_INFO_REG 0x0044 + +#define SSD_WL_VAL_REG 0x0048 //32-bit + +#define SSD_BB_INFO_REG 0x004C + +#define SSD_ECC_TEST_REG 0x0050 //test only +#define SSD_ERASE_TEST_REG 0x0058 //test only +#define SSD_WRITE_TEST_REG 0x0060 //test only + +#define SSD_RESET_REG 0x0068 +#define SSD_RELOAD_FW_REG 0x0070 + +#define SSD_RESERVED_BLKS_REG 0x0074 +#define SSD_VALID_PAGES_REG 0x0078 +#define SSD_CH_INFO_REG 0x007C + +#define SSD_CTRL_TEST_REG_SZ 0x8 +#define SSD_CTRL_TEST_REG0 0x0080 +#define SSD_CTRL_TEST_REG1 0x0088 +#define SSD_CTRL_TEST_REG2 0x0090 +#define SSD_CTRL_TEST_REG3 0x0098 +#define SSD_CTRL_TEST_REG4 0x00A0 +#define SSD_CTRL_TEST_REG5 0x00A8 +#define SSD_CTRL_TEST_REG6 0x00B0 +#define SSD_CTRL_TEST_REG7 0x00B8 + +#define SSD_FLASH_INFO_REG0 0x00C0 +#define SSD_FLASH_INFO_REG1 0x00C8 +#define SSD_FLASH_INFO_REG2 0x00D0 +#define SSD_FLASH_INFO_REG3 0x00D8 +#define SSD_FLASH_INFO_REG4 0x00E0 +#define SSD_FLASH_INFO_REG5 0x00E8 +#define SSD_FLASH_INFO_REG6 0x00F0 +#define SSD_FLASH_INFO_REG7 0x00F8 + +#define SSD_RESP_INFO_REG 0x01B8 +#define SSD_NAND_BUFF_BASE 0x01BC //for nand write + +#define SSD_CHIP_INFO_REG_SZ 0x10 +#define SSD_CHIP_INFO_REG0 0x0100 //128 bit +#define SSD_CHIP_INFO_REG1 0x0110 +#define SSD_CHIP_INFO_REG2 0x0120 +#define SSD_CHIP_INFO_REG3 0x0130 +#define SSD_CHIP_INFO_REG4 0x0140 +#define SSD_CHIP_INFO_REG5 0x0150 +#define SSD_CHIP_INFO_REG6 0x0160 +#define SSD_CHIP_INFO_REG7 0x0170 + +#define SSD_RAM_INFO_REG 0x01C4 + +#define SSD_BBT_BASE_REG 0x01C8 +#define SSD_ECT_BASE_REG 0x01CC + +#define SSD_CLEAR_INTR_REG 0x01F0 + +#define SSD_INIT_STATE_REG_SZ 0x8 +#define SSD_INIT_STATE_REG0 0x0200 +#define SSD_INIT_STATE_REG1 0x0208 +#define SSD_INIT_STATE_REG2 0x0210 +#define SSD_INIT_STATE_REG3 0x0218 +#define SSD_INIT_STATE_REG4 0x0220 +#define SSD_INIT_STATE_REG5 0x0228 +#define SSD_INIT_STATE_REG6 0x0230 +#define SSD_INIT_STATE_REG7 0x0238 + +#define SSD_ROM_INFO_REG 0x0600 +#define SSD_ROM_BRIDGE_FW_INFO_REG 0x0604 +#define SSD_ROM_CTRL_FW_INFO_REG 0x0608 +#define SSD_ROM_VP_INFO_REG 0x060C + +#define SSD_LOG_INFO_REG 0x0610 +#define SSD_LED_REG 0x0614 +#define SSD_MSG_BASE_REG 0x06F8 + +/*spi reg */ +#define SSD_SPI_REG_CMD 0x0180 +#define SSD_SPI_REG_CMD_HI 0x0184 +#define SSD_SPI_REG_WDATA 0x0188 +#define SSD_SPI_REG_ID 0x0190 +#define SSD_SPI_REG_STATUS 0x0198 +#define SSD_SPI_REG_RDATA 0x01A0 +#define SSD_SPI_REG_READY 0x01A8 + +/* i2c register */ +#define SSD_I2C_CTRL_REG 0x06F0 +#define SSD_I2C_RDATA_REG 0x06F4 + +/* temperature reg */ +#define SSD_BRIGE_TEMP_REG 0x0618 + +#define SSD_CTRL_TEMP_REG0 0x0700 +#define SSD_CTRL_TEMP_REG1 0x0708 +#define SSD_CTRL_TEMP_REG2 0x0710 +#define SSD_CTRL_TEMP_REG3 0x0718 +#define SSD_CTRL_TEMP_REG4 0x0720 +#define SSD_CTRL_TEMP_REG5 0x0728 +#define SSD_CTRL_TEMP_REG6 0x0730 +#define SSD_CTRL_TEMP_REG7 0x0738 + +/* reversion 3 reg */ +#define SSD_PROTOCOL_VER_REG 0x01B4 + +#define SSD_FLUSH_TIMEOUT_REG 0x02A4 +#define SSD_BM_FAULT_REG 0x0660 + +#define SSD_PV3_RAM_STATUS_REG_SZ 0x4 +#define SSD_PV3_RAM_STATUS_REG0 0x0260 +#define SSD_PV3_RAM_STATUS_REG1 0x0264 +#define SSD_PV3_RAM_STATUS_REG2 0x0268 +#define SSD_PV3_RAM_STATUS_REG3 0x026C +#define SSD_PV3_RAM_STATUS_REG4 0x0270 +#define SSD_PV3_RAM_STATUS_REG5 0x0274 +#define SSD_PV3_RAM_STATUS_REG6 0x0278 +#define SSD_PV3_RAM_STATUS_REG7 0x027C + +#define SSD_PV3_CHIP_INFO_REG_SZ 0x40 +#define SSD_PV3_CHIP_INFO_REG0 0x0300 +#define SSD_PV3_CHIP_INFO_REG1 0x0340 +#define SSD_PV3_CHIP_INFO_REG2 0x0380 +#define SSD_PV3_CHIP_INFO_REG3 0x03B0 +#define SSD_PV3_CHIP_INFO_REG4 0x0400 +#define SSD_PV3_CHIP_INFO_REG5 0x0440 +#define SSD_PV3_CHIP_INFO_REG6 0x0480 +#define SSD_PV3_CHIP_INFO_REG7 0x04B0 + +#define SSD_PV3_INIT_STATE_REG_SZ 0x20 +#define SSD_PV3_INIT_STATE_REG0 0x0500 +#define SSD_PV3_INIT_STATE_REG1 0x0520 +#define SSD_PV3_INIT_STATE_REG2 0x0540 +#define SSD_PV3_INIT_STATE_REG3 0x0560 +#define SSD_PV3_INIT_STATE_REG4 0x0580 +#define SSD_PV3_INIT_STATE_REG5 0x05A0 +#define SSD_PV3_INIT_STATE_REG6 0x05C0 +#define SSD_PV3_INIT_STATE_REG7 0x05E0 + +/* reversion 3.1.1 reg */ +#define SSD_FULL_RESET_REG 0x01B0 + +#define SSD_CTRL_REG_ZONE_SZ 0x800 + +#define SSD_BB_THRESHOLD_L1_REG 0x2C0 +#define SSD_BB_THRESHOLD_L2_REG 0x2C4 + +#define SSD_BB_ACC_REG_SZ 0x4 +#define SSD_BB_ACC_REG0 0x21C0 +#define SSD_BB_ACC_REG1 0x29C0 +#define SSD_BB_ACC_REG2 0x31C0 + +#define SSD_EC_THRESHOLD_L1_REG 0x2C8 +#define SSD_EC_THRESHOLD_L2_REG 0x2CC + +#define SSD_EC_ACC_REG_SZ 0x4 +#define SSD_EC_ACC_REG0 0x21E0 +#define SSD_EC_ACC_REG1 0x29E0 +#define SSD_EC_ACC_REG2 0x31E0 + +/* reversion 3.1.2 & 3.1.3 reg */ +#define SSD_HW_STATUS_REG 0x02AC + +#define SSD_PLP_INFO_REG 0x0664 + +/*reversion 3.2 reg*/ +#define SSD_POWER_ON_REG 0x01EC +#define SSD_PCIE_LINKSTATUS_REG 0x01F8 +#define SSD_PL_CAP_LEARN_REG 0x01FC + +#define SSD_FPGA_1V0_REG0 0x2070 +#define SSD_FPGA_1V8_REG0 0x2078 +#define SSD_FPGA_1V0_REG1 0x2870 +#define SSD_FPGA_1V8_REG1 0x2878 + +/*reversion 3.2 reg*/ +#define SSD_READ_OT_REG0 0x2260 +#define SSD_WRITE_OT_REG0 0x2264 +#define SSD_READ_OT_REG1 0x2A60 +#define SSD_WRITE_OT_REG1 0x2A64 + + +/* function */ +#define SSD_FUNC_READ 0x01 +#define SSD_FUNC_WRITE 0x02 +#define SSD_FUNC_NAND_READ_WOOB 0x03 +#define SSD_FUNC_NAND_READ 0x04 +#define SSD_FUNC_NAND_WRITE 0x05 +#define SSD_FUNC_NAND_ERASE 0x06 +#define SSD_FUNC_NAND_READ_ID 0x07 +#define SSD_FUNC_READ_LOG 0x08 +#define SSD_FUNC_TRIM 0x09 +#define SSD_FUNC_RAM_READ 0x10 +#define SSD_FUNC_RAM_WRITE 0x11 +#define SSD_FUNC_FLUSH 0x12 //cache / bbt + +/* spi function */ +#define SSD_SPI_CMD_PROGRAM 0x02 +#define SSD_SPI_CMD_READ 0x03 +#define SSD_SPI_CMD_W_DISABLE 0x04 +#define SSD_SPI_CMD_READ_STATUS 0x05 +#define SSD_SPI_CMD_W_ENABLE 0x06 +#define SSD_SPI_CMD_ERASE 0xd8 +#define SSD_SPI_CMD_CLSR 0x30 +#define SSD_SPI_CMD_READ_ID 0x9f + +/* i2c */ +#define SSD_I2C_CTRL_READ 0x00 +#define SSD_I2C_CTRL_WRITE 0x01 + +/* i2c internal register */ +#define SSD_I2C_CFG_REG 0x00 +#define SSD_I2C_DATA_REG 0x01 +#define SSD_I2C_CMD_REG 0x02 +#define SSD_I2C_STATUS_REG 0x03 +#define SSD_I2C_SADDR_REG 0x04 +#define SSD_I2C_LEN_REG 0x05 +#define SSD_I2C_RLEN_REG 0x06 +#define SSD_I2C_WLEN_REG 0x07 +#define SSD_I2C_RESET_REG 0x08 //write for reset +#define SSD_I2C_PRER_REG 0x09 + + +/* hw mon */ +/* FPGA volt = ADC_value / 4096 * 3v */ +#define SSD_FPGA_1V0_ADC_MIN 1228 // 0.9v +#define SSD_FPGA_1V0_ADC_MAX 1502 // 1.1v +#define SSD_FPGA_1V8_ADC_MIN 2211 // 1.62v +#define SSD_FPGA_1V8_ADC_MAX 2703 // 1.98 + +/* ADC value */ +#define SSD_FPGA_VOLT_MAX(val) (((val) & 0xffff) >> 4) +#define SSD_FPGA_VOLT_MIN(val) (((val >> 16) & 0xffff) >> 4) +#define SSD_FPGA_VOLT_CUR(val) (((val >> 32) & 0xffff) >> 4) +#define SSD_FPGA_VOLT(val) ((val * 3000) >> 12) + +#define SSD_VOLT_LOG_DATA(idx, ctrl, volt) (((uint32_t)idx << 24) | ((uint32_t)ctrl << 16) | ((uint32_t)volt)) + +enum ssd_fpga_volt +{ + SSD_FPGA_1V0 = 0, + SSD_FPGA_1V8, + SSD_FPGA_VOLT_NR +}; + +enum ssd_clock +{ + SSD_CLOCK_166M_LOST = 0, + SSD_CLOCK_166M_SKEW, + SSD_CLOCK_156M_LOST, + SSD_CLOCK_156M_SKEW, + SSD_CLOCK_NR +}; + +/* sensor */ +#define SSD_SENSOR_LM75_SADDRESS (0x49 << 1) +#define SSD_SENSOR_LM80_SADDRESS (0x28 << 1) + +#define SSD_SENSOR_CONVERT_TEMP(val) ((int)(val >> 8)) + +#define SSD_INLET_OT_TEMP (55) //55 DegC +#define SSD_INLET_OT_HYST (50) //50 DegC +#define SSD_FLASH_OT_TEMP (70) //70 DegC +#define SSD_FLASH_OT_HYST (65) //65 DegC + +enum ssd_sensor +{ + SSD_SENSOR_LM80 = 0, + SSD_SENSOR_LM75, + SSD_SENSOR_NR +}; + + +/* lm75 */ +enum ssd_lm75_reg +{ + SSD_LM75_REG_TEMP = 0, + SSD_LM75_REG_CONF, + SSD_LM75_REG_THYST, + SSD_LM75_REG_TOS +}; + +/* lm96080 */ +#define SSD_LM80_REG_IN_MAX(nr) (0x2a + (nr) * 2) +#define SSD_LM80_REG_IN_MIN(nr) (0x2b + (nr) * 2) +#define SSD_LM80_REG_IN(nr) (0x20 + (nr)) + +#define SSD_LM80_REG_FAN1 0x28 +#define SSD_LM80_REG_FAN2 0x29 +#define SSD_LM80_REG_FAN_MIN(nr) (0x3b + (nr)) + +#define SSD_LM80_REG_TEMP 0x27 +#define SSD_LM80_REG_TEMP_HOT_MAX 0x38 +#define SSD_LM80_REG_TEMP_HOT_HYST 0x39 +#define SSD_LM80_REG_TEMP_OS_MAX 0x3a +#define SSD_LM80_REG_TEMP_OS_HYST 0x3b + +#define SSD_LM80_REG_CONFIG 0x00 +#define SSD_LM80_REG_ALARM1 0x01 +#define SSD_LM80_REG_ALARM2 0x02 +#define SSD_LM80_REG_MASK1 0x03 +#define SSD_LM80_REG_MASK2 0x04 +#define SSD_LM80_REG_FANDIV 0x05 +#define SSD_LM80_REG_RES 0x06 + +#define SSD_LM80_CONVERT_VOLT(val) ((val * 10) >> 8) + +#define SSD_LM80_3V3_VOLT(val) ((val)*33/19) + +#define SSD_LM80_CONV_INTERVAL (1000) + +enum ssd_lm80_in +{ + SSD_LM80_IN_CAP = 0, + SSD_LM80_IN_1V2, + SSD_LM80_IN_1V2a, + SSD_LM80_IN_1V5, + SSD_LM80_IN_1V8, + SSD_LM80_IN_FPGA_3V3, + SSD_LM80_IN_3V3, + SSD_LM80_IN_NR +}; + +struct ssd_lm80_limit +{ + uint8_t low; + uint8_t high; +}; + +/* +/- 5% except cap in*/ +static struct ssd_lm80_limit ssd_lm80_limit[SSD_LM80_IN_NR] = { + {171, 217}, /* CAP in: 1710 ~ 2170 */ + {114, 126}, + {114, 126}, + {142, 158}, + {171, 189}, + {180, 200}, + {180, 200}, +}; + +/* temperature sensors */ +enum ssd_temp_sensor +{ + SSD_TEMP_INLET = 0, + SSD_TEMP_FLASH, + SSD_TEMP_CTRL, + SSD_TEMP_NR +}; + + +#ifdef SSD_OT_PROTECT +#define SSD_OT_DELAY (60) //ms + +#define SSD_OT_TEMP (90) //90 DegC + +#define SSD_OT_TEMP_HYST (85) //85 DegC +#endif + +/* fpga temperature */ +//#define CONVERT_TEMP(val) ((float)(val)*503.975f/4096.0f-273.15f) +#define CONVERT_TEMP(val) ((val)*504/4096-273) + +#define MAX_TEMP(val) CONVERT_TEMP(((val & 0xffff) >> 4)) +#define MIN_TEMP(val) CONVERT_TEMP((((val>>16) & 0xffff) >> 4)) +#define CUR_TEMP(val) CONVERT_TEMP((((val>>32) & 0xffff) >> 4)) + + +/* CAP monitor */ +#define SSD_PL_CAP_U1 SSD_LM80_REG_IN(SSD_LM80_IN_CAP) +#define SSD_PL_CAP_U2 SSD_LM80_REG_IN(SSD_LM80_IN_1V8) +#define SSD_PL_CAP_LEARN(u1, u2, t) ((t*(u1+u2))/(2*162*(u1-u2))) +#define SSD_PL_CAP_LEARN_WAIT (20) //20ms +#define SSD_PL_CAP_LEARN_MAX_WAIT (1000/SSD_PL_CAP_LEARN_WAIT) //1s + +#define SSD_PL_CAP_CHARGE_WAIT (1000) +#define SSD_PL_CAP_CHARGE_MAX_WAIT ((120*1000)/SSD_PL_CAP_CHARGE_WAIT) //120s + +#define SSD_PL_CAP_VOLT(val) (val*7) + +#define SSD_PL_CAP_VOLT_FULL (13700) +#define SSD_PL_CAP_VOLT_READY (12880) + +#define SSD_PL_CAP_THRESHOLD (8900) +#define SSD_PL_CAP_CP_THRESHOLD (5800) +#define SSD_PL_CAP_THRESHOLD_HYST (100) + +enum ssd_pl_cap_status +{ + SSD_PL_CAP = 0, + SSD_PL_CAP_NR +}; + +enum ssd_pl_cap_type +{ + SSD_PL_CAP_DEFAULT = 0, /* 4 cap */ + SSD_PL_CAP_CP /* 3 cap */ +}; + + +/* hwmon offset */ +#define SSD_HWMON_OFFS_TEMP (0) +#define SSD_HWMON_OFFS_SENSOR (SSD_HWMON_OFFS_TEMP + SSD_TEMP_NR) +#define SSD_HWMON_OFFS_PL_CAP (SSD_HWMON_OFFS_SENSOR + SSD_SENSOR_NR) +#define SSD_HWMON_OFFS_LM80 (SSD_HWMON_OFFS_PL_CAP + SSD_PL_CAP_NR) +#define SSD_HWMON_OFFS_CLOCK (SSD_HWMON_OFFS_LM80 + SSD_LM80_IN_NR) +#define SSD_HWMON_OFFS_FPGA (SSD_HWMON_OFFS_CLOCK + SSD_CLOCK_NR) + +#define SSD_HWMON_TEMP(idx) (SSD_HWMON_OFFS_TEMP + idx) +#define SSD_HWMON_SENSOR(idx) (SSD_HWMON_OFFS_SENSOR + idx) +#define SSD_HWMON_PL_CAP(idx) (SSD_HWMON_OFFS_PL_CAP + idx) +#define SSD_HWMON_LM80(idx) (SSD_HWMON_OFFS_LM80 + idx) +#define SSD_HWMON_CLOCK(idx) (SSD_HWMON_OFFS_CLOCK + idx) +#define SSD_HWMON_FPGA(ctrl, idx) (SSD_HWMON_OFFS_FPGA + (ctrl * SSD_FPGA_VOLT_NR) + idx) + + + +/* fifo */ +typedef struct sfifo +{ + uint32_t in; + uint32_t out; + uint32_t size; + uint32_t esize; + uint32_t mask; + spinlock_t lock; + void *data; +} sfifo_t; + +static int sfifo_alloc(struct sfifo *fifo, uint32_t size, uint32_t esize) +{ + uint32_t __size = 1; + + if (!fifo || size > INT_MAX || esize == 0) { + return -EINVAL; + } + + while (__size < size) __size <<= 1; + + if (__size < 2) { + return -EINVAL; + } + + fifo->data = vmalloc(esize * __size); + if (!fifo->data) { + return -ENOMEM; + } + + fifo->in = 0; + fifo->out = 0; + fifo->mask = __size - 1; + fifo->size = __size; + fifo->esize = esize; + spin_lock_init(&fifo->lock); + + return 0; +} + +static void sfifo_free(struct sfifo *fifo) +{ + if (!fifo) { + return; + } + + vfree(fifo->data); + fifo->data = NULL; + fifo->in = 0; + fifo->out = 0; + fifo->mask = 0; + fifo->size = 0; + fifo->esize = 0; +} + +static int __sfifo_put(struct sfifo *fifo, void *val) +{ + if (((fifo->in + 1) & fifo->mask) == fifo->out) { + return -1; + } + + memcpy((fifo->data + (fifo->in * fifo->esize)), val, fifo->esize); + fifo->in = (fifo->in + 1) & fifo->mask; + + return 0; +} + +static int sfifo_put(struct sfifo *fifo, void *val) +{ + int ret = 0; + + if (!fifo || !val) { + return -EINVAL; + } + + if (!in_interrupt()) { + spin_lock_irq(&fifo->lock); + ret = __sfifo_put(fifo, val); + spin_unlock_irq(&fifo->lock); + } else { + spin_lock(&fifo->lock); + ret = __sfifo_put(fifo, val); + spin_unlock(&fifo->lock); + } + + return ret; +} + +static int __sfifo_get(struct sfifo *fifo, void *val) +{ + if (fifo->out == fifo->in) { + return -1; + } + + memcpy(val, (fifo->data + (fifo->out * fifo->esize)), fifo->esize); + fifo->out = (fifo->out + 1) & fifo->mask; + + return 0; +} + +static int sfifo_get(struct sfifo *fifo, void *val) +{ + int ret = 0; + + if (!fifo || !val) { + return -EINVAL; + } + + if (!in_interrupt()) { + spin_lock_irq(&fifo->lock); + ret = __sfifo_get(fifo, val); + spin_unlock_irq(&fifo->lock); + } else { + spin_lock(&fifo->lock); + ret = __sfifo_get(fifo, val); + spin_unlock(&fifo->lock); + } + + return ret; +} + +/* bio list */ +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,30)) +struct ssd_blist { + struct bio *prev; + struct bio *next; +}; + +static inline void ssd_blist_init(struct ssd_blist *ssd_bl) +{ + ssd_bl->prev = NULL; + ssd_bl->next = NULL; +} + +static inline struct bio *ssd_blist_get(struct ssd_blist *ssd_bl) +{ + struct bio *bio = ssd_bl->prev; + + ssd_bl->prev = NULL; + ssd_bl->next = NULL; + + return bio; +} + +static inline void ssd_blist_add(struct ssd_blist *ssd_bl, struct bio *bio) +{ + bio->bi_next = NULL; + + if (ssd_bl->next) { + ssd_bl->next->bi_next = bio; + } else { + ssd_bl->prev = bio; + } + + ssd_bl->next = bio; +} + +#else +#define ssd_blist bio_list +#define ssd_blist_init bio_list_init +#define ssd_blist_get bio_list_get +#define ssd_blist_add bio_list_add +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,14,0)) +#define bio_start(bio) (bio->bi_sector) +#else +#define bio_start(bio) (bio->bi_iter.bi_sector) +#endif + +/* mutex */ +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,16)) +#define mutex_lock down +#define mutex_unlock up +#define mutex semaphore +#define mutex_init init_MUTEX +#endif + +/* i2c */ +typedef union ssd_i2c_ctrl { + uint32_t val; + struct { + uint8_t wdata; + uint8_t addr; + uint16_t rw:1; + uint16_t pad:15; + } bits; +}__attribute__((packed)) ssd_i2c_ctrl_t; + +typedef union ssd_i2c_data { + uint32_t val; + struct { + uint32_t rdata:8; + uint32_t valid:1; + uint32_t pad:23; + } bits; +}__attribute__((packed)) ssd_i2c_data_t; + +/* write mode */ +enum ssd_write_mode +{ + SSD_WMODE_BUFFER = 0, + SSD_WMODE_BUFFER_EX, + SSD_WMODE_FUA, + /* dummy */ + SSD_WMODE_AUTO, + SSD_WMODE_DEFAULT +}; + +/* reset type */ +enum ssd_reset_type +{ + SSD_RST_NOINIT = 0, + SSD_RST_NORMAL, + SSD_RST_FULL +}; + +/* ssd msg */ +typedef struct ssd_sg_entry +{ + uint64_t block:48; + uint64_t length:16; + uint64_t buf; +}__attribute__((packed))ssd_sg_entry_t; + +typedef struct ssd_rw_msg +{ + uint8_t tag; + uint8_t flag; + uint8_t nsegs; + uint8_t fun; + uint32_t reserved; //for 64-bit align + struct ssd_sg_entry sge[1]; //base +}__attribute__((packed))ssd_rw_msg_t; + +typedef struct ssd_resp_msg +{ + uint8_t tag; + uint8_t status:2; + uint8_t bitflip:6; + uint8_t log; + uint8_t fun; + uint32_t reserved; +}__attribute__((packed))ssd_resp_msg_t; + +typedef struct ssd_flush_msg +{ + uint8_t tag; + uint8_t flag:2; //flash cache 0 or bbt 1 + uint8_t flash:6; + uint8_t ctrl_idx; + uint8_t fun; + uint32_t reserved; //align +}__attribute__((packed))ssd_flush_msg_t; + +typedef struct ssd_nand_op_msg +{ + uint8_t tag; + uint8_t flag; + uint8_t ctrl_idx; + uint8_t fun; + uint32_t reserved; //align + uint16_t page_count; + uint8_t chip_ce; + uint8_t chip_no; + uint32_t page_no; + uint64_t buf; +}__attribute__((packed))ssd_nand_op_msg_t; + +typedef struct ssd_ram_op_msg +{ + uint8_t tag; + uint8_t flag; + uint8_t ctrl_idx; + uint8_t fun; + uint32_t reserved; //align + uint32_t start; + uint32_t length; + uint64_t buf; +}__attribute__((packed))ssd_ram_op_msg_t; + + +/* log msg */ +typedef struct ssd_log_msg +{ + uint8_t tag; + uint8_t flag; + uint8_t ctrl_idx; + uint8_t fun; + uint32_t reserved; //align + uint64_t buf; +}__attribute__((packed))ssd_log_msg_t; + +typedef struct ssd_log_op_msg +{ + uint8_t tag; + uint8_t flag; + uint8_t ctrl_idx; + uint8_t fun; + uint32_t reserved; //align + uint64_t reserved1; //align + uint64_t buf; +}__attribute__((packed))ssd_log_op_msg_t; + +typedef struct ssd_log_resp_msg +{ + uint8_t tag; + uint16_t status :2; + uint16_t reserved1 :2; //align with the normal resp msg + uint16_t nr_log :12; + uint8_t fun; + uint32_t reserved; +}__attribute__((packed))ssd_log_resp_msg_t; + + +/* resp msg */ +typedef union ssd_response_msq +{ + ssd_resp_msg_t resp_msg; + ssd_log_resp_msg_t log_resp_msg; + uint64_t u64_msg; + uint32_t u32_msg[2]; +} ssd_response_msq_t; + + +/* custom struct */ +typedef struct ssd_protocol_info +{ + uint32_t ver; + uint32_t init_state_reg; + uint32_t init_state_reg_sz; + uint32_t chip_info_reg; + uint32_t chip_info_reg_sz; +} ssd_protocol_info_t; + +typedef struct ssd_hw_info +{ + uint32_t bridge_ver; + uint32_t ctrl_ver; + + uint32_t cmd_fifo_sz; + uint32_t cmd_fifo_sz_mask; + uint32_t cmd_max_sg; + uint32_t sg_max_sec; + uint32_t resp_ptr_sz; + uint32_t resp_msg_sz; + + uint16_t nr_ctrl; + + uint16_t nr_data_ch; + uint16_t nr_ch; + uint16_t max_ch; + uint16_t nr_chip; + + uint8_t pcb_ver; + uint8_t upper_pcb_ver; + + uint8_t nand_vendor_id; + uint8_t nand_dev_id; + + uint8_t max_ce; + uint8_t id_size; + uint16_t oob_size; + + uint16_t bbf_pages; + uint16_t bbf_seek; // + + uint16_t page_count; //per block + uint32_t page_size; + uint32_t block_count; //per flash + + uint64_t ram_size; + uint32_t ram_align; + uint32_t ram_max_len; + + uint64_t bbt_base; + uint32_t bbt_size; + uint64_t md_base; //metadata + uint32_t md_size; + uint32_t md_entry_sz; + + uint32_t log_sz; + + uint64_t nand_wbuff_base; + + uint32_t md_reserved_blks; + uint32_t reserved_blks; + uint32_t valid_pages; + uint32_t max_valid_pages; + uint64_t size; +} ssd_hw_info_t; + +typedef struct ssd_hw_info_extend +{ + uint8_t board_type; + uint8_t cap_type; + uint8_t plp_type; + uint8_t work_mode; + uint8_t form_factor; + + uint8_t pad[59]; +}ssd_hw_info_extend_t; + +typedef struct ssd_rom_info +{ + uint32_t size; + uint32_t block_size; + uint16_t page_size; + uint8_t nr_bridge_fw; + uint8_t nr_ctrl_fw; + uint8_t nr_bm_fw; + uint8_t nr_smart; + uint32_t bridge_fw_base; + uint32_t bridge_fw_sz; + uint32_t ctrl_fw_base; + uint32_t ctrl_fw_sz; + uint32_t bm_fw_base; + uint32_t bm_fw_sz; + uint32_t log_base; + uint32_t log_sz; + uint32_t smart_base; + uint32_t smart_sz; + uint32_t vp_base; + uint32_t label_base; +} ssd_rom_info_t; + +/* debug info */ +enum ssd_debug_type +{ + SSD_DEBUG_NONE = 0, + SSD_DEBUG_READ_ERR, + SSD_DEBUG_WRITE_ERR, + SSD_DEBUG_RW_ERR, + SSD_DEBUG_READ_TO, + SSD_DEBUG_WRITE_TO, + SSD_DEBUG_RW_TO, + SSD_DEBUG_LOG, + SSD_DEBUG_OFFLINE, + SSD_DEBUG_NR +}; + +typedef struct ssd_debug_info +{ + int type; + union { + struct { + uint64_t off; + uint32_t len; + } loc; + struct { + int event; + uint32_t extra; + } log; + } data; +}ssd_debug_info_t; + +/* label */ +#define SSD_LABEL_FIELD_SZ 32 +#define SSD_SN_SZ 16 + +typedef struct ssd_label +{ + char date[SSD_LABEL_FIELD_SZ]; + char sn[SSD_LABEL_FIELD_SZ]; + char part[SSD_LABEL_FIELD_SZ]; + char desc[SSD_LABEL_FIELD_SZ]; + char other[SSD_LABEL_FIELD_SZ]; + char maf[SSD_LABEL_FIELD_SZ]; +} ssd_label_t; + +#define SSD_LABEL_DESC_SZ 256 + +typedef struct ssd_labelv3 +{ + char boardtype[SSD_LABEL_FIELD_SZ]; + char barcode[SSD_LABEL_FIELD_SZ]; + char item[SSD_LABEL_FIELD_SZ]; + char description[SSD_LABEL_DESC_SZ]; + char manufactured[SSD_LABEL_FIELD_SZ]; + char vendorname[SSD_LABEL_FIELD_SZ]; + char issuenumber[SSD_LABEL_FIELD_SZ]; + char cleicode[SSD_LABEL_FIELD_SZ]; + char bom[SSD_LABEL_FIELD_SZ]; +} ssd_labelv3_t; + +/* battery */ +typedef struct ssd_battery_info +{ + uint32_t fw_ver; +} ssd_battery_info_t; + +/* ssd power stat */ +typedef struct ssd_power_stat +{ + uint64_t nr_poweron; + uint64_t nr_powerloss; + uint64_t init_failed; +} ssd_power_stat_t; + +/* io stat */ +typedef struct ssd_io_stat +{ + uint64_t run_time; + uint64_t nr_to; + uint64_t nr_ioerr; + uint64_t nr_rwerr; + uint64_t nr_read; + uint64_t nr_write; + uint64_t rsectors; + uint64_t wsectors; +} ssd_io_stat_t; + +/* ecc */ +typedef struct ssd_ecc_info +{ + uint64_t bitflip[SSD_ECC_MAX_FLIP]; +} ssd_ecc_info_t; + +/* log */ +enum ssd_log_level +{ + SSD_LOG_LEVEL_INFO = 0, + SSD_LOG_LEVEL_NOTICE, + SSD_LOG_LEVEL_WARNING, + SSD_LOG_LEVEL_ERR, + SSD_LOG_NR_LEVEL +}; + +typedef struct ssd_log_info +{ + uint64_t nr_log; + uint64_t stat[SSD_LOG_NR_LEVEL]; +} ssd_log_info_t; + +/* S.M.A.R.T. */ +#define SSD_SMART_MAGIC (0x5452414D53445353ull) + +typedef struct ssd_smart +{ + struct ssd_power_stat pstat; + struct ssd_io_stat io_stat; + struct ssd_ecc_info ecc_info; + struct ssd_log_info log_info; + uint64_t version; + uint64_t magic; +} ssd_smart_t; + +/* internal log */ +typedef struct ssd_internal_log +{ + uint32_t nr_log; + void *log; +} ssd_internal_log_t; + +/* ssd cmd */ +typedef struct ssd_cmd +{ + struct bio *bio; + struct scatterlist *sgl; + struct list_head list; + void *dev; + int nsegs; + int flag; /*pbio(1) or bio(0)*/ + + int tag; + void *msg; + dma_addr_t msg_dma; + + unsigned long start_time; + + int errors; + unsigned int nr_log; + + struct timer_list cmd_timer; + struct completion *waiting; +} ssd_cmd_t; + +typedef void (*send_cmd_func)(struct ssd_cmd *); +typedef int (*ssd_event_call)(struct gendisk *, int, int); /* gendisk, event id, event level */ + +/* dcmd sz */ +#define SSD_DCMD_MAX_SZ 32 + +typedef struct ssd_dcmd +{ + struct list_head list; + void *dev; + uint8_t msg[SSD_DCMD_MAX_SZ]; +} ssd_dcmd_t; + + +enum ssd_state { + SSD_INIT_WORKQ, + SSD_INIT_BD, + SSD_ONLINE, + /* full reset */ + SSD_RESETING, + /* hw log */ + SSD_LOG_HW, + /* log err */ + SSD_LOG_ERR +}; + +#define SSD_QUEUE_NAME_LEN 16 +typedef struct ssd_queue { + char name[SSD_QUEUE_NAME_LEN]; + void *dev; + + int idx; + + uint32_t resp_idx; + uint32_t resp_idx_mask; + uint32_t resp_msg_sz; + + void *resp_msg; + void *resp_ptr; + + struct ssd_cmd *cmd; + + struct ssd_io_stat io_stat; + struct ssd_ecc_info ecc_info; +} ssd_queue_t; + +typedef struct ssd_device { + char name[SSD_DEV_NAME_LEN]; + + int idx; + int major; + int readonly; + + int int_mode; +#ifdef SSD_ESCAPE_IRQ + int irq_cpu; +#endif + + int reload_fw; + + int ot_delay; //in ms + + atomic_t refcnt; + atomic_t tocnt; + atomic_t in_flight[2]; //r&w + + uint64_t uptime; + + struct list_head list; + struct pci_dev *pdev; + + unsigned long mmio_base; + unsigned long mmio_len; + void __iomem *ctrlp; + + struct mutex spi_mutex; + struct mutex i2c_mutex; + + struct ssd_protocol_info protocol_info; + struct ssd_hw_info hw_info; + struct ssd_rom_info rom_info; + struct ssd_label label; + + struct ssd_smart smart; + + atomic_t in_sendq; + spinlock_t sendq_lock; + struct ssd_blist sendq; + struct task_struct *send_thread; + wait_queue_head_t send_waitq; + + atomic_t in_doneq; + spinlock_t doneq_lock; + struct ssd_blist doneq; + struct task_struct *done_thread; + wait_queue_head_t done_waitq; + + struct ssd_dcmd *dcmd; + spinlock_t dcmd_lock; + struct list_head dcmd_list; /* direct cmd list */ + wait_queue_head_t dcmd_wq; + + unsigned long *tag_map; + wait_queue_head_t tag_wq; + + spinlock_t cmd_lock; + struct ssd_cmd *cmd; + send_cmd_func scmd; + + ssd_event_call event_call; + void *msg_base; + dma_addr_t msg_base_dma; + + uint32_t resp_idx; + void *resp_msg_base; + void *resp_ptr_base; + dma_addr_t resp_msg_base_dma; + dma_addr_t resp_ptr_base_dma; + + int nr_queue; + struct msix_entry entry[SSD_MSIX_VEC]; + struct ssd_queue queue[SSD_MSIX_VEC]; + + struct request_queue *rq; /* The device request queue */ + struct gendisk *gd; /* The gendisk structure */ + + struct mutex internal_log_mutex; + struct ssd_internal_log internal_log; + struct workqueue_struct *workq; + struct work_struct log_work; /* get log */ + void *log_buf; + + unsigned long state; /* device state, for example, block device inited */ + + struct module *owner; + + /* extend */ + + int slave; + int cmajor; + int save_md; + int ot_protect; + + struct kref kref; + + struct mutex gd_mutex; + struct ssd_log_info log_info; /* volatile */ + + atomic_t queue_depth; + struct mutex barrier_mutex; + struct mutex fw_mutex; + + struct ssd_hw_info_extend hw_info_ext; + struct ssd_labelv3 labelv3; + + int wmode; + int user_wmode; + struct mutex bm_mutex; + struct work_struct bm_work; /* check bm */ + struct timer_list bm_timer; + struct sfifo log_fifo; + + struct timer_list routine_timer; + unsigned long routine_tick; + unsigned long hwmon; + + struct work_struct hwmon_work; /* check hw */ + struct work_struct capmon_work; /* check battery */ + struct work_struct tempmon_work; /* check temp */ + + /* debug info */ + struct ssd_debug_info db_info; +} ssd_device_t; + + +/* Ioctl struct */ +typedef struct ssd_acc_info { + uint32_t threshold_l1; + uint32_t threshold_l2; + uint32_t val; +} ssd_acc_info_t; + +typedef struct ssd_reg_op_info +{ + uint32_t offset; + uint32_t value; +} ssd_reg_op_info_t; + +typedef struct ssd_spi_op_info +{ + void __user *buf; + uint32_t off; + uint32_t len; +} ssd_spi_op_info_t; + +typedef struct ssd_i2c_op_info +{ + uint8_t saddr; + uint8_t wsize; + uint8_t rsize; + void __user *wbuf; + void __user *rbuf; +} ssd_i2c_op_info_t; + +typedef struct ssd_smbus_op_info +{ + uint8_t saddr; + uint8_t cmd; + uint8_t size; + void __user *buf; +} ssd_smbus_op_info_t; + +typedef struct ssd_ram_op_info { + uint8_t ctrl_idx; + uint32_t length; + uint64_t start; + uint8_t __user *buf; +} ssd_ram_op_info_t; + +typedef struct ssd_flash_op_info { + uint32_t page; + uint16_t flash; + uint8_t chip; + uint8_t ctrl_idx; + uint8_t __user *buf; +} ssd_flash_op_info_t; + +typedef struct ssd_sw_log_info { + uint16_t event; + uint16_t pad; + uint32_t data; +} ssd_sw_log_info_t; + +typedef struct ssd_version_info +{ + uint32_t bridge_ver; /* bridge fw version */ + uint32_t ctrl_ver; /* controller fw version */ + uint32_t bm_ver; /* battery manager fw version */ + uint8_t pcb_ver; /* main pcb version */ + uint8_t upper_pcb_ver; + uint8_t pad0; + uint8_t pad1; +} ssd_version_info_t; + +typedef struct pci_addr +{ + uint16_t domain; + uint8_t bus; + uint8_t slot; + uint8_t func; +} pci_addr_t; + +typedef struct ssd_drv_param_info { + int mode; + int status_mask; + int int_mode; + int threaded_irq; + int log_level; + int wmode; + int ot_protect; + int finject; + int pad[8]; +} ssd_drv_param_info_t; + + +/* form factor */ +enum ssd_form_factor +{ + SSD_FORM_FACTOR_HHHL = 0, + SSD_FORM_FACTOR_FHHL +}; + + +/* ssd power loss protect */ +enum ssd_plp_type +{ + SSD_PLP_SCAP = 0, + SSD_PLP_CAP, + SSD_PLP_NONE +}; + +/* ssd bm */ +#define SSD_BM_SLAVE_ADDRESS 0x16 +#define SSD_BM_CAP 5 + +/* SBS cmd */ +#define SSD_BM_SAFETYSTATUS 0x51 +#define SSD_BM_OPERATIONSTATUS 0x54 + +/* ManufacturerAccess */ +#define SSD_BM_MANUFACTURERACCESS 0x00 +#define SSD_BM_ENTER_CAP_LEARNING 0x0023 /* cap learning */ + +/* Data flash access */ +#define SSD_BM_DATA_FLASH_SUBCLASS_ID 0x77 +#define SSD_BM_DATA_FLASH_SUBCLASS_ID_PAGE1 0x78 +#define SSD_BM_SYSTEM_DATA_SUBCLASS_ID 56 +#define SSD_BM_CONFIGURATION_REGISTERS_ID 64 + +/* min cap voltage */ +#define SSD_BM_CAP_VOLT_MIN 500 + +/* +enum ssd_bm_cap +{ + SSD_BM_CAP_VINA = 1, + SSD_BM_CAP_JH = 3 +};*/ + +enum ssd_bmstatus +{ + SSD_BMSTATUS_OK = 0, + SSD_BMSTATUS_CHARGING, /* not fully charged */ + SSD_BMSTATUS_WARNING +}; + +enum sbs_unit { + SBS_UNIT_VALUE = 0, + SBS_UNIT_TEMPERATURE, + SBS_UNIT_VOLTAGE, + SBS_UNIT_CURRENT, + SBS_UNIT_ESR, + SBS_UNIT_PERCENT, + SBS_UNIT_CAPACITANCE +}; + +enum sbs_size { + SBS_SIZE_BYTE = 1, + SBS_SIZE_WORD, + SBS_SIZE_BLK, +}; + +struct sbs_cmd { + uint8_t cmd; + uint8_t size; + uint8_t unit; + uint8_t off; + uint16_t mask; + char *desc; +}; + +struct ssd_bm { + uint16_t temp; + uint16_t volt; + uint16_t curr; + uint16_t esr; + uint16_t rsoc; + uint16_t health; + uint16_t cap; + uint16_t chg_curr; + uint16_t chg_volt; + uint16_t cap_volt[SSD_BM_CAP]; + uint16_t sf_alert; + uint16_t sf_status; + uint16_t op_status; + uint16_t sys_volt; +}; + +struct ssd_bm_manufacturer_data +{ + uint16_t pack_lot_code; + uint16_t pcb_lot_code; + uint16_t firmware_ver; + uint16_t hardware_ver; +}; + +struct ssd_bm_configuration_registers +{ + struct { + uint16_t cc:3; + uint16_t rsvd:5; + uint16_t stack:1; + uint16_t rsvd1:2; + uint16_t temp:2; + uint16_t rsvd2:1; + uint16_t lt_en:1; + uint16_t rsvd3:1; + } operation_cfg; + uint16_t pad; + uint16_t fet_action; + uint16_t pad1; + uint16_t fault; +}; + +#define SBS_VALUE_MASK 0xffff + +#define bm_var_offset(var) ((size_t) &((struct ssd_bm *)0)->var) +#define bm_var(start, offset) ((void *) start + (offset)) + +static struct sbs_cmd ssd_bm_sbs[] = { + {0x08, SBS_SIZE_WORD, SBS_UNIT_TEMPERATURE, bm_var_offset(temp), SBS_VALUE_MASK, "Temperature"}, + {0x09, SBS_SIZE_WORD, SBS_UNIT_VOLTAGE, bm_var_offset(volt), SBS_VALUE_MASK, "Voltage"}, + {0x0a, SBS_SIZE_WORD, SBS_UNIT_CURRENT, bm_var_offset(curr), SBS_VALUE_MASK, "Current"}, + {0x0b, SBS_SIZE_WORD, SBS_UNIT_ESR, bm_var_offset(esr), SBS_VALUE_MASK, "ESR"}, + {0x0d, SBS_SIZE_BYTE, SBS_UNIT_PERCENT, bm_var_offset(rsoc), SBS_VALUE_MASK, "RelativeStateOfCharge"}, + {0x0e, SBS_SIZE_BYTE, SBS_UNIT_PERCENT, bm_var_offset(health), SBS_VALUE_MASK, "Health"}, + {0x10, SBS_SIZE_WORD, SBS_UNIT_CAPACITANCE, bm_var_offset(cap), SBS_VALUE_MASK, "Capacitance"}, + {0x14, SBS_SIZE_WORD, SBS_UNIT_CURRENT, bm_var_offset(chg_curr), SBS_VALUE_MASK, "ChargingCurrent"}, + {0x15, SBS_SIZE_WORD, SBS_UNIT_VOLTAGE, bm_var_offset(chg_volt), SBS_VALUE_MASK, "ChargingVoltage"}, + {0x3b, SBS_SIZE_WORD, SBS_UNIT_VOLTAGE, (uint8_t)bm_var_offset(cap_volt[4]), SBS_VALUE_MASK, "CapacitorVoltage5"}, + {0x3c, SBS_SIZE_WORD, SBS_UNIT_VOLTAGE, (uint8_t)bm_var_offset(cap_volt[3]), SBS_VALUE_MASK, "CapacitorVoltage4"}, + {0x3d, SBS_SIZE_WORD, SBS_UNIT_VOLTAGE, (uint8_t)bm_var_offset(cap_volt[2]), SBS_VALUE_MASK, "CapacitorVoltage3"}, + {0x3e, SBS_SIZE_WORD, SBS_UNIT_VOLTAGE, (uint8_t)bm_var_offset(cap_volt[1]), SBS_VALUE_MASK, "CapacitorVoltage2"}, + {0x3f, SBS_SIZE_WORD, SBS_UNIT_VOLTAGE, (uint8_t)bm_var_offset(cap_volt[0]), SBS_VALUE_MASK, "CapacitorVoltage1"}, + {0x50, SBS_SIZE_WORD, SBS_UNIT_VALUE, bm_var_offset(sf_alert), 0x870F, "SafetyAlert"}, + {0x51, SBS_SIZE_WORD, SBS_UNIT_VALUE, bm_var_offset(sf_status), 0xE7BF, "SafetyStatus"}, + {0x54, SBS_SIZE_WORD, SBS_UNIT_VALUE, bm_var_offset(op_status), 0x79F4, "OperationStatus"}, + {0x5a, SBS_SIZE_WORD, SBS_UNIT_VOLTAGE, bm_var_offset(sys_volt), SBS_VALUE_MASK, "SystemVoltage"}, + {0, 0, 0, 0, 0, NULL}, +}; + +/* ssd ioctl */ +#define SSD_CMD_GET_PROTOCOL_INFO _IOR('H', 100, struct ssd_protocol_info) +#define SSD_CMD_GET_HW_INFO _IOR('H', 101, struct ssd_hw_info) +#define SSD_CMD_GET_ROM_INFO _IOR('H', 102, struct ssd_rom_info) +#define SSD_CMD_GET_SMART _IOR('H', 103, struct ssd_smart) +#define SSD_CMD_GET_IDX _IOR('H', 105, int) +#define SSD_CMD_GET_AMOUNT _IOR('H', 106, int) +#define SSD_CMD_GET_TO_INFO _IOR('H', 107, int) +#define SSD_CMD_GET_DRV_VER _IOR('H', 108, char[DRIVER_VERSION_LEN]) + +#define SSD_CMD_GET_BBACC_INFO _IOR('H', 109, struct ssd_acc_info) +#define SSD_CMD_GET_ECACC_INFO _IOR('H', 110, struct ssd_acc_info) + +#define SSD_CMD_GET_HW_INFO_EXT _IOR('H', 111, struct ssd_hw_info_extend) + +#define SSD_CMD_REG_READ _IOWR('H', 120, struct ssd_reg_op_info) +#define SSD_CMD_REG_WRITE _IOWR('H', 121, struct ssd_reg_op_info) + +#define SSD_CMD_SPI_READ _IOWR('H', 125, struct ssd_spi_op_info) +#define SSD_CMD_SPI_WRITE _IOWR('H', 126, struct ssd_spi_op_info) +#define SSD_CMD_SPI_ERASE _IOWR('H', 127, struct ssd_spi_op_info) + +#define SSD_CMD_I2C_READ _IOWR('H', 128, struct ssd_i2c_op_info) +#define SSD_CMD_I2C_WRITE _IOWR('H', 129, struct ssd_i2c_op_info) +#define SSD_CMD_I2C_WRITE_READ _IOWR('H', 130, struct ssd_i2c_op_info) + +#define SSD_CMD_SMBUS_SEND_BYTE _IOWR('H', 131, struct ssd_smbus_op_info) +#define SSD_CMD_SMBUS_RECEIVE_BYTE _IOWR('H', 132, struct ssd_smbus_op_info) +#define SSD_CMD_SMBUS_WRITE_BYTE _IOWR('H', 133, struct ssd_smbus_op_info) +#define SSD_CMD_SMBUS_READ_BYTE _IOWR('H', 135, struct ssd_smbus_op_info) +#define SSD_CMD_SMBUS_WRITE_WORD _IOWR('H', 136, struct ssd_smbus_op_info) +#define SSD_CMD_SMBUS_READ_WORD _IOWR('H', 137, struct ssd_smbus_op_info) +#define SSD_CMD_SMBUS_WRITE_BLOCK _IOWR('H', 138, struct ssd_smbus_op_info) +#define SSD_CMD_SMBUS_READ_BLOCK _IOWR('H', 139, struct ssd_smbus_op_info) + +#define SSD_CMD_BM_GET_VER _IOR('H', 140, uint16_t) +#define SSD_CMD_BM_GET_NR_CAP _IOR('H', 141, int) +#define SSD_CMD_BM_CAP_LEARNING _IOW('H', 142, int) +#define SSD_CMD_CAP_LEARN _IOR('H', 143, uint32_t) +#define SSD_CMD_GET_CAP_STATUS _IOR('H', 144, int) + +#define SSD_CMD_RAM_READ _IOWR('H', 150, struct ssd_ram_op_info) +#define SSD_CMD_RAM_WRITE _IOWR('H', 151, struct ssd_ram_op_info) + +#define SSD_CMD_NAND_READ_ID _IOR('H', 160, struct ssd_flash_op_info) +#define SSD_CMD_NAND_READ _IOWR('H', 161, struct ssd_flash_op_info) //with oob +#define SSD_CMD_NAND_WRITE _IOWR('H', 162, struct ssd_flash_op_info) +#define SSD_CMD_NAND_ERASE _IOWR('H', 163, struct ssd_flash_op_info) +#define SSD_CMD_NAND_READ_EXT _IOWR('H', 164, struct ssd_flash_op_info) //ingore EIO + +#define SSD_CMD_UPDATE_BBT _IOW('H', 180, struct ssd_flash_op_info) + +#define SSD_CMD_CLEAR_ALARM _IOW('H', 190, int) +#define SSD_CMD_SET_ALARM _IOW('H', 191, int) + +#define SSD_CMD_RESET _IOW('H', 200, int) +#define SSD_CMD_RELOAD_FW _IOW('H', 201, int) +#define SSD_CMD_UNLOAD_DEV _IOW('H', 202, int) +#define SSD_CMD_LOAD_DEV _IOW('H', 203, int) +#define SSD_CMD_UPDATE_VP _IOWR('H', 205, uint32_t) +#define SSD_CMD_FULL_RESET _IOW('H', 206, int) + +#define SSD_CMD_GET_NR_LOG _IOR('H', 220, uint32_t) +#define SSD_CMD_GET_LOG _IOR('H', 221, void *) +#define SSD_CMD_LOG_LEVEL _IOW('H', 222, int) + +#define SSD_CMD_OT_PROTECT _IOW('H', 223, int) +#define SSD_CMD_GET_OT_STATUS _IOR('H', 224, int) + +#define SSD_CMD_CLEAR_LOG _IOW('H', 230, int) +#define SSD_CMD_CLEAR_SMART _IOW('H', 231, int) + +#define SSD_CMD_SW_LOG _IOW('H', 232, struct ssd_sw_log_info) + +#define SSD_CMD_GET_LABEL _IOR('H', 235, struct ssd_label) +#define SSD_CMD_GET_VERSION _IOR('H', 236, struct ssd_version_info) +#define SSD_CMD_GET_TEMPERATURE _IOR('H', 237, int) +#define SSD_CMD_GET_BMSTATUS _IOR('H', 238, int) +#define SSD_CMD_GET_LABEL2 _IOR('H', 239, void *) + + +#define SSD_CMD_FLUSH _IOW('H', 240, int) +#define SSD_CMD_SAVE_MD _IOW('H', 241, int) + +#define SSD_CMD_SET_WMODE _IOW('H', 242, int) +#define SSD_CMD_GET_WMODE _IOR('H', 243, int) +#define SSD_CMD_GET_USER_WMODE _IOR('H', 244, int) + +#define SSD_CMD_DEBUG _IOW('H', 250, struct ssd_debug_info) +#define SSD_CMD_DRV_PARAM_INFO _IOR('H', 251, struct ssd_drv_param_info) + + +/* log */ +#define SSD_LOG_MAX_SZ 4096 +#define SSD_LOG_LEVEL SSD_LOG_LEVEL_NOTICE + +enum ssd_log_data +{ + SSD_LOG_DATA_NONE = 0, + SSD_LOG_DATA_LOC, + SSD_LOG_DATA_HEX +}; + +typedef struct ssd_log_entry +{ + union { + struct { + uint32_t page:10; + uint32_t block:14; + uint32_t flash:8; + } loc; + struct { + uint32_t page:12; + uint32_t block:12; + uint32_t flash:8; + } loc1; + uint32_t val; + } data; + uint16_t event:10; + uint16_t mod:6; + uint16_t idx; +}__attribute__((packed))ssd_log_entry_t; + +typedef struct ssd_log +{ + uint64_t time:56; + uint64_t ctrl_idx:8; + ssd_log_entry_t le; +} __attribute__((packed)) ssd_log_t; + +typedef struct ssd_log_desc +{ + uint16_t event; + uint8_t level; + uint8_t data; + uint8_t sblock; + uint8_t spage; + char *desc; +} __attribute__((packed)) ssd_log_desc_t; + +#define SSD_LOG_SW_IDX 0xF +#define SSD_UNKNOWN_EVENT ((uint16_t)-1) +static struct ssd_log_desc ssd_log_desc[] = { + /* event, level, show flash, show block, show page, desc */ + {0x0, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_LOC, 0, 0, "Create BBT failure"}, //g3 + {0x1, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_LOC, 0, 0, "Read BBT failure"}, //g3 + {0x2, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "Mark bad block"}, + {0x3, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 0, 0, "Flush BBT failure"}, + {0x4, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Program failure"}, + {0x7, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "No available blocks"}, + {0x8, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "Bad EC header"}, + {0x9, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_LOC, 1, 0, "Bad VID header"}, //g3 + {0xa, SSD_LOG_LEVEL_INFO, SSD_LOG_DATA_LOC, 1, 0, "Wear leveling"}, + {0xb, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "WL read back failure"}, + {0x11, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "Data recovery failure"}, // err + {0x20, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "Init: scan mapping table failure"}, // err g3 + {0x21, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Program failure"}, + {0x22, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Program failure"}, + {0x23, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Program failure"}, + {0x24, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "Merge: read mapping page failure"}, + {0x25, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Merge: read back failure"}, + {0x26, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Program failure"}, + {0x27, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_LOC, 1, 1, "Data corrupted for abnormal power down"}, //g3 + {0x28, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Merge: mapping page corrupted"}, + {0x29, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "Init: no mapping page"}, + {0x2a, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: mapping pages incomplete"}, + {0x2b, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "Read back failure after programming failure"}, // err + {0xf1, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "Read failure without recovery"}, // err + {0xf2, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 0, 0, "No available blocks"}, // maybe err g3 + {0xf3, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 0, "Init: RAID incomplete"}, // err g3 + {0xf4, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Program failure"}, + {0xf5, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Read failure in moving data"}, + {0xf6, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Program failure"}, + {0xf7, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_LOC, 1, 1, "Init: RAID not complete"}, + {0xf8, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "Init: data moving interrupted"}, + {0xfe, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 0, 0, "Data inspection failure"}, + {0xff, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "IO: ECC failed"}, + + /* new */ + {0x2e, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 0, 0, "No available reserved blocks" }, // err + {0x30, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 0, 0, "Init: PMT membership not found"}, + {0x31, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "Init: PMT corrupted"}, + {0x32, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 0, 0, "Init: PBT membership not found"}, + {0x33, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 0, 0, "Init: PBT not found"}, + {0x34, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 0, 0, "Init: PBT corrupted"}, + {0x35, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: PMT page read failure"}, + {0x36, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: PBT page read failure"}, + {0x37, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: PBT backup page read failure"}, + {0x38, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: PBMT read failure"}, + {0x39, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "Init: PBMT scan failure"}, // err + {0x3a, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: first page read failure"}, + {0x3b, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "Init: first page scan failure"}, // err + {0x3c, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "Init: scan unclosed block failure"}, // err + {0x3d, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: write pointer mismatch"}, + {0x3e, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: PMT recovery: PBMT read failure"}, + {0x3f, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "Init: PMT recovery: PBMT scan failure"}, + {0x40, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "Init: PMT recovery: data page read failure"}, //err + {0x41, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: PBT write pointer mismatch"}, + {0x42, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: PBT latest version corrupted"}, + {0x43, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 0, "Init: too many unclosed blocks"}, + {0x44, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "Init: PDW block found"}, + {0x45, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_HEX, 0, 0, "Init: more than one PDW block found"}, //err + {0x46, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Init: first page is blank or read failure"}, + {0x47, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 0, 0, "Init: PDW block not found"}, + + {0x50, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 0, "Cache: hit error data"}, // err + {0x51, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 0, "Cache: read back failure"}, // err + {0x52, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Cache: unknown command"}, //? + {0x53, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_LOC, 1, 1, "GC/WL read back failure"}, // err + + {0x60, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "Erase failure"}, + + {0x70, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "LPA not matched"}, + {0x71, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "PBN not matched"}, + {0x72, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Read retry failure"}, + {0x73, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Need raid recovery"}, + {0x74, SSD_LOG_LEVEL_INFO, SSD_LOG_DATA_LOC, 1, 1, "Need read retry"}, + {0x75, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Read invalid data page"}, + {0x76, SSD_LOG_LEVEL_INFO, SSD_LOG_DATA_LOC, 1, 1, "ECC error, data in cache, PBN matched"}, + {0x77, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "ECC error, data in cache, PBN not matched"}, + {0x78, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "ECC error, data in flash, PBN not matched"}, + {0x79, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "ECC ok, data in cache, LPA not matched"}, + {0x7a, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "ECC ok, data in flash, LPA not matched"}, + {0x7b, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "RAID data in cache, LPA not matched"}, + {0x7c, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "RAID data in flash, LPA not matched"}, + {0x7d, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Read data page status error"}, + {0x7e, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Read blank page"}, + {0x7f, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Access flash timeout"}, + + {0x80, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "EC overflow"}, + {0x81, SSD_LOG_LEVEL_INFO, SSD_LOG_DATA_NONE, 0, 0, "Scrubbing completed"}, + {0x82, SSD_LOG_LEVEL_INFO, SSD_LOG_DATA_LOC, 1, 0, "Unstable block(too much bit flip)"}, + {0x83, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "GC: ram error"}, //? + {0x84, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "GC: one PBMT read failure"}, + + {0x88, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "GC: mark bad block"}, + {0x89, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 0, "GC: invalid page count error"}, // maybe err + {0x8a, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_NONE, 0, 0, "Warning: Bad Block close to limit"}, + {0x8b, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_NONE, 0, 0, "Error: Bad Block over limit"}, + {0x8c, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_NONE, 0, 0, "Warning: P/E cycles close to limit"}, + {0x8d, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_NONE, 0, 0, "Error: P/E cycles over limit"}, + + {0x90, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Over temperature"}, //xx + {0x91, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Temperature is OK"}, //xx + {0x92, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_NONE, 0, 0, "Battery fault"}, + {0x93, SSD_LOG_LEVEL_WARNING, SSD_LOG_DATA_NONE, 0, 0, "SEU fault"}, //err + {0x94, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_NONE, 0, 0, "DDR error"}, //err + {0x95, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_NONE, 0, 0, "Controller serdes error"}, //err + {0x96, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_NONE, 0, 0, "Bridge serdes 1 error"}, //err + {0x97, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_NONE, 0, 0, "Bridge serdes 2 error"}, //err + {0x98, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "SEU fault (corrected)"}, //err + {0x99, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Battery is OK"}, + {0x9a, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Temperature close to limit"}, //xx + + {0x9b, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "SEU fault address (low)"}, + {0x9c, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "SEU fault address (high)"}, + {0x9d, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "I2C fault" }, + {0x9e, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "DDR single bit error" }, + {0x9f, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Board voltage fault" }, + + {0xa0, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "LPA not matched"}, + {0xa1, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Re-read data in cache"}, + {0xa2, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Read blank page"}, + {0xa3, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "RAID recovery: Read blank page"}, + {0xa4, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "RAID recovery: new data in cache"}, + {0xa5, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "RAID recovery: PBN not matched"}, + {0xa6, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Read data with error flag"}, + {0xa7, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "RAID recovery: recoverd data with error flag"}, + {0xa8, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Blank page in cache, PBN matched"}, + {0xa9, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "RAID recovery: Blank page in cache, PBN matched"}, + {0xaa, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 0, 0, "Flash init failure"}, + {0xab, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "Mapping table recovery failure"}, + {0xac, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_LOC, 1, 1, "RAID recovery: ECC failed"}, + {0xb0, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Temperature is up to degree 95"}, + {0xb1, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Temperature is up to degree 100"}, + + {0x300, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_HEX, 0, 0, "CMD timeout"}, + {0x301, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "Power on"}, + {0x302, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Power off"}, + {0x303, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Clear log"}, + {0x304, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "Set capacity"}, + {0x305, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Clear data"}, + {0x306, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "BM safety status"}, + {0x307, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_HEX, 0, 0, "I/O error"}, + {0x308, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "CMD error"}, + {0x309, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "Set wmode"}, + {0x30a, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_HEX, 0, 0, "DDR init failed" }, + {0x30b, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "PCIe link status" }, + {0x30c, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_HEX, 0, 0, "Controller reset sync error" }, + {0x30d, SSD_LOG_LEVEL_ERR, SSD_LOG_DATA_HEX, 0, 0, "Clock fault" }, + {0x30e, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "FPGA voltage fault status" }, + {0x30f, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "Set capacity finished"}, + {0x310, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Clear data finished"}, + {0x311, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "Reset"}, + {0x312, SSD_LOG_LEVEL_WARNING,SSD_LOG_DATA_HEX, 0, 0, "CAP: voltage fault"}, + {0x313, SSD_LOG_LEVEL_WARNING,SSD_LOG_DATA_NONE, 0, 0, "CAP: learn fault"}, + {0x314, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "CAP status"}, + {0x315, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "Board voltage fault status"}, + {0x316, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Inlet over temperature"}, + {0x317, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Inlet temperature is OK"}, + {0x318, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Flash over temperature"}, + {0x319, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Flash temperature is OK"}, + {0x31a, SSD_LOG_LEVEL_WARNING,SSD_LOG_DATA_NONE, 0, 0, "CAP: short circuit"}, + {0x31b, SSD_LOG_LEVEL_WARNING,SSD_LOG_DATA_HEX, 0, 0, "Sensor fault"}, + {0x31c, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Erase all data"}, + {0x31d, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_NONE, 0, 0, "Erase all data finished"}, + + {SSD_UNKNOWN_EVENT, SSD_LOG_LEVEL_NOTICE, SSD_LOG_DATA_HEX, 0, 0, "unknown event"}, +}; +/* */ +#define SSD_LOG_OVER_TEMP 0x90 +#define SSD_LOG_NORMAL_TEMP 0x91 +#define SSD_LOG_WARN_TEMP 0x9a +#define SSD_LOG_SEU_FAULT 0x93 +#define SSD_LOG_SEU_FAULT1 0x98 +#define SSD_LOG_BATTERY_FAULT 0x92 +#define SSD_LOG_BATTERY_OK 0x99 +#define SSD_LOG_BOARD_VOLT_FAULT 0x9f + +/* software log */ +#define SSD_LOG_TIMEOUT 0x300 +#define SSD_LOG_POWER_ON 0x301 +#define SSD_LOG_POWER_OFF 0x302 +#define SSD_LOG_CLEAR_LOG 0x303 +#define SSD_LOG_SET_CAPACITY 0x304 +#define SSD_LOG_CLEAR_DATA 0x305 +#define SSD_LOG_BM_SFSTATUS 0x306 +#define SSD_LOG_EIO 0x307 +#define SSD_LOG_ECMD 0x308 +#define SSD_LOG_SET_WMODE 0x309 +#define SSD_LOG_DDR_INIT_ERR 0x30a +#define SSD_LOG_PCIE_LINK_STATUS 0x30b +#define SSD_LOG_CTRL_RST_SYNC 0x30c +#define SSD_LOG_CLK_FAULT 0x30d +#define SSD_LOG_VOLT_FAULT 0x30e +#define SSD_LOG_SET_CAPACITY_END 0x30F +#define SSD_LOG_CLEAR_DATA_END 0x310 +#define SSD_LOG_RESET 0x311 +#define SSD_LOG_CAP_VOLT_FAULT 0x312 +#define SSD_LOG_CAP_LEARN_FAULT 0x313 +#define SSD_LOG_CAP_STATUS 0x314 +#define SSD_LOG_VOLT_STATUS 0x315 +#define SSD_LOG_INLET_OVER_TEMP 0x316 +#define SSD_LOG_INLET_NORMAL_TEMP 0x317 +#define SSD_LOG_FLASH_OVER_TEMP 0x318 +#define SSD_LOG_FLASH_NORMAL_TEMP 0x319 +#define SSD_LOG_CAP_SHORT_CIRCUIT 0x31a +#define SSD_LOG_SENSOR_FAULT 0x31b +#define SSD_LOG_ERASE_ALL 0x31c +#define SSD_LOG_ERASE_ALL_END 0x31d + + +/* sw log fifo depth */ +#define SSD_LOG_FIFO_SZ 1024 + + +/* done queue */ +static DEFINE_PER_CPU(struct list_head, ssd_doneq); +static DEFINE_PER_CPU(struct tasklet_struct, ssd_tasklet); + + +/* unloading driver */ +static volatile int ssd_exiting = 0; + +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,12)) +static struct class_simple *ssd_class; +#else +static struct class *ssd_class; +#endif + +static int ssd_cmajor = SSD_CMAJOR; + +/* ssd block device major, minors */ +static int ssd_major = SSD_MAJOR; +static int ssd_major_sl = SSD_MAJOR_SL; +static int ssd_minors = SSD_MINORS; + +/* ssd device list */ +static struct list_head ssd_list; +static unsigned long ssd_index_bits[SSD_MAX_DEV / BITS_PER_LONG + 1]; +static unsigned long ssd_index_bits_sl[SSD_MAX_DEV / BITS_PER_LONG + 1]; +static atomic_t ssd_nr; + +/* module param */ +enum ssd_drv_mode +{ + SSD_DRV_MODE_STANDARD = 0, /* full */ + SSD_DRV_MODE_DEBUG = 2, /* debug */ + SSD_DRV_MODE_BASE /* base only */ +}; + +enum ssd_int_mode +{ + SSD_INT_LEGACY = 0, + SSD_INT_MSI, + SSD_INT_MSIX +}; + +#if (defined SSD_MSIX) +#define SSD_INT_MODE_DEFAULT SSD_INT_MSIX +#elif (defined SSD_MSI) +#define SSD_INT_MODE_DEFAULT SSD_INT_MSI +#else +/* auto select the defaut int mode according to the kernel version*/ +/* suse 11 sp1 irqbalance bug: use msi instead*/ +#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,35)) || (defined RHEL_MAJOR && RHEL_MAJOR >= 6) || (defined RHEL_MAJOR && RHEL_MAJOR == 5 && RHEL_MINOR >= 5)) +#define SSD_INT_MODE_DEFAULT SSD_INT_MSIX +#else +#define SSD_INT_MODE_DEFAULT SSD_INT_MSI +#endif +#endif + +static int mode = SSD_DRV_MODE_STANDARD; +static int status_mask = 0xFF; +static int int_mode = SSD_INT_MODE_DEFAULT; +static int threaded_irq = 0; +static int log_level = SSD_LOG_LEVEL_WARNING; +static int ot_protect = 1; +static int wmode = SSD_WMODE_DEFAULT; +static int finject = 0; + +module_param(mode, int, 0); +module_param(status_mask, int, 0); +module_param(int_mode, int, 0); +module_param(threaded_irq, int, 0); +module_param(log_level, int, 0); +module_param(ot_protect, int, 0); +module_param(wmode, int, 0); +module_param(finject, int, 0); + + +MODULE_PARM_DESC(mode, "driver mode, 0 - standard, 1 - debug, 2 - debug without IO, 3 - basic debug mode"); +MODULE_PARM_DESC(status_mask, "command status mask, 0 - without command error, 0xff - with command error"); +MODULE_PARM_DESC(int_mode, "preferred interrupt mode, 0 - legacy, 1 - msi, 2 - msix"); +MODULE_PARM_DESC(threaded_irq, "threaded irq, 0 - normal irq, 1 - threaded irq"); +MODULE_PARM_DESC(log_level, "log level to display, 0 - info and above, 1 - notice and above, 2 - warning and above, 3 - error only"); +MODULE_PARM_DESC(ot_protect, "over temperature protect, 0 - disable, 1 - enable"); +MODULE_PARM_DESC(wmode, "write mode, 0 - write buffer (with risk for the 6xx firmware), 1 - write buffer ex, 2 - write through, 3 - auto, 4 - default"); +MODULE_PARM_DESC(finject, "enable fault simulation, 0 - off, 1 - on, for debug purpose only"); + + +#ifndef MODULE +static int __init ssd_drv_mode(char *str) +{ + mode = (int)simple_strtoul(str, NULL, 0); + + return 1; +} + +static int __init ssd_status_mask(char *str) +{ + status_mask = (int)simple_strtoul(str, NULL, 16); + + return 1; +} + +static int __init ssd_int_mode(char *str) +{ + int_mode = (int)simple_strtoul(str, NULL, 0); + + return 1; +} + +static int __init ssd_threaded_irq(char *str) +{ + threaded_irq = (int)simple_strtoul(str, NULL, 0); + + return 1; +} + +static int __init ssd_log_level(char *str) +{ + log_level = (int)simple_strtoul(str, NULL, 0); + + return 1; +} + +static int __init ssd_ot_protect(char *str) +{ + ot_protect = (int)simple_strtoul(str, NULL, 0); + + return 1; +} + +static int __init ssd_wmode(char *str) +{ + wmode = (int)simple_strtoul(str, NULL, 0); + + return 1; +} + +static int __init ssd_finject(char *str) +{ + finject = (int)simple_strtoul(str, NULL, 0); + + return 1; +} + +__setup(MODULE_NAME"_mode=", ssd_drv_mode); +__setup(MODULE_NAME"_status_mask=", ssd_status_mask); +__setup(MODULE_NAME"_int_mode=", ssd_int_mode); +__setup(MODULE_NAME"_threaded_irq=", ssd_threaded_irq); +__setup(MODULE_NAME"_log_level=", ssd_log_level); +__setup(MODULE_NAME"_ot_protect=", ssd_ot_protect); +__setup(MODULE_NAME"_wmode=", ssd_wmode); +__setup(MODULE_NAME"_finject=", ssd_finject); +#endif + + +#ifdef CONFIG_PROC_FS +#include +#include + +#define SSD_PROC_DIR MODULE_NAME +#define SSD_PROC_INFO "info" + +static struct proc_dir_entry *ssd_proc_dir = NULL; +static struct proc_dir_entry *ssd_proc_info = NULL; + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,2,0)) +static int ssd_proc_read(char *page, char **start, + off_t off, int count, int *eof, void *data) +{ + struct ssd_device *dev = NULL; + struct ssd_device *n = NULL; + uint64_t size; + int idx; + int len = 0; + //char type; //xx + + if (ssd_exiting) { + return 0; + } + + len += snprintf((page + len), (count - len), "Driver Version:\t%s\n", DRIVER_VERSION); + + list_for_each_entry_safe(dev, n, &ssd_list, list) { + idx = dev->idx + 1; + size = dev->hw_info.size ; + do_div(size, 1000000000); + + len += snprintf((page + len), (count - len), "\n"); + + len += snprintf((page + len), (count - len), "HIO %d Size:\t%uGB\n", idx, (uint32_t)size); + + len += snprintf((page + len), (count - len), "HIO %d Bridge FW VER:\t%03X\n", idx, dev->hw_info.bridge_ver); + if (dev->hw_info.ctrl_ver != 0) { + len += snprintf((page + len), (count - len), "HIO %d Controller FW VER:\t%03X\n", idx, dev->hw_info.ctrl_ver); + } + + len += snprintf((page + len), (count - len), "HIO %d PCB VER:\t.%c\n", idx, dev->hw_info.pcb_ver); + + if (dev->hw_info.upper_pcb_ver >= 'A') { + len += snprintf((page + len), (count - len), "HIO %d Upper PCB VER:\t.%c\n", idx, dev->hw_info.upper_pcb_ver); + } + + len += snprintf((page + len), (count - len), "HIO %d Device:\t%s\n", idx, dev->name); + } + + return len; +} + +#else + +static int ssd_proc_show(struct seq_file *m, void *v) +{ + struct ssd_device *dev = NULL; + struct ssd_device *n = NULL; + uint64_t size; + int idx; + + if (ssd_exiting) { + return 0; + } + + seq_printf(m, "Driver Version:\t%s\n", DRIVER_VERSION); + + list_for_each_entry_safe(dev, n, &ssd_list, list) { + idx = dev->idx + 1; + size = dev->hw_info.size ; + do_div(size, 1000000000); + + seq_printf(m, "\n"); + + seq_printf(m, "HIO %d Size:\t%uGB\n", idx, (uint32_t)size); + + seq_printf(m, "HIO %d Bridge FW VER:\t%03X\n", idx, dev->hw_info.bridge_ver); + if (dev->hw_info.ctrl_ver != 0) { + seq_printf(m, "HIO %d Controller FW VER:\t%03X\n", idx, dev->hw_info.ctrl_ver); + } + + seq_printf(m, "HIO %d PCB VER:\t.%c\n", idx, dev->hw_info.pcb_ver); + + if (dev->hw_info.upper_pcb_ver >= 'A') { + seq_printf(m, "HIO %d Upper PCB VER:\t.%c\n", idx, dev->hw_info.upper_pcb_ver); + } + + seq_printf(m, "HIO %d Device:\t%s\n", idx, dev->name); + } + + return 0; +} + +static int ssd_proc_open(struct inode *inode, struct file *file) +{ +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(3,9,0)) + return single_open(file, ssd_proc_show, PDE(inode)->data); +#else + return single_open(file, ssd_proc_show, PDE_DATA(inode)); +#endif +} + +static const struct file_operations ssd_proc_fops = { + .open = ssd_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + + +static void ssd_cleanup_proc(void) +{ + if (ssd_proc_info) { + remove_proc_entry(SSD_PROC_INFO, ssd_proc_dir); + ssd_proc_info = NULL; + } + if (ssd_proc_dir) { + remove_proc_entry(SSD_PROC_DIR, NULL); + ssd_proc_dir = NULL; + } +} +static int ssd_init_proc(void) +{ + ssd_proc_dir = proc_mkdir(SSD_PROC_DIR, NULL); + if (!ssd_proc_dir) + goto out_proc_mkdir; + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,2,0)) + ssd_proc_info = create_proc_entry(SSD_PROC_INFO, S_IFREG | S_IRUGO | S_IWUSR, ssd_proc_dir); + if (!ssd_proc_info) + goto out_create_proc_entry; + + ssd_proc_info->read_proc = ssd_proc_read; + +/* kernel bug */ +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,30)) + ssd_proc_info->owner = THIS_MODULE; +#endif +#else + ssd_proc_info = proc_create(SSD_PROC_INFO, 0600, ssd_proc_dir, &ssd_proc_fops); + if (!ssd_proc_info) + goto out_create_proc_entry; +#endif + + return 0; + +out_create_proc_entry: + remove_proc_entry(SSD_PROC_DIR, NULL); +out_proc_mkdir: + return -ENOMEM; +} + +#else +static void ssd_cleanup_proc(void) +{ + return; +} +static int ssd_init_proc(void) +{ + return 0; +} +#endif /* CONFIG_PROC_FS */ + +/* sysfs */ +static void ssd_unregister_sysfs(struct ssd_device *dev) +{ + return; +} + +static int ssd_register_sysfs(struct ssd_device *dev) +{ + return 0; +} + +static void ssd_cleanup_sysfs(void) +{ + return; +} + +static int ssd_init_sysfs(void) +{ + return 0; +} + +static inline void ssd_put_index(int slave, int index) +{ + unsigned long *index_bits = ssd_index_bits; + + if (slave) { + index_bits = ssd_index_bits_sl; + } + + if (test_and_clear_bit(index, index_bits)) { + atomic_dec(&ssd_nr); + } +} + +static inline int ssd_get_index(int slave) +{ + unsigned long *index_bits = ssd_index_bits; + int index; + + if (slave) { + index_bits = ssd_index_bits_sl; + } + +find_index: + if ((index = find_first_zero_bit(index_bits, SSD_MAX_DEV)) >= SSD_MAX_DEV) { + return -1; + } + + if (test_and_set_bit(index, index_bits)) { + goto find_index; + } + + atomic_inc(&ssd_nr); + + return index; +} + +static void ssd_cleanup_index(void) +{ + return; +} + +static int ssd_init_index(void) +{ + INIT_LIST_HEAD(&ssd_list); + atomic_set(&ssd_nr, 0); + memset(ssd_index_bits, 0, (SSD_MAX_DEV / BITS_PER_LONG + 1)); + memset(ssd_index_bits_sl, 0, (SSD_MAX_DEV / BITS_PER_LONG + 1)); + + return 0; +} + +static void ssd_set_dev_name(char *name, size_t size, int idx) +{ + if(idx < SSD_ALPHABET_NUM) { + snprintf(name, size, "%c", 'a'+idx); + } else { + idx -= SSD_ALPHABET_NUM; + snprintf(name, size, "%c%c", 'a'+(idx/SSD_ALPHABET_NUM), 'a'+(idx%SSD_ALPHABET_NUM)); + } +} + +/* pci register r&w */ +static inline void ssd_reg_write(void *addr, uint64_t val) +{ + iowrite32((uint32_t)val, addr); + iowrite32((uint32_t)(val >> 32), addr + 4); + wmb(); +} + +static inline uint64_t ssd_reg_read(void *addr) +{ + uint64_t val; + uint32_t val_lo, val_hi; + + val_lo = ioread32(addr); + val_hi = ioread32(addr + 4); + + rmb(); + val = val_lo | ((uint64_t)val_hi << 32); + + return val; +} + + +#define ssd_reg32_write(addr, val) writel(val, addr) +#define ssd_reg32_read(addr) readl(addr) + +/* alarm led */ +static void ssd_clear_alarm(struct ssd_device *dev) +{ + uint32_t val; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_LED_REG); + + /* firmware control */ + val &= ~0x2; + + ssd_reg32_write(dev->ctrlp + SSD_LED_REG, val); +} + +static void ssd_set_alarm(struct ssd_device *dev) +{ + uint32_t val; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_LED_REG); + + /* light up */ + val &= ~0x1; + /* software control */ + val |= 0x2; + + ssd_reg32_write(dev->ctrlp + SSD_LED_REG, val); +} + +#define u32_swap(x) \ + ((uint32_t)( \ + (((uint32_t)(x) & (uint32_t)0x000000ffUL) << 24) | \ + (((uint32_t)(x) & (uint32_t)0x0000ff00UL) << 8) | \ + (((uint32_t)(x) & (uint32_t)0x00ff0000UL) >> 8) | \ + (((uint32_t)(x) & (uint32_t)0xff000000UL) >> 24))) + +#define u16_swap(x) \ + ((uint16_t)( \ + (((uint16_t)(x) & (uint16_t)0x00ff) << 8) | \ + (((uint16_t)(x) & (uint16_t)0xff00) >> 8) )) + + +#if 0 +/* No lock, for init only*/ +static int ssd_spi_read_id(struct ssd_device *dev, uint32_t *id) +{ + uint32_t val; + unsigned long st; + int ret = 0; + + if (!dev || !id) { + return -EINVAL; + } + + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_READ_ID); + + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + + st = jiffies; + for (;;) { + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + if (val == 0x1000000) { + break; + } + + if (time_after(jiffies, (st + SSD_SPI_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } + + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_ID); + *id = val; + +out: + return ret; +} +#endif + +/* spi access */ +static int ssd_init_spi(struct ssd_device *dev) +{ + uint32_t val; + unsigned long st; + int ret = 0; + + mutex_lock(&dev->spi_mutex); + st = jiffies; + for(;;) { + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_READ_STATUS); + + do { + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + + if (time_after(jiffies, (st + SSD_SPI_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } while (val != 0x1000000); + + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_STATUS); + if (!(val & 0x1)) { + break; + } + + if (time_after(jiffies, (st + SSD_SPI_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } + +out: + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + if (val & 0x1) { + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_CLSR); + } + } + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_W_DISABLE); + mutex_unlock(&dev->spi_mutex); + + ret = 0; + + return ret; +} + +static int ssd_spi_page_read(struct ssd_device *dev, void *buf, uint32_t off, uint32_t size) +{ + uint32_t val; + uint32_t rlen = 0; + unsigned long st; + int ret = 0; + + if (!dev || !buf) { + return -EINVAL; + } + + if ((off % sizeof(uint32_t)) != 0 || (size % sizeof(uint32_t)) != 0 || size == 0 || + ((uint64_t)off + (uint64_t)size) > dev->rom_info.size || size > dev->rom_info.page_size) { + return -EINVAL; + } + + mutex_lock(&dev->spi_mutex); + while (rlen < size) { + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD_HI, ((off + rlen) >> 24)); + wmb(); + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, (((off + rlen) << 8) | SSD_SPI_CMD_READ)); + + (void)ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + (void)ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + (void)ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + (void)ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + + st = jiffies; + for (;;) { + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + if (val == 0x1000000) { + break; + } + + if (time_after(jiffies, (st + SSD_SPI_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } + + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_RDATA); + *(uint32_t *)(buf + rlen)= u32_swap(val); + + rlen += sizeof(uint32_t); + } + +out: + mutex_unlock(&dev->spi_mutex); + return ret; +} + +static int ssd_spi_page_write(struct ssd_device *dev, void *buf, uint32_t off, uint32_t size) +{ + uint32_t val; + uint32_t wlen; + unsigned long st; + int i; + int ret = 0; + + if (!dev || !buf) { + return -EINVAL; + } + + if ((off % sizeof(uint32_t)) != 0 || (size % sizeof(uint32_t)) != 0 || size == 0 || + ((uint64_t)off + (uint64_t)size) > dev->rom_info.size || size > dev->rom_info.page_size || + (off / dev->rom_info.page_size) != ((off + size - 1) / dev->rom_info.page_size)) { + return -EINVAL; + } + + mutex_lock(&dev->spi_mutex); + + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_W_ENABLE); + + wlen = size / sizeof(uint32_t); + for (i=0; i<(int)wlen; i++) { + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_WDATA, u32_swap(*((uint32_t *)buf + i))); + } + + wmb(); + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD_HI, (off >> 24)); + wmb(); + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, ((off << 8) | SSD_SPI_CMD_PROGRAM)); + + udelay(1); + + st = jiffies; + for (;;) { + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_READ_STATUS); + do { + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + + if (time_after(jiffies, (st + SSD_SPI_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } while (val != 0x1000000); + + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_STATUS); + if (!(val & 0x1)) { + break; + } + + if (time_after(jiffies, (st + SSD_SPI_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } + + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + if ((val >> 6) & 0x1) { + ret = -EIO; + goto out; + } + } + +out: + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + if (val & 0x1) { + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_CLSR); + } + } + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_W_DISABLE); + + mutex_unlock(&dev->spi_mutex); + + return ret; +} + +static int ssd_spi_block_erase(struct ssd_device *dev, uint32_t off) +{ + uint32_t val; + unsigned long st; + int ret = 0; + + if (!dev) { + return -EINVAL; + } + + if ((off % dev->rom_info.block_size) != 0 || off >= dev->rom_info.size) { + return -EINVAL; + } + + mutex_lock(&dev->spi_mutex); + + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_W_ENABLE); + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_W_ENABLE); + + wmb(); + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD_HI, (off >> 24)); + wmb(); + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, ((off << 8) | SSD_SPI_CMD_ERASE)); + + st = jiffies; + for (;;) { + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_READ_STATUS); + + do { + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_READY); + + if (time_after(jiffies, (st + SSD_SPI_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } while (val != 0x1000000); + + val = ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_STATUS); + if (!(val & 0x1)) { + break; + } + + if (time_after(jiffies, (st + SSD_SPI_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } + + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + if ((val >> 5) & 0x1) { + ret = -EIO; + goto out; + } + } + +out: + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + if (val & 0x1) { + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_CLSR); + } + } + ssd_reg32_write(dev->ctrlp + SSD_SPI_REG_CMD, SSD_SPI_CMD_W_DISABLE); + + mutex_unlock(&dev->spi_mutex); + + return ret; +} + +static int ssd_spi_read(struct ssd_device *dev, void *buf, uint32_t off, uint32_t size) +{ + uint32_t len = 0; + uint32_t roff; + uint32_t rsize; + int ret = 0; + + if (!dev || !buf) { + return -EINVAL; + } + + if ((off % sizeof(uint32_t)) != 0 || (size % sizeof(uint32_t)) != 0 || size == 0 || + ((uint64_t)off + (uint64_t)size) > dev->rom_info.size) { + return -EINVAL; + } + + while (len < size) { + roff = (off + len) % dev->rom_info.page_size; + rsize = dev->rom_info.page_size - roff; + if ((size - len) < rsize) { + rsize = (size - len); + } + roff = off + len; + + ret = ssd_spi_page_read(dev, (buf + len), roff, rsize); + if (ret) { + goto out; + } + + len += rsize; + + cond_resched(); + } + +out: + return ret; +} + +static int ssd_spi_write(struct ssd_device *dev, void *buf, uint32_t off, uint32_t size) +{ + uint32_t len = 0; + uint32_t woff; + uint32_t wsize; + int ret = 0; + + if (!dev || !buf) { + return -EINVAL; + } + + if ((off % sizeof(uint32_t)) != 0 || (size % sizeof(uint32_t)) != 0 || size == 0 || + ((uint64_t)off + (uint64_t)size) > dev->rom_info.size) { + return -EINVAL; + } + + while (len < size) { + woff = (off + len) % dev->rom_info.page_size; + wsize = dev->rom_info.page_size - woff; + if ((size - len) < wsize) { + wsize = (size - len); + } + woff = off + len; + + ret = ssd_spi_page_write(dev, (buf + len), woff, wsize); + if (ret) { + goto out; + } + + len += wsize; + + cond_resched(); + } + +out: + return ret; +} + +static int ssd_spi_erase(struct ssd_device *dev, uint32_t off, uint32_t size) +{ + uint32_t len = 0; + uint32_t eoff; + int ret = 0; + + if (!dev) { + return -EINVAL; + } + + if (size == 0 || ((uint64_t)off + (uint64_t)size) > dev->rom_info.size || + (off % dev->rom_info.block_size) != 0 || (size % dev->rom_info.block_size) != 0) { + return -EINVAL; + } + + while (len < size) { + eoff = (off + len); + + ret = ssd_spi_block_erase(dev, eoff); + if (ret) { + goto out; + } + + len += dev->rom_info.block_size; + + cond_resched(); + } + +out: + return ret; +} + +/* i2c access */ +static uint32_t __ssd_i2c_reg32_read(void *addr) +{ + return ssd_reg32_read(addr); +} + +static void __ssd_i2c_reg32_write(void *addr, uint32_t val) +{ + ssd_reg32_write(addr, val); + ssd_reg32_read(addr); +} + +static int __ssd_i2c_clear(struct ssd_device *dev, uint8_t saddr) +{ + ssd_i2c_ctrl_t ctrl; + ssd_i2c_data_t data; + uint8_t status = 0; + int nr_data = 0; + unsigned long st; + int ret = 0; + +check_status: + ctrl.bits.wdata = 0; + ctrl.bits.addr = SSD_I2C_STATUS_REG; + ctrl.bits.rw = SSD_I2C_CTRL_READ; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + st = jiffies; + for (;;) { + data.val = __ssd_i2c_reg32_read(dev->ctrlp + SSD_I2C_RDATA_REG); + if (data.bits.valid == 0) { + break; + } + + /* retry */ + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } + status = data.bits.rdata; + + if (!(status & 0x4)) { + /* clear read fifo data */ + ctrl.bits.wdata = 0; + ctrl.bits.addr = SSD_I2C_DATA_REG; + ctrl.bits.rw = SSD_I2C_CTRL_READ; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + st = jiffies; + for (;;) { + data.val = __ssd_i2c_reg32_read(dev->ctrlp + SSD_I2C_RDATA_REG); + if (data.bits.valid == 0) { + break; + } + + /* retry */ + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out; + } + cond_resched(); + } + + nr_data++; + if (nr_data <= SSD_I2C_MAX_DATA) { + goto check_status; + } else { + goto out_reset; + } + } + + if (status & 0x3) { + /* clear int */ + ctrl.bits.wdata = 0x04; + ctrl.bits.addr = SSD_I2C_CMD_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + } + + if (!(status & 0x8)) { +out_reset: + /* reset i2c controller */ + ctrl.bits.wdata = 0x0; + ctrl.bits.addr = SSD_I2C_RESET_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + } + +out: + return ret; +} + +static int ssd_i2c_write(struct ssd_device *dev, uint8_t saddr, uint8_t size, uint8_t *buf) +{ + ssd_i2c_ctrl_t ctrl; + ssd_i2c_data_t data; + uint8_t off = 0; + uint8_t status = 0; + unsigned long st; + int ret = 0; + + mutex_lock(&dev->i2c_mutex); + + ctrl.val = 0; + + /* slave addr */ + ctrl.bits.wdata = saddr; + ctrl.bits.addr = SSD_I2C_SADDR_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + /* data */ + while (off < size) { + ctrl.bits.wdata = buf[off]; + ctrl.bits.addr = SSD_I2C_DATA_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + off++; + } + + /* write */ + ctrl.bits.wdata = 0x01; + ctrl.bits.addr = SSD_I2C_CMD_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + /* wait */ + st = jiffies; + for (;;) { + ctrl.bits.wdata = 0; + ctrl.bits.addr = SSD_I2C_STATUS_REG; + ctrl.bits.rw = SSD_I2C_CTRL_READ; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + for (;;) { + data.val = __ssd_i2c_reg32_read(dev->ctrlp + SSD_I2C_RDATA_REG); + if (data.bits.valid == 0) { + break; + } + + /* retry */ + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out_clear; + } + cond_resched(); + } + + status = data.bits.rdata; + if (status & 0x1) { + break; + } + + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out_clear; + } + cond_resched(); + } + + if (!(status & 0x1)) { + ret = -1; + goto out_clear; + } + + /* busy ? */ + if (status & 0x20) { + ret = -2; + goto out_clear; + } + + /* ack ? */ + if (status & 0x10) { + ret = -3; + goto out_clear; + } + + /* clear */ +out_clear: + if (__ssd_i2c_clear(dev, saddr)) { + if (!ret) ret = -4; + } + + mutex_unlock(&dev->i2c_mutex); + + return ret; +} + +static int ssd_i2c_read(struct ssd_device *dev, uint8_t saddr, uint8_t size, uint8_t *buf) +{ + ssd_i2c_ctrl_t ctrl; + ssd_i2c_data_t data; + uint8_t off = 0; + uint8_t status = 0; + unsigned long st; + int ret = 0; + + mutex_lock(&dev->i2c_mutex); + + ctrl.val = 0; + + /* slave addr */ + ctrl.bits.wdata = saddr; + ctrl.bits.addr = SSD_I2C_SADDR_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + /* read len */ + ctrl.bits.wdata = size; + ctrl.bits.addr = SSD_I2C_LEN_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + /* read */ + ctrl.bits.wdata = 0x02; + ctrl.bits.addr = SSD_I2C_CMD_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + /* wait */ + st = jiffies; + for (;;) { + ctrl.bits.wdata = 0; + ctrl.bits.addr = SSD_I2C_STATUS_REG; + ctrl.bits.rw = SSD_I2C_CTRL_READ; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + for (;;) { + data.val = __ssd_i2c_reg32_read(dev->ctrlp + SSD_I2C_RDATA_REG); + if (data.bits.valid == 0) { + break; + } + + /* retry */ + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out_clear; + } + cond_resched(); + } + + status = data.bits.rdata; + if (status & 0x2) { + break; + } + + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out_clear; + } + cond_resched(); + } + + if (!(status & 0x2)) { + ret = -1; + goto out_clear; + } + + /* busy ? */ + if (status & 0x20) { + ret = -2; + goto out_clear; + } + + /* ack ? */ + if (status & 0x10) { + ret = -3; + goto out_clear; + } + + /* data */ + while (off < size) { + ctrl.bits.wdata = 0; + ctrl.bits.addr = SSD_I2C_DATA_REG; + ctrl.bits.rw = SSD_I2C_CTRL_READ; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + st = jiffies; + for (;;) { + data.val = __ssd_i2c_reg32_read(dev->ctrlp + SSD_I2C_RDATA_REG); + if (data.bits.valid == 0) { + break; + } + + /* retry */ + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out_clear; + } + cond_resched(); + } + + buf[off] = data.bits.rdata; + + off++; + } + + /* clear */ +out_clear: + if (__ssd_i2c_clear(dev, saddr)) { + if (!ret) ret = -4; + } + + mutex_unlock(&dev->i2c_mutex); + + return ret; +} + +static int ssd_i2c_write_read(struct ssd_device *dev, uint8_t saddr, uint8_t wsize, uint8_t *wbuf, uint8_t rsize, uint8_t *rbuf) +{ + ssd_i2c_ctrl_t ctrl; + ssd_i2c_data_t data; + uint8_t off = 0; + uint8_t status = 0; + unsigned long st; + int ret = 0; + + mutex_lock(&dev->i2c_mutex); + + ctrl.val = 0; + + /* slave addr */ + ctrl.bits.wdata = saddr; + ctrl.bits.addr = SSD_I2C_SADDR_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + /* data */ + off = 0; + while (off < wsize) { + ctrl.bits.wdata = wbuf[off]; + ctrl.bits.addr = SSD_I2C_DATA_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + off++; + } + + /* read len */ + ctrl.bits.wdata = rsize; + ctrl.bits.addr = SSD_I2C_LEN_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + /* write -> read */ + ctrl.bits.wdata = 0x03; + ctrl.bits.addr = SSD_I2C_CMD_REG; + ctrl.bits.rw = SSD_I2C_CTRL_WRITE; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + /* wait */ + st = jiffies; + for (;;) { + ctrl.bits.wdata = 0; + ctrl.bits.addr = SSD_I2C_STATUS_REG; + ctrl.bits.rw = SSD_I2C_CTRL_READ; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + for (;;) { + data.val = __ssd_i2c_reg32_read(dev->ctrlp + SSD_I2C_RDATA_REG); + if (data.bits.valid == 0) { + break; + } + + /* retry */ + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out_clear; + } + cond_resched(); + } + + status = data.bits.rdata; + if (status & 0x2) { + break; + } + + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out_clear; + } + cond_resched(); + } + + if (!(status & 0x2)) { + ret = -1; + goto out_clear; + } + + /* busy ? */ + if (status & 0x20) { + ret = -2; + goto out_clear; + } + + /* ack ? */ + if (status & 0x10) { + ret = -3; + goto out_clear; + } + + /* data */ + off = 0; + while (off < rsize) { + ctrl.bits.wdata = 0; + ctrl.bits.addr = SSD_I2C_DATA_REG; + ctrl.bits.rw = SSD_I2C_CTRL_READ; + __ssd_i2c_reg32_write(dev->ctrlp + SSD_I2C_CTRL_REG, ctrl.val); + + st = jiffies; + for (;;) { + data.val = __ssd_i2c_reg32_read(dev->ctrlp + SSD_I2C_RDATA_REG); + if (data.bits.valid == 0) { + break; + } + + /* retry */ + if (time_after(jiffies, (st + SSD_I2C_TIMEOUT))) { + ret = -ETIMEDOUT; + goto out_clear; + } + cond_resched(); + } + + rbuf[off] = data.bits.rdata; + + off++; + } + + /* clear */ +out_clear: + if (__ssd_i2c_clear(dev, saddr)) { + if (!ret) ret = -4; + } + mutex_unlock(&dev->i2c_mutex); + + return ret; +} + +static int ssd_smbus_send_byte(struct ssd_device *dev, uint8_t saddr, uint8_t *buf) +{ + int i = 0; + int ret = 0; + + for (;;) { + ret = ssd_i2c_write(dev, saddr, 1, buf); + if (!ret || -ETIMEDOUT == ret) { + break; + } + + i++; + if (i >= SSD_SMBUS_RETRY_MAX) { + break; + } + msleep(SSD_SMBUS_RETRY_INTERVAL); + } + + return ret; +} + +static int ssd_smbus_receive_byte(struct ssd_device *dev, uint8_t saddr, uint8_t *buf) +{ + int i = 0; + int ret = 0; + + for (;;) { + ret = ssd_i2c_read(dev, saddr, 1, buf); + if (!ret || -ETIMEDOUT == ret) { + break; + } + + i++; + if (i >= SSD_SMBUS_RETRY_MAX) { + break; + } + msleep(SSD_SMBUS_RETRY_INTERVAL); + } + + return ret; +} + +static int ssd_smbus_write_byte(struct ssd_device *dev, uint8_t saddr, uint8_t cmd, uint8_t *buf) +{ + uint8_t smb_data[SSD_SMBUS_DATA_MAX] = {0}; + int i = 0; + int ret = 0; + + smb_data[0] = cmd; + memcpy((smb_data + 1), buf, 1); + + for (;;) { + ret = ssd_i2c_write(dev, saddr, 2, smb_data); + if (!ret || -ETIMEDOUT == ret) { + break; + } + + i++; + if (i >= SSD_SMBUS_RETRY_MAX) { + break; + } + msleep(SSD_SMBUS_RETRY_INTERVAL); + } + + return ret; +} + +static int ssd_smbus_read_byte(struct ssd_device *dev, uint8_t saddr, uint8_t cmd, uint8_t *buf) +{ + uint8_t smb_data[SSD_SMBUS_DATA_MAX] = {0}; + int i = 0; + int ret = 0; + + smb_data[0] = cmd; + + for (;;) { + ret = ssd_i2c_write_read(dev, saddr, 1, smb_data, 1, buf); + if (!ret || -ETIMEDOUT == ret) { + break; + } + + i++; + if (i >= SSD_SMBUS_RETRY_MAX) { + break; + } + msleep(SSD_SMBUS_RETRY_INTERVAL); + } + + return ret; +} + +static int ssd_smbus_write_word(struct ssd_device *dev, uint8_t saddr, uint8_t cmd, uint8_t *buf) +{ + uint8_t smb_data[SSD_SMBUS_DATA_MAX] = {0}; + int i = 0; + int ret = 0; + + smb_data[0] = cmd; + memcpy((smb_data + 1), buf, 2); + + for (;;) { + ret = ssd_i2c_write(dev, saddr, 3, smb_data); + if (!ret || -ETIMEDOUT == ret) { + break; + } + + i++; + if (i >= SSD_SMBUS_RETRY_MAX) { + break; + } + msleep(SSD_SMBUS_RETRY_INTERVAL); + } + + return ret; +} + +static int ssd_smbus_read_word(struct ssd_device *dev, uint8_t saddr, uint8_t cmd, uint8_t *buf) +{ + uint8_t smb_data[SSD_SMBUS_DATA_MAX] = {0}; + int i = 0; + int ret = 0; + + smb_data[0] = cmd; + + for (;;) { + ret = ssd_i2c_write_read(dev, saddr, 1, smb_data, 2, buf); + if (!ret || -ETIMEDOUT == ret) { + break; + } + + i++; + if (i >= SSD_SMBUS_RETRY_MAX) { + break; + } + msleep(SSD_SMBUS_RETRY_INTERVAL); + } + + return ret; +} + +static int ssd_smbus_write_block(struct ssd_device *dev, uint8_t saddr, uint8_t cmd, uint8_t size, uint8_t *buf) +{ + uint8_t smb_data[SSD_SMBUS_DATA_MAX] = {0}; + int i = 0; + int ret = 0; + + smb_data[0] = cmd; + smb_data[1] = size; + memcpy((smb_data + 2), buf, size); + + for (;;) { + ret = ssd_i2c_write(dev, saddr, (2 + size), smb_data); + if (!ret || -ETIMEDOUT == ret) { + break; + } + + i++; + if (i >= SSD_SMBUS_RETRY_MAX) { + break; + } + msleep(SSD_SMBUS_RETRY_INTERVAL); + } + + return ret; +} + +static int ssd_smbus_read_block(struct ssd_device *dev, uint8_t saddr, uint8_t cmd, uint8_t size, uint8_t *buf) +{ + uint8_t smb_data[SSD_SMBUS_DATA_MAX] = {0}; + uint8_t rsize; + int i = 0; + int ret = 0; + + smb_data[0] = cmd; + + for (;;) { + ret = ssd_i2c_write_read(dev, saddr, 1, smb_data, (SSD_SMBUS_BLOCK_MAX + 1), (smb_data + 1)); + if (!ret || -ETIMEDOUT == ret) { + break; + } + + i++; + if (i >= SSD_SMBUS_RETRY_MAX) { + break; + } + msleep(SSD_SMBUS_RETRY_INTERVAL); + } + if (ret) { + return ret; + } + + rsize = smb_data[1]; + + if (rsize > size ) { + rsize = size; + } + + memcpy(buf, (smb_data + 2), rsize); + + return 0; +} + + +static int ssd_gen_swlog(struct ssd_device *dev, uint16_t event, uint32_t data); + +/* sensor */ +static int ssd_init_lm75(struct ssd_device *dev, uint8_t saddr) +{ + uint8_t conf = 0; + int ret = 0; + + ret = ssd_smbus_read_byte(dev, saddr, SSD_LM75_REG_CONF, &conf); + if (ret) { + goto out; + } + + conf &= (uint8_t)(~1u); + + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM75_REG_CONF, &conf); + if (ret) { + goto out; + } + +out: + return ret; +} + +static int ssd_lm75_read(struct ssd_device *dev, uint8_t saddr, uint16_t *data) +{ + uint16_t val = 0; + int ret; + + ret = ssd_smbus_read_word(dev, saddr, SSD_LM75_REG_TEMP, (uint8_t *)&val); + if (ret) { + return ret; + } + + *data = u16_swap(val); + + return 0; +} + +static int ssd_init_lm80(struct ssd_device *dev, uint8_t saddr) +{ + uint8_t val; + uint8_t low, high; + int i; + int ret = 0; + + /* init */ + val = 0x80; + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_CONFIG, &val); + if (ret) { + goto out; + } + + /* 11-bit temp */ + val = 0x08; + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_RES, &val); + if (ret) { + goto out; + } + + /* set volt limit */ + for (i=0; ihw_info.nr_ctrl <= 1 && SSD_LM80_IN_1V2 == i) { + high = 0xFF; + low = 0; + } + + /* high limit */ + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_IN_MAX(i), &high); + if (ret) { + goto out; + } + + /* low limit*/ + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_IN_MIN(i), &low); + if (ret) { + goto out; + } + } + + /* set interrupt mask: allow volt in interrupt except cap in*/ + val = 0x81; + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_MASK1, &val); + if (ret) { + goto out; + } + + /* set interrupt mask: disable others */ + val = 0xFF; + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_MASK2, &val); + if (ret) { + goto out; + } + + /* start */ + val = 0x03; + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_CONFIG, &val); + if (ret) { + goto out; + } + +out: + return ret; +} + +static int ssd_lm80_enable_in(struct ssd_device *dev, uint8_t saddr, int idx) +{ + uint8_t val = 0; + int ret = 0; + + if (idx >= SSD_LM80_IN_NR || idx < 0) { + return -EINVAL; + } + + ret = ssd_smbus_read_byte(dev, saddr, SSD_LM80_REG_MASK1, &val); + if (ret) { + goto out; + } + + val &= ~(1UL << (uint32_t)idx); + + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_MASK1, &val); + if (ret) { + goto out; + } + +out: + return ret; +} + +static int ssd_lm80_disable_in(struct ssd_device *dev, uint8_t saddr, int idx) +{ + uint8_t val = 0; + int ret = 0; + + if (idx >= SSD_LM80_IN_NR || idx < 0) { + return -EINVAL; + } + + ret = ssd_smbus_read_byte(dev, saddr, SSD_LM80_REG_MASK1, &val); + if (ret) { + goto out; + } + + val |= (1UL << (uint32_t)idx); + + ret = ssd_smbus_write_byte(dev, saddr, SSD_LM80_REG_MASK1, &val); + if (ret) { + goto out; + } + +out: + return ret; +} + +static int ssd_lm80_read_temp(struct ssd_device *dev, uint8_t saddr, uint16_t *data) +{ + uint16_t val = 0; + int ret; + + ret = ssd_smbus_read_word(dev, saddr, SSD_LM80_REG_TEMP, (uint8_t *)&val); + if (ret) { + return ret; + } + + *data = u16_swap(val); + + return 0; +} + +static int ssd_lm80_check_event(struct ssd_device *dev, uint8_t saddr) +{ + uint32_t volt; + uint16_t val = 0, status; + uint8_t alarm1 = 0, alarm2 = 0; + int i; + int ret = 0; + + /* read interrupt status to clear interrupt */ + ret = ssd_smbus_read_byte(dev, saddr, SSD_LM80_REG_ALARM1, &alarm1); + if (ret) { + goto out; + } + + ret = ssd_smbus_read_byte(dev, saddr, SSD_LM80_REG_ALARM2, &alarm2); + if (ret) { + goto out; + } + + status = (uint16_t)alarm1 | ((uint16_t)alarm2 << 8); + + /* parse inetrrupt status */ + for (i=0; i> (uint32_t)i) & 0x1)) { + if (test_and_clear_bit(SSD_HWMON_LM80(i), &dev->hwmon)) { + /* enable INx irq */ + ret = ssd_lm80_enable_in(dev, saddr, i); + if (ret) { + goto out; + } + } + + continue; + } + + /* disable INx irq */ + ret = ssd_lm80_disable_in(dev, saddr, i); + if (ret) { + goto out; + } + + if (test_and_set_bit(SSD_HWMON_LM80(i), &dev->hwmon)) { + continue; + } + + ret = ssd_smbus_read_word(dev, saddr, SSD_LM80_REG_IN(i), (uint8_t *)&val); + if (ret) { + goto out; + } + + volt = SSD_LM80_CONVERT_VOLT(u16_swap(val)); + + switch (i) { + case SSD_LM80_IN_CAP: { + if (0 == volt) { + ssd_gen_swlog(dev, SSD_LOG_CAP_SHORT_CIRCUIT, 0); + } else { + ssd_gen_swlog(dev, SSD_LOG_CAP_VOLT_FAULT, SSD_PL_CAP_VOLT(volt)); + } + break; + } + + case SSD_LM80_IN_1V2: + case SSD_LM80_IN_1V2a: + case SSD_LM80_IN_1V5: + case SSD_LM80_IN_1V8: { + ssd_gen_swlog(dev, SSD_LOG_VOLT_STATUS, SSD_VOLT_LOG_DATA(i, 0, volt)); + break; + } + case SSD_LM80_IN_FPGA_3V3: + case SSD_LM80_IN_3V3: { + ssd_gen_swlog(dev, SSD_LOG_VOLT_STATUS, SSD_VOLT_LOG_DATA(i, 0, SSD_LM80_3V3_VOLT(volt))); + break; + } + default: + break; + } + } + +out: + if (ret) { + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, (uint32_t)saddr); + } + } else { + test_and_clear_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon); + } + return ret; +} + +static int ssd_init_sensor(struct ssd_device *dev) +{ + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + goto out; + } + + ret = ssd_init_lm75(dev, SSD_SENSOR_LM75_SADDRESS); + if (ret) { + hio_warn("%s: init lm75 failed\n", dev->name); + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM75), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, SSD_SENSOR_LM75_SADDRESS); + } + goto out; + } + + if (dev->hw_info.pcb_ver >= 'B' || dev->hw_info_ext.form_factor == SSD_FORM_FACTOR_HHHL) { + ret = ssd_init_lm80(dev, SSD_SENSOR_LM80_SADDRESS); + if (ret) { + hio_warn("%s: init lm80 failed\n", dev->name); + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, SSD_SENSOR_LM80_SADDRESS); + } + goto out; + } + } + +out: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +/* board volt */ +static int ssd_mon_boardvolt(struct ssd_device *dev) +{ + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + return 0; + } + + if (dev->hw_info_ext.form_factor == SSD_FORM_FACTOR_FHHL && dev->hw_info.pcb_ver < 'B') { + return 0; + } + + return ssd_lm80_check_event(dev, SSD_SENSOR_LM80_SADDRESS); +} + +/* temperature */ +static int ssd_mon_temp(struct ssd_device *dev) +{ + int cur; + uint16_t val = 0; + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + return 0; + } + + if (dev->hw_info_ext.form_factor == SSD_FORM_FACTOR_FHHL && dev->hw_info.pcb_ver < 'B') { + return 0; + } + + /* inlet */ + ret = ssd_lm80_read_temp(dev, SSD_SENSOR_LM80_SADDRESS, &val); + if (ret) { + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, SSD_SENSOR_LM80_SADDRESS); + } + goto out; + } + test_and_clear_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon); + + cur = SSD_SENSOR_CONVERT_TEMP(val); + if (cur >= SSD_INLET_OT_TEMP) { + if (!test_and_set_bit(SSD_HWMON_TEMP(SSD_TEMP_INLET), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_INLET_OVER_TEMP, (uint32_t)cur); + } + } else if(cur < SSD_INLET_OT_HYST) { + if (test_and_clear_bit(SSD_HWMON_TEMP(SSD_TEMP_INLET), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_INLET_NORMAL_TEMP, (uint32_t)cur); + } + } + + /* flash */ + ret = ssd_lm75_read(dev, SSD_SENSOR_LM75_SADDRESS, &val); + if (ret) { + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM75), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, SSD_SENSOR_LM75_SADDRESS); + } + goto out; + } + test_and_clear_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM75), &dev->hwmon); + + cur = SSD_SENSOR_CONVERT_TEMP(val); + if (cur >= SSD_FLASH_OT_TEMP) { + if (!test_and_set_bit(SSD_HWMON_TEMP(SSD_TEMP_FLASH), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_FLASH_OVER_TEMP, (uint32_t)cur); + } + } else if(cur < SSD_FLASH_OT_HYST) { + if (test_and_clear_bit(SSD_HWMON_TEMP(SSD_TEMP_FLASH), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_FLASH_NORMAL_TEMP, (uint32_t)cur); + } + } + +out: + return ret; +} + +/* cmd tag */ +static inline void ssd_put_tag(struct ssd_device *dev, int tag) +{ + test_and_clear_bit(tag, dev->tag_map); + wake_up(&dev->tag_wq); +} + +static inline int ssd_get_tag(struct ssd_device *dev, int wait) +{ + int tag; + +find_tag: + while ((tag = find_first_zero_bit(dev->tag_map, dev->hw_info.cmd_fifo_sz)) >= atomic_read(&dev->queue_depth)) { + DEFINE_WAIT(__wait); + + if (!wait) { + return -1; + } + + prepare_to_wait_exclusive(&dev->tag_wq, &__wait, TASK_UNINTERRUPTIBLE); + schedule(); + + finish_wait(&dev->tag_wq, &__wait); + } + + if (test_and_set_bit(tag, dev->tag_map)) { + goto find_tag; + } + + return tag; +} + +static void ssd_barrier_put_tag(struct ssd_device *dev, int tag) +{ + test_and_clear_bit(tag, dev->tag_map); +} + +static int ssd_barrier_get_tag(struct ssd_device *dev) +{ + int tag = 0; + + if (test_and_set_bit(tag, dev->tag_map)) { + return -1; + } + + return tag; +} + +static void ssd_barrier_end(struct ssd_device *dev) +{ + atomic_set(&dev->queue_depth, dev->hw_info.cmd_fifo_sz); + wake_up_all(&dev->tag_wq); + + mutex_unlock(&dev->barrier_mutex); +} + +static int ssd_barrier_start(struct ssd_device *dev) +{ + int i; + + mutex_lock(&dev->barrier_mutex); + + atomic_set(&dev->queue_depth, 0); + + for (i=0; itag_map, dev->hw_info.cmd_fifo_sz) >= dev->hw_info.cmd_fifo_sz) { + return 0; + } + + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(1); + } + + atomic_set(&dev->queue_depth, dev->hw_info.cmd_fifo_sz); + wake_up_all(&dev->tag_wq); + + mutex_unlock(&dev->barrier_mutex); + + return -EBUSY; +} + +static int ssd_busy(struct ssd_device *dev) +{ + if (find_first_bit(dev->tag_map, dev->hw_info.cmd_fifo_sz) >= dev->hw_info.cmd_fifo_sz) { + return 0; + } + + return 1; +} + +static int ssd_wait_io(struct ssd_device *dev) +{ + int i; + + for (i=0; itag_map, dev->hw_info.cmd_fifo_sz) >= dev->hw_info.cmd_fifo_sz) { + return 0; + } + + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(1); + } + + return -EBUSY; +} + +#if 0 +static int ssd_in_barrier(struct ssd_device *dev) +{ + return (0 == atomic_read(&dev->queue_depth)); +} +#endif + +static void ssd_cleanup_tag(struct ssd_device *dev) +{ + kfree(dev->tag_map); +} + +static int ssd_init_tag(struct ssd_device *dev) +{ + int nr_ulongs = ALIGN(dev->hw_info.cmd_fifo_sz, BITS_PER_LONG) / BITS_PER_LONG; + + mutex_init(&dev->barrier_mutex); + + atomic_set(&dev->queue_depth, dev->hw_info.cmd_fifo_sz); + + dev->tag_map = kmalloc(nr_ulongs * sizeof(unsigned long), GFP_ATOMIC); + if (!dev->tag_map) { + return -ENOMEM; + } + + memset(dev->tag_map, 0, nr_ulongs * sizeof(unsigned long)); + + init_waitqueue_head(&dev->tag_wq); + + return 0; +} + +/* io stat */ +static void ssd_end_io_acct(struct ssd_cmd *cmd) +{ + struct ssd_device *dev = cmd->dev; + struct bio *bio = cmd->bio; + unsigned long dur = jiffies - cmd->start_time; + int rw = bio_data_dir(bio); + +#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(3,0,0)) || (defined RHEL_MAJOR && RHEL_MAJOR == 6 && RHEL_MINOR >= 7)) + int cpu = part_stat_lock(); + struct hd_struct *part = disk_map_sector_rcu(dev->gd, bio_start(bio)); + part_round_stats(cpu, part); + part_stat_add(cpu, part, ticks[rw], dur); + part_dec_in_flight(part, rw); + part_stat_unlock(); +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,27)) + int cpu = part_stat_lock(); + struct hd_struct *part = &dev->gd->part0; + part_round_stats(cpu, part); + part_stat_add(cpu, part, ticks[rw], dur); + part_stat_unlock(); + part->in_flight[rw] = atomic_dec_return(&dev->in_flight[rw]); +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,14)) + preempt_disable(); + disk_round_stats(dev->gd); + preempt_enable(); + disk_stat_add(dev->gd, ticks[rw], dur); + dev->gd->in_flight = atomic_dec_return(&dev->in_flight[0]); +#else + preempt_disable(); + disk_round_stats(dev->gd); + preempt_enable(); + if (rw == WRITE) { + disk_stat_add(dev->gd, write_ticks, dur); + } else { + disk_stat_add(dev->gd, read_ticks, dur); + } + dev->gd->in_flight = atomic_dec_return(&dev->in_flight[0]); +#endif +} + +static void ssd_start_io_acct(struct ssd_cmd *cmd) +{ + struct ssd_device *dev = cmd->dev; + struct bio *bio = cmd->bio; + int rw = bio_data_dir(bio); + +#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(3,0,0)) || (defined RHEL_MAJOR && RHEL_MAJOR == 6 && RHEL_MINOR >= 7)) + int cpu = part_stat_lock(); + struct hd_struct *part = disk_map_sector_rcu(dev->gd, bio_start(bio)); + part_round_stats(cpu, part); + part_stat_inc(cpu, part, ios[rw]); + part_stat_add(cpu, part, sectors[rw], bio_sectors(bio)); + part_inc_in_flight(part, rw); + part_stat_unlock(); +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,27)) + int cpu = part_stat_lock(); + struct hd_struct *part = &dev->gd->part0; + part_round_stats(cpu, part); + part_stat_inc(cpu, part, ios[rw]); + part_stat_add(cpu, part, sectors[rw], bio_sectors(bio)); + part_stat_unlock(); + part->in_flight[rw] = atomic_inc_return(&dev->in_flight[rw]); +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,14)) + preempt_disable(); + disk_round_stats(dev->gd); + preempt_enable(); + disk_stat_inc(dev->gd, ios[rw]); + disk_stat_add(dev->gd, sectors[rw], bio_sectors(bio)); + dev->gd->in_flight = atomic_inc_return(&dev->in_flight[0]); +#else + preempt_disable(); + disk_round_stats(dev->gd); + preempt_enable(); + if (rw == WRITE) { + disk_stat_inc(dev->gd, writes); + disk_stat_add(dev->gd, write_sectors, bio_sectors(bio)); + } else { + disk_stat_inc(dev->gd, reads); + disk_stat_add(dev->gd, read_sectors, bio_sectors(bio)); + } + dev->gd->in_flight = atomic_inc_return(&dev->in_flight[0]); +#endif + + cmd->start_time = jiffies; +} + +/* io */ +static void ssd_queue_bio(struct ssd_device *dev, struct bio *bio) +{ + spin_lock(&dev->sendq_lock); + ssd_blist_add(&dev->sendq, bio); + spin_unlock(&dev->sendq_lock); + + atomic_inc(&dev->in_sendq); + wake_up(&dev->send_waitq); +} + +static inline void ssd_end_request(struct ssd_cmd *cmd) +{ + struct ssd_device *dev = cmd->dev; + struct bio *bio = cmd->bio; + int errors = cmd->errors; + int tag = cmd->tag; + + if (bio) { +#if (defined SSD_TRIM && (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,36))) + if (!(bio->bi_rw & REQ_DISCARD)) { + ssd_end_io_acct(cmd); + if (!cmd->flag) { + pci_unmap_sg(dev->pdev, cmd->sgl, cmd->nsegs, + bio_data_dir(bio) == READ ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE); + } + } +#elif (defined SSD_TRIM && (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,32))) + if (!bio_rw_flagged(bio, BIO_RW_DISCARD)) { + ssd_end_io_acct(cmd); + if (!cmd->flag) { + pci_unmap_sg(dev->pdev, cmd->sgl, cmd->nsegs, + bio_data_dir(bio) == READ ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE); + } + } +#else + ssd_end_io_acct(cmd); + + if (!cmd->flag) { + pci_unmap_sg(dev->pdev, cmd->sgl, cmd->nsegs, + bio_data_dir(bio) == READ ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE); + } +#endif + + cmd->bio = NULL; + ssd_put_tag(dev, tag); + + if (SSD_INT_MSIX == dev->int_mode || tag < 16 || errors) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, errors); +#else + bio_endio(bio, bio->bi_size, errors); +#endif + } else /* if (bio->bi_idx >= bio->bi_vcnt)*/ { + spin_lock(&dev->doneq_lock); + ssd_blist_add(&dev->doneq, bio); + spin_unlock(&dev->doneq_lock); + + atomic_inc(&dev->in_doneq); + wake_up(&dev->done_waitq); + } + } else { + if (cmd->waiting) { + complete(cmd->waiting); + } + } +} + +static void ssd_end_timeout_request(struct ssd_cmd *cmd) +{ + struct ssd_device *dev = cmd->dev; + struct ssd_rw_msg *msg = (struct ssd_rw_msg *)cmd->msg; + int i; + + for (i=0; inr_queue; i++) { + disable_irq(dev->entry[i].vector); + } + + atomic_inc(&dev->tocnt); + //if (cmd->bio) { + hio_err("%s: cmd timeout: tag %d fun %#x\n", dev->name, msg->tag, msg->fun); + cmd->errors = -ETIMEDOUT; + ssd_end_request(cmd); + //} + + for (i=0; inr_queue; i++) { + enable_irq(dev->entry[i].vector); + } + + /* alarm led */ + ssd_set_alarm(dev); +} + +/* cmd timer */ +static void ssd_cmd_add_timer(struct ssd_cmd *cmd, int timeout, void (*complt)(struct ssd_cmd *)) +{ + init_timer(&cmd->cmd_timer); + + cmd->cmd_timer.data = (unsigned long)cmd; + cmd->cmd_timer.expires = jiffies + timeout; + cmd->cmd_timer.function = (void (*)(unsigned long)) complt; + + add_timer(&cmd->cmd_timer); +} + +static int ssd_cmd_del_timer(struct ssd_cmd *cmd) +{ + return del_timer(&cmd->cmd_timer); +} + +static void ssd_add_timer(struct timer_list *timer, int timeout, void (*complt)(void *), void *data) +{ + init_timer(timer); + + timer->data = (unsigned long)data; + timer->expires = jiffies + timeout; + timer->function = (void (*)(unsigned long)) complt; + + add_timer(timer); +} + +static int ssd_del_timer(struct timer_list *timer) +{ + return del_timer(timer); +} + +static void ssd_cmd_timeout(struct ssd_cmd *cmd) +{ + struct ssd_device *dev = cmd->dev; + uint32_t msg = *(uint32_t *)cmd->msg; + + ssd_end_timeout_request(cmd); + + ssd_gen_swlog(dev, SSD_LOG_TIMEOUT, msg); +} + + +static void __ssd_done(unsigned long data) +{ + struct ssd_cmd *cmd; + LIST_HEAD(localq); + + local_irq_disable(); +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,13,0)) + list_splice_init(&__get_cpu_var(ssd_doneq), &localq); +#else + list_splice_init(this_cpu_ptr(&ssd_doneq), &localq); +#endif + local_irq_enable(); + + while (!list_empty(&localq)) { + cmd = list_entry(localq.next, struct ssd_cmd, list); + list_del_init(&cmd->list); + + ssd_end_request(cmd); + } +} + +static void __ssd_done_db(unsigned long data) +{ + struct ssd_cmd *cmd; + struct ssd_device *dev; + struct bio *bio; + LIST_HEAD(localq); + + local_irq_disable(); +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,13,0)) + list_splice_init(&__get_cpu_var(ssd_doneq), &localq); +#else + list_splice_init(this_cpu_ptr(&ssd_doneq), &localq); +#endif + local_irq_enable(); + + while (!list_empty(&localq)) { + cmd = list_entry(localq.next, struct ssd_cmd, list); + list_del_init(&cmd->list); + + dev = (struct ssd_device *)cmd->dev; + bio = cmd->bio; + + if (bio) { + sector_t off = dev->db_info.data.loc.off; + uint32_t len = dev->db_info.data.loc.len; + + switch (dev->db_info.type) { + case SSD_DEBUG_READ_ERR: + if (bio_data_dir(bio) == READ && + !((off + len) <= bio_start(bio) || off >= (bio_start(bio) + bio_sectors(bio)))) { + cmd->errors = -EIO; + } + break; + case SSD_DEBUG_WRITE_ERR: + if (bio_data_dir(bio) == WRITE && + !((off + len) <= bio_start(bio) || off >= (bio_start(bio) + bio_sectors(bio)))) { + cmd->errors = -EROFS; + } + break; + case SSD_DEBUG_RW_ERR: + if (!((off + len) <= bio_start(bio) || off >= (bio_start(bio) + bio_sectors(bio)))) { + if (bio_data_dir(bio) == READ) { + cmd->errors = -EIO; + } else { + cmd->errors = -EROFS; + } + } + break; + default: + break; + } + } + + ssd_end_request(cmd); + } +} + +static inline void ssd_done_bh(struct ssd_cmd *cmd) +{ + unsigned long flags = 0; + + if (unlikely(!ssd_cmd_del_timer(cmd))) { + struct ssd_device *dev = cmd->dev; + struct ssd_rw_msg *msg = (struct ssd_rw_msg *)cmd->msg; + hio_err("%s: unknown cmd: tag %d fun %#x\n", dev->name, msg->tag, msg->fun); + + /* alarm led */ + ssd_set_alarm(dev); + return; + } + + local_irq_save(flags); +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,13,0)) + list_add_tail(&cmd->list, &__get_cpu_var(ssd_doneq)); + tasklet_hi_schedule(&__get_cpu_var(ssd_tasklet)); +#else + list_add_tail(&cmd->list, this_cpu_ptr(&ssd_doneq)); + tasklet_hi_schedule(this_cpu_ptr(&ssd_tasklet)); +#endif + local_irq_restore(flags); + + return; +} + +static inline void ssd_done(struct ssd_cmd *cmd) +{ + if (unlikely(!ssd_cmd_del_timer(cmd))) { + struct ssd_device *dev = cmd->dev; + struct ssd_rw_msg *msg = (struct ssd_rw_msg *)cmd->msg; + hio_err("%s: unknown cmd: tag %d fun %#x\n", dev->name, msg->tag, msg->fun); + + /* alarm led */ + ssd_set_alarm(dev); + return; + } + + ssd_end_request(cmd); + + return; +} + +static inline void ssd_dispatch_cmd(struct ssd_cmd *cmd) +{ + struct ssd_device *dev = (struct ssd_device *)cmd->dev; + + ssd_cmd_add_timer(cmd, SSD_CMD_TIMEOUT, ssd_cmd_timeout); + + spin_lock(&dev->cmd_lock); + ssd_reg_write(dev->ctrlp + SSD_REQ_FIFO_REG, cmd->msg_dma); + spin_unlock(&dev->cmd_lock); +} + +static inline void ssd_send_cmd(struct ssd_cmd *cmd) +{ + struct ssd_device *dev = (struct ssd_device *)cmd->dev; + + ssd_cmd_add_timer(cmd, SSD_CMD_TIMEOUT, ssd_cmd_timeout); + + ssd_reg32_write(dev->ctrlp + SSD_REQ_FIFO_REG, ((uint32_t)cmd->tag | ((uint32_t)cmd->nsegs << 16))); +} + +static inline void ssd_send_cmd_db(struct ssd_cmd *cmd) +{ + struct ssd_device *dev = (struct ssd_device *)cmd->dev; + struct bio *bio = cmd->bio; + + ssd_cmd_add_timer(cmd, SSD_CMD_TIMEOUT, ssd_cmd_timeout); + + if (bio) { + switch (dev->db_info.type) { + case SSD_DEBUG_READ_TO: + if (bio_data_dir(bio) == READ) { + return; + } + break; + case SSD_DEBUG_WRITE_TO: + if (bio_data_dir(bio) == WRITE) { + return; + } + break; + case SSD_DEBUG_RW_TO: + return; + break; + default: + break; + } + } + + ssd_reg32_write(dev->ctrlp + SSD_REQ_FIFO_REG, ((uint32_t)cmd->tag | ((uint32_t)cmd->nsegs << 16))); +} + + +/* fixed for BIOVEC_PHYS_MERGEABLE */ +#ifdef SSD_BIOVEC_PHYS_MERGEABLE_FIXED +#include +#include +#include + +static bool xen_biovec_phys_mergeable_fixed(const struct bio_vec *vec1, + const struct bio_vec *vec2) +{ + unsigned long mfn1 = pfn_to_mfn(page_to_pfn(vec1->bv_page)); + unsigned long mfn2 = pfn_to_mfn(page_to_pfn(vec2->bv_page)); + + return __BIOVEC_PHYS_MERGEABLE(vec1, vec2) && + ((mfn1 == mfn2) || ((mfn1+1) == mfn2)); +} + +#ifdef BIOVEC_PHYS_MERGEABLE +#undef BIOVEC_PHYS_MERGEABLE +#endif +#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ + (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \ + (!xen_domain() || xen_biovec_phys_mergeable_fixed(vec1, vec2))) + +#endif + +static inline int ssd_bio_map_sg(struct ssd_device *dev, struct bio *bio, struct scatterlist *sgl) +{ +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,14,0)) + struct bio_vec *bvec, *bvprv = NULL; + struct scatterlist *sg = NULL; + int i = 0, nsegs = 0; + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,23)) + sg_init_table(sgl, dev->hw_info.cmd_max_sg); +#endif + + /* + * for each segment in bio + */ + bio_for_each_segment(bvec, bio, i) { + if (bvprv && BIOVEC_PHYS_MERGEABLE(bvprv, bvec)) { + sg->length += bvec->bv_len; + } else { + if (unlikely(nsegs >= (int)dev->hw_info.cmd_max_sg)) { + break; + } + + sg = sg ? (sg + 1) : sgl; +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + sg_set_page(sg, bvec->bv_page, bvec->bv_len, bvec->bv_offset); +#else + sg->page = bvec->bv_page; + sg->length = bvec->bv_len; + sg->offset = bvec->bv_offset; +#endif + nsegs++; + } + bvprv = bvec; + } + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + if (sg) { + sg_mark_end(sg); + } +#endif + + bio->bi_idx = i; + + return nsegs; +#else + struct bio_vec bvec, bvprv; + struct bvec_iter iter; + struct scatterlist *sg = NULL; + int nsegs = 0; + int first = 1; + + sg_init_table(sgl, dev->hw_info.cmd_max_sg); + + /* + * for each segment in bio + */ + bio_for_each_segment(bvec, bio, iter) { + if (!first && BIOVEC_PHYS_MERGEABLE(&bvprv, &bvec)) { + sg->length += bvec.bv_len; + } else { + if (unlikely(nsegs >= (int)dev->hw_info.cmd_max_sg)) { + break; + } + + sg = sg ? (sg + 1) : sgl; + + sg_set_page(sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); + + nsegs++; + first = 0; + } + bvprv = bvec; + } + + if (sg) { + sg_mark_end(sg); + } + + return nsegs; +#endif +} + + +static int __ssd_submit_pbio(struct ssd_device *dev, struct bio *bio, int wait) +{ + struct ssd_cmd *cmd; + struct ssd_rw_msg *msg; + struct ssd_sg_entry *sge; + sector_t block = bio_start(bio); + int tag; + int i; + + tag = ssd_get_tag(dev, wait); + if (tag < 0) { + return -EBUSY; + } + + cmd = &dev->cmd[tag]; + cmd->bio = bio; + cmd->flag = 1; + + msg = (struct ssd_rw_msg *)cmd->msg; + +#if (defined SSD_TRIM && (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,36))) + if (bio->bi_rw & REQ_DISCARD) { + unsigned int length = bio_sectors(bio); + + //printk(KERN_WARNING "%s: discard len %u, block %llu\n", dev->name, bio_sectors(bio), block); + msg->tag = tag; + msg->fun = SSD_FUNC_TRIM; + + sge = msg->sge; + for (i=0; i<(dev->hw_info.cmd_max_sg); i++) { + sge->block = block; + sge->length = (length >= dev->hw_info.sg_max_sec) ? dev->hw_info.sg_max_sec : length; + sge->buf = 0; + + block += sge->length; + length -= sge->length; + sge++; + + if (length <= 0) { + break; + } + } + msg->nsegs = cmd->nsegs = (i + 1); + + dev->scmd(cmd); + return 0; + } +#elif (defined SSD_TRIM && (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,32))) + if (bio_rw_flagged(bio, BIO_RW_DISCARD)) { + unsigned int length = bio_sectors(bio); + + //printk(KERN_WARNING "%s: discard len %u, block %llu\n", dev->name, bio_sectors(bio), block); + msg->tag = tag; + msg->fun = SSD_FUNC_TRIM; + + sge = msg->sge; + for (i=0; i<(dev->hw_info.cmd_max_sg); i++) { + sge->block = block; + sge->length = (length >= dev->hw_info.sg_max_sec) ? dev->hw_info.sg_max_sec : length; + sge->buf = 0; + + block += sge->length; + length -= sge->length; + sge++; + + if (length <= 0) { + break; + } + } + msg->nsegs = cmd->nsegs = (i + 1); + + dev->scmd(cmd); + return 0; + } +#endif + + //msg->nsegs = cmd->nsegs = ssd_bio_map_sg(dev, bio, sgl); + msg->nsegs = cmd->nsegs = bio->bi_vcnt; + + //xx + if (bio_data_dir(bio) == READ) { + msg->fun = SSD_FUNC_READ; + msg->flag = 0; + } else { + msg->fun = SSD_FUNC_WRITE; + msg->flag = dev->wmode; + } + + sge = msg->sge; + for (i=0; ibi_vcnt; i++) { + sge->block = block; + sge->length = bio->bi_io_vec[i].bv_len >> 9; + sge->buf = (uint64_t)((void *)bio->bi_io_vec[i].bv_page + bio->bi_io_vec[i].bv_offset); + + block += sge->length; + sge++; + } + + msg->tag = tag; + +#ifdef SSD_OT_PROTECT + if (unlikely(dev->ot_delay > 0 && dev->ot_protect != 0)) { + msleep_interruptible(dev->ot_delay); + } +#endif + + ssd_start_io_acct(cmd); + dev->scmd(cmd); + + return 0; +} + +static inline int ssd_submit_bio(struct ssd_device *dev, struct bio *bio, int wait) +{ + struct ssd_cmd *cmd; + struct ssd_rw_msg *msg; + struct ssd_sg_entry *sge; + struct scatterlist *sgl; + sector_t block = bio_start(bio); + int tag; + int i; + + tag = ssd_get_tag(dev, wait); + if (tag < 0) { + return -EBUSY; + } + + cmd = &dev->cmd[tag]; + cmd->bio = bio; + cmd->flag = 0; + + msg = (struct ssd_rw_msg *)cmd->msg; + + sgl = cmd->sgl; + +#if (defined SSD_TRIM && (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,36))) + if (bio->bi_rw & REQ_DISCARD) { + unsigned int length = bio_sectors(bio); + + //printk(KERN_WARNING "%s: discard len %u, block %llu\n", dev->name, bio_sectors(bio), block); + msg->tag = tag; + msg->fun = SSD_FUNC_TRIM; + + sge = msg->sge; + for (i=0; i<(dev->hw_info.cmd_max_sg); i++) { + sge->block = block; + sge->length = (length >= dev->hw_info.sg_max_sec) ? dev->hw_info.sg_max_sec : length; + sge->buf = 0; + + block += sge->length; + length -= sge->length; + sge++; + + if (length <= 0) { + break; + } + } + msg->nsegs = cmd->nsegs = (i + 1); + + dev->scmd(cmd); + return 0; + } +#elif (defined SSD_TRIM && (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,32))) + if (bio_rw_flagged(bio, BIO_RW_DISCARD)) { + unsigned int length = bio_sectors(bio); + + //printk(KERN_WARNING "%s: discard len %u, block %llu\n", dev->name, bio_sectors(bio), block); + msg->tag = tag; + msg->fun = SSD_FUNC_TRIM; + + sge = msg->sge; + for (i=0; i<(dev->hw_info.cmd_max_sg); i++) { + sge->block = block; + sge->length = (length >= dev->hw_info.sg_max_sec) ? dev->hw_info.sg_max_sec : length; + sge->buf = 0; + + block += sge->length; + length -= sge->length; + sge++; + + if (length <= 0) { + break; + } + } + msg->nsegs = cmd->nsegs = (i + 1); + + dev->scmd(cmd); + return 0; + } +#endif + + msg->nsegs = cmd->nsegs = ssd_bio_map_sg(dev, bio, sgl); + + //xx + if (bio_data_dir(bio) == READ) { + msg->fun = SSD_FUNC_READ; + msg->flag = 0; + pci_map_sg(dev->pdev, sgl, cmd->nsegs, PCI_DMA_FROMDEVICE); + } else { + msg->fun = SSD_FUNC_WRITE; + msg->flag = dev->wmode; + pci_map_sg(dev->pdev, sgl, cmd->nsegs, PCI_DMA_TODEVICE); + } + + sge = msg->sge; + for (i=0; insegs; i++) { + sge->block = block; + sge->length = sg_dma_len(sgl) >> 9; + sge->buf = sg_dma_address(sgl); + + block += sge->length; + sgl++; + sge++; + } + + msg->tag = tag; + +#ifdef SSD_OT_PROTECT + if (unlikely(dev->ot_delay > 0 && dev->ot_protect != 0)) { + msleep_interruptible(dev->ot_delay); + } +#endif + + ssd_start_io_acct(cmd); + dev->scmd(cmd); + + return 0; +} + +/* threads */ +static int ssd_done_thread(void *data) +{ + struct ssd_device *dev; + struct bio *bio; + struct bio *next; +#ifdef SSD_ESCAPE_IRQ + cpumask_t new_mask; +#endif + + if (!data) { + return -EINVAL; + } + dev = data; + + //set_user_nice(current, -5); + + while (!kthread_should_stop()) { + wait_event_interruptible(dev->done_waitq, (atomic_read(&dev->in_doneq) || kthread_should_stop())); + + while (atomic_read(&dev->in_doneq)) { + if (threaded_irq) { + spin_lock(&dev->doneq_lock); + bio = ssd_blist_get(&dev->doneq); + spin_unlock(&dev->doneq_lock); + } else { + spin_lock_irq(&dev->doneq_lock); + bio = ssd_blist_get(&dev->doneq); + spin_unlock_irq(&dev->doneq_lock); + } + + while (bio) { + next = bio->bi_next; + bio->bi_next = NULL; +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, 0); +#else + bio_endio(bio, bio->bi_size, 0); +#endif + atomic_dec(&dev->in_doneq); + bio = next; + } + + cond_resched(); + +#ifdef SSD_ESCAPE_IRQ + if (unlikely(smp_processor_id() == dev->irq_cpu)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,28)) + cpumask_setall(&new_mask); + cpumask_clear_cpu(dev->irq_cpu, &new_mask); + set_cpus_allowed_ptr(current, &new_mask); +#else + cpus_setall(new_mask); + cpu_clear(dev->irq_cpu, new_mask); + set_cpus_allowed(current, new_mask); +#endif + } +#endif + } + } + return 0; +} + +static int ssd_send_thread(void *data) +{ + struct ssd_device *dev; + struct bio *bio; + struct bio *next; +#ifdef SSD_ESCAPE_IRQ + cpumask_t new_mask; +#endif + + if (!data) { + return -EINVAL; + } + dev = data; + + //set_user_nice(current, -5); + + while (!kthread_should_stop()) { + wait_event_interruptible(dev->send_waitq, (atomic_read(&dev->in_sendq) || kthread_should_stop())); + + while (atomic_read(&dev->in_sendq)) { + spin_lock(&dev->sendq_lock); + bio = ssd_blist_get(&dev->sendq); + spin_unlock(&dev->sendq_lock); + + while (bio) { + next = bio->bi_next; + bio->bi_next = NULL; +#ifdef SSD_QUEUE_PBIO + if (test_and_clear_bit(BIO_SSD_PBIO, &bio->bi_flags)) { + __ssd_submit_pbio(dev, bio, 1); + } else { + ssd_submit_bio(dev, bio, 1); + } +#else + ssd_submit_bio(dev, bio, 1); +#endif + atomic_dec(&dev->in_sendq); + bio = next; + } + + cond_resched(); + +#ifdef SSD_ESCAPE_IRQ + if (unlikely(smp_processor_id() == dev->irq_cpu)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,28)) + cpumask_setall(&new_mask); + cpumask_clear_cpu(dev->irq_cpu, &new_mask); + set_cpus_allowed_ptr(current, &new_mask); +#else + cpus_setall(new_mask); + cpu_clear(dev->irq_cpu, new_mask); + set_cpus_allowed(current, new_mask); +#endif + } +#endif + } + } + + return 0; +} + +static void ssd_cleanup_thread(struct ssd_device *dev) +{ + kthread_stop(dev->send_thread); + kthread_stop(dev->done_thread); +} + +static int ssd_init_thread(struct ssd_device *dev) +{ + int ret; + + atomic_set(&dev->in_doneq, 0); + atomic_set(&dev->in_sendq, 0); + + spin_lock_init(&dev->doneq_lock); + spin_lock_init(&dev->sendq_lock); + + ssd_blist_init(&dev->doneq); + ssd_blist_init(&dev->sendq); + + init_waitqueue_head(&dev->done_waitq); + init_waitqueue_head(&dev->send_waitq); + + dev->done_thread = kthread_run(ssd_done_thread, dev, "%s/d", dev->name); + if (IS_ERR(dev->done_thread)) { + ret = PTR_ERR(dev->done_thread); + goto out_done_thread; + } + + dev->send_thread = kthread_run(ssd_send_thread, dev, "%s/s", dev->name); + if (IS_ERR(dev->send_thread)) { + ret = PTR_ERR(dev->send_thread); + goto out_send_thread; + } + + return 0; + +out_send_thread: + kthread_stop(dev->done_thread); +out_done_thread: + return ret; +} + +/* dcmd pool */ +static void ssd_put_dcmd(struct ssd_dcmd *dcmd) +{ + struct ssd_device *dev = (struct ssd_device *)dcmd->dev; + + spin_lock(&dev->dcmd_lock); + list_add_tail(&dcmd->list, &dev->dcmd_list); + spin_unlock(&dev->dcmd_lock); +} + +static struct ssd_dcmd *ssd_get_dcmd(struct ssd_device *dev) +{ + struct ssd_dcmd *dcmd = NULL; + + spin_lock(&dev->dcmd_lock); + if (!list_empty(&dev->dcmd_list)) { + dcmd = list_entry(dev->dcmd_list.next, + struct ssd_dcmd, list); + list_del_init(&dcmd->list); + } + spin_unlock(&dev->dcmd_lock); + + return dcmd; +} + +static void ssd_cleanup_dcmd(struct ssd_device *dev) +{ + kfree(dev->dcmd); +} + +static int ssd_init_dcmd(struct ssd_device *dev) +{ + struct ssd_dcmd *dcmd; + int dcmd_sz = sizeof(struct ssd_dcmd)*dev->hw_info.cmd_fifo_sz; + int i; + + spin_lock_init(&dev->dcmd_lock); + INIT_LIST_HEAD(&dev->dcmd_list); + init_waitqueue_head(&dev->dcmd_wq); + + dev->dcmd = kmalloc(dcmd_sz, GFP_KERNEL); + if (!dev->dcmd) { + hio_warn("%s: can not alloc dcmd\n", dev->name); + goto out_alloc_dcmd; + } + memset(dev->dcmd, 0, dcmd_sz); + + for (i=0, dcmd=dev->dcmd; i<(int)dev->hw_info.cmd_fifo_sz; i++, dcmd++) { + dcmd->dev = dev; + INIT_LIST_HEAD(&dcmd->list); + list_add_tail(&dcmd->list, &dev->dcmd_list); + } + + return 0; + +out_alloc_dcmd: + return -ENOMEM; +} + +static void ssd_put_dmsg(void *msg) +{ + struct ssd_dcmd *dcmd = container_of(msg, struct ssd_dcmd, msg); + struct ssd_device *dev = (struct ssd_device *)dcmd->dev; + + memset(dcmd->msg, 0, SSD_DCMD_MAX_SZ); + ssd_put_dcmd(dcmd); + wake_up(&dev->dcmd_wq); +} + +static void *ssd_get_dmsg(struct ssd_device *dev) +{ + struct ssd_dcmd *dcmd = ssd_get_dcmd(dev); + + while (!dcmd) { + DEFINE_WAIT(wait); + prepare_to_wait_exclusive(&dev->dcmd_wq, &wait, TASK_UNINTERRUPTIBLE); + schedule(); + + dcmd = ssd_get_dcmd(dev); + + finish_wait(&dev->dcmd_wq, &wait); + } + return dcmd->msg; +} + +/* do direct cmd */ +static int ssd_do_request(struct ssd_device *dev, int rw, void *msg, int *done) +{ + DECLARE_COMPLETION(wait); + struct ssd_cmd *cmd; + int tag; + int ret = 0; + + tag = ssd_get_tag(dev, 1); + if (tag < 0) { + return -EBUSY; + } + + cmd = &dev->cmd[tag]; + cmd->nsegs = 1; + memcpy(cmd->msg, msg, SSD_DCMD_MAX_SZ); + ((struct ssd_rw_msg *)cmd->msg)->tag = tag; + + cmd->waiting = &wait; + + dev->scmd(cmd); + + wait_for_completion(cmd->waiting); + cmd->waiting = NULL; + + if (cmd->errors == -ETIMEDOUT) { + ret = cmd->errors; + } else if (cmd->errors) { + ret = -EIO; + } + + if (done != NULL) { + *done = cmd->nr_log; + } + ssd_put_tag(dev, cmd->tag); + + return ret; +} + +static int ssd_do_barrier_request(struct ssd_device *dev, int rw, void *msg, int *done) +{ + DECLARE_COMPLETION(wait); + struct ssd_cmd *cmd; + int tag; + int ret = 0; + + tag = ssd_barrier_get_tag(dev); + if (tag < 0) { + return -EBUSY; + } + + cmd = &dev->cmd[tag]; + cmd->nsegs = 1; + memcpy(cmd->msg, msg, SSD_DCMD_MAX_SZ); + ((struct ssd_rw_msg *)cmd->msg)->tag = tag; + + cmd->waiting = &wait; + + dev->scmd(cmd); + + wait_for_completion(cmd->waiting); + cmd->waiting = NULL; + + if (cmd->errors == -ETIMEDOUT) { + ret = cmd->errors; + } else if (cmd->errors) { + ret = -EIO; + } + + if (done != NULL) { + *done = cmd->nr_log; + } + ssd_barrier_put_tag(dev, cmd->tag); + + return ret; +} + +#ifdef SSD_OT_PROTECT +static void ssd_check_temperature(struct ssd_device *dev, int temp) +{ + uint64_t val; + uint32_t off; + int cur; + int i; + + if (mode != SSD_DRV_MODE_STANDARD) { + return; + } + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + } + + for (i=0; ihw_info.nr_ctrl; i++) { + off = SSD_CTRL_TEMP_REG0 + i * sizeof(uint64_t); + + val = ssd_reg_read(dev->ctrlp + off); + if (val == 0xffffffffffffffffull) { + continue; + } + + cur = (int)CUR_TEMP(val); + if (cur >= temp) { + if (!test_and_set_bit(SSD_HWMON_TEMP(SSD_TEMP_CTRL), &dev->hwmon)) { + if (dev->protocol_info.ver > SSD_PROTOCOL_V3 && dev->protocol_info.ver < SSD_PROTOCOL_V3_2_2) { + hio_warn("%s: Over temperature, please check the fans.\n", dev->name); + dev->ot_delay = SSD_OT_DELAY; + } + } + return; + } + } + + if (test_and_clear_bit(SSD_HWMON_TEMP(SSD_TEMP_CTRL), &dev->hwmon)) { + if (dev->protocol_info.ver > SSD_PROTOCOL_V3 && dev->protocol_info.ver < SSD_PROTOCOL_V3_2_2) { + hio_warn("%s: Temperature is OK.\n", dev->name); + dev->ot_delay = 0; + } + } +} +#endif + +static int ssd_get_ot_status(struct ssd_device *dev, int *status) +{ + uint32_t off; + uint32_t val; + int i; + + if (!dev || !status) { + return -EINVAL; + } + + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2_2) { + for (i=0; ihw_info.nr_ctrl; i++) { + off = SSD_READ_OT_REG0 + (i * SSD_CTRL_REG_ZONE_SZ); + val = ssd_reg32_read(dev->ctrlp + off); + if ((val >> 22) & 0x1) { + *status = 1; + goto out; + } + + + off = SSD_WRITE_OT_REG0 + (i * SSD_CTRL_REG_ZONE_SZ); + val = ssd_reg32_read(dev->ctrlp + off); + if ((val >> 22) & 0x1) { + *status = 1; + goto out; + } + } + } else { + *status = !!dev->ot_delay; + } + +out: + return 0; +} + +static void ssd_set_ot_protect(struct ssd_device *dev, int protect) +{ + uint32_t off; + uint32_t val; + int i; + + mutex_lock(&dev->fw_mutex); + + dev->ot_protect = !!protect; + + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2_2) { + for (i=0; ihw_info.nr_ctrl; i++) { + off = SSD_READ_OT_REG0 + (i * SSD_CTRL_REG_ZONE_SZ); + val = ssd_reg32_read(dev->ctrlp + off); + if (dev->ot_protect) { + val |= (1U << 21); + } else { + val &= ~(1U << 21); + } + ssd_reg32_write(dev->ctrlp + off, val); + + + off = SSD_WRITE_OT_REG0 + (i * SSD_CTRL_REG_ZONE_SZ); + val = ssd_reg32_read(dev->ctrlp + off); + if (dev->ot_protect) { + val |= (1U << 21); + } else { + val &= ~(1U << 21); + } + ssd_reg32_write(dev->ctrlp + off, val); + } + } + + mutex_unlock(&dev->fw_mutex); +} + +static int ssd_init_ot_protect(struct ssd_device *dev) +{ + ssd_set_ot_protect(dev, ot_protect); + +#ifdef SSD_OT_PROTECT + ssd_check_temperature(dev, SSD_OT_TEMP); +#endif + + return 0; +} + +/* log */ +static int ssd_read_log(struct ssd_device *dev, int ctrl_idx, void *buf, int *nr_log) +{ + struct ssd_log_op_msg *msg; + struct ssd_log_msg *lmsg; + dma_addr_t buf_dma; + size_t length = dev->hw_info.log_sz; + int ret = 0; + + if (ctrl_idx >= dev->hw_info.nr_ctrl) { + return -EINVAL; + } + + buf_dma = pci_map_single(dev->pdev, buf, length, PCI_DMA_FROMDEVICE); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,26)) + ret = dma_mapping_error(buf_dma); +#else + ret = dma_mapping_error(&(dev->pdev->dev), buf_dma); +#endif + if (ret) { + hio_warn("%s: unable to map read DMA buffer\n", dev->name); + goto out_dma_mapping; + } + + msg = (struct ssd_log_op_msg *)ssd_get_dmsg(dev); + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + lmsg = (struct ssd_log_msg *)msg; + lmsg->fun = SSD_FUNC_READ_LOG; + lmsg->ctrl_idx = ctrl_idx; + lmsg->buf = buf_dma; + } else { + msg->fun = SSD_FUNC_READ_LOG; + msg->ctrl_idx = ctrl_idx; + msg->buf = buf_dma; + } + + ret = ssd_do_request(dev, READ, msg, nr_log); + ssd_put_dmsg(msg); + + pci_unmap_single(dev->pdev, buf_dma, length, PCI_DMA_FROMDEVICE); + +out_dma_mapping: + return ret; +} + +#define SSD_LOG_PRINT_BUF_SZ 256 +static int ssd_parse_log(struct ssd_device *dev, struct ssd_log *log, int print) +{ + struct ssd_log_desc *log_desc = ssd_log_desc; + struct ssd_log_entry *le; + char *sn = NULL; + char print_buf[SSD_LOG_PRINT_BUF_SZ]; + int print_len; + + le = &log->le; + + /* find desc */ + while (log_desc->event != SSD_UNKNOWN_EVENT) { + if (log_desc->event == le->event) { + break; + } + log_desc++; + } + + if (!print) { + goto out; + } + + if (log_desc->level < log_level) { + goto out; + } + + /* parse */ + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + sn = dev->label.sn; + } else { + sn = dev->labelv3.barcode; + } + + print_len = snprintf(print_buf, SSD_LOG_PRINT_BUF_SZ, "%s (%s): <%#x>", dev->name, sn, le->event); + + if (log->ctrl_idx != SSD_LOG_SW_IDX) { + print_len += snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), " controller %d", log->ctrl_idx); + } + + switch (log_desc->data) { + case SSD_LOG_DATA_NONE: + break; + case SSD_LOG_DATA_LOC: + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + print_len += snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), " flash %d", le->data.loc.flash); + if (log_desc->sblock) { + print_len += snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), " block %d", le->data.loc.block); + } + if (log_desc->spage) { + print_len += snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), " page %d", le->data.loc.page); + } + } else { + print_len += snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), " flash %d", le->data.loc1.flash); + if (log_desc->sblock) { + print_len += snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), " block %d", le->data.loc1.block); + } + if (log_desc->spage) { + print_len += snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), " page %d", le->data.loc1.page); + } + } + break; + case SSD_LOG_DATA_HEX: + print_len += snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), " info %#x", le->data.val); + break; + default: + break; + } + /*print_len += */snprintf((print_buf + print_len), (SSD_LOG_PRINT_BUF_SZ - print_len), ": %s", log_desc->desc); + + switch (log_desc->level) { + case SSD_LOG_LEVEL_INFO: + hio_info("%s\n", print_buf); + break; + case SSD_LOG_LEVEL_NOTICE: + hio_note("%s\n", print_buf); + break; + case SSD_LOG_LEVEL_WARNING: + hio_warn("%s\n", print_buf); + break; + case SSD_LOG_LEVEL_ERR: + hio_err("%s\n", print_buf); + //printk(KERN_ERR MODULE_NAME": some exception occurred, please check the data or refer to FAQ."); + break; + default: + hio_warn("%s\n", print_buf); + break; + } + +out: + return log_desc->level; +} + +static int ssd_bm_get_sfstatus(struct ssd_device *dev, uint16_t *status); +static int ssd_switch_wmode(struct ssd_device *dev, int wmode); + + +static int ssd_handle_event(struct ssd_device *dev, uint16_t event, int level) +{ + int ret = 0; + + switch (event) { + case SSD_LOG_OVER_TEMP: { +#ifdef SSD_OT_PROTECT + if (!test_and_set_bit(SSD_HWMON_TEMP(SSD_TEMP_CTRL), &dev->hwmon)) { + if (dev->protocol_info.ver > SSD_PROTOCOL_V3 && dev->protocol_info.ver < SSD_PROTOCOL_V3_2_2) { + hio_warn("%s: Over temperature, please check the fans.\n", dev->name); + dev->ot_delay = SSD_OT_DELAY; + } + } +#endif + break; + } + + case SSD_LOG_NORMAL_TEMP: { +#ifdef SSD_OT_PROTECT + /* need to check all controller's temperature */ + ssd_check_temperature(dev, SSD_OT_TEMP_HYST); +#endif + break; + } + + case SSD_LOG_BATTERY_FAULT: { + uint16_t sfstatus; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + if (!ssd_bm_get_sfstatus(dev, &sfstatus)) { + ssd_gen_swlog(dev, SSD_LOG_BM_SFSTATUS, sfstatus); + } + } + + if (!test_and_set_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + ssd_switch_wmode(dev, dev->user_wmode); + } + break; + } + + case SSD_LOG_BATTERY_OK: { + if (test_and_clear_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + ssd_switch_wmode(dev, dev->user_wmode); + } + break; + } + + case SSD_LOG_BOARD_VOLT_FAULT: { + ssd_mon_boardvolt(dev); + break; + } + + case SSD_LOG_CLEAR_LOG: { + /* update smart */ + memset(&dev->smart.log_info, 0, sizeof(struct ssd_log_info)); + break; + } + + case SSD_LOG_CAP_VOLT_FAULT: + case SSD_LOG_CAP_LEARN_FAULT: + case SSD_LOG_CAP_SHORT_CIRCUIT: { + if (!test_and_set_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + ssd_switch_wmode(dev, dev->user_wmode); + } + break; + } + + default: + break; + } + + /* ssd event call */ + if (dev->event_call) { + dev->event_call(dev->gd, event, level); + + /* FIXME */ + if (SSD_LOG_CAP_VOLT_FAULT == event || SSD_LOG_CAP_LEARN_FAULT == event || SSD_LOG_CAP_SHORT_CIRCUIT == event) { + dev->event_call(dev->gd, SSD_LOG_BATTERY_FAULT, level); + } + } + + return ret; +} + +static int ssd_save_log(struct ssd_device *dev, struct ssd_log *log) +{ + uint32_t off, size; + void *internal_log; + int ret = 0; + + mutex_lock(&dev->internal_log_mutex); + + size = sizeof(struct ssd_log); + off = dev->internal_log.nr_log * size; + + if (off == dev->rom_info.log_sz) { + if (dev->internal_log.nr_log == dev->smart.log_info.nr_log) { + hio_warn("%s: internal log is full\n", dev->name); + } + goto out; + } + + internal_log = dev->internal_log.log + off; + memcpy(internal_log, log, size); + + if (dev->protocol_info.ver > SSD_PROTOCOL_V3) { + off += dev->rom_info.log_base; + + ret = ssd_spi_write(dev, log, off, size); + if (ret) { + goto out; + } + } + + dev->internal_log.nr_log++; + +out: + mutex_unlock(&dev->internal_log_mutex); + return ret; +} + +static int ssd_save_swlog(struct ssd_device *dev, uint16_t event, uint32_t data) +{ + struct ssd_log log; + struct timeval tv; + int level; + int ret = 0; + + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return 0; + + memset(&log, 0, sizeof(struct ssd_log)); + + do_gettimeofday(&tv); + log.ctrl_idx = SSD_LOG_SW_IDX; + log.time = tv.tv_sec; + log.le.event = event; + log.le.data.val = data; + + level = ssd_parse_log(dev, &log, 0); + if (level >= SSD_LOG_LEVEL) { + ret = ssd_save_log(dev, &log); + } + + /* set alarm */ + if (SSD_LOG_LEVEL_ERR == level) { + ssd_set_alarm(dev); + } + + /* update smart */ + dev->smart.log_info.nr_log++; + dev->smart.log_info.stat[level]++; + + /* handle event */ + ssd_handle_event(dev, event, level); + + return ret; +} + +static int ssd_gen_swlog(struct ssd_device *dev, uint16_t event, uint32_t data) +{ + struct ssd_log_entry le; + int ret; + + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return 0; + + /* slave port ? */ + if (dev->slave) { + return 0; + } + + memset(&le, 0, sizeof(struct ssd_log_entry)); + le.event = event; + le.data.val = data; + + ret = sfifo_put(&dev->log_fifo, &le); + if (ret) { + return ret; + } + + if (test_bit(SSD_INIT_WORKQ, &dev->state)) { + queue_work(dev->workq, &dev->log_work); + } + + return 0; +} + +static int ssd_do_swlog(struct ssd_device *dev) +{ + struct ssd_log_entry le; + int ret = 0; + + memset(&le, 0, sizeof(struct ssd_log_entry)); + while (!sfifo_get(&dev->log_fifo, &le)) { + ret = ssd_save_swlog(dev, le.event, le.data.val); + if (ret) { + break; + } + } + + return ret; +} + +static int __ssd_clear_log(struct ssd_device *dev) +{ + uint32_t off, length; + int ret; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return 0; + } + + if (dev->internal_log.nr_log == 0) { + return 0; + } + + mutex_lock(&dev->internal_log_mutex); + + off = dev->rom_info.log_base; + length = dev->rom_info.log_sz; + + ret = ssd_spi_erase(dev, off, length); + if (ret) { + hio_warn("%s: log erase: failed\n", dev->name); + goto out; + } + + dev->internal_log.nr_log = 0; + +out: + mutex_unlock(&dev->internal_log_mutex); + return ret; +} + +static int ssd_clear_log(struct ssd_device *dev) +{ + int ret; + + ret = __ssd_clear_log(dev); + if(!ret) { + ssd_gen_swlog(dev, SSD_LOG_CLEAR_LOG, 0); + } + + return ret; +} + +static int ssd_do_log(struct ssd_device *dev, int ctrl_idx, void *buf) +{ + struct ssd_log_entry *le; + struct ssd_log log; + struct timeval tv; + int nr_log = 0; + int level; + int ret = 0; + + ret = ssd_read_log(dev, ctrl_idx, buf, &nr_log); + if (ret) { + return ret; + } + + do_gettimeofday(&tv); + + log.time = tv.tv_sec; + log.ctrl_idx = ctrl_idx; + + le = (ssd_log_entry_t *)buf; + while (nr_log > 0) { + memcpy(&log.le, le, sizeof(struct ssd_log_entry)); + + level = ssd_parse_log(dev, &log, 1); + if (level >= SSD_LOG_LEVEL) { + ssd_save_log(dev, &log); + } + + /* set alarm */ + if (SSD_LOG_LEVEL_ERR == level) { + ssd_set_alarm(dev); + } + + dev->smart.log_info.nr_log++; + if (SSD_LOG_SEU_FAULT != le->event && SSD_LOG_SEU_FAULT1 != le->event) { + dev->smart.log_info.stat[level]++; + } else { + /* SEU fault */ + + /* log to the volatile log info */ + dev->log_info.nr_log++; + dev->log_info.stat[level]++; + + /* do something */ + dev->reload_fw = 1; + ssd_reg32_write(dev->ctrlp + SSD_RELOAD_FW_REG, SSD_RELOAD_FLAG); + + /*dev->readonly = 1; + set_disk_ro(dev->gd, 1); + hio_warn("%s: switched to read-only mode.\n", dev->name);*/ + } + + /* handle event */ + ssd_handle_event(dev, le->event, level); + + le++; + nr_log--; + } + + return 0; +} + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) +static void ssd_log_worker(void *data) +{ + struct ssd_device *dev = (struct ssd_device *)data; +#else +static void ssd_log_worker(struct work_struct *work) +{ + struct ssd_device *dev = container_of(work, struct ssd_device, log_work); +#endif + int i; + int ret; + + if (!test_bit(SSD_LOG_ERR, &dev->state) && test_bit(SSD_ONLINE, &dev->state)) { + /* alloc log buf */ + if (!dev->log_buf) { + dev->log_buf = kmalloc(dev->hw_info.log_sz, GFP_KERNEL); + if (!dev->log_buf) { + hio_warn("%s: ssd_log_worker: no mem\n", dev->name); + return; + } + } + + /* get log */ + if (test_and_clear_bit(SSD_LOG_HW, &dev->state)) { + for (i=0; ihw_info.nr_ctrl; i++) { + ret = ssd_do_log(dev, i, dev->log_buf); + if (ret) { + (void)test_and_set_bit(SSD_LOG_ERR, &dev->state); + hio_warn("%s: do log fail\n", dev->name); + } + } + } + } + + ret = ssd_do_swlog(dev); + if (ret) { + hio_warn("%s: do swlog fail\n", dev->name); + } +} + +static void ssd_cleanup_log(struct ssd_device *dev) +{ + if (dev->log_buf) { + kfree(dev->log_buf); + dev->log_buf = NULL; + } + + sfifo_free(&dev->log_fifo); + + if (dev->internal_log.log) { + vfree(dev->internal_log.log); + dev->internal_log.log = NULL; + } +} + +static int ssd_init_log(struct ssd_device *dev) +{ + struct ssd_log *log; + uint32_t off, size; + uint32_t len = 0; + int ret = 0; + + mutex_init(&dev->internal_log_mutex); + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) + INIT_WORK(&dev->log_work, ssd_log_worker, dev); +#else + INIT_WORK(&dev->log_work, ssd_log_worker); +#endif + + off = dev->rom_info.log_base; + size = dev->rom_info.log_sz; + + dev->internal_log.log = vmalloc(size); + if (!dev->internal_log.log) { + ret = -ENOMEM; + goto out_alloc_log; + } + + ret = sfifo_alloc(&dev->log_fifo, SSD_LOG_FIFO_SZ, sizeof(struct ssd_log_entry)); + if (ret < 0) { + goto out_alloc_log_fifo; + } + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return 0; + } + + log = (struct ssd_log *)dev->internal_log.log; + while (len < size) { + ret = ssd_spi_read(dev, log, off, sizeof(struct ssd_log)); + if (ret) { + goto out_read_log; + } + + if (log->ctrl_idx == 0xff) { + break; + } + + dev->internal_log.nr_log++; + log++; + len += sizeof(struct ssd_log); + off += sizeof(struct ssd_log); + } + + return 0; + +out_read_log: + sfifo_free(&dev->log_fifo); +out_alloc_log_fifo: + vfree(dev->internal_log.log); + dev->internal_log.log = NULL; + dev->internal_log.nr_log = 0; +out_alloc_log: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +/* work queue */ +static void ssd_stop_workq(struct ssd_device *dev) +{ + test_and_clear_bit(SSD_INIT_WORKQ, &dev->state); + flush_workqueue(dev->workq); +} + +static void ssd_start_workq(struct ssd_device *dev) +{ + (void)test_and_set_bit(SSD_INIT_WORKQ, &dev->state); + + /* log ? */ + queue_work(dev->workq, &dev->log_work); +} + +static void ssd_cleanup_workq(struct ssd_device *dev) +{ + flush_workqueue(dev->workq); + destroy_workqueue(dev->workq); + dev->workq = NULL; +} + +static int ssd_init_workq(struct ssd_device *dev) +{ + int ret = 0; + + dev->workq = create_singlethread_workqueue(dev->name); + if (!dev->workq) { + ret = -ESRCH; + goto out; + } + +out: + return ret; +} + +/* rom */ +static int ssd_init_rom_info(struct ssd_device *dev) +{ + uint32_t val; + + mutex_init(&dev->spi_mutex); + mutex_init(&dev->i2c_mutex); + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + /* fix bug: read data to clear status */ + (void)ssd_reg32_read(dev->ctrlp + SSD_SPI_REG_RDATA); + + dev->rom_info.size = SSD_ROM_SIZE; + dev->rom_info.block_size = SSD_ROM_BLK_SIZE; + dev->rom_info.page_size = SSD_ROM_PAGE_SIZE; + + dev->rom_info.bridge_fw_base = SSD_ROM_BRIDGE_FW_BASE; + dev->rom_info.bridge_fw_sz = SSD_ROM_BRIDGE_FW_SIZE; + dev->rom_info.nr_bridge_fw = SSD_ROM_NR_BRIDGE_FW; + + dev->rom_info.ctrl_fw_base = SSD_ROM_CTRL_FW_BASE; + dev->rom_info.ctrl_fw_sz = SSD_ROM_CTRL_FW_SIZE; + dev->rom_info.nr_ctrl_fw = SSD_ROM_NR_CTRL_FW; + + dev->rom_info.log_sz = SSD_ROM_LOG_SZ; + + dev->rom_info.vp_base = SSD_ROM_VP_BASE; + dev->rom_info.label_base = SSD_ROM_LABEL_BASE; + } else if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + val = ssd_reg32_read(dev->ctrlp + SSD_ROM_INFO_REG); + dev->rom_info.size = 0x100000 * (1U << (val & 0xFF)); + dev->rom_info.block_size = 0x10000 * (1U << ((val>>8) & 0xFF)); + dev->rom_info.page_size = (val>>16) & 0xFFFF; + + val = ssd_reg32_read(dev->ctrlp + SSD_ROM_BRIDGE_FW_INFO_REG); + dev->rom_info.bridge_fw_base = dev->rom_info.block_size * (val & 0xFFFF); + dev->rom_info.bridge_fw_sz = dev->rom_info.block_size * ((val>>16) & 0x3FFF); + dev->rom_info.nr_bridge_fw = ((val >> 30) & 0x3) + 1; + + val = ssd_reg32_read(dev->ctrlp + SSD_ROM_CTRL_FW_INFO_REG); + dev->rom_info.ctrl_fw_base = dev->rom_info.block_size * (val & 0xFFFF); + dev->rom_info.ctrl_fw_sz = dev->rom_info.block_size * ((val>>16) & 0x3FFF); + dev->rom_info.nr_ctrl_fw = ((val >> 30) & 0x3) + 1; + + dev->rom_info.bm_fw_base = dev->rom_info.ctrl_fw_base + (dev->rom_info.nr_ctrl_fw * dev->rom_info.ctrl_fw_sz); + dev->rom_info.bm_fw_sz = SSD_PV3_ROM_BM_FW_SZ; + dev->rom_info.nr_bm_fw = SSD_PV3_ROM_NR_BM_FW; + + dev->rom_info.log_base = dev->rom_info.bm_fw_base + (dev->rom_info.nr_bm_fw * dev->rom_info.bm_fw_sz); + dev->rom_info.log_sz = SSD_ROM_LOG_SZ; + + dev->rom_info.smart_base = dev->rom_info.log_base + dev->rom_info.log_sz; + dev->rom_info.smart_sz = SSD_PV3_ROM_SMART_SZ; + dev->rom_info.nr_smart = SSD_PV3_ROM_NR_SMART; + + val = ssd_reg32_read(dev->ctrlp + SSD_ROM_VP_INFO_REG); + dev->rom_info.vp_base = dev->rom_info.block_size * val; + dev->rom_info.label_base = dev->rom_info.vp_base + dev->rom_info.block_size; + if (dev->rom_info.label_base >= dev->rom_info.size) { + dev->rom_info.label_base = dev->rom_info.vp_base - dev->rom_info.block_size; + } + } else { + val = ssd_reg32_read(dev->ctrlp + SSD_ROM_INFO_REG); + dev->rom_info.size = 0x100000 * (1U << (val & 0xFF)); + dev->rom_info.block_size = 0x10000 * (1U << ((val>>8) & 0xFF)); + dev->rom_info.page_size = (val>>16) & 0xFFFF; + + val = ssd_reg32_read(dev->ctrlp + SSD_ROM_BRIDGE_FW_INFO_REG); + dev->rom_info.bridge_fw_base = dev->rom_info.block_size * (val & 0xFFFF); + dev->rom_info.bridge_fw_sz = dev->rom_info.block_size * ((val>>16) & 0x3FFF); + dev->rom_info.nr_bridge_fw = ((val >> 30) & 0x3) + 1; + + val = ssd_reg32_read(dev->ctrlp + SSD_ROM_CTRL_FW_INFO_REG); + dev->rom_info.ctrl_fw_base = dev->rom_info.block_size * (val & 0xFFFF); + dev->rom_info.ctrl_fw_sz = dev->rom_info.block_size * ((val>>16) & 0x3FFF); + dev->rom_info.nr_ctrl_fw = ((val >> 30) & 0x3) + 1; + + val = ssd_reg32_read(dev->ctrlp + SSD_ROM_VP_INFO_REG); + dev->rom_info.vp_base = dev->rom_info.block_size * val; + dev->rom_info.label_base = dev->rom_info.vp_base - SSD_PV3_2_ROM_SEC_SZ; + + dev->rom_info.nr_smart = SSD_PV3_ROM_NR_SMART; + dev->rom_info.smart_sz = SSD_PV3_2_ROM_SEC_SZ; + dev->rom_info.smart_base = dev->rom_info.label_base - (dev->rom_info.smart_sz * dev->rom_info.nr_smart); + if (dev->rom_info.smart_sz > dev->rom_info.block_size) { + dev->rom_info.smart_sz = dev->rom_info.block_size; + } + + dev->rom_info.log_sz = SSD_PV3_2_ROM_LOG_SZ; + dev->rom_info.log_base = dev->rom_info.smart_base - dev->rom_info.log_sz; + } + + return ssd_init_spi(dev); +} + +/* smart */ +static int ssd_update_smart(struct ssd_device *dev, struct ssd_smart *smart) +{ + struct timeval tv; + uint64_t run_time; +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,27)) + struct hd_struct *part; + int cpu; +#endif + int i, j; + int ret = 0; + + if (!test_bit(SSD_INIT_BD, &dev->state)) { + return 0; + } + + do_gettimeofday(&tv); + if ((uint64_t)tv.tv_sec < dev->uptime) { + run_time = 0; + } else { + run_time = tv.tv_sec - dev->uptime; + } + + /* avoid frequently update */ + if (run_time >= 60) { + ret = 1; + } + + /* io stat */ + smart->io_stat.run_time += run_time; + +#if (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,27)) + cpu = part_stat_lock(); + part = &dev->gd->part0; + part_round_stats(cpu, part); + part_stat_unlock(); + + smart->io_stat.nr_read += part_stat_read(part, ios[READ]); + smart->io_stat.nr_write += part_stat_read(part, ios[WRITE]); + smart->io_stat.rsectors += part_stat_read(part, sectors[READ]); + smart->io_stat.wsectors += part_stat_read(part, sectors[WRITE]); +#elif (LINUX_VERSION_CODE > KERNEL_VERSION(2,6,14)) + preempt_disable(); + disk_round_stats(dev->gd); + preempt_enable(); + + smart->io_stat.nr_read += disk_stat_read(dev->gd, ios[READ]); + smart->io_stat.nr_write += disk_stat_read(dev->gd, ios[WRITE]); + smart->io_stat.rsectors += disk_stat_read(dev->gd, sectors[READ]); + smart->io_stat.wsectors += disk_stat_read(dev->gd, sectors[WRITE]); +#else + preempt_disable(); + disk_round_stats(dev->gd); + preempt_enable(); + + smart->io_stat.nr_read += disk_stat_read(dev->gd, reads); + smart->io_stat.nr_write += disk_stat_read(dev->gd, writes); + smart->io_stat.rsectors += disk_stat_read(dev->gd, read_sectors); + smart->io_stat.wsectors += disk_stat_read(dev->gd, write_sectors); +#endif + + smart->io_stat.nr_to += atomic_read(&dev->tocnt); + + for (i=0; inr_queue; i++) { + smart->io_stat.nr_rwerr += dev->queue[i].io_stat.nr_rwerr; + smart->io_stat.nr_ioerr += dev->queue[i].io_stat.nr_ioerr; + } + + for (i=0; inr_queue; i++) { + for (j=0; jecc_info.bitflip[j] += dev->queue[i].ecc_info.bitflip[j]; + } + } + + //dev->uptime = tv.tv_sec; + + return ret; +} + +static int ssd_clear_smart(struct ssd_device *dev) +{ + struct timeval tv; + uint64_t sversion; + uint32_t off, length; + int i; + int ret; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return 0; + } + + /* clear smart */ + off = dev->rom_info.smart_base; + length = dev->rom_info.smart_sz * dev->rom_info.nr_smart; + + ret = ssd_spi_erase(dev, off, length); + if (ret) { + hio_warn("%s: info erase: failed\n", dev->name); + goto out; + } + + sversion = dev->smart.version; + + memset(&dev->smart, 0, sizeof(struct ssd_smart)); + dev->smart.version = sversion + 1; + dev->smart.magic = SSD_SMART_MAGIC; + + /* clear all tmp acc */ + for (i=0; inr_queue; i++) { + memset(&(dev->queue[i].io_stat), 0, sizeof(struct ssd_io_stat)); + memset(&(dev->queue[i].ecc_info), 0, sizeof(struct ssd_ecc_info)); + } + + atomic_set(&dev->tocnt, 0); + + /* clear tmp log info */ + memset(&dev->log_info, 0, sizeof(struct ssd_log_info)); + + do_gettimeofday(&tv); + dev->uptime = tv.tv_sec; + + /* clear alarm ? */ + //ssd_clear_alarm(dev); +out: + return ret; +} + +static int ssd_save_smart(struct ssd_device *dev) +{ + uint32_t off, size; + int i; + int ret = 0; + + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return 0; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return 0; + } + + if (!ssd_update_smart(dev, &dev->smart)) { + return 0; + } + + dev->smart.version++; + + for (i=0; irom_info.nr_smart; i++) { + off = dev->rom_info.smart_base + (dev->rom_info.smart_sz * i); + size = dev->rom_info.smart_sz; + + ret = ssd_spi_erase(dev, off, size); + if (ret) { + hio_warn("%s: info erase failed\n", dev->name); + goto out; + } + + size = sizeof(struct ssd_smart); + + ret = ssd_spi_write(dev, &dev->smart, off, size); + if (ret) { + hio_warn("%s: info write failed\n", dev->name); + goto out; + } + + //xx + } + +out: + return ret; +} + +static int ssd_init_smart(struct ssd_device *dev) +{ + struct ssd_smart *smart; + struct timeval tv; + uint32_t off, size; + int i; + int ret = 0; + + do_gettimeofday(&tv); + dev->uptime = tv.tv_sec; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return 0; + } + + smart = kmalloc(sizeof(struct ssd_smart) * SSD_ROM_NR_SMART_MAX, GFP_KERNEL); + if (!smart) { + ret = -ENOMEM; + goto out_nomem; + } + + memset(&dev->smart, 0, sizeof(struct ssd_smart)); + + /* read smart */ + for (i=0; irom_info.nr_smart; i++) { + memset(&smart[i], 0, sizeof(struct ssd_smart)); + + off = dev->rom_info.smart_base + (dev->rom_info.smart_sz * i); + size = sizeof(struct ssd_smart); + + ret = ssd_spi_read(dev, &smart[i], off, size); + if (ret) { + hio_warn("%s: info read failed\n", dev->name); + goto out; + } + + if (smart[i].magic != SSD_SMART_MAGIC) { + smart[i].magic = 0; + smart[i].version = 0; + continue; + } + + if (smart[i].version > dev->smart.version) { + memcpy(&dev->smart, &smart[i], sizeof(struct ssd_smart)); + } + } + + if (dev->smart.magic != SSD_SMART_MAGIC) { + /* first time power up */ + dev->smart.magic = SSD_SMART_MAGIC; + dev->smart.version = 1; + } + + /* check log info */ + { + struct ssd_log_info log_info; + struct ssd_log *log = (struct ssd_log *)dev->internal_log.log; + + memset(&log_info, 0, sizeof(struct ssd_log_info)); + + while (log_info.nr_log < dev->internal_log.nr_log) { + /* skip the volatile log info */ + if (SSD_LOG_SEU_FAULT != log->le.event && SSD_LOG_SEU_FAULT1 != log->le.event) { + log_info.stat[ssd_parse_log(dev, log, 0)]++; + } + + log_info.nr_log++; + log++; + } + + /* check */ + for (i=(SSD_LOG_NR_LEVEL-1); i>=0; i--) { + if (log_info.stat[i] > dev->smart.log_info.stat[i]) { + /* unclean */ + memcpy(&dev->smart.log_info, &log_info, sizeof(struct ssd_log_info)); + dev->smart.version++; + break; + } + } + } + + for (i=0; irom_info.nr_smart; i++) { + if (smart[i].magic == SSD_SMART_MAGIC && smart[i].version == dev->smart.version) { + continue; + } + + off = dev->rom_info.smart_base + (dev->rom_info.smart_sz * i); + size = dev->rom_info.smart_sz; + + ret = ssd_spi_erase(dev, off, size); + if (ret) { + hio_warn("%s: info erase failed\n", dev->name); + goto out; + } + + size = sizeof(struct ssd_smart); + ret = ssd_spi_write(dev, &dev->smart, off, size); + if (ret) { + hio_warn("%s: info write failed\n", dev->name); + goto out; + } + + //xx + } + + /* sync smart with alarm led */ + if (dev->smart.io_stat.nr_to || dev->smart.io_stat.nr_rwerr || dev->smart.log_info.stat[SSD_LOG_LEVEL_ERR]) { + hio_warn("%s: some fault found in the history info\n", dev->name); + ssd_set_alarm(dev); + } + +out: + kfree(smart); +out_nomem: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +/* bm */ +static int __ssd_bm_get_version(struct ssd_device *dev, uint16_t *ver) +{ + struct ssd_bm_manufacturer_data bm_md = {0}; + uint16_t sc_id = SSD_BM_SYSTEM_DATA_SUBCLASS_ID; + uint8_t cmd; + int ret = 0; + + if (!dev || !ver) { + return -EINVAL; + } + + mutex_lock(&dev->bm_mutex); + + cmd = SSD_BM_DATA_FLASH_SUBCLASS_ID; + ret = ssd_smbus_write_word(dev, SSD_BM_SLAVE_ADDRESS, cmd, (uint8_t *)&sc_id); + if (ret) { + goto out; + } + + cmd = SSD_BM_DATA_FLASH_SUBCLASS_ID_PAGE1; + ret = ssd_smbus_read_block(dev, SSD_BM_SLAVE_ADDRESS, cmd, sizeof(struct ssd_bm_manufacturer_data), (uint8_t *)&bm_md); + if (ret) { + goto out; + } + + if (bm_md.firmware_ver & 0xF000) { + ret = -EIO; + goto out; + } + + *ver = bm_md.firmware_ver; + +out: + mutex_unlock(&dev->bm_mutex); + return ret; +} + +static int ssd_bm_get_version(struct ssd_device *dev, uint16_t *ver) +{ + uint16_t tmp = 0; + int i = SSD_BM_RETRY_MAX; + int ret = 0; + + while (i-- > 0) { + ret = __ssd_bm_get_version(dev, &tmp); + if (!ret) { + break; + } + } + if (ret) { + return ret; + } + + *ver = tmp; + + return 0; +} + +static int __ssd_bm_nr_cap(struct ssd_device *dev, int *nr_cap) +{ + struct ssd_bm_configuration_registers bm_cr; + uint16_t sc_id = SSD_BM_CONFIGURATION_REGISTERS_ID; + uint8_t cmd; + int ret; + + mutex_lock(&dev->bm_mutex); + + cmd = SSD_BM_DATA_FLASH_SUBCLASS_ID; + ret = ssd_smbus_write_word(dev, SSD_BM_SLAVE_ADDRESS, cmd, (uint8_t *)&sc_id); + if (ret) { + goto out; + } + + cmd = SSD_BM_DATA_FLASH_SUBCLASS_ID_PAGE1; + ret = ssd_smbus_read_block(dev, SSD_BM_SLAVE_ADDRESS, cmd, sizeof(struct ssd_bm_configuration_registers), (uint8_t *)&bm_cr); + if (ret) { + goto out; + } + + if (bm_cr.operation_cfg.cc == 0 || bm_cr.operation_cfg.cc > 4) { + ret = -EIO; + goto out; + } + + *nr_cap = bm_cr.operation_cfg.cc + 1; + +out: + mutex_unlock(&dev->bm_mutex); + return ret; +} + +static int ssd_bm_nr_cap(struct ssd_device *dev, int *nr_cap) +{ + int tmp = 0; + int i = SSD_BM_RETRY_MAX; + int ret = 0; + + while (i-- > 0) { + ret = __ssd_bm_nr_cap(dev, &tmp); + if (!ret) { + break; + } + } + if (ret) { + return ret; + } + + *nr_cap = tmp; + + return 0; +} + +static int ssd_bm_enter_cap_learning(struct ssd_device *dev) +{ + uint16_t buf = SSD_BM_ENTER_CAP_LEARNING; + uint8_t cmd = SSD_BM_MANUFACTURERACCESS; + int ret; + + ret = ssd_smbus_write_word(dev, SSD_BM_SLAVE_ADDRESS, cmd, (uint8_t *)&buf); + if (ret) { + goto out; + } + +out: + return ret; +} + +static int ssd_bm_get_sfstatus(struct ssd_device *dev, uint16_t *status) +{ + uint16_t val = 0; + uint8_t cmd = SSD_BM_SAFETYSTATUS; + int ret; + + ret = ssd_smbus_read_word(dev, SSD_BM_SLAVE_ADDRESS, cmd, (uint8_t *)&val); + if (ret) { + goto out; + } + + *status = val; +out: + return ret; +} + +static int ssd_bm_get_opstatus(struct ssd_device *dev, uint16_t *status) +{ + uint16_t val = 0; + uint8_t cmd = SSD_BM_OPERATIONSTATUS; + int ret; + + ret = ssd_smbus_read_word(dev, SSD_BM_SLAVE_ADDRESS, cmd, (uint8_t *)&val); + if (ret) { + goto out; + } + + *status = val; +out: + return ret; +} + +static int ssd_get_bmstruct(struct ssd_device *dev, struct ssd_bm *bm_status_out) +{ + struct sbs_cmd *bm_sbs = ssd_bm_sbs; + struct ssd_bm bm_status; + uint8_t buf[2] = {0, }; + uint16_t val = 0; + uint16_t cval; + int ret = 0; + + memset(&bm_status, 0, sizeof(struct ssd_bm)); + + while (bm_sbs->desc != NULL) { + switch (bm_sbs->size) { + case SBS_SIZE_BYTE: + ret = ssd_smbus_read_byte(dev, SSD_BM_SLAVE_ADDRESS, bm_sbs->cmd, buf); + if (ret) { + //printf("Error: smbus read byte %#x\n", bm_sbs->cmd); + goto out; + } + val = buf[0]; + break; + case SBS_SIZE_WORD: + ret = ssd_smbus_read_word(dev, SSD_BM_SLAVE_ADDRESS, bm_sbs->cmd, (uint8_t *)&val); + if (ret) { + //printf("Error: smbus read word %#x\n", bm_sbs->cmd); + goto out; + } + //val = *(uint16_t *)buf; + break; + default: + ret = -1; + goto out; + break; + } + + switch (bm_sbs->unit) { + case SBS_UNIT_VALUE: + *(uint16_t *)bm_var(&bm_status, bm_sbs->off) = val & bm_sbs->mask; + break; + case SBS_UNIT_TEMPERATURE: + cval = (uint16_t)(val - 2731) / 10; + *(uint16_t *)bm_var(&bm_status, bm_sbs->off) = cval; + break; + case SBS_UNIT_VOLTAGE: + *(uint16_t *)bm_var(&bm_status, bm_sbs->off) = val; + break; + case SBS_UNIT_CURRENT: + *(uint16_t *)bm_var(&bm_status, bm_sbs->off) = val; + break; + case SBS_UNIT_ESR: + *(uint16_t *)bm_var(&bm_status, bm_sbs->off) = val; + break; + case SBS_UNIT_PERCENT: + *(uint16_t *)bm_var(&bm_status, bm_sbs->off) = val; + break; + case SBS_UNIT_CAPACITANCE: + *(uint16_t *)bm_var(&bm_status, bm_sbs->off) = val; + break; + default: + ret = -1; + goto out; + break; + } + + bm_sbs++; + } + + memcpy(bm_status_out, &bm_status, sizeof(struct ssd_bm)); + +out: + return ret; +} + +static int __ssd_bm_status(struct ssd_device *dev, int *status) +{ + struct ssd_bm bm_status = {0}; + int nr_cap = 0; + int i; + int ret = 0; + + ret = ssd_get_bmstruct(dev, &bm_status); + if (ret) { + goto out; + } + + /* capacitor voltage */ + ret = ssd_bm_nr_cap(dev, &nr_cap); + if (ret) { + goto out; + } + + for (i=0; i> 12) & 0x1)) { + *status = SSD_BMSTATUS_CHARGING; + }else{ + *status = SSD_BMSTATUS_OK; + } + +out: + return ret; +} + +static void ssd_set_flush_timeout(struct ssd_device *dev, int mode); + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) +static void ssd_bm_worker(void *data) +{ + struct ssd_device *dev = (struct ssd_device *)data; +#else +static void ssd_bm_worker(struct work_struct *work) +{ + struct ssd_device *dev = container_of(work, struct ssd_device, bm_work); +#endif + + uint16_t opstatus; + int ret = 0; + + if (mode != SSD_DRV_MODE_STANDARD) { + return; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_1) { + return; + } + + if (dev->hw_info_ext.plp_type != SSD_PLP_SCAP) { + return; + } + + ret = ssd_bm_get_opstatus(dev, &opstatus); + if (ret) { + hio_warn("%s: get bm operationstatus failed\n", dev->name); + return; + } + + /* need cap learning ? */ + if (!(opstatus & 0xF0)) { + ret = ssd_bm_enter_cap_learning(dev); + if (ret) { + hio_warn("%s: enter capacitance learning failed\n", dev->name); + return; + } + } +} + +static void ssd_bm_routine_start(void *data) +{ + struct ssd_device *dev; + + if (!data) { + return; + } + dev = data; + + if (test_bit(SSD_INIT_WORKQ, &dev->state)) { + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + queue_work(dev->workq, &dev->bm_work); + } else { + queue_work(dev->workq, &dev->capmon_work); + } + } +} + +/* CAP */ +static int ssd_do_cap_learn(struct ssd_device *dev, uint32_t *cap) +{ + uint32_t u1, u2, t; + uint16_t val = 0; + int wait = 0; + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + *cap = 0; + return 0; + } + + if (dev->hw_info_ext.form_factor == SSD_FORM_FACTOR_FHHL && dev->hw_info.pcb_ver < 'B') { + *cap = 0; + return 0; + } + + /* make sure the lm80 voltage value is updated */ + msleep(SSD_LM80_CONV_INTERVAL); + + /* check if full charged */ + wait = 0; + for (;;) { + ret = ssd_smbus_read_word(dev, SSD_SENSOR_LM80_SADDRESS, SSD_PL_CAP_U1, (uint8_t *)&val); + if (ret) { + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, SSD_SENSOR_LM80_SADDRESS); + } + goto out; + } + u1 = SSD_LM80_CONVERT_VOLT(u16_swap(val)); + if (SSD_PL_CAP_VOLT(u1) >= SSD_PL_CAP_VOLT_FULL) { + break; + } + + wait++; + if (wait > SSD_PL_CAP_CHARGE_MAX_WAIT) { + ret = -ETIMEDOUT; + goto out; + } + msleep(SSD_PL_CAP_CHARGE_WAIT); + } + + ret = ssd_smbus_read_word(dev, SSD_SENSOR_LM80_SADDRESS, SSD_PL_CAP_U2, (uint8_t *)&val); + if (ret) { + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, SSD_SENSOR_LM80_SADDRESS); + } + goto out; + } + u2 = SSD_LM80_CONVERT_VOLT(u16_swap(val)); + + if (u1 == u2) { + ret = -EINVAL; + goto out; + } + + /* enter cap learn */ + ssd_reg32_write(dev->ctrlp + SSD_PL_CAP_LEARN_REG, 0x1); + + wait = 0; + for (;;) { + msleep(SSD_PL_CAP_LEARN_WAIT); + + t = ssd_reg32_read(dev->ctrlp + SSD_PL_CAP_LEARN_REG); + if (!((t >> 1) & 0x1)) { + break; + } + + wait++; + if (wait > SSD_PL_CAP_LEARN_MAX_WAIT) { + ret = -ETIMEDOUT; + goto out; + } + } + + if ((t >> 4) & 0x1) { + ret = -ETIMEDOUT; + goto out; + } + + t = (t >> 8); + if (0 == t) { + ret = -EINVAL; + goto out; + } + + *cap = SSD_PL_CAP_LEARN(u1, u2, t); + +out: + return ret; +} + +static int ssd_cap_learn(struct ssd_device *dev, uint32_t *cap) +{ + int ret = 0; + + if (!dev || !cap) { + return -EINVAL; + } + + mutex_lock(&dev->bm_mutex); + + ssd_stop_workq(dev); + + ret = ssd_do_cap_learn(dev, cap); + if (ret) { + ssd_gen_swlog(dev, SSD_LOG_CAP_LEARN_FAULT, 0); + goto out; + } + + ssd_gen_swlog(dev, SSD_LOG_CAP_STATUS, *cap); + +out: + ssd_start_workq(dev); + mutex_unlock(&dev->bm_mutex); + + return ret; +} + +static int ssd_check_pl_cap(struct ssd_device *dev) +{ + uint32_t u1; + uint16_t val = 0; + uint8_t low = 0; + int wait = 0; + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + return 0; + } + + if (dev->hw_info_ext.form_factor == SSD_FORM_FACTOR_FHHL && dev->hw_info.pcb_ver < 'B') { + return 0; + } + + /* cap ready ? */ + wait = 0; + for (;;) { + ret = ssd_smbus_read_word(dev, SSD_SENSOR_LM80_SADDRESS, SSD_PL_CAP_U1, (uint8_t *)&val); + if (ret) { + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, SSD_SENSOR_LM80_SADDRESS); + } + goto out; + } + u1 = SSD_LM80_CONVERT_VOLT(u16_swap(val)); + if (SSD_PL_CAP_VOLT(u1) >= SSD_PL_CAP_VOLT_READY) { + break; + } + + wait++; + if (wait > SSD_PL_CAP_CHARGE_MAX_WAIT) { + ret = -ETIMEDOUT; + ssd_gen_swlog(dev, SSD_LOG_CAP_VOLT_FAULT, SSD_PL_CAP_VOLT(u1)); + goto out; + } + msleep(SSD_PL_CAP_CHARGE_WAIT); + } + + low = ssd_lm80_limit[SSD_LM80_IN_CAP].low; + ret = ssd_smbus_write_byte(dev, SSD_SENSOR_LM80_SADDRESS, SSD_LM80_REG_IN_MIN(SSD_LM80_IN_CAP), &low); + if (ret) { + goto out; + } + + /* enable cap INx */ + ret = ssd_lm80_enable_in(dev, SSD_SENSOR_LM80_SADDRESS, SSD_LM80_IN_CAP); + if (ret) { + if (!test_and_set_bit(SSD_HWMON_SENSOR(SSD_SENSOR_LM80), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_SENSOR_FAULT, SSD_SENSOR_LM80_SADDRESS); + } + goto out; + } + +out: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +static int ssd_check_pl_cap_fast(struct ssd_device *dev) +{ + uint32_t u1; + uint16_t val = 0; + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + return 0; + } + + if (dev->hw_info_ext.form_factor == SSD_FORM_FACTOR_FHHL && dev->hw_info.pcb_ver < 'B') { + return 0; + } + + /* cap ready ? */ + ret = ssd_smbus_read_word(dev, SSD_SENSOR_LM80_SADDRESS, SSD_PL_CAP_U1, (uint8_t *)&val); + if (ret) { + goto out; + } + u1 = SSD_LM80_CONVERT_VOLT(u16_swap(val)); + if (SSD_PL_CAP_VOLT(u1) < SSD_PL_CAP_VOLT_READY) { + ret = 1; + } + +out: + return ret; +} + +static int ssd_init_pl_cap(struct ssd_device *dev) +{ + int ret = 0; + + /* set here: user write mode */ + dev->user_wmode = wmode; + + mutex_init(&dev->bm_mutex); + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + uint32_t val; + val = ssd_reg32_read(dev->ctrlp + SSD_BM_FAULT_REG); + if ((val >> 1) & 0x1) { + (void)test_and_set_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon); + } + } else { + ret = ssd_check_pl_cap(dev); + if (ret) { + (void)test_and_set_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon); + } + } + + return 0; +} + +/* label */ +static void __end_str(char *str, int len) +{ + int i; + + for(i=0; irom_info.label_base; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + size = sizeof(struct ssd_label); + + /* read label */ + ret = ssd_spi_read(dev, &dev->label, off, size); + if (ret) { + memset(&dev->label, 0, size); + goto out; + } + + __end_str(dev->label.date, SSD_LABEL_FIELD_SZ); + __end_str(dev->label.sn, SSD_LABEL_FIELD_SZ); + __end_str(dev->label.part, SSD_LABEL_FIELD_SZ); + __end_str(dev->label.desc, SSD_LABEL_FIELD_SZ); + __end_str(dev->label.other, SSD_LABEL_FIELD_SZ); + __end_str(dev->label.maf, SSD_LABEL_FIELD_SZ); + } else { + size = sizeof(struct ssd_labelv3); + + /* read label */ + ret = ssd_spi_read(dev, &dev->labelv3, off, size); + if (ret) { + memset(&dev->labelv3, 0, size); + goto out; + } + + __end_str(dev->labelv3.boardtype, SSD_LABEL_FIELD_SZ); + __end_str(dev->labelv3.barcode, SSD_LABEL_FIELD_SZ); + __end_str(dev->labelv3.item, SSD_LABEL_FIELD_SZ); + __end_str(dev->labelv3.description, SSD_LABEL_DESC_SZ); + __end_str(dev->labelv3.manufactured, SSD_LABEL_FIELD_SZ); + __end_str(dev->labelv3.vendorname, SSD_LABEL_FIELD_SZ); + __end_str(dev->labelv3.issuenumber, SSD_LABEL_FIELD_SZ); + __end_str(dev->labelv3.cleicode, SSD_LABEL_FIELD_SZ); + __end_str(dev->labelv3.bom, SSD_LABEL_FIELD_SZ); + } + +out: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +int ssd_get_label(struct block_device *bdev, struct ssd_label *label) +{ + struct ssd_device *dev; + + if (!bdev || !label || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + memset(label, 0, sizeof(struct ssd_label)); + memcpy(label->date, dev->labelv3.manufactured, SSD_LABEL_FIELD_SZ); + memcpy(label->sn, dev->labelv3.barcode, SSD_LABEL_FIELD_SZ); + memcpy(label->desc, dev->labelv3.boardtype, SSD_LABEL_FIELD_SZ); + memcpy(label->maf, dev->labelv3.vendorname, SSD_LABEL_FIELD_SZ); + } else { + memcpy(label, &dev->label, sizeof(struct ssd_label)); + } + + return 0; +} + +static int __ssd_get_version(struct ssd_device *dev, struct ssd_version_info *ver) +{ + uint16_t bm_ver = 0; + int ret = 0; + + if (dev->protocol_info.ver > SSD_PROTOCOL_V3 && dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + ret = ssd_bm_get_version(dev, &bm_ver); + if(ret){ + goto out; + } + } + + ver->bridge_ver = dev->hw_info.bridge_ver; + ver->ctrl_ver = dev->hw_info.ctrl_ver; + ver->bm_ver = bm_ver; + ver->pcb_ver = dev->hw_info.pcb_ver; + ver->upper_pcb_ver = dev->hw_info.upper_pcb_ver; + +out: + return ret; + +} + +int ssd_get_version(struct block_device *bdev, struct ssd_version_info *ver) +{ + struct ssd_device *dev; + int ret; + + if (!bdev || !ver || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + + mutex_lock(&dev->fw_mutex); + ret = __ssd_get_version(dev, ver); + mutex_unlock(&dev->fw_mutex); + + return ret; +} + +static int __ssd_get_temperature(struct ssd_device *dev, int *temp) +{ + uint64_t val; + uint32_t off; + int max = -300; + int cur; + int i; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + *temp = 0; + return 0; + } + + if (finject) { + if (dev->db_info.type == SSD_DEBUG_LOG && + (dev->db_info.data.log.event == SSD_LOG_OVER_TEMP || + dev->db_info.data.log.event == SSD_LOG_NORMAL_TEMP || + dev->db_info.data.log.event == SSD_LOG_WARN_TEMP)) { + *temp = (int)dev->db_info.data.log.extra; + return 0; + } + } + + for (i=0; ihw_info.nr_ctrl; i++) { + off = SSD_CTRL_TEMP_REG0 + i * sizeof(uint64_t); + + val = ssd_reg_read(dev->ctrlp + off); + if (val == 0xffffffffffffffffull) { + continue; + } + + cur = (int)CUR_TEMP(val); + if (cur >= max) { + max = cur; + } + } + + *temp = max; + + return 0; +} + +int ssd_get_temperature(struct block_device *bdev, int *temp) +{ + struct ssd_device *dev; + int ret; + + if (!bdev || !temp || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + + + mutex_lock(&dev->fw_mutex); + ret = __ssd_get_temperature(dev, temp); + mutex_unlock(&dev->fw_mutex); + + return ret; +} + +int ssd_set_otprotect(struct block_device *bdev, int otprotect) + { + struct ssd_device *dev; + + if (!bdev || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + ssd_set_ot_protect(dev, !!otprotect); + + return 0; + } + +int ssd_bm_status(struct block_device *bdev, int *status) +{ + struct ssd_device *dev; + int ret = 0; + + if (!bdev || !status || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + + mutex_lock(&dev->fw_mutex); + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + if (test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + *status = SSD_BMSTATUS_WARNING; + } else { + *status = SSD_BMSTATUS_OK; + } + } else if(dev->protocol_info.ver > SSD_PROTOCOL_V3) { + ret = __ssd_bm_status(dev, status); + } else { + *status = SSD_BMSTATUS_OK; + } + mutex_unlock(&dev->fw_mutex); + + return ret; +} + +int ssd_get_pciaddr(struct block_device *bdev, struct pci_addr *paddr) +{ + struct ssd_device *dev; + + if (!bdev || !paddr || !bdev->bd_disk) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + + paddr->domain = pci_domain_nr(dev->pdev->bus); + paddr->bus = dev->pdev->bus->number; + paddr->slot = PCI_SLOT(dev->pdev->devfn); + paddr->func= PCI_FUNC(dev->pdev->devfn); + + return 0; +} + +/* acc */ +static int ssd_bb_acc(struct ssd_device *dev, struct ssd_acc_info *acc) +{ + uint32_t val; + int ctrl, chip; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_1) { + return -EOPNOTSUPP; + } + + acc->threshold_l1 = ssd_reg32_read(dev->ctrlp + SSD_BB_THRESHOLD_L1_REG); + if (0xffffffffull == acc->threshold_l1) { + return -EIO; + } + acc->threshold_l2 = ssd_reg32_read(dev->ctrlp + SSD_BB_THRESHOLD_L2_REG); + if (0xffffffffull == acc->threshold_l2) { + return -EIO; + } + acc->val = 0; + + for (ctrl=0; ctrlhw_info.nr_ctrl; ctrl++) { + for (chip=0; chiphw_info.nr_chip; chip++) { + val = ssd_reg32_read(dev->ctrlp + SSD_BB_ACC_REG0 + (SSD_CTRL_REG_ZONE_SZ * ctrl) + (SSD_BB_ACC_REG_SZ * chip)); + if (0xffffffffull == acc->val) { + return -EIO; + } + if (val > acc->val) { + acc->val = val; + } + } + } + + return 0; +} + +static int ssd_ec_acc(struct ssd_device *dev, struct ssd_acc_info *acc) +{ + uint32_t val; + int ctrl, chip; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_1) { + return -EOPNOTSUPP; + } + + acc->threshold_l1 = ssd_reg32_read(dev->ctrlp + SSD_EC_THRESHOLD_L1_REG); + if (0xffffffffull == acc->threshold_l1) { + return -EIO; + } + acc->threshold_l2 = ssd_reg32_read(dev->ctrlp + SSD_EC_THRESHOLD_L2_REG); + if (0xffffffffull == acc->threshold_l2) { + return -EIO; + } + acc->val = 0; + + for (ctrl=0; ctrlhw_info.nr_ctrl; ctrl++) { + for (chip=0; chiphw_info.nr_chip; chip++) { + val = ssd_reg32_read(dev->ctrlp + SSD_EC_ACC_REG0 + (SSD_CTRL_REG_ZONE_SZ * ctrl) + (SSD_EC_ACC_REG_SZ * chip)); + if (0xffffffffull == acc->val) { + return -EIO; + } + + if (val > acc->val) { + acc->val = val; + } + } + } + + return 0; +} + + +/* ram r&w */ +static int ssd_ram_read_4k(struct ssd_device *dev, void *buf, size_t length, loff_t ofs, int ctrl_idx) +{ + struct ssd_ram_op_msg *msg; + dma_addr_t buf_dma; + size_t len = length; + loff_t ofs_w = ofs; + int ret = 0; + + if (ctrl_idx >= dev->hw_info.nr_ctrl || (uint64_t)(ofs + length) > dev->hw_info.ram_size + || !length || length > dev->hw_info.ram_max_len + || (length & (dev->hw_info.ram_align - 1)) != 0 || ((uint64_t)ofs & (dev->hw_info.ram_align - 1)) != 0) { + return -EINVAL; + } + + len /= dev->hw_info.ram_align; + do_div(ofs_w, dev->hw_info.ram_align); + + buf_dma = pci_map_single(dev->pdev, buf, length, PCI_DMA_FROMDEVICE); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,26)) + ret = dma_mapping_error(buf_dma); +#else + ret = dma_mapping_error(&(dev->pdev->dev), buf_dma); +#endif + if (ret) { + hio_warn("%s: unable to map read DMA buffer\n", dev->name); + goto out_dma_mapping; + } + + msg = (struct ssd_ram_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_RAM_READ; + msg->ctrl_idx = ctrl_idx; + msg->start = (uint32_t)ofs_w; + msg->length = len; + msg->buf = buf_dma; + + ret = ssd_do_request(dev, READ, msg, NULL); + ssd_put_dmsg(msg); + + pci_unmap_single(dev->pdev, buf_dma, length, PCI_DMA_FROMDEVICE); + +out_dma_mapping: + return ret; +} + +static int ssd_ram_write_4k(struct ssd_device *dev, void *buf, size_t length, loff_t ofs, int ctrl_idx) +{ + struct ssd_ram_op_msg *msg; + dma_addr_t buf_dma; + size_t len = length; + loff_t ofs_w = ofs; + int ret = 0; + + if (ctrl_idx >= dev->hw_info.nr_ctrl || (uint64_t)(ofs + length) > dev->hw_info.ram_size + || !length || length > dev->hw_info.ram_max_len + || (length & (dev->hw_info.ram_align - 1)) != 0 || ((uint64_t)ofs & (dev->hw_info.ram_align - 1)) != 0) { + return -EINVAL; + } + + len /= dev->hw_info.ram_align; + do_div(ofs_w, dev->hw_info.ram_align); + + buf_dma = pci_map_single(dev->pdev, buf, length, PCI_DMA_TODEVICE); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,26)) + ret = dma_mapping_error(buf_dma); +#else + ret = dma_mapping_error(&(dev->pdev->dev), buf_dma); +#endif + if (ret) { + hio_warn("%s: unable to map write DMA buffer\n", dev->name); + goto out_dma_mapping; + } + + msg = (struct ssd_ram_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_RAM_WRITE; + msg->ctrl_idx = ctrl_idx; + msg->start = (uint32_t)ofs_w; + msg->length = len; + msg->buf = buf_dma; + + ret = ssd_do_request(dev, WRITE, msg, NULL); + ssd_put_dmsg(msg); + + pci_unmap_single(dev->pdev, buf_dma, length, PCI_DMA_TODEVICE); + +out_dma_mapping: + return ret; + +} + +static int ssd_ram_read(struct ssd_device *dev, void *buf, size_t length, loff_t ofs, int ctrl_idx) +{ + int left = length; + size_t len; + loff_t off = ofs; + int ret = 0; + + if (ctrl_idx >= dev->hw_info.nr_ctrl || (uint64_t)(ofs + length) > dev->hw_info.ram_size || !length + || (length & (dev->hw_info.ram_align - 1)) != 0 || ((uint64_t)ofs & (dev->hw_info.ram_align - 1)) != 0) { + return -EINVAL; + } + + while (left > 0) { + len = dev->hw_info.ram_max_len; + if (left < (int)dev->hw_info.ram_max_len) { + len = left; + } + + ret = ssd_ram_read_4k(dev, buf, len, off, ctrl_idx); + if (ret) { + break; + } + + left -= len; + off += len; + buf += len; + } + + return ret; +} + +static int ssd_ram_write(struct ssd_device *dev, void *buf, size_t length, loff_t ofs, int ctrl_idx) +{ + int left = length; + size_t len; + loff_t off = ofs; + int ret = 0; + + if (ctrl_idx >= dev->hw_info.nr_ctrl || (uint64_t)(ofs + length) > dev->hw_info.ram_size || !length + || (length & (dev->hw_info.ram_align - 1)) != 0 || ((uint64_t)ofs & (dev->hw_info.ram_align - 1)) != 0) { + return -EINVAL; + } + + while (left > 0) { + len = dev->hw_info.ram_max_len; + if (left < (int)dev->hw_info.ram_max_len) { + len = left; + } + + ret = ssd_ram_write_4k(dev, buf, len, off, ctrl_idx); + if (ret) { + break; + } + + left -= len; + off += len; + buf += len; + } + + return ret; +} + + +/* flash op */ +static int ssd_check_flash(struct ssd_device *dev, int flash, int page, int ctrl_idx) +{ + int cur_ch = flash % dev->hw_info.max_ch; + int cur_chip = flash /dev->hw_info.max_ch; + + if (ctrl_idx >= dev->hw_info.nr_ctrl) { + return -EINVAL; + } + + if (cur_ch >= dev->hw_info.nr_ch || cur_chip >= dev->hw_info.nr_chip) { + return -EINVAL; + } + + if (page >= (int)(dev->hw_info.block_count * dev->hw_info.page_count)) { + return -EINVAL; + } + return 0; +} + +static int ssd_nand_read_id(struct ssd_device *dev, void *id, int flash, int chip, int ctrl_idx) +{ + struct ssd_nand_op_msg *msg; + dma_addr_t buf_dma; + int ret = 0; + + if (unlikely(!id)) + return -EINVAL; + + buf_dma = pci_map_single(dev->pdev, id, SSD_NAND_ID_BUFF_SZ, PCI_DMA_FROMDEVICE); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,26)) + ret = dma_mapping_error(buf_dma); +#else + ret = dma_mapping_error(&(dev->pdev->dev), buf_dma); +#endif + if (ret) { + hio_warn("%s: unable to map read DMA buffer\n", dev->name); + goto out_dma_mapping; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + flash = ((uint32_t)flash << 1) | (uint32_t)chip; + chip = 0; + } + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_NAND_READ_ID; + msg->chip_no = flash; + msg->chip_ce = chip; + msg->ctrl_idx = ctrl_idx; + msg->buf = buf_dma; + + ret = ssd_do_request(dev, READ, msg, NULL); + ssd_put_dmsg(msg); + + pci_unmap_single(dev->pdev, buf_dma, SSD_NAND_ID_BUFF_SZ, PCI_DMA_FROMDEVICE); + +out_dma_mapping: + return ret; +} + +#if 0 +static int ssd_nand_read(struct ssd_device *dev, void *buf, + int flash, int chip, int page, int page_count, int ctrl_idx) +{ + struct ssd_nand_op_msg *msg; + dma_addr_t buf_dma; + int length; + int ret = 0; + + if (!buf) { + return -EINVAL; + } + + if ((page + page_count) > dev->hw_info.block_count*dev->hw_info.page_count) { + return -EINVAL; + } + + ret = ssd_check_flash(dev, flash, page, ctrl_idx); + if (ret) { + return ret; + } + + length = page_count * dev->hw_info.page_size; + + buf_dma = pci_map_single(dev->pdev, buf, length, PCI_DMA_FROMDEVICE); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,26)) + ret = dma_mapping_error(buf_dma); +#else + ret = dma_mapping_error(&(dev->pdev->dev), buf_dma); +#endif + if (ret) { + hio_warn("%s: unable to map read DMA buffer\n", dev->name); + goto out_dma_mapping; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + flash = (flash << 1) | chip; + chip = 0; + } + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_NAND_READ; + msg->ctrl_idx = ctrl_idx; + msg->chip_no = flash; + msg->chip_ce = chip; + msg->page_no = page; + msg->page_count = page_count; + msg->buf = buf_dma; + + ret = ssd_do_request(dev, READ, msg, NULL); + ssd_put_dmsg(msg); + + pci_unmap_single(dev->pdev, buf_dma, length, PCI_DMA_FROMDEVICE); + +out_dma_mapping: + return ret; +} +#endif + +static int ssd_nand_read_w_oob(struct ssd_device *dev, void *buf, + int flash, int chip, int page, int count, int ctrl_idx) +{ + struct ssd_nand_op_msg *msg; + dma_addr_t buf_dma; + int length; + int ret = 0; + + if (!buf) { + return -EINVAL; + } + + if ((page + count) > (int)(dev->hw_info.block_count * dev->hw_info.page_count)) { + return -EINVAL; + } + + ret = ssd_check_flash(dev, flash, page, ctrl_idx); + if (ret) { + return ret; + } + + length = count * (dev->hw_info.page_size + dev->hw_info.oob_size); + + buf_dma = pci_map_single(dev->pdev, buf, length, PCI_DMA_FROMDEVICE); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,26)) + ret = dma_mapping_error(buf_dma); +#else + ret = dma_mapping_error(&(dev->pdev->dev), buf_dma); +#endif + if (ret) { + hio_warn("%s: unable to map read DMA buffer\n", dev->name); + goto out_dma_mapping; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + flash = ((uint32_t)flash << 1) | (uint32_t)chip; + chip = 0; + } + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_NAND_READ_WOOB; + msg->ctrl_idx = ctrl_idx; + msg->chip_no = flash; + msg->chip_ce = chip; + msg->page_no = page; + msg->page_count = count; + msg->buf = buf_dma; + + ret = ssd_do_request(dev, READ, msg, NULL); + ssd_put_dmsg(msg); + + pci_unmap_single(dev->pdev, buf_dma, length, PCI_DMA_FROMDEVICE); + +out_dma_mapping: + return ret; +} + +/* write 1 page */ +static int ssd_nand_write(struct ssd_device *dev, void *buf, + int flash, int chip, int page, int count, int ctrl_idx) +{ + struct ssd_nand_op_msg *msg; + dma_addr_t buf_dma; + int length; + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + return -EINVAL; + } + + if (!buf) { + return -EINVAL; + } + + if (count != 1) { + return -EINVAL; + } + + ret = ssd_check_flash(dev, flash, page, ctrl_idx); + if (ret) { + return ret; + } + + length = count * (dev->hw_info.page_size + dev->hw_info.oob_size); + + /* write data to ram */ + /*ret = ssd_ram_write(dev, buf, length, dev->hw_info.nand_wbuff_base, ctrl_idx); + if (ret) { + return ret; + }*/ + + buf_dma = pci_map_single(dev->pdev, buf, length, PCI_DMA_TODEVICE); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,26)) + ret = dma_mapping_error(buf_dma); +#else + ret = dma_mapping_error(&(dev->pdev->dev), buf_dma); +#endif + if (ret) { + hio_warn("%s: unable to map write DMA buffer\n", dev->name); + goto out_dma_mapping; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + flash = ((uint32_t)flash << 1) | (uint32_t)chip; + chip = 0; + } + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_NAND_WRITE; + msg->ctrl_idx = ctrl_idx; + msg->chip_no = flash; + msg->chip_ce = chip; + + msg->page_no = page; + msg->page_count = count; + msg->buf = buf_dma; + + ret = ssd_do_request(dev, WRITE, msg, NULL); + ssd_put_dmsg(msg); + + pci_unmap_single(dev->pdev, buf_dma, length, PCI_DMA_TODEVICE); + +out_dma_mapping: + return ret; +} + +static int ssd_nand_erase(struct ssd_device *dev, int flash, int chip, int page, int ctrl_idx) +{ + struct ssd_nand_op_msg *msg; + int ret = 0; + + ret = ssd_check_flash(dev, flash, page, ctrl_idx); + if (ret) { + return ret; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + flash = ((uint32_t)flash << 1) | (uint32_t)chip; + chip = 0; + } + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_NAND_ERASE; + msg->ctrl_idx = ctrl_idx; + msg->chip_no = flash; + msg->chip_ce = chip; + msg->page_no = page; + + ret = ssd_do_request(dev, WRITE, msg, NULL); + ssd_put_dmsg(msg); + + return ret; +} + +static int ssd_update_bbt(struct ssd_device *dev, int flash, int ctrl_idx) +{ + struct ssd_nand_op_msg *msg; + struct ssd_flush_msg *fmsg; + int ret = 0; + + ret = ssd_check_flash(dev, flash, 0, ctrl_idx); + if (ret) { + return ret; + } + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + fmsg = (struct ssd_flush_msg *)msg; + + fmsg->fun = SSD_FUNC_FLUSH; + fmsg->flag = 0x1; + fmsg->flash = flash; + fmsg->ctrl_idx = ctrl_idx; + } else { + msg->fun = SSD_FUNC_FLUSH; + msg->flag = 0x1; + msg->chip_no = flash; + msg->ctrl_idx = ctrl_idx; + } + + ret = ssd_do_request(dev, WRITE, msg, NULL); + ssd_put_dmsg(msg); + + return ret; +} + +/* flash controller init state */ +static int __ssd_check_init_state(struct ssd_device *dev) +{ + uint32_t *init_state = NULL; + int reg_base, reg_sz; + int max_wait = SSD_INIT_MAX_WAIT; + int init_wait = 0; + int i, j, k; + int ch_start = 0; + +/* + for (i=0; ihw_info.nr_ctrl; i++) { + ssd_reg32_write(dev->ctrlp + SSD_CTRL_TEST_REG0 + i * 8, test_data); + read_data = ssd_reg32_read(dev->ctrlp + SSD_CTRL_TEST_REG0 + i * 8); + if (read_data == ~test_data) { + //dev->hw_info.nr_ctrl++; + dev->hw_info.nr_ctrl_map |= 1<ctrlp + SSD_READY_REG); + j=0; + for (i=0; ihw_info.nr_ctrl; i++) { + if (((read_data>>i) & 0x1) == 0) { + j++; + } + } + + if (dev->hw_info.nr_ctrl != j) { + printk(KERN_WARNING "%s: nr_ctrl mismatch: %d %d\n", dev->name, dev->hw_info.nr_ctrl, j); + return -1; + } +*/ + +/* + init_state = ssd_reg_read(dev->ctrlp + SSD_FLASH_INFO_REG0); + for (j=1; jhw_info.nr_ctrl;j++) { + if (init_state != ssd_reg_read(dev->ctrlp + SSD_FLASH_INFO_REG0 + j*8)) { + printk(KERN_WARNING "SSD_FLASH_INFO_REG[%d], not match\n", j); + return -1; + } + } +*/ + +/* init_state = ssd_reg_read(dev->ctrlp + SSD_CHIP_INFO_REG0); + for (j=1; jhw_info.nr_ctrl; j++) { + if (init_state != ssd_reg_read(dev->ctrlp + SSD_CHIP_INFO_REG0 + j*16)) { + printk(KERN_WARNING "SSD_CHIP_INFO_REG Lo [%d], not match\n", j); + return -1; + } + } + + init_state = ssd_reg_read(dev->ctrlp + SSD_CHIP_INFO_REG0 + 8); + for (j=1; jhw_info.nr_ctrl; j++) { + if (init_state != ssd_reg_read(dev->ctrlp + SSD_CHIP_INFO_REG0 + 8 + j*16)) { + printk(KERN_WARNING "SSD_CHIP_INFO_REG Hi [%d], not match\n", j); + return -1; + } + } +*/ + + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + max_wait = SSD_INIT_MAX_WAIT_V3_2; + } + + reg_base = dev->protocol_info.init_state_reg; + reg_sz = dev->protocol_info.init_state_reg_sz; + + init_state = (uint32_t *)kmalloc(reg_sz, GFP_KERNEL); + if (!init_state) { + return -ENOMEM; + } + + for (i=0; ihw_info.nr_ctrl; i++) { +check_init: + for (j=0, k=0; jctrlp + reg_base + j); + } + + if (dev->protocol_info.ver > SSD_PROTOCOL_V3) { + /* just check the last bit, no need to check all channel */ + ch_start = dev->hw_info.max_ch - 1; + } else { + ch_start = 0; + } + + for (j=0; jhw_info.nr_chip; j++) { + for (k=ch_start; khw_info.max_ch; k++) { + if (test_bit((j*dev->hw_info.max_ch + k), (void *)init_state)) { + continue; + } + + init_wait++; + if (init_wait <= max_wait) { + msleep(SSD_INIT_WAIT); + goto check_init; + } else { + if (k < dev->hw_info.nr_ch) { + hio_warn("%s: controller %d chip %d ch %d init failed\n", + dev->name, i, j, k); + } else { + hio_warn("%s: controller %d chip %d init failed\n", + dev->name, i, j); + } + + kfree(init_state); + return -1; + } + } + } + reg_base += reg_sz; + } + //printk(KERN_WARNING "%s: init wait %d\n", dev->name, init_wait); + + kfree(init_state); + return 0; +} + +static int ssd_check_init_state(struct ssd_device *dev) +{ + if (mode != SSD_DRV_MODE_STANDARD) { + return 0; + } + + return __ssd_check_init_state(dev); +} + +static void ssd_reset_resp_ptr(struct ssd_device *dev); + +/* reset flash controller etc */ +static int __ssd_reset(struct ssd_device *dev, int type) +{ + if (type < SSD_RST_NOINIT || type > SSD_RST_FULL) { + return -EINVAL; + } + + mutex_lock(&dev->fw_mutex); + + if (type == SSD_RST_NOINIT) { //no init + ssd_reg32_write(dev->ctrlp + SSD_RESET_REG, SSD_RESET_NOINIT); + } else if (type == SSD_RST_NORMAL) { //reset & init + ssd_reg32_write(dev->ctrlp + SSD_RESET_REG, SSD_RESET); + } else { // full reset + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + mutex_unlock(&dev->fw_mutex); + return -EINVAL; + } + + ssd_reg32_write(dev->ctrlp + SSD_FULL_RESET_REG, SSD_RESET_FULL); + + /* ?? */ + ssd_reset_resp_ptr(dev); + } + +#ifdef SSD_OT_PROTECT + dev->ot_delay = 0; +#endif + + msleep(1000); + + /* xx */ + ssd_set_flush_timeout(dev, dev->wmode); + + mutex_unlock(&dev->fw_mutex); + ssd_gen_swlog(dev, SSD_LOG_RESET, (uint32_t)type); + + return __ssd_check_init_state(dev); +} + +static int ssd_save_md(struct ssd_device *dev) +{ + struct ssd_nand_op_msg *msg; + int ret = 0; + + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return 0; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return 0; + } + + if (!dev->save_md) { + return 0; + } + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_FLUSH; + msg->flag = 0x2; + msg->ctrl_idx = 0; + msg->chip_no = 0; + + ret = ssd_do_request(dev, WRITE, msg, NULL); + ssd_put_dmsg(msg); + + return ret; +} + +static int ssd_barrier_save_md(struct ssd_device *dev) +{ + struct ssd_nand_op_msg *msg; + int ret = 0; + + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return 0; + + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return 0; + } + + if (!dev->save_md) { + return 0; + } + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + msg->fun = SSD_FUNC_FLUSH; + msg->flag = 0x2; + msg->ctrl_idx = 0; + msg->chip_no = 0; + + ret = ssd_do_barrier_request(dev, WRITE, msg, NULL); + ssd_put_dmsg(msg); + + return ret; +} + +static int ssd_flush(struct ssd_device *dev) +{ + struct ssd_nand_op_msg *msg; + struct ssd_flush_msg *fmsg; + int ret = 0; + + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return 0; + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + fmsg = (struct ssd_flush_msg *)msg; + + fmsg->fun = SSD_FUNC_FLUSH; + fmsg->flag = 0; + fmsg->ctrl_idx = 0; + fmsg->flash = 0; + } else { + msg->fun = SSD_FUNC_FLUSH; + msg->flag = 0; + msg->ctrl_idx = 0; + msg->chip_no = 0; + } + + ret = ssd_do_request(dev, WRITE, msg, NULL); + ssd_put_dmsg(msg); + + return ret; +} + +static int ssd_barrier_flush(struct ssd_device *dev) +{ + struct ssd_nand_op_msg *msg; + struct ssd_flush_msg *fmsg; + int ret = 0; + + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return 0; + + msg = (struct ssd_nand_op_msg *)ssd_get_dmsg(dev); + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + fmsg = (struct ssd_flush_msg *)msg; + + fmsg->fun = SSD_FUNC_FLUSH; + fmsg->flag = 0; + fmsg->ctrl_idx = 0; + fmsg->flash = 0; + } else { + msg->fun = SSD_FUNC_FLUSH; + msg->flag = 0; + msg->ctrl_idx = 0; + msg->chip_no = 0; + } + + ret = ssd_do_barrier_request(dev, WRITE, msg, NULL); + ssd_put_dmsg(msg); + + return ret; +} + +#define SSD_WMODE_BUFFER_TIMEOUT 0x00c82710 +#define SSD_WMODE_BUFFER_EX_TIMEOUT 0x000500c8 +#define SSD_WMODE_FUA_TIMEOUT 0x000503E8 +static void ssd_set_flush_timeout(struct ssd_device *dev, int m) +{ + uint32_t to; + uint32_t val = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_1) { + return; + } + + switch(m) { + case SSD_WMODE_BUFFER: + to = SSD_WMODE_BUFFER_TIMEOUT; + break; + case SSD_WMODE_BUFFER_EX: + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2_1) { + to = SSD_WMODE_BUFFER_EX_TIMEOUT; + } else { + to = SSD_WMODE_BUFFER_TIMEOUT; + } + break; + case SSD_WMODE_FUA: + to = SSD_WMODE_FUA_TIMEOUT; + break; + default: + return; + } + + val = (((uint32_t)((uint32_t)m & 0x3) << 28) | to); + + ssd_reg32_write(dev->ctrlp + SSD_FLUSH_TIMEOUT_REG, val); +} + +static int ssd_do_switch_wmode(struct ssd_device *dev, int m) +{ + int ret = 0; + + ret = ssd_barrier_start(dev); + if (ret) { + goto out; + } + + ret = ssd_barrier_flush(dev); + if (ret) { + goto out_barrier_end; + } + + /* set contoller flush timeout */ + ssd_set_flush_timeout(dev, m); + + dev->wmode = m; + mb(); + +out_barrier_end: + ssd_barrier_end(dev); +out: + return ret; +} + +static int ssd_switch_wmode(struct ssd_device *dev, int m) +{ + int default_wmode; + int next_wmode; + int ret = 0; + + if (!test_bit(SSD_ONLINE, &dev->state)) { + return -ENODEV; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + default_wmode = SSD_WMODE_BUFFER; + } else { + default_wmode = SSD_WMODE_BUFFER_EX; + } + + if (SSD_WMODE_AUTO == m) { + /* battery fault ? */ + if (test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + next_wmode = SSD_WMODE_FUA; + } else { + next_wmode = default_wmode; + } + } else if (SSD_WMODE_DEFAULT == m) { + next_wmode = default_wmode; + } else { + next_wmode = m; + } + + if (next_wmode != dev->wmode) { + hio_warn("%s: switch write mode (%d -> %d)\n", dev->name, dev->wmode, next_wmode); + ret = ssd_do_switch_wmode(dev, next_wmode); + if (ret) { + hio_err("%s: can not switch write mode (%d -> %d)\n", dev->name, dev->wmode, next_wmode); + } + } + + return ret; +} + +static int ssd_init_wmode(struct ssd_device *dev) +{ + int default_wmode; + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + default_wmode = SSD_WMODE_BUFFER; + } else { + default_wmode = SSD_WMODE_BUFFER_EX; + } + + /* dummy mode */ + if (SSD_WMODE_AUTO == dev->user_wmode) { + /* battery fault ? */ + if (test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + dev->wmode = SSD_WMODE_FUA; + } else { + dev->wmode = default_wmode; + } + } else if (SSD_WMODE_DEFAULT == dev->user_wmode) { + dev->wmode = default_wmode; + } else { + dev->wmode = dev->user_wmode; + } + ssd_set_flush_timeout(dev, dev->wmode); + + return ret; +} + +static int __ssd_set_wmode(struct ssd_device *dev, int m) +{ + int ret = 0; + + /* not support old fw*/ + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_1) { + ret = -EOPNOTSUPP; + goto out; + } + + if (m < SSD_WMODE_BUFFER || m > SSD_WMODE_DEFAULT) { + ret = -EINVAL; + goto out; + } + + ssd_gen_swlog(dev, SSD_LOG_SET_WMODE, m); + + dev->user_wmode = m; + + ret = ssd_switch_wmode(dev, dev->user_wmode); + if (ret) { + goto out; + } + +out: + return ret; +} + +int ssd_set_wmode(struct block_device *bdev, int m) +{ + struct ssd_device *dev; + + if (!bdev || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + + return __ssd_set_wmode(dev, m); +} + +static int ssd_do_reset(struct ssd_device *dev) +{ + int ret = 0; + + if (test_and_set_bit(SSD_RESETING, &dev->state)) { + return 0; + } + + ssd_stop_workq(dev); + + ret = ssd_barrier_start(dev); + if (ret) { + goto out; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + /* old reset */ + ret = __ssd_reset(dev, SSD_RST_NORMAL); + } else { + /* full reset */ + //ret = __ssd_reset(dev, SSD_RST_FULL); + ret = __ssd_reset(dev, SSD_RST_NORMAL); + } + if (ret) { + goto out_barrier_end; + } + +out_barrier_end: + ssd_barrier_end(dev); +out: + ssd_start_workq(dev); + test_and_clear_bit(SSD_RESETING, &dev->state); + return ret; +} + +static int ssd_full_reset(struct ssd_device *dev) +{ + int ret = 0; + + if (test_and_set_bit(SSD_RESETING, &dev->state)) { + return 0; + } + + ssd_stop_workq(dev); + + ret = ssd_barrier_start(dev); + if (ret) { + goto out; + } + + ret = ssd_barrier_flush(dev); + if (ret) { + goto out_barrier_end; + } + + ret = ssd_barrier_save_md(dev); + if (ret) { + goto out_barrier_end; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + /* old reset */ + ret = __ssd_reset(dev, SSD_RST_NORMAL); + } else { + /* full reset */ + //ret = __ssd_reset(dev, SSD_RST_FULL); + ret = __ssd_reset(dev, SSD_RST_NORMAL); + } + if (ret) { + goto out_barrier_end; + } + +out_barrier_end: + ssd_barrier_end(dev); +out: + ssd_start_workq(dev); + test_and_clear_bit(SSD_RESETING, &dev->state); + return ret; +} + +int ssd_reset(struct block_device *bdev) +{ + struct ssd_device *dev; + + if (!bdev || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + + return ssd_full_reset(dev); +} + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) +static int ssd_issue_flush_fn(struct request_queue *q, struct gendisk *disk, + sector_t *error_sector) +{ + struct ssd_device *dev = q->queuedata; + + return ssd_flush(dev); +} +#endif + +void ssd_submit_pbio(struct request_queue *q, struct bio *bio) +{ + struct ssd_device *dev = q->queuedata; +#ifdef SSD_QUEUE_PBIO + int ret = -EBUSY; +#endif + + if (!test_bit(SSD_ONLINE, &dev->state)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -ENODEV); +#else + bio_endio(bio, bio->bi_size, -ENODEV); +#endif + goto out; + } + +#ifdef SSD_DEBUG_ERR + if (atomic_read(&dev->tocnt)) { + hio_warn("%s: IO rejected because of IO timeout!\n", dev->name); +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EIO); +#else + bio_endio(bio, bio->bi_size, -EIO); +#endif + goto out; + } +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,32)) + if (unlikely(bio_barrier(bio))) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EOPNOTSUPP); +#else + bio_endio(bio, bio->bi_size, -EOPNOTSUPP); +#endif + goto out; + } +#elif (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,36)) + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EOPNOTSUPP); +#else + bio_endio(bio, bio->bi_size, -EOPNOTSUPP); +#endif + goto out; + } +#elif (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,37)) + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EOPNOTSUPP); +#else + bio_endio(bio, bio->bi_size, -EOPNOTSUPP); +#endif + goto out; + } +#else + //xx + if (unlikely(bio->bi_rw & REQ_FUA)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EOPNOTSUPP); +#else + bio_endio(bio, bio->bi_size, -EOPNOTSUPP); +#endif + goto out; + } +#endif + + if (unlikely(dev->readonly && bio_data_dir(bio) == WRITE)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EROFS); +#else + bio_endio(bio, bio->bi_size, -EROFS); +#endif + goto out; + } + +#ifdef SSD_QUEUE_PBIO + if (0 == atomic_read(&dev->in_sendq)) { + ret = __ssd_submit_pbio(dev, bio, 0); + } + + if (ret) { + (void)test_and_set_bit(BIO_SSD_PBIO, &bio->bi_flags); + ssd_queue_bio(dev, bio); + } +#else + __ssd_submit_pbio(dev, bio, 1); +#endif + +out: + return; +} + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,2,0)) +static int ssd_make_request(struct request_queue *q, struct bio *bio) +#else +static void ssd_make_request(struct request_queue *q, struct bio *bio) +#endif +{ + struct ssd_device *dev = q->queuedata; + int ret = -EBUSY; + + if (!test_bit(SSD_ONLINE, &dev->state)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -ENODEV); +#else + bio_endio(bio, bio->bi_size, -ENODEV); +#endif + goto out; + } + +#ifdef SSD_DEBUG_ERR + if (atomic_read(&dev->tocnt)) { + hio_warn("%s: IO rejected because of IO timeout!\n", dev->name); +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EIO); +#else + bio_endio(bio, bio->bi_size, -EIO); +#endif + goto out; + } +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,32)) + if (unlikely(bio_barrier(bio))) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EOPNOTSUPP); +#else + bio_endio(bio, bio->bi_size, -EOPNOTSUPP); +#endif + goto out; + } +#elif (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,36)) + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EOPNOTSUPP); +#else + bio_endio(bio, bio->bi_size, -EOPNOTSUPP); +#endif + goto out; + } +#elif (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,37)) + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EOPNOTSUPP); +#else + bio_endio(bio, bio->bi_size, -EOPNOTSUPP); +#endif + goto out; + } +#else + //xx + if (unlikely(bio->bi_rw & REQ_FUA)) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,24)) + bio_endio(bio, -EOPNOTSUPP); +#else + bio_endio(bio, bio->bi_size, -EOPNOTSUPP); +#endif + goto out; + } + + /* writeback_cache_control.txt: REQ_FLUSH requests without data can be completed successfully without doing any work */ + if (unlikely((bio->bi_rw & REQ_FLUSH) && !bio_sectors(bio))) { + bio_endio(bio, 0); + goto out; + } + +#endif + + if (0 == atomic_read(&dev->in_sendq)) { + ret = ssd_submit_bio(dev, bio, 0); + } + + if (ret) { + ssd_queue_bio(dev, bio); + } + +out: +#if (LINUX_VERSION_CODE < KERNEL_VERSION(3,2,0)) + return 0; +#else + return; +#endif +} + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,16)) +static int ssd_block_getgeo(struct block_device *bdev, struct hd_geometry *geo) +{ + struct ssd_device *dev; + + if (!bdev) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + if (!dev) { + return -EINVAL; + } + + geo->heads = 4; + geo->sectors = 16; + geo->cylinders = (dev->hw_info.size & ~0x3f) >> 6; + return 0; +} +#endif + +static void ssd_cleanup_blkdev(struct ssd_device *dev); +static int ssd_init_blkdev(struct ssd_device *dev); +static int ssd_ioctl_common(struct ssd_device *dev, unsigned int cmd, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + void __user *buf = NULL; + void *kbuf = NULL; + int ret = 0; + + switch (cmd) { + case SSD_CMD_GET_PROTOCOL_INFO: + if (copy_to_user(argp, &dev->protocol_info, sizeof(struct ssd_protocol_info))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + + case SSD_CMD_GET_HW_INFO: + if (copy_to_user(argp, &dev->hw_info, sizeof(struct ssd_hw_info))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + + case SSD_CMD_GET_ROM_INFO: + if (copy_to_user(argp, &dev->rom_info, sizeof(struct ssd_rom_info))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + + case SSD_CMD_GET_SMART: { + struct ssd_smart smart; + int i; + + memcpy(&smart, &dev->smart, sizeof(struct ssd_smart)); + + mutex_lock(&dev->gd_mutex); + ssd_update_smart(dev, &smart); + mutex_unlock(&dev->gd_mutex); + + /* combine the volatile log info */ + if (dev->log_info.nr_log) { + for (i=0; ilog_info.stat[i]; + } + } + + if (copy_to_user(argp, &smart, sizeof(struct ssd_smart))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_GET_IDX: + if (copy_to_user(argp, &dev->idx, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + + case SSD_CMD_GET_AMOUNT: { + int nr_ssd = atomic_read(&ssd_nr); + if (copy_to_user(argp, &nr_ssd, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_TO_INFO: { + int tocnt = atomic_read(&dev->tocnt); + + if (copy_to_user(argp, &tocnt, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_DRV_VER: { + char ver[] = DRIVER_VERSION; + int len = sizeof(ver); + + if (len > (DRIVER_VERSION_LEN - 1)) { + len = (DRIVER_VERSION_LEN - 1); + } + if (copy_to_user(argp, ver, len)) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_BBACC_INFO: { + struct ssd_acc_info acc; + + mutex_lock(&dev->fw_mutex); + ret = ssd_bb_acc(dev, &acc); + mutex_unlock(&dev->fw_mutex); + if (ret) { + break; + } + + if (copy_to_user(argp, &acc, sizeof(struct ssd_acc_info))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_ECACC_INFO: { + struct ssd_acc_info acc; + + mutex_lock(&dev->fw_mutex); + ret = ssd_ec_acc(dev, &acc); + mutex_unlock(&dev->fw_mutex); + if (ret) { + break; + } + + if (copy_to_user(argp, &acc, sizeof(struct ssd_acc_info))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_HW_INFO_EXT: + if (copy_to_user(argp, &dev->hw_info_ext, sizeof(struct ssd_hw_info_extend))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + + case SSD_CMD_REG_READ: { + struct ssd_reg_op_info reg_info; + + if (copy_from_user(®_info, argp, sizeof(struct ssd_reg_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + if (reg_info.offset > dev->mmio_len-sizeof(uint32_t)) { + ret = -EINVAL; + break; + } + + reg_info.value = ssd_reg32_read(dev->ctrlp + reg_info.offset); + if (copy_to_user(argp, ®_info, sizeof(struct ssd_reg_op_info))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_REG_WRITE: { + struct ssd_reg_op_info reg_info; + + if (copy_from_user(®_info, argp, sizeof(struct ssd_reg_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + if (reg_info.offset > dev->mmio_len-sizeof(uint32_t)) { + ret = -EINVAL; + break; + } + + ssd_reg32_write(dev->ctrlp + reg_info.offset, reg_info.value); + + break; + } + + case SSD_CMD_SPI_READ: { + struct ssd_spi_op_info spi_info; + uint32_t off, size; + + if (copy_from_user(&spi_info, argp, sizeof(struct ssd_spi_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + off = spi_info.off; + size = spi_info.len; + buf = spi_info.buf; + + if (size > dev->rom_info.size || 0 == size || (off + size) > dev->rom_info.size) { + ret = -EINVAL; + break; + } + + kbuf = kmalloc(size, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + ret = ssd_spi_page_read(dev, kbuf, off, size); + if (ret) { + kfree(kbuf); + break; + } + + if (copy_to_user(buf, kbuf, size)) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + kfree(kbuf); + ret = -EFAULT; + break; + } + + kfree(kbuf); + + break; + } + + case SSD_CMD_SPI_WRITE: { + struct ssd_spi_op_info spi_info; + uint32_t off, size; + + if (copy_from_user(&spi_info, argp, sizeof(struct ssd_spi_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + off = spi_info.off; + size = spi_info.len; + buf = spi_info.buf; + + if (size > dev->rom_info.size || 0 == size || (off + size) > dev->rom_info.size) { + ret = -EINVAL; + break; + } + + kbuf = kmalloc(size, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + if (copy_from_user(kbuf, buf, size)) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + kfree(kbuf); + ret = -EFAULT; + break; + } + + ret = ssd_spi_page_write(dev, kbuf, off, size); + if (ret) { + kfree(kbuf); + break; + } + + kfree(kbuf); + + break; + } + + case SSD_CMD_SPI_ERASE: { + struct ssd_spi_op_info spi_info; + uint32_t off; + + if (copy_from_user(&spi_info, argp, sizeof(struct ssd_spi_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + off = spi_info.off; + + if ((off + dev->rom_info.block_size) > dev->rom_info.size) { + ret = -EINVAL; + break; + } + + ret = ssd_spi_block_erase(dev, off); + if (ret) { + break; + } + + break; + } + + case SSD_CMD_I2C_READ: { + struct ssd_i2c_op_info i2c_info; + uint8_t saddr; + uint8_t rsize; + + if (copy_from_user(&i2c_info, argp, sizeof(struct ssd_i2c_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = i2c_info.saddr; + rsize = i2c_info.rsize; + buf = i2c_info.rbuf; + + if (rsize <= 0 || rsize > SSD_I2C_MAX_DATA) { + ret = -EINVAL; + break; + } + + kbuf = kmalloc(rsize, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + ret = ssd_i2c_read(dev, saddr, rsize, kbuf); + if (ret) { + kfree(kbuf); + break; + } + + if (copy_to_user(buf, kbuf, rsize)) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + kfree(kbuf); + ret = -EFAULT; + break; + } + + kfree(kbuf); + + break; + } + + case SSD_CMD_I2C_WRITE: { + struct ssd_i2c_op_info i2c_info; + uint8_t saddr; + uint8_t wsize; + + if (copy_from_user(&i2c_info, argp, sizeof(struct ssd_i2c_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = i2c_info.saddr; + wsize = i2c_info.wsize; + buf = i2c_info.wbuf; + + if (wsize <= 0 || wsize > SSD_I2C_MAX_DATA) { + ret = -EINVAL; + break; + } + + kbuf = kmalloc(wsize, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + if (copy_from_user(kbuf, buf, wsize)) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + kfree(kbuf); + ret = -EFAULT; + break; + } + + ret = ssd_i2c_write(dev, saddr, wsize, kbuf); + if (ret) { + kfree(kbuf); + break; + } + + kfree(kbuf); + + break; + } + + case SSD_CMD_I2C_WRITE_READ: { + struct ssd_i2c_op_info i2c_info; + uint8_t saddr; + uint8_t wsize; + uint8_t rsize; + uint8_t size; + + if (copy_from_user(&i2c_info, argp, sizeof(struct ssd_i2c_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = i2c_info.saddr; + wsize = i2c_info.wsize; + rsize = i2c_info.rsize; + buf = i2c_info.wbuf; + + if (wsize <= 0 || wsize > SSD_I2C_MAX_DATA) { + ret = -EINVAL; + break; + } + + if (rsize <= 0 || rsize > SSD_I2C_MAX_DATA) { + ret = -EINVAL; + break; + } + + size = wsize + rsize; + + kbuf = kmalloc(size, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + if (copy_from_user((kbuf + rsize), buf, wsize)) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + kfree(kbuf); + ret = -EFAULT; + break; + } + + buf = i2c_info.rbuf; + + ret = ssd_i2c_write_read(dev, saddr, wsize, (kbuf + rsize), rsize, kbuf); + if (ret) { + kfree(kbuf); + break; + } + + if (copy_to_user(buf, kbuf, rsize)) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + kfree(kbuf); + ret = -EFAULT; + break; + } + + kfree(kbuf); + + break; + } + + case SSD_CMD_SMBUS_SEND_BYTE: { + struct ssd_smbus_op_info smbus_info; + uint8_t smb_data[SSD_SMBUS_BLOCK_MAX]; + uint8_t saddr; + uint8_t size; + + if (copy_from_user(&smbus_info, argp, sizeof(struct ssd_smbus_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = smbus_info.saddr; + buf = smbus_info.buf; + size = 1; + + if (copy_from_user(smb_data, buf, size)) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ret = ssd_smbus_send_byte(dev, saddr, smb_data); + if (ret) { + break; + } + + break; + } + + case SSD_CMD_SMBUS_RECEIVE_BYTE: { + struct ssd_smbus_op_info smbus_info; + uint8_t smb_data[SSD_SMBUS_BLOCK_MAX]; + uint8_t saddr; + uint8_t size; + + if (copy_from_user(&smbus_info, argp, sizeof(struct ssd_smbus_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = smbus_info.saddr; + buf = smbus_info.buf; + size = 1; + + ret = ssd_smbus_receive_byte(dev, saddr, smb_data); + if (ret) { + break; + } + + if (copy_to_user(buf, smb_data, size)) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_SMBUS_WRITE_BYTE: { + struct ssd_smbus_op_info smbus_info; + uint8_t smb_data[SSD_SMBUS_BLOCK_MAX]; + uint8_t saddr; + uint8_t command; + uint8_t size; + + if (copy_from_user(&smbus_info, argp, sizeof(struct ssd_smbus_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = smbus_info.saddr; + command = smbus_info.cmd; + buf = smbus_info.buf; + size = 1; + + if (copy_from_user(smb_data, buf, size)) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ret = ssd_smbus_write_byte(dev, saddr, command, smb_data); + if (ret) { + break; + } + + break; + } + + case SSD_CMD_SMBUS_READ_BYTE: { + struct ssd_smbus_op_info smbus_info; + uint8_t smb_data[SSD_SMBUS_BLOCK_MAX]; + uint8_t saddr; + uint8_t command; + uint8_t size; + + if (copy_from_user(&smbus_info, argp, sizeof(struct ssd_smbus_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = smbus_info.saddr; + command = smbus_info.cmd; + buf = smbus_info.buf; + size = 1; + + ret = ssd_smbus_read_byte(dev, saddr, command, smb_data); + if (ret) { + break; + } + + if (copy_to_user(buf, smb_data, size)) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_SMBUS_WRITE_WORD: { + struct ssd_smbus_op_info smbus_info; + uint8_t smb_data[SSD_SMBUS_BLOCK_MAX]; + uint8_t saddr; + uint8_t command; + uint8_t size; + + if (copy_from_user(&smbus_info, argp, sizeof(struct ssd_smbus_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = smbus_info.saddr; + command = smbus_info.cmd; + buf = smbus_info.buf; + size = 2; + + if (copy_from_user(smb_data, buf, size)) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ret = ssd_smbus_write_word(dev, saddr, command, smb_data); + if (ret) { + break; + } + + break; + } + + case SSD_CMD_SMBUS_READ_WORD: { + struct ssd_smbus_op_info smbus_info; + uint8_t smb_data[SSD_SMBUS_BLOCK_MAX]; + uint8_t saddr; + uint8_t command; + uint8_t size; + + if (copy_from_user(&smbus_info, argp, sizeof(struct ssd_smbus_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = smbus_info.saddr; + command = smbus_info.cmd; + buf = smbus_info.buf; + size = 2; + + ret = ssd_smbus_read_word(dev, saddr, command, smb_data); + if (ret) { + break; + } + + if (copy_to_user(buf, smb_data, size)) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_SMBUS_WRITE_BLOCK: { + struct ssd_smbus_op_info smbus_info; + uint8_t smb_data[SSD_SMBUS_BLOCK_MAX]; + uint8_t saddr; + uint8_t command; + uint8_t size; + + if (copy_from_user(&smbus_info, argp, sizeof(struct ssd_smbus_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = smbus_info.saddr; + command = smbus_info.cmd; + buf = smbus_info.buf; + size = smbus_info.size; + + if (size > SSD_SMBUS_BLOCK_MAX) { + ret = -EINVAL; + break; + } + + if (copy_from_user(smb_data, buf, size)) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ret = ssd_smbus_write_block(dev, saddr, command, size, smb_data); + if (ret) { + break; + } + + break; + } + + case SSD_CMD_SMBUS_READ_BLOCK: { + struct ssd_smbus_op_info smbus_info; + uint8_t smb_data[SSD_SMBUS_BLOCK_MAX]; + uint8_t saddr; + uint8_t command; + uint8_t size; + + if (copy_from_user(&smbus_info, argp, sizeof(struct ssd_smbus_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + saddr = smbus_info.saddr; + command = smbus_info.cmd; + buf = smbus_info.buf; + size = smbus_info.size; + + if (size > SSD_SMBUS_BLOCK_MAX) { + ret = -EINVAL; + break; + } + + ret = ssd_smbus_read_block(dev, saddr, command, size, smb_data); + if (ret) { + break; + } + + if (copy_to_user(buf, smb_data, size)) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_BM_GET_VER: { + uint16_t ver; + + ret = ssd_bm_get_version(dev, &ver); + if (ret) { + break; + } + + if (copy_to_user(argp, &ver, sizeof(uint16_t))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_BM_GET_NR_CAP: { + int nr_cap; + + ret = ssd_bm_nr_cap(dev, &nr_cap); + if (ret) { + break; + } + + if (copy_to_user(argp, &nr_cap, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_BM_CAP_LEARNING: { + ret = ssd_bm_enter_cap_learning(dev); + + if (ret) { + break; + } + + break; + } + + case SSD_CMD_CAP_LEARN: { + uint32_t cap = 0; + + ret = ssd_cap_learn(dev, &cap); + if (ret) { + break; + } + + if (copy_to_user(argp, &cap, sizeof(uint32_t))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_GET_CAP_STATUS: { + int cap_status = 0; + + if (test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + cap_status = 1; + } + + if (copy_to_user(argp, &cap_status, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_RAM_READ: { + struct ssd_ram_op_info ram_info; + uint64_t ofs; + uint32_t length; + size_t rlen, len = dev->hw_info.ram_max_len; + int ctrl_idx; + + if (copy_from_user(&ram_info, argp, sizeof(struct ssd_ram_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ofs = ram_info.start; + length = ram_info.length; + buf = ram_info.buf; + ctrl_idx = ram_info.ctrl_idx; + + if (ofs >= dev->hw_info.ram_size || length > dev->hw_info.ram_size || 0 == length || (ofs + length) > dev->hw_info.ram_size) { + ret = -EINVAL; + break; + } + + kbuf = kmalloc(len, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + for (rlen=0; rlenhw_info.ram_max_len; + int ctrl_idx; + + if (copy_from_user(&ram_info, argp, sizeof(struct ssd_ram_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + ofs = ram_info.start; + length = ram_info.length; + buf = ram_info.buf; + ctrl_idx = ram_info.ctrl_idx; + + if (ofs >= dev->hw_info.ram_size || length > dev->hw_info.ram_size || 0 == length || (ofs + length) > dev->hw_info.ram_size) { + ret = -EINVAL; + break; + } + + kbuf = kmalloc(len, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + for (wlen=0; wlenname); + ret = -EFAULT; + break; + } + + chip_no = flash_info.flash; + chip_ce = flash_info.chip; + ctrl_idx = flash_info.ctrl_idx; + buf = flash_info.buf; + length = dev->hw_info.id_size; + + //kbuf = kmalloc(length, GFP_KERNEL); + kbuf = kmalloc(SSD_NAND_ID_BUFF_SZ, GFP_KERNEL); //xx + if (!kbuf) { + ret = -ENOMEM; + break; + } + memset(kbuf, 0, length); + + ret = ssd_nand_read_id(dev, kbuf, chip_no, chip_ce, ctrl_idx); + if (ret) { + kfree(kbuf); + break; + } + + if (copy_to_user(buf, kbuf, length)) { + kfree(kbuf); + ret = -EFAULT; + break; + } + + kfree(kbuf); + + break; + } + + case SSD_CMD_NAND_READ: { //with oob + struct ssd_flash_op_info flash_info; + uint32_t length; + int flash, chip, page, ctrl_idx; + int err = 0; + + if (copy_from_user(&flash_info, argp, sizeof(struct ssd_flash_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + flash = flash_info.flash; + chip = flash_info.chip; + page = flash_info.page; + buf = flash_info.buf; + ctrl_idx = flash_info.ctrl_idx; + + length = dev->hw_info.page_size + dev->hw_info.oob_size; + + kbuf = kmalloc(length, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + err = ret = ssd_nand_read_w_oob(dev, kbuf, flash, chip, page, 1, ctrl_idx); + if (ret && (-EIO != ret)) { + kfree(kbuf); + break; + } + + if (copy_to_user(buf, kbuf, length)) { + kfree(kbuf); + ret = -EFAULT; + break; + } + + ret = err; + + kfree(kbuf); + break; + } + + case SSD_CMD_NAND_WRITE: { + struct ssd_flash_op_info flash_info; + int flash, chip, page, ctrl_idx; + uint32_t length; + + if (copy_from_user(&flash_info, argp, sizeof(struct ssd_flash_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + flash = flash_info.flash; + chip = flash_info.chip; + page = flash_info.page; + buf = flash_info.buf; + ctrl_idx = flash_info.ctrl_idx; + + length = dev->hw_info.page_size + dev->hw_info.oob_size; + + kbuf = kmalloc(length, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + if (copy_from_user(kbuf, buf, length)) { + kfree(kbuf); + ret = -EFAULT; + break; + } + + ret = ssd_nand_write(dev, kbuf, flash, chip, page, 1, ctrl_idx); + if (ret) { + kfree(kbuf); + break; + } + + kfree(kbuf); + break; + } + + case SSD_CMD_NAND_ERASE: { + struct ssd_flash_op_info flash_info; + int flash, chip, page, ctrl_idx; + + if (copy_from_user(&flash_info, argp, sizeof(struct ssd_flash_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + flash = flash_info.flash; + chip = flash_info.chip; + page = flash_info.page; + ctrl_idx = flash_info.ctrl_idx; + + if ((page % dev->hw_info.page_count) != 0) { + ret = -EINVAL; + break; + } + + //hio_warn("erase fs = %llx\n", ofs); + ret = ssd_nand_erase(dev, flash, chip, page, ctrl_idx); + if (ret) { + break; + } + + break; + } + + case SSD_CMD_NAND_READ_EXT: { //ingore EIO + struct ssd_flash_op_info flash_info; + uint32_t length; + int flash, chip, page, ctrl_idx; + + if (copy_from_user(&flash_info, argp, sizeof(struct ssd_flash_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + flash = flash_info.flash; + chip = flash_info.chip; + page = flash_info.page; + buf = flash_info.buf; + ctrl_idx = flash_info.ctrl_idx; + + length = dev->hw_info.page_size + dev->hw_info.oob_size; + + kbuf = kmalloc(length, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + break; + } + + ret = ssd_nand_read_w_oob(dev, kbuf, flash, chip, page, 1, ctrl_idx); + if (-EIO == ret) { //ingore EIO + ret = 0; + } + if (ret) { + kfree(kbuf); + break; + } + + if (copy_to_user(buf, kbuf, length)) { + kfree(kbuf); + ret = -EFAULT; + break; + } + + kfree(kbuf); + break; + } + + case SSD_CMD_UPDATE_BBT: { + struct ssd_flash_op_info flash_info; + int ctrl_idx, flash; + + if (copy_from_user(&flash_info, argp, sizeof(struct ssd_flash_op_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ctrl_idx = flash_info.ctrl_idx; + flash = flash_info.flash; + ret = ssd_update_bbt(dev, flash, ctrl_idx); + if (ret) { + break; + } + + break; + } + + case SSD_CMD_CLEAR_ALARM: + ssd_clear_alarm(dev); + break; + + case SSD_CMD_SET_ALARM: + ssd_set_alarm(dev); + break; + + case SSD_CMD_RESET: + ret = ssd_do_reset(dev); + break; + + case SSD_CMD_RELOAD_FW: + dev->reload_fw = 1; + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + ssd_reg32_write(dev->ctrlp + SSD_RELOAD_FW_REG, SSD_RELOAD_FLAG); + } else if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_1_1) { + ssd_reg32_write(dev->ctrlp + SSD_RELOAD_FW_REG, SSD_RELOAD_FW); + + } + break; + + case SSD_CMD_UNLOAD_DEV: { + if (atomic_read(&dev->refcnt)) { + ret = -EBUSY; + break; + } + + /* save smart */ + ssd_save_smart(dev); + + ret = ssd_flush(dev); + if (ret) { + break; + } + + /* cleanup the block device */ + if (test_and_clear_bit(SSD_INIT_BD, &dev->state)) { + mutex_lock(&dev->gd_mutex); + ssd_cleanup_blkdev(dev); + mutex_unlock(&dev->gd_mutex); + } + + break; + } + + case SSD_CMD_LOAD_DEV: { + + if (test_bit(SSD_INIT_BD, &dev->state)) { + ret = -EINVAL; + break; + } + + ret = ssd_init_smart(dev); + if (ret) { + hio_warn("%s: init info: failed\n", dev->name); + break; + } + + ret = ssd_init_blkdev(dev); + if (ret) { + hio_warn("%s: register block device: failed\n", dev->name); + break; + } + (void)test_and_set_bit(SSD_INIT_BD, &dev->state); + + break; + } + + case SSD_CMD_UPDATE_VP: { + uint32_t val; + uint32_t new_vp, new_vp1 = 0; + + if (test_bit(SSD_INIT_BD, &dev->state)) { + ret = -EINVAL; + break; + } + + if (copy_from_user(&new_vp, argp, sizeof(uint32_t))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + if (new_vp > dev->hw_info.max_valid_pages || new_vp <= 0) { + ret = -EINVAL; + break; + } + + while (new_vp <= dev->hw_info.max_valid_pages) { + ssd_reg32_write(dev->ctrlp + SSD_VALID_PAGES_REG, new_vp); + msleep(10); + val = ssd_reg32_read(dev->ctrlp + SSD_VALID_PAGES_REG); + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + new_vp1 = val & 0x3FF; + } else { + new_vp1 = val & 0x7FFF; + } + + if (new_vp1 == new_vp) { + break; + } + + new_vp++; + /*if (new_vp == dev->hw_info.valid_pages) { + new_vp++; + }*/ + } + + if (new_vp1 != new_vp || new_vp > dev->hw_info.max_valid_pages) { + /* restore */ + ssd_reg32_write(dev->ctrlp + SSD_VALID_PAGES_REG, dev->hw_info.valid_pages); + ret = -EINVAL; + break; + } + + if (copy_to_user(argp, &new_vp, sizeof(uint32_t))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ssd_reg32_write(dev->ctrlp + SSD_VALID_PAGES_REG, dev->hw_info.valid_pages); + ret = -EFAULT; + break; + } + + /* new */ + dev->hw_info.valid_pages = new_vp; + dev->hw_info.size = (uint64_t)dev->hw_info.valid_pages * dev->hw_info.page_size; + dev->hw_info.size *= (dev->hw_info.block_count - dev->hw_info.reserved_blks); + dev->hw_info.size *= ((uint64_t)dev->hw_info.nr_data_ch * (uint64_t)dev->hw_info.nr_chip * (uint64_t)dev->hw_info.nr_ctrl); + + break; + } + + case SSD_CMD_FULL_RESET: { + ret = ssd_full_reset(dev); + break; + } + + case SSD_CMD_GET_NR_LOG: { + if (copy_to_user(argp, &dev->internal_log.nr_log, sizeof(dev->internal_log.nr_log))) { + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_LOG: { + uint32_t length = dev->rom_info.log_sz; + + buf = argp; + + if (copy_to_user(buf, dev->internal_log.log, length)) { + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_LOG_LEVEL: { + int level = 0; + if (copy_from_user(&level, argp, sizeof(int))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + if (level >= SSD_LOG_NR_LEVEL || level < SSD_LOG_LEVEL_INFO) { + level = SSD_LOG_LEVEL_ERR; + } + + //just for showing log, no need to protect + log_level = level; + break; + } + + case SSD_CMD_OT_PROTECT: { + int protect = 0; + + if (copy_from_user(&protect, argp, sizeof(int))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ssd_set_ot_protect(dev, !!protect); + break; + } + + case SSD_CMD_GET_OT_STATUS: { + int status = ssd_get_ot_status(dev, &status); + + if (copy_to_user(argp, &status, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_CLEAR_LOG: { + ret = ssd_clear_log(dev); + break; + } + + case SSD_CMD_CLEAR_SMART: { + ret = ssd_clear_smart(dev); + break; + } + + case SSD_CMD_SW_LOG: { + struct ssd_sw_log_info sw_log; + + if (copy_from_user(&sw_log, argp, sizeof(struct ssd_sw_log_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ret = ssd_gen_swlog(dev, sw_log.event, sw_log.data); + break; + } + + case SSD_CMD_GET_LABEL: { + + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + ret = -EINVAL; + break; + } + + if (copy_to_user(argp, &dev->label, sizeof(struct ssd_label))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_VERSION: { + struct ssd_version_info ver; + + mutex_lock(&dev->fw_mutex); + ret = __ssd_get_version(dev, &ver); + mutex_unlock(&dev->fw_mutex); + if (ret) { + break; + } + + if (copy_to_user(argp, &ver, sizeof(struct ssd_version_info))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_TEMPERATURE: { + int temp; + + mutex_lock(&dev->fw_mutex); + ret = __ssd_get_temperature(dev, &temp); + mutex_unlock(&dev->fw_mutex); + if (ret) { + break; + } + + if (copy_to_user(argp, &temp, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_BMSTATUS: { + int status; + + mutex_lock(&dev->fw_mutex); + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + if (test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + status = SSD_BMSTATUS_WARNING; + } else { + status = SSD_BMSTATUS_OK; + } + } else if(dev->protocol_info.ver > SSD_PROTOCOL_V3) { + ret = __ssd_bm_status(dev, &status); + } else { + status = SSD_BMSTATUS_OK; + } + mutex_unlock(&dev->fw_mutex); + if (ret) { + break; + } + + if (copy_to_user(argp, &status, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_GET_LABEL2: { + void *label; + int length; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + label = &dev->label; + length = sizeof(struct ssd_label); + } else { + label = &dev->labelv3; + length = sizeof(struct ssd_labelv3); + } + + if (copy_to_user(argp, label, length)) { + ret = -EFAULT; + break; + } + break; + } + + case SSD_CMD_FLUSH: + ret = ssd_flush(dev); + if (ret) { + hio_warn("%s: ssd_flush: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + + case SSD_CMD_SAVE_MD: { + int save_md = 0; + + if (copy_from_user(&save_md, argp, sizeof(int))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + dev->save_md = !!save_md; + break; + } + + case SSD_CMD_SET_WMODE: { + int new_wmode = 0; + + if (copy_from_user(&new_wmode, argp, sizeof(int))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + ret = __ssd_set_wmode(dev, new_wmode); + if (ret) { + break; + } + + break; + } + + case SSD_CMD_GET_WMODE: { + if (copy_to_user(argp, &dev->wmode, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_GET_USER_WMODE: { + if (copy_to_user(argp, &dev->user_wmode, sizeof(int))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + break; + } + + case SSD_CMD_DEBUG: { + struct ssd_debug_info db_info; + + if (!finject) { + ret = -EOPNOTSUPP; + break; + } + + if (copy_from_user(&db_info, argp, sizeof(struct ssd_debug_info))) { + hio_warn("%s: copy_from_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + + if (db_info.type < SSD_DEBUG_NONE || db_info.type >= SSD_DEBUG_NR) { + ret = -EINVAL; + break; + } + + /* IO */ + if (db_info.type >= SSD_DEBUG_READ_ERR && db_info.type <= SSD_DEBUG_RW_ERR && + (db_info.data.loc.off + db_info.data.loc.len) > (dev->hw_info.size >> 9)) { + ret = -EINVAL; + break; + } + + memcpy(&dev->db_info, &db_info, sizeof(struct ssd_debug_info)); + +#ifdef SSD_OT_PROTECT + /* temperature */ + if (db_info.type == SSD_DEBUG_NONE) { + ssd_check_temperature(dev, SSD_OT_TEMP); + } else if (db_info.type == SSD_DEBUG_LOG) { + if (db_info.data.log.event == SSD_LOG_OVER_TEMP) { + dev->ot_delay = SSD_OT_DELAY; + } else if (db_info.data.log.event == SSD_LOG_NORMAL_TEMP) { + dev->ot_delay = 0; + } + } +#endif + + /* offline */ + if (db_info.type == SSD_DEBUG_OFFLINE) { + test_and_clear_bit(SSD_ONLINE, &dev->state); + } else if (db_info.type == SSD_DEBUG_NONE) { + (void)test_and_set_bit(SSD_ONLINE, &dev->state); + } + + /* log */ + if (db_info.type == SSD_DEBUG_LOG && dev->event_call && dev->gd) { + dev->event_call(dev->gd, db_info.data.log.event, 0); + } + + break; + } + + case SSD_CMD_DRV_PARAM_INFO: { + struct ssd_drv_param_info drv_param; + + memset(&drv_param, 0, sizeof(struct ssd_drv_param_info)); + + drv_param.mode = mode; + drv_param.status_mask = status_mask; + drv_param.int_mode = int_mode; + drv_param.threaded_irq = threaded_irq; + drv_param.log_level = log_level; + drv_param.wmode = wmode; + drv_param.ot_protect = ot_protect; + drv_param.finject = finject; + + if (copy_to_user(argp, &drv_param, sizeof(struct ssd_drv_param_info))) { + hio_warn("%s: copy_to_user: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + } + + default: + ret = -EINVAL; + break; + } + + return ret; +} + + +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,27)) +static int ssd_block_ioctl(struct inode *inode, struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct ssd_device *dev; + void __user *argp = (void __user *)arg; + int ret = 0; + + if (!inode) { + return -EINVAL; + } + dev = inode->i_bdev->bd_disk->private_data; + if (!dev) { + return -EINVAL; + } +#else +static int ssd_block_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + struct ssd_device *dev; + void __user *argp = (void __user *)arg; + int ret = 0; + + if (!bdev) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + if (!dev) { + return -EINVAL; + } +#endif + + switch (cmd) { + case HDIO_GETGEO: { + struct hd_geometry geo; + geo.cylinders = (dev->hw_info.size & ~0x3f) >> 6; + geo.heads = 4; + geo.sectors = 16; +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,27)) + geo.start = get_start_sect(inode->i_bdev); +#else + geo.start = get_start_sect(bdev); +#endif + if (copy_to_user(argp, &geo, sizeof(geo))) { + ret = -EFAULT; + break; + } + + break; + } + + case BLKFLSBUF: + ret = ssd_flush(dev); + if (ret) { + hio_warn("%s: ssd_flush: failed\n", dev->name); + ret = -EFAULT; + break; + } + break; + + default: + if (!dev->slave) { + ret = ssd_ioctl_common(dev, cmd, arg); + } else { + ret = -EFAULT; + } + break; + } + + return ret; +} + + +static void ssd_free_dev(struct kref *kref) +{ + struct ssd_device *dev; + + if (!kref) { + return; + } + + dev = container_of(kref, struct ssd_device, kref); + + put_disk(dev->gd); + + ssd_put_index(dev->slave, dev->idx); + + kfree(dev); +} + +static void ssd_put(struct ssd_device *dev) +{ + kref_put(&dev->kref, ssd_free_dev); +} + +static int ssd_get(struct ssd_device *dev) +{ + kref_get(&dev->kref); + return 0; +} + +/* block device */ +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,27)) +static int ssd_block_open(struct inode *inode, struct file *filp) +{ + struct ssd_device *dev; + + if (!inode) { + return -EINVAL; + } + + dev = inode->i_bdev->bd_disk->private_data; + if (!dev) { + return -EINVAL; + } +#else +static int ssd_block_open(struct block_device *bdev, fmode_t mode) +{ + struct ssd_device *dev; + + if (!bdev) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + if (!dev) { + return -EINVAL; + } +#endif + + /*if (!try_module_get(dev->owner)) + return -ENODEV; + */ + + ssd_get(dev); + + atomic_inc(&dev->refcnt); + + return 0; +} + +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,27)) +static int ssd_block_release(struct inode *inode, struct file *filp) +{ + struct ssd_device *dev; + + if (!inode) { + return -EINVAL; + } + + dev = inode->i_bdev->bd_disk->private_data; + if (!dev) { + return -EINVAL; + } +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(3,9,0)) +static int ssd_block_release(struct gendisk *disk, fmode_t mode) +{ + struct ssd_device *dev; + + if (!disk) { + return -EINVAL; + } + + dev = disk->private_data; + if (!dev) { + return -EINVAL; + } +#else +static void ssd_block_release(struct gendisk *disk, fmode_t mode) +{ + struct ssd_device *dev; + + if (!disk) { + return; + } + + dev = disk->private_data; + if (!dev) { + return; + } +#endif + + atomic_dec(&dev->refcnt); + + ssd_put(dev); + + //module_put(dev->owner); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(3,9,0)) + return 0; +#endif +} + +static struct block_device_operations ssd_fops = { + .owner = THIS_MODULE, + .open = ssd_block_open, + .release = ssd_block_release, + .ioctl = ssd_block_ioctl, +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,16)) + .getgeo = ssd_block_getgeo, +#endif +}; + +static void ssd_init_trim(ssd_device_t *dev) +{ +#if (defined SSD_TRIM && (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,32))) + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + return; + } + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, dev->rq); + +#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,33)) || (defined RHEL_MAJOR && RHEL_MAJOR >= 6)) + dev->rq->limits.discard_zeroes_data = 1; + dev->rq->limits.discard_alignment = 4096; + dev->rq->limits.discard_granularity = 4096; +#endif + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2_4) { + dev->rq->limits.max_discard_sectors = dev->hw_info.sg_max_sec; + } else { + dev->rq->limits.max_discard_sectors = (dev->hw_info.sg_max_sec) * (dev->hw_info.cmd_max_sg); + } +#endif +} + +static void ssd_cleanup_queue(struct ssd_device *dev) +{ + ssd_wait_io(dev); + + blk_cleanup_queue(dev->rq); + dev->rq = NULL; +} + +static int ssd_init_queue(struct ssd_device *dev) +{ + dev->rq = blk_alloc_queue(GFP_KERNEL); + if (dev->rq == NULL) { + hio_warn("%s: alloc queue: failed\n ", dev->name); + goto out_init_queue; + } + + /* must be first */ + blk_queue_make_request(dev->rq, ssd_make_request); + +#if ((LINUX_VERSION_CODE < KERNEL_VERSION(2,6,34)) && !(defined RHEL_MAJOR && RHEL_MAJOR == 6)) + blk_queue_max_hw_segments(dev->rq, dev->hw_info.cmd_max_sg); + blk_queue_max_phys_segments(dev->rq, dev->hw_info.cmd_max_sg); + blk_queue_max_sectors(dev->rq, dev->hw_info.sg_max_sec); +#else + blk_queue_max_segments(dev->rq, dev->hw_info.cmd_max_sg); + blk_queue_max_hw_sectors(dev->rq, dev->hw_info.sg_max_sec); +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,31)) + blk_queue_hardsect_size(dev->rq, 512); +#else + blk_queue_logical_block_size(dev->rq, 512); +#endif + /* not work for make_request based drivers(bio) */ + blk_queue_max_segment_size(dev->rq, dev->hw_info.sg_max_sec << 9); + + blk_queue_bounce_limit(dev->rq, BLK_BOUNCE_HIGH); + + dev->rq->queuedata = dev; + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) + blk_queue_issue_flush_fn(dev->rq, ssd_issue_flush_fn); +#endif + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,28)) + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, dev->rq); +#endif + + ssd_init_trim(dev); + + return 0; + +out_init_queue: + return -ENOMEM; +} + +static void ssd_cleanup_blkdev(struct ssd_device *dev) +{ + del_gendisk(dev->gd); +} + +static int ssd_init_blkdev(struct ssd_device *dev) +{ + if (dev->gd) { + put_disk(dev->gd); + } + + dev->gd = alloc_disk(ssd_minors); + if (!dev->gd) { + hio_warn("%s: alloc_disk fail\n", dev->name); + goto out_alloc_gd; + } + dev->gd->major = dev->major; + dev->gd->first_minor = dev->idx * ssd_minors; + dev->gd->fops = &ssd_fops; + dev->gd->queue = dev->rq; + dev->gd->private_data = dev; + dev->gd->driverfs_dev = &dev->pdev->dev; + snprintf (dev->gd->disk_name, sizeof(dev->gd->disk_name), "%s", dev->name); + + set_capacity(dev->gd, dev->hw_info.size >> 9); + + add_disk(dev->gd); + + return 0; + +out_alloc_gd: + return -ENOMEM; +} + +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,10)) +static int ssd_ioctl(struct inode *inode, struct file *file, + unsigned int cmd, unsigned long arg) +#else +static long ssd_ioctl(struct file *file, + unsigned int cmd, unsigned long arg) +#endif +{ + struct ssd_device *dev; + + if (!file) { + return -EINVAL; + } + + dev = file->private_data; + if (!dev) { + return -EINVAL; + } + + return (long)ssd_ioctl_common(dev, cmd, arg); +} + +static int ssd_open(struct inode *inode, struct file *file) +{ + struct ssd_device *dev = NULL; + struct ssd_device *n = NULL; + int idx; + int ret = -ENODEV; + + if (!inode || !file) { + return -EINVAL; + } + + idx = iminor(inode); + + list_for_each_entry_safe(dev, n, &ssd_list, list) { + if (dev->idx == idx) { + ret = 0; + break; + } + } + + if (ret) { + return ret; + } + + file->private_data = dev; + + ssd_get(dev); + + return 0; +} + +static int ssd_release(struct inode *inode, struct file *file) +{ + struct ssd_device *dev; + + if (!file) { + return -EINVAL; + } + + dev = file->private_data; + if (!dev) { + return -EINVAL; + } + + ssd_put(dev); + + file->private_data = NULL; + + return 0; +} + +static struct file_operations ssd_cfops = { + .owner = THIS_MODULE, + .open = ssd_open, + .release = ssd_release, +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,10)) + .ioctl = ssd_ioctl, +#else + .unlocked_ioctl = ssd_ioctl, +#endif +}; + +static void ssd_cleanup_chardev(struct ssd_device *dev) +{ + if (dev->slave) { + return; + } + +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,12)) + class_simple_device_remove(MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx)); + devfs_remove("c%s", dev->name); +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,14)) + class_device_destroy(ssd_class, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx)); + devfs_remove("c%s", dev->name); +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,17)) + class_device_destroy(ssd_class, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx)); + devfs_remove("c%s", dev->name); +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,24)) + class_device_destroy(ssd_class, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx)); +#else + device_destroy(ssd_class, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx)); +#endif +} + +static int ssd_init_chardev(struct ssd_device *dev) +{ + int ret = 0; + + if (dev->slave) { + return 0; + } + +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,12)) + ret = devfs_mk_cdev(MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), S_IFCHR|S_IRUSR|S_IWUSR, "c%s", dev->name); + if (ret) { + goto out; + } + class_simple_device_add(ssd_class, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), NULL, "c%s", dev->name); +out: +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,14)) + ret = devfs_mk_cdev(MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), S_IFCHR|S_IRUSR|S_IWUSR, "c%s", dev->name); + if (ret) { + goto out; + } + class_device_create(ssd_class, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), NULL, "c%s", dev->name); +out: +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,17)) + ret = devfs_mk_cdev(MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), S_IFCHR|S_IRUSR|S_IWUSR, "c%s", dev->name); + if (ret) { + goto out; + } + class_device_create(ssd_class, NULL, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), NULL, "c%s", dev->name); +out: +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,24)) + class_device_create(ssd_class, NULL, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), NULL, "c%s", dev->name); +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,26)) + device_create(ssd_class, NULL, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), "c%s", dev->name); +#elif (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,27)) + device_create_drvdata(ssd_class, NULL, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), NULL, "c%s", dev->name); +#else + device_create(ssd_class, NULL, MKDEV((dev_t)dev->cmajor, (dev_t)dev->idx), NULL, "c%s", dev->name); +#endif + + return ret; +} + +static int ssd_check_hw(struct ssd_device *dev) +{ + uint32_t test_data = 0x55AA5AA5; + uint32_t read_data; + + ssd_reg32_write(dev->ctrlp + SSD_BRIDGE_TEST_REG, test_data); + read_data = ssd_reg32_read(dev->ctrlp + SSD_BRIDGE_TEST_REG); + if (read_data != ~(test_data)) { + //hio_warn("%s: check bridge error: %#x\n", dev->name, read_data); + return -1; + } + + return 0; +} + +static int ssd_check_fw(struct ssd_device *dev) +{ + uint32_t val = 0; + int i; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_3) { + return 0; + } + + for (i=0; ictrlp + SSD_HW_STATUS_REG); + if ((val & 0x1) && ((val >> 8) & 0x1)) { + break; + } + + msleep(SSD_INIT_WAIT); + } + + if (!(val & 0x1)) { + /* controller fw status */ + hio_warn("%s: controller firmware load failed: %#x\n", dev->name, val); + return -1; + } else if (!((val >> 8) & 0x1)) { + /* controller state */ + hio_warn("%s: controller state error: %#x\n", dev->name, val); + return -1; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_RELOAD_FW_REG); + if (val) { + dev->reload_fw = 1; + } + + return 0; +} + +static int ssd_init_fw_info(struct ssd_device *dev) +{ + uint32_t val; + int ret = 0; + + val = ssd_reg32_read(dev->ctrlp + SSD_BRIDGE_VER_REG); + dev->hw_info.bridge_ver = val & 0xFFF; + if (dev->hw_info.bridge_ver < SSD_FW_MIN) { + hio_warn("%s: bridge firmware version %03X is not supported\n", dev->name, dev->hw_info.bridge_ver); + return -EINVAL; + } + hio_info("%s: bridge firmware version: %03X\n", dev->name, dev->hw_info.bridge_ver); + + ret = ssd_check_fw(dev); + if (ret) { + goto out; + } + +out: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +static int ssd_check_clock(struct ssd_device *dev) +{ + uint32_t val; + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_3) { + return 0; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_HW_STATUS_REG); + + /* clock status */ + if (!((val >> 4 ) & 0x1)) { + if (!test_and_set_bit(SSD_HWMON_CLOCK(SSD_CLOCK_166M_LOST), &dev->hwmon)) { + hio_warn("%s: 166MHz clock losed: %#x\n", dev->name, val); + ssd_gen_swlog(dev, SSD_LOG_CLK_FAULT, val); + } + ret = -1; + } + + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + if (!((val >> 5 ) & 0x1)) { + if (!test_and_set_bit(SSD_HWMON_CLOCK(SSD_CLOCK_166M_SKEW), &dev->hwmon)) { + hio_warn("%s: 166MHz clock is skew: %#x\n", dev->name, val); + ssd_gen_swlog(dev, SSD_LOG_CLK_FAULT, val); + } + ret = -1; + } + if (!((val >> 6 ) & 0x1)) { + if (!test_and_set_bit(SSD_HWMON_CLOCK(SSD_CLOCK_156M_LOST), &dev->hwmon)) { + hio_warn("%s: 156.25MHz clock lost: %#x\n", dev->name, val); + ssd_gen_swlog(dev, SSD_LOG_CLK_FAULT, val); + } + ret = -1; + } + if (!((val >> 7 ) & 0x1)) { + if (!test_and_set_bit(SSD_HWMON_CLOCK(SSD_CLOCK_156M_SKEW), &dev->hwmon)) { + hio_warn("%s: 156.25MHz clock is skew: %#x\n", dev->name, val); + ssd_gen_swlog(dev, SSD_LOG_CLK_FAULT, val); + } + ret = -1; + } + } + + return ret; +} + +static int ssd_check_volt(struct ssd_device *dev) +{ + int i = 0; + uint64_t val; + uint32_t adc_val; + int ret =0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + return 0; + } + + for (i=0; ihw_info.nr_ctrl; i++) { + /* 1.0v */ + if (!test_bit(SSD_HWMON_FPGA(i, SSD_FPGA_1V0), &dev->hwmon)) { + val = ssd_reg_read(dev->ctrlp + SSD_FPGA_1V0_REG0 + i * SSD_CTRL_REG_ZONE_SZ); + adc_val = SSD_FPGA_VOLT_MAX(val); + if (adc_val < SSD_FPGA_1V0_ADC_MIN || adc_val > SSD_FPGA_1V0_ADC_MAX) { + (void)test_and_set_bit(SSD_HWMON_FPGA(i, SSD_FPGA_1V0), &dev->hwmon); + hio_warn("%s: controller %d 1.0V fault: %d mV.\n", dev->name, i, SSD_FPGA_VOLT(adc_val)); + ssd_gen_swlog(dev, SSD_LOG_VOLT_FAULT, SSD_VOLT_LOG_DATA(SSD_FPGA_1V0, i, adc_val)); + ret = -1; + } + + adc_val = SSD_FPGA_VOLT_MIN(val); + if (adc_val < SSD_FPGA_1V0_ADC_MIN || adc_val > SSD_FPGA_1V0_ADC_MAX) { + (void)test_and_set_bit(SSD_HWMON_FPGA(i, SSD_FPGA_1V0), &dev->hwmon); + hio_warn("%s: controller %d 1.0V fault: %d mV.\n", dev->name, i, SSD_FPGA_VOLT(adc_val)); + ssd_gen_swlog(dev, SSD_LOG_VOLT_FAULT, SSD_VOLT_LOG_DATA(SSD_FPGA_1V0, i, adc_val)); + ret = -2; + } + } + + /* 1.8v */ + if (!test_bit(SSD_HWMON_FPGA(i, SSD_FPGA_1V8), &dev->hwmon)) { + val = ssd_reg_read(dev->ctrlp + SSD_FPGA_1V8_REG0 + i * SSD_CTRL_REG_ZONE_SZ); + adc_val = SSD_FPGA_VOLT_MAX(val); + if (adc_val < SSD_FPGA_1V8_ADC_MIN || adc_val > SSD_FPGA_1V8_ADC_MAX) { + (void)test_and_set_bit(SSD_HWMON_FPGA(i, SSD_FPGA_1V8), &dev->hwmon); + hio_warn("%s: controller %d 1.8V fault: %d mV.\n", dev->name, i, SSD_FPGA_VOLT(adc_val)); + ssd_gen_swlog(dev, SSD_LOG_VOLT_FAULT, SSD_VOLT_LOG_DATA(SSD_FPGA_1V8, i, adc_val)); + ret = -3; + } + + adc_val = SSD_FPGA_VOLT_MIN(val); + if (adc_val < SSD_FPGA_1V8_ADC_MIN || adc_val > SSD_FPGA_1V8_ADC_MAX) { + (void)test_and_set_bit(SSD_HWMON_FPGA(i, SSD_FPGA_1V8), &dev->hwmon); + hio_warn("%s: controller %d 1.8V fault: %d mV.\n", dev->name, i, SSD_FPGA_VOLT(adc_val)); + ssd_gen_swlog(dev, SSD_LOG_VOLT_FAULT, SSD_VOLT_LOG_DATA(SSD_FPGA_1V8, i, adc_val)); + ret = -4; + } + } + } + + return ret; +} + +static int ssd_check_reset_sync(struct ssd_device *dev) +{ + uint32_t val; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_3) { + return 0; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_HW_STATUS_REG); + if (!((val >> 8) & 0x1)) { + /* controller state */ + hio_warn("%s: controller state error: %#x\n", dev->name, val); + return -1; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + return 0; + } + + if (((val >> 9 ) & 0x1)) { + hio_warn("%s: controller reset asynchronously: %#x\n", dev->name, val); + ssd_gen_swlog(dev, SSD_LOG_CTRL_RST_SYNC, val); + return -1; + } + + return 0; +} + +static int ssd_check_hw_bh(struct ssd_device *dev) +{ + int ret; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_3) { + return 0; + } + + /* clock status */ + ret = ssd_check_clock(dev); + if (ret) { + goto out; + } + +out: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +static int ssd_check_controller(struct ssd_device *dev) +{ + int ret; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_1_3) { + return 0; + } + + /* sync reset */ + ret = ssd_check_reset_sync(dev); + if (ret) { + goto out; + } + +out: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +static int ssd_check_controller_bh(struct ssd_device *dev) +{ + uint32_t test_data = 0x55AA5AA5; + uint32_t val; + int reg_base, reg_sz; + int init_wait = 0; + int i; + int ret = 0; + + if (mode != SSD_DRV_MODE_STANDARD) { + return 0; + } + + /* controller */ + val = ssd_reg32_read(dev->ctrlp + SSD_READY_REG); + if (val & 0x1) { + hio_warn("%s: controller 0 not ready\n", dev->name); + return -1; + } + + for (i=0; ihw_info.nr_ctrl; i++) { + reg_base = SSD_CTRL_TEST_REG0 + i * SSD_CTRL_TEST_REG_SZ; + ssd_reg32_write(dev->ctrlp + reg_base, test_data); + val = ssd_reg32_read(dev->ctrlp + reg_base); + if (val != ~(test_data)) { + hio_warn("%s: check controller %d error: %#x\n", dev->name, i, val); + return -1; + } + } + + /* clock */ + ret = ssd_check_volt(dev); + if (ret) { + return ret; + } + + /* ddr */ + if (dev->protocol_info.ver > SSD_PROTOCOL_V3) { + reg_base = SSD_PV3_RAM_STATUS_REG0; + reg_sz = SSD_PV3_RAM_STATUS_REG_SZ; + + for (i=0; ihw_info.nr_ctrl; i++) { +check_ram_status: + val = ssd_reg32_read(dev->ctrlp + reg_base); + + if (!((val >> 1) & 0x1)) { + init_wait++; + if (init_wait <= SSD_RAM_INIT_MAX_WAIT) { + msleep(SSD_INIT_WAIT); + goto check_ram_status; + } else { + hio_warn("%s: controller %d ram init failed: %#x\n", dev->name, i, val); + ssd_gen_swlog(dev, SSD_LOG_DDR_INIT_ERR, i); + return -1; + } + } + + reg_base += reg_sz; + } + } + + /* ch info */ + for (i=0; ictrlp + SSD_CH_INFO_REG); + if (!((val >> 31) & 0x1)) { + break; + } + + msleep(SSD_INIT_WAIT); + } + if ((val >> 31) & 0x1) { + hio_warn("%s: channel info init failed: %#x\n", dev->name, val); + return -1; + } + + return 0; +} + +static int ssd_init_protocol_info(struct ssd_device *dev) +{ + uint32_t val; + + val = ssd_reg32_read(dev->ctrlp + SSD_PROTOCOL_VER_REG); + if (val == (uint32_t)-1) { + hio_warn("%s: protocol version error: %#x\n", dev->name, val); + return -EINVAL; + } + dev->protocol_info.ver = val; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + dev->protocol_info.init_state_reg = SSD_INIT_STATE_REG0; + dev->protocol_info.init_state_reg_sz = SSD_INIT_STATE_REG_SZ; + + dev->protocol_info.chip_info_reg = SSD_CHIP_INFO_REG0; + dev->protocol_info.chip_info_reg_sz = SSD_CHIP_INFO_REG_SZ; + } else { + dev->protocol_info.init_state_reg = SSD_PV3_INIT_STATE_REG0; + dev->protocol_info.init_state_reg_sz = SSD_PV3_INIT_STATE_REG_SZ; + + dev->protocol_info.chip_info_reg = SSD_PV3_CHIP_INFO_REG0; + dev->protocol_info.chip_info_reg_sz = SSD_PV3_CHIP_INFO_REG_SZ; + } + + return 0; +} + +static int ssd_init_hw_info(struct ssd_device *dev) +{ + uint64_t val64; + uint32_t val; + uint32_t nr_ctrl; + int ret = 0; + + /* base info */ + val = ssd_reg32_read(dev->ctrlp + SSD_RESP_INFO_REG); + dev->hw_info.resp_ptr_sz = 16 * (1U << (val & 0xFF)); + dev->hw_info.resp_msg_sz = 16 * (1U << ((val >> 8) & 0xFF)); + + if (0 == dev->hw_info.resp_ptr_sz || 0 == dev->hw_info.resp_msg_sz) { + hio_warn("%s: response info error\n", dev->name); + ret = -EINVAL; + goto out; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_BRIDGE_INFO_REG); + dev->hw_info.cmd_fifo_sz = 1U << ((val >> 4) & 0xF); + dev->hw_info.cmd_max_sg = 1U << ((val >> 8) & 0xF); + dev->hw_info.sg_max_sec = 1U << ((val >> 12) & 0xF); + dev->hw_info.cmd_fifo_sz_mask = dev->hw_info.cmd_fifo_sz - 1; + + if (0 == dev->hw_info.cmd_fifo_sz || 0 == dev->hw_info.cmd_max_sg || 0 == dev->hw_info.sg_max_sec) { + hio_warn("%s: cmd info error\n", dev->name); + ret = -EINVAL; + goto out; + } + + /* check hw */ + if (ssd_check_hw_bh(dev)) { + hio_warn("%s: check hardware status failed\n", dev->name); + ret = -EINVAL; + goto out; + } + + if (ssd_check_controller(dev)) { + hio_warn("%s: check controller state failed\n", dev->name); + ret = -EINVAL; + goto out; + } + + /* nr controller : read again*/ + val = ssd_reg32_read(dev->ctrlp + SSD_BRIDGE_INFO_REG); + dev->hw_info.nr_ctrl = (val >> 16) & 0xF; + + /* nr ctrl configured */ + nr_ctrl = (val >> 20) & 0xF; + if (0 == dev->hw_info.nr_ctrl) { + hio_warn("%s: nr controller error: %u\n", dev->name, dev->hw_info.nr_ctrl); + ret = -EINVAL; + goto out; + } else if (0 != nr_ctrl && nr_ctrl != dev->hw_info.nr_ctrl) { + hio_warn("%s: nr controller error: configured %u but found %u\n", dev->name, nr_ctrl, dev->hw_info.nr_ctrl); + if (mode <= SSD_DRV_MODE_STANDARD) { + ret = -EINVAL; + goto out; + } + } + + if (ssd_check_controller_bh(dev)) { + hio_warn("%s: check controller failed\n", dev->name); + ret = -EINVAL; + goto out; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_PCB_VER_REG); + dev->hw_info.pcb_ver = (uint8_t) ((val >> 4) & 0xF) + 'A' -1; + if ((val & 0xF) != 0xF) { + dev->hw_info.upper_pcb_ver = (uint8_t) (val & 0xF) + 'A' -1; + } + + if (dev->hw_info.pcb_ver < 'A' || (0 != dev->hw_info.upper_pcb_ver && dev->hw_info.upper_pcb_ver < 'A')) { + hio_warn("%s: PCB version error: %#x %#x\n", dev->name, dev->hw_info.pcb_ver, dev->hw_info.upper_pcb_ver); + ret = -EINVAL; + goto out; + } + + /* channel info */ + if (mode <= SSD_DRV_MODE_DEBUG) { + val = ssd_reg32_read(dev->ctrlp + SSD_CH_INFO_REG); + dev->hw_info.nr_data_ch = val & 0xFF; + dev->hw_info.nr_ch = dev->hw_info.nr_data_ch + ((val >> 8) & 0xFF); + dev->hw_info.nr_chip = (val >> 16) & 0xFF; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + dev->hw_info.max_ch = 1; + while (dev->hw_info.max_ch < dev->hw_info.nr_ch) dev->hw_info.max_ch <<= 1; + } else { + /* set max channel 32 */ + dev->hw_info.max_ch = 32; + } + + if (0 == dev->hw_info.nr_chip) { + //for debug mode + dev->hw_info.nr_chip = 1; + } + + //xx + dev->hw_info.id_size = SSD_NAND_ID_SZ; + dev->hw_info.max_ce = SSD_NAND_MAX_CE; + + if (0 == dev->hw_info.nr_data_ch || 0 == dev->hw_info.nr_ch || 0 == dev->hw_info.nr_chip) { + hio_warn("%s: channel info error: data_ch %u ch %u chip %u\n", dev->name, dev->hw_info.nr_data_ch, dev->hw_info.nr_ch, dev->hw_info.nr_chip); + ret = -EINVAL; + goto out; + } + } + + /* ram info */ + if (mode <= SSD_DRV_MODE_DEBUG) { + val = ssd_reg32_read(dev->ctrlp + SSD_RAM_INFO_REG); + dev->hw_info.ram_size = 0x4000000ull * (1ULL << (val & 0xF)); + dev->hw_info.ram_align = 1U << ((val >> 12) & 0xF); + if (dev->hw_info.ram_align < SSD_RAM_ALIGN) { + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + dev->hw_info.ram_align = SSD_RAM_ALIGN; + } else { + hio_warn("%s: ram align error: %u\n", dev->name, dev->hw_info.ram_align); + ret = -EINVAL; + goto out; + } + } + dev->hw_info.ram_max_len = 0x1000 * (1U << ((val >> 16) & 0xF)); + + if (0 == dev->hw_info.ram_size || 0 == dev->hw_info.ram_align || 0 == dev->hw_info.ram_max_len || dev->hw_info.ram_align > dev->hw_info.ram_max_len) { + hio_warn("%s: ram info error\n", dev->name); + ret = -EINVAL; + goto out; + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + dev->hw_info.log_sz = SSD_LOG_MAX_SZ; + } else { + val = ssd_reg32_read(dev->ctrlp + SSD_LOG_INFO_REG); + dev->hw_info.log_sz = 0x1000 * (1U << (val & 0xFF)); + } + if (0 == dev->hw_info.log_sz) { + hio_warn("%s: log size error\n", dev->name); + ret = -EINVAL; + goto out; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_BBT_BASE_REG); + dev->hw_info.bbt_base = 0x40000ull * (val & 0xFFFF); + dev->hw_info.bbt_size = 0x40000 * (((val >> 16) & 0xFFFF) + 1) / (dev->hw_info.max_ch * dev->hw_info.nr_chip); + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + if (dev->hw_info.bbt_base > dev->hw_info.ram_size || 0 == dev->hw_info.bbt_size) { + hio_warn("%s: bbt info error\n", dev->name); + ret = -EINVAL; + goto out; + } + } + + val = ssd_reg32_read(dev->ctrlp + SSD_ECT_BASE_REG); + dev->hw_info.md_base = 0x40000ull * (val & 0xFFFF); + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + dev->hw_info.md_size = 0x40000 * (((val >> 16) & 0xFFF) + 1) / (dev->hw_info.max_ch * dev->hw_info.nr_chip); + } else { + dev->hw_info.md_size = 0x40000 * (((val >> 16) & 0xFFF) + 1) / (dev->hw_info.nr_chip); + } + dev->hw_info.md_entry_sz = 8 * (1U << ((val >> 28) & 0xF)); + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3) { + if (dev->hw_info.md_base > dev->hw_info.ram_size || 0 == dev->hw_info.md_size || + 0 == dev->hw_info.md_entry_sz || dev->hw_info.md_entry_sz > dev->hw_info.md_size) { + hio_warn("%s: md info error\n", dev->name); + ret = -EINVAL; + goto out; + } + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + dev->hw_info.nand_wbuff_base = dev->hw_info.ram_size + 1; + } else { + val = ssd_reg32_read(dev->ctrlp + SSD_NAND_BUFF_BASE); + dev->hw_info.nand_wbuff_base = 0x8000ull * val; + } + } + + /* flash info */ + if (mode <= SSD_DRV_MODE_DEBUG) { + if (dev->hw_info.nr_ctrl > 1) { + val = ssd_reg32_read(dev->ctrlp + SSD_CTRL_VER_REG); + dev->hw_info.ctrl_ver = val & 0xFFF; + hio_info("%s: controller firmware version: %03X\n", dev->name, dev->hw_info.ctrl_ver); + } + + val64 = ssd_reg_read(dev->ctrlp + SSD_FLASH_INFO_REG0); + dev->hw_info.nand_vendor_id = ((val64 >> 56) & 0xFF); + dev->hw_info.nand_dev_id = ((val64 >> 48) & 0xFF); + + dev->hw_info.block_count = (((val64 >> 32) & 0xFFFF) + 1); + dev->hw_info.page_count = ((val64>>16) & 0xFFFF); + dev->hw_info.page_size = (val64 & 0xFFFF); + + val = ssd_reg32_read(dev->ctrlp + SSD_BB_INFO_REG); + dev->hw_info.bbf_pages = val & 0xFF; + dev->hw_info.bbf_seek = (val >> 8) & 0x1; + + if (0 == dev->hw_info.block_count || 0 == dev->hw_info.page_count || 0 == dev->hw_info.page_size || dev->hw_info.block_count > INT_MAX) { + hio_warn("%s: flash info error\n", dev->name); + ret = -EINVAL; + goto out; + } + + //xx + dev->hw_info.oob_size = SSD_NAND_OOB_SZ; //(dev->hw_info.page_size) >> 5; + + val = ssd_reg32_read(dev->ctrlp + SSD_VALID_PAGES_REG); + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + dev->hw_info.valid_pages = val & 0x3FF; + dev->hw_info.max_valid_pages = (val>>20) & 0x3FF; + } else { + dev->hw_info.valid_pages = val & 0x7FFF; + dev->hw_info.max_valid_pages = (val>>15) & 0x7FFF; + } + if (0 == dev->hw_info.valid_pages || 0 == dev->hw_info.max_valid_pages || + dev->hw_info.valid_pages > dev->hw_info.max_valid_pages || dev->hw_info.max_valid_pages > dev->hw_info.page_count) { + hio_warn("%s: valid page info error: valid_pages %d, max_valid_pages %d\n", dev->name, dev->hw_info.valid_pages, dev->hw_info.max_valid_pages); + ret = -EINVAL; + goto out; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_RESERVED_BLKS_REG); + dev->hw_info.reserved_blks = val & 0xFFFF; + dev->hw_info.md_reserved_blks = (val >> 16) & 0xFF; + if (dev->protocol_info.ver <= SSD_PROTOCOL_V3) { + dev->hw_info.md_reserved_blks = SSD_BBT_RESERVED; + } + if (dev->hw_info.reserved_blks > dev->hw_info.block_count || dev->hw_info.md_reserved_blks > dev->hw_info.block_count) { + hio_warn("%s: reserved blocks info error: reserved_blks %d, md_reserved_blks %d\n", dev->name, dev->hw_info.reserved_blks, dev->hw_info.md_reserved_blks); + ret = -EINVAL; + goto out; + } + } + + /* size */ + if (mode < SSD_DRV_MODE_DEBUG) { + dev->hw_info.size = (uint64_t)dev->hw_info.valid_pages * dev->hw_info.page_size; + dev->hw_info.size *= (dev->hw_info.block_count - dev->hw_info.reserved_blks); + dev->hw_info.size *= ((uint64_t)dev->hw_info.nr_data_ch * (uint64_t)dev->hw_info.nr_chip * (uint64_t)dev->hw_info.nr_ctrl); + } + + /* extend hardware info */ + val = ssd_reg32_read(dev->ctrlp + SSD_PCB_VER_REG); + dev->hw_info_ext.board_type = (val >> 24) & 0xF; + + dev->hw_info_ext.form_factor = SSD_FORM_FACTOR_FHHL; + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2_1) { + dev->hw_info_ext.form_factor = (val >> 31) & 0x1; + } + /* + dev->hw_info_ext.cap_type = (val >> 28) & 0x3; + if (SSD_BM_CAP_VINA != dev->hw_info_ext.cap_type && SSD_BM_CAP_JH != dev->hw_info_ext.cap_type) { + dev->hw_info_ext.cap_type = SSD_BM_CAP_VINA; + }*/ + + /* power loss protect */ + val = ssd_reg32_read(dev->ctrlp + SSD_PLP_INFO_REG); + dev->hw_info_ext.plp_type = (val & 0x3); + if (dev->protocol_info.ver >= SSD_PROTOCOL_V3_2) { + /* 3 or 4 cap */ + dev->hw_info_ext.cap_type = ((val >> 2)& 0x1); + } + + /* work mode */ + val = ssd_reg32_read(dev->ctrlp + SSD_CH_INFO_REG); + dev->hw_info_ext.work_mode = (val >> 25) & 0x1; + +out: + /* skip error if not in standard mode */ + if (mode != SSD_DRV_MODE_STANDARD) { + ret = 0; + } + return ret; +} + +static void ssd_cleanup_response(struct ssd_device *dev) +{ + int resp_msg_sz = dev->hw_info.resp_msg_sz * dev->hw_info.cmd_fifo_sz * SSD_MSIX_VEC; + int resp_ptr_sz = dev->hw_info.resp_ptr_sz * SSD_MSIX_VEC; + + pci_free_consistent(dev->pdev, resp_ptr_sz, dev->resp_ptr_base, dev->resp_ptr_base_dma); + pci_free_consistent(dev->pdev, resp_msg_sz, dev->resp_msg_base, dev->resp_msg_base_dma); +} + +static int ssd_init_response(struct ssd_device *dev) +{ + int resp_msg_sz = dev->hw_info.resp_msg_sz * dev->hw_info.cmd_fifo_sz * SSD_MSIX_VEC; + int resp_ptr_sz = dev->hw_info.resp_ptr_sz * SSD_MSIX_VEC; + + dev->resp_msg_base = pci_alloc_consistent(dev->pdev, resp_msg_sz, &(dev->resp_msg_base_dma)); + if (!dev->resp_msg_base) { + hio_warn("%s: unable to allocate resp msg DMA buffer\n", dev->name); + goto out_alloc_resp_msg; + } + memset(dev->resp_msg_base, 0xFF, resp_msg_sz); + + dev->resp_ptr_base = pci_alloc_consistent(dev->pdev, resp_ptr_sz, &(dev->resp_ptr_base_dma)); + if (!dev->resp_ptr_base){ + hio_warn("%s: unable to allocate resp ptr DMA buffer\n", dev->name); + goto out_alloc_resp_ptr; + } + memset(dev->resp_ptr_base, 0, resp_ptr_sz); + dev->resp_idx = *(uint32_t *)(dev->resp_ptr_base) = dev->hw_info.cmd_fifo_sz * 2 - 1; + + ssd_reg_write(dev->ctrlp + SSD_RESP_FIFO_REG, dev->resp_msg_base_dma); + ssd_reg_write(dev->ctrlp + SSD_RESP_PTR_REG, dev->resp_ptr_base_dma); + + return 0; + +out_alloc_resp_ptr: + pci_free_consistent(dev->pdev, resp_msg_sz, dev->resp_msg_base, dev->resp_msg_base_dma); +out_alloc_resp_msg: + return -ENOMEM; +} + +static int ssd_cleanup_cmd(struct ssd_device *dev) +{ + int msg_sz = ALIGN(sizeof(struct ssd_rw_msg) + (dev->hw_info.cmd_max_sg - 1) * sizeof(struct ssd_sg_entry), SSD_DMA_ALIGN); + int i; + + for (i=0; i<(int)dev->hw_info.cmd_fifo_sz; i++) { + kfree(dev->cmd[i].sgl); + } + kfree(dev->cmd); + pci_free_consistent(dev->pdev, (msg_sz * dev->hw_info.cmd_fifo_sz), dev->msg_base, dev->msg_base_dma); + return 0; +} + +static int ssd_init_cmd(struct ssd_device *dev) +{ + int sgl_sz = sizeof(struct scatterlist) * dev->hw_info.cmd_max_sg; + int cmd_sz = sizeof(struct ssd_cmd) * dev->hw_info.cmd_fifo_sz; + int msg_sz = ALIGN(sizeof(struct ssd_rw_msg) + (dev->hw_info.cmd_max_sg - 1) * sizeof(struct ssd_sg_entry), SSD_DMA_ALIGN); + int i; + + spin_lock_init(&dev->cmd_lock); + + dev->msg_base = pci_alloc_consistent(dev->pdev, (msg_sz * dev->hw_info.cmd_fifo_sz), &dev->msg_base_dma); + if (!dev->msg_base) { + hio_warn("%s: can not alloc cmd msg\n", dev->name); + goto out_alloc_msg; + } + + dev->cmd = kmalloc(cmd_sz, GFP_KERNEL); + if (!dev->cmd) { + hio_warn("%s: can not alloc cmd\n", dev->name); + goto out_alloc_cmd; + } + memset(dev->cmd, 0, cmd_sz); + + for (i=0; i<(int)dev->hw_info.cmd_fifo_sz; i++) { + dev->cmd[i].sgl = kmalloc(sgl_sz, GFP_KERNEL); + if (!dev->cmd[i].sgl) { + hio_warn("%s: can not alloc cmd sgl %d\n", dev->name, i); + goto out_alloc_sgl; + } + + dev->cmd[i].msg = dev->msg_base + (msg_sz * i); + dev->cmd[i].msg_dma = dev->msg_base_dma + ((dma_addr_t)msg_sz * i); + + dev->cmd[i].dev = dev; + dev->cmd[i].tag = i; + dev->cmd[i].flag = 0; + + INIT_LIST_HEAD(&dev->cmd[i].list); + } + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3) { + dev->scmd = ssd_dispatch_cmd; + } else { + ssd_reg_write(dev->ctrlp + SSD_MSG_BASE_REG, dev->msg_base_dma); + if (finject) { + dev->scmd = ssd_send_cmd_db; + } else { + dev->scmd = ssd_send_cmd; + } + } + + return 0; + +out_alloc_sgl: + for (i--; i>=0; i--) { + kfree(dev->cmd[i].sgl); + } + kfree(dev->cmd); +out_alloc_cmd: + pci_free_consistent(dev->pdev, (msg_sz * dev->hw_info.cmd_fifo_sz), dev->msg_base, dev->msg_base_dma); +out_alloc_msg: + return -ENOMEM; +} + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,30)) +static irqreturn_t ssd_interrupt_check(int irq, void *dev_id) +{ + struct ssd_queue *queue = (struct ssd_queue *)dev_id; + + if (*(uint32_t *)queue->resp_ptr == queue->resp_idx) { + return IRQ_NONE; + } + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t ssd_interrupt_threaded(int irq, void *dev_id) +{ + struct ssd_queue *queue = (struct ssd_queue *)dev_id; + struct ssd_device *dev = (struct ssd_device *)queue->dev; + struct ssd_cmd *cmd; + union ssd_response_msq __msg; + union ssd_response_msq *msg = &__msg; + uint64_t *u64_msg; + uint32_t resp_idx = queue->resp_idx; + uint32_t new_resp_idx = *(uint32_t *)queue->resp_ptr; + uint32_t end_resp_idx; + + if (unlikely(resp_idx == new_resp_idx)) { + return IRQ_NONE; + } + + end_resp_idx = new_resp_idx & queue->resp_idx_mask; + + do { + resp_idx = (resp_idx + 1) & queue->resp_idx_mask; + + /* the resp msg */ + u64_msg = (uint64_t *)(queue->resp_msg + queue->resp_msg_sz * resp_idx); + msg->u64_msg = *u64_msg; + + if (unlikely(msg->u64_msg == (uint64_t)(-1))) { + hio_err("%s: empty resp msg: queue %d idx %u\n", dev->name, queue->idx, resp_idx); + continue; + } + /* clear the resp msg */ + *u64_msg = (uint64_t)(-1); + + cmd = &queue->cmd[msg->resp_msg.tag]; + /*if (unlikely(!cmd->bio)) { + printk(KERN_WARNING "%s: unknown tag %d fun %#x\n", + dev->name, msg->resp_msg.tag, msg->resp_msg.fun); + continue; + }*/ + + if(unlikely(msg->resp_msg.status & (uint32_t)status_mask)) { + cmd->errors = -EIO; + } else { + cmd->errors = 0; + } + cmd->nr_log = msg->log_resp_msg.nr_log; + + ssd_done(cmd); + + if (unlikely(msg->resp_msg.fun != SSD_FUNC_READ_LOG && msg->resp_msg.log > 0)) { + (void)test_and_set_bit(SSD_LOG_HW, &dev->state); + if (test_bit(SSD_INIT_WORKQ, &dev->state)) { + queue_work(dev->workq, &dev->log_work); + } + } + + if (unlikely(msg->resp_msg.status)) { + if (msg->resp_msg.fun == SSD_FUNC_READ || msg->resp_msg.fun == SSD_FUNC_WRITE) { + hio_err("%s: I/O error %d: tag %d fun %#x\n", + dev->name, msg->resp_msg.status, msg->resp_msg.tag, msg->resp_msg.fun); + + /* alarm led */ + ssd_set_alarm(dev); + queue->io_stat.nr_rwerr++; + ssd_gen_swlog(dev, SSD_LOG_EIO, msg->u32_msg[0]); + } else { + hio_info("%s: CMD error %d: tag %d fun %#x\n", + dev->name, msg->resp_msg.status, msg->resp_msg.tag, msg->resp_msg.fun); + + ssd_gen_swlog(dev, SSD_LOG_ECMD, msg->u32_msg[0]); + } + queue->io_stat.nr_ioerr++; + } + + if (msg->resp_msg.fun == SSD_FUNC_READ || + msg->resp_msg.fun == SSD_FUNC_NAND_READ_WOOB || + msg->resp_msg.fun == SSD_FUNC_NAND_READ) { + + queue->ecc_info.bitflip[msg->resp_msg.bitflip]++; + } + }while (resp_idx != end_resp_idx); + + queue->resp_idx = new_resp_idx; + + return IRQ_HANDLED; +} +#endif + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,19)) +static irqreturn_t ssd_interrupt(int irq, void *dev_id, struct pt_regs *regs) +#else +static irqreturn_t ssd_interrupt(int irq, void *dev_id) +#endif +{ + struct ssd_queue *queue = (struct ssd_queue *)dev_id; + struct ssd_device *dev = (struct ssd_device *)queue->dev; + struct ssd_cmd *cmd; + union ssd_response_msq __msg; + union ssd_response_msq *msg = &__msg; + uint64_t *u64_msg; + uint32_t resp_idx = queue->resp_idx; + uint32_t new_resp_idx = *(uint32_t *)queue->resp_ptr; + uint32_t end_resp_idx; + + if (unlikely(resp_idx == new_resp_idx)) { + return IRQ_NONE; + } + +#if (defined SSD_ESCAPE_IRQ) + if (SSD_INT_MSIX != dev->int_mode) { + dev->irq_cpu = smp_processor_id(); + } +#endif + + end_resp_idx = new_resp_idx & queue->resp_idx_mask; + + do { + resp_idx = (resp_idx + 1) & queue->resp_idx_mask; + + /* the resp msg */ + u64_msg = (uint64_t *)(queue->resp_msg + queue->resp_msg_sz * resp_idx); + msg->u64_msg = *u64_msg; + + if (unlikely(msg->u64_msg == (uint64_t)(-1))) { + hio_err("%s: empty resp msg: queue %d idx %u\n", dev->name, queue->idx, resp_idx); + continue; + } + /* clear the resp msg */ + *u64_msg = (uint64_t)(-1); + + cmd = &queue->cmd[msg->resp_msg.tag]; + /*if (unlikely(!cmd->bio)) { + printk(KERN_WARNING "%s: unknown tag %d fun %#x\n", + dev->name, msg->resp_msg.tag, msg->resp_msg.fun); + continue; + }*/ + + if(unlikely(msg->resp_msg.status & (uint32_t)status_mask)) { + cmd->errors = -EIO; + } else { + cmd->errors = 0; + } + cmd->nr_log = msg->log_resp_msg.nr_log; + + ssd_done_bh(cmd); + + if (unlikely(msg->resp_msg.fun != SSD_FUNC_READ_LOG && msg->resp_msg.log > 0)) { + (void)test_and_set_bit(SSD_LOG_HW, &dev->state); + if (test_bit(SSD_INIT_WORKQ, &dev->state)) { + queue_work(dev->workq, &dev->log_work); + } + } + + if (unlikely(msg->resp_msg.status)) { + if (msg->resp_msg.fun == SSD_FUNC_READ || msg->resp_msg.fun == SSD_FUNC_WRITE) { + hio_err("%s: I/O error %d: tag %d fun %#x\n", + dev->name, msg->resp_msg.status, msg->resp_msg.tag, msg->resp_msg.fun); + + /* alarm led */ + ssd_set_alarm(dev); + queue->io_stat.nr_rwerr++; + ssd_gen_swlog(dev, SSD_LOG_EIO, msg->u32_msg[0]); + } else { + hio_info("%s: CMD error %d: tag %d fun %#x\n", + dev->name, msg->resp_msg.status, msg->resp_msg.tag, msg->resp_msg.fun); + + ssd_gen_swlog(dev, SSD_LOG_ECMD, msg->u32_msg[0]); + } + queue->io_stat.nr_ioerr++; + } + + if (msg->resp_msg.fun == SSD_FUNC_READ || + msg->resp_msg.fun == SSD_FUNC_NAND_READ_WOOB || + msg->resp_msg.fun == SSD_FUNC_NAND_READ) { + + queue->ecc_info.bitflip[msg->resp_msg.bitflip]++; + } + }while (resp_idx != end_resp_idx); + + queue->resp_idx = new_resp_idx; + + return IRQ_HANDLED; +} + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,19)) +static irqreturn_t ssd_interrupt_legacy(int irq, void *dev_id, struct pt_regs *regs) +#else +static irqreturn_t ssd_interrupt_legacy(int irq, void *dev_id) +#endif +{ + irqreturn_t ret; + struct ssd_queue *queue = (struct ssd_queue *)dev_id; + struct ssd_device *dev = (struct ssd_device *)queue->dev; + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,19)) + ret = ssd_interrupt(irq, dev_id, regs); +#else + ret = ssd_interrupt(irq, dev_id); +#endif + + /* clear intr */ + if (IRQ_HANDLED == ret) { + ssd_reg32_write(dev->ctrlp + SSD_CLEAR_INTR_REG, 1); + } + + return ret; +} + +static void ssd_reset_resp_ptr(struct ssd_device *dev) +{ + int i; + + for (i=0; inr_queue; i++) { + *(uint32_t *)dev->queue[i].resp_ptr = dev->queue[i].resp_idx = (dev->hw_info.cmd_fifo_sz * 2) - 1; + } +} + +static void ssd_free_irq(struct ssd_device *dev) +{ + int i; + +#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,35)) || (defined RHEL_MAJOR && RHEL_MAJOR == 6)) + if (SSD_INT_MSIX == dev->int_mode) { + for (i=0; inr_queue; i++) { + irq_set_affinity_hint(dev->entry[i].vector, NULL); + } + } +#endif + + for (i=0; inr_queue; i++) { + free_irq(dev->entry[i].vector, &dev->queue[i]); + } + + if (SSD_INT_MSIX == dev->int_mode) { + pci_disable_msix(dev->pdev); + } else if (SSD_INT_MSI == dev->int_mode) { + pci_disable_msi(dev->pdev); + } + +} + +static int ssd_init_irq(struct ssd_device *dev) +{ +#if (!defined MODULE) && (defined SSD_MSIX_AFFINITY_FORCE) + const struct cpumask *cpu_mask; + static int cpu_affinity = 0; +#endif +#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,35)) || (defined RHEL_MAJOR && RHEL_MAJOR == 6)) + const struct cpumask *mask; + static int cpu = 0; + int j; +#endif + int i; + unsigned long flags = 0; + int ret = 0; + + ssd_reg32_write(dev->ctrlp + SSD_INTR_INTERVAL_REG, 0x800); + +#ifdef SSD_ESCAPE_IRQ + dev->irq_cpu = -1; +#endif + + if (int_mode >= SSD_INT_MSIX && pci_find_capability(dev->pdev, PCI_CAP_ID_MSIX)) { + dev->nr_queue = SSD_MSIX_VEC; + for (i=0; inr_queue; i++) { + dev->entry[i].entry = i; + } + for (;;) { + ret = pci_enable_msix(dev->pdev, dev->entry, dev->nr_queue); + if (ret == 0) { + break; + } else if (ret > 0) { + dev->nr_queue = ret; + } else { + hio_warn("%s: can not enable msix\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out; + } + } + +#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,35)) || (defined RHEL_MAJOR && RHEL_MAJOR == 6)) + mask = (dev_to_node(&dev->pdev->dev) == -1) ? cpu_online_mask : cpumask_of_node(dev_to_node(&dev->pdev->dev)); + if ((0 == cpu) || (!cpumask_intersects(mask, cpumask_of(cpu)))) { + cpu = cpumask_first(mask); + } + for (i=0; inr_queue; i++) { + irq_set_affinity_hint(dev->entry[i].vector, cpumask_of(cpu)); + cpu = cpumask_next(cpu, mask); + if (cpu >= nr_cpu_ids) { + cpu = cpumask_first(mask); + } + } +#endif + + dev->int_mode = SSD_INT_MSIX; + } else if (int_mode >= SSD_INT_MSI && pci_find_capability(dev->pdev, PCI_CAP_ID_MSI)) { + ret = pci_enable_msi(dev->pdev); + if (ret) { + hio_warn("%s: can not enable msi\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out; + } + + dev->nr_queue = 1; + dev->entry[0].vector = dev->pdev->irq; + + dev->int_mode = SSD_INT_MSI; + } else { + dev->nr_queue = 1; + dev->entry[0].vector = dev->pdev->irq; + + dev->int_mode = SSD_INT_LEGACY; + } + + for (i=0; inr_queue; i++) { + if (dev->nr_queue > 1) { + snprintf(dev->queue[i].name, SSD_QUEUE_NAME_LEN, "%s_e100-%d", dev->name, i); + } else { + snprintf(dev->queue[i].name, SSD_QUEUE_NAME_LEN, "%s_e100", dev->name); + } + + dev->queue[i].dev = dev; + dev->queue[i].idx = i; + + dev->queue[i].resp_idx = (dev->hw_info.cmd_fifo_sz * 2) - 1; + dev->queue[i].resp_idx_mask = dev->hw_info.cmd_fifo_sz - 1; + + dev->queue[i].resp_msg_sz = dev->hw_info.resp_msg_sz; + dev->queue[i].resp_msg = dev->resp_msg_base + dev->hw_info.resp_msg_sz * dev->hw_info.cmd_fifo_sz * i; + dev->queue[i].resp_ptr = dev->resp_ptr_base + dev->hw_info.resp_ptr_sz * i; + *(uint32_t *)dev->queue[i].resp_ptr = dev->queue[i].resp_idx; + + dev->queue[i].cmd = dev->cmd; + } + +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20)) + flags = IRQF_SHARED; +#else + flags = SA_SHIRQ; +#endif + + for (i=0; inr_queue; i++) { +#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,30)) + if (threaded_irq) { + ret = request_threaded_irq(dev->entry[i].vector, ssd_interrupt_check, ssd_interrupt_threaded, flags, dev->queue[i].name, &dev->queue[i]); + } else if (dev->int_mode == SSD_INT_LEGACY) { + ret = request_irq(dev->entry[i].vector, &ssd_interrupt_legacy, flags, dev->queue[i].name, &dev->queue[i]); + } else { + ret = request_irq(dev->entry[i].vector, &ssd_interrupt, flags, dev->queue[i].name, &dev->queue[i]); + } +#else + if (dev->int_mode == SSD_INT_LEGACY) { + ret = request_irq(dev->entry[i].vector, &ssd_interrupt_legacy, flags, dev->queue[i].name, &dev->queue[i]); + } else { + ret = request_irq(dev->entry[i].vector, &ssd_interrupt, flags, dev->queue[i].name, &dev->queue[i]); + } +#endif + if (ret) { + hio_warn("%s: request irq failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_request_irq; + } + +#if (!defined MODULE) && (defined SSD_MSIX_AFFINITY_FORCE) + cpu_mask = (dev_to_node(&dev->pdev->dev) == -1) ? cpu_online_mask : cpumask_of_node(dev_to_node(&dev->pdev->dev)); + if (SSD_INT_MSIX == dev->int_mode) { + if ((0 == cpu_affinity) || (!cpumask_intersects(mask, cpumask_of(cpu_affinity)))) { + cpu_affinity = cpumask_first(cpu_mask); + } + + irq_set_affinity(dev->entry[i].vector, cpumask_of(cpu_affinity)); + cpu_affinity = cpumask_next(cpu_affinity, cpu_mask); + if (cpu_affinity >= nr_cpu_ids) { + cpu_affinity = cpumask_first(cpu_mask); + } + } +#endif + } + + return ret; + +out_request_irq: +#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,35)) || (defined RHEL_MAJOR && RHEL_MAJOR == 6)) + if (SSD_INT_MSIX == dev->int_mode) { + for (j=0; jnr_queue; j++) { + irq_set_affinity_hint(dev->entry[j].vector, NULL); + } + } +#endif + + for (i--; i>=0; i--) { + free_irq(dev->entry[i].vector, &dev->queue[i]); + } + + if (SSD_INT_MSIX == dev->int_mode) { + pci_disable_msix(dev->pdev); + } else if (SSD_INT_MSI == dev->int_mode) { + pci_disable_msi(dev->pdev); + } + +out: + return ret; +} + +static void ssd_initial_log(struct ssd_device *dev) +{ + uint32_t val; + uint32_t speed, width; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + return; + } + + val = ssd_reg32_read(dev->ctrlp + SSD_POWER_ON_REG); + if (val) { + ssd_gen_swlog(dev, SSD_LOG_POWER_ON, dev->hw_info.bridge_ver); + } + + val = ssd_reg32_read(dev->ctrlp + SSD_PCIE_LINKSTATUS_REG); + speed = val & 0xF; + width = (val >> 4)& 0x3F; + if (0x1 == speed) { + hio_info("%s: PCIe: 2.5GT/s, x%u\n", dev->name, width); + } else if (0x2 == speed) { + hio_info("%s: PCIe: 5GT/s, x%u\n", dev->name, width); + } else { + hio_info("%s: PCIe: unknown GT/s, x%u\n", dev->name, width); + } + ssd_gen_swlog(dev, SSD_LOG_PCIE_LINK_STATUS, val); + + return; +} + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) +static void ssd_hwmon_worker(void *data) +{ + struct ssd_device *dev = (struct ssd_device *)data; +#else +static void ssd_hwmon_worker(struct work_struct *work) +{ + struct ssd_device *dev = container_of(work, struct ssd_device, hwmon_work); +#endif + + if (ssd_check_hw(dev)) { + //hio_err("%s: check hardware failed\n", dev->name); + return; + } + + ssd_check_clock(dev); + ssd_check_volt(dev); + + ssd_mon_boardvolt(dev); +} + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) +static void ssd_tempmon_worker(void *data) +{ + struct ssd_device *dev = (struct ssd_device *)data; +#else +static void ssd_tempmon_worker(struct work_struct *work) +{ + struct ssd_device *dev = container_of(work, struct ssd_device, tempmon_work); +#endif + + if (ssd_check_hw(dev)) { + //hio_err("%s: check hardware failed\n", dev->name); + return; + } + + ssd_mon_temp(dev); +} + + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) +static void ssd_capmon_worker(void *data) +{ + struct ssd_device *dev = (struct ssd_device *)data; +#else +static void ssd_capmon_worker(struct work_struct *work) +{ + struct ssd_device *dev = container_of(work, struct ssd_device, capmon_work); +#endif + uint32_t cap = 0; + uint32_t cap_threshold = SSD_PL_CAP_THRESHOLD; + int ret = 0; + + if (dev->protocol_info.ver < SSD_PROTOCOL_V3_2) { + return; + } + + if (dev->hw_info_ext.form_factor == SSD_FORM_FACTOR_FHHL && dev->hw_info.pcb_ver < 'B') { + return; + } + + /* fault before? */ + if (test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + ret = ssd_check_pl_cap_fast(dev); + if (ret) { + return; + } + } + + /* learn */ + ret = ssd_do_cap_learn(dev, &cap); + if (ret) { + hio_err("%s: cap learn failed\n", dev->name); + ssd_gen_swlog(dev, SSD_LOG_CAP_LEARN_FAULT, 0); + return; + } + + ssd_gen_swlog(dev, SSD_LOG_CAP_STATUS, cap); + + if (SSD_PL_CAP_CP == dev->hw_info_ext.cap_type) { + cap_threshold = SSD_PL_CAP_CP_THRESHOLD; + } + + //use the fw event id? + if (cap < cap_threshold) { + if (!test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_BATTERY_FAULT, 0); + } + } else if (cap >= (cap_threshold + SSD_PL_CAP_THRESHOLD_HYST)) { + if (test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon)) { + ssd_gen_swlog(dev, SSD_LOG_BATTERY_OK, 0); + } + } +} + +static void ssd_routine_start(void *data) +{ + struct ssd_device *dev; + + if (!data) { + return; + } + dev = data; + + dev->routine_tick++; + + if (test_bit(SSD_INIT_WORKQ, &dev->state) && !ssd_busy(dev)) { + (void)test_and_set_bit(SSD_LOG_HW, &dev->state); + queue_work(dev->workq, &dev->log_work); + } + + if ((dev->routine_tick % SSD_HWMON_ROUTINE_TICK) == 0 && test_bit(SSD_INIT_WORKQ, &dev->state)) { + queue_work(dev->workq, &dev->hwmon_work); + } + + if ((dev->routine_tick % SSD_CAPMON_ROUTINE_TICK) == 0 && test_bit(SSD_INIT_WORKQ, &dev->state)) { + queue_work(dev->workq, &dev->capmon_work); + } + + if ((dev->routine_tick % SSD_CAPMON2_ROUTINE_TICK) == 0 && test_bit(SSD_HWMON_PL_CAP(SSD_PL_CAP), &dev->hwmon) && test_bit(SSD_INIT_WORKQ, &dev->state)) { + /* CAP fault? check again */ + queue_work(dev->workq, &dev->capmon_work); + } + + if (test_bit(SSD_INIT_WORKQ, &dev->state)) { + queue_work(dev->workq, &dev->tempmon_work); + } + + /* schedule routine */ + mod_timer(&dev->routine_timer, jiffies + msecs_to_jiffies(SSD_ROUTINE_INTERVAL)); +} + +static void ssd_cleanup_routine(struct ssd_device *dev) +{ + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return; + + (void)ssd_del_timer(&dev->routine_timer); + + (void)ssd_del_timer(&dev->bm_timer); +} + +static int ssd_init_routine(struct ssd_device *dev) +{ + if (unlikely(mode != SSD_DRV_MODE_STANDARD)) + return 0; + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) + INIT_WORK(&dev->bm_work, ssd_bm_worker, dev); + INIT_WORK(&dev->hwmon_work, ssd_hwmon_worker, dev); + INIT_WORK(&dev->capmon_work, ssd_capmon_worker, dev); + INIT_WORK(&dev->tempmon_work, ssd_tempmon_worker, dev); +#else + INIT_WORK(&dev->bm_work, ssd_bm_worker); + INIT_WORK(&dev->hwmon_work, ssd_hwmon_worker); + INIT_WORK(&dev->capmon_work, ssd_capmon_worker); + INIT_WORK(&dev->tempmon_work, ssd_tempmon_worker); +#endif + + /* initial log */ + ssd_initial_log(dev); + + /* schedule bm routine */ + ssd_add_timer(&dev->bm_timer, msecs_to_jiffies(SSD_BM_CAP_LEARNING_DELAY), ssd_bm_routine_start, dev); + + /* schedule routine */ + ssd_add_timer(&dev->routine_timer, msecs_to_jiffies(SSD_ROUTINE_INTERVAL), ssd_routine_start, dev); + + return 0; +} + +static void +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,38)) +__devexit +#endif +ssd_remove_one (struct pci_dev *pdev) +{ + struct ssd_device *dev; + + if (!pdev) { + return; + } + + dev = pci_get_drvdata(pdev); + if (!dev) { + return; + } + + list_del_init(&dev->list); + + ssd_unregister_sysfs(dev); + + /* offline firstly */ + test_and_clear_bit(SSD_ONLINE, &dev->state); + + /* clean work queue first */ + if (!dev->slave) { + test_and_clear_bit(SSD_INIT_WORKQ, &dev->state); + ssd_cleanup_workq(dev); + } + + /* flush cache */ + (void)ssd_flush(dev); + (void)ssd_save_md(dev); + + /* save smart */ + if (!dev->slave) { + ssd_save_smart(dev); + } + + if (test_and_clear_bit(SSD_INIT_BD, &dev->state)) { + ssd_cleanup_blkdev(dev); + } + + if (!dev->slave) { + ssd_cleanup_chardev(dev); + } + + /* clean routine */ + if (!dev->slave) { + ssd_cleanup_routine(dev); + } + + ssd_cleanup_queue(dev); + + ssd_cleanup_tag(dev); + ssd_cleanup_thread(dev); + + ssd_free_irq(dev); + + ssd_cleanup_dcmd(dev); + ssd_cleanup_cmd(dev); + ssd_cleanup_response(dev); + + if (!dev->slave) { + ssd_cleanup_log(dev); + } + + if (dev->reload_fw) { //reload fw + ssd_reg32_write(dev->ctrlp + SSD_RELOAD_FW_REG, SSD_RELOAD_FW); + } + + /* unmap physical adress */ +#ifdef LINUX_SUSE_OS + iounmap(dev->ctrlp); +#else + pci_iounmap(pdev, dev->ctrlp); +#endif + + release_mem_region(dev->mmio_base, dev->mmio_len); + + pci_disable_device(pdev); + + pci_set_drvdata(pdev, NULL); + + ssd_put(dev); +} + +static int +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,38)) +__devinit +#endif +ssd_init_one(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct ssd_device *dev; + int ret = 0; + + if (!pdev || !ent) { + ret = -EINVAL; + goto out; + } + + dev = kmalloc(sizeof(struct ssd_device), GFP_KERNEL); + if (!dev) { + ret = -ENOMEM; + goto out_alloc_dev; + } + memset(dev, 0, sizeof(struct ssd_device)); + + dev->owner = THIS_MODULE; + + if (SSD_SLAVE_PORT_DEVID == ent->device) { + dev->slave = 1; + } + + dev->idx = ssd_get_index(dev->slave); + if (dev->idx < 0) { + ret = -ENOMEM; + goto out_get_index; + } + + if (!dev->slave) { + snprintf(dev->name, SSD_DEV_NAME_LEN, SSD_DEV_NAME); + ssd_set_dev_name(&dev->name[strlen(SSD_DEV_NAME)], SSD_DEV_NAME_LEN-strlen(SSD_DEV_NAME), dev->idx); + + dev->major = ssd_major; + dev->cmajor = ssd_cmajor; + } else { + snprintf(dev->name, SSD_DEV_NAME_LEN, SSD_SDEV_NAME); + ssd_set_dev_name(&dev->name[strlen(SSD_SDEV_NAME)], SSD_DEV_NAME_LEN-strlen(SSD_SDEV_NAME), dev->idx); + dev->major = ssd_major_sl; + dev->cmajor = 0; + } + + atomic_set(&(dev->refcnt), 0); + atomic_set(&(dev->tocnt), 0); + + mutex_init(&dev->fw_mutex); + + //xx + mutex_init(&dev->gd_mutex); + + dev->pdev = pdev; + pci_set_drvdata(pdev, dev); + + kref_init(&dev->kref); + + ret = pci_enable_device(pdev); + if (ret) { + hio_warn("%s: can not enable device\n", dev->name); + goto out_enable_device; + } + + pci_set_master(pdev); + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,31)) + ret = pci_set_dma_mask(pdev, DMA_64BIT_MASK); +#else + ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); +#endif + if (ret) { + hio_warn("%s: set dma mask: failed\n", dev->name); + goto out_set_dma_mask; + } + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,31)) + ret = pci_set_consistent_dma_mask(pdev, DMA_64BIT_MASK); +#else + ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); +#endif + if (ret) { + hio_warn("%s: set consistent dma mask: failed\n", dev->name); + goto out_set_dma_mask; + } + + dev->mmio_base = pci_resource_start(pdev, 0); + dev->mmio_len = pci_resource_len(pdev, 0); + + if (!request_mem_region(dev->mmio_base, dev->mmio_len, SSD_DEV_NAME)) { + hio_warn("%s: can not reserve MMIO region 0\n", dev->name); + ret = -EBUSY; + goto out_request_mem_region; + } + + /* 2.6.9 kernel bug */ + dev->ctrlp = pci_iomap(pdev, 0, 0); + if (!dev->ctrlp) { + hio_warn("%s: can not remap IO region 0\n", dev->name); + ret = -ENOMEM; + goto out_pci_iomap; + } + + ret = ssd_check_hw(dev); + if (ret) { + hio_err("%s: check hardware failed\n", dev->name); + goto out_check_hw; + } + + ret = ssd_init_protocol_info(dev); + if (ret) { + hio_err("%s: init protocol info failed\n", dev->name); + goto out_init_protocol_info; + } + + /* alarm led ? */ + ssd_clear_alarm(dev); + + ret = ssd_init_fw_info(dev); + if (ret) { + hio_err("%s: init firmware info failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_init_fw_info; + } + + /* slave port ? */ + if (dev->slave) { + goto init_next1; + } + + ret = ssd_init_rom_info(dev); + if (ret) { + hio_err("%s: init rom info failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_init_rom_info; + } + + ret = ssd_init_label(dev); + if (ret) { + hio_err("%s: init label failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_init_label; + } + + ret = ssd_init_workq(dev); + if (ret) { + hio_warn("%s: init workq failed\n", dev->name); + goto out_init_workq; + } + (void)test_and_set_bit(SSD_INIT_WORKQ, &dev->state); + + ret = ssd_init_log(dev); + if (ret) { + hio_err("%s: init log failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_init_log; + } + + ret = ssd_init_smart(dev); + if (ret) { + hio_err("%s: init info failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_init_smart; + } + +init_next1: + ret = ssd_init_hw_info(dev); + if (ret) { + hio_err("%s: init hardware info failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_init_hw_info; + } + + /* slave port ? */ + if (dev->slave) { + goto init_next2; + } + + ret = ssd_init_sensor(dev); + if (ret) { + hio_err("%s: init sensor failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_init_sensor; + } + + ret = ssd_init_pl_cap(dev); + if (ret) { + hio_err("%s: int pl_cap failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_init_pl_cap; + } + +init_next2: + ret = ssd_check_init_state(dev); + if (ret) { + hio_err("%s: check init state failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_check_init_state; + } + + ret = ssd_init_response(dev); + if (ret) { + hio_warn("%s: init resp_msg failed\n", dev->name); + goto out_init_response; + } + + ret = ssd_init_cmd(dev); + if (ret) { + hio_warn("%s: init msg failed\n", dev->name); + goto out_init_cmd; + } + + ret = ssd_init_dcmd(dev); + if (ret) { + hio_warn("%s: init cmd failed\n", dev->name); + goto out_init_dcmd; + } + + ret = ssd_init_irq(dev); + if (ret) { + hio_warn("%s: init irq failed\n", dev->name); + goto out_init_irq; + } + + ret = ssd_init_thread(dev); + if (ret) { + hio_warn("%s: init thread failed\n", dev->name); + goto out_init_thread; + } + + ret = ssd_init_tag(dev); + if(ret) { + hio_warn("%s: init tags failed\n", dev->name); + goto out_init_tags; + } + + /* */ + (void)test_and_set_bit(SSD_ONLINE, &dev->state); + + ret = ssd_init_queue(dev); + if (ret) { + hio_warn("%s: init queue failed\n", dev->name); + goto out_init_queue; + } + + /* slave port ? */ + if (dev->slave) { + goto init_next3; + } + + ret = ssd_init_ot_protect(dev); + if (ret) { + hio_err("%s: int ot_protect failed\n", dev->name); + /* alarm led */ + ssd_set_alarm(dev); + goto out_int_ot_protect; + } + + ret = ssd_init_wmode(dev); + if (ret) { + hio_warn("%s: init write mode\n", dev->name); + goto out_init_wmode; + } + + /* init routine after hw is ready */ + ret = ssd_init_routine(dev); + if (ret) { + hio_warn("%s: init routine\n", dev->name); + goto out_init_routine; + } + + ret = ssd_init_chardev(dev); + if (ret) { + hio_warn("%s: register char device failed\n", dev->name); + goto out_init_chardev; + } + +init_next3: + ret = ssd_init_blkdev(dev); + if (ret) { + hio_warn("%s: register block device failed\n", dev->name); + goto out_init_blkdev; + } + (void)test_and_set_bit(SSD_INIT_BD, &dev->state); + + ret = ssd_register_sysfs(dev); + if (ret) { + hio_warn("%s: register sysfs failed\n", dev->name); + goto out_register_sysfs; + } + + dev->save_md = 1; + + list_add_tail(&dev->list, &ssd_list); + + return 0; + +out_register_sysfs: + test_and_clear_bit(SSD_INIT_BD, &dev->state); + ssd_cleanup_blkdev(dev); +out_init_blkdev: + /* slave port ? */ + if (!dev->slave) { + ssd_cleanup_chardev(dev); + } +out_init_chardev: + /* slave port ? */ + if (!dev->slave) { + ssd_cleanup_routine(dev); + } +out_init_routine: +out_init_wmode: +out_int_ot_protect: + ssd_cleanup_queue(dev); +out_init_queue: + test_and_clear_bit(SSD_ONLINE, &dev->state); + ssd_cleanup_tag(dev); +out_init_tags: + ssd_cleanup_thread(dev); +out_init_thread: + ssd_free_irq(dev); +out_init_irq: + ssd_cleanup_dcmd(dev); +out_init_dcmd: + ssd_cleanup_cmd(dev); +out_init_cmd: + ssd_cleanup_response(dev); +out_init_response: +out_check_init_state: +out_init_pl_cap: +out_init_sensor: +out_init_hw_info: +out_init_smart: + /* slave port ? */ + if (!dev->slave) { + ssd_cleanup_log(dev); + } +out_init_log: + /* slave port ? */ + if (!dev->slave) { + test_and_clear_bit(SSD_INIT_WORKQ, &dev->state); + ssd_cleanup_workq(dev); + } +out_init_workq: +out_init_label: +out_init_rom_info: +out_init_fw_info: +out_init_protocol_info: +out_check_hw: +#ifdef LINUX_SUSE_OS + iounmap(dev->ctrlp); +#else + pci_iounmap(pdev, dev->ctrlp); +#endif +out_pci_iomap: + release_mem_region(dev->mmio_base, dev->mmio_len); +out_request_mem_region: +out_set_dma_mask: + pci_disable_device(pdev); +out_enable_device: + pci_set_drvdata(pdev, NULL); +out_get_index: + kfree(dev); +out_alloc_dev: +out: + return ret; +} + +static void ssd_cleanup_tasklet(void) +{ + int i; + for_each_online_cpu(i) { + tasklet_kill(&per_cpu(ssd_tasklet, i)); + } +} + +static int ssd_init_tasklet(void) +{ + int i; + + for_each_online_cpu(i) { + INIT_LIST_HEAD(&per_cpu(ssd_doneq, i)); + + if (finject) { + tasklet_init(&per_cpu(ssd_tasklet, i), __ssd_done_db, 0); + } else { + tasklet_init(&per_cpu(ssd_tasklet, i), __ssd_done, 0); + } + } + + return 0; +} + +static struct pci_device_id ssd_pci_tbl[] = { + { 0x10ee, 0x0007, PCI_ANY_ID, PCI_ANY_ID, }, /* g3 */ + { 0x19e5, 0x0007, PCI_ANY_ID, PCI_ANY_ID, }, /* v1 */ + //{ 0x19e5, 0x0008, PCI_ANY_ID, PCI_ANY_ID, }, /* v1 sp*/ + { 0x19e5, 0x0009, PCI_ANY_ID, PCI_ANY_ID, }, /* v2 */ + { 0x19e5, 0x000a, PCI_ANY_ID, PCI_ANY_ID, }, /* v2 dp slave*/ + { 0, } +}; +MODULE_DEVICE_TABLE(pci, ssd_pci_tbl); + +static struct pci_driver ssd_driver = { + .name = MODULE_NAME, + .id_table = ssd_pci_tbl, + .probe = ssd_init_one, +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,38)) + .remove = __devexit_p(ssd_remove_one), +#else + .remove = ssd_remove_one, +#endif +}; + +/* notifier block to get a notify on system shutdown/halt/reboot */ +static int ssd_notify_reboot(struct notifier_block *nb, unsigned long event, void *buf) +{ + struct ssd_device *dev = NULL; + struct ssd_device *n = NULL; + + list_for_each_entry_safe(dev, n, &ssd_list, list) { + ssd_gen_swlog(dev, SSD_LOG_POWER_OFF, 0); + + (void)ssd_flush(dev); + (void)ssd_save_md(dev); + + /* slave port ? */ + if (!dev->slave) { + ssd_save_smart(dev); + + ssd_stop_workq(dev); + + if (dev->reload_fw) { + ssd_reg32_write(dev->ctrlp + SSD_RELOAD_FW_REG, SSD_RELOAD_FW); + } + } + } + + return NOTIFY_OK; +} + +static struct notifier_block ssd_notifier = { + ssd_notify_reboot, NULL, 0 +}; + +static int __init ssd_init_module(void) +{ + int ret = 0; + + hio_info("driver version: %s\n", DRIVER_VERSION); + + ret = ssd_init_index(); + if (ret) { + hio_warn("init index failed\n"); + goto out_init_index; + } + + ret = ssd_init_proc(); + if (ret) { + hio_warn("init proc failed\n"); + goto out_init_proc; + } + + ret = ssd_init_sysfs(); + if (ret) { + hio_warn("init sysfs failed\n"); + goto out_init_sysfs; + } + + ret = ssd_init_tasklet(); + if (ret) { + hio_warn("init tasklet failed\n"); + goto out_init_tasklet; + } + +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,12)) + ssd_class = class_simple_create(THIS_MODULE, SSD_DEV_NAME); +#else + ssd_class = class_create(THIS_MODULE, SSD_DEV_NAME); +#endif + if (IS_ERR(ssd_class)) { + ret = PTR_ERR(ssd_class); + goto out_class_create; + } + + if (ssd_cmajor > 0) { + ret = register_chrdev(ssd_cmajor, SSD_CDEV_NAME, &ssd_cfops); + } else { + ret = ssd_cmajor = register_chrdev(ssd_cmajor, SSD_CDEV_NAME, &ssd_cfops); + } + if (ret < 0) { + hio_warn("unable to register chardev major number\n"); + goto out_register_chardev; + } + + if (ssd_major > 0) { + ret = register_blkdev(ssd_major, SSD_DEV_NAME); + } else { + ret = ssd_major = register_blkdev(ssd_major, SSD_DEV_NAME); + } + if (ret < 0) { + hio_warn("unable to register major number\n"); + goto out_register_blkdev; + } + + if (ssd_major_sl > 0) { + ret = register_blkdev(ssd_major_sl, SSD_SDEV_NAME); + } else { + ret = ssd_major_sl = register_blkdev(ssd_major_sl, SSD_SDEV_NAME); + } + if (ret < 0) { + hio_warn("unable to register slave major number\n"); + goto out_register_blkdev_sl; + } + + if (mode < SSD_DRV_MODE_STANDARD || mode > SSD_DRV_MODE_BASE) { + mode = SSD_DRV_MODE_STANDARD; + } + + /* for debug */ + if (mode != SSD_DRV_MODE_STANDARD) { + ssd_minors = 1; + } + + if (int_mode < SSD_INT_LEGACY || int_mode > SSD_INT_MSIX) { + int_mode = SSD_INT_MODE_DEFAULT; + } + + if (threaded_irq) { + int_mode = SSD_INT_MSI; + } + + if (log_level >= SSD_LOG_NR_LEVEL || log_level < SSD_LOG_LEVEL_INFO) { + log_level = SSD_LOG_LEVEL_ERR; + } + + if (wmode < SSD_WMODE_BUFFER || wmode > SSD_WMODE_DEFAULT) { + wmode = SSD_WMODE_DEFAULT; + } + +#if (LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20)) + ret = pci_module_init(&ssd_driver); +#else + ret = pci_register_driver(&ssd_driver); +#endif + if (ret) { + hio_warn("pci init failed\n"); + goto out_pci_init; + } + + ret = register_reboot_notifier(&ssd_notifier); + if (ret) { + hio_warn("register reboot notifier failed\n"); + goto out_register_reboot_notifier; + } + + return 0; + +out_register_reboot_notifier: +out_pci_init: + pci_unregister_driver(&ssd_driver); + unregister_blkdev(ssd_major_sl, SSD_SDEV_NAME); +out_register_blkdev_sl: + unregister_blkdev(ssd_major, SSD_DEV_NAME); +out_register_blkdev: + unregister_chrdev(ssd_cmajor, SSD_CDEV_NAME); +out_register_chardev: +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,12)) + class_simple_destroy(ssd_class); +#else + class_destroy(ssd_class); +#endif +out_class_create: + ssd_cleanup_tasklet(); +out_init_tasklet: + ssd_cleanup_sysfs(); +out_init_sysfs: + ssd_cleanup_proc(); +out_init_proc: + ssd_cleanup_index(); +out_init_index: + return ret; + +} + +static void __exit ssd_cleanup_module(void) +{ + + hio_info("unload driver: %s\n", DRIVER_VERSION); + /* exiting */ + ssd_exiting = 1; + + unregister_reboot_notifier(&ssd_notifier); + + pci_unregister_driver(&ssd_driver); + + unregister_blkdev(ssd_major_sl, SSD_SDEV_NAME); + unregister_blkdev(ssd_major, SSD_DEV_NAME); + unregister_chrdev(ssd_cmajor, SSD_CDEV_NAME); +#if (LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,12)) + class_simple_destroy(ssd_class); +#else + class_destroy(ssd_class); +#endif + + ssd_cleanup_tasklet(); + ssd_cleanup_sysfs(); + ssd_cleanup_proc(); + ssd_cleanup_index(); +} + +int ssd_register_event_notifier(struct block_device *bdev, ssd_event_call event_call) +{ + struct ssd_device *dev; + struct timeval tv; + struct ssd_log *le; + uint64_t cur; + int log_nr; + + if (!bdev || !event_call || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + dev->event_call = event_call; + + do_gettimeofday(&tv); + cur = tv.tv_sec; + + le = (struct ssd_log *)(dev->internal_log.log); + log_nr = dev->internal_log.nr_log; + + while (log_nr--) { + if (le->time <= cur && le->time >= dev->uptime) { + (void)dev->event_call(dev->gd, le->le.event, ssd_parse_log(dev, le, 0)); + } + le++; + } + + return 0; +} + +int ssd_unregister_event_notifier(struct block_device *bdev) +{ + struct ssd_device *dev; + + if (!bdev || !(bdev->bd_disk)) { + return -EINVAL; + } + + dev = bdev->bd_disk->private_data; + dev->event_call = NULL; + + return 0; +} + +EXPORT_SYMBOL(ssd_get_label); +EXPORT_SYMBOL(ssd_get_version); +EXPORT_SYMBOL(ssd_set_otprotect); +EXPORT_SYMBOL(ssd_bm_status); +EXPORT_SYMBOL(ssd_submit_pbio); +EXPORT_SYMBOL(ssd_get_pciaddr); +EXPORT_SYMBOL(ssd_get_temperature); +EXPORT_SYMBOL(ssd_register_event_notifier); +EXPORT_SYMBOL(ssd_unregister_event_notifier); +EXPORT_SYMBOL(ssd_reset); +EXPORT_SYMBOL(ssd_set_wmode); + + + +module_init(ssd_init_module); +module_exit(ssd_cleanup_module); +MODULE_VERSION(DRIVER_VERSION); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Huawei SSD DEV Team"); +MODULE_DESCRIPTION("Huawei SSD driver"); diff --git a/ubuntu/hio/hio.h b/ubuntu/hio/hio.h new file mode 100644 index 0000000000000..49fbb458c25cc --- /dev/null +++ b/ubuntu/hio/hio.h @@ -0,0 +1,104 @@ +/* +* Huawei SSD device driver +* Copyright (c) 2016, Huawei Technologies Co., Ltd. +* +* This program is free software; you can redistribute it and/or modify it +* under the terms and conditions of the GNU General Public License, +* version 2, as published by the Free Software Foundation. +* +* This program is distributed in the hope it will be useful, but WITHOUT +* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +* more details. +*/ + +#ifndef _HIO_H +#define _HIO_H + +#include +#include +#include +#include + + + +typedef int (*ssd_event_call)(struct gendisk *, int, int); /* gendisk, event id, event level */ +extern int ssd_register_event_notifier(struct block_device *bdev, ssd_event_call event_call); +/* unregister event notifier before module exit */ +extern int ssd_unregister_event_notifier(struct block_device *bdev); + + +/* label */ +#define SSD_LABEL_FIELD_SZ 32 +#define SSD_SN_SZ 16 + +typedef struct ssd_label +{ + char date[SSD_LABEL_FIELD_SZ]; + char sn[SSD_LABEL_FIELD_SZ]; + char part[SSD_LABEL_FIELD_SZ]; + char desc[SSD_LABEL_FIELD_SZ]; + char other[SSD_LABEL_FIELD_SZ]; + char maf[SSD_LABEL_FIELD_SZ]; +} ssd_label_t; + + +/* version */ +typedef struct ssd_version_info +{ + uint32_t bridge_ver; /* bridge fw version: hex */ + uint32_t ctrl_ver; /* controller fw version: hex */ + uint32_t bm_ver; /* battery manager fw version: hex */ + uint8_t pcb_ver; /* main pcb version: char */ + uint8_t upper_pcb_ver; + uint8_t pad0; + uint8_t pad1; +} ssd_version_info_t; + +extern int ssd_get_label(struct block_device *bdev, struct ssd_label *label); +extern int ssd_get_version(struct block_device *bdev, struct ssd_version_info *ver); +extern int ssd_get_temperature(struct block_device *bdev, int *temp); + + +enum ssd_bmstatus +{ + SSD_BMSTATUS_OK = 0, + SSD_BMSTATUS_CHARGING, + SSD_BMSTATUS_WARNING +}; +extern int ssd_bm_status(struct block_device *bdev, int *status); + +enum ssd_otprotect +{ + SSD_OTPROTECT_OFF = 0, + SSD_OTPROTECT_ON +}; +extern int ssd_set_otprotect(struct block_device *bdev, int otprotect); + +typedef struct pci_addr +{ + uint16_t domain; + uint8_t bus; + uint8_t slot; + uint8_t func; +} pci_addr_t; +extern int ssd_get_pciaddr(struct block_device *bdev, struct pci_addr *paddr); + +/* submit phys bio: phys addr in iovec */ +extern void ssd_submit_pbio(struct request_queue *q, struct bio *bio); + +extern int ssd_reset(struct block_device *bdev); + +enum ssd_write_mode +{ + SSD_WMODE_BUFFER = 0, + SSD_WMODE_BUFFER_EX, + SSD_WMODE_FUA, + /* dummy */ + SSD_WMODE_AUTO, + SSD_WMODE_DEFAULT +}; +extern int ssd_set_wmode(struct block_device *bdev, int wmode); + +#endif + diff --git a/ubuntu/include/Kbuild b/ubuntu/include/Kbuild new file mode 100644 index 0000000000000..139597f9cb07c --- /dev/null +++ b/ubuntu/include/Kbuild @@ -0,0 +1,2 @@ + + diff --git a/ubuntu/include/README b/ubuntu/include/README new file mode 100644 index 0000000000000..adc8d33e6d8e8 --- /dev/null +++ b/ubuntu/include/README @@ -0,0 +1,4 @@ +Only use this directory for things which need to share their headers with +other parts of the kernel or other modules in ubuntu/ + +Otherwise, keep them local to the module directory. diff --git a/ubuntu/ubuntu-host/Kconfig b/ubuntu/ubuntu-host/Kconfig new file mode 100644 index 0000000000000..1989da68b62f5 --- /dev/null +++ b/ubuntu/ubuntu-host/Kconfig @@ -0,0 +1,5 @@ +config UBUNTU_HOST + tristate "proc dir for exporting host data to containers" + help + Creates an ubuntu-host directory in proc for providing data from + Ubuntu hosts to containers. diff --git a/ubuntu/ubuntu-host/Makefile b/ubuntu/ubuntu-host/Makefile new file mode 100644 index 0000000000000..fef3c13196760 --- /dev/null +++ b/ubuntu/ubuntu-host/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_UBUNTU_HOST) += ubuntu-host.o diff --git a/ubuntu/ubuntu-host/ubuntu-host.c b/ubuntu/ubuntu-host/ubuntu-host.c new file mode 100644 index 0000000000000..1abd402533b4d --- /dev/null +++ b/ubuntu/ubuntu-host/ubuntu-host.c @@ -0,0 +1,68 @@ +#include +#include +#include +#include +#include + +#define PROC_DIR "ubuntu-host" + +#define ESM_TOKEN_FILE "esm-token" +#define ESM_TOKEN_MAX_SIZE 64 + +static struct proc_dir_entry *proc_dir; +static char esm_token_buffer[ESM_TOKEN_MAX_SIZE]; + +static ssize_t esm_token_read(struct file *f, char __user *buf, size_t len, + loff_t *off) +{ + return simple_read_from_buffer(buf, len, off, esm_token_buffer, + strlen(esm_token_buffer)); +} + +static ssize_t esm_token_write(struct file *f, const char __user *buf, + size_t len, loff_t *off) +{ + ssize_t ret; + + if (len >= ESM_TOKEN_MAX_SIZE - 1) + return -EINVAL; + + ret = simple_write_to_buffer(esm_token_buffer, ESM_TOKEN_MAX_SIZE - 1, + off, buf, len); + if (ret >= 0) + esm_token_buffer[ret] = '\0'; + + return ret; +} + +static const struct proc_ops esm_token_fops = { + .proc_read = esm_token_read, + .proc_write = esm_token_write, +}; + +static void ubuntu_host_cleanup(void) +{ + remove_proc_entry(ESM_TOKEN_FILE, proc_dir); + proc_remove(proc_dir); +} + +static int __init ubuntu_host_init(void) +{ + proc_dir = proc_mkdir(PROC_DIR, NULL); + if (!proc_dir) { + pr_err("Failed to create ubuntu-host dir\n"); + return -ENOMEM; + } + + if (!proc_create_data(ESM_TOKEN_FILE, 0644, proc_dir, &esm_token_fops, NULL)) { + pr_err("Failed to create esm-tokan file\n"); + ubuntu_host_cleanup(); + return -ENOMEM; + } + + return 0; +} + +module_init(ubuntu_host_init); +module_exit(ubuntu_host_cleanup); +MODULE_LICENSE("GPL"); diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index e033c79d528e0..28658b9e0d968 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -87,7 +87,27 @@ static void async_pf_execute(struct work_struct *work) __kvm_vcpu_wake_up(vcpu); mmput(mm); - kvm_put_kvm(vcpu->kvm); +} + +static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work) +{ + /* + * The async #PF is "done", but KVM must wait for the work item itself, + * i.e. async_pf_execute(), to run to completion. If KVM is a module, + * KVM must ensure *no* code owned by the KVM (the module) can be run + * after the last call to module_put(). Note, flushing the work item + * is always required when the item is taken off the completion queue. + * E.g. even if the vCPU handles the item in the "normal" path, the VM + * could be terminated before async_pf_execute() completes. + * + * Wake all events skip the queue and go straight done, i.e. don't + * need to be flushed (but sanity check that the work wasn't queued). + */ + if (work->wakeup_all) + WARN_ON_ONCE(work->work.func); + else + flush_work(&work->work); + kmem_cache_free(async_pf_cache, work); } void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) @@ -114,7 +134,6 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) #else if (cancel_work_sync(&work->work)) { mmput(work->mm); - kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */ kmem_cache_free(async_pf_cache, work); } #endif @@ -126,7 +145,10 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) list_first_entry(&vcpu->async_pf.done, typeof(*work), link); list_del(&work->link); - kmem_cache_free(async_pf_cache, work); + + spin_unlock(&vcpu->async_pf.lock); + kvm_flush_and_free_async_pf_work(work); + spin_lock(&vcpu->async_pf.lock); } spin_unlock(&vcpu->async_pf.lock); @@ -151,7 +173,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) list_del(&work->queue); vcpu->async_pf.queued--; - kmem_cache_free(async_pf_cache, work); + kvm_flush_and_free_async_pf_work(work); } } @@ -186,7 +208,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, work->arch = *arch; work->mm = current->mm; mmget(work->mm); - kvm_get_kvm(work->vcpu->kvm); INIT_WORK(&work->work, async_pf_execute); diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 0f4e0cf4f158b..747fe251e445b 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -510,8 +510,10 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, } if (folio_test_hwpoison(folio)) { + folio_unlock(folio); + folio_put(folio); r = -EHWPOISON; - goto out_unlock; + goto out_fput; } page = folio_file_page(folio, index); @@ -522,7 +524,6 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, r = 0; -out_unlock: folio_unlock(folio); out_fput: fput(file); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 0f50960b0e3a8..6a56de7ff82e7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4057,12 +4057,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; - int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + int last_boosted_vcpu; unsigned long i; int yielded = 0; int try = 3; int pass; + last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not @@ -4093,7 +4094,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - kvm->last_boosted_vcpu = i; + WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--;